{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4466546112115732,
  "eval_steps": 1000,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007233273056057866,
      "grad_norm": 0.41587013006210327,
      "learning_rate": 2e-05,
      "loss": 1.4019,
      "step": 1
    },
    {
      "epoch": 0.014466546112115732,
      "grad_norm": 0.44406870007514954,
      "learning_rate": 4e-05,
      "loss": 1.3296,
      "step": 2
    },
    {
      "epoch": 0.0216998191681736,
      "grad_norm": 0.36022505164146423,
      "learning_rate": 6e-05,
      "loss": 1.2996,
      "step": 3
    },
    {
      "epoch": 0.028933092224231464,
      "grad_norm": 0.4058440923690796,
      "learning_rate": 8e-05,
      "loss": 1.3372,
      "step": 4
    },
    {
      "epoch": 0.03616636528028933,
      "grad_norm": 0.22433464229106903,
      "learning_rate": 0.0001,
      "loss": 1.2748,
      "step": 5
    },
    {
      "epoch": 0.0433996383363472,
      "grad_norm": 0.1584281474351883,
      "learning_rate": 9.963099630996311e-05,
      "loss": 1.1955,
      "step": 6
    },
    {
      "epoch": 0.05063291139240506,
      "grad_norm": 0.1598576456308365,
      "learning_rate": 9.92619926199262e-05,
      "loss": 1.132,
      "step": 7
    },
    {
      "epoch": 0.05786618444846293,
      "grad_norm": 1.4637757539749146,
      "learning_rate": 9.889298892988931e-05,
      "loss": 1.1369,
      "step": 8
    },
    {
      "epoch": 0.0650994575045208,
      "grad_norm": 0.18311572074890137,
      "learning_rate": 9.85239852398524e-05,
      "loss": 1.0405,
      "step": 9
    },
    {
      "epoch": 0.07233273056057866,
      "grad_norm": 1.6665862798690796,
      "learning_rate": 9.81549815498155e-05,
      "loss": 0.9399,
      "step": 10
    },
    {
      "epoch": 0.07956600361663653,
      "grad_norm": 0.3348374366760254,
      "learning_rate": 9.77859778597786e-05,
      "loss": 0.8621,
      "step": 11
    },
    {
      "epoch": 0.0867992766726944,
      "grad_norm": 0.3106568157672882,
      "learning_rate": 9.74169741697417e-05,
      "loss": 0.7543,
      "step": 12
    },
    {
      "epoch": 0.09403254972875226,
      "grad_norm": 0.4362149238586426,
      "learning_rate": 9.70479704797048e-05,
      "loss": 0.7134,
      "step": 13
    },
    {
      "epoch": 0.10126582278481013,
      "grad_norm": 0.26037415862083435,
      "learning_rate": 9.66789667896679e-05,
      "loss": 0.6487,
      "step": 14
    },
    {
      "epoch": 0.10849909584086799,
      "grad_norm": 0.2504118084907532,
      "learning_rate": 9.6309963099631e-05,
      "loss": 0.56,
      "step": 15
    },
    {
      "epoch": 0.11573236889692586,
      "grad_norm": 0.18326584994792938,
      "learning_rate": 9.59409594095941e-05,
      "loss": 0.5336,
      "step": 16
    },
    {
      "epoch": 0.12296564195298372,
      "grad_norm": 0.13953259587287903,
      "learning_rate": 9.55719557195572e-05,
      "loss": 0.5503,
      "step": 17
    },
    {
      "epoch": 0.1301989150090416,
      "grad_norm": 0.1669919639825821,
      "learning_rate": 9.52029520295203e-05,
      "loss": 0.4679,
      "step": 18
    },
    {
      "epoch": 0.13743218806509946,
      "grad_norm": 0.1242203637957573,
      "learning_rate": 9.48339483394834e-05,
      "loss": 0.5007,
      "step": 19
    },
    {
      "epoch": 0.14466546112115733,
      "grad_norm": 0.1188986673951149,
      "learning_rate": 9.44649446494465e-05,
      "loss": 0.4713,
      "step": 20
    },
    {
      "epoch": 0.1518987341772152,
      "grad_norm": 0.10761572420597076,
      "learning_rate": 9.40959409594096e-05,
      "loss": 0.5056,
      "step": 21
    },
    {
      "epoch": 0.15913200723327306,
      "grad_norm": 0.0960497260093689,
      "learning_rate": 9.37269372693727e-05,
      "loss": 0.4628,
      "step": 22
    },
    {
      "epoch": 0.16636528028933092,
      "grad_norm": 0.09519140422344208,
      "learning_rate": 9.33579335793358e-05,
      "loss": 0.5124,
      "step": 23
    },
    {
      "epoch": 0.1735985533453888,
      "grad_norm": 0.09196989238262177,
      "learning_rate": 9.298892988929889e-05,
      "loss": 0.4828,
      "step": 24
    },
    {
      "epoch": 0.18083182640144665,
      "grad_norm": 0.0806601420044899,
      "learning_rate": 9.2619926199262e-05,
      "loss": 0.4565,
      "step": 25
    },
    {
      "epoch": 0.18806509945750452,
      "grad_norm": 0.09966598451137543,
      "learning_rate": 9.22509225092251e-05,
      "loss": 0.4614,
      "step": 26
    },
    {
      "epoch": 0.19529837251356238,
      "grad_norm": 0.0852133184671402,
      "learning_rate": 9.18819188191882e-05,
      "loss": 0.5014,
      "step": 27
    },
    {
      "epoch": 0.20253164556962025,
      "grad_norm": 0.1128767654299736,
      "learning_rate": 9.15129151291513e-05,
      "loss": 0.4671,
      "step": 28
    },
    {
      "epoch": 0.20976491862567812,
      "grad_norm": 0.08861073851585388,
      "learning_rate": 9.11439114391144e-05,
      "loss": 0.4635,
      "step": 29
    },
    {
      "epoch": 0.21699819168173598,
      "grad_norm": 0.08107278496026993,
      "learning_rate": 9.077490774907749e-05,
      "loss": 0.4796,
      "step": 30
    },
    {
      "epoch": 0.22423146473779385,
      "grad_norm": 0.08996085822582245,
      "learning_rate": 9.040590405904059e-05,
      "loss": 0.4691,
      "step": 31
    },
    {
      "epoch": 0.2314647377938517,
      "grad_norm": 0.11098525673151016,
      "learning_rate": 9.00369003690037e-05,
      "loss": 0.4796,
      "step": 32
    },
    {
      "epoch": 0.23869801084990958,
      "grad_norm": 0.09458429366350174,
      "learning_rate": 8.966789667896679e-05,
      "loss": 0.4645,
      "step": 33
    },
    {
      "epoch": 0.24593128390596744,
      "grad_norm": 0.09619155526161194,
      "learning_rate": 8.92988929889299e-05,
      "loss": 0.4653,
      "step": 34
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 0.0921136811375618,
      "learning_rate": 8.892988929889299e-05,
      "loss": 0.4627,
      "step": 35
    },
    {
      "epoch": 0.2603978300180832,
      "grad_norm": 0.0855991542339325,
      "learning_rate": 8.85608856088561e-05,
      "loss": 0.4703,
      "step": 36
    },
    {
      "epoch": 0.26763110307414106,
      "grad_norm": 0.08778424561023712,
      "learning_rate": 8.819188191881919e-05,
      "loss": 0.4555,
      "step": 37
    },
    {
      "epoch": 0.27486437613019893,
      "grad_norm": 0.08391483128070831,
      "learning_rate": 8.782287822878229e-05,
      "loss": 0.4438,
      "step": 38
    },
    {
      "epoch": 0.2820976491862568,
      "grad_norm": 0.084780752658844,
      "learning_rate": 8.74538745387454e-05,
      "loss": 0.4674,
      "step": 39
    },
    {
      "epoch": 0.28933092224231466,
      "grad_norm": 0.10035159438848495,
      "learning_rate": 8.708487084870849e-05,
      "loss": 0.3861,
      "step": 40
    },
    {
      "epoch": 0.2965641952983725,
      "grad_norm": 0.08539566397666931,
      "learning_rate": 8.67158671586716e-05,
      "loss": 0.4729,
      "step": 41
    },
    {
      "epoch": 0.3037974683544304,
      "grad_norm": 0.0902961790561676,
      "learning_rate": 8.634686346863469e-05,
      "loss": 0.4292,
      "step": 42
    },
    {
      "epoch": 0.31103074141048825,
      "grad_norm": 0.08653435111045837,
      "learning_rate": 8.59778597785978e-05,
      "loss": 0.4643,
      "step": 43
    },
    {
      "epoch": 0.3182640144665461,
      "grad_norm": 0.079147107899189,
      "learning_rate": 8.560885608856088e-05,
      "loss": 0.4705,
      "step": 44
    },
    {
      "epoch": 0.325497287522604,
      "grad_norm": 0.10212749987840652,
      "learning_rate": 8.523985239852399e-05,
      "loss": 0.4731,
      "step": 45
    },
    {
      "epoch": 0.33273056057866185,
      "grad_norm": 0.10761305689811707,
      "learning_rate": 8.48708487084871e-05,
      "loss": 0.4227,
      "step": 46
    },
    {
      "epoch": 0.3399638336347197,
      "grad_norm": 0.08965682238340378,
      "learning_rate": 8.450184501845019e-05,
      "loss": 0.4233,
      "step": 47
    },
    {
      "epoch": 0.3471971066907776,
      "grad_norm": 0.08309852331876755,
      "learning_rate": 8.41328413284133e-05,
      "loss": 0.4551,
      "step": 48
    },
    {
      "epoch": 0.35443037974683544,
      "grad_norm": 0.07594166696071625,
      "learning_rate": 8.376383763837639e-05,
      "loss": 0.4217,
      "step": 49
    },
    {
      "epoch": 0.3616636528028933,
      "grad_norm": 0.08812757581472397,
      "learning_rate": 8.339483394833948e-05,
      "loss": 0.4255,
      "step": 50
    },
    {
      "epoch": 0.3688969258589512,
      "grad_norm": 0.08730728924274445,
      "learning_rate": 8.302583025830258e-05,
      "loss": 0.4128,
      "step": 51
    },
    {
      "epoch": 0.37613019891500904,
      "grad_norm": 0.09240879118442535,
      "learning_rate": 8.265682656826569e-05,
      "loss": 0.4653,
      "step": 52
    },
    {
      "epoch": 0.3833634719710669,
      "grad_norm": 0.08884631842374802,
      "learning_rate": 8.228782287822878e-05,
      "loss": 0.4742,
      "step": 53
    },
    {
      "epoch": 0.39059674502712477,
      "grad_norm": 0.0874699056148529,
      "learning_rate": 8.191881918819189e-05,
      "loss": 0.3974,
      "step": 54
    },
    {
      "epoch": 0.39783001808318263,
      "grad_norm": 0.08770371228456497,
      "learning_rate": 8.154981549815498e-05,
      "loss": 0.4451,
      "step": 55
    },
    {
      "epoch": 0.4050632911392405,
      "grad_norm": 0.08077302575111389,
      "learning_rate": 8.118081180811809e-05,
      "loss": 0.4346,
      "step": 56
    },
    {
      "epoch": 0.41229656419529837,
      "grad_norm": 0.09575826674699783,
      "learning_rate": 8.081180811808118e-05,
      "loss": 0.4494,
      "step": 57
    },
    {
      "epoch": 0.41952983725135623,
      "grad_norm": 0.08907500654459,
      "learning_rate": 8.044280442804428e-05,
      "loss": 0.4918,
      "step": 58
    },
    {
      "epoch": 0.4267631103074141,
      "grad_norm": 0.0987161323428154,
      "learning_rate": 8.007380073800739e-05,
      "loss": 0.4145,
      "step": 59
    },
    {
      "epoch": 0.43399638336347196,
      "grad_norm": 0.07847721874713898,
      "learning_rate": 7.970479704797048e-05,
      "loss": 0.4415,
      "step": 60
    },
    {
      "epoch": 0.4412296564195298,
      "grad_norm": 0.08011084794998169,
      "learning_rate": 7.933579335793359e-05,
      "loss": 0.398,
      "step": 61
    },
    {
      "epoch": 0.4484629294755877,
      "grad_norm": 0.0902714878320694,
      "learning_rate": 7.896678966789668e-05,
      "loss": 0.4167,
      "step": 62
    },
    {
      "epoch": 0.45569620253164556,
      "grad_norm": 0.0794120728969574,
      "learning_rate": 7.859778597785979e-05,
      "loss": 0.388,
      "step": 63
    },
    {
      "epoch": 0.4629294755877034,
      "grad_norm": 0.07921893149614334,
      "learning_rate": 7.822878228782288e-05,
      "loss": 0.4366,
      "step": 64
    },
    {
      "epoch": 0.4701627486437613,
      "grad_norm": 0.09170780330896378,
      "learning_rate": 7.785977859778598e-05,
      "loss": 0.4349,
      "step": 65
    },
    {
      "epoch": 0.47739602169981915,
      "grad_norm": 0.084025539457798,
      "learning_rate": 7.749077490774908e-05,
      "loss": 0.4183,
      "step": 66
    },
    {
      "epoch": 0.484629294755877,
      "grad_norm": 0.08458651602268219,
      "learning_rate": 7.712177121771218e-05,
      "loss": 0.405,
      "step": 67
    },
    {
      "epoch": 0.4918625678119349,
      "grad_norm": 0.09312830120325089,
      "learning_rate": 7.675276752767529e-05,
      "loss": 0.4499,
      "step": 68
    },
    {
      "epoch": 0.49909584086799275,
      "grad_norm": 0.09968719631433487,
      "learning_rate": 7.638376383763838e-05,
      "loss": 0.4457,
      "step": 69
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.0874272808432579,
      "learning_rate": 7.601476014760149e-05,
      "loss": 0.418,
      "step": 70
    },
    {
      "epoch": 0.5135623869801085,
      "grad_norm": 0.23602771759033203,
      "learning_rate": 7.564575645756458e-05,
      "loss": 0.4256,
      "step": 71
    },
    {
      "epoch": 0.5207956600361664,
      "grad_norm": 0.08977050334215164,
      "learning_rate": 7.527675276752768e-05,
      "loss": 0.4294,
      "step": 72
    },
    {
      "epoch": 0.5280289330922242,
      "grad_norm": 0.10940728336572647,
      "learning_rate": 7.490774907749077e-05,
      "loss": 0.4049,
      "step": 73
    },
    {
      "epoch": 0.5352622061482821,
      "grad_norm": 0.08830838650465012,
      "learning_rate": 7.453874538745388e-05,
      "loss": 0.4485,
      "step": 74
    },
    {
      "epoch": 0.5424954792043399,
      "grad_norm": 0.1179407611489296,
      "learning_rate": 7.416974169741697e-05,
      "loss": 0.4356,
      "step": 75
    },
    {
      "epoch": 0.5497287522603979,
      "grad_norm": 0.08437330275774002,
      "learning_rate": 7.380073800738008e-05,
      "loss": 0.4223,
      "step": 76
    },
    {
      "epoch": 0.5569620253164557,
      "grad_norm": 0.08194423466920853,
      "learning_rate": 7.343173431734319e-05,
      "loss": 0.4233,
      "step": 77
    },
    {
      "epoch": 0.5641952983725136,
      "grad_norm": 0.10404617339372635,
      "learning_rate": 7.306273062730628e-05,
      "loss": 0.4049,
      "step": 78
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.07664304226636887,
      "learning_rate": 7.269372693726938e-05,
      "loss": 0.4025,
      "step": 79
    },
    {
      "epoch": 0.5786618444846293,
      "grad_norm": 0.07666060328483582,
      "learning_rate": 7.232472324723247e-05,
      "loss": 0.3881,
      "step": 80
    },
    {
      "epoch": 0.5858951175406871,
      "grad_norm": 0.08287478983402252,
      "learning_rate": 7.195571955719558e-05,
      "loss": 0.413,
      "step": 81
    },
    {
      "epoch": 0.593128390596745,
      "grad_norm": 0.13137191534042358,
      "learning_rate": 7.158671586715867e-05,
      "loss": 0.3793,
      "step": 82
    },
    {
      "epoch": 0.6003616636528029,
      "grad_norm": 0.07782291620969772,
      "learning_rate": 7.121771217712178e-05,
      "loss": 0.4577,
      "step": 83
    },
    {
      "epoch": 0.6075949367088608,
      "grad_norm": 0.07620645314455032,
      "learning_rate": 7.084870848708487e-05,
      "loss": 0.4075,
      "step": 84
    },
    {
      "epoch": 0.6148282097649186,
      "grad_norm": 0.07860767841339111,
      "learning_rate": 7.047970479704797e-05,
      "loss": 0.3953,
      "step": 85
    },
    {
      "epoch": 0.6220614828209765,
      "grad_norm": 0.08548825234174728,
      "learning_rate": 7.011070110701108e-05,
      "loss": 0.3983,
      "step": 86
    },
    {
      "epoch": 0.6292947558770343,
      "grad_norm": 0.08447708934545517,
      "learning_rate": 6.974169741697417e-05,
      "loss": 0.3816,
      "step": 87
    },
    {
      "epoch": 0.6365280289330922,
      "grad_norm": 0.09994114190340042,
      "learning_rate": 6.937269372693728e-05,
      "loss": 0.453,
      "step": 88
    },
    {
      "epoch": 0.64376130198915,
      "grad_norm": 0.0818142294883728,
      "learning_rate": 6.900369003690037e-05,
      "loss": 0.4038,
      "step": 89
    },
    {
      "epoch": 0.650994575045208,
      "grad_norm": 0.1171378344297409,
      "learning_rate": 6.863468634686348e-05,
      "loss": 0.4143,
      "step": 90
    },
    {
      "epoch": 0.6582278481012658,
      "grad_norm": 0.08540075272321701,
      "learning_rate": 6.826568265682657e-05,
      "loss": 0.4273,
      "step": 91
    },
    {
      "epoch": 0.6654611211573237,
      "grad_norm": 0.08481594175100327,
      "learning_rate": 6.789667896678967e-05,
      "loss": 0.4258,
      "step": 92
    },
    {
      "epoch": 0.6726943942133815,
      "grad_norm": 0.11805010586977005,
      "learning_rate": 6.752767527675276e-05,
      "loss": 0.4122,
      "step": 93
    },
    {
      "epoch": 0.6799276672694394,
      "grad_norm": 0.09864703565835953,
      "learning_rate": 6.715867158671587e-05,
      "loss": 0.4385,
      "step": 94
    },
    {
      "epoch": 0.6871609403254972,
      "grad_norm": 0.08949287980794907,
      "learning_rate": 6.678966789667896e-05,
      "loss": 0.4023,
      "step": 95
    },
    {
      "epoch": 0.6943942133815552,
      "grad_norm": 0.1031746193766594,
      "learning_rate": 6.642066420664207e-05,
      "loss": 0.4477,
      "step": 96
    },
    {
      "epoch": 0.701627486437613,
      "grad_norm": 0.09214156121015549,
      "learning_rate": 6.605166051660518e-05,
      "loss": 0.4245,
      "step": 97
    },
    {
      "epoch": 0.7088607594936709,
      "grad_norm": 0.08504794538021088,
      "learning_rate": 6.568265682656827e-05,
      "loss": 0.4031,
      "step": 98
    },
    {
      "epoch": 0.7160940325497287,
      "grad_norm": 0.08531343191862106,
      "learning_rate": 6.531365313653137e-05,
      "loss": 0.4216,
      "step": 99
    },
    {
      "epoch": 0.7233273056057866,
      "grad_norm": 0.08720685541629791,
      "learning_rate": 6.494464944649446e-05,
      "loss": 0.4259,
      "step": 100
    },
    {
      "epoch": 0.7305605786618445,
      "grad_norm": 0.09215860813856125,
      "learning_rate": 6.457564575645757e-05,
      "loss": 0.4344,
      "step": 101
    },
    {
      "epoch": 0.7377938517179023,
      "grad_norm": 0.15789636969566345,
      "learning_rate": 6.420664206642066e-05,
      "loss": 0.397,
      "step": 102
    },
    {
      "epoch": 0.7450271247739603,
      "grad_norm": 0.0937284305691719,
      "learning_rate": 6.383763837638377e-05,
      "loss": 0.3967,
      "step": 103
    },
    {
      "epoch": 0.7522603978300181,
      "grad_norm": 0.08737578988075256,
      "learning_rate": 6.346863468634686e-05,
      "loss": 0.4398,
      "step": 104
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 0.09929600358009338,
      "learning_rate": 6.309963099630997e-05,
      "loss": 0.3853,
      "step": 105
    },
    {
      "epoch": 0.7667269439421338,
      "grad_norm": 0.08004901558160782,
      "learning_rate": 6.273062730627307e-05,
      "loss": 0.4303,
      "step": 106
    },
    {
      "epoch": 0.7739602169981917,
      "grad_norm": 0.12077657133340836,
      "learning_rate": 6.236162361623616e-05,
      "loss": 0.4028,
      "step": 107
    },
    {
      "epoch": 0.7811934900542495,
      "grad_norm": 0.09763742983341217,
      "learning_rate": 6.199261992619927e-05,
      "loss": 0.3978,
      "step": 108
    },
    {
      "epoch": 0.7884267631103075,
      "grad_norm": 0.09035875648260117,
      "learning_rate": 6.162361623616236e-05,
      "loss": 0.4255,
      "step": 109
    },
    {
      "epoch": 0.7956600361663653,
      "grad_norm": 0.08758627623319626,
      "learning_rate": 6.125461254612547e-05,
      "loss": 0.4174,
      "step": 110
    },
    {
      "epoch": 0.8028933092224232,
      "grad_norm": 0.08751779049634933,
      "learning_rate": 6.0885608856088563e-05,
      "loss": 0.3956,
      "step": 111
    },
    {
      "epoch": 0.810126582278481,
      "grad_norm": 0.08873230963945389,
      "learning_rate": 6.0516605166051664e-05,
      "loss": 0.3919,
      "step": 112
    },
    {
      "epoch": 0.8173598553345389,
      "grad_norm": 0.093721404671669,
      "learning_rate": 6.014760147601476e-05,
      "loss": 0.3987,
      "step": 113
    },
    {
      "epoch": 0.8245931283905967,
      "grad_norm": 0.09308823943138123,
      "learning_rate": 5.9778597785977866e-05,
      "loss": 0.4344,
      "step": 114
    },
    {
      "epoch": 0.8318264014466547,
      "grad_norm": 0.09041070193052292,
      "learning_rate": 5.940959409594096e-05,
      "loss": 0.4278,
      "step": 115
    },
    {
      "epoch": 0.8390596745027125,
      "grad_norm": 0.08302716165781021,
      "learning_rate": 5.904059040590406e-05,
      "loss": 0.3806,
      "step": 116
    },
    {
      "epoch": 0.8462929475587704,
      "grad_norm": 0.09246783703565598,
      "learning_rate": 5.867158671586717e-05,
      "loss": 0.4459,
      "step": 117
    },
    {
      "epoch": 0.8535262206148282,
      "grad_norm": 0.09770411998033524,
      "learning_rate": 5.830258302583026e-05,
      "loss": 0.4026,
      "step": 118
    },
    {
      "epoch": 0.8607594936708861,
      "grad_norm": 0.08586518466472626,
      "learning_rate": 5.7933579335793364e-05,
      "loss": 0.3768,
      "step": 119
    },
    {
      "epoch": 0.8679927667269439,
      "grad_norm": 0.09560060501098633,
      "learning_rate": 5.756457564575646e-05,
      "loss": 0.4223,
      "step": 120
    },
    {
      "epoch": 0.8752260397830018,
      "grad_norm": 0.11039328575134277,
      "learning_rate": 5.7195571955719566e-05,
      "loss": 0.4136,
      "step": 121
    },
    {
      "epoch": 0.8824593128390597,
      "grad_norm": 0.09169413149356842,
      "learning_rate": 5.682656826568265e-05,
      "loss": 0.4136,
      "step": 122
    },
    {
      "epoch": 0.8896925858951176,
      "grad_norm": 0.08437476307153702,
      "learning_rate": 5.645756457564576e-05,
      "loss": 0.4148,
      "step": 123
    },
    {
      "epoch": 0.8969258589511754,
      "grad_norm": 0.09134487807750702,
      "learning_rate": 5.6088560885608855e-05,
      "loss": 0.3816,
      "step": 124
    },
    {
      "epoch": 0.9041591320072333,
      "grad_norm": 0.10290499776601791,
      "learning_rate": 5.5719557195571956e-05,
      "loss": 0.4165,
      "step": 125
    },
    {
      "epoch": 0.9113924050632911,
      "grad_norm": 0.09082211554050446,
      "learning_rate": 5.535055350553506e-05,
      "loss": 0.4035,
      "step": 126
    },
    {
      "epoch": 0.918625678119349,
      "grad_norm": 0.08819489926099777,
      "learning_rate": 5.498154981549816e-05,
      "loss": 0.3979,
      "step": 127
    },
    {
      "epoch": 0.9258589511754068,
      "grad_norm": 0.13042791187763214,
      "learning_rate": 5.461254612546126e-05,
      "loss": 0.3724,
      "step": 128
    },
    {
      "epoch": 0.9330922242314648,
      "grad_norm": 0.08860334753990173,
      "learning_rate": 5.424354243542435e-05,
      "loss": 0.4137,
      "step": 129
    },
    {
      "epoch": 0.9403254972875226,
      "grad_norm": 0.09522847831249237,
      "learning_rate": 5.387453874538746e-05,
      "loss": 0.434,
      "step": 130
    },
    {
      "epoch": 0.9475587703435805,
      "grad_norm": 0.11293577402830124,
      "learning_rate": 5.3505535055350554e-05,
      "loss": 0.3895,
      "step": 131
    },
    {
      "epoch": 0.9547920433996383,
      "grad_norm": 0.08971936255693436,
      "learning_rate": 5.3136531365313655e-05,
      "loss": 0.4036,
      "step": 132
    },
    {
      "epoch": 0.9620253164556962,
      "grad_norm": 0.0903216153383255,
      "learning_rate": 5.276752767527675e-05,
      "loss": 0.409,
      "step": 133
    },
    {
      "epoch": 0.969258589511754,
      "grad_norm": 0.09261274337768555,
      "learning_rate": 5.239852398523986e-05,
      "loss": 0.4091,
      "step": 134
    },
    {
      "epoch": 0.976491862567812,
      "grad_norm": 0.08835142105817795,
      "learning_rate": 5.202952029520295e-05,
      "loss": 0.4108,
      "step": 135
    },
    {
      "epoch": 0.9837251356238698,
      "grad_norm": 0.09010673314332962,
      "learning_rate": 5.166051660516605e-05,
      "loss": 0.3736,
      "step": 136
    },
    {
      "epoch": 0.9909584086799277,
      "grad_norm": 0.09533007442951202,
      "learning_rate": 5.129151291512916e-05,
      "loss": 0.3847,
      "step": 137
    },
    {
      "epoch": 0.9981916817359855,
      "grad_norm": 0.10801621526479721,
      "learning_rate": 5.0922509225092254e-05,
      "loss": 0.4156,
      "step": 138
    },
    {
      "epoch": 1.0054249547920433,
      "grad_norm": 0.11016502231359482,
      "learning_rate": 5.0553505535055354e-05,
      "loss": 0.3826,
      "step": 139
    },
    {
      "epoch": 1.0126582278481013,
      "grad_norm": 0.0894998237490654,
      "learning_rate": 5.018450184501845e-05,
      "loss": 0.3728,
      "step": 140
    },
    {
      "epoch": 1.0198915009041591,
      "grad_norm": 0.09203777462244034,
      "learning_rate": 4.9815498154981556e-05,
      "loss": 0.3744,
      "step": 141
    },
    {
      "epoch": 1.027124773960217,
      "grad_norm": 0.09373292326927185,
      "learning_rate": 4.944649446494466e-05,
      "loss": 0.3901,
      "step": 142
    },
    {
      "epoch": 1.0343580470162748,
      "grad_norm": 0.09995180368423462,
      "learning_rate": 4.907749077490775e-05,
      "loss": 0.4163,
      "step": 143
    },
    {
      "epoch": 1.0415913200723328,
      "grad_norm": 0.09669777750968933,
      "learning_rate": 4.870848708487085e-05,
      "loss": 0.3637,
      "step": 144
    },
    {
      "epoch": 1.0488245931283906,
      "grad_norm": 0.09966889768838882,
      "learning_rate": 4.833948339483395e-05,
      "loss": 0.3968,
      "step": 145
    },
    {
      "epoch": 1.0560578661844484,
      "grad_norm": 0.09891881793737411,
      "learning_rate": 4.797047970479705e-05,
      "loss": 0.3493,
      "step": 146
    },
    {
      "epoch": 1.0632911392405062,
      "grad_norm": 0.10730701684951782,
      "learning_rate": 4.760147601476015e-05,
      "loss": 0.3589,
      "step": 147
    },
    {
      "epoch": 1.0705244122965643,
      "grad_norm": 0.2513408660888672,
      "learning_rate": 4.723247232472325e-05,
      "loss": 0.3956,
      "step": 148
    },
    {
      "epoch": 1.077757685352622,
      "grad_norm": 0.11056191474199295,
      "learning_rate": 4.686346863468635e-05,
      "loss": 0.3704,
      "step": 149
    },
    {
      "epoch": 1.0849909584086799,
      "grad_norm": 0.1271658092737198,
      "learning_rate": 4.6494464944649444e-05,
      "loss": 0.3505,
      "step": 150
    },
    {
      "epoch": 1.092224231464738,
      "grad_norm": 0.10155227780342102,
      "learning_rate": 4.612546125461255e-05,
      "loss": 0.3737,
      "step": 151
    },
    {
      "epoch": 1.0994575045207957,
      "grad_norm": 0.10666938871145248,
      "learning_rate": 4.575645756457565e-05,
      "loss": 0.3743,
      "step": 152
    },
    {
      "epoch": 1.1066907775768535,
      "grad_norm": 0.1048259511590004,
      "learning_rate": 4.5387453874538747e-05,
      "loss": 0.3598,
      "step": 153
    },
    {
      "epoch": 1.1139240506329113,
      "grad_norm": 0.10699986666440964,
      "learning_rate": 4.501845018450185e-05,
      "loss": 0.4048,
      "step": 154
    },
    {
      "epoch": 1.1211573236889691,
      "grad_norm": 0.09939727187156677,
      "learning_rate": 4.464944649446495e-05,
      "loss": 0.3325,
      "step": 155
    },
    {
      "epoch": 1.1283905967450272,
      "grad_norm": 0.1125202625989914,
      "learning_rate": 4.428044280442805e-05,
      "loss": 0.3404,
      "step": 156
    },
    {
      "epoch": 1.135623869801085,
      "grad_norm": 0.09763387590646744,
      "learning_rate": 4.391143911439114e-05,
      "loss": 0.407,
      "step": 157
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.10112911462783813,
      "learning_rate": 4.3542435424354244e-05,
      "loss": 0.4015,
      "step": 158
    },
    {
      "epoch": 1.1500904159132008,
      "grad_norm": 0.10274617373943329,
      "learning_rate": 4.3173431734317345e-05,
      "loss": 0.3506,
      "step": 159
    },
    {
      "epoch": 1.1573236889692586,
      "grad_norm": 0.1066206619143486,
      "learning_rate": 4.280442804428044e-05,
      "loss": 0.3732,
      "step": 160
    },
    {
      "epoch": 1.1645569620253164,
      "grad_norm": 0.10560917854309082,
      "learning_rate": 4.243542435424355e-05,
      "loss": 0.3672,
      "step": 161
    },
    {
      "epoch": 1.1717902350813743,
      "grad_norm": 0.11759281903505325,
      "learning_rate": 4.206642066420665e-05,
      "loss": 0.3762,
      "step": 162
    },
    {
      "epoch": 1.179023508137432,
      "grad_norm": 0.10840923339128494,
      "learning_rate": 4.169741697416974e-05,
      "loss": 0.3682,
      "step": 163
    },
    {
      "epoch": 1.18625678119349,
      "grad_norm": 0.11086386442184448,
      "learning_rate": 4.132841328413284e-05,
      "loss": 0.3614,
      "step": 164
    },
    {
      "epoch": 1.193490054249548,
      "grad_norm": 0.1039872020483017,
      "learning_rate": 4.0959409594095944e-05,
      "loss": 0.3694,
      "step": 165
    },
    {
      "epoch": 1.2007233273056057,
      "grad_norm": 0.104191854596138,
      "learning_rate": 4.0590405904059045e-05,
      "loss": 0.3472,
      "step": 166
    },
    {
      "epoch": 1.2079566003616637,
      "grad_norm": 0.10681155323982239,
      "learning_rate": 4.022140221402214e-05,
      "loss": 0.366,
      "step": 167
    },
    {
      "epoch": 1.2151898734177216,
      "grad_norm": 0.10887061804533005,
      "learning_rate": 3.985239852398524e-05,
      "loss": 0.3604,
      "step": 168
    },
    {
      "epoch": 1.2224231464737794,
      "grad_norm": 0.11261174827814102,
      "learning_rate": 3.948339483394834e-05,
      "loss": 0.3258,
      "step": 169
    },
    {
      "epoch": 1.2296564195298372,
      "grad_norm": 0.11184070259332657,
      "learning_rate": 3.911439114391144e-05,
      "loss": 0.3403,
      "step": 170
    },
    {
      "epoch": 1.2368896925858952,
      "grad_norm": 0.10564827173948288,
      "learning_rate": 3.874538745387454e-05,
      "loss": 0.3541,
      "step": 171
    },
    {
      "epoch": 1.244122965641953,
      "grad_norm": 0.11773871630430222,
      "learning_rate": 3.837638376383764e-05,
      "loss": 0.3853,
      "step": 172
    },
    {
      "epoch": 1.2513562386980108,
      "grad_norm": 0.10713667422533035,
      "learning_rate": 3.8007380073800744e-05,
      "loss": 0.3185,
      "step": 173
    },
    {
      "epoch": 1.2585895117540686,
      "grad_norm": 0.10778232663869858,
      "learning_rate": 3.763837638376384e-05,
      "loss": 0.3211,
      "step": 174
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 0.10577027499675751,
      "learning_rate": 3.726937269372694e-05,
      "loss": 0.3393,
      "step": 175
    },
    {
      "epoch": 1.2730560578661845,
      "grad_norm": 0.11202805489301682,
      "learning_rate": 3.690036900369004e-05,
      "loss": 0.3582,
      "step": 176
    },
    {
      "epoch": 1.2802893309222423,
      "grad_norm": 0.10652373731136322,
      "learning_rate": 3.653136531365314e-05,
      "loss": 0.3456,
      "step": 177
    },
    {
      "epoch": 1.2875226039783003,
      "grad_norm": 0.14714586734771729,
      "learning_rate": 3.6162361623616235e-05,
      "loss": 0.3417,
      "step": 178
    },
    {
      "epoch": 1.2947558770343581,
      "grad_norm": 0.10715153813362122,
      "learning_rate": 3.5793357933579336e-05,
      "loss": 0.3412,
      "step": 179
    },
    {
      "epoch": 1.301989150090416,
      "grad_norm": 0.11732357740402222,
      "learning_rate": 3.542435424354244e-05,
      "loss": 0.3792,
      "step": 180
    },
    {
      "epoch": 1.3092224231464737,
      "grad_norm": 0.17690294981002808,
      "learning_rate": 3.505535055350554e-05,
      "loss": 0.3686,
      "step": 181
    },
    {
      "epoch": 1.3164556962025316,
      "grad_norm": 0.10941877961158752,
      "learning_rate": 3.468634686346864e-05,
      "loss": 0.3582,
      "step": 182
    },
    {
      "epoch": 1.3236889692585896,
      "grad_norm": 0.14567327499389648,
      "learning_rate": 3.431734317343174e-05,
      "loss": 0.336,
      "step": 183
    },
    {
      "epoch": 1.3309222423146474,
      "grad_norm": 0.12351348996162415,
      "learning_rate": 3.3948339483394833e-05,
      "loss": 0.3533,
      "step": 184
    },
    {
      "epoch": 1.3381555153707052,
      "grad_norm": 0.11480335891246796,
      "learning_rate": 3.3579335793357934e-05,
      "loss": 0.3482,
      "step": 185
    },
    {
      "epoch": 1.3453887884267632,
      "grad_norm": 0.12205879390239716,
      "learning_rate": 3.3210332103321035e-05,
      "loss": 0.3385,
      "step": 186
    },
    {
      "epoch": 1.352622061482821,
      "grad_norm": 0.11025048792362213,
      "learning_rate": 3.2841328413284136e-05,
      "loss": 0.3578,
      "step": 187
    },
    {
      "epoch": 1.3598553345388789,
      "grad_norm": 0.11126164346933365,
      "learning_rate": 3.247232472324723e-05,
      "loss": 0.3307,
      "step": 188
    },
    {
      "epoch": 1.3670886075949367,
      "grad_norm": 0.1165134385228157,
      "learning_rate": 3.210332103321033e-05,
      "loss": 0.3789,
      "step": 189
    },
    {
      "epoch": 1.3743218806509945,
      "grad_norm": 0.11351227760314941,
      "learning_rate": 3.173431734317343e-05,
      "loss": 0.3996,
      "step": 190
    },
    {
      "epoch": 1.3815551537070525,
      "grad_norm": 0.13154295086860657,
      "learning_rate": 3.136531365313653e-05,
      "loss": 0.3965,
      "step": 191
    },
    {
      "epoch": 1.3887884267631103,
      "grad_norm": 0.11638002842664719,
      "learning_rate": 3.0996309963099634e-05,
      "loss": 0.3801,
      "step": 192
    },
    {
      "epoch": 1.3960216998191681,
      "grad_norm": 0.11662168800830841,
      "learning_rate": 3.0627306273062735e-05,
      "loss": 0.3358,
      "step": 193
    },
    {
      "epoch": 1.4032549728752262,
      "grad_norm": 0.11403173208236694,
      "learning_rate": 3.0258302583025832e-05,
      "loss": 0.3158,
      "step": 194
    },
    {
      "epoch": 1.410488245931284,
      "grad_norm": 0.11493474245071411,
      "learning_rate": 2.9889298892988933e-05,
      "loss": 0.3533,
      "step": 195
    },
    {
      "epoch": 1.4177215189873418,
      "grad_norm": 0.11141743510961533,
      "learning_rate": 2.952029520295203e-05,
      "loss": 0.353,
      "step": 196
    },
    {
      "epoch": 1.4249547920433996,
      "grad_norm": 0.12248177826404572,
      "learning_rate": 2.915129151291513e-05,
      "loss": 0.352,
      "step": 197
    },
    {
      "epoch": 1.4321880650994574,
      "grad_norm": 0.1919812560081482,
      "learning_rate": 2.878228782287823e-05,
      "loss": 0.3796,
      "step": 198
    },
    {
      "epoch": 1.4394213381555154,
      "grad_norm": 0.11889157444238663,
      "learning_rate": 2.8413284132841326e-05,
      "loss": 0.3685,
      "step": 199
    },
    {
      "epoch": 1.4466546112115732,
      "grad_norm": 0.11996401846408844,
      "learning_rate": 2.8044280442804427e-05,
      "loss": 0.3215,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 276,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.61836422398301e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}