{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 184,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010869565217391304,
      "grad_norm": 0.03240465296922696,
      "learning_rate": 1.0526315789473685e-06,
      "loss": 0.5318,
      "step": 1
    },
    {
      "epoch": 0.021739130434782608,
      "grad_norm": 0.031148191782486748,
      "learning_rate": 2.105263157894737e-06,
      "loss": 0.505,
      "step": 2
    },
    {
      "epoch": 0.03260869565217391,
      "grad_norm": 0.03287048185671828,
      "learning_rate": 3.157894736842105e-06,
      "loss": 0.517,
      "step": 3
    },
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.03645975365762924,
      "learning_rate": 4.210526315789474e-06,
      "loss": 0.5547,
      "step": 4
    },
    {
      "epoch": 0.05434782608695652,
      "grad_norm": 0.03208238827298806,
      "learning_rate": 5.263157894736842e-06,
      "loss": 0.5284,
      "step": 5
    },
    {
      "epoch": 0.06521739130434782,
      "grad_norm": 0.038367637681218175,
      "learning_rate": 6.31578947368421e-06,
      "loss": 0.5838,
      "step": 6
    },
    {
      "epoch": 0.07608695652173914,
      "grad_norm": 0.03450300334168957,
      "learning_rate": 7.368421052631579e-06,
      "loss": 0.5382,
      "step": 7
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.03388554313817737,
      "learning_rate": 8.421052631578948e-06,
      "loss": 0.524,
      "step": 8
    },
    {
      "epoch": 0.09782608695652174,
      "grad_norm": 0.03544242363659419,
      "learning_rate": 9.473684210526315e-06,
      "loss": 0.5501,
      "step": 9
    },
    {
      "epoch": 0.10869565217391304,
      "grad_norm": 0.03352231239492054,
      "learning_rate": 1.0526315789473684e-05,
      "loss": 0.5069,
      "step": 10
    },
    {
      "epoch": 0.11956521739130435,
      "grad_norm": 0.03572670440459065,
      "learning_rate": 1.1578947368421053e-05,
      "loss": 0.5223,
      "step": 11
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.03663832921257728,
      "learning_rate": 1.263157894736842e-05,
      "loss": 0.5509,
      "step": 12
    },
    {
      "epoch": 0.14130434782608695,
      "grad_norm": 0.03809520900571492,
      "learning_rate": 1.3684210526315791e-05,
      "loss": 0.5401,
      "step": 13
    },
    {
      "epoch": 0.15217391304347827,
      "grad_norm": 0.03789719542276196,
      "learning_rate": 1.4736842105263159e-05,
      "loss": 0.5408,
      "step": 14
    },
    {
      "epoch": 0.16304347826086957,
      "grad_norm": 0.03420580590941963,
      "learning_rate": 1.578947368421053e-05,
      "loss": 0.4729,
      "step": 15
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.03602266807911341,
      "learning_rate": 1.6842105263157896e-05,
      "loss": 0.4934,
      "step": 16
    },
    {
      "epoch": 0.18478260869565216,
      "grad_norm": 0.04138637589841341,
      "learning_rate": 1.7894736842105264e-05,
      "loss": 0.5376,
      "step": 17
    },
    {
      "epoch": 0.1956521739130435,
      "grad_norm": 0.04435583894932485,
      "learning_rate": 1.894736842105263e-05,
      "loss": 0.5642,
      "step": 18
    },
    {
      "epoch": 0.20652173913043478,
      "grad_norm": 0.04141900808302216,
      "learning_rate": 2e-05,
      "loss": 0.5591,
      "step": 19
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.03675591300747317,
      "learning_rate": 1.999818745523526e-05,
      "loss": 0.5022,
      "step": 20
    },
    {
      "epoch": 0.22826086956521738,
      "grad_norm": 0.035936674391353805,
      "learning_rate": 1.999275047800474e-05,
      "loss": 0.5342,
      "step": 21
    },
    {
      "epoch": 0.2391304347826087,
      "grad_norm": 0.03766128882621122,
      "learning_rate": 1.9983691039261358e-05,
      "loss": 0.5437,
      "step": 22
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.03747365385813838,
      "learning_rate": 1.9971012423132776e-05,
      "loss": 0.5113,
      "step": 23
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.037562789979165546,
      "learning_rate": 1.9954719225730847e-05,
      "loss": 0.5219,
      "step": 24
    },
    {
      "epoch": 0.2717391304347826,
      "grad_norm": 0.033732964863589725,
      "learning_rate": 1.99348173534855e-05,
      "loss": 0.4899,
      "step": 25
    },
    {
      "epoch": 0.2826086956521739,
      "grad_norm": 0.032706454390573285,
      "learning_rate": 1.9911314021003614e-05,
      "loss": 0.46,
      "step": 26
    },
    {
      "epoch": 0.29347826086956524,
      "grad_norm": 0.03299013215961956,
      "learning_rate": 1.9884217748453625e-05,
      "loss": 0.4464,
      "step": 27
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.036322686035091326,
      "learning_rate": 1.9853538358476933e-05,
      "loss": 0.525,
      "step": 28
    },
    {
      "epoch": 0.31521739130434784,
      "grad_norm": 0.035349035280986665,
      "learning_rate": 1.9819286972627066e-05,
      "loss": 0.481,
      "step": 29
    },
    {
      "epoch": 0.32608695652173914,
      "grad_norm": 0.03304667685973592,
      "learning_rate": 1.9781476007338058e-05,
      "loss": 0.486,
      "step": 30
    },
    {
      "epoch": 0.33695652173913043,
      "grad_norm": 0.03594690118986878,
      "learning_rate": 1.9740119169423337e-05,
      "loss": 0.4459,
      "step": 31
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.03722435746668587,
      "learning_rate": 1.9695231451106914e-05,
      "loss": 0.4884,
      "step": 32
    },
    {
      "epoch": 0.358695652173913,
      "grad_norm": 0.03234546772265382,
      "learning_rate": 1.964682912458856e-05,
      "loss": 0.4538,
      "step": 33
    },
    {
      "epoch": 0.3695652173913043,
      "grad_norm": 0.03332715856138033,
      "learning_rate": 1.9594929736144978e-05,
      "loss": 0.4684,
      "step": 34
    },
    {
      "epoch": 0.3804347826086957,
      "grad_norm": 0.03192258021162577,
      "learning_rate": 1.9539552099769128e-05,
      "loss": 0.5074,
      "step": 35
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.028905879450475694,
      "learning_rate": 1.9480716290349998e-05,
      "loss": 0.4329,
      "step": 36
    },
    {
      "epoch": 0.40217391304347827,
      "grad_norm": 0.026272771750420486,
      "learning_rate": 1.941844363639525e-05,
      "loss": 0.4104,
      "step": 37
    },
    {
      "epoch": 0.41304347826086957,
      "grad_norm": 0.029512600659781462,
      "learning_rate": 1.9352756712299467e-05,
      "loss": 0.4352,
      "step": 38
    },
    {
      "epoch": 0.42391304347826086,
      "grad_norm": 0.03106074409081994,
      "learning_rate": 1.9283679330160726e-05,
      "loss": 0.4617,
      "step": 39
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.02877012176170005,
      "learning_rate": 1.92112365311485e-05,
      "loss": 0.4492,
      "step": 40
    },
    {
      "epoch": 0.44565217391304346,
      "grad_norm": 0.028504695790476927,
      "learning_rate": 1.913545457642601e-05,
      "loss": 0.4388,
      "step": 41
    },
    {
      "epoch": 0.45652173913043476,
      "grad_norm": 0.02776562257630969,
      "learning_rate": 1.905636093763031e-05,
      "loss": 0.457,
      "step": 42
    },
    {
      "epoch": 0.4673913043478261,
      "grad_norm": 0.02279898042963453,
      "learning_rate": 1.8973984286913584e-05,
      "loss": 0.4228,
      "step": 43
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.022273693107528456,
      "learning_rate": 1.8888354486549238e-05,
      "loss": 0.4141,
      "step": 44
    },
    {
      "epoch": 0.4891304347826087,
      "grad_norm": 0.022833837988057187,
      "learning_rate": 1.8799502578106533e-05,
      "loss": 0.4252,
      "step": 45
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.021546758234096523,
      "learning_rate": 1.8707460771197773e-05,
      "loss": 0.4417,
      "step": 46
    },
    {
      "epoch": 0.5108695652173914,
      "grad_norm": 0.019884209926995258,
      "learning_rate": 1.861226243180201e-05,
      "loss": 0.4249,
      "step": 47
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.02067326340118169,
      "learning_rate": 1.8513942070169572e-05,
      "loss": 0.4498,
      "step": 48
    },
    {
      "epoch": 0.532608695652174,
      "grad_norm": 0.018558394593515687,
      "learning_rate": 1.8412535328311813e-05,
      "loss": 0.4188,
      "step": 49
    },
    {
      "epoch": 0.5434782608695652,
      "grad_norm": 0.019420981988919603,
      "learning_rate": 1.8308078967080547e-05,
      "loss": 0.425,
      "step": 50
    },
    {
      "epoch": 0.5543478260869565,
      "grad_norm": 0.01678791068237689,
      "learning_rate": 1.8200610852841913e-05,
      "loss": 0.3955,
      "step": 51
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.018788790486373518,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.4273,
      "step": 52
    },
    {
      "epoch": 0.5760869565217391,
      "grad_norm": 0.01812533816051695,
      "learning_rate": 1.7976796275621556e-05,
      "loss": 0.3664,
      "step": 53
    },
    {
      "epoch": 0.5869565217391305,
      "grad_norm": 0.017190627828475347,
      "learning_rate": 1.7860530947427878e-05,
      "loss": 0.4481,
      "step": 54
    },
    {
      "epoch": 0.5978260869565217,
      "grad_norm": 0.019689749698733695,
      "learning_rate": 1.7741416106390828e-05,
      "loss": 0.4529,
      "step": 55
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.017252168109986435,
      "learning_rate": 1.761949493270671e-05,
      "loss": 0.4251,
      "step": 56
    },
    {
      "epoch": 0.6195652173913043,
      "grad_norm": 0.017554978035306083,
      "learning_rate": 1.7494811623892543e-05,
      "loss": 0.4348,
      "step": 57
    },
    {
      "epoch": 0.6304347826086957,
      "grad_norm": 0.01728596934943526,
      "learning_rate": 1.736741137876405e-05,
      "loss": 0.4298,
      "step": 58
    },
    {
      "epoch": 0.6413043478260869,
      "grad_norm": 0.016841718915483313,
      "learning_rate": 1.72373403810507e-05,
      "loss": 0.424,
      "step": 59
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.017988846143621267,
      "learning_rate": 1.710464578265369e-05,
      "loss": 0.4192,
      "step": 60
    },
    {
      "epoch": 0.6630434782608695,
      "grad_norm": 0.016118964656136582,
      "learning_rate": 1.696937568655294e-05,
      "loss": 0.4388,
      "step": 61
    },
    {
      "epoch": 0.6739130434782609,
      "grad_norm": 0.016980548999802704,
      "learning_rate": 1.6831579129369347e-05,
      "loss": 0.4337,
      "step": 62
    },
    {
      "epoch": 0.6847826086956522,
      "grad_norm": 0.016896592627422335,
      "learning_rate": 1.6691306063588583e-05,
      "loss": 0.4004,
      "step": 63
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.015889660322036148,
      "learning_rate": 1.6548607339452853e-05,
      "loss": 0.4393,
      "step": 64
    },
    {
      "epoch": 0.7065217391304348,
      "grad_norm": 0.016428852385924283,
      "learning_rate": 1.6403534686527223e-05,
      "loss": 0.4239,
      "step": 65
    },
    {
      "epoch": 0.717391304347826,
      "grad_norm": 0.01539489673351542,
      "learning_rate": 1.6256140694947217e-05,
      "loss": 0.3979,
      "step": 66
    },
    {
      "epoch": 0.7282608695652174,
      "grad_norm": 0.017016571801118784,
      "learning_rate": 1.6106478796354382e-05,
      "loss": 0.4531,
      "step": 67
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.018614609000821066,
      "learning_rate": 1.595460324452688e-05,
      "loss": 0.3969,
      "step": 68
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.01603990010550668,
      "learning_rate": 1.5800569095711983e-05,
      "loss": 0.4444,
      "step": 69
    },
    {
      "epoch": 0.7608695652173914,
      "grad_norm": 0.016345231925260058,
      "learning_rate": 1.5644432188667695e-05,
      "loss": 0.43,
      "step": 70
    },
    {
      "epoch": 0.7717391304347826,
      "grad_norm": 0.014545507199229903,
      "learning_rate": 1.5486249124420702e-05,
      "loss": 0.4395,
      "step": 71
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.016159427204217675,
      "learning_rate": 1.5326077245747998e-05,
      "loss": 0.4324,
      "step": 72
    },
    {
      "epoch": 0.7934782608695652,
      "grad_norm": 0.01577781927643107,
      "learning_rate": 1.5163974616389621e-05,
      "loss": 0.3783,
      "step": 73
    },
    {
      "epoch": 0.8043478260869565,
      "grad_norm": 0.020543349930487027,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.4517,
      "step": 74
    },
    {
      "epoch": 0.8152173913043478,
      "grad_norm": 0.0162387560400049,
      "learning_rate": 1.4834212838845639e-05,
      "loss": 0.4323,
      "step": 75
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.017194073308575693,
      "learning_rate": 1.4666673232256738e-05,
      "loss": 0.4531,
      "step": 76
    },
    {
      "epoch": 0.8369565217391305,
      "grad_norm": 0.014830688698626977,
      "learning_rate": 1.449744191484066e-05,
      "loss": 0.4044,
      "step": 77
    },
    {
      "epoch": 0.8478260869565217,
      "grad_norm": 0.017667656527989815,
      "learning_rate": 1.4326580234465084e-05,
      "loss": 0.4084,
      "step": 78
    },
    {
      "epoch": 0.8586956521739131,
      "grad_norm": 0.01665626106397431,
      "learning_rate": 1.4154150130018867e-05,
      "loss": 0.3811,
      "step": 79
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.015487133239067268,
      "learning_rate": 1.3980214108958626e-05,
      "loss": 0.3792,
      "step": 80
    },
    {
      "epoch": 0.8804347826086957,
      "grad_norm": 0.015980794746876442,
      "learning_rate": 1.380483522464923e-05,
      "loss": 0.3567,
      "step": 81
    },
    {
      "epoch": 0.8913043478260869,
      "grad_norm": 0.01742924875832292,
      "learning_rate": 1.362807705350641e-05,
      "loss": 0.4108,
      "step": 82
    },
    {
      "epoch": 0.9021739130434783,
      "grad_norm": 0.01621883533665314,
      "learning_rate": 1.3450003671949707e-05,
      "loss": 0.3885,
      "step": 83
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.01816609517986378,
      "learning_rate": 1.3270679633174219e-05,
      "loss": 0.4195,
      "step": 84
    },
    {
      "epoch": 0.9239130434782609,
      "grad_norm": 0.01700022402834444,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.4008,
      "step": 85
    },
    {
      "epoch": 0.9347826086956522,
      "grad_norm": 0.015423948003415178,
      "learning_rate": 1.2908540040053992e-05,
      "loss": 0.4284,
      "step": 86
    },
    {
      "epoch": 0.9456521739130435,
      "grad_norm": 0.016648244343970338,
      "learning_rate": 1.2725855764553981e-05,
      "loss": 0.4353,
      "step": 87
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.018695896408094728,
      "learning_rate": 1.2542183341934873e-05,
      "loss": 0.4454,
      "step": 88
    },
    {
      "epoch": 0.967391304347826,
      "grad_norm": 0.014985563910038587,
      "learning_rate": 1.2357589355094275e-05,
      "loss": 0.4254,
      "step": 89
    },
    {
      "epoch": 0.9782608695652174,
      "grad_norm": 0.0158615730686512,
      "learning_rate": 1.217214072100508e-05,
      "loss": 0.4141,
      "step": 90
    },
    {
      "epoch": 0.9891304347826086,
      "grad_norm": 0.01615877678103288,
      "learning_rate": 1.1985904666457455e-05,
      "loss": 0.3743,
      "step": 91
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.017892852375543514,
      "learning_rate": 1.179894870368854e-05,
      "loss": 0.4298,
      "step": 92
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.48603561520576477,
      "eval_runtime": 5.8299,
      "eval_samples_per_second": 0.172,
      "eval_steps_per_second": 0.172,
      "step": 92
    },
    {
      "epoch": 1.0108695652173914,
      "grad_norm": 0.017298462574072342,
      "learning_rate": 1.1611340605908643e-05,
      "loss": 0.4148,
      "step": 93
    },
    {
      "epoch": 1.0217391304347827,
      "grad_norm": 0.017838476342072244,
      "learning_rate": 1.1423148382732854e-05,
      "loss": 0.4034,
      "step": 94
    },
    {
      "epoch": 1.0326086956521738,
      "grad_norm": 0.01861199740817311,
      "learning_rate": 1.1234440255526948e-05,
      "loss": 0.4219,
      "step": 95
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.01671425099245661,
      "learning_rate": 1.1045284632676535e-05,
      "loss": 0.4046,
      "step": 96
    },
    {
      "epoch": 1.0543478260869565,
      "grad_norm": 0.01861001152790246,
      "learning_rate": 1.08557500847884e-05,
      "loss": 0.4009,
      "step": 97
    },
    {
      "epoch": 1.065217391304348,
      "grad_norm": 0.018107901828337766,
      "learning_rate": 1.066590531983304e-05,
      "loss": 0.4089,
      "step": 98
    },
    {
      "epoch": 1.0760869565217392,
      "grad_norm": 0.0174920546188433,
      "learning_rate": 1.0475819158237426e-05,
      "loss": 0.3954,
      "step": 99
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.016682152706871897,
      "learning_rate": 1.0285560507936962e-05,
      "loss": 0.4289,
      "step": 100
    },
    {
      "epoch": 1.0978260869565217,
      "grad_norm": 0.018098011701254673,
      "learning_rate": 1.0095198339395769e-05,
      "loss": 0.4302,
      "step": 101
    },
    {
      "epoch": 1.108695652173913,
      "grad_norm": 0.015568335864025949,
      "learning_rate": 9.904801660604234e-06,
      "loss": 0.409,
      "step": 102
    },
    {
      "epoch": 1.1195652173913044,
      "grad_norm": 0.016958799953214254,
      "learning_rate": 9.71443949206304e-06,
      "loss": 0.4039,
      "step": 103
    },
    {
      "epoch": 1.1304347826086956,
      "grad_norm": 0.017521827484537653,
      "learning_rate": 9.524180841762577e-06,
      "loss": 0.4142,
      "step": 104
    },
    {
      "epoch": 1.141304347826087,
      "grad_norm": 0.018438050806712614,
      "learning_rate": 9.334094680166962e-06,
      "loss": 0.4085,
      "step": 105
    },
    {
      "epoch": 1.1521739130434783,
      "grad_norm": 0.01941444882552903,
      "learning_rate": 9.144249915211605e-06,
      "loss": 0.4298,
      "step": 106
    },
    {
      "epoch": 1.1630434782608696,
      "grad_norm": 0.017649511484447825,
      "learning_rate": 8.954715367323468e-06,
      "loss": 0.4161,
      "step": 107
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 0.01677483752186088,
      "learning_rate": 8.765559744473054e-06,
      "loss": 0.4042,
      "step": 108
    },
    {
      "epoch": 1.184782608695652,
      "grad_norm": 0.017213373571849412,
      "learning_rate": 8.576851617267151e-06,
      "loss": 0.409,
      "step": 109
    },
    {
      "epoch": 1.1956521739130435,
      "grad_norm": 0.01804604085921314,
      "learning_rate": 8.388659394091362e-06,
      "loss": 0.4195,
      "step": 110
    },
    {
      "epoch": 1.2065217391304348,
      "grad_norm": 0.019524779611806008,
      "learning_rate": 8.201051296311462e-06,
      "loss": 0.4144,
      "step": 111
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.01961583109753067,
      "learning_rate": 8.014095333542548e-06,
      "loss": 0.4169,
      "step": 112
    },
    {
      "epoch": 1.2282608695652173,
      "grad_norm": 0.01828151965518523,
      "learning_rate": 7.827859278994924e-06,
      "loss": 0.3989,
      "step": 113
    },
    {
      "epoch": 1.2391304347826086,
      "grad_norm": 0.01958662355054947,
      "learning_rate": 7.642410644905726e-06,
      "loss": 0.4166,
      "step": 114
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.018324698258002987,
      "learning_rate": 7.4578166580651335e-06,
      "loss": 0.4191,
      "step": 115
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 0.01711860737234338,
      "learning_rate": 7.274144235446024e-06,
      "loss": 0.3976,
      "step": 116
    },
    {
      "epoch": 1.2717391304347827,
      "grad_norm": 0.015977161100683545,
      "learning_rate": 7.0914599599460095e-06,
      "loss": 0.4301,
      "step": 117
    },
    {
      "epoch": 1.2826086956521738,
      "grad_norm": 0.017423189335602548,
      "learning_rate": 6.909830056250527e-06,
      "loss": 0.3972,
      "step": 118
    },
    {
      "epoch": 1.2934782608695652,
      "grad_norm": 0.020183820621289872,
      "learning_rate": 6.729320366825785e-06,
      "loss": 0.406,
      "step": 119
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.0188473400999686,
      "learning_rate": 6.549996328050296e-06,
      "loss": 0.3886,
      "step": 120
    },
    {
      "epoch": 1.315217391304348,
      "grad_norm": 0.02064149059917863,
      "learning_rate": 6.3719229464935915e-06,
      "loss": 0.456,
      "step": 121
    },
    {
      "epoch": 1.3260869565217392,
      "grad_norm": 0.02178374309057221,
      "learning_rate": 6.19516477535077e-06,
      "loss": 0.4171,
      "step": 122
    },
    {
      "epoch": 1.3369565217391304,
      "grad_norm": 0.02027707601043217,
      "learning_rate": 6.019785891041381e-06,
      "loss": 0.3642,
      "step": 123
    },
    {
      "epoch": 1.3478260869565217,
      "grad_norm": 0.021269660172408174,
      "learning_rate": 5.845849869981137e-06,
      "loss": 0.4017,
      "step": 124
    },
    {
      "epoch": 1.358695652173913,
      "grad_norm": 0.022411495134838297,
      "learning_rate": 5.673419765534915e-06,
      "loss": 0.4071,
      "step": 125
    },
    {
      "epoch": 1.3695652173913042,
      "grad_norm": 0.01951721173355996,
      "learning_rate": 5.502558085159344e-06,
      "loss": 0.3481,
      "step": 126
    },
    {
      "epoch": 1.3804347826086958,
      "grad_norm": 0.024116070335566953,
      "learning_rate": 5.333326767743263e-06,
      "loss": 0.4188,
      "step": 127
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.026359215985631845,
      "learning_rate": 5.165787161154361e-06,
      "loss": 0.4169,
      "step": 128
    },
    {
      "epoch": 1.4021739130434783,
      "grad_norm": 0.022217706817923774,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.4236,
      "step": 129
    },
    {
      "epoch": 1.4130434782608696,
      "grad_norm": 0.021753073317964423,
      "learning_rate": 4.836025383610382e-06,
      "loss": 0.432,
      "step": 130
    },
    {
      "epoch": 1.4239130434782608,
      "grad_norm": 0.022436739303883135,
      "learning_rate": 4.673922754252001e-06,
      "loss": 0.4187,
      "step": 131
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 0.021898203612681105,
      "learning_rate": 4.513750875579303e-06,
      "loss": 0.4006,
      "step": 132
    },
    {
      "epoch": 1.4456521739130435,
      "grad_norm": 0.022105558271218153,
      "learning_rate": 4.355567811332311e-06,
      "loss": 0.428,
      "step": 133
    },
    {
      "epoch": 1.4565217391304348,
      "grad_norm": 0.02033202844138333,
      "learning_rate": 4.19943090428802e-06,
      "loss": 0.3973,
      "step": 134
    },
    {
      "epoch": 1.4673913043478262,
      "grad_norm": 0.01963872298504158,
      "learning_rate": 4.045396755473121e-06,
      "loss": 0.4008,
      "step": 135
    },
    {
      "epoch": 1.4782608695652173,
      "grad_norm": 0.020345281605454676,
      "learning_rate": 3.893521203645618e-06,
      "loss": 0.4147,
      "step": 136
    },
    {
      "epoch": 1.4891304347826086,
      "grad_norm": 0.021452868059861192,
      "learning_rate": 3.743859305052785e-06,
      "loss": 0.4149,
      "step": 137
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.020207806262184335,
      "learning_rate": 3.596465313472778e-06,
      "loss": 0.3836,
      "step": 138
    },
    {
      "epoch": 1.5108695652173914,
      "grad_norm": 0.02088539870362614,
      "learning_rate": 3.4513926605471504e-06,
      "loss": 0.4138,
      "step": 139
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.019077086049604102,
      "learning_rate": 3.308693936411421e-06,
      "loss": 0.3832,
      "step": 140
    },
    {
      "epoch": 1.5326086956521738,
      "grad_norm": 0.020912600263192083,
      "learning_rate": 3.1684208706306572e-06,
      "loss": 0.4136,
      "step": 141
    },
    {
      "epoch": 1.5434782608695652,
      "grad_norm": 0.02070907606152171,
      "learning_rate": 3.0306243134470668e-06,
      "loss": 0.4311,
      "step": 142
    },
    {
      "epoch": 1.5543478260869565,
      "grad_norm": 0.02054030797884719,
      "learning_rate": 2.8953542173463133e-06,
      "loss": 0.3938,
      "step": 143
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.022068383731631152,
      "learning_rate": 2.7626596189492983e-06,
      "loss": 0.3869,
      "step": 144
    },
    {
      "epoch": 1.5760869565217392,
      "grad_norm": 0.022095291706298183,
      "learning_rate": 2.6325886212359496e-06,
      "loss": 0.4151,
      "step": 145
    },
    {
      "epoch": 1.5869565217391304,
      "grad_norm": 0.021111713836599773,
      "learning_rate": 2.5051883761074613e-06,
      "loss": 0.4354,
      "step": 146
    },
    {
      "epoch": 1.5978260869565217,
      "grad_norm": 0.02237517232258718,
      "learning_rate": 2.380505067293293e-06,
      "loss": 0.4146,
      "step": 147
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 0.019623457979118124,
      "learning_rate": 2.2585838936091753e-06,
      "loss": 0.4119,
      "step": 148
    },
    {
      "epoch": 1.6195652173913042,
      "grad_norm": 0.021829275784838623,
      "learning_rate": 2.1394690525721275e-06,
      "loss": 0.4135,
      "step": 149
    },
    {
      "epoch": 1.6304347826086958,
      "grad_norm": 0.021180171763894674,
      "learning_rate": 2.0232037243784475e-06,
      "loss": 0.423,
      "step": 150
    },
    {
      "epoch": 1.641304347826087,
      "grad_norm": 0.02703521598184206,
      "learning_rate": 1.9098300562505266e-06,
      "loss": 0.4279,
      "step": 151
    },
    {
      "epoch": 1.6521739130434783,
      "grad_norm": 0.020030953141784397,
      "learning_rate": 1.7993891471580894e-06,
      "loss": 0.3998,
      "step": 152
    },
    {
      "epoch": 1.6630434782608696,
      "grad_norm": 0.02096005243951767,
      "learning_rate": 1.6919210329194535e-06,
      "loss": 0.4117,
      "step": 153
    },
    {
      "epoch": 1.6739130434782608,
      "grad_norm": 0.02114720153165263,
      "learning_rate": 1.587464671688187e-06,
      "loss": 0.4267,
      "step": 154
    },
    {
      "epoch": 1.6847826086956523,
      "grad_norm": 0.025390809807677033,
      "learning_rate": 1.4860579298304311e-06,
      "loss": 0.415,
      "step": 155
    },
    {
      "epoch": 1.6956521739130435,
      "grad_norm": 0.021410687428214302,
      "learning_rate": 1.3877375681979944e-06,
      "loss": 0.4043,
      "step": 156
    },
    {
      "epoch": 1.7065217391304348,
      "grad_norm": 0.023909950655856917,
      "learning_rate": 1.2925392288022299e-06,
      "loss": 0.4445,
      "step": 157
    },
    {
      "epoch": 1.7173913043478262,
      "grad_norm": 0.021428679509317893,
      "learning_rate": 1.2004974218934695e-06,
      "loss": 0.4238,
      "step": 158
    },
    {
      "epoch": 1.7282608695652173,
      "grad_norm": 0.02137946805669467,
      "learning_rate": 1.1116455134507665e-06,
      "loss": 0.3674,
      "step": 159
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.022243431881806403,
      "learning_rate": 1.0260157130864178e-06,
      "loss": 0.426,
      "step": 160
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.024681458739084422,
      "learning_rate": 9.436390623696911e-07,
      "loss": 0.4313,
      "step": 161
    },
    {
      "epoch": 1.7608695652173914,
      "grad_norm": 0.020315997518542663,
      "learning_rate": 8.645454235739903e-07,
      "loss": 0.3921,
      "step": 162
    },
    {
      "epoch": 1.7717391304347827,
      "grad_norm": 0.02332809992280282,
      "learning_rate": 7.887634688515e-07,
      "loss": 0.4273,
      "step": 163
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.020023620557189287,
      "learning_rate": 7.163206698392744e-07,
      "loss": 0.3738,
      "step": 164
    },
    {
      "epoch": 1.7934782608695652,
      "grad_norm": 0.022892114041331832,
      "learning_rate": 6.472432877005341e-07,
      "loss": 0.404,
      "step": 165
    },
    {
      "epoch": 1.8043478260869565,
      "grad_norm": 0.021905535119289433,
      "learning_rate": 5.815563636047539e-07,
      "loss": 0.4049,
      "step": 166
    },
    {
      "epoch": 1.8152173913043477,
      "grad_norm": 0.02074267534357053,
      "learning_rate": 5.192837096500058e-07,
      "loss": 0.4166,
      "step": 167
    },
    {
      "epoch": 1.8260869565217392,
      "grad_norm": 0.01843268176253824,
      "learning_rate": 4.6044790023087373e-07,
      "loss": 0.357,
      "step": 168
    },
    {
      "epoch": 1.8369565217391304,
      "grad_norm": 0.02079361540838812,
      "learning_rate": 4.0507026385502747e-07,
      "loss": 0.4344,
      "step": 169
    },
    {
      "epoch": 1.8478260869565217,
      "grad_norm": 0.021623517427470682,
      "learning_rate": 3.531708754114438e-07,
      "loss": 0.3878,
      "step": 170
    },
    {
      "epoch": 1.858695652173913,
      "grad_norm": 0.02038214952768136,
      "learning_rate": 3.0476854889308737e-07,
      "loss": 0.3856,
      "step": 171
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.023803627119720294,
      "learning_rate": 2.5988083057666534e-07,
      "loss": 0.416,
      "step": 172
    },
    {
      "epoch": 1.8804347826086958,
      "grad_norm": 0.02284511042725229,
      "learning_rate": 2.1852399266194312e-07,
      "loss": 0.4268,
      "step": 173
    },
    {
      "epoch": 1.891304347826087,
      "grad_norm": 0.022105485087235137,
      "learning_rate": 1.8071302737293294e-07,
      "loss": 0.3996,
      "step": 174
    },
    {
      "epoch": 1.9021739130434783,
      "grad_norm": 0.02196082349655336,
      "learning_rate": 1.464616415230702e-07,
      "loss": 0.3977,
      "step": 175
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.02582111983328924,
      "learning_rate": 1.1578225154637579e-07,
      "loss": 0.4167,
      "step": 176
    },
    {
      "epoch": 1.9239130434782608,
      "grad_norm": 0.020467066579464847,
      "learning_rate": 8.868597899638897e-08,
      "loss": 0.4022,
      "step": 177
    },
    {
      "epoch": 1.9347826086956523,
      "grad_norm": 0.018578643308574946,
      "learning_rate": 6.51826465144978e-08,
      "loss": 0.4305,
      "step": 178
    },
    {
      "epoch": 1.9456521739130435,
      "grad_norm": 0.020351166995274374,
      "learning_rate": 4.528077426915412e-08,
      "loss": 0.4323,
      "step": 179
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 0.01983648675971413,
      "learning_rate": 2.898757686722542e-08,
      "loss": 0.3953,
      "step": 180
    },
    {
      "epoch": 1.9673913043478262,
      "grad_norm": 0.01924389485648581,
      "learning_rate": 1.630896073864352e-08,
      "loss": 0.4024,
      "step": 181
    },
    {
      "epoch": 1.9782608695652173,
      "grad_norm": 0.021496764470333395,
      "learning_rate": 7.2495219952639636e-09,
      "loss": 0.4284,
      "step": 182
    },
    {
      "epoch": 1.9891304347826086,
      "grad_norm": 0.02172124469681476,
      "learning_rate": 1.8125447647421302e-09,
      "loss": 0.3954,
      "step": 183
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.021341261717375007,
      "learning_rate": 0.0,
      "loss": 0.3989,
      "step": 184
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.481020450592041,
      "eval_runtime": 2.8131,
      "eval_samples_per_second": 0.355,
      "eval_steps_per_second": 0.355,
      "step": 184
    },
    {
      "epoch": 2.0,
      "step": 184,
      "total_flos": 2780892130967552.0,
      "train_loss": 0.43346462998053303,
      "train_runtime": 8632.6044,
      "train_samples_per_second": 0.675,
      "train_steps_per_second": 0.021
    }
  ],
  "logging_steps": 1,
  "max_steps": 184,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2780892130967552.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}