{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.929260450160772,
  "eval_steps": 20,
  "global_step": 231,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 0.19299747049808502,
      "learning_rate": 2e-05,
      "loss": 1.3437,
      "step": 1
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.3747950792312622,
      "eval_runtime": 11.0278,
      "eval_samples_per_second": 235.858,
      "eval_steps_per_second": 59.032,
      "step": 1
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.19121848046779633,
      "learning_rate": 4e-05,
      "loss": 1.3845,
      "step": 2
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.19551381468772888,
      "learning_rate": 6e-05,
      "loss": 1.3774,
      "step": 3
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.19498884677886963,
      "learning_rate": 8e-05,
      "loss": 1.3771,
      "step": 4
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.24242694675922394,
      "learning_rate": 0.0001,
      "loss": 1.3558,
      "step": 5
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.1539306640625,
      "learning_rate": 0.00012,
      "loss": 1.2809,
      "step": 6
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.22252629697322845,
      "learning_rate": 0.00014,
      "loss": 1.2982,
      "step": 7
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.18322250247001648,
      "learning_rate": 0.00016,
      "loss": 1.2663,
      "step": 8
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.144040048122406,
      "learning_rate": 0.00018,
      "loss": 1.245,
      "step": 9
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.16758786141872406,
      "learning_rate": 0.0002,
      "loss": 1.2265,
      "step": 10
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.12311970442533493,
      "learning_rate": 0.00019999444309209432,
      "loss": 1.2582,
      "step": 11
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.1770094484090805,
      "learning_rate": 0.0001999777729859618,
      "loss": 1.2295,
      "step": 12
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.1003749668598175,
      "learning_rate": 0.00019994999153428737,
      "loss": 1.202,
      "step": 13
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.10201102495193481,
      "learning_rate": 0.00019991110182465032,
      "loss": 1.2693,
      "step": 14
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.10821792483329773,
      "learning_rate": 0.0001998611081791814,
      "loss": 1.2339,
      "step": 15
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0722450315952301,
      "learning_rate": 0.00019980001615408228,
      "loss": 1.2122,
      "step": 16
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.0798899456858635,
      "learning_rate": 0.00019972783253900808,
      "loss": 1.2107,
      "step": 17
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.06952076405286789,
      "learning_rate": 0.00019964456535631286,
      "loss": 1.2585,
      "step": 18
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.060726992785930634,
      "learning_rate": 0.00019955022386015792,
      "loss": 1.1975,
      "step": 19
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.06560595333576202,
      "learning_rate": 0.00019944481853548335,
      "loss": 1.2174,
      "step": 20
    },
    {
      "epoch": 0.26,
      "eval_loss": 1.2183723449707031,
      "eval_runtime": 11.1201,
      "eval_samples_per_second": 233.9,
      "eval_steps_per_second": 58.543,
      "step": 20
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.06686750054359436,
      "learning_rate": 0.00019932836109684286,
      "loss": 1.2287,
      "step": 21
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.05899977311491966,
      "learning_rate": 0.0001992008644871016,
      "loss": 1.177,
      "step": 22
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.06782848387956619,
      "learning_rate": 0.00019906234287599798,
      "loss": 1.248,
      "step": 23
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.07001505047082901,
      "learning_rate": 0.00019891281165856873,
      "loss": 1.2467,
      "step": 24
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.05859360471367836,
      "learning_rate": 0.00019875228745343794,
      "loss": 1.2126,
      "step": 25
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.06061583012342453,
      "learning_rate": 0.00019858078810097002,
      "loss": 1.2395,
      "step": 26
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.058314863592386246,
      "learning_rate": 0.00019839833266128724,
      "loss": 1.1868,
      "step": 27
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.05482524260878563,
      "learning_rate": 0.00019820494141215104,
      "loss": 1.1378,
      "step": 28
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.056380610913038254,
      "learning_rate": 0.00019800063584670863,
      "loss": 1.2303,
      "step": 29
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.05643482878804207,
      "learning_rate": 0.00019778543867110426,
      "loss": 1.2546,
      "step": 30
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.05201110243797302,
      "learning_rate": 0.00019755937380195568,
      "loss": 1.2279,
      "step": 31
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.0630900114774704,
      "learning_rate": 0.00019732246636369605,
      "loss": 1.1497,
      "step": 32
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.0517457090318203,
      "learning_rate": 0.0001970747426857817,
      "loss": 1.2043,
      "step": 33
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.05967947468161583,
      "learning_rate": 0.00019681623029976588,
      "loss": 1.1867,
      "step": 34
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.05957586690783501,
      "learning_rate": 0.00019654695793623907,
      "loss": 1.2171,
      "step": 35
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.05819874256849289,
      "learning_rate": 0.00019626695552163578,
      "loss": 1.2242,
      "step": 36
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.05496300384402275,
      "learning_rate": 0.0001959762541749086,
      "loss": 1.2311,
      "step": 37
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.05849285423755646,
      "learning_rate": 0.00019567488620406983,
      "loss": 1.2037,
      "step": 38
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.05827626585960388,
      "learning_rate": 0.00019536288510260056,
      "loss": 1.2251,
      "step": 39
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.05698635056614876,
      "learning_rate": 0.00019504028554572864,
      "loss": 1.2468,
      "step": 40
    },
    {
      "epoch": 0.51,
      "eval_loss": 1.2000694274902344,
      "eval_runtime": 11.1133,
      "eval_samples_per_second": 234.043,
      "eval_steps_per_second": 58.578,
      "step": 40
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.058647479861974716,
      "learning_rate": 0.00019470712338657458,
      "loss": 1.1732,
      "step": 41
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.05649631842970848,
      "learning_rate": 0.00019436343565216711,
      "loss": 1.1747,
      "step": 42
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.05524146929383278,
      "learning_rate": 0.000194009260539328,
      "loss": 1.2022,
      "step": 43
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.05937836691737175,
      "learning_rate": 0.00019364463741042694,
      "loss": 1.1534,
      "step": 44
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.061414506286382675,
      "learning_rate": 0.00019326960678900688,
      "loss": 1.215,
      "step": 45
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.05350738391280174,
      "learning_rate": 0.00019288421035528028,
      "loss": 1.2095,
      "step": 46
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.05849866196513176,
      "learning_rate": 0.000192488490941497,
      "loss": 1.1703,
      "step": 47
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.05610804632306099,
      "learning_rate": 0.0001920824925271838,
      "loss": 1.1423,
      "step": 48
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.053889110684394836,
      "learning_rate": 0.00019166626023425662,
      "loss": 1.21,
      "step": 49
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.057582154870033264,
      "learning_rate": 0.00019123984032200586,
      "loss": 1.2279,
      "step": 50
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.05618985369801521,
      "learning_rate": 0.00019080328018195513,
      "loss": 1.1671,
      "step": 51
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.055953964591026306,
      "learning_rate": 0.00019035662833259432,
      "loss": 1.2564,
      "step": 52
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.05924614518880844,
      "learning_rate": 0.00018989993441398726,
      "loss": 1.1691,
      "step": 53
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.06068262457847595,
      "learning_rate": 0.00018943324918225494,
      "loss": 1.1482,
      "step": 54
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.05965428054332733,
      "learning_rate": 0.00018895662450393438,
      "loss": 1.2091,
      "step": 55
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.059606753289699554,
      "learning_rate": 0.00018847011335021449,
      "loss": 1.2394,
      "step": 56
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.059509821236133575,
      "learning_rate": 0.00018797376979104872,
      "loss": 1.1737,
      "step": 57
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.06392043828964233,
      "learning_rate": 0.0001874676489891461,
      "loss": 1.1871,
      "step": 58
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.06026330962777138,
      "learning_rate": 0.00018695180719384029,
      "loss": 1.1912,
      "step": 59
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.06576694548130035,
      "learning_rate": 0.00018642630173483832,
      "loss": 1.183,
      "step": 60
    },
    {
      "epoch": 0.77,
      "eval_loss": 1.1930629014968872,
      "eval_runtime": 11.089,
      "eval_samples_per_second": 234.556,
      "eval_steps_per_second": 58.707,
      "step": 60
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.05714555084705353,
      "learning_rate": 0.00018589119101584898,
      "loss": 1.208,
      "step": 61
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.059180356562137604,
      "learning_rate": 0.00018534653450809197,
      "loss": 1.2427,
      "step": 62
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.05717024207115173,
      "learning_rate": 0.0001847923927436884,
      "loss": 1.1717,
      "step": 63
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.06259780377149582,
      "learning_rate": 0.0001842288273089332,
      "loss": 1.2008,
      "step": 64
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.05737931653857231,
      "learning_rate": 0.00018365590083745085,
      "loss": 1.1685,
      "step": 65
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.06073923781514168,
      "learning_rate": 0.0001830736770032341,
      "loss": 1.1572,
      "step": 66
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.059637729078531265,
      "learning_rate": 0.00018248222051356754,
      "loss": 1.1963,
      "step": 67
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.06196809560060501,
      "learning_rate": 0.00018188159710183594,
      "loss": 1.1727,
      "step": 68
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.07422679662704468,
      "learning_rate": 0.00018127187352021907,
      "loss": 1.1976,
      "step": 69
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.05969575420022011,
      "learning_rate": 0.00018065311753227273,
      "loss": 1.1523,
      "step": 70
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.06363425403833389,
      "learning_rate": 0.00018002539790539773,
      "loss": 1.1861,
      "step": 71
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.059063684195280075,
      "learning_rate": 0.0001793887844031972,
      "loss": 1.2235,
      "step": 72
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.0626487135887146,
      "learning_rate": 0.00017874334777772327,
      "loss": 1.19,
      "step": 73
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.05672723054885864,
      "learning_rate": 0.00017808915976161362,
      "loss": 1.1781,
      "step": 74
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.061358433216810226,
      "learning_rate": 0.00017742629306011944,
      "loss": 1.2017,
      "step": 75
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.05795949324965477,
      "learning_rate": 0.000176754821343025,
      "loss": 1.1802,
      "step": 76
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.06237269937992096,
      "learning_rate": 0.00017607481923646016,
      "loss": 1.1777,
      "step": 77
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.05692945048213005,
      "learning_rate": 0.0001753863623146066,
      "loss": 1.1938,
      "step": 78
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.059807874262332916,
      "learning_rate": 0.00017468952709129846,
      "loss": 1.1685,
      "step": 79
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.07109411805868149,
      "learning_rate": 0.00017398439101151905,
      "loss": 1.1977,
      "step": 80
    },
    {
      "epoch": 1.01,
      "eval_loss": 1.1896089315414429,
      "eval_runtime": 11.089,
      "eval_samples_per_second": 234.558,
      "eval_steps_per_second": 58.707,
      "step": 80
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.05896366387605667,
      "learning_rate": 0.00017327103244279348,
      "loss": 1.1763,
      "step": 81
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.08269200474023819,
      "learning_rate": 0.00017254953066647913,
      "loss": 1.1641,
      "step": 82
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.06595351547002792,
      "learning_rate": 0.00017181996586895454,
      "loss": 1.1634,
      "step": 83
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.06604241579771042,
      "learning_rate": 0.0001710824191327075,
      "loss": 1.1239,
      "step": 84
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.07021407783031464,
      "learning_rate": 0.00017033697242732377,
      "loss": 1.1669,
      "step": 85
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.06747168302536011,
      "learning_rate": 0.00016958370860037717,
      "loss": 1.1433,
      "step": 86
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.06354415416717529,
      "learning_rate": 0.00016882271136822206,
      "loss": 1.1654,
      "step": 87
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.06672206521034241,
      "learning_rate": 0.0001680540653066891,
      "loss": 1.1496,
      "step": 88
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.07277010381221771,
      "learning_rate": 0.00016727785584168581,
      "loss": 1.1536,
      "step": 89
    },
    {
      "epoch": 1.14,
      "grad_norm": 0.06562938541173935,
      "learning_rate": 0.0001664941692397025,
      "loss": 1.1426,
      "step": 90
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.07519260793924332,
      "learning_rate": 0.00016570309259822453,
      "loss": 1.1224,
      "step": 91
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.0678098201751709,
      "learning_rate": 0.00016490471383605288,
      "loss": 1.1504,
      "step": 92
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.0652153342962265,
      "learning_rate": 0.0001640991216835326,
      "loss": 1.1371,
      "step": 93
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.07604055106639862,
      "learning_rate": 0.0001632864056726917,
      "loss": 1.1339,
      "step": 94
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.07262595742940903,
      "learning_rate": 0.00016246665612729074,
      "loss": 1.1725,
      "step": 95
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.06982827931642532,
      "learning_rate": 0.00016163996415278424,
      "loss": 1.1351,
      "step": 96
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.07324743270874023,
      "learning_rate": 0.00016080642162619565,
      "loss": 1.1496,
      "step": 97
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.08407079428434372,
      "learning_rate": 0.00015996612118590603,
      "loss": 1.1549,
      "step": 98
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.07180128991603851,
      "learning_rate": 0.00015911915622135862,
      "loss": 1.1311,
      "step": 99
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.08804436773061752,
      "learning_rate": 0.00015826562086267956,
      "loss": 1.1471,
      "step": 100
    },
    {
      "epoch": 1.26,
      "eval_loss": 1.1906447410583496,
      "eval_runtime": 11.084,
      "eval_samples_per_second": 234.662,
      "eval_steps_per_second": 58.733,
      "step": 100
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.08186957985162735,
      "learning_rate": 0.00015740560997021648,
      "loss": 1.1858,
      "step": 101
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.07139725238084793,
      "learning_rate": 0.00015653921912399589,
      "loss": 1.1356,
      "step": 102
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.07663066685199738,
      "learning_rate": 0.0001556665446131007,
      "loss": 1.1787,
      "step": 103
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.07882555574178696,
      "learning_rate": 0.0001547876834249687,
      "loss": 1.1738,
      "step": 104
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.07430710643529892,
      "learning_rate": 0.00015390273323461352,
      "loss": 1.1517,
      "step": 105
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.07954781502485275,
      "learning_rate": 0.00015301179239376938,
      "loss": 1.1281,
      "step": 106
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.07749734818935394,
      "learning_rate": 0.00015211495991996027,
      "loss": 1.1459,
      "step": 107
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.08005411177873611,
      "learning_rate": 0.0001512123354854955,
      "loss": 1.1766,
      "step": 108
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.07647199928760529,
      "learning_rate": 0.0001503040194063922,
      "loss": 1.1737,
      "step": 109
    },
    {
      "epoch": 1.39,
      "grad_norm": 0.0819963812828064,
      "learning_rate": 0.00014939011263122634,
      "loss": 1.1781,
      "step": 110
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.08222784847021103,
      "learning_rate": 0.00014847071672991367,
      "loss": 1.1882,
      "step": 111
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.07998190820217133,
      "learning_rate": 0.00014754593388242117,
      "loss": 1.1609,
      "step": 112
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.08468078076839447,
      "learning_rate": 0.0001466158668674112,
      "loss": 1.1513,
      "step": 113
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.09136669337749481,
      "learning_rate": 0.00014568061905081875,
      "loss": 1.1576,
      "step": 114
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.07721763849258423,
      "learning_rate": 0.00014474029437436348,
      "loss": 1.128,
      "step": 115
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.08751308917999268,
      "learning_rate": 0.00014379499734399798,
      "loss": 1.1504,
      "step": 116
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.08155680447816849,
      "learning_rate": 0.0001428448330182931,
      "loss": 1.1022,
      "step": 117
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.078422911465168,
      "learning_rate": 0.00014188990699676184,
      "loss": 1.1638,
      "step": 118
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.08801288157701492,
      "learning_rate": 0.00014093032540812348,
      "loss": 1.1993,
      "step": 119
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.08341657370328903,
      "learning_rate": 0.00013996619489850822,
      "loss": 1.1711,
      "step": 120
    },
    {
      "epoch": 1.52,
      "eval_loss": 1.1901248693466187,
      "eval_runtime": 11.1106,
      "eval_samples_per_second": 234.101,
      "eval_steps_per_second": 58.593,
      "step": 120
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.0804174616932869,
      "learning_rate": 0.00013899762261960518,
      "loss": 1.1479,
      "step": 121
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.07937135547399521,
      "learning_rate": 0.00013802471621675338,
      "loss": 1.1628,
      "step": 122
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.08624235540628433,
      "learning_rate": 0.00013704758381697844,
      "loss": 1.1533,
      "step": 123
    },
    {
      "epoch": 1.57,
      "grad_norm": 0.0815419852733612,
      "learning_rate": 0.00013606633401697557,
      "loss": 1.1444,
      "step": 124
    },
    {
      "epoch": 1.59,
      "grad_norm": 0.07709202915430069,
      "learning_rate": 0.0001350810758710401,
      "loss": 1.1644,
      "step": 125
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.08101613074541092,
      "learning_rate": 0.0001340919188789477,
      "loss": 1.1425,
      "step": 126
    },
    {
      "epoch": 1.61,
      "grad_norm": 0.08749125152826309,
      "learning_rate": 0.00013309897297378455,
      "loss": 1.1884,
      "step": 127
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.081383615732193,
      "learning_rate": 0.00013210234850972964,
      "loss": 1.1658,
      "step": 128
    },
    {
      "epoch": 1.64,
      "grad_norm": 0.08141542971134186,
      "learning_rate": 0.00013110215624979025,
      "loss": 1.1531,
      "step": 129
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.08194302022457123,
      "learning_rate": 0.0001300985073534919,
      "loss": 1.1593,
      "step": 130
    },
    {
      "epoch": 1.66,
      "grad_norm": 0.07621721178293228,
      "learning_rate": 0.0001290915133645243,
      "loss": 1.1529,
      "step": 131
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.07566998898983002,
      "learning_rate": 0.00012808128619834461,
      "loss": 1.1842,
      "step": 132
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.07865401357412338,
      "learning_rate": 0.00012706793812973941,
      "loss": 1.1718,
      "step": 133
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.08009400218725204,
      "learning_rate": 0.00012605158178034654,
      "loss": 1.1261,
      "step": 134
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.08229468762874603,
      "learning_rate": 0.00012503233010613865,
      "loss": 1.1576,
      "step": 135
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.08450435101985931,
      "learning_rate": 0.00012401029638486953,
      "loss": 1.2012,
      "step": 136
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.07879026234149933,
      "learning_rate": 0.00012298559420348437,
      "loss": 1.1856,
      "step": 137
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.07778112590312958,
      "learning_rate": 0.0001219583374454963,
      "loss": 1.1626,
      "step": 138
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.07738618552684784,
      "learning_rate": 0.00012092864027832933,
      "loss": 1.1496,
      "step": 139
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.07988622784614563,
      "learning_rate": 0.00011989661714062999,
      "loss": 1.1749,
      "step": 140
    },
    {
      "epoch": 1.78,
      "eval_loss": 1.1883182525634766,
      "eval_runtime": 11.1351,
      "eval_samples_per_second": 233.586,
      "eval_steps_per_second": 58.464,
      "step": 140
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.08023218810558319,
      "learning_rate": 0.00011886238272954897,
      "loss": 1.1623,
      "step": 141
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.07769781351089478,
      "learning_rate": 0.0001178260519879937,
      "loss": 1.1498,
      "step": 142
    },
    {
      "epoch": 1.82,
      "grad_norm": 0.07680430263280869,
      "learning_rate": 0.0001167877400918541,
      "loss": 1.1341,
      "step": 143
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.08009691536426544,
      "learning_rate": 0.0001157475624372018,
      "loss": 1.1662,
      "step": 144
    },
    {
      "epoch": 1.84,
      "grad_norm": 0.0748942419886589,
      "learning_rate": 0.00011470563462746541,
      "loss": 1.1499,
      "step": 145
    },
    {
      "epoch": 1.86,
      "grad_norm": 0.07798086851835251,
      "learning_rate": 0.0001136620724605827,
      "loss": 1.1493,
      "step": 146
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.08360154926776886,
      "learning_rate": 0.00011261699191613066,
      "loss": 1.1474,
      "step": 147
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.08265041559934616,
      "learning_rate": 0.00011157050914243614,
      "loss": 1.1274,
      "step": 148
    },
    {
      "epoch": 1.89,
      "grad_norm": 0.07973820716142654,
      "learning_rate": 0.00011052274044366711,
      "loss": 1.147,
      "step": 149
    },
    {
      "epoch": 1.91,
      "grad_norm": 0.07632620632648468,
      "learning_rate": 0.00010947380226690684,
      "loss": 1.1228,
      "step": 150
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.0813874751329422,
      "learning_rate": 0.00010842381118921232,
      "loss": 1.1464,
      "step": 151
    },
    {
      "epoch": 1.93,
      "grad_norm": 0.08030478656291962,
      "learning_rate": 0.00010737288390465792,
      "loss": 1.1154,
      "step": 152
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.07874114066362381,
      "learning_rate": 0.00010632113721136636,
      "loss": 1.1608,
      "step": 153
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.0795789510011673,
      "learning_rate": 0.00010526868799852796,
      "loss": 1.0918,
      "step": 154
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.07888780534267426,
      "learning_rate": 0.00010421565323340971,
      "loss": 1.1535,
      "step": 155
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.08071374148130417,
      "learning_rate": 0.0001031621499483559,
      "loss": 1.1306,
      "step": 156
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.0843919888138771,
      "learning_rate": 0.00010210829522778111,
      "loss": 1.1597,
      "step": 157
    },
    {
      "epoch": 2.01,
      "grad_norm": 0.07720304280519485,
      "learning_rate": 0.00010105420619515798,
      "loss": 1.1234,
      "step": 158
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.07769129425287247,
      "learning_rate": 0.0001,
      "loss": 1.1594,
      "step": 159
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.08473801612854004,
      "learning_rate": 9.894579380484204e-05,
      "loss": 1.1057,
      "step": 160
    },
    {
      "epoch": 2.02,
      "eval_loss": 1.1866793632507324,
      "eval_runtime": 11.0867,
      "eval_samples_per_second": 234.605,
      "eval_steps_per_second": 58.719,
      "step": 160
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.08069656789302826,
      "learning_rate": 9.789170477221891e-05,
      "loss": 1.1069,
      "step": 161
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.08355725556612015,
      "learning_rate": 9.683785005164411e-05,
      "loss": 1.076,
      "step": 162
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.09702204912900925,
      "learning_rate": 9.57843467665903e-05,
      "loss": 1.105,
      "step": 163
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.08148284256458282,
      "learning_rate": 9.473131200147205e-05,
      "loss": 1.0932,
      "step": 164
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.08034205436706543,
      "learning_rate": 9.367886278863366e-05,
      "loss": 1.096,
      "step": 165
    },
    {
      "epoch": 2.09,
      "grad_norm": 0.08467669785022736,
      "learning_rate": 9.26271160953421e-05,
      "loss": 1.1349,
      "step": 166
    },
    {
      "epoch": 2.11,
      "grad_norm": 0.08533730357885361,
      "learning_rate": 9.157618881078772e-05,
      "loss": 1.1344,
      "step": 167
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.09051905572414398,
      "learning_rate": 9.052619773309317e-05,
      "loss": 1.0794,
      "step": 168
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.08847147971391678,
      "learning_rate": 8.947725955633294e-05,
      "loss": 1.1084,
      "step": 169
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.08844807744026184,
      "learning_rate": 8.84294908575639e-05,
      "loss": 1.1123,
      "step": 170
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.09571530669927597,
      "learning_rate": 8.738300808386935e-05,
      "loss": 1.0753,
      "step": 171
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.09825875610113144,
      "learning_rate": 8.633792753941733e-05,
      "loss": 1.0986,
      "step": 172
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.09977909922599792,
      "learning_rate": 8.529436537253458e-05,
      "loss": 1.1116,
      "step": 173
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.090195432305336,
      "learning_rate": 8.425243756279824e-05,
      "loss": 1.0809,
      "step": 174
    },
    {
      "epoch": 2.21,
      "grad_norm": 0.09112106263637543,
      "learning_rate": 8.321225990814591e-05,
      "loss": 1.1074,
      "step": 175
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.09786658734083176,
      "learning_rate": 8.217394801200631e-05,
      "loss": 1.1107,
      "step": 176
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.0941900834441185,
      "learning_rate": 8.113761727045105e-05,
      "loss": 1.0686,
      "step": 177
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.09430352598428726,
      "learning_rate": 8.010338285937006e-05,
      "loss": 1.0676,
      "step": 178
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.09434497356414795,
      "learning_rate": 7.907135972167069e-05,
      "loss": 1.0885,
      "step": 179
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.09693111479282379,
      "learning_rate": 7.804166255450373e-05,
      "loss": 1.103,
      "step": 180
    },
    {
      "epoch": 2.27,
      "eval_loss": 1.194423794746399,
      "eval_runtime": 11.0499,
      "eval_samples_per_second": 235.387,
      "eval_steps_per_second": 58.915,
      "step": 180
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.09600096195936203,
      "learning_rate": 7.701440579651566e-05,
      "loss": 1.048,
      "step": 181
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.09983541816473007,
      "learning_rate": 7.598970361513051e-05,
      "loss": 1.1519,
      "step": 182
    },
    {
      "epoch": 2.31,
      "grad_norm": 0.09226010739803314,
      "learning_rate": 7.496766989386136e-05,
      "loss": 1.0913,
      "step": 183
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.09644059091806412,
      "learning_rate": 7.394841821965345e-05,
      "loss": 1.1105,
      "step": 184
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.09558931738138199,
      "learning_rate": 7.293206187026061e-05,
      "loss": 1.1251,
      "step": 185
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.09943023324012756,
      "learning_rate": 7.191871380165538e-05,
      "loss": 1.0779,
      "step": 186
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.09804826229810715,
      "learning_rate": 7.090848663547574e-05,
      "loss": 1.1258,
      "step": 187
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.10091326385736465,
      "learning_rate": 6.990149264650814e-05,
      "loss": 1.0677,
      "step": 188
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.09859558939933777,
      "learning_rate": 6.889784375020978e-05,
      "loss": 1.1112,
      "step": 189
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.1040605828166008,
      "learning_rate": 6.789765149027039e-05,
      "loss": 1.1375,
      "step": 190
    },
    {
      "epoch": 2.41,
      "grad_norm": 0.11397302150726318,
      "learning_rate": 6.690102702621548e-05,
      "loss": 1.1079,
      "step": 191
    },
    {
      "epoch": 2.43,
      "grad_norm": 0.11060205101966858,
      "learning_rate": 6.590808112105232e-05,
      "loss": 1.128,
      "step": 192
    },
    {
      "epoch": 2.44,
      "grad_norm": 0.10098471492528915,
      "learning_rate": 6.491892412895995e-05,
      "loss": 1.1437,
      "step": 193
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.1036130040884018,
      "learning_rate": 6.393366598302446e-05,
      "loss": 1.1106,
      "step": 194
    },
    {
      "epoch": 2.47,
      "grad_norm": 0.10566971451044083,
      "learning_rate": 6.295241618302156e-05,
      "loss": 1.1209,
      "step": 195
    },
    {
      "epoch": 2.48,
      "grad_norm": 0.1123911514878273,
      "learning_rate": 6.197528378324665e-05,
      "loss": 1.133,
      "step": 196
    },
    {
      "epoch": 2.49,
      "grad_norm": 0.10308899730443954,
      "learning_rate": 6.100237738039484e-05,
      "loss": 1.0973,
      "step": 197
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.10143700242042542,
      "learning_rate": 6.0033805101491794e-05,
      "loss": 1.118,
      "step": 198
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.10845794528722763,
      "learning_rate": 5.9069674591876534e-05,
      "loss": 1.0832,
      "step": 199
    },
    {
      "epoch": 2.53,
      "grad_norm": 0.115594282746315,
      "learning_rate": 5.811009300323818e-05,
      "loss": 1.0881,
      "step": 200
    },
    {
      "epoch": 2.53,
      "eval_loss": 1.1978853940963745,
      "eval_runtime": 11.0803,
      "eval_samples_per_second": 234.74,
      "eval_steps_per_second": 58.753,
      "step": 200
    },
    {
      "epoch": 2.54,
      "grad_norm": 0.10974434018135071,
      "learning_rate": 5.7155166981706956e-05,
      "loss": 1.1413,
      "step": 201
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.10608117282390594,
      "learning_rate": 5.620500265600206e-05,
      "loss": 1.1216,
      "step": 202
    },
    {
      "epoch": 2.57,
      "grad_norm": 0.1109042689204216,
      "learning_rate": 5.525970562563656e-05,
      "loss": 1.1106,
      "step": 203
    },
    {
      "epoch": 2.58,
      "grad_norm": 0.11192983388900757,
      "learning_rate": 5.431938094918132e-05,
      "loss": 1.1122,
      "step": 204
    },
    {
      "epoch": 2.59,
      "grad_norm": 0.10309618711471558,
      "learning_rate": 5.3384133132588784e-05,
      "loss": 1.1012,
      "step": 205
    },
    {
      "epoch": 2.61,
      "grad_norm": 0.09989263117313385,
      "learning_rate": 5.2454066117578815e-05,
      "loss": 1.1164,
      "step": 206
    },
    {
      "epoch": 2.62,
      "grad_norm": 0.1028265655040741,
      "learning_rate": 5.152928327008635e-05,
      "loss": 1.1335,
      "step": 207
    },
    {
      "epoch": 2.63,
      "grad_norm": 0.1162625402212143,
      "learning_rate": 5.060988736877366e-05,
      "loss": 1.1484,
      "step": 208
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.10568027198314667,
      "learning_rate": 4.9695980593607817e-05,
      "loss": 1.0821,
      "step": 209
    },
    {
      "epoch": 2.66,
      "grad_norm": 0.10472647845745087,
      "learning_rate": 4.8787664514504504e-05,
      "loss": 1.0867,
      "step": 210
    },
    {
      "epoch": 2.67,
      "grad_norm": 0.10326943546533585,
      "learning_rate": 4.788504008003978e-05,
      "loss": 1.0787,
      "step": 211
    },
    {
      "epoch": 2.68,
      "grad_norm": 0.10474622249603271,
      "learning_rate": 4.698820760623064e-05,
      "loss": 1.1189,
      "step": 212
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.10698090493679047,
      "learning_rate": 4.609726676538652e-05,
      "loss": 1.0987,
      "step": 213
    },
    {
      "epoch": 2.71,
      "grad_norm": 0.10720671713352203,
      "learning_rate": 4.521231657503132e-05,
      "loss": 1.0837,
      "step": 214
    },
    {
      "epoch": 2.72,
      "grad_norm": 0.10953236371278763,
      "learning_rate": 4.433345538689929e-05,
      "loss": 1.1136,
      "step": 215
    },
    {
      "epoch": 2.74,
      "grad_norm": 0.10939928144216537,
      "learning_rate": 4.346078087600412e-05,
      "loss": 1.1346,
      "step": 216
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.10348028689622879,
      "learning_rate": 4.2594390029783534e-05,
      "loss": 1.0539,
      "step": 217
    },
    {
      "epoch": 2.76,
      "grad_norm": 0.10443831980228424,
      "learning_rate": 4.173437913732048e-05,
      "loss": 1.1246,
      "step": 218
    },
    {
      "epoch": 2.77,
      "grad_norm": 0.10903069376945496,
      "learning_rate": 4.088084377864135e-05,
      "loss": 1.0711,
      "step": 219
    },
    {
      "epoch": 2.79,
      "grad_norm": 0.10401046276092529,
      "learning_rate": 4.003387881409397e-05,
      "loss": 1.1117,
      "step": 220
    },
    {
      "epoch": 2.79,
      "eval_loss": 1.1959346532821655,
      "eval_runtime": 11.1605,
      "eval_samples_per_second": 233.054,
      "eval_steps_per_second": 58.331,
      "step": 220
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.10746972262859344,
      "learning_rate": 3.9193578373804364e-05,
      "loss": 1.1183,
      "step": 221
    },
    {
      "epoch": 2.81,
      "grad_norm": 0.10168997198343277,
      "learning_rate": 3.836003584721577e-05,
      "loss": 1.1311,
      "step": 222
    },
    {
      "epoch": 2.83,
      "grad_norm": 0.10692451149225235,
      "learning_rate": 3.7533343872709294e-05,
      "loss": 1.1081,
      "step": 223
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.1075156182050705,
      "learning_rate": 3.671359432730834e-05,
      "loss": 1.1085,
      "step": 224
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.10297439247369766,
      "learning_rate": 3.5900878316467454e-05,
      "loss": 1.1376,
      "step": 225
    },
    {
      "epoch": 2.86,
      "grad_norm": 0.10721824318170547,
      "learning_rate": 3.509528616394716e-05,
      "loss": 1.1136,
      "step": 226
    },
    {
      "epoch": 2.88,
      "grad_norm": 0.11028096079826355,
      "learning_rate": 3.429690740177549e-05,
      "loss": 1.1318,
      "step": 227
    },
    {
      "epoch": 2.89,
      "grad_norm": 0.10864273458719254,
      "learning_rate": 3.350583076029754e-05,
      "loss": 1.1396,
      "step": 228
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.1059827134013176,
      "learning_rate": 3.272214415831418e-05,
      "loss": 1.1048,
      "step": 229
    },
    {
      "epoch": 2.92,
      "grad_norm": 0.10945747792720795,
      "learning_rate": 3.1945934693310896e-05,
      "loss": 1.106,
      "step": 230
    },
    {
      "epoch": 2.93,
      "grad_norm": 0.10941856354475021,
      "learning_rate": 3.117728863177796e-05,
      "loss": 1.1144,
      "step": 231
    }
  ],
  "logging_steps": 1,
  "max_steps": 308,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 77,
  "total_flos": 6.893136578000978e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}