agentlans/GIST-small-topic
028
1{2 "best_global_step": 211530,3 "best_metric": 0.9179618788534967,4 "best_model_checkpoint": "./GIST-small-topic/checkpoint-211530",5 "epoch": 3.0,6 "eval_steps": 500,7 "global_step": 211530,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.0070911927386186355,14 "grad_norm": 2.0094034671783447,15 "learning_rate": 4.988204982744765e-05,16 "loss": 2.21929736328125,17 "step": 50018 },19 {20 "epoch": 0.014182385477237271,21 "grad_norm": 19.219717025756836,22 "learning_rate": 4.9763863281804004e-05,23 "loss": 1.0627626953125,24 "step": 100025 },26 {27 "epoch": 0.021273578215855907,28 "grad_norm": 12.463168144226074,29 "learning_rate": 4.964567673616036e-05,30 "loss": 0.7230818481445312,31 "step": 150032 },33 {34 "epoch": 0.028364770954474542,35 "grad_norm": 30.950218200683594,36 "learning_rate": 4.952749019051671e-05,37 "loss": 0.56197265625,38 "step": 200039 },40 {41 "epoch": 0.03545596369309318,42 "grad_norm": 2.983157157897949,43 "learning_rate": 4.940930364487307e-05,44 "loss": 0.542384033203125,45 "step": 250046 },47 {48 "epoch": 0.042547156431711815,49 "grad_norm": 5.0553436279296875,50 "learning_rate": 4.929111709922943e-05,51 "loss": 0.4953382568359375,52 "step": 300053 },54 {55 "epoch": 0.04963834917033045,56 "grad_norm": 12.18031120300293,57 "learning_rate": 4.917293055358578e-05,58 "loss": 0.4707428283691406,59 "step": 350060 },61 {62 "epoch": 0.056729541908949084,63 "grad_norm": 13.765538215637207,64 "learning_rate": 4.905474400794214e-05,65 "loss": 0.46302090454101563,66 "step": 400067 },68 {69 "epoch": 0.06382073464756773,70 "grad_norm": 27.128658294677734,71 "learning_rate": 4.893655746229849e-05,72 "loss": 0.4627261962890625,73 "step": 450074 },75 {76 "epoch": 0.07091192738618636,77 "grad_norm": 22.089130401611328,78 "learning_rate": 4.8818370916654845e-05,79 "loss": 0.48565313720703124,80 "step": 500081 },82 {83 "epoch": 0.078003120124805,84 "grad_norm": 19.198444366455078,85 "learning_rate": 4.8700184371011206e-05,86 "loss": 0.4377886962890625,87 "step": 550088 },89 {90 "epoch": 0.08509431286342363,91 "grad_norm": 26.68898582458496,92 "learning_rate": 4.858199782536757e-05,93 "loss": 0.45854840087890625,94 "step": 600095 },96 {97 "epoch": 0.09218550560204226,98 "grad_norm": 1.396219253540039,99 "learning_rate": 4.846381127972392e-05,100 "loss": 0.42720388793945313,101 "step": 6500102 },103 {104 "epoch": 0.0992766983406609,105 "grad_norm": 17.45922088623047,106 "learning_rate": 4.8345624734080276e-05,107 "loss": 0.4388797912597656,108 "step": 7000109 },110 {111 "epoch": 0.10636789107927953,112 "grad_norm": 13.813079833984375,113 "learning_rate": 4.822743818843663e-05,114 "loss": 0.43045758056640626,115 "step": 7500116 },117 {118 "epoch": 0.11345908381789817,119 "grad_norm": 19.49132537841797,120 "learning_rate": 4.8109251642792985e-05,121 "loss": 0.4109803771972656,122 "step": 8000123 },124 {125 "epoch": 0.1205502765565168,126 "grad_norm": 15.026893615722656,127 "learning_rate": 4.799106509714934e-05,128 "loss": 0.43473480224609373,129 "step": 8500130 },131 {132 "epoch": 0.12764146929513545,133 "grad_norm": 0.4883650541305542,134 "learning_rate": 4.78728785515057e-05,135 "loss": 0.4177641296386719,136 "step": 9000137 },138 {139 "epoch": 0.13473266203375409,140 "grad_norm": 18.900754928588867,141 "learning_rate": 4.7754692005862054e-05,142 "loss": 0.38533172607421873,143 "step": 9500144 },145 {146 "epoch": 0.14182385477237272,147 "grad_norm": 1.1473286151885986,148 "learning_rate": 4.763650546021841e-05,149 "loss": 0.4119681396484375,150 "step": 10000151 },152 {153 "epoch": 0.14891504751099136,154 "grad_norm": 11.821301460266113,155 "learning_rate": 4.751831891457477e-05,156 "loss": 0.40965200805664065,157 "step": 10500158 },159 {160 "epoch": 0.15600624024961,161 "grad_norm": 23.506179809570312,162 "learning_rate": 4.7400132368931124e-05,163 "loss": 0.3976383972167969,164 "step": 11000165 },166 {167 "epoch": 0.16309743298822862,168 "grad_norm": 5.233912944793701,169 "learning_rate": 4.728194582328748e-05,170 "loss": 0.42674627685546873,171 "step": 11500172 },173 {174 "epoch": 0.17018862572684726,175 "grad_norm": 0.5937948226928711,176 "learning_rate": 4.716375927764384e-05,177 "loss": 0.40512103271484373,178 "step": 12000179 },180 {181 "epoch": 0.1772798184654659,182 "grad_norm": 17.91236686706543,183 "learning_rate": 4.7045572732000194e-05,184 "loss": 0.4136376953125,185 "step": 12500186 },187 {188 "epoch": 0.18437101120408453,189 "grad_norm": 22.474529266357422,190 "learning_rate": 4.692738618635655e-05,191 "loss": 0.4313943176269531,192 "step": 13000193 },194 {195 "epoch": 0.19146220394270316,196 "grad_norm": 8.908188819885254,197 "learning_rate": 4.68091996407129e-05,198 "loss": 0.407843017578125,199 "step": 13500200 },201 {202 "epoch": 0.1985533966813218,203 "grad_norm": 18.582136154174805,204 "learning_rate": 4.6691013095069256e-05,205 "loss": 0.4009266357421875,206 "step": 14000207 },208 {209 "epoch": 0.20564458941994043,210 "grad_norm": 10.631417274475098,211 "learning_rate": 4.657282654942561e-05,212 "loss": 0.3847767333984375,213 "step": 14500214 },215 {216 "epoch": 0.21273578215855907,217 "grad_norm": 0.06845115125179291,218 "learning_rate": 4.645464000378197e-05,219 "loss": 0.404919189453125,220 "step": 15000221 },222 {223 "epoch": 0.2198269748971777,224 "grad_norm": 10.31063175201416,225 "learning_rate": 4.6336453458138326e-05,226 "loss": 0.41001177978515624,227 "step": 15500228 },229 {230 "epoch": 0.22691816763579634,231 "grad_norm": 22.720964431762695,232 "learning_rate": 4.621826691249469e-05,233 "loss": 0.4126224365234375,234 "step": 16000235 },236 {237 "epoch": 0.23400936037441497,238 "grad_norm": 15.995619773864746,239 "learning_rate": 4.610008036685104e-05,240 "loss": 0.39923910522460937,241 "step": 16500242 },243 {244 "epoch": 0.2411005531130336,245 "grad_norm": 45.834747314453125,246 "learning_rate": 4.5981893821207396e-05,247 "loss": 0.3683683166503906,248 "step": 17000249 },250 {251 "epoch": 0.24819174585165224,252 "grad_norm": 10.192611694335938,253 "learning_rate": 4.586370727556375e-05,254 "loss": 0.38183563232421874,255 "step": 17500256 },257 {258 "epoch": 0.2552829385902709,259 "grad_norm": 17.221702575683594,260 "learning_rate": 4.574552072992011e-05,261 "loss": 0.3848875427246094,262 "step": 18000263 },264 {265 "epoch": 0.26237413132888954,266 "grad_norm": 11.800912857055664,267 "learning_rate": 4.5627334184276465e-05,268 "loss": 0.3841501159667969,269 "step": 18500270 },271 {272 "epoch": 0.26946532406750817,273 "grad_norm": 10.162900924682617,274 "learning_rate": 4.550914763863282e-05,275 "loss": 0.3888123779296875,276 "step": 19000277 },278 {279 "epoch": 0.2765565168061268,280 "grad_norm": 4.604160785675049,281 "learning_rate": 4.5390961092989174e-05,282 "loss": 0.3991587219238281,283 "step": 19500284 },285 {286 "epoch": 0.28364770954474544,287 "grad_norm": 20.095441818237305,288 "learning_rate": 4.527277454734553e-05,289 "loss": 0.3958879089355469,290 "step": 20000291 },292 {293 "epoch": 0.2907389022833641,294 "grad_norm": 12.304089546203613,295 "learning_rate": 4.515458800170189e-05,296 "loss": 0.3968980712890625,297 "step": 20500298 },299 {300 "epoch": 0.2978300950219827,301 "grad_norm": 0.5610142350196838,302 "learning_rate": 4.503640145605825e-05,303 "loss": 0.4232771301269531,304 "step": 21000305 },306 {307 "epoch": 0.30492128776060134,308 "grad_norm": 2.9310262203216553,309 "learning_rate": 4.4918214910414605e-05,310 "loss": 0.39260968017578124,311 "step": 21500312 },313 {314 "epoch": 0.31201248049922,315 "grad_norm": 0.5716455578804016,316 "learning_rate": 4.480002836477096e-05,317 "loss": 0.38827359008789064,318 "step": 22000319 },320 {321 "epoch": 0.3191036732378386,322 "grad_norm": 1.3526256084442139,323 "learning_rate": 4.468184181912731e-05,324 "loss": 0.37964959716796876,325 "step": 22500326 },327 {328 "epoch": 0.32619486597645725,329 "grad_norm": 15.395561218261719,330 "learning_rate": 4.456365527348367e-05,331 "loss": 0.3920819091796875,332 "step": 23000333 },334 {335 "epoch": 0.3332860587150759,336 "grad_norm": 10.289068222045898,337 "learning_rate": 4.444546872784002e-05,338 "loss": 0.38668710327148437,339 "step": 23500340 },341 {342 "epoch": 0.3403772514536945,343 "grad_norm": 1.6159920692443848,344 "learning_rate": 4.432728218219638e-05,345 "loss": 0.3819559326171875,346 "step": 24000347 },348 {349 "epoch": 0.34746844419231315,350 "grad_norm": 7.291048526763916,351 "learning_rate": 4.420909563655274e-05,352 "loss": 0.34942718505859377,353 "step": 24500354 },355 {356 "epoch": 0.3545596369309318,357 "grad_norm": 21.11905288696289,358 "learning_rate": 4.409090909090909e-05,359 "loss": 0.4017558898925781,360 "step": 25000361 },362 {363 "epoch": 0.3616508296695504,364 "grad_norm": 11.451282501220703,365 "learning_rate": 4.3972722545265446e-05,366 "loss": 0.37077435302734374,367 "step": 25500368 },369 {370 "epoch": 0.36874202240816906,371 "grad_norm": 16.3957462310791,372 "learning_rate": 4.385453599962181e-05,373 "loss": 0.3965981140136719,374 "step": 26000375 },376 {377 "epoch": 0.3758332151467877,378 "grad_norm": 26.137174606323242,379 "learning_rate": 4.373634945397816e-05,380 "loss": 0.40133779907226563,381 "step": 26500382 },383 {384 "epoch": 0.3829244078854063,385 "grad_norm": 21.809417724609375,386 "learning_rate": 4.361816290833452e-05,387 "loss": 0.3455391845703125,388 "step": 27000389 },390 {391 "epoch": 0.39001560062402496,392 "grad_norm": 9.511174201965332,393 "learning_rate": 4.3499976362690876e-05,394 "loss": 0.39233285522460937,395 "step": 27500396 },397 {398 "epoch": 0.3971067933626436,399 "grad_norm": 31.224679946899414,400 "learning_rate": 4.338178981704723e-05,401 "loss": 0.37783285522460935,402 "step": 28000403 },404 {405 "epoch": 0.40419798610126223,406 "grad_norm": 3.0387356281280518,407 "learning_rate": 4.3263603271403585e-05,408 "loss": 0.36522085571289065,409 "step": 28500410 },411 {412 "epoch": 0.41128917883988086,413 "grad_norm": 9.661357879638672,414 "learning_rate": 4.314541672575994e-05,415 "loss": 0.3850714721679688,416 "step": 29000417 },418 {419 "epoch": 0.4183803715784995,420 "grad_norm": 20.81166648864746,421 "learning_rate": 4.3027230180116293e-05,422 "loss": 0.3951400146484375,423 "step": 29500424 },425 {426 "epoch": 0.42547156431711813,427 "grad_norm": 11.138774871826172,428 "learning_rate": 4.290904363447265e-05,429 "loss": 0.3763404541015625,430 "step": 30000431 },432 {433 "epoch": 0.43256275705573677,434 "grad_norm": 0.7437636852264404,435 "learning_rate": 4.279085708882901e-05,436 "loss": 0.36979705810546876,437 "step": 30500438 },439 {440 "epoch": 0.4396539497943554,441 "grad_norm": 23.123035430908203,442 "learning_rate": 4.267267054318537e-05,443 "loss": 0.3605682373046875,444 "step": 31000445 },446 {447 "epoch": 0.44674514253297404,448 "grad_norm": 11.462782859802246,449 "learning_rate": 4.2554483997541724e-05,450 "loss": 0.3390813293457031,451 "step": 31500452 },453 {454 "epoch": 0.4538363352715927,455 "grad_norm": 12.093498229980469,456 "learning_rate": 4.243629745189808e-05,457 "loss": 0.37293450927734373,458 "step": 32000459 },460 {461 "epoch": 0.4609275280102113,462 "grad_norm": 0.0507306233048439,463 "learning_rate": 4.231811090625443e-05,464 "loss": 0.39073757934570313,465 "step": 32500466 },467 {468 "epoch": 0.46801872074882994,469 "grad_norm": 15.834416389465332,470 "learning_rate": 4.219992436061079e-05,471 "loss": 0.3769065856933594,472 "step": 33000473 },474 {475 "epoch": 0.4751099134874486,476 "grad_norm": 38.923831939697266,477 "learning_rate": 4.208173781496715e-05,478 "loss": 0.34681292724609375,479 "step": 33500480 },481 {482 "epoch": 0.4822011062260672,483 "grad_norm": 3.2983150482177734,484 "learning_rate": 4.19635512693235e-05,485 "loss": 0.3393735961914062,486 "step": 34000487 },488 {489 "epoch": 0.48929229896468585,490 "grad_norm": 13.693626403808594,491 "learning_rate": 4.184536472367986e-05,492 "loss": 0.3842292175292969,493 "step": 34500494 },495 {496 "epoch": 0.4963834917033045,497 "grad_norm": 17.57269287109375,498 "learning_rate": 4.172717817803621e-05,499 "loss": 0.3563892517089844,500 "step": 35000501 },502 {503 "epoch": 0.5034746844419231,504 "grad_norm": 4.0084710121154785,505 "learning_rate": 4.160899163239257e-05,506 "loss": 0.39765109252929687,507 "step": 35500508 },509 {510 "epoch": 0.5105658771805418,511 "grad_norm": 20.67154884338379,512 "learning_rate": 4.1490805086748926e-05,513 "loss": 0.35460427856445315,514 "step": 36000515 },516 {517 "epoch": 0.5176570699191604,518 "grad_norm": 0.30911800265312195,519 "learning_rate": 4.137261854110529e-05,520 "loss": 0.36283389282226564,521 "step": 36500522 },523 {524 "epoch": 0.5247482626577791,525 "grad_norm": 3.699970245361328,526 "learning_rate": 4.125443199546164e-05,527 "loss": 0.3951703491210937,528 "step": 37000529 },530 {531 "epoch": 0.5318394553963977,532 "grad_norm": 35.91598129272461,533 "learning_rate": 4.1136245449817996e-05,534 "loss": 0.3673123779296875,535 "step": 37500536 },537 {538 "epoch": 0.5389306481350163,539 "grad_norm": 15.166389465332031,540 "learning_rate": 4.101805890417435e-05,541 "loss": 0.3646431579589844,542 "step": 38000543 },544 {545 "epoch": 0.5460218408736349,546 "grad_norm": 4.839053630828857,547 "learning_rate": 4.0899872358530705e-05,548 "loss": 0.37225506591796875,549 "step": 38500550 },551 {552 "epoch": 0.5531130336122536,553 "grad_norm": 16.341421127319336,554 "learning_rate": 4.078168581288706e-05,555 "loss": 0.3248492431640625,556 "step": 39000557 },558 {559 "epoch": 0.5602042263508722,560 "grad_norm": 12.289342880249023,561 "learning_rate": 4.066349926724342e-05,562 "loss": 0.35200335693359375,563 "step": 39500564 },565 {566 "epoch": 0.5672954190894909,567 "grad_norm": 0.07165870815515518,568 "learning_rate": 4.0545312721599774e-05,569 "loss": 0.3465135192871094,570 "step": 40000571 },572 {573 "epoch": 0.5743866118281095,574 "grad_norm": 19.236539840698242,575 "learning_rate": 4.042712617595613e-05,576 "loss": 0.36539205932617186,577 "step": 40500578 },579 {580 "epoch": 0.5814778045667282,581 "grad_norm": 1.1958494186401367,582 "learning_rate": 4.030893963031249e-05,583 "loss": 0.3689007873535156,584 "step": 41000585 },586 {587 "epoch": 0.5885689973053467,588 "grad_norm": 22.092870712280273,589 "learning_rate": 4.0190753084668844e-05,590 "loss": 0.37182241821289064,591 "step": 41500592 },593 {594 "epoch": 0.5956601900439654,595 "grad_norm": 0.08594904839992523,596 "learning_rate": 4.00725665390252e-05,597 "loss": 0.36475091552734373,598 "step": 42000599 },600 {601 "epoch": 0.602751382782584,602 "grad_norm": 29.551023483276367,603 "learning_rate": 3.995437999338156e-05,604 "loss": 0.331034423828125,605 "step": 42500606 },607 {608 "epoch": 0.6098425755212027,609 "grad_norm": 0.04614920914173126,610 "learning_rate": 3.9836193447737913e-05,611 "loss": 0.33374911499023435,612 "step": 43000613 },614 {615 "epoch": 0.6169337682598213,616 "grad_norm": 15.710551261901855,617 "learning_rate": 3.971800690209427e-05,618 "loss": 0.37484417724609376,619 "step": 43500620 },621 {622 "epoch": 0.62402496099844,623 "grad_norm": 37.30379104614258,624 "learning_rate": 3.959982035645062e-05,625 "loss": 0.32213079833984376,626 "step": 44000627 },628 {629 "epoch": 0.6311161537370585,630 "grad_norm": 6.224698543548584,631 "learning_rate": 3.9481633810806976e-05,632 "loss": 0.3595847473144531,633 "step": 44500634 },635 {636 "epoch": 0.6382073464756772,637 "grad_norm": 6.233162879943848,638 "learning_rate": 3.936344726516333e-05,639 "loss": 0.34365115356445314,640 "step": 45000641 },642 {643 "epoch": 0.6452985392142958,644 "grad_norm": 14.356497764587402,645 "learning_rate": 3.924526071951969e-05,646 "loss": 0.3619053955078125,647 "step": 45500648 },649 {650 "epoch": 0.6523897319529145,651 "grad_norm": 9.267119407653809,652 "learning_rate": 3.912707417387605e-05,653 "loss": 0.35733905029296875,654 "step": 46000655 },656 {657 "epoch": 0.6594809246915331,658 "grad_norm": 4.029196739196777,659 "learning_rate": 3.900888762823241e-05,660 "loss": 0.3212258605957031,661 "step": 46500662 },663 {664 "epoch": 0.6665721174301518,665 "grad_norm": 34.695552825927734,666 "learning_rate": 3.889070108258876e-05,667 "loss": 0.3341042785644531,668 "step": 47000669 },670 {671 "epoch": 0.6736633101687703,672 "grad_norm": 0.026256900280714035,673 "learning_rate": 3.8772514536945116e-05,674 "loss": 0.336823486328125,675 "step": 47500676 },677 {678 "epoch": 0.680754502907389,679 "grad_norm": 17.9473819732666,680 "learning_rate": 3.865432799130147e-05,681 "loss": 0.3473232727050781,682 "step": 48000683 },684 {685 "epoch": 0.6878456956460076,686 "grad_norm": 10.06433391571045,687 "learning_rate": 3.853614144565783e-05,688 "loss": 0.3433890075683594,689 "step": 48500690 },691 {692 "epoch": 0.6949368883846263,693 "grad_norm": 9.97581672668457,694 "learning_rate": 3.8417954900014185e-05,695 "loss": 0.3339334716796875,696 "step": 49000697 },698 {699 "epoch": 0.7020280811232449,700 "grad_norm": 2.1598761081695557,701 "learning_rate": 3.829976835437054e-05,702 "loss": 0.34377346801757813,703 "step": 49500704 },705 {706 "epoch": 0.7091192738618636,707 "grad_norm": 0.6067615747451782,708 "learning_rate": 3.8181581808726894e-05,709 "loss": 0.3535705261230469,710 "step": 50000711 },712 {713 "epoch": 0.7162104666004822,714 "grad_norm": 4.127110958099365,715 "learning_rate": 3.806339526308325e-05,716 "loss": 0.3544539794921875,717 "step": 50500718 },719 {720 "epoch": 0.7233016593391008,721 "grad_norm": 0.1849542111158371,722 "learning_rate": 3.794520871743961e-05,723 "loss": 0.3537879943847656,724 "step": 51000725 },726 {727 "epoch": 0.7303928520777194,728 "grad_norm": 3.8822484016418457,729 "learning_rate": 3.782702217179597e-05,730 "loss": 0.3630632629394531,731 "step": 51500732 },733 {734 "epoch": 0.7374840448163381,735 "grad_norm": 7.645042419433594,736 "learning_rate": 3.7708835626152324e-05,737 "loss": 0.3490135498046875,738 "step": 52000739 },740 {741 "epoch": 0.7445752375549567,742 "grad_norm": 8.459843635559082,743 "learning_rate": 3.759064908050868e-05,744 "loss": 0.31747186279296874,745 "step": 52500746 },747 {748 "epoch": 0.7516664302935754,749 "grad_norm": 1.0256061553955078,750 "learning_rate": 3.747246253486503e-05,751 "loss": 0.37400778198242185,752 "step": 53000753 },754 {755 "epoch": 0.758757623032194,756 "grad_norm": 15.987700462341309,757 "learning_rate": 3.735427598922139e-05,758 "loss": 0.32377114868164064,759 "step": 53500760 },761 {762 "epoch": 0.7658488157708127,763 "grad_norm": 0.1935882717370987,764 "learning_rate": 3.723608944357774e-05,765 "loss": 0.3376795654296875,766 "step": 54000767 },768 {769 "epoch": 0.7729400085094312,770 "grad_norm": 1.3788025379180908,771 "learning_rate": 3.71179028979341e-05,772 "loss": 0.3611544189453125,773 "step": 54500774 },775 {776 "epoch": 0.7800312012480499,777 "grad_norm": 26.272855758666992,778 "learning_rate": 3.699971635229046e-05,779 "loss": 0.32168243408203123,780 "step": 55000781 },782 {783 "epoch": 0.7871223939866686,784 "grad_norm": 0.6588231921195984,785 "learning_rate": 3.688152980664681e-05,786 "loss": 0.33372409057617186,787 "step": 55500788 },789 {790 "epoch": 0.7942135867252872,791 "grad_norm": 11.952702522277832,792 "learning_rate": 3.676334326100317e-05,793 "loss": 0.35271978759765626,794 "step": 56000795 },796 {797 "epoch": 0.8013047794639059,798 "grad_norm": 7.862829685211182,799 "learning_rate": 3.6645156715359527e-05,800 "loss": 0.37077886962890627,801 "step": 56500802 },803 {804 "epoch": 0.8083959722025245,805 "grad_norm": 0.029279431328177452,806 "learning_rate": 3.652697016971588e-05,807 "loss": 0.330326171875,808 "step": 57000809 },810 {811 "epoch": 0.8154871649411432,812 "grad_norm": 34.08498001098633,813 "learning_rate": 3.6408783624072235e-05,814 "loss": 0.34447216796875,815 "step": 57500816 },817 {818 "epoch": 0.8225783576797617,819 "grad_norm": 0.06102259084582329,820 "learning_rate": 3.6290597078428596e-05,821 "loss": 0.33774069213867186,822 "step": 58000823 },824 {825 "epoch": 0.8296695504183804,826 "grad_norm": 11.09460163116455,827 "learning_rate": 3.617241053278495e-05,828 "loss": 0.33897756958007813,829 "step": 58500830 },831 {832 "epoch": 0.836760743156999,833 "grad_norm": 0.3205820322036743,834 "learning_rate": 3.6054223987141305e-05,835 "loss": 0.3516035461425781,836 "step": 59000837 },838 {839 "epoch": 0.8438519358956177,840 "grad_norm": 6.811905860900879,841 "learning_rate": 3.593603744149766e-05,842 "loss": 0.3145771179199219,843 "step": 59500844 },845 {846 "epoch": 0.8509431286342363,847 "grad_norm": 0.2537534832954407,848 "learning_rate": 3.581785089585401e-05,849 "loss": 0.3381671447753906,850 "step": 60000851 },852 {853 "epoch": 0.858034321372855,854 "grad_norm": 32.04276657104492,855 "learning_rate": 3.5699664350210374e-05,856 "loss": 0.3617617797851562,857 "step": 60500858 },859 {860 "epoch": 0.8651255141114735,861 "grad_norm": 23.124114990234375,862 "learning_rate": 3.558147780456673e-05,863 "loss": 0.29876913452148435,864 "step": 61000865 },866 {867 "epoch": 0.8722167068500922,868 "grad_norm": 18.933256149291992,869 "learning_rate": 3.546329125892309e-05,870 "loss": 0.3718148803710937,871 "step": 61500872 },873 {874 "epoch": 0.8793078995887108,875 "grad_norm": 0.27876582741737366,876 "learning_rate": 3.5345104713279444e-05,877 "loss": 0.3371610717773437,878 "step": 62000879 },880 {881 "epoch": 0.8863990923273295,882 "grad_norm": 0.8196110129356384,883 "learning_rate": 3.52269181676358e-05,884 "loss": 0.35435800170898435,885 "step": 62500886 },887 {888 "epoch": 0.8934902850659481,889 "grad_norm": 1.0336010456085205,890 "learning_rate": 3.510873162199215e-05,891 "loss": 0.34713302612304686,892 "step": 63000893 },894 {895 "epoch": 0.9005814778045668,896 "grad_norm": 7.554769515991211,897 "learning_rate": 3.499054507634851e-05,898 "loss": 0.30580343627929685,899 "step": 63500900 },901 {902 "epoch": 0.9076726705431853,903 "grad_norm": 13.311524391174316,904 "learning_rate": 3.487235853070487e-05,905 "loss": 0.3226221618652344,906 "step": 64000907 },908 {909 "epoch": 0.914763863281804,910 "grad_norm": 8.582770347595215,911 "learning_rate": 3.475417198506122e-05,912 "loss": 0.3254347229003906,913 "step": 64500914 },915 {916 "epoch": 0.9218550560204226,917 "grad_norm": 13.36210823059082,918 "learning_rate": 3.4635985439417577e-05,919 "loss": 0.32660067749023436,920 "step": 65000921 },922 {923 "epoch": 0.9289462487590413,924 "grad_norm": 9.560787200927734,925 "learning_rate": 3.451779889377393e-05,926 "loss": 0.33592776489257814,927 "step": 65500928 },929 {930 "epoch": 0.9360374414976599,931 "grad_norm": 2.2018673419952393,932 "learning_rate": 3.439961234813029e-05,933 "loss": 0.34028265380859374,934 "step": 66000935 },936 {937 "epoch": 0.9431286342362786,938 "grad_norm": 0.298260897397995,939 "learning_rate": 3.4281425802486646e-05,940 "loss": 0.3319949951171875,941 "step": 66500942 },943 {944 "epoch": 0.9502198269748972,945 "grad_norm": 25.438379287719727,946 "learning_rate": 3.416323925684301e-05,947 "loss": 0.33092230224609376,948 "step": 67000949 },950 {951 "epoch": 0.9573110197135158,952 "grad_norm": 20.164203643798828,953 "learning_rate": 3.404505271119936e-05,954 "loss": 0.3341027526855469,955 "step": 67500956 },957 {958 "epoch": 0.9644022124521344,959 "grad_norm": 1.966504454612732,960 "learning_rate": 3.3926866165555716e-05,961 "loss": 0.3280333557128906,962 "step": 68000963 },964 {965 "epoch": 0.9714934051907531,966 "grad_norm": 0.7266027331352234,967 "learning_rate": 3.380867961991207e-05,968 "loss": 0.30428872680664065,969 "step": 68500970 },971 {972 "epoch": 0.9785845979293717,973 "grad_norm": 10.37846565246582,974 "learning_rate": 3.3690493074268424e-05,975 "loss": 0.3406554870605469,976 "step": 69000977 },978 {979 "epoch": 0.9856757906679904,980 "grad_norm": 10.847968101501465,981 "learning_rate": 3.357230652862478e-05,982 "loss": 0.3461930847167969,983 "step": 69500984 },985 {986 "epoch": 0.992766983406609,987 "grad_norm": 4.485472679138184,988 "learning_rate": 3.345411998298114e-05,989 "loss": 0.32495584106445313,990 "step": 70000991 },992 {993 "epoch": 0.9998581761452277,994 "grad_norm": 7.784725189208984,995 "learning_rate": 3.3335933437337494e-05,996 "loss": 0.32551593017578123,997 "step": 70500998 },999 {1000 "epoch": 1.0,1001 "eval_f1": 0.9001437024994532,1002 "eval_loss": 0.3130093514919281,1003 "eval_runtime": 35.0631,1004 "eval_samples_per_second": 1787.518,1005 "eval_steps_per_second": 223.454,1006 "step": 705101007 },1008 {1009 "epoch": 1.0069493688838462,1010 "grad_norm": 18.948123931884766,1011 "learning_rate": 3.321774689169385e-05,1012 "loss": 0.2339570770263672,1013 "step": 710001014 },1015 {1016 "epoch": 1.0140405616224648,1017 "grad_norm": 29.96381187438965,1018 "learning_rate": 3.309956034605021e-05,1019 "loss": 0.24531968688964845,1020 "step": 715001021 },1022 {1023 "epoch": 1.0211317543610836,1024 "grad_norm": 9.150673866271973,1025 "learning_rate": 3.2981373800406564e-05,1026 "loss": 0.23301620483398439,1027 "step": 720001028 },1029 {1030 "epoch": 1.0282229470997022,1031 "grad_norm": 3.4844117164611816,1032 "learning_rate": 3.286318725476292e-05,1033 "loss": 0.24279484558105469,1034 "step": 725001035 },1036 {1037 "epoch": 1.0353141398383208,1038 "grad_norm": 16.226896286010742,1039 "learning_rate": 3.274500070911928e-05,1040 "loss": 0.26405026245117186,1041 "step": 730001042 },1043 {1044 "epoch": 1.0424053325769393,1045 "grad_norm": 16.192201614379883,1046 "learning_rate": 3.262681416347563e-05,1047 "loss": 0.26442111206054686,1048 "step": 735001049 },1050 {1051 "epoch": 1.0494965253155581,1052 "grad_norm": 4.49188756942749,1053 "learning_rate": 3.250862761783199e-05,1054 "loss": 0.24738125610351563,1055 "step": 740001056 },1057 {1058 "epoch": 1.0565877180541767,1059 "grad_norm": 7.046379566192627,1060 "learning_rate": 3.239044107218834e-05,1061 "loss": 0.24555711364746094,1062 "step": 745001063 },1064 {1065 "epoch": 1.0636789107927953,1066 "grad_norm": 6.727515697479248,1067 "learning_rate": 3.2272254526544696e-05,1068 "loss": 0.24705020141601564,1069 "step": 750001070 },1071 {1072 "epoch": 1.0707701035314139,1073 "grad_norm": 0.3115968406200409,1074 "learning_rate": 3.215406798090105e-05,1075 "loss": 0.2594069213867187,1076 "step": 755001077 },1078 {1079 "epoch": 1.0778612962700327,1080 "grad_norm": 0.05208302289247513,1081 "learning_rate": 3.203588143525741e-05,1082 "loss": 0.25708364868164063,1083 "step": 760001084 },1085 {1086 "epoch": 1.0849524890086513,1087 "grad_norm": 37.00107955932617,1088 "learning_rate": 3.191769488961377e-05,1089 "loss": 0.2607995300292969,1090 "step": 765001091 },1092 {1093 "epoch": 1.0920436817472698,1094 "grad_norm": 0.03668564558029175,1095 "learning_rate": 3.179950834397013e-05,1096 "loss": 0.24529719543457032,1097 "step": 770001098 },1099 {1100 "epoch": 1.0991348744858884,1101 "grad_norm": 12.771923065185547,1102 "learning_rate": 3.168132179832648e-05,1103 "loss": 0.26328732299804686,1104 "step": 775001105 },1106 {1107 "epoch": 1.1062260672245072,1108 "grad_norm": 14.881919860839844,1109 "learning_rate": 3.1563135252682835e-05,1110 "loss": 0.23408724975585937,1111 "step": 780001112 },1113 {1114 "epoch": 1.1133172599631258,1115 "grad_norm": 0.04091072082519531,1116 "learning_rate": 3.144494870703919e-05,1117 "loss": 0.2638915710449219,1118 "step": 785001119 },1120 {1121 "epoch": 1.1204084527017444,1122 "grad_norm": 0.10562195628881454,1123 "learning_rate": 3.132676216139555e-05,1124 "loss": 0.2641329040527344,1125 "step": 790001126 },1127 {1128 "epoch": 1.1274996454403632,1129 "grad_norm": 21.768539428710938,1130 "learning_rate": 3.1208575615751905e-05,1131 "loss": 0.2338363494873047,1132 "step": 795001133 },1134 {1135 "epoch": 1.1345908381789818,1136 "grad_norm": 17.84772300720215,1137 "learning_rate": 3.109038907010826e-05,1138 "loss": 0.27257015991210937,1139 "step": 800001140 },1141 {1142 "epoch": 1.1416820309176003,1143 "grad_norm": 30.124338150024414,1144 "learning_rate": 3.0972202524464614e-05,1145 "loss": 0.24515379333496093,1146 "step": 805001147 },1148 {1149 "epoch": 1.148773223656219,1150 "grad_norm": 11.695418357849121,1151 "learning_rate": 3.0854015978820975e-05,1152 "loss": 0.2721016845703125,1153 "step": 810001154 },1155 {1156 "epoch": 1.1558644163948375,1157 "grad_norm": 26.140457153320312,1158 "learning_rate": 3.073582943317733e-05,1159 "loss": 0.24677125549316406,1160 "step": 815001161 },1162 {1163 "epoch": 1.1629556091334563,1164 "grad_norm": 29.512819290161133,1165 "learning_rate": 3.061764288753369e-05,1166 "loss": 0.23260931396484374,1167 "step": 820001168 },1169 {1170 "epoch": 1.1700468018720749,1171 "grad_norm": 18.654695510864258,1172 "learning_rate": 3.049945634189004e-05,1173 "loss": 0.2659488525390625,1174 "step": 825001175 },1176 {1177 "epoch": 1.1771379946106935,1178 "grad_norm": 0.5423130393028259,1179 "learning_rate": 3.03812697962464e-05,1180 "loss": 0.28602008056640627,1181 "step": 830001182 },1183 {1184 "epoch": 1.1842291873493123,1185 "grad_norm": 2.1269562244415283,1186 "learning_rate": 3.0263083250602753e-05,1187 "loss": 0.25295765686035154,1188 "step": 835001189 },1190 {1191 "epoch": 1.1913203800879308,1192 "grad_norm": 0.2145138829946518,1193 "learning_rate": 3.0144896704959107e-05,1194 "loss": 0.270892822265625,1195 "step": 840001196 },1197 {1198 "epoch": 1.1984115728265494,1199 "grad_norm": 14.912803649902344,1200 "learning_rate": 3.0026710159315465e-05,