{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010344186647917829,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.465116654948643e-05,
      "grad_norm": 44.632102966308594,
      "learning_rate": 6.451612903225807e-08,
      "loss": 1.8854,
      "step": 1
    },
    {
      "epoch": 0.00012930233309897286,
      "grad_norm": 46.18963623046875,
      "learning_rate": 1.2903225806451614e-07,
      "loss": 1.7711,
      "step": 2
    },
    {
      "epoch": 0.0001939534996484593,
      "grad_norm": 45.15989685058594,
      "learning_rate": 1.935483870967742e-07,
      "loss": 1.9258,
      "step": 3
    },
    {
      "epoch": 0.0002586046661979457,
      "grad_norm": 48.17970275878906,
      "learning_rate": 2.580645161290323e-07,
      "loss": 1.9478,
      "step": 4
    },
    {
      "epoch": 0.00032325583274743215,
      "grad_norm": 46.92567443847656,
      "learning_rate": 3.2258064516129035e-07,
      "loss": 1.8888,
      "step": 5
    },
    {
      "epoch": 0.0003879069992969186,
      "grad_norm": 32.95823287963867,
      "learning_rate": 3.870967741935484e-07,
      "loss": 1.877,
      "step": 6
    },
    {
      "epoch": 0.000452558165846405,
      "grad_norm": 25.36848258972168,
      "learning_rate": 4.5161290322580644e-07,
      "loss": 1.7888,
      "step": 7
    },
    {
      "epoch": 0.0005172093323958914,
      "grad_norm": 31.360990524291992,
      "learning_rate": 5.161290322580646e-07,
      "loss": 1.8526,
      "step": 8
    },
    {
      "epoch": 0.0005818604989453779,
      "grad_norm": 23.622682571411133,
      "learning_rate": 5.806451612903227e-07,
      "loss": 1.8157,
      "step": 9
    },
    {
      "epoch": 0.0006465116654948643,
      "grad_norm": 22.565826416015625,
      "learning_rate": 6.451612903225807e-07,
      "loss": 1.7774,
      "step": 10
    },
    {
      "epoch": 0.0007111628320443507,
      "grad_norm": 22.03154945373535,
      "learning_rate": 7.096774193548388e-07,
      "loss": 1.7796,
      "step": 11
    },
    {
      "epoch": 0.0007758139985938372,
      "grad_norm": 22.295787811279297,
      "learning_rate": 7.741935483870968e-07,
      "loss": 1.7066,
      "step": 12
    },
    {
      "epoch": 0.0008404651651433236,
      "grad_norm": 18.35325050354004,
      "learning_rate": 8.38709677419355e-07,
      "loss": 1.7261,
      "step": 13
    },
    {
      "epoch": 0.00090511633169281,
      "grad_norm": 20.82447052001953,
      "learning_rate": 9.032258064516129e-07,
      "loss": 1.8172,
      "step": 14
    },
    {
      "epoch": 0.0009697674982422964,
      "grad_norm": 10.829120635986328,
      "learning_rate": 9.67741935483871e-07,
      "loss": 1.7402,
      "step": 15
    },
    {
      "epoch": 0.0010344186647917829,
      "grad_norm": 31.75849723815918,
      "learning_rate": 1.0322580645161291e-06,
      "loss": 1.618,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 15467,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 16,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.605109794349056e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}