{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "grad_norm": 2.0762882232666016,
      "learning_rate": 0.0001952,
      "loss": 2.921174430847168,
      "step": 10
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.494314432144165,
      "learning_rate": 0.00018986666666666668,
      "loss": 0.8493177413940429,
      "step": 20
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.8940829634666443,
      "learning_rate": 0.00018453333333333334,
      "loss": 0.29891698360443114,
      "step": 30
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.6761481761932373,
      "learning_rate": 0.00017920000000000002,
      "loss": 0.24503071308135987,
      "step": 40
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8483666181564331,
      "learning_rate": 0.00017386666666666667,
      "loss": 0.23532724380493164,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2299281227093760.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}