{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24986604750848365,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000893016610108948,
      "grad_norm": 3.7484283447265625,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 1.4058,
      "step": 10
    },
    {
      "epoch": 0.001786033220217896,
      "grad_norm": 1.9000362157821655,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 1.3045,
      "step": 20
    },
    {
      "epoch": 0.002679049830326844,
      "grad_norm": 2.4037389755249023,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.1338,
      "step": 30
    },
    {
      "epoch": 0.003572066440435792,
      "grad_norm": 1.0070688724517822,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.0082,
      "step": 40
    },
    {
      "epoch": 0.00446508305054474,
      "grad_norm": 0.6030862927436829,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 0.8595,
      "step": 50
    },
    {
      "epoch": 0.005358099660653688,
      "grad_norm": 0.6932407021522522,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 0.7768,
      "step": 60
    },
    {
      "epoch": 0.006251116270762636,
      "grad_norm": 0.5126384496688843,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.7961,
      "step": 70
    },
    {
      "epoch": 0.007144132880871584,
      "grad_norm": 0.5326073169708252,
      "learning_rate": 8.932022471910112e-06,
      "loss": 0.777,
      "step": 80
    },
    {
      "epoch": 0.008037149490980533,
      "grad_norm": 0.4840937554836273,
      "learning_rate": 1.005e-05,
      "loss": 0.8092,
      "step": 90
    },
    {
      "epoch": 0.00893016610108948,
      "grad_norm": 0.4524643123149872,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.7689,
      "step": 100
    },
    {
      "epoch": 0.009823182711198428,
      "grad_norm": 0.4209403097629547,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.7862,
      "step": 110
    },
    {
      "epoch": 0.010716199321307376,
      "grad_norm": 0.47385457158088684,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.7922,
      "step": 120
    },
    {
      "epoch": 0.011609215931416325,
      "grad_norm": 0.4067447781562805,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.7441,
      "step": 130
    },
    {
      "epoch": 0.012502232541525273,
      "grad_norm": 0.467846542596817,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.8082,
      "step": 140
    },
    {
      "epoch": 0.01339524915163422,
      "grad_norm": 0.5435770153999329,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.8008,
      "step": 150
    },
    {
      "epoch": 0.014288265761743168,
      "grad_norm": 0.4837871789932251,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.7348,
      "step": 160
    },
    {
      "epoch": 0.015181282371852116,
      "grad_norm": 0.44955676794052124,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.7796,
      "step": 170
    },
    {
      "epoch": 0.016074298981961065,
      "grad_norm": 0.4254562258720398,
      "learning_rate": 2e-05,
      "loss": 0.7696,
      "step": 180
    },
    {
      "epoch": 0.01696731559207001,
      "grad_norm": 0.4308949410915375,
      "learning_rate": 2e-05,
      "loss": 0.7623,
      "step": 190
    },
    {
      "epoch": 0.01786033220217896,
      "grad_norm": 0.4657016098499298,
      "learning_rate": 2e-05,
      "loss": 0.741,
      "step": 200
    },
    {
      "epoch": 0.01875334881228791,
      "grad_norm": 0.4654051661491394,
      "learning_rate": 2e-05,
      "loss": 0.7624,
      "step": 210
    },
    {
      "epoch": 0.019646365422396856,
      "grad_norm": 0.4155106544494629,
      "learning_rate": 2e-05,
      "loss": 0.7521,
      "step": 220
    },
    {
      "epoch": 0.020539382032505805,
      "grad_norm": 0.47818872332572937,
      "learning_rate": 2e-05,
      "loss": 0.7431,
      "step": 230
    },
    {
      "epoch": 0.02143239864261475,
      "grad_norm": 0.43436357378959656,
      "learning_rate": 2e-05,
      "loss": 0.7559,
      "step": 240
    },
    {
      "epoch": 0.0223254152527237,
      "grad_norm": 0.4438256621360779,
      "learning_rate": 2e-05,
      "loss": 0.7874,
      "step": 250
    },
    {
      "epoch": 0.02321843186283265,
      "grad_norm": 0.42037931084632874,
      "learning_rate": 2e-05,
      "loss": 0.7776,
      "step": 260
    },
    {
      "epoch": 0.024111448472941596,
      "grad_norm": 0.4763539433479309,
      "learning_rate": 2e-05,
      "loss": 0.7769,
      "step": 270
    },
    {
      "epoch": 0.025004465083050546,
      "grad_norm": 0.4746975898742676,
      "learning_rate": 2e-05,
      "loss": 0.7761,
      "step": 280
    },
    {
      "epoch": 0.02589748169315949,
      "grad_norm": 0.4424160122871399,
      "learning_rate": 2e-05,
      "loss": 0.7603,
      "step": 290
    },
    {
      "epoch": 0.02679049830326844,
      "grad_norm": 0.4469321668148041,
      "learning_rate": 2e-05,
      "loss": 0.756,
      "step": 300
    },
    {
      "epoch": 0.02768351491337739,
      "grad_norm": 0.42572203278541565,
      "learning_rate": 2e-05,
      "loss": 0.7527,
      "step": 310
    },
    {
      "epoch": 0.028576531523486336,
      "grad_norm": 0.37948864698410034,
      "learning_rate": 2e-05,
      "loss": 0.6629,
      "step": 320
    },
    {
      "epoch": 0.029469548133595286,
      "grad_norm": 0.4720393717288971,
      "learning_rate": 2e-05,
      "loss": 0.7598,
      "step": 330
    },
    {
      "epoch": 0.030362564743704232,
      "grad_norm": 0.4645335078239441,
      "learning_rate": 2e-05,
      "loss": 0.7635,
      "step": 340
    },
    {
      "epoch": 0.03125558135381318,
      "grad_norm": 0.4660659432411194,
      "learning_rate": 2e-05,
      "loss": 0.77,
      "step": 350
    },
    {
      "epoch": 0.03214859796392213,
      "grad_norm": 0.47986748814582825,
      "learning_rate": 2e-05,
      "loss": 0.7442,
      "step": 360
    },
    {
      "epoch": 0.03304161457403108,
      "grad_norm": 0.4416871964931488,
      "learning_rate": 2e-05,
      "loss": 0.7316,
      "step": 370
    },
    {
      "epoch": 0.03393463118414002,
      "grad_norm": 0.3982086181640625,
      "learning_rate": 2e-05,
      "loss": 0.7805,
      "step": 380
    },
    {
      "epoch": 0.034827647794248975,
      "grad_norm": 0.4491710662841797,
      "learning_rate": 2e-05,
      "loss": 0.743,
      "step": 390
    },
    {
      "epoch": 0.03572066440435792,
      "grad_norm": 0.4009242653846741,
      "learning_rate": 2e-05,
      "loss": 0.7401,
      "step": 400
    },
    {
      "epoch": 0.03661368101446687,
      "grad_norm": 0.3790673017501831,
      "learning_rate": 2e-05,
      "loss": 0.7317,
      "step": 410
    },
    {
      "epoch": 0.03750669762457582,
      "grad_norm": 0.38693296909332275,
      "learning_rate": 2e-05,
      "loss": 0.7373,
      "step": 420
    },
    {
      "epoch": 0.038399714234684766,
      "grad_norm": 0.4592219293117523,
      "learning_rate": 2e-05,
      "loss": 0.7421,
      "step": 430
    },
    {
      "epoch": 0.03929273084479371,
      "grad_norm": 0.48258858919143677,
      "learning_rate": 2e-05,
      "loss": 0.7904,
      "step": 440
    },
    {
      "epoch": 0.04018574745490266,
      "grad_norm": 0.8017710447311401,
      "learning_rate": 2e-05,
      "loss": 0.7501,
      "step": 450
    },
    {
      "epoch": 0.04107876406501161,
      "grad_norm": 0.41467684507369995,
      "learning_rate": 2e-05,
      "loss": 0.7129,
      "step": 460
    },
    {
      "epoch": 0.04197178067512056,
      "grad_norm": 0.490904301404953,
      "learning_rate": 2e-05,
      "loss": 0.7671,
      "step": 470
    },
    {
      "epoch": 0.0428647972852295,
      "grad_norm": 0.4521087110042572,
      "learning_rate": 2e-05,
      "loss": 0.7397,
      "step": 480
    },
    {
      "epoch": 0.043757813895338456,
      "grad_norm": 0.4126375913619995,
      "learning_rate": 2e-05,
      "loss": 0.7391,
      "step": 490
    },
    {
      "epoch": 0.0446508305054474,
      "grad_norm": 0.4476797878742218,
      "learning_rate": 2e-05,
      "loss": 0.7796,
      "step": 500
    },
    {
      "epoch": 0.04554384711555635,
      "grad_norm": 0.43812263011932373,
      "learning_rate": 2e-05,
      "loss": 0.7352,
      "step": 510
    },
    {
      "epoch": 0.0464368637256653,
      "grad_norm": 0.48256680369377136,
      "learning_rate": 2e-05,
      "loss": 0.755,
      "step": 520
    },
    {
      "epoch": 0.047329880335774246,
      "grad_norm": 0.39438191056251526,
      "learning_rate": 2e-05,
      "loss": 0.7438,
      "step": 530
    },
    {
      "epoch": 0.04822289694588319,
      "grad_norm": 0.4146062731742859,
      "learning_rate": 2e-05,
      "loss": 0.7275,
      "step": 540
    },
    {
      "epoch": 0.04911591355599214,
      "grad_norm": 0.41129109263420105,
      "learning_rate": 2e-05,
      "loss": 0.7226,
      "step": 550
    },
    {
      "epoch": 0.05000893016610109,
      "grad_norm": 0.38930240273475647,
      "learning_rate": 2e-05,
      "loss": 0.7625,
      "step": 560
    },
    {
      "epoch": 0.05090194677621004,
      "grad_norm": 0.48423701524734497,
      "learning_rate": 2e-05,
      "loss": 0.7631,
      "step": 570
    },
    {
      "epoch": 0.05179496338631898,
      "grad_norm": 0.40557992458343506,
      "learning_rate": 2e-05,
      "loss": 0.7481,
      "step": 580
    },
    {
      "epoch": 0.052687979996427936,
      "grad_norm": 0.4137013554573059,
      "learning_rate": 2e-05,
      "loss": 0.7481,
      "step": 590
    },
    {
      "epoch": 0.05358099660653688,
      "grad_norm": 0.45856934785842896,
      "learning_rate": 2e-05,
      "loss": 0.7721,
      "step": 600
    },
    {
      "epoch": 0.05447401321664583,
      "grad_norm": 0.4169819951057434,
      "learning_rate": 2e-05,
      "loss": 0.7525,
      "step": 610
    },
    {
      "epoch": 0.05536702982675478,
      "grad_norm": 0.38590312004089355,
      "learning_rate": 2e-05,
      "loss": 0.7374,
      "step": 620
    },
    {
      "epoch": 0.05626004643686373,
      "grad_norm": 0.40914642810821533,
      "learning_rate": 2e-05,
      "loss": 0.7495,
      "step": 630
    },
    {
      "epoch": 0.05715306304697267,
      "grad_norm": 0.41702547669410706,
      "learning_rate": 2e-05,
      "loss": 0.7398,
      "step": 640
    },
    {
      "epoch": 0.05804607965708162,
      "grad_norm": 0.39613404870033264,
      "learning_rate": 2e-05,
      "loss": 0.74,
      "step": 650
    },
    {
      "epoch": 0.05893909626719057,
      "grad_norm": 0.39417654275894165,
      "learning_rate": 2e-05,
      "loss": 0.7308,
      "step": 660
    },
    {
      "epoch": 0.05983211287729952,
      "grad_norm": 0.3835000693798065,
      "learning_rate": 2e-05,
      "loss": 0.7184,
      "step": 670
    },
    {
      "epoch": 0.060725129487408464,
      "grad_norm": 0.40290987491607666,
      "learning_rate": 2e-05,
      "loss": 0.7252,
      "step": 680
    },
    {
      "epoch": 0.061618146097517416,
      "grad_norm": 0.5707727074623108,
      "learning_rate": 2e-05,
      "loss": 0.7349,
      "step": 690
    },
    {
      "epoch": 0.06251116270762636,
      "grad_norm": 0.44035205245018005,
      "learning_rate": 2e-05,
      "loss": 0.7322,
      "step": 700
    },
    {
      "epoch": 0.06340417931773532,
      "grad_norm": 0.4347422420978546,
      "learning_rate": 2e-05,
      "loss": 0.7574,
      "step": 710
    },
    {
      "epoch": 0.06429719592784426,
      "grad_norm": 0.4078957140445709,
      "learning_rate": 2e-05,
      "loss": 0.7621,
      "step": 720
    },
    {
      "epoch": 0.06519021253795321,
      "grad_norm": 0.3920077979564667,
      "learning_rate": 2e-05,
      "loss": 0.7195,
      "step": 730
    },
    {
      "epoch": 0.06608322914806215,
      "grad_norm": 0.38933590054512024,
      "learning_rate": 2e-05,
      "loss": 0.7471,
      "step": 740
    },
    {
      "epoch": 0.0669762457581711,
      "grad_norm": 0.4065713584423065,
      "learning_rate": 2e-05,
      "loss": 0.7767,
      "step": 750
    },
    {
      "epoch": 0.06786926236828004,
      "grad_norm": 0.41228511929512024,
      "learning_rate": 2e-05,
      "loss": 0.7547,
      "step": 760
    },
    {
      "epoch": 0.068762278978389,
      "grad_norm": 0.3922688364982605,
      "learning_rate": 2e-05,
      "loss": 0.7148,
      "step": 770
    },
    {
      "epoch": 0.06965529558849795,
      "grad_norm": 0.4028988778591156,
      "learning_rate": 2e-05,
      "loss": 0.7262,
      "step": 780
    },
    {
      "epoch": 0.0705483121986069,
      "grad_norm": 0.44637545943260193,
      "learning_rate": 2e-05,
      "loss": 0.7614,
      "step": 790
    },
    {
      "epoch": 0.07144132880871584,
      "grad_norm": 0.40410199761390686,
      "learning_rate": 2e-05,
      "loss": 0.7524,
      "step": 800
    },
    {
      "epoch": 0.07233434541882479,
      "grad_norm": 0.41571539640426636,
      "learning_rate": 2e-05,
      "loss": 0.7423,
      "step": 810
    },
    {
      "epoch": 0.07322736202893373,
      "grad_norm": 0.48081284761428833,
      "learning_rate": 2e-05,
      "loss": 0.7067,
      "step": 820
    },
    {
      "epoch": 0.07412037863904268,
      "grad_norm": 0.40906158089637756,
      "learning_rate": 2e-05,
      "loss": 0.7576,
      "step": 830
    },
    {
      "epoch": 0.07501339524915164,
      "grad_norm": 0.37821027636528015,
      "learning_rate": 2e-05,
      "loss": 0.7579,
      "step": 840
    },
    {
      "epoch": 0.07590641185926059,
      "grad_norm": 0.3791477382183075,
      "learning_rate": 2e-05,
      "loss": 0.7153,
      "step": 850
    },
    {
      "epoch": 0.07679942846936953,
      "grad_norm": 0.38766372203826904,
      "learning_rate": 2e-05,
      "loss": 0.7393,
      "step": 860
    },
    {
      "epoch": 0.07769244507947848,
      "grad_norm": 0.3937142491340637,
      "learning_rate": 2e-05,
      "loss": 0.7371,
      "step": 870
    },
    {
      "epoch": 0.07858546168958742,
      "grad_norm": 0.3776763677597046,
      "learning_rate": 2e-05,
      "loss": 0.7221,
      "step": 880
    },
    {
      "epoch": 0.07947847829969637,
      "grad_norm": 0.4015044867992401,
      "learning_rate": 2e-05,
      "loss": 0.723,
      "step": 890
    },
    {
      "epoch": 0.08037149490980532,
      "grad_norm": 0.43104034662246704,
      "learning_rate": 2e-05,
      "loss": 0.7621,
      "step": 900
    },
    {
      "epoch": 0.08126451151991428,
      "grad_norm": 0.3779524564743042,
      "learning_rate": 2e-05,
      "loss": 0.7332,
      "step": 910
    },
    {
      "epoch": 0.08215752813002322,
      "grad_norm": 0.3575296998023987,
      "learning_rate": 2e-05,
      "loss": 0.7575,
      "step": 920
    },
    {
      "epoch": 0.08305054474013217,
      "grad_norm": 0.43516188859939575,
      "learning_rate": 2e-05,
      "loss": 0.7601,
      "step": 930
    },
    {
      "epoch": 0.08394356135024111,
      "grad_norm": 0.3753051161766052,
      "learning_rate": 2e-05,
      "loss": 0.7269,
      "step": 940
    },
    {
      "epoch": 0.08483657796035006,
      "grad_norm": 0.3971746861934662,
      "learning_rate": 2e-05,
      "loss": 0.7396,
      "step": 950
    },
    {
      "epoch": 0.085729594570459,
      "grad_norm": 0.41950562596321106,
      "learning_rate": 2e-05,
      "loss": 0.7804,
      "step": 960
    },
    {
      "epoch": 0.08662261118056797,
      "grad_norm": 0.3685847222805023,
      "learning_rate": 2e-05,
      "loss": 0.722,
      "step": 970
    },
    {
      "epoch": 0.08751562779067691,
      "grad_norm": 0.3798861801624298,
      "learning_rate": 2e-05,
      "loss": 0.752,
      "step": 980
    },
    {
      "epoch": 0.08840864440078586,
      "grad_norm": 0.40628236532211304,
      "learning_rate": 2e-05,
      "loss": 0.7563,
      "step": 990
    },
    {
      "epoch": 0.0893016610108948,
      "grad_norm": 0.37584495544433594,
      "learning_rate": 2e-05,
      "loss": 0.719,
      "step": 1000
    },
    {
      "epoch": 0.09019467762100375,
      "grad_norm": 0.3755060136318207,
      "learning_rate": 2e-05,
      "loss": 0.7321,
      "step": 1010
    },
    {
      "epoch": 0.0910876942311127,
      "grad_norm": 0.3935806155204773,
      "learning_rate": 2e-05,
      "loss": 0.7296,
      "step": 1020
    },
    {
      "epoch": 0.09198071084122164,
      "grad_norm": 0.4500720798969269,
      "learning_rate": 2e-05,
      "loss": 0.7681,
      "step": 1030
    },
    {
      "epoch": 0.0928737274513306,
      "grad_norm": 0.4131600856781006,
      "learning_rate": 2e-05,
      "loss": 0.7691,
      "step": 1040
    },
    {
      "epoch": 0.09376674406143955,
      "grad_norm": 0.38126325607299805,
      "learning_rate": 2e-05,
      "loss": 0.7203,
      "step": 1050
    },
    {
      "epoch": 0.09465976067154849,
      "grad_norm": 0.438177227973938,
      "learning_rate": 2e-05,
      "loss": 0.7332,
      "step": 1060
    },
    {
      "epoch": 0.09555277728165744,
      "grad_norm": 0.3714941143989563,
      "learning_rate": 2e-05,
      "loss": 0.7107,
      "step": 1070
    },
    {
      "epoch": 0.09644579389176638,
      "grad_norm": 0.37563997507095337,
      "learning_rate": 2e-05,
      "loss": 0.7064,
      "step": 1080
    },
    {
      "epoch": 0.09733881050187533,
      "grad_norm": 0.38376548886299133,
      "learning_rate": 2e-05,
      "loss": 0.7471,
      "step": 1090
    },
    {
      "epoch": 0.09823182711198428,
      "grad_norm": 0.4249208867549896,
      "learning_rate": 2e-05,
      "loss": 0.7632,
      "step": 1100
    },
    {
      "epoch": 0.09912484372209324,
      "grad_norm": 0.39996418356895447,
      "learning_rate": 2e-05,
      "loss": 0.7302,
      "step": 1110
    },
    {
      "epoch": 0.10001786033220218,
      "grad_norm": 0.4173353612422943,
      "learning_rate": 2e-05,
      "loss": 0.7412,
      "step": 1120
    },
    {
      "epoch": 0.10091087694231113,
      "grad_norm": 0.3551906943321228,
      "learning_rate": 2e-05,
      "loss": 0.7452,
      "step": 1130
    },
    {
      "epoch": 0.10180389355242007,
      "grad_norm": 0.4338817894458771,
      "learning_rate": 2e-05,
      "loss": 0.7549,
      "step": 1140
    },
    {
      "epoch": 0.10269691016252902,
      "grad_norm": 0.49487829208374023,
      "learning_rate": 2e-05,
      "loss": 0.7578,
      "step": 1150
    },
    {
      "epoch": 0.10358992677263797,
      "grad_norm": 0.37487703561782837,
      "learning_rate": 2e-05,
      "loss": 0.7532,
      "step": 1160
    },
    {
      "epoch": 0.10448294338274691,
      "grad_norm": 0.36092835664749146,
      "learning_rate": 2e-05,
      "loss": 0.7386,
      "step": 1170
    },
    {
      "epoch": 0.10537595999285587,
      "grad_norm": 0.3902466297149658,
      "learning_rate": 2e-05,
      "loss": 0.7287,
      "step": 1180
    },
    {
      "epoch": 0.10626897660296482,
      "grad_norm": 0.36106592416763306,
      "learning_rate": 2e-05,
      "loss": 0.7497,
      "step": 1190
    },
    {
      "epoch": 0.10716199321307376,
      "grad_norm": 0.42885327339172363,
      "learning_rate": 2e-05,
      "loss": 0.7801,
      "step": 1200
    },
    {
      "epoch": 0.10805500982318271,
      "grad_norm": 0.36564674973487854,
      "learning_rate": 2e-05,
      "loss": 0.7152,
      "step": 1210
    },
    {
      "epoch": 0.10894802643329166,
      "grad_norm": 0.34475770592689514,
      "learning_rate": 2e-05,
      "loss": 0.7162,
      "step": 1220
    },
    {
      "epoch": 0.1098410430434006,
      "grad_norm": 0.379625529050827,
      "learning_rate": 2e-05,
      "loss": 0.7211,
      "step": 1230
    },
    {
      "epoch": 0.11073405965350956,
      "grad_norm": 0.3452484905719757,
      "learning_rate": 2e-05,
      "loss": 0.7218,
      "step": 1240
    },
    {
      "epoch": 0.11162707626361851,
      "grad_norm": 0.4212513566017151,
      "learning_rate": 2e-05,
      "loss": 0.7304,
      "step": 1250
    },
    {
      "epoch": 0.11252009287372745,
      "grad_norm": 0.40886190533638,
      "learning_rate": 2e-05,
      "loss": 0.7373,
      "step": 1260
    },
    {
      "epoch": 0.1134131094838364,
      "grad_norm": 0.3536968529224396,
      "learning_rate": 2e-05,
      "loss": 0.7323,
      "step": 1270
    },
    {
      "epoch": 0.11430612609394535,
      "grad_norm": 0.38670650124549866,
      "learning_rate": 2e-05,
      "loss": 0.741,
      "step": 1280
    },
    {
      "epoch": 0.11519914270405429,
      "grad_norm": 0.42771264910697937,
      "learning_rate": 2e-05,
      "loss": 0.7424,
      "step": 1290
    },
    {
      "epoch": 0.11609215931416324,
      "grad_norm": 0.39867374300956726,
      "learning_rate": 2e-05,
      "loss": 0.7251,
      "step": 1300
    },
    {
      "epoch": 0.1169851759242722,
      "grad_norm": 0.38744813203811646,
      "learning_rate": 2e-05,
      "loss": 0.715,
      "step": 1310
    },
    {
      "epoch": 0.11787819253438114,
      "grad_norm": 0.4313223958015442,
      "learning_rate": 2e-05,
      "loss": 0.6988,
      "step": 1320
    },
    {
      "epoch": 0.11877120914449009,
      "grad_norm": 0.3686710298061371,
      "learning_rate": 2e-05,
      "loss": 0.7162,
      "step": 1330
    },
    {
      "epoch": 0.11966422575459904,
      "grad_norm": 0.8750284314155579,
      "learning_rate": 2e-05,
      "loss": 0.7319,
      "step": 1340
    },
    {
      "epoch": 0.12055724236470798,
      "grad_norm": 0.3907322287559509,
      "learning_rate": 2e-05,
      "loss": 0.7475,
      "step": 1350
    },
    {
      "epoch": 0.12145025897481693,
      "grad_norm": 0.355712354183197,
      "learning_rate": 2e-05,
      "loss": 0.7475,
      "step": 1360
    },
    {
      "epoch": 0.12234327558492587,
      "grad_norm": 0.3635517954826355,
      "learning_rate": 2e-05,
      "loss": 0.7576,
      "step": 1370
    },
    {
      "epoch": 0.12323629219503483,
      "grad_norm": 0.39474037289619446,
      "learning_rate": 2e-05,
      "loss": 0.6988,
      "step": 1380
    },
    {
      "epoch": 0.12412930880514378,
      "grad_norm": 0.38797375559806824,
      "learning_rate": 2e-05,
      "loss": 0.7089,
      "step": 1390
    },
    {
      "epoch": 0.1250223254152527,
      "grad_norm": 0.35904696583747864,
      "learning_rate": 2e-05,
      "loss": 0.7187,
      "step": 1400
    },
    {
      "epoch": 0.12591534202536167,
      "grad_norm": 0.4828942120075226,
      "learning_rate": 2e-05,
      "loss": 0.7326,
      "step": 1410
    },
    {
      "epoch": 0.12680835863547063,
      "grad_norm": 0.3671641945838928,
      "learning_rate": 2e-05,
      "loss": 0.7149,
      "step": 1420
    },
    {
      "epoch": 0.12770137524557956,
      "grad_norm": 0.40876835584640503,
      "learning_rate": 2e-05,
      "loss": 0.7398,
      "step": 1430
    },
    {
      "epoch": 0.12859439185568852,
      "grad_norm": 0.3652034401893616,
      "learning_rate": 2e-05,
      "loss": 0.724,
      "step": 1440
    },
    {
      "epoch": 0.12948740846579745,
      "grad_norm": 0.3712545931339264,
      "learning_rate": 2e-05,
      "loss": 0.7169,
      "step": 1450
    },
    {
      "epoch": 0.13038042507590641,
      "grad_norm": 0.39639317989349365,
      "learning_rate": 2e-05,
      "loss": 0.7623,
      "step": 1460
    },
    {
      "epoch": 0.13127344168601535,
      "grad_norm": 0.38050130009651184,
      "learning_rate": 2e-05,
      "loss": 0.7259,
      "step": 1470
    },
    {
      "epoch": 0.1321664582961243,
      "grad_norm": 0.39309820532798767,
      "learning_rate": 2e-05,
      "loss": 0.7601,
      "step": 1480
    },
    {
      "epoch": 0.13305947490623327,
      "grad_norm": 0.3582014739513397,
      "learning_rate": 2e-05,
      "loss": 0.7489,
      "step": 1490
    },
    {
      "epoch": 0.1339524915163422,
      "grad_norm": 0.37961331009864807,
      "learning_rate": 2e-05,
      "loss": 0.7129,
      "step": 1500
    },
    {
      "epoch": 0.13484550812645116,
      "grad_norm": 0.5690667033195496,
      "learning_rate": 2e-05,
      "loss": 0.7345,
      "step": 1510
    },
    {
      "epoch": 0.1357385247365601,
      "grad_norm": 0.3793013095855713,
      "learning_rate": 2e-05,
      "loss": 0.718,
      "step": 1520
    },
    {
      "epoch": 0.13663154134666905,
      "grad_norm": 0.38825497031211853,
      "learning_rate": 2e-05,
      "loss": 0.7198,
      "step": 1530
    },
    {
      "epoch": 0.137524557956778,
      "grad_norm": 0.38483718037605286,
      "learning_rate": 2e-05,
      "loss": 0.716,
      "step": 1540
    },
    {
      "epoch": 0.13841757456688694,
      "grad_norm": 0.3974905014038086,
      "learning_rate": 2e-05,
      "loss": 0.7388,
      "step": 1550
    },
    {
      "epoch": 0.1393105911769959,
      "grad_norm": 0.390345960855484,
      "learning_rate": 2e-05,
      "loss": 0.729,
      "step": 1560
    },
    {
      "epoch": 0.14020360778710483,
      "grad_norm": 0.3711761236190796,
      "learning_rate": 2e-05,
      "loss": 0.7439,
      "step": 1570
    },
    {
      "epoch": 0.1410966243972138,
      "grad_norm": 0.39335206151008606,
      "learning_rate": 2e-05,
      "loss": 0.6857,
      "step": 1580
    },
    {
      "epoch": 0.14198964100732273,
      "grad_norm": 0.431006520986557,
      "learning_rate": 2e-05,
      "loss": 0.6739,
      "step": 1590
    },
    {
      "epoch": 0.14288265761743169,
      "grad_norm": 0.37578749656677246,
      "learning_rate": 2e-05,
      "loss": 0.7253,
      "step": 1600
    },
    {
      "epoch": 0.14377567422754065,
      "grad_norm": 0.36983808875083923,
      "learning_rate": 2e-05,
      "loss": 0.7087,
      "step": 1610
    },
    {
      "epoch": 0.14466869083764958,
      "grad_norm": 0.36534303426742554,
      "learning_rate": 2e-05,
      "loss": 0.7048,
      "step": 1620
    },
    {
      "epoch": 0.14556170744775854,
      "grad_norm": 0.3659409284591675,
      "learning_rate": 2e-05,
      "loss": 0.7145,
      "step": 1630
    },
    {
      "epoch": 0.14645472405786747,
      "grad_norm": 0.4026823341846466,
      "learning_rate": 2e-05,
      "loss": 0.7084,
      "step": 1640
    },
    {
      "epoch": 0.14734774066797643,
      "grad_norm": 0.40227675437927246,
      "learning_rate": 2e-05,
      "loss": 0.7521,
      "step": 1650
    },
    {
      "epoch": 0.14824075727808536,
      "grad_norm": 0.3589552640914917,
      "learning_rate": 2e-05,
      "loss": 0.6962,
      "step": 1660
    },
    {
      "epoch": 0.14913377388819432,
      "grad_norm": 0.40876489877700806,
      "learning_rate": 2e-05,
      "loss": 0.7581,
      "step": 1670
    },
    {
      "epoch": 0.15002679049830328,
      "grad_norm": 0.3787183463573456,
      "learning_rate": 2e-05,
      "loss": 0.712,
      "step": 1680
    },
    {
      "epoch": 0.1509198071084122,
      "grad_norm": 0.3726568818092346,
      "learning_rate": 2e-05,
      "loss": 0.7329,
      "step": 1690
    },
    {
      "epoch": 0.15181282371852117,
      "grad_norm": 0.36480188369750977,
      "learning_rate": 2e-05,
      "loss": 0.7192,
      "step": 1700
    },
    {
      "epoch": 0.1527058403286301,
      "grad_norm": 0.4598802328109741,
      "learning_rate": 2e-05,
      "loss": 0.742,
      "step": 1710
    },
    {
      "epoch": 0.15359885693873906,
      "grad_norm": 0.34519508481025696,
      "learning_rate": 2e-05,
      "loss": 0.7418,
      "step": 1720
    },
    {
      "epoch": 0.154491873548848,
      "grad_norm": 0.39450502395629883,
      "learning_rate": 2e-05,
      "loss": 0.7245,
      "step": 1730
    },
    {
      "epoch": 0.15538489015895696,
      "grad_norm": 0.44403451681137085,
      "learning_rate": 2e-05,
      "loss": 0.7168,
      "step": 1740
    },
    {
      "epoch": 0.15627790676906592,
      "grad_norm": 0.3881482183933258,
      "learning_rate": 2e-05,
      "loss": 0.7322,
      "step": 1750
    },
    {
      "epoch": 0.15717092337917485,
      "grad_norm": 0.3961481750011444,
      "learning_rate": 2e-05,
      "loss": 0.7593,
      "step": 1760
    },
    {
      "epoch": 0.1580639399892838,
      "grad_norm": 0.38921841979026794,
      "learning_rate": 2e-05,
      "loss": 0.7356,
      "step": 1770
    },
    {
      "epoch": 0.15895695659939274,
      "grad_norm": 0.3746980130672455,
      "learning_rate": 2e-05,
      "loss": 0.7109,
      "step": 1780
    },
    {
      "epoch": 0.1598499732095017,
      "grad_norm": 0.36172837018966675,
      "learning_rate": 2e-05,
      "loss": 0.7193,
      "step": 1790
    },
    {
      "epoch": 0.16074298981961063,
      "grad_norm": 0.34081071615219116,
      "learning_rate": 2e-05,
      "loss": 0.734,
      "step": 1800
    },
    {
      "epoch": 0.1616360064297196,
      "grad_norm": 0.3822826147079468,
      "learning_rate": 2e-05,
      "loss": 0.7213,
      "step": 1810
    },
    {
      "epoch": 0.16252902303982855,
      "grad_norm": 0.39521777629852295,
      "learning_rate": 2e-05,
      "loss": 0.7071,
      "step": 1820
    },
    {
      "epoch": 0.16342203964993748,
      "grad_norm": 0.3572978973388672,
      "learning_rate": 2e-05,
      "loss": 0.7122,
      "step": 1830
    },
    {
      "epoch": 0.16431505626004644,
      "grad_norm": 0.37090566754341125,
      "learning_rate": 2e-05,
      "loss": 0.7656,
      "step": 1840
    },
    {
      "epoch": 0.16520807287015538,
      "grad_norm": 1.1004981994628906,
      "learning_rate": 2e-05,
      "loss": 0.7045,
      "step": 1850
    },
    {
      "epoch": 0.16610108948026434,
      "grad_norm": 0.406376451253891,
      "learning_rate": 2e-05,
      "loss": 0.7121,
      "step": 1860
    },
    {
      "epoch": 0.16699410609037327,
      "grad_norm": 0.410037100315094,
      "learning_rate": 2e-05,
      "loss": 0.6982,
      "step": 1870
    },
    {
      "epoch": 0.16788712270048223,
      "grad_norm": 0.4311705231666565,
      "learning_rate": 2e-05,
      "loss": 0.6981,
      "step": 1880
    },
    {
      "epoch": 0.1687801393105912,
      "grad_norm": 0.4563307464122772,
      "learning_rate": 2e-05,
      "loss": 0.7065,
      "step": 1890
    },
    {
      "epoch": 0.16967315592070012,
      "grad_norm": 0.4294278621673584,
      "learning_rate": 2e-05,
      "loss": 0.7177,
      "step": 1900
    },
    {
      "epoch": 0.17056617253080908,
      "grad_norm": 0.41810211539268494,
      "learning_rate": 2e-05,
      "loss": 0.7447,
      "step": 1910
    },
    {
      "epoch": 0.171459189140918,
      "grad_norm": 0.47829675674438477,
      "learning_rate": 2e-05,
      "loss": 0.7345,
      "step": 1920
    },
    {
      "epoch": 0.17235220575102697,
      "grad_norm": 0.40736883878707886,
      "learning_rate": 2e-05,
      "loss": 0.7146,
      "step": 1930
    },
    {
      "epoch": 0.17324522236113593,
      "grad_norm": 0.43190640211105347,
      "learning_rate": 2e-05,
      "loss": 0.7641,
      "step": 1940
    },
    {
      "epoch": 0.17413823897124486,
      "grad_norm": 0.4052496552467346,
      "learning_rate": 2e-05,
      "loss": 0.6961,
      "step": 1950
    },
    {
      "epoch": 0.17503125558135382,
      "grad_norm": 0.3576786518096924,
      "learning_rate": 2e-05,
      "loss": 0.7191,
      "step": 1960
    },
    {
      "epoch": 0.17592427219146275,
      "grad_norm": 0.38320717215538025,
      "learning_rate": 2e-05,
      "loss": 0.7182,
      "step": 1970
    },
    {
      "epoch": 0.17681728880157171,
      "grad_norm": 0.33529797196388245,
      "learning_rate": 2e-05,
      "loss": 0.6998,
      "step": 1980
    },
    {
      "epoch": 0.17771030541168065,
      "grad_norm": 0.4263617992401123,
      "learning_rate": 2e-05,
      "loss": 0.7237,
      "step": 1990
    },
    {
      "epoch": 0.1786033220217896,
      "grad_norm": 0.3683549761772156,
      "learning_rate": 2e-05,
      "loss": 0.7177,
      "step": 2000
    },
    {
      "epoch": 0.17949633863189857,
      "grad_norm": 0.37825068831443787,
      "learning_rate": 2e-05,
      "loss": 0.6936,
      "step": 2010
    },
    {
      "epoch": 0.1803893552420075,
      "grad_norm": 0.38845622539520264,
      "learning_rate": 2e-05,
      "loss": 0.6886,
      "step": 2020
    },
    {
      "epoch": 0.18128237185211646,
      "grad_norm": 0.41564154624938965,
      "learning_rate": 2e-05,
      "loss": 0.6744,
      "step": 2030
    },
    {
      "epoch": 0.1821753884622254,
      "grad_norm": 0.375347763299942,
      "learning_rate": 2e-05,
      "loss": 0.6926,
      "step": 2040
    },
    {
      "epoch": 0.18306840507233435,
      "grad_norm": 0.39925751090049744,
      "learning_rate": 2e-05,
      "loss": 0.7214,
      "step": 2050
    },
    {
      "epoch": 0.18396142168244328,
      "grad_norm": 0.3923713266849518,
      "learning_rate": 2e-05,
      "loss": 0.7478,
      "step": 2060
    },
    {
      "epoch": 0.18485443829255224,
      "grad_norm": 0.33927154541015625,
      "learning_rate": 2e-05,
      "loss": 0.7259,
      "step": 2070
    },
    {
      "epoch": 0.1857474549026612,
      "grad_norm": 0.3772149384021759,
      "learning_rate": 2e-05,
      "loss": 0.7127,
      "step": 2080
    },
    {
      "epoch": 0.18664047151277013,
      "grad_norm": 0.4021603763103485,
      "learning_rate": 2e-05,
      "loss": 0.6927,
      "step": 2090
    },
    {
      "epoch": 0.1875334881228791,
      "grad_norm": 0.400551974773407,
      "learning_rate": 2e-05,
      "loss": 0.7256,
      "step": 2100
    },
    {
      "epoch": 0.18842650473298803,
      "grad_norm": 0.41825857758522034,
      "learning_rate": 2e-05,
      "loss": 0.6991,
      "step": 2110
    },
    {
      "epoch": 0.18931952134309699,
      "grad_norm": 0.3584500551223755,
      "learning_rate": 2e-05,
      "loss": 0.7141,
      "step": 2120
    },
    {
      "epoch": 0.19021253795320592,
      "grad_norm": 0.8151934146881104,
      "learning_rate": 2e-05,
      "loss": 0.6834,
      "step": 2130
    },
    {
      "epoch": 0.19110555456331488,
      "grad_norm": 0.36020809412002563,
      "learning_rate": 2e-05,
      "loss": 0.7175,
      "step": 2140
    },
    {
      "epoch": 0.19199857117342384,
      "grad_norm": 0.3733537495136261,
      "learning_rate": 2e-05,
      "loss": 0.7156,
      "step": 2150
    },
    {
      "epoch": 0.19289158778353277,
      "grad_norm": 0.4166247844696045,
      "learning_rate": 2e-05,
      "loss": 0.7636,
      "step": 2160
    },
    {
      "epoch": 0.19378460439364173,
      "grad_norm": 0.3874996602535248,
      "learning_rate": 2e-05,
      "loss": 0.699,
      "step": 2170
    },
    {
      "epoch": 0.19467762100375066,
      "grad_norm": 0.3566342294216156,
      "learning_rate": 2e-05,
      "loss": 0.7453,
      "step": 2180
    },
    {
      "epoch": 0.19557063761385962,
      "grad_norm": 0.35978227853775024,
      "learning_rate": 2e-05,
      "loss": 0.7152,
      "step": 2190
    },
    {
      "epoch": 0.19646365422396855,
      "grad_norm": 0.34371668100357056,
      "learning_rate": 2e-05,
      "loss": 0.7258,
      "step": 2200
    },
    {
      "epoch": 0.1973566708340775,
      "grad_norm": 0.36636587977409363,
      "learning_rate": 2e-05,
      "loss": 0.7109,
      "step": 2210
    },
    {
      "epoch": 0.19824968744418647,
      "grad_norm": 0.3694961667060852,
      "learning_rate": 2e-05,
      "loss": 0.7266,
      "step": 2220
    },
    {
      "epoch": 0.1991427040542954,
      "grad_norm": 0.3831530809402466,
      "learning_rate": 2e-05,
      "loss": 0.7165,
      "step": 2230
    },
    {
      "epoch": 0.20003572066440437,
      "grad_norm": 0.4752442538738251,
      "learning_rate": 2e-05,
      "loss": 0.7054,
      "step": 2240
    },
    {
      "epoch": 0.2009287372745133,
      "grad_norm": 0.3605307638645172,
      "learning_rate": 2e-05,
      "loss": 0.7232,
      "step": 2250
    },
    {
      "epoch": 0.20182175388462226,
      "grad_norm": 0.3741367757320404,
      "learning_rate": 2e-05,
      "loss": 0.7164,
      "step": 2260
    },
    {
      "epoch": 0.2027147704947312,
      "grad_norm": 0.44306308031082153,
      "learning_rate": 2e-05,
      "loss": 0.7054,
      "step": 2270
    },
    {
      "epoch": 0.20360778710484015,
      "grad_norm": 0.35885170102119446,
      "learning_rate": 2e-05,
      "loss": 0.7193,
      "step": 2280
    },
    {
      "epoch": 0.2045008037149491,
      "grad_norm": 0.42225345969200134,
      "learning_rate": 2e-05,
      "loss": 0.7167,
      "step": 2290
    },
    {
      "epoch": 0.20539382032505804,
      "grad_norm": 0.36834093928337097,
      "learning_rate": 2e-05,
      "loss": 0.699,
      "step": 2300
    },
    {
      "epoch": 0.206286836935167,
      "grad_norm": 0.37331831455230713,
      "learning_rate": 2e-05,
      "loss": 0.6864,
      "step": 2310
    },
    {
      "epoch": 0.20717985354527593,
      "grad_norm": 0.33582958579063416,
      "learning_rate": 2e-05,
      "loss": 0.7447,
      "step": 2320
    },
    {
      "epoch": 0.2080728701553849,
      "grad_norm": 0.3406867980957031,
      "learning_rate": 2e-05,
      "loss": 0.6888,
      "step": 2330
    },
    {
      "epoch": 0.20896588676549382,
      "grad_norm": 0.7537785768508911,
      "learning_rate": 2e-05,
      "loss": 0.7387,
      "step": 2340
    },
    {
      "epoch": 0.20985890337560278,
      "grad_norm": 0.3987394869327545,
      "learning_rate": 2e-05,
      "loss": 0.6995,
      "step": 2350
    },
    {
      "epoch": 0.21075191998571174,
      "grad_norm": 0.3712831437587738,
      "learning_rate": 2e-05,
      "loss": 0.6763,
      "step": 2360
    },
    {
      "epoch": 0.21164493659582068,
      "grad_norm": 0.3862318992614746,
      "learning_rate": 2e-05,
      "loss": 0.7021,
      "step": 2370
    },
    {
      "epoch": 0.21253795320592964,
      "grad_norm": 0.35739755630493164,
      "learning_rate": 2e-05,
      "loss": 0.7143,
      "step": 2380
    },
    {
      "epoch": 0.21343096981603857,
      "grad_norm": 0.37976863980293274,
      "learning_rate": 2e-05,
      "loss": 0.721,
      "step": 2390
    },
    {
      "epoch": 0.21432398642614753,
      "grad_norm": 0.3507783114910126,
      "learning_rate": 2e-05,
      "loss": 0.7008,
      "step": 2400
    },
    {
      "epoch": 0.2152170030362565,
      "grad_norm": 0.37717995047569275,
      "learning_rate": 2e-05,
      "loss": 0.7123,
      "step": 2410
    },
    {
      "epoch": 0.21611001964636542,
      "grad_norm": 0.5691996216773987,
      "learning_rate": 2e-05,
      "loss": 0.7418,
      "step": 2420
    },
    {
      "epoch": 0.21700303625647438,
      "grad_norm": 0.38756728172302246,
      "learning_rate": 2e-05,
      "loss": 0.7104,
      "step": 2430
    },
    {
      "epoch": 0.2178960528665833,
      "grad_norm": 0.554707407951355,
      "learning_rate": 2e-05,
      "loss": 0.68,
      "step": 2440
    },
    {
      "epoch": 0.21878906947669227,
      "grad_norm": 0.3568492829799652,
      "learning_rate": 2e-05,
      "loss": 0.6845,
      "step": 2450
    },
    {
      "epoch": 0.2196820860868012,
      "grad_norm": 0.3751198947429657,
      "learning_rate": 2e-05,
      "loss": 0.6868,
      "step": 2460
    },
    {
      "epoch": 0.22057510269691016,
      "grad_norm": 0.39954832196235657,
      "learning_rate": 2e-05,
      "loss": 0.7364,
      "step": 2470
    },
    {
      "epoch": 0.22146811930701912,
      "grad_norm": 0.37244030833244324,
      "learning_rate": 2e-05,
      "loss": 0.7365,
      "step": 2480
    },
    {
      "epoch": 0.22236113591712806,
      "grad_norm": 0.38988977670669556,
      "learning_rate": 2e-05,
      "loss": 0.7324,
      "step": 2490
    },
    {
      "epoch": 0.22325415252723702,
      "grad_norm": 0.3926638662815094,
      "learning_rate": 2e-05,
      "loss": 0.7181,
      "step": 2500
    },
    {
      "epoch": 0.22414716913734595,
      "grad_norm": 0.361802339553833,
      "learning_rate": 2e-05,
      "loss": 0.6984,
      "step": 2510
    },
    {
      "epoch": 0.2250401857474549,
      "grad_norm": 0.38118746876716614,
      "learning_rate": 2e-05,
      "loss": 0.7376,
      "step": 2520
    },
    {
      "epoch": 0.22593320235756384,
      "grad_norm": 0.39917808771133423,
      "learning_rate": 2e-05,
      "loss": 0.7166,
      "step": 2530
    },
    {
      "epoch": 0.2268262189676728,
      "grad_norm": 0.39203181862831116,
      "learning_rate": 2e-05,
      "loss": 0.7142,
      "step": 2540
    },
    {
      "epoch": 0.22771923557778176,
      "grad_norm": 0.36294257640838623,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.6914,
      "step": 2550
    },
    {
      "epoch": 0.2286122521878907,
      "grad_norm": 0.3801777958869934,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.7014,
      "step": 2560
    },
    {
      "epoch": 0.22950526879799965,
      "grad_norm": 0.43727347254753113,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.698,
      "step": 2570
    },
    {
      "epoch": 0.23039828540810858,
      "grad_norm": 0.5819860100746155,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.7135,
      "step": 2580
    },
    {
      "epoch": 0.23129130201821754,
      "grad_norm": 0.37421056628227234,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.6888,
      "step": 2590
    },
    {
      "epoch": 0.23218431862832647,
      "grad_norm": 0.3741321265697479,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.7261,
      "step": 2600
    },
    {
      "epoch": 0.23307733523843543,
      "grad_norm": 0.36540302634239197,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.7126,
      "step": 2610
    },
    {
      "epoch": 0.2339703518485444,
      "grad_norm": 0.3569313585758209,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.6852,
      "step": 2620
    },
    {
      "epoch": 0.23486336845865333,
      "grad_norm": 0.3557926118373871,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.6991,
      "step": 2630
    },
    {
      "epoch": 0.2357563850687623,
      "grad_norm": 0.39714688062667847,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.6997,
      "step": 2640
    },
    {
      "epoch": 0.23664940167887122,
      "grad_norm": 0.3588697016239166,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.7056,
      "step": 2650
    },
    {
      "epoch": 0.23754241828898018,
      "grad_norm": 0.36892077326774597,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.6847,
      "step": 2660
    },
    {
      "epoch": 0.2384354348990891,
      "grad_norm": 0.3804692327976227,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.699,
      "step": 2670
    },
    {
      "epoch": 0.23932845150919807,
      "grad_norm": 0.3504442274570465,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.6995,
      "step": 2680
    },
    {
      "epoch": 0.24022146811930703,
      "grad_norm": 0.39477452635765076,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.712,
      "step": 2690
    },
    {
      "epoch": 0.24111448472941596,
      "grad_norm": 0.37073835730552673,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.7135,
      "step": 2700
    },
    {
      "epoch": 0.24200750133952492,
      "grad_norm": 0.4418194890022278,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.7003,
      "step": 2710
    },
    {
      "epoch": 0.24290051794963385,
      "grad_norm": 0.40942591428756714,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.7094,
      "step": 2720
    },
    {
      "epoch": 0.2437935345597428,
      "grad_norm": 0.35024014115333557,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.6729,
      "step": 2730
    },
    {
      "epoch": 0.24468655116985175,
      "grad_norm": 0.34503915905952454,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.6768,
      "step": 2740
    },
    {
      "epoch": 0.2455795677799607,
      "grad_norm": 0.34917470812797546,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.6787,
      "step": 2750
    },
    {
      "epoch": 0.24647258439006967,
      "grad_norm": 0.3615460693836212,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.6634,
      "step": 2760
    },
    {
      "epoch": 0.2473656010001786,
      "grad_norm": 0.3222164809703827,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.6758,
      "step": 2770
    },
    {
      "epoch": 0.24825861761028756,
      "grad_norm": 0.3308277428150177,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.6992,
      "step": 2780
    },
    {
      "epoch": 0.2491516342203965,
      "grad_norm": 0.3545868694782257,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.6891,
      "step": 2790
    },
    {
      "epoch": 0.24986604750848365,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.06305826979930951,
      "train_runtime": 2744.8932,
      "train_samples_per_second": 12.232,
      "train_steps_per_second": 1.019
    }
  ],
  "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
}