{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 7.800250053405762,
      "learning_rate": 0.0001,
      "loss": 2.810793399810791,
      "step": 2
    },
    {
      "epoch": 0.4,
      "grad_norm": 2.157320737838745,
      "learning_rate": 0.00018888888888888888,
      "loss": 2.231755018234253,
      "step": 4
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.0025198459625244,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.6232446432113647,
      "step": 6
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.7017460465431213,
      "learning_rate": 0.00014444444444444444,
      "loss": 1.4629032611846924,
      "step": 8
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.6504539251327515,
      "learning_rate": 0.00012222222222222224,
      "loss": 1.3223334550857544,
      "step": 10
    }
  ],
  "logging_steps": 2,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 648508533663744.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}