{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 69,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.043478260869565216,
      "grad_norm": 0.11003581272579467,
      "learning_rate": 0.0,
      "loss": 5.4659,
      "step": 1
    },
    {
      "epoch": 0.08695652173913043,
      "grad_norm": 0.14916557699467736,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 5.2137,
      "step": 2
    },
    {
      "epoch": 0.13043478260869565,
      "grad_norm": 0.0495245982251039,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 3.9417,
      "step": 3
    },
    {
      "epoch": 0.17391304347826086,
      "grad_norm": 0.0378571396686179,
      "learning_rate": 4.2857142857142855e-06,
      "loss": 3.4155,
      "step": 4
    },
    {
      "epoch": 0.21739130434782608,
      "grad_norm": 0.03738334247965367,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 3.2131,
      "step": 5
    },
    {
      "epoch": 0.2608695652173913,
      "grad_norm": 0.02853986163672258,
      "learning_rate": 7.1428571428571436e-06,
      "loss": 3.0253,
      "step": 6
    },
    {
      "epoch": 0.30434782608695654,
      "grad_norm": 0.05250470401391558,
      "learning_rate": 8.571428571428571e-06,
      "loss": 3.1584,
      "step": 7
    },
    {
      "epoch": 0.34782608695652173,
      "grad_norm": 0.03446246407651581,
      "learning_rate": 1e-05,
      "loss": 3.1989,
      "step": 8
    },
    {
      "epoch": 0.391304347826087,
      "grad_norm": 0.026758839795741698,
      "learning_rate": 9.993582535855265e-06,
      "loss": 3.3491,
      "step": 9
    },
    {
      "epoch": 0.43478260869565216,
      "grad_norm": 0.02112613138963606,
      "learning_rate": 9.974346616959476e-06,
      "loss": 3.0726,
      "step": 10
    },
    {
      "epoch": 0.4782608695652174,
      "grad_norm": 0.04293791715248718,
      "learning_rate": 9.942341621640558e-06,
      "loss": 2.916,
      "step": 11
    },
    {
      "epoch": 0.5217391304347826,
      "grad_norm": 0.018567661665039994,
      "learning_rate": 9.897649706262474e-06,
      "loss": 2.9468,
      "step": 12
    },
    {
      "epoch": 0.5652173913043478,
      "grad_norm": 0.07821394497332174,
      "learning_rate": 9.840385594331022e-06,
      "loss": 3.0014,
      "step": 13
    },
    {
      "epoch": 0.6086956521739131,
      "grad_norm": 0.02125098443020095,
      "learning_rate": 9.770696282000245e-06,
      "loss": 3.0129,
      "step": 14
    },
    {
      "epoch": 0.6521739130434783,
      "grad_norm": 0.011803126147495646,
      "learning_rate": 9.688760660735403e-06,
      "loss": 2.6871,
      "step": 15
    },
    {
      "epoch": 0.6956521739130435,
      "grad_norm": 0.05181349744100345,
      "learning_rate": 9.594789058101154e-06,
      "loss": 2.7554,
      "step": 16
    },
    {
      "epoch": 0.7391304347826086,
      "grad_norm": 0.016694370227069603,
      "learning_rate": 9.48902269785371e-06,
      "loss": 2.7162,
      "step": 17
    },
    {
      "epoch": 0.782608695652174,
      "grad_norm": 0.024737281327626783,
      "learning_rate": 9.371733080722911e-06,
      "loss": 2.7666,
      "step": 18
    },
    {
      "epoch": 0.8260869565217391,
      "grad_norm": 0.01605068021178836,
      "learning_rate": 9.243221287473755e-06,
      "loss": 2.6084,
      "step": 19
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.06631441107418981,
      "learning_rate": 9.103817206036383e-06,
      "loss": 2.786,
      "step": 20
    },
    {
      "epoch": 0.9130434782608695,
      "grad_norm": 0.6577184929863591,
      "learning_rate": 8.953878684688492e-06,
      "loss": 3.0823,
      "step": 21
    },
    {
      "epoch": 0.9565217391304348,
      "grad_norm": 0.0172058612247759,
      "learning_rate": 8.793790613463956e-06,
      "loss": 3.176,
      "step": 22
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.03433049524911961,
      "learning_rate": 8.6239639361456e-06,
      "loss": 2.9342,
      "step": 23
    },
    {
      "epoch": 1.0434782608695652,
      "grad_norm": 0.5479489712382244,
      "learning_rate": 8.444834595378434e-06,
      "loss": 2.2107,
      "step": 24
    },
    {
      "epoch": 1.0869565217391304,
      "grad_norm": 0.021127587716516117,
      "learning_rate": 8.256862413611113e-06,
      "loss": 2.986,
      "step": 25
    },
    {
      "epoch": 1.1304347826086956,
      "grad_norm": 0.048679406127313446,
      "learning_rate": 8.060529912738316e-06,
      "loss": 2.6089,
      "step": 26
    },
    {
      "epoch": 1.1739130434782608,
      "grad_norm": 0.014170939735623311,
      "learning_rate": 7.856341075473963e-06,
      "loss": 2.4115,
      "step": 27
    },
    {
      "epoch": 1.2173913043478262,
      "grad_norm": 0.0236962663475307,
      "learning_rate": 7.644820051634813e-06,
      "loss": 2.2743,
      "step": 28
    },
    {
      "epoch": 1.2608695652173914,
      "grad_norm": 0.012188959014980485,
      "learning_rate": 7.4265098126554065e-06,
      "loss": 2.3353,
      "step": 29
    },
    {
      "epoch": 1.3043478260869565,
      "grad_norm": 0.01399255197331707,
      "learning_rate": 7.201970757788172e-06,
      "loss": 2.2918,
      "step": 30
    },
    {
      "epoch": 1.3478260869565217,
      "grad_norm": 0.0231589220925467,
      "learning_rate": 6.971779275566593e-06,
      "loss": 2.3899,
      "step": 31
    },
    {
      "epoch": 1.391304347826087,
      "grad_norm": 0.016269583008799614,
      "learning_rate": 6.736526264224101e-06,
      "loss": 2.4792,
      "step": 32
    },
    {
      "epoch": 1.434782608695652,
      "grad_norm": 0.013459191741900951,
      "learning_rate": 6.496815614866792e-06,
      "loss": 2.2598,
      "step": 33
    },
    {
      "epoch": 1.4782608695652173,
      "grad_norm": 0.03347259873939099,
      "learning_rate": 6.2532626612936035e-06,
      "loss": 2.1974,
      "step": 34
    },
    {
      "epoch": 1.5217391304347827,
      "grad_norm": 0.013328407175997871,
      "learning_rate": 6.006492600443301e-06,
      "loss": 2.253,
      "step": 35
    },
    {
      "epoch": 1.5652173913043477,
      "grad_norm": 0.021432276910984253,
      "learning_rate": 5.757138887522884e-06,
      "loss": 2.212,
      "step": 36
    },
    {
      "epoch": 1.608695652173913,
      "grad_norm": 0.02571544622127433,
      "learning_rate": 5.505841609937162e-06,
      "loss": 2.1007,
      "step": 37
    },
    {
      "epoch": 1.6521739130434783,
      "grad_norm": 0.01632908919333525,
      "learning_rate": 5.253245844193564e-06,
      "loss": 2.2236,
      "step": 38
    },
    {
      "epoch": 1.6956521739130435,
      "grad_norm": 0.012718896692220047,
      "learning_rate": 5e-06,
      "loss": 2.057,
      "step": 39
    },
    {
      "epoch": 1.7391304347826086,
      "grad_norm": 0.07932852625331445,
      "learning_rate": 4.746754155806437e-06,
      "loss": 2.0451,
      "step": 40
    },
    {
      "epoch": 1.7826086956521738,
      "grad_norm": 0.018925267481795092,
      "learning_rate": 4.49415839006284e-06,
      "loss": 2.1936,
      "step": 41
    },
    {
      "epoch": 1.8260869565217392,
      "grad_norm": 0.01419421031205175,
      "learning_rate": 4.2428611124771184e-06,
      "loss": 2.3204,
      "step": 42
    },
    {
      "epoch": 1.8695652173913042,
      "grad_norm": 0.07687500330443668,
      "learning_rate": 3.993507399556699e-06,
      "loss": 2.0988,
      "step": 43
    },
    {
      "epoch": 1.9130434782608696,
      "grad_norm": 0.027662451933944943,
      "learning_rate": 3.7467373387063973e-06,
      "loss": 2.122,
      "step": 44
    },
    {
      "epoch": 1.9565217391304348,
      "grad_norm": 0.020533775534898973,
      "learning_rate": 3.5031843851332105e-06,
      "loss": 2.0874,
      "step": 45
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.029601791864931747,
      "learning_rate": 3.2634737357758994e-06,
      "loss": 2.2097,
      "step": 46
    },
    {
      "epoch": 2.0434782608695654,
      "grad_norm": 0.06134276711065825,
      "learning_rate": 3.0282207244334084e-06,
      "loss": 1.6145,
      "step": 47
    },
    {
      "epoch": 2.0869565217391304,
      "grad_norm": 0.0255180975130561,
      "learning_rate": 2.7980292422118282e-06,
      "loss": 1.8412,
      "step": 48
    },
    {
      "epoch": 2.130434782608696,
      "grad_norm": 0.018734948702092594,
      "learning_rate": 2.573490187344596e-06,
      "loss": 1.7516,
      "step": 49
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.016352413968137487,
      "learning_rate": 2.3551799483651894e-06,
      "loss": 1.5816,
      "step": 50
    },
    {
      "epoch": 2.217391304347826,
      "grad_norm": 0.014584726768063392,
      "learning_rate": 2.1436589245260375e-06,
      "loss": 1.9159,
      "step": 51
    },
    {
      "epoch": 2.260869565217391,
      "grad_norm": 0.009821021575318195,
      "learning_rate": 1.9394700872616856e-06,
      "loss": 1.8426,
      "step": 52
    },
    {
      "epoch": 2.3043478260869565,
      "grad_norm": 0.03493249780767714,
      "learning_rate": 1.74313758638889e-06,
      "loss": 1.6217,
      "step": 53
    },
    {
      "epoch": 2.3478260869565215,
      "grad_norm": 0.027101791964572713,
      "learning_rate": 1.555165404621567e-06,
      "loss": 1.6961,
      "step": 54
    },
    {
      "epoch": 2.391304347826087,
      "grad_norm": 0.022414124997451698,
      "learning_rate": 1.3760360638544012e-06,
      "loss": 1.8585,
      "step": 55
    },
    {
      "epoch": 2.4347826086956523,
      "grad_norm": 0.011003519635927975,
      "learning_rate": 1.2062093865360458e-06,
      "loss": 1.8188,
      "step": 56
    },
    {
      "epoch": 2.4782608695652173,
      "grad_norm": 0.020469182267391726,
      "learning_rate": 1.046121315311508e-06,
      "loss": 1.7176,
      "step": 57
    },
    {
      "epoch": 2.5217391304347827,
      "grad_norm": 0.033901095222778725,
      "learning_rate": 8.961827939636198e-07,
      "loss": 1.719,
      "step": 58
    },
    {
      "epoch": 2.5652173913043477,
      "grad_norm": 0.01569337668370056,
      "learning_rate": 7.567787125262449e-07,
      "loss": 1.7157,
      "step": 59
    },
    {
      "epoch": 2.608695652173913,
      "grad_norm": 0.07812483399559327,
      "learning_rate": 6.282669192770896e-07,
      "loss": 1.5018,
      "step": 60
    },
    {
      "epoch": 2.6521739130434785,
      "grad_norm": 0.026914865320544424,
      "learning_rate": 5.109773021462921e-07,
      "loss": 1.6208,
      "step": 61
    },
    {
      "epoch": 2.6956521739130435,
      "grad_norm": 0.06737271304790672,
      "learning_rate": 4.05210941898847e-07,
      "loss": 1.6434,
      "step": 62
    },
    {
      "epoch": 2.7391304347826084,
      "grad_norm": 0.02341844727481117,
      "learning_rate": 3.112393392645985e-07,
      "loss": 1.6943,
      "step": 63
    },
    {
      "epoch": 2.782608695652174,
      "grad_norm": 0.017062247890506126,
      "learning_rate": 2.2930371799975593e-07,
      "loss": 1.7067,
      "step": 64
    },
    {
      "epoch": 2.8260869565217392,
      "grad_norm": 0.017984179754937133,
      "learning_rate": 1.5961440566897913e-07,
      "loss": 1.8561,
      "step": 65
    },
    {
      "epoch": 2.869565217391304,
      "grad_norm": 0.016763171974884035,
      "learning_rate": 1.0235029373752758e-07,
      "loss": 1.7158,
      "step": 66
    },
    {
      "epoch": 2.9130434782608696,
      "grad_norm": 0.022258236138097437,
      "learning_rate": 5.7658378359443104e-08,
      "loss": 1.725,
      "step": 67
    },
    {
      "epoch": 2.9565217391304346,
      "grad_norm": 0.01996593890702,
      "learning_rate": 2.5653383040524228e-08,
      "loss": 1.7101,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.017015954271691305,
      "learning_rate": 6.417464144736208e-09,
      "loss": 1.5716,
      "step": 69
    }
  ],
  "logging_steps": 1,
  "max_steps": 69,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 496459436261376.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}