{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010529513010023287,
  "eval_steps": 13,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00040498126961628026,
      "grad_norm": 0.016281457617878914,
      "learning_rate": 1e-05,
      "loss": 11.929,
      "step": 1
    },
    {
      "epoch": 0.00040498126961628026,
      "eval_loss": 11.929625511169434,
      "eval_runtime": 20.8534,
      "eval_samples_per_second": 199.44,
      "eval_steps_per_second": 99.744,
      "step": 1
    },
    {
      "epoch": 0.0008099625392325605,
      "grad_norm": 0.016497384756803513,
      "learning_rate": 2e-05,
      "loss": 11.9295,
      "step": 2
    },
    {
      "epoch": 0.0012149438088488408,
      "grad_norm": 0.014399677515029907,
      "learning_rate": 3e-05,
      "loss": 11.9307,
      "step": 3
    },
    {
      "epoch": 0.001619925078465121,
      "grad_norm": 0.012118221260607243,
      "learning_rate": 4e-05,
      "loss": 11.93,
      "step": 4
    },
    {
      "epoch": 0.0020249063480814013,
      "grad_norm": 0.014372492209076881,
      "learning_rate": 5e-05,
      "loss": 11.9299,
      "step": 5
    },
    {
      "epoch": 0.0024298876176976816,
      "grad_norm": 0.014841921627521515,
      "learning_rate": 6e-05,
      "loss": 11.929,
      "step": 6
    },
    {
      "epoch": 0.002834868887313962,
      "grad_norm": 0.013597904704511166,
      "learning_rate": 7e-05,
      "loss": 11.9283,
      "step": 7
    },
    {
      "epoch": 0.003239850156930242,
      "grad_norm": 0.016889022663235664,
      "learning_rate": 8e-05,
      "loss": 11.9291,
      "step": 8
    },
    {
      "epoch": 0.0036448314265465223,
      "grad_norm": 0.012072063982486725,
      "learning_rate": 9e-05,
      "loss": 11.9299,
      "step": 9
    },
    {
      "epoch": 0.004049812696162803,
      "grad_norm": 0.014724480919539928,
      "learning_rate": 0.0001,
      "loss": 11.9314,
      "step": 10
    },
    {
      "epoch": 0.004454793965779083,
      "grad_norm": 0.014864698983728886,
      "learning_rate": 9.98458666866564e-05,
      "loss": 11.9283,
      "step": 11
    },
    {
      "epoch": 0.004859775235395363,
      "grad_norm": 0.012745369225740433,
      "learning_rate": 9.938441702975689e-05,
      "loss": 11.9302,
      "step": 12
    },
    {
      "epoch": 0.005264756505011643,
      "grad_norm": 0.01918998919427395,
      "learning_rate": 9.861849601988383e-05,
      "loss": 11.9299,
      "step": 13
    },
    {
      "epoch": 0.005264756505011643,
      "eval_loss": 11.929468154907227,
      "eval_runtime": 7.0015,
      "eval_samples_per_second": 594.019,
      "eval_steps_per_second": 297.081,
      "step": 13
    },
    {
      "epoch": 0.005669737774627924,
      "grad_norm": 0.013973494991660118,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.9297,
      "step": 14
    },
    {
      "epoch": 0.006074719044244204,
      "grad_norm": 0.014227038249373436,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9289,
      "step": 15
    },
    {
      "epoch": 0.006479700313860484,
      "grad_norm": 0.014232249930500984,
      "learning_rate": 9.45503262094184e-05,
      "loss": 11.9294,
      "step": 16
    },
    {
      "epoch": 0.0068846815834767644,
      "grad_norm": 0.01532355509698391,
      "learning_rate": 9.263200821770461e-05,
      "loss": 11.9282,
      "step": 17
    },
    {
      "epoch": 0.007289662853093045,
      "grad_norm": 0.01495895441621542,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.9276,
      "step": 18
    },
    {
      "epoch": 0.007694644122709325,
      "grad_norm": 0.012949861586093903,
      "learning_rate": 8.802029828000156e-05,
      "loss": 11.9292,
      "step": 19
    },
    {
      "epoch": 0.008099625392325605,
      "grad_norm": 0.015499262139201164,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9285,
      "step": 20
    },
    {
      "epoch": 0.008504606661941885,
      "grad_norm": 0.016316721215844154,
      "learning_rate": 8.247240241650918e-05,
      "loss": 11.9294,
      "step": 21
    },
    {
      "epoch": 0.008909587931558166,
      "grad_norm": 0.01622353307902813,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.929,
      "step": 22
    },
    {
      "epoch": 0.009314569201174445,
      "grad_norm": 0.0137627013027668,
      "learning_rate": 7.612492823579745e-05,
      "loss": 11.9301,
      "step": 23
    },
    {
      "epoch": 0.009719550470790726,
      "grad_norm": 0.015497871674597263,
      "learning_rate": 7.269952498697734e-05,
      "loss": 11.9295,
      "step": 24
    },
    {
      "epoch": 0.010124531740407006,
      "grad_norm": 0.01868840865790844,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9277,
      "step": 25
    },
    {
      "epoch": 0.010529513010023287,
      "grad_norm": 0.012535473331809044,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.9298,
      "step": 26
    },
    {
      "epoch": 0.010529513010023287,
      "eval_loss": 11.92922306060791,
      "eval_runtime": 7.0474,
      "eval_samples_per_second": 590.143,
      "eval_steps_per_second": 295.142,
      "step": 26
    }
  ],
  "logging_steps": 1,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 12288786432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}