{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04241331778178348,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008482663556356696,
      "grad_norm": 14.401731491088867,
      "learning_rate": 0.0001,
      "loss": 6.023,
      "step": 1
    },
    {
      "epoch": 0.0016965327112713393,
      "grad_norm": 12.187810897827148,
      "learning_rate": 0.0002,
      "loss": 5.9775,
      "step": 2
    },
    {
      "epoch": 0.002544799066907009,
      "grad_norm": 12.369268417358398,
      "learning_rate": 0.00019978589232386035,
      "loss": 5.4492,
      "step": 3
    },
    {
      "epoch": 0.0033930654225426786,
      "grad_norm": 11.223816871643066,
      "learning_rate": 0.00019914448613738106,
      "loss": 3.9348,
      "step": 4
    },
    {
      "epoch": 0.004241331778178348,
      "grad_norm": 9.1347074508667,
      "learning_rate": 0.00019807852804032305,
      "loss": 2.3093,
      "step": 5
    },
    {
      "epoch": 0.005089598133814018,
      "grad_norm": 6.055950164794922,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.3156,
      "step": 6
    },
    {
      "epoch": 0.0059378644894496875,
      "grad_norm": 3.676882743835449,
      "learning_rate": 0.0001946930129495106,
      "loss": 1.0411,
      "step": 7
    },
    {
      "epoch": 0.006786130845085357,
      "grad_norm": 4.150704383850098,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.8048,
      "step": 8
    },
    {
      "epoch": 0.007634397200721026,
      "grad_norm": 3.6138298511505127,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.7477,
      "step": 9
    },
    {
      "epoch": 0.008482663556356696,
      "grad_norm": 2.753798484802246,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.542,
      "step": 10
    },
    {
      "epoch": 0.009330929911992365,
      "grad_norm": 4.54025411605835,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.496,
      "step": 11
    },
    {
      "epoch": 0.010179196267628036,
      "grad_norm": 13.51045036315918,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.9441,
      "step": 12
    },
    {
      "epoch": 0.011027462623263705,
      "grad_norm": 14.223007202148438,
      "learning_rate": 0.00017518398074789775,
      "loss": 1.0033,
      "step": 13
    },
    {
      "epoch": 0.011875728978899375,
      "grad_norm": 2.892982006072998,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.5323,
      "step": 14
    },
    {
      "epoch": 0.012723995334535044,
      "grad_norm": 4.61104154586792,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.4663,
      "step": 15
    },
    {
      "epoch": 0.013572261690170714,
      "grad_norm": 2.2477262020111084,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.4505,
      "step": 16
    },
    {
      "epoch": 0.014420528045806383,
      "grad_norm": 4.4651899337768555,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.6104,
      "step": 17
    },
    {
      "epoch": 0.015268794401442052,
      "grad_norm": 2.236485004425049,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.4329,
      "step": 18
    },
    {
      "epoch": 0.016117060757077722,
      "grad_norm": 3.9798102378845215,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.5202,
      "step": 19
    },
    {
      "epoch": 0.016965327112713393,
      "grad_norm": 1.3175522089004517,
      "learning_rate": 0.000138268343236509,
      "loss": 0.4673,
      "step": 20
    },
    {
      "epoch": 0.01781359346834906,
      "grad_norm": 1.3106902837753296,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.4498,
      "step": 21
    },
    {
      "epoch": 0.01866185982398473,
      "grad_norm": 1.7499768733978271,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.4964,
      "step": 22
    },
    {
      "epoch": 0.0195101261796204,
      "grad_norm": 2.9013662338256836,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.5628,
      "step": 23
    },
    {
      "epoch": 0.02035839253525607,
      "grad_norm": 0.665701687335968,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.4783,
      "step": 24
    },
    {
      "epoch": 0.02120665889089174,
      "grad_norm": 0.7912172675132751,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.4836,
      "step": 25
    },
    {
      "epoch": 0.02205492524652741,
      "grad_norm": 0.6106640100479126,
      "learning_rate": 0.0001,
      "loss": 0.4531,
      "step": 26
    },
    {
      "epoch": 0.02290319160216308,
      "grad_norm": 1.1405478715896606,
      "learning_rate": 9.345968707698569e-05,
      "loss": 0.4376,
      "step": 27
    },
    {
      "epoch": 0.02375145795779875,
      "grad_norm": 0.7410005331039429,
      "learning_rate": 8.694738077799488e-05,
      "loss": 0.4823,
      "step": 28
    },
    {
      "epoch": 0.024599724313434417,
      "grad_norm": 1.1606342792510986,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.4912,
      "step": 29
    },
    {
      "epoch": 0.025447990669070088,
      "grad_norm": 1.0744168758392334,
      "learning_rate": 7.411809548974792e-05,
      "loss": 0.5038,
      "step": 30
    },
    {
      "epoch": 0.026296257024705758,
      "grad_norm": 1.7132534980773926,
      "learning_rate": 6.785605346968386e-05,
      "loss": 0.5004,
      "step": 31
    },
    {
      "epoch": 0.02714452338034143,
      "grad_norm": 1.147415280342102,
      "learning_rate": 6.173165676349103e-05,
      "loss": 0.466,
      "step": 32
    },
    {
      "epoch": 0.027992789735977096,
      "grad_norm": 0.8624941110610962,
      "learning_rate": 5.577113097809989e-05,
      "loss": 0.4736,
      "step": 33
    },
    {
      "epoch": 0.028841056091612766,
      "grad_norm": 0.4240086078643799,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.4587,
      "step": 34
    },
    {
      "epoch": 0.029689322447248437,
      "grad_norm": 0.32580769062042236,
      "learning_rate": 4.444297669803981e-05,
      "loss": 0.4665,
      "step": 35
    },
    {
      "epoch": 0.030537588802884104,
      "grad_norm": 7.6701531410217285,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 0.5514,
      "step": 36
    },
    {
      "epoch": 0.03138585515851978,
      "grad_norm": 0.9737427234649658,
      "learning_rate": 3.406541848999312e-05,
      "loss": 0.4935,
      "step": 37
    },
    {
      "epoch": 0.032234121514155445,
      "grad_norm": 0.7094717025756836,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.4657,
      "step": 38
    },
    {
      "epoch": 0.03308238786979111,
      "grad_norm": 0.39363011717796326,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 0.4559,
      "step": 39
    },
    {
      "epoch": 0.033930654225426786,
      "grad_norm": 0.3725380599498749,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 0.4558,
      "step": 40
    },
    {
      "epoch": 0.03477892058106245,
      "grad_norm": 1.143078088760376,
      "learning_rate": 1.6853038769745467e-05,
      "loss": 0.4563,
      "step": 41
    },
    {
      "epoch": 0.03562718693669812,
      "grad_norm": 0.5376627445220947,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.4571,
      "step": 42
    },
    {
      "epoch": 0.036475453292333794,
      "grad_norm": 0.742919385433197,
      "learning_rate": 1.0312725846731175e-05,
      "loss": 0.4705,
      "step": 43
    },
    {
      "epoch": 0.03732371964796946,
      "grad_norm": 0.7047212719917297,
      "learning_rate": 7.612046748871327e-06,
      "loss": 0.4764,
      "step": 44
    },
    {
      "epoch": 0.038171986003605135,
      "grad_norm": 1.3539237976074219,
      "learning_rate": 5.306987050489442e-06,
      "loss": 0.4871,
      "step": 45
    },
    {
      "epoch": 0.0390202523592408,
      "grad_norm": 2.224294424057007,
      "learning_rate": 3.40741737109318e-06,
      "loss": 0.5089,
      "step": 46
    },
    {
      "epoch": 0.03986851871487647,
      "grad_norm": 1.2979936599731445,
      "learning_rate": 1.921471959676957e-06,
      "loss": 0.4834,
      "step": 47
    },
    {
      "epoch": 0.04071678507051214,
      "grad_norm": 0.9504252672195435,
      "learning_rate": 8.555138626189618e-07,
      "loss": 0.4433,
      "step": 48
    },
    {
      "epoch": 0.04156505142614781,
      "grad_norm": 0.7085014581680298,
      "learning_rate": 2.141076761396521e-07,
      "loss": 0.4401,
      "step": 49
    },
    {
      "epoch": 0.04241331778178348,
      "grad_norm": 1.5509270429611206,
      "learning_rate": 0.0,
      "loss": 0.4014,
      "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": 1.02936877203456e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}