{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 2.0897409915924072,
      "learning_rate": 0.00015996052482925854,
      "loss": 1.2438,
      "step": 1
    },
    {
      "epoch": 0.04,
      "grad_norm": 28.813220977783203,
      "learning_rate": 0.00015984213827426174,
      "loss": 3.7464,
      "step": 2
    },
    {
      "epoch": 0.06,
      "grad_norm": 16.25991439819336,
      "learning_rate": 0.0001596449571682464,
      "loss": 2.9219,
      "step": 3
    },
    {
      "epoch": 0.08,
      "grad_norm": 5.324892520904541,
      "learning_rate": 0.00015936917610515826,
      "loss": 2.1242,
      "step": 4
    },
    {
      "epoch": 0.1,
      "grad_norm": 2.8375790119171143,
      "learning_rate": 0.00015901506724761103,
      "loss": 1.7799,
      "step": 5
    },
    {
      "epoch": 0.12,
      "grad_norm": 4.01439905166626,
      "learning_rate": 0.00015858298005829512,
      "loss": 1.6514,
      "step": 6
    },
    {
      "epoch": 0.14,
      "grad_norm": 2.095858335494995,
      "learning_rate": 0.0001580733409550998,
      "loss": 1.5758,
      "step": 7
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.694789171218872,
      "learning_rate": 0.0001574866528902905,
      "loss": 1.4651,
      "step": 8
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.4686285257339478,
      "learning_rate": 0.00015682349485415545,
      "loss": 1.3782,
      "step": 9
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.9562129378318787,
      "learning_rate": 0.0001560845213036123,
      "loss": 1.353,
      "step": 10
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.4398468732833862,
      "learning_rate": 0.00015527046151633805,
      "loss": 1.3325,
      "step": 11
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.827878475189209,
      "learning_rate": 0.00015438211887106013,
      "loss": 1.2997,
      "step": 12
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.015064001083374,
      "learning_rate": 0.0001534203700547185,
      "loss": 1.2664,
      "step": 13
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.680793821811676,
      "learning_rate": 0.00015238616419728157,
      "loss": 1.239,
      "step": 14
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.9654543995857239,
      "learning_rate": 0.00015128052193506944,
      "loss": 1.2528,
      "step": 15
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.7509903907775879,
      "learning_rate": 0.0001501045344035091,
      "loss": 1.2447,
      "step": 16
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.6938178539276123,
      "learning_rate": 0.0001488593621603155,
      "loss": 1.2231,
      "step": 17
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.6297674179077148,
      "learning_rate": 0.00014754623404016122,
      "loss": 1.2305,
      "step": 18
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.535707950592041,
      "learning_rate": 0.00014616644594196495,
      "loss": 1.2339,
      "step": 19
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.5825291275978088,
      "learning_rate": 0.00014472135954999581,
      "loss": 1.1903,
      "step": 20
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.36997389793395996,
      "learning_rate": 0.00014321240099005524,
      "loss": 1.1979,
      "step": 21
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.4852772355079651,
      "learning_rate": 0.00014164105942206316,
      "loss": 1.1951,
      "step": 22
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.43263790011405945,
      "learning_rate": 0.00014000888557043678,
      "loss": 1.1632,
      "step": 23
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.39633846282958984,
      "learning_rate": 0.00013831749019371293,
      "loss": 1.1631,
      "step": 24
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.41002726554870605,
      "learning_rate": 0.00013656854249492382,
      "loss": 1.1886,
      "step": 25
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.39650410413742065,
      "learning_rate": 0.00013476376847429511,
      "loss": 1.202,
      "step": 26
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.3824397921562195,
      "learning_rate": 0.00013290494922589216,
      "loss": 1.1832,
      "step": 27
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.3212684094905853,
      "learning_rate": 0.0001309939191798952,
      "loss": 1.1466,
      "step": 28
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.32189854979515076,
      "learning_rate": 0.00012903256429223813,
      "loss": 1.1975,
      "step": 29
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3070578873157501,
      "learning_rate": 0.00012702282018339786,
      "loss": 1.154,
      "step": 30
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.25685596466064453,
      "learning_rate": 0.00012496667022817044,
      "loss": 1.1357,
      "step": 31
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.2539421021938324,
      "learning_rate": 0.00012286614359831974,
      "loss": 1.158,
      "step": 32
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.2875991761684418,
      "learning_rate": 0.00012072331326002972,
      "loss": 1.1849,
      "step": 33
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.2683248221874237,
      "learning_rate": 0.00011854029392813723,
      "loss": 1.1935,
      "step": 34
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.2622566819190979,
      "learning_rate": 0.00011631923997916375,
      "loss": 1.1624,
      "step": 35
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.2862881124019623,
      "learning_rate": 0.00011406234332520582,
      "loss": 1.1854,
      "step": 36
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.24599239230155945,
      "learning_rate": 0.00011177183125078245,
      "loss": 1.1597,
      "step": 37
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.23713542520999908,
      "learning_rate": 0.00010944996421477426,
      "loss": 1.125,
      "step": 38
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.26411688327789307,
      "learning_rate": 0.00010709903361962333,
      "loss": 1.1144,
      "step": 39
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.24425670504570007,
      "learning_rate": 0.0001047213595499958,
      "loss": 1.1443,
      "step": 40
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.26452597975730896,
      "learning_rate": 0.00010231928848313836,
      "loss": 1.1376,
      "step": 41
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.21576781570911407,
      "learning_rate": 9.989519097318841e-05,
      "loss": 1.1616,
      "step": 42
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.2854762375354767,
      "learning_rate": 9.745145931172342e-05,
      "loss": 1.1511,
      "step": 43
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.2194770872592926,
      "learning_rate": 9.4990505166858e-05,
      "loss": 1.1385,
      "step": 44
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.22979624569416046,
      "learning_rate": 9.251475720321848e-05,
      "loss": 1.1429,
      "step": 45
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.22235210239887238,
      "learning_rate": 9.002665868514435e-05,
      "loss": 1.119,
      "step": 46
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.22438690066337585,
      "learning_rate": 8.752866506548117e-05,
      "loss": 1.1642,
      "step": 47
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.18937288224697113,
      "learning_rate": 8.502324156234508e-05,
      "loss": 1.1281,
      "step": 48
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.22655418515205383,
      "learning_rate": 8.251286072625027e-05,
      "loss": 1.1399,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.21689347922801971,
      "learning_rate": 8e-05,
      "loss": 1.0937,
      "step": 50
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.370595782995224,
      "learning_rate": 7.748713927374974e-05,
      "loss": 1.0383,
      "step": 51
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.45078134536743164,
      "learning_rate": 7.497675843765493e-05,
      "loss": 1.1376,
      "step": 52
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.3670865297317505,
      "learning_rate": 7.247133493451886e-05,
      "loss": 1.1206,
      "step": 53
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.3233189582824707,
      "learning_rate": 6.997334131485565e-05,
      "loss": 1.1502,
      "step": 54
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.399816632270813,
      "learning_rate": 6.748524279678152e-05,
      "loss": 1.1279,
      "step": 55
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.33596694469451904,
      "learning_rate": 6.500949483314202e-05,
      "loss": 1.1218,
      "step": 56
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.5186057090759277,
      "learning_rate": 6.254854068827662e-05,
      "loss": 1.1378,
      "step": 57
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.2955310344696045,
      "learning_rate": 6.0104809026811634e-05,
      "loss": 1.1156,
      "step": 58
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.5075625777244568,
      "learning_rate": 5.7680711516861674e-05,
      "loss": 1.079,
      "step": 59
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.25788846611976624,
      "learning_rate": 5.5278640450004216e-05,
      "loss": 1.078,
      "step": 60
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.4179430603981018,
      "learning_rate": 5.2900966380376693e-05,
      "loss": 1.0959,
      "step": 61
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.34371474385261536,
      "learning_rate": 5.055003578522577e-05,
      "loss": 1.0807,
      "step": 62
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.2947935461997986,
      "learning_rate": 4.822816874921756e-05,
      "loss": 1.0645,
      "step": 63
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.27775266766548157,
      "learning_rate": 4.593765667479419e-05,
      "loss": 1.0591,
      "step": 64
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.23427054286003113,
      "learning_rate": 4.3680760020836266e-05,
      "loss": 1.0848,
      "step": 65
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.26551228761672974,
      "learning_rate": 4.145970607186277e-05,
      "loss": 1.0722,
      "step": 66
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.20378205180168152,
      "learning_rate": 3.92766867399703e-05,
      "loss": 1.0654,
      "step": 67
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.3097435235977173,
      "learning_rate": 3.7133856401680256e-05,
      "loss": 1.0786,
      "step": 68
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.1919064074754715,
      "learning_rate": 3.5033329771829576e-05,
      "loss": 1.0804,
      "step": 69
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.19627317786216736,
      "learning_rate": 3.297717981660216e-05,
      "loss": 1.0532,
      "step": 70
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.22595791518688202,
      "learning_rate": 3.09674357077619e-05,
      "loss": 1.0669,
      "step": 71
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.20693820714950562,
      "learning_rate": 2.9006080820104823e-05,
      "loss": 1.0586,
      "step": 72
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.21305669844150543,
      "learning_rate": 2.7095050774107867e-05,
      "loss": 1.0425,
      "step": 73
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.19866228103637695,
      "learning_rate": 2.5236231525704902e-05,
      "loss": 1.0439,
      "step": 74
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.1801978200674057,
      "learning_rate": 2.3431457505076205e-05,
      "loss": 1.067,
      "step": 75
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.19466304779052734,
      "learning_rate": 2.1682509806287094e-05,
      "loss": 1.0777,
      "step": 76
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.23117047548294067,
      "learning_rate": 1.9991114429563236e-05,
      "loss": 1.064,
      "step": 77
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.1913105994462967,
      "learning_rate": 1.835894057793687e-05,
      "loss": 1.0343,
      "step": 78
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.17815832793712616,
      "learning_rate": 1.678759900994477e-05,
      "loss": 1.0886,
      "step": 79
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.20096604526042938,
      "learning_rate": 1.5278640450004213e-05,
      "loss": 1.0535,
      "step": 80
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.18867887556552887,
      "learning_rate": 1.3833554058035045e-05,
      "loss": 1.0352,
      "step": 81
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.1709662228822708,
      "learning_rate": 1.2453765959838813e-05,
      "loss": 1.0571,
      "step": 82
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.17397433519363403,
      "learning_rate": 1.1140637839684519e-05,
      "loss": 1.0827,
      "step": 83
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.1669914424419403,
      "learning_rate": 9.895465596490931e-06,
      "loss": 1.0925,
      "step": 84
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.1735496073961258,
      "learning_rate": 8.719478064930578e-06,
      "loss": 1.0733,
      "step": 85
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.17620506882667542,
      "learning_rate": 7.613835802718452e-06,
      "loss": 1.0804,
      "step": 86
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.14163199067115784,
      "learning_rate": 6.579629945281509e-06,
      "loss": 1.0658,
      "step": 87
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.13924406468868256,
      "learning_rate": 5.6178811289398925e-06,
      "loss": 1.0417,
      "step": 88
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.1430363655090332,
      "learning_rate": 4.729538483661964e-06,
      "loss": 1.0325,
      "step": 89
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.1582486629486084,
      "learning_rate": 3.915478696387718e-06,
      "loss": 1.0589,
      "step": 90
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.1521899402141571,
      "learning_rate": 3.176505145844555e-06,
      "loss": 1.0562,
      "step": 91
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.1510230004787445,
      "learning_rate": 2.513347109709514e-06,
      "loss": 1.0795,
      "step": 92
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.14750948548316956,
      "learning_rate": 1.9266590449002052e-06,
      "loss": 1.0656,
      "step": 93
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.13227519392967224,
      "learning_rate": 1.4170199417049114e-06,
      "loss": 1.0675,
      "step": 94
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.1416577845811844,
      "learning_rate": 9.849327523889873e-07,
      "loss": 1.065,
      "step": 95
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.1315535306930542,
      "learning_rate": 6.308238948417788e-07,
      "loss": 1.0449,
      "step": 96
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.1372697800397873,
      "learning_rate": 3.550428317536003e-07,
      "loss": 1.0836,
      "step": 97
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.1258520931005478,
      "learning_rate": 1.578617257382753e-07,
      "loss": 1.0578,
      "step": 98
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.12827666103839874,
      "learning_rate": 3.9475170741472005e-08,
      "loss": 1.0651,
      "step": 99
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.13206015527248383,
      "learning_rate": 0.0,
      "loss": 1.0265,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.263464103047594e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}