{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 204,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07428040854224698,
      "grad_norm": 0.0166015625,
      "learning_rate": 4.970588235294118e-05,
      "loss": 0.6377665996551514,
      "step": 5
    },
    {
      "epoch": 0.14856081708449395,
      "grad_norm": 0.0146484375,
      "learning_rate": 4.933823529411765e-05,
      "loss": 0.6021791934967041,
      "step": 10
    },
    {
      "epoch": 0.22284122562674094,
      "grad_norm": 0.01373291015625,
      "learning_rate": 4.897058823529412e-05,
      "loss": 0.6274982929229737,
      "step": 15
    },
    {
      "epoch": 0.2971216341689879,
      "grad_norm": 0.0135498046875,
      "learning_rate": 4.860294117647059e-05,
      "loss": 0.599825382232666,
      "step": 20
    },
    {
      "epoch": 0.3714020427112349,
      "grad_norm": 0.0159912109375,
      "learning_rate": 4.823529411764706e-05,
      "loss": 0.6859479427337647,
      "step": 25
    },
    {
      "epoch": 0.4456824512534819,
      "grad_norm": 0.01422119140625,
      "learning_rate": 4.7867647058823535e-05,
      "loss": 0.636006212234497,
      "step": 30
    },
    {
      "epoch": 0.5199628597957289,
      "grad_norm": 0.01116943359375,
      "learning_rate": 4.75e-05,
      "loss": 0.6127719879150391,
      "step": 35
    },
    {
      "epoch": 0.5942432683379758,
      "grad_norm": 0.01531982421875,
      "learning_rate": 4.713235294117647e-05,
      "loss": 0.5927554130554199,
      "step": 40
    },
    {
      "epoch": 0.6685236768802229,
      "grad_norm": 0.011474609375,
      "learning_rate": 4.6764705882352944e-05,
      "loss": 0.6282303333282471,
      "step": 45
    },
    {
      "epoch": 0.7428040854224698,
      "grad_norm": 0.015869140625,
      "learning_rate": 4.639705882352942e-05,
      "loss": 0.5779662609100342,
      "step": 50
    },
    {
      "epoch": 0.8170844939647168,
      "grad_norm": 0.01318359375,
      "learning_rate": 4.6029411764705885e-05,
      "loss": 0.617146348953247,
      "step": 55
    },
    {
      "epoch": 0.8913649025069638,
      "grad_norm": 0.0130615234375,
      "learning_rate": 4.566176470588235e-05,
      "loss": 0.5746903896331788,
      "step": 60
    },
    {
      "epoch": 0.9656453110492108,
      "grad_norm": 0.0108642578125,
      "learning_rate": 4.5294117647058826e-05,
      "loss": 0.5909358024597168,
      "step": 65
    },
    {
      "epoch": 1.0297121634168989,
      "grad_norm": 0.00994873046875,
      "learning_rate": 4.49264705882353e-05,
      "loss": 0.5567221164703369,
      "step": 70
    },
    {
      "epoch": 1.1039925719591457,
      "grad_norm": 0.01031494140625,
      "learning_rate": 4.455882352941177e-05,
      "loss": 0.5583184242248536,
      "step": 75
    },
    {
      "epoch": 1.1782729805013927,
      "grad_norm": 0.01214599609375,
      "learning_rate": 4.4191176470588235e-05,
      "loss": 0.5047792911529541,
      "step": 80
    },
    {
      "epoch": 1.2525533890436398,
      "grad_norm": 0.014892578125,
      "learning_rate": 4.382352941176471e-05,
      "loss": 0.509721040725708,
      "step": 85
    },
    {
      "epoch": 1.3268337975858868,
      "grad_norm": 0.0162353515625,
      "learning_rate": 4.345588235294118e-05,
      "loss": 0.522771167755127,
      "step": 90
    },
    {
      "epoch": 1.4011142061281336,
      "grad_norm": 0.01263427734375,
      "learning_rate": 4.308823529411765e-05,
      "loss": 0.48066258430480957,
      "step": 95
    },
    {
      "epoch": 1.4753946146703807,
      "grad_norm": 0.02294921875,
      "learning_rate": 4.272058823529412e-05,
      "loss": 0.5085556030273437,
      "step": 100
    },
    {
      "epoch": 1.5496750232126275,
      "grad_norm": 0.01287841796875,
      "learning_rate": 4.235294117647059e-05,
      "loss": 0.4806520462036133,
      "step": 105
    },
    {
      "epoch": 1.6239554317548746,
      "grad_norm": 0.0107421875,
      "learning_rate": 4.198529411764706e-05,
      "loss": 0.48960013389587403,
      "step": 110
    },
    {
      "epoch": 1.6982358402971216,
      "grad_norm": 0.0120849609375,
      "learning_rate": 4.161764705882353e-05,
      "loss": 0.47647743225097655,
      "step": 115
    },
    {
      "epoch": 1.7725162488393686,
      "grad_norm": 0.0230712890625,
      "learning_rate": 4.125e-05,
      "loss": 0.5240037918090821,
      "step": 120
    },
    {
      "epoch": 1.8467966573816157,
      "grad_norm": 0.0152587890625,
      "learning_rate": 4.0882352941176474e-05,
      "loss": 0.5106610298156739,
      "step": 125
    },
    {
      "epoch": 1.9210770659238627,
      "grad_norm": 0.01312255859375,
      "learning_rate": 4.051470588235294e-05,
      "loss": 0.5423622608184815,
      "step": 130
    },
    {
      "epoch": 1.9953574744661096,
      "grad_norm": 0.01214599609375,
      "learning_rate": 4.0147058823529415e-05,
      "loss": 0.48050861358642577,
      "step": 135
    },
    {
      "epoch": 2.0594243268337977,
      "grad_norm": 0.01177978515625,
      "learning_rate": 3.977941176470588e-05,
      "loss": 0.4528938293457031,
      "step": 140
    },
    {
      "epoch": 2.1337047353760448,
      "grad_norm": 0.0135498046875,
      "learning_rate": 3.9411764705882356e-05,
      "loss": 0.4708698749542236,
      "step": 145
    },
    {
      "epoch": 2.2079851439182914,
      "grad_norm": 0.015869140625,
      "learning_rate": 3.9044117647058823e-05,
      "loss": 0.40610790252685547,
      "step": 150
    },
    {
      "epoch": 2.2822655524605384,
      "grad_norm": 0.020263671875,
      "learning_rate": 3.86764705882353e-05,
      "loss": 0.4004369735717773,
      "step": 155
    },
    {
      "epoch": 2.3565459610027855,
      "grad_norm": 0.01495361328125,
      "learning_rate": 3.830882352941177e-05,
      "loss": 0.402101993560791,
      "step": 160
    },
    {
      "epoch": 2.4308263695450325,
      "grad_norm": 0.01519775390625,
      "learning_rate": 3.794117647058824e-05,
      "loss": 0.41231889724731446,
      "step": 165
    },
    {
      "epoch": 2.5051067780872796,
      "grad_norm": 0.01611328125,
      "learning_rate": 3.7573529411764706e-05,
      "loss": 0.4784365653991699,
      "step": 170
    },
    {
      "epoch": 2.5793871866295266,
      "grad_norm": 0.0174560546875,
      "learning_rate": 3.720588235294118e-05,
      "loss": 0.4141225814819336,
      "step": 175
    },
    {
      "epoch": 2.6536675951717736,
      "grad_norm": 0.0189208984375,
      "learning_rate": 3.6838235294117654e-05,
      "loss": 0.44509315490722656,
      "step": 180
    },
    {
      "epoch": 2.7279480037140207,
      "grad_norm": 0.018310546875,
      "learning_rate": 3.6470588235294114e-05,
      "loss": 0.4210689067840576,
      "step": 185
    },
    {
      "epoch": 2.8022284122562673,
      "grad_norm": 0.0272216796875,
      "learning_rate": 3.610294117647059e-05,
      "loss": 0.4066977024078369,
      "step": 190
    },
    {
      "epoch": 2.8765088207985143,
      "grad_norm": 0.0128173828125,
      "learning_rate": 3.573529411764706e-05,
      "loss": 0.4026792049407959,
      "step": 195
    },
    {
      "epoch": 2.9507892293407614,
      "grad_norm": 0.0174560546875,
      "learning_rate": 3.5367647058823536e-05,
      "loss": 0.44449539184570314,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.2473975207572275e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}