{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22977744928964441,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008212203334154554,
      "grad_norm": 8.587085723876953,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 2.3386,
      "step": 10
    },
    {
      "epoch": 0.0016424406668309108,
      "grad_norm": 4.4222412109375,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 2.1657,
      "step": 20
    },
    {
      "epoch": 0.002463661000246366,
      "grad_norm": 3.2723898887634277,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.8691,
      "step": 30
    },
    {
      "epoch": 0.0032848813336618216,
      "grad_norm": 1.605501413345337,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.4938,
      "step": 40
    },
    {
      "epoch": 0.004106101667077277,
      "grad_norm": 1.1179364919662476,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 1.2218,
      "step": 50
    },
    {
      "epoch": 0.004927322000492732,
      "grad_norm": 1.5302199125289917,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 1.0617,
      "step": 60
    },
    {
      "epoch": 0.005748542333908187,
      "grad_norm": 0.6661491990089417,
      "learning_rate": 7.814044943820226e-06,
      "loss": 1.0192,
      "step": 70
    },
    {
      "epoch": 0.006569762667323643,
      "grad_norm": 0.6883566975593567,
      "learning_rate": 8.932022471910112e-06,
      "loss": 1.0114,
      "step": 80
    },
    {
      "epoch": 0.007390983000739098,
      "grad_norm": 0.762592613697052,
      "learning_rate": 1.005e-05,
      "loss": 0.9338,
      "step": 90
    },
    {
      "epoch": 0.008212203334154554,
      "grad_norm": 0.6071498394012451,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.913,
      "step": 100
    },
    {
      "epoch": 0.009033423667570008,
      "grad_norm": 0.6040300130844116,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.8946,
      "step": 110
    },
    {
      "epoch": 0.009854644000985464,
      "grad_norm": 0.6161038279533386,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.9095,
      "step": 120
    },
    {
      "epoch": 0.01067586433440092,
      "grad_norm": 0.6221404671669006,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.9015,
      "step": 130
    },
    {
      "epoch": 0.011497084667816375,
      "grad_norm": 0.6306547522544861,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.9068,
      "step": 140
    },
    {
      "epoch": 0.01231830500123183,
      "grad_norm": 0.5591278672218323,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.9018,
      "step": 150
    },
    {
      "epoch": 0.013139525334647286,
      "grad_norm": 0.5367937684059143,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.7905,
      "step": 160
    },
    {
      "epoch": 0.01396074566806274,
      "grad_norm": 0.5446851253509521,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.8516,
      "step": 170
    },
    {
      "epoch": 0.014781966001478197,
      "grad_norm": 0.6117768287658691,
      "learning_rate": 2e-05,
      "loss": 0.8769,
      "step": 180
    },
    {
      "epoch": 0.015603186334893653,
      "grad_norm": 0.5499733090400696,
      "learning_rate": 2e-05,
      "loss": 0.8929,
      "step": 190
    },
    {
      "epoch": 0.01642440666830911,
      "grad_norm": 0.5772490501403809,
      "learning_rate": 2e-05,
      "loss": 0.8402,
      "step": 200
    },
    {
      "epoch": 0.017245627001724564,
      "grad_norm": 0.5514219999313354,
      "learning_rate": 2e-05,
      "loss": 0.8938,
      "step": 210
    },
    {
      "epoch": 0.018066847335140017,
      "grad_norm": 0.5629882216453552,
      "learning_rate": 2e-05,
      "loss": 0.8873,
      "step": 220
    },
    {
      "epoch": 0.018888067668555473,
      "grad_norm": 0.5477422475814819,
      "learning_rate": 2e-05,
      "loss": 0.8596,
      "step": 230
    },
    {
      "epoch": 0.01970928800197093,
      "grad_norm": 0.5064891576766968,
      "learning_rate": 2e-05,
      "loss": 0.8442,
      "step": 240
    },
    {
      "epoch": 0.020530508335386385,
      "grad_norm": 1.1094902753829956,
      "learning_rate": 2e-05,
      "loss": 0.8506,
      "step": 250
    },
    {
      "epoch": 0.02135172866880184,
      "grad_norm": 0.5511003732681274,
      "learning_rate": 2e-05,
      "loss": 0.8865,
      "step": 260
    },
    {
      "epoch": 0.022172949002217297,
      "grad_norm": 0.5206192135810852,
      "learning_rate": 2e-05,
      "loss": 0.8665,
      "step": 270
    },
    {
      "epoch": 0.02299416933563275,
      "grad_norm": 0.515914797782898,
      "learning_rate": 2e-05,
      "loss": 0.8456,
      "step": 280
    },
    {
      "epoch": 0.023815389669048205,
      "grad_norm": 0.5267996788024902,
      "learning_rate": 2e-05,
      "loss": 0.8356,
      "step": 290
    },
    {
      "epoch": 0.02463661000246366,
      "grad_norm": 0.5458669066429138,
      "learning_rate": 2e-05,
      "loss": 0.836,
      "step": 300
    },
    {
      "epoch": 0.025457830335879117,
      "grad_norm": 0.525846004486084,
      "learning_rate": 2e-05,
      "loss": 0.814,
      "step": 310
    },
    {
      "epoch": 0.026279050669294573,
      "grad_norm": 0.5086902379989624,
      "learning_rate": 2e-05,
      "loss": 0.8287,
      "step": 320
    },
    {
      "epoch": 0.02710027100271003,
      "grad_norm": 0.4971238374710083,
      "learning_rate": 2e-05,
      "loss": 0.8497,
      "step": 330
    },
    {
      "epoch": 0.02792149133612548,
      "grad_norm": 0.5196722745895386,
      "learning_rate": 2e-05,
      "loss": 0.8592,
      "step": 340
    },
    {
      "epoch": 0.028742711669540937,
      "grad_norm": 0.5308536291122437,
      "learning_rate": 2e-05,
      "loss": 0.8503,
      "step": 350
    },
    {
      "epoch": 0.029563932002956393,
      "grad_norm": 0.516264796257019,
      "learning_rate": 2e-05,
      "loss": 0.8753,
      "step": 360
    },
    {
      "epoch": 0.03038515233637185,
      "grad_norm": 0.5216997861862183,
      "learning_rate": 2e-05,
      "loss": 0.8095,
      "step": 370
    },
    {
      "epoch": 0.031206372669787305,
      "grad_norm": 0.5078901052474976,
      "learning_rate": 2e-05,
      "loss": 0.8461,
      "step": 380
    },
    {
      "epoch": 0.03202759300320276,
      "grad_norm": 0.48943689465522766,
      "learning_rate": 2e-05,
      "loss": 0.8472,
      "step": 390
    },
    {
      "epoch": 0.03284881333661822,
      "grad_norm": 0.4968130886554718,
      "learning_rate": 2e-05,
      "loss": 0.8429,
      "step": 400
    },
    {
      "epoch": 0.03367003367003367,
      "grad_norm": 0.5077145099639893,
      "learning_rate": 2e-05,
      "loss": 0.8115,
      "step": 410
    },
    {
      "epoch": 0.03449125400344913,
      "grad_norm": 0.47043702006340027,
      "learning_rate": 2e-05,
      "loss": 0.8497,
      "step": 420
    },
    {
      "epoch": 0.03531247433686458,
      "grad_norm": 0.8502866625785828,
      "learning_rate": 2e-05,
      "loss": 0.8208,
      "step": 430
    },
    {
      "epoch": 0.036133694670280034,
      "grad_norm": 0.5105547308921814,
      "learning_rate": 2e-05,
      "loss": 0.8235,
      "step": 440
    },
    {
      "epoch": 0.03695491500369549,
      "grad_norm": 0.5259561538696289,
      "learning_rate": 2e-05,
      "loss": 0.8505,
      "step": 450
    },
    {
      "epoch": 0.037776135337110946,
      "grad_norm": 0.5170012712478638,
      "learning_rate": 2e-05,
      "loss": 0.8135,
      "step": 460
    },
    {
      "epoch": 0.038597355670526405,
      "grad_norm": 0.47574323415756226,
      "learning_rate": 2e-05,
      "loss": 0.8399,
      "step": 470
    },
    {
      "epoch": 0.03941857600394186,
      "grad_norm": 0.5556318163871765,
      "learning_rate": 2e-05,
      "loss": 0.7829,
      "step": 480
    },
    {
      "epoch": 0.04023979633735731,
      "grad_norm": 0.521508514881134,
      "learning_rate": 2e-05,
      "loss": 0.8201,
      "step": 490
    },
    {
      "epoch": 0.04106101667077277,
      "grad_norm": 0.5001388788223267,
      "learning_rate": 2e-05,
      "loss": 0.8267,
      "step": 500
    },
    {
      "epoch": 0.04188223700418822,
      "grad_norm": 0.4890121817588806,
      "learning_rate": 2e-05,
      "loss": 0.8037,
      "step": 510
    },
    {
      "epoch": 0.04270345733760368,
      "grad_norm": 0.5156166553497314,
      "learning_rate": 2e-05,
      "loss": 0.816,
      "step": 520
    },
    {
      "epoch": 0.043524677671019134,
      "grad_norm": 0.5050928592681885,
      "learning_rate": 2e-05,
      "loss": 0.847,
      "step": 530
    },
    {
      "epoch": 0.04434589800443459,
      "grad_norm": 0.4809299111366272,
      "learning_rate": 2e-05,
      "loss": 0.8349,
      "step": 540
    },
    {
      "epoch": 0.045167118337850046,
      "grad_norm": 0.4897677004337311,
      "learning_rate": 2e-05,
      "loss": 0.8261,
      "step": 550
    },
    {
      "epoch": 0.0459883386712655,
      "grad_norm": 0.4984337389469147,
      "learning_rate": 2e-05,
      "loss": 0.8612,
      "step": 560
    },
    {
      "epoch": 0.04680955900468096,
      "grad_norm": 0.5070453882217407,
      "learning_rate": 2e-05,
      "loss": 0.8536,
      "step": 570
    },
    {
      "epoch": 0.04763077933809641,
      "grad_norm": 0.45646464824676514,
      "learning_rate": 2e-05,
      "loss": 0.8381,
      "step": 580
    },
    {
      "epoch": 0.04845199967151187,
      "grad_norm": 0.4721323549747467,
      "learning_rate": 2e-05,
      "loss": 0.8201,
      "step": 590
    },
    {
      "epoch": 0.04927322000492732,
      "grad_norm": 0.4687247574329376,
      "learning_rate": 2e-05,
      "loss": 0.8288,
      "step": 600
    },
    {
      "epoch": 0.050094440338342774,
      "grad_norm": 0.4447396993637085,
      "learning_rate": 2e-05,
      "loss": 0.8308,
      "step": 610
    },
    {
      "epoch": 0.050915660671758234,
      "grad_norm": 0.49292364716529846,
      "learning_rate": 2e-05,
      "loss": 0.8139,
      "step": 620
    },
    {
      "epoch": 0.051736881005173686,
      "grad_norm": 0.46408599615097046,
      "learning_rate": 2e-05,
      "loss": 0.8092,
      "step": 630
    },
    {
      "epoch": 0.052558101338589146,
      "grad_norm": 0.5292156338691711,
      "learning_rate": 2e-05,
      "loss": 0.8603,
      "step": 640
    },
    {
      "epoch": 0.0533793216720046,
      "grad_norm": 0.46266090869903564,
      "learning_rate": 2e-05,
      "loss": 0.8071,
      "step": 650
    },
    {
      "epoch": 0.05420054200542006,
      "grad_norm": 0.5302640795707703,
      "learning_rate": 2e-05,
      "loss": 0.8231,
      "step": 660
    },
    {
      "epoch": 0.05502176233883551,
      "grad_norm": 0.4566280245780945,
      "learning_rate": 2e-05,
      "loss": 0.8006,
      "step": 670
    },
    {
      "epoch": 0.05584298267225096,
      "grad_norm": 0.4889671206474304,
      "learning_rate": 2e-05,
      "loss": 0.8209,
      "step": 680
    },
    {
      "epoch": 0.05666420300566642,
      "grad_norm": 0.4641304910182953,
      "learning_rate": 2e-05,
      "loss": 0.8092,
      "step": 690
    },
    {
      "epoch": 0.057485423339081874,
      "grad_norm": 0.4148608446121216,
      "learning_rate": 2e-05,
      "loss": 0.8292,
      "step": 700
    },
    {
      "epoch": 0.058306643672497334,
      "grad_norm": 0.4525546133518219,
      "learning_rate": 2e-05,
      "loss": 0.823,
      "step": 710
    },
    {
      "epoch": 0.059127864005912786,
      "grad_norm": 0.45530539751052856,
      "learning_rate": 2e-05,
      "loss": 0.8285,
      "step": 720
    },
    {
      "epoch": 0.05994908433932824,
      "grad_norm": 0.46801939606666565,
      "learning_rate": 2e-05,
      "loss": 0.8136,
      "step": 730
    },
    {
      "epoch": 0.0607703046727437,
      "grad_norm": 0.47091159224510193,
      "learning_rate": 2e-05,
      "loss": 0.8148,
      "step": 740
    },
    {
      "epoch": 0.06159152500615915,
      "grad_norm": 0.4805493652820587,
      "learning_rate": 2e-05,
      "loss": 0.7893,
      "step": 750
    },
    {
      "epoch": 0.06241274533957461,
      "grad_norm": 0.46650201082229614,
      "learning_rate": 2e-05,
      "loss": 0.7947,
      "step": 760
    },
    {
      "epoch": 0.06323396567299007,
      "grad_norm": 0.4958495497703552,
      "learning_rate": 2e-05,
      "loss": 0.8035,
      "step": 770
    },
    {
      "epoch": 0.06405518600640552,
      "grad_norm": 0.45363372564315796,
      "learning_rate": 2e-05,
      "loss": 0.8113,
      "step": 780
    },
    {
      "epoch": 0.06487640633982097,
      "grad_norm": 0.5573371648788452,
      "learning_rate": 2e-05,
      "loss": 0.8294,
      "step": 790
    },
    {
      "epoch": 0.06569762667323643,
      "grad_norm": 0.463094025850296,
      "learning_rate": 2e-05,
      "loss": 0.8263,
      "step": 800
    },
    {
      "epoch": 0.06651884700665188,
      "grad_norm": 0.44852298498153687,
      "learning_rate": 2e-05,
      "loss": 0.8288,
      "step": 810
    },
    {
      "epoch": 0.06734006734006734,
      "grad_norm": 0.4633004367351532,
      "learning_rate": 2e-05,
      "loss": 0.8031,
      "step": 820
    },
    {
      "epoch": 0.0681612876734828,
      "grad_norm": 0.5351435542106628,
      "learning_rate": 2e-05,
      "loss": 0.7989,
      "step": 830
    },
    {
      "epoch": 0.06898250800689826,
      "grad_norm": 0.44983765482902527,
      "learning_rate": 2e-05,
      "loss": 0.7741,
      "step": 840
    },
    {
      "epoch": 0.0698037283403137,
      "grad_norm": 0.46665406227111816,
      "learning_rate": 2e-05,
      "loss": 0.8371,
      "step": 850
    },
    {
      "epoch": 0.07062494867372916,
      "grad_norm": 0.4422172009944916,
      "learning_rate": 2e-05,
      "loss": 0.8323,
      "step": 860
    },
    {
      "epoch": 0.07144616900714462,
      "grad_norm": 0.4459817111492157,
      "learning_rate": 2e-05,
      "loss": 0.7696,
      "step": 870
    },
    {
      "epoch": 0.07226738934056007,
      "grad_norm": 0.45233848690986633,
      "learning_rate": 2e-05,
      "loss": 0.7935,
      "step": 880
    },
    {
      "epoch": 0.07308860967397553,
      "grad_norm": 0.4778662919998169,
      "learning_rate": 2e-05,
      "loss": 0.8028,
      "step": 890
    },
    {
      "epoch": 0.07390983000739099,
      "grad_norm": 0.478687584400177,
      "learning_rate": 2e-05,
      "loss": 0.7836,
      "step": 900
    },
    {
      "epoch": 0.07473105034080643,
      "grad_norm": 0.45005080103874207,
      "learning_rate": 2e-05,
      "loss": 0.8078,
      "step": 910
    },
    {
      "epoch": 0.07555227067422189,
      "grad_norm": 0.461701363325119,
      "learning_rate": 2e-05,
      "loss": 0.7897,
      "step": 920
    },
    {
      "epoch": 0.07637349100763735,
      "grad_norm": 0.4510675072669983,
      "learning_rate": 2e-05,
      "loss": 0.8079,
      "step": 930
    },
    {
      "epoch": 0.07719471134105281,
      "grad_norm": 0.44589269161224365,
      "learning_rate": 2e-05,
      "loss": 0.8069,
      "step": 940
    },
    {
      "epoch": 0.07801593167446826,
      "grad_norm": 0.44631075859069824,
      "learning_rate": 2e-05,
      "loss": 0.7879,
      "step": 950
    },
    {
      "epoch": 0.07883715200788372,
      "grad_norm": 0.4562603533267975,
      "learning_rate": 2e-05,
      "loss": 0.7897,
      "step": 960
    },
    {
      "epoch": 0.07965837234129917,
      "grad_norm": 0.4626533091068268,
      "learning_rate": 2e-05,
      "loss": 0.8222,
      "step": 970
    },
    {
      "epoch": 0.08047959267471462,
      "grad_norm": 0.4357568919658661,
      "learning_rate": 2e-05,
      "loss": 0.7865,
      "step": 980
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 0.47860822081565857,
      "learning_rate": 2e-05,
      "loss": 0.8178,
      "step": 990
    },
    {
      "epoch": 0.08212203334154554,
      "grad_norm": 0.450439453125,
      "learning_rate": 2e-05,
      "loss": 0.799,
      "step": 1000
    },
    {
      "epoch": 0.082943253674961,
      "grad_norm": 0.44870707392692566,
      "learning_rate": 2e-05,
      "loss": 0.7867,
      "step": 1010
    },
    {
      "epoch": 0.08376447400837644,
      "grad_norm": 0.425043523311615,
      "learning_rate": 2e-05,
      "loss": 0.7827,
      "step": 1020
    },
    {
      "epoch": 0.0845856943417919,
      "grad_norm": 0.44783613085746765,
      "learning_rate": 2e-05,
      "loss": 0.7968,
      "step": 1030
    },
    {
      "epoch": 0.08540691467520736,
      "grad_norm": 0.44678232073783875,
      "learning_rate": 2e-05,
      "loss": 0.7987,
      "step": 1040
    },
    {
      "epoch": 0.08622813500862281,
      "grad_norm": 0.43474194407463074,
      "learning_rate": 2e-05,
      "loss": 0.8344,
      "step": 1050
    },
    {
      "epoch": 0.08704935534203827,
      "grad_norm": 0.4671313762664795,
      "learning_rate": 2e-05,
      "loss": 0.8042,
      "step": 1060
    },
    {
      "epoch": 0.08787057567545373,
      "grad_norm": 0.4562723934650421,
      "learning_rate": 2e-05,
      "loss": 0.7735,
      "step": 1070
    },
    {
      "epoch": 0.08869179600886919,
      "grad_norm": 0.42270052433013916,
      "learning_rate": 2e-05,
      "loss": 0.8089,
      "step": 1080
    },
    {
      "epoch": 0.08951301634228463,
      "grad_norm": 0.48901864886283875,
      "learning_rate": 2e-05,
      "loss": 0.8132,
      "step": 1090
    },
    {
      "epoch": 0.09033423667570009,
      "grad_norm": 0.45863649249076843,
      "learning_rate": 2e-05,
      "loss": 0.8134,
      "step": 1100
    },
    {
      "epoch": 0.09115545700911555,
      "grad_norm": 0.4497729539871216,
      "learning_rate": 2e-05,
      "loss": 0.8279,
      "step": 1110
    },
    {
      "epoch": 0.091976677342531,
      "grad_norm": 0.44030267000198364,
      "learning_rate": 2e-05,
      "loss": 0.7768,
      "step": 1120
    },
    {
      "epoch": 0.09279789767594646,
      "grad_norm": 0.46033450961112976,
      "learning_rate": 2e-05,
      "loss": 0.7889,
      "step": 1130
    },
    {
      "epoch": 0.09361911800936192,
      "grad_norm": 0.4357089102268219,
      "learning_rate": 2e-05,
      "loss": 0.7675,
      "step": 1140
    },
    {
      "epoch": 0.09444033834277736,
      "grad_norm": 0.43551215529441833,
      "learning_rate": 2e-05,
      "loss": 0.7472,
      "step": 1150
    },
    {
      "epoch": 0.09526155867619282,
      "grad_norm": 0.4561745822429657,
      "learning_rate": 2e-05,
      "loss": 0.8058,
      "step": 1160
    },
    {
      "epoch": 0.09608277900960828,
      "grad_norm": 0.43203088641166687,
      "learning_rate": 2e-05,
      "loss": 0.8083,
      "step": 1170
    },
    {
      "epoch": 0.09690399934302374,
      "grad_norm": 0.4373405873775482,
      "learning_rate": 2e-05,
      "loss": 0.7751,
      "step": 1180
    },
    {
      "epoch": 0.09772521967643918,
      "grad_norm": 0.4452410936355591,
      "learning_rate": 2e-05,
      "loss": 0.7902,
      "step": 1190
    },
    {
      "epoch": 0.09854644000985464,
      "grad_norm": 0.43690672516822815,
      "learning_rate": 2e-05,
      "loss": 0.7861,
      "step": 1200
    },
    {
      "epoch": 0.0993676603432701,
      "grad_norm": 0.4637196958065033,
      "learning_rate": 2e-05,
      "loss": 0.8077,
      "step": 1210
    },
    {
      "epoch": 0.10018888067668555,
      "grad_norm": 0.45546796917915344,
      "learning_rate": 2e-05,
      "loss": 0.767,
      "step": 1220
    },
    {
      "epoch": 0.10101010101010101,
      "grad_norm": 0.461551308631897,
      "learning_rate": 2e-05,
      "loss": 0.7884,
      "step": 1230
    },
    {
      "epoch": 0.10183132134351647,
      "grad_norm": 0.4352053999900818,
      "learning_rate": 2e-05,
      "loss": 0.8028,
      "step": 1240
    },
    {
      "epoch": 0.10265254167693193,
      "grad_norm": 0.44627439975738525,
      "learning_rate": 2e-05,
      "loss": 0.815,
      "step": 1250
    },
    {
      "epoch": 0.10347376201034737,
      "grad_norm": 0.4140150547027588,
      "learning_rate": 2e-05,
      "loss": 0.7819,
      "step": 1260
    },
    {
      "epoch": 0.10429498234376283,
      "grad_norm": 0.4781087040901184,
      "learning_rate": 2e-05,
      "loss": 0.7974,
      "step": 1270
    },
    {
      "epoch": 0.10511620267717829,
      "grad_norm": 0.4421789348125458,
      "learning_rate": 2e-05,
      "loss": 0.7632,
      "step": 1280
    },
    {
      "epoch": 0.10593742301059374,
      "grad_norm": 0.44503435492515564,
      "learning_rate": 2e-05,
      "loss": 0.7974,
      "step": 1290
    },
    {
      "epoch": 0.1067586433440092,
      "grad_norm": 0.4360303282737732,
      "learning_rate": 2e-05,
      "loss": 0.7789,
      "step": 1300
    },
    {
      "epoch": 0.10757986367742466,
      "grad_norm": 0.4185614585876465,
      "learning_rate": 2e-05,
      "loss": 0.7962,
      "step": 1310
    },
    {
      "epoch": 0.10840108401084012,
      "grad_norm": 0.46108296513557434,
      "learning_rate": 2e-05,
      "loss": 0.7752,
      "step": 1320
    },
    {
      "epoch": 0.10922230434425556,
      "grad_norm": 0.46323254704475403,
      "learning_rate": 2e-05,
      "loss": 0.8015,
      "step": 1330
    },
    {
      "epoch": 0.11004352467767102,
      "grad_norm": 0.441444456577301,
      "learning_rate": 2e-05,
      "loss": 0.7934,
      "step": 1340
    },
    {
      "epoch": 0.11086474501108648,
      "grad_norm": 0.42753297090530396,
      "learning_rate": 2e-05,
      "loss": 0.7869,
      "step": 1350
    },
    {
      "epoch": 0.11168596534450193,
      "grad_norm": 0.5354635715484619,
      "learning_rate": 2e-05,
      "loss": 0.7668,
      "step": 1360
    },
    {
      "epoch": 0.11250718567791738,
      "grad_norm": 0.4485228657722473,
      "learning_rate": 2e-05,
      "loss": 0.7916,
      "step": 1370
    },
    {
      "epoch": 0.11332840601133284,
      "grad_norm": 0.4402100145816803,
      "learning_rate": 2e-05,
      "loss": 0.7785,
      "step": 1380
    },
    {
      "epoch": 0.11414962634474829,
      "grad_norm": 0.44067618250846863,
      "learning_rate": 2e-05,
      "loss": 0.796,
      "step": 1390
    },
    {
      "epoch": 0.11497084667816375,
      "grad_norm": 0.41861099004745483,
      "learning_rate": 2e-05,
      "loss": 0.7896,
      "step": 1400
    },
    {
      "epoch": 0.11579206701157921,
      "grad_norm": 0.427713006734848,
      "learning_rate": 2e-05,
      "loss": 0.7876,
      "step": 1410
    },
    {
      "epoch": 0.11661328734499467,
      "grad_norm": 0.5142576098442078,
      "learning_rate": 2e-05,
      "loss": 0.7832,
      "step": 1420
    },
    {
      "epoch": 0.11743450767841011,
      "grad_norm": 0.4011819660663605,
      "learning_rate": 2e-05,
      "loss": 0.7894,
      "step": 1430
    },
    {
      "epoch": 0.11825572801182557,
      "grad_norm": 0.4302540421485901,
      "learning_rate": 2e-05,
      "loss": 0.7805,
      "step": 1440
    },
    {
      "epoch": 0.11907694834524103,
      "grad_norm": 0.4870634973049164,
      "learning_rate": 2e-05,
      "loss": 0.7596,
      "step": 1450
    },
    {
      "epoch": 0.11989816867865648,
      "grad_norm": 0.4451192021369934,
      "learning_rate": 2e-05,
      "loss": 0.7769,
      "step": 1460
    },
    {
      "epoch": 0.12071938901207194,
      "grad_norm": 0.42198508977890015,
      "learning_rate": 2e-05,
      "loss": 0.7746,
      "step": 1470
    },
    {
      "epoch": 0.1215406093454874,
      "grad_norm": 0.4552297294139862,
      "learning_rate": 2e-05,
      "loss": 0.8001,
      "step": 1480
    },
    {
      "epoch": 0.12236182967890286,
      "grad_norm": 0.44329190254211426,
      "learning_rate": 2e-05,
      "loss": 0.7702,
      "step": 1490
    },
    {
      "epoch": 0.1231830500123183,
      "grad_norm": 0.44024938344955444,
      "learning_rate": 2e-05,
      "loss": 0.7976,
      "step": 1500
    },
    {
      "epoch": 0.12400427034573376,
      "grad_norm": 0.4466274082660675,
      "learning_rate": 2e-05,
      "loss": 0.8065,
      "step": 1510
    },
    {
      "epoch": 0.12482549067914922,
      "grad_norm": 0.4443671703338623,
      "learning_rate": 2e-05,
      "loss": 0.7734,
      "step": 1520
    },
    {
      "epoch": 0.12564671101256467,
      "grad_norm": 0.4458763301372528,
      "learning_rate": 2e-05,
      "loss": 0.7849,
      "step": 1530
    },
    {
      "epoch": 0.12646793134598014,
      "grad_norm": 0.4324412941932678,
      "learning_rate": 2e-05,
      "loss": 0.8091,
      "step": 1540
    },
    {
      "epoch": 0.12728915167939558,
      "grad_norm": 0.474600613117218,
      "learning_rate": 2e-05,
      "loss": 0.7841,
      "step": 1550
    },
    {
      "epoch": 0.12811037201281103,
      "grad_norm": 0.42612481117248535,
      "learning_rate": 2e-05,
      "loss": 0.779,
      "step": 1560
    },
    {
      "epoch": 0.1289315923462265,
      "grad_norm": 0.41486653685569763,
      "learning_rate": 2e-05,
      "loss": 0.7862,
      "step": 1570
    },
    {
      "epoch": 0.12975281267964195,
      "grad_norm": 0.4324989318847656,
      "learning_rate": 2e-05,
      "loss": 0.7953,
      "step": 1580
    },
    {
      "epoch": 0.1305740330130574,
      "grad_norm": 0.4577152729034424,
      "learning_rate": 2e-05,
      "loss": 0.7666,
      "step": 1590
    },
    {
      "epoch": 0.13139525334647287,
      "grad_norm": 0.44246548414230347,
      "learning_rate": 2e-05,
      "loss": 0.7608,
      "step": 1600
    },
    {
      "epoch": 0.1322164736798883,
      "grad_norm": 0.4186859130859375,
      "learning_rate": 2e-05,
      "loss": 0.7604,
      "step": 1610
    },
    {
      "epoch": 0.13303769401330376,
      "grad_norm": 0.42295071482658386,
      "learning_rate": 2e-05,
      "loss": 0.7466,
      "step": 1620
    },
    {
      "epoch": 0.13385891434671923,
      "grad_norm": 0.425224632024765,
      "learning_rate": 2e-05,
      "loss": 0.7704,
      "step": 1630
    },
    {
      "epoch": 0.13468013468013468,
      "grad_norm": 0.4620305895805359,
      "learning_rate": 2e-05,
      "loss": 0.7699,
      "step": 1640
    },
    {
      "epoch": 0.13550135501355012,
      "grad_norm": 0.4204477369785309,
      "learning_rate": 2e-05,
      "loss": 0.8106,
      "step": 1650
    },
    {
      "epoch": 0.1363225753469656,
      "grad_norm": 0.41886085271835327,
      "learning_rate": 2e-05,
      "loss": 0.7764,
      "step": 1660
    },
    {
      "epoch": 0.13714379568038104,
      "grad_norm": 0.45777595043182373,
      "learning_rate": 2e-05,
      "loss": 0.7689,
      "step": 1670
    },
    {
      "epoch": 0.13796501601379652,
      "grad_norm": 0.41233789920806885,
      "learning_rate": 2e-05,
      "loss": 0.7701,
      "step": 1680
    },
    {
      "epoch": 0.13878623634721196,
      "grad_norm": 0.44005653262138367,
      "learning_rate": 2e-05,
      "loss": 0.7717,
      "step": 1690
    },
    {
      "epoch": 0.1396074566806274,
      "grad_norm": 0.47396785020828247,
      "learning_rate": 2e-05,
      "loss": 0.7398,
      "step": 1700
    },
    {
      "epoch": 0.14042867701404288,
      "grad_norm": 0.43871358036994934,
      "learning_rate": 2e-05,
      "loss": 0.7747,
      "step": 1710
    },
    {
      "epoch": 0.14124989734745833,
      "grad_norm": 0.421408474445343,
      "learning_rate": 2e-05,
      "loss": 0.7905,
      "step": 1720
    },
    {
      "epoch": 0.14207111768087377,
      "grad_norm": 0.43005624413490295,
      "learning_rate": 2e-05,
      "loss": 0.7609,
      "step": 1730
    },
    {
      "epoch": 0.14289233801428924,
      "grad_norm": 0.4219532012939453,
      "learning_rate": 2e-05,
      "loss": 0.7609,
      "step": 1740
    },
    {
      "epoch": 0.1437135583477047,
      "grad_norm": 0.4508216083049774,
      "learning_rate": 2e-05,
      "loss": 0.6405,
      "step": 1750
    },
    {
      "epoch": 0.14453477868112014,
      "grad_norm": 0.4121701121330261,
      "learning_rate": 2e-05,
      "loss": 0.7763,
      "step": 1760
    },
    {
      "epoch": 0.1453559990145356,
      "grad_norm": 0.4090173542499542,
      "learning_rate": 2e-05,
      "loss": 0.7645,
      "step": 1770
    },
    {
      "epoch": 0.14617721934795105,
      "grad_norm": 0.43645748496055603,
      "learning_rate": 2e-05,
      "loss": 0.8122,
      "step": 1780
    },
    {
      "epoch": 0.1469984396813665,
      "grad_norm": 1.1069415807724,
      "learning_rate": 2e-05,
      "loss": 0.767,
      "step": 1790
    },
    {
      "epoch": 0.14781966001478197,
      "grad_norm": 0.4456346035003662,
      "learning_rate": 2e-05,
      "loss": 0.7763,
      "step": 1800
    },
    {
      "epoch": 0.14864088034819742,
      "grad_norm": 0.42877396941185,
      "learning_rate": 2e-05,
      "loss": 0.7624,
      "step": 1810
    },
    {
      "epoch": 0.14946210068161286,
      "grad_norm": 0.4232544004917145,
      "learning_rate": 2e-05,
      "loss": 0.7606,
      "step": 1820
    },
    {
      "epoch": 0.15028332101502834,
      "grad_norm": 0.421718031167984,
      "learning_rate": 2e-05,
      "loss": 0.7834,
      "step": 1830
    },
    {
      "epoch": 0.15110454134844378,
      "grad_norm": 0.44949644804000854,
      "learning_rate": 2e-05,
      "loss": 0.778,
      "step": 1840
    },
    {
      "epoch": 0.15192576168185926,
      "grad_norm": 0.430152028799057,
      "learning_rate": 2e-05,
      "loss": 0.74,
      "step": 1850
    },
    {
      "epoch": 0.1527469820152747,
      "grad_norm": 0.48783883452415466,
      "learning_rate": 2e-05,
      "loss": 0.768,
      "step": 1860
    },
    {
      "epoch": 0.15356820234869015,
      "grad_norm": 0.405388206243515,
      "learning_rate": 2e-05,
      "loss": 0.7677,
      "step": 1870
    },
    {
      "epoch": 0.15438942268210562,
      "grad_norm": 0.4099145531654358,
      "learning_rate": 2e-05,
      "loss": 0.7448,
      "step": 1880
    },
    {
      "epoch": 0.15521064301552107,
      "grad_norm": 0.4216562509536743,
      "learning_rate": 2e-05,
      "loss": 0.7771,
      "step": 1890
    },
    {
      "epoch": 0.1560318633489365,
      "grad_norm": 0.42413970828056335,
      "learning_rate": 2e-05,
      "loss": 0.7534,
      "step": 1900
    },
    {
      "epoch": 0.15685308368235198,
      "grad_norm": 0.43225663900375366,
      "learning_rate": 2e-05,
      "loss": 0.7739,
      "step": 1910
    },
    {
      "epoch": 0.15767430401576743,
      "grad_norm": 0.4282965362071991,
      "learning_rate": 2e-05,
      "loss": 0.7698,
      "step": 1920
    },
    {
      "epoch": 0.15849552434918288,
      "grad_norm": 0.49937933683395386,
      "learning_rate": 2e-05,
      "loss": 0.7814,
      "step": 1930
    },
    {
      "epoch": 0.15931674468259835,
      "grad_norm": 0.4623638093471527,
      "learning_rate": 2e-05,
      "loss": 0.7455,
      "step": 1940
    },
    {
      "epoch": 0.1601379650160138,
      "grad_norm": 0.40429919958114624,
      "learning_rate": 2e-05,
      "loss": 0.7624,
      "step": 1950
    },
    {
      "epoch": 0.16095918534942924,
      "grad_norm": 0.4180993139743805,
      "learning_rate": 2e-05,
      "loss": 0.812,
      "step": 1960
    },
    {
      "epoch": 0.1617804056828447,
      "grad_norm": 0.4380674362182617,
      "learning_rate": 2e-05,
      "loss": 0.7812,
      "step": 1970
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.4467218518257141,
      "learning_rate": 2e-05,
      "loss": 0.777,
      "step": 1980
    },
    {
      "epoch": 0.1634228463496756,
      "grad_norm": 0.6018455624580383,
      "learning_rate": 2e-05,
      "loss": 0.8078,
      "step": 1990
    },
    {
      "epoch": 0.16424406668309108,
      "grad_norm": 0.42848190665245056,
      "learning_rate": 2e-05,
      "loss": 0.7712,
      "step": 2000
    },
    {
      "epoch": 0.16506528701650652,
      "grad_norm": 0.434704065322876,
      "learning_rate": 2e-05,
      "loss": 0.7626,
      "step": 2010
    },
    {
      "epoch": 0.165886507349922,
      "grad_norm": 0.4402262270450592,
      "learning_rate": 2e-05,
      "loss": 0.7705,
      "step": 2020
    },
    {
      "epoch": 0.16670772768333744,
      "grad_norm": 0.42635026574134827,
      "learning_rate": 2e-05,
      "loss": 0.7682,
      "step": 2030
    },
    {
      "epoch": 0.1675289480167529,
      "grad_norm": 0.4290219843387604,
      "learning_rate": 2e-05,
      "loss": 0.7966,
      "step": 2040
    },
    {
      "epoch": 0.16835016835016836,
      "grad_norm": 0.4775022268295288,
      "learning_rate": 2e-05,
      "loss": 0.7724,
      "step": 2050
    },
    {
      "epoch": 0.1691713886835838,
      "grad_norm": 0.43119269609451294,
      "learning_rate": 2e-05,
      "loss": 0.7801,
      "step": 2060
    },
    {
      "epoch": 0.16999260901699925,
      "grad_norm": 0.5889827013015747,
      "learning_rate": 2e-05,
      "loss": 0.8041,
      "step": 2070
    },
    {
      "epoch": 0.17081382935041473,
      "grad_norm": 0.4321953356266022,
      "learning_rate": 2e-05,
      "loss": 0.8019,
      "step": 2080
    },
    {
      "epoch": 0.17163504968383017,
      "grad_norm": 0.428431898355484,
      "learning_rate": 2e-05,
      "loss": 0.7751,
      "step": 2090
    },
    {
      "epoch": 0.17245627001724562,
      "grad_norm": 0.402853399515152,
      "learning_rate": 2e-05,
      "loss": 0.7717,
      "step": 2100
    },
    {
      "epoch": 0.1732774903506611,
      "grad_norm": 0.4419548511505127,
      "learning_rate": 2e-05,
      "loss": 0.7806,
      "step": 2110
    },
    {
      "epoch": 0.17409871068407654,
      "grad_norm": 0.44852688908576965,
      "learning_rate": 2e-05,
      "loss": 0.7935,
      "step": 2120
    },
    {
      "epoch": 0.17491993101749198,
      "grad_norm": 0.4230371415615082,
      "learning_rate": 2e-05,
      "loss": 0.7914,
      "step": 2130
    },
    {
      "epoch": 0.17574115135090745,
      "grad_norm": 0.3861851394176483,
      "learning_rate": 2e-05,
      "loss": 0.7233,
      "step": 2140
    },
    {
      "epoch": 0.1765623716843229,
      "grad_norm": 0.41707614064216614,
      "learning_rate": 2e-05,
      "loss": 0.7569,
      "step": 2150
    },
    {
      "epoch": 0.17738359201773837,
      "grad_norm": 0.4453151226043701,
      "learning_rate": 2e-05,
      "loss": 0.758,
      "step": 2160
    },
    {
      "epoch": 0.17820481235115382,
      "grad_norm": 0.433058500289917,
      "learning_rate": 2e-05,
      "loss": 0.8025,
      "step": 2170
    },
    {
      "epoch": 0.17902603268456926,
      "grad_norm": 0.5075773596763611,
      "learning_rate": 2e-05,
      "loss": 0.7356,
      "step": 2180
    },
    {
      "epoch": 0.17984725301798474,
      "grad_norm": 0.4086076617240906,
      "learning_rate": 2e-05,
      "loss": 0.7379,
      "step": 2190
    },
    {
      "epoch": 0.18066847335140018,
      "grad_norm": 0.4531570076942444,
      "learning_rate": 2e-05,
      "loss": 0.7911,
      "step": 2200
    },
    {
      "epoch": 0.18148969368481563,
      "grad_norm": 0.41858381032943726,
      "learning_rate": 2e-05,
      "loss": 0.7672,
      "step": 2210
    },
    {
      "epoch": 0.1823109140182311,
      "grad_norm": 0.4220307767391205,
      "learning_rate": 2e-05,
      "loss": 0.7534,
      "step": 2220
    },
    {
      "epoch": 0.18313213435164655,
      "grad_norm": 0.4243931472301483,
      "learning_rate": 2e-05,
      "loss": 0.7547,
      "step": 2230
    },
    {
      "epoch": 0.183953354685062,
      "grad_norm": 0.4126180410385132,
      "learning_rate": 2e-05,
      "loss": 0.7489,
      "step": 2240
    },
    {
      "epoch": 0.18477457501847747,
      "grad_norm": 0.42353975772857666,
      "learning_rate": 2e-05,
      "loss": 0.7961,
      "step": 2250
    },
    {
      "epoch": 0.1855957953518929,
      "grad_norm": 0.4082265794277191,
      "learning_rate": 2e-05,
      "loss": 0.757,
      "step": 2260
    },
    {
      "epoch": 0.18641701568530836,
      "grad_norm": 0.407305508852005,
      "learning_rate": 2e-05,
      "loss": 0.7543,
      "step": 2270
    },
    {
      "epoch": 0.18723823601872383,
      "grad_norm": 0.42294174432754517,
      "learning_rate": 2e-05,
      "loss": 0.7583,
      "step": 2280
    },
    {
      "epoch": 0.18805945635213928,
      "grad_norm": 0.39620959758758545,
      "learning_rate": 2e-05,
      "loss": 0.7566,
      "step": 2290
    },
    {
      "epoch": 0.18888067668555472,
      "grad_norm": 0.4146956205368042,
      "learning_rate": 2e-05,
      "loss": 0.7802,
      "step": 2300
    },
    {
      "epoch": 0.1897018970189702,
      "grad_norm": 0.43170496821403503,
      "learning_rate": 2e-05,
      "loss": 0.7559,
      "step": 2310
    },
    {
      "epoch": 0.19052311735238564,
      "grad_norm": 0.4103269577026367,
      "learning_rate": 2e-05,
      "loss": 0.7575,
      "step": 2320
    },
    {
      "epoch": 0.1913443376858011,
      "grad_norm": 0.39337730407714844,
      "learning_rate": 2e-05,
      "loss": 0.7466,
      "step": 2330
    },
    {
      "epoch": 0.19216555801921656,
      "grad_norm": 0.4346054196357727,
      "learning_rate": 2e-05,
      "loss": 0.7906,
      "step": 2340
    },
    {
      "epoch": 0.192986778352632,
      "grad_norm": 0.42356476187705994,
      "learning_rate": 2e-05,
      "loss": 0.7628,
      "step": 2350
    },
    {
      "epoch": 0.19380799868604748,
      "grad_norm": 0.377941370010376,
      "learning_rate": 2e-05,
      "loss": 0.7514,
      "step": 2360
    },
    {
      "epoch": 0.19462921901946292,
      "grad_norm": 0.4733028709888458,
      "learning_rate": 2e-05,
      "loss": 0.7463,
      "step": 2370
    },
    {
      "epoch": 0.19545043935287837,
      "grad_norm": 0.4126057028770447,
      "learning_rate": 2e-05,
      "loss": 0.7892,
      "step": 2380
    },
    {
      "epoch": 0.19627165968629384,
      "grad_norm": 0.4060257375240326,
      "learning_rate": 2e-05,
      "loss": 0.7651,
      "step": 2390
    },
    {
      "epoch": 0.1970928800197093,
      "grad_norm": 0.41388368606567383,
      "learning_rate": 2e-05,
      "loss": 0.7562,
      "step": 2400
    },
    {
      "epoch": 0.19791410035312473,
      "grad_norm": 0.42862391471862793,
      "learning_rate": 2e-05,
      "loss": 0.7811,
      "step": 2410
    },
    {
      "epoch": 0.1987353206865402,
      "grad_norm": 0.4284455180168152,
      "learning_rate": 2e-05,
      "loss": 0.7721,
      "step": 2420
    },
    {
      "epoch": 0.19955654101995565,
      "grad_norm": 0.4654240310192108,
      "learning_rate": 2e-05,
      "loss": 0.7944,
      "step": 2430
    },
    {
      "epoch": 0.2003777613533711,
      "grad_norm": 0.38943159580230713,
      "learning_rate": 2e-05,
      "loss": 0.7601,
      "step": 2440
    },
    {
      "epoch": 0.20119898168678657,
      "grad_norm": 0.40954166650772095,
      "learning_rate": 2e-05,
      "loss": 0.7495,
      "step": 2450
    },
    {
      "epoch": 0.20202020202020202,
      "grad_norm": 0.3856504261493683,
      "learning_rate": 2e-05,
      "loss": 0.7451,
      "step": 2460
    },
    {
      "epoch": 0.20284142235361746,
      "grad_norm": 0.39670035243034363,
      "learning_rate": 2e-05,
      "loss": 0.7394,
      "step": 2470
    },
    {
      "epoch": 0.20366264268703294,
      "grad_norm": 0.39305543899536133,
      "learning_rate": 2e-05,
      "loss": 0.7679,
      "step": 2480
    },
    {
      "epoch": 0.20448386302044838,
      "grad_norm": 0.39719080924987793,
      "learning_rate": 2e-05,
      "loss": 0.784,
      "step": 2490
    },
    {
      "epoch": 0.20530508335386385,
      "grad_norm": 0.41948506236076355,
      "learning_rate": 2e-05,
      "loss": 0.7668,
      "step": 2500
    },
    {
      "epoch": 0.2061263036872793,
      "grad_norm": 0.42262619733810425,
      "learning_rate": 2e-05,
      "loss": 0.7699,
      "step": 2510
    },
    {
      "epoch": 0.20694752402069475,
      "grad_norm": 0.40783119201660156,
      "learning_rate": 2e-05,
      "loss": 0.7699,
      "step": 2520
    },
    {
      "epoch": 0.20776874435411022,
      "grad_norm": 0.4184160828590393,
      "learning_rate": 2e-05,
      "loss": 0.8074,
      "step": 2530
    },
    {
      "epoch": 0.20858996468752566,
      "grad_norm": 0.40542080998420715,
      "learning_rate": 2e-05,
      "loss": 0.7752,
      "step": 2540
    },
    {
      "epoch": 0.2094111850209411,
      "grad_norm": 0.415578156709671,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.7517,
      "step": 2550
    },
    {
      "epoch": 0.21023240535435658,
      "grad_norm": 0.4102272689342499,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.7943,
      "step": 2560
    },
    {
      "epoch": 0.21105362568777203,
      "grad_norm": 0.4246770143508911,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.7733,
      "step": 2570
    },
    {
      "epoch": 0.21187484602118747,
      "grad_norm": 0.4192459285259247,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.7442,
      "step": 2580
    },
    {
      "epoch": 0.21269606635460295,
      "grad_norm": 0.40219646692276,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.753,
      "step": 2590
    },
    {
      "epoch": 0.2135172866880184,
      "grad_norm": 0.42748501896858215,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.7842,
      "step": 2600
    },
    {
      "epoch": 0.21433850702143384,
      "grad_norm": 0.4438921809196472,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.7725,
      "step": 2610
    },
    {
      "epoch": 0.2151597273548493,
      "grad_norm": 0.4111967384815216,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.7493,
      "step": 2620
    },
    {
      "epoch": 0.21598094768826476,
      "grad_norm": 0.39807483553886414,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.7597,
      "step": 2630
    },
    {
      "epoch": 0.21680216802168023,
      "grad_norm": 0.40660804510116577,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.7699,
      "step": 2640
    },
    {
      "epoch": 0.21762338835509568,
      "grad_norm": 0.4234255850315094,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.7605,
      "step": 2650
    },
    {
      "epoch": 0.21844460868851112,
      "grad_norm": 0.41879191994667053,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.7324,
      "step": 2660
    },
    {
      "epoch": 0.2192658290219266,
      "grad_norm": 0.42060863971710205,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.728,
      "step": 2670
    },
    {
      "epoch": 0.22008704935534204,
      "grad_norm": 0.40805500745773315,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.7339,
      "step": 2680
    },
    {
      "epoch": 0.22090826968875749,
      "grad_norm": 0.3834691345691681,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.7461,
      "step": 2690
    },
    {
      "epoch": 0.22172949002217296,
      "grad_norm": 0.42002376914024353,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.7638,
      "step": 2700
    },
    {
      "epoch": 0.2225507103555884,
      "grad_norm": 0.4362441897392273,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.7229,
      "step": 2710
    },
    {
      "epoch": 0.22337193068900385,
      "grad_norm": 0.40450742840766907,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.7321,
      "step": 2720
    },
    {
      "epoch": 0.22419315102241932,
      "grad_norm": 0.3918675482273102,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.7349,
      "step": 2730
    },
    {
      "epoch": 0.22501437135583477,
      "grad_norm": 0.44335079193115234,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.7257,
      "step": 2740
    },
    {
      "epoch": 0.22583559168925021,
      "grad_norm": 0.39592915773391724,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.7634,
      "step": 2750
    },
    {
      "epoch": 0.2266568120226657,
      "grad_norm": 0.38564053177833557,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.7675,
      "step": 2760
    },
    {
      "epoch": 0.22747803235608113,
      "grad_norm": 0.3890281915664673,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.7533,
      "step": 2770
    },
    {
      "epoch": 0.22829925268949658,
      "grad_norm": 0.38082170486450195,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.7507,
      "step": 2780
    },
    {
      "epoch": 0.22912047302291205,
      "grad_norm": 0.3816937506198883,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.7259,
      "step": 2790
    },
    {
      "epoch": 0.22977744928964441,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.06815362658306391,
      "train_runtime": 2291.9437,
      "train_samples_per_second": 14.65,
      "train_steps_per_second": 1.221
    }
  ],
  "logging_steps": 10,
  "max_steps": 2798,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 159,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1366756130249245e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}