FierceLLM/CoreGPT-small
09
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": 1860,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.016148566814695196,14 "grad_norm": 0.5020289421081543,15 "learning_rate": 8.999999999999999e-05,16 "loss": 2.439466857910156,17 "step": 1018 },19 {20 "epoch": 0.03229713362939039,21 "grad_norm": 0.6233699321746826,22 "learning_rate": 0.00019,23 "loss": 2.4973506927490234,24 "step": 2025 },26 {27 "epoch": 0.04844570044408559,28 "grad_norm": 0.6460151076316833,29 "learning_rate": 0.00029,30 "loss": 2.579629898071289,31 "step": 3032 },33 {34 "epoch": 0.06459426725878079,35 "grad_norm": 0.5584802031517029,36 "learning_rate": 0.00039000000000000005,37 "loss": 2.5269956588745117,38 "step": 4039 },40 {41 "epoch": 0.08074283407347597,42 "grad_norm": 0.5267783403396606,43 "learning_rate": 0.00049,44 "loss": 2.5723337173461913,45 "step": 5046 },47 {48 "epoch": 0.09689140088817118,49 "grad_norm": 0.492374062538147,50 "learning_rate": 0.00059,51 "loss": 2.6084869384765623,52 "step": 6053 },54 {55 "epoch": 0.11303996770286637,56 "grad_norm": 0.533662736415863,57 "learning_rate": 0.00069,58 "loss": 2.527654838562012,59 "step": 7060 },61 {62 "epoch": 0.12918853451756157,63 "grad_norm": 0.568081796169281,64 "learning_rate": 0.00079,65 "loss": 2.584039497375488,66 "step": 8067 },68 {69 "epoch": 0.14533710133225677,70 "grad_norm": 0.5420770049095154,71 "learning_rate": 0.0008900000000000001,72 "loss": 2.5998212814331056,73 "step": 9074 },75 {76 "epoch": 0.16148566814695195,77 "grad_norm": 0.5972040295600891,78 "learning_rate": 0.00099,79 "loss": 2.61820011138916,80 "step": 10081 },82 {83 "epoch": 0.17763423496164715,84 "grad_norm": 0.622533917427063,85 "learning_rate": 0.0009999354806331361,86 "loss": 2.5819944381713866,87 "step": 11088 },89 {90 "epoch": 0.19378280177634236,91 "grad_norm": 0.6911935210227966,92 "learning_rate": 0.0009997124721002689,93 "loss": 2.5768102645874023,94 "step": 12095 },96 {97 "epoch": 0.20993136859103753,98 "grad_norm": 0.7095156908035278,99 "learning_rate": 0.000999330248902402,100 "loss": 2.6130306243896486,101 "step": 130102 },103 {104 "epoch": 0.22607993540573273,105 "grad_norm": 0.5791682600975037,106 "learning_rate": 0.0009987889328206437,107 "loss": 2.562555503845215,108 "step": 140109 },110 {111 "epoch": 0.24222850222042794,112 "grad_norm": 0.5518380403518677,113 "learning_rate": 0.0009980886963250907,114 "loss": 2.518760108947754,115 "step": 150116 },117 {118 "epoch": 0.25837706903512314,119 "grad_norm": 0.4897823631763458,120 "learning_rate": 0.000997229762519879,121 "loss": 2.6402866363525392,122 "step": 160123 },124 {125 "epoch": 0.2745256358498183,126 "grad_norm": 0.5050747394561768,127 "learning_rate": 0.0009962124050720978,128 "loss": 2.684323310852051,129 "step": 170130 },131 {132 "epoch": 0.29067420266451355,133 "grad_norm": 0.468423068523407,134 "learning_rate": 0.0009950369481245985,135 "loss": 2.6152185440063476,136 "step": 180137 },138 {139 "epoch": 0.3068227694792087,140 "grad_norm": 0.5091232657432556,141 "learning_rate": 0.0009937037661927161,142 "loss": 2.531853675842285,143 "step": 190144 },145 {146 "epoch": 0.3229713362939039,147 "grad_norm": 0.4922482967376709,148 "learning_rate": 0.0009922132840449458,149 "loss": 2.6094560623168945,150 "step": 200151 },152 {153 "epoch": 0.33911990310859913,154 "grad_norm": 0.5051465034484863,155 "learning_rate": 0.0009905659765676053,156 "loss": 2.559980583190918,157 "step": 210158 },159 {160 "epoch": 0.3552684699232943,161 "grad_norm": 0.4865105450153351,162 "learning_rate": 0.0009887623686135306,163 "loss": 2.508647346496582,164 "step": 220165 },166 {167 "epoch": 0.3714170367379895,168 "grad_norm": 0.5287356376647949,169 "learning_rate": 0.0009868030348348512,170 "loss": 2.6150222778320313,171 "step": 230172 },173 {174 "epoch": 0.3875656035526847,175 "grad_norm": 0.4643533229827881,176 "learning_rate": 0.0009846885994998983,177 "loss": 2.6150381088256838,178 "step": 240179 },180 {181 "epoch": 0.4037141703673799,182 "grad_norm": 0.46244189143180847,183 "learning_rate": 0.0009824197362943063,184 "loss": 2.5374935150146483,185 "step": 250186 },187 {188 "epoch": 0.41986273718207506,189 "grad_norm": 0.480276882648468,190 "learning_rate": 0.000979997168106366,191 "loss": 2.5654741287231446,192 "step": 260193 },194 {195 "epoch": 0.4360113039967703,196 "grad_norm": 0.5552269816398621,197 "learning_rate": 0.0009774216667967062,198 "loss": 2.6036794662475584,199 "step": 270200 },201 {202 "epoch": 0.45215987081146547,203 "grad_norm": 0.511289656162262,204 "learning_rate": 0.000974694052952366,205 "loss": 2.610031318664551,206 "step": 280207 },208 {209 "epoch": 0.4683084376261607,210 "grad_norm": 0.5037236213684082,211 "learning_rate": 0.000971815195625348,212 "loss": 2.516169548034668,213 "step": 290214 },215 {216 "epoch": 0.4844570044408559,217 "grad_norm": 0.5199276804924011,218 "learning_rate": 0.000968786012055726,219 "loss": 2.5069480895996095,220 "step": 300221 },222 {223 "epoch": 0.500605571255551,224 "grad_norm": 0.5875343680381775,225 "learning_rate": 0.0009656074673794017,226 "loss": 2.639841651916504,227 "step": 310228 },229 {230 "epoch": 0.5167541380702463,231 "grad_norm": 0.5489600896835327,232 "learning_rate": 0.0009622805743205998,233 "loss": 2.5628652572631836,234 "step": 320235 },236 {237 "epoch": 0.5329027048849415,238 "grad_norm": 0.4753468334674835,239 "learning_rate": 0.0009588063928692012,240 "loss": 2.5956233978271483,241 "step": 330242 },243 {244 "epoch": 0.5490512716996366,245 "grad_norm": 0.5152420997619629,246 "learning_rate": 0.0009551860299430173,247 "loss": 2.597700500488281,248 "step": 340249 },250 {251 "epoch": 0.5651998385143319,252 "grad_norm": 0.4520896375179291,253 "learning_rate": 0.0009514206390351116,254 "loss": 2.586415481567383,255 "step": 350256 },257 {258 "epoch": 0.5813484053290271,259 "grad_norm": 0.5123590230941772,260 "learning_rate": 0.0009475114198462837,261 "loss": 2.555033302307129,262 "step": 360263 },264 {265 "epoch": 0.5974969721437222,266 "grad_norm": 0.6008352637290955,267 "learning_rate": 0.0009434596179028271,268 "loss": 2.6199901580810545,269 "step": 370270 },271 {272 "epoch": 0.6136455389584174,273 "grad_norm": 0.4769132435321808,274 "learning_rate": 0.0009392665241596914,275 "loss": 2.5420787811279295,276 "step": 380277 },278 {279 "epoch": 0.6297941057731127,280 "grad_norm": 0.4474424421787262,281 "learning_rate": 0.0009349334745891666,282 "loss": 2.549270820617676,283 "step": 390284 },285 {286 "epoch": 0.6459426725878078,287 "grad_norm": 0.5046530365943909,288 "learning_rate": 0.0009304618497552253,289 "loss": 2.540346145629883,290 "step": 400291 },292 {293 "epoch": 0.662091239402503,294 "grad_norm": 0.5442773699760437,295 "learning_rate": 0.0009258530743736586,296 "loss": 2.550925636291504,297 "step": 410298 },299 {300 "epoch": 0.6782398062171983,301 "grad_norm": 0.45155641436576843,302 "learning_rate": 0.0009211086168581433,303 "loss": 2.5896928787231444,304 "step": 420305 },306 {307 "epoch": 0.6943883730318934,308 "grad_norm": 0.48448678851127625,309 "learning_rate": 0.0009162299888523867,310 "loss": 2.568522834777832,311 "step": 430312 },313 {314 "epoch": 0.7105369398465886,315 "grad_norm": 0.4634808897972107,316 "learning_rate": 0.0009112187447484979,317 "loss": 2.543706512451172,318 "step": 440319 },320 {321 "epoch": 0.7266855066612838,322 "grad_norm": 0.520962655544281,323 "learning_rate": 0.0009060764811917397,324 "loss": 2.4791580200195313,325 "step": 450326 },327 {328 "epoch": 0.742834073475979,329 "grad_norm": 0.495394766330719,330 "learning_rate": 0.0009008048365718167,331 "loss": 2.6086082458496094,332 "step": 460333 },334 {335 "epoch": 0.7589826402906742,336 "grad_norm": 0.4325544834136963,337 "learning_rate": 0.0008954054905008639,338 "loss": 2.5405605316162108,339 "step": 470340 },341 {342 "epoch": 0.7751312071053694,343 "grad_norm": 0.4992341697216034,344 "learning_rate": 0.0008898801632783013,345 "loss": 2.6021982192993165,346 "step": 480347 },348 {349 "epoch": 0.7912797739200645,350 "grad_norm": 0.5032821893692017,351 "learning_rate": 0.0008842306153427246,352 "loss": 2.5671119689941406,353 "step": 490354 },355 {356 "epoch": 0.8074283407347598,357 "grad_norm": 0.44175952672958374,358 "learning_rate": 0.000878458646711008,359 "loss": 2.5145410537719726,360 "step": 500361 },362 {363 "epoch": 0.823576907549455,364 "grad_norm": 0.48530301451683044,365 "learning_rate": 0.0008725660964047959,366 "loss": 2.4978832244873046,367 "step": 510368 },369 {370 "epoch": 0.8397254743641501,371 "grad_norm": 0.4604915976524353,372 "learning_rate": 0.0008665548418645672,373 "loss": 2.5596445083618162,374 "step": 520375 },376 {377 "epoch": 0.8558740411788454,378 "grad_norm": 0.45781826972961426,379 "learning_rate": 0.0008604267983514594,380 "loss": 2.6085268020629884,381 "step": 530382 },383 {384 "epoch": 0.8720226079935406,385 "grad_norm": 0.48819592595100403,386 "learning_rate": 0.000854183918337043,387 "loss": 2.5747554779052733,388 "step": 540389 },390 {391 "epoch": 0.8881711748082358,392 "grad_norm": 0.4929693043231964,393 "learning_rate": 0.0008478281908812387,394 "loss": 2.543058395385742,395 "step": 550396 },397 {398 "epoch": 0.9043197416229309,399 "grad_norm": 0.4913038909435272,400 "learning_rate": 0.0008413616409985779,401 "loss": 2.5399295806884767,402 "step": 560403 },404 {405 "epoch": 0.9204683084376262,406 "grad_norm": 0.47384563088417053,407 "learning_rate": 0.0008347863290130087,408 "loss": 2.5927974700927736,409 "step": 570410 },411 {412 "epoch": 0.9366168752523214,413 "grad_norm": 0.4775764048099518,414 "learning_rate": 0.0008281043499014498,415 "loss": 2.5593168258666994,416 "step": 580417 },418 {419 "epoch": 0.9527654420670165,420 "grad_norm": 0.5058761239051819,421 "learning_rate": 0.0008213178326263049,422 "loss": 2.552435111999512,423 "step": 590424 },425 {426 "epoch": 0.9689140088817118,427 "grad_norm": 0.4922596216201782,428 "learning_rate": 0.0008144289394571484,429 "loss": 2.5472679138183594,430 "step": 600431 },432 {433 "epoch": 0.985062575696407,434 "grad_norm": 0.49022358655929565,435 "learning_rate": 0.0008074398652817998,436 "loss": 2.5109460830688475,437 "step": 610438 },439 {440 "epoch": 1.0,441 "grad_norm": 1.6876914501190186,442 "learning_rate": 0.0008003528369070043,443 "loss": 2.465944290161133,444 "step": 620445 },446 {447 "epoch": 1.0161485668146952,448 "grad_norm": 0.4119199812412262,449 "learning_rate": 0.0007931701123489439,450 "loss": 2.520769500732422,451 "step": 630452 },453 {454 "epoch": 1.0322971336293905,455 "grad_norm": 0.4147922992706299,456 "learning_rate": 0.000785893980113806,457 "loss": 2.5548782348632812,458 "step": 640459 },460 {461 "epoch": 1.0484457004440857,462 "grad_norm": 0.5313045382499695,463 "learning_rate": 0.0007785267584686366,464 "loss": 2.6331764221191407,465 "step": 650466 },467 {468 "epoch": 1.0645942672587807,469 "grad_norm": 0.45284605026245117,470 "learning_rate": 0.00077107079470271,471 "loss": 2.519462013244629,472 "step": 660473 },474 {475 "epoch": 1.080742834073476,476 "grad_norm": 0.5042719841003418,477 "learning_rate": 0.0007635284643796545,478 "loss": 2.4921422958374024,479 "step": 670480 },481 {482 "epoch": 1.0968914008881712,483 "grad_norm": 0.4403098225593567,484 "learning_rate": 0.0007559021705805671,485 "loss": 2.454839897155762,486 "step": 680487 },488 {489 "epoch": 1.1130399677028664,490 "grad_norm": 0.4963165819644928,491 "learning_rate": 0.0007481943431383622,492 "loss": 2.5821470260620116,493 "step": 690494 },495 {496 "epoch": 1.1291885345175616,497 "grad_norm": 0.4509197175502777,498 "learning_rate": 0.000740407437863596,499 "loss": 2.4973094940185545,500 "step": 700501 },502 {503 "epoch": 1.1453371013322569,504 "grad_norm": 0.49439796805381775,505 "learning_rate": 0.0007325439357620147,506 "loss": 2.6476114273071287,507 "step": 710508 },509 {510 "epoch": 1.1614856681469519,511 "grad_norm": 0.5243302583694458,512 "learning_rate": 0.0007246063422440747,513 "loss": 2.4758913040161135,514 "step": 720515 },516 {517 "epoch": 1.177634234961647,518 "grad_norm": 0.6043158769607544,519 "learning_rate": 0.0007165971863266878,520 "loss": 2.5820987701416014,521 "step": 730522 },523 {524 "epoch": 1.1937828017763423,525 "grad_norm": 0.44207850098609924,526 "learning_rate": 0.0007085190198274438,527 "loss": 2.4599235534667967,528 "step": 740529 },530 {531 "epoch": 1.2099313685910376,532 "grad_norm": 0.4254566431045532,533 "learning_rate": 0.0007003744165515704,534 "loss": 2.4942739486694334,535 "step": 750536 },537 {538 "epoch": 1.2260799354057328,539 "grad_norm": 0.41949278116226196,540 "learning_rate": 0.0006921659714718863,541 "loss": 2.505445098876953,542 "step": 760543 },544 {545 "epoch": 1.242228502220428,546 "grad_norm": 0.4123310148715973,547 "learning_rate": 0.0006838962999020094,548 "loss": 2.5693735122680663,549 "step": 770550 },551 {552 "epoch": 1.2583770690351233,553 "grad_norm": 0.4186009168624878,554 "learning_rate": 0.0006755680366630865,555 "loss": 2.4493398666381836,556 "step": 780557 },558 {559 "epoch": 1.2745256358498183,560 "grad_norm": 0.444654643535614,561 "learning_rate": 0.0006671838352443049,562 "loss": 2.5728691101074217,563 "step": 790564 },565 {566 "epoch": 1.2906742026645135,567 "grad_norm": 0.40202823281288147,568 "learning_rate": 0.0006587463669574584,569 "loss": 2.526685333251953,570 "step": 800571 },572 {573 "epoch": 1.3068227694792087,574 "grad_norm": 0.4873361885547638,575 "learning_rate": 0.0006502583200858335,576 "loss": 2.5635454177856447,577 "step": 810578 },579 {580 "epoch": 1.322971336293904,581 "grad_norm": 0.5394927859306335,582 "learning_rate": 0.0006417223990276883,583 "loss": 2.6018707275390627,584 "step": 820585 },586 {587 "epoch": 1.3391199031085992,588 "grad_norm": 0.5254472494125366,589 "learning_rate": 0.0006331413234345977,590 "loss": 2.5202842712402345,591 "step": 830592 },593 {594 "epoch": 1.3552684699232942,595 "grad_norm": 0.4611901342868805,596 "learning_rate": 0.0006245178273449383,597 "loss": 2.527310371398926,598 "step": 840599 },600 {601 "epoch": 1.3714170367379894,602 "grad_norm": 0.46280530095100403,603 "learning_rate": 0.0006158546583127886,604 "loss": 2.5010074615478515,605 "step": 850606 },607 {608 "epoch": 1.3875656035526847,609 "grad_norm": 0.47044530510902405,610 "learning_rate": 0.0006071545765325253,611 "loss": 2.658343505859375,612 "step": 860613 },614 {615 "epoch": 1.4037141703673799,616 "grad_norm": 0.5649057030677795,617 "learning_rate": 0.0005984203539593897,618 "loss": 2.514650344848633,619 "step": 870620 },621 {622 "epoch": 1.4198627371820751,623 "grad_norm": 0.5100232362747192,624 "learning_rate": 0.0005896547734263077,625 "loss": 2.4994720458984374,626 "step": 880627 },628 {629 "epoch": 1.4360113039967703,630 "grad_norm": 0.4990105926990509,631 "learning_rate": 0.0005808606277572453,632 "loss": 2.489163398742676,633 "step": 890634 },635 {636 "epoch": 1.4521598708114656,637 "grad_norm": 0.473297655582428,638 "learning_rate": 0.0005720407188773791,639 "loss": 2.534769630432129,640 "step": 900641 },642 {643 "epoch": 1.4683084376261606,644 "grad_norm": 0.5112643837928772,645 "learning_rate": 0.000563197856920368,646 "loss": 2.5247997283935546,647 "step": 910648 },649 {650 "epoch": 1.4844570044408558,651 "grad_norm": 0.4357326924800873,652 "learning_rate": 0.0005543348593330093,653 "loss": 2.508163642883301,654 "step": 920655 },656 {657 "epoch": 1.500605571255551,658 "grad_norm": 0.47014695405960083,659 "learning_rate": 0.0005454545499775651,660 "loss": 2.6127824783325195,661 "step": 930662 },663 {664 "epoch": 1.5167541380702463,665 "grad_norm": 0.4659437835216522,666 "learning_rate": 0.0005365597582320436,667 "loss": 2.4793100357055664,668 "step": 940669 },670 {671 "epoch": 1.5329027048849415,672 "grad_norm": 0.5408269166946411,673 "learning_rate": 0.0005276533180887248,674 "loss": 2.45506591796875,675 "step": 950676 },677 {678 "epoch": 1.5490512716996365,679 "grad_norm": 0.5870039463043213,680 "learning_rate": 0.000518738067251214,681 "loss": 2.480586814880371,682 "step": 960683 },684 {685 "epoch": 1.565199838514332,686 "grad_norm": 0.48131951689720154,687 "learning_rate": 0.0005098168462303141,688 "loss": 2.589830207824707,689 "step": 970690 },691 {692 "epoch": 1.581348405329027,693 "grad_norm": 0.4618188440799713,694 "learning_rate": 0.0005008924974390041,695 "loss": 2.5488056182861327,696 "step": 980697 },698 {699 "epoch": 1.5974969721437222,700 "grad_norm": 0.49082285165786743,701 "learning_rate": 0.0004919678642868092,702 "loss": 2.4781982421875,703 "step": 990704 },705 {706 "epoch": 1.6136455389584174,707 "grad_norm": 0.47744420170783997,708 "learning_rate": 0.0004830457902738558,709 "loss": 2.517325210571289,710 "step": 1000711 },712 {713 "epoch": 1.6297941057731127,714 "grad_norm": 0.507945716381073,715 "learning_rate": 0.0004741291180848961,716 "loss": 2.5076452255249024,717 "step": 1010718 },719 {720 "epoch": 1.645942672587808,721 "grad_norm": 0.42816001176834106,722 "learning_rate": 0.000465220688683594,723 "loss": 2.671817398071289,724 "step": 1020725 },726 {727 "epoch": 1.662091239402503,728 "grad_norm": 0.4258963167667389,729 "learning_rate": 0.00045632334040735764,730 "loss": 2.533784103393555,731 "step": 1030732 },733 {734 "epoch": 1.6782398062171984,735 "grad_norm": 0.494028240442276,736 "learning_rate": 0.00044743990806300917,737 "loss": 2.514291000366211,738 "step": 1040739 },740 {741 "epoch": 1.6943883730318934,742 "grad_norm": 0.4230322539806366,743 "learning_rate": 0.00043857322202358066,744 "loss": 2.5531696319580077,745 "step": 1050746 },747 {748 "epoch": 1.7105369398465886,749 "grad_norm": 0.5738111734390259,750 "learning_rate": 0.00042972610732652105,751 "loss": 2.5059112548828124,752 "step": 1060753 },754 {755 "epoch": 1.7266855066612838,756 "grad_norm": 0.5092839002609253,757 "learning_rate": 0.0004209013827736042,758 "loss": 2.5219795227050783,759 "step": 1070760 },761 {762 "epoch": 1.7428340734759789,763 "grad_norm": 0.4812857508659363,764 "learning_rate": 0.00041210186003282274,765 "loss": 2.5235408782958983,766 "step": 1080767 },768 {769 "epoch": 1.7589826402906743,770 "grad_norm": 0.47096627950668335,771 "learning_rate": 0.000403330342742556,772 "loss": 2.574551582336426,773 "step": 1090774 },775 {776 "epoch": 1.7751312071053693,777 "grad_norm": 0.4319113790988922,778 "learning_rate": 0.0003945896256182949,779 "loss": 2.610904502868652,780 "step": 1100781 },782 {783 "epoch": 1.7912797739200645,784 "grad_norm": 0.44047966599464417,785 "learning_rate": 0.0003858824935622115,786 "loss": 2.5323257446289062,787 "step": 1110788 },789 {790 "epoch": 1.8074283407347598,791 "grad_norm": 0.548047661781311,792 "learning_rate": 0.00037721172077585287,793 "loss": 2.5165468215942384,794 "step": 1120795 },796 {797 "epoch": 1.823576907549455,798 "grad_norm": 0.46526339650154114,799 "learning_rate": 0.00036858006987624723,800 "loss": 2.502303886413574,801 "step": 1130802 },803 {804 "epoch": 1.8397254743641502,805 "grad_norm": 0.4635223150253296,806 "learning_rate": 0.0003599902910156984,807 "loss": 2.5442089080810546,808 "step": 1140809 },810 {811 "epoch": 1.8558740411788452,812 "grad_norm": 0.5317935347557068,813 "learning_rate": 0.0003514451210055527,814 "loss": 2.600077247619629,815 "step": 1150816 },817 {818 "epoch": 1.8720226079935407,819 "grad_norm": 0.5463606119155884,820 "learning_rate": 0.00034294728244421756,821 "loss": 2.574476623535156,822 "step": 1160823 },824 {825 "epoch": 1.8881711748082357,826 "grad_norm": 0.4650241732597351,827 "learning_rate": 0.00033449948284970617,828 "loss": 2.500654411315918,829 "step": 1170830 },831 {832 "epoch": 1.904319741622931,833 "grad_norm": 0.40839987993240356,834 "learning_rate": 0.00032610441379698937,835 "loss": 2.4712839126586914,836 "step": 1180837 },838 {839 "epoch": 1.9204683084376262,840 "grad_norm": 0.49943020939826965,841 "learning_rate": 0.0003177647500604252,842 "loss": 2.5296091079711913,843 "step": 1190844 },845 {846 "epoch": 1.9366168752523214,847 "grad_norm": 0.4655015468597412,848 "learning_rate": 0.00030948314876154306,849 "loss": 2.5075130462646484,850 "step": 1200851 },852 {853 "epoch": 1.9527654420670166,854 "grad_norm": 0.45307499170303345,855 "learning_rate": 0.00030126224852245056,856 "loss": 2.464124298095703,857 "step": 1210858 },859 {860 "epoch": 1.9689140088817116,861 "grad_norm": 0.5530602931976318,862 "learning_rate": 0.0002931046686251365,863 "loss": 2.553061866760254,864 "step": 1220865 },866 {867 "epoch": 1.985062575696407,868 "grad_norm": 0.46495500206947327,869 "learning_rate": 0.0002850130081769334,870 "loss": 2.486197853088379,871 "step": 1230872 },873 {874 "epoch": 2.0,875 "grad_norm": 1.9545954465866089,876 "learning_rate": 0.00027698984528241036,877 "loss": 2.4371877670288087,878 "step": 1240879 },880 {881 "epoch": 2.016148566814695,882 "grad_norm": 0.48022302985191345,883 "learning_rate": 0.00026903773622195636,884 "loss": 2.512773895263672,885 "step": 1250886 },887 {888 "epoch": 2.0322971336293905,889 "grad_norm": 0.433242529630661,890 "learning_rate": 0.00026115921463731694,891 "loss": 2.5300994873046876,892 "step": 1260893 },894 {895 "epoch": 2.0484457004440855,896 "grad_norm": 0.47226834297180176,897 "learning_rate": 0.0002533567907243446,898 "loss": 2.421502113342285,899 "step": 1270900 },901 {902 "epoch": 2.064594267258781,903 "grad_norm": 0.5992064476013184,904 "learning_rate": 0.00024563295043321783,905 "loss": 2.5453359603881838,906 "step": 1280907 },908 {909 "epoch": 2.080742834073476,910 "grad_norm": 0.4261581599712372,911 "learning_rate": 0.0002379901546763879,912 "loss": 2.495037841796875,913 "step": 1290914 },915 {916 "epoch": 2.0968914008881714,917 "grad_norm": 0.4328082203865051,918 "learning_rate": 0.00023043083854449987,919 "loss": 2.464985466003418,920 "step": 1300921 },922 {923 "epoch": 2.1130399677028664,924 "grad_norm": 0.4510248303413391,925 "learning_rate": 0.00022295741053054296,926 "loss": 2.5308864593505858,927 "step": 1310928 },929 {930 "epoch": 2.1291885345175614,931 "grad_norm": 0.49293237924575806,932 "learning_rate": 0.00021557225176247353,933 "loss": 2.5278299331665037,934 "step": 1320935 },936 {937 "epoch": 2.145337101332257,938 "grad_norm": 0.4132377505302429,939 "learning_rate": 0.0002082777152445589,940 "loss": 2.398031234741211,941 "step": 1330942 },943 {944 "epoch": 2.161485668146952,945 "grad_norm": 0.5191354751586914,946 "learning_rate": 0.00020107612510768014,947 "loss": 2.5248828887939454,948 "step": 1340949 },950 {951 "epoch": 2.1776342349616473,952 "grad_norm": 0.5512005686759949,953 "learning_rate": 0.00019396977586883475,954 "loss": 2.4451154708862304,955 "step": 1350956 },957 {958 "epoch": 2.1937828017763423,959 "grad_norm": 0.42351678013801575,960 "learning_rate": 0.00018696093170007493,961 "loss": 2.573942756652832,962 "step": 1360963 },964 {965 "epoch": 2.2099313685910373,966 "grad_norm": 0.45575806498527527,967 "learning_rate": 0.00018005182570711366,968 "loss": 2.5537620544433595,969 "step": 1370970 },971 {972 "epoch": 2.226079935405733,973 "grad_norm": 0.46785682439804077,974 "learning_rate": 0.0001732446592178295,975 "loss": 2.491817092895508,976 "step": 1380977 },978 {979 "epoch": 2.242228502220428,980 "grad_norm": 0.45513054728507996,981 "learning_rate": 0.00016654160108089594,982 "loss": 2.5171764373779295,983 "step": 1390984 },985 {986 "epoch": 2.2583770690351233,987 "grad_norm": 0.43288710713386536,988 "learning_rate": 0.00015994478697475885,989 "loss": 2.5143251419067383,990 "step": 1400991 },992 {993 "epoch": 2.2745256358498183,994 "grad_norm": 0.4459301233291626,995 "learning_rate": 0.00015345631872718213,996 "loss": 2.5065849304199217,997 "step": 1410998 },999 {1000 "epoch": 2.2906742026645137,1001 "grad_norm": 0.501880407333374,1002 "learning_rate": 0.00014707826364557985,1003 "loss": 2.4833837509155274,1004 "step": 14201005 },1006 {1007 "epoch": 2.3068227694792087,1008 "grad_norm": 0.4559042453765869,1009 "learning_rate": 0.00014081265385834557,1010 "loss": 2.5120367050170898,1011 "step": 14301012 },1013 {1014 "epoch": 2.3229713362939037,1015 "grad_norm": 0.48048946261405945,1016 "learning_rate": 0.000134661485667391,1017 "loss": 2.4629817962646485,1018 "step": 14401019 },1020 {1021 "epoch": 2.339119903108599,1022 "grad_norm": 0.46413764357566833,1023 "learning_rate": 0.0001286267189120986,1024 "loss": 2.4572961807250975,1025 "step": 14501026 },1027 {1028 "epoch": 2.355268469923294,1029 "grad_norm": 0.4971129298210144,1030 "learning_rate": 0.000122710276344893,1031 "loss": 2.5448049545288085,1032 "step": 14601033 },1034 {1035 "epoch": 2.3714170367379896,1036 "grad_norm": 0.45018401741981506,1037 "learning_rate": 0.00011691404301862746,1038 "loss": 2.551463317871094,1039 "step": 14701040 },1041 {1042 "epoch": 2.3875656035526847,1043 "grad_norm": 0.49596303701400757,1044 "learning_rate": 0.00011123986568598249,1045 "loss": 2.5440711975097656,1046 "step": 14801047 },1048 {1049 "epoch": 2.4037141703673797,1050 "grad_norm": 0.47923141717910767,1051 "learning_rate": 0.00010568955221106713,1052 "loss": 2.45603084564209,1053 "step": 14901054 },1055 {1056 "epoch": 2.419862737182075,1057 "grad_norm": 0.4507387578487396,1058 "learning_rate": 0.0001002648709934108,1059 "loss": 2.458144187927246,1060 "step": 15001061 },1062 {1063 "epoch": 2.43601130399677,1064 "grad_norm": 0.46995073556900024,1065 "learning_rate": 9.496755040452915e-05,1066 "loss": 2.4886669158935546,1067 "step": 15101068 },1069 {1070 "epoch": 2.4521598708114656,1071 "grad_norm": 0.4773581326007843,1072 "learning_rate": 8.979927823724321e-05,1073 "loss": 2.548818016052246,1074 "step": 15201075 },1076 {1077 "epoch": 2.4683084376261606,1078 "grad_norm": 0.49100548028945923,1079 "learning_rate": 8.476170116792736e-05,1080 "loss": 2.5328250885009767,1081 "step": 15301082 },1083 {1084 "epoch": 2.484457004440856,1085 "grad_norm": 0.5164358615875244,1086 "learning_rate": 7.985642423185718e-05,1087 "loss": 2.4474281311035155,1088 "step": 15401089 },1090 {1091 "epoch": 2.500605571255551,1092 "grad_norm": 0.48450803756713867,1093 "learning_rate": 7.508501031182585e-05,1094 "loss": 2.470208168029785,1095 "step": 15501096 },1097 {1098 "epoch": 2.5167541380702465,1099 "grad_norm": 0.4779358208179474,1100 "learning_rate": 7.044897964018949e-05,1101 "loss": 2.443818283081055,1102 "step": 15601103 },1104 {1105 "epoch": 2.5329027048849415,1106 "grad_norm": 0.42919352650642395,1107 "learning_rate": 6.594980931450223e-05,1108 "loss": 2.4840776443481447,1109 "step": 15701110 },1111 {1112 "epoch": 2.5490512716996365,1113 "grad_norm": 0.4021783769130707,1114 "learning_rate": 6.158893282689454e-05,1115 "loss": 2.450935173034668,1116 "step": 15801117 },1118 {1119 "epoch": 2.565199838514332,1120 "grad_norm": 0.5504807829856873,1121 "learning_rate": 5.7367739607344093e-05,1122 "loss": 2.477644348144531,1123 "step": 15901124 },1125 {1126 "epoch": 2.581348405329027,1127 "grad_norm": 0.3885093331336975,1128 "learning_rate": 5.328757458098665e-05,1129 "loss": 2.449785041809082,1130 "step": 16001131 },1132 {1133 "epoch": 2.5974969721437224,1134 "grad_norm": 0.5313092470169067,1135 "learning_rate": 4.934973773960572e-05,1136 "loss": 2.564461898803711,1137 "step": 16101138 },1139 {1140 "epoch": 2.6136455389584174,1141 "grad_norm": 0.5081238150596619,1142 "learning_rate": 4.5555483727438896e-05,1143 "loss": 2.5144027709960937,1144 "step": 16201145 },1146 {1147 "epoch": 2.6297941057731125,1148 "grad_norm": 0.45351824164390564,1149 "learning_rate": 4.190602144143207e-05,1150 "loss": 2.5690656661987306,1151 "step": 16301152 },1153 {1154 "epoch": 2.645942672587808,1155 "grad_norm": 0.49749699234962463,1156 "learning_rate": 3.840251364607045e-05,1157 "loss": 2.5524566650390623,1158 "step": 16401159 },1160 {1161 "epoch": 2.662091239402503,1162 "grad_norm": 0.4736417233943939,1163 "learning_rate": 3.50460766029066e-05,1164 "loss": 2.437306022644043,1165 "step": 16501166 },1167 {1168 "epoch": 2.6782398062171984,1169 "grad_norm": 0.54044508934021,1170 "learning_rate": 3.183777971490576e-05,1171 "loss": 2.4329130172729494,1172 "step": 16601173 },1174 {1175 "epoch": 2.6943883730318934,1176 "grad_norm": 0.5381774306297302,1177 "learning_rate": 2.8778645185720487e-05,1178 "loss": 2.5384393692016602,1179 "step": 16701180 },1181 {1182 "epoch": 2.7105369398465884,1183 "grad_norm": 0.4624033570289612,1184 "learning_rate": 2.5869647694003962e-05,1185 "loss": 2.5221799850463866,1186 "step": 16801187 },1188 {1189 "epoch": 2.726685506661284,1190 "grad_norm": 0.49552807211875916,1191 "learning_rate": 2.3111714082864887e-05,1192 "loss": 2.519091987609863,1193 "step": 16901194 },1195 {1196 "epoch": 2.742834073475979,1197 "grad_norm": 0.4731680154800415,1198 "learning_rate": 2.0505723064563886e-05,1199 "loss": 2.4723621368408204,1200 "step": 1700