{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 6.149578783679878,
      "learning_rate": 4.5e-06,
      "loss": 0.6331,
      "step": 10
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.2384800800867497,
      "learning_rate": 9.5e-06,
      "loss": 0.0325,
      "step": 20
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.1503923352654872,
      "learning_rate": 9.938441702975689e-06,
      "loss": 0.0177,
      "step": 30
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.43831478111519223,
      "learning_rate": 9.727592877996585e-06,
      "loss": 0.0136,
      "step": 40
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.5436900390920579,
      "learning_rate": 9.37309853569698e-06,
      "loss": 0.01,
      "step": 50
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.341282163428036,
      "learning_rate": 8.885729807284855e-06,
      "loss": 0.0091,
      "step": 60
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.6005309416341524,
      "learning_rate": 8.280295144952537e-06,
      "loss": 0.0111,
      "step": 70
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.1499254354190196,
      "learning_rate": 7.575190374550272e-06,
      "loss": 0.0174,
      "step": 80
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.16970870354718348,
      "learning_rate": 6.7918397477265e-06,
      "loss": 0.0073,
      "step": 90
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5079130124387106,
      "learning_rate": 5.954044976882725e-06,
      "loss": 0.0156,
      "step": 100
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.31418067538593064,
      "learning_rate": 5.087262032186418e-06,
      "loss": 0.0062,
      "step": 110
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.4872591198644674,
      "learning_rate": 4.217827674798845e-06,
      "loss": 0.0064,
      "step": 120
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.27785728343682203,
      "learning_rate": 3.372159227714218e-06,
      "loss": 0.0046,
      "step": 130
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.28237621470377,
      "learning_rate": 2.5759518987683154e-06,
      "loss": 0.0044,
      "step": 140
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.2645424004724206,
      "learning_rate": 1.8533980447508138e-06,
      "loss": 0.0036,
      "step": 150
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.37036978334692616,
      "learning_rate": 1.22645209888614e-06,
      "loss": 0.0037,
      "step": 160
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.22511149333212746,
      "learning_rate": 7.141634964894389e-07,
      "loss": 0.005,
      "step": 170
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.4108492885842886,
      "learning_rate": 3.320978675139919e-07,
      "loss": 0.0026,
      "step": 180
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.42153747386713103,
      "learning_rate": 9.186408276168012e-08,
      "loss": 0.0026,
      "step": 190
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4250403670308988,
      "learning_rate": 7.615242180436521e-10,
      "loss": 0.0048,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5921732984832.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}