{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9904153354632586,
  "eval_steps": 500,
  "global_step": 78,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.038338658146964855,
      "grad_norm": 6.268963813781738,
      "learning_rate": 1.25e-06,
      "loss": 1.2115,
      "step": 1
    },
    {
      "epoch": 0.07667731629392971,
      "grad_norm": 6.341134548187256,
      "learning_rate": 2.5e-06,
      "loss": 1.2297,
      "step": 2
    },
    {
      "epoch": 0.11501597444089456,
      "grad_norm": 6.060571670532227,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.2244,
      "step": 3
    },
    {
      "epoch": 0.15335463258785942,
      "grad_norm": 5.834828853607178,
      "learning_rate": 5e-06,
      "loss": 1.2321,
      "step": 4
    },
    {
      "epoch": 0.19169329073482427,
      "grad_norm": 4.031907081604004,
      "learning_rate": 6.25e-06,
      "loss": 1.1354,
      "step": 5
    },
    {
      "epoch": 0.23003194888178913,
      "grad_norm": 2.566441535949707,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1373,
      "step": 6
    },
    {
      "epoch": 0.268370607028754,
      "grad_norm": 4.936546802520752,
      "learning_rate": 8.750000000000001e-06,
      "loss": 1.1164,
      "step": 7
    },
    {
      "epoch": 0.30670926517571884,
      "grad_norm": 5.281982421875,
      "learning_rate": 1e-05,
      "loss": 1.1487,
      "step": 8
    },
    {
      "epoch": 0.3450479233226837,
      "grad_norm": 4.784050464630127,
      "learning_rate": 9.994965332706574e-06,
      "loss": 1.1092,
      "step": 9
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 4.35185432434082,
      "learning_rate": 9.979871469976197e-06,
      "loss": 1.0593,
      "step": 10
    },
    {
      "epoch": 0.4217252396166134,
      "grad_norm": 3.066632032394409,
      "learning_rate": 9.954748808839675e-06,
      "loss": 1.0775,
      "step": 11
    },
    {
      "epoch": 0.46006389776357826,
      "grad_norm": 2.1742818355560303,
      "learning_rate": 9.91964794299315e-06,
      "loss": 1.0507,
      "step": 12
    },
    {
      "epoch": 0.4984025559105431,
      "grad_norm": 2.0748846530914307,
      "learning_rate": 9.874639560909118e-06,
      "loss": 1.0538,
      "step": 13
    },
    {
      "epoch": 0.536741214057508,
      "grad_norm": 1.7165900468826294,
      "learning_rate": 9.819814303479268e-06,
      "loss": 1.0135,
      "step": 14
    },
    {
      "epoch": 0.5750798722044729,
      "grad_norm": 1.1524348258972168,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.9451,
      "step": 15
    },
    {
      "epoch": 0.6134185303514377,
      "grad_norm": 1.1045109033584595,
      "learning_rate": 9.681174353198687e-06,
      "loss": 0.9612,
      "step": 16
    },
    {
      "epoch": 0.6517571884984026,
      "grad_norm": 1.0113556385040283,
      "learning_rate": 9.597638862757255e-06,
      "loss": 0.933,
      "step": 17
    },
    {
      "epoch": 0.6900958466453674,
      "grad_norm": 1.0217912197113037,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.952,
      "step": 18
    },
    {
      "epoch": 0.7284345047923323,
      "grad_norm": 0.9327982068061829,
      "learning_rate": 9.40297765928369e-06,
      "loss": 0.9445,
      "step": 19
    },
    {
      "epoch": 0.7667731629392971,
      "grad_norm": 1.1761642694473267,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.9118,
      "step": 20
    },
    {
      "epoch": 0.805111821086262,
      "grad_norm": 1.0297203063964844,
      "learning_rate": 9.172866268606514e-06,
      "loss": 0.9449,
      "step": 21
    },
    {
      "epoch": 0.8434504792332268,
      "grad_norm": 0.89028000831604,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.9324,
      "step": 22
    },
    {
      "epoch": 0.8817891373801917,
      "grad_norm": 0.9008014798164368,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.9171,
      "step": 23
    },
    {
      "epoch": 0.9201277955271565,
      "grad_norm": 0.811389684677124,
      "learning_rate": 8.765357330018056e-06,
      "loss": 0.8944,
      "step": 24
    },
    {
      "epoch": 0.9584664536741214,
      "grad_norm": 0.7690094113349915,
      "learning_rate": 8.613974319136959e-06,
      "loss": 0.9277,
      "step": 25
    },
    {
      "epoch": 0.9968051118210862,
      "grad_norm": 0.797437310218811,
      "learning_rate": 8.455313244934324e-06,
      "loss": 0.8892,
      "step": 26
    },
    {
      "epoch": 1.035143769968051,
      "grad_norm": 2.0572807788848877,
      "learning_rate": 8.289693629698564e-06,
      "loss": 1.6425,
      "step": 27
    },
    {
      "epoch": 1.073482428115016,
      "grad_norm": 0.8024719953536987,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.8882,
      "step": 28
    },
    {
      "epoch": 1.1118210862619808,
      "grad_norm": 0.732552170753479,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.8174,
      "step": 29
    },
    {
      "epoch": 1.1501597444089458,
      "grad_norm": 0.7644696831703186,
      "learning_rate": 7.754484907260513e-06,
      "loss": 0.8943,
      "step": 30
    },
    {
      "epoch": 1.1884984025559104,
      "grad_norm": 0.8279052972793579,
      "learning_rate": 7.564496387029532e-06,
      "loss": 0.9146,
      "step": 31
    },
    {
      "epoch": 1.2268370607028753,
      "grad_norm": 0.6625746488571167,
      "learning_rate": 7.369343312364994e-06,
      "loss": 0.8061,
      "step": 32
    },
    {
      "epoch": 1.2651757188498403,
      "grad_norm": 0.8740842342376709,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.9283,
      "step": 33
    },
    {
      "epoch": 1.3035143769968052,
      "grad_norm": 1.0007681846618652,
      "learning_rate": 6.965125158269619e-06,
      "loss": 0.8699,
      "step": 34
    },
    {
      "epoch": 1.34185303514377,
      "grad_norm": 0.7899899482727051,
      "learning_rate": 6.7568741204067145e-06,
      "loss": 0.8696,
      "step": 35
    },
    {
      "epoch": 1.3801916932907348,
      "grad_norm": 0.8275483846664429,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.883,
      "step": 36
    },
    {
      "epoch": 1.4185303514376997,
      "grad_norm": 0.6930125951766968,
      "learning_rate": 6.330184227833376e-06,
      "loss": 0.844,
      "step": 37
    },
    {
      "epoch": 1.4568690095846646,
      "grad_norm": 0.9502591490745544,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.9176,
      "step": 38
    },
    {
      "epoch": 1.4952076677316293,
      "grad_norm": 0.7643057703971863,
      "learning_rate": 5.892784473993184e-06,
      "loss": 0.8606,
      "step": 39
    },
    {
      "epoch": 1.5335463258785942,
      "grad_norm": 0.6755321025848389,
      "learning_rate": 5.671166329088278e-06,
      "loss": 0.8542,
      "step": 40
    },
    {
      "epoch": 1.571884984025559,
      "grad_norm": 0.6078510880470276,
      "learning_rate": 5.448196544517168e-06,
      "loss": 0.8272,
      "step": 41
    },
    {
      "epoch": 1.610223642172524,
      "grad_norm": 0.6227731704711914,
      "learning_rate": 5.224324151752575e-06,
      "loss": 0.8341,
      "step": 42
    },
    {
      "epoch": 1.648562300319489,
      "grad_norm": 0.6520214676856995,
      "learning_rate": 5e-06,
      "loss": 0.8258,
      "step": 43
    },
    {
      "epoch": 1.6869009584664538,
      "grad_norm": 0.5231408476829529,
      "learning_rate": 4.775675848247427e-06,
      "loss": 0.8092,
      "step": 44
    },
    {
      "epoch": 1.7252396166134185,
      "grad_norm": 0.5697768926620483,
      "learning_rate": 4.551803455482833e-06,
      "loss": 0.8257,
      "step": 45
    },
    {
      "epoch": 1.7635782747603834,
      "grad_norm": 0.600039005279541,
      "learning_rate": 4.3288336709117246e-06,
      "loss": 0.9231,
      "step": 46
    },
    {
      "epoch": 1.8019169329073481,
      "grad_norm": 0.552922248840332,
      "learning_rate": 4.107215526006818e-06,
      "loss": 0.8637,
      "step": 47
    },
    {
      "epoch": 1.840255591054313,
      "grad_norm": 0.5337823629379272,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.8697,
      "step": 48
    },
    {
      "epoch": 1.878594249201278,
      "grad_norm": 0.543074369430542,
      "learning_rate": 3.669815772166625e-06,
      "loss": 0.8528,
      "step": 49
    },
    {
      "epoch": 1.9169329073482428,
      "grad_norm": 0.49268418550491333,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.8719,
      "step": 50
    },
    {
      "epoch": 1.9552715654952078,
      "grad_norm": 0.5731656551361084,
      "learning_rate": 3.2431258795932863e-06,
      "loss": 0.8398,
      "step": 51
    },
    {
      "epoch": 1.9936102236421727,
      "grad_norm": 0.5479597449302673,
      "learning_rate": 3.0348748417303826e-06,
      "loss": 0.8779,
      "step": 52
    },
    {
      "epoch": 2.0319488817891376,
      "grad_norm": 1.617209792137146,
      "learning_rate": 2.83058130441221e-06,
      "loss": 1.4471,
      "step": 53
    },
    {
      "epoch": 2.070287539936102,
      "grad_norm": 0.4556597173213959,
      "learning_rate": 2.6306566876350072e-06,
      "loss": 0.8478,
      "step": 54
    },
    {
      "epoch": 2.108626198083067,
      "grad_norm": 0.47189801931381226,
      "learning_rate": 2.43550361297047e-06,
      "loss": 0.6975,
      "step": 55
    },
    {
      "epoch": 2.146964856230032,
      "grad_norm": 0.530375063419342,
      "learning_rate": 2.245515092739488e-06,
      "loss": 0.8813,
      "step": 56
    },
    {
      "epoch": 2.1853035143769968,
      "grad_norm": 0.4751721918582916,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.7837,
      "step": 57
    },
    {
      "epoch": 2.2236421725239617,
      "grad_norm": 0.4963734745979309,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.813,
      "step": 58
    },
    {
      "epoch": 2.2619808306709266,
      "grad_norm": 0.4415941536426544,
      "learning_rate": 1.7103063703014372e-06,
      "loss": 0.8443,
      "step": 59
    },
    {
      "epoch": 2.3003194888178915,
      "grad_norm": 0.46203547716140747,
      "learning_rate": 1.544686755065677e-06,
      "loss": 0.8034,
      "step": 60
    },
    {
      "epoch": 2.3386581469648564,
      "grad_norm": 0.46348705887794495,
      "learning_rate": 1.3860256808630429e-06,
      "loss": 0.8218,
      "step": 61
    },
    {
      "epoch": 2.376996805111821,
      "grad_norm": 0.5105081796646118,
      "learning_rate": 1.234642669981946e-06,
      "loss": 0.8328,
      "step": 62
    },
    {
      "epoch": 2.415335463258786,
      "grad_norm": 0.4578910171985626,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.8163,
      "step": 63
    },
    {
      "epoch": 2.4536741214057507,
      "grad_norm": 0.43735674023628235,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.8503,
      "step": 64
    },
    {
      "epoch": 2.4920127795527156,
      "grad_norm": 0.4174916744232178,
      "learning_rate": 8.271337313934869e-07,
      "loss": 0.8144,
      "step": 65
    },
    {
      "epoch": 2.5303514376996805,
      "grad_norm": 0.4164718985557556,
      "learning_rate": 7.077560319906696e-07,
      "loss": 0.8012,
      "step": 66
    },
    {
      "epoch": 2.5686900958466454,
      "grad_norm": 0.4239489734172821,
      "learning_rate": 5.9702234071631e-07,
      "loss": 0.8369,
      "step": 67
    },
    {
      "epoch": 2.6070287539936103,
      "grad_norm": 0.4047086834907532,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.8044,
      "step": 68
    },
    {
      "epoch": 2.6453674121405752,
      "grad_norm": 0.46145617961883545,
      "learning_rate": 4.0236113724274716e-07,
      "loss": 0.8484,
      "step": 69
    },
    {
      "epoch": 2.68370607028754,
      "grad_norm": 0.40475496649742126,
      "learning_rate": 3.18825646801314e-07,
      "loss": 0.8267,
      "step": 70
    },
    {
      "epoch": 2.722044728434505,
      "grad_norm": 0.40019193291664124,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.7495,
      "step": 71
    },
    {
      "epoch": 2.7603833865814695,
      "grad_norm": 0.5259660482406616,
      "learning_rate": 1.801856965207338e-07,
      "loss": 0.8841,
      "step": 72
    },
    {
      "epoch": 2.7987220447284344,
      "grad_norm": 0.40922901034355164,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.7166,
      "step": 73
    },
    {
      "epoch": 2.8370607028753994,
      "grad_norm": 0.4288291335105896,
      "learning_rate": 8.035205700685167e-08,
      "loss": 0.8212,
      "step": 74
    },
    {
      "epoch": 2.8753993610223643,
      "grad_norm": 0.48746126890182495,
      "learning_rate": 4.52511911603265e-08,
      "loss": 0.8516,
      "step": 75
    },
    {
      "epoch": 2.913738019169329,
      "grad_norm": 0.41395363211631775,
      "learning_rate": 2.012853002380466e-08,
      "loss": 0.7457,
      "step": 76
    },
    {
      "epoch": 2.952076677316294,
      "grad_norm": 0.46223482489585876,
      "learning_rate": 5.034667293427053e-09,
      "loss": 0.8133,
      "step": 77
    },
    {
      "epoch": 2.9904153354632586,
      "grad_norm": 0.3912806212902069,
      "learning_rate": 0.0,
      "loss": 0.7707,
      "step": 78
    },
    {
      "epoch": 2.9904153354632586,
      "step": 78,
      "total_flos": 74381350977536.0,
      "train_loss": 0.9216354114887042,
      "train_runtime": 4315.2973,
      "train_samples_per_second": 1.738,
      "train_steps_per_second": 0.018
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 78,
  "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": 74381350977536.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}