{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 100,
  "global_step": 33,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.17733469381928443,
      "epoch": 0.9876543209876543,
      "grad_norm": 1.6561490297317505,
      "learning_rate": 7.500000000000001e-05,
      "loss": 19.02234802246094,
      "mean_token_accuracy": 0.09697876162827015,
      "num_tokens": 162113.0,
      "step": 10
    },
    {
      "entropy": 0.1562326379018287,
      "epoch": 1.8888888888888888,
      "grad_norm": 0.4980040490627289,
      "learning_rate": 4.375e-05,
      "loss": 12.02085189819336,
      "mean_token_accuracy": 0.09252177444222855,
      "num_tokens": 309890.0,
      "step": 20
    },
    {
      "entropy": 0.21534234203704417,
      "epoch": 2.7901234567901234,
      "grad_norm": 0.6889352202415466,
      "learning_rate": 1.25e-05,
      "loss": 1.2283188819885253,
      "mean_token_accuracy": 0.0909152039109844,
      "num_tokens": 458756.0,
      "step": 30
    },
    {
      "epoch": 3.0,
      "eval_entropy": 0.09051553408304851,
      "eval_loss": NaN,
      "eval_mean_token_accuracy": 0.0862596763504876,
      "eval_num_tokens": 492483.0,
      "eval_runtime": 10.3363,
      "eval_samples_per_second": 0.871,
      "eval_steps_per_second": 0.871,
      "step": 33
    }
  ],
  "logging_steps": 10,
  "max_steps": 33,
  "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": 1060747676575488.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}