{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 22,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 1.1512951850891113,
      "learning_rate": 8e-05,
      "loss": 1.5335,
      "step": 5
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.6571760177612305,
      "learning_rate": 0.00018,
      "loss": 1.2135,
      "step": 10
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.43884041905403137,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.961,
      "step": 15
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.3839874267578125,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 0.8429,
      "step": 20
    }
  ],
  "logging_steps": 5,
  "max_steps": 22,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.686351059550618e+16,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}