{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5194805194805194,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005194805194805195,
      "grad_norm": 0.6512172818183899,
      "learning_rate": 1e-05,
      "loss": 0.2975,
      "step": 1
    },
    {
      "epoch": 0.005194805194805195,
      "eval_loss": 0.31846052408218384,
      "eval_runtime": 23.0058,
      "eval_samples_per_second": 7.042,
      "eval_steps_per_second": 0.913,
      "step": 1
    },
    {
      "epoch": 0.01038961038961039,
      "grad_norm": 0.582506000995636,
      "learning_rate": 2e-05,
      "loss": 0.3404,
      "step": 2
    },
    {
      "epoch": 0.015584415584415584,
      "grad_norm": 0.617966890335083,
      "learning_rate": 3e-05,
      "loss": 0.2898,
      "step": 3
    },
    {
      "epoch": 0.02077922077922078,
      "grad_norm": 0.520855724811554,
      "learning_rate": 4e-05,
      "loss": 0.2852,
      "step": 4
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 0.4192945659160614,
      "learning_rate": 5e-05,
      "loss": 0.2385,
      "step": 5
    },
    {
      "epoch": 0.03116883116883117,
      "grad_norm": 0.505161464214325,
      "learning_rate": 6e-05,
      "loss": 0.2575,
      "step": 6
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 0.38516223430633545,
      "learning_rate": 7e-05,
      "loss": 0.2214,
      "step": 7
    },
    {
      "epoch": 0.04155844155844156,
      "grad_norm": 0.4020881652832031,
      "learning_rate": 8e-05,
      "loss": 0.2133,
      "step": 8
    },
    {
      "epoch": 0.046753246753246755,
      "grad_norm": 0.3436403274536133,
      "learning_rate": 9e-05,
      "loss": 0.1667,
      "step": 9
    },
    {
      "epoch": 0.046753246753246755,
      "eval_loss": 0.1596369743347168,
      "eval_runtime": 22.5839,
      "eval_samples_per_second": 7.173,
      "eval_steps_per_second": 0.93,
      "step": 9
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 0.49033334851264954,
      "learning_rate": 0.0001,
      "loss": 0.134,
      "step": 10
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.6079919934272766,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.1385,
      "step": 11
    },
    {
      "epoch": 0.06233766233766234,
      "grad_norm": 0.36646488308906555,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.1043,
      "step": 12
    },
    {
      "epoch": 0.06753246753246753,
      "grad_norm": 0.4232967495918274,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.096,
      "step": 13
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 0.33586767315864563,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0841,
      "step": 14
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 0.3924535810947418,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.1285,
      "step": 15
    },
    {
      "epoch": 0.08311688311688312,
      "grad_norm": 0.18153129518032074,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.0785,
      "step": 16
    },
    {
      "epoch": 0.08831168831168831,
      "grad_norm": 0.24562297761440277,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.1021,
      "step": 17
    },
    {
      "epoch": 0.09350649350649351,
      "grad_norm": 0.26164862513542175,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.1018,
      "step": 18
    },
    {
      "epoch": 0.09350649350649351,
      "eval_loss": 0.09928437322378159,
      "eval_runtime": 22.6029,
      "eval_samples_per_second": 7.167,
      "eval_steps_per_second": 0.929,
      "step": 18
    },
    {
      "epoch": 0.0987012987012987,
      "grad_norm": 0.22686384618282318,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0877,
      "step": 19
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 0.28908219933509827,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0838,
      "step": 20
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 0.18994401395320892,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0871,
      "step": 21
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.264817476272583,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1082,
      "step": 22
    },
    {
      "epoch": 0.11948051948051948,
      "grad_norm": 0.2291824370622635,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.1011,
      "step": 23
    },
    {
      "epoch": 0.12467532467532468,
      "grad_norm": 0.21350443363189697,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0845,
      "step": 24
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 0.29027238488197327,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0808,
      "step": 25
    },
    {
      "epoch": 0.13506493506493505,
      "grad_norm": 0.18834447860717773,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0753,
      "step": 26
    },
    {
      "epoch": 0.14025974025974025,
      "grad_norm": 0.20661011338233948,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.069,
      "step": 27
    },
    {
      "epoch": 0.14025974025974025,
      "eval_loss": 0.08679472655057907,
      "eval_runtime": 22.6145,
      "eval_samples_per_second": 7.164,
      "eval_steps_per_second": 0.929,
      "step": 27
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 0.20090429484844208,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0937,
      "step": 28
    },
    {
      "epoch": 0.15064935064935064,
      "grad_norm": 0.16515026986598969,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.0914,
      "step": 29
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 0.1607162356376648,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0817,
      "step": 30
    },
    {
      "epoch": 0.16103896103896104,
      "grad_norm": 0.1903841644525528,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.0783,
      "step": 31
    },
    {
      "epoch": 0.16623376623376623,
      "grad_norm": 0.16916249692440033,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.0755,
      "step": 32
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.16402561962604523,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0841,
      "step": 33
    },
    {
      "epoch": 0.17662337662337663,
      "grad_norm": 0.14771829545497894,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0673,
      "step": 34
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.1731143295764923,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0719,
      "step": 35
    },
    {
      "epoch": 0.18701298701298702,
      "grad_norm": 0.1377805471420288,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.042,
      "step": 36
    },
    {
      "epoch": 0.18701298701298702,
      "eval_loss": 0.08124008774757385,
      "eval_runtime": 22.6185,
      "eval_samples_per_second": 7.162,
      "eval_steps_per_second": 0.928,
      "step": 36
    },
    {
      "epoch": 0.19220779220779222,
      "grad_norm": 0.2264535129070282,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.1083,
      "step": 37
    },
    {
      "epoch": 0.1974025974025974,
      "grad_norm": 0.20371174812316895,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.1143,
      "step": 38
    },
    {
      "epoch": 0.2025974025974026,
      "grad_norm": 0.17776520550251007,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.0901,
      "step": 39
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 0.18457242846488953,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0453,
      "step": 40
    },
    {
      "epoch": 0.21298701298701297,
      "grad_norm": 0.16957609355449677,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.0667,
      "step": 41
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 0.17374463379383087,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0931,
      "step": 42
    },
    {
      "epoch": 0.22337662337662337,
      "grad_norm": 0.1706293821334839,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.0836,
      "step": 43
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.19250139594078064,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0656,
      "step": 44
    },
    {
      "epoch": 0.23376623376623376,
      "grad_norm": 0.20472918450832367,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0763,
      "step": 45
    },
    {
      "epoch": 0.23376623376623376,
      "eval_loss": 0.07584932446479797,
      "eval_runtime": 22.6222,
      "eval_samples_per_second": 7.161,
      "eval_steps_per_second": 0.928,
      "step": 45
    },
    {
      "epoch": 0.23896103896103896,
      "grad_norm": 0.231777623295784,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.1004,
      "step": 46
    },
    {
      "epoch": 0.24415584415584415,
      "grad_norm": 0.11294512450695038,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.0348,
      "step": 47
    },
    {
      "epoch": 0.24935064935064935,
      "grad_norm": 0.1873050183057785,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0585,
      "step": 48
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 0.16472087800502777,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.0741,
      "step": 49
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 0.18180659413337708,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0601,
      "step": 50
    },
    {
      "epoch": 0.2649350649350649,
      "grad_norm": 0.16862627863883972,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.0804,
      "step": 51
    },
    {
      "epoch": 0.2701298701298701,
      "grad_norm": 0.13611538708209991,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.0543,
      "step": 52
    },
    {
      "epoch": 0.2753246753246753,
      "grad_norm": 0.1309695988893509,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.0373,
      "step": 53
    },
    {
      "epoch": 0.2805194805194805,
      "grad_norm": 0.1477537453174591,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0624,
      "step": 54
    },
    {
      "epoch": 0.2805194805194805,
      "eval_loss": 0.07352881133556366,
      "eval_runtime": 22.5921,
      "eval_samples_per_second": 7.171,
      "eval_steps_per_second": 0.93,
      "step": 54
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.20091575384140015,
      "learning_rate": 5e-05,
      "loss": 0.1192,
      "step": 55
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 0.13857708871364594,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0512,
      "step": 56
    },
    {
      "epoch": 0.2961038961038961,
      "grad_norm": 0.1847558617591858,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.0761,
      "step": 57
    },
    {
      "epoch": 0.3012987012987013,
      "grad_norm": 0.21804849803447723,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0864,
      "step": 58
    },
    {
      "epoch": 0.3064935064935065,
      "grad_norm": 0.16650082170963287,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0695,
      "step": 59
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 0.17148281633853912,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0684,
      "step": 60
    },
    {
      "epoch": 0.3168831168831169,
      "grad_norm": 0.1832764744758606,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0866,
      "step": 61
    },
    {
      "epoch": 0.3220779220779221,
      "grad_norm": 0.1815570890903473,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0558,
      "step": 62
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 0.1455354541540146,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0574,
      "step": 63
    },
    {
      "epoch": 0.32727272727272727,
      "eval_loss": 0.07065539807081223,
      "eval_runtime": 22.6068,
      "eval_samples_per_second": 7.166,
      "eval_steps_per_second": 0.929,
      "step": 63
    },
    {
      "epoch": 0.33246753246753247,
      "grad_norm": 0.17949555814266205,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0897,
      "step": 64
    },
    {
      "epoch": 0.33766233766233766,
      "grad_norm": 0.1759766936302185,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0975,
      "step": 65
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.22971631586551666,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0789,
      "step": 66
    },
    {
      "epoch": 0.34805194805194806,
      "grad_norm": 0.15745718777179718,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.0591,
      "step": 67
    },
    {
      "epoch": 0.35324675324675325,
      "grad_norm": 0.1421278715133667,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0495,
      "step": 68
    },
    {
      "epoch": 0.35844155844155845,
      "grad_norm": 0.16501501202583313,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.0805,
      "step": 69
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.12246041744947433,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0629,
      "step": 70
    },
    {
      "epoch": 0.36883116883116884,
      "grad_norm": 0.13903050124645233,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0502,
      "step": 71
    },
    {
      "epoch": 0.37402597402597404,
      "grad_norm": 0.14397020637989044,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.076,
      "step": 72
    },
    {
      "epoch": 0.37402597402597404,
      "eval_loss": 0.06936134397983551,
      "eval_runtime": 22.6362,
      "eval_samples_per_second": 7.157,
      "eval_steps_per_second": 0.928,
      "step": 72
    },
    {
      "epoch": 0.37922077922077924,
      "grad_norm": 0.20336154103279114,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0601,
      "step": 73
    },
    {
      "epoch": 0.38441558441558443,
      "grad_norm": 0.17200997471809387,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0884,
      "step": 74
    },
    {
      "epoch": 0.38961038961038963,
      "grad_norm": 0.23166747391223907,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0878,
      "step": 75
    },
    {
      "epoch": 0.3948051948051948,
      "grad_norm": 0.17590440809726715,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0735,
      "step": 76
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.14351186156272888,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.0445,
      "step": 77
    },
    {
      "epoch": 0.4051948051948052,
      "grad_norm": 0.18998196721076965,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0669,
      "step": 78
    },
    {
      "epoch": 0.4103896103896104,
      "grad_norm": 0.13183800876140594,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.0446,
      "step": 79
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 0.12525179982185364,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0512,
      "step": 80
    },
    {
      "epoch": 0.42077922077922075,
      "grad_norm": 0.10664654523134232,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.0534,
      "step": 81
    },
    {
      "epoch": 0.42077922077922075,
      "eval_loss": 0.06824448704719543,
      "eval_runtime": 22.6037,
      "eval_samples_per_second": 7.167,
      "eval_steps_per_second": 0.929,
      "step": 81
    },
    {
      "epoch": 0.42597402597402595,
      "grad_norm": 0.1638413369655609,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0666,
      "step": 82
    },
    {
      "epoch": 0.43116883116883115,
      "grad_norm": 0.20585042238235474,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.0702,
      "step": 83
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 0.21151496469974518,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0954,
      "step": 84
    },
    {
      "epoch": 0.44155844155844154,
      "grad_norm": 0.1546739637851715,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0782,
      "step": 85
    },
    {
      "epoch": 0.44675324675324674,
      "grad_norm": 0.16944894194602966,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0643,
      "step": 86
    },
    {
      "epoch": 0.45194805194805193,
      "grad_norm": 0.16189202666282654,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.09,
      "step": 87
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.15692783892154694,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0607,
      "step": 88
    },
    {
      "epoch": 0.4623376623376623,
      "grad_norm": 0.208195298910141,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.0686,
      "step": 89
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 0.15665802359580994,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0544,
      "step": 90
    },
    {
      "epoch": 0.4675324675324675,
      "eval_loss": 0.06768222153186798,
      "eval_runtime": 22.6003,
      "eval_samples_per_second": 7.168,
      "eval_steps_per_second": 0.929,
      "step": 90
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 0.1396227329969406,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0581,
      "step": 91
    },
    {
      "epoch": 0.4779220779220779,
      "grad_norm": 0.1297990381717682,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0534,
      "step": 92
    },
    {
      "epoch": 0.4831168831168831,
      "grad_norm": 0.1293753981590271,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.0439,
      "step": 93
    },
    {
      "epoch": 0.4883116883116883,
      "grad_norm": 0.14105373620986938,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0622,
      "step": 94
    },
    {
      "epoch": 0.4935064935064935,
      "grad_norm": 0.17408247292041779,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0733,
      "step": 95
    },
    {
      "epoch": 0.4987012987012987,
      "grad_norm": 0.10883349925279617,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0461,
      "step": 96
    },
    {
      "epoch": 0.5038961038961038,
      "grad_norm": 0.18541282415390015,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.1061,
      "step": 97
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 0.12432613968849182,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0606,
      "step": 98
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.14815571904182434,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.0744,
      "step": 99
    },
    {
      "epoch": 0.5142857142857142,
      "eval_loss": 0.0675034150481224,
      "eval_runtime": 22.5971,
      "eval_samples_per_second": 7.169,
      "eval_steps_per_second": 0.929,
      "step": 99
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 0.23351338505744934,
      "learning_rate": 0.0,
      "loss": 0.0747,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0720271247448474e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}