{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16796136888515642,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003359227377703128,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 1.9546,
      "step": 1
    },
    {
      "epoch": 0.003359227377703128,
      "eval_loss": NaN,
      "eval_runtime": 61.1706,
      "eval_samples_per_second": 8.207,
      "eval_steps_per_second": 4.103,
      "step": 1
    },
    {
      "epoch": 0.006718454755406256,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 2.0227,
      "step": 2
    },
    {
      "epoch": 0.010077682133109386,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 4.1069,
      "step": 3
    },
    {
      "epoch": 0.013436909510812512,
      "grad_norm": 0.3233916461467743,
      "learning_rate": 4e-05,
      "loss": 1.5745,
      "step": 4
    },
    {
      "epoch": 0.016796136888515643,
      "grad_norm": 0.32183876633644104,
      "learning_rate": 5e-05,
      "loss": 1.5581,
      "step": 5
    },
    {
      "epoch": 0.02015536426621877,
      "grad_norm": 0.33219215273857117,
      "learning_rate": 6e-05,
      "loss": 1.5906,
      "step": 6
    },
    {
      "epoch": 0.023514591643921896,
      "grad_norm": NaN,
      "learning_rate": 7e-05,
      "loss": 2.2802,
      "step": 7
    },
    {
      "epoch": 0.026873819021625025,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 1.7134,
      "step": 8
    },
    {
      "epoch": 0.030233046399328153,
      "grad_norm": 0.37869352102279663,
      "learning_rate": 9e-05,
      "loss": 1.5389,
      "step": 9
    },
    {
      "epoch": 0.033592273777031285,
      "grad_norm": 0.414662629365921,
      "learning_rate": 0.0001,
      "loss": 1.5451,
      "step": 10
    },
    {
      "epoch": 0.03695150115473441,
      "grad_norm": 0.5286617279052734,
      "learning_rate": 9.98458666866564e-05,
      "loss": 1.508,
      "step": 11
    },
    {
      "epoch": 0.04031072853243754,
      "grad_norm": 0.571130633354187,
      "learning_rate": 9.938441702975689e-05,
      "loss": 1.4923,
      "step": 12
    },
    {
      "epoch": 0.04366995591014067,
      "grad_norm": 0.5468776226043701,
      "learning_rate": 9.861849601988383e-05,
      "loss": 1.4145,
      "step": 13
    },
    {
      "epoch": 0.04366995591014067,
      "eval_loss": NaN,
      "eval_runtime": 21.2042,
      "eval_samples_per_second": 23.675,
      "eval_steps_per_second": 11.837,
      "step": 13
    },
    {
      "epoch": 0.04702918328784379,
      "grad_norm": 0.5036017894744873,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.3422,
      "step": 14
    },
    {
      "epoch": 0.050388410665546925,
      "grad_norm": 0.429851233959198,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2768,
      "step": 15
    },
    {
      "epoch": 0.05374763804325005,
      "grad_norm": 0.43012356758117676,
      "learning_rate": 9.45503262094184e-05,
      "loss": 1.2485,
      "step": 16
    },
    {
      "epoch": 0.05710686542095318,
      "grad_norm": 0.43632248044013977,
      "learning_rate": 9.263200821770461e-05,
      "loss": 1.1458,
      "step": 17
    },
    {
      "epoch": 0.06046609279865631,
      "grad_norm": 0.4527662992477417,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.1514,
      "step": 18
    },
    {
      "epoch": 0.06382532017635943,
      "grad_norm": NaN,
      "learning_rate": 8.802029828000156e-05,
      "loss": 1.8809,
      "step": 19
    },
    {
      "epoch": 0.06718454755406257,
      "grad_norm": 0.43924033641815186,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.1503,
      "step": 20
    },
    {
      "epoch": 0.0705437749317657,
      "grad_norm": NaN,
      "learning_rate": 8.247240241650918e-05,
      "loss": 1.9837,
      "step": 21
    },
    {
      "epoch": 0.07390300230946882,
      "grad_norm": NaN,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.4764,
      "step": 22
    },
    {
      "epoch": 0.07726222968717195,
      "grad_norm": 0.39424705505371094,
      "learning_rate": 7.612492823579745e-05,
      "loss": 1.1039,
      "step": 23
    },
    {
      "epoch": 0.08062145706487509,
      "grad_norm": NaN,
      "learning_rate": 7.269952498697734e-05,
      "loss": 1.4906,
      "step": 24
    },
    {
      "epoch": 0.08398068444257821,
      "grad_norm": 0.34690049290657043,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.0607,
      "step": 25
    },
    {
      "epoch": 0.08733991182028134,
      "grad_norm": 0.34878969192504883,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.0336,
      "step": 26
    },
    {
      "epoch": 0.08733991182028134,
      "eval_loss": NaN,
      "eval_runtime": 21.1636,
      "eval_samples_per_second": 23.72,
      "eval_steps_per_second": 11.86,
      "step": 26
    },
    {
      "epoch": 0.09069913919798446,
      "grad_norm": 0.3356166183948517,
      "learning_rate": 6.167226819279528e-05,
      "loss": 1.0614,
      "step": 27
    },
    {
      "epoch": 0.09405836657568759,
      "grad_norm": NaN,
      "learning_rate": 5.782172325201155e-05,
      "loss": 1.5224,
      "step": 28
    },
    {
      "epoch": 0.09741759395339072,
      "grad_norm": NaN,
      "learning_rate": 5.392295478639225e-05,
      "loss": 1.774,
      "step": 29
    },
    {
      "epoch": 0.10077682133109385,
      "grad_norm": 0.33320266008377075,
      "learning_rate": 5e-05,
      "loss": 1.0382,
      "step": 30
    },
    {
      "epoch": 0.10413604870879697,
      "grad_norm": 0.3378564417362213,
      "learning_rate": 4.607704521360776e-05,
      "loss": 0.9827,
      "step": 31
    },
    {
      "epoch": 0.1074952760865001,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.4901,
      "step": 32
    },
    {
      "epoch": 0.11085450346420324,
      "grad_norm": 0.3424948453903198,
      "learning_rate": 3.832773180720475e-05,
      "loss": 0.9419,
      "step": 33
    },
    {
      "epoch": 0.11421373084190636,
      "grad_norm": 0.3185945749282837,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.9325,
      "step": 34
    },
    {
      "epoch": 0.11757295821960949,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.1159,
      "step": 35
    },
    {
      "epoch": 0.12093218559731261,
      "grad_norm": 0.3276839554309845,
      "learning_rate": 2.7300475013022663e-05,
      "loss": 0.9843,
      "step": 36
    },
    {
      "epoch": 0.12429141297501575,
      "grad_norm": NaN,
      "learning_rate": 2.3875071764202563e-05,
      "loss": 0.9924,
      "step": 37
    },
    {
      "epoch": 0.12765064035271886,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.3187,
      "step": 38
    },
    {
      "epoch": 0.131009867730422,
      "grad_norm": 0.31996309757232666,
      "learning_rate": 1.7527597583490822e-05,
      "loss": 0.9506,
      "step": 39
    },
    {
      "epoch": 0.131009867730422,
      "eval_loss": NaN,
      "eval_runtime": 21.1859,
      "eval_samples_per_second": 23.695,
      "eval_steps_per_second": 11.847,
      "step": 39
    },
    {
      "epoch": 0.13436909510812514,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.2932,
      "step": 40
    },
    {
      "epoch": 0.13772832248582825,
      "grad_norm": NaN,
      "learning_rate": 1.1979701719998453e-05,
      "loss": 1.5242,
      "step": 41
    },
    {
      "epoch": 0.1410875498635314,
      "grad_norm": 0.3238716125488281,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9333,
      "step": 42
    },
    {
      "epoch": 0.1444467772412345,
      "grad_norm": 0.3042464852333069,
      "learning_rate": 7.367991782295391e-06,
      "loss": 0.9319,
      "step": 43
    },
    {
      "epoch": 0.14780600461893764,
      "grad_norm": 0.31937065720558167,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.8955,
      "step": 44
    },
    {
      "epoch": 0.15116523199664078,
      "grad_norm": 0.30120527744293213,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.9155,
      "step": 45
    },
    {
      "epoch": 0.1545244593743439,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 1.735,
      "step": 46
    },
    {
      "epoch": 0.15788368675204703,
      "grad_norm": NaN,
      "learning_rate": 1.3815039801161721e-06,
      "loss": 1.5965,
      "step": 47
    },
    {
      "epoch": 0.16124291412975017,
      "grad_norm": 0.3180822730064392,
      "learning_rate": 6.15582970243117e-07,
      "loss": 0.9638,
      "step": 48
    },
    {
      "epoch": 0.16460214150745328,
      "grad_norm": NaN,
      "learning_rate": 1.5413331334360182e-07,
      "loss": 0.9644,
      "step": 49
    },
    {
      "epoch": 0.16796136888515642,
      "grad_norm": 0.3325708508491516,
      "learning_rate": 0.0,
      "loss": 0.9511,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.57265690411008e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}