{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.4868131868131869,
  "eval_steps": 36,
  "global_step": 213,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007032967032967033,
      "grad_norm": 35.26959420627133,
      "learning_rate": 3.7037037037037036e-07,
      "loss": 1.2446,
      "step": 1
    },
    {
      "epoch": 0.007032967032967033,
      "eval_loss": 2.0324625968933105,
      "eval_runtime": 226.4201,
      "eval_samples_per_second": 13.705,
      "eval_steps_per_second": 3.427,
      "step": 1
    },
    {
      "epoch": 0.014065934065934066,
      "grad_norm": 36.83848200011581,
      "learning_rate": 7.407407407407407e-07,
      "loss": 1.2517,
      "step": 2
    },
    {
      "epoch": 0.0210989010989011,
      "grad_norm": 34.19087139357936,
      "learning_rate": 1.111111111111111e-06,
      "loss": 1.2471,
      "step": 3
    },
    {
      "epoch": 0.028131868131868132,
      "grad_norm": 27.541225332943558,
      "learning_rate": 1.4814814814814815e-06,
      "loss": 1.2362,
      "step": 4
    },
    {
      "epoch": 0.035164835164835165,
      "grad_norm": 15.57856703468476,
      "learning_rate": 1.8518518518518519e-06,
      "loss": 1.2332,
      "step": 5
    },
    {
      "epoch": 0.0421978021978022,
      "grad_norm": 8.528472835565562,
      "learning_rate": 2.222222222222222e-06,
      "loss": 1.2307,
      "step": 6
    },
    {
      "epoch": 0.04923076923076923,
      "grad_norm": 16.759402720703044,
      "learning_rate": 2.5925925925925925e-06,
      "loss": 1.199,
      "step": 7
    },
    {
      "epoch": 0.056263736263736264,
      "grad_norm": 18.137822554727045,
      "learning_rate": 2.962962962962963e-06,
      "loss": 1.1867,
      "step": 8
    },
    {
      "epoch": 0.0632967032967033,
      "grad_norm": 10.608949122260702,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.1342,
      "step": 9
    },
    {
      "epoch": 0.07032967032967033,
      "grad_norm": 9.138194583762399,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 1.1253,
      "step": 10
    },
    {
      "epoch": 0.07736263736263736,
      "grad_norm": 7.585351194968479,
      "learning_rate": 4.074074074074074e-06,
      "loss": 1.0929,
      "step": 11
    },
    {
      "epoch": 0.0843956043956044,
      "grad_norm": 3.1314432257964384,
      "learning_rate": 4.444444444444444e-06,
      "loss": 1.1159,
      "step": 12
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 1.9754939241031118,
      "learning_rate": 4.814814814814815e-06,
      "loss": 1.0872,
      "step": 13
    },
    {
      "epoch": 0.09846153846153846,
      "grad_norm": 2.333789509418066,
      "learning_rate": 5.185185185185185e-06,
      "loss": 1.0829,
      "step": 14
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 2.0991930564058823,
      "learning_rate": 5.555555555555557e-06,
      "loss": 1.0723,
      "step": 15
    },
    {
      "epoch": 0.11252747252747253,
      "grad_norm": 1.6926854903696387,
      "learning_rate": 5.925925925925926e-06,
      "loss": 1.0419,
      "step": 16
    },
    {
      "epoch": 0.11956043956043956,
      "grad_norm": 2.1909718155790214,
      "learning_rate": 6.296296296296297e-06,
      "loss": 1.0298,
      "step": 17
    },
    {
      "epoch": 0.1265934065934066,
      "grad_norm": 1.3067568935177465,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.0151,
      "step": 18
    },
    {
      "epoch": 0.13362637362637364,
      "grad_norm": 1.2377225828827996,
      "learning_rate": 7.0370370370370375e-06,
      "loss": 0.999,
      "step": 19
    },
    {
      "epoch": 0.14065934065934066,
      "grad_norm": 1.18450679388531,
      "learning_rate": 7.4074074074074075e-06,
      "loss": 1.0112,
      "step": 20
    },
    {
      "epoch": 0.1476923076923077,
      "grad_norm": 1.1838798074824592,
      "learning_rate": 7.77777777777778e-06,
      "loss": 1.0103,
      "step": 21
    },
    {
      "epoch": 0.15472527472527473,
      "grad_norm": 1.6373782903630898,
      "learning_rate": 8.148148148148148e-06,
      "loss": 0.9852,
      "step": 22
    },
    {
      "epoch": 0.16175824175824177,
      "grad_norm": 1.0047054227944252,
      "learning_rate": 8.518518518518519e-06,
      "loss": 0.9733,
      "step": 23
    },
    {
      "epoch": 0.1687912087912088,
      "grad_norm": 1.0931935152651058,
      "learning_rate": 8.888888888888888e-06,
      "loss": 0.9684,
      "step": 24
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 1.7486444656061693,
      "learning_rate": 9.25925925925926e-06,
      "loss": 0.9604,
      "step": 25
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 1.0797697063478033,
      "learning_rate": 9.62962962962963e-06,
      "loss": 0.9545,
      "step": 26
    },
    {
      "epoch": 0.1898901098901099,
      "grad_norm": 1.33357617818566,
      "learning_rate": 1e-05,
      "loss": 0.952,
      "step": 27
    },
    {
      "epoch": 0.19692307692307692,
      "grad_norm": 1.3658902210874033,
      "learning_rate": 9.999626433348664e-06,
      "loss": 0.9361,
      "step": 28
    },
    {
      "epoch": 0.20395604395604397,
      "grad_norm": 0.9917827240952933,
      "learning_rate": 9.998505789215469e-06,
      "loss": 0.9421,
      "step": 29
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 1.1470622779223378,
      "learning_rate": 9.996638235054527e-06,
      "loss": 0.931,
      "step": 30
    },
    {
      "epoch": 0.21802197802197804,
      "grad_norm": 1.0091725798819224,
      "learning_rate": 9.994024049928222e-06,
      "loss": 0.923,
      "step": 31
    },
    {
      "epoch": 0.22505494505494505,
      "grad_norm": 1.1504273652433235,
      "learning_rate": 9.990663624465504e-06,
      "loss": 0.912,
      "step": 32
    },
    {
      "epoch": 0.2320879120879121,
      "grad_norm": 0.9664429874093261,
      "learning_rate": 9.986557460803527e-06,
      "loss": 0.896,
      "step": 33
    },
    {
      "epoch": 0.23912087912087912,
      "grad_norm": 1.1282340407259235,
      "learning_rate": 9.98170617251262e-06,
      "loss": 0.8983,
      "step": 34
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 0.8113157988650623,
      "learning_rate": 9.976110484504587e-06,
      "loss": 0.9127,
      "step": 35
    },
    {
      "epoch": 0.2531868131868132,
      "grad_norm": 0.8682114462819939,
      "learning_rate": 9.969771232924404e-06,
      "loss": 0.8915,
      "step": 36
    },
    {
      "epoch": 0.2531868131868132,
      "eval_loss": 1.6713504791259766,
      "eval_runtime": 226.2942,
      "eval_samples_per_second": 13.712,
      "eval_steps_per_second": 3.429,
      "step": 36
    },
    {
      "epoch": 0.2602197802197802,
      "grad_norm": 0.9962271463149754,
      "learning_rate": 9.962689365025259e-06,
      "loss": 0.8931,
      "step": 37
    },
    {
      "epoch": 0.2672527472527473,
      "grad_norm": 1.0334672110868601,
      "learning_rate": 9.954865939027028e-06,
      "loss": 0.8686,
      "step": 38
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 1.0817099930756773,
      "learning_rate": 9.94630212395813e-06,
      "loss": 0.8723,
      "step": 39
    },
    {
      "epoch": 0.2813186813186813,
      "grad_norm": 0.9550865674827331,
      "learning_rate": 9.936999199480854e-06,
      "loss": 0.8652,
      "step": 40
    },
    {
      "epoch": 0.28835164835164834,
      "grad_norm": 0.721743556234875,
      "learning_rate": 9.926958555700134e-06,
      "loss": 0.8811,
      "step": 41
    },
    {
      "epoch": 0.2953846153846154,
      "grad_norm": 0.8648576858639633,
      "learning_rate": 9.916181692955841e-06,
      "loss": 0.8679,
      "step": 42
    },
    {
      "epoch": 0.30241758241758243,
      "grad_norm": 0.9727121051173584,
      "learning_rate": 9.90467022159859e-06,
      "loss": 0.8833,
      "step": 43
    },
    {
      "epoch": 0.30945054945054945,
      "grad_norm": 0.8209899450978613,
      "learning_rate": 9.8924258617491e-06,
      "loss": 0.8692,
      "step": 44
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.8102558598398344,
      "learning_rate": 9.879450443041172e-06,
      "loss": 0.8649,
      "step": 45
    },
    {
      "epoch": 0.32351648351648354,
      "grad_norm": 0.7780994681889157,
      "learning_rate": 9.865745904348296e-06,
      "loss": 0.8616,
      "step": 46
    },
    {
      "epoch": 0.33054945054945056,
      "grad_norm": 0.846186796164239,
      "learning_rate": 9.851314293493923e-06,
      "loss": 0.8537,
      "step": 47
    },
    {
      "epoch": 0.3375824175824176,
      "grad_norm": 0.888533727866688,
      "learning_rate": 9.836157766945467e-06,
      "loss": 0.8521,
      "step": 48
    },
    {
      "epoch": 0.3446153846153846,
      "grad_norm": 0.7390076763494808,
      "learning_rate": 9.820278589492076e-06,
      "loss": 0.8634,
      "step": 49
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 0.7427563819683852,
      "learning_rate": 9.80367913390621e-06,
      "loss": 0.8497,
      "step": 50
    },
    {
      "epoch": 0.3586813186813187,
      "grad_norm": 0.8828003502820779,
      "learning_rate": 9.786361880589084e-06,
      "loss": 0.8411,
      "step": 51
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.8404598366983553,
      "learning_rate": 9.768329417200029e-06,
      "loss": 0.8503,
      "step": 52
    },
    {
      "epoch": 0.37274725274725273,
      "grad_norm": 0.7409532940009589,
      "learning_rate": 9.749584438269833e-06,
      "loss": 0.8472,
      "step": 53
    },
    {
      "epoch": 0.3797802197802198,
      "grad_norm": 0.704480780825874,
      "learning_rate": 9.730129744798096e-06,
      "loss": 0.8481,
      "step": 54
    },
    {
      "epoch": 0.3868131868131868,
      "grad_norm": 0.8434855833377527,
      "learning_rate": 9.709968243834698e-06,
      "loss": 0.839,
      "step": 55
    },
    {
      "epoch": 0.39384615384615385,
      "grad_norm": 0.9683384695522282,
      "learning_rate": 9.689102948045398e-06,
      "loss": 0.8313,
      "step": 56
    },
    {
      "epoch": 0.40087912087912086,
      "grad_norm": 0.9186046603340778,
      "learning_rate": 9.667536975261667e-06,
      "loss": 0.8233,
      "step": 57
    },
    {
      "epoch": 0.40791208791208794,
      "grad_norm": 0.7511022110825254,
      "learning_rate": 9.6452735480148e-06,
      "loss": 0.8241,
      "step": 58
    },
    {
      "epoch": 0.41494505494505496,
      "grad_norm": 0.7183393918795576,
      "learning_rate": 9.622315993054384e-06,
      "loss": 0.8248,
      "step": 59
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.6656476000626029,
      "learning_rate": 9.598667740851187e-06,
      "loss": 0.8231,
      "step": 60
    },
    {
      "epoch": 0.429010989010989,
      "grad_norm": 0.6850840786935145,
      "learning_rate": 9.574332325084564e-06,
      "loss": 0.8183,
      "step": 61
    },
    {
      "epoch": 0.43604395604395607,
      "grad_norm": 0.8678005280431648,
      "learning_rate": 9.549313382114427e-06,
      "loss": 0.8266,
      "step": 62
    },
    {
      "epoch": 0.4430769230769231,
      "grad_norm": 0.778515033629181,
      "learning_rate": 9.523614650437876e-06,
      "loss": 0.831,
      "step": 63
    },
    {
      "epoch": 0.4501098901098901,
      "grad_norm": 0.7952968005831371,
      "learning_rate": 9.497239970130561e-06,
      "loss": 0.8277,
      "step": 64
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 0.6755106613138295,
      "learning_rate": 9.470193282272886e-06,
      "loss": 0.8193,
      "step": 65
    },
    {
      "epoch": 0.4641758241758242,
      "grad_norm": 0.6472446322999437,
      "learning_rate": 9.442478628361098e-06,
      "loss": 0.8191,
      "step": 66
    },
    {
      "epoch": 0.4712087912087912,
      "grad_norm": 0.6592803480610206,
      "learning_rate": 9.414100149703373e-06,
      "loss": 0.8092,
      "step": 67
    },
    {
      "epoch": 0.47824175824175824,
      "grad_norm": 0.6147517002023887,
      "learning_rate": 9.385062086801013e-06,
      "loss": 0.8207,
      "step": 68
    },
    {
      "epoch": 0.48527472527472526,
      "grad_norm": 0.7006129357637451,
      "learning_rate": 9.355368778714784e-06,
      "loss": 0.8088,
      "step": 69
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 0.8466485623047939,
      "learning_rate": 9.325024662416553e-06,
      "loss": 0.8079,
      "step": 70
    },
    {
      "epoch": 0.49934065934065935,
      "grad_norm": 0.6702085323484384,
      "learning_rate": 9.294034272126286e-06,
      "loss": 0.8058,
      "step": 71
    },
    {
      "epoch": 0.5063736263736264,
      "grad_norm": 0.6407728805954488,
      "learning_rate": 9.262402238634514e-06,
      "loss": 0.8262,
      "step": 72
    },
    {
      "epoch": 0.5063736263736264,
      "eval_loss": 1.599279522895813,
      "eval_runtime": 226.9414,
      "eval_samples_per_second": 13.673,
      "eval_steps_per_second": 3.419,
      "step": 72
    },
    {
      "epoch": 0.5134065934065934,
      "grad_norm": 0.7583031052152963,
      "learning_rate": 9.230133288610366e-06,
      "loss": 0.816,
      "step": 73
    },
    {
      "epoch": 0.5204395604395604,
      "grad_norm": 0.6318364253543153,
      "learning_rate": 9.197232243895285e-06,
      "loss": 0.8071,
      "step": 74
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.6568566221486245,
      "learning_rate": 9.163704020782507e-06,
      "loss": 0.8073,
      "step": 75
    },
    {
      "epoch": 0.5345054945054946,
      "grad_norm": 0.7717955800373636,
      "learning_rate": 9.129553629282448e-06,
      "loss": 0.8139,
      "step": 76
    },
    {
      "epoch": 0.5415384615384615,
      "grad_norm": 0.6843074458720456,
      "learning_rate": 9.094786172374066e-06,
      "loss": 0.7947,
      "step": 77
    },
    {
      "epoch": 0.5485714285714286,
      "grad_norm": 0.5785589869406929,
      "learning_rate": 9.059406845242343e-06,
      "loss": 0.8037,
      "step": 78
    },
    {
      "epoch": 0.5556043956043956,
      "grad_norm": 0.7307405632179867,
      "learning_rate": 9.023420934501981e-06,
      "loss": 0.791,
      "step": 79
    },
    {
      "epoch": 0.5626373626373626,
      "grad_norm": 0.624688349109228,
      "learning_rate": 8.98683381740745e-06,
      "loss": 0.8101,
      "step": 80
    },
    {
      "epoch": 0.5696703296703297,
      "grad_norm": 0.6529550895634888,
      "learning_rate": 8.949650961049479e-06,
      "loss": 0.795,
      "step": 81
    },
    {
      "epoch": 0.5767032967032967,
      "grad_norm": 0.7439504174496507,
      "learning_rate": 8.911877921538117e-06,
      "loss": 0.7953,
      "step": 82
    },
    {
      "epoch": 0.5837362637362637,
      "grad_norm": 0.607525650080481,
      "learning_rate": 8.87352034317252e-06,
      "loss": 0.8085,
      "step": 83
    },
    {
      "epoch": 0.5907692307692308,
      "grad_norm": 0.6363605072935006,
      "learning_rate": 8.83458395759753e-06,
      "loss": 0.8009,
      "step": 84
    },
    {
      "epoch": 0.5978021978021978,
      "grad_norm": 0.80304305040893,
      "learning_rate": 8.795074582947214e-06,
      "loss": 0.7937,
      "step": 85
    },
    {
      "epoch": 0.6048351648351649,
      "grad_norm": 0.7186872256432066,
      "learning_rate": 8.754998122975489e-06,
      "loss": 0.8059,
      "step": 86
    },
    {
      "epoch": 0.6118681318681318,
      "grad_norm": 0.7583738305755567,
      "learning_rate": 8.714360566173932e-06,
      "loss": 0.8056,
      "step": 87
    },
    {
      "epoch": 0.6189010989010989,
      "grad_norm": 0.6845388006016243,
      "learning_rate": 8.67316798487695e-06,
      "loss": 0.7946,
      "step": 88
    },
    {
      "epoch": 0.625934065934066,
      "grad_norm": 0.52893400556635,
      "learning_rate": 8.631426534354404e-06,
      "loss": 0.7991,
      "step": 89
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.562141119911408,
      "learning_rate": 8.589142451891849e-06,
      "loss": 0.7895,
      "step": 90
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.5986754251442403,
      "learning_rate": 8.546322055858526e-06,
      "loss": 0.7997,
      "step": 91
    },
    {
      "epoch": 0.6470329670329671,
      "grad_norm": 0.585680730864744,
      "learning_rate": 8.502971744763216e-06,
      "loss": 0.7942,
      "step": 92
    },
    {
      "epoch": 0.654065934065934,
      "grad_norm": 0.5372905314311949,
      "learning_rate": 8.459097996298137e-06,
      "loss": 0.7997,
      "step": 93
    },
    {
      "epoch": 0.6610989010989011,
      "grad_norm": 0.5670305768190042,
      "learning_rate": 8.414707366371006e-06,
      "loss": 0.7929,
      "step": 94
    },
    {
      "epoch": 0.6681318681318681,
      "grad_norm": 0.5573782301950155,
      "learning_rate": 8.369806488125418e-06,
      "loss": 0.7854,
      "step": 95
    },
    {
      "epoch": 0.6751648351648352,
      "grad_norm": 0.5677519493613411,
      "learning_rate": 8.324402070949658e-06,
      "loss": 0.7914,
      "step": 96
    },
    {
      "epoch": 0.6821978021978022,
      "grad_norm": 0.5914729175606039,
      "learning_rate": 8.278500899474162e-06,
      "loss": 0.787,
      "step": 97
    },
    {
      "epoch": 0.6892307692307692,
      "grad_norm": 0.5233289657421258,
      "learning_rate": 8.232109832557696e-06,
      "loss": 0.7848,
      "step": 98
    },
    {
      "epoch": 0.6962637362637363,
      "grad_norm": 0.5547427081220171,
      "learning_rate": 8.18523580226247e-06,
      "loss": 0.7707,
      "step": 99
    },
    {
      "epoch": 0.7032967032967034,
      "grad_norm": 0.6955676830431037,
      "learning_rate": 8.137885812818296e-06,
      "loss": 0.7728,
      "step": 100
    },
    {
      "epoch": 0.7103296703296703,
      "grad_norm": 0.7045349043398937,
      "learning_rate": 8.090066939575972e-06,
      "loss": 0.7715,
      "step": 101
    },
    {
      "epoch": 0.7173626373626374,
      "grad_norm": 0.6443893217574687,
      "learning_rate": 8.041786327950037e-06,
      "loss": 0.777,
      "step": 102
    },
    {
      "epoch": 0.7243956043956044,
      "grad_norm": 0.6026841629687064,
      "learning_rate": 7.993051192351056e-06,
      "loss": 0.7925,
      "step": 103
    },
    {
      "epoch": 0.7314285714285714,
      "grad_norm": 0.5850830356296551,
      "learning_rate": 7.943868815107594e-06,
      "loss": 0.7644,
      "step": 104
    },
    {
      "epoch": 0.7384615384615385,
      "grad_norm": 0.7999343109870123,
      "learning_rate": 7.894246545378037e-06,
      "loss": 0.7754,
      "step": 105
    },
    {
      "epoch": 0.7454945054945055,
      "grad_norm": 0.7343984497545941,
      "learning_rate": 7.844191798052438e-06,
      "loss": 0.7904,
      "step": 106
    },
    {
      "epoch": 0.7525274725274725,
      "grad_norm": 0.5774072895167719,
      "learning_rate": 7.793712052644535e-06,
      "loss": 0.7851,
      "step": 107
    },
    {
      "epoch": 0.7595604395604396,
      "grad_norm": 0.6957073884866434,
      "learning_rate": 7.742814852174112e-06,
      "loss": 0.7705,
      "step": 108
    },
    {
      "epoch": 0.7595604395604396,
      "eval_loss": 1.568657398223877,
      "eval_runtime": 225.5453,
      "eval_samples_per_second": 13.758,
      "eval_steps_per_second": 3.441,
      "step": 108
    },
    {
      "epoch": 0.7665934065934066,
      "grad_norm": 0.7848099301993303,
      "learning_rate": 7.691507802039861e-06,
      "loss": 0.7667,
      "step": 109
    },
    {
      "epoch": 0.7736263736263737,
      "grad_norm": 0.5890076385548152,
      "learning_rate": 7.639798568882947e-06,
      "loss": 0.7654,
      "step": 110
    },
    {
      "epoch": 0.7806593406593406,
      "grad_norm": 0.66395733723176,
      "learning_rate": 7.5876948794414015e-06,
      "loss": 0.7891,
      "step": 111
    },
    {
      "epoch": 0.7876923076923077,
      "grad_norm": 0.6066531044825103,
      "learning_rate": 7.535204519395538e-06,
      "loss": 0.7876,
      "step": 112
    },
    {
      "epoch": 0.7947252747252748,
      "grad_norm": 0.6726394793172733,
      "learning_rate": 7.482335332204568e-06,
      "loss": 0.7623,
      "step": 113
    },
    {
      "epoch": 0.8017582417582417,
      "grad_norm": 0.6147140261019698,
      "learning_rate": 7.429095217934578e-06,
      "loss": 0.7723,
      "step": 114
    },
    {
      "epoch": 0.8087912087912088,
      "grad_norm": 0.5959989276123557,
      "learning_rate": 7.375492132078051e-06,
      "loss": 0.7689,
      "step": 115
    },
    {
      "epoch": 0.8158241758241759,
      "grad_norm": 0.7546232716676239,
      "learning_rate": 7.321534084365101e-06,
      "loss": 0.7789,
      "step": 116
    },
    {
      "epoch": 0.8228571428571428,
      "grad_norm": 0.4958344733247894,
      "learning_rate": 7.267229137566607e-06,
      "loss": 0.7766,
      "step": 117
    },
    {
      "epoch": 0.8298901098901099,
      "grad_norm": 0.6580768669811061,
      "learning_rate": 7.2125854062894184e-06,
      "loss": 0.7741,
      "step": 118
    },
    {
      "epoch": 0.8369230769230769,
      "grad_norm": 0.582649581214651,
      "learning_rate": 7.15761105576382e-06,
      "loss": 0.77,
      "step": 119
    },
    {
      "epoch": 0.843956043956044,
      "grad_norm": 0.7084036185253777,
      "learning_rate": 7.102314300623425e-06,
      "loss": 0.7556,
      "step": 120
    },
    {
      "epoch": 0.850989010989011,
      "grad_norm": 0.6176038580158096,
      "learning_rate": 7.0467034036776945e-06,
      "loss": 0.7624,
      "step": 121
    },
    {
      "epoch": 0.858021978021978,
      "grad_norm": 0.6193127391409796,
      "learning_rate": 6.990786674677246e-06,
      "loss": 0.7699,
      "step": 122
    },
    {
      "epoch": 0.8650549450549451,
      "grad_norm": 0.5136851770278229,
      "learning_rate": 6.934572469072163e-06,
      "loss": 0.7586,
      "step": 123
    },
    {
      "epoch": 0.8720879120879121,
      "grad_norm": 0.5414980080981208,
      "learning_rate": 6.878069186763466e-06,
      "loss": 0.7647,
      "step": 124
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.5298901704966885,
      "learning_rate": 6.821285270847934e-06,
      "loss": 0.7638,
      "step": 125
    },
    {
      "epoch": 0.8861538461538462,
      "grad_norm": 0.536579104438463,
      "learning_rate": 6.764229206356498e-06,
      "loss": 0.7718,
      "step": 126
    },
    {
      "epoch": 0.8931868131868131,
      "grad_norm": 0.5513753693058956,
      "learning_rate": 6.706909518986341e-06,
      "loss": 0.7557,
      "step": 127
    },
    {
      "epoch": 0.9002197802197802,
      "grad_norm": 0.541397328359122,
      "learning_rate": 6.649334773826924e-06,
      "loss": 0.7519,
      "step": 128
    },
    {
      "epoch": 0.9072527472527473,
      "grad_norm": 0.4984745030205108,
      "learning_rate": 6.591513574080152e-06,
      "loss": 0.7877,
      "step": 129
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.5218531200041907,
      "learning_rate": 6.5334545597748075e-06,
      "loss": 0.7713,
      "step": 130
    },
    {
      "epoch": 0.9213186813186813,
      "grad_norm": 0.5317339972640247,
      "learning_rate": 6.475166406475515e-06,
      "loss": 0.7455,
      "step": 131
    },
    {
      "epoch": 0.9283516483516484,
      "grad_norm": 0.5131963532051536,
      "learning_rate": 6.41665782398637e-06,
      "loss": 0.7582,
      "step": 132
    },
    {
      "epoch": 0.9353846153846154,
      "grad_norm": 0.5202136619940336,
      "learning_rate": 6.357937555049465e-06,
      "loss": 0.7484,
      "step": 133
    },
    {
      "epoch": 0.9424175824175824,
      "grad_norm": 0.5191886467339242,
      "learning_rate": 6.299014374038493e-06,
      "loss": 0.772,
      "step": 134
    },
    {
      "epoch": 0.9494505494505494,
      "grad_norm": 0.5650396432233695,
      "learning_rate": 6.239897085647624e-06,
      "loss": 0.7372,
      "step": 135
    },
    {
      "epoch": 0.9564835164835165,
      "grad_norm": 0.5009481153808558,
      "learning_rate": 6.180594523575838e-06,
      "loss": 0.7615,
      "step": 136
    },
    {
      "epoch": 0.9635164835164836,
      "grad_norm": 0.5009820597229956,
      "learning_rate": 6.12111554920695e-06,
      "loss": 0.7549,
      "step": 137
    },
    {
      "epoch": 0.9705494505494505,
      "grad_norm": 0.504199654644018,
      "learning_rate": 6.061469050285469e-06,
      "loss": 0.7624,
      "step": 138
    },
    {
      "epoch": 0.9775824175824176,
      "grad_norm": 0.4908461913624682,
      "learning_rate": 6.0016639395885424e-06,
      "loss": 0.7444,
      "step": 139
    },
    {
      "epoch": 0.9846153846153847,
      "grad_norm": 0.5554236899312124,
      "learning_rate": 5.941709153594146e-06,
      "loss": 0.757,
      "step": 140
    },
    {
      "epoch": 0.9916483516483516,
      "grad_norm": 0.627089978818849,
      "learning_rate": 5.881613651145732e-06,
      "loss": 0.7465,
      "step": 141
    },
    {
      "epoch": 0.9986813186813187,
      "grad_norm": 0.5613844035445381,
      "learning_rate": 5.821386412113546e-06,
      "loss": 0.7643,
      "step": 142
    },
    {
      "epoch": 1.0057142857142858,
      "grad_norm": 0.481627058589778,
      "learning_rate": 5.761036436052788e-06,
      "loss": 0.7515,
      "step": 143
    },
    {
      "epoch": 1.0015384615384615,
      "grad_norm": 0.5657262479926654,
      "learning_rate": 5.700572740858847e-06,
      "loss": 0.7547,
      "step": 144
    },
    {
      "epoch": 1.0015384615384615,
      "eval_loss": 1.5540971755981445,
      "eval_runtime": 225.9682,
      "eval_samples_per_second": 13.732,
      "eval_steps_per_second": 3.434,
      "step": 144
    },
    {
      "epoch": 1.0085714285714287,
      "grad_norm": 0.7044866764167006,
      "learning_rate": 5.640004361419776e-06,
      "loss": 0.6997,
      "step": 145
    },
    {
      "epoch": 1.0156043956043956,
      "grad_norm": 0.7035496400173301,
      "learning_rate": 5.579340348266251e-06,
      "loss": 0.7128,
      "step": 146
    },
    {
      "epoch": 1.0226373626373626,
      "grad_norm": 0.7064639323234874,
      "learning_rate": 5.518589766219173e-06,
      "loss": 0.7144,
      "step": 147
    },
    {
      "epoch": 1.0296703296703296,
      "grad_norm": 0.7971240631744954,
      "learning_rate": 5.457761693035139e-06,
      "loss": 0.6987,
      "step": 148
    },
    {
      "epoch": 1.0367032967032968,
      "grad_norm": 0.558357704286495,
      "learning_rate": 5.396865218049995e-06,
      "loss": 0.6993,
      "step": 149
    },
    {
      "epoch": 1.0437362637362637,
      "grad_norm": 0.756627096578572,
      "learning_rate": 5.335909440820635e-06,
      "loss": 0.6944,
      "step": 150
    },
    {
      "epoch": 1.0507692307692307,
      "grad_norm": 0.6399997539019588,
      "learning_rate": 5.27490346976529e-06,
      "loss": 0.7065,
      "step": 151
    },
    {
      "epoch": 1.0578021978021979,
      "grad_norm": 0.671365696382851,
      "learning_rate": 5.21385642080249e-06,
      "loss": 0.6901,
      "step": 152
    },
    {
      "epoch": 1.0648351648351648,
      "grad_norm": 0.7118806590752661,
      "learning_rate": 5.152777415988894e-06,
      "loss": 0.6958,
      "step": 153
    },
    {
      "epoch": 1.0718681318681318,
      "grad_norm": 0.6792290355353818,
      "learning_rate": 5.091675582156224e-06,
      "loss": 0.696,
      "step": 154
    },
    {
      "epoch": 1.078901098901099,
      "grad_norm": 0.6848137162218305,
      "learning_rate": 5.0305600495474586e-06,
      "loss": 0.7088,
      "step": 155
    },
    {
      "epoch": 1.085934065934066,
      "grad_norm": 0.7159849638970576,
      "learning_rate": 4.969439950452543e-06,
      "loss": 0.7031,
      "step": 156
    },
    {
      "epoch": 1.092967032967033,
      "grad_norm": 0.6300333557911728,
      "learning_rate": 4.908324417843779e-06,
      "loss": 0.7007,
      "step": 157
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.7043936127658559,
      "learning_rate": 4.847222584011107e-06,
      "loss": 0.6994,
      "step": 158
    },
    {
      "epoch": 1.107032967032967,
      "grad_norm": 0.6867413622419056,
      "learning_rate": 4.7861435791975124e-06,
      "loss": 0.6935,
      "step": 159
    },
    {
      "epoch": 1.114065934065934,
      "grad_norm": 0.6538416822081471,
      "learning_rate": 4.72509653023471e-06,
      "loss": 0.6941,
      "step": 160
    },
    {
      "epoch": 1.1210989010989012,
      "grad_norm": 0.7020985463183896,
      "learning_rate": 4.664090559179367e-06,
      "loss": 0.7048,
      "step": 161
    },
    {
      "epoch": 1.1281318681318682,
      "grad_norm": 0.5772539183951623,
      "learning_rate": 4.603134781950007e-06,
      "loss": 0.6935,
      "step": 162
    },
    {
      "epoch": 1.1351648351648351,
      "grad_norm": 0.6904805292612487,
      "learning_rate": 4.542238306964863e-06,
      "loss": 0.6833,
      "step": 163
    },
    {
      "epoch": 1.1421978021978023,
      "grad_norm": 0.5106506921363563,
      "learning_rate": 4.48141023378083e-06,
      "loss": 0.6853,
      "step": 164
    },
    {
      "epoch": 1.1492307692307693,
      "grad_norm": 0.666628487493406,
      "learning_rate": 4.420659651733751e-06,
      "loss": 0.6989,
      "step": 165
    },
    {
      "epoch": 1.1562637362637362,
      "grad_norm": 0.5494302202195188,
      "learning_rate": 4.359995638580226e-06,
      "loss": 0.6958,
      "step": 166
    },
    {
      "epoch": 1.1632967032967032,
      "grad_norm": 0.6245450783892555,
      "learning_rate": 4.299427259141155e-06,
      "loss": 0.7012,
      "step": 167
    },
    {
      "epoch": 1.1703296703296704,
      "grad_norm": 0.5884535676395213,
      "learning_rate": 4.238963563947212e-06,
      "loss": 0.6869,
      "step": 168
    },
    {
      "epoch": 1.1773626373626374,
      "grad_norm": 0.5775278896688378,
      "learning_rate": 4.178613587886455e-06,
      "loss": 0.6977,
      "step": 169
    },
    {
      "epoch": 1.1843956043956043,
      "grad_norm": 0.5884501150840619,
      "learning_rate": 4.1183863488542686e-06,
      "loss": 0.6896,
      "step": 170
    },
    {
      "epoch": 1.1914285714285715,
      "grad_norm": 0.6243380627891476,
      "learning_rate": 4.058290846405856e-06,
      "loss": 0.6769,
      "step": 171
    },
    {
      "epoch": 1.1984615384615385,
      "grad_norm": 0.5198772958280654,
      "learning_rate": 3.998336060411459e-06,
      "loss": 0.6819,
      "step": 172
    },
    {
      "epoch": 1.2054945054945054,
      "grad_norm": 0.5794957559059861,
      "learning_rate": 3.938530949714533e-06,
      "loss": 0.6954,
      "step": 173
    },
    {
      "epoch": 1.2125274725274726,
      "grad_norm": 0.5092522893722937,
      "learning_rate": 3.878884450793053e-06,
      "loss": 0.6992,
      "step": 174
    },
    {
      "epoch": 1.2195604395604396,
      "grad_norm": 0.5343196689876678,
      "learning_rate": 3.819405476424164e-06,
      "loss": 0.6959,
      "step": 175
    },
    {
      "epoch": 1.2265934065934065,
      "grad_norm": 0.4933833699856012,
      "learning_rate": 3.7601029143523767e-06,
      "loss": 0.6938,
      "step": 176
    },
    {
      "epoch": 1.2336263736263735,
      "grad_norm": 0.5014086855443777,
      "learning_rate": 3.7009856259615074e-06,
      "loss": 0.6892,
      "step": 177
    },
    {
      "epoch": 1.2406593406593407,
      "grad_norm": 0.5523527929810598,
      "learning_rate": 3.642062444950537e-06,
      "loss": 0.7017,
      "step": 178
    },
    {
      "epoch": 1.2476923076923077,
      "grad_norm": 0.4818738912562937,
      "learning_rate": 3.5833421760136323e-06,
      "loss": 0.6774,
      "step": 179
    },
    {
      "epoch": 1.2547252747252746,
      "grad_norm": 0.5461147310455838,
      "learning_rate": 3.524833593524487e-06,
      "loss": 0.6979,
      "step": 180
    },
    {
      "epoch": 1.2547252747252746,
      "eval_loss": 1.5613536834716797,
      "eval_runtime": 227.3007,
      "eval_samples_per_second": 13.652,
      "eval_steps_per_second": 3.414,
      "step": 180
    },
    {
      "epoch": 1.2617582417582418,
      "grad_norm": 0.5109365510573675,
      "learning_rate": 3.4665454402251937e-06,
      "loss": 0.6852,
      "step": 181
    },
    {
      "epoch": 1.2687912087912088,
      "grad_norm": 0.4944349858439552,
      "learning_rate": 3.40848642591985e-06,
      "loss": 0.6878,
      "step": 182
    },
    {
      "epoch": 1.2758241758241757,
      "grad_norm": 0.5159952929170575,
      "learning_rate": 3.350665226173078e-06,
      "loss": 0.687,
      "step": 183
    },
    {
      "epoch": 1.282857142857143,
      "grad_norm": 0.5549596460552958,
      "learning_rate": 3.293090481013661e-06,
      "loss": 0.6846,
      "step": 184
    },
    {
      "epoch": 1.2898901098901099,
      "grad_norm": 0.4726962925967871,
      "learning_rate": 3.2357707936435013e-06,
      "loss": 0.7052,
      "step": 185
    },
    {
      "epoch": 1.2969230769230768,
      "grad_norm": 0.5871155312495273,
      "learning_rate": 3.1787147291520675e-06,
      "loss": 0.6913,
      "step": 186
    },
    {
      "epoch": 1.303956043956044,
      "grad_norm": 0.5365998516217266,
      "learning_rate": 3.1219308132365365e-06,
      "loss": 0.6875,
      "step": 187
    },
    {
      "epoch": 1.310989010989011,
      "grad_norm": 0.5631340881658085,
      "learning_rate": 3.0654275309278382e-06,
      "loss": 0.6957,
      "step": 188
    },
    {
      "epoch": 1.318021978021978,
      "grad_norm": 0.5382778843347812,
      "learning_rate": 3.0092133253227563e-06,
      "loss": 0.6882,
      "step": 189
    },
    {
      "epoch": 1.3250549450549451,
      "grad_norm": 0.5205915810175865,
      "learning_rate": 2.9532965963223076e-06,
      "loss": 0.6925,
      "step": 190
    },
    {
      "epoch": 1.332087912087912,
      "grad_norm": 0.5089202754962188,
      "learning_rate": 2.8976856993765766e-06,
      "loss": 0.6946,
      "step": 191
    },
    {
      "epoch": 1.339120879120879,
      "grad_norm": 0.5241959505519166,
      "learning_rate": 2.8423889442361797e-06,
      "loss": 0.6821,
      "step": 192
    },
    {
      "epoch": 1.3461538461538463,
      "grad_norm": 0.4791744200405188,
      "learning_rate": 2.787414593710583e-06,
      "loss": 0.6703,
      "step": 193
    },
    {
      "epoch": 1.3531868131868132,
      "grad_norm": 0.5338167716156891,
      "learning_rate": 2.7327708624333936e-06,
      "loss": 0.6917,
      "step": 194
    },
    {
      "epoch": 1.3602197802197802,
      "grad_norm": 0.5221883229297136,
      "learning_rate": 2.678465915634899e-06,
      "loss": 0.6767,
      "step": 195
    },
    {
      "epoch": 1.3672527472527474,
      "grad_norm": 0.4931589375431747,
      "learning_rate": 2.6245078679219503e-06,
      "loss": 0.6779,
      "step": 196
    },
    {
      "epoch": 1.3742857142857143,
      "grad_norm": 0.517354019882498,
      "learning_rate": 2.5709047820654236e-06,
      "loss": 0.6802,
      "step": 197
    },
    {
      "epoch": 1.3813186813186813,
      "grad_norm": 0.49471704157814983,
      "learning_rate": 2.517664667795434e-06,
      "loss": 0.685,
      "step": 198
    },
    {
      "epoch": 1.3883516483516485,
      "grad_norm": 0.4837616496269841,
      "learning_rate": 2.4647954806044633e-06,
      "loss": 0.6735,
      "step": 199
    },
    {
      "epoch": 1.3953846153846154,
      "grad_norm": 0.5172749197596505,
      "learning_rate": 2.412305120558599e-06,
      "loss": 0.6832,
      "step": 200
    },
    {
      "epoch": 1.4024175824175824,
      "grad_norm": 0.49124469230673196,
      "learning_rate": 2.3602014311170524e-06,
      "loss": 0.6935,
      "step": 201
    },
    {
      "epoch": 1.4094505494505494,
      "grad_norm": 0.5064492540961577,
      "learning_rate": 2.308492197960141e-06,
      "loss": 0.6874,
      "step": 202
    },
    {
      "epoch": 1.4164835164835166,
      "grad_norm": 0.4856449960670854,
      "learning_rate": 2.2571851478258903e-06,
      "loss": 0.679,
      "step": 203
    },
    {
      "epoch": 1.4235164835164835,
      "grad_norm": 0.4952752928736292,
      "learning_rate": 2.2062879473554654e-06,
      "loss": 0.7041,
      "step": 204
    },
    {
      "epoch": 1.4305494505494505,
      "grad_norm": 0.4638341342791591,
      "learning_rate": 2.155808201947563e-06,
      "loss": 0.6998,
      "step": 205
    },
    {
      "epoch": 1.4375824175824174,
      "grad_norm": 0.4785344340695752,
      "learning_rate": 2.105753454621966e-06,
      "loss": 0.6985,
      "step": 206
    },
    {
      "epoch": 1.4446153846153846,
      "grad_norm": 0.5069994126640873,
      "learning_rate": 2.0561311848924082e-06,
      "loss": 0.6786,
      "step": 207
    },
    {
      "epoch": 1.4516483516483516,
      "grad_norm": 0.45914925243384214,
      "learning_rate": 2.0069488076489445e-06,
      "loss": 0.6974,
      "step": 208
    },
    {
      "epoch": 1.4586813186813186,
      "grad_norm": 0.47163331174683165,
      "learning_rate": 1.958213672049964e-06,
      "loss": 0.6977,
      "step": 209
    },
    {
      "epoch": 1.4657142857142857,
      "grad_norm": 0.4899597697854046,
      "learning_rate": 1.909933060424029e-06,
      "loss": 0.7008,
      "step": 210
    },
    {
      "epoch": 1.4727472527472527,
      "grad_norm": 0.4558417478252458,
      "learning_rate": 1.862114187181705e-06,
      "loss": 0.6876,
      "step": 211
    },
    {
      "epoch": 1.4797802197802197,
      "grad_norm": 0.47448115453479683,
      "learning_rate": 1.8147641977375313e-06,
      "loss": 0.6988,
      "step": 212
    },
    {
      "epoch": 1.4868131868131869,
      "grad_norm": 0.4556522922174643,
      "learning_rate": 1.7678901674423044e-06,
      "loss": 0.7004,
      "step": 213
    }
  ],
  "logging_steps": 1,
  "max_steps": 284,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 71,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.1174316342194995e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}