{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 10.0,
  "global_step": 1388,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0004999359657561555,
      "loss": 0.5112,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004997438958276968,
      "loss": 0.2283,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004994238886070454,
      "loss": 0.2077,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0004989761080255641,
      "loss": 0.2174,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0004984007834695806,
      "loss": 0.1994,
      "step": 50
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0004976982096628782,
      "loss": 0.2143,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0004968687465157165,
      "loss": 0.2168,
      "step": 70
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0004959128189404589,
      "loss": 0.2175,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000494830916633901,
      "loss": 0.2134,
      "step": 90
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004936235938264118,
      "loss": 0.2064,
      "step": 100
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0004922914689980156,
      "loss": 0.2032,
      "step": 110
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0004908352245615613,
      "loss": 0.2017,
      "step": 120
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0004892556065131395,
      "loss": 0.2127,
      "step": 130
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0004875534240499285,
      "loss": 0.2074,
      "step": 140
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00048572954915566393,
      "loss": 0.2013,
      "step": 150
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0004837849161539432,
      "loss": 0.2188,
      "step": 160
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00048172052122959707,
      "loss": 0.1919,
      "step": 170
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0004795374219183694,
      "loss": 0.1966,
      "step": 180
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0004772367365651691,
      "loss": 0.2088,
      "step": 190
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0004748196437511716,
      "loss": 0.2163,
      "step": 200
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00047228738169006204,
      "loss": 0.2013,
      "step": 210
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00046964124759373086,
      "loss": 0.194,
      "step": 220
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0004668825970077457,
      "loss": 0.2002,
      "step": 230
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0004640128431169411,
      "loss": 0.2095,
      "step": 240
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0004613362851634204,
      "loss": 0.1917,
      "step": 250
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0004582595315535216,
      "loss": 0.2054,
      "step": 260
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0004550760920106112,
      "loss": 0.1925,
      "step": 270
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00045178759732784093,
      "loss": 0.2157,
      "step": 280
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0004483957321153738,
      "loss": 0.2246,
      "step": 290
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0004449022339374027,
      "loss": 0.191,
      "step": 300
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00044130889242204133,
      "loss": 0.1808,
      "step": 310
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.000437617548344544,
      "loss": 0.2044,
      "step": 320
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.000433830092684325,
      "loss": 0.1829,
      "step": 330
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00042994846565625865,
      "loss": 0.2009,
      "step": 340
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0004259746557167581,
      "loss": 0.1963,
      "step": 350
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0004219106985451405,
      "loss": 0.1933,
      "step": 360
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00041775867600080184,
      "loss": 0.1948,
      "step": 370
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0004135207150567347,
      "loss": 0.2036,
      "step": 380
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00040919898670993484,
      "loss": 0.2048,
      "step": 390
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0004047957048692567,
      "loss": 0.1881,
      "step": 400
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00040031312522128507,
      "loss": 0.2143,
      "step": 410
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00039575354407480576,
      "loss": 0.1904,
      "step": 420
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00039111929718446654,
      "loss": 0.1989,
      "step": 430
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00038641275855423065,
      "loss": 0.1971,
      "step": 440
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003816363392212366,
      "loss": 0.1899,
      "step": 450
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00037679248602068657,
      "loss": 0.2091,
      "step": 460
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003718836803323966,
      "loss": 0.1943,
      "step": 470
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00036691243680964987,
      "loss": 0.1907,
      "step": 480
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003618813020910061,
      "loss": 0.1983,
      "step": 490
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00035679285349572454,
      "loss": 0.2036,
      "step": 500
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00035164969770347013,
      "loss": 0.1852,
      "step": 510
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003464544694189799,
      "loss": 0.1825,
      "step": 520
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003412098300223723,
      "loss": 0.2118,
      "step": 530
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003359184662057914,
      "loss": 0.19,
      "step": 540
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00033058308859708433,
      "loss": 0.1877,
      "step": 550
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003252064303712174,
      "loss": 0.1932,
      "step": 560
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.000319791245850142,
      "loss": 0.1983,
      "step": 570
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00031434030909182665,
      "loss": 0.2146,
      "step": 580
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00030885641246917994,
      "loss": 0.1957,
      "step": 590
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00030334236523959037,
      "loss": 0.1933,
      "step": 600
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00029780099210581685,
      "loss": 0.1981,
      "step": 610
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002922351317689671,
      "loss": 0.2009,
      "step": 620
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002866476354743054,
      "loss": 0.1849,
      "step": 630
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0002810413655506334,
      "loss": 0.2011,
      "step": 640
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00027541919394399395,
      "loss": 0.1786,
      "step": 650
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00026978400074644773,
      "loss": 0.1929,
      "step": 660
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002641386727206773,
      "loss": 0.2051,
      "step": 670
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0002584861018211739,
      "loss": 0.1916,
      "step": 680
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00025282918371276396,
      "loss": 0.1748,
      "step": 690
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002471708162872361,
      "loss": 0.1949,
      "step": 700
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00024151389817882616,
      "loss": 0.1775,
      "step": 710
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0002358613272793227,
      "loss": 0.1885,
      "step": 720
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002302159992535523,
      "loss": 0.1959,
      "step": 730
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00022458080605600617,
      "loss": 0.1842,
      "step": 740
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00021895863444936663,
      "loss": 0.1943,
      "step": 750
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.0002133523645256946,
      "loss": 0.1779,
      "step": 760
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002077648682310329,
      "loss": 0.178,
      "step": 770
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0002021990078941832,
      "loss": 0.1978,
      "step": 780
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00019665763476040964,
      "loss": 0.165,
      "step": 790
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00019114358753082,
      "loss": 0.1731,
      "step": 800
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001856596909081734,
      "loss": 0.1926,
      "step": 810
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001802087541498581,
      "loss": 0.1844,
      "step": 820
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001747935696287826,
      "loss": 0.1672,
      "step": 830
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0001694169114029157,
      "loss": 0.1857,
      "step": 840
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001640815337942086,
      "loss": 0.171,
      "step": 850
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00015879016997762767,
      "loss": 0.1693,
      "step": 860
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00015354553058102009,
      "loss": 0.175,
      "step": 870
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00014835030229652999,
      "loss": 0.1764,
      "step": 880
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00014320714650427552,
      "loss": 0.1803,
      "step": 890
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001381186979089939,
      "loss": 0.1916,
      "step": 900
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00013308756319035017,
      "loss": 0.1639,
      "step": 910
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0001281163196676035,
      "loss": 0.1835,
      "step": 920
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00012320751397931342,
      "loss": 0.1869,
      "step": 930
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001183636607787634,
      "loss": 0.1858,
      "step": 940
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00011358724144576943,
      "loss": 0.1773,
      "step": 950
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00010888070281553353,
      "loss": 0.177,
      "step": 960
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001042464559251943,
      "loss": 0.2,
      "step": 970
    },
    {
      "epoch": 1.41,
      "learning_rate": 9.9686874778715e-05,
      "loss": 0.1809,
      "step": 980
    },
    {
      "epoch": 1.43,
      "learning_rate": 9.520429513074334e-05,
      "loss": 0.1784,
      "step": 990
    },
    {
      "epoch": 1.44,
      "learning_rate": 9.080101329006519e-05,
      "loss": 0.1873,
      "step": 1000
    },
    {
      "epoch": 1.46,
      "learning_rate": 8.647928494326535e-05,
      "loss": 0.1681,
      "step": 1010
    },
    {
      "epoch": 1.47,
      "learning_rate": 8.224132399919812e-05,
      "loss": 0.1873,
      "step": 1020
    },
    {
      "epoch": 1.48,
      "learning_rate": 7.808930145485957e-05,
      "loss": 0.1849,
      "step": 1030
    },
    {
      "epoch": 1.5,
      "learning_rate": 7.402534428324195e-05,
      "loss": 0.2012,
      "step": 1040
    },
    {
      "epoch": 1.51,
      "learning_rate": 7.005153434374137e-05,
      "loss": 0.193,
      "step": 1050
    },
    {
      "epoch": 1.53,
      "learning_rate": 6.616990731567505e-05,
      "loss": 0.1779,
      "step": 1060
    },
    {
      "epoch": 1.54,
      "learning_rate": 6.238245165545606e-05,
      "loss": 0.1651,
      "step": 1070
    },
    {
      "epoch": 1.56,
      "learning_rate": 5.869110757795876e-05,
      "loss": 0.1727,
      "step": 1080
    },
    {
      "epoch": 1.57,
      "learning_rate": 5.509776606259731e-05,
      "loss": 0.1933,
      "step": 1090
    },
    {
      "epoch": 1.59,
      "learning_rate": 5.16042678846263e-05,
      "loss": 0.1969,
      "step": 1100
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.821240267215918e-05,
      "loss": 0.1819,
      "step": 1110
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.492390798938883e-05,
      "loss": 0.168,
      "step": 1120
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.174046844647844e-05,
      "loss": 0.1774,
      "step": 1130
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.8663714836579624e-05,
      "loss": 0.1836,
      "step": 1140
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.569522330041969e-05,
      "loss": 0.1664,
      "step": 1150
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.2836514518885615e-05,
      "loss": 0.1638,
      "step": 1160
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.008905293401895e-05,
      "loss": 0.2014,
      "step": 1170
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.7454245998820376e-05,
      "loss": 0.1918,
      "step": 1180
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.4933443456248068e-05,
      "loss": 0.1968,
      "step": 1190
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.2527936647779522e-05,
      "loss": 0.1702,
      "step": 1200
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.0238957851891172e-05,
      "loss": 0.1611,
      "step": 1210
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.8067679652793905e-05,
      "loss": 0.186,
      "step": 1220
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.6015214339749063e-05,
      "loss": 0.1758,
      "step": 1230
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.4082613337271234e-05,
      "loss": 0.1624,
      "step": 1240
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.2270866666511254e-05,
      "loss": 0.1843,
      "step": 1250
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.0580902438093925e-05,
      "loss": 0.191,
      "step": 1260
    },
    {
      "epoch": 1.83,
      "learning_rate": 9.013586376671157e-06,
      "loss": 0.1807,
      "step": 1270
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.569721377433808e-06,
      "loss": 0.1891,
      "step": 1280
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.250047094809447e-06,
      "loss": 0.1855,
      "step": 1290
    },
    {
      "epoch": 1.87,
      "learning_rate": 5.055239563556496e-06,
      "loss": 0.1924,
      "step": 1300
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.985910852449398e-06,
      "loss": 0.1995,
      "step": 1310
    },
    {
      "epoch": 1.9,
      "learning_rate": 3.0426087507316735e-06,
      "loss": 0.1938,
      "step": 1320
    },
    {
      "epoch": 1.92,
      "learning_rate": 2.2258164874976726e-06,
      "loss": 0.1813,
      "step": 1330
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.5359524841470907e-06,
      "loss": 0.1723,
      "step": 1340
    },
    {
      "epoch": 1.95,
      "learning_rate": 9.73370140038371e-07,
      "loss": 0.1804,
      "step": 1350
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.383576514515487e-07,
      "loss": 0.1838,
      "step": 1360
    },
    {
      "epoch": 1.97,
      "learning_rate": 2.3113786395281833e-07,
      "loss": 0.1753,
      "step": 1370
    },
    {
      "epoch": 1.99,
      "learning_rate": 5.1868158236434427e-08,
      "loss": 0.1876,
      "step": 1380
    },
    {
      "epoch": 2.0,
      "step": 1388,
      "total_flos": 3.2633842202899907e+18,
      "train_loss": 0.19332071949837873,
      "train_runtime": 22791.3585,
      "train_samples_per_second": 3.893,
      "train_steps_per_second": 0.061
    }
  ],
  "logging_steps": 10,
  "max_steps": 1388,
  "num_train_epochs": 2,
  "save_steps": 300,
  "total_flos": 3.2633842202899907e+18,
  "trial_name": null,
  "trial_params": null
}