{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99945085118067,
  "eval_steps": 114,
  "global_step": 455,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "grad_norm": 0.1220703125,
      "learning_rate": 2e-05,
      "loss": 1.1845,
      "step": 1
    },
    {
      "epoch": 0.0,
      "eval_loss": 1.1820911169052124,
      "eval_runtime": 382.4714,
      "eval_samples_per_second": 7.676,
      "eval_steps_per_second": 3.838,
      "step": 1
    },
    {
      "epoch": 0.0,
      "grad_norm": 0.1162109375,
      "learning_rate": 4e-05,
      "loss": 1.1777,
      "step": 2
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.115234375,
      "learning_rate": 6e-05,
      "loss": 1.1406,
      "step": 3
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.126953125,
      "learning_rate": 8e-05,
      "loss": 1.2366,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.150390625,
      "learning_rate": 0.0001,
      "loss": 1.2321,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.1513671875,
      "learning_rate": 0.00012,
      "loss": 1.0941,
      "step": 6
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00014,
      "loss": 1.0609,
      "step": 7
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00016,
      "loss": 1.0332,
      "step": 8
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.00018,
      "loss": 1.1241,
      "step": 9
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.0002,
      "loss": 1.1964,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.150390625,
      "learning_rate": 0.00019999750800065415,
      "loss": 1.254,
      "step": 11
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.130859375,
      "learning_rate": 0.00019999003212681782,
      "loss": 1.0003,
      "step": 12
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.00019997757275108847,
      "loss": 1.033,
      "step": 13
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.00019996013049444118,
      "loss": 1.0915,
      "step": 14
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.00019993770622619782,
      "loss": 1.027,
      "step": 15
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.00019991030106398364,
      "loss": 0.8964,
      "step": 16
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.08203125,
      "learning_rate": 0.00019987791637367158,
      "loss": 0.9778,
      "step": 17
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.07666015625,
      "learning_rate": 0.00019984055376931413,
      "loss": 1.0588,
      "step": 18
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.076171875,
      "learning_rate": 0.00019979821511306308,
      "loss": 0.9921,
      "step": 19
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.0830078125,
      "learning_rate": 0.00019975090251507638,
      "loss": 1.0424,
      "step": 20
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.08642578125,
      "learning_rate": 0.0001996986183334134,
      "loss": 1.0514,
      "step": 21
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.07568359375,
      "learning_rate": 0.00019964136517391706,
      "loss": 1.0248,
      "step": 22
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.00019957914589008405,
      "loss": 1.0394,
      "step": 23
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.07568359375,
      "learning_rate": 0.00019951196358292266,
      "loss": 1.0678,
      "step": 24
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.07861328125,
      "learning_rate": 0.0001994398216007982,
      "loss": 0.9298,
      "step": 25
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.095703125,
      "learning_rate": 0.00019936272353926615,
      "loss": 0.991,
      "step": 26
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.07958984375,
      "learning_rate": 0.00019928067324089286,
      "loss": 0.9823,
      "step": 27
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.08349609375,
      "learning_rate": 0.00019919367479506413,
      "loss": 1.0103,
      "step": 28
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.07568359375,
      "learning_rate": 0.00019910173253778136,
      "loss": 0.9725,
      "step": 29
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.07421875,
      "learning_rate": 0.00019900485105144543,
      "loss": 1.0453,
      "step": 30
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0830078125,
      "learning_rate": 0.00019890303516462843,
      "loss": 1.0282,
      "step": 31
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.00019879628995183272,
      "loss": 0.9683,
      "step": 32
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.0732421875,
      "learning_rate": 0.00019868462073323838,
      "loss": 0.9711,
      "step": 33
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.07666015625,
      "learning_rate": 0.00019856803307443781,
      "loss": 0.9303,
      "step": 34
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0751953125,
      "learning_rate": 0.00019844653278615833,
      "loss": 0.9018,
      "step": 35
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.07470703125,
      "learning_rate": 0.0001983201259239728,
      "loss": 0.932,
      "step": 36
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.072265625,
      "learning_rate": 0.00019818881878799752,
      "loss": 0.9073,
      "step": 37
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.0791015625,
      "learning_rate": 0.00019805261792257847,
      "loss": 0.9367,
      "step": 38
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.0771484375,
      "learning_rate": 0.00019791153011596496,
      "loss": 1.0177,
      "step": 39
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.07666015625,
      "learning_rate": 0.00019776556239997146,
      "loss": 0.8887,
      "step": 40
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.08056640625,
      "learning_rate": 0.000197614722049627,
      "loss": 1.0279,
      "step": 41
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.00019745901658281266,
      "loss": 1.0993,
      "step": 42
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.0751953125,
      "learning_rate": 0.00019729845375988694,
      "loss": 0.9436,
      "step": 43
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.08203125,
      "learning_rate": 0.00019713304158329873,
      "loss": 1.0442,
      "step": 44
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.00019696278829718883,
      "loss": 1.0196,
      "step": 45
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00019678770238697874,
      "loss": 1.0415,
      "step": 46
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.08935546875,
      "learning_rate": 0.00019660779257894796,
      "loss": 0.983,
      "step": 47
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.07763671875,
      "learning_rate": 0.000196423067839799,
      "loss": 0.9415,
      "step": 48
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.09228515625,
      "learning_rate": 0.00019623353737621035,
      "loss": 0.9829,
      "step": 49
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00019603921063437793,
      "loss": 0.9223,
      "step": 50
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.08447265625,
      "learning_rate": 0.00019584009729954396,
      "loss": 0.8714,
      "step": 51
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.00019563620729551445,
      "loss": 0.8981,
      "step": 52
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00019542755078416456,
      "loss": 0.9528,
      "step": 53
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.00019521413816493206,
      "loss": 1.0403,
      "step": 54
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.0001949959800742991,
      "loss": 1.0177,
      "step": 55
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.09375,
      "learning_rate": 0.00019477308738526206,
      "loss": 1.0504,
      "step": 56
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.087890625,
      "learning_rate": 0.00019454547120678967,
      "loss": 0.9463,
      "step": 57
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00019431314288326926,
      "loss": 0.907,
      "step": 58
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.083984375,
      "learning_rate": 0.00019407611399394143,
      "loss": 0.8962,
      "step": 59
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00019383439635232294,
      "loss": 0.9455,
      "step": 60
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.0001935880020056179,
      "loss": 1.0383,
      "step": 61
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.0849609375,
      "learning_rate": 0.00019333694323411734,
      "loss": 0.9763,
      "step": 62
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00019308123255058708,
      "loss": 1.0526,
      "step": 63
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.0001928208826996443,
      "loss": 0.8888,
      "step": 64
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.00019255590665712214,
      "loss": 0.925,
      "step": 65
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.08203125,
      "learning_rate": 0.00019228631762942307,
      "loss": 0.8944,
      "step": 66
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00019201212905286074,
      "loss": 0.9638,
      "step": 67
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00019173335459299025,
      "loss": 0.9773,
      "step": 68
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.09130859375,
      "learning_rate": 0.00019145000814392696,
      "loss": 0.9241,
      "step": 69
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.091796875,
      "learning_rate": 0.0001911621038276542,
      "loss": 0.9495,
      "step": 70
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.09375,
      "learning_rate": 0.00019086965599331938,
      "loss": 0.9238,
      "step": 71
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.09326171875,
      "learning_rate": 0.00019057267921651866,
      "loss": 0.9721,
      "step": 72
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.09326171875,
      "learning_rate": 0.00019027118829857077,
      "loss": 0.9081,
      "step": 73
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.10546875,
      "learning_rate": 0.00018996519826577907,
      "loss": 0.9803,
      "step": 74
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.0830078125,
      "learning_rate": 0.00018965472436868286,
      "loss": 0.9435,
      "step": 75
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00018933978208129706,
      "loss": 0.8613,
      "step": 76
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.091796875,
      "learning_rate": 0.00018902038710034112,
      "loss": 0.9293,
      "step": 77
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.1015625,
      "learning_rate": 0.0001886965553444568,
      "loss": 1.0039,
      "step": 78
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.091796875,
      "learning_rate": 0.0001883683029534145,
      "loss": 0.9316,
      "step": 79
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.00018803564628730915,
      "loss": 0.987,
      "step": 80
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.0908203125,
      "learning_rate": 0.0001876986019257446,
      "loss": 0.9598,
      "step": 81
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.1044921875,
      "learning_rate": 0.0001873571866670074,
      "loss": 0.872,
      "step": 82
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.0859375,
      "learning_rate": 0.00018701141752722964,
      "loss": 0.9035,
      "step": 83
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.095703125,
      "learning_rate": 0.0001866613117395407,
      "loss": 0.9103,
      "step": 84
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.087890625,
      "learning_rate": 0.00018630688675320842,
      "loss": 0.9446,
      "step": 85
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.08251953125,
      "learning_rate": 0.00018594816023276953,
      "loss": 0.8302,
      "step": 86
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.091796875,
      "learning_rate": 0.0001855851500571491,
      "loss": 0.9336,
      "step": 87
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.00018521787431876954,
      "loss": 0.9285,
      "step": 88
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.08984375,
      "learning_rate": 0.0001848463513226488,
      "loss": 0.8675,
      "step": 89
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.0001844705995854882,
      "loss": 0.9251,
      "step": 90
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.0859375,
      "learning_rate": 0.0001840906378347494,
      "loss": 0.8655,
      "step": 91
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.107421875,
      "learning_rate": 0.00018370648500772108,
      "loss": 0.9182,
      "step": 92
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.0001833181602505751,
      "loss": 0.873,
      "step": 93
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0947265625,
      "learning_rate": 0.00018292568291741228,
      "loss": 0.9838,
      "step": 94
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00018252907256929775,
      "loss": 0.8565,
      "step": 95
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0888671875,
      "learning_rate": 0.00018212834897328613,
      "loss": 0.8747,
      "step": 96
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.0888671875,
      "learning_rate": 0.0001817235321014361,
      "loss": 0.9313,
      "step": 97
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.099609375,
      "learning_rate": 0.0001813146421298154,
      "loss": 0.8365,
      "step": 98
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.0068,
      "step": 99
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.09228515625,
      "learning_rate": 0.00018048472460553257,
      "loss": 0.8783,
      "step": 100
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.00018006373841594905,
      "loss": 0.9325,
      "step": 101
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.00017963876185069034,
      "loss": 1.0326,
      "step": 102
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.00017920981609058289,
      "loss": 0.8769,
      "step": 103
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.0869140625,
      "learning_rate": 0.00017877692251427782,
      "loss": 0.9167,
      "step": 104
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.1142578125,
      "learning_rate": 0.00017834010269718526,
      "loss": 0.9688,
      "step": 105
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.00017789937841039918,
      "loss": 0.8039,
      "step": 106
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.0001774547716196123,
      "loss": 0.9943,
      "step": 107
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.00017700630448402125,
      "loss": 0.9769,
      "step": 108
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.00017655399935522217,
      "loss": 0.8973,
      "step": 109
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.0001760978787760968,
      "loss": 0.8602,
      "step": 110
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.0001756379654796888,
      "loss": 0.8966,
      "step": 111
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.00017517428238807085,
      "loss": 0.8997,
      "step": 112
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.0947265625,
      "learning_rate": 0.0001747068526112022,
      "loss": 0.9476,
      "step": 113
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00017423569944577678,
      "loss": 0.9328,
      "step": 114
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.922809362411499,
      "eval_runtime": 418.8489,
      "eval_samples_per_second": 7.01,
      "eval_steps_per_second": 3.505,
      "step": 114
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.09619140625,
      "learning_rate": 0.00017376084637406222,
      "loss": 0.8643,
      "step": 115
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.10302734375,
      "learning_rate": 0.0001732823170627294,
      "loss": 0.9659,
      "step": 116
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.00017280013536167293,
      "loss": 0.8158,
      "step": 117
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.00017231432530282246,
      "loss": 0.9843,
      "step": 118
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.08984375,
      "learning_rate": 0.000171824911098945,
      "loss": 0.9591,
      "step": 119
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.00017133191714243805,
      "loss": 0.9331,
      "step": 120
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00017083536800411393,
      "loss": 0.8647,
      "step": 121
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0888671875,
      "learning_rate": 0.00017033528843197525,
      "loss": 1.0038,
      "step": 122
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00016983170334998132,
      "loss": 0.8214,
      "step": 123
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.08544921875,
      "learning_rate": 0.000169324637856806,
      "loss": 0.8832,
      "step": 124
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.0859375,
      "learning_rate": 0.00016881411722458688,
      "loss": 0.8642,
      "step": 125
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.09375,
      "learning_rate": 0.00016830016689766558,
      "loss": 0.9047,
      "step": 126
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.095703125,
      "learning_rate": 0.0001677828124913197,
      "loss": 0.8494,
      "step": 127
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.00016726207979048604,
      "loss": 0.9421,
      "step": 128
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.0001667379947484756,
      "loss": 0.8429,
      "step": 129
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.00016621058348568007,
      "loss": 0.8319,
      "step": 130
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.0001656798722882698,
      "loss": 0.8681,
      "step": 131
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00016514588760688397,
      "loss": 0.9469,
      "step": 132
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.091796875,
      "learning_rate": 0.00016460865605531213,
      "loss": 0.9818,
      "step": 133
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.0001640682044091678,
      "loss": 0.9046,
      "step": 134
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.09326171875,
      "learning_rate": 0.00016352455960455387,
      "loss": 0.9319,
      "step": 135
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.00016297774873672035,
      "loss": 0.963,
      "step": 136
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00016242779905871374,
      "loss": 0.8749,
      "step": 137
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.00016187473798001879,
      "loss": 0.9731,
      "step": 138
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.1015625,
      "learning_rate": 0.00016131859306519242,
      "loss": 0.8319,
      "step": 139
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.0908203125,
      "learning_rate": 0.0001607593920324899,
      "loss": 0.8156,
      "step": 140
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.00016019716275248342,
      "loss": 0.9433,
      "step": 141
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.12451171875,
      "learning_rate": 0.0001596319332466729,
      "loss": 0.913,
      "step": 142
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00015906373168608952,
      "loss": 0.9255,
      "step": 143
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00015849258638989165,
      "loss": 0.9524,
      "step": 144
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.1015625,
      "learning_rate": 0.00015791852582395334,
      "loss": 1.0442,
      "step": 145
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.123046875,
      "learning_rate": 0.00015734157859944575,
      "loss": 0.8188,
      "step": 146
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.00015676177347141094,
      "loss": 0.8675,
      "step": 147
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.00015617913933732892,
      "loss": 0.9065,
      "step": 148
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.00015559370523567732,
      "loss": 0.9665,
      "step": 149
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.00015500550034448413,
      "loss": 0.8779,
      "step": 150
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.08837890625,
      "learning_rate": 0.0001544145539798734,
      "loss": 0.8539,
      "step": 151
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.1142578125,
      "learning_rate": 0.00015382089559460422,
      "loss": 0.9068,
      "step": 152
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00015322455477660273,
      "loss": 0.9563,
      "step": 153
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.00015262556124748751,
      "loss": 0.8071,
      "step": 154
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.1123046875,
      "learning_rate": 0.0001520239448610882,
      "loss": 0.8971,
      "step": 155
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00015141973560195768,
      "loss": 0.883,
      "step": 156
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.0001508129635838775,
      "loss": 0.8609,
      "step": 157
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.10986328125,
      "learning_rate": 0.000150203659048357,
      "loss": 0.9184,
      "step": 158
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.109375,
      "learning_rate": 0.00014959185236312642,
      "loss": 0.8602,
      "step": 159
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.107421875,
      "learning_rate": 0.00014897757402062284,
      "loss": 0.8908,
      "step": 160
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.00014836085463647088,
      "loss": 0.9134,
      "step": 161
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.109375,
      "learning_rate": 0.00014774172494795652,
      "loss": 0.9385,
      "step": 162
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.00014712021581249533,
      "loss": 0.8183,
      "step": 163
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00014649635820609456,
      "loss": 0.8806,
      "step": 164
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00014587018322180905,
      "loss": 0.915,
      "step": 165
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.12109375,
      "learning_rate": 0.00014524172206819194,
      "loss": 0.848,
      "step": 166
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00014461100606773884,
      "loss": 0.9189,
      "step": 167
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.099609375,
      "learning_rate": 0.00014397806665532694,
      "loss": 0.78,
      "step": 168
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.10205078125,
      "learning_rate": 0.00014334293537664837,
      "loss": 0.8854,
      "step": 169
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.0001427056438866376,
      "loss": 0.7996,
      "step": 170
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.10693359375,
      "learning_rate": 0.00014206622394789432,
      "loss": 0.9002,
      "step": 171
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.1083984375,
      "learning_rate": 0.00014142470742909975,
      "loss": 0.9172,
      "step": 172
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.10693359375,
      "learning_rate": 0.0001407811263034289,
      "loss": 0.9438,
      "step": 173
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.12890625,
      "learning_rate": 0.00014013551264695662,
      "loss": 0.8709,
      "step": 174
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.11328125,
      "learning_rate": 0.00013948789863705912,
      "loss": 0.8717,
      "step": 175
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.10205078125,
      "learning_rate": 0.00013883831655081018,
      "loss": 0.9313,
      "step": 176
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.00013818679876337247,
      "loss": 0.914,
      "step": 177
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.1064453125,
      "learning_rate": 0.00013753337774638396,
      "loss": 0.919,
      "step": 178
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.00013687808606633966,
      "loss": 0.9628,
      "step": 179
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.11376953125,
      "learning_rate": 0.00013622095638296826,
      "loss": 0.8947,
      "step": 180
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.0001355620214476046,
      "loss": 0.9269,
      "step": 181
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.10595703125,
      "learning_rate": 0.00013490131410155728,
      "loss": 0.8438,
      "step": 182
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.00013423886727447176,
      "loss": 0.8986,
      "step": 183
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.11474609375,
      "learning_rate": 0.00013357471398268918,
      "loss": 0.9274,
      "step": 184
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.111328125,
      "learning_rate": 0.000132908887327601,
      "loss": 0.8511,
      "step": 185
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.11767578125,
      "learning_rate": 0.00013224142049399895,
      "loss": 0.809,
      "step": 186
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.12158203125,
      "learning_rate": 0.00013157234674842128,
      "loss": 0.7523,
      "step": 187
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.9021,
      "step": 188
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.11865234375,
      "learning_rate": 0.00013022951198627254,
      "loss": 0.8875,
      "step": 189
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.09521484375,
      "learning_rate": 0.00012955581789656843,
      "loss": 0.8563,
      "step": 190
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.1123046875,
      "learning_rate": 0.000128880650745287,
      "loss": 0.7841,
      "step": 191
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.0001282040441827503,
      "loss": 0.925,
      "step": 192
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.0001275260319310205,
      "loss": 1.0102,
      "step": 193
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.115234375,
      "learning_rate": 0.00012684664778221942,
      "loss": 0.7835,
      "step": 194
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.0001261659255968441,
      "loss": 0.9312,
      "step": 195
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.09716796875,
      "learning_rate": 0.0001254838993020793,
      "loss": 0.9214,
      "step": 196
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.10009765625,
      "learning_rate": 0.00012480060289010679,
      "loss": 0.8237,
      "step": 197
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.00012411607041641062,
      "loss": 0.9152,
      "step": 198
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.1123046875,
      "learning_rate": 0.00012343033599808044,
      "loss": 0.9036,
      "step": 199
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.1416015625,
      "learning_rate": 0.00012274343381211066,
      "loss": 0.901,
      "step": 200
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.00012205539809369719,
      "loss": 0.7381,
      "step": 201
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.111328125,
      "learning_rate": 0.00012136626313453134,
      "loss": 0.9358,
      "step": 202
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.00012067606328109038,
      "loss": 0.8706,
      "step": 203
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.11572265625,
      "learning_rate": 0.00011998483293292602,
      "loss": 0.9957,
      "step": 204
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00011929260654094969,
      "loss": 0.8489,
      "step": 205
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.0001185994186057158,
      "loss": 0.8718,
      "step": 206
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.09912109375,
      "learning_rate": 0.00011790530367570194,
      "loss": 0.8182,
      "step": 207
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.00011721029634558709,
      "loss": 0.8512,
      "step": 208
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.150390625,
      "learning_rate": 0.00011651443125452759,
      "loss": 0.9216,
      "step": 209
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.0001158177430844304,
      "loss": 0.7999,
      "step": 210
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00011512026655822483,
      "loss": 0.7343,
      "step": 211
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.1005859375,
      "learning_rate": 0.00011442203643813183,
      "loss": 0.861,
      "step": 212
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.1220703125,
      "learning_rate": 0.00011372308752393144,
      "loss": 0.8731,
      "step": 213
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.1298828125,
      "learning_rate": 0.00011302345465122839,
      "loss": 0.9257,
      "step": 214
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.00011232317268971585,
      "loss": 1.0089,
      "step": 215
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.1220703125,
      "learning_rate": 0.00011162227654143778,
      "loss": 0.877,
      "step": 216
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.0927734375,
      "learning_rate": 0.00011092080113904886,
      "loss": 0.8373,
      "step": 217
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.10693359375,
      "learning_rate": 0.00011021878144407408,
      "loss": 0.8474,
      "step": 218
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.00010951625244516583,
      "loss": 0.788,
      "step": 219
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.1142578125,
      "learning_rate": 0.00010881324915636019,
      "loss": 0.8093,
      "step": 220
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.10986328125,
      "learning_rate": 0.0001081098066153319,
      "loss": 0.9342,
      "step": 221
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.10986328125,
      "learning_rate": 0.00010740595988164801,
      "loss": 0.836,
      "step": 222
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.09423828125,
      "learning_rate": 0.00010670174403502052,
      "loss": 0.8206,
      "step": 223
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.0986328125,
      "learning_rate": 0.000105997194173558,
      "loss": 0.8645,
      "step": 224
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.10107421875,
      "learning_rate": 0.00010529234541201631,
      "loss": 0.8027,
      "step": 225
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.00010458723288004857,
      "loss": 0.8333,
      "step": 226
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.10400390625,
      "learning_rate": 0.00010388189172045406,
      "loss": 0.8999,
      "step": 227
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.1142578125,
      "learning_rate": 0.00010317635708742699,
      "loss": 0.8961,
      "step": 228
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.8713043332099915,
      "eval_runtime": 415.0516,
      "eval_samples_per_second": 7.074,
      "eval_steps_per_second": 3.537,
      "step": 228
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00010247066414480424,
      "loss": 0.8739,
      "step": 229
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.134765625,
      "learning_rate": 0.00010176484806431288,
      "loss": 0.8045,
      "step": 230
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.103515625,
      "learning_rate": 0.00010105894402381704,
      "loss": 0.9281,
      "step": 231
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.1025390625,
      "learning_rate": 0.00010035298720556493,
      "loss": 0.8426,
      "step": 232
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.11669921875,
      "learning_rate": 9.964701279443508e-05,
      "loss": 0.7591,
      "step": 233
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.11328125,
      "learning_rate": 9.894105597618296e-05,
      "loss": 0.8066,
      "step": 234
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.1064453125,
      "learning_rate": 9.823515193568715e-05,
      "loss": 0.8372,
      "step": 235
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.1015625,
      "learning_rate": 9.752933585519577e-05,
      "loss": 0.81,
      "step": 236
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.10986328125,
      "learning_rate": 9.682364291257304e-05,
      "loss": 1.0054,
      "step": 237
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.09814453125,
      "learning_rate": 9.611810827954599e-05,
      "loss": 0.8229,
      "step": 238
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.19140625,
      "learning_rate": 9.541276711995148e-05,
      "loss": 0.7994,
      "step": 239
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.1279296875,
      "learning_rate": 9.470765458798368e-05,
      "loss": 0.8103,
      "step": 240
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.1171875,
      "learning_rate": 9.400280582644203e-05,
      "loss": 0.7667,
      "step": 241
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.0966796875,
      "learning_rate": 9.329825596497949e-05,
      "loss": 0.9226,
      "step": 242
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.11279296875,
      "learning_rate": 9.259404011835201e-05,
      "loss": 0.751,
      "step": 243
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.10498046875,
      "learning_rate": 9.189019338466812e-05,
      "loss": 0.978,
      "step": 244
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0986328125,
      "learning_rate": 9.118675084363986e-05,
      "loss": 0.8746,
      "step": 245
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.1318359375,
      "learning_rate": 9.048374755483419e-05,
      "loss": 0.8223,
      "step": 246
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.16015625,
      "learning_rate": 8.978121855592593e-05,
      "loss": 0.9778,
      "step": 247
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.134765625,
      "learning_rate": 8.907919886095115e-05,
      "loss": 0.8693,
      "step": 248
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.1201171875,
      "learning_rate": 8.837772345856226e-05,
      "loss": 0.7726,
      "step": 249
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.1494140625,
      "learning_rate": 8.767682731028415e-05,
      "loss": 0.7388,
      "step": 250
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.1337890625,
      "learning_rate": 8.697654534877165e-05,
      "loss": 0.8422,
      "step": 251
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.11572265625,
      "learning_rate": 8.627691247606862e-05,
      "loss": 0.8306,
      "step": 252
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.08984375,
      "learning_rate": 8.557796356186818e-05,
      "loss": 0.7276,
      "step": 253
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.1337890625,
      "learning_rate": 8.487973344177517e-05,
      "loss": 0.8244,
      "step": 254
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.10693359375,
      "learning_rate": 8.418225691556962e-05,
      "loss": 0.7665,
      "step": 255
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.09765625,
      "learning_rate": 8.348556874547242e-05,
      "loss": 0.8114,
      "step": 256
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.1318359375,
      "learning_rate": 8.278970365441292e-05,
      "loss": 0.7918,
      "step": 257
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.11669921875,
      "learning_rate": 8.20946963242981e-05,
      "loss": 0.8266,
      "step": 258
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.11083984375,
      "learning_rate": 8.140058139428425e-05,
      "loss": 0.7967,
      "step": 259
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.09912109375,
      "learning_rate": 8.070739345905032e-05,
      "loss": 0.9177,
      "step": 260
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.11474609375,
      "learning_rate": 8.001516706707401e-05,
      "loss": 0.9526,
      "step": 261
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.11083984375,
      "learning_rate": 7.932393671890965e-05,
      "loss": 0.9914,
      "step": 262
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.10205078125,
      "learning_rate": 7.863373686546867e-05,
      "loss": 0.8242,
      "step": 263
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.09716796875,
      "learning_rate": 7.794460190630282e-05,
      "loss": 0.6837,
      "step": 264
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.11328125,
      "learning_rate": 7.725656618788937e-05,
      "loss": 0.8758,
      "step": 265
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.11181640625,
      "learning_rate": 7.656966400191956e-05,
      "loss": 0.8655,
      "step": 266
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.11328125,
      "learning_rate": 7.58839295835894e-05,
      "loss": 1.0563,
      "step": 267
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.11962890625,
      "learning_rate": 7.519939710989325e-05,
      "loss": 0.832,
      "step": 268
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.1142578125,
      "learning_rate": 7.45161006979207e-05,
      "loss": 0.8198,
      "step": 269
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.1103515625,
      "learning_rate": 7.383407440315596e-05,
      "loss": 0.8246,
      "step": 270
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.10498046875,
      "learning_rate": 7.315335221778064e-05,
      "loss": 0.8314,
      "step": 271
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.1240234375,
      "learning_rate": 7.247396806897952e-05,
      "loss": 0.7107,
      "step": 272
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.10498046875,
      "learning_rate": 7.17959558172497e-05,
      "loss": 0.8982,
      "step": 273
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.1103515625,
      "learning_rate": 7.111934925471302e-05,
      "loss": 0.9427,
      "step": 274
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.1279296875,
      "learning_rate": 7.04441821034316e-05,
      "loss": 0.8454,
      "step": 275
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.115234375,
      "learning_rate": 6.97704880137275e-05,
      "loss": 0.8044,
      "step": 276
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.12451171875,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.8196,
      "step": 277
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.13671875,
      "learning_rate": 6.842765325157874e-05,
      "loss": 0.8221,
      "step": 278
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.119140625,
      "learning_rate": 6.775857950600106e-05,
      "loss": 0.8273,
      "step": 279
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0966796875,
      "learning_rate": 6.7091112672399e-05,
      "loss": 0.9296,
      "step": 280
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.103515625,
      "learning_rate": 6.642528601731082e-05,
      "loss": 0.8635,
      "step": 281
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.10693359375,
      "learning_rate": 6.576113272552826e-05,
      "loss": 0.8622,
      "step": 282
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.10693359375,
      "learning_rate": 6.509868589844273e-05,
      "loss": 0.8982,
      "step": 283
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.1220703125,
      "learning_rate": 6.44379785523954e-05,
      "loss": 0.8564,
      "step": 284
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.1923828125,
      "learning_rate": 6.377904361703178e-05,
      "loss": 0.7286,
      "step": 285
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.1005859375,
      "learning_rate": 6.312191393366035e-05,
      "loss": 1.0057,
      "step": 286
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.12158203125,
      "learning_rate": 6.246662225361602e-05,
      "loss": 0.7258,
      "step": 287
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.099609375,
      "learning_rate": 6.181320123662755e-05,
      "loss": 0.8115,
      "step": 288
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.1298828125,
      "learning_rate": 6.116168344918983e-05,
      "loss": 0.7434,
      "step": 289
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.10009765625,
      "learning_rate": 6.051210136294089e-05,
      "loss": 0.875,
      "step": 290
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.10791015625,
      "learning_rate": 5.986448735304339e-05,
      "loss": 0.9115,
      "step": 291
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.1064453125,
      "learning_rate": 5.921887369657113e-05,
      "loss": 0.8492,
      "step": 292
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.126953125,
      "learning_rate": 5.857529257090027e-05,
      "loss": 0.7701,
      "step": 293
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.11083984375,
      "learning_rate": 5.7933776052105745e-05,
      "loss": 0.9333,
      "step": 294
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.1279296875,
      "learning_rate": 5.729435611336239e-05,
      "loss": 0.7718,
      "step": 295
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.123046875,
      "learning_rate": 5.6657064623351676e-05,
      "loss": 0.8522,
      "step": 296
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.1982421875,
      "learning_rate": 5.602193334467307e-05,
      "loss": 0.7019,
      "step": 297
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.11865234375,
      "learning_rate": 5.5388993932261215e-05,
      "loss": 0.8389,
      "step": 298
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.1259765625,
      "learning_rate": 5.4758277931808075e-05,
      "loss": 0.863,
      "step": 299
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.115234375,
      "learning_rate": 5.4129816778190936e-05,
      "loss": 0.7688,
      "step": 300
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.11328125,
      "learning_rate": 5.350364179390548e-05,
      "loss": 0.8084,
      "step": 301
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.1005859375,
      "learning_rate": 5.28797841875047e-05,
      "loss": 0.9221,
      "step": 302
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.12255859375,
      "learning_rate": 5.2258275052043546e-05,
      "loss": 0.8468,
      "step": 303
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.1181640625,
      "learning_rate": 5.163914536352918e-05,
      "loss": 0.918,
      "step": 304
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.11572265625,
      "learning_rate": 5.102242597937717e-05,
      "loss": 0.8958,
      "step": 305
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.126953125,
      "learning_rate": 5.040814763687358e-05,
      "loss": 0.8718,
      "step": 306
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.11376953125,
      "learning_rate": 4.9796340951642986e-05,
      "loss": 0.8603,
      "step": 307
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.11669921875,
      "learning_rate": 4.918703641612255e-05,
      "loss": 0.8245,
      "step": 308
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.12890625,
      "learning_rate": 4.858026439804235e-05,
      "loss": 0.8881,
      "step": 309
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.10791015625,
      "learning_rate": 4.797605513891179e-05,
      "loss": 0.921,
      "step": 310
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.232421875,
      "learning_rate": 4.737443875251251e-05,
      "loss": 0.8585,
      "step": 311
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.11474609375,
      "learning_rate": 4.6775445223397306e-05,
      "loss": 0.8024,
      "step": 312
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.1767578125,
      "learning_rate": 4.61791044053958e-05,
      "loss": 0.7499,
      "step": 313
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.130859375,
      "learning_rate": 4.558544602012663e-05,
      "loss": 0.8993,
      "step": 314
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.115234375,
      "learning_rate": 4.4994499655515865e-05,
      "loss": 0.8938,
      "step": 315
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.11083984375,
      "learning_rate": 4.440629476432267e-05,
      "loss": 0.8357,
      "step": 316
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.1328125,
      "learning_rate": 4.3820860662671107e-05,
      "loss": 0.719,
      "step": 317
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.1015625,
      "learning_rate": 4.323822652858911e-05,
      "loss": 0.8492,
      "step": 318
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.126953125,
      "learning_rate": 4.265842140055428e-05,
      "loss": 0.7805,
      "step": 319
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.11376953125,
      "learning_rate": 4.2081474176046646e-05,
      "loss": 0.814,
      "step": 320
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1103515625,
      "learning_rate": 4.150741361010837e-05,
      "loss": 0.8448,
      "step": 321
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1142578125,
      "learning_rate": 4.093626831391051e-05,
      "loss": 0.8212,
      "step": 322
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.1435546875,
      "learning_rate": 4.036806675332715e-05,
      "loss": 0.8006,
      "step": 323
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.111328125,
      "learning_rate": 3.98028372475166e-05,
      "loss": 0.8723,
      "step": 324
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.130859375,
      "learning_rate": 3.924060796751012e-05,
      "loss": 0.7984,
      "step": 325
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.10302734375,
      "learning_rate": 3.8681406934807585e-05,
      "loss": 0.8581,
      "step": 326
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.12060546875,
      "learning_rate": 3.8125262019981224e-05,
      "loss": 0.8222,
      "step": 327
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.12255859375,
      "learning_rate": 3.757220094128629e-05,
      "loss": 0.8624,
      "step": 328
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.12353515625,
      "learning_rate": 3.702225126327965e-05,
      "loss": 0.7377,
      "step": 329
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.1044921875,
      "learning_rate": 3.647544039544615e-05,
      "loss": 0.8021,
      "step": 330
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.125,
      "learning_rate": 3.5931795590832254e-05,
      "loss": 0.8053,
      "step": 331
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.10546875,
      "learning_rate": 3.53913439446879e-05,
      "loss": 1.0031,
      "step": 332
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.173828125,
      "learning_rate": 3.485411239311604e-05,
      "loss": 0.773,
      "step": 333
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.138671875,
      "learning_rate": 3.432012771173021e-05,
      "loss": 0.785,
      "step": 334
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.0986328125,
      "learning_rate": 3.378941651431996e-05,
      "loss": 0.7751,
      "step": 335
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.10595703125,
      "learning_rate": 3.326200525152441e-05,
      "loss": 0.7843,
      "step": 336
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.10302734375,
      "learning_rate": 3.2737920209514e-05,
      "loss": 0.8728,
      "step": 337
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.1279296875,
      "learning_rate": 3.2217187508680315e-05,
      "loss": 0.7532,
      "step": 338
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.1328125,
      "learning_rate": 3.1699833102334395e-05,
      "loss": 0.8074,
      "step": 339
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.0927734375,
      "learning_rate": 3.118588277541312e-05,
      "loss": 1.0021,
      "step": 340
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.1044921875,
      "learning_rate": 3.067536214319402e-05,
      "loss": 0.8352,
      "step": 341
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.11767578125,
      "learning_rate": 3.0168296650018735e-05,
      "loss": 0.824,
      "step": 342
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.8436947464942932,
      "eval_runtime": 422.1114,
      "eval_samples_per_second": 6.956,
      "eval_steps_per_second": 3.478,
      "step": 342
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.138671875,
      "learning_rate": 2.966471156802477e-05,
      "loss": 0.9148,
      "step": 343
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.12353515625,
      "learning_rate": 2.9164631995886093e-05,
      "loss": 0.9928,
      "step": 344
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.1162109375,
      "learning_rate": 2.8668082857562005e-05,
      "loss": 0.8124,
      "step": 345
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.10107421875,
      "learning_rate": 2.8175088901055026e-05,
      "loss": 0.8412,
      "step": 346
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.10986328125,
      "learning_rate": 2.7685674697177566e-05,
      "loss": 0.7348,
      "step": 347
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.103515625,
      "learning_rate": 2.7199864638327077e-05,
      "loss": 0.7976,
      "step": 348
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.126953125,
      "learning_rate": 2.6717682937270604e-05,
      "loss": 0.7628,
      "step": 349
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.10693359375,
      "learning_rate": 2.6239153625937784e-05,
      "loss": 0.8783,
      "step": 350
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.1337890625,
      "learning_rate": 2.5764300554223242e-05,
      "loss": 0.6852,
      "step": 351
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.1181640625,
      "learning_rate": 2.529314738879781e-05,
      "loss": 0.8181,
      "step": 352
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.10693359375,
      "learning_rate": 2.4825717611929146e-05,
      "loss": 0.8616,
      "step": 353
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.119140625,
      "learning_rate": 2.4362034520311216e-05,
      "loss": 0.8029,
      "step": 354
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.126953125,
      "learning_rate": 2.390212122390323e-05,
      "loss": 0.8134,
      "step": 355
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.1298828125,
      "learning_rate": 2.3446000644777853e-05,
      "loss": 0.7766,
      "step": 356
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.107421875,
      "learning_rate": 2.2993695515978762e-05,
      "loss": 0.8786,
      "step": 357
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.1181640625,
      "learning_rate": 2.2545228380387706e-05,
      "loss": 0.8264,
      "step": 358
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.10986328125,
      "learning_rate": 2.210062158960081e-05,
      "loss": 0.8366,
      "step": 359
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.1025390625,
      "learning_rate": 2.1659897302814747e-05,
      "loss": 0.8282,
      "step": 360
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.10009765625,
      "learning_rate": 2.1223077485722198e-05,
      "loss": 0.9779,
      "step": 361
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.11181640625,
      "learning_rate": 2.0790183909417093e-05,
      "loss": 0.8431,
      "step": 362
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.12451171875,
      "learning_rate": 2.036123814930967e-05,
      "loss": 0.8402,
      "step": 363
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.10302734375,
      "learning_rate": 1.9936261584050973e-05,
      "loss": 0.9097,
      "step": 364
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1083984375,
      "learning_rate": 1.9515275394467446e-05,
      "loss": 0.7467,
      "step": 365
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.11376953125,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.9132,
      "step": 366
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.09765625,
      "learning_rate": 1.8685357870184605e-05,
      "loss": 0.9088,
      "step": 367
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.09130859375,
      "learning_rate": 1.8276467898563887e-05,
      "loss": 0.8388,
      "step": 368
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.09228515625,
      "learning_rate": 1.7871651026713908e-05,
      "loss": 0.703,
      "step": 369
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.1435546875,
      "learning_rate": 1.7470927430702277e-05,
      "loss": 0.8362,
      "step": 370
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.09375,
      "learning_rate": 1.7074317082587755e-05,
      "loss": 0.7667,
      "step": 371
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.185546875,
      "learning_rate": 1.668183974942491e-05,
      "loss": 0.8881,
      "step": 372
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.12158203125,
      "learning_rate": 1.6293514992278936e-05,
      "loss": 0.8335,
      "step": 373
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.12353515625,
      "learning_rate": 1.590936216525061e-05,
      "loss": 0.8181,
      "step": 374
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.1015625,
      "learning_rate": 1.5529400414511806e-05,
      "loss": 0.7918,
      "step": 375
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.12109375,
      "learning_rate": 1.5153648677351195e-05,
      "loss": 0.8674,
      "step": 376
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.1123046875,
      "learning_rate": 1.4782125681230497e-05,
      "loss": 0.7134,
      "step": 377
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.09228515625,
      "learning_rate": 1.4414849942850927e-05,
      "loss": 0.8532,
      "step": 378
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.1025390625,
      "learning_rate": 1.4051839767230478e-05,
      "loss": 0.7936,
      "step": 379
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.1025390625,
      "learning_rate": 1.3693113246791589e-05,
      "loss": 0.7971,
      "step": 380
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.123046875,
      "learning_rate": 1.333868826045932e-05,
      "loss": 0.7371,
      "step": 381
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.11962890625,
      "learning_rate": 1.2988582472770373e-05,
      "loss": 0.7324,
      "step": 382
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.10888671875,
      "learning_rate": 1.2642813332992608e-05,
      "loss": 0.7527,
      "step": 383
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.095703125,
      "learning_rate": 1.2301398074255443e-05,
      "loss": 0.8041,
      "step": 384
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.09814453125,
      "learning_rate": 1.196435371269089e-05,
      "loss": 0.9232,
      "step": 385
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.0947265625,
      "learning_rate": 1.163169704658551e-05,
      "loss": 0.875,
      "step": 386
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.11181640625,
      "learning_rate": 1.1303444655543206e-05,
      "loss": 0.9133,
      "step": 387
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.1064453125,
      "learning_rate": 1.0979612899658876e-05,
      "loss": 0.7921,
      "step": 388
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.1064453125,
      "learning_rate": 1.0660217918702965e-05,
      "loss": 0.7747,
      "step": 389
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.1171875,
      "learning_rate": 1.0345275631317163e-05,
      "loss": 0.8552,
      "step": 390
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.1005859375,
      "learning_rate": 1.0034801734220922e-05,
      "loss": 0.8868,
      "step": 391
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.09716796875,
      "learning_rate": 9.728811701429241e-06,
      "loss": 0.8623,
      "step": 392
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.123046875,
      "learning_rate": 9.427320783481353e-06,
      "loss": 0.8697,
      "step": 393
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.1279296875,
      "learning_rate": 9.130344006680657e-06,
      "loss": 0.749,
      "step": 394
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.087890625,
      "learning_rate": 8.837896172345827e-06,
      "loss": 0.8668,
      "step": 395
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.10009765625,
      "learning_rate": 8.549991856073069e-06,
      "loss": 0.9327,
      "step": 396
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.111328125,
      "learning_rate": 8.266645407009788e-06,
      "loss": 0.8025,
      "step": 397
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.10888671875,
      "learning_rate": 7.987870947139275e-06,
      "loss": 0.8903,
      "step": 398
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.11279296875,
      "learning_rate": 7.713682370576946e-06,
      "loss": 0.8081,
      "step": 399
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.12158203125,
      "learning_rate": 7.4440933428779e-06,
      "loss": 0.7926,
      "step": 400
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.10498046875,
      "learning_rate": 7.17911730035572e-06,
      "loss": 0.863,
      "step": 401
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.10400390625,
      "learning_rate": 6.9187674494129325e-06,
      "loss": 0.7536,
      "step": 402
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.11328125,
      "learning_rate": 6.663056765882692e-06,
      "loss": 0.7939,
      "step": 403
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.10693359375,
      "learning_rate": 6.4119979943821015e-06,
      "loss": 0.7258,
      "step": 404
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.11083984375,
      "learning_rate": 6.165603647677054e-06,
      "loss": 0.7775,
      "step": 405
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.09716796875,
      "learning_rate": 5.923886006058565e-06,
      "loss": 0.8807,
      "step": 406
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.09765625,
      "learning_rate": 5.6868571167307595e-06,
      "loss": 0.911,
      "step": 407
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.103515625,
      "learning_rate": 5.454528793210356e-06,
      "loss": 0.8141,
      "step": 408
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.10400390625,
      "learning_rate": 5.2269126147379555e-06,
      "loss": 0.8843,
      "step": 409
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.10107421875,
      "learning_rate": 5.00401992570092e-06,
      "loss": 0.7764,
      "step": 410
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.109375,
      "learning_rate": 4.785861835067962e-06,
      "loss": 0.7584,
      "step": 411
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.10595703125,
      "learning_rate": 4.5724492158354396e-06,
      "loss": 0.8061,
      "step": 412
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.11669921875,
      "learning_rate": 4.3637927044855475e-06,
      "loss": 0.8835,
      "step": 413
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.1123046875,
      "learning_rate": 4.159902700456053e-06,
      "loss": 0.8228,
      "step": 414
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.11376953125,
      "learning_rate": 3.960789365622075e-06,
      "loss": 0.7909,
      "step": 415
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.10693359375,
      "learning_rate": 3.766462623789646e-06,
      "loss": 0.9526,
      "step": 416
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.08837890625,
      "learning_rate": 3.57693216020103e-06,
      "loss": 0.8374,
      "step": 417
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.10693359375,
      "learning_rate": 3.3922074210520405e-06,
      "loss": 0.8091,
      "step": 418
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.1083984375,
      "learning_rate": 3.2122976130212646e-06,
      "loss": 0.886,
      "step": 419
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.1025390625,
      "learning_rate": 3.0372117028111825e-06,
      "loss": 0.7662,
      "step": 420
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.1171875,
      "learning_rate": 2.866958416701271e-06,
      "loss": 0.9222,
      "step": 421
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.103515625,
      "learning_rate": 2.7015462401130843e-06,
      "loss": 0.7954,
      "step": 422
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.09423828125,
      "learning_rate": 2.5409834171873482e-06,
      "loss": 0.7532,
      "step": 423
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.11962890625,
      "learning_rate": 2.3852779503730216e-06,
      "loss": 0.8322,
      "step": 424
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.12890625,
      "learning_rate": 2.2344376000285604e-06,
      "loss": 0.7971,
      "step": 425
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.1279296875,
      "learning_rate": 2.088469884035049e-06,
      "loss": 0.8257,
      "step": 426
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.13671875,
      "learning_rate": 1.9473820774215555e-06,
      "loss": 0.7701,
      "step": 427
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.12109375,
      "learning_rate": 1.8111812120024885e-06,
      "loss": 0.8043,
      "step": 428
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.10595703125,
      "learning_rate": 1.6798740760272103e-06,
      "loss": 0.7984,
      "step": 429
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.11767578125,
      "learning_rate": 1.553467213841664e-06,
      "loss": 0.8012,
      "step": 430
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.10400390625,
      "learning_rate": 1.4319669255622115e-06,
      "loss": 0.8198,
      "step": 431
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.1083984375,
      "learning_rate": 1.3153792667616183e-06,
      "loss": 0.8186,
      "step": 432
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.09912109375,
      "learning_rate": 1.2037100481672835e-06,
      "loss": 0.722,
      "step": 433
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.12158203125,
      "learning_rate": 1.0969648353715945e-06,
      "loss": 0.8273,
      "step": 434
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.10791015625,
      "learning_rate": 9.951489485545695e-07,
      "loss": 0.8434,
      "step": 435
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.1123046875,
      "learning_rate": 8.982674622186605e-07,
      "loss": 0.8882,
      "step": 436
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.130859375,
      "learning_rate": 8.063252049358982e-07,
      "loss": 0.9377,
      "step": 437
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.0986328125,
      "learning_rate": 7.193267591071529e-07,
      "loss": 0.8761,
      "step": 438
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.10595703125,
      "learning_rate": 6.372764607338599e-07,
      "loss": 0.8163,
      "step": 439
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.1005859375,
      "learning_rate": 5.60178399201805e-07,
      "loss": 0.8317,
      "step": 440
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.11474609375,
      "learning_rate": 4.880364170773533e-07,
      "loss": 0.8711,
      "step": 441
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.1005859375,
      "learning_rate": 4.208541099159691e-07,
      "loss": 0.7127,
      "step": 442
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.125,
      "learning_rate": 3.586348260829486e-07,
      "loss": 0.8064,
      "step": 443
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.10498046875,
      "learning_rate": 3.013816665865976e-07,
      "loss": 0.9065,
      "step": 444
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.11328125,
      "learning_rate": 2.490974849236216e-07,
      "loss": 0.7879,
      "step": 445
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.10498046875,
      "learning_rate": 2.0178488693695096e-07,
      "loss": 0.7726,
      "step": 446
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.11376953125,
      "learning_rate": 1.5944623068586685e-07,
      "loss": 0.8243,
      "step": 447
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.107421875,
      "learning_rate": 1.2208362632842862e-07,
      "loss": 0.8225,
      "step": 448
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.10595703125,
      "learning_rate": 8.969893601634694e-08,
      "loss": 0.7913,
      "step": 449
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.11865234375,
      "learning_rate": 6.229377380218005e-08,
      "loss": 0.7748,
      "step": 450
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.111328125,
      "learning_rate": 3.986950555883162e-08,
      "loss": 0.8305,
      "step": 451
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.125,
      "learning_rate": 2.242724891156067e-08,
      "loss": 0.8547,
      "step": 452
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11181640625,
      "learning_rate": 9.96787318218173e-09,
      "loss": 1.0104,
      "step": 453
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11865234375,
      "learning_rate": 2.4919993458549784e-09,
      "loss": 0.8115,
      "step": 454
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.146484375,
      "learning_rate": 0.0,
      "loss": 0.8365,
      "step": 455
    }
  ],
  "logging_steps": 1,
  "max_steps": 455,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 1.3577390229395866e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}