{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0025369084951199746,
  "eval_steps": 2,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001409393608399986,
      "grad_norm": 0.40887540578842163,
      "learning_rate": 1e-05,
      "loss": 10.3962,
      "step": 1
    },
    {
      "epoch": 0.0001409393608399986,
      "eval_loss": NaN,
      "eval_runtime": 11.4051,
      "eval_samples_per_second": 261.988,
      "eval_steps_per_second": 130.994,
      "step": 1
    },
    {
      "epoch": 0.0002818787216799972,
      "grad_norm": 0.41520577669143677,
      "learning_rate": 2e-05,
      "loss": 10.3918,
      "step": 2
    },
    {
      "epoch": 0.0002818787216799972,
      "eval_loss": NaN,
      "eval_runtime": 11.9,
      "eval_samples_per_second": 251.092,
      "eval_steps_per_second": 125.546,
      "step": 2
    },
    {
      "epoch": 0.00042281808251999576,
      "grad_norm": 0.43705397844314575,
      "learning_rate": 3e-05,
      "loss": 10.3964,
      "step": 3
    },
    {
      "epoch": 0.0005637574433599944,
      "grad_norm": 0.46050891280174255,
      "learning_rate": 4e-05,
      "loss": 10.3956,
      "step": 4
    },
    {
      "epoch": 0.0005637574433599944,
      "eval_loss": NaN,
      "eval_runtime": 12.179,
      "eval_samples_per_second": 245.341,
      "eval_steps_per_second": 122.67,
      "step": 4
    },
    {
      "epoch": 0.0007046968041999929,
      "grad_norm": 0.4756773114204407,
      "learning_rate": 5e-05,
      "loss": 10.4132,
      "step": 5
    },
    {
      "epoch": 0.0008456361650399915,
      "grad_norm": 0.3863561153411865,
      "learning_rate": 6e-05,
      "loss": 10.3797,
      "step": 6
    },
    {
      "epoch": 0.0008456361650399915,
      "eval_loss": NaN,
      "eval_runtime": 12.0499,
      "eval_samples_per_second": 247.968,
      "eval_steps_per_second": 123.984,
      "step": 6
    },
    {
      "epoch": 0.0009865755258799901,
      "grad_norm": 0.47305724024772644,
      "learning_rate": 7e-05,
      "loss": 10.398,
      "step": 7
    },
    {
      "epoch": 0.0011275148867199887,
      "grad_norm": 0.4628412425518036,
      "learning_rate": 8e-05,
      "loss": 10.3953,
      "step": 8
    },
    {
      "epoch": 0.0011275148867199887,
      "eval_loss": NaN,
      "eval_runtime": 12.0344,
      "eval_samples_per_second": 248.289,
      "eval_steps_per_second": 124.145,
      "step": 8
    },
    {
      "epoch": 0.0012684542475599873,
      "grad_norm": 0.4279620945453644,
      "learning_rate": 9e-05,
      "loss": 10.3821,
      "step": 9
    },
    {
      "epoch": 0.0014093936083999859,
      "grad_norm": 0.40721234679222107,
      "learning_rate": 0.0001,
      "loss": 10.4019,
      "step": 10
    },
    {
      "epoch": 0.0014093936083999859,
      "eval_loss": NaN,
      "eval_runtime": 12.085,
      "eval_samples_per_second": 247.249,
      "eval_steps_per_second": 123.624,
      "step": 10
    },
    {
      "epoch": 0.0015503329692399845,
      "grad_norm": 0.4028102457523346,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.3758,
      "step": 11
    },
    {
      "epoch": 0.001691272330079983,
      "grad_norm": 0.45374321937561035,
      "learning_rate": 9.045084971874738e-05,
      "loss": 10.4035,
      "step": 12
    },
    {
      "epoch": 0.001691272330079983,
      "eval_loss": NaN,
      "eval_runtime": 11.9986,
      "eval_samples_per_second": 249.029,
      "eval_steps_per_second": 124.514,
      "step": 12
    },
    {
      "epoch": 0.0018322116909199816,
      "grad_norm": 0.4572100043296814,
      "learning_rate": 7.938926261462366e-05,
      "loss": 10.3763,
      "step": 13
    },
    {
      "epoch": 0.0019731510517599802,
      "grad_norm": 0.47349345684051514,
      "learning_rate": 6.545084971874738e-05,
      "loss": 10.3903,
      "step": 14
    },
    {
      "epoch": 0.0019731510517599802,
      "eval_loss": NaN,
      "eval_runtime": 12.3087,
      "eval_samples_per_second": 242.756,
      "eval_steps_per_second": 121.378,
      "step": 14
    },
    {
      "epoch": 0.002114090412599979,
      "grad_norm": 0.4572914242744446,
      "learning_rate": 5e-05,
      "loss": 10.3862,
      "step": 15
    },
    {
      "epoch": 0.0022550297734399774,
      "grad_norm": 0.4461607336997986,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 10.3791,
      "step": 16
    },
    {
      "epoch": 0.0022550297734399774,
      "eval_loss": NaN,
      "eval_runtime": 12.2292,
      "eval_samples_per_second": 244.333,
      "eval_steps_per_second": 122.166,
      "step": 16
    },
    {
      "epoch": 0.002395969134279976,
      "grad_norm": 0.5067576766014099,
      "learning_rate": 2.061073738537635e-05,
      "loss": 10.3954,
      "step": 17
    },
    {
      "epoch": 0.0025369084951199746,
      "grad_norm": 0.40567123889923096,
      "learning_rate": 9.549150281252633e-06,
      "loss": 10.3808,
      "step": 18
    },
    {
      "epoch": 0.0025369084951199746,
      "eval_loss": NaN,
      "eval_runtime": 12.1062,
      "eval_samples_per_second": 246.815,
      "eval_steps_per_second": 123.408,
      "step": 18
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 470722019328.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}