{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.94482421875,
      "epoch": 0.42105263157894735,
      "grad_norm": 1.220973014831543,
      "learning_rate": 8.117449009293668e-06,
      "loss": 1.0281194686889648,
      "mean_token_accuracy": 0.7450900584459305,
      "num_tokens": 446328.0,
      "step": 10
    },
    {
      "entropy": 0.79443359375,
      "epoch": 0.8421052631578947,
      "grad_norm": 0.8065003156661987,
      "learning_rate": 1.3347406408508695e-06,
      "loss": 0.809284782409668,
      "mean_token_accuracy": 0.7809456035494804,
      "num_tokens": 889091.0,
      "step": 20
    },
    {
      "entropy": 0.7966145833333333,
      "epoch": 1.0,
      "mean_token_accuracy": 0.7856397827466329,
      "num_tokens": 1051899.0,
      "step": 24,
      "total_flos": 3227199406080.0,
      "train_loss": 0.8965883255004883,
      "train_runtime": 1919.1037,
      "train_samples_per_second": 0.788,
      "train_steps_per_second": 0.013
    }
  ],
  "logging_steps": 10,
  "max_steps": 24,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3227199406080.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}