{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.6962053060531614,
      "epoch": 0.3389830508474576,
      "grad_norm": 5.6875,
      "learning_rate": 1.9689373017815076e-05,
      "loss": 2.622,
      "mean_token_accuracy": 0.4749481610953808,
      "num_tokens": 5419.0,
      "step": 10
    },
    {
      "entropy": 2.698164188861847,
      "epoch": 0.6779661016949152,
      "grad_norm": 3.328125,
      "learning_rate": 1.8214207751204917e-05,
      "loss": 2.4606,
      "mean_token_accuracy": 0.49576075151562693,
      "num_tokens": 11175.0,
      "step": 20
    },
    {
      "entropy": 2.676299622184352,
      "epoch": 1.0,
      "grad_norm": 2.640625,
      "learning_rate": 1.5703226369349642e-05,
      "loss": 2.3682,
      "mean_token_accuracy": 0.49295464863902644,
      "num_tokens": 16450.0,
      "step": 30
    },
    {
      "entropy": 2.69452788233757,
      "epoch": 1.3389830508474576,
      "grad_norm": 1.8828125,
      "learning_rate": 1.2473065005542155e-05,
      "loss": 2.2639,
      "mean_token_accuracy": 0.5272781491279602,
      "num_tokens": 22083.0,
      "step": 40
    },
    {
      "entropy": 2.6724473893642426,
      "epoch": 1.6779661016949152,
      "grad_norm": 2.046875,
      "learning_rate": 8.931048784348875e-06,
      "loss": 2.318,
      "mean_token_accuracy": 0.5053238138556481,
      "num_tokens": 27625.0,
      "step": 50
    },
    {
      "entropy": 2.72734388552214,
      "epoch": 2.0,
      "grad_norm": 2.5625,
      "learning_rate": 5.523827899372876e-06,
      "loss": 2.3562,
      "mean_token_accuracy": 0.5088289270275518,
      "num_tokens": 32900.0,
      "step": 60
    },
    {
      "entropy": 2.6972490429878233,
      "epoch": 2.3389830508474576,
      "grad_norm": 1.9609375,
      "learning_rate": 2.681054778182748e-06,
      "loss": 2.3019,
      "mean_token_accuracy": 0.5131353832781315,
      "num_tokens": 38497.0,
      "step": 70
    },
    {
      "entropy": 2.6893122375011442,
      "epoch": 2.6779661016949152,
      "grad_norm": 1.984375,
      "learning_rate": 7.612046748871327e-07,
      "loss": 2.2939,
      "mean_token_accuracy": 0.520061531662941,
      "num_tokens": 44003.0,
      "step": 80
    },
    {
      "entropy": 2.6991821401997615,
      "epoch": 3.0,
      "grad_norm": 2.875,
      "learning_rate": 6.371743430082511e-09,
      "loss": 2.2783,
      "mean_token_accuracy": 0.5276820785120914,
      "num_tokens": 49350.0,
      "step": 90
    }
  ],
  "logging_steps": 10,
  "max_steps": 90,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 847960927833600.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}