{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00125,
  "eval_steps": 500,
  "global_step": 125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1e-05,
      "grad_norm": 1.7129806011276105,
      "learning_rate": 3e-06,
      "loss": 10.8348,
      "step": 1
    },
    {
      "epoch": 2e-05,
      "grad_norm": 1.6872753303603527,
      "learning_rate": 6e-06,
      "loss": 10.8356,
      "step": 2
    },
    {
      "epoch": 3e-05,
      "grad_norm": 1.6970020903903387,
      "learning_rate": 9e-06,
      "loss": 10.834,
      "step": 3
    },
    {
      "epoch": 4e-05,
      "grad_norm": 1.690199421583159,
      "learning_rate": 1.2e-05,
      "loss": 10.8334,
      "step": 4
    },
    {
      "epoch": 5e-05,
      "grad_norm": 1.6936208883930068,
      "learning_rate": 1.5e-05,
      "loss": 10.8294,
      "step": 5
    },
    {
      "epoch": 6e-05,
      "grad_norm": 1.6935154610161474,
      "learning_rate": 1.8e-05,
      "loss": 10.8281,
      "step": 6
    },
    {
      "epoch": 7e-05,
      "grad_norm": 1.6333694173725648,
      "learning_rate": 2.1000000000000002e-05,
      "loss": 10.8133,
      "step": 7
    },
    {
      "epoch": 8e-05,
      "grad_norm": 1.4463755011186001,
      "learning_rate": 2.4e-05,
      "loss": 10.783,
      "step": 8
    },
    {
      "epoch": 9e-05,
      "grad_norm": 1.3815123169360315,
      "learning_rate": 2.7e-05,
      "loss": 10.7779,
      "step": 9
    },
    {
      "epoch": 0.0001,
      "grad_norm": 1.3507621465484316,
      "learning_rate": 3e-05,
      "loss": 10.7629,
      "step": 10
    },
    {
      "epoch": 0.00011,
      "grad_norm": 1.257508561634155,
      "learning_rate": 3.2999999999999996e-05,
      "loss": 10.7454,
      "step": 11
    },
    {
      "epoch": 0.00012,
      "grad_norm": 1.224298046820689,
      "learning_rate": 3.6e-05,
      "loss": 10.7321,
      "step": 12
    },
    {
      "epoch": 0.00013,
      "grad_norm": 1.1609107458726389,
      "learning_rate": 3.9e-05,
      "loss": 10.7098,
      "step": 13
    },
    {
      "epoch": 0.00014,
      "grad_norm": 1.1251765756585856,
      "learning_rate": 4.2000000000000004e-05,
      "loss": 10.6986,
      "step": 14
    },
    {
      "epoch": 0.00015,
      "grad_norm": 1.1021031797679595,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 10.6882,
      "step": 15
    },
    {
      "epoch": 0.00016,
      "grad_norm": 1.05231707077907,
      "learning_rate": 4.8e-05,
      "loss": 10.6681,
      "step": 16
    },
    {
      "epoch": 0.00017,
      "grad_norm": 1.0082613504118885,
      "learning_rate": 5.1000000000000006e-05,
      "loss": 10.6513,
      "step": 17
    },
    {
      "epoch": 0.00018,
      "grad_norm": 0.9840324393168475,
      "learning_rate": 5.4e-05,
      "loss": 10.6344,
      "step": 18
    },
    {
      "epoch": 0.00019,
      "grad_norm": 0.953923239589578,
      "learning_rate": 5.7e-05,
      "loss": 10.6196,
      "step": 19
    },
    {
      "epoch": 0.0002,
      "grad_norm": 0.9458057853193742,
      "learning_rate": 6e-05,
      "loss": 10.6069,
      "step": 20
    },
    {
      "epoch": 0.00021,
      "grad_norm": 0.9177457999897578,
      "learning_rate": 6.3e-05,
      "loss": 10.5922,
      "step": 21
    },
    {
      "epoch": 0.00022,
      "grad_norm": 0.9134874433162486,
      "learning_rate": 6.599999999999999e-05,
      "loss": 10.576,
      "step": 22
    },
    {
      "epoch": 0.00023,
      "grad_norm": 0.908696989628468,
      "learning_rate": 6.9e-05,
      "loss": 10.5635,
      "step": 23
    },
    {
      "epoch": 0.00024,
      "grad_norm": 0.9051143007426985,
      "learning_rate": 7.2e-05,
      "loss": 10.5499,
      "step": 24
    },
    {
      "epoch": 0.00025,
      "grad_norm": 0.9082451576693834,
      "learning_rate": 7.500000000000001e-05,
      "loss": 10.5361,
      "step": 25
    },
    {
      "epoch": 0.00026,
      "grad_norm": 0.9099344486243927,
      "learning_rate": 7.8e-05,
      "loss": 10.521,
      "step": 26
    },
    {
      "epoch": 0.00027,
      "grad_norm": 0.9053293550746107,
      "learning_rate": 8.1e-05,
      "loss": 10.5103,
      "step": 27
    },
    {
      "epoch": 0.00028,
      "grad_norm": 0.9002471153364864,
      "learning_rate": 8.400000000000001e-05,
      "loss": 10.4955,
      "step": 28
    },
    {
      "epoch": 0.00029,
      "grad_norm": 0.9068699186733776,
      "learning_rate": 8.7e-05,
      "loss": 10.4811,
      "step": 29
    },
    {
      "epoch": 0.0003,
      "grad_norm": 0.9095271030063902,
      "learning_rate": 8.999999999999999e-05,
      "loss": 10.4648,
      "step": 30
    },
    {
      "epoch": 0.00031,
      "grad_norm": 0.9097010936405139,
      "learning_rate": 9.3e-05,
      "loss": 10.4503,
      "step": 31
    },
    {
      "epoch": 0.00032,
      "grad_norm": 0.9047462396891427,
      "learning_rate": 9.6e-05,
      "loss": 10.4348,
      "step": 32
    },
    {
      "epoch": 0.00033,
      "grad_norm": 0.9068703333942145,
      "learning_rate": 9.900000000000001e-05,
      "loss": 10.418,
      "step": 33
    },
    {
      "epoch": 0.00034,
      "grad_norm": 0.9072965837486595,
      "learning_rate": 0.00010200000000000001,
      "loss": 10.4,
      "step": 34
    },
    {
      "epoch": 0.00035,
      "grad_norm": 0.9110003633890357,
      "learning_rate": 0.00010500000000000002,
      "loss": 10.3835,
      "step": 35
    },
    {
      "epoch": 0.00036,
      "grad_norm": 0.9049119959927198,
      "learning_rate": 0.000108,
      "loss": 10.3652,
      "step": 36
    },
    {
      "epoch": 0.00037,
      "grad_norm": 0.8970709544624084,
      "learning_rate": 0.000111,
      "loss": 10.3479,
      "step": 37
    },
    {
      "epoch": 0.00038,
      "grad_norm": 0.8959068278842482,
      "learning_rate": 0.000114,
      "loss": 10.3275,
      "step": 38
    },
    {
      "epoch": 0.00039,
      "grad_norm": 0.9005947927478184,
      "learning_rate": 0.000117,
      "loss": 10.3069,
      "step": 39
    },
    {
      "epoch": 0.0004,
      "grad_norm": 0.9014442598894896,
      "learning_rate": 0.00012,
      "loss": 10.2842,
      "step": 40
    },
    {
      "epoch": 0.00041,
      "grad_norm": 0.8992939718171602,
      "learning_rate": 0.000123,
      "loss": 10.2657,
      "step": 41
    },
    {
      "epoch": 0.00042,
      "grad_norm": 0.8994818536906172,
      "learning_rate": 0.000126,
      "loss": 10.2444,
      "step": 42
    },
    {
      "epoch": 0.00043,
      "grad_norm": 0.9062946670458473,
      "learning_rate": 0.000129,
      "loss": 10.2208,
      "step": 43
    },
    {
      "epoch": 0.00044,
      "grad_norm": 0.9072550424345267,
      "learning_rate": 0.00013199999999999998,
      "loss": 10.1985,
      "step": 44
    },
    {
      "epoch": 0.00045,
      "grad_norm": 0.908308760029939,
      "learning_rate": 0.000135,
      "loss": 10.1758,
      "step": 45
    },
    {
      "epoch": 0.00046,
      "grad_norm": 0.8994605508976834,
      "learning_rate": 0.000138,
      "loss": 10.1528,
      "step": 46
    },
    {
      "epoch": 0.00047,
      "grad_norm": 0.904955141258698,
      "learning_rate": 0.000141,
      "loss": 10.1274,
      "step": 47
    },
    {
      "epoch": 0.00048,
      "grad_norm": 0.9044693581157806,
      "learning_rate": 0.000144,
      "loss": 10.1031,
      "step": 48
    },
    {
      "epoch": 0.00049,
      "grad_norm": 0.8992120995192336,
      "learning_rate": 0.000147,
      "loss": 10.0777,
      "step": 49
    },
    {
      "epoch": 0.0005,
      "grad_norm": 0.905676588399281,
      "learning_rate": 0.00015000000000000001,
      "loss": 10.0519,
      "step": 50
    },
    {
      "epoch": 0.00051,
      "grad_norm": 0.9066841497261428,
      "learning_rate": 0.000153,
      "loss": 10.0251,
      "step": 51
    },
    {
      "epoch": 0.00052,
      "grad_norm": 0.9046656683417261,
      "learning_rate": 0.000156,
      "loss": 9.9981,
      "step": 52
    },
    {
      "epoch": 0.00053,
      "grad_norm": 0.8943714853313668,
      "learning_rate": 0.000159,
      "loss": 9.974,
      "step": 53
    },
    {
      "epoch": 0.00054,
      "grad_norm": 0.9141658233846578,
      "learning_rate": 0.000162,
      "loss": 9.9419,
      "step": 54
    },
    {
      "epoch": 0.00055,
      "grad_norm": 0.9035944774643171,
      "learning_rate": 0.000165,
      "loss": 9.9169,
      "step": 55
    },
    {
      "epoch": 0.00056,
      "grad_norm": 0.895407870582166,
      "learning_rate": 0.00016800000000000002,
      "loss": 9.8872,
      "step": 56
    },
    {
      "epoch": 0.00057,
      "grad_norm": 0.9021731997760362,
      "learning_rate": 0.000171,
      "loss": 9.8601,
      "step": 57
    },
    {
      "epoch": 0.00058,
      "grad_norm": 0.8980871554912008,
      "learning_rate": 0.000174,
      "loss": 9.8343,
      "step": 58
    },
    {
      "epoch": 0.00059,
      "grad_norm": 0.9073832283363998,
      "learning_rate": 0.000177,
      "loss": 9.8028,
      "step": 59
    },
    {
      "epoch": 0.0006,
      "grad_norm": 0.8921071838486323,
      "learning_rate": 0.00017999999999999998,
      "loss": 9.777,
      "step": 60
    },
    {
      "epoch": 0.00061,
      "grad_norm": 0.8918001641348363,
      "learning_rate": 0.000183,
      "loss": 9.7484,
      "step": 61
    },
    {
      "epoch": 0.00062,
      "grad_norm": 0.897401330332219,
      "learning_rate": 0.000186,
      "loss": 9.717,
      "step": 62
    },
    {
      "epoch": 0.00063,
      "grad_norm": 0.8914516241190131,
      "learning_rate": 0.000189,
      "loss": 9.6894,
      "step": 63
    },
    {
      "epoch": 0.00064,
      "grad_norm": 0.8896652156254973,
      "learning_rate": 0.000192,
      "loss": 9.6587,
      "step": 64
    },
    {
      "epoch": 0.00065,
      "grad_norm": 0.8995447585153489,
      "learning_rate": 0.00019500000000000002,
      "loss": 9.6261,
      "step": 65
    },
    {
      "epoch": 0.00066,
      "grad_norm": 0.8896939041293862,
      "learning_rate": 0.00019800000000000002,
      "loss": 9.6026,
      "step": 66
    },
    {
      "epoch": 0.00067,
      "grad_norm": 0.8935314234316469,
      "learning_rate": 0.000201,
      "loss": 9.5723,
      "step": 67
    },
    {
      "epoch": 0.00068,
      "grad_norm": 0.8971584182008717,
      "learning_rate": 0.00020400000000000003,
      "loss": 9.5393,
      "step": 68
    },
    {
      "epoch": 0.00069,
      "grad_norm": 0.8806455604370673,
      "learning_rate": 0.00020700000000000002,
      "loss": 9.5119,
      "step": 69
    },
    {
      "epoch": 0.0007,
      "grad_norm": 0.892956094531968,
      "learning_rate": 0.00021000000000000004,
      "loss": 9.4751,
      "step": 70
    },
    {
      "epoch": 0.00071,
      "grad_norm": 0.8848452972865632,
      "learning_rate": 0.00021299999999999997,
      "loss": 9.4495,
      "step": 71
    },
    {
      "epoch": 0.00072,
      "grad_norm": 0.8831148731992822,
      "learning_rate": 0.000216,
      "loss": 9.4223,
      "step": 72
    },
    {
      "epoch": 0.00073,
      "grad_norm": 0.887150899449638,
      "learning_rate": 0.00021899999999999998,
      "loss": 9.3879,
      "step": 73
    },
    {
      "epoch": 0.00074,
      "grad_norm": 0.8878619769377328,
      "learning_rate": 0.000222,
      "loss": 9.3616,
      "step": 74
    },
    {
      "epoch": 0.00075,
      "grad_norm": 0.8808154408936898,
      "learning_rate": 0.000225,
      "loss": 9.3275,
      "step": 75
    },
    {
      "epoch": 0.00076,
      "grad_norm": 0.8908035269749474,
      "learning_rate": 0.000228,
      "loss": 9.3009,
      "step": 76
    },
    {
      "epoch": 0.00077,
      "grad_norm": 0.884531047332737,
      "learning_rate": 0.000231,
      "loss": 9.2727,
      "step": 77
    },
    {
      "epoch": 0.00078,
      "grad_norm": 0.8838664917591654,
      "learning_rate": 0.000234,
      "loss": 9.2422,
      "step": 78
    },
    {
      "epoch": 0.00079,
      "grad_norm": 0.8858668201182466,
      "learning_rate": 0.00023700000000000001,
      "loss": 9.2056,
      "step": 79
    },
    {
      "epoch": 0.0008,
      "grad_norm": 0.8856967305037482,
      "learning_rate": 0.00024,
      "loss": 9.1711,
      "step": 80
    },
    {
      "epoch": 0.00081,
      "grad_norm": 0.8942846826675519,
      "learning_rate": 0.00024300000000000002,
      "loss": 9.1382,
      "step": 81
    },
    {
      "epoch": 0.00082,
      "grad_norm": 0.897767651472895,
      "learning_rate": 0.000246,
      "loss": 9.1142,
      "step": 82
    },
    {
      "epoch": 0.00083,
      "grad_norm": 0.8951752702012633,
      "learning_rate": 0.00024900000000000004,
      "loss": 9.0778,
      "step": 83
    },
    {
      "epoch": 0.00084,
      "grad_norm": 0.8980395289622467,
      "learning_rate": 0.000252,
      "loss": 9.0469,
      "step": 84
    },
    {
      "epoch": 0.00085,
      "grad_norm": 0.8894006576183595,
      "learning_rate": 0.000255,
      "loss": 9.0242,
      "step": 85
    },
    {
      "epoch": 0.00086,
      "grad_norm": 0.8907945566480024,
      "learning_rate": 0.000258,
      "loss": 8.9886,
      "step": 86
    },
    {
      "epoch": 0.00087,
      "grad_norm": 0.8869170795764568,
      "learning_rate": 0.000261,
      "loss": 8.9664,
      "step": 87
    },
    {
      "epoch": 0.00088,
      "grad_norm": 0.8860541210154026,
      "learning_rate": 0.00026399999999999997,
      "loss": 8.9293,
      "step": 88
    },
    {
      "epoch": 0.00089,
      "grad_norm": 0.8822605600899943,
      "learning_rate": 0.000267,
      "loss": 8.9037,
      "step": 89
    },
    {
      "epoch": 0.0009,
      "grad_norm": 0.8817151929172502,
      "learning_rate": 0.00027,
      "loss": 8.8766,
      "step": 90
    },
    {
      "epoch": 0.00091,
      "grad_norm": 0.877617615465877,
      "learning_rate": 0.000273,
      "loss": 8.8478,
      "step": 91
    },
    {
      "epoch": 0.00092,
      "grad_norm": 0.8822716293479064,
      "learning_rate": 0.000276,
      "loss": 8.8156,
      "step": 92
    },
    {
      "epoch": 0.00093,
      "grad_norm": 0.8823661552266111,
      "learning_rate": 0.000279,
      "loss": 8.7863,
      "step": 93
    },
    {
      "epoch": 0.00094,
      "grad_norm": 0.8830384482321385,
      "learning_rate": 0.000282,
      "loss": 8.7609,
      "step": 94
    },
    {
      "epoch": 0.00095,
      "grad_norm": 0.8735042737334501,
      "learning_rate": 0.000285,
      "loss": 8.7321,
      "step": 95
    },
    {
      "epoch": 0.00096,
      "grad_norm": 0.8799214796836804,
      "learning_rate": 0.000288,
      "loss": 8.7028,
      "step": 96
    },
    {
      "epoch": 0.00097,
      "grad_norm": 0.8704594748643596,
      "learning_rate": 0.000291,
      "loss": 8.6791,
      "step": 97
    },
    {
      "epoch": 0.00098,
      "grad_norm": 0.8706415983834461,
      "learning_rate": 0.000294,
      "loss": 8.642,
      "step": 98
    },
    {
      "epoch": 0.00099,
      "grad_norm": 0.8683426041650804,
      "learning_rate": 0.000297,
      "loss": 8.62,
      "step": 99
    },
    {
      "epoch": 0.001,
      "grad_norm": 0.8690594926543161,
      "learning_rate": 0.00030000000000000003,
      "loss": 8.5941,
      "step": 100
    },
    {
      "epoch": 0.00101,
      "grad_norm": 0.8744725161423202,
      "learning_rate": 0.00030300000000000005,
      "loss": 8.5597,
      "step": 101
    },
    {
      "epoch": 0.00102,
      "grad_norm": 0.8626538117869429,
      "learning_rate": 0.000306,
      "loss": 8.5407,
      "step": 102
    },
    {
      "epoch": 0.00103,
      "grad_norm": 0.8630292491448714,
      "learning_rate": 0.000309,
      "loss": 8.5165,
      "step": 103
    },
    {
      "epoch": 0.00104,
      "grad_norm": 0.8566580756350954,
      "learning_rate": 0.000312,
      "loss": 8.4948,
      "step": 104
    },
    {
      "epoch": 0.00105,
      "grad_norm": 0.8588931967033124,
      "learning_rate": 0.000315,
      "loss": 8.4689,
      "step": 105
    },
    {
      "epoch": 0.00106,
      "grad_norm": 0.8531867230327145,
      "learning_rate": 0.000318,
      "loss": 8.4397,
      "step": 106
    },
    {
      "epoch": 0.00107,
      "grad_norm": 0.8474808010000593,
      "learning_rate": 0.000321,
      "loss": 8.4149,
      "step": 107
    },
    {
      "epoch": 0.00108,
      "grad_norm": 0.858890949163445,
      "learning_rate": 0.000324,
      "loss": 8.3866,
      "step": 108
    },
    {
      "epoch": 0.00109,
      "grad_norm": 0.862504115159085,
      "learning_rate": 0.000327,
      "loss": 8.3673,
      "step": 109
    },
    {
      "epoch": 0.0011,
      "grad_norm": 0.8797254817902618,
      "learning_rate": 0.00033,
      "loss": 8.3453,
      "step": 110
    },
    {
      "epoch": 0.00111,
      "grad_norm": 0.8938450574121157,
      "learning_rate": 0.000333,
      "loss": 8.3162,
      "step": 111
    },
    {
      "epoch": 0.00112,
      "grad_norm": 0.8984693362159062,
      "learning_rate": 0.00033600000000000004,
      "loss": 8.2961,
      "step": 112
    },
    {
      "epoch": 0.00113,
      "grad_norm": 0.8741969532880793,
      "learning_rate": 0.000339,
      "loss": 8.2543,
      "step": 113
    },
    {
      "epoch": 0.00114,
      "grad_norm": 0.8263135137442741,
      "learning_rate": 0.000342,
      "loss": 8.2446,
      "step": 114
    },
    {
      "epoch": 0.00115,
      "grad_norm": 0.8311105019716521,
      "learning_rate": 0.00034500000000000004,
      "loss": 8.2164,
      "step": 115
    },
    {
      "epoch": 0.00116,
      "grad_norm": 0.8585271561560018,
      "learning_rate": 0.000348,
      "loss": 8.1938,
      "step": 116
    },
    {
      "epoch": 0.00117,
      "grad_norm": 0.8687047969468357,
      "learning_rate": 0.000351,
      "loss": 8.1623,
      "step": 117
    },
    {
      "epoch": 0.00118,
      "grad_norm": 0.8460500876754268,
      "learning_rate": 0.000354,
      "loss": 8.1456,
      "step": 118
    },
    {
      "epoch": 0.00119,
      "grad_norm": 0.80734714043103,
      "learning_rate": 0.000357,
      "loss": 8.131,
      "step": 119
    },
    {
      "epoch": 0.0012,
      "grad_norm": 0.7912470130916918,
      "learning_rate": 0.00035999999999999997,
      "loss": 8.103,
      "step": 120
    },
    {
      "epoch": 0.00121,
      "grad_norm": 0.811181199244069,
      "learning_rate": 0.000363,
      "loss": 8.0751,
      "step": 121
    },
    {
      "epoch": 0.00122,
      "grad_norm": 0.8641427784894331,
      "learning_rate": 0.000366,
      "loss": 8.0581,
      "step": 122
    },
    {
      "epoch": 0.00123,
      "grad_norm": 1.059706847686213,
      "learning_rate": 0.000369,
      "loss": 8.038,
      "step": 123
    },
    {
      "epoch": 0.00124,
      "grad_norm": 1.1727027216994725,
      "learning_rate": 0.000372,
      "loss": 8.021,
      "step": 124
    },
    {
      "epoch": 0.00125,
      "grad_norm": 0.8130002892684417,
      "learning_rate": 0.000375,
      "loss": 7.9874,
      "step": 125
    }
  ],
  "logging_steps": 1,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4955455356928000.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}