{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012587324564163886,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00012587324564163887,
      "grad_norm": 4.972455978393555,
      "learning_rate": 2e-05,
      "loss": 11.8587,
      "step": 1
    },
    {
      "epoch": 0.00012587324564163887,
      "eval_loss": NaN,
      "eval_runtime": 3606.4326,
      "eval_samples_per_second": 0.928,
      "eval_steps_per_second": 0.464,
      "step": 1
    },
    {
      "epoch": 0.00025174649128327774,
      "grad_norm": 12.494519233703613,
      "learning_rate": 4e-05,
      "loss": 5.71,
      "step": 2
    },
    {
      "epoch": 0.0003776197369249166,
      "grad_norm": 18.601806640625,
      "learning_rate": 6e-05,
      "loss": 11.1117,
      "step": 3
    },
    {
      "epoch": 0.0005034929825665555,
      "grad_norm": 8.032801628112793,
      "learning_rate": 8e-05,
      "loss": 3.9358,
      "step": 4
    },
    {
      "epoch": 0.0006293662282081943,
      "grad_norm": 12.177727699279785,
      "learning_rate": 0.0001,
      "loss": 16.7821,
      "step": 5
    },
    {
      "epoch": 0.0007552394738498332,
      "grad_norm": 6.706995964050293,
      "learning_rate": 0.00012,
      "loss": 10.3418,
      "step": 6
    },
    {
      "epoch": 0.0008811127194914721,
      "grad_norm": 6.680157661437988,
      "learning_rate": 0.00014,
      "loss": 4.845,
      "step": 7
    },
    {
      "epoch": 0.001006985965133111,
      "grad_norm": 9.944180488586426,
      "learning_rate": 0.00016,
      "loss": 2.6742,
      "step": 8
    },
    {
      "epoch": 0.0011328592107747498,
      "grad_norm": 14.13370418548584,
      "learning_rate": 0.00018,
      "loss": 3.8844,
      "step": 9
    },
    {
      "epoch": 0.0012587324564163887,
      "grad_norm": 17.886985778808594,
      "learning_rate": 0.0002,
      "loss": 3.3169,
      "step": 10
    },
    {
      "epoch": 0.0013846057020580275,
      "grad_norm": 21.377635955810547,
      "learning_rate": 0.0001999390827019096,
      "loss": 1.0058,
      "step": 11
    },
    {
      "epoch": 0.0015104789476996663,
      "grad_norm": 11.985687255859375,
      "learning_rate": 0.00019975640502598244,
      "loss": 0.8173,
      "step": 12
    },
    {
      "epoch": 0.0016363521933413054,
      "grad_norm": 17.24648666381836,
      "learning_rate": 0.00019945218953682734,
      "loss": 0.3288,
      "step": 13
    },
    {
      "epoch": 0.0017622254389829443,
      "grad_norm": 38.9212532043457,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.7752,
      "step": 14
    },
    {
      "epoch": 0.001888098684624583,
      "grad_norm": 12.58133316040039,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.7308,
      "step": 15
    },
    {
      "epoch": 0.002013971930266222,
      "grad_norm": 5.521592617034912,
      "learning_rate": 0.00019781476007338058,
      "loss": 0.1023,
      "step": 16
    },
    {
      "epoch": 0.002139845175907861,
      "grad_norm": 1.7692532539367676,
      "learning_rate": 0.00019702957262759965,
      "loss": 0.0166,
      "step": 17
    },
    {
      "epoch": 0.0022657184215494996,
      "grad_norm": 9.756790161132812,
      "learning_rate": 0.0001961261695938319,
      "loss": 1.1932,
      "step": 18
    },
    {
      "epoch": 0.0023915916671911385,
      "grad_norm": 8.156234741210938,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.3879,
      "step": 19
    },
    {
      "epoch": 0.0025174649128327773,
      "grad_norm": 6.355808258056641,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.4888,
      "step": 20
    },
    {
      "epoch": 0.002643338158474416,
      "grad_norm": 6.595178127288818,
      "learning_rate": 0.00019271838545667876,
      "loss": 0.6385,
      "step": 21
    },
    {
      "epoch": 0.002769211404116055,
      "grad_norm": 3.2132580280303955,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.518,
      "step": 22
    },
    {
      "epoch": 0.002895084649757694,
      "grad_norm": 16.919002532958984,
      "learning_rate": 0.0001898794046299167,
      "loss": 0.3769,
      "step": 23
    },
    {
      "epoch": 0.0030209578953993327,
      "grad_norm": 0.020209377631545067,
      "learning_rate": 0.00018829475928589271,
      "loss": 0.0002,
      "step": 24
    },
    {
      "epoch": 0.0031468311410409715,
      "grad_norm": 0.8074254989624023,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.0241,
      "step": 25
    },
    {
      "epoch": 0.0031468311410409715,
      "eval_loss": NaN,
      "eval_runtime": 3493.5914,
      "eval_samples_per_second": 0.957,
      "eval_steps_per_second": 0.479,
      "step": 25
    },
    {
      "epoch": 0.003272704386682611,
      "grad_norm": 19.329341888427734,
      "learning_rate": 0.0001848048096156426,
      "loss": 0.7896,
      "step": 26
    },
    {
      "epoch": 0.0033985776323242497,
      "grad_norm": 8.426005363464355,
      "learning_rate": 0.00018290375725550417,
      "loss": 0.4921,
      "step": 27
    },
    {
      "epoch": 0.0035244508779658885,
      "grad_norm": 6.269211292266846,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.5567,
      "step": 28
    },
    {
      "epoch": 0.0036503241236075274,
      "grad_norm": 4.1337480545043945,
      "learning_rate": 0.00017880107536067218,
      "loss": 0.0482,
      "step": 29
    },
    {
      "epoch": 0.003776197369249166,
      "grad_norm": 0.4672463834285736,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.0424,
      "step": 30
    },
    {
      "epoch": 0.003902070614890805,
      "grad_norm": 0.22993697226047516,
      "learning_rate": 0.00017431448254773944,
      "loss": 0.0041,
      "step": 31
    },
    {
      "epoch": 0.004027943860532444,
      "grad_norm": 1.7465827465057373,
      "learning_rate": 0.0001719339800338651,
      "loss": 0.0228,
      "step": 32
    },
    {
      "epoch": 0.004153817106174082,
      "grad_norm": 0.28992122411727905,
      "learning_rate": 0.00016946583704589973,
      "loss": 0.0067,
      "step": 33
    },
    {
      "epoch": 0.004279690351815722,
      "grad_norm": 0.9798206090927124,
      "learning_rate": 0.00016691306063588583,
      "loss": 0.0262,
      "step": 34
    },
    {
      "epoch": 0.004405563597457361,
      "grad_norm": 0.009784302674233913,
      "learning_rate": 0.00016427876096865394,
      "loss": 0.0007,
      "step": 35
    },
    {
      "epoch": 0.004531436843098999,
      "grad_norm": 2.536167860031128,
      "learning_rate": 0.0001615661475325658,
      "loss": 1.0487,
      "step": 36
    },
    {
      "epoch": 0.0046573100887406385,
      "grad_norm": 0.8000788688659668,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.0149,
      "step": 37
    },
    {
      "epoch": 0.004783183334382277,
      "grad_norm": 0.0,
      "learning_rate": 0.0001559192903470747,
      "loss": 0.0,
      "step": 38
    },
    {
      "epoch": 0.004909056580023916,
      "grad_norm": 0.015558776445686817,
      "learning_rate": 0.0001529919264233205,
      "loss": 0.0014,
      "step": 39
    },
    {
      "epoch": 0.005034929825665555,
      "grad_norm": 3.2701315879821777,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.2162,
      "step": 40
    },
    {
      "epoch": 0.005160803071307194,
      "grad_norm": 4.584814071655273,
      "learning_rate": 0.00014694715627858908,
      "loss": 0.8873,
      "step": 41
    },
    {
      "epoch": 0.005286676316948832,
      "grad_norm": 0.006552003789693117,
      "learning_rate": 0.00014383711467890774,
      "loss": 0.0004,
      "step": 42
    },
    {
      "epoch": 0.005412549562590472,
      "grad_norm": 3.2025034427642822,
      "learning_rate": 0.00014067366430758004,
      "loss": 0.2046,
      "step": 43
    },
    {
      "epoch": 0.00553842280823211,
      "grad_norm": 0.2174777388572693,
      "learning_rate": 0.00013746065934159123,
      "loss": 0.0041,
      "step": 44
    },
    {
      "epoch": 0.005664296053873749,
      "grad_norm": 0.0,
      "learning_rate": 0.00013420201433256689,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.005790169299515388,
      "grad_norm": 2.011909246444702,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.052,
      "step": 46
    },
    {
      "epoch": 0.005916042545157027,
      "grad_norm": 0.04959569871425629,
      "learning_rate": 0.0001275637355816999,
      "loss": 0.0016,
      "step": 47
    },
    {
      "epoch": 0.006041915790798665,
      "grad_norm": 9.175588607788086,
      "learning_rate": 0.00012419218955996676,
      "loss": 0.4144,
      "step": 48
    },
    {
      "epoch": 0.006167789036440305,
      "grad_norm": 1.922889232635498,
      "learning_rate": 0.00012079116908177593,
      "loss": 0.0746,
      "step": 49
    },
    {
      "epoch": 0.006293662282081943,
      "grad_norm": 3.5199947357177734,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.092,
      "step": 50
    },
    {
      "epoch": 0.006293662282081943,
      "eval_loss": NaN,
      "eval_runtime": 3519.1151,
      "eval_samples_per_second": 0.951,
      "eval_steps_per_second": 0.475,
      "step": 50
    },
    {
      "epoch": 0.006419535527723582,
      "grad_norm": 0.006420983001589775,
      "learning_rate": 0.00011391731009600654,
      "loss": 0.0011,
      "step": 51
    },
    {
      "epoch": 0.006545408773365222,
      "grad_norm": 0.5650655627250671,
      "learning_rate": 0.00011045284632676536,
      "loss": 0.0442,
      "step": 52
    },
    {
      "epoch": 0.00667128201900686,
      "grad_norm": 0.09890392422676086,
      "learning_rate": 0.00010697564737441252,
      "loss": 0.0048,
      "step": 53
    },
    {
      "epoch": 0.006797155264648499,
      "grad_norm": 0.05633799359202385,
      "learning_rate": 0.00010348994967025012,
      "loss": 0.002,
      "step": 54
    },
    {
      "epoch": 0.006923028510290138,
      "grad_norm": 3.1540989875793457,
      "learning_rate": 0.0001,
      "loss": 1.6562,
      "step": 55
    },
    {
      "epoch": 0.007048901755931777,
      "grad_norm": 5.062186241149902,
      "learning_rate": 9.651005032974994e-05,
      "loss": 0.2802,
      "step": 56
    },
    {
      "epoch": 0.007174775001573415,
      "grad_norm": 1.7618149518966675,
      "learning_rate": 9.302435262558747e-05,
      "loss": 0.1865,
      "step": 57
    },
    {
      "epoch": 0.007300648247215055,
      "grad_norm": 0.37688034772872925,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0144,
      "step": 58
    },
    {
      "epoch": 0.007426521492856693,
      "grad_norm": 0.11028943210840225,
      "learning_rate": 8.608268990399349e-05,
      "loss": 0.0063,
      "step": 59
    },
    {
      "epoch": 0.007552394738498332,
      "grad_norm": 0.5467414855957031,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.0118,
      "step": 60
    },
    {
      "epoch": 0.007678267984139971,
      "grad_norm": 0.029303928837180138,
      "learning_rate": 7.920883091822408e-05,
      "loss": 0.0006,
      "step": 61
    },
    {
      "epoch": 0.00780414122978161,
      "grad_norm": 0.16770148277282715,
      "learning_rate": 7.580781044003324e-05,
      "loss": 0.0068,
      "step": 62
    },
    {
      "epoch": 0.007930014475423248,
      "grad_norm": 0.1437792032957077,
      "learning_rate": 7.243626441830009e-05,
      "loss": 0.0024,
      "step": 63
    },
    {
      "epoch": 0.008055887721064888,
      "grad_norm": 0.11593683063983917,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0146,
      "step": 64
    },
    {
      "epoch": 0.008181760966706527,
      "grad_norm": 1.9799082279205322,
      "learning_rate": 6.579798566743314e-05,
      "loss": 0.0358,
      "step": 65
    },
    {
      "epoch": 0.008307634212348165,
      "grad_norm": 0.15605556964874268,
      "learning_rate": 6.25393406584088e-05,
      "loss": 0.0031,
      "step": 66
    },
    {
      "epoch": 0.008433507457989804,
      "grad_norm": 0.03782504051923752,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 0.0008,
      "step": 67
    },
    {
      "epoch": 0.008559380703631443,
      "grad_norm": 0.013293488882482052,
      "learning_rate": 5.616288532109225e-05,
      "loss": 0.0006,
      "step": 68
    },
    {
      "epoch": 0.008685253949273082,
      "grad_norm": 2.1244702339172363,
      "learning_rate": 5.305284372141095e-05,
      "loss": 0.3516,
      "step": 69
    },
    {
      "epoch": 0.008811127194914722,
      "grad_norm": 0.1244107261300087,
      "learning_rate": 5.000000000000002e-05,
      "loss": 0.0042,
      "step": 70
    },
    {
      "epoch": 0.00893700044055636,
      "grad_norm": 0.05394396558403969,
      "learning_rate": 4.700807357667952e-05,
      "loss": 0.0018,
      "step": 71
    },
    {
      "epoch": 0.009062873686197999,
      "grad_norm": 2.811530113220215,
      "learning_rate": 4.4080709652925336e-05,
      "loss": 0.2694,
      "step": 72
    },
    {
      "epoch": 0.009188746931839638,
      "grad_norm": 0.06051735207438469,
      "learning_rate": 4.12214747707527e-05,
      "loss": 0.0016,
      "step": 73
    },
    {
      "epoch": 0.009314620177481277,
      "grad_norm": 0.596136748790741,
      "learning_rate": 3.843385246743417e-05,
      "loss": 0.0087,
      "step": 74
    },
    {
      "epoch": 0.009440493423122915,
      "grad_norm": 0.11233700811862946,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.0045,
      "step": 75
    },
    {
      "epoch": 0.009440493423122915,
      "eval_loss": NaN,
      "eval_runtime": 3551.4208,
      "eval_samples_per_second": 0.942,
      "eval_steps_per_second": 0.471,
      "step": 75
    },
    {
      "epoch": 0.009566366668764554,
      "grad_norm": 0.09344177693128586,
      "learning_rate": 3.308693936411421e-05,
      "loss": 0.0053,
      "step": 76
    },
    {
      "epoch": 0.009692239914406193,
      "grad_norm": 0.017914390191435814,
      "learning_rate": 3.053416295410026e-05,
      "loss": 0.0009,
      "step": 77
    },
    {
      "epoch": 0.009818113160047832,
      "grad_norm": 0.14340530335903168,
      "learning_rate": 2.8066019966134904e-05,
      "loss": 0.007,
      "step": 78
    },
    {
      "epoch": 0.00994398640568947,
      "grad_norm": 2.4637436866760254,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 0.2807,
      "step": 79
    },
    {
      "epoch": 0.01006985965133111,
      "grad_norm": 0.016049662604928017,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.0003,
      "step": 80
    },
    {
      "epoch": 0.010195732896972749,
      "grad_norm": 5.916388511657715,
      "learning_rate": 2.119892463932781e-05,
      "loss": 1.0992,
      "step": 81
    },
    {
      "epoch": 0.010321606142614388,
      "grad_norm": 0.010422502644360065,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0005,
      "step": 82
    },
    {
      "epoch": 0.010447479388256025,
      "grad_norm": 3.361562728881836,
      "learning_rate": 1.7096242744495837e-05,
      "loss": 0.1324,
      "step": 83
    },
    {
      "epoch": 0.010573352633897665,
      "grad_norm": 0.04859397932887077,
      "learning_rate": 1.5195190384357404e-05,
      "loss": 0.0013,
      "step": 84
    },
    {
      "epoch": 0.010699225879539304,
      "grad_norm": 0.023048996925354004,
      "learning_rate": 1.339745962155613e-05,
      "loss": 0.0011,
      "step": 85
    },
    {
      "epoch": 0.010825099125180943,
      "grad_norm": 0.02878495492041111,
      "learning_rate": 1.1705240714107302e-05,
      "loss": 0.0012,
      "step": 86
    },
    {
      "epoch": 0.010950972370822582,
      "grad_norm": 0.03888264298439026,
      "learning_rate": 1.0120595370083318e-05,
      "loss": 0.0033,
      "step": 87
    },
    {
      "epoch": 0.01107684561646422,
      "grad_norm": 3.1203830242156982,
      "learning_rate": 8.645454235739903e-06,
      "loss": 0.1787,
      "step": 88
    },
    {
      "epoch": 0.01120271886210586,
      "grad_norm": 3.7907369136810303,
      "learning_rate": 7.281614543321269e-06,
      "loss": 0.3365,
      "step": 89
    },
    {
      "epoch": 0.011328592107747499,
      "grad_norm": 2.6835732460021973,
      "learning_rate": 6.030737921409169e-06,
      "loss": 0.0975,
      "step": 90
    },
    {
      "epoch": 0.011454465353389138,
      "grad_norm": 0.0066988165490329266,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 0.0004,
      "step": 91
    },
    {
      "epoch": 0.011580338599030775,
      "grad_norm": 0.0022131705190986395,
      "learning_rate": 3.873830406168111e-06,
      "loss": 0.0004,
      "step": 92
    },
    {
      "epoch": 0.011706211844672415,
      "grad_norm": 0.01956171914935112,
      "learning_rate": 2.970427372400353e-06,
      "loss": 0.0015,
      "step": 93
    },
    {
      "epoch": 0.011832085090314054,
      "grad_norm": 0.0475313700735569,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 0.0016,
      "step": 94
    },
    {
      "epoch": 0.011957958335955693,
      "grad_norm": 3.4122633934020996,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 0.7071,
      "step": 95
    },
    {
      "epoch": 0.01208383158159733,
      "grad_norm": 0.13446319103240967,
      "learning_rate": 9.731931258429638e-07,
      "loss": 0.0256,
      "step": 96
    },
    {
      "epoch": 0.01220970482723897,
      "grad_norm": 0.10620174556970596,
      "learning_rate": 5.478104631726711e-07,
      "loss": 0.0039,
      "step": 97
    },
    {
      "epoch": 0.01233557807288061,
      "grad_norm": 0.5097644329071045,
      "learning_rate": 2.4359497401758024e-07,
      "loss": 0.0671,
      "step": 98
    },
    {
      "epoch": 0.012461451318522249,
      "grad_norm": 1.6247103214263916,
      "learning_rate": 6.09172980904238e-08,
      "loss": 0.0878,
      "step": 99
    },
    {
      "epoch": 0.012587324564163886,
      "grad_norm": 0.002280471846461296,
      "learning_rate": 0.0,
      "loss": 0.0001,
      "step": 100
    },
    {
      "epoch": 0.012587324564163886,
      "eval_loss": NaN,
      "eval_runtime": 3565.9397,
      "eval_samples_per_second": 0.938,
      "eval_steps_per_second": 0.469,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.5853840162816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}