{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7407407407407407,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.1715362322330476,
      "epoch": 0.07407407407407407,
      "grad_norm": 1.0598933696746826,
      "learning_rate": 8.032786885245902e-05,
      "loss": 2.0077,
      "mean_token_accuracy": 0.5798640113323927,
      "num_tokens": 338396.0,
      "step": 50
    },
    {
      "entropy": 0.6553284931182861,
      "epoch": 0.14814814814814814,
      "grad_norm": 0.3852575719356537,
      "learning_rate": 9.990765991730485e-05,
      "loss": 0.5993,
      "mean_token_accuracy": 0.8612996307015419,
      "num_tokens": 677239.0,
      "step": 100
    },
    {
      "entropy": 0.4204328820481896,
      "epoch": 0.2222222222222222,
      "grad_norm": 0.2863098680973053,
      "learning_rate": 9.950545603782162e-05,
      "loss": 0.4172,
      "mean_token_accuracy": 0.9052096186578273,
      "num_tokens": 1015420.0,
      "step": 150
    },
    {
      "entropy": 0.3820256270095706,
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2698630690574646,
      "learning_rate": 9.878674879048427e-05,
      "loss": 0.383,
      "mean_token_accuracy": 0.9129502369463444,
      "num_tokens": 1355048.0,
      "step": 200
    },
    {
      "entropy": 0.37178467601537707,
      "epoch": 0.37037037037037035,
      "grad_norm": 0.21257849037647247,
      "learning_rate": 9.775613308830824e-05,
      "loss": 0.37,
      "mean_token_accuracy": 0.9151540066301823,
      "num_tokens": 1691649.0,
      "step": 250
    },
    {
      "entropy": 0.36766253888607026,
      "epoch": 0.4444444444444444,
      "grad_norm": 0.31453582644462585,
      "learning_rate": 9.642019796948866e-05,
      "loss": 0.3634,
      "mean_token_accuracy": 0.9162409096956253,
      "num_tokens": 2029267.0,
      "step": 300
    },
    {
      "entropy": 0.35622088231146337,
      "epoch": 0.5185185185185185,
      "grad_norm": 0.20113833248615265,
      "learning_rate": 9.478748447168449e-05,
      "loss": 0.3533,
      "mean_token_accuracy": 0.9183417546749115,
      "num_tokens": 2369465.0,
      "step": 350
    },
    {
      "entropy": 0.3494216964393854,
      "epoch": 0.5925925925925926,
      "grad_norm": 0.20226770639419556,
      "learning_rate": 9.28684310265789e-05,
      "loss": 0.3492,
      "mean_token_accuracy": 0.919527986496687,
      "num_tokens": 2707235.0,
      "step": 400
    },
    {
      "entropy": 0.3433630639687181,
      "epoch": 0.6666666666666666,
      "grad_norm": 0.1721702516078949,
      "learning_rate": 9.067530672382544e-05,
      "loss": 0.3453,
      "mean_token_accuracy": 0.9204271128773689,
      "num_tokens": 3041282.0,
      "step": 450
    },
    {
      "entropy": 0.3465565311536193,
      "epoch": 0.7407407407407407,
      "grad_norm": 0.1957043558359146,
      "learning_rate": 8.822213287104348e-05,
      "loss": 0.3483,
      "mean_token_accuracy": 0.9200405342876912,
      "num_tokens": 3378157.0,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 2025,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.411146339478057e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}