{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7547169811320755,
  "eval_steps": 500,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.27734375,
      "epoch": 0.18867924528301888,
      "grad_norm": 1.4095726013183594,
      "learning_rate": 0.0001999145758387301,
      "loss": 2.535823440551758,
      "mean_token_accuracy": 0.4902416098862886,
      "num_tokens": 36112.0,
      "step": 10
    },
    {
      "entropy": 2.03623046875,
      "epoch": 0.37735849056603776,
      "grad_norm": 1.8039652109146118,
      "learning_rate": 0.00019694002659393305,
      "loss": 1.8651376724243165,
      "mean_token_accuracy": 0.5952314671128989,
      "num_tokens": 72245.0,
      "step": 20
    },
    {
      "entropy": 1.49443359375,
      "epoch": 0.5660377358490566,
      "grad_norm": 0.7885380387306213,
      "learning_rate": 0.0001898390981891979,
      "loss": 1.5259657859802247,
      "mean_token_accuracy": 0.6693046040832996,
      "num_tokens": 108540.0,
      "step": 30
    },
    {
      "entropy": 1.421875,
      "epoch": 0.7547169811320755,
      "grad_norm": 0.7279834747314453,
      "learning_rate": 0.00017891405093963938,
      "loss": 1.4288103103637695,
      "mean_token_accuracy": 0.6861812733113766,
      "num_tokens": 144637.0,
      "step": 40
    }
  ],
  "logging_steps": 10,
  "max_steps": 159,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 452432126406912.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}