{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15891934843067143,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007945967421533572,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 2.9992,
      "step": 1
    },
    {
      "epoch": 0.0015891934843067143,
      "grad_norm": 2.3542397022247314,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.4211,
      "step": 2
    },
    {
      "epoch": 0.0023837902264600714,
      "grad_norm": 1.7234137058258057,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.4802,
      "step": 3
    },
    {
      "epoch": 0.0031783869686134287,
      "grad_norm": 1.8402104377746582,
      "learning_rate": 6e-06,
      "loss": 2.5004,
      "step": 4
    },
    {
      "epoch": 0.003972983710766786,
      "grad_norm": 1.9447062015533447,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.5601,
      "step": 5
    },
    {
      "epoch": 0.004767580452920143,
      "grad_norm": 1.6480785608291626,
      "learning_rate": 1e-05,
      "loss": 2.3849,
      "step": 6
    },
    {
      "epoch": 0.0055621771950735005,
      "grad_norm": 8.942625999450684,
      "learning_rate": 1.2e-05,
      "loss": 2.9789,
      "step": 7
    },
    {
      "epoch": 0.006356773937226857,
      "grad_norm": 4.155797958374023,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.6198,
      "step": 8
    },
    {
      "epoch": 0.007151370679380214,
      "grad_norm": 1.6816856861114502,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.4154,
      "step": 9
    },
    {
      "epoch": 0.007945967421533572,
      "grad_norm": 2.22641921043396,
      "learning_rate": 1.8e-05,
      "loss": 2.5419,
      "step": 10
    },
    {
      "epoch": 0.00874056416368693,
      "grad_norm": 8.44351577758789,
      "learning_rate": 2e-05,
      "loss": 2.2415,
      "step": 11
    },
    {
      "epoch": 0.009535160905840286,
      "grad_norm": 1.797033667564392,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.4743,
      "step": 12
    },
    {
      "epoch": 0.010329757647993643,
      "grad_norm": 2.222118616104126,
      "learning_rate": 2.4e-05,
      "loss": 2.3,
      "step": 13
    },
    {
      "epoch": 0.011124354390147001,
      "grad_norm": 2.0043039321899414,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.1184,
      "step": 14
    },
    {
      "epoch": 0.011918951132300357,
      "grad_norm": 2.0246055126190186,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.159,
      "step": 15
    },
    {
      "epoch": 0.012713547874453715,
      "grad_norm": 9.5096435546875,
      "learning_rate": 3e-05,
      "loss": 3.0276,
      "step": 16
    },
    {
      "epoch": 0.013508144616607072,
      "grad_norm": 2.858501672744751,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.4969,
      "step": 17
    },
    {
      "epoch": 0.014302741358760428,
      "grad_norm": 10.519010543823242,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 2.9221,
      "step": 18
    },
    {
      "epoch": 0.015097338100913786,
      "grad_norm": 2.304163932800293,
      "learning_rate": 3.6e-05,
      "loss": 2.4857,
      "step": 19
    },
    {
      "epoch": 0.015891934843067144,
      "grad_norm": 2.059422731399536,
      "learning_rate": 3.8e-05,
      "loss": 2.2824,
      "step": 20
    },
    {
      "epoch": 0.0166865315852205,
      "grad_norm": 2.584183692932129,
      "learning_rate": 4e-05,
      "loss": 2.2176,
      "step": 21
    },
    {
      "epoch": 0.01748112832737386,
      "grad_norm": 3.7771871089935303,
      "learning_rate": 4.2e-05,
      "loss": 2.9221,
      "step": 22
    },
    {
      "epoch": 0.018275725069527213,
      "grad_norm": 1.889650583267212,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.3082,
      "step": 23
    },
    {
      "epoch": 0.01907032181168057,
      "grad_norm": 3.319291353225708,
      "learning_rate": 4.600000000000001e-05,
      "loss": 2.19,
      "step": 24
    },
    {
      "epoch": 0.01986491855383393,
      "grad_norm": 4.1281352043151855,
      "learning_rate": 4.8e-05,
      "loss": 2.1096,
      "step": 25
    },
    {
      "epoch": 0.020659515295987287,
      "grad_norm": 2.4024288654327393,
      "learning_rate": 5e-05,
      "loss": 2.208,
      "step": 26
    },
    {
      "epoch": 0.021454112038140644,
      "grad_norm": 15.567670822143555,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.4704,
      "step": 27
    },
    {
      "epoch": 0.022248708780294002,
      "grad_norm": 2.64872145652771,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 2.1112,
      "step": 28
    },
    {
      "epoch": 0.023043305522447356,
      "grad_norm": 6.033721446990967,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.7668,
      "step": 29
    },
    {
      "epoch": 0.023837902264600714,
      "grad_norm": 2.7915563583374023,
      "learning_rate": 5.8e-05,
      "loss": 2.1103,
      "step": 30
    },
    {
      "epoch": 0.02463249900675407,
      "grad_norm": 2.611234664916992,
      "learning_rate": 6e-05,
      "loss": 2.038,
      "step": 31
    },
    {
      "epoch": 0.02542709574890743,
      "grad_norm": 2.3000996112823486,
      "learning_rate": 6.2e-05,
      "loss": 1.6268,
      "step": 32
    },
    {
      "epoch": 0.026221692491060787,
      "grad_norm": 3.713061571121216,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.9121,
      "step": 33
    },
    {
      "epoch": 0.027016289233214145,
      "grad_norm": 2.776019811630249,
      "learning_rate": 6.6e-05,
      "loss": 1.817,
      "step": 34
    },
    {
      "epoch": 0.027810885975367503,
      "grad_norm": 2.564723491668701,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.9355,
      "step": 35
    },
    {
      "epoch": 0.028605482717520857,
      "grad_norm": 6.116189002990723,
      "learning_rate": 7e-05,
      "loss": 1.7766,
      "step": 36
    },
    {
      "epoch": 0.029400079459674214,
      "grad_norm": 2.6253204345703125,
      "learning_rate": 7.2e-05,
      "loss": 1.7565,
      "step": 37
    },
    {
      "epoch": 0.030194676201827572,
      "grad_norm": 2.706721544265747,
      "learning_rate": 7.4e-05,
      "loss": 1.9456,
      "step": 38
    },
    {
      "epoch": 0.03098927294398093,
      "grad_norm": 2.7343411445617676,
      "learning_rate": 7.6e-05,
      "loss": 1.6768,
      "step": 39
    },
    {
      "epoch": 0.03178386968613429,
      "grad_norm": 2.1730287075042725,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.4658,
      "step": 40
    },
    {
      "epoch": 0.03257846642828764,
      "grad_norm": 2.681889295578003,
      "learning_rate": 8e-05,
      "loss": 1.5583,
      "step": 41
    },
    {
      "epoch": 0.033373063170441,
      "grad_norm": 2.6841020584106445,
      "learning_rate": 8.2e-05,
      "loss": 1.6734,
      "step": 42
    },
    {
      "epoch": 0.03416765991259436,
      "grad_norm": 3.1267893314361572,
      "learning_rate": 8.4e-05,
      "loss": 1.6114,
      "step": 43
    },
    {
      "epoch": 0.03496225665474772,
      "grad_norm": 3.066925525665283,
      "learning_rate": 8.6e-05,
      "loss": 1.558,
      "step": 44
    },
    {
      "epoch": 0.03575685339690107,
      "grad_norm": 2.6647801399230957,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.4592,
      "step": 45
    },
    {
      "epoch": 0.03655145013905443,
      "grad_norm": 2.6715352535247803,
      "learning_rate": 9e-05,
      "loss": 1.4846,
      "step": 46
    },
    {
      "epoch": 0.03734604688120779,
      "grad_norm": 8.9569091796875,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.7494,
      "step": 47
    },
    {
      "epoch": 0.03814064362336114,
      "grad_norm": 2.7488503456115723,
      "learning_rate": 9.4e-05,
      "loss": 1.2653,
      "step": 48
    },
    {
      "epoch": 0.038935240365514504,
      "grad_norm": 2.520211696624756,
      "learning_rate": 9.6e-05,
      "loss": 1.2965,
      "step": 49
    },
    {
      "epoch": 0.03972983710766786,
      "grad_norm": 2.678025960922241,
      "learning_rate": 9.8e-05,
      "loss": 1.199,
      "step": 50
    },
    {
      "epoch": 0.04052443384982122,
      "grad_norm": 2.6799986362457275,
      "learning_rate": 0.0001,
      "loss": 1.2672,
      "step": 51
    },
    {
      "epoch": 0.04131903059197457,
      "grad_norm": 2.907582998275757,
      "learning_rate": 0.00010200000000000001,
      "loss": 1.3114,
      "step": 52
    },
    {
      "epoch": 0.04211362733412793,
      "grad_norm": 2.7622241973876953,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.2173,
      "step": 53
    },
    {
      "epoch": 0.04290822407628129,
      "grad_norm": 3.829127550125122,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.2657,
      "step": 54
    },
    {
      "epoch": 0.04370282081843464,
      "grad_norm": 4.464277267456055,
      "learning_rate": 0.00010800000000000001,
      "loss": 1.3206,
      "step": 55
    },
    {
      "epoch": 0.044497417560588004,
      "grad_norm": 2.5400142669677734,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.1097,
      "step": 56
    },
    {
      "epoch": 0.04529201430274136,
      "grad_norm": 2.6496193408966064,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.097,
      "step": 57
    },
    {
      "epoch": 0.04608661104489471,
      "grad_norm": 4.215746879577637,
      "learning_rate": 0.00011399999999999999,
      "loss": 1.1642,
      "step": 58
    },
    {
      "epoch": 0.046881207787048074,
      "grad_norm": 2.93621826171875,
      "learning_rate": 0.000116,
      "loss": 1.2385,
      "step": 59
    },
    {
      "epoch": 0.04767580452920143,
      "grad_norm": 10.44421672821045,
      "learning_rate": 0.000118,
      "loss": 1.1682,
      "step": 60
    },
    {
      "epoch": 0.04847040127135479,
      "grad_norm": 3.617307424545288,
      "learning_rate": 0.00012,
      "loss": 1.3271,
      "step": 61
    },
    {
      "epoch": 0.04926499801350814,
      "grad_norm": 2.5892326831817627,
      "learning_rate": 0.000122,
      "loss": 0.9714,
      "step": 62
    },
    {
      "epoch": 0.050059594755661505,
      "grad_norm": NaN,
      "learning_rate": 0.000122,
      "loss": 1.2764,
      "step": 63
    },
    {
      "epoch": 0.05085419149781486,
      "grad_norm": 2.9196863174438477,
      "learning_rate": 0.000124,
      "loss": 1.1406,
      "step": 64
    },
    {
      "epoch": 0.05164878823996821,
      "grad_norm": 4.006603717803955,
      "learning_rate": 0.000126,
      "loss": 0.9797,
      "step": 65
    },
    {
      "epoch": 0.052443384982121574,
      "grad_norm": 2.5575106143951416,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.2092,
      "step": 66
    },
    {
      "epoch": 0.05323798172427493,
      "grad_norm": 3.1613786220550537,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.2598,
      "step": 67
    },
    {
      "epoch": 0.05403257846642829,
      "grad_norm": 2.542789936065674,
      "learning_rate": 0.000132,
      "loss": 0.9497,
      "step": 68
    },
    {
      "epoch": 0.054827175208581644,
      "grad_norm": 2.4051780700683594,
      "learning_rate": 0.000134,
      "loss": 0.7992,
      "step": 69
    },
    {
      "epoch": 0.055621771950735005,
      "grad_norm": 51.893409729003906,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.9683,
      "step": 70
    },
    {
      "epoch": 0.05641636869288836,
      "grad_norm": 4.105207920074463,
      "learning_rate": 0.000138,
      "loss": 1.0815,
      "step": 71
    },
    {
      "epoch": 0.057210965435041714,
      "grad_norm": 92.10639190673828,
      "learning_rate": 0.00014,
      "loss": 1.1767,
      "step": 72
    },
    {
      "epoch": 0.058005562177195075,
      "grad_norm": 2.4499878883361816,
      "learning_rate": 0.000142,
      "loss": 0.8912,
      "step": 73
    },
    {
      "epoch": 0.05880015891934843,
      "grad_norm": 2.4928042888641357,
      "learning_rate": 0.000144,
      "loss": 0.9457,
      "step": 74
    },
    {
      "epoch": 0.05959475566150179,
      "grad_norm": 2.761523485183716,
      "learning_rate": 0.000146,
      "loss": 0.9493,
      "step": 75
    },
    {
      "epoch": 0.060389352403655144,
      "grad_norm": 2.9320006370544434,
      "learning_rate": 0.000148,
      "loss": 0.9657,
      "step": 76
    },
    {
      "epoch": 0.061183949145808506,
      "grad_norm": 2.067227840423584,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8115,
      "step": 77
    },
    {
      "epoch": 0.06197854588796186,
      "grad_norm": 78.78492736816406,
      "learning_rate": 0.000152,
      "loss": 1.4676,
      "step": 78
    },
    {
      "epoch": 0.06277314263011521,
      "grad_norm": 2.335451364517212,
      "learning_rate": 0.000154,
      "loss": 0.9271,
      "step": 79
    },
    {
      "epoch": 0.06356773937226858,
      "grad_norm": 3.434222459793091,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.8938,
      "step": 80
    },
    {
      "epoch": 0.06436233611442194,
      "grad_norm": 2.38944673538208,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.9277,
      "step": 81
    },
    {
      "epoch": 0.06515693285657528,
      "grad_norm": 2.960742712020874,
      "learning_rate": 0.00016,
      "loss": 1.1237,
      "step": 82
    },
    {
      "epoch": 0.06595152959872864,
      "grad_norm": 2.1033873558044434,
      "learning_rate": 0.000162,
      "loss": 0.8095,
      "step": 83
    },
    {
      "epoch": 0.066746126340882,
      "grad_norm": 2.611531972885132,
      "learning_rate": 0.000164,
      "loss": 0.927,
      "step": 84
    },
    {
      "epoch": 0.06754072308303535,
      "grad_norm": 2.9163801670074463,
      "learning_rate": 0.000166,
      "loss": 0.8363,
      "step": 85
    },
    {
      "epoch": 0.06833531982518871,
      "grad_norm": 2.6492106914520264,
      "learning_rate": 0.000168,
      "loss": 0.9831,
      "step": 86
    },
    {
      "epoch": 0.06912991656734208,
      "grad_norm": 2.027588367462158,
      "learning_rate": 0.00017,
      "loss": 0.8676,
      "step": 87
    },
    {
      "epoch": 0.06992451330949544,
      "grad_norm": 2.7688043117523193,
      "learning_rate": 0.000172,
      "loss": 1.1266,
      "step": 88
    },
    {
      "epoch": 0.07071911005164878,
      "grad_norm": 2.4787685871124268,
      "learning_rate": 0.000174,
      "loss": 0.8832,
      "step": 89
    },
    {
      "epoch": 0.07151370679380215,
      "grad_norm": 5.127519130706787,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.8945,
      "step": 90
    },
    {
      "epoch": 0.0723083035359555,
      "grad_norm": 3.4531705379486084,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.1205,
      "step": 91
    },
    {
      "epoch": 0.07310290027810885,
      "grad_norm": 2.749129056930542,
      "learning_rate": 0.00018,
      "loss": 1.019,
      "step": 92
    },
    {
      "epoch": 0.07389749702026222,
      "grad_norm": Infinity,
      "learning_rate": 0.00018,
      "loss": 1.3832,
      "step": 93
    },
    {
      "epoch": 0.07469209376241558,
      "grad_norm": 2.6057441234588623,
      "learning_rate": 0.000182,
      "loss": 1.1318,
      "step": 94
    },
    {
      "epoch": 0.07548669050456894,
      "grad_norm": 4.503351211547852,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.033,
      "step": 95
    },
    {
      "epoch": 0.07628128724672228,
      "grad_norm": 2.7054409980773926,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.9466,
      "step": 96
    },
    {
      "epoch": 0.07707588398887565,
      "grad_norm": 2.1828339099884033,
      "learning_rate": 0.000188,
      "loss": 0.8253,
      "step": 97
    },
    {
      "epoch": 0.07787048073102901,
      "grad_norm": 2.062911033630371,
      "learning_rate": 0.00019,
      "loss": 0.8997,
      "step": 98
    },
    {
      "epoch": 0.07866507747318235,
      "grad_norm": 2.1747360229492188,
      "learning_rate": 0.000192,
      "loss": 0.928,
      "step": 99
    },
    {
      "epoch": 0.07945967421533572,
      "grad_norm": 2.3616063594818115,
      "learning_rate": 0.000194,
      "loss": 0.8595,
      "step": 100
    },
    {
      "epoch": 0.08025427095748908,
      "grad_norm": 2.007453203201294,
      "learning_rate": 0.000196,
      "loss": 0.9071,
      "step": 101
    },
    {
      "epoch": 0.08104886769964244,
      "grad_norm": 2.822878837585449,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.1856,
      "step": 102
    },
    {
      "epoch": 0.08184346444179579,
      "grad_norm": 2.162837505340576,
      "learning_rate": 0.0002,
      "loss": 1.0198,
      "step": 103
    },
    {
      "epoch": 0.08263806118394915,
      "grad_norm": 2.004056453704834,
      "learning_rate": 0.00019800000000000002,
      "loss": 0.8352,
      "step": 104
    },
    {
      "epoch": 0.08343265792610251,
      "grad_norm": 2.5484063625335693,
      "learning_rate": 0.000196,
      "loss": 1.0226,
      "step": 105
    },
    {
      "epoch": 0.08422725466825585,
      "grad_norm": 2.2759130001068115,
      "learning_rate": 0.000194,
      "loss": 0.8884,
      "step": 106
    },
    {
      "epoch": 0.08502185141040922,
      "grad_norm": 2.4136946201324463,
      "learning_rate": 0.000192,
      "loss": 0.8374,
      "step": 107
    },
    {
      "epoch": 0.08581644815256258,
      "grad_norm": 2.8566195964813232,
      "learning_rate": 0.00019,
      "loss": 0.9112,
      "step": 108
    },
    {
      "epoch": 0.08661104489471594,
      "grad_norm": 2.241708755493164,
      "learning_rate": 0.000188,
      "loss": 0.8695,
      "step": 109
    },
    {
      "epoch": 0.08740564163686929,
      "grad_norm": 2.1674909591674805,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.708,
      "step": 110
    },
    {
      "epoch": 0.08820023837902265,
      "grad_norm": 3.16097092628479,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.0946,
      "step": 111
    },
    {
      "epoch": 0.08899483512117601,
      "grad_norm": 2.7531492710113525,
      "learning_rate": 0.000182,
      "loss": 0.8907,
      "step": 112
    },
    {
      "epoch": 0.08978943186332936,
      "grad_norm": 2.3830761909484863,
      "learning_rate": 0.00018,
      "loss": 0.9243,
      "step": 113
    },
    {
      "epoch": 0.09058402860548272,
      "grad_norm": 27.347421646118164,
      "learning_rate": 0.00017800000000000002,
      "loss": 1.0328,
      "step": 114
    },
    {
      "epoch": 0.09137862534763608,
      "grad_norm": 2.1043972969055176,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.9195,
      "step": 115
    },
    {
      "epoch": 0.09217322208978942,
      "grad_norm": 1.9787133932113647,
      "learning_rate": 0.000174,
      "loss": 0.7395,
      "step": 116
    },
    {
      "epoch": 0.09296781883194279,
      "grad_norm": 2.395308256149292,
      "learning_rate": 0.000172,
      "loss": 1.0193,
      "step": 117
    },
    {
      "epoch": 0.09376241557409615,
      "grad_norm": 1.9864846467971802,
      "learning_rate": 0.00017,
      "loss": 0.948,
      "step": 118
    },
    {
      "epoch": 0.09455701231624951,
      "grad_norm": 2.823315382003784,
      "learning_rate": 0.000168,
      "loss": 1.0902,
      "step": 119
    },
    {
      "epoch": 0.09535160905840286,
      "grad_norm": 2.5823678970336914,
      "learning_rate": 0.000166,
      "loss": 1.0905,
      "step": 120
    },
    {
      "epoch": 0.09614620580055622,
      "grad_norm": 1.8948626518249512,
      "learning_rate": 0.000164,
      "loss": 0.9203,
      "step": 121
    },
    {
      "epoch": 0.09694080254270958,
      "grad_norm": 1.9721623659133911,
      "learning_rate": 0.000162,
      "loss": 0.9591,
      "step": 122
    },
    {
      "epoch": 0.09773539928486293,
      "grad_norm": 1.9776030778884888,
      "learning_rate": 0.00016,
      "loss": 0.9887,
      "step": 123
    },
    {
      "epoch": 0.09852999602701629,
      "grad_norm": 2.8131155967712402,
      "learning_rate": 0.00015800000000000002,
      "loss": 1.0197,
      "step": 124
    },
    {
      "epoch": 0.09932459276916965,
      "grad_norm": 2.0642547607421875,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.9931,
      "step": 125
    },
    {
      "epoch": 0.10011918951132301,
      "grad_norm": 2.9410674571990967,
      "learning_rate": 0.000154,
      "loss": 1.3742,
      "step": 126
    },
    {
      "epoch": 0.10091378625347636,
      "grad_norm": 2.1221704483032227,
      "learning_rate": 0.000152,
      "loss": 1.0526,
      "step": 127
    },
    {
      "epoch": 0.10170838299562972,
      "grad_norm": 2.831902503967285,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8048,
      "step": 128
    },
    {
      "epoch": 0.10250297973778308,
      "grad_norm": 2.066681146621704,
      "learning_rate": 0.000148,
      "loss": 0.985,
      "step": 129
    },
    {
      "epoch": 0.10329757647993643,
      "grad_norm": 1.8252568244934082,
      "learning_rate": 0.000146,
      "loss": 0.7689,
      "step": 130
    },
    {
      "epoch": 0.10409217322208979,
      "grad_norm": 2.0231878757476807,
      "learning_rate": 0.000144,
      "loss": 1.0247,
      "step": 131
    },
    {
      "epoch": 0.10488676996424315,
      "grad_norm": 2.200442314147949,
      "learning_rate": 0.000142,
      "loss": 0.8775,
      "step": 132
    },
    {
      "epoch": 0.10568136670639651,
      "grad_norm": 1.7937211990356445,
      "learning_rate": 0.00014,
      "loss": 0.9357,
      "step": 133
    },
    {
      "epoch": 0.10647596344854986,
      "grad_norm": 1.685763955116272,
      "learning_rate": 0.000138,
      "loss": 0.8664,
      "step": 134
    },
    {
      "epoch": 0.10727056019070322,
      "grad_norm": 1.9033604860305786,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.9793,
      "step": 135
    },
    {
      "epoch": 0.10806515693285658,
      "grad_norm": 1.8052781820297241,
      "learning_rate": 0.000134,
      "loss": 0.8154,
      "step": 136
    },
    {
      "epoch": 0.10885975367500993,
      "grad_norm": 2.400908946990967,
      "learning_rate": 0.000132,
      "loss": 0.9604,
      "step": 137
    },
    {
      "epoch": 0.10965435041716329,
      "grad_norm": 1.7619413137435913,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.8187,
      "step": 138
    },
    {
      "epoch": 0.11044894715931665,
      "grad_norm": 1.8535854816436768,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.9487,
      "step": 139
    },
    {
      "epoch": 0.11124354390147001,
      "grad_norm": 1.8936333656311035,
      "learning_rate": 0.000126,
      "loss": 0.9852,
      "step": 140
    },
    {
      "epoch": 0.11203814064362336,
      "grad_norm": 1.821515440940857,
      "learning_rate": 0.000124,
      "loss": 0.8442,
      "step": 141
    },
    {
      "epoch": 0.11283273738577672,
      "grad_norm": 2.1713123321533203,
      "learning_rate": 0.000122,
      "loss": 1.1723,
      "step": 142
    },
    {
      "epoch": 0.11362733412793008,
      "grad_norm": 1.6912201642990112,
      "learning_rate": 0.00012,
      "loss": 0.7486,
      "step": 143
    },
    {
      "epoch": 0.11442193087008343,
      "grad_norm": 1.630624532699585,
      "learning_rate": 0.000118,
      "loss": 0.7462,
      "step": 144
    },
    {
      "epoch": 0.11521652761223679,
      "grad_norm": 2.0852651596069336,
      "learning_rate": 0.000116,
      "loss": 0.7821,
      "step": 145
    },
    {
      "epoch": 0.11601112435439015,
      "grad_norm": 1.5113400220870972,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.7768,
      "step": 146
    },
    {
      "epoch": 0.11680572109654351,
      "grad_norm": 1.9536205530166626,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.9478,
      "step": 147
    },
    {
      "epoch": 0.11760031783869686,
      "grad_norm": 1.8963311910629272,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.9085,
      "step": 148
    },
    {
      "epoch": 0.11839491458085022,
      "grad_norm": 1.8368561267852783,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.757,
      "step": 149
    },
    {
      "epoch": 0.11918951132300358,
      "grad_norm": 2.7951648235321045,
      "learning_rate": 0.00010600000000000002,
      "loss": 1.0677,
      "step": 150
    },
    {
      "epoch": 0.11998410806515693,
      "grad_norm": 2.015962839126587,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.7874,
      "step": 151
    },
    {
      "epoch": 0.12077870480731029,
      "grad_norm": 2.661062479019165,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.9311,
      "step": 152
    },
    {
      "epoch": 0.12157330154946365,
      "grad_norm": 2.020232677459717,
      "learning_rate": 0.0001,
      "loss": 0.7958,
      "step": 153
    },
    {
      "epoch": 0.12236789829161701,
      "grad_norm": 2.5150179862976074,
      "learning_rate": 9.8e-05,
      "loss": 0.8354,
      "step": 154
    },
    {
      "epoch": 0.12316249503377036,
      "grad_norm": 1.65029776096344,
      "learning_rate": 9.6e-05,
      "loss": 0.8512,
      "step": 155
    },
    {
      "epoch": 0.12395709177592372,
      "grad_norm": 2.004103183746338,
      "learning_rate": 9.4e-05,
      "loss": 0.7002,
      "step": 156
    },
    {
      "epoch": 0.12475168851807708,
      "grad_norm": 2.198091506958008,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.8539,
      "step": 157
    },
    {
      "epoch": 0.12554628526023043,
      "grad_norm": 2.1458988189697266,
      "learning_rate": 9e-05,
      "loss": 1.1292,
      "step": 158
    },
    {
      "epoch": 0.1263408820023838,
      "grad_norm": 1.7759689092636108,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.8792,
      "step": 159
    },
    {
      "epoch": 0.12713547874453715,
      "grad_norm": 2.0215320587158203,
      "learning_rate": 8.6e-05,
      "loss": 0.9206,
      "step": 160
    },
    {
      "epoch": 0.1279300754866905,
      "grad_norm": 2.324572801589966,
      "learning_rate": 8.4e-05,
      "loss": 1.0041,
      "step": 161
    },
    {
      "epoch": 0.12872467222884387,
      "grad_norm": 2.3949570655822754,
      "learning_rate": 8.2e-05,
      "loss": 0.7894,
      "step": 162
    },
    {
      "epoch": 0.12951926897099722,
      "grad_norm": 1.8736156225204468,
      "learning_rate": 8e-05,
      "loss": 0.8928,
      "step": 163
    },
    {
      "epoch": 0.13031386571315057,
      "grad_norm": 2.373562812805176,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.8739,
      "step": 164
    },
    {
      "epoch": 0.13110846245530394,
      "grad_norm": 1.6126917600631714,
      "learning_rate": 7.6e-05,
      "loss": 0.6292,
      "step": 165
    },
    {
      "epoch": 0.1319030591974573,
      "grad_norm": 2.6151697635650635,
      "learning_rate": 7.4e-05,
      "loss": 1.2176,
      "step": 166
    },
    {
      "epoch": 0.13269765593961064,
      "grad_norm": 1.883436918258667,
      "learning_rate": 7.2e-05,
      "loss": 0.7664,
      "step": 167
    },
    {
      "epoch": 0.133492252681764,
      "grad_norm": 2.2091007232666016,
      "learning_rate": 7e-05,
      "loss": 0.9501,
      "step": 168
    },
    {
      "epoch": 0.13428684942391736,
      "grad_norm": 1.903889775276184,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.9322,
      "step": 169
    },
    {
      "epoch": 0.1350814461660707,
      "grad_norm": 1.9040536880493164,
      "learning_rate": 6.6e-05,
      "loss": 0.851,
      "step": 170
    },
    {
      "epoch": 0.13587604290822408,
      "grad_norm": 1.7239336967468262,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.9033,
      "step": 171
    },
    {
      "epoch": 0.13667063965037743,
      "grad_norm": 3.3629558086395264,
      "learning_rate": 6.2e-05,
      "loss": 0.918,
      "step": 172
    },
    {
      "epoch": 0.1374652363925308,
      "grad_norm": 1.9918290376663208,
      "learning_rate": 6e-05,
      "loss": 0.8825,
      "step": 173
    },
    {
      "epoch": 0.13825983313468415,
      "grad_norm": 2.3540871143341064,
      "learning_rate": 5.8e-05,
      "loss": 0.6484,
      "step": 174
    },
    {
      "epoch": 0.1390544298768375,
      "grad_norm": 2.2806777954101562,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.7137,
      "step": 175
    },
    {
      "epoch": 0.13984902661899087,
      "grad_norm": 2.21384334564209,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.5965,
      "step": 176
    },
    {
      "epoch": 0.14064362336114422,
      "grad_norm": 1.9977487325668335,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.7671,
      "step": 177
    },
    {
      "epoch": 0.14143822010329757,
      "grad_norm": 31.215999603271484,
      "learning_rate": 5e-05,
      "loss": 0.9116,
      "step": 178
    },
    {
      "epoch": 0.14223281684545094,
      "grad_norm": 2.2257730960845947,
      "learning_rate": 4.8e-05,
      "loss": 0.8838,
      "step": 179
    },
    {
      "epoch": 0.1430274135876043,
      "grad_norm": 2.9200854301452637,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.9615,
      "step": 180
    },
    {
      "epoch": 0.14382201032975764,
      "grad_norm": 2.2704315185546875,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.0132,
      "step": 181
    },
    {
      "epoch": 0.144616607071911,
      "grad_norm": 2.058189868927002,
      "learning_rate": 4.2e-05,
      "loss": 0.8201,
      "step": 182
    },
    {
      "epoch": 0.14541120381406436,
      "grad_norm": 1.7903186082839966,
      "learning_rate": 4e-05,
      "loss": 0.7128,
      "step": 183
    },
    {
      "epoch": 0.1462058005562177,
      "grad_norm": 1.9608381986618042,
      "learning_rate": 3.8e-05,
      "loss": 0.8236,
      "step": 184
    },
    {
      "epoch": 0.14700039729837108,
      "grad_norm": 2.1937220096588135,
      "learning_rate": 3.6e-05,
      "loss": 0.8442,
      "step": 185
    },
    {
      "epoch": 0.14779499404052443,
      "grad_norm": 2.047407627105713,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.966,
      "step": 186
    },
    {
      "epoch": 0.14858959078267778,
      "grad_norm": 2.0216119289398193,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.9564,
      "step": 187
    },
    {
      "epoch": 0.14938418752483115,
      "grad_norm": 1.629753589630127,
      "learning_rate": 3e-05,
      "loss": 0.6504,
      "step": 188
    },
    {
      "epoch": 0.1501787842669845,
      "grad_norm": 1.7381154298782349,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.8346,
      "step": 189
    },
    {
      "epoch": 0.15097338100913787,
      "grad_norm": 2.1300833225250244,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.8631,
      "step": 190
    },
    {
      "epoch": 0.15176797775129122,
      "grad_norm": 1.8977206945419312,
      "learning_rate": 2.4e-05,
      "loss": 0.8653,
      "step": 191
    },
    {
      "epoch": 0.15256257449344457,
      "grad_norm": 1.7362009286880493,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.8278,
      "step": 192
    },
    {
      "epoch": 0.15335717123559794,
      "grad_norm": 1.838982105255127,
      "learning_rate": 2e-05,
      "loss": 0.6521,
      "step": 193
    },
    {
      "epoch": 0.1541517679777513,
      "grad_norm": 2.4685189723968506,
      "learning_rate": 1.8e-05,
      "loss": 0.9639,
      "step": 194
    },
    {
      "epoch": 0.15494636471990464,
      "grad_norm": 1.8960801362991333,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.7338,
      "step": 195
    },
    {
      "epoch": 0.15574096146205801,
      "grad_norm": 2.139636993408203,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.6774,
      "step": 196
    },
    {
      "epoch": 0.15653555820421136,
      "grad_norm": 2.0349552631378174,
      "learning_rate": 1.2e-05,
      "loss": 0.8435,
      "step": 197
    },
    {
      "epoch": 0.1573301549463647,
      "grad_norm": 1.5157055854797363,
      "learning_rate": 1e-05,
      "loss": 0.7087,
      "step": 198
    },
    {
      "epoch": 0.15812475168851808,
      "grad_norm": 2.498692035675049,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.0298,
      "step": 199
    },
    {
      "epoch": 0.15891934843067143,
      "grad_norm": 1.7967320680618286,
      "learning_rate": 6e-06,
      "loss": 0.7717,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2473157095243776.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}