{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22870211549456831,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011435105774728416,
      "eval_loss": NaN,
      "eval_runtime": 22.7683,
      "eval_samples_per_second": 16.207,
      "eval_steps_per_second": 8.125,
      "step": 1
    },
    {
      "epoch": 0.011435105774728416,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 1.4199,
      "step": 10
    },
    {
      "epoch": 0.022870211549456832,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 28.5375,
      "step": 20
    },
    {
      "epoch": 0.03430531732418525,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 19.8312,
      "step": 30
    },
    {
      "epoch": 0.045740423098913664,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 79.4673,
      "step": 40
    },
    {
      "epoch": 0.05717552887364208,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 18.5405,
      "step": 50
    },
    {
      "epoch": 0.05717552887364208,
      "eval_loss": NaN,
      "eval_runtime": 21.0699,
      "eval_samples_per_second": 17.513,
      "eval_steps_per_second": 8.78,
      "step": 50
    },
    {
      "epoch": 0.0686106346483705,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 90.8954,
      "step": 60
    },
    {
      "epoch": 0.08004574042309891,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 18.4395,
      "step": 70
    },
    {
      "epoch": 0.09148084619782733,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 9.3505,
      "step": 80
    },
    {
      "epoch": 0.10291595197255575,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 9.4442,
      "step": 90
    },
    {
      "epoch": 0.11435105774728416,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 12.0121,
      "step": 100
    },
    {
      "epoch": 0.11435105774728416,
      "eval_loss": NaN,
      "eval_runtime": 21.0675,
      "eval_samples_per_second": 17.515,
      "eval_steps_per_second": 8.781,
      "step": 100
    },
    {
      "epoch": 0.12578616352201258,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 9.6699,
      "step": 110
    },
    {
      "epoch": 0.137221269296741,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 14.4873,
      "step": 120
    },
    {
      "epoch": 0.14865637507146942,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 11.8371,
      "step": 130
    },
    {
      "epoch": 0.16009148084619781,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 5.245,
      "step": 140
    },
    {
      "epoch": 0.17152658662092624,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 26.7057,
      "step": 150
    },
    {
      "epoch": 0.17152658662092624,
      "eval_loss": NaN,
      "eval_runtime": 21.0628,
      "eval_samples_per_second": 17.519,
      "eval_steps_per_second": 8.783,
      "step": 150
    },
    {
      "epoch": 0.18296169239565466,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 16.942,
      "step": 160
    },
    {
      "epoch": 0.19439679817038308,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 8.9252,
      "step": 170
    },
    {
      "epoch": 0.2058319039451115,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 16.2143,
      "step": 180
    },
    {
      "epoch": 0.21726700971983992,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 19.0338,
      "step": 190
    },
    {
      "epoch": 0.22870211549456831,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 17.9537,
      "step": 200
    },
    {
      "epoch": 0.22870211549456831,
      "eval_loss": NaN,
      "eval_runtime": 21.0805,
      "eval_samples_per_second": 17.504,
      "eval_steps_per_second": 8.776,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.474218216620032e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}