{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 4689,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06397952655150352,
      "grad_norm": 5.188015460968018,
      "learning_rate": 4.8944337811900195e-05,
      "loss": 0.5162,
      "step": 100
    },
    {
      "epoch": 0.12795905310300704,
      "grad_norm": 8.62886905670166,
      "learning_rate": 4.7878012369375135e-05,
      "loss": 0.4123,
      "step": 200
    },
    {
      "epoch": 0.19193857965451055,
      "grad_norm": 6.661285877227783,
      "learning_rate": 4.681168692685008e-05,
      "loss": 0.4106,
      "step": 300
    },
    {
      "epoch": 0.2559181062060141,
      "grad_norm": 7.992310523986816,
      "learning_rate": 4.5745361484325014e-05,
      "loss": 0.3619,
      "step": 400
    },
    {
      "epoch": 0.3198976327575176,
      "grad_norm": 8.48903751373291,
      "learning_rate": 4.467903604179996e-05,
      "loss": 0.3724,
      "step": 500
    },
    {
      "epoch": 0.3838771593090211,
      "grad_norm": 7.3620219230651855,
      "learning_rate": 4.3612710599274906e-05,
      "loss": 0.3582,
      "step": 600
    },
    {
      "epoch": 0.44785668586052463,
      "grad_norm": 7.127757549285889,
      "learning_rate": 4.254638515674984e-05,
      "loss": 0.351,
      "step": 700
    },
    {
      "epoch": 0.5118362124120281,
      "grad_norm": 8.284778594970703,
      "learning_rate": 4.1480059714224785e-05,
      "loss": 0.3517,
      "step": 800
    },
    {
      "epoch": 0.5758157389635317,
      "grad_norm": 6.389641284942627,
      "learning_rate": 4.0413734271699725e-05,
      "loss": 0.3197,
      "step": 900
    },
    {
      "epoch": 0.6397952655150352,
      "grad_norm": 8.652924537658691,
      "learning_rate": 3.9347408829174664e-05,
      "loss": 0.3457,
      "step": 1000
    },
    {
      "epoch": 0.7037747920665387,
      "grad_norm": 9.87730598449707,
      "learning_rate": 3.828108338664961e-05,
      "loss": 0.3152,
      "step": 1100
    },
    {
      "epoch": 0.7677543186180422,
      "grad_norm": 9.235931396484375,
      "learning_rate": 3.721475794412455e-05,
      "loss": 0.3312,
      "step": 1200
    },
    {
      "epoch": 0.8317338451695457,
      "grad_norm": 8.75272274017334,
      "learning_rate": 3.614843250159949e-05,
      "loss": 0.3098,
      "step": 1300
    },
    {
      "epoch": 0.8957133717210493,
      "grad_norm": 3.6930184364318848,
      "learning_rate": 3.508210705907443e-05,
      "loss": 0.3057,
      "step": 1400
    },
    {
      "epoch": 0.9596928982725528,
      "grad_norm": 15.71256160736084,
      "learning_rate": 3.4015781616549375e-05,
      "loss": 0.2994,
      "step": 1500
    },
    {
      "epoch": 1.0236724248240563,
      "grad_norm": 10.11008071899414,
      "learning_rate": 3.2949456174024315e-05,
      "loss": 0.2945,
      "step": 1600
    },
    {
      "epoch": 1.0876519513755598,
      "grad_norm": 1.052371859550476,
      "learning_rate": 3.1883130731499254e-05,
      "loss": 0.2072,
      "step": 1700
    },
    {
      "epoch": 1.1516314779270633,
      "grad_norm": 0.17214666306972504,
      "learning_rate": 3.08168052889742e-05,
      "loss": 0.1915,
      "step": 1800
    },
    {
      "epoch": 1.2156110044785668,
      "grad_norm": 3.5573925971984863,
      "learning_rate": 2.9750479846449137e-05,
      "loss": 0.2268,
      "step": 1900
    },
    {
      "epoch": 1.2795905310300704,
      "grad_norm": 12.984672546386719,
      "learning_rate": 2.868415440392408e-05,
      "loss": 0.1639,
      "step": 2000
    },
    {
      "epoch": 1.3435700575815739,
      "grad_norm": 0.8138177990913391,
      "learning_rate": 2.7617828961399022e-05,
      "loss": 0.1866,
      "step": 2100
    },
    {
      "epoch": 1.4075495841330774,
      "grad_norm": 10.373751640319824,
      "learning_rate": 2.6551503518873962e-05,
      "loss": 0.2171,
      "step": 2200
    },
    {
      "epoch": 1.471529110684581,
      "grad_norm": 5.024399757385254,
      "learning_rate": 2.5485178076348905e-05,
      "loss": 0.1796,
      "step": 2300
    },
    {
      "epoch": 1.5355086372360844,
      "grad_norm": 7.260871887207031,
      "learning_rate": 2.4418852633823844e-05,
      "loss": 0.1878,
      "step": 2400
    },
    {
      "epoch": 1.599488163787588,
      "grad_norm": 6.540918350219727,
      "learning_rate": 2.3352527191298784e-05,
      "loss": 0.1675,
      "step": 2500
    },
    {
      "epoch": 1.6634676903390915,
      "grad_norm": 2.625058650970459,
      "learning_rate": 2.2286201748773727e-05,
      "loss": 0.2044,
      "step": 2600
    },
    {
      "epoch": 1.727447216890595,
      "grad_norm": 7.691290855407715,
      "learning_rate": 2.1219876306248666e-05,
      "loss": 0.1827,
      "step": 2700
    },
    {
      "epoch": 1.7914267434420985,
      "grad_norm": 8.49361515045166,
      "learning_rate": 2.015355086372361e-05,
      "loss": 0.1954,
      "step": 2800
    },
    {
      "epoch": 1.855406269993602,
      "grad_norm": 0.37825897336006165,
      "learning_rate": 1.9087225421198552e-05,
      "loss": 0.1838,
      "step": 2900
    },
    {
      "epoch": 1.9193857965451055,
      "grad_norm": 22.31838035583496,
      "learning_rate": 1.802089997867349e-05,
      "loss": 0.1847,
      "step": 3000
    },
    {
      "epoch": 1.983365323096609,
      "grad_norm": 20.675575256347656,
      "learning_rate": 1.695457453614843e-05,
      "loss": 0.1817,
      "step": 3100
    },
    {
      "epoch": 2.0473448496481126,
      "grad_norm": 0.051862724125385284,
      "learning_rate": 1.5888249093623374e-05,
      "loss": 0.1106,
      "step": 3200
    },
    {
      "epoch": 2.111324376199616,
      "grad_norm": 31.099328994750977,
      "learning_rate": 1.4821923651098315e-05,
      "loss": 0.0715,
      "step": 3300
    },
    {
      "epoch": 2.1753039027511196,
      "grad_norm": 17.968420028686523,
      "learning_rate": 1.3755598208573256e-05,
      "loss": 0.0986,
      "step": 3400
    },
    {
      "epoch": 2.239283429302623,
      "grad_norm": 11.89964485168457,
      "learning_rate": 1.2689272766048199e-05,
      "loss": 0.0842,
      "step": 3500
    },
    {
      "epoch": 2.3032629558541267,
      "grad_norm": 0.15594251453876495,
      "learning_rate": 1.162294732352314e-05,
      "loss": 0.0859,
      "step": 3600
    },
    {
      "epoch": 2.36724248240563,
      "grad_norm": 0.04546676576137543,
      "learning_rate": 1.0556621880998081e-05,
      "loss": 0.0831,
      "step": 3700
    },
    {
      "epoch": 2.4312220089571337,
      "grad_norm": 0.08984202891588211,
      "learning_rate": 9.490296438473023e-06,
      "loss": 0.0859,
      "step": 3800
    },
    {
      "epoch": 2.495201535508637,
      "grad_norm": 25.065441131591797,
      "learning_rate": 8.423970995947964e-06,
      "loss": 0.0972,
      "step": 3900
    },
    {
      "epoch": 2.5591810620601407,
      "grad_norm": 0.09699796140193939,
      "learning_rate": 7.357645553422905e-06,
      "loss": 0.0777,
      "step": 4000
    },
    {
      "epoch": 2.6231605886116443,
      "grad_norm": 9.286548614501953,
      "learning_rate": 6.291320110897847e-06,
      "loss": 0.0896,
      "step": 4100
    },
    {
      "epoch": 2.6871401151631478,
      "grad_norm": 26.573453903198242,
      "learning_rate": 5.224994668372787e-06,
      "loss": 0.0966,
      "step": 4200
    },
    {
      "epoch": 2.7511196417146513,
      "grad_norm": 8.264235496520996,
      "learning_rate": 4.158669225847729e-06,
      "loss": 0.0734,
      "step": 4300
    },
    {
      "epoch": 2.815099168266155,
      "grad_norm": 29.1925048828125,
      "learning_rate": 3.09234378332267e-06,
      "loss": 0.0863,
      "step": 4400
    },
    {
      "epoch": 2.8790786948176583,
      "grad_norm": 0.08194595575332642,
      "learning_rate": 2.0260183407976117e-06,
      "loss": 0.0607,
      "step": 4500
    },
    {
      "epoch": 2.943058221369162,
      "grad_norm": 0.2947525084018707,
      "learning_rate": 9.596928982725527e-07,
      "loss": 0.059,
      "step": 4600
    }
  ],
  "logging_steps": 100,
  "max_steps": 4689,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4933332288000000.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}