{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10634328358208955,
  "eval_steps": 38,
  "global_step": 114,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009328358208955224,
      "grad_norm": 2.931856870651245,
      "learning_rate": 4e-05,
      "loss": 3.1183,
      "step": 1
    },
    {
      "epoch": 0.0009328358208955224,
      "eval_loss": 0.7989240884780884,
      "eval_runtime": 61.068,
      "eval_samples_per_second": 7.402,
      "eval_steps_per_second": 3.701,
      "step": 1
    },
    {
      "epoch": 0.0018656716417910447,
      "grad_norm": 3.0857083797454834,
      "learning_rate": 8e-05,
      "loss": 3.3967,
      "step": 2
    },
    {
      "epoch": 0.002798507462686567,
      "grad_norm": 2.9495201110839844,
      "learning_rate": 0.00012,
      "loss": 3.4361,
      "step": 3
    },
    {
      "epoch": 0.0037313432835820895,
      "grad_norm": 2.4459776878356934,
      "learning_rate": 0.00016,
      "loss": 3.2275,
      "step": 4
    },
    {
      "epoch": 0.0046641791044776115,
      "grad_norm": 2.410581588745117,
      "learning_rate": 0.0002,
      "loss": 3.0069,
      "step": 5
    },
    {
      "epoch": 0.005597014925373134,
      "grad_norm": 1.99094820022583,
      "learning_rate": 0.00024,
      "loss": 2.6997,
      "step": 6
    },
    {
      "epoch": 0.0065298507462686565,
      "grad_norm": 1.850408911705017,
      "learning_rate": 0.00028,
      "loss": 2.6469,
      "step": 7
    },
    {
      "epoch": 0.007462686567164179,
      "grad_norm": 2.972104072570801,
      "learning_rate": 0.00032,
      "loss": 3.351,
      "step": 8
    },
    {
      "epoch": 0.008395522388059701,
      "grad_norm": 2.8936173915863037,
      "learning_rate": 0.00036,
      "loss": 2.8041,
      "step": 9
    },
    {
      "epoch": 0.009328358208955223,
      "grad_norm": 2.354464530944824,
      "learning_rate": 0.0004,
      "loss": 2.7652,
      "step": 10
    },
    {
      "epoch": 0.010261194029850746,
      "grad_norm": 2.024070978164673,
      "learning_rate": 0.0003999496469885013,
      "loss": 2.8786,
      "step": 11
    },
    {
      "epoch": 0.011194029850746268,
      "grad_norm": 1.8775830268859863,
      "learning_rate": 0.00039979861330826294,
      "loss": 2.0356,
      "step": 12
    },
    {
      "epoch": 0.012126865671641791,
      "grad_norm": 1.7130846977233887,
      "learning_rate": 0.0003995469750092912,
      "loss": 2.6772,
      "step": 13
    },
    {
      "epoch": 0.013059701492537313,
      "grad_norm": 1.9945520162582397,
      "learning_rate": 0.00039919485879904784,
      "loss": 2.8959,
      "step": 14
    },
    {
      "epoch": 0.013992537313432836,
      "grad_norm": 1.6973563432693481,
      "learning_rate": 0.00039874244197864856,
      "loss": 2.3531,
      "step": 15
    },
    {
      "epoch": 0.014925373134328358,
      "grad_norm": 1.5936486721038818,
      "learning_rate": 0.00039818995235358696,
      "loss": 1.9481,
      "step": 16
    },
    {
      "epoch": 0.01585820895522388,
      "grad_norm": 1.828995943069458,
      "learning_rate": 0.00039753766811902755,
      "loss": 3.6787,
      "step": 17
    },
    {
      "epoch": 0.016791044776119403,
      "grad_norm": 1.553421139717102,
      "learning_rate": 0.0003967859177197259,
      "loss": 2.2696,
      "step": 18
    },
    {
      "epoch": 0.017723880597014924,
      "grad_norm": 1.2893372774124146,
      "learning_rate": 0.00039593507968464716,
      "loss": 1.9452,
      "step": 19
    },
    {
      "epoch": 0.018656716417910446,
      "grad_norm": 1.674631953239441,
      "learning_rate": 0.0003949855824363647,
      "loss": 2.2916,
      "step": 20
    },
    {
      "epoch": 0.01958955223880597,
      "grad_norm": 1.4569449424743652,
      "learning_rate": 0.0003939379040753374,
      "loss": 2.1701,
      "step": 21
    },
    {
      "epoch": 0.020522388059701493,
      "grad_norm": 1.438828468322754,
      "learning_rate": 0.00039279257213917066,
      "loss": 2.5621,
      "step": 22
    },
    {
      "epoch": 0.021455223880597014,
      "grad_norm": 1.3770123720169067,
      "learning_rate": 0.0003915501633369861,
      "loss": 2.1366,
      "step": 23
    },
    {
      "epoch": 0.022388059701492536,
      "grad_norm": 1.4712828397750854,
      "learning_rate": 0.00039021130325903074,
      "loss": 2.319,
      "step": 24
    },
    {
      "epoch": 0.02332089552238806,
      "grad_norm": 1.465248465538025,
      "learning_rate": 0.00038877666606167355,
      "loss": 2.3959,
      "step": 25
    },
    {
      "epoch": 0.024253731343283583,
      "grad_norm": 1.4384740591049194,
      "learning_rate": 0.00038724697412794747,
      "loss": 2.097,
      "step": 26
    },
    {
      "epoch": 0.025186567164179104,
      "grad_norm": 1.3539812564849854,
      "learning_rate": 0.0003856229977038078,
      "loss": 2.2313,
      "step": 27
    },
    {
      "epoch": 0.026119402985074626,
      "grad_norm": 1.3618801832199097,
      "learning_rate": 0.0003839055545102902,
      "loss": 2.1054,
      "step": 28
    },
    {
      "epoch": 0.027052238805970148,
      "grad_norm": 1.422633409500122,
      "learning_rate": 0.00038209550933176323,
      "loss": 2.276,
      "step": 29
    },
    {
      "epoch": 0.027985074626865673,
      "grad_norm": 1.4232622385025024,
      "learning_rate": 0.0003801937735804838,
      "loss": 2.1735,
      "step": 30
    },
    {
      "epoch": 0.028917910447761194,
      "grad_norm": 1.4555679559707642,
      "learning_rate": 0.0003782013048376736,
      "loss": 2.2706,
      "step": 31
    },
    {
      "epoch": 0.029850746268656716,
      "grad_norm": 1.2929563522338867,
      "learning_rate": 0.0003761191063713476,
      "loss": 1.9037,
      "step": 32
    },
    {
      "epoch": 0.030783582089552237,
      "grad_norm": 1.2687627077102661,
      "learning_rate": 0.0003739482266311391,
      "loss": 2.1032,
      "step": 33
    },
    {
      "epoch": 0.03171641791044776,
      "grad_norm": 1.2993357181549072,
      "learning_rate": 0.00037168975872037323,
      "loss": 2.0062,
      "step": 34
    },
    {
      "epoch": 0.03264925373134328,
      "grad_norm": 1.3507018089294434,
      "learning_rate": 0.00036934483984565685,
      "loss": 2.1522,
      "step": 35
    },
    {
      "epoch": 0.033582089552238806,
      "grad_norm": 1.4183921813964844,
      "learning_rate": 0.00036691465074426054,
      "loss": 1.845,
      "step": 36
    },
    {
      "epoch": 0.03451492537313433,
      "grad_norm": 1.3370906114578247,
      "learning_rate": 0.00036440041508958203,
      "loss": 1.9448,
      "step": 37
    },
    {
      "epoch": 0.03544776119402985,
      "grad_norm": 1.4249347448349,
      "learning_rate": 0.0003618033988749895,
      "loss": 2.4594,
      "step": 38
    },
    {
      "epoch": 0.03544776119402985,
      "eval_loss": 0.5035107135772705,
      "eval_runtime": 60.2427,
      "eval_samples_per_second": 7.503,
      "eval_steps_per_second": 3.751,
      "step": 38
    },
    {
      "epoch": 0.036380597014925374,
      "grad_norm": 1.4865802526474,
      "learning_rate": 0.00035912490977635625,
      "loss": 2.2656,
      "step": 39
    },
    {
      "epoch": 0.03731343283582089,
      "grad_norm": 1.3488837480545044,
      "learning_rate": 0.000356366296493606,
      "loss": 1.9688,
      "step": 40
    },
    {
      "epoch": 0.03824626865671642,
      "grad_norm": 1.4332904815673828,
      "learning_rate": 0.0003535289480716022,
      "loss": 2.2615,
      "step": 41
    },
    {
      "epoch": 0.03917910447761194,
      "grad_norm": 1.516402006149292,
      "learning_rate": 0.00035061429320072223,
      "loss": 2.059,
      "step": 42
    },
    {
      "epoch": 0.04011194029850746,
      "grad_norm": 1.4039419889450073,
      "learning_rate": 0.00034762379949746815,
      "loss": 2.1295,
      "step": 43
    },
    {
      "epoch": 0.041044776119402986,
      "grad_norm": 1.2742645740509033,
      "learning_rate": 0.0003445589727654783,
      "loss": 2.1964,
      "step": 44
    },
    {
      "epoch": 0.04197761194029851,
      "grad_norm": 1.115033507347107,
      "learning_rate": 0.0003414213562373095,
      "loss": 1.8306,
      "step": 45
    },
    {
      "epoch": 0.04291044776119403,
      "grad_norm": 1.1708894968032837,
      "learning_rate": 0.00033821252979737297,
      "loss": 1.9652,
      "step": 46
    },
    {
      "epoch": 0.043843283582089554,
      "grad_norm": 1.185393214225769,
      "learning_rate": 0.0003349341091864149,
      "loss": 1.8172,
      "step": 47
    },
    {
      "epoch": 0.04477611940298507,
      "grad_norm": 1.1099275350570679,
      "learning_rate": 0.00033158774518794254,
      "loss": 1.7576,
      "step": 48
    },
    {
      "epoch": 0.0457089552238806,
      "grad_norm": 1.0703908205032349,
      "learning_rate": 0.0003281751227970048,
      "loss": 1.9036,
      "step": 49
    },
    {
      "epoch": 0.04664179104477612,
      "grad_norm": 1.1421232223510742,
      "learning_rate": 0.00032469796037174674,
      "loss": 1.9759,
      "step": 50
    },
    {
      "epoch": 0.04757462686567164,
      "grad_norm": 1.1319009065628052,
      "learning_rate": 0.000321158008768164,
      "loss": 1.7476,
      "step": 51
    },
    {
      "epoch": 0.048507462686567165,
      "grad_norm": 1.1899311542510986,
      "learning_rate": 0.00031755705045849464,
      "loss": 1.8308,
      "step": 52
    },
    {
      "epoch": 0.049440298507462684,
      "grad_norm": 1.246800184249878,
      "learning_rate": 0.0003138968986336904,
      "loss": 1.9183,
      "step": 53
    },
    {
      "epoch": 0.05037313432835821,
      "grad_norm": 1.207138180732727,
      "learning_rate": 0.0003101793962904205,
      "loss": 1.8768,
      "step": 54
    },
    {
      "epoch": 0.051305970149253734,
      "grad_norm": 0.9686072468757629,
      "learning_rate": 0.00030640641530306733,
      "loss": 1.6107,
      "step": 55
    },
    {
      "epoch": 0.05223880597014925,
      "grad_norm": 1.1268424987792969,
      "learning_rate": 0.00030257985548118126,
      "loss": 1.9169,
      "step": 56
    },
    {
      "epoch": 0.05317164179104478,
      "grad_norm": 1.3243463039398193,
      "learning_rate": 0.0002987016436128694,
      "loss": 2.1651,
      "step": 57
    },
    {
      "epoch": 0.054104477611940295,
      "grad_norm": 1.230141043663025,
      "learning_rate": 0.0002947737324945997,
      "loss": 2.0871,
      "step": 58
    },
    {
      "epoch": 0.05503731343283582,
      "grad_norm": 1.0468418598175049,
      "learning_rate": 0.00029079809994790937,
      "loss": 1.7348,
      "step": 59
    },
    {
      "epoch": 0.055970149253731345,
      "grad_norm": 1.3394778966903687,
      "learning_rate": 0.00028677674782351165,
      "loss": 2.3597,
      "step": 60
    },
    {
      "epoch": 0.05690298507462686,
      "grad_norm": 1.2126855850219727,
      "learning_rate": 0.00028271170099330415,
      "loss": 2.0063,
      "step": 61
    },
    {
      "epoch": 0.05783582089552239,
      "grad_norm": 1.2102502584457397,
      "learning_rate": 0.00027860500633078477,
      "loss": 2.0048,
      "step": 62
    },
    {
      "epoch": 0.058768656716417914,
      "grad_norm": 1.2987444400787354,
      "learning_rate": 0.00027445873168038907,
      "loss": 2.6436,
      "step": 63
    },
    {
      "epoch": 0.05970149253731343,
      "grad_norm": 1.1055057048797607,
      "learning_rate": 0.0002702749648162686,
      "loss": 1.8015,
      "step": 64
    },
    {
      "epoch": 0.06063432835820896,
      "grad_norm": 1.1894230842590332,
      "learning_rate": 0.00026605581239103347,
      "loss": 2.0075,
      "step": 65
    },
    {
      "epoch": 0.061567164179104475,
      "grad_norm": 0.9544552564620972,
      "learning_rate": 0.00026180339887498953,
      "loss": 1.5043,
      "step": 66
    },
    {
      "epoch": 0.0625,
      "grad_norm": 1.2134445905685425,
      "learning_rate": 0.00025751986548640346,
      "loss": 1.9537,
      "step": 67
    },
    {
      "epoch": 0.06343283582089553,
      "grad_norm": 1.061187505722046,
      "learning_rate": 0.00025320736911333503,
      "loss": 1.6231,
      "step": 68
    },
    {
      "epoch": 0.06436567164179105,
      "grad_norm": 1.1641594171524048,
      "learning_rate": 0.0002488680812275788,
      "loss": 1.6016,
      "step": 69
    },
    {
      "epoch": 0.06529850746268656,
      "grad_norm": 1.1650375127792358,
      "learning_rate": 0.0002445041867912629,
      "loss": 1.8811,
      "step": 70
    },
    {
      "epoch": 0.06623134328358209,
      "grad_norm": 1.319548487663269,
      "learning_rate": 0.00024011788315665458,
      "loss": 1.7969,
      "step": 71
    },
    {
      "epoch": 0.06716417910447761,
      "grad_norm": 1.009516954421997,
      "learning_rate": 0.00023571137895972733,
      "loss": 1.4261,
      "step": 72
    },
    {
      "epoch": 0.06809701492537314,
      "grad_norm": 1.1219674348831177,
      "learning_rate": 0.0002312868930080462,
      "loss": 1.5247,
      "step": 73
    },
    {
      "epoch": 0.06902985074626866,
      "grad_norm": 1.0498907566070557,
      "learning_rate": 0.0002268466531635311,
      "loss": 1.7131,
      "step": 74
    },
    {
      "epoch": 0.06996268656716417,
      "grad_norm": 1.0986140966415405,
      "learning_rate": 0.00022239289522066157,
      "loss": 1.7584,
      "step": 75
    },
    {
      "epoch": 0.0708955223880597,
      "grad_norm": 1.2214365005493164,
      "learning_rate": 0.00021792786178068672,
      "loss": 1.7782,
      "step": 76
    },
    {
      "epoch": 0.0708955223880597,
      "eval_loss": 0.47117629647254944,
      "eval_runtime": 60.2201,
      "eval_samples_per_second": 7.506,
      "eval_steps_per_second": 3.753,
      "step": 76
    },
    {
      "epoch": 0.07182835820895522,
      "grad_norm": 1.2228177785873413,
      "learning_rate": 0.00021345380112240797,
      "loss": 2.1149,
      "step": 77
    },
    {
      "epoch": 0.07276119402985075,
      "grad_norm": 1.0541841983795166,
      "learning_rate": 0.00020897296607010301,
      "loss": 1.6306,
      "step": 78
    },
    {
      "epoch": 0.07369402985074627,
      "grad_norm": 1.1272865533828735,
      "learning_rate": 0.00020448761285916104,
      "loss": 1.9262,
      "step": 79
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 1.1912484169006348,
      "learning_rate": 0.0002,
      "loss": 2.0926,
      "step": 80
    },
    {
      "epoch": 0.07555970149253731,
      "grad_norm": 1.2342007160186768,
      "learning_rate": 0.00019551238714083903,
      "loss": 2.3557,
      "step": 81
    },
    {
      "epoch": 0.07649253731343283,
      "grad_norm": 1.068264365196228,
      "learning_rate": 0.00019102703392989709,
      "loss": 1.9768,
      "step": 82
    },
    {
      "epoch": 0.07742537313432836,
      "grad_norm": 1.035170555114746,
      "learning_rate": 0.00018654619887759207,
      "loss": 1.6881,
      "step": 83
    },
    {
      "epoch": 0.07835820895522388,
      "grad_norm": 1.2881474494934082,
      "learning_rate": 0.00018207213821931333,
      "loss": 2.1289,
      "step": 84
    },
    {
      "epoch": 0.07929104477611941,
      "grad_norm": 1.1358542442321777,
      "learning_rate": 0.00017760710477933845,
      "loss": 2.2829,
      "step": 85
    },
    {
      "epoch": 0.08022388059701492,
      "grad_norm": 1.2520966529846191,
      "learning_rate": 0.00017315334683646897,
      "loss": 1.552,
      "step": 86
    },
    {
      "epoch": 0.08115671641791045,
      "grad_norm": 0.9834119081497192,
      "learning_rate": 0.00016871310699195379,
      "loss": 1.5413,
      "step": 87
    },
    {
      "epoch": 0.08208955223880597,
      "grad_norm": 1.043672800064087,
      "learning_rate": 0.00016428862104027268,
      "loss": 1.7337,
      "step": 88
    },
    {
      "epoch": 0.0830223880597015,
      "grad_norm": 1.0788074731826782,
      "learning_rate": 0.00015988211684334546,
      "loss": 1.3079,
      "step": 89
    },
    {
      "epoch": 0.08395522388059702,
      "grad_norm": 1.0924961566925049,
      "learning_rate": 0.00015549581320873715,
      "loss": 1.7402,
      "step": 90
    },
    {
      "epoch": 0.08488805970149253,
      "grad_norm": 1.1585627794265747,
      "learning_rate": 0.00015113191877242117,
      "loss": 1.7314,
      "step": 91
    },
    {
      "epoch": 0.08582089552238806,
      "grad_norm": 1.0373111963272095,
      "learning_rate": 0.00014679263088666499,
      "loss": 1.7103,
      "step": 92
    },
    {
      "epoch": 0.08675373134328358,
      "grad_norm": 1.178009271621704,
      "learning_rate": 0.00014248013451359656,
      "loss": 1.8889,
      "step": 93
    },
    {
      "epoch": 0.08768656716417911,
      "grad_norm": 1.110259771347046,
      "learning_rate": 0.00013819660112501054,
      "loss": 1.685,
      "step": 94
    },
    {
      "epoch": 0.08861940298507463,
      "grad_norm": 1.0290873050689697,
      "learning_rate": 0.00013394418760896666,
      "loss": 1.6533,
      "step": 95
    },
    {
      "epoch": 0.08955223880597014,
      "grad_norm": 1.0740941762924194,
      "learning_rate": 0.00012972503518373144,
      "loss": 1.8436,
      "step": 96
    },
    {
      "epoch": 0.09048507462686567,
      "grad_norm": 1.1851738691329956,
      "learning_rate": 0.00012554126831961098,
      "loss": 1.8081,
      "step": 97
    },
    {
      "epoch": 0.0914179104477612,
      "grad_norm": 1.0965279340744019,
      "learning_rate": 0.0001213949936692153,
      "loss": 1.8133,
      "step": 98
    },
    {
      "epoch": 0.09235074626865672,
      "grad_norm": 1.0990545749664307,
      "learning_rate": 0.00011728829900669591,
      "loss": 1.7193,
      "step": 99
    },
    {
      "epoch": 0.09328358208955224,
      "grad_norm": 1.0958396196365356,
      "learning_rate": 0.00011322325217648839,
      "loss": 1.3802,
      "step": 100
    },
    {
      "epoch": 0.09421641791044776,
      "grad_norm": 1.0536209344863892,
      "learning_rate": 0.00010920190005209065,
      "loss": 1.8329,
      "step": 101
    },
    {
      "epoch": 0.09514925373134328,
      "grad_norm": 1.0651001930236816,
      "learning_rate": 0.00010522626750540028,
      "loss": 1.6494,
      "step": 102
    },
    {
      "epoch": 0.0960820895522388,
      "grad_norm": 1.1998820304870605,
      "learning_rate": 0.00010129835638713063,
      "loss": 2.0276,
      "step": 103
    },
    {
      "epoch": 0.09701492537313433,
      "grad_norm": 0.9894289374351501,
      "learning_rate": 9.74201445188188e-05,
      "loss": 1.5171,
      "step": 104
    },
    {
      "epoch": 0.09794776119402986,
      "grad_norm": 1.2795695066452026,
      "learning_rate": 9.359358469693271e-05,
      "loss": 1.7987,
      "step": 105
    },
    {
      "epoch": 0.09888059701492537,
      "grad_norm": 1.0911823511123657,
      "learning_rate": 8.982060370957952e-05,
      "loss": 1.6949,
      "step": 106
    },
    {
      "epoch": 0.09981343283582089,
      "grad_norm": 0.9669733047485352,
      "learning_rate": 8.610310136630962e-05,
      "loss": 1.405,
      "step": 107
    },
    {
      "epoch": 0.10074626865671642,
      "grad_norm": 1.1521021127700806,
      "learning_rate": 8.24429495415054e-05,
      "loss": 1.8475,
      "step": 108
    },
    {
      "epoch": 0.10167910447761194,
      "grad_norm": 1.085671305656433,
      "learning_rate": 7.884199123183605e-05,
      "loss": 1.5308,
      "step": 109
    },
    {
      "epoch": 0.10261194029850747,
      "grad_norm": 1.141276240348816,
      "learning_rate": 7.530203962825331e-05,
      "loss": 1.8675,
      "step": 110
    },
    {
      "epoch": 0.10354477611940298,
      "grad_norm": 1.0789172649383545,
      "learning_rate": 7.182487720299517e-05,
      "loss": 1.7724,
      "step": 111
    },
    {
      "epoch": 0.1044776119402985,
      "grad_norm": 1.0939713716506958,
      "learning_rate": 6.841225481205749e-05,
      "loss": 1.5574,
      "step": 112
    },
    {
      "epoch": 0.10541044776119403,
      "grad_norm": 1.2875022888183594,
      "learning_rate": 6.506589081358514e-05,
      "loss": 1.7821,
      "step": 113
    },
    {
      "epoch": 0.10634328358208955,
      "grad_norm": 1.1060545444488525,
      "learning_rate": 6.178747020262707e-05,
      "loss": 1.543,
      "step": 114
    },
    {
      "epoch": 0.10634328358208955,
      "eval_loss": 0.44875675439834595,
      "eval_runtime": 61.3854,
      "eval_samples_per_second": 7.363,
      "eval_steps_per_second": 3.682,
      "step": 114
    }
  ],
  "logging_steps": 1,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 38,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.494599973470208e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}