{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13052274358807023,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006526137179403511,
      "grad_norm": 17.690582114691438,
      "learning_rate": 1.948051948051948e-06,
      "loss": 1.3559,
      "step": 10
    },
    {
      "epoch": 0.0013052274358807021,
      "grad_norm": 7.768088366444893,
      "learning_rate": 3.896103896103896e-06,
      "loss": 1.2706,
      "step": 20
    },
    {
      "epoch": 0.001957841153821053,
      "grad_norm": 7.705313536090087,
      "learning_rate": 5.844155844155845e-06,
      "loss": 1.3781,
      "step": 30
    },
    {
      "epoch": 0.0026104548717614043,
      "grad_norm": 34.39078827766783,
      "learning_rate": 7.792207792207792e-06,
      "loss": 1.2749,
      "step": 40
    },
    {
      "epoch": 0.0032630685897017554,
      "grad_norm": 68.28824334896528,
      "learning_rate": 9.74025974025974e-06,
      "loss": 1.2955,
      "step": 50
    },
    {
      "epoch": 0.003915682307642106,
      "grad_norm": 14.220322607917241,
      "learning_rate": 1.168831168831169e-05,
      "loss": 1.2315,
      "step": 60
    },
    {
      "epoch": 0.0045682960255824575,
      "grad_norm": 12.611848231734811,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 1.0953,
      "step": 70
    },
    {
      "epoch": 0.0052209097435228086,
      "grad_norm": 6.055664298727015,
      "learning_rate": 1.5584415584415583e-05,
      "loss": 1.105,
      "step": 80
    },
    {
      "epoch": 0.00587352346146316,
      "grad_norm": 3.52269227801977,
      "learning_rate": 1.753246753246753e-05,
      "loss": 0.9563,
      "step": 90
    },
    {
      "epoch": 0.006526137179403511,
      "grad_norm": 10.771884023354394,
      "learning_rate": 1.948051948051948e-05,
      "loss": 0.9523,
      "step": 100
    },
    {
      "epoch": 0.007178750897343862,
      "grad_norm": 33.41476483216757,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.832,
      "step": 110
    },
    {
      "epoch": 0.007831364615284213,
      "grad_norm": 31.120240364617406,
      "learning_rate": 2.337662337662338e-05,
      "loss": 0.8376,
      "step": 120
    },
    {
      "epoch": 0.008483978333224564,
      "grad_norm": 5.517231564060886,
      "learning_rate": 2.5324675324675325e-05,
      "loss": 0.8293,
      "step": 130
    },
    {
      "epoch": 0.009136592051164915,
      "grad_norm": 4.311605388342058,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 0.8295,
      "step": 140
    },
    {
      "epoch": 0.009789205769105266,
      "grad_norm": 6.997724163121519,
      "learning_rate": 2.922077922077922e-05,
      "loss": 0.7662,
      "step": 150
    },
    {
      "epoch": 0.010441819487045617,
      "grad_norm": 6.517836234400708,
      "learning_rate": 2.999998841890695e-05,
      "loss": 0.8158,
      "step": 160
    },
    {
      "epoch": 0.011094433204985968,
      "grad_norm": 4.186989141019666,
      "learning_rate": 2.99999176456253e-05,
      "loss": 0.8037,
      "step": 170
    },
    {
      "epoch": 0.01174704692292632,
      "grad_norm": 5.181546943355458,
      "learning_rate": 2.9999782533305785e-05,
      "loss": 0.7274,
      "step": 180
    },
    {
      "epoch": 0.01239966064086667,
      "grad_norm": 3.767076521211455,
      "learning_rate": 2.9999583082527935e-05,
      "loss": 0.7474,
      "step": 190
    },
    {
      "epoch": 0.013052274358807021,
      "grad_norm": 18.84416377940188,
      "learning_rate": 2.999931929414726e-05,
      "loss": 0.7708,
      "step": 200
    },
    {
      "epoch": 0.013704888076747372,
      "grad_norm": 3.169160630444992,
      "learning_rate": 2.999899116929522e-05,
      "loss": 0.8279,
      "step": 210
    },
    {
      "epoch": 0.014357501794687724,
      "grad_norm": 1.912782077307437,
      "learning_rate": 2.999859870937924e-05,
      "loss": 0.7407,
      "step": 220
    },
    {
      "epoch": 0.015010115512628075,
      "grad_norm": 3.3906505952914974,
      "learning_rate": 2.9998141916082696e-05,
      "loss": 0.7732,
      "step": 230
    },
    {
      "epoch": 0.015662729230568426,
      "grad_norm": 2.7144492322383584,
      "learning_rate": 2.999762079136491e-05,
      "loss": 0.7272,
      "step": 240
    },
    {
      "epoch": 0.01631534294850878,
      "grad_norm": 7.109330196029837,
      "learning_rate": 2.9997035337461135e-05,
      "loss": 0.7748,
      "step": 250
    },
    {
      "epoch": 0.016967956666449128,
      "grad_norm": 1.6054280593801813,
      "learning_rate": 2.9996385556882555e-05,
      "loss": 0.7676,
      "step": 260
    },
    {
      "epoch": 0.01762057038438948,
      "grad_norm": 10.883212441614672,
      "learning_rate": 2.9995671452416274e-05,
      "loss": 0.735,
      "step": 270
    },
    {
      "epoch": 0.01827318410232983,
      "grad_norm": 3.511064886507805,
      "learning_rate": 2.999489302712529e-05,
      "loss": 0.7741,
      "step": 280
    },
    {
      "epoch": 0.018925797820270183,
      "grad_norm": 3.618603818375307,
      "learning_rate": 2.9994050284348497e-05,
      "loss": 0.749,
      "step": 290
    },
    {
      "epoch": 0.019578411538210532,
      "grad_norm": 6.012944880342178,
      "learning_rate": 2.9993143227700668e-05,
      "loss": 0.7411,
      "step": 300
    },
    {
      "epoch": 0.020231025256150885,
      "grad_norm": 2.348670372295822,
      "learning_rate": 2.9992171861072428e-05,
      "loss": 0.7394,
      "step": 310
    },
    {
      "epoch": 0.020883638974091234,
      "grad_norm": 4.728309497649916,
      "learning_rate": 2.9991136188630263e-05,
      "loss": 0.8077,
      "step": 320
    },
    {
      "epoch": 0.021536252692031587,
      "grad_norm": 15.611917863290122,
      "learning_rate": 2.9990036214816467e-05,
      "loss": 0.7209,
      "step": 330
    },
    {
      "epoch": 0.022188866409971936,
      "grad_norm": 3.7315277354070817,
      "learning_rate": 2.998887194434916e-05,
      "loss": 0.7101,
      "step": 340
    },
    {
      "epoch": 0.02284148012791229,
      "grad_norm": 6.618759094750745,
      "learning_rate": 2.998764338222222e-05,
      "loss": 0.7759,
      "step": 350
    },
    {
      "epoch": 0.02349409384585264,
      "grad_norm": 6.770044306239603,
      "learning_rate": 2.998635053370533e-05,
      "loss": 0.7398,
      "step": 360
    },
    {
      "epoch": 0.02414670756379299,
      "grad_norm": 12.471224202357552,
      "learning_rate": 2.998499340434389e-05,
      "loss": 0.7046,
      "step": 370
    },
    {
      "epoch": 0.02479932128173334,
      "grad_norm": 4.147359416986547,
      "learning_rate": 2.9983571999959013e-05,
      "loss": 0.761,
      "step": 380
    },
    {
      "epoch": 0.025451934999673693,
      "grad_norm": 34.84722866603778,
      "learning_rate": 2.9982086326647533e-05,
      "loss": 0.757,
      "step": 390
    },
    {
      "epoch": 0.026104548717614043,
      "grad_norm": 5.245498180313093,
      "learning_rate": 2.998053639078193e-05,
      "loss": 0.7536,
      "step": 400
    },
    {
      "epoch": 0.026757162435554396,
      "grad_norm": 36.55990241841121,
      "learning_rate": 2.997892219901034e-05,
      "loss": 0.7395,
      "step": 410
    },
    {
      "epoch": 0.027409776153494745,
      "grad_norm": 5.03198653806696,
      "learning_rate": 2.9977243758256494e-05,
      "loss": 0.7208,
      "step": 420
    },
    {
      "epoch": 0.028062389871435098,
      "grad_norm": 11.376914733036081,
      "learning_rate": 2.997550107571972e-05,
      "loss": 0.719,
      "step": 430
    },
    {
      "epoch": 0.028715003589375447,
      "grad_norm": 2.958119684662306,
      "learning_rate": 2.9973694158874898e-05,
      "loss": 0.7271,
      "step": 440
    },
    {
      "epoch": 0.0293676173073158,
      "grad_norm": 6.037096737490817,
      "learning_rate": 2.9971823015472418e-05,
      "loss": 0.7356,
      "step": 450
    },
    {
      "epoch": 0.03002023102525615,
      "grad_norm": 5.3042973640363575,
      "learning_rate": 2.9969887653538164e-05,
      "loss": 0.7207,
      "step": 460
    },
    {
      "epoch": 0.030672844743196502,
      "grad_norm": 2.4985603001745624,
      "learning_rate": 2.996788808137347e-05,
      "loss": 0.7769,
      "step": 470
    },
    {
      "epoch": 0.03132545846113685,
      "grad_norm": 7.607065841315647,
      "learning_rate": 2.9965824307555084e-05,
      "loss": 0.7091,
      "step": 480
    },
    {
      "epoch": 0.03197807217907721,
      "grad_norm": 4.322533035107957,
      "learning_rate": 2.9963696340935144e-05,
      "loss": 0.7114,
      "step": 490
    },
    {
      "epoch": 0.03263068589701756,
      "grad_norm": 5.878565903250334,
      "learning_rate": 2.9961504190641108e-05,
      "loss": 0.7284,
      "step": 500
    },
    {
      "epoch": 0.033283299614957906,
      "grad_norm": 5.0026507027119855,
      "learning_rate": 2.9959247866075764e-05,
      "loss": 0.6992,
      "step": 510
    },
    {
      "epoch": 0.033935913332898256,
      "grad_norm": 7.12632150273901,
      "learning_rate": 2.9956927376917137e-05,
      "loss": 0.7285,
      "step": 520
    },
    {
      "epoch": 0.03458852705083861,
      "grad_norm": 5.211123255860348,
      "learning_rate": 2.9954542733118496e-05,
      "loss": 0.7511,
      "step": 530
    },
    {
      "epoch": 0.03524114076877896,
      "grad_norm": 9.925273547498618,
      "learning_rate": 2.995209394490827e-05,
      "loss": 0.7699,
      "step": 540
    },
    {
      "epoch": 0.03589375448671931,
      "grad_norm": 7.418381681996765,
      "learning_rate": 2.9949581022790025e-05,
      "loss": 0.759,
      "step": 550
    },
    {
      "epoch": 0.03654636820465966,
      "grad_norm": 4.352380973507467,
      "learning_rate": 2.9947003977542423e-05,
      "loss": 0.7537,
      "step": 560
    },
    {
      "epoch": 0.037198981922600016,
      "grad_norm": 9.712842120769198,
      "learning_rate": 2.9944362820219167e-05,
      "loss": 0.7063,
      "step": 570
    },
    {
      "epoch": 0.037851595640540366,
      "grad_norm": 5.757600819230482,
      "learning_rate": 2.994165756214895e-05,
      "loss": 0.7893,
      "step": 580
    },
    {
      "epoch": 0.038504209358480715,
      "grad_norm": 5.529209601152462,
      "learning_rate": 2.9938888214935426e-05,
      "loss": 0.6771,
      "step": 590
    },
    {
      "epoch": 0.039156823076421064,
      "grad_norm": 10.550479346499758,
      "learning_rate": 2.9936054790457127e-05,
      "loss": 0.737,
      "step": 600
    },
    {
      "epoch": 0.03980943679436142,
      "grad_norm": 8.284279553451016,
      "learning_rate": 2.9933157300867437e-05,
      "loss": 0.7182,
      "step": 610
    },
    {
      "epoch": 0.04046205051230177,
      "grad_norm": 8.18511648646326,
      "learning_rate": 2.9930195758594542e-05,
      "loss": 0.6901,
      "step": 620
    },
    {
      "epoch": 0.04111466423024212,
      "grad_norm": 14.569754827631956,
      "learning_rate": 2.9927170176341365e-05,
      "loss": 0.7008,
      "step": 630
    },
    {
      "epoch": 0.04176727794818247,
      "grad_norm": 4.214581273685441,
      "learning_rate": 2.992408056708551e-05,
      "loss": 0.7489,
      "step": 640
    },
    {
      "epoch": 0.042419891666122825,
      "grad_norm": 10.038596627079452,
      "learning_rate": 2.9920926944079224e-05,
      "loss": 0.7649,
      "step": 650
    },
    {
      "epoch": 0.043072505384063174,
      "grad_norm": 2.386544029221306,
      "learning_rate": 2.9917709320849305e-05,
      "loss": 0.7223,
      "step": 660
    },
    {
      "epoch": 0.043725119102003523,
      "grad_norm": 8.286359254511249,
      "learning_rate": 2.9914427711197096e-05,
      "loss": 0.7089,
      "step": 670
    },
    {
      "epoch": 0.04437773281994387,
      "grad_norm": 4.235819327444911,
      "learning_rate": 2.9911082129198372e-05,
      "loss": 0.7138,
      "step": 680
    },
    {
      "epoch": 0.04503034653788423,
      "grad_norm": 5.187338033698449,
      "learning_rate": 2.9907672589203316e-05,
      "loss": 0.7192,
      "step": 690
    },
    {
      "epoch": 0.04568296025582458,
      "grad_norm": 6.360475337181379,
      "learning_rate": 2.9904199105836443e-05,
      "loss": 0.7094,
      "step": 700
    },
    {
      "epoch": 0.04633557397376493,
      "grad_norm": 4.906400836156689,
      "learning_rate": 2.990066169399654e-05,
      "loss": 0.654,
      "step": 710
    },
    {
      "epoch": 0.04698818769170528,
      "grad_norm": 17.600495314130633,
      "learning_rate": 2.9897060368856603e-05,
      "loss": 0.7299,
      "step": 720
    },
    {
      "epoch": 0.04764080140964563,
      "grad_norm": 7.765935941492389,
      "learning_rate": 2.989339514586377e-05,
      "loss": 0.7486,
      "step": 730
    },
    {
      "epoch": 0.04829341512758598,
      "grad_norm": 7.30026395137639,
      "learning_rate": 2.9889666040739252e-05,
      "loss": 0.6941,
      "step": 740
    },
    {
      "epoch": 0.04894602884552633,
      "grad_norm": 4.676985481218465,
      "learning_rate": 2.9885873069478275e-05,
      "loss": 0.7701,
      "step": 750
    },
    {
      "epoch": 0.04959864256346668,
      "grad_norm": 42.50656974727186,
      "learning_rate": 2.9882016248350006e-05,
      "loss": 0.7428,
      "step": 760
    },
    {
      "epoch": 0.05025125628140704,
      "grad_norm": 3.9893667031114766,
      "learning_rate": 2.9878095593897474e-05,
      "loss": 0.7204,
      "step": 770
    },
    {
      "epoch": 0.05090386999934739,
      "grad_norm": 8.909028486553332,
      "learning_rate": 2.9874111122937518e-05,
      "loss": 0.7336,
      "step": 780
    },
    {
      "epoch": 0.051556483717287736,
      "grad_norm": 5.256925284136456,
      "learning_rate": 2.9870062852560698e-05,
      "loss": 0.7674,
      "step": 790
    },
    {
      "epoch": 0.052209097435228086,
      "grad_norm": 5.835535487534073,
      "learning_rate": 2.986595080013123e-05,
      "loss": 0.7547,
      "step": 800
    },
    {
      "epoch": 0.05286171115316844,
      "grad_norm": 4.7337998648314565,
      "learning_rate": 2.9861774983286913e-05,
      "loss": 0.7412,
      "step": 810
    },
    {
      "epoch": 0.05351432487110879,
      "grad_norm": 4.020304406250962,
      "learning_rate": 2.9857535419939053e-05,
      "loss": 0.7351,
      "step": 820
    },
    {
      "epoch": 0.05416693858904914,
      "grad_norm": 7.005748568175158,
      "learning_rate": 2.9853232128272367e-05,
      "loss": 0.7146,
      "step": 830
    },
    {
      "epoch": 0.05481955230698949,
      "grad_norm": 12.598315147497464,
      "learning_rate": 2.984886512674494e-05,
      "loss": 0.7066,
      "step": 840
    },
    {
      "epoch": 0.055472166024929846,
      "grad_norm": 5.636755294839953,
      "learning_rate": 2.9844434434088114e-05,
      "loss": 0.8033,
      "step": 850
    },
    {
      "epoch": 0.056124779742870196,
      "grad_norm": 2.5964949457129305,
      "learning_rate": 2.9839940069306436e-05,
      "loss": 0.718,
      "step": 860
    },
    {
      "epoch": 0.056777393460810545,
      "grad_norm": 5.496060434333994,
      "learning_rate": 2.9835382051677548e-05,
      "loss": 0.7382,
      "step": 870
    },
    {
      "epoch": 0.057430007178750894,
      "grad_norm": 3.367511777906771,
      "learning_rate": 2.9830760400752117e-05,
      "loss": 0.7049,
      "step": 880
    },
    {
      "epoch": 0.05808262089669125,
      "grad_norm": 12.228282751386294,
      "learning_rate": 2.9826075136353762e-05,
      "loss": 0.7135,
      "step": 890
    },
    {
      "epoch": 0.0587352346146316,
      "grad_norm": 7.426066867205744,
      "learning_rate": 2.9821326278578955e-05,
      "loss": 0.6966,
      "step": 900
    },
    {
      "epoch": 0.05938784833257195,
      "grad_norm": 5.720080945169142,
      "learning_rate": 2.981651384779693e-05,
      "loss": 0.7325,
      "step": 910
    },
    {
      "epoch": 0.0600404620505123,
      "grad_norm": 3.3362738196336275,
      "learning_rate": 2.9811637864649622e-05,
      "loss": 0.7013,
      "step": 920
    },
    {
      "epoch": 0.060693075768452655,
      "grad_norm": 5.5481143050516675,
      "learning_rate": 2.980669835005154e-05,
      "loss": 0.7107,
      "step": 930
    },
    {
      "epoch": 0.061345689486393004,
      "grad_norm": 2.7247889305754533,
      "learning_rate": 2.980169532518971e-05,
      "loss": 0.6839,
      "step": 940
    },
    {
      "epoch": 0.06199830320433335,
      "grad_norm": 12.705144630158374,
      "learning_rate": 2.9796628811523576e-05,
      "loss": 0.7061,
      "step": 950
    },
    {
      "epoch": 0.0626509169222737,
      "grad_norm": 3.1174966376805777,
      "learning_rate": 2.9791498830784896e-05,
      "loss": 0.706,
      "step": 960
    },
    {
      "epoch": 0.06330353064021406,
      "grad_norm": 6.454819870022971,
      "learning_rate": 2.9786305404977657e-05,
      "loss": 0.6901,
      "step": 970
    },
    {
      "epoch": 0.06395614435815442,
      "grad_norm": 8.62099817289566,
      "learning_rate": 2.9781048556377982e-05,
      "loss": 0.6737,
      "step": 980
    },
    {
      "epoch": 0.06460875807609476,
      "grad_norm": 12.649532843245389,
      "learning_rate": 2.977572830753404e-05,
      "loss": 0.6777,
      "step": 990
    },
    {
      "epoch": 0.06526137179403511,
      "grad_norm": 5.019508830810828,
      "learning_rate": 2.9770344681265925e-05,
      "loss": 0.7125,
      "step": 1000
    },
    {
      "epoch": 0.06591398551197546,
      "grad_norm": 5.417114630539967,
      "learning_rate": 2.9764897700665595e-05,
      "loss": 0.7558,
      "step": 1010
    },
    {
      "epoch": 0.06656659922991581,
      "grad_norm": 13.487574757960102,
      "learning_rate": 2.975938738909674e-05,
      "loss": 0.7305,
      "step": 1020
    },
    {
      "epoch": 0.06721921294785617,
      "grad_norm": 4.115297871929447,
      "learning_rate": 2.97538137701947e-05,
      "loss": 0.7382,
      "step": 1030
    },
    {
      "epoch": 0.06787182666579651,
      "grad_norm": 4.218133725965425,
      "learning_rate": 2.974817686786636e-05,
      "loss": 0.7131,
      "step": 1040
    },
    {
      "epoch": 0.06852444038373687,
      "grad_norm": 23.754945260227526,
      "learning_rate": 2.9742476706290044e-05,
      "loss": 0.6854,
      "step": 1050
    },
    {
      "epoch": 0.06917705410167722,
      "grad_norm": 9.992382581534882,
      "learning_rate": 2.973671330991541e-05,
      "loss": 0.7224,
      "step": 1060
    },
    {
      "epoch": 0.06982966781961757,
      "grad_norm": 9.022842665053004,
      "learning_rate": 2.973088670346336e-05,
      "loss": 0.69,
      "step": 1070
    },
    {
      "epoch": 0.07048228153755792,
      "grad_norm": 7.180693480173149,
      "learning_rate": 2.97249969119259e-05,
      "loss": 0.6752,
      "step": 1080
    },
    {
      "epoch": 0.07113489525549826,
      "grad_norm": 4.631581340679664,
      "learning_rate": 2.9719043960566088e-05,
      "loss": 0.7078,
      "step": 1090
    },
    {
      "epoch": 0.07178750897343862,
      "grad_norm": 3.8365551360021497,
      "learning_rate": 2.9713027874917867e-05,
      "loss": 0.7455,
      "step": 1100
    },
    {
      "epoch": 0.07244012269137898,
      "grad_norm": 20.612721990589407,
      "learning_rate": 2.9706948680785984e-05,
      "loss": 0.7123,
      "step": 1110
    },
    {
      "epoch": 0.07309273640931932,
      "grad_norm": 8.515913036269723,
      "learning_rate": 2.9700806404245893e-05,
      "loss": 0.6755,
      "step": 1120
    },
    {
      "epoch": 0.07374535012725968,
      "grad_norm": 8.702591994450561,
      "learning_rate": 2.9694601071643607e-05,
      "loss": 0.743,
      "step": 1130
    },
    {
      "epoch": 0.07439796384520003,
      "grad_norm": 20.204623397644042,
      "learning_rate": 2.968833270959562e-05,
      "loss": 0.6995,
      "step": 1140
    },
    {
      "epoch": 0.07505057756314037,
      "grad_norm": 3.4150625200259563,
      "learning_rate": 2.9682001344988768e-05,
      "loss": 0.7245,
      "step": 1150
    },
    {
      "epoch": 0.07570319128108073,
      "grad_norm": 4.827412673105033,
      "learning_rate": 2.967560700498013e-05,
      "loss": 0.6764,
      "step": 1160
    },
    {
      "epoch": 0.07635580499902107,
      "grad_norm": 5.9778449783108965,
      "learning_rate": 2.9669149716996897e-05,
      "loss": 0.7094,
      "step": 1170
    },
    {
      "epoch": 0.07700841871696143,
      "grad_norm": 4.626419468156439,
      "learning_rate": 2.9662629508736278e-05,
      "loss": 0.7139,
      "step": 1180
    },
    {
      "epoch": 0.07766103243490179,
      "grad_norm": 8.23953369228554,
      "learning_rate": 2.9656046408165344e-05,
      "loss": 0.7132,
      "step": 1190
    },
    {
      "epoch": 0.07831364615284213,
      "grad_norm": 5.755275462407804,
      "learning_rate": 2.964940044352095e-05,
      "loss": 0.6923,
      "step": 1200
    },
    {
      "epoch": 0.07896625987078248,
      "grad_norm": 3.8396649246253816,
      "learning_rate": 2.9642691643309572e-05,
      "loss": 0.7082,
      "step": 1210
    },
    {
      "epoch": 0.07961887358872284,
      "grad_norm": 5.7429454484886415,
      "learning_rate": 2.963592003630723e-05,
      "loss": 0.7095,
      "step": 1220
    },
    {
      "epoch": 0.08027148730666318,
      "grad_norm": 17.628494673763004,
      "learning_rate": 2.962908565155932e-05,
      "loss": 0.7309,
      "step": 1230
    },
    {
      "epoch": 0.08092410102460354,
      "grad_norm": 4.83400055237192,
      "learning_rate": 2.9622188518380528e-05,
      "loss": 0.6925,
      "step": 1240
    },
    {
      "epoch": 0.08157671474254388,
      "grad_norm": 3.1535973307593905,
      "learning_rate": 2.9615228666354667e-05,
      "loss": 0.7441,
      "step": 1250
    },
    {
      "epoch": 0.08222932846048424,
      "grad_norm": 4.085385929026401,
      "learning_rate": 2.9608206125334586e-05,
      "loss": 0.7137,
      "step": 1260
    },
    {
      "epoch": 0.0828819421784246,
      "grad_norm": 4.299591870123697,
      "learning_rate": 2.9601120925442016e-05,
      "loss": 0.7515,
      "step": 1270
    },
    {
      "epoch": 0.08353455589636494,
      "grad_norm": 12.873434323415678,
      "learning_rate": 2.959397309706746e-05,
      "loss": 0.6852,
      "step": 1280
    },
    {
      "epoch": 0.0841871696143053,
      "grad_norm": 6.427088345402557,
      "learning_rate": 2.958676267087004e-05,
      "loss": 0.6499,
      "step": 1290
    },
    {
      "epoch": 0.08483978333224565,
      "grad_norm": 4.70723263638176,
      "learning_rate": 2.9579489677777387e-05,
      "loss": 0.6803,
      "step": 1300
    },
    {
      "epoch": 0.08549239705018599,
      "grad_norm": 4.819218491318424,
      "learning_rate": 2.9572154148985495e-05,
      "loss": 0.6798,
      "step": 1310
    },
    {
      "epoch": 0.08614501076812635,
      "grad_norm": 3.0652661968089827,
      "learning_rate": 2.9564756115958592e-05,
      "loss": 0.6935,
      "step": 1320
    },
    {
      "epoch": 0.08679762448606669,
      "grad_norm": 5.997224165634556,
      "learning_rate": 2.9557295610429017e-05,
      "loss": 0.7133,
      "step": 1330
    },
    {
      "epoch": 0.08745023820400705,
      "grad_norm": 3.3593003375605717,
      "learning_rate": 2.954977266439706e-05,
      "loss": 0.7335,
      "step": 1340
    },
    {
      "epoch": 0.0881028519219474,
      "grad_norm": 4.161242018302672,
      "learning_rate": 2.954218731013083e-05,
      "loss": 0.7054,
      "step": 1350
    },
    {
      "epoch": 0.08875546563988775,
      "grad_norm": 5.827431481546491,
      "learning_rate": 2.953453958016614e-05,
      "loss": 0.6321,
      "step": 1360
    },
    {
      "epoch": 0.0894080793578281,
      "grad_norm": 7.1039105888444904,
      "learning_rate": 2.952682950730634e-05,
      "loss": 0.6941,
      "step": 1370
    },
    {
      "epoch": 0.09006069307576846,
      "grad_norm": 2.7616336275225892,
      "learning_rate": 2.951905712462219e-05,
      "loss": 0.6928,
      "step": 1380
    },
    {
      "epoch": 0.0907133067937088,
      "grad_norm": 4.261061690296871,
      "learning_rate": 2.9511222465451716e-05,
      "loss": 0.7176,
      "step": 1390
    },
    {
      "epoch": 0.09136592051164916,
      "grad_norm": 5.4134818862551395,
      "learning_rate": 2.950332556340006e-05,
      "loss": 0.7048,
      "step": 1400
    },
    {
      "epoch": 0.0920185342295895,
      "grad_norm": 6.3477656240577085,
      "learning_rate": 2.949536645233935e-05,
      "loss": 0.6842,
      "step": 1410
    },
    {
      "epoch": 0.09267114794752986,
      "grad_norm": 63.477804314776044,
      "learning_rate": 2.9487345166408545e-05,
      "loss": 0.6876,
      "step": 1420
    },
    {
      "epoch": 0.09332376166547021,
      "grad_norm": 4.368664541213622,
      "learning_rate": 2.9479261740013286e-05,
      "loss": 0.6913,
      "step": 1430
    },
    {
      "epoch": 0.09397637538341055,
      "grad_norm": 9.476938465079238,
      "learning_rate": 2.9471116207825754e-05,
      "loss": 0.6891,
      "step": 1440
    },
    {
      "epoch": 0.09462898910135091,
      "grad_norm": 8.434794578560851,
      "learning_rate": 2.9462908604784523e-05,
      "loss": 0.6585,
      "step": 1450
    },
    {
      "epoch": 0.09528160281929127,
      "grad_norm": 4.798759761163433,
      "learning_rate": 2.945463896609441e-05,
      "loss": 0.6736,
      "step": 1460
    },
    {
      "epoch": 0.09593421653723161,
      "grad_norm": 9.782724872581115,
      "learning_rate": 2.9446307327226306e-05,
      "loss": 0.6659,
      "step": 1470
    },
    {
      "epoch": 0.09658683025517197,
      "grad_norm": 3.997516099278308,
      "learning_rate": 2.9437913723917058e-05,
      "loss": 0.6527,
      "step": 1480
    },
    {
      "epoch": 0.09723944397311232,
      "grad_norm": 4.623015725563099,
      "learning_rate": 2.942945819216928e-05,
      "loss": 0.7274,
      "step": 1490
    },
    {
      "epoch": 0.09789205769105266,
      "grad_norm": 3.2197835799755055,
      "learning_rate": 2.942094076825123e-05,
      "loss": 0.6966,
      "step": 1500
    },
    {
      "epoch": 0.09854467140899302,
      "grad_norm": 3.5107988249516984,
      "learning_rate": 2.9412361488696628e-05,
      "loss": 0.7235,
      "step": 1510
    },
    {
      "epoch": 0.09919728512693336,
      "grad_norm": 18.7865650951996,
      "learning_rate": 2.9403720390304518e-05,
      "loss": 0.7382,
      "step": 1520
    },
    {
      "epoch": 0.09984989884487372,
      "grad_norm": 3.85598692653545,
      "learning_rate": 2.93950175101391e-05,
      "loss": 0.7475,
      "step": 1530
    },
    {
      "epoch": 0.10050251256281408,
      "grad_norm": 20.459657003411998,
      "learning_rate": 2.938625288552957e-05,
      "loss": 0.6558,
      "step": 1540
    },
    {
      "epoch": 0.10115512628075442,
      "grad_norm": 6.416583997846208,
      "learning_rate": 2.9377426554069976e-05,
      "loss": 0.7205,
      "step": 1550
    },
    {
      "epoch": 0.10180773999869477,
      "grad_norm": 5.532087704430113,
      "learning_rate": 2.936853855361904e-05,
      "loss": 0.7189,
      "step": 1560
    },
    {
      "epoch": 0.10246035371663513,
      "grad_norm": 4.756518458886862,
      "learning_rate": 2.9359588922299986e-05,
      "loss": 0.7088,
      "step": 1570
    },
    {
      "epoch": 0.10311296743457547,
      "grad_norm": 5.775658785412931,
      "learning_rate": 2.9350577698500408e-05,
      "loss": 0.682,
      "step": 1580
    },
    {
      "epoch": 0.10376558115251583,
      "grad_norm": 7.714313915746094,
      "learning_rate": 2.9341504920872087e-05,
      "loss": 0.7393,
      "step": 1590
    },
    {
      "epoch": 0.10441819487045617,
      "grad_norm": 11.153510433173501,
      "learning_rate": 2.933237062833082e-05,
      "loss": 0.6616,
      "step": 1600
    },
    {
      "epoch": 0.10507080858839653,
      "grad_norm": 4.575896778703132,
      "learning_rate": 2.9323174860056258e-05,
      "loss": 0.7168,
      "step": 1610
    },
    {
      "epoch": 0.10572342230633688,
      "grad_norm": 46.2282201673799,
      "learning_rate": 2.9313917655491744e-05,
      "loss": 0.7016,
      "step": 1620
    },
    {
      "epoch": 0.10637603602427723,
      "grad_norm": 51.80540559466864,
      "learning_rate": 2.9304599054344148e-05,
      "loss": 0.6709,
      "step": 1630
    },
    {
      "epoch": 0.10702864974221758,
      "grad_norm": 4.607057564284905,
      "learning_rate": 2.9295219096583663e-05,
      "loss": 0.6894,
      "step": 1640
    },
    {
      "epoch": 0.10768126346015794,
      "grad_norm": 4.158724628963882,
      "learning_rate": 2.9285777822443686e-05,
      "loss": 0.6847,
      "step": 1650
    },
    {
      "epoch": 0.10833387717809828,
      "grad_norm": 6.634813921115065,
      "learning_rate": 2.92762752724206e-05,
      "loss": 0.7094,
      "step": 1660
    },
    {
      "epoch": 0.10898649089603864,
      "grad_norm": 2.437577662086608,
      "learning_rate": 2.926671148727362e-05,
      "loss": 0.69,
      "step": 1670
    },
    {
      "epoch": 0.10963910461397898,
      "grad_norm": 22.722071681603026,
      "learning_rate": 2.925708650802463e-05,
      "loss": 0.704,
      "step": 1680
    },
    {
      "epoch": 0.11029171833191934,
      "grad_norm": 2.913996227830109,
      "learning_rate": 2.9247400375957976e-05,
      "loss": 0.7211,
      "step": 1690
    },
    {
      "epoch": 0.11094433204985969,
      "grad_norm": 5.279852146043678,
      "learning_rate": 2.923765313262032e-05,
      "loss": 0.6693,
      "step": 1700
    },
    {
      "epoch": 0.11159694576780003,
      "grad_norm": 4.47116557104752,
      "learning_rate": 2.9227844819820434e-05,
      "loss": 0.6958,
      "step": 1710
    },
    {
      "epoch": 0.11224955948574039,
      "grad_norm": 6.9451125709413,
      "learning_rate": 2.9217975479629047e-05,
      "loss": 0.6549,
      "step": 1720
    },
    {
      "epoch": 0.11290217320368075,
      "grad_norm": 8.218016152925602,
      "learning_rate": 2.920804515437865e-05,
      "loss": 0.7034,
      "step": 1730
    },
    {
      "epoch": 0.11355478692162109,
      "grad_norm": 4.725968454405007,
      "learning_rate": 2.9198053886663314e-05,
      "loss": 0.7292,
      "step": 1740
    },
    {
      "epoch": 0.11420740063956145,
      "grad_norm": 8.078717621365517,
      "learning_rate": 2.9188001719338514e-05,
      "loss": 0.6556,
      "step": 1750
    },
    {
      "epoch": 0.11486001435750179,
      "grad_norm": 9.045448414751244,
      "learning_rate": 2.9177888695520933e-05,
      "loss": 0.7223,
      "step": 1760
    },
    {
      "epoch": 0.11551262807544214,
      "grad_norm": 4.318313439658446,
      "learning_rate": 2.916771485858829e-05,
      "loss": 0.6762,
      "step": 1770
    },
    {
      "epoch": 0.1161652417933825,
      "grad_norm": 13.078874026489483,
      "learning_rate": 2.9157480252179156e-05,
      "loss": 0.7189,
      "step": 1780
    },
    {
      "epoch": 0.11681785551132284,
      "grad_norm": 8.585825980992096,
      "learning_rate": 2.9147184920192745e-05,
      "loss": 0.7142,
      "step": 1790
    },
    {
      "epoch": 0.1174704692292632,
      "grad_norm": 138.05135197182966,
      "learning_rate": 2.9136828906788765e-05,
      "loss": 0.6514,
      "step": 1800
    },
    {
      "epoch": 0.11812308294720356,
      "grad_norm": 2.9764498791953167,
      "learning_rate": 2.9126412256387172e-05,
      "loss": 0.6835,
      "step": 1810
    },
    {
      "epoch": 0.1187756966651439,
      "grad_norm": 10.553495101154766,
      "learning_rate": 2.9115935013668038e-05,
      "loss": 0.7049,
      "step": 1820
    },
    {
      "epoch": 0.11942831038308425,
      "grad_norm": 3.8520760029457755,
      "learning_rate": 2.910539722357132e-05,
      "loss": 0.6805,
      "step": 1830
    },
    {
      "epoch": 0.1200809241010246,
      "grad_norm": 6.002281391018973,
      "learning_rate": 2.9094798931296692e-05,
      "loss": 0.7044,
      "step": 1840
    },
    {
      "epoch": 0.12073353781896495,
      "grad_norm": 9.04002888227592,
      "learning_rate": 2.9084140182303328e-05,
      "loss": 0.7221,
      "step": 1850
    },
    {
      "epoch": 0.12138615153690531,
      "grad_norm": 2.324509546376411,
      "learning_rate": 2.907342102230972e-05,
      "loss": 0.7,
      "step": 1860
    },
    {
      "epoch": 0.12203876525484565,
      "grad_norm": 4.136482440945801,
      "learning_rate": 2.9062641497293485e-05,
      "loss": 0.7213,
      "step": 1870
    },
    {
      "epoch": 0.12269137897278601,
      "grad_norm": 2.9193932096141673,
      "learning_rate": 2.9051801653491158e-05,
      "loss": 0.6656,
      "step": 1880
    },
    {
      "epoch": 0.12334399269072636,
      "grad_norm": 6.319528726800553,
      "learning_rate": 2.9040901537398008e-05,
      "loss": 0.6701,
      "step": 1890
    },
    {
      "epoch": 0.1239966064086667,
      "grad_norm": 3.5042010027049533,
      "learning_rate": 2.9029941195767824e-05,
      "loss": 0.6454,
      "step": 1900
    },
    {
      "epoch": 0.12464922012660706,
      "grad_norm": 4.3096531856338895,
      "learning_rate": 2.9018920675612712e-05,
      "loss": 0.6818,
      "step": 1910
    },
    {
      "epoch": 0.1253018338445474,
      "grad_norm": 6.849873350879978,
      "learning_rate": 2.900784002420292e-05,
      "loss": 0.7674,
      "step": 1920
    },
    {
      "epoch": 0.12595444756248778,
      "grad_norm": 7.645127543651015,
      "learning_rate": 2.89966992890666e-05,
      "loss": 0.7,
      "step": 1930
    },
    {
      "epoch": 0.12660706128042812,
      "grad_norm": 3.334578297503325,
      "learning_rate": 2.8985498517989623e-05,
      "loss": 0.6783,
      "step": 1940
    },
    {
      "epoch": 0.12725967499836846,
      "grad_norm": 7.91381208921764,
      "learning_rate": 2.897423775901538e-05,
      "loss": 0.7327,
      "step": 1950
    },
    {
      "epoch": 0.12791228871630883,
      "grad_norm": 7.74516810255062,
      "learning_rate": 2.8962917060444562e-05,
      "loss": 0.7145,
      "step": 1960
    },
    {
      "epoch": 0.12856490243424917,
      "grad_norm": 5.468499401345368,
      "learning_rate": 2.8951536470834957e-05,
      "loss": 0.6807,
      "step": 1970
    },
    {
      "epoch": 0.12921751615218952,
      "grad_norm": 3.7005534196349963,
      "learning_rate": 2.894009603900125e-05,
      "loss": 0.7004,
      "step": 1980
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 3.6355286647446716,
      "learning_rate": 2.89285958140148e-05,
      "loss": 0.6804,
      "step": 1990
    },
    {
      "epoch": 0.13052274358807023,
      "grad_norm": 4.199898882057381,
      "learning_rate": 2.891703584520343e-05,
      "loss": 0.7268,
      "step": 2000
    }
  ],
  "logging_steps": 10,
  "max_steps": 15323,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.467141180489728e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}