{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 11.906340599060059,
      "learning_rate": 1e-05,
      "loss": 3.9824,
      "step": 1
    },
    {
      "epoch": 0.08,
      "grad_norm": 10.25975227355957,
      "learning_rate": 9.990133642141359e-06,
      "loss": 3.0566,
      "step": 2
    },
    {
      "epoch": 0.12,
      "grad_norm": 8.298895835876465,
      "learning_rate": 9.960573506572391e-06,
      "loss": 3.3691,
      "step": 3
    },
    {
      "epoch": 0.16,
      "grad_norm": 6.6183857917785645,
      "learning_rate": 9.911436253643445e-06,
      "loss": 2.8252,
      "step": 4
    },
    {
      "epoch": 0.2,
      "grad_norm": 14.412359237670898,
      "learning_rate": 9.842915805643156e-06,
      "loss": 2.7207,
      "step": 5
    },
    {
      "epoch": 0.24,
      "grad_norm": 6.7871809005737305,
      "learning_rate": 9.755282581475769e-06,
      "loss": 2.3525,
      "step": 6
    },
    {
      "epoch": 0.28,
      "grad_norm": 5.780737400054932,
      "learning_rate": 9.648882429441258e-06,
      "loss": 2.459,
      "step": 7
    },
    {
      "epoch": 0.32,
      "grad_norm": 5.381155014038086,
      "learning_rate": 9.524135262330098e-06,
      "loss": 2.0127,
      "step": 8
    },
    {
      "epoch": 0.36,
      "grad_norm": 4.218533992767334,
      "learning_rate": 9.381533400219319e-06,
      "loss": 1.8193,
      "step": 9
    },
    {
      "epoch": 0.4,
      "grad_norm": 4.716296672821045,
      "learning_rate": 9.221639627510076e-06,
      "loss": 1.9609,
      "step": 10
    },
    {
      "epoch": 0.44,
      "grad_norm": 5.695241928100586,
      "learning_rate": 9.045084971874738e-06,
      "loss": 1.6338,
      "step": 11
    },
    {
      "epoch": 0.48,
      "grad_norm": 5.441693305969238,
      "learning_rate": 8.852566213878947e-06,
      "loss": 1.7583,
      "step": 12
    },
    {
      "epoch": 0.52,
      "grad_norm": 4.540189266204834,
      "learning_rate": 8.644843137107058e-06,
      "loss": 1.8013,
      "step": 13
    },
    {
      "epoch": 0.56,
      "grad_norm": 5.0026140213012695,
      "learning_rate": 8.422735529643445e-06,
      "loss": 1.9912,
      "step": 14
    },
    {
      "epoch": 0.6,
      "grad_norm": 4.888060092926025,
      "learning_rate": 8.18711994874345e-06,
      "loss": 1.8115,
      "step": 15
    },
    {
      "epoch": 0.64,
      "grad_norm": 3.9493956565856934,
      "learning_rate": 7.938926261462366e-06,
      "loss": 1.5962,
      "step": 16
    },
    {
      "epoch": 0.68,
      "grad_norm": 4.674317836761475,
      "learning_rate": 7.679133974894984e-06,
      "loss": 1.7031,
      "step": 17
    },
    {
      "epoch": 0.72,
      "grad_norm": 4.73283576965332,
      "learning_rate": 7.408768370508577e-06,
      "loss": 1.5901,
      "step": 18
    },
    {
      "epoch": 0.76,
      "grad_norm": 5.161931991577148,
      "learning_rate": 7.128896457825364e-06,
      "loss": 1.5977,
      "step": 19
    },
    {
      "epoch": 0.8,
      "grad_norm": 4.312277317047119,
      "learning_rate": 6.840622763423391e-06,
      "loss": 1.5112,
      "step": 20
    },
    {
      "epoch": 0.84,
      "grad_norm": 4.844031810760498,
      "learning_rate": 6.545084971874738e-06,
      "loss": 1.7095,
      "step": 21
    },
    {
      "epoch": 0.88,
      "grad_norm": 4.074965476989746,
      "learning_rate": 6.243449435824276e-06,
      "loss": 1.5,
      "step": 22
    },
    {
      "epoch": 0.92,
      "grad_norm": 4.28408145904541,
      "learning_rate": 5.936906572928625e-06,
      "loss": 1.4189,
      "step": 23
    },
    {
      "epoch": 0.96,
      "grad_norm": 4.0645928382873535,
      "learning_rate": 5.626666167821522e-06,
      "loss": 1.563,
      "step": 24
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.447252035140991,
      "learning_rate": 5.3139525976465675e-06,
      "loss": 1.1304,
      "step": 25
    },
    {
      "epoch": 1.04,
      "grad_norm": 3.8235199451446533,
      "learning_rate": 5e-06,
      "loss": 1.0225,
      "step": 26
    },
    {
      "epoch": 1.08,
      "grad_norm": 3.1808114051818848,
      "learning_rate": 4.686047402353433e-06,
      "loss": 0.8237,
      "step": 27
    },
    {
      "epoch": 1.12,
      "grad_norm": 4.179178714752197,
      "learning_rate": 4.373333832178478e-06,
      "loss": 1.1797,
      "step": 28
    },
    {
      "epoch": 1.16,
      "grad_norm": 3.843412399291992,
      "learning_rate": 4.063093427071376e-06,
      "loss": 1.0762,
      "step": 29
    },
    {
      "epoch": 1.2,
      "grad_norm": 4.179634094238281,
      "learning_rate": 3.756550564175727e-06,
      "loss": 1.1484,
      "step": 30
    },
    {
      "epoch": 1.24,
      "grad_norm": 3.223548412322998,
      "learning_rate": 3.4549150281252635e-06,
      "loss": 0.9036,
      "step": 31
    },
    {
      "epoch": 1.28,
      "grad_norm": 3.2801642417907715,
      "learning_rate": 3.1593772365766107e-06,
      "loss": 0.9443,
      "step": 32
    },
    {
      "epoch": 1.32,
      "grad_norm": 2.876748561859131,
      "learning_rate": 2.871103542174637e-06,
      "loss": 0.7505,
      "step": 33
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 2.8197476863861084,
      "learning_rate": 2.5912316294914232e-06,
      "loss": 0.688,
      "step": 34
    },
    {
      "epoch": 1.4,
      "grad_norm": 2.811995506286621,
      "learning_rate": 2.320866025105016e-06,
      "loss": 0.7581,
      "step": 35
    },
    {
      "epoch": 1.44,
      "grad_norm": 2.8211636543273926,
      "learning_rate": 2.061073738537635e-06,
      "loss": 0.656,
      "step": 36
    },
    {
      "epoch": 1.48,
      "grad_norm": 2.586003303527832,
      "learning_rate": 1.8128800512565514e-06,
      "loss": 0.7266,
      "step": 37
    },
    {
      "epoch": 1.52,
      "grad_norm": 2.7780256271362305,
      "learning_rate": 1.5772644703565564e-06,
      "loss": 0.7122,
      "step": 38
    },
    {
      "epoch": 1.56,
      "grad_norm": 3.0717930793762207,
      "learning_rate": 1.3551568628929434e-06,
      "loss": 0.8303,
      "step": 39
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.8177034854888916,
      "learning_rate": 1.1474337861210543e-06,
      "loss": 0.7646,
      "step": 40
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 2.5809686183929443,
      "learning_rate": 9.549150281252633e-07,
      "loss": 0.6765,
      "step": 41
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 2.680948257446289,
      "learning_rate": 7.783603724899258e-07,
      "loss": 0.7625,
      "step": 42
    },
    {
      "epoch": 1.72,
      "grad_norm": 2.7830235958099365,
      "learning_rate": 6.184665997806832e-07,
      "loss": 0.6846,
      "step": 43
    },
    {
      "epoch": 1.76,
      "grad_norm": 2.9110989570617676,
      "learning_rate": 4.758647376699033e-07,
      "loss": 0.7314,
      "step": 44
    },
    {
      "epoch": 1.8,
      "grad_norm": 2.6902732849121094,
      "learning_rate": 3.511175705587433e-07,
      "loss": 0.748,
      "step": 45
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 3.2946643829345703,
      "learning_rate": 2.447174185242324e-07,
      "loss": 0.8599,
      "step": 46
    },
    {
      "epoch": 1.88,
      "grad_norm": 2.7693867683410645,
      "learning_rate": 1.5708419435684463e-07,
      "loss": 0.7791,
      "step": 47
    },
    {
      "epoch": 1.92,
      "grad_norm": 2.958845376968384,
      "learning_rate": 8.856374635655696e-08,
      "loss": 0.7798,
      "step": 48
    },
    {
      "epoch": 1.96,
      "grad_norm": 3.4218244552612305,
      "learning_rate": 3.9426493427611177e-08,
      "loss": 0.8979,
      "step": 49
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.060529947280884,
      "learning_rate": 9.866357858642206e-09,
      "loss": 0.5559,
      "step": 50
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.484375,
      "eval_runtime": 0.5483,
      "eval_samples_per_second": 1.824,
      "eval_steps_per_second": 1.824,
      "step": 50
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8079956500283392.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}