{
  "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": 6.851932525634766,
      "learning_rate": 1.25e-06,
      "loss": 1.2451,
      "step": 1
    },
    {
      "epoch": 0.07667731629392971,
      "grad_norm": 6.881481647491455,
      "learning_rate": 2.5e-06,
      "loss": 1.2562,
      "step": 2
    },
    {
      "epoch": 0.11501597444089456,
      "grad_norm": 6.416891574859619,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.2154,
      "step": 3
    },
    {
      "epoch": 0.15335463258785942,
      "grad_norm": 5.947795867919922,
      "learning_rate": 5e-06,
      "loss": 1.1468,
      "step": 4
    },
    {
      "epoch": 0.19169329073482427,
      "grad_norm": 4.5445637702941895,
      "learning_rate": 6.25e-06,
      "loss": 1.18,
      "step": 5
    },
    {
      "epoch": 0.23003194888178913,
      "grad_norm": 2.8148229122161865,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1071,
      "step": 6
    },
    {
      "epoch": 0.268370607028754,
      "grad_norm": 5.686256408691406,
      "learning_rate": 8.750000000000001e-06,
      "loss": 1.1148,
      "step": 7
    },
    {
      "epoch": 0.30670926517571884,
      "grad_norm": 5.797161102294922,
      "learning_rate": 1e-05,
      "loss": 1.1183,
      "step": 8
    },
    {
      "epoch": 0.3450479233226837,
      "grad_norm": 5.505243301391602,
      "learning_rate": 9.994965332706574e-06,
      "loss": 1.1136,
      "step": 9
    },
    {
      "epoch": 0.38338658146964855,
      "grad_norm": 5.709074974060059,
      "learning_rate": 9.979871469976197e-06,
      "loss": 1.1077,
      "step": 10
    },
    {
      "epoch": 0.4217252396166134,
      "grad_norm": 3.893484354019165,
      "learning_rate": 9.954748808839675e-06,
      "loss": 1.0919,
      "step": 11
    },
    {
      "epoch": 0.46006389776357826,
      "grad_norm": 2.2531075477600098,
      "learning_rate": 9.91964794299315e-06,
      "loss": 1.0399,
      "step": 12
    },
    {
      "epoch": 0.4984025559105431,
      "grad_norm": 2.4258840084075928,
      "learning_rate": 9.874639560909118e-06,
      "loss": 0.9963,
      "step": 13
    },
    {
      "epoch": 0.536741214057508,
      "grad_norm": 1.882415533065796,
      "learning_rate": 9.819814303479268e-06,
      "loss": 0.9848,
      "step": 14
    },
    {
      "epoch": 0.5750798722044729,
      "grad_norm": 1.6820740699768066,
      "learning_rate": 9.755282581475769e-06,
      "loss": 0.967,
      "step": 15
    },
    {
      "epoch": 0.6134185303514377,
      "grad_norm": 1.2889771461486816,
      "learning_rate": 9.681174353198687e-06,
      "loss": 0.9844,
      "step": 16
    },
    {
      "epoch": 0.6517571884984026,
      "grad_norm": 1.4085086584091187,
      "learning_rate": 9.597638862757255e-06,
      "loss": 0.975,
      "step": 17
    },
    {
      "epoch": 0.6900958466453674,
      "grad_norm": 1.2910341024398804,
      "learning_rate": 9.504844339512096e-06,
      "loss": 0.974,
      "step": 18
    },
    {
      "epoch": 0.7284345047923323,
      "grad_norm": 1.0245163440704346,
      "learning_rate": 9.40297765928369e-06,
      "loss": 0.9392,
      "step": 19
    },
    {
      "epoch": 0.7667731629392971,
      "grad_norm": 1.0739946365356445,
      "learning_rate": 9.292243968009332e-06,
      "loss": 0.9596,
      "step": 20
    },
    {
      "epoch": 0.805111821086262,
      "grad_norm": 1.1098713874816895,
      "learning_rate": 9.172866268606514e-06,
      "loss": 0.9502,
      "step": 21
    },
    {
      "epoch": 0.8434504792332268,
      "grad_norm": 0.9709510207176208,
      "learning_rate": 9.045084971874738e-06,
      "loss": 0.9642,
      "step": 22
    },
    {
      "epoch": 0.8817891373801917,
      "grad_norm": 0.9078324437141418,
      "learning_rate": 8.90915741234015e-06,
      "loss": 0.9736,
      "step": 23
    },
    {
      "epoch": 0.9201277955271565,
      "grad_norm": 0.917485773563385,
      "learning_rate": 8.765357330018056e-06,
      "loss": 0.9156,
      "step": 24
    },
    {
      "epoch": 0.9584664536741214,
      "grad_norm": 0.7244415879249573,
      "learning_rate": 8.613974319136959e-06,
      "loss": 0.9242,
      "step": 25
    },
    {
      "epoch": 0.9968051118210862,
      "grad_norm": 0.9716023802757263,
      "learning_rate": 8.455313244934324e-06,
      "loss": 0.9282,
      "step": 26
    },
    {
      "epoch": 1.035143769968051,
      "grad_norm": 2.170344591140747,
      "learning_rate": 8.289693629698564e-06,
      "loss": 1.5945,
      "step": 27
    },
    {
      "epoch": 1.073482428115016,
      "grad_norm": 1.0997891426086426,
      "learning_rate": 8.117449009293668e-06,
      "loss": 0.8625,
      "step": 28
    },
    {
      "epoch": 1.1118210862619808,
      "grad_norm": 0.8359212875366211,
      "learning_rate": 7.938926261462366e-06,
      "loss": 0.9256,
      "step": 29
    },
    {
      "epoch": 1.1501597444089458,
      "grad_norm": 0.9022307395935059,
      "learning_rate": 7.754484907260513e-06,
      "loss": 0.8793,
      "step": 30
    },
    {
      "epoch": 1.1884984025559104,
      "grad_norm": 1.0525832176208496,
      "learning_rate": 7.564496387029532e-06,
      "loss": 0.8727,
      "step": 31
    },
    {
      "epoch": 1.2268370607028753,
      "grad_norm": 0.7678513526916504,
      "learning_rate": 7.369343312364994e-06,
      "loss": 0.9104,
      "step": 32
    },
    {
      "epoch": 1.2651757188498403,
      "grad_norm": 0.753359317779541,
      "learning_rate": 7.169418695587791e-06,
      "loss": 0.8983,
      "step": 33
    },
    {
      "epoch": 1.3035143769968052,
      "grad_norm": 0.9841468334197998,
      "learning_rate": 6.965125158269619e-06,
      "loss": 0.8353,
      "step": 34
    },
    {
      "epoch": 1.34185303514377,
      "grad_norm": 0.7916426062583923,
      "learning_rate": 6.7568741204067145e-06,
      "loss": 0.9397,
      "step": 35
    },
    {
      "epoch": 1.3801916932907348,
      "grad_norm": 0.7216443419456482,
      "learning_rate": 6.545084971874738e-06,
      "loss": 0.868,
      "step": 36
    },
    {
      "epoch": 1.4185303514376997,
      "grad_norm": 0.7299794554710388,
      "learning_rate": 6.330184227833376e-06,
      "loss": 0.8584,
      "step": 37
    },
    {
      "epoch": 1.4568690095846646,
      "grad_norm": 0.7498561143875122,
      "learning_rate": 6.112604669781572e-06,
      "loss": 0.8576,
      "step": 38
    },
    {
      "epoch": 1.4952076677316293,
      "grad_norm": 0.5861709713935852,
      "learning_rate": 5.892784473993184e-06,
      "loss": 0.9014,
      "step": 39
    },
    {
      "epoch": 1.5335463258785942,
      "grad_norm": 0.5760552287101746,
      "learning_rate": 5.671166329088278e-06,
      "loss": 0.8704,
      "step": 40
    },
    {
      "epoch": 1.571884984025559,
      "grad_norm": 0.5792278051376343,
      "learning_rate": 5.448196544517168e-06,
      "loss": 0.8483,
      "step": 41
    },
    {
      "epoch": 1.610223642172524,
      "grad_norm": 0.6824653744697571,
      "learning_rate": 5.224324151752575e-06,
      "loss": 0.8579,
      "step": 42
    },
    {
      "epoch": 1.648562300319489,
      "grad_norm": 0.5566161870956421,
      "learning_rate": 5e-06,
      "loss": 0.8479,
      "step": 43
    },
    {
      "epoch": 1.6869009584664538,
      "grad_norm": 0.5421015620231628,
      "learning_rate": 4.775675848247427e-06,
      "loss": 0.8059,
      "step": 44
    },
    {
      "epoch": 1.7252396166134185,
      "grad_norm": 0.6022278666496277,
      "learning_rate": 4.551803455482833e-06,
      "loss": 0.9113,
      "step": 45
    },
    {
      "epoch": 1.7635782747603834,
      "grad_norm": 0.585304319858551,
      "learning_rate": 4.3288336709117246e-06,
      "loss": 0.8447,
      "step": 46
    },
    {
      "epoch": 1.8019169329073481,
      "grad_norm": 0.5503995418548584,
      "learning_rate": 4.107215526006818e-06,
      "loss": 0.8962,
      "step": 47
    },
    {
      "epoch": 1.840255591054313,
      "grad_norm": 0.5808898210525513,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.8754,
      "step": 48
    },
    {
      "epoch": 1.878594249201278,
      "grad_norm": 0.5363302826881409,
      "learning_rate": 3.669815772166625e-06,
      "loss": 0.8463,
      "step": 49
    },
    {
      "epoch": 1.9169329073482428,
      "grad_norm": 0.5210480093955994,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.7642,
      "step": 50
    },
    {
      "epoch": 1.9552715654952078,
      "grad_norm": 0.5406612157821655,
      "learning_rate": 3.2431258795932863e-06,
      "loss": 0.8819,
      "step": 51
    },
    {
      "epoch": 1.9936102236421727,
      "grad_norm": 0.5197424292564392,
      "learning_rate": 3.0348748417303826e-06,
      "loss": 0.85,
      "step": 52
    },
    {
      "epoch": 2.0319488817891376,
      "grad_norm": 1.7937531471252441,
      "learning_rate": 2.83058130441221e-06,
      "loss": 1.601,
      "step": 53
    },
    {
      "epoch": 2.070287539936102,
      "grad_norm": 0.5455480813980103,
      "learning_rate": 2.6306566876350072e-06,
      "loss": 0.8305,
      "step": 54
    },
    {
      "epoch": 2.108626198083067,
      "grad_norm": 0.5711581110954285,
      "learning_rate": 2.43550361297047e-06,
      "loss": 0.844,
      "step": 55
    },
    {
      "epoch": 2.146964856230032,
      "grad_norm": 0.5067282319068909,
      "learning_rate": 2.245515092739488e-06,
      "loss": 0.8332,
      "step": 56
    },
    {
      "epoch": 2.1853035143769968,
      "grad_norm": 0.4786854088306427,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.8052,
      "step": 57
    },
    {
      "epoch": 2.2236421725239617,
      "grad_norm": 0.5459759831428528,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.8728,
      "step": 58
    },
    {
      "epoch": 2.2619808306709266,
      "grad_norm": 0.43300294876098633,
      "learning_rate": 1.7103063703014372e-06,
      "loss": 0.7948,
      "step": 59
    },
    {
      "epoch": 2.3003194888178915,
      "grad_norm": 0.47953519225120544,
      "learning_rate": 1.544686755065677e-06,
      "loss": 0.848,
      "step": 60
    },
    {
      "epoch": 2.3386581469648564,
      "grad_norm": 0.47395646572113037,
      "learning_rate": 1.3860256808630429e-06,
      "loss": 0.7951,
      "step": 61
    },
    {
      "epoch": 2.376996805111821,
      "grad_norm": 0.48872408270835876,
      "learning_rate": 1.234642669981946e-06,
      "loss": 0.8461,
      "step": 62
    },
    {
      "epoch": 2.415335463258786,
      "grad_norm": 0.46870657801628113,
      "learning_rate": 1.0908425876598512e-06,
      "loss": 0.7849,
      "step": 63
    },
    {
      "epoch": 2.4536741214057507,
      "grad_norm": 0.45592182874679565,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.8575,
      "step": 64
    },
    {
      "epoch": 2.4920127795527156,
      "grad_norm": 0.4340704083442688,
      "learning_rate": 8.271337313934869e-07,
      "loss": 0.8107,
      "step": 65
    },
    {
      "epoch": 2.5303514376996805,
      "grad_norm": 0.43528518080711365,
      "learning_rate": 7.077560319906696e-07,
      "loss": 0.874,
      "step": 66
    },
    {
      "epoch": 2.5686900958466454,
      "grad_norm": 0.42759549617767334,
      "learning_rate": 5.9702234071631e-07,
      "loss": 0.7766,
      "step": 67
    },
    {
      "epoch": 2.6070287539936103,
      "grad_norm": 0.3982022702693939,
      "learning_rate": 4.951556604879049e-07,
      "loss": 0.7594,
      "step": 68
    },
    {
      "epoch": 2.6453674121405752,
      "grad_norm": 0.42235422134399414,
      "learning_rate": 4.0236113724274716e-07,
      "loss": 0.8796,
      "step": 69
    },
    {
      "epoch": 2.68370607028754,
      "grad_norm": 0.4170537292957306,
      "learning_rate": 3.18825646801314e-07,
      "loss": 0.8476,
      "step": 70
    },
    {
      "epoch": 2.722044728434505,
      "grad_norm": 0.42290008068084717,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.8594,
      "step": 71
    },
    {
      "epoch": 2.7603833865814695,
      "grad_norm": 0.4242245852947235,
      "learning_rate": 1.801856965207338e-07,
      "loss": 0.8086,
      "step": 72
    },
    {
      "epoch": 2.7987220447284344,
      "grad_norm": 0.4372583031654358,
      "learning_rate": 1.253604390908819e-07,
      "loss": 0.7548,
      "step": 73
    },
    {
      "epoch": 2.8370607028753994,
      "grad_norm": 0.4234861731529236,
      "learning_rate": 8.035205700685167e-08,
      "loss": 0.8781,
      "step": 74
    },
    {
      "epoch": 2.8753993610223643,
      "grad_norm": 0.41401535272598267,
      "learning_rate": 4.52511911603265e-08,
      "loss": 0.8319,
      "step": 75
    },
    {
      "epoch": 2.913738019169329,
      "grad_norm": 0.4394582211971283,
      "learning_rate": 2.012853002380466e-08,
      "loss": 0.8333,
      "step": 76
    },
    {
      "epoch": 2.952076677316294,
      "grad_norm": 0.4185008406639099,
      "learning_rate": 5.034667293427053e-09,
      "loss": 0.7689,
      "step": 77
    },
    {
      "epoch": 2.9904153354632586,
      "grad_norm": 0.42545270919799805,
      "learning_rate": 0.0,
      "loss": 0.8351,
      "step": 78
    },
    {
      "epoch": 2.9904153354632586,
      "step": 78,
      "total_flos": 82635974623232.0,
      "train_loss": 0.9321590577944731,
      "train_runtime": 7568.4855,
      "train_samples_per_second": 0.991,
      "train_steps_per_second": 0.01
    }
  ],
  "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": 82635974623232.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}