{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1314060446780552,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002628120893561104,
      "eval_loss": NaN,
      "eval_runtime": 6.5943,
      "eval_samples_per_second": 24.415,
      "eval_steps_per_second": 12.283,
      "step": 1
    },
    {
      "epoch": 0.013140604467805518,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.026281208935611037,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.026281208935611037,
      "eval_loss": NaN,
      "eval_runtime": 5.3138,
      "eval_samples_per_second": 30.298,
      "eval_steps_per_second": 15.243,
      "step": 10
    },
    {
      "epoch": 0.03942181340341656,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.052562417871222074,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.052562417871222074,
      "eval_loss": NaN,
      "eval_runtime": 5.2645,
      "eval_samples_per_second": 30.582,
      "eval_steps_per_second": 15.386,
      "step": 20
    },
    {
      "epoch": 0.0657030223390276,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.07884362680683311,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.07884362680683311,
      "eval_loss": NaN,
      "eval_runtime": 5.2935,
      "eval_samples_per_second": 30.415,
      "eval_steps_per_second": 15.302,
      "step": 30
    },
    {
      "epoch": 0.09198423127463863,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.10512483574244415,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.10512483574244415,
      "eval_loss": NaN,
      "eval_runtime": 5.3498,
      "eval_samples_per_second": 30.094,
      "eval_steps_per_second": 15.141,
      "step": 40
    },
    {
      "epoch": 0.11826544021024968,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.1314060446780552,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.1314060446780552,
      "eval_loss": NaN,
      "eval_runtime": 5.2665,
      "eval_samples_per_second": 30.571,
      "eval_steps_per_second": 15.38,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 451868681306112.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}