{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03496503496503497,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017482517482517483,
      "eval_loss": NaN,
      "eval_runtime": 14.9721,
      "eval_samples_per_second": 16.097,
      "eval_steps_per_second": 8.082,
      "step": 1
    },
    {
      "epoch": 0.005244755244755245,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.008741258741258742,
      "eval_loss": NaN,
      "eval_runtime": 13.3291,
      "eval_samples_per_second": 18.081,
      "eval_steps_per_second": 9.078,
      "step": 5
    },
    {
      "epoch": 0.01048951048951049,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.015734265734265736,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.017482517482517484,
      "eval_loss": NaN,
      "eval_runtime": 13.3275,
      "eval_samples_per_second": 18.083,
      "eval_steps_per_second": 9.079,
      "step": 10
    },
    {
      "epoch": 0.02097902097902098,
      "grad_norm": NaN,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.026223776223776224,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.026223776223776224,
      "eval_loss": NaN,
      "eval_runtime": 13.3722,
      "eval_samples_per_second": 18.022,
      "eval_steps_per_second": 9.049,
      "step": 15
    },
    {
      "epoch": 0.03146853146853147,
      "grad_norm": NaN,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.03496503496503497,
      "eval_loss": NaN,
      "eval_runtime": 13.3333,
      "eval_samples_per_second": 18.075,
      "eval_steps_per_second": 9.075,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6592306379489280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}