{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05790622665655238,
  "eval_steps": 500,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002895311332827619,
      "grad_norm": 1.7338896989822388,
      "learning_rate": 4.985523443335862e-05,
      "loss": 3.1507,
      "step": 500
    },
    {
      "epoch": 0.005790622665655238,
      "grad_norm": 1.2579742670059204,
      "learning_rate": 4.9710468866717244e-05,
      "loss": 2.6357,
      "step": 1000
    },
    {
      "epoch": 0.008685933998482857,
      "grad_norm": 0.9996505975723267,
      "learning_rate": 4.956570330007586e-05,
      "loss": 2.4288,
      "step": 1500
    },
    {
      "epoch": 0.011581245331310476,
      "grad_norm": 0.9657206535339355,
      "learning_rate": 4.942093773343448e-05,
      "loss": 2.2119,
      "step": 2000
    },
    {
      "epoch": 0.014476556664138095,
      "grad_norm": 1.044640064239502,
      "learning_rate": 4.92761721667931e-05,
      "loss": 2.1225,
      "step": 2500
    },
    {
      "epoch": 0.017371867996965714,
      "grad_norm": 0.8428456783294678,
      "learning_rate": 4.913140660015172e-05,
      "loss": 2.0409,
      "step": 3000
    },
    {
      "epoch": 0.02026717932979333,
      "grad_norm": 1.2827749252319336,
      "learning_rate": 4.898664103351033e-05,
      "loss": 1.9031,
      "step": 3500
    },
    {
      "epoch": 0.023162490662620952,
      "grad_norm": 0.9291247129440308,
      "learning_rate": 4.884187546686895e-05,
      "loss": 1.8438,
      "step": 4000
    },
    {
      "epoch": 0.02605780199544857,
      "grad_norm": 0.7757951617240906,
      "learning_rate": 4.8697109900227575e-05,
      "loss": 1.7833,
      "step": 4500
    },
    {
      "epoch": 0.02895311332827619,
      "grad_norm": 1.520269751548767,
      "learning_rate": 4.855234433358619e-05,
      "loss": 1.6942,
      "step": 5000
    },
    {
      "epoch": 0.03184842466110381,
      "grad_norm": 1.2558553218841553,
      "learning_rate": 4.840757876694481e-05,
      "loss": 1.6669,
      "step": 5500
    },
    {
      "epoch": 0.03474373599393143,
      "grad_norm": 1.3526251316070557,
      "learning_rate": 4.826281320030343e-05,
      "loss": 1.6115,
      "step": 6000
    },
    {
      "epoch": 0.037639047326759045,
      "grad_norm": 2.5751099586486816,
      "learning_rate": 4.811804763366205e-05,
      "loss": 1.5629,
      "step": 6500
    },
    {
      "epoch": 0.04053435865958666,
      "grad_norm": 1.3569105863571167,
      "learning_rate": 4.797328206702067e-05,
      "loss": 1.5258,
      "step": 7000
    },
    {
      "epoch": 0.04342966999241429,
      "grad_norm": 1.7734428644180298,
      "learning_rate": 4.782851650037929e-05,
      "loss": 1.475,
      "step": 7500
    },
    {
      "epoch": 0.046324981325241904,
      "grad_norm": 0.7975415587425232,
      "learning_rate": 4.7683750933737905e-05,
      "loss": 1.437,
      "step": 8000
    },
    {
      "epoch": 0.04922029265806952,
      "grad_norm": 0.8590123057365417,
      "learning_rate": 4.753898536709653e-05,
      "loss": 1.4263,
      "step": 8500
    },
    {
      "epoch": 0.05211560399089714,
      "grad_norm": 1.1225152015686035,
      "learning_rate": 4.739421980045515e-05,
      "loss": 1.3528,
      "step": 9000
    },
    {
      "epoch": 0.05501091532372476,
      "grad_norm": 1.1342971324920654,
      "learning_rate": 4.7249454233813765e-05,
      "loss": 1.3576,
      "step": 9500
    },
    {
      "epoch": 0.05790622665655238,
      "grad_norm": 0.9445364475250244,
      "learning_rate": 4.710468866717238e-05,
      "loss": 1.3283,
      "step": 10000
    }
  ],
  "logging_steps": 500,
  "max_steps": 172693,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.180672512e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}