Tonic/adaption_emir_reporting_code_gen
012
1{2 "best_global_step": null,3 "best_metric": null,4 "best_model_checkpoint": null,5 "epoch": 4.0,6 "eval_steps": 125,7 "global_step": 628,8 "is_hyper_param_search": false,9 "is_local_process_zero": true,10 "is_world_process_zero": true,11 "log_history": [12 {13 "epoch": 0.006369426751592357,14 "grad_norm": 14.634740829467773,15 "learning_rate": 0.0,16 "loss": 1.8326416015625,17 "step": 118 },19 {20 "epoch": 0.012738853503184714,21 "grad_norm": 13.922843933105469,22 "learning_rate": 9.375e-06,23 "loss": 1.771697998046875,24 "step": 225 },26 {27 "epoch": 0.01910828025477707,28 "grad_norm": 14.774005889892578,29 "learning_rate": 1.875e-05,30 "loss": 1.85638427734375,31 "step": 332 },33 {34 "epoch": 0.025477707006369428,35 "grad_norm": 10.349848747253418,36 "learning_rate": 2.8125e-05,37 "loss": 1.5071837902069092,38 "step": 439 },40 {41 "epoch": 0.03184713375796178,42 "grad_norm": 6.5954909324646,43 "learning_rate": 3.75e-05,44 "loss": 1.4010009765625,45 "step": 546 },47 {48 "epoch": 0.03821656050955414,49 "grad_norm": 3.024427890777588,50 "learning_rate": 4.6874999999999994e-05,51 "loss": 1.2522125244140625,52 "step": 653 },54 {55 "epoch": 0.044585987261146494,56 "grad_norm": 1.8201521635055542,57 "learning_rate": 5.625e-05,58 "loss": 1.2423095703125,59 "step": 760 },61 {62 "epoch": 0.050955414012738856,63 "grad_norm": 1.9971822500228882,64 "learning_rate": 6.5625e-05,65 "loss": 1.1450324058532715,66 "step": 867 },68 {69 "epoch": 0.05732484076433121,70 "grad_norm": 2.0520060062408447,71 "learning_rate": 7.5e-05,72 "loss": 0.9954171180725098,73 "step": 974 },75 {76 "epoch": 0.06369426751592357,77 "grad_norm": 1.7549692392349243,78 "learning_rate": 8.437499999999999e-05,79 "loss": 1.1235504150390625,80 "step": 1081 },82 {83 "epoch": 0.07006369426751592,84 "grad_norm": 1.2025140523910522,85 "learning_rate": 9.374999999999999e-05,86 "loss": 1.0770721435546875,87 "step": 1188 },89 {90 "epoch": 0.07643312101910828,91 "grad_norm": 0.7220160961151123,92 "learning_rate": 0.00010312499999999999,93 "loss": 1.0740203857421875,94 "step": 1295 },96 {97 "epoch": 0.08280254777070063,98 "grad_norm": 0.5354941487312317,99 "learning_rate": 0.0001125,100 "loss": 1.0075836181640625,101 "step": 13102 },103 {104 "epoch": 0.08917197452229299,105 "grad_norm": 0.7336816787719727,106 "learning_rate": 0.000121875,107 "loss": 1.04559326171875,108 "step": 14109 },110 {111 "epoch": 0.09554140127388536,112 "grad_norm": 0.6976461410522461,113 "learning_rate": 0.00013125,114 "loss": 0.9922637939453125,115 "step": 15116 },117 {118 "epoch": 0.10191082802547771,119 "grad_norm": 0.4800432622432709,120 "learning_rate": 0.000140625,121 "loss": 0.9724864959716797,122 "step": 16123 },124 {125 "epoch": 0.10828025477707007,126 "grad_norm": 0.337033748626709,127 "learning_rate": 0.00015,128 "loss": 0.9916305541992188,129 "step": 17130 },131 {132 "epoch": 0.11464968152866242,133 "grad_norm": 0.35018786787986755,134 "learning_rate": 0.00015937499999999998,135 "loss": 1.01153564453125,136 "step": 18137 },138 {139 "epoch": 0.12101910828025478,140 "grad_norm": 0.3646854758262634,141 "learning_rate": 0.00016874999999999998,142 "loss": 0.9244003295898438,143 "step": 19144 },145 {146 "epoch": 0.12738853503184713,147 "grad_norm": 0.29458990693092346,148 "learning_rate": 0.00017812499999999998,149 "loss": 0.94232177734375,150 "step": 20151 },152 {153 "epoch": 0.1337579617834395,154 "grad_norm": 0.26776453852653503,155 "learning_rate": 0.00018749999999999998,156 "loss": 0.948822021484375,157 "step": 21158 },159 {160 "epoch": 0.14012738853503184,161 "grad_norm": 0.27545294165611267,162 "learning_rate": 0.00019687499999999997,163 "loss": 0.9884185791015625,164 "step": 22165 },166 {167 "epoch": 0.1464968152866242,168 "grad_norm": 0.27437588572502136,169 "learning_rate": 0.00020624999999999997,170 "loss": 0.9786376953125,171 "step": 23172 },173 {174 "epoch": 0.15286624203821655,175 "grad_norm": 0.25814566016197205,176 "learning_rate": 0.00021562499999999997,177 "loss": 0.9479827880859375,178 "step": 24179 },180 {181 "epoch": 0.1592356687898089,182 "grad_norm": 0.20565250515937805,183 "learning_rate": 0.000225,184 "loss": 0.9623298645019531,185 "step": 25186 },187 {188 "epoch": 0.16560509554140126,189 "grad_norm": 0.23908597230911255,190 "learning_rate": 0.000234375,191 "loss": 0.8784637451171875,192 "step": 26193 },194 {195 "epoch": 0.17197452229299362,196 "grad_norm": 0.22095371782779694,197 "learning_rate": 0.00024375,198 "loss": 0.8614120483398438,199 "step": 27200 },201 {202 "epoch": 0.17834394904458598,203 "grad_norm": 0.17901843786239624,204 "learning_rate": 0.000253125,205 "loss": 0.8215179443359375,206 "step": 28207 },208 {209 "epoch": 0.18471337579617833,210 "grad_norm": 0.238013356924057,211 "learning_rate": 0.0002625,212 "loss": 0.925048828125,213 "step": 29214 },215 {216 "epoch": 0.1910828025477707,217 "grad_norm": 0.1779915690422058,218 "learning_rate": 0.000271875,219 "loss": 0.865264892578125,220 "step": 30221 },222 {223 "epoch": 0.19745222929936307,224 "grad_norm": 0.20595991611480713,225 "learning_rate": 0.00028125,226 "loss": 0.8397705554962158,227 "step": 31228 },229 {230 "epoch": 0.20382165605095542,231 "grad_norm": 0.19492584466934204,232 "learning_rate": 0.000290625,233 "loss": 0.8128700256347656,234 "step": 32235 },236 {237 "epoch": 0.21019108280254778,238 "grad_norm": 0.17935727536678314,239 "learning_rate": 0.0003,240 "loss": 0.8271636962890625,241 "step": 33242 },243 {244 "epoch": 0.21656050955414013,245 "grad_norm": 0.23040995001792908,246 "learning_rate": 0.0002999981245305545,247 "loss": 0.8703155517578125,248 "step": 34249 },250 {251 "epoch": 0.2229299363057325,252 "grad_norm": 0.2647894620895386,253 "learning_rate": 0.00029999249817432727,254 "loss": 0.8524932861328125,255 "step": 35256 },257 {258 "epoch": 0.22929936305732485,259 "grad_norm": 0.15038178861141205,260 "learning_rate": 0.00029998312108764537,261 "loss": 0.7906417846679688,262 "step": 36263 },264 {265 "epoch": 0.2356687898089172,266 "grad_norm": 0.21919266879558563,267 "learning_rate": 0.0002999699935310484,268 "loss": 0.8485870361328125,269 "step": 37270 },271 {272 "epoch": 0.24203821656050956,273 "grad_norm": 0.15890416502952576,274 "learning_rate": 0.00029995311586928215,275 "loss": 0.8249359130859375,276 "step": 38277 },278 {279 "epoch": 0.2484076433121019,280 "grad_norm": 0.15894381701946259,281 "learning_rate": 0.0002999324885712879,282 "loss": 0.75238037109375,283 "step": 39284 },285 {286 "epoch": 0.25477707006369427,287 "grad_norm": 0.193678617477417,288 "learning_rate": 0.0002999081122101896,289 "loss": 0.847900390625,290 "step": 40291 },292 {293 "epoch": 0.2611464968152866,294 "grad_norm": 0.14389629662036896,295 "learning_rate": 0.0002998799874632779,296 "loss": 0.7450682520866394,297 "step": 41298 },299 {300 "epoch": 0.267515923566879,301 "grad_norm": 0.21948423981666565,302 "learning_rate": 0.00029984811511199136,303 "loss": 0.803375244140625,304 "step": 42305 },306 {307 "epoch": 0.27388535031847133,308 "grad_norm": 0.16477927565574646,309 "learning_rate": 0.00029981249604189484,310 "loss": 0.7503585815429688,311 "step": 43312 },313 {314 "epoch": 0.2802547770700637,315 "grad_norm": 0.21690034866333008,316 "learning_rate": 0.0002997731312426546,317 "loss": 0.79840087890625,318 "step": 44319 },320 {321 "epoch": 0.28662420382165604,322 "grad_norm": 0.1361113041639328,323 "learning_rate": 0.000299730021808011,324 "loss": 0.76605224609375,325 "step": 45326 },327 {328 "epoch": 0.2929936305732484,329 "grad_norm": 0.15949746966362,330 "learning_rate": 0.0002996831689357482,331 "loss": 0.7372894287109375,332 "step": 46333 },334 {335 "epoch": 0.29936305732484075,336 "grad_norm": 0.13118144869804382,337 "learning_rate": 0.0002996325739276609,338 "loss": 0.766143798828125,339 "step": 47340 },341 {342 "epoch": 0.3057324840764331,343 "grad_norm": 0.14016607403755188,344 "learning_rate": 0.0002995782381895176,345 "loss": 0.7620620727539062,346 "step": 48347 },348 {349 "epoch": 0.31210191082802546,350 "grad_norm": 0.1928688883781433,351 "learning_rate": 0.00029952016323102235,352 "loss": 0.8002471923828125,353 "step": 49354 },355 {356 "epoch": 0.3184713375796178,357 "grad_norm": 0.19723062217235565,358 "learning_rate": 0.0002994583506657723,359 "loss": 0.763778805732727,360 "step": 50361 },362 {363 "epoch": 0.3248407643312102,364 "grad_norm": 0.2530524432659149,365 "learning_rate": 0.00029939280221121314,366 "loss": 0.7891502380371094,367 "step": 51368 },369 {370 "epoch": 0.33121019108280253,371 "grad_norm": 0.20972968637943268,372 "learning_rate": 0.0002993235196885911,373 "loss": 0.7976531982421875,374 "step": 52375 },376 {377 "epoch": 0.3375796178343949,378 "grad_norm": 0.1319575309753418,379 "learning_rate": 0.0002992505050229025,380 "loss": 0.75244140625,381 "step": 53382 },383 {384 "epoch": 0.34394904458598724,385 "grad_norm": 0.21391642093658447,386 "learning_rate": 0.0002991737602428403,387 "loss": 0.6784820556640625,388 "step": 54389 },390 {391 "epoch": 0.3503184713375796,392 "grad_norm": 0.24353541433811188,393 "learning_rate": 0.0002990932874807378,394 "loss": 0.762359619140625,395 "step": 55396 },397 {398 "epoch": 0.35668789808917195,399 "grad_norm": 0.17982617020606995,400 "learning_rate": 0.0002990090889725091,401 "loss": 0.690155029296875,402 "step": 56403 },404 {405 "epoch": 0.3630573248407643,406 "grad_norm": 0.1485365778207779,407 "learning_rate": 0.0002989211670575871,408 "loss": 0.7690277099609375,409 "step": 57410 },411 {412 "epoch": 0.36942675159235666,413 "grad_norm": 0.23111550509929657,414 "learning_rate": 0.0002988295241788589,415 "loss": 0.711944580078125,416 "step": 58417 },418 {419 "epoch": 0.37579617834394907,420 "grad_norm": 0.14703889191150665,421 "learning_rate": 0.00029873416288259726,422 "loss": 0.7354278564453125,423 "step": 59424 },425 {426 "epoch": 0.3821656050955414,427 "grad_norm": 0.21715037524700165,428 "learning_rate": 0.00029863508581839027,429 "loss": 0.7352346181869507,430 "step": 60431 },432 {433 "epoch": 0.3885350318471338,434 "grad_norm": 0.2302205115556717,435 "learning_rate": 0.00029853229573906774,436 "loss": 0.7104644775390625,437 "step": 61438 },439 {440 "epoch": 0.39490445859872614,441 "grad_norm": 0.14830107986927032,442 "learning_rate": 0.00029842579550062447,443 "loss": 0.7044873237609863,444 "step": 62445 },446 {447 "epoch": 0.4012738853503185,448 "grad_norm": 0.21264120936393738,449 "learning_rate": 0.00029831558806214114,450 "loss": 0.7453155517578125,451 "step": 63452 },453 {454 "epoch": 0.40764331210191085,455 "grad_norm": 0.17891322076320648,456 "learning_rate": 0.000298201676485702,457 "loss": 0.7078933715820312,458 "step": 64459 },460 {461 "epoch": 0.4140127388535032,462 "grad_norm": 0.1606503278017044,463 "learning_rate": 0.0002980840639363095,464 "loss": 0.7210578918457031,465 "step": 65466 },467 {468 "epoch": 0.42038216560509556,469 "grad_norm": 0.16794052720069885,470 "learning_rate": 0.0002979627536817971,471 "loss": 0.6704587936401367,472 "step": 66473 },474 {475 "epoch": 0.4267515923566879,476 "grad_norm": 0.14437231421470642,477 "learning_rate": 0.0002978377490927377,478 "loss": 0.7686614990234375,479 "step": 67480 },481 {482 "epoch": 0.43312101910828027,483 "grad_norm": 0.15216439962387085,484 "learning_rate": 0.00029770905364235044,485 "loss": 0.7377853393554688,486 "step": 68487 },488 {489 "epoch": 0.4394904458598726,490 "grad_norm": 0.15043821930885315,491 "learning_rate": 0.00029757667090640386,492 "loss": 0.7062454223632812,493 "step": 69494 },495 {496 "epoch": 0.445859872611465,497 "grad_norm": 0.15341544151306152,498 "learning_rate": 0.0002974406045631169,499 "loss": 0.7042083740234375,500 "step": 70501 },502 {503 "epoch": 0.45222929936305734,504 "grad_norm": 0.14280380308628082,505 "learning_rate": 0.00029730085839305663,506 "loss": 0.6313236951828003,507 "step": 71508 },509 {510 "epoch": 0.4585987261146497,511 "grad_norm": 0.14860248565673828,512 "learning_rate": 0.00029715743627903285,513 "loss": 0.7414970397949219,514 "step": 72515 },516 {517 "epoch": 0.46496815286624205,518 "grad_norm": 0.15411949157714844,519 "learning_rate": 0.0002970103422059907,520 "loss": 0.7120361328125,521 "step": 73522 },523 {524 "epoch": 0.4713375796178344,525 "grad_norm": 0.1319582611322403,526 "learning_rate": 0.0002968595802608997,527 "loss": 0.71319580078125,528 "step": 74529 },530 {531 "epoch": 0.47770700636942676,532 "grad_norm": 0.14194566011428833,533 "learning_rate": 0.0002967051546326401,534 "loss": 0.7166900634765625,535 "step": 75536 },537 {538 "epoch": 0.4840764331210191,539 "grad_norm": 0.15048225224018097,540 "learning_rate": 0.00029654706961188676,541 "loss": 0.71392822265625,542 "step": 76543 },544 {545 "epoch": 0.49044585987261147,546 "grad_norm": 0.1446928232908249,547 "learning_rate": 0.0002963853295909896,548 "loss": 0.708343505859375,549 "step": 77550 },551 {552 "epoch": 0.4968152866242038,553 "grad_norm": 0.1399853229522705,554 "learning_rate": 0.0002962199390638519,555 "loss": 0.690521240234375,556 "step": 78557 },558 {559 "epoch": 0.5031847133757962,560 "grad_norm": 0.15705810487270355,561 "learning_rate": 0.0002960509026258052,562 "loss": 0.7089481353759766,563 "step": 79564 },565 {566 "epoch": 0.5095541401273885,567 "grad_norm": 0.1441253274679184,568 "learning_rate": 0.00029587822497348175,569 "loss": 0.736480712890625,570 "step": 80571 },572 {573 "epoch": 0.5159235668789809,574 "grad_norm": 0.13917307555675507,575 "learning_rate": 0.0002957019109046839,576 "loss": 0.69671630859375,577 "step": 81578 },579 {580 "epoch": 0.5222929936305732,581 "grad_norm": 0.15637345612049103,582 "learning_rate": 0.0002955219653182509,583 "loss": 0.7079315185546875,584 "step": 82585 },586 {587 "epoch": 0.5286624203821656,588 "grad_norm": 0.17719104886054993,589 "learning_rate": 0.0002953383932139227,590 "loss": 0.727935791015625,591 "step": 83592 },593 {594 "epoch": 0.535031847133758,595 "grad_norm": 0.16060574352741241,596 "learning_rate": 0.0002951511996922012,597 "loss": 0.64898681640625,598 "step": 84599 },600 {601 "epoch": 0.5414012738853503,602 "grad_norm": 0.14753378927707672,603 "learning_rate": 0.0002949603899542083,604 "loss": 0.6824111938476562,605 "step": 85606 },607 {608 "epoch": 0.5477707006369427,609 "grad_norm": 0.14623405039310455,610 "learning_rate": 0.00029476596930154143,611 "loss": 0.6638870239257812,612 "step": 86613 },614 {615 "epoch": 0.554140127388535,616 "grad_norm": 0.2025822550058365,617 "learning_rate": 0.00029456794313612657,618 "loss": 0.7407073974609375,619 "step": 87620 },621 {622 "epoch": 0.5605095541401274,623 "grad_norm": 0.20111721754074097,624 "learning_rate": 0.0002943663169600677,625 "loss": 0.634765625,626 "step": 88627 },628 {629 "epoch": 0.5668789808917197,630 "grad_norm": 0.16288472712039948,631 "learning_rate": 0.0002941610963754942,632 "loss": 0.7083282470703125,633 "step": 89634 },635 {636 "epoch": 0.5732484076433121,637 "grad_norm": 0.1873498409986496,638 "learning_rate": 0.0002939522870844051,639 "loss": 0.6896438598632812,640 "step": 90641 },642 {643 "epoch": 0.5796178343949044,644 "grad_norm": 0.16933931410312653,645 "learning_rate": 0.00029373989488851073,646 "loss": 0.7074050903320312,647 "step": 91648 },649 {650 "epoch": 0.5859872611464968,651 "grad_norm": 0.1743369698524475,652 "learning_rate": 0.0002935239256890714,653 "loss": 0.7069091796875,654 "step": 92655 },656 {657 "epoch": 0.5923566878980892,658 "grad_norm": 0.1373268961906433,659 "learning_rate": 0.00029330438548673366,660 "loss": 0.6788864135742188,661 "step": 93662 },663 {664 "epoch": 0.5987261146496815,665 "grad_norm": 0.1815701127052307,666 "learning_rate": 0.0002930812803813632,667 "loss": 0.66387939453125,668 "step": 94669 },670 {671 "epoch": 0.6050955414012739,672 "grad_norm": 0.17448744177818298,673 "learning_rate": 0.00029285461657187564,674 "loss": 0.7216981649398804,675 "step": 95676 },677 {678 "epoch": 0.6114649681528662,679 "grad_norm": 0.11934467405080795,680 "learning_rate": 0.00029262440035606444,681 "loss": 0.6801834106445312,682 "step": 96683 },684 {685 "epoch": 0.6178343949044586,686 "grad_norm": 0.16852253675460815,687 "learning_rate": 0.0002923906381304256,688 "loss": 0.6863555908203125,689 "step": 97690 },691 {692 "epoch": 0.6242038216560509,693 "grad_norm": 0.16186685860157013,694 "learning_rate": 0.00029215333638997986,695 "loss": 0.6582489013671875,696 "step": 98697 },698 {699 "epoch": 0.6305732484076433,700 "grad_norm": 0.18058981001377106,701 "learning_rate": 0.00029191250172809274,702 "loss": 0.6726799011230469,703 "step": 99704 },705 {706 "epoch": 0.6369426751592356,707 "grad_norm": 0.21598166227340698,708 "learning_rate": 0.0002916681408362909,709 "loss": 0.6689566969871521,710 "step": 100711 },712 {713 "epoch": 0.643312101910828,714 "grad_norm": 0.1937216967344284,715 "learning_rate": 0.00029142026050407634,716 "loss": 0.6519851684570312,717 "step": 101718 },719 {720 "epoch": 0.6496815286624203,721 "grad_norm": 0.1824830025434494,722 "learning_rate": 0.0002911688676187377,723 "loss": 0.6694857478141785,724 "step": 102725 },726 {727 "epoch": 0.6560509554140127,728 "grad_norm": 0.1829107701778412,729 "learning_rate": 0.00029091396916515927,730 "loss": 0.7089385986328125,731 "step": 103732 },733 {734 "epoch": 0.6624203821656051,735 "grad_norm": 0.1789492815732956,736 "learning_rate": 0.00029065557222562616,737 "loss": 0.6807861328125,738 "step": 104739 },740 {741 "epoch": 0.6687898089171974,742 "grad_norm": 0.17036959528923035,743 "learning_rate": 0.00029039368397962837,744 "loss": 0.6617279052734375,745 "step": 105746 },747 {748 "epoch": 0.6751592356687898,749 "grad_norm": 0.1865333616733551,750 "learning_rate": 0.0002901283117036607,751 "loss": 0.6889495849609375,752 "step": 106753 },754 {755 "epoch": 0.6815286624203821,756 "grad_norm": 0.202290877699852,757 "learning_rate": 0.00028985946277102094,758 "loss": 0.7136383056640625,759 "step": 107760 },761 {762 "epoch": 0.6878980891719745,763 "grad_norm": 0.1646660417318344,764 "learning_rate": 0.0002895871446516047,765 "loss": 0.6327409744262695,766 "step": 108767 },768 {769 "epoch": 0.6942675159235668,770 "grad_norm": 0.15508386492729187,771 "learning_rate": 0.0002893113649116981,772 "loss": 0.6970291137695312,773 "step": 109774 },775 {776 "epoch": 0.7006369426751592,777 "grad_norm": 0.23790733516216278,778 "learning_rate": 0.00028903213121376744,779 "loss": 0.701690673828125,780 "step": 110781 },782 {783 "epoch": 0.7070063694267515,784 "grad_norm": 0.23440833389759064,785 "learning_rate": 0.0002887494513162464,786 "loss": 0.6858749389648438,787 "step": 111788 },789 {790 "epoch": 0.7133757961783439,791 "grad_norm": 0.16020652651786804,792 "learning_rate": 0.0002884633330733202,793 "loss": 0.679046630859375,794 "step": 112795 },796 {797 "epoch": 0.7197452229299363,798 "grad_norm": 0.16401633620262146,799 "learning_rate": 0.00028817378443470786,800 "loss": 0.6446990966796875,801 "step": 113802 },803 {804 "epoch": 0.7261146496815286,805 "grad_norm": 0.1972404420375824,806 "learning_rate": 0.0002878808134454407,807 "loss": 0.6556560397148132,808 "step": 114809 },810 {811 "epoch": 0.732484076433121,812 "grad_norm": 0.1584540456533432,813 "learning_rate": 0.0002875844282456394,814 "loss": 0.6459579467773438,815 "step": 115816 },817 {818 "epoch": 0.7388535031847133,819 "grad_norm": 0.1724664270877838,820 "learning_rate": 0.0002872846370702874,821 "loss": 0.666351318359375,822 "step": 116823 },824 {825 "epoch": 0.7452229299363057,826 "grad_norm": 0.15662480890750885,827 "learning_rate": 0.0002869814482490023,828 "loss": 0.6523818969726562,829 "step": 117830 },831 {832 "epoch": 0.7515923566878981,833 "grad_norm": 0.16173236072063446,834 "learning_rate": 0.00028667487020580444,835 "loss": 0.6941604614257812,836 "step": 118837 },838 {839 "epoch": 0.7579617834394905,840 "grad_norm": 0.15774263441562653,841 "learning_rate": 0.00028636491145888276,842 "loss": 0.65179443359375,843 "step": 119844 },845 {846 "epoch": 0.7643312101910829,847 "grad_norm": 0.15777266025543213,848 "learning_rate": 0.00028605158062035816,849 "loss": 0.5868377685546875,850 "step": 120851 },852 {853 "epoch": 0.7707006369426752,854 "grad_norm": 0.14408300817012787,855 "learning_rate": 0.00028573488639604413,856 "loss": 0.6986846923828125,857 "step": 121858 },859 {860 "epoch": 0.7770700636942676,861 "grad_norm": 0.16124875843524933,862 "learning_rate": 0.000285414837585205,863 "loss": 0.6715621948242188,864 "step": 122865 },866 {867 "epoch": 0.7834394904458599,868 "grad_norm": 0.15004760026931763,869 "learning_rate": 0.0002850914430803114,870 "loss": 0.6120376586914062,871 "step": 123872 },873 {874 "epoch": 0.7898089171974523,875 "grad_norm": 0.17481908202171326,876 "learning_rate": 0.0002847647118667931,877 "loss": 0.680206298828125,878 "step": 124879 },880 {881 "epoch": 0.7961783439490446,882 "grad_norm": 0.1774885207414627,883 "learning_rate": 0.0002844346530227895,884 "loss": 0.66265869140625,885 "step": 125886 },887 {888 "epoch": 0.802547770700637,889 "grad_norm": 0.18009056150913239,890 "learning_rate": 0.0002841012757188973,891 "loss": 0.6852645874023438,892 "step": 126893 },894 {895 "epoch": 0.8089171974522293,896 "grad_norm": 0.19692178070545197,897 "learning_rate": 0.00028376458921791577,898 "loss": 0.616912841796875,899 "step": 127900 },901 {902 "epoch": 0.8152866242038217,903 "grad_norm": 0.21690639853477478,904 "learning_rate": 0.0002834246028745892,905 "loss": 0.6993408203125,906 "step": 128907 },908 {909 "epoch": 0.8152866242038217,910 "eval_loss": 0.625178337097168,911 "eval_runtime": 5.1564,912 "eval_samples_per_second": 1.358,913 "eval_steps_per_second": 0.194,914 "step": 128915 },916 {917 "epoch": 0.821656050955414,918 "grad_norm": 0.19200018048286438,919 "learning_rate": 0.00028308132613534716,920 "loss": 0.6799163818359375,921 "step": 129922 },923 {924 "epoch": 0.8280254777070064,925 "grad_norm": 0.18255098164081573,926 "learning_rate": 0.0002827347685380422,927 "loss": 0.62457275390625,928 "step": 130929 },930 {931 "epoch": 0.8343949044585988,932 "grad_norm": 0.15668107569217682,933 "learning_rate": 0.00028238493971168433,934 "loss": 0.6515045166015625,935 "step": 131936 },937 {938 "epoch": 0.8407643312101911,939 "grad_norm": 0.16620191931724548,940 "learning_rate": 0.00028203184937617397,941 "loss": 0.6193771362304688,942 "step": 132943 },944 {945 "epoch": 0.8471337579617835,946 "grad_norm": 0.18261539936065674,947 "learning_rate": 0.0002816755073420317,948 "loss": 0.716033935546875,949 "step": 133950 },951 {952 "epoch": 0.8535031847133758,953 "grad_norm": 0.1520560085773468,954 "learning_rate": 0.00028131592351012555,955 "loss": 0.6133193969726562,956 "step": 134957 },958 {959 "epoch": 0.8598726114649682,960 "grad_norm": 0.16571491956710815,961 "learning_rate": 0.00028095310787139613,962 "loss": 0.6478843688964844,963 "step": 135964 },965 {966 "epoch": 0.8662420382165605,967 "grad_norm": 0.17786805331707,968 "learning_rate": 0.0002805870705065789,969 "loss": 0.6279449462890625,970 "step": 136971 },972 {973 "epoch": 0.8726114649681529,974 "grad_norm": 0.13904328644275665,975 "learning_rate": 0.0002802178215859241,976 "loss": 0.671142578125,977 "step": 137978 },979 {980 "epoch": 0.8789808917197452,981 "grad_norm": 0.14942413568496704,982 "learning_rate": 0.0002798453713689144,983 "loss": 0.5923829674720764,984 "step": 138985 },986 {987 "epoch": 0.8853503184713376,988 "grad_norm": 0.16308893263339996,989 "learning_rate": 0.00027946973020397933,990 "loss": 0.6803417205810547,991 "step": 139992 },993 {994 "epoch": 0.89171974522293,995 "grad_norm": 0.1690857857465744,996 "learning_rate": 0.00027909090852820814,997 "loss": 0.6681976318359375,998 "step": 140999 },1000 {1001 "epoch": 0.8980891719745223,1002 "grad_norm": 0.15127228200435638,1003 "learning_rate": 0.0002787089168670598,1004 "loss": 0.65283203125,1005 "step": 1411006 },1007 {1008 "epoch": 0.9044585987261147,1009 "grad_norm": 0.15152615308761597,1010 "learning_rate": 0.0002783237658340705,1011 "loss": 0.6745452880859375,1012 "step": 1421013 },1014 {1015 "epoch": 0.910828025477707,1016 "grad_norm": 0.18258291482925415,1017 "learning_rate": 0.0002779354661305586,1018 "loss": 0.631072998046875,1019 "step": 1431020 },1021 {1022 "epoch": 0.9171974522292994,1023 "grad_norm": 0.18597263097763062,1024 "learning_rate": 0.0002775440285453276,1025 "loss": 0.705718994140625,1026 "step": 1441027 },1028 {1029 "epoch": 0.9235668789808917,1030 "grad_norm": 0.17591795325279236,1031 "learning_rate": 0.000277149463954366,1032 "loss": 0.6915283203125,1033 "step": 1451034 },1035 {1036 "epoch": 0.9299363057324841,1037 "grad_norm": 0.17014524340629578,1038 "learning_rate": 0.0002767517833205455,1039 "loss": 0.6183319091796875,1040 "step": 1461041 },1042 {1043 "epoch": 0.9363057324840764,1044 "grad_norm": 0.18762874603271484,1045 "learning_rate": 0.00027635099769331617,1046 "loss": 0.6309661865234375,1047 "step": 1471048 },1049 {1050 "epoch": 0.9426751592356688,1051 "grad_norm": 0.19945642352104187,1052 "learning_rate": 0.0002759471182083993,1053 "loss": 0.6492996215820312,1054 "step": 1481055 },1056 {1057 "epoch": 0.9490445859872612,1058 "grad_norm": 0.15386110544204712,1059 "learning_rate": 0.00027554015608747845,1060 "loss": 0.6570892333984375,1061 "step": 1491062 },1063 {1064 "epoch": 0.9554140127388535,1065 "grad_norm": 0.1597049981355667,1066 "learning_rate": 0.00027513012263788737,1067 "loss": 0.6250181198120117,1068 "step": 1501069 },1070 {1071 "epoch": 0.9617834394904459,1072 "grad_norm": 0.1697262078523636,1073 "learning_rate": 0.0002747170292522957,1074 "loss": 0.6492233276367188,1075 "step": 1511076 },1077 {1078 "epoch": 0.9681528662420382,1079 "grad_norm": 0.16555513441562653,1080 "learning_rate": 0.0002743008874083927,1081 "loss": 0.6356735229492188,1082 "step": 1521083 },1084 {1085 "epoch": 0.9745222929936306,1086 "grad_norm": 0.16877028346061707,1087 "learning_rate": 0.0002738817086685681,1088 "loss": 0.6483078002929688,1089 "step": 1531090 },1091 {1092 "epoch": 0.9808917197452229,1093 "grad_norm": 0.15073354542255402,1094 "learning_rate": 0.00027345950467959123,1095 "loss": 0.6661834716796875,1096 "step": 1541097 },1098 {1099 "epoch": 0.9872611464968153,1100 "grad_norm": 0.1822793185710907,1101 "learning_rate": 0.0002730342871722869,1102 "loss": 0.6563186645507812,1103 "step": 1551104 },1105 {1106 "epoch": 0.9936305732484076,1107 "grad_norm": 0.19067645072937012,1108 "learning_rate": 0.00027260606796120974,1109 "loss": 0.6632080078125,1110 "step": 1561111 },1112 {1113 "epoch": 1.0,1114 "grad_norm": 0.20216046273708344,1115 "learning_rate": 0.0002721748589443162,1116 "loss": 0.6433029174804688,1117 "step": 1571118 },1119 {1120 "epoch": 1.0063694267515924,1121 "grad_norm": 0.20415550470352173,1122 "learning_rate": 0.0002717406721026333,1123 "loss": 0.661224365234375,1124 "step": 1581125 },1126 {1127 "epoch": 1.0127388535031847,1128 "grad_norm": 0.20491866767406464,1129 "learning_rate": 0.0002713035194999264,1130 "loss": 0.64361572265625,1131 "step": 1591132 },1133 {1134 "epoch": 1.019108280254777,1135 "grad_norm": 0.24666599929332733,1136 "learning_rate": 0.00027086341328236356,1137 "loss": 0.692962646484375,1138 "step": 1601139 },1140 {1141 "epoch": 1.0254777070063694,1142 "grad_norm": 0.32244184613227844,1143 "learning_rate": 0.00027042036567817833,1144 "loss": 0.6512019038200378,1145 "step": 1611146 },1147 {1148 "epoch": 1.0318471337579618,1149 "grad_norm": 0.1902998685836792,1150 "learning_rate": 0.00026997438899733,1151 "loss": 0.650390625,1152 "step": 1621153 },1154 {1155 "epoch": 1.0382165605095541,1156 "grad_norm": 0.32200613617897034,1157 "learning_rate": 0.0002695254956311612,1158 "loss": 0.63275146484375,1159 "step": 1631160 },1161 {1162 "epoch": 1.0445859872611465,1163 "grad_norm": 0.2785264551639557,1164 "learning_rate": 0.00026907369805205414,1165 "loss": 0.6525421142578125,1166 "step": 1641167 },1168 {1169 "epoch": 1.0509554140127388,1170 "grad_norm": 0.22845248878002167,1171 "learning_rate": 0.0002686190088130837,1172 "loss": 0.6388189792633057,1173 "step": 1651174 },1175 {1176 "epoch": 1.0573248407643312,1177 "grad_norm": 0.15489083528518677,1178 "learning_rate": 0.0002681614405476688,1179 "loss": 0.560907781124115,1180 "step": 1661181 },1182 {1183 "epoch": 1.0636942675159236,1184 "grad_norm": 0.240184023976326,1185 "learning_rate": 0.0002677010059692212,1186 "loss": 0.6396026611328125,1187 "step": 1671188 },1189 {1190 "epoch": 1.070063694267516,1191 "grad_norm": 0.18049825727939606,1192 "learning_rate": 0.00026723771787079257,1193 "loss": 0.6528244018554688,1194 "step": 1681195 },1196 {1197 "epoch": 1.0764331210191083,1198 "grad_norm": 0.21166716516017914,1199 "learning_rate": 0.00026677158912471885,1200 "loss": 0.6523818969726562,