{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04225649693640397,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008451299387280794,
      "eval_loss": NaN,
      "eval_runtime": 32.5409,
      "eval_samples_per_second": 15.335,
      "eval_steps_per_second": 7.683,
      "step": 1
    },
    {
      "epoch": 0.0042256496936403974,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.008451299387280795,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.008451299387280795,
      "eval_loss": NaN,
      "eval_runtime": 31.2695,
      "eval_samples_per_second": 15.958,
      "eval_steps_per_second": 7.995,
      "step": 10
    },
    {
      "epoch": 0.012676949080921191,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.01690259877456159,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.01690259877456159,
      "eval_loss": NaN,
      "eval_runtime": 31.2804,
      "eval_samples_per_second": 15.952,
      "eval_steps_per_second": 7.992,
      "step": 20
    },
    {
      "epoch": 0.021128248468201986,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.025353898161842383,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.025353898161842383,
      "eval_loss": NaN,
      "eval_runtime": 31.2782,
      "eval_samples_per_second": 15.954,
      "eval_steps_per_second": 7.993,
      "step": 30
    },
    {
      "epoch": 0.02957954785548278,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.03380519754912318,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.03380519754912318,
      "eval_loss": NaN,
      "eval_runtime": 31.275,
      "eval_samples_per_second": 15.955,
      "eval_steps_per_second": 7.994,
      "step": 40
    },
    {
      "epoch": 0.03803084724276357,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.04225649693640397,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.04225649693640397,
      "eval_loss": NaN,
      "eval_runtime": 31.3133,
      "eval_samples_per_second": 15.936,
      "eval_steps_per_second": 7.984,
      "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": 8807165674389504.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}