{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3956043956043956,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.6567009687423706,
      "learning_rate": 0.0,
      "loss": 2.767,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.3838800191879272,
      "learning_rate": 4e-05,
      "loss": 2.2945,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.9234319925308228,
      "learning_rate": 8e-05,
      "loss": 2.9474,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.9659762382507324,
      "learning_rate": 0.00012,
      "loss": 2.9853,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.1689095497131348,
      "learning_rate": 0.00016,
      "loss": 2.7449,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.7526321411132812,
      "learning_rate": 0.0002,
      "loss": 2.4316,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.216229200363159,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.5923,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.076944589614868,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4113,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.8331300020217896,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.1678,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4564743041992188,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.4995,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.923876166343689,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2383,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8946003317832947,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.153,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5039580464363098,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1056,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5277471542358398,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0161,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4442140460014343,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9613,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.38263705372810364,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8934,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.42776256799697876,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0797,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.43527865409851074,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.8707,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.32646483182907104,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.0146,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.40627530217170715,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.9273,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.46039798855781555,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.8705,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.41969212889671326,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0961,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.4023812413215637,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1031,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3344135284423828,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8892,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3448273241519928,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8705,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.2724474370479584,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.8999,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.40961214900016785,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.2188,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3562145531177521,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9201,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3152042031288147,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.936,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.27859261631965637,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.8427,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.2839672565460205,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0559,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.2582114636898041,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9073,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.32668337225914,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9628,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.30008381605148315,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.1248,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3355301320552826,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9885,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.29906919598579407,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.8781,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.30698609352111816,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0222,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3538931906223297,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0791,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.37524330615997314,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.1857,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.2466009110212326,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.8989,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3097603917121887,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8067,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.33890318870544434,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.9267,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.2851554751396179,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.854,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3237600326538086,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8857,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.299290269613266,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8993,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2949437201023102,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.8557,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.2869762182235718,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.8459,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.28831377625465393,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.9929,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2845543324947357,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.0737,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.35254544019699097,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9845,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.27268919348716736,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.8531,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2979799807071686,
      "learning_rate": 0.00017960088691796008,
      "loss": 1.0148,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.28734323382377625,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.9678,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.32514873147010803,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9336,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3372485935688019,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0235,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.26649677753448486,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.1352,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.28168147802352905,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8594,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3652113974094391,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0333,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.28549066185951233,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.9242,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3495144546031952,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9354,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9892553876570112.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}