{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9954430379746837,
  "eval_steps": 500,
  "global_step": 1479,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020253164556962026,
      "grad_norm": 4.742581199201631,
      "learning_rate": 6.756756756756758e-07,
      "loss": 0.8238,
      "step": 10
    },
    {
      "epoch": 0.04050632911392405,
      "grad_norm": 2.7089177182440225,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 0.7256,
      "step": 20
    },
    {
      "epoch": 0.060759493670886074,
      "grad_norm": 1.6438330526897271,
      "learning_rate": 2.0270270270270273e-06,
      "loss": 0.6705,
      "step": 30
    },
    {
      "epoch": 0.0810126582278481,
      "grad_norm": 1.9649059006708485,
      "learning_rate": 2.702702702702703e-06,
      "loss": 0.6382,
      "step": 40
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 1.8319812554661556,
      "learning_rate": 3.3783783783783788e-06,
      "loss": 0.62,
      "step": 50
    },
    {
      "epoch": 0.12151898734177215,
      "grad_norm": 1.8563981143868757,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 0.6097,
      "step": 60
    },
    {
      "epoch": 0.14177215189873418,
      "grad_norm": 2.0369557567075196,
      "learning_rate": 4.72972972972973e-06,
      "loss": 0.6039,
      "step": 70
    },
    {
      "epoch": 0.1620253164556962,
      "grad_norm": 3.933193428286484,
      "learning_rate": 4.978647686832741e-06,
      "loss": 0.5981,
      "step": 80
    },
    {
      "epoch": 0.18227848101265823,
      "grad_norm": 3.961786031844899,
      "learning_rate": 4.943060498220641e-06,
      "loss": 0.5957,
      "step": 90
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 3.016653386179453,
      "learning_rate": 4.907473309608541e-06,
      "loss": 0.5966,
      "step": 100
    },
    {
      "epoch": 0.22278481012658227,
      "grad_norm": 2.0911611009486664,
      "learning_rate": 4.8718861209964415e-06,
      "loss": 0.5874,
      "step": 110
    },
    {
      "epoch": 0.2430379746835443,
      "grad_norm": 2.3577222635919877,
      "learning_rate": 4.836298932384342e-06,
      "loss": 0.5851,
      "step": 120
    },
    {
      "epoch": 0.26329113924050634,
      "grad_norm": 2.4189498060173826,
      "learning_rate": 4.800711743772242e-06,
      "loss": 0.5839,
      "step": 130
    },
    {
      "epoch": 0.28354430379746837,
      "grad_norm": 1.9667579738688012,
      "learning_rate": 4.765124555160142e-06,
      "loss": 0.573,
      "step": 140
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 1.369959691403867,
      "learning_rate": 4.7295373665480435e-06,
      "loss": 0.5838,
      "step": 150
    },
    {
      "epoch": 0.3240506329113924,
      "grad_norm": 1.4080935903120366,
      "learning_rate": 4.693950177935944e-06,
      "loss": 0.5826,
      "step": 160
    },
    {
      "epoch": 0.34430379746835443,
      "grad_norm": 1.375777676837261,
      "learning_rate": 4.658362989323843e-06,
      "loss": 0.5827,
      "step": 170
    },
    {
      "epoch": 0.36455696202531646,
      "grad_norm": 1.6546345406257401,
      "learning_rate": 4.622775800711744e-06,
      "loss": 0.5783,
      "step": 180
    },
    {
      "epoch": 0.3848101265822785,
      "grad_norm": 2.138184576302769,
      "learning_rate": 4.587188612099645e-06,
      "loss": 0.578,
      "step": 190
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 1.5042114599648924,
      "learning_rate": 4.551601423487545e-06,
      "loss": 0.5713,
      "step": 200
    },
    {
      "epoch": 0.4253164556962025,
      "grad_norm": 2.34307337846717,
      "learning_rate": 4.516014234875445e-06,
      "loss": 0.5659,
      "step": 210
    },
    {
      "epoch": 0.44556962025316454,
      "grad_norm": 2.2965660467623983,
      "learning_rate": 4.4804270462633455e-06,
      "loss": 0.5711,
      "step": 220
    },
    {
      "epoch": 0.46582278481012657,
      "grad_norm": 2.2958689571859363,
      "learning_rate": 4.444839857651246e-06,
      "loss": 0.5693,
      "step": 230
    },
    {
      "epoch": 0.4860759493670886,
      "grad_norm": 2.417004138332344,
      "learning_rate": 4.409252669039146e-06,
      "loss": 0.5646,
      "step": 240
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 2.12941087663038,
      "learning_rate": 4.373665480427046e-06,
      "loss": 0.5681,
      "step": 250
    },
    {
      "epoch": 0.5265822784810127,
      "grad_norm": 1.8555366173965417,
      "learning_rate": 4.3380782918149475e-06,
      "loss": 0.5543,
      "step": 260
    },
    {
      "epoch": 0.5468354430379747,
      "grad_norm": 1.5852520856985666,
      "learning_rate": 4.302491103202847e-06,
      "loss": 0.5639,
      "step": 270
    },
    {
      "epoch": 0.5670886075949367,
      "grad_norm": 1.460016106438118,
      "learning_rate": 4.266903914590747e-06,
      "loss": 0.5593,
      "step": 280
    },
    {
      "epoch": 0.5873417721518988,
      "grad_norm": 1.7121558558722028,
      "learning_rate": 4.231316725978648e-06,
      "loss": 0.5608,
      "step": 290
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 1.3067137647800322,
      "learning_rate": 4.195729537366549e-06,
      "loss": 0.5607,
      "step": 300
    },
    {
      "epoch": 0.6278481012658228,
      "grad_norm": 1.418773706013845,
      "learning_rate": 4.160142348754449e-06,
      "loss": 0.5666,
      "step": 310
    },
    {
      "epoch": 0.6481012658227848,
      "grad_norm": 1.4267499965709702,
      "learning_rate": 4.124555160142349e-06,
      "loss": 0.5629,
      "step": 320
    },
    {
      "epoch": 0.6683544303797468,
      "grad_norm": 1.3749578870885502,
      "learning_rate": 4.0889679715302495e-06,
      "loss": 0.5619,
      "step": 330
    },
    {
      "epoch": 0.6886075949367089,
      "grad_norm": 1.275893799768224,
      "learning_rate": 4.05338078291815e-06,
      "loss": 0.5611,
      "step": 340
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 1.2613374964537525,
      "learning_rate": 4.01779359430605e-06,
      "loss": 0.5625,
      "step": 350
    },
    {
      "epoch": 0.7291139240506329,
      "grad_norm": 1.282128305662025,
      "learning_rate": 3.98220640569395e-06,
      "loss": 0.5647,
      "step": 360
    },
    {
      "epoch": 0.7493670886075949,
      "grad_norm": 1.2183620482413273,
      "learning_rate": 3.946619217081851e-06,
      "loss": 0.557,
      "step": 370
    },
    {
      "epoch": 0.769620253164557,
      "grad_norm": 1.1816403948954313,
      "learning_rate": 3.911032028469751e-06,
      "loss": 0.5535,
      "step": 380
    },
    {
      "epoch": 0.789873417721519,
      "grad_norm": 1.343065511383417,
      "learning_rate": 3.875444839857651e-06,
      "loss": 0.5564,
      "step": 390
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 1.1056411836705247,
      "learning_rate": 3.839857651245552e-06,
      "loss": 0.5562,
      "step": 400
    },
    {
      "epoch": 0.830379746835443,
      "grad_norm": 1.1617514638384954,
      "learning_rate": 3.804270462633452e-06,
      "loss": 0.5509,
      "step": 410
    },
    {
      "epoch": 0.850632911392405,
      "grad_norm": 1.2456514736887305,
      "learning_rate": 3.7686832740213525e-06,
      "loss": 0.5589,
      "step": 420
    },
    {
      "epoch": 0.8708860759493671,
      "grad_norm": 1.0959898492388527,
      "learning_rate": 3.733096085409253e-06,
      "loss": 0.5521,
      "step": 430
    },
    {
      "epoch": 0.8911392405063291,
      "grad_norm": 1.295665638247925,
      "learning_rate": 3.6975088967971536e-06,
      "loss": 0.5572,
      "step": 440
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 1.0535123677725715,
      "learning_rate": 3.661921708185054e-06,
      "loss": 0.5482,
      "step": 450
    },
    {
      "epoch": 0.9316455696202531,
      "grad_norm": 1.0683406426734499,
      "learning_rate": 3.6263345195729537e-06,
      "loss": 0.5525,
      "step": 460
    },
    {
      "epoch": 0.9518987341772152,
      "grad_norm": 1.253383608055468,
      "learning_rate": 3.5907473309608544e-06,
      "loss": 0.5533,
      "step": 470
    },
    {
      "epoch": 0.9721518987341772,
      "grad_norm": 1.2809747280599841,
      "learning_rate": 3.5551601423487547e-06,
      "loss": 0.5505,
      "step": 480
    },
    {
      "epoch": 0.9924050632911392,
      "grad_norm": 1.1325843807943288,
      "learning_rate": 3.519572953736655e-06,
      "loss": 0.5465,
      "step": 490
    },
    {
      "epoch": 0.9984810126582279,
      "eval_loss": 0.068679079413414,
      "eval_runtime": 507.7278,
      "eval_samples_per_second": 26.203,
      "eval_steps_per_second": 0.41,
      "step": 493
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 1.7325407692218586,
      "learning_rate": 3.4839857651245557e-06,
      "loss": 0.5125,
      "step": 500
    },
    {
      "epoch": 1.0329113924050632,
      "grad_norm": 1.9559729603669886,
      "learning_rate": 3.4483985765124556e-06,
      "loss": 0.4812,
      "step": 510
    },
    {
      "epoch": 1.0531645569620254,
      "grad_norm": 1.4932963289367234,
      "learning_rate": 3.412811387900356e-06,
      "loss": 0.4774,
      "step": 520
    },
    {
      "epoch": 1.0734177215189873,
      "grad_norm": 1.185384048798669,
      "learning_rate": 3.3772241992882566e-06,
      "loss": 0.4785,
      "step": 530
    },
    {
      "epoch": 1.0936708860759494,
      "grad_norm": 1.1972600486999827,
      "learning_rate": 3.341637010676157e-06,
      "loss": 0.4758,
      "step": 540
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 1.1460022054980692,
      "learning_rate": 3.3060498220640576e-06,
      "loss": 0.4778,
      "step": 550
    },
    {
      "epoch": 1.1341772151898735,
      "grad_norm": 1.1197932329811855,
      "learning_rate": 3.2704626334519575e-06,
      "loss": 0.4752,
      "step": 560
    },
    {
      "epoch": 1.1544303797468354,
      "grad_norm": 1.194566549573746,
      "learning_rate": 3.2348754448398577e-06,
      "loss": 0.4818,
      "step": 570
    },
    {
      "epoch": 1.1746835443037975,
      "grad_norm": 1.2784411634842332,
      "learning_rate": 3.1992882562277585e-06,
      "loss": 0.4798,
      "step": 580
    },
    {
      "epoch": 1.1949367088607594,
      "grad_norm": 1.123327911933,
      "learning_rate": 3.1637010676156587e-06,
      "loss": 0.4736,
      "step": 590
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 1.193089413979018,
      "learning_rate": 3.128113879003559e-06,
      "loss": 0.4804,
      "step": 600
    },
    {
      "epoch": 1.2354430379746835,
      "grad_norm": 1.1785101089717391,
      "learning_rate": 3.0925266903914593e-06,
      "loss": 0.4762,
      "step": 610
    },
    {
      "epoch": 1.2556962025316456,
      "grad_norm": 1.2080168650481182,
      "learning_rate": 3.0569395017793596e-06,
      "loss": 0.4798,
      "step": 620
    },
    {
      "epoch": 1.2759493670886077,
      "grad_norm": 1.3205102063888547,
      "learning_rate": 3.02135231316726e-06,
      "loss": 0.4796,
      "step": 630
    },
    {
      "epoch": 1.2962025316455696,
      "grad_norm": 1.3147319714200894,
      "learning_rate": 2.9857651245551606e-06,
      "loss": 0.4787,
      "step": 640
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 1.1490461889736139,
      "learning_rate": 2.950177935943061e-06,
      "loss": 0.482,
      "step": 650
    },
    {
      "epoch": 1.3367088607594937,
      "grad_norm": 1.3228852312739667,
      "learning_rate": 2.9145907473309608e-06,
      "loss": 0.4705,
      "step": 660
    },
    {
      "epoch": 1.3569620253164558,
      "grad_norm": 1.2638864667189769,
      "learning_rate": 2.8790035587188615e-06,
      "loss": 0.4839,
      "step": 670
    },
    {
      "epoch": 1.3772151898734177,
      "grad_norm": 1.1378222725461256,
      "learning_rate": 2.8434163701067618e-06,
      "loss": 0.4807,
      "step": 680
    },
    {
      "epoch": 1.3974683544303796,
      "grad_norm": 1.136931180029992,
      "learning_rate": 2.8078291814946625e-06,
      "loss": 0.4793,
      "step": 690
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 1.2382582028693814,
      "learning_rate": 2.7722419928825624e-06,
      "loss": 0.476,
      "step": 700
    },
    {
      "epoch": 1.437974683544304,
      "grad_norm": 1.2304522818128008,
      "learning_rate": 2.7366548042704626e-06,
      "loss": 0.4813,
      "step": 710
    },
    {
      "epoch": 1.4582278481012658,
      "grad_norm": 1.123509723565589,
      "learning_rate": 2.7010676156583634e-06,
      "loss": 0.4809,
      "step": 720
    },
    {
      "epoch": 1.4784810126582277,
      "grad_norm": 1.1387958282357735,
      "learning_rate": 2.6654804270462636e-06,
      "loss": 0.4833,
      "step": 730
    },
    {
      "epoch": 1.4987341772151899,
      "grad_norm": 1.118649730450664,
      "learning_rate": 2.629893238434164e-06,
      "loss": 0.4758,
      "step": 740
    },
    {
      "epoch": 1.518987341772152,
      "grad_norm": 1.222896592137077,
      "learning_rate": 2.5943060498220642e-06,
      "loss": 0.4779,
      "step": 750
    },
    {
      "epoch": 1.539240506329114,
      "grad_norm": 1.4074398237958103,
      "learning_rate": 2.5587188612099645e-06,
      "loss": 0.4788,
      "step": 760
    },
    {
      "epoch": 1.5594936708860758,
      "grad_norm": 1.1619300400485018,
      "learning_rate": 2.523131672597865e-06,
      "loss": 0.4772,
      "step": 770
    },
    {
      "epoch": 1.579746835443038,
      "grad_norm": 1.422184034548514,
      "learning_rate": 2.4875444839857655e-06,
      "loss": 0.4778,
      "step": 780
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.2234336626816806,
      "learning_rate": 2.451957295373666e-06,
      "loss": 0.4792,
      "step": 790
    },
    {
      "epoch": 1.620253164556962,
      "grad_norm": 1.1332543250276066,
      "learning_rate": 2.416370106761566e-06,
      "loss": 0.4753,
      "step": 800
    },
    {
      "epoch": 1.640506329113924,
      "grad_norm": 1.2069589755433405,
      "learning_rate": 2.3807829181494664e-06,
      "loss": 0.4683,
      "step": 810
    },
    {
      "epoch": 1.660759493670886,
      "grad_norm": 1.106986539594195,
      "learning_rate": 2.3451957295373667e-06,
      "loss": 0.4773,
      "step": 820
    },
    {
      "epoch": 1.6810126582278482,
      "grad_norm": 1.1080989558058947,
      "learning_rate": 2.3096085409252674e-06,
      "loss": 0.472,
      "step": 830
    },
    {
      "epoch": 1.70126582278481,
      "grad_norm": 1.1905792829948112,
      "learning_rate": 2.2740213523131673e-06,
      "loss": 0.4734,
      "step": 840
    },
    {
      "epoch": 1.721518987341772,
      "grad_norm": 1.1263868733328295,
      "learning_rate": 2.238434163701068e-06,
      "loss": 0.4755,
      "step": 850
    },
    {
      "epoch": 1.7417721518987341,
      "grad_norm": 1.033205957803366,
      "learning_rate": 2.2028469750889683e-06,
      "loss": 0.475,
      "step": 860
    },
    {
      "epoch": 1.7620253164556963,
      "grad_norm": 1.127189794873212,
      "learning_rate": 2.1672597864768685e-06,
      "loss": 0.4785,
      "step": 870
    },
    {
      "epoch": 1.7822784810126582,
      "grad_norm": 1.1788992895844184,
      "learning_rate": 2.131672597864769e-06,
      "loss": 0.479,
      "step": 880
    },
    {
      "epoch": 1.80253164556962,
      "grad_norm": 1.186766190893949,
      "learning_rate": 2.096085409252669e-06,
      "loss": 0.4763,
      "step": 890
    },
    {
      "epoch": 1.8227848101265822,
      "grad_norm": 1.1866935971232218,
      "learning_rate": 2.06049822064057e-06,
      "loss": 0.4751,
      "step": 900
    },
    {
      "epoch": 1.8430379746835444,
      "grad_norm": 1.2254733687693131,
      "learning_rate": 2.0249110320284697e-06,
      "loss": 0.4767,
      "step": 910
    },
    {
      "epoch": 1.8632911392405065,
      "grad_norm": 1.0999643877142318,
      "learning_rate": 1.9893238434163704e-06,
      "loss": 0.475,
      "step": 920
    },
    {
      "epoch": 1.8835443037974684,
      "grad_norm": 1.1191194093430747,
      "learning_rate": 1.9537366548042703e-06,
      "loss": 0.4714,
      "step": 930
    },
    {
      "epoch": 1.9037974683544303,
      "grad_norm": 1.1342720462254603,
      "learning_rate": 1.918149466192171e-06,
      "loss": 0.4751,
      "step": 940
    },
    {
      "epoch": 1.9240506329113924,
      "grad_norm": 1.0241324911004035,
      "learning_rate": 1.8825622775800715e-06,
      "loss": 0.4759,
      "step": 950
    },
    {
      "epoch": 1.9443037974683546,
      "grad_norm": 1.1373301367884234,
      "learning_rate": 1.8469750889679716e-06,
      "loss": 0.4795,
      "step": 960
    },
    {
      "epoch": 1.9645569620253165,
      "grad_norm": 1.047662657429949,
      "learning_rate": 1.811387900355872e-06,
      "loss": 0.4778,
      "step": 970
    },
    {
      "epoch": 1.9848101265822784,
      "grad_norm": 1.0623876456662695,
      "learning_rate": 1.7758007117437724e-06,
      "loss": 0.4778,
      "step": 980
    },
    {
      "epoch": 1.998987341772152,
      "eval_loss": 0.06775479018688202,
      "eval_runtime": 509.7296,
      "eval_samples_per_second": 26.1,
      "eval_steps_per_second": 0.408,
      "step": 987
    },
    {
      "epoch": 2.0050632911392405,
      "grad_norm": 1.885410249625527,
      "learning_rate": 1.7402135231316727e-06,
      "loss": 0.456,
      "step": 990
    },
    {
      "epoch": 2.0253164556962027,
      "grad_norm": 1.4856083185892484,
      "learning_rate": 1.7046263345195732e-06,
      "loss": 0.4107,
      "step": 1000
    },
    {
      "epoch": 2.0455696202531644,
      "grad_norm": 1.309133994163287,
      "learning_rate": 1.6690391459074735e-06,
      "loss": 0.4093,
      "step": 1010
    },
    {
      "epoch": 2.0658227848101265,
      "grad_norm": 1.1938535418758685,
      "learning_rate": 1.633451957295374e-06,
      "loss": 0.4054,
      "step": 1020
    },
    {
      "epoch": 2.0860759493670886,
      "grad_norm": 1.107962295104452,
      "learning_rate": 1.597864768683274e-06,
      "loss": 0.4053,
      "step": 1030
    },
    {
      "epoch": 2.1063291139240508,
      "grad_norm": 1.2052202862963048,
      "learning_rate": 1.5622775800711745e-06,
      "loss": 0.4024,
      "step": 1040
    },
    {
      "epoch": 2.1265822784810124,
      "grad_norm": 1.1688527474064736,
      "learning_rate": 1.526690391459075e-06,
      "loss": 0.411,
      "step": 1050
    },
    {
      "epoch": 2.1468354430379746,
      "grad_norm": 1.159582820630888,
      "learning_rate": 1.4911032028469751e-06,
      "loss": 0.4056,
      "step": 1060
    },
    {
      "epoch": 2.1670886075949367,
      "grad_norm": 1.1801911147741104,
      "learning_rate": 1.4555160142348756e-06,
      "loss": 0.4079,
      "step": 1070
    },
    {
      "epoch": 2.187341772151899,
      "grad_norm": 1.1866560972006943,
      "learning_rate": 1.419928825622776e-06,
      "loss": 0.4061,
      "step": 1080
    },
    {
      "epoch": 2.207594936708861,
      "grad_norm": 1.1271721136927093,
      "learning_rate": 1.3843416370106764e-06,
      "loss": 0.4035,
      "step": 1090
    },
    {
      "epoch": 2.2278481012658227,
      "grad_norm": 1.148968106587725,
      "learning_rate": 1.3487544483985765e-06,
      "loss": 0.412,
      "step": 1100
    },
    {
      "epoch": 2.248101265822785,
      "grad_norm": 1.17444595906901,
      "learning_rate": 1.313167259786477e-06,
      "loss": 0.4078,
      "step": 1110
    },
    {
      "epoch": 2.268354430379747,
      "grad_norm": 1.241550247309238,
      "learning_rate": 1.2775800711743775e-06,
      "loss": 0.4091,
      "step": 1120
    },
    {
      "epoch": 2.2886075949367086,
      "grad_norm": 1.1322921512574697,
      "learning_rate": 1.2419928825622776e-06,
      "loss": 0.41,
      "step": 1130
    },
    {
      "epoch": 2.3088607594936708,
      "grad_norm": 1.1038688400048324,
      "learning_rate": 1.206405693950178e-06,
      "loss": 0.4052,
      "step": 1140
    },
    {
      "epoch": 2.329113924050633,
      "grad_norm": 1.1471785710291027,
      "learning_rate": 1.1708185053380784e-06,
      "loss": 0.4116,
      "step": 1150
    },
    {
      "epoch": 2.349367088607595,
      "grad_norm": 1.1748513395840992,
      "learning_rate": 1.1352313167259789e-06,
      "loss": 0.4104,
      "step": 1160
    },
    {
      "epoch": 2.369620253164557,
      "grad_norm": 1.1687832541778012,
      "learning_rate": 1.0996441281138791e-06,
      "loss": 0.4103,
      "step": 1170
    },
    {
      "epoch": 2.389873417721519,
      "grad_norm": 1.2153707569716299,
      "learning_rate": 1.0640569395017794e-06,
      "loss": 0.4102,
      "step": 1180
    },
    {
      "epoch": 2.410126582278481,
      "grad_norm": 1.2043915036892876,
      "learning_rate": 1.0284697508896797e-06,
      "loss": 0.4093,
      "step": 1190
    },
    {
      "epoch": 2.430379746835443,
      "grad_norm": 1.1154060559605754,
      "learning_rate": 9.928825622775802e-07,
      "loss": 0.4077,
      "step": 1200
    },
    {
      "epoch": 2.4506329113924052,
      "grad_norm": 1.1249500649551158,
      "learning_rate": 9.572953736654805e-07,
      "loss": 0.4067,
      "step": 1210
    },
    {
      "epoch": 2.470886075949367,
      "grad_norm": 1.1373080270061644,
      "learning_rate": 9.217081850533809e-07,
      "loss": 0.4094,
      "step": 1220
    },
    {
      "epoch": 2.491139240506329,
      "grad_norm": 1.2009940834893456,
      "learning_rate": 8.861209964412812e-07,
      "loss": 0.4081,
      "step": 1230
    },
    {
      "epoch": 2.511392405063291,
      "grad_norm": 1.1805699402158027,
      "learning_rate": 8.505338078291815e-07,
      "loss": 0.412,
      "step": 1240
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 1.1650230538613433,
      "learning_rate": 8.14946619217082e-07,
      "loss": 0.4053,
      "step": 1250
    },
    {
      "epoch": 2.5518987341772155,
      "grad_norm": 1.1148652618881494,
      "learning_rate": 7.793594306049823e-07,
      "loss": 0.4003,
      "step": 1260
    },
    {
      "epoch": 2.572151898734177,
      "grad_norm": 1.1203790714411743,
      "learning_rate": 7.437722419928827e-07,
      "loss": 0.4071,
      "step": 1270
    },
    {
      "epoch": 2.5924050632911393,
      "grad_norm": 1.1540738131106723,
      "learning_rate": 7.08185053380783e-07,
      "loss": 0.4088,
      "step": 1280
    },
    {
      "epoch": 2.6126582278481014,
      "grad_norm": 1.1564560350860578,
      "learning_rate": 6.725978647686833e-07,
      "loss": 0.4136,
      "step": 1290
    },
    {
      "epoch": 2.632911392405063,
      "grad_norm": 1.1502008333731566,
      "learning_rate": 6.370106761565837e-07,
      "loss": 0.4074,
      "step": 1300
    },
    {
      "epoch": 2.6531645569620252,
      "grad_norm": 1.084342294241873,
      "learning_rate": 6.01423487544484e-07,
      "loss": 0.4068,
      "step": 1310
    },
    {
      "epoch": 2.6734177215189874,
      "grad_norm": 1.0975552769986037,
      "learning_rate": 5.658362989323843e-07,
      "loss": 0.408,
      "step": 1320
    },
    {
      "epoch": 2.6936708860759495,
      "grad_norm": 1.1097418341903917,
      "learning_rate": 5.302491103202847e-07,
      "loss": 0.4103,
      "step": 1330
    },
    {
      "epoch": 2.7139240506329116,
      "grad_norm": 1.158009570288043,
      "learning_rate": 4.946619217081851e-07,
      "loss": 0.4086,
      "step": 1340
    },
    {
      "epoch": 2.7341772151898733,
      "grad_norm": 1.082032638132166,
      "learning_rate": 4.5907473309608547e-07,
      "loss": 0.4067,
      "step": 1350
    },
    {
      "epoch": 2.7544303797468355,
      "grad_norm": 1.0910706188001162,
      "learning_rate": 4.234875444839858e-07,
      "loss": 0.4025,
      "step": 1360
    },
    {
      "epoch": 2.7746835443037976,
      "grad_norm": 1.1340308917418294,
      "learning_rate": 3.8790035587188615e-07,
      "loss": 0.4074,
      "step": 1370
    },
    {
      "epoch": 2.7949367088607593,
      "grad_norm": 1.0972217494408671,
      "learning_rate": 3.5231316725978655e-07,
      "loss": 0.4059,
      "step": 1380
    },
    {
      "epoch": 2.8151898734177214,
      "grad_norm": 1.1023421234405986,
      "learning_rate": 3.1672597864768684e-07,
      "loss": 0.408,
      "step": 1390
    },
    {
      "epoch": 2.8354430379746836,
      "grad_norm": 1.076348844263821,
      "learning_rate": 2.811387900355872e-07,
      "loss": 0.4008,
      "step": 1400
    },
    {
      "epoch": 2.8556962025316457,
      "grad_norm": 1.0727773827003273,
      "learning_rate": 2.455516014234876e-07,
      "loss": 0.4095,
      "step": 1410
    },
    {
      "epoch": 2.875949367088608,
      "grad_norm": 1.094488859203195,
      "learning_rate": 2.0996441281138792e-07,
      "loss": 0.4044,
      "step": 1420
    },
    {
      "epoch": 2.8962025316455695,
      "grad_norm": 1.1022638043714281,
      "learning_rate": 1.743772241992883e-07,
      "loss": 0.4053,
      "step": 1430
    },
    {
      "epoch": 2.9164556962025316,
      "grad_norm": 1.056288437679614,
      "learning_rate": 1.3879003558718863e-07,
      "loss": 0.407,
      "step": 1440
    },
    {
      "epoch": 2.9367088607594938,
      "grad_norm": 1.1311358899472859,
      "learning_rate": 1.0320284697508897e-07,
      "loss": 0.4152,
      "step": 1450
    },
    {
      "epoch": 2.9569620253164555,
      "grad_norm": 1.0577864076415648,
      "learning_rate": 6.761565836298933e-08,
      "loss": 0.4032,
      "step": 1460
    },
    {
      "epoch": 2.9772151898734176,
      "grad_norm": 1.0913097767086777,
      "learning_rate": 3.202846975088968e-08,
      "loss": 0.4067,
      "step": 1470
    },
    {
      "epoch": 2.9954430379746837,
      "eval_loss": 0.0700838565826416,
      "eval_runtime": 511.013,
      "eval_samples_per_second": 26.035,
      "eval_steps_per_second": 0.407,
      "step": 1479
    },
    {
      "epoch": 2.9954430379746837,
      "step": 1479,
      "total_flos": 2477170706350080.0,
      "train_loss": 0.4888964453768779,
      "train_runtime": 84815.3932,
      "train_samples_per_second": 8.94,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 1479,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2477170706350080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}