{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 282,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010723860589812333,
      "grad_norm": 0.09956473857164383,
      "learning_rate": 0.0,
      "loss": 1.187880516052246,
      "step": 1
    },
    {
      "epoch": 0.021447721179624665,
      "grad_norm": 0.11292029917240143,
      "learning_rate": 6.896551724137932e-06,
      "loss": 1.2154676914215088,
      "step": 2
    },
    {
      "epoch": 0.032171581769437,
      "grad_norm": 0.10153086483478546,
      "learning_rate": 1.3793103448275863e-05,
      "loss": 1.0373685359954834,
      "step": 3
    },
    {
      "epoch": 0.04289544235924933,
      "grad_norm": 0.11490683257579803,
      "learning_rate": 2.0689655172413793e-05,
      "loss": 1.1642744541168213,
      "step": 4
    },
    {
      "epoch": 0.05361930294906166,
      "grad_norm": 0.10738470405340195,
      "learning_rate": 2.7586206896551727e-05,
      "loss": 1.0547881126403809,
      "step": 5
    },
    {
      "epoch": 0.064343163538874,
      "grad_norm": 0.09365780651569366,
      "learning_rate": 3.4482758620689657e-05,
      "loss": 0.9747384190559387,
      "step": 6
    },
    {
      "epoch": 0.07506702412868632,
      "grad_norm": 0.11804107576608658,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 1.1494673490524292,
      "step": 7
    },
    {
      "epoch": 0.08579088471849866,
      "grad_norm": 0.1242947056889534,
      "learning_rate": 4.827586206896552e-05,
      "loss": 1.1914423704147339,
      "step": 8
    },
    {
      "epoch": 0.09651474530831099,
      "grad_norm": 0.11152593791484833,
      "learning_rate": 5.517241379310345e-05,
      "loss": 0.9928394556045532,
      "step": 9
    },
    {
      "epoch": 0.10723860589812333,
      "grad_norm": 0.11541841924190521,
      "learning_rate": 6.206896551724138e-05,
      "loss": 0.9315593242645264,
      "step": 10
    },
    {
      "epoch": 0.11796246648793565,
      "grad_norm": 0.11834950000047684,
      "learning_rate": 6.896551724137931e-05,
      "loss": 0.8903577327728271,
      "step": 11
    },
    {
      "epoch": 0.128686327077748,
      "grad_norm": 0.14892849326133728,
      "learning_rate": 7.586206896551724e-05,
      "loss": 1.0821267366409302,
      "step": 12
    },
    {
      "epoch": 0.13941018766756033,
      "grad_norm": 0.1506800651550293,
      "learning_rate": 8.275862068965517e-05,
      "loss": 1.0795198678970337,
      "step": 13
    },
    {
      "epoch": 0.15013404825737264,
      "grad_norm": 0.14844302833080292,
      "learning_rate": 8.96551724137931e-05,
      "loss": 1.026419758796692,
      "step": 14
    },
    {
      "epoch": 0.16085790884718498,
      "grad_norm": 0.16847245395183563,
      "learning_rate": 9.655172413793105e-05,
      "loss": 1.0807701349258423,
      "step": 15
    },
    {
      "epoch": 0.17158176943699732,
      "grad_norm": 0.1590828001499176,
      "learning_rate": 0.00010344827586206898,
      "loss": 0.9547437429428101,
      "step": 16
    },
    {
      "epoch": 0.18230563002680966,
      "grad_norm": 0.1714753657579422,
      "learning_rate": 0.0001103448275862069,
      "loss": 0.9339712858200073,
      "step": 17
    },
    {
      "epoch": 0.19302949061662197,
      "grad_norm": 0.17293080687522888,
      "learning_rate": 0.00011724137931034482,
      "loss": 0.9700860977172852,
      "step": 18
    },
    {
      "epoch": 0.2037533512064343,
      "grad_norm": 0.18182949721813202,
      "learning_rate": 0.00012413793103448277,
      "loss": 0.9788463115692139,
      "step": 19
    },
    {
      "epoch": 0.21447721179624665,
      "grad_norm": 0.14979304373264313,
      "learning_rate": 0.00013103448275862068,
      "loss": 0.7673980593681335,
      "step": 20
    },
    {
      "epoch": 0.225201072386059,
      "grad_norm": 0.1847337931394577,
      "learning_rate": 0.00013793103448275863,
      "loss": 0.8736073970794678,
      "step": 21
    },
    {
      "epoch": 0.2359249329758713,
      "grad_norm": 0.1613779366016388,
      "learning_rate": 0.00014482758620689657,
      "loss": 0.7171751260757446,
      "step": 22
    },
    {
      "epoch": 0.24664879356568364,
      "grad_norm": 0.20078714191913605,
      "learning_rate": 0.00015172413793103449,
      "loss": 0.8132349848747253,
      "step": 23
    },
    {
      "epoch": 0.257372654155496,
      "grad_norm": 0.23513053357601166,
      "learning_rate": 0.00015862068965517243,
      "loss": 0.767032265663147,
      "step": 24
    },
    {
      "epoch": 0.2680965147453083,
      "grad_norm": 0.264248788356781,
      "learning_rate": 0.00016551724137931035,
      "loss": 0.9374470114707947,
      "step": 25
    },
    {
      "epoch": 0.27882037533512066,
      "grad_norm": 0.23587241768836975,
      "learning_rate": 0.00017241379310344826,
      "loss": 0.85521000623703,
      "step": 26
    },
    {
      "epoch": 0.289544235924933,
      "grad_norm": 0.2163752019405365,
      "learning_rate": 0.0001793103448275862,
      "loss": 0.685062050819397,
      "step": 27
    },
    {
      "epoch": 0.3002680965147453,
      "grad_norm": 0.23211570084095,
      "learning_rate": 0.00018620689655172415,
      "loss": 0.7995907068252563,
      "step": 28
    },
    {
      "epoch": 0.3109919571045576,
      "grad_norm": 0.28809505701065063,
      "learning_rate": 0.0001931034482758621,
      "loss": 0.7216339111328125,
      "step": 29
    },
    {
      "epoch": 0.32171581769436997,
      "grad_norm": 0.306933730840683,
      "learning_rate": 0.0002,
      "loss": 0.7865221500396729,
      "step": 30
    },
    {
      "epoch": 0.3324396782841823,
      "grad_norm": 0.23336660861968994,
      "learning_rate": 0.00019920948616600792,
      "loss": 0.5897479057312012,
      "step": 31
    },
    {
      "epoch": 0.34316353887399464,
      "grad_norm": 0.2930724024772644,
      "learning_rate": 0.00019841897233201583,
      "loss": 0.7502959966659546,
      "step": 32
    },
    {
      "epoch": 0.353887399463807,
      "grad_norm": 0.2703939974308014,
      "learning_rate": 0.0001976284584980237,
      "loss": 0.659548282623291,
      "step": 33
    },
    {
      "epoch": 0.3646112600536193,
      "grad_norm": 0.2767476737499237,
      "learning_rate": 0.00019683794466403162,
      "loss": 0.7053808569908142,
      "step": 34
    },
    {
      "epoch": 0.3753351206434316,
      "grad_norm": 0.31025224924087524,
      "learning_rate": 0.00019604743083003953,
      "loss": 0.7129980325698853,
      "step": 35
    },
    {
      "epoch": 0.38605898123324395,
      "grad_norm": 0.24430641531944275,
      "learning_rate": 0.00019525691699604744,
      "loss": 0.6667079925537109,
      "step": 36
    },
    {
      "epoch": 0.3967828418230563,
      "grad_norm": 0.23834890127182007,
      "learning_rate": 0.00019446640316205535,
      "loss": 0.6788681149482727,
      "step": 37
    },
    {
      "epoch": 0.4075067024128686,
      "grad_norm": 0.24645410478115082,
      "learning_rate": 0.00019367588932806324,
      "loss": 0.6573145389556885,
      "step": 38
    },
    {
      "epoch": 0.41823056300268097,
      "grad_norm": 0.2453237771987915,
      "learning_rate": 0.00019288537549407115,
      "loss": 0.6146591901779175,
      "step": 39
    },
    {
      "epoch": 0.4289544235924933,
      "grad_norm": 0.28095656633377075,
      "learning_rate": 0.00019209486166007906,
      "loss": 0.8814584612846375,
      "step": 40
    },
    {
      "epoch": 0.43967828418230565,
      "grad_norm": 0.2434511035680771,
      "learning_rate": 0.00019130434782608697,
      "loss": 0.5752735137939453,
      "step": 41
    },
    {
      "epoch": 0.450402144772118,
      "grad_norm": 0.2717647850513458,
      "learning_rate": 0.00019051383399209488,
      "loss": 0.7667861580848694,
      "step": 42
    },
    {
      "epoch": 0.46112600536193027,
      "grad_norm": 0.2082528918981552,
      "learning_rate": 0.00018972332015810276,
      "loss": 0.4807273745536804,
      "step": 43
    },
    {
      "epoch": 0.4718498659517426,
      "grad_norm": 0.2160937786102295,
      "learning_rate": 0.00018893280632411067,
      "loss": 0.6491277813911438,
      "step": 44
    },
    {
      "epoch": 0.48257372654155495,
      "grad_norm": 0.2040049135684967,
      "learning_rate": 0.00018814229249011858,
      "loss": 0.5802018642425537,
      "step": 45
    },
    {
      "epoch": 0.4932975871313673,
      "grad_norm": 0.2226921021938324,
      "learning_rate": 0.0001873517786561265,
      "loss": 0.5459230542182922,
      "step": 46
    },
    {
      "epoch": 0.5040214477211796,
      "grad_norm": 0.2842342257499695,
      "learning_rate": 0.0001865612648221344,
      "loss": 0.6073319315910339,
      "step": 47
    },
    {
      "epoch": 0.514745308310992,
      "grad_norm": 0.27150487899780273,
      "learning_rate": 0.00018577075098814228,
      "loss": 0.5493534803390503,
      "step": 48
    },
    {
      "epoch": 0.5254691689008043,
      "grad_norm": 0.3216560482978821,
      "learning_rate": 0.0001849802371541502,
      "loss": 0.6763379573822021,
      "step": 49
    },
    {
      "epoch": 0.5361930294906166,
      "grad_norm": 0.25345465540885925,
      "learning_rate": 0.0001841897233201581,
      "loss": 0.6142692565917969,
      "step": 50
    },
    {
      "epoch": 0.546916890080429,
      "grad_norm": 0.2614583671092987,
      "learning_rate": 0.00018339920948616601,
      "loss": 0.5745217204093933,
      "step": 51
    },
    {
      "epoch": 0.5576407506702413,
      "grad_norm": 0.2511961758136749,
      "learning_rate": 0.00018260869565217392,
      "loss": 0.5694140195846558,
      "step": 52
    },
    {
      "epoch": 0.5683646112600537,
      "grad_norm": 0.2542041540145874,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.58800208568573,
      "step": 53
    },
    {
      "epoch": 0.579088471849866,
      "grad_norm": 0.3461075723171234,
      "learning_rate": 0.00018102766798418972,
      "loss": 0.6247663497924805,
      "step": 54
    },
    {
      "epoch": 0.5898123324396782,
      "grad_norm": 0.30197465419769287,
      "learning_rate": 0.00018023715415019763,
      "loss": 0.5455595254898071,
      "step": 55
    },
    {
      "epoch": 0.6005361930294906,
      "grad_norm": 0.28050318360328674,
      "learning_rate": 0.00017944664031620554,
      "loss": 0.5253524780273438,
      "step": 56
    },
    {
      "epoch": 0.6112600536193029,
      "grad_norm": 0.25096285343170166,
      "learning_rate": 0.00017865612648221345,
      "loss": 0.47590434551239014,
      "step": 57
    },
    {
      "epoch": 0.6219839142091153,
      "grad_norm": 0.24267607927322388,
      "learning_rate": 0.00017786561264822136,
      "loss": 0.533282995223999,
      "step": 58
    },
    {
      "epoch": 0.6327077747989276,
      "grad_norm": 0.2805137038230896,
      "learning_rate": 0.00017707509881422927,
      "loss": 0.5030880570411682,
      "step": 59
    },
    {
      "epoch": 0.6434316353887399,
      "grad_norm": 0.2617737650871277,
      "learning_rate": 0.00017628458498023718,
      "loss": 0.5744041800498962,
      "step": 60
    },
    {
      "epoch": 0.6541554959785523,
      "grad_norm": 0.2669621407985687,
      "learning_rate": 0.0001754940711462451,
      "loss": 0.622750997543335,
      "step": 61
    },
    {
      "epoch": 0.6648793565683646,
      "grad_norm": 0.3352331817150116,
      "learning_rate": 0.00017470355731225297,
      "loss": 0.6852260231971741,
      "step": 62
    },
    {
      "epoch": 0.675603217158177,
      "grad_norm": 0.29469311237335205,
      "learning_rate": 0.00017391304347826088,
      "loss": 0.5582889318466187,
      "step": 63
    },
    {
      "epoch": 0.6863270777479893,
      "grad_norm": 0.28165683150291443,
      "learning_rate": 0.0001731225296442688,
      "loss": 0.5959634184837341,
      "step": 64
    },
    {
      "epoch": 0.6970509383378016,
      "grad_norm": 0.27457600831985474,
      "learning_rate": 0.0001723320158102767,
      "loss": 0.5719581842422485,
      "step": 65
    },
    {
      "epoch": 0.707774798927614,
      "grad_norm": 0.25963717699050903,
      "learning_rate": 0.0001715415019762846,
      "loss": 0.5438885688781738,
      "step": 66
    },
    {
      "epoch": 0.7184986595174263,
      "grad_norm": 0.2500856816768646,
      "learning_rate": 0.0001707509881422925,
      "loss": 0.4802711606025696,
      "step": 67
    },
    {
      "epoch": 0.7292225201072386,
      "grad_norm": 0.33261388540267944,
      "learning_rate": 0.0001699604743083004,
      "loss": 0.5482622981071472,
      "step": 68
    },
    {
      "epoch": 0.739946380697051,
      "grad_norm": 0.32809919118881226,
      "learning_rate": 0.00016916996047430832,
      "loss": 0.5493278503417969,
      "step": 69
    },
    {
      "epoch": 0.7506702412868632,
      "grad_norm": 0.30052393674850464,
      "learning_rate": 0.00016837944664031623,
      "loss": 0.571394681930542,
      "step": 70
    },
    {
      "epoch": 0.7613941018766756,
      "grad_norm": 0.2913955748081207,
      "learning_rate": 0.00016758893280632414,
      "loss": 0.5969862341880798,
      "step": 71
    },
    {
      "epoch": 0.7721179624664879,
      "grad_norm": 0.29803213477134705,
      "learning_rate": 0.00016679841897233202,
      "loss": 0.5084568858146667,
      "step": 72
    },
    {
      "epoch": 0.7828418230563002,
      "grad_norm": 0.25044989585876465,
      "learning_rate": 0.00016600790513833993,
      "loss": 0.4812390208244324,
      "step": 73
    },
    {
      "epoch": 0.7935656836461126,
      "grad_norm": 0.2839549779891968,
      "learning_rate": 0.00016521739130434784,
      "loss": 0.5099290609359741,
      "step": 74
    },
    {
      "epoch": 0.8042895442359249,
      "grad_norm": 0.3287063539028168,
      "learning_rate": 0.00016442687747035575,
      "loss": 0.6249513626098633,
      "step": 75
    },
    {
      "epoch": 0.8150134048257373,
      "grad_norm": 0.26829907298088074,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.5250214338302612,
      "step": 76
    },
    {
      "epoch": 0.8257372654155496,
      "grad_norm": 0.29728639125823975,
      "learning_rate": 0.00016284584980237154,
      "loss": 0.5088335275650024,
      "step": 77
    },
    {
      "epoch": 0.8364611260053619,
      "grad_norm": 0.33355408906936646,
      "learning_rate": 0.00016205533596837945,
      "loss": 0.5413830876350403,
      "step": 78
    },
    {
      "epoch": 0.8471849865951743,
      "grad_norm": 0.29799699783325195,
      "learning_rate": 0.00016126482213438736,
      "loss": 0.5053578615188599,
      "step": 79
    },
    {
      "epoch": 0.8579088471849866,
      "grad_norm": 0.3381000757217407,
      "learning_rate": 0.00016047430830039527,
      "loss": 0.5565289258956909,
      "step": 80
    },
    {
      "epoch": 0.868632707774799,
      "grad_norm": 0.3973819315433502,
      "learning_rate": 0.00015968379446640318,
      "loss": 0.711586594581604,
      "step": 81
    },
    {
      "epoch": 0.8793565683646113,
      "grad_norm": 0.40298908948898315,
      "learning_rate": 0.00015889328063241107,
      "loss": 0.6098839044570923,
      "step": 82
    },
    {
      "epoch": 0.8900804289544236,
      "grad_norm": 0.30284130573272705,
      "learning_rate": 0.00015810276679841898,
      "loss": 0.4950011372566223,
      "step": 83
    },
    {
      "epoch": 0.900804289544236,
      "grad_norm": 0.3403407037258148,
      "learning_rate": 0.00015731225296442689,
      "loss": 0.6132961511611938,
      "step": 84
    },
    {
      "epoch": 0.9115281501340483,
      "grad_norm": 0.2879418432712555,
      "learning_rate": 0.0001565217391304348,
      "loss": 0.43917202949523926,
      "step": 85
    },
    {
      "epoch": 0.9222520107238605,
      "grad_norm": 0.33686619997024536,
      "learning_rate": 0.00015573122529644268,
      "loss": 0.5142088532447815,
      "step": 86
    },
    {
      "epoch": 0.9329758713136729,
      "grad_norm": 0.325030654668808,
      "learning_rate": 0.0001549407114624506,
      "loss": 0.5654577016830444,
      "step": 87
    },
    {
      "epoch": 0.9436997319034852,
      "grad_norm": 0.33111876249313354,
      "learning_rate": 0.0001541501976284585,
      "loss": 0.5170025825500488,
      "step": 88
    },
    {
      "epoch": 0.9544235924932976,
      "grad_norm": 0.27954328060150146,
      "learning_rate": 0.0001533596837944664,
      "loss": 0.4477558135986328,
      "step": 89
    },
    {
      "epoch": 0.9651474530831099,
      "grad_norm": 0.32940271496772766,
      "learning_rate": 0.00015256916996047432,
      "loss": 0.5770028829574585,
      "step": 90
    },
    {
      "epoch": 0.9758713136729222,
      "grad_norm": 0.2901531755924225,
      "learning_rate": 0.0001517786561264822,
      "loss": 0.5113964080810547,
      "step": 91
    },
    {
      "epoch": 0.9865951742627346,
      "grad_norm": 0.35382938385009766,
      "learning_rate": 0.0001509881422924901,
      "loss": 0.5637056827545166,
      "step": 92
    },
    {
      "epoch": 0.9973190348525469,
      "grad_norm": 0.3409457802772522,
      "learning_rate": 0.00015019762845849802,
      "loss": 0.6113982200622559,
      "step": 93
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.9160968661308289,
      "learning_rate": 0.00014940711462450593,
      "loss": 0.6628789901733398,
      "step": 94
    },
    {
      "epoch": 1.0107238605898123,
      "grad_norm": 0.29314255714416504,
      "learning_rate": 0.00014861660079051384,
      "loss": 0.46988680958747864,
      "step": 95
    },
    {
      "epoch": 1.0214477211796247,
      "grad_norm": 0.25285112857818604,
      "learning_rate": 0.00014782608695652173,
      "loss": 0.37834423780441284,
      "step": 96
    },
    {
      "epoch": 1.032171581769437,
      "grad_norm": 0.333655446767807,
      "learning_rate": 0.00014703557312252964,
      "loss": 0.4831538498401642,
      "step": 97
    },
    {
      "epoch": 1.0428954423592494,
      "grad_norm": 0.2649567127227783,
      "learning_rate": 0.00014624505928853755,
      "loss": 0.41907089948654175,
      "step": 98
    },
    {
      "epoch": 1.0536193029490617,
      "grad_norm": 0.27437201142311096,
      "learning_rate": 0.00014545454545454546,
      "loss": 0.2983744144439697,
      "step": 99
    },
    {
      "epoch": 1.064343163538874,
      "grad_norm": 0.3050195276737213,
      "learning_rate": 0.00014466403162055337,
      "loss": 0.3996342718601227,
      "step": 100
    },
    {
      "epoch": 1.0750670241286864,
      "grad_norm": 0.31925857067108154,
      "learning_rate": 0.00014387351778656125,
      "loss": 0.5546276569366455,
      "step": 101
    },
    {
      "epoch": 1.0857908847184987,
      "grad_norm": 0.32142284512519836,
      "learning_rate": 0.00014308300395256916,
      "loss": 0.4055824279785156,
      "step": 102
    },
    {
      "epoch": 1.096514745308311,
      "grad_norm": 0.307692289352417,
      "learning_rate": 0.00014229249011857707,
      "loss": 0.3661179840564728,
      "step": 103
    },
    {
      "epoch": 1.1072386058981234,
      "grad_norm": 0.3772393763065338,
      "learning_rate": 0.00014150197628458498,
      "loss": 0.33995968103408813,
      "step": 104
    },
    {
      "epoch": 1.1179624664879357,
      "grad_norm": 0.33760136365890503,
      "learning_rate": 0.0001407114624505929,
      "loss": 0.3819088935852051,
      "step": 105
    },
    {
      "epoch": 1.128686327077748,
      "grad_norm": 0.4074546694755554,
      "learning_rate": 0.0001399209486166008,
      "loss": 0.41713619232177734,
      "step": 106
    },
    {
      "epoch": 1.1394101876675604,
      "grad_norm": 0.37227675318717957,
      "learning_rate": 0.0001391304347826087,
      "loss": 0.42982980608940125,
      "step": 107
    },
    {
      "epoch": 1.1501340482573728,
      "grad_norm": 0.4107712209224701,
      "learning_rate": 0.00013833992094861662,
      "loss": 0.4299226403236389,
      "step": 108
    },
    {
      "epoch": 1.160857908847185,
      "grad_norm": 0.5368478894233704,
      "learning_rate": 0.00013754940711462453,
      "loss": 0.5186800956726074,
      "step": 109
    },
    {
      "epoch": 1.1715817694369974,
      "grad_norm": 0.45028287172317505,
      "learning_rate": 0.00013675889328063244,
      "loss": 0.5149720311164856,
      "step": 110
    },
    {
      "epoch": 1.1823056300268098,
      "grad_norm": 0.34304189682006836,
      "learning_rate": 0.00013596837944664032,
      "loss": 0.375017374753952,
      "step": 111
    },
    {
      "epoch": 1.193029490616622,
      "grad_norm": 0.32003459334373474,
      "learning_rate": 0.00013517786561264823,
      "loss": 0.34155839681625366,
      "step": 112
    },
    {
      "epoch": 1.2037533512064342,
      "grad_norm": 0.3889811933040619,
      "learning_rate": 0.00013438735177865614,
      "loss": 0.40539929270744324,
      "step": 113
    },
    {
      "epoch": 1.2144772117962466,
      "grad_norm": 0.3523079752922058,
      "learning_rate": 0.00013359683794466405,
      "loss": 0.458846777677536,
      "step": 114
    },
    {
      "epoch": 1.225201072386059,
      "grad_norm": 0.37520793080329895,
      "learning_rate": 0.00013280632411067196,
      "loss": 0.39731982350349426,
      "step": 115
    },
    {
      "epoch": 1.2359249329758712,
      "grad_norm": 0.4330201745033264,
      "learning_rate": 0.00013201581027667985,
      "loss": 0.5581794381141663,
      "step": 116
    },
    {
      "epoch": 1.2466487935656836,
      "grad_norm": 0.3163258135318756,
      "learning_rate": 0.00013122529644268776,
      "loss": 0.3818089962005615,
      "step": 117
    },
    {
      "epoch": 1.257372654155496,
      "grad_norm": 0.3622339069843292,
      "learning_rate": 0.00013043478260869567,
      "loss": 0.5328987240791321,
      "step": 118
    },
    {
      "epoch": 1.2680965147453083,
      "grad_norm": 0.30175745487213135,
      "learning_rate": 0.00012964426877470358,
      "loss": 0.39232969284057617,
      "step": 119
    },
    {
      "epoch": 1.2788203753351206,
      "grad_norm": 0.3683181703090668,
      "learning_rate": 0.0001288537549407115,
      "loss": 0.3934139013290405,
      "step": 120
    },
    {
      "epoch": 1.289544235924933,
      "grad_norm": 0.3973405957221985,
      "learning_rate": 0.00012806324110671937,
      "loss": 0.43174073100090027,
      "step": 121
    },
    {
      "epoch": 1.3002680965147453,
      "grad_norm": 0.33689525723457336,
      "learning_rate": 0.00012727272727272728,
      "loss": 0.38391372561454773,
      "step": 122
    },
    {
      "epoch": 1.3109919571045576,
      "grad_norm": 0.3917376399040222,
      "learning_rate": 0.0001264822134387352,
      "loss": 0.505753219127655,
      "step": 123
    },
    {
      "epoch": 1.32171581769437,
      "grad_norm": 0.44805291295051575,
      "learning_rate": 0.0001256916996047431,
      "loss": 0.39223286509513855,
      "step": 124
    },
    {
      "epoch": 1.3324396782841823,
      "grad_norm": 0.41950568556785583,
      "learning_rate": 0.00012490118577075098,
      "loss": 0.4417312741279602,
      "step": 125
    },
    {
      "epoch": 1.3431635388739946,
      "grad_norm": 0.36143216490745544,
      "learning_rate": 0.0001241106719367589,
      "loss": 0.3527093231678009,
      "step": 126
    },
    {
      "epoch": 1.353887399463807,
      "grad_norm": 0.3897385895252228,
      "learning_rate": 0.0001233201581027668,
      "loss": 0.3796389698982239,
      "step": 127
    },
    {
      "epoch": 1.3646112600536193,
      "grad_norm": 0.36867862939834595,
      "learning_rate": 0.00012252964426877472,
      "loss": 0.3496738374233246,
      "step": 128
    },
    {
      "epoch": 1.3753351206434317,
      "grad_norm": 0.4386043846607208,
      "learning_rate": 0.00012173913043478263,
      "loss": 0.5254644751548767,
      "step": 129
    },
    {
      "epoch": 1.386058981233244,
      "grad_norm": 0.40041038393974304,
      "learning_rate": 0.00012094861660079051,
      "loss": 0.4998672604560852,
      "step": 130
    },
    {
      "epoch": 1.3967828418230563,
      "grad_norm": 0.4058981239795685,
      "learning_rate": 0.00012015810276679842,
      "loss": 0.358295202255249,
      "step": 131
    },
    {
      "epoch": 1.4075067024128687,
      "grad_norm": 0.4888080656528473,
      "learning_rate": 0.00011936758893280633,
      "loss": 0.4625028073787689,
      "step": 132
    },
    {
      "epoch": 1.418230563002681,
      "grad_norm": 0.43401890993118286,
      "learning_rate": 0.00011857707509881424,
      "loss": 0.4242851138114929,
      "step": 133
    },
    {
      "epoch": 1.4289544235924934,
      "grad_norm": 0.4579969346523285,
      "learning_rate": 0.00011778656126482215,
      "loss": 0.37796008586883545,
      "step": 134
    },
    {
      "epoch": 1.4396782841823057,
      "grad_norm": 0.4127224385738373,
      "learning_rate": 0.00011699604743083003,
      "loss": 0.38415277004241943,
      "step": 135
    },
    {
      "epoch": 1.450402144772118,
      "grad_norm": 0.47420403361320496,
      "learning_rate": 0.00011620553359683794,
      "loss": 0.42805853486061096,
      "step": 136
    },
    {
      "epoch": 1.4611260053619302,
      "grad_norm": 0.549434244632721,
      "learning_rate": 0.00011541501976284585,
      "loss": 0.449143648147583,
      "step": 137
    },
    {
      "epoch": 1.4718498659517425,
      "grad_norm": 0.45274561643600464,
      "learning_rate": 0.00011462450592885376,
      "loss": 0.42617177963256836,
      "step": 138
    },
    {
      "epoch": 1.4825737265415548,
      "grad_norm": 0.4037245213985443,
      "learning_rate": 0.00011383399209486167,
      "loss": 0.4060184955596924,
      "step": 139
    },
    {
      "epoch": 1.4932975871313672,
      "grad_norm": 0.35869210958480835,
      "learning_rate": 0.00011304347826086956,
      "loss": 0.3349171280860901,
      "step": 140
    },
    {
      "epoch": 1.5040214477211795,
      "grad_norm": 0.4207170903682709,
      "learning_rate": 0.00011225296442687747,
      "loss": 0.4263383448123932,
      "step": 141
    },
    {
      "epoch": 1.5147453083109919,
      "grad_norm": 0.5284790992736816,
      "learning_rate": 0.00011146245059288538,
      "loss": 0.5672209858894348,
      "step": 142
    },
    {
      "epoch": 1.5254691689008042,
      "grad_norm": 0.41607561707496643,
      "learning_rate": 0.00011067193675889329,
      "loss": 0.4448755979537964,
      "step": 143
    },
    {
      "epoch": 1.5361930294906165,
      "grad_norm": 0.4201499819755554,
      "learning_rate": 0.0001098814229249012,
      "loss": 0.46206071972846985,
      "step": 144
    },
    {
      "epoch": 1.5469168900804289,
      "grad_norm": 0.4577239155769348,
      "learning_rate": 0.00010909090909090909,
      "loss": 0.4559464454650879,
      "step": 145
    },
    {
      "epoch": 1.5576407506702412,
      "grad_norm": 0.3478381931781769,
      "learning_rate": 0.000108300395256917,
      "loss": 0.3294685482978821,
      "step": 146
    },
    {
      "epoch": 1.5683646112600536,
      "grad_norm": 0.4360603988170624,
      "learning_rate": 0.00010750988142292491,
      "loss": 0.3287108540534973,
      "step": 147
    },
    {
      "epoch": 1.579088471849866,
      "grad_norm": 0.39799708127975464,
      "learning_rate": 0.00010671936758893282,
      "loss": 0.3988645374774933,
      "step": 148
    },
    {
      "epoch": 1.5898123324396782,
      "grad_norm": 0.3618183732032776,
      "learning_rate": 0.00010592885375494073,
      "loss": 0.38425952196121216,
      "step": 149
    },
    {
      "epoch": 1.6005361930294906,
      "grad_norm": 0.4565318524837494,
      "learning_rate": 0.00010513833992094862,
      "loss": 0.3619772493839264,
      "step": 150
    },
    {
      "epoch": 1.611260053619303,
      "grad_norm": 0.3710864782333374,
      "learning_rate": 0.00010434782608695653,
      "loss": 0.34765082597732544,
      "step": 151
    },
    {
      "epoch": 1.6219839142091153,
      "grad_norm": 0.43709254264831543,
      "learning_rate": 0.00010355731225296444,
      "loss": 0.36712560057640076,
      "step": 152
    },
    {
      "epoch": 1.6327077747989276,
      "grad_norm": 0.41445794701576233,
      "learning_rate": 0.00010276679841897235,
      "loss": 0.46864867210388184,
      "step": 153
    },
    {
      "epoch": 1.64343163538874,
      "grad_norm": 0.4972689747810364,
      "learning_rate": 0.00010197628458498026,
      "loss": 0.46844732761383057,
      "step": 154
    },
    {
      "epoch": 1.6541554959785523,
      "grad_norm": 0.37691959738731384,
      "learning_rate": 0.00010118577075098814,
      "loss": 0.3644738793373108,
      "step": 155
    },
    {
      "epoch": 1.6648793565683646,
      "grad_norm": 0.3355158269405365,
      "learning_rate": 0.00010039525691699605,
      "loss": 0.2941320538520813,
      "step": 156
    },
    {
      "epoch": 1.675603217158177,
      "grad_norm": 0.47247281670570374,
      "learning_rate": 9.960474308300396e-05,
      "loss": 0.3141013979911804,
      "step": 157
    },
    {
      "epoch": 1.6863270777479893,
      "grad_norm": 0.46272745728492737,
      "learning_rate": 9.881422924901186e-05,
      "loss": 0.36926206946372986,
      "step": 158
    },
    {
      "epoch": 1.6970509383378016,
      "grad_norm": 0.38559988141059875,
      "learning_rate": 9.802371541501977e-05,
      "loss": 0.35696208477020264,
      "step": 159
    },
    {
      "epoch": 1.707774798927614,
      "grad_norm": 0.380924791097641,
      "learning_rate": 9.723320158102768e-05,
      "loss": 0.3731119632720947,
      "step": 160
    },
    {
      "epoch": 1.7184986595174263,
      "grad_norm": 0.3812347650527954,
      "learning_rate": 9.644268774703557e-05,
      "loss": 0.36795520782470703,
      "step": 161
    },
    {
      "epoch": 1.7292225201072386,
      "grad_norm": 0.42182034254074097,
      "learning_rate": 9.565217391304348e-05,
      "loss": 0.38642388582229614,
      "step": 162
    },
    {
      "epoch": 1.739946380697051,
      "grad_norm": 0.4464418292045593,
      "learning_rate": 9.486166007905138e-05,
      "loss": 0.3390141427516937,
      "step": 163
    },
    {
      "epoch": 1.7506702412868633,
      "grad_norm": 0.41914135217666626,
      "learning_rate": 9.407114624505929e-05,
      "loss": 0.3221234679222107,
      "step": 164
    },
    {
      "epoch": 1.7613941018766757,
      "grad_norm": 0.478661447763443,
      "learning_rate": 9.32806324110672e-05,
      "loss": 0.5106721520423889,
      "step": 165
    },
    {
      "epoch": 1.772117962466488,
      "grad_norm": 0.4210912585258484,
      "learning_rate": 9.24901185770751e-05,
      "loss": 0.38831913471221924,
      "step": 166
    },
    {
      "epoch": 1.7828418230563003,
      "grad_norm": 0.3871179223060608,
      "learning_rate": 9.169960474308301e-05,
      "loss": 0.34748589992523193,
      "step": 167
    },
    {
      "epoch": 1.7935656836461127,
      "grad_norm": 0.4435052275657654,
      "learning_rate": 9.090909090909092e-05,
      "loss": 0.48339927196502686,
      "step": 168
    },
    {
      "epoch": 1.804289544235925,
      "grad_norm": 0.4627319276332855,
      "learning_rate": 9.011857707509881e-05,
      "loss": 0.4779326319694519,
      "step": 169
    },
    {
      "epoch": 1.8150134048257374,
      "grad_norm": 0.4093571603298187,
      "learning_rate": 8.932806324110672e-05,
      "loss": 0.3994932174682617,
      "step": 170
    },
    {
      "epoch": 1.8257372654155497,
      "grad_norm": 0.3777295649051666,
      "learning_rate": 8.853754940711463e-05,
      "loss": 0.29758769273757935,
      "step": 171
    },
    {
      "epoch": 1.836461126005362,
      "grad_norm": 0.4444163143634796,
      "learning_rate": 8.774703557312254e-05,
      "loss": 0.5211812257766724,
      "step": 172
    },
    {
      "epoch": 1.8471849865951744,
      "grad_norm": 0.44008299708366394,
      "learning_rate": 8.695652173913044e-05,
      "loss": 0.4367752969264984,
      "step": 173
    },
    {
      "epoch": 1.8579088471849867,
      "grad_norm": 0.3680829703807831,
      "learning_rate": 8.616600790513835e-05,
      "loss": 0.38142716884613037,
      "step": 174
    },
    {
      "epoch": 1.868632707774799,
      "grad_norm": 0.42378222942352295,
      "learning_rate": 8.537549407114625e-05,
      "loss": 0.3738633394241333,
      "step": 175
    },
    {
      "epoch": 1.8793565683646114,
      "grad_norm": 0.447982519865036,
      "learning_rate": 8.458498023715416e-05,
      "loss": 0.3980375826358795,
      "step": 176
    },
    {
      "epoch": 1.8900804289544237,
      "grad_norm": 0.4780956506729126,
      "learning_rate": 8.379446640316207e-05,
      "loss": 0.3593772053718567,
      "step": 177
    },
    {
      "epoch": 1.900804289544236,
      "grad_norm": 0.4041815996170044,
      "learning_rate": 8.300395256916996e-05,
      "loss": 0.32343748211860657,
      "step": 178
    },
    {
      "epoch": 1.9115281501340484,
      "grad_norm": 0.40126705169677734,
      "learning_rate": 8.221343873517787e-05,
      "loss": 0.39796900749206543,
      "step": 179
    },
    {
      "epoch": 1.9222520107238605,
      "grad_norm": 0.4228574335575104,
      "learning_rate": 8.142292490118577e-05,
      "loss": 0.30352118611335754,
      "step": 180
    },
    {
      "epoch": 1.9329758713136729,
      "grad_norm": 0.3965367078781128,
      "learning_rate": 8.063241106719368e-05,
      "loss": 0.4007437229156494,
      "step": 181
    },
    {
      "epoch": 1.9436997319034852,
      "grad_norm": 0.520819365978241,
      "learning_rate": 7.984189723320159e-05,
      "loss": 0.4561784863471985,
      "step": 182
    },
    {
      "epoch": 1.9544235924932976,
      "grad_norm": 0.4546199142932892,
      "learning_rate": 7.905138339920949e-05,
      "loss": 0.42645519971847534,
      "step": 183
    },
    {
      "epoch": 1.96514745308311,
      "grad_norm": 0.4249766170978546,
      "learning_rate": 7.82608695652174e-05,
      "loss": 0.40960007905960083,
      "step": 184
    },
    {
      "epoch": 1.9758713136729222,
      "grad_norm": 0.43849310278892517,
      "learning_rate": 7.74703557312253e-05,
      "loss": 0.3888928294181824,
      "step": 185
    },
    {
      "epoch": 1.9865951742627346,
      "grad_norm": 0.3805074095726013,
      "learning_rate": 7.66798418972332e-05,
      "loss": 0.33679670095443726,
      "step": 186
    },
    {
      "epoch": 1.997319034852547,
      "grad_norm": 0.3982532024383545,
      "learning_rate": 7.58893280632411e-05,
      "loss": 0.4251680374145508,
      "step": 187
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8578111529350281,
      "learning_rate": 7.509881422924901e-05,
      "loss": 0.3112189769744873,
      "step": 188
    },
    {
      "epoch": 2.0107238605898123,
      "grad_norm": 0.3796326518058777,
      "learning_rate": 7.430830039525692e-05,
      "loss": 0.3179461658000946,
      "step": 189
    },
    {
      "epoch": 2.0214477211796247,
      "grad_norm": 0.4111069440841675,
      "learning_rate": 7.351778656126482e-05,
      "loss": 0.2951521873474121,
      "step": 190
    },
    {
      "epoch": 2.032171581769437,
      "grad_norm": 0.47031712532043457,
      "learning_rate": 7.272727272727273e-05,
      "loss": 0.356897234916687,
      "step": 191
    },
    {
      "epoch": 2.0428954423592494,
      "grad_norm": 0.42409181594848633,
      "learning_rate": 7.193675889328062e-05,
      "loss": 0.29118770360946655,
      "step": 192
    },
    {
      "epoch": 2.0536193029490617,
      "grad_norm": 0.41851696372032166,
      "learning_rate": 7.114624505928854e-05,
      "loss": 0.28936752676963806,
      "step": 193
    },
    {
      "epoch": 2.064343163538874,
      "grad_norm": 0.4010869264602661,
      "learning_rate": 7.035573122529645e-05,
      "loss": 0.26238322257995605,
      "step": 194
    },
    {
      "epoch": 2.0750670241286864,
      "grad_norm": 0.3862994313240051,
      "learning_rate": 6.956521739130436e-05,
      "loss": 0.27142423391342163,
      "step": 195
    },
    {
      "epoch": 2.0857908847184987,
      "grad_norm": 0.4864669442176819,
      "learning_rate": 6.877470355731227e-05,
      "loss": 0.37142568826675415,
      "step": 196
    },
    {
      "epoch": 2.096514745308311,
      "grad_norm": 0.4558348059654236,
      "learning_rate": 6.798418972332016e-05,
      "loss": 0.24382558465003967,
      "step": 197
    },
    {
      "epoch": 2.1072386058981234,
      "grad_norm": 0.4399399161338806,
      "learning_rate": 6.719367588932807e-05,
      "loss": 0.2435164749622345,
      "step": 198
    },
    {
      "epoch": 2.1179624664879357,
      "grad_norm": 0.4485020041465759,
      "learning_rate": 6.640316205533598e-05,
      "loss": 0.2527099549770355,
      "step": 199
    },
    {
      "epoch": 2.128686327077748,
      "grad_norm": 0.5087027549743652,
      "learning_rate": 6.561264822134388e-05,
      "loss": 0.2982422113418579,
      "step": 200
    },
    {
      "epoch": 2.1394101876675604,
      "grad_norm": 0.48561012744903564,
      "learning_rate": 6.482213438735179e-05,
      "loss": 0.2485373616218567,
      "step": 201
    },
    {
      "epoch": 2.1501340482573728,
      "grad_norm": 0.5011835098266602,
      "learning_rate": 6.403162055335969e-05,
      "loss": 0.2464626431465149,
      "step": 202
    },
    {
      "epoch": 2.160857908847185,
      "grad_norm": 0.45680928230285645,
      "learning_rate": 6.32411067193676e-05,
      "loss": 0.2839566469192505,
      "step": 203
    },
    {
      "epoch": 2.1715817694369974,
      "grad_norm": 0.4385458528995514,
      "learning_rate": 6.245059288537549e-05,
      "loss": 0.23959431052207947,
      "step": 204
    },
    {
      "epoch": 2.1823056300268098,
      "grad_norm": 0.43261128664016724,
      "learning_rate": 6.16600790513834e-05,
      "loss": 0.21801936626434326,
      "step": 205
    },
    {
      "epoch": 2.193029490616622,
      "grad_norm": 0.4627765715122223,
      "learning_rate": 6.086956521739131e-05,
      "loss": 0.23210036754608154,
      "step": 206
    },
    {
      "epoch": 2.2037533512064345,
      "grad_norm": 0.502792477607727,
      "learning_rate": 6.007905138339921e-05,
      "loss": 0.2555053234100342,
      "step": 207
    },
    {
      "epoch": 2.214477211796247,
      "grad_norm": 0.49858319759368896,
      "learning_rate": 5.928853754940712e-05,
      "loss": 0.37681910395622253,
      "step": 208
    },
    {
      "epoch": 2.225201072386059,
      "grad_norm": 0.5667821764945984,
      "learning_rate": 5.8498023715415016e-05,
      "loss": 0.31617334485054016,
      "step": 209
    },
    {
      "epoch": 2.2359249329758715,
      "grad_norm": 0.46932312846183777,
      "learning_rate": 5.7707509881422926e-05,
      "loss": 0.19316962361335754,
      "step": 210
    },
    {
      "epoch": 2.246648793565684,
      "grad_norm": 0.6215251684188843,
      "learning_rate": 5.6916996047430836e-05,
      "loss": 0.3278288245201111,
      "step": 211
    },
    {
      "epoch": 2.257372654155496,
      "grad_norm": 0.5422892570495605,
      "learning_rate": 5.612648221343873e-05,
      "loss": 0.291220486164093,
      "step": 212
    },
    {
      "epoch": 2.2680965147453085,
      "grad_norm": 0.5241540670394897,
      "learning_rate": 5.533596837944664e-05,
      "loss": 0.24275189638137817,
      "step": 213
    },
    {
      "epoch": 2.278820375335121,
      "grad_norm": 0.49944326281547546,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 0.34785425662994385,
      "step": 214
    },
    {
      "epoch": 2.289544235924933,
      "grad_norm": 0.43588748574256897,
      "learning_rate": 5.3754940711462456e-05,
      "loss": 0.2969186305999756,
      "step": 215
    },
    {
      "epoch": 2.3002680965147455,
      "grad_norm": 0.6216847896575928,
      "learning_rate": 5.2964426877470366e-05,
      "loss": 0.39824792742729187,
      "step": 216
    },
    {
      "epoch": 2.310991957104558,
      "grad_norm": 0.4306747615337372,
      "learning_rate": 5.217391304347826e-05,
      "loss": 0.2311907559633255,
      "step": 217
    },
    {
      "epoch": 2.32171581769437,
      "grad_norm": 0.40540629625320435,
      "learning_rate": 5.138339920948617e-05,
      "loss": 0.2750304937362671,
      "step": 218
    },
    {
      "epoch": 2.3324396782841825,
      "grad_norm": 0.4646793305873871,
      "learning_rate": 5.059288537549407e-05,
      "loss": 0.3514980673789978,
      "step": 219
    },
    {
      "epoch": 2.343163538873995,
      "grad_norm": 0.5125492215156555,
      "learning_rate": 4.980237154150198e-05,
      "loss": 0.2827247679233551,
      "step": 220
    },
    {
      "epoch": 2.353887399463807,
      "grad_norm": 0.4126996099948883,
      "learning_rate": 4.901185770750988e-05,
      "loss": 0.28631478548049927,
      "step": 221
    },
    {
      "epoch": 2.3646112600536195,
      "grad_norm": 0.554176926612854,
      "learning_rate": 4.822134387351779e-05,
      "loss": 0.2757015824317932,
      "step": 222
    },
    {
      "epoch": 2.3753351206434314,
      "grad_norm": 0.498518168926239,
      "learning_rate": 4.743083003952569e-05,
      "loss": 0.4271239638328552,
      "step": 223
    },
    {
      "epoch": 2.386058981233244,
      "grad_norm": 0.48358744382858276,
      "learning_rate": 4.66403162055336e-05,
      "loss": 0.24824775755405426,
      "step": 224
    },
    {
      "epoch": 2.396782841823056,
      "grad_norm": 0.4421731233596802,
      "learning_rate": 4.5849802371541504e-05,
      "loss": 0.24138133227825165,
      "step": 225
    },
    {
      "epoch": 2.4075067024128685,
      "grad_norm": 0.5678989291191101,
      "learning_rate": 4.505928853754941e-05,
      "loss": 0.3733794689178467,
      "step": 226
    },
    {
      "epoch": 2.418230563002681,
      "grad_norm": 0.3931693434715271,
      "learning_rate": 4.426877470355732e-05,
      "loss": 0.21732917428016663,
      "step": 227
    },
    {
      "epoch": 2.428954423592493,
      "grad_norm": 0.5858852863311768,
      "learning_rate": 4.347826086956522e-05,
      "loss": 0.27989453077316284,
      "step": 228
    },
    {
      "epoch": 2.4396782841823055,
      "grad_norm": 0.563900887966156,
      "learning_rate": 4.2687747035573124e-05,
      "loss": 0.24179348349571228,
      "step": 229
    },
    {
      "epoch": 2.450402144772118,
      "grad_norm": 0.560583233833313,
      "learning_rate": 4.1897233201581034e-05,
      "loss": 0.32947486639022827,
      "step": 230
    },
    {
      "epoch": 2.46112600536193,
      "grad_norm": 0.44924235343933105,
      "learning_rate": 4.110671936758894e-05,
      "loss": 0.22358451783657074,
      "step": 231
    },
    {
      "epoch": 2.4718498659517425,
      "grad_norm": 0.45432764291763306,
      "learning_rate": 4.031620553359684e-05,
      "loss": 0.27067574858665466,
      "step": 232
    },
    {
      "epoch": 2.482573726541555,
      "grad_norm": 0.593735933303833,
      "learning_rate": 3.9525691699604744e-05,
      "loss": 0.2724727988243103,
      "step": 233
    },
    {
      "epoch": 2.493297587131367,
      "grad_norm": 0.4509212374687195,
      "learning_rate": 3.873517786561265e-05,
      "loss": 0.2286791056394577,
      "step": 234
    },
    {
      "epoch": 2.5040214477211795,
      "grad_norm": 0.574708104133606,
      "learning_rate": 3.794466403162055e-05,
      "loss": 0.39047005772590637,
      "step": 235
    },
    {
      "epoch": 2.514745308310992,
      "grad_norm": 0.4967159330844879,
      "learning_rate": 3.715415019762846e-05,
      "loss": 0.3607536852359772,
      "step": 236
    },
    {
      "epoch": 2.525469168900804,
      "grad_norm": 0.5810816884040833,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 0.28996798396110535,
      "step": 237
    },
    {
      "epoch": 2.5361930294906165,
      "grad_norm": 0.605388879776001,
      "learning_rate": 3.557312252964427e-05,
      "loss": 0.3083586096763611,
      "step": 238
    },
    {
      "epoch": 2.546916890080429,
      "grad_norm": 0.5502549409866333,
      "learning_rate": 3.478260869565218e-05,
      "loss": 0.26683732867240906,
      "step": 239
    },
    {
      "epoch": 2.557640750670241,
      "grad_norm": 0.5668724179267883,
      "learning_rate": 3.399209486166008e-05,
      "loss": 0.2840242385864258,
      "step": 240
    },
    {
      "epoch": 2.5683646112600536,
      "grad_norm": 0.44743263721466064,
      "learning_rate": 3.320158102766799e-05,
      "loss": 0.2404075413942337,
      "step": 241
    },
    {
      "epoch": 2.579088471849866,
      "grad_norm": 0.7013267278671265,
      "learning_rate": 3.2411067193675894e-05,
      "loss": 0.3185945749282837,
      "step": 242
    },
    {
      "epoch": 2.5898123324396782,
      "grad_norm": 0.6694422364234924,
      "learning_rate": 3.16205533596838e-05,
      "loss": 0.28978461027145386,
      "step": 243
    },
    {
      "epoch": 2.6005361930294906,
      "grad_norm": 0.4603322446346283,
      "learning_rate": 3.08300395256917e-05,
      "loss": 0.2629821002483368,
      "step": 244
    },
    {
      "epoch": 2.611260053619303,
      "grad_norm": 0.5630055665969849,
      "learning_rate": 3.0039525691699605e-05,
      "loss": 0.2665753960609436,
      "step": 245
    },
    {
      "epoch": 2.6219839142091153,
      "grad_norm": 0.3915822207927704,
      "learning_rate": 2.9249011857707508e-05,
      "loss": 0.2179432064294815,
      "step": 246
    },
    {
      "epoch": 2.6327077747989276,
      "grad_norm": 0.5798822045326233,
      "learning_rate": 2.8458498023715418e-05,
      "loss": 0.31813907623291016,
      "step": 247
    },
    {
      "epoch": 2.64343163538874,
      "grad_norm": 0.5073499083518982,
      "learning_rate": 2.766798418972332e-05,
      "loss": 0.2670523524284363,
      "step": 248
    },
    {
      "epoch": 2.6541554959785523,
      "grad_norm": 0.44620683789253235,
      "learning_rate": 2.6877470355731228e-05,
      "loss": 0.25869786739349365,
      "step": 249
    },
    {
      "epoch": 2.6648793565683646,
      "grad_norm": 0.5914870500564575,
      "learning_rate": 2.608695652173913e-05,
      "loss": 0.3205704391002655,
      "step": 250
    },
    {
      "epoch": 2.675603217158177,
      "grad_norm": 0.5035210251808167,
      "learning_rate": 2.5296442687747035e-05,
      "loss": 0.2746676504611969,
      "step": 251
    },
    {
      "epoch": 2.6863270777479893,
      "grad_norm": 0.4630255103111267,
      "learning_rate": 2.450592885375494e-05,
      "loss": 0.262162446975708,
      "step": 252
    },
    {
      "epoch": 2.6970509383378016,
      "grad_norm": 0.5340390205383301,
      "learning_rate": 2.3715415019762845e-05,
      "loss": 0.22825723886489868,
      "step": 253
    },
    {
      "epoch": 2.707774798927614,
      "grad_norm": 0.555592954158783,
      "learning_rate": 2.2924901185770752e-05,
      "loss": 0.24794229865074158,
      "step": 254
    },
    {
      "epoch": 2.7184986595174263,
      "grad_norm": 0.4784729480743408,
      "learning_rate": 2.213438735177866e-05,
      "loss": 0.20105186104774475,
      "step": 255
    },
    {
      "epoch": 2.7292225201072386,
      "grad_norm": 0.7181131839752197,
      "learning_rate": 2.1343873517786562e-05,
      "loss": 0.3564614951610565,
      "step": 256
    },
    {
      "epoch": 2.739946380697051,
      "grad_norm": 0.4376419484615326,
      "learning_rate": 2.055335968379447e-05,
      "loss": 0.20554706454277039,
      "step": 257
    },
    {
      "epoch": 2.7506702412868633,
      "grad_norm": 0.5815340876579285,
      "learning_rate": 1.9762845849802372e-05,
      "loss": 0.2694174349308014,
      "step": 258
    },
    {
      "epoch": 2.7613941018766757,
      "grad_norm": 0.48075157403945923,
      "learning_rate": 1.8972332015810275e-05,
      "loss": 0.21963372826576233,
      "step": 259
    },
    {
      "epoch": 2.772117962466488,
      "grad_norm": 0.620573103427887,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.3293127715587616,
      "step": 260
    },
    {
      "epoch": 2.7828418230563003,
      "grad_norm": 0.5430031418800354,
      "learning_rate": 1.739130434782609e-05,
      "loss": 0.25511273741722107,
      "step": 261
    },
    {
      "epoch": 2.7935656836461127,
      "grad_norm": 0.6154038906097412,
      "learning_rate": 1.6600790513833996e-05,
      "loss": 0.28183019161224365,
      "step": 262
    },
    {
      "epoch": 2.804289544235925,
      "grad_norm": 0.5438246726989746,
      "learning_rate": 1.58102766798419e-05,
      "loss": 0.2609254717826843,
      "step": 263
    },
    {
      "epoch": 2.8150134048257374,
      "grad_norm": 0.671107828617096,
      "learning_rate": 1.5019762845849802e-05,
      "loss": 0.3069862723350525,
      "step": 264
    },
    {
      "epoch": 2.8257372654155497,
      "grad_norm": 0.5226935148239136,
      "learning_rate": 1.4229249011857709e-05,
      "loss": 0.2255355566740036,
      "step": 265
    },
    {
      "epoch": 2.836461126005362,
      "grad_norm": 0.5719597339630127,
      "learning_rate": 1.3438735177865614e-05,
      "loss": 0.2844502329826355,
      "step": 266
    },
    {
      "epoch": 2.8471849865951744,
      "grad_norm": 0.5313884615898132,
      "learning_rate": 1.2648221343873517e-05,
      "loss": 0.3107653558254242,
      "step": 267
    },
    {
      "epoch": 2.8579088471849867,
      "grad_norm": 0.5169429183006287,
      "learning_rate": 1.1857707509881423e-05,
      "loss": 0.2877541184425354,
      "step": 268
    },
    {
      "epoch": 2.868632707774799,
      "grad_norm": 0.5085014700889587,
      "learning_rate": 1.106719367588933e-05,
      "loss": 0.21509462594985962,
      "step": 269
    },
    {
      "epoch": 2.8793565683646114,
      "grad_norm": 0.4762232005596161,
      "learning_rate": 1.0276679841897234e-05,
      "loss": 0.23946139216423035,
      "step": 270
    },
    {
      "epoch": 2.8900804289544237,
      "grad_norm": 0.5875873565673828,
      "learning_rate": 9.486166007905138e-06,
      "loss": 0.288002073764801,
      "step": 271
    },
    {
      "epoch": 2.900804289544236,
      "grad_norm": 0.6287146210670471,
      "learning_rate": 8.695652173913044e-06,
      "loss": 0.28586676716804504,
      "step": 272
    },
    {
      "epoch": 2.9115281501340484,
      "grad_norm": 0.5751309990882874,
      "learning_rate": 7.90513833992095e-06,
      "loss": 0.26002803444862366,
      "step": 273
    },
    {
      "epoch": 2.9222520107238603,
      "grad_norm": 0.5319899916648865,
      "learning_rate": 7.1146245059288545e-06,
      "loss": 0.2816118597984314,
      "step": 274
    },
    {
      "epoch": 2.9329758713136727,
      "grad_norm": 0.580845057964325,
      "learning_rate": 6.324110671936759e-06,
      "loss": 0.2594989538192749,
      "step": 275
    },
    {
      "epoch": 2.943699731903485,
      "grad_norm": 0.6090609431266785,
      "learning_rate": 5.533596837944665e-06,
      "loss": 0.30808189511299133,
      "step": 276
    },
    {
      "epoch": 2.9544235924932973,
      "grad_norm": 0.5708959698677063,
      "learning_rate": 4.743083003952569e-06,
      "loss": 0.3111344873905182,
      "step": 277
    },
    {
      "epoch": 2.9651474530831097,
      "grad_norm": 0.4517657458782196,
      "learning_rate": 3.952569169960475e-06,
      "loss": 0.244952991604805,
      "step": 278
    },
    {
      "epoch": 2.975871313672922,
      "grad_norm": 0.4914667308330536,
      "learning_rate": 3.1620553359683794e-06,
      "loss": 0.25697410106658936,
      "step": 279
    },
    {
      "epoch": 2.9865951742627344,
      "grad_norm": 0.5489192008972168,
      "learning_rate": 2.3715415019762844e-06,
      "loss": 0.2900347113609314,
      "step": 280
    },
    {
      "epoch": 2.9973190348525467,
      "grad_norm": 0.5205079317092896,
      "learning_rate": 1.5810276679841897e-06,
      "loss": 0.2045833170413971,
      "step": 281
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.3801476955413818,
      "learning_rate": 7.905138339920948e-07,
      "loss": 0.26903223991394043,
      "step": 282
    }
  ],
  "logging_steps": 1,
  "max_steps": 282,
  "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": 4.313385319070822e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}