{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 64,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03125,
      "grad_norm": 0.042211709723423994,
      "learning_rate": 7.142857142857143e-06,
      "loss": 0.1826,
      "step": 1
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.040523357558985305,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.1697,
      "step": 2
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.04167011745239068,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.1922,
      "step": 3
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.04332694019851011,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.1826,
      "step": 4
    },
    {
      "epoch": 0.15625,
      "grad_norm": 0.04289781626308719,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.1933,
      "step": 5
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.048927401557601384,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.1792,
      "step": 6
    },
    {
      "epoch": 0.21875,
      "grad_norm": 0.04917933368077925,
      "learning_rate": 5e-05,
      "loss": 0.1785,
      "step": 7
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.042531202393428634,
      "learning_rate": 4.996203791083291e-05,
      "loss": 0.1782,
      "step": 8
    },
    {
      "epoch": 0.28125,
      "grad_norm": 0.03423472324986091,
      "learning_rate": 4.984826693294874e-05,
      "loss": 0.1553,
      "step": 9
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.02536269873026519,
      "learning_rate": 4.965903258506806e-05,
      "loss": 0.162,
      "step": 10
    },
    {
      "epoch": 0.34375,
      "grad_norm": 0.03414579032479303,
      "learning_rate": 4.9394909565685894e-05,
      "loss": 0.1805,
      "step": 11
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.04499054740361273,
      "learning_rate": 4.905670000773126e-05,
      "loss": 0.1633,
      "step": 12
    },
    {
      "epoch": 0.40625,
      "grad_norm": 0.054239841431854424,
      "learning_rate": 4.864543104251587e-05,
      "loss": 0.1632,
      "step": 13
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.04808977247007115,
      "learning_rate": 4.8162351680370044e-05,
      "loss": 0.1491,
      "step": 14
    },
    {
      "epoch": 0.46875,
      "grad_norm": 0.04220777198225847,
      "learning_rate": 4.760892901743944e-05,
      "loss": 0.1504,
      "step": 15
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.02944080547232296,
      "learning_rate": 4.698684378016222e-05,
      "loss": 0.1476,
      "step": 16
    },
    {
      "epoch": 0.53125,
      "grad_norm": 0.022946753850242432,
      "learning_rate": 4.629798522095818e-05,
      "loss": 0.1398,
      "step": 17
    },
    {
      "epoch": 0.5625,
      "grad_norm": 0.018713023972775928,
      "learning_rate": 4.554444538063113e-05,
      "loss": 0.1586,
      "step": 18
    },
    {
      "epoch": 0.59375,
      "grad_norm": 0.01989174806605767,
      "learning_rate": 4.4728512734909844e-05,
      "loss": 0.1378,
      "step": 19
    },
    {
      "epoch": 0.625,
      "grad_norm": 0.023054897121146254,
      "learning_rate": 4.385266524442241e-05,
      "loss": 0.1334,
      "step": 20
    },
    {
      "epoch": 0.65625,
      "grad_norm": 0.02399880426486958,
      "learning_rate": 4.2919562829211283e-05,
      "loss": 0.1246,
      "step": 21
    },
    {
      "epoch": 0.6875,
      "grad_norm": 0.027211398286697646,
      "learning_rate": 4.193203929064353e-05,
      "loss": 0.142,
      "step": 22
    },
    {
      "epoch": 0.71875,
      "grad_norm": 0.02336043662637302,
      "learning_rate": 4.089309370524921e-05,
      "loss": 0.1173,
      "step": 23
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.025261125777024232,
      "learning_rate": 3.9805881316624506e-05,
      "loss": 0.1259,
      "step": 24
    },
    {
      "epoch": 0.78125,
      "grad_norm": 0.02143183000772084,
      "learning_rate": 3.867370395306068e-05,
      "loss": 0.1205,
      "step": 25
    },
    {
      "epoch": 0.8125,
      "grad_norm": 0.022292087028719917,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.1155,
      "step": 26
    },
    {
      "epoch": 0.84375,
      "grad_norm": 0.019679819265901136,
      "learning_rate": 3.628833395777224e-05,
      "loss": 0.1232,
      "step": 27
    },
    {
      "epoch": 0.875,
      "grad_norm": 0.020714109057838017,
      "learning_rate": 3.504238561632424e-05,
      "loss": 0.1168,
      "step": 28
    },
    {
      "epoch": 0.90625,
      "grad_norm": 0.019403140215305675,
      "learning_rate": 3.376593887981887e-05,
      "loss": 0.1025,
      "step": 29
    },
    {
      "epoch": 0.9375,
      "grad_norm": 0.018873000340986552,
      "learning_rate": 3.246287027504237e-05,
      "loss": 0.1075,
      "step": 30
    },
    {
      "epoch": 0.96875,
      "grad_norm": 0.019583048283476286,
      "learning_rate": 3.1137137178519985e-05,
      "loss": 0.0966,
      "step": 31
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.020023991728142915,
      "learning_rate": 2.9792765798093465e-05,
      "loss": 0.1077,
      "step": 32
    },
    {
      "epoch": 1.03125,
      "grad_norm": 0.02014336988909588,
      "learning_rate": 2.8433838945460205e-05,
      "loss": 0.114,
      "step": 33
    },
    {
      "epoch": 1.0625,
      "grad_norm": 0.018645793178802845,
      "learning_rate": 2.7064483636808313e-05,
      "loss": 0.1129,
      "step": 34
    },
    {
      "epoch": 1.09375,
      "grad_norm": 0.017769270453618723,
      "learning_rate": 2.5688858559204053e-05,
      "loss": 0.0885,
      "step": 35
    },
    {
      "epoch": 1.125,
      "grad_norm": 0.018237269189223717,
      "learning_rate": 2.4311141440795953e-05,
      "loss": 0.1085,
      "step": 36
    },
    {
      "epoch": 1.15625,
      "grad_norm": 0.019420564407489134,
      "learning_rate": 2.2935516363191693e-05,
      "loss": 0.1009,
      "step": 37
    },
    {
      "epoch": 1.1875,
      "grad_norm": 0.01818503869300628,
      "learning_rate": 2.1566161054539798e-05,
      "loss": 0.0909,
      "step": 38
    },
    {
      "epoch": 1.21875,
      "grad_norm": 0.01977177642557231,
      "learning_rate": 2.0207234201906547e-05,
      "loss": 0.0993,
      "step": 39
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.018860196742925606,
      "learning_rate": 1.8862862821480025e-05,
      "loss": 0.0881,
      "step": 40
    },
    {
      "epoch": 1.28125,
      "grad_norm": 0.01789538986871461,
      "learning_rate": 1.7537129724957642e-05,
      "loss": 0.1031,
      "step": 41
    },
    {
      "epoch": 1.3125,
      "grad_norm": 0.019440146647284384,
      "learning_rate": 1.6234061120181142e-05,
      "loss": 0.1011,
      "step": 42
    },
    {
      "epoch": 1.34375,
      "grad_norm": 0.01773027173909912,
      "learning_rate": 1.495761438367577e-05,
      "loss": 0.0873,
      "step": 43
    },
    {
      "epoch": 1.375,
      "grad_norm": 0.018053120975854698,
      "learning_rate": 1.3711666042227772e-05,
      "loss": 0.0942,
      "step": 44
    },
    {
      "epoch": 1.40625,
      "grad_norm": 0.01599530366821666,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.0864,
      "step": 45
    },
    {
      "epoch": 1.4375,
      "grad_norm": 0.018506143523795423,
      "learning_rate": 1.1326296046939333e-05,
      "loss": 0.0897,
      "step": 46
    },
    {
      "epoch": 1.46875,
      "grad_norm": 0.019285636800618775,
      "learning_rate": 1.0194118683375503e-05,
      "loss": 0.0945,
      "step": 47
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.01851733435975437,
      "learning_rate": 9.106906294750805e-06,
      "loss": 0.089,
      "step": 48
    },
    {
      "epoch": 1.53125,
      "grad_norm": 0.01615116629140626,
      "learning_rate": 8.067960709356478e-06,
      "loss": 0.0829,
      "step": 49
    },
    {
      "epoch": 1.5625,
      "grad_norm": 0.01999530228835859,
      "learning_rate": 7.080437170788723e-06,
      "loss": 0.0806,
      "step": 50
    },
    {
      "epoch": 1.59375,
      "grad_norm": 0.018698060874040544,
      "learning_rate": 6.147334755577596e-06,
      "loss": 0.0745,
      "step": 51
    },
    {
      "epoch": 1.625,
      "grad_norm": 0.020647083613217352,
      "learning_rate": 5.271487265090163e-06,
      "loss": 0.0762,
      "step": 52
    },
    {
      "epoch": 1.65625,
      "grad_norm": 0.018963763952432634,
      "learning_rate": 4.4555546193688735e-06,
      "loss": 0.0767,
      "step": 53
    },
    {
      "epoch": 1.6875,
      "grad_norm": 0.016352645860581026,
      "learning_rate": 3.7020147790418263e-06,
      "loss": 0.0886,
      "step": 54
    },
    {
      "epoch": 1.71875,
      "grad_norm": 0.018189380607389477,
      "learning_rate": 3.013156219837776e-06,
      "loss": 0.0872,
      "step": 55
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.016586579136002214,
      "learning_rate": 2.391070982560564e-06,
      "loss": 0.0748,
      "step": 56
    },
    {
      "epoch": 1.78125,
      "grad_norm": 0.017951491429409636,
      "learning_rate": 1.837648319629956e-06,
      "loss": 0.111,
      "step": 57
    },
    {
      "epoch": 1.8125,
      "grad_norm": 0.016524711157425227,
      "learning_rate": 1.3545689574841342e-06,
      "loss": 0.0906,
      "step": 58
    },
    {
      "epoch": 1.84375,
      "grad_norm": 0.016444127025366004,
      "learning_rate": 9.432999922687396e-07,
      "loss": 0.0817,
      "step": 59
    },
    {
      "epoch": 1.875,
      "grad_norm": 0.01799234707191234,
      "learning_rate": 6.050904343141095e-07,
      "loss": 0.0969,
      "step": 60
    },
    {
      "epoch": 1.90625,
      "grad_norm": 0.020873493821065264,
      "learning_rate": 3.4096741493194197e-07,
      "loss": 0.0921,
      "step": 61
    },
    {
      "epoch": 1.9375,
      "grad_norm": 0.016975329426932043,
      "learning_rate": 1.517330670512629e-07,
      "loss": 0.0818,
      "step": 62
    },
    {
      "epoch": 1.96875,
      "grad_norm": 0.016262557073136383,
      "learning_rate": 3.796208916709565e-08,
      "loss": 0.0846,
      "step": 63
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.016105491523942778,
      "learning_rate": 0.0,
      "loss": 0.0837,
      "step": 64
    },
    {
      "epoch": 2.0,
      "step": 64,
      "total_flos": 570726028935168.0,
      "train_loss": 0.11890232225414366,
      "train_runtime": 1057.719,
      "train_samples_per_second": 0.473,
      "train_steps_per_second": 0.061
    }
  ],
  "logging_steps": 1,
  "max_steps": 64,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 570726028935168.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}