{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 255,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 10.613981432938344,
      "learning_rate": 3.4615384615384617e-06,
      "loss": 0.658917236328125,
      "step": 10
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 7.728391235474098,
      "learning_rate": 7.307692307692308e-06,
      "loss": 0.27490599155426027,
      "step": 20
    },
    {
      "epoch": 0.35294117647058826,
      "grad_norm": 4.794910718922691,
      "learning_rate": 9.99576600836172e-06,
      "loss": 0.1927626371383667,
      "step": 30
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 3.4899456855845994,
      "learning_rate": 9.920694360015864e-06,
      "loss": 0.1680201292037964,
      "step": 40
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 3.0889053111763083,
      "learning_rate": 9.753158444620013e-06,
      "loss": 0.14774863719940184,
      "step": 50
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 5.152709962767952,
      "learning_rate": 9.496306412513989e-06,
      "loss": 0.1617424249649048,
      "step": 60
    },
    {
      "epoch": 0.8235294117647058,
      "grad_norm": 4.627987857042282,
      "learning_rate": 9.154964744099006e-06,
      "loss": 0.15984852313995362,
      "step": 70
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 2.766861341315355,
      "learning_rate": 8.735547555935538e-06,
      "loss": 0.14139217138290405,
      "step": 80
    },
    {
      "epoch": 1.0588235294117647,
      "grad_norm": 2.2855245907805255,
      "learning_rate": 8.245936073731654e-06,
      "loss": 0.1276170253753662,
      "step": 90
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 5.247709874831045,
      "learning_rate": 7.695330537032629e-06,
      "loss": 0.11268491744995117,
      "step": 100
    },
    {
      "epoch": 1.2941176470588236,
      "grad_norm": 2.4254635085114473,
      "learning_rate": 7.094077318455762e-06,
      "loss": 0.11160995960235595,
      "step": 110
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 2.1701716137440483,
      "learning_rate": 6.453474506055228e-06,
      "loss": 0.09826507568359374,
      "step": 120
    },
    {
      "epoch": 1.5294117647058822,
      "grad_norm": 2.2706482639227703,
      "learning_rate": 5.785559602099019e-06,
      "loss": 0.09899702668190002,
      "step": 130
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 3.9764369233609878,
      "learning_rate": 5.102883327588608e-06,
      "loss": 0.10635545253753662,
      "step": 140
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 3.5307300483709505,
      "learning_rate": 4.4182737829376135e-06,
      "loss": 0.09335322380065918,
      "step": 150
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 4.230529156038284,
      "learning_rate": 3.744595396442169e-06,
      "loss": 0.0806308388710022,
      "step": 160
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.3130753385617564,
      "learning_rate": 3.094507190117715e-06,
      "loss": 0.08276625275611878,
      "step": 170
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 2.553362858301541,
      "learning_rate": 2.4802249053043525e-06,
      "loss": 0.047041893005371094,
      "step": 180
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 3.8462698464867535,
      "learning_rate": 1.913291457914234e-06,
      "loss": 0.045320945978164676,
      "step": 190
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 3.3971992957543486,
      "learning_rate": 1.4043600366731213e-06,
      "loss": 0.053915214538574216,
      "step": 200
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 3.442663331353308,
      "learning_rate": 9.629939201349852e-07,
      "loss": 0.049304771423339847,
      "step": 210
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 3.2501045459202405,
      "learning_rate": 5.974867740877282e-07,
      "loss": 0.04598000645637512,
      "step": 220
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 2.6951750099386653,
      "learning_rate": 3.1470680612323503e-07,
      "loss": 0.043671274185180665,
      "step": 230
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 3.035507290196828,
      "learning_rate": 1.199677058473292e-07,
      "loss": 0.04035001397132874,
      "step": 240
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 2.946991168484204,
      "learning_rate": 1.692879587904983e-08,
      "loss": 0.03688072860240936,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 255,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8505000755200.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}