{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.17761989342806395,
  "eval_steps": 200,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.035523978685612786,
      "grad_norm": 30.68755531311035,
      "learning_rate": 2.1176470588235296e-05,
      "loss": 10.0284,
      "step": 10
    },
    {
      "epoch": 0.07104795737122557,
      "grad_norm": 11.449149131774902,
      "learning_rate": 4.470588235294118e-05,
      "loss": 8.8672,
      "step": 20
    },
    {
      "epoch": 0.10657193605683836,
      "grad_norm": 8.332048416137695,
      "learning_rate": 6.823529411764707e-05,
      "loss": 7.2862,
      "step": 30
    },
    {
      "epoch": 0.14209591474245115,
      "grad_norm": 8.64196491241455,
      "learning_rate": 9.176470588235295e-05,
      "loss": 5.7446,
      "step": 40
    },
    {
      "epoch": 0.17761989342806395,
      "grad_norm": 9.184565544128418,
      "learning_rate": 0.00011529411764705881,
      "loss": 4.3277,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 846,
  "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": 2018622500093952.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}