{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08437038599451592,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016874077198903185,
      "grad_norm": 65.32470703125,
      "learning_rate": 0.0001,
      "loss": 25.2321,
      "step": 1
    },
    {
      "epoch": 0.003374815439780637,
      "grad_norm": 70.6180419921875,
      "learning_rate": 0.0002,
      "loss": 25.3485,
      "step": 2
    },
    {
      "epoch": 0.0050622231596709555,
      "grad_norm": 51.371097564697266,
      "learning_rate": 0.00019978589232386035,
      "loss": 21.7018,
      "step": 3
    },
    {
      "epoch": 0.006749630879561274,
      "grad_norm": 590.1074829101562,
      "learning_rate": 0.00019914448613738106,
      "loss": 54.5225,
      "step": 4
    },
    {
      "epoch": 0.008437038599451592,
      "grad_norm": 209.5045623779297,
      "learning_rate": 0.00019807852804032305,
      "loss": 31.0961,
      "step": 5
    },
    {
      "epoch": 0.010124446319341911,
      "grad_norm": 58.842044830322266,
      "learning_rate": 0.00019659258262890683,
      "loss": 24.73,
      "step": 6
    },
    {
      "epoch": 0.011811854039232229,
      "grad_norm": 71.44770812988281,
      "learning_rate": 0.0001946930129495106,
      "loss": 23.8403,
      "step": 7
    },
    {
      "epoch": 0.013499261759122548,
      "grad_norm": 106.37022399902344,
      "learning_rate": 0.0001923879532511287,
      "loss": 27.1841,
      "step": 8
    },
    {
      "epoch": 0.015186669479012866,
      "grad_norm": 45.72689437866211,
      "learning_rate": 0.00018968727415326884,
      "loss": 19.8725,
      "step": 9
    },
    {
      "epoch": 0.016874077198903183,
      "grad_norm": 37.188865661621094,
      "learning_rate": 0.00018660254037844388,
      "loss": 21.7315,
      "step": 10
    },
    {
      "epoch": 0.018561484918793503,
      "grad_norm": 45.79566192626953,
      "learning_rate": 0.00018314696123025454,
      "loss": 22.6619,
      "step": 11
    },
    {
      "epoch": 0.020248892638683822,
      "grad_norm": 55.1727180480957,
      "learning_rate": 0.00017933533402912354,
      "loss": 21.1365,
      "step": 12
    },
    {
      "epoch": 0.02193630035857414,
      "grad_norm": 41.42280578613281,
      "learning_rate": 0.00017518398074789775,
      "loss": 22.4909,
      "step": 13
    },
    {
      "epoch": 0.023623708078464457,
      "grad_norm": 45.82218551635742,
      "learning_rate": 0.00017071067811865476,
      "loss": 18.2044,
      "step": 14
    },
    {
      "epoch": 0.025311115798354777,
      "grad_norm": 37.43087387084961,
      "learning_rate": 0.00016593458151000688,
      "loss": 20.438,
      "step": 15
    },
    {
      "epoch": 0.026998523518245096,
      "grad_norm": 114.20457458496094,
      "learning_rate": 0.00016087614290087208,
      "loss": 23.5819,
      "step": 16
    },
    {
      "epoch": 0.028685931238135415,
      "grad_norm": 67.7957992553711,
      "learning_rate": 0.00015555702330196023,
      "loss": 21.258,
      "step": 17
    },
    {
      "epoch": 0.03037333895802573,
      "grad_norm": 33.19402313232422,
      "learning_rate": 0.00015000000000000001,
      "loss": 20.2971,
      "step": 18
    },
    {
      "epoch": 0.03206074667791605,
      "grad_norm": 40.10993194580078,
      "learning_rate": 0.00014422886902190014,
      "loss": 19.7575,
      "step": 19
    },
    {
      "epoch": 0.03374815439780637,
      "grad_norm": 49.910343170166016,
      "learning_rate": 0.000138268343236509,
      "loss": 18.6194,
      "step": 20
    },
    {
      "epoch": 0.03543556211769669,
      "grad_norm": 38.23054504394531,
      "learning_rate": 0.00013214394653031616,
      "loss": 20.5953,
      "step": 21
    },
    {
      "epoch": 0.037122969837587005,
      "grad_norm": 56.188289642333984,
      "learning_rate": 0.00012588190451025207,
      "loss": 20.2318,
      "step": 22
    },
    {
      "epoch": 0.03881037755747733,
      "grad_norm": 44.83216857910156,
      "learning_rate": 0.00011950903220161285,
      "loss": 19.2367,
      "step": 23
    },
    {
      "epoch": 0.040497785277367644,
      "grad_norm": 48.0411262512207,
      "learning_rate": 0.00011305261922200519,
      "loss": 20.9958,
      "step": 24
    },
    {
      "epoch": 0.04218519299725796,
      "grad_norm": 52.180850982666016,
      "learning_rate": 0.00010654031292301432,
      "loss": 20.8292,
      "step": 25
    },
    {
      "epoch": 0.04387260071714828,
      "grad_norm": 46.67422103881836,
      "learning_rate": 0.0001,
      "loss": 23.289,
      "step": 26
    },
    {
      "epoch": 0.0455600084370386,
      "grad_norm": 38.597694396972656,
      "learning_rate": 9.345968707698569e-05,
      "loss": 19.8904,
      "step": 27
    },
    {
      "epoch": 0.047247416156928915,
      "grad_norm": 47.50412368774414,
      "learning_rate": 8.694738077799488e-05,
      "loss": 19.5885,
      "step": 28
    },
    {
      "epoch": 0.04893482387681924,
      "grad_norm": 37.85395431518555,
      "learning_rate": 8.049096779838719e-05,
      "loss": 21.6278,
      "step": 29
    },
    {
      "epoch": 0.050622231596709553,
      "grad_norm": 33.44654083251953,
      "learning_rate": 7.411809548974792e-05,
      "loss": 21.5126,
      "step": 30
    },
    {
      "epoch": 0.052309639316599876,
      "grad_norm": 37.50754165649414,
      "learning_rate": 6.785605346968386e-05,
      "loss": 20.6339,
      "step": 31
    },
    {
      "epoch": 0.05399704703649019,
      "grad_norm": 43.75811767578125,
      "learning_rate": 6.173165676349103e-05,
      "loss": 19.563,
      "step": 32
    },
    {
      "epoch": 0.05568445475638051,
      "grad_norm": 40.8135986328125,
      "learning_rate": 5.577113097809989e-05,
      "loss": 17.5488,
      "step": 33
    },
    {
      "epoch": 0.05737186247627083,
      "grad_norm": 31.21071434020996,
      "learning_rate": 5.000000000000002e-05,
      "loss": 17.7708,
      "step": 34
    },
    {
      "epoch": 0.05905927019616115,
      "grad_norm": 29.12379264831543,
      "learning_rate": 4.444297669803981e-05,
      "loss": 16.4581,
      "step": 35
    },
    {
      "epoch": 0.06074667791605146,
      "grad_norm": 44.50994873046875,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 17.5144,
      "step": 36
    },
    {
      "epoch": 0.062434085635941786,
      "grad_norm": 41.542293548583984,
      "learning_rate": 3.406541848999312e-05,
      "loss": 21.657,
      "step": 37
    },
    {
      "epoch": 0.0641214933558321,
      "grad_norm": 37.01569747924805,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 18.6949,
      "step": 38
    },
    {
      "epoch": 0.06580890107572242,
      "grad_norm": 31.14872932434082,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 17.1006,
      "step": 39
    },
    {
      "epoch": 0.06749630879561273,
      "grad_norm": 37.147621154785156,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 21.1422,
      "step": 40
    },
    {
      "epoch": 0.06918371651550306,
      "grad_norm": 38.87228775024414,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 20.6313,
      "step": 41
    },
    {
      "epoch": 0.07087112423539338,
      "grad_norm": 28.88852882385254,
      "learning_rate": 1.339745962155613e-05,
      "loss": 16.6456,
      "step": 42
    },
    {
      "epoch": 0.0725585319552837,
      "grad_norm": 31.49118995666504,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 20.5823,
      "step": 43
    },
    {
      "epoch": 0.07424593967517401,
      "grad_norm": 26.752351760864258,
      "learning_rate": 7.612046748871327e-06,
      "loss": 16.891,
      "step": 44
    },
    {
      "epoch": 0.07593334739506433,
      "grad_norm": 30.51628303527832,
      "learning_rate": 5.306987050489442e-06,
      "loss": 16.887,
      "step": 45
    },
    {
      "epoch": 0.07762075511495466,
      "grad_norm": 37.371604919433594,
      "learning_rate": 3.40741737109318e-06,
      "loss": 18.2874,
      "step": 46
    },
    {
      "epoch": 0.07930816283484497,
      "grad_norm": 32.94172286987305,
      "learning_rate": 1.921471959676957e-06,
      "loss": 20.0595,
      "step": 47
    },
    {
      "epoch": 0.08099557055473529,
      "grad_norm": 33.590179443359375,
      "learning_rate": 8.555138626189618e-07,
      "loss": 18.6175,
      "step": 48
    },
    {
      "epoch": 0.0826829782746256,
      "grad_norm": 34.63749694824219,
      "learning_rate": 2.141076761396521e-07,
      "loss": 18.973,
      "step": 49
    },
    {
      "epoch": 0.08437038599451592,
      "grad_norm": 32.18989944458008,
      "learning_rate": 0.0,
      "loss": 19.8617,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.03130303987712e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}