{
  "best_metric": 1.5694061517715454,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.015280589830767468,
  "eval_steps": 200,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9100737288459333e-05,
      "grad_norm": 2.8862252235412598,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.1395,
      "step": 1
    },
    {
      "epoch": 1.9100737288459333e-05,
      "eval_loss": 2.2263200283050537,
      "eval_runtime": 316.0822,
      "eval_samples_per_second": 3.331,
      "eval_steps_per_second": 3.331,
      "step": 1
    },
    {
      "epoch": 3.8201474576918666e-05,
      "grad_norm": 3.4391584396362305,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.8027,
      "step": 2
    },
    {
      "epoch": 5.7302211865378006e-05,
      "grad_norm": 3.24825382232666,
      "learning_rate": 2e-05,
      "loss": 2.4491,
      "step": 3
    },
    {
      "epoch": 7.640294915383733e-05,
      "grad_norm": 2.733004570007324,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 2.0916,
      "step": 4
    },
    {
      "epoch": 9.550368644229668e-05,
      "grad_norm": 2.9276905059814453,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.0489,
      "step": 5
    },
    {
      "epoch": 0.00011460442373075601,
      "grad_norm": 3.00897216796875,
      "learning_rate": 4e-05,
      "loss": 1.9238,
      "step": 6
    },
    {
      "epoch": 0.00013370516101921534,
      "grad_norm": 3.4740657806396484,
      "learning_rate": 4.666666666666667e-05,
      "loss": 2.1695,
      "step": 7
    },
    {
      "epoch": 0.00015280589830767466,
      "grad_norm": 3.4462039470672607,
      "learning_rate": 5.333333333333333e-05,
      "loss": 2.1095,
      "step": 8
    },
    {
      "epoch": 0.000171906635596134,
      "grad_norm": 3.4225332736968994,
      "learning_rate": 6e-05,
      "loss": 2.0757,
      "step": 9
    },
    {
      "epoch": 0.00019100737288459336,
      "grad_norm": 3.198228359222412,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.9697,
      "step": 10
    },
    {
      "epoch": 0.00021010811017305268,
      "grad_norm": 3.0764546394348145,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.5943,
      "step": 11
    },
    {
      "epoch": 0.00022920884746151202,
      "grad_norm": 1.6784659624099731,
      "learning_rate": 8e-05,
      "loss": 1.3522,
      "step": 12
    },
    {
      "epoch": 0.00024830958474997137,
      "grad_norm": 2.5861074924468994,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.8046,
      "step": 13
    },
    {
      "epoch": 0.0002674103220384307,
      "grad_norm": 3.264624834060669,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.6148,
      "step": 14
    },
    {
      "epoch": 0.00028651105932689,
      "grad_norm": 2.808166265487671,
      "learning_rate": 0.0001,
      "loss": 1.936,
      "step": 15
    },
    {
      "epoch": 0.0003056117966153493,
      "grad_norm": 2.9306869506835938,
      "learning_rate": 0.00010666666666666667,
      "loss": 1.5395,
      "step": 16
    },
    {
      "epoch": 0.0003247125339038087,
      "grad_norm": 3.3971645832061768,
      "learning_rate": 0.00011333333333333334,
      "loss": 1.8517,
      "step": 17
    },
    {
      "epoch": 0.000343813271192268,
      "grad_norm": 2.8275866508483887,
      "learning_rate": 0.00012,
      "loss": 1.6786,
      "step": 18
    },
    {
      "epoch": 0.00036291400848072734,
      "grad_norm": 2.278487205505371,
      "learning_rate": 0.00012666666666666666,
      "loss": 1.6503,
      "step": 19
    },
    {
      "epoch": 0.0003820147457691867,
      "grad_norm": 2.1270406246185303,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.5918,
      "step": 20
    },
    {
      "epoch": 0.00040111548305764603,
      "grad_norm": 2.463719367980957,
      "learning_rate": 0.00014,
      "loss": 1.5191,
      "step": 21
    },
    {
      "epoch": 0.00042021622034610535,
      "grad_norm": 2.275932550430298,
      "learning_rate": 0.00014666666666666666,
      "loss": 2.0279,
      "step": 22
    },
    {
      "epoch": 0.00043931695763456467,
      "grad_norm": 2.329066753387451,
      "learning_rate": 0.00015333333333333334,
      "loss": 1.8537,
      "step": 23
    },
    {
      "epoch": 0.00045841769492302404,
      "grad_norm": 2.675140142440796,
      "learning_rate": 0.00016,
      "loss": 1.4386,
      "step": 24
    },
    {
      "epoch": 0.00047751843221148336,
      "grad_norm": 2.268019676208496,
      "learning_rate": 0.0001666666666666667,
      "loss": 1.2343,
      "step": 25
    },
    {
      "epoch": 0.0004966191694999427,
      "grad_norm": 2.177272081375122,
      "learning_rate": 0.00017333333333333334,
      "loss": 1.4084,
      "step": 26
    },
    {
      "epoch": 0.0005157199067884021,
      "grad_norm": 2.1658875942230225,
      "learning_rate": 0.00018,
      "loss": 1.7442,
      "step": 27
    },
    {
      "epoch": 0.0005348206440768614,
      "grad_norm": 1.8271211385726929,
      "learning_rate": 0.0001866666666666667,
      "loss": 1.5215,
      "step": 28
    },
    {
      "epoch": 0.0005539213813653207,
      "grad_norm": 2.1778268814086914,
      "learning_rate": 0.00019333333333333333,
      "loss": 1.5868,
      "step": 29
    },
    {
      "epoch": 0.00057302211865378,
      "grad_norm": 3.8509902954101562,
      "learning_rate": 0.0002,
      "loss": 2.0605,
      "step": 30
    },
    {
      "epoch": 0.0005921228559422393,
      "grad_norm": 2.5701615810394287,
      "learning_rate": 0.0001999999999799879,
      "loss": 1.4426,
      "step": 31
    },
    {
      "epoch": 0.0006112235932306987,
      "grad_norm": 2.279927968978882,
      "learning_rate": 0.00019999999991995147,
      "loss": 2.1571,
      "step": 32
    },
    {
      "epoch": 0.0006303243305191581,
      "grad_norm": 2.038774013519287,
      "learning_rate": 0.0001999999998198908,
      "loss": 1.9971,
      "step": 33
    },
    {
      "epoch": 0.0006494250678076174,
      "grad_norm": 1.8254480361938477,
      "learning_rate": 0.00019999999967980586,
      "loss": 2.0356,
      "step": 34
    },
    {
      "epoch": 0.0006685258050960767,
      "grad_norm": 1.9942517280578613,
      "learning_rate": 0.00019999999949969662,
      "loss": 1.6483,
      "step": 35
    },
    {
      "epoch": 0.000687626542384536,
      "grad_norm": 2.3504881858825684,
      "learning_rate": 0.00019999999927956314,
      "loss": 1.84,
      "step": 36
    },
    {
      "epoch": 0.0007067272796729954,
      "grad_norm": 2.0903565883636475,
      "learning_rate": 0.0001999999990194054,
      "loss": 1.6657,
      "step": 37
    },
    {
      "epoch": 0.0007258280169614547,
      "grad_norm": 2.1086957454681396,
      "learning_rate": 0.00019999999871922336,
      "loss": 1.3955,
      "step": 38
    },
    {
      "epoch": 0.000744928754249914,
      "grad_norm": 2.021134853363037,
      "learning_rate": 0.00019999999837901707,
      "loss": 1.8902,
      "step": 39
    },
    {
      "epoch": 0.0007640294915383734,
      "grad_norm": 2.0780029296875,
      "learning_rate": 0.0001999999979987865,
      "loss": 1.4245,
      "step": 40
    },
    {
      "epoch": 0.0007831302288268327,
      "grad_norm": 1.9456417560577393,
      "learning_rate": 0.00019999999757853168,
      "loss": 1.4706,
      "step": 41
    },
    {
      "epoch": 0.0008022309661152921,
      "grad_norm": 2.299532413482666,
      "learning_rate": 0.00019999999711825257,
      "loss": 1.5172,
      "step": 42
    },
    {
      "epoch": 0.0008213317034037514,
      "grad_norm": 1.8858073949813843,
      "learning_rate": 0.00019999999661794919,
      "loss": 1.4382,
      "step": 43
    },
    {
      "epoch": 0.0008404324406922107,
      "grad_norm": 1.940314531326294,
      "learning_rate": 0.00019999999607762156,
      "loss": 1.79,
      "step": 44
    },
    {
      "epoch": 0.00085953317798067,
      "grad_norm": 2.42816162109375,
      "learning_rate": 0.00019999999549726965,
      "loss": 1.5518,
      "step": 45
    },
    {
      "epoch": 0.0008786339152691293,
      "grad_norm": 2.3732922077178955,
      "learning_rate": 0.00019999999487689348,
      "loss": 1.2767,
      "step": 46
    },
    {
      "epoch": 0.0008977346525575888,
      "grad_norm": 2.3355696201324463,
      "learning_rate": 0.00019999999421649304,
      "loss": 1.9033,
      "step": 47
    },
    {
      "epoch": 0.0009168353898460481,
      "grad_norm": 2.610511541366577,
      "learning_rate": 0.00019999999351606832,
      "loss": 1.3478,
      "step": 48
    },
    {
      "epoch": 0.0009359361271345074,
      "grad_norm": 2.216140031814575,
      "learning_rate": 0.00019999999277561933,
      "loss": 1.7938,
      "step": 49
    },
    {
      "epoch": 0.0009550368644229667,
      "grad_norm": 2.0531485080718994,
      "learning_rate": 0.00019999999199514607,
      "loss": 1.8071,
      "step": 50
    },
    {
      "epoch": 0.000974137601711426,
      "grad_norm": 1.8329895734786987,
      "learning_rate": 0.0001999999911746486,
      "loss": 1.3811,
      "step": 51
    },
    {
      "epoch": 0.0009932383389998855,
      "grad_norm": 2.031695604324341,
      "learning_rate": 0.00019999999031412679,
      "loss": 1.5682,
      "step": 52
    },
    {
      "epoch": 0.0010123390762883447,
      "grad_norm": 1.998159646987915,
      "learning_rate": 0.00019999998941358074,
      "loss": 1.7952,
      "step": 53
    },
    {
      "epoch": 0.0010314398135768041,
      "grad_norm": 2.856948137283325,
      "learning_rate": 0.00019999998847301041,
      "loss": 1.7871,
      "step": 54
    },
    {
      "epoch": 0.0010505405508652633,
      "grad_norm": 2.231086015701294,
      "learning_rate": 0.00019999998749241585,
      "loss": 1.4914,
      "step": 55
    },
    {
      "epoch": 0.0010696412881537228,
      "grad_norm": 4.362732887268066,
      "learning_rate": 0.000199999986471797,
      "loss": 1.5,
      "step": 56
    },
    {
      "epoch": 0.001088742025442182,
      "grad_norm": 2.6997902393341064,
      "learning_rate": 0.00019999998541115387,
      "loss": 1.5444,
      "step": 57
    },
    {
      "epoch": 0.0011078427627306414,
      "grad_norm": 2.353186845779419,
      "learning_rate": 0.00019999998431048652,
      "loss": 1.5371,
      "step": 58
    },
    {
      "epoch": 0.0011269435000191008,
      "grad_norm": 2.691775321960449,
      "learning_rate": 0.00019999998316979487,
      "loss": 1.7803,
      "step": 59
    },
    {
      "epoch": 0.00114604423730756,
      "grad_norm": 3.6163430213928223,
      "learning_rate": 0.000199999981989079,
      "loss": 1.8752,
      "step": 60
    },
    {
      "epoch": 0.0011651449745960195,
      "grad_norm": 2.948490858078003,
      "learning_rate": 0.00019999998076833882,
      "loss": 1.7717,
      "step": 61
    },
    {
      "epoch": 0.0011842457118844787,
      "grad_norm": 2.596435785293579,
      "learning_rate": 0.00019999997950757438,
      "loss": 1.4604,
      "step": 62
    },
    {
      "epoch": 0.001203346449172938,
      "grad_norm": 2.1044397354125977,
      "learning_rate": 0.00019999997820678572,
      "loss": 1.427,
      "step": 63
    },
    {
      "epoch": 0.0012224471864613973,
      "grad_norm": 3.173208713531494,
      "learning_rate": 0.00019999997686597274,
      "loss": 1.5585,
      "step": 64
    },
    {
      "epoch": 0.0012415479237498567,
      "grad_norm": 2.3645482063293457,
      "learning_rate": 0.00019999997548513553,
      "loss": 1.3976,
      "step": 65
    },
    {
      "epoch": 0.0012606486610383162,
      "grad_norm": 2.745518684387207,
      "learning_rate": 0.00019999997406427406,
      "loss": 2.108,
      "step": 66
    },
    {
      "epoch": 0.0012797493983267754,
      "grad_norm": 2.378756523132324,
      "learning_rate": 0.0001999999726033883,
      "loss": 1.7581,
      "step": 67
    },
    {
      "epoch": 0.0012988501356152348,
      "grad_norm": 2.1616084575653076,
      "learning_rate": 0.00019999997110247835,
      "loss": 1.824,
      "step": 68
    },
    {
      "epoch": 0.001317950872903694,
      "grad_norm": 2.809875249862671,
      "learning_rate": 0.0001999999695615441,
      "loss": 1.5963,
      "step": 69
    },
    {
      "epoch": 0.0013370516101921534,
      "grad_norm": 2.1254022121429443,
      "learning_rate": 0.0001999999679805856,
      "loss": 1.3171,
      "step": 70
    },
    {
      "epoch": 0.0013561523474806127,
      "grad_norm": 2.1234116554260254,
      "learning_rate": 0.00019999996635960282,
      "loss": 1.4015,
      "step": 71
    },
    {
      "epoch": 0.001375253084769072,
      "grad_norm": 1.7554460763931274,
      "learning_rate": 0.00019999996469859582,
      "loss": 1.0786,
      "step": 72
    },
    {
      "epoch": 0.0013943538220575315,
      "grad_norm": 2.334164619445801,
      "learning_rate": 0.00019999996299756455,
      "loss": 1.8696,
      "step": 73
    },
    {
      "epoch": 0.0014134545593459907,
      "grad_norm": 2.00146222114563,
      "learning_rate": 0.00019999996125650898,
      "loss": 1.6692,
      "step": 74
    },
    {
      "epoch": 0.0014325552966344501,
      "grad_norm": 3.107241630554199,
      "learning_rate": 0.0001999999594754292,
      "loss": 1.8065,
      "step": 75
    },
    {
      "epoch": 0.0014516560339229094,
      "grad_norm": 2.5778086185455322,
      "learning_rate": 0.00019999995765432516,
      "loss": 1.6653,
      "step": 76
    },
    {
      "epoch": 0.0014707567712113688,
      "grad_norm": 3.0558886528015137,
      "learning_rate": 0.00019999995579319686,
      "loss": 1.7406,
      "step": 77
    },
    {
      "epoch": 0.001489857508499828,
      "grad_norm": 2.4782676696777344,
      "learning_rate": 0.00019999995389204434,
      "loss": 1.7546,
      "step": 78
    },
    {
      "epoch": 0.0015089582457882874,
      "grad_norm": 2.281754970550537,
      "learning_rate": 0.00019999995195086752,
      "loss": 1.7369,
      "step": 79
    },
    {
      "epoch": 0.0015280589830767469,
      "grad_norm": 2.5520246028900146,
      "learning_rate": 0.00019999994996966648,
      "loss": 1.7154,
      "step": 80
    },
    {
      "epoch": 0.001547159720365206,
      "grad_norm": 1.9986528158187866,
      "learning_rate": 0.00019999994794844117,
      "loss": 1.4905,
      "step": 81
    },
    {
      "epoch": 0.0015662604576536655,
      "grad_norm": 2.220820188522339,
      "learning_rate": 0.00019999994588719165,
      "loss": 1.2747,
      "step": 82
    },
    {
      "epoch": 0.0015853611949421247,
      "grad_norm": 2.518646478652954,
      "learning_rate": 0.00019999994378591782,
      "loss": 1.2548,
      "step": 83
    },
    {
      "epoch": 0.0016044619322305841,
      "grad_norm": 1.9261964559555054,
      "learning_rate": 0.0001999999416446198,
      "loss": 1.9776,
      "step": 84
    },
    {
      "epoch": 0.0016235626695190433,
      "grad_norm": 2.5148706436157227,
      "learning_rate": 0.0001999999394632975,
      "loss": 1.5207,
      "step": 85
    },
    {
      "epoch": 0.0016426634068075028,
      "grad_norm": 2.192227840423584,
      "learning_rate": 0.00019999993724195095,
      "loss": 1.6417,
      "step": 86
    },
    {
      "epoch": 0.0016617641440959622,
      "grad_norm": 2.313175916671753,
      "learning_rate": 0.00019999993498058015,
      "loss": 1.3595,
      "step": 87
    },
    {
      "epoch": 0.0016808648813844214,
      "grad_norm": 2.8898582458496094,
      "learning_rate": 0.00019999993267918515,
      "loss": 1.7908,
      "step": 88
    },
    {
      "epoch": 0.0016999656186728808,
      "grad_norm": 3.6070396900177,
      "learning_rate": 0.00019999993033776588,
      "loss": 1.7674,
      "step": 89
    },
    {
      "epoch": 0.00171906635596134,
      "grad_norm": 2.1871302127838135,
      "learning_rate": 0.00019999992795632237,
      "loss": 1.316,
      "step": 90
    },
    {
      "epoch": 0.0017381670932497995,
      "grad_norm": 2.926851749420166,
      "learning_rate": 0.00019999992553485462,
      "loss": 1.7474,
      "step": 91
    },
    {
      "epoch": 0.0017572678305382587,
      "grad_norm": 2.6435787677764893,
      "learning_rate": 0.0001999999230733626,
      "loss": 1.5406,
      "step": 92
    },
    {
      "epoch": 0.0017763685678267181,
      "grad_norm": 2.5064949989318848,
      "learning_rate": 0.0001999999205718464,
      "loss": 1.5079,
      "step": 93
    },
    {
      "epoch": 0.0017954693051151775,
      "grad_norm": 1.9534028768539429,
      "learning_rate": 0.0001999999180303059,
      "loss": 1.3219,
      "step": 94
    },
    {
      "epoch": 0.0018145700424036368,
      "grad_norm": 2.5084455013275146,
      "learning_rate": 0.00019999991544874122,
      "loss": 1.5544,
      "step": 95
    },
    {
      "epoch": 0.0018336707796920962,
      "grad_norm": 2.4156782627105713,
      "learning_rate": 0.00019999991282715227,
      "loss": 1.2772,
      "step": 96
    },
    {
      "epoch": 0.0018527715169805554,
      "grad_norm": 2.3028922080993652,
      "learning_rate": 0.00019999991016553907,
      "loss": 1.8476,
      "step": 97
    },
    {
      "epoch": 0.0018718722542690148,
      "grad_norm": 3.617969036102295,
      "learning_rate": 0.00019999990746390168,
      "loss": 1.7461,
      "step": 98
    },
    {
      "epoch": 0.001890972991557474,
      "grad_norm": 2.1743767261505127,
      "learning_rate": 0.00019999990472224002,
      "loss": 1.6019,
      "step": 99
    },
    {
      "epoch": 0.0019100737288459335,
      "grad_norm": 1.988259196281433,
      "learning_rate": 0.00019999990194055414,
      "loss": 1.1356,
      "step": 100
    },
    {
      "epoch": 0.0019291744661343929,
      "grad_norm": 2.7918896675109863,
      "learning_rate": 0.00019999989911884401,
      "loss": 1.2827,
      "step": 101
    },
    {
      "epoch": 0.001948275203422852,
      "grad_norm": 2.2214574813842773,
      "learning_rate": 0.00019999989625710967,
      "loss": 1.3161,
      "step": 102
    },
    {
      "epoch": 0.0019673759407113113,
      "grad_norm": 2.7484312057495117,
      "learning_rate": 0.00019999989335535111,
      "loss": 1.4554,
      "step": 103
    },
    {
      "epoch": 0.001986476677999771,
      "grad_norm": 2.3056230545043945,
      "learning_rate": 0.0001999998904135683,
      "loss": 1.5543,
      "step": 104
    },
    {
      "epoch": 0.00200557741528823,
      "grad_norm": 2.3826181888580322,
      "learning_rate": 0.0001999998874317613,
      "loss": 1.8049,
      "step": 105
    },
    {
      "epoch": 0.0020246781525766894,
      "grad_norm": 2.8164000511169434,
      "learning_rate": 0.00019999988440993005,
      "loss": 1.6252,
      "step": 106
    },
    {
      "epoch": 0.0020437788898651486,
      "grad_norm": 2.1725380420684814,
      "learning_rate": 0.00019999988134807457,
      "loss": 1.6536,
      "step": 107
    },
    {
      "epoch": 0.0020628796271536082,
      "grad_norm": 2.126236915588379,
      "learning_rate": 0.0001999998782461949,
      "loss": 1.4284,
      "step": 108
    },
    {
      "epoch": 0.0020819803644420674,
      "grad_norm": 2.229064702987671,
      "learning_rate": 0.00019999987510429097,
      "loss": 1.5593,
      "step": 109
    },
    {
      "epoch": 0.0021010811017305266,
      "grad_norm": 1.810829758644104,
      "learning_rate": 0.00019999987192236284,
      "loss": 1.4279,
      "step": 110
    },
    {
      "epoch": 0.0021201818390189863,
      "grad_norm": 2.8166043758392334,
      "learning_rate": 0.00019999986870041048,
      "loss": 1.6154,
      "step": 111
    },
    {
      "epoch": 0.0021392825763074455,
      "grad_norm": 2.3450582027435303,
      "learning_rate": 0.0001999998654384339,
      "loss": 1.6323,
      "step": 112
    },
    {
      "epoch": 0.0021583833135959047,
      "grad_norm": 2.489325523376465,
      "learning_rate": 0.00019999986213643312,
      "loss": 1.2157,
      "step": 113
    },
    {
      "epoch": 0.002177484050884364,
      "grad_norm": 2.057915449142456,
      "learning_rate": 0.0001999998587944081,
      "loss": 1.3839,
      "step": 114
    },
    {
      "epoch": 0.0021965847881728236,
      "grad_norm": 2.890739917755127,
      "learning_rate": 0.0001999998554123589,
      "loss": 1.8263,
      "step": 115
    },
    {
      "epoch": 0.0022156855254612828,
      "grad_norm": 3.21287202835083,
      "learning_rate": 0.00019999985199028547,
      "loss": 1.3502,
      "step": 116
    },
    {
      "epoch": 0.002234786262749742,
      "grad_norm": 2.981541395187378,
      "learning_rate": 0.0001999998485281878,
      "loss": 1.7858,
      "step": 117
    },
    {
      "epoch": 0.0022538870000382016,
      "grad_norm": 2.3792598247528076,
      "learning_rate": 0.00019999984502606596,
      "loss": 1.348,
      "step": 118
    },
    {
      "epoch": 0.002272987737326661,
      "grad_norm": 2.3506853580474854,
      "learning_rate": 0.0001999998414839199,
      "loss": 1.6198,
      "step": 119
    },
    {
      "epoch": 0.00229208847461512,
      "grad_norm": 2.1338250637054443,
      "learning_rate": 0.00019999983790174963,
      "loss": 1.8746,
      "step": 120
    },
    {
      "epoch": 0.0023111892119035793,
      "grad_norm": 2.2762632369995117,
      "learning_rate": 0.00019999983427955518,
      "loss": 1.6265,
      "step": 121
    },
    {
      "epoch": 0.002330289949192039,
      "grad_norm": 2.2870967388153076,
      "learning_rate": 0.0001999998306173365,
      "loss": 1.3229,
      "step": 122
    },
    {
      "epoch": 0.002349390686480498,
      "grad_norm": 2.090313196182251,
      "learning_rate": 0.0001999998269150936,
      "loss": 1.362,
      "step": 123
    },
    {
      "epoch": 0.0023684914237689573,
      "grad_norm": 2.3947181701660156,
      "learning_rate": 0.00019999982317282653,
      "loss": 1.3455,
      "step": 124
    },
    {
      "epoch": 0.002387592161057417,
      "grad_norm": 2.235891580581665,
      "learning_rate": 0.00019999981939053526,
      "loss": 1.7658,
      "step": 125
    },
    {
      "epoch": 0.002406692898345876,
      "grad_norm": 3.690429210662842,
      "learning_rate": 0.00019999981556821978,
      "loss": 1.6444,
      "step": 126
    },
    {
      "epoch": 0.0024257936356343354,
      "grad_norm": 2.4051835536956787,
      "learning_rate": 0.0001999998117058801,
      "loss": 1.7419,
      "step": 127
    },
    {
      "epoch": 0.0024448943729227946,
      "grad_norm": 2.426670551300049,
      "learning_rate": 0.00019999980780351627,
      "loss": 1.2884,
      "step": 128
    },
    {
      "epoch": 0.0024639951102112543,
      "grad_norm": 3.2974772453308105,
      "learning_rate": 0.0001999998038611282,
      "loss": 1.6563,
      "step": 129
    },
    {
      "epoch": 0.0024830958474997135,
      "grad_norm": 2.5536463260650635,
      "learning_rate": 0.00019999979987871594,
      "loss": 1.9819,
      "step": 130
    },
    {
      "epoch": 0.0025021965847881727,
      "grad_norm": 2.1051740646362305,
      "learning_rate": 0.0001999997958562795,
      "loss": 1.8811,
      "step": 131
    },
    {
      "epoch": 0.0025212973220766323,
      "grad_norm": 2.2078933715820312,
      "learning_rate": 0.00019999979179381887,
      "loss": 1.5382,
      "step": 132
    },
    {
      "epoch": 0.0025403980593650915,
      "grad_norm": 3.383906364440918,
      "learning_rate": 0.00019999978769133405,
      "loss": 2.216,
      "step": 133
    },
    {
      "epoch": 0.0025594987966535507,
      "grad_norm": 2.5879104137420654,
      "learning_rate": 0.00019999978354882505,
      "loss": 1.6759,
      "step": 134
    },
    {
      "epoch": 0.00257859953394201,
      "grad_norm": 2.6320433616638184,
      "learning_rate": 0.00019999977936629187,
      "loss": 1.8411,
      "step": 135
    },
    {
      "epoch": 0.0025977002712304696,
      "grad_norm": 2.4231834411621094,
      "learning_rate": 0.00019999977514373449,
      "loss": 1.5956,
      "step": 136
    },
    {
      "epoch": 0.002616801008518929,
      "grad_norm": 2.0169620513916016,
      "learning_rate": 0.00019999977088115296,
      "loss": 1.2277,
      "step": 137
    },
    {
      "epoch": 0.002635901745807388,
      "grad_norm": 3.472231864929199,
      "learning_rate": 0.00019999976657854722,
      "loss": 1.5948,
      "step": 138
    },
    {
      "epoch": 0.0026550024830958477,
      "grad_norm": 2.5279154777526855,
      "learning_rate": 0.0001999997622359173,
      "loss": 1.4737,
      "step": 139
    },
    {
      "epoch": 0.002674103220384307,
      "grad_norm": 2.6564242839813232,
      "learning_rate": 0.00019999975785326327,
      "loss": 1.4845,
      "step": 140
    },
    {
      "epoch": 0.002693203957672766,
      "grad_norm": 2.5151352882385254,
      "learning_rate": 0.00019999975343058498,
      "loss": 1.938,
      "step": 141
    },
    {
      "epoch": 0.0027123046949612253,
      "grad_norm": 2.485100746154785,
      "learning_rate": 0.00019999974896788255,
      "loss": 1.2789,
      "step": 142
    },
    {
      "epoch": 0.002731405432249685,
      "grad_norm": 2.683363199234009,
      "learning_rate": 0.00019999974446515597,
      "loss": 1.3936,
      "step": 143
    },
    {
      "epoch": 0.002750506169538144,
      "grad_norm": 3.2525599002838135,
      "learning_rate": 0.00019999973992240521,
      "loss": 1.7275,
      "step": 144
    },
    {
      "epoch": 0.0027696069068266034,
      "grad_norm": 3.371795892715454,
      "learning_rate": 0.0001999997353396303,
      "loss": 1.8081,
      "step": 145
    },
    {
      "epoch": 0.002788707644115063,
      "grad_norm": 2.4094715118408203,
      "learning_rate": 0.0001999997307168312,
      "loss": 2.1101,
      "step": 146
    },
    {
      "epoch": 0.0028078083814035222,
      "grad_norm": 1.8274271488189697,
      "learning_rate": 0.00019999972605400795,
      "loss": 1.7585,
      "step": 147
    },
    {
      "epoch": 0.0028269091186919814,
      "grad_norm": 2.364269733428955,
      "learning_rate": 0.00019999972135116055,
      "loss": 1.2389,
      "step": 148
    },
    {
      "epoch": 0.0028460098559804406,
      "grad_norm": 2.3882956504821777,
      "learning_rate": 0.00019999971660828898,
      "loss": 1.1999,
      "step": 149
    },
    {
      "epoch": 0.0028651105932689003,
      "grad_norm": 2.5090866088867188,
      "learning_rate": 0.00019999971182539325,
      "loss": 1.4175,
      "step": 150
    },
    {
      "epoch": 0.0028842113305573595,
      "grad_norm": 2.3067572116851807,
      "learning_rate": 0.00019999970700247338,
      "loss": 2.4155,
      "step": 151
    },
    {
      "epoch": 0.0029033120678458187,
      "grad_norm": 2.9375226497650146,
      "learning_rate": 0.00019999970213952932,
      "loss": 1.3831,
      "step": 152
    },
    {
      "epoch": 0.0029224128051342784,
      "grad_norm": 5.2036519050598145,
      "learning_rate": 0.00019999969723656112,
      "loss": 1.753,
      "step": 153
    },
    {
      "epoch": 0.0029415135424227376,
      "grad_norm": 2.1016502380371094,
      "learning_rate": 0.0001999996922935688,
      "loss": 1.2807,
      "step": 154
    },
    {
      "epoch": 0.0029606142797111968,
      "grad_norm": 2.7958061695098877,
      "learning_rate": 0.00019999968731055232,
      "loss": 1.7738,
      "step": 155
    },
    {
      "epoch": 0.002979715016999656,
      "grad_norm": 2.226079225540161,
      "learning_rate": 0.0001999996822875117,
      "loss": 1.2521,
      "step": 156
    },
    {
      "epoch": 0.0029988157542881156,
      "grad_norm": 2.214858293533325,
      "learning_rate": 0.00019999967722444693,
      "loss": 1.4534,
      "step": 157
    },
    {
      "epoch": 0.003017916491576575,
      "grad_norm": 2.0783298015594482,
      "learning_rate": 0.000199999672121358,
      "loss": 1.5081,
      "step": 158
    },
    {
      "epoch": 0.003037017228865034,
      "grad_norm": 2.807636022567749,
      "learning_rate": 0.00019999966697824495,
      "loss": 1.4873,
      "step": 159
    },
    {
      "epoch": 0.0030561179661534937,
      "grad_norm": 2.907313108444214,
      "learning_rate": 0.00019999966179510775,
      "loss": 2.033,
      "step": 160
    },
    {
      "epoch": 0.003075218703441953,
      "grad_norm": 2.160527467727661,
      "learning_rate": 0.00019999965657194646,
      "loss": 1.3221,
      "step": 161
    },
    {
      "epoch": 0.003094319440730412,
      "grad_norm": 2.844459295272827,
      "learning_rate": 0.000199999651308761,
      "loss": 1.7455,
      "step": 162
    },
    {
      "epoch": 0.0031134201780188713,
      "grad_norm": 2.577413558959961,
      "learning_rate": 0.0001999996460055514,
      "loss": 1.7371,
      "step": 163
    },
    {
      "epoch": 0.003132520915307331,
      "grad_norm": 2.604863405227661,
      "learning_rate": 0.00019999964066231768,
      "loss": 1.7457,
      "step": 164
    },
    {
      "epoch": 0.00315162165259579,
      "grad_norm": 2.5157277584075928,
      "learning_rate": 0.00019999963527905985,
      "loss": 1.5424,
      "step": 165
    },
    {
      "epoch": 0.0031707223898842494,
      "grad_norm": 3.825356960296631,
      "learning_rate": 0.00019999962985577788,
      "loss": 2.1176,
      "step": 166
    },
    {
      "epoch": 0.003189823127172709,
      "grad_norm": 2.772426128387451,
      "learning_rate": 0.0001999996243924718,
      "loss": 2.049,
      "step": 167
    },
    {
      "epoch": 0.0032089238644611683,
      "grad_norm": 2.5323781967163086,
      "learning_rate": 0.0001999996188891416,
      "loss": 1.5429,
      "step": 168
    },
    {
      "epoch": 0.0032280246017496275,
      "grad_norm": 2.2850685119628906,
      "learning_rate": 0.00019999961334578727,
      "loss": 1.5157,
      "step": 169
    },
    {
      "epoch": 0.0032471253390380867,
      "grad_norm": 2.675960063934326,
      "learning_rate": 0.00019999960776240883,
      "loss": 1.6712,
      "step": 170
    },
    {
      "epoch": 0.0032662260763265463,
      "grad_norm": 2.75435471534729,
      "learning_rate": 0.00019999960213900627,
      "loss": 1.6005,
      "step": 171
    },
    {
      "epoch": 0.0032853268136150055,
      "grad_norm": 2.3467557430267334,
      "learning_rate": 0.0001999995964755796,
      "loss": 1.4715,
      "step": 172
    },
    {
      "epoch": 0.0033044275509034647,
      "grad_norm": 2.336695432662964,
      "learning_rate": 0.00019999959077212883,
      "loss": 1.2254,
      "step": 173
    },
    {
      "epoch": 0.0033235282881919244,
      "grad_norm": 2.7015461921691895,
      "learning_rate": 0.00019999958502865396,
      "loss": 1.5923,
      "step": 174
    },
    {
      "epoch": 0.0033426290254803836,
      "grad_norm": 2.431546211242676,
      "learning_rate": 0.00019999957924515498,
      "loss": 1.7406,
      "step": 175
    },
    {
      "epoch": 0.003361729762768843,
      "grad_norm": 2.4438321590423584,
      "learning_rate": 0.0001999995734216319,
      "loss": 1.5958,
      "step": 176
    },
    {
      "epoch": 0.003380830500057302,
      "grad_norm": 2.4403486251831055,
      "learning_rate": 0.0001999995675580847,
      "loss": 1.3929,
      "step": 177
    },
    {
      "epoch": 0.0033999312373457617,
      "grad_norm": 2.921821117401123,
      "learning_rate": 0.00019999956165451345,
      "loss": 1.6266,
      "step": 178
    },
    {
      "epoch": 0.003419031974634221,
      "grad_norm": 2.6319615840911865,
      "learning_rate": 0.00019999955571091803,
      "loss": 1.7989,
      "step": 179
    },
    {
      "epoch": 0.00343813271192268,
      "grad_norm": 3.2718515396118164,
      "learning_rate": 0.00019999954972729856,
      "loss": 1.7098,
      "step": 180
    },
    {
      "epoch": 0.0034572334492111397,
      "grad_norm": 2.654764175415039,
      "learning_rate": 0.00019999954370365504,
      "loss": 1.5692,
      "step": 181
    },
    {
      "epoch": 0.003476334186499599,
      "grad_norm": 2.028338670730591,
      "learning_rate": 0.00019999953763998737,
      "loss": 1.3906,
      "step": 182
    },
    {
      "epoch": 0.003495434923788058,
      "grad_norm": 2.1966071128845215,
      "learning_rate": 0.00019999953153629566,
      "loss": 1.1697,
      "step": 183
    },
    {
      "epoch": 0.0035145356610765174,
      "grad_norm": 2.3460724353790283,
      "learning_rate": 0.00019999952539257983,
      "loss": 1.7295,
      "step": 184
    },
    {
      "epoch": 0.003533636398364977,
      "grad_norm": 1.9645721912384033,
      "learning_rate": 0.00019999951920883992,
      "loss": 1.486,
      "step": 185
    },
    {
      "epoch": 0.0035527371356534362,
      "grad_norm": 2.7481298446655273,
      "learning_rate": 0.000199999512985076,
      "loss": 1.6084,
      "step": 186
    },
    {
      "epoch": 0.0035718378729418954,
      "grad_norm": 2.696279287338257,
      "learning_rate": 0.00019999950672128792,
      "loss": 2.4454,
      "step": 187
    },
    {
      "epoch": 0.003590938610230355,
      "grad_norm": 2.639486312866211,
      "learning_rate": 0.00019999950041747582,
      "loss": 1.25,
      "step": 188
    },
    {
      "epoch": 0.0036100393475188143,
      "grad_norm": 2.5585715770721436,
      "learning_rate": 0.0001999994940736396,
      "loss": 1.546,
      "step": 189
    },
    {
      "epoch": 0.0036291400848072735,
      "grad_norm": 1.905794620513916,
      "learning_rate": 0.00019999948768977937,
      "loss": 1.8474,
      "step": 190
    },
    {
      "epoch": 0.0036482408220957327,
      "grad_norm": 2.779628276824951,
      "learning_rate": 0.00019999948126589502,
      "loss": 1.4795,
      "step": 191
    },
    {
      "epoch": 0.0036673415593841924,
      "grad_norm": 6.035836219787598,
      "learning_rate": 0.00019999947480198668,
      "loss": 1.6951,
      "step": 192
    },
    {
      "epoch": 0.0036864422966726516,
      "grad_norm": 2.193131685256958,
      "learning_rate": 0.0001999994682980542,
      "loss": 1.5978,
      "step": 193
    },
    {
      "epoch": 0.0037055430339611108,
      "grad_norm": 2.585526943206787,
      "learning_rate": 0.0001999994617540977,
      "loss": 1.9917,
      "step": 194
    },
    {
      "epoch": 0.0037246437712495704,
      "grad_norm": 2.113621234893799,
      "learning_rate": 0.00019999945517011717,
      "loss": 1.8738,
      "step": 195
    },
    {
      "epoch": 0.0037437445085380296,
      "grad_norm": 2.504206895828247,
      "learning_rate": 0.00019999944854611252,
      "loss": 1.2504,
      "step": 196
    },
    {
      "epoch": 0.003762845245826489,
      "grad_norm": 1.9457672834396362,
      "learning_rate": 0.00019999944188208387,
      "loss": 1.7049,
      "step": 197
    },
    {
      "epoch": 0.003781945983114948,
      "grad_norm": 2.117798089981079,
      "learning_rate": 0.00019999943517803116,
      "loss": 1.0466,
      "step": 198
    },
    {
      "epoch": 0.0038010467204034077,
      "grad_norm": 2.2993369102478027,
      "learning_rate": 0.0001999994284339544,
      "loss": 1.5536,
      "step": 199
    },
    {
      "epoch": 0.003820147457691867,
      "grad_norm": 2.8902273178100586,
      "learning_rate": 0.00019999942164985364,
      "loss": 2.1359,
      "step": 200
    },
    {
      "epoch": 0.003820147457691867,
      "eval_loss": 1.5694061517715454,
      "eval_runtime": 316.2531,
      "eval_samples_per_second": 3.33,
      "eval_steps_per_second": 3.33,
      "step": 200
    },
    {
      "epoch": 0.003839248194980326,
      "grad_norm": 2.9669551849365234,
      "learning_rate": 0.0001999994148257288,
      "loss": 1.8086,
      "step": 201
    },
    {
      "epoch": 0.0038583489322687858,
      "grad_norm": 2.314497232437134,
      "learning_rate": 0.00019999940796157993,
      "loss": 1.7036,
      "step": 202
    },
    {
      "epoch": 0.003877449669557245,
      "grad_norm": 2.9868078231811523,
      "learning_rate": 0.00019999940105740703,
      "loss": 1.7222,
      "step": 203
    },
    {
      "epoch": 0.003896550406845704,
      "grad_norm": 1.6720106601715088,
      "learning_rate": 0.0001999993941132101,
      "loss": 1.2311,
      "step": 204
    },
    {
      "epoch": 0.003915651144134164,
      "grad_norm": 3.0014541149139404,
      "learning_rate": 0.00019999938712898912,
      "loss": 1.69,
      "step": 205
    },
    {
      "epoch": 0.003934751881422623,
      "grad_norm": 2.1490390300750732,
      "learning_rate": 0.00019999938010474417,
      "loss": 1.566,
      "step": 206
    },
    {
      "epoch": 0.003953852618711082,
      "grad_norm": 4.846123695373535,
      "learning_rate": 0.00019999937304047519,
      "loss": 1.0657,
      "step": 207
    },
    {
      "epoch": 0.003972953355999542,
      "grad_norm": 2.1639959812164307,
      "learning_rate": 0.00019999936593618215,
      "loss": 1.9125,
      "step": 208
    },
    {
      "epoch": 0.003992054093288001,
      "grad_norm": 2.041269540786743,
      "learning_rate": 0.0001999993587918651,
      "loss": 1.6156,
      "step": 209
    },
    {
      "epoch": 0.00401115483057646,
      "grad_norm": 2.101771354675293,
      "learning_rate": 0.00019999935160752404,
      "loss": 1.4753,
      "step": 210
    },
    {
      "epoch": 0.00403025556786492,
      "grad_norm": 2.394887685775757,
      "learning_rate": 0.000199999344383159,
      "loss": 1.8092,
      "step": 211
    },
    {
      "epoch": 0.004049356305153379,
      "grad_norm": 2.0639126300811768,
      "learning_rate": 0.00019999933711876993,
      "loss": 1.4567,
      "step": 212
    },
    {
      "epoch": 0.004068457042441838,
      "grad_norm": 2.625164747238159,
      "learning_rate": 0.00019999932981435686,
      "loss": 1.2324,
      "step": 213
    },
    {
      "epoch": 0.004087557779730297,
      "grad_norm": 2.592604637145996,
      "learning_rate": 0.00019999932246991974,
      "loss": 1.8654,
      "step": 214
    },
    {
      "epoch": 0.004106658517018757,
      "grad_norm": 2.2053794860839844,
      "learning_rate": 0.0001999993150854587,
      "loss": 1.7314,
      "step": 215
    },
    {
      "epoch": 0.0041257592543072165,
      "grad_norm": 2.5555896759033203,
      "learning_rate": 0.00019999930766097362,
      "loss": 1.6176,
      "step": 216
    },
    {
      "epoch": 0.004144859991595675,
      "grad_norm": 2.4063844680786133,
      "learning_rate": 0.00019999930019646452,
      "loss": 1.6133,
      "step": 217
    },
    {
      "epoch": 0.004163960728884135,
      "grad_norm": 2.402606964111328,
      "learning_rate": 0.0001999992926919315,
      "loss": 1.4556,
      "step": 218
    },
    {
      "epoch": 0.0041830614661725945,
      "grad_norm": 2.182407855987549,
      "learning_rate": 0.00019999928514737446,
      "loss": 1.9838,
      "step": 219
    },
    {
      "epoch": 0.004202162203461053,
      "grad_norm": 2.622894287109375,
      "learning_rate": 0.0001999992775627934,
      "loss": 1.5775,
      "step": 220
    },
    {
      "epoch": 0.004221262940749513,
      "grad_norm": 2.917387008666992,
      "learning_rate": 0.00019999926993818844,
      "loss": 1.9823,
      "step": 221
    },
    {
      "epoch": 0.004240363678037973,
      "grad_norm": 2.3956801891326904,
      "learning_rate": 0.00019999926227355942,
      "loss": 1.6548,
      "step": 222
    },
    {
      "epoch": 0.004259464415326431,
      "grad_norm": 2.1777632236480713,
      "learning_rate": 0.00019999925456890648,
      "loss": 1.4028,
      "step": 223
    },
    {
      "epoch": 0.004278565152614891,
      "grad_norm": 4.18602991104126,
      "learning_rate": 0.00019999924682422956,
      "loss": 1.9421,
      "step": 224
    },
    {
      "epoch": 0.004297665889903351,
      "grad_norm": 2.107757806777954,
      "learning_rate": 0.00019999923903952862,
      "loss": 1.304,
      "step": 225
    },
    {
      "epoch": 0.004316766627191809,
      "grad_norm": 1.9320684671401978,
      "learning_rate": 0.00019999923121480375,
      "loss": 1.3505,
      "step": 226
    },
    {
      "epoch": 0.004335867364480269,
      "grad_norm": 1.994712233543396,
      "learning_rate": 0.00019999922335005494,
      "loss": 1.8085,
      "step": 227
    },
    {
      "epoch": 0.004354968101768728,
      "grad_norm": 3.3286828994750977,
      "learning_rate": 0.00019999921544528216,
      "loss": 1.9973,
      "step": 228
    },
    {
      "epoch": 0.0043740688390571875,
      "grad_norm": 2.727083683013916,
      "learning_rate": 0.0001999992075004854,
      "loss": 1.3361,
      "step": 229
    },
    {
      "epoch": 0.004393169576345647,
      "grad_norm": 2.5915353298187256,
      "learning_rate": 0.0001999991995156647,
      "loss": 1.7552,
      "step": 230
    },
    {
      "epoch": 0.004412270313634106,
      "grad_norm": 2.5398311614990234,
      "learning_rate": 0.00019999919149082005,
      "loss": 1.7367,
      "step": 231
    },
    {
      "epoch": 0.0044313710509225656,
      "grad_norm": 2.2256052494049072,
      "learning_rate": 0.00019999918342595145,
      "loss": 1.5497,
      "step": 232
    },
    {
      "epoch": 0.004450471788211025,
      "grad_norm": 2.3258724212646484,
      "learning_rate": 0.0001999991753210589,
      "loss": 1.8043,
      "step": 233
    },
    {
      "epoch": 0.004469572525499484,
      "grad_norm": 2.068586826324463,
      "learning_rate": 0.00019999916717614244,
      "loss": 1.4092,
      "step": 234
    },
    {
      "epoch": 0.004488673262787944,
      "grad_norm": 2.238818883895874,
      "learning_rate": 0.00019999915899120203,
      "loss": 1.5836,
      "step": 235
    },
    {
      "epoch": 0.004507774000076403,
      "grad_norm": 2.731762409210205,
      "learning_rate": 0.00019999915076623768,
      "loss": 1.355,
      "step": 236
    },
    {
      "epoch": 0.004526874737364862,
      "grad_norm": 2.6667187213897705,
      "learning_rate": 0.0001999991425012494,
      "loss": 1.6843,
      "step": 237
    },
    {
      "epoch": 0.004545975474653322,
      "grad_norm": 3.716928005218506,
      "learning_rate": 0.0001999991341962372,
      "loss": 1.5883,
      "step": 238
    },
    {
      "epoch": 0.004565076211941781,
      "grad_norm": 2.1799416542053223,
      "learning_rate": 0.00019999912585120106,
      "loss": 1.2868,
      "step": 239
    },
    {
      "epoch": 0.00458417694923024,
      "grad_norm": 2.3812787532806396,
      "learning_rate": 0.00019999911746614103,
      "loss": 1.7196,
      "step": 240
    },
    {
      "epoch": 0.0046032776865187,
      "grad_norm": 2.2973108291625977,
      "learning_rate": 0.00019999910904105705,
      "loss": 1.4399,
      "step": 241
    },
    {
      "epoch": 0.0046223784238071585,
      "grad_norm": 3.101738452911377,
      "learning_rate": 0.00019999910057594917,
      "loss": 2.1029,
      "step": 242
    },
    {
      "epoch": 0.004641479161095618,
      "grad_norm": 2.475390911102295,
      "learning_rate": 0.00019999909207081738,
      "loss": 1.4124,
      "step": 243
    },
    {
      "epoch": 0.004660579898384078,
      "grad_norm": 3.236670732498169,
      "learning_rate": 0.00019999908352566167,
      "loss": 1.5515,
      "step": 244
    },
    {
      "epoch": 0.004679680635672537,
      "grad_norm": 2.3940582275390625,
      "learning_rate": 0.0001999990749404821,
      "loss": 1.3174,
      "step": 245
    },
    {
      "epoch": 0.004698781372960996,
      "grad_norm": 2.7314326763153076,
      "learning_rate": 0.0001999990663152786,
      "loss": 2.0186,
      "step": 246
    },
    {
      "epoch": 0.004717882110249456,
      "grad_norm": 2.418043613433838,
      "learning_rate": 0.00019999905765005118,
      "loss": 1.61,
      "step": 247
    },
    {
      "epoch": 0.004736982847537915,
      "grad_norm": 3.49133038520813,
      "learning_rate": 0.0001999990489447999,
      "loss": 1.8164,
      "step": 248
    },
    {
      "epoch": 0.004756083584826374,
      "grad_norm": 2.3593246936798096,
      "learning_rate": 0.00019999904019952475,
      "loss": 1.6072,
      "step": 249
    },
    {
      "epoch": 0.004775184322114834,
      "grad_norm": 2.652388095855713,
      "learning_rate": 0.00019999903141422568,
      "loss": 1.4118,
      "step": 250
    },
    {
      "epoch": 0.004794285059403293,
      "grad_norm": 2.161137342453003,
      "learning_rate": 0.00019999902258890272,
      "loss": 2.1488,
      "step": 251
    },
    {
      "epoch": 0.004813385796691752,
      "grad_norm": 2.220066785812378,
      "learning_rate": 0.0001999990137235559,
      "loss": 1.4553,
      "step": 252
    },
    {
      "epoch": 0.004832486533980212,
      "grad_norm": 2.3280110359191895,
      "learning_rate": 0.00019999900481818518,
      "loss": 1.4795,
      "step": 253
    },
    {
      "epoch": 0.004851587271268671,
      "grad_norm": 2.9444568157196045,
      "learning_rate": 0.0001999989958727906,
      "loss": 2.1126,
      "step": 254
    },
    {
      "epoch": 0.0048706880085571305,
      "grad_norm": 2.641145706176758,
      "learning_rate": 0.00019999898688737218,
      "loss": 1.5769,
      "step": 255
    },
    {
      "epoch": 0.004889788745845589,
      "grad_norm": 2.4189071655273438,
      "learning_rate": 0.00019999897786192986,
      "loss": 1.6801,
      "step": 256
    },
    {
      "epoch": 0.004908889483134049,
      "grad_norm": 2.3720786571502686,
      "learning_rate": 0.00019999896879646368,
      "loss": 1.595,
      "step": 257
    },
    {
      "epoch": 0.0049279902204225085,
      "grad_norm": 3.879718065261841,
      "learning_rate": 0.00019999895969097367,
      "loss": 1.476,
      "step": 258
    },
    {
      "epoch": 0.004947090957710967,
      "grad_norm": 2.4743292331695557,
      "learning_rate": 0.00019999895054545979,
      "loss": 1.409,
      "step": 259
    },
    {
      "epoch": 0.004966191694999427,
      "grad_norm": 2.172733783721924,
      "learning_rate": 0.00019999894135992207,
      "loss": 1.6257,
      "step": 260
    },
    {
      "epoch": 0.004985292432287887,
      "grad_norm": 2.145429849624634,
      "learning_rate": 0.0001999989321343605,
      "loss": 1.6105,
      "step": 261
    },
    {
      "epoch": 0.005004393169576345,
      "grad_norm": 2.600046396255493,
      "learning_rate": 0.00019999892286877506,
      "loss": 1.6536,
      "step": 262
    },
    {
      "epoch": 0.005023493906864805,
      "grad_norm": 2.6234681606292725,
      "learning_rate": 0.0001999989135631658,
      "loss": 1.5664,
      "step": 263
    },
    {
      "epoch": 0.005042594644153265,
      "grad_norm": 2.6681876182556152,
      "learning_rate": 0.00019999890421753272,
      "loss": 1.6102,
      "step": 264
    },
    {
      "epoch": 0.005061695381441723,
      "grad_norm": 2.438842296600342,
      "learning_rate": 0.00019999889483187578,
      "loss": 1.4981,
      "step": 265
    },
    {
      "epoch": 0.005080796118730183,
      "grad_norm": 1.9915356636047363,
      "learning_rate": 0.00019999888540619504,
      "loss": 1.5781,
      "step": 266
    },
    {
      "epoch": 0.005099896856018643,
      "grad_norm": 2.5042529106140137,
      "learning_rate": 0.00019999887594049045,
      "loss": 1.6614,
      "step": 267
    },
    {
      "epoch": 0.0051189975933071015,
      "grad_norm": 2.347902774810791,
      "learning_rate": 0.00019999886643476208,
      "loss": 1.9729,
      "step": 268
    },
    {
      "epoch": 0.005138098330595561,
      "grad_norm": 2.7311923503875732,
      "learning_rate": 0.00019999885688900987,
      "loss": 1.9283,
      "step": 269
    },
    {
      "epoch": 0.00515719906788402,
      "grad_norm": 7.060927867889404,
      "learning_rate": 0.00019999884730323385,
      "loss": 1.7788,
      "step": 270
    },
    {
      "epoch": 0.0051762998051724796,
      "grad_norm": 2.908926010131836,
      "learning_rate": 0.000199998837677434,
      "loss": 1.5582,
      "step": 271
    },
    {
      "epoch": 0.005195400542460939,
      "grad_norm": 2.7608449459075928,
      "learning_rate": 0.00019999882801161035,
      "loss": 1.4279,
      "step": 272
    },
    {
      "epoch": 0.005214501279749398,
      "grad_norm": 2.4342403411865234,
      "learning_rate": 0.00019999881830576292,
      "loss": 1.5961,
      "step": 273
    },
    {
      "epoch": 0.005233602017037858,
      "grad_norm": 2.514329433441162,
      "learning_rate": 0.00019999880855989165,
      "loss": 1.4153,
      "step": 274
    },
    {
      "epoch": 0.005252702754326317,
      "grad_norm": 2.096613883972168,
      "learning_rate": 0.00019999879877399663,
      "loss": 1.2946,
      "step": 275
    },
    {
      "epoch": 0.005271803491614776,
      "grad_norm": 1.928249478340149,
      "learning_rate": 0.00019999878894807783,
      "loss": 1.7875,
      "step": 276
    },
    {
      "epoch": 0.005290904228903236,
      "grad_norm": 2.9557576179504395,
      "learning_rate": 0.00019999877908213524,
      "loss": 1.7892,
      "step": 277
    },
    {
      "epoch": 0.005310004966191695,
      "grad_norm": 2.318290948867798,
      "learning_rate": 0.00019999876917616884,
      "loss": 1.5078,
      "step": 278
    },
    {
      "epoch": 0.005329105703480154,
      "grad_norm": 3.1633083820343018,
      "learning_rate": 0.00019999875923017868,
      "loss": 1.6988,
      "step": 279
    },
    {
      "epoch": 0.005348206440768614,
      "grad_norm": 2.840820550918579,
      "learning_rate": 0.00019999874924416474,
      "loss": 1.5239,
      "step": 280
    },
    {
      "epoch": 0.005367307178057073,
      "grad_norm": 2.397858142852783,
      "learning_rate": 0.000199998739218127,
      "loss": 1.7149,
      "step": 281
    },
    {
      "epoch": 0.005386407915345532,
      "grad_norm": 2.456008195877075,
      "learning_rate": 0.00019999872915206555,
      "loss": 1.9987,
      "step": 282
    },
    {
      "epoch": 0.005405508652633992,
      "grad_norm": 2.534327983856201,
      "learning_rate": 0.00019999871904598031,
      "loss": 1.1789,
      "step": 283
    },
    {
      "epoch": 0.005424609389922451,
      "grad_norm": 2.4632952213287354,
      "learning_rate": 0.00019999870889987135,
      "loss": 1.4924,
      "step": 284
    },
    {
      "epoch": 0.00544371012721091,
      "grad_norm": 2.4687716960906982,
      "learning_rate": 0.00019999869871373857,
      "loss": 1.3929,
      "step": 285
    },
    {
      "epoch": 0.00546281086449937,
      "grad_norm": 1.802878737449646,
      "learning_rate": 0.00019999868848758208,
      "loss": 1.5466,
      "step": 286
    },
    {
      "epoch": 0.005481911601787829,
      "grad_norm": 2.1746609210968018,
      "learning_rate": 0.00019999867822140184,
      "loss": 0.9748,
      "step": 287
    },
    {
      "epoch": 0.005501012339076288,
      "grad_norm": 2.171687602996826,
      "learning_rate": 0.00019999866791519785,
      "loss": 1.6514,
      "step": 288
    },
    {
      "epoch": 0.005520113076364748,
      "grad_norm": 2.813917875289917,
      "learning_rate": 0.00019999865756897015,
      "loss": 1.3555,
      "step": 289
    },
    {
      "epoch": 0.005539213813653207,
      "grad_norm": 2.3484740257263184,
      "learning_rate": 0.0001999986471827187,
      "loss": 1.306,
      "step": 290
    },
    {
      "epoch": 0.005558314550941666,
      "grad_norm": 2.5684242248535156,
      "learning_rate": 0.00019999863675644353,
      "loss": 1.9274,
      "step": 291
    },
    {
      "epoch": 0.005577415288230126,
      "grad_norm": 2.8437721729278564,
      "learning_rate": 0.00019999862629014461,
      "loss": 1.4884,
      "step": 292
    },
    {
      "epoch": 0.005596516025518585,
      "grad_norm": 2.5073318481445312,
      "learning_rate": 0.00019999861578382197,
      "loss": 1.5352,
      "step": 293
    },
    {
      "epoch": 0.0056156167628070445,
      "grad_norm": 2.3817365169525146,
      "learning_rate": 0.00019999860523747565,
      "loss": 1.8222,
      "step": 294
    },
    {
      "epoch": 0.005634717500095504,
      "grad_norm": 2.8287923336029053,
      "learning_rate": 0.0001999985946511056,
      "loss": 2.1014,
      "step": 295
    },
    {
      "epoch": 0.005653818237383963,
      "grad_norm": 2.331005334854126,
      "learning_rate": 0.00019999858402471184,
      "loss": 1.9462,
      "step": 296
    },
    {
      "epoch": 0.0056729189746724225,
      "grad_norm": 2.6518707275390625,
      "learning_rate": 0.00019999857335829436,
      "loss": 1.4405,
      "step": 297
    },
    {
      "epoch": 0.005692019711960881,
      "grad_norm": 2.3987011909484863,
      "learning_rate": 0.0001999985626518532,
      "loss": 1.7377,
      "step": 298
    },
    {
      "epoch": 0.005711120449249341,
      "grad_norm": 2.2604761123657227,
      "learning_rate": 0.00019999855190538834,
      "loss": 1.1498,
      "step": 299
    },
    {
      "epoch": 0.005730221186537801,
      "grad_norm": 1.9913378953933716,
      "learning_rate": 0.0001999985411188998,
      "loss": 1.4505,
      "step": 300
    },
    {
      "epoch": 0.005749321923826259,
      "grad_norm": 2.059391975402832,
      "learning_rate": 0.00019999853029238756,
      "loss": 1.4317,
      "step": 301
    },
    {
      "epoch": 0.005768422661114719,
      "grad_norm": 2.590132713317871,
      "learning_rate": 0.00019999851942585165,
      "loss": 1.5514,
      "step": 302
    },
    {
      "epoch": 0.005787523398403179,
      "grad_norm": 2.5913166999816895,
      "learning_rate": 0.00019999850851929206,
      "loss": 1.3262,
      "step": 303
    },
    {
      "epoch": 0.005806624135691637,
      "grad_norm": 3.2078757286071777,
      "learning_rate": 0.00019999849757270876,
      "loss": 1.7497,
      "step": 304
    },
    {
      "epoch": 0.005825724872980097,
      "grad_norm": 2.803560733795166,
      "learning_rate": 0.00019999848658610185,
      "loss": 1.6381,
      "step": 305
    },
    {
      "epoch": 0.005844825610268557,
      "grad_norm": 1.9924579858779907,
      "learning_rate": 0.00019999847555947126,
      "loss": 1.6787,
      "step": 306
    },
    {
      "epoch": 0.0058639263475570155,
      "grad_norm": 2.2011969089508057,
      "learning_rate": 0.000199998464492817,
      "loss": 1.6406,
      "step": 307
    },
    {
      "epoch": 0.005883027084845475,
      "grad_norm": 2.3322267532348633,
      "learning_rate": 0.00019999845338613908,
      "loss": 1.59,
      "step": 308
    },
    {
      "epoch": 0.005902127822133935,
      "grad_norm": 2.443119764328003,
      "learning_rate": 0.0001999984422394375,
      "loss": 1.5477,
      "step": 309
    },
    {
      "epoch": 0.0059212285594223936,
      "grad_norm": 2.9440555572509766,
      "learning_rate": 0.00019999843105271227,
      "loss": 1.6249,
      "step": 310
    },
    {
      "epoch": 0.005940329296710853,
      "grad_norm": 3.0538511276245117,
      "learning_rate": 0.00019999841982596341,
      "loss": 1.714,
      "step": 311
    },
    {
      "epoch": 0.005959430033999312,
      "grad_norm": 2.5331990718841553,
      "learning_rate": 0.00019999840855919093,
      "loss": 1.7102,
      "step": 312
    },
    {
      "epoch": 0.005978530771287772,
      "grad_norm": 2.777237892150879,
      "learning_rate": 0.0001999983972523948,
      "loss": 1.8371,
      "step": 313
    },
    {
      "epoch": 0.005997631508576231,
      "grad_norm": 2.565290927886963,
      "learning_rate": 0.00019999838590557505,
      "loss": 2.0846,
      "step": 314
    },
    {
      "epoch": 0.00601673224586469,
      "grad_norm": 2.3339264392852783,
      "learning_rate": 0.00019999837451873168,
      "loss": 1.5554,
      "step": 315
    },
    {
      "epoch": 0.00603583298315315,
      "grad_norm": 2.47808837890625,
      "learning_rate": 0.00019999836309186466,
      "loss": 1.8356,
      "step": 316
    },
    {
      "epoch": 0.006054933720441609,
      "grad_norm": 2.185377597808838,
      "learning_rate": 0.00019999835162497407,
      "loss": 1.4791,
      "step": 317
    },
    {
      "epoch": 0.006074034457730068,
      "grad_norm": 2.720505714416504,
      "learning_rate": 0.00019999834011805983,
      "loss": 1.7271,
      "step": 318
    },
    {
      "epoch": 0.006093135195018528,
      "grad_norm": 2.449997663497925,
      "learning_rate": 0.000199998328571122,
      "loss": 1.9716,
      "step": 319
    },
    {
      "epoch": 0.006112235932306987,
      "grad_norm": 2.1626601219177246,
      "learning_rate": 0.00019999831698416055,
      "loss": 1.2932,
      "step": 320
    },
    {
      "epoch": 0.006131336669595446,
      "grad_norm": 2.0520811080932617,
      "learning_rate": 0.00019999830535717553,
      "loss": 1.6149,
      "step": 321
    },
    {
      "epoch": 0.006150437406883906,
      "grad_norm": 2.45487642288208,
      "learning_rate": 0.00019999829369016692,
      "loss": 1.2408,
      "step": 322
    },
    {
      "epoch": 0.0061695381441723655,
      "grad_norm": 2.289139986038208,
      "learning_rate": 0.0001999982819831347,
      "loss": 1.5036,
      "step": 323
    },
    {
      "epoch": 0.006188638881460824,
      "grad_norm": 2.5456228256225586,
      "learning_rate": 0.00019999827023607893,
      "loss": 1.7942,
      "step": 324
    },
    {
      "epoch": 0.006207739618749284,
      "grad_norm": 2.466486692428589,
      "learning_rate": 0.00019999825844899957,
      "loss": 1.9354,
      "step": 325
    },
    {
      "epoch": 0.006226840356037743,
      "grad_norm": 2.5167582035064697,
      "learning_rate": 0.0001999982466218966,
      "loss": 1.5073,
      "step": 326
    },
    {
      "epoch": 0.006245941093326202,
      "grad_norm": 2.4258038997650146,
      "learning_rate": 0.0001999982347547701,
      "loss": 1.3982,
      "step": 327
    },
    {
      "epoch": 0.006265041830614662,
      "grad_norm": 2.050057888031006,
      "learning_rate": 0.00019999822284762003,
      "loss": 1.5373,
      "step": 328
    },
    {
      "epoch": 0.006284142567903121,
      "grad_norm": 2.9023921489715576,
      "learning_rate": 0.0001999982109004464,
      "loss": 1.4609,
      "step": 329
    },
    {
      "epoch": 0.00630324330519158,
      "grad_norm": 3.0532312393188477,
      "learning_rate": 0.0001999981989132492,
      "loss": 1.6672,
      "step": 330
    },
    {
      "epoch": 0.00632234404248004,
      "grad_norm": 2.834312677383423,
      "learning_rate": 0.00019999818688602847,
      "loss": 1.7068,
      "step": 331
    },
    {
      "epoch": 0.006341444779768499,
      "grad_norm": 2.3190486431121826,
      "learning_rate": 0.0001999981748187842,
      "loss": 1.4493,
      "step": 332
    },
    {
      "epoch": 0.0063605455170569584,
      "grad_norm": 2.7529187202453613,
      "learning_rate": 0.00019999816271151636,
      "loss": 1.538,
      "step": 333
    },
    {
      "epoch": 0.006379646254345418,
      "grad_norm": 2.55694317817688,
      "learning_rate": 0.00019999815056422502,
      "loss": 1.9779,
      "step": 334
    },
    {
      "epoch": 0.006398746991633877,
      "grad_norm": 2.140547752380371,
      "learning_rate": 0.00019999813837691011,
      "loss": 1.4737,
      "step": 335
    },
    {
      "epoch": 0.0064178477289223365,
      "grad_norm": 2.410367965698242,
      "learning_rate": 0.00019999812614957172,
      "loss": 1.5282,
      "step": 336
    },
    {
      "epoch": 0.006436948466210796,
      "grad_norm": 2.31577467918396,
      "learning_rate": 0.0001999981138822098,
      "loss": 1.6732,
      "step": 337
    },
    {
      "epoch": 0.006456049203499255,
      "grad_norm": 3.1474103927612305,
      "learning_rate": 0.00019999810157482435,
      "loss": 1.9066,
      "step": 338
    },
    {
      "epoch": 0.006475149940787715,
      "grad_norm": 2.760754108428955,
      "learning_rate": 0.0001999980892274154,
      "loss": 1.2408,
      "step": 339
    },
    {
      "epoch": 0.006494250678076173,
      "grad_norm": 2.6064438819885254,
      "learning_rate": 0.00019999807683998292,
      "loss": 1.368,
      "step": 340
    },
    {
      "epoch": 0.006513351415364633,
      "grad_norm": 3.139028310775757,
      "learning_rate": 0.00019999806441252697,
      "loss": 1.8326,
      "step": 341
    },
    {
      "epoch": 0.006532452152653093,
      "grad_norm": 2.8424229621887207,
      "learning_rate": 0.0001999980519450475,
      "loss": 1.4229,
      "step": 342
    },
    {
      "epoch": 0.006551552889941551,
      "grad_norm": 2.0625228881835938,
      "learning_rate": 0.00019999803943754457,
      "loss": 1.5668,
      "step": 343
    },
    {
      "epoch": 0.006570653627230011,
      "grad_norm": 2.547196626663208,
      "learning_rate": 0.00019999802689001813,
      "loss": 1.7168,
      "step": 344
    },
    {
      "epoch": 0.006589754364518471,
      "grad_norm": 2.7613818645477295,
      "learning_rate": 0.00019999801430246823,
      "loss": 1.8383,
      "step": 345
    },
    {
      "epoch": 0.0066088551018069295,
      "grad_norm": 2.039952516555786,
      "learning_rate": 0.00019999800167489485,
      "loss": 1.2382,
      "step": 346
    },
    {
      "epoch": 0.006627955839095389,
      "grad_norm": 2.296131134033203,
      "learning_rate": 0.00019999798900729795,
      "loss": 1.8538,
      "step": 347
    },
    {
      "epoch": 0.006647056576383849,
      "grad_norm": 2.3972854614257812,
      "learning_rate": 0.00019999797629967765,
      "loss": 1.5312,
      "step": 348
    },
    {
      "epoch": 0.0066661573136723076,
      "grad_norm": 2.320819139480591,
      "learning_rate": 0.00019999796355203386,
      "loss": 1.6467,
      "step": 349
    },
    {
      "epoch": 0.006685258050960767,
      "grad_norm": 2.1188600063323975,
      "learning_rate": 0.0001999979507643666,
      "loss": 1.3611,
      "step": 350
    },
    {
      "epoch": 0.006704358788249227,
      "grad_norm": 2.604168653488159,
      "learning_rate": 0.00019999793793667593,
      "loss": 1.1762,
      "step": 351
    },
    {
      "epoch": 0.006723459525537686,
      "grad_norm": 2.4345123767852783,
      "learning_rate": 0.0001999979250689618,
      "loss": 1.5253,
      "step": 352
    },
    {
      "epoch": 0.006742560262826145,
      "grad_norm": 2.443851947784424,
      "learning_rate": 0.00019999791216122423,
      "loss": 1.4916,
      "step": 353
    },
    {
      "epoch": 0.006761661000114604,
      "grad_norm": 2.5085508823394775,
      "learning_rate": 0.00019999789921346323,
      "loss": 1.4051,
      "step": 354
    },
    {
      "epoch": 0.006780761737403064,
      "grad_norm": 2.546678304672241,
      "learning_rate": 0.0001999978862256788,
      "loss": 1.6257,
      "step": 355
    },
    {
      "epoch": 0.006799862474691523,
      "grad_norm": 2.556316375732422,
      "learning_rate": 0.00019999787319787093,
      "loss": 1.8699,
      "step": 356
    },
    {
      "epoch": 0.006818963211979982,
      "grad_norm": 2.547018051147461,
      "learning_rate": 0.00019999786013003964,
      "loss": 1.7752,
      "step": 357
    },
    {
      "epoch": 0.006838063949268442,
      "grad_norm": 2.409594774246216,
      "learning_rate": 0.00019999784702218497,
      "loss": 1.395,
      "step": 358
    },
    {
      "epoch": 0.006857164686556901,
      "grad_norm": 2.2260589599609375,
      "learning_rate": 0.00019999783387430683,
      "loss": 1.0786,
      "step": 359
    },
    {
      "epoch": 0.00687626542384536,
      "grad_norm": 2.7292861938476562,
      "learning_rate": 0.00019999782068640533,
      "loss": 1.6054,
      "step": 360
    },
    {
      "epoch": 0.00689536616113382,
      "grad_norm": 3.652573823928833,
      "learning_rate": 0.0001999978074584804,
      "loss": 2.0971,
      "step": 361
    },
    {
      "epoch": 0.0069144668984222795,
      "grad_norm": 2.963015556335449,
      "learning_rate": 0.00019999779419053212,
      "loss": 1.9197,
      "step": 362
    },
    {
      "epoch": 0.006933567635710738,
      "grad_norm": 2.413249969482422,
      "learning_rate": 0.00019999778088256048,
      "loss": 1.6475,
      "step": 363
    },
    {
      "epoch": 0.006952668372999198,
      "grad_norm": 2.8964953422546387,
      "learning_rate": 0.00019999776753456538,
      "loss": 1.5661,
      "step": 364
    },
    {
      "epoch": 0.0069717691102876575,
      "grad_norm": 2.4090354442596436,
      "learning_rate": 0.00019999775414654693,
      "loss": 1.5145,
      "step": 365
    },
    {
      "epoch": 0.006990869847576116,
      "grad_norm": 3.104567527770996,
      "learning_rate": 0.00019999774071850516,
      "loss": 1.5597,
      "step": 366
    },
    {
      "epoch": 0.007009970584864576,
      "grad_norm": 2.843949794769287,
      "learning_rate": 0.00019999772725043995,
      "loss": 1.7268,
      "step": 367
    },
    {
      "epoch": 0.007029071322153035,
      "grad_norm": 2.5484068393707275,
      "learning_rate": 0.0001999977137423514,
      "loss": 1.7767,
      "step": 368
    },
    {
      "epoch": 0.007048172059441494,
      "grad_norm": 1.7710931301116943,
      "learning_rate": 0.00019999770019423952,
      "loss": 1.358,
      "step": 369
    },
    {
      "epoch": 0.007067272796729954,
      "grad_norm": 2.0392966270446777,
      "learning_rate": 0.00019999768660610426,
      "loss": 1.3099,
      "step": 370
    },
    {
      "epoch": 0.007086373534018413,
      "grad_norm": 2.6020655632019043,
      "learning_rate": 0.00019999767297794566,
      "loss": 2.0509,
      "step": 371
    },
    {
      "epoch": 0.0071054742713068724,
      "grad_norm": 2.515227794647217,
      "learning_rate": 0.00019999765930976376,
      "loss": 1.5643,
      "step": 372
    },
    {
      "epoch": 0.007124575008595332,
      "grad_norm": 2.9806149005889893,
      "learning_rate": 0.0001999976456015585,
      "loss": 1.7666,
      "step": 373
    },
    {
      "epoch": 0.007143675745883791,
      "grad_norm": 2.014387845993042,
      "learning_rate": 0.0001999976318533299,
      "loss": 1.4667,
      "step": 374
    },
    {
      "epoch": 0.0071627764831722505,
      "grad_norm": 2.4668030738830566,
      "learning_rate": 0.000199997618065078,
      "loss": 1.6565,
      "step": 375
    },
    {
      "epoch": 0.00718187722046071,
      "grad_norm": 2.330427885055542,
      "learning_rate": 0.00019999760423680275,
      "loss": 1.587,
      "step": 376
    },
    {
      "epoch": 0.007200977957749169,
      "grad_norm": 2.6013922691345215,
      "learning_rate": 0.00019999759036850424,
      "loss": 1.539,
      "step": 377
    },
    {
      "epoch": 0.007220078695037629,
      "grad_norm": 2.468669891357422,
      "learning_rate": 0.00019999757646018237,
      "loss": 1.6976,
      "step": 378
    },
    {
      "epoch": 0.007239179432326087,
      "grad_norm": 2.414419651031494,
      "learning_rate": 0.00019999756251183723,
      "loss": 1.8634,
      "step": 379
    },
    {
      "epoch": 0.007258280169614547,
      "grad_norm": 2.080955743789673,
      "learning_rate": 0.0001999975485234688,
      "loss": 1.5331,
      "step": 380
    },
    {
      "epoch": 0.007277380906903007,
      "grad_norm": 2.4972786903381348,
      "learning_rate": 0.00019999753449507707,
      "loss": 1.7693,
      "step": 381
    },
    {
      "epoch": 0.007296481644191465,
      "grad_norm": 3.161458730697632,
      "learning_rate": 0.00019999752042666207,
      "loss": 1.4416,
      "step": 382
    },
    {
      "epoch": 0.007315582381479925,
      "grad_norm": 3.2398030757904053,
      "learning_rate": 0.00019999750631822375,
      "loss": 1.8361,
      "step": 383
    },
    {
      "epoch": 0.007334683118768385,
      "grad_norm": 2.8465404510498047,
      "learning_rate": 0.0001999974921697622,
      "loss": 1.6258,
      "step": 384
    },
    {
      "epoch": 0.0073537838560568435,
      "grad_norm": 2.5873472690582275,
      "learning_rate": 0.00019999747798127738,
      "loss": 1.6767,
      "step": 385
    },
    {
      "epoch": 0.007372884593345303,
      "grad_norm": 2.4411063194274902,
      "learning_rate": 0.00019999746375276928,
      "loss": 1.7531,
      "step": 386
    },
    {
      "epoch": 0.007391985330633763,
      "grad_norm": 2.9703269004821777,
      "learning_rate": 0.00019999744948423796,
      "loss": 1.7696,
      "step": 387
    },
    {
      "epoch": 0.0074110860679222216,
      "grad_norm": 3.4337642192840576,
      "learning_rate": 0.00019999743517568335,
      "loss": 1.9271,
      "step": 388
    },
    {
      "epoch": 0.007430186805210681,
      "grad_norm": 2.4452531337738037,
      "learning_rate": 0.00019999742082710552,
      "loss": 1.3515,
      "step": 389
    },
    {
      "epoch": 0.007449287542499141,
      "grad_norm": 2.720768690109253,
      "learning_rate": 0.00019999740643850445,
      "loss": 1.7717,
      "step": 390
    },
    {
      "epoch": 0.0074683882797876,
      "grad_norm": 2.2326765060424805,
      "learning_rate": 0.0001999973920098801,
      "loss": 0.9797,
      "step": 391
    },
    {
      "epoch": 0.007487489017076059,
      "grad_norm": 2.3779385089874268,
      "learning_rate": 0.0001999973775412326,
      "loss": 1.7361,
      "step": 392
    },
    {
      "epoch": 0.007506589754364518,
      "grad_norm": 2.2658519744873047,
      "learning_rate": 0.00019999736303256182,
      "loss": 1.9659,
      "step": 393
    },
    {
      "epoch": 0.007525690491652978,
      "grad_norm": 2.268893003463745,
      "learning_rate": 0.0001999973484838679,
      "loss": 1.833,
      "step": 394
    },
    {
      "epoch": 0.007544791228941437,
      "grad_norm": 2.264033794403076,
      "learning_rate": 0.0001999973338951507,
      "loss": 1.2003,
      "step": 395
    },
    {
      "epoch": 0.007563891966229896,
      "grad_norm": 2.690825939178467,
      "learning_rate": 0.0001999973192664103,
      "loss": 1.3837,
      "step": 396
    },
    {
      "epoch": 0.007582992703518356,
      "grad_norm": 2.656245708465576,
      "learning_rate": 0.00019999730459764674,
      "loss": 1.6814,
      "step": 397
    },
    {
      "epoch": 0.007602093440806815,
      "grad_norm": 2.3673367500305176,
      "learning_rate": 0.00019999728988885998,
      "loss": 1.6518,
      "step": 398
    },
    {
      "epoch": 0.007621194178095274,
      "grad_norm": 2.6253745555877686,
      "learning_rate": 0.00019999727514005003,
      "loss": 1.6141,
      "step": 399
    },
    {
      "epoch": 0.007640294915383734,
      "grad_norm": 2.750826358795166,
      "learning_rate": 0.0001999972603512169,
      "loss": 1.6049,
      "step": 400
    },
    {
      "epoch": 0.007640294915383734,
      "eval_loss": 1.5975301265716553,
      "eval_runtime": 316.4087,
      "eval_samples_per_second": 3.328,
      "eval_steps_per_second": 3.328,
      "step": 400
    },
    {
      "epoch": 0.0076593956526721935,
      "grad_norm": 2.531731367111206,
      "learning_rate": 0.00019999724552236057,
      "loss": 1.7776,
      "step": 401
    },
    {
      "epoch": 0.007678496389960652,
      "grad_norm": 2.259174108505249,
      "learning_rate": 0.0001999972306534811,
      "loss": 1.724,
      "step": 402
    },
    {
      "epoch": 0.007697597127249112,
      "grad_norm": 1.9552803039550781,
      "learning_rate": 0.00019999721574457847,
      "loss": 1.5126,
      "step": 403
    },
    {
      "epoch": 0.0077166978645375715,
      "grad_norm": 2.8023886680603027,
      "learning_rate": 0.00019999720079565266,
      "loss": 1.279,
      "step": 404
    },
    {
      "epoch": 0.00773579860182603,
      "grad_norm": 2.7784056663513184,
      "learning_rate": 0.0001999971858067037,
      "loss": 1.7147,
      "step": 405
    },
    {
      "epoch": 0.00775489933911449,
      "grad_norm": 2.8792099952697754,
      "learning_rate": 0.00019999717077773163,
      "loss": 1.9034,
      "step": 406
    },
    {
      "epoch": 0.007774000076402949,
      "grad_norm": 3.2865023612976074,
      "learning_rate": 0.0001999971557087364,
      "loss": 1.5709,
      "step": 407
    },
    {
      "epoch": 0.007793100813691408,
      "grad_norm": 2.8620948791503906,
      "learning_rate": 0.00019999714059971803,
      "loss": 1.9347,
      "step": 408
    },
    {
      "epoch": 0.007812201550979868,
      "grad_norm": 2.770881175994873,
      "learning_rate": 0.00019999712545067658,
      "loss": 1.2646,
      "step": 409
    },
    {
      "epoch": 0.007831302288268328,
      "grad_norm": 2.7692856788635254,
      "learning_rate": 0.00019999711026161198,
      "loss": 1.4742,
      "step": 410
    },
    {
      "epoch": 0.007850403025556786,
      "grad_norm": 2.8973124027252197,
      "learning_rate": 0.00019999709503252424,
      "loss": 1.6016,
      "step": 411
    },
    {
      "epoch": 0.007869503762845245,
      "grad_norm": 2.675713539123535,
      "learning_rate": 0.00019999707976341342,
      "loss": 1.306,
      "step": 412
    },
    {
      "epoch": 0.007888604500133706,
      "grad_norm": 2.793464183807373,
      "learning_rate": 0.0001999970644542795,
      "loss": 1.3984,
      "step": 413
    },
    {
      "epoch": 0.007907705237422165,
      "grad_norm": 2.560112237930298,
      "learning_rate": 0.0001999970491051225,
      "loss": 1.5959,
      "step": 414
    },
    {
      "epoch": 0.007926805974710623,
      "grad_norm": 2.688323497772217,
      "learning_rate": 0.00019999703371594238,
      "loss": 1.7697,
      "step": 415
    },
    {
      "epoch": 0.007945906711999084,
      "grad_norm": 2.7031538486480713,
      "learning_rate": 0.0001999970182867392,
      "loss": 1.5062,
      "step": 416
    },
    {
      "epoch": 0.007965007449287543,
      "grad_norm": 2.2163774967193604,
      "learning_rate": 0.00019999700281751292,
      "loss": 1.0287,
      "step": 417
    },
    {
      "epoch": 0.007984108186576001,
      "grad_norm": 3.0294740200042725,
      "learning_rate": 0.00019999698730826357,
      "loss": 1.3892,
      "step": 418
    },
    {
      "epoch": 0.008003208923864462,
      "grad_norm": 2.5948808193206787,
      "learning_rate": 0.00019999697175899117,
      "loss": 1.9476,
      "step": 419
    },
    {
      "epoch": 0.00802230966115292,
      "grad_norm": 2.6687822341918945,
      "learning_rate": 0.00019999695616969572,
      "loss": 1.3159,
      "step": 420
    },
    {
      "epoch": 0.00804141039844138,
      "grad_norm": 3.449863910675049,
      "learning_rate": 0.00019999694054037722,
      "loss": 1.3212,
      "step": 421
    },
    {
      "epoch": 0.00806051113572984,
      "grad_norm": 2.695855140686035,
      "learning_rate": 0.00019999692487103566,
      "loss": 1.8838,
      "step": 422
    },
    {
      "epoch": 0.008079611873018299,
      "grad_norm": 2.4449732303619385,
      "learning_rate": 0.00019999690916167105,
      "loss": 1.4953,
      "step": 423
    },
    {
      "epoch": 0.008098712610306757,
      "grad_norm": 2.498776912689209,
      "learning_rate": 0.00019999689341228342,
      "loss": 1.5717,
      "step": 424
    },
    {
      "epoch": 0.008117813347595218,
      "grad_norm": 3.0220947265625,
      "learning_rate": 0.00019999687762287276,
      "loss": 1.6229,
      "step": 425
    },
    {
      "epoch": 0.008136914084883677,
      "grad_norm": 2.9955813884735107,
      "learning_rate": 0.00019999686179343907,
      "loss": 1.617,
      "step": 426
    },
    {
      "epoch": 0.008156014822172136,
      "grad_norm": 2.4608311653137207,
      "learning_rate": 0.00019999684592398237,
      "loss": 1.7347,
      "step": 427
    },
    {
      "epoch": 0.008175115559460594,
      "grad_norm": 3.114436149597168,
      "learning_rate": 0.00019999683001450266,
      "loss": 1.7974,
      "step": 428
    },
    {
      "epoch": 0.008194216296749055,
      "grad_norm": 2.695807456970215,
      "learning_rate": 0.00019999681406499998,
      "loss": 1.3335,
      "step": 429
    },
    {
      "epoch": 0.008213317034037514,
      "grad_norm": 2.300337314605713,
      "learning_rate": 0.00019999679807547428,
      "loss": 1.9181,
      "step": 430
    },
    {
      "epoch": 0.008232417771325972,
      "grad_norm": 2.688138484954834,
      "learning_rate": 0.0001999967820459256,
      "loss": 1.5778,
      "step": 431
    },
    {
      "epoch": 0.008251518508614433,
      "grad_norm": 2.5156707763671875,
      "learning_rate": 0.00019999676597635393,
      "loss": 2.1265,
      "step": 432
    },
    {
      "epoch": 0.008270619245902892,
      "grad_norm": 2.2643203735351562,
      "learning_rate": 0.0001999967498667593,
      "loss": 1.4801,
      "step": 433
    },
    {
      "epoch": 0.00828971998319135,
      "grad_norm": 2.2554121017456055,
      "learning_rate": 0.00019999673371714168,
      "loss": 1.4137,
      "step": 434
    },
    {
      "epoch": 0.008308820720479811,
      "grad_norm": 2.3421030044555664,
      "learning_rate": 0.0001999967175275011,
      "loss": 1.6533,
      "step": 435
    },
    {
      "epoch": 0.00832792145776827,
      "grad_norm": 2.666293144226074,
      "learning_rate": 0.00019999670129783757,
      "loss": 1.9797,
      "step": 436
    },
    {
      "epoch": 0.008347022195056729,
      "grad_norm": 3.229341506958008,
      "learning_rate": 0.00019999668502815107,
      "loss": 1.6407,
      "step": 437
    },
    {
      "epoch": 0.008366122932345189,
      "grad_norm": 2.9579315185546875,
      "learning_rate": 0.00019999666871844168,
      "loss": 1.644,
      "step": 438
    },
    {
      "epoch": 0.008385223669633648,
      "grad_norm": 3.336353302001953,
      "learning_rate": 0.0001999966523687093,
      "loss": 1.8731,
      "step": 439
    },
    {
      "epoch": 0.008404324406922107,
      "grad_norm": 2.5255820751190186,
      "learning_rate": 0.00019999663597895402,
      "loss": 1.552,
      "step": 440
    },
    {
      "epoch": 0.008423425144210567,
      "grad_norm": 2.63663649559021,
      "learning_rate": 0.0001999966195491758,
      "loss": 2.0228,
      "step": 441
    },
    {
      "epoch": 0.008442525881499026,
      "grad_norm": 2.3991165161132812,
      "learning_rate": 0.00019999660307937463,
      "loss": 1.506,
      "step": 442
    },
    {
      "epoch": 0.008461626618787485,
      "grad_norm": 2.3112056255340576,
      "learning_rate": 0.0001999965865695506,
      "loss": 1.446,
      "step": 443
    },
    {
      "epoch": 0.008480727356075945,
      "grad_norm": 3.8713126182556152,
      "learning_rate": 0.00019999657001970367,
      "loss": 1.8916,
      "step": 444
    },
    {
      "epoch": 0.008499828093364404,
      "grad_norm": 2.221510887145996,
      "learning_rate": 0.0001999965534298338,
      "loss": 1.4538,
      "step": 445
    },
    {
      "epoch": 0.008518928830652863,
      "grad_norm": 2.5886125564575195,
      "learning_rate": 0.00019999653679994111,
      "loss": 1.9302,
      "step": 446
    },
    {
      "epoch": 0.008538029567941323,
      "grad_norm": 2.6926279067993164,
      "learning_rate": 0.00019999652013002548,
      "loss": 1.9399,
      "step": 447
    },
    {
      "epoch": 0.008557130305229782,
      "grad_norm": 2.7773020267486572,
      "learning_rate": 0.00019999650342008698,
      "loss": 1.7835,
      "step": 448
    },
    {
      "epoch": 0.00857623104251824,
      "grad_norm": 2.628206968307495,
      "learning_rate": 0.00019999648667012561,
      "loss": 1.3265,
      "step": 449
    },
    {
      "epoch": 0.008595331779806701,
      "grad_norm": 2.0614936351776123,
      "learning_rate": 0.00019999646988014136,
      "loss": 1.4474,
      "step": 450
    },
    {
      "epoch": 0.00861443251709516,
      "grad_norm": 2.636680841445923,
      "learning_rate": 0.00019999645305013427,
      "loss": 1.6134,
      "step": 451
    },
    {
      "epoch": 0.008633533254383619,
      "grad_norm": 2.5600035190582275,
      "learning_rate": 0.00019999643618010432,
      "loss": 1.5745,
      "step": 452
    },
    {
      "epoch": 0.00865263399167208,
      "grad_norm": 2.2144875526428223,
      "learning_rate": 0.00019999641927005154,
      "loss": 1.8026,
      "step": 453
    },
    {
      "epoch": 0.008671734728960538,
      "grad_norm": 2.865643262863159,
      "learning_rate": 0.00019999640231997595,
      "loss": 2.0289,
      "step": 454
    },
    {
      "epoch": 0.008690835466248997,
      "grad_norm": 2.229433059692383,
      "learning_rate": 0.0001999963853298775,
      "loss": 1.4272,
      "step": 455
    },
    {
      "epoch": 0.008709936203537456,
      "grad_norm": 2.693742275238037,
      "learning_rate": 0.0001999963682997562,
      "loss": 1.6958,
      "step": 456
    },
    {
      "epoch": 0.008729036940825916,
      "grad_norm": 2.305137872695923,
      "learning_rate": 0.00019999635122961213,
      "loss": 1.7138,
      "step": 457
    },
    {
      "epoch": 0.008748137678114375,
      "grad_norm": 2.2521307468414307,
      "learning_rate": 0.00019999633411944522,
      "loss": 1.6088,
      "step": 458
    },
    {
      "epoch": 0.008767238415402834,
      "grad_norm": 2.239412546157837,
      "learning_rate": 0.0001999963169692555,
      "loss": 1.4312,
      "step": 459
    },
    {
      "epoch": 0.008786339152691294,
      "grad_norm": 2.7948105335235596,
      "learning_rate": 0.000199996299779043,
      "loss": 1.7943,
      "step": 460
    },
    {
      "epoch": 0.008805439889979753,
      "grad_norm": 2.494868278503418,
      "learning_rate": 0.00019999628254880773,
      "loss": 1.805,
      "step": 461
    },
    {
      "epoch": 0.008824540627268212,
      "grad_norm": 2.281214714050293,
      "learning_rate": 0.00019999626527854967,
      "loss": 1.6908,
      "step": 462
    },
    {
      "epoch": 0.008843641364556672,
      "grad_norm": 3.3299174308776855,
      "learning_rate": 0.0001999962479682688,
      "loss": 1.6818,
      "step": 463
    },
    {
      "epoch": 0.008862742101845131,
      "grad_norm": 2.8233964443206787,
      "learning_rate": 0.0001999962306179652,
      "loss": 1.6824,
      "step": 464
    },
    {
      "epoch": 0.00888184283913359,
      "grad_norm": 2.410487651824951,
      "learning_rate": 0.0001999962132276388,
      "loss": 1.7582,
      "step": 465
    },
    {
      "epoch": 0.00890094357642205,
      "grad_norm": 11.607137680053711,
      "learning_rate": 0.0001999961957972897,
      "loss": 1.6613,
      "step": 466
    },
    {
      "epoch": 0.00892004431371051,
      "grad_norm": 2.5743236541748047,
      "learning_rate": 0.00019999617832691782,
      "loss": 1.7846,
      "step": 467
    },
    {
      "epoch": 0.008939145050998968,
      "grad_norm": 2.4734020233154297,
      "learning_rate": 0.00019999616081652318,
      "loss": 1.3232,
      "step": 468
    },
    {
      "epoch": 0.008958245788287428,
      "grad_norm": 2.7250263690948486,
      "learning_rate": 0.00019999614326610585,
      "loss": 1.5613,
      "step": 469
    },
    {
      "epoch": 0.008977346525575887,
      "grad_norm": 2.7981746196746826,
      "learning_rate": 0.00019999612567566576,
      "loss": 1.5999,
      "step": 470
    },
    {
      "epoch": 0.008996447262864346,
      "grad_norm": 2.744213342666626,
      "learning_rate": 0.00019999610804520297,
      "loss": 2.0815,
      "step": 471
    },
    {
      "epoch": 0.009015548000152807,
      "grad_norm": 2.5034499168395996,
      "learning_rate": 0.00019999609037471748,
      "loss": 1.8573,
      "step": 472
    },
    {
      "epoch": 0.009034648737441265,
      "grad_norm": 2.700078010559082,
      "learning_rate": 0.00019999607266420926,
      "loss": 1.5098,
      "step": 473
    },
    {
      "epoch": 0.009053749474729724,
      "grad_norm": 2.2172675132751465,
      "learning_rate": 0.00019999605491367834,
      "loss": 1.6181,
      "step": 474
    },
    {
      "epoch": 0.009072850212018185,
      "grad_norm": 2.776186227798462,
      "learning_rate": 0.00019999603712312472,
      "loss": 1.8926,
      "step": 475
    },
    {
      "epoch": 0.009091950949306643,
      "grad_norm": 2.7656168937683105,
      "learning_rate": 0.00019999601929254844,
      "loss": 1.8352,
      "step": 476
    },
    {
      "epoch": 0.009111051686595102,
      "grad_norm": 2.783086061477661,
      "learning_rate": 0.00019999600142194947,
      "loss": 1.7487,
      "step": 477
    },
    {
      "epoch": 0.009130152423883563,
      "grad_norm": 5.61555814743042,
      "learning_rate": 0.0001999959835113278,
      "loss": 1.5753,
      "step": 478
    },
    {
      "epoch": 0.009149253161172021,
      "grad_norm": 2.427133083343506,
      "learning_rate": 0.00019999596556068353,
      "loss": 1.8291,
      "step": 479
    },
    {
      "epoch": 0.00916835389846048,
      "grad_norm": 2.6037750244140625,
      "learning_rate": 0.00019999594757001655,
      "loss": 1.9781,
      "step": 480
    },
    {
      "epoch": 0.00918745463574894,
      "grad_norm": 3.008629322052002,
      "learning_rate": 0.00019999592953932698,
      "loss": 1.7883,
      "step": 481
    },
    {
      "epoch": 0.0092065553730374,
      "grad_norm": 3.0140273571014404,
      "learning_rate": 0.00019999591146861473,
      "loss": 1.5834,
      "step": 482
    },
    {
      "epoch": 0.009225656110325858,
      "grad_norm": 2.377284049987793,
      "learning_rate": 0.00019999589335787984,
      "loss": 1.3955,
      "step": 483
    },
    {
      "epoch": 0.009244756847614317,
      "grad_norm": 2.635270833969116,
      "learning_rate": 0.00019999587520712236,
      "loss": 1.7041,
      "step": 484
    },
    {
      "epoch": 0.009263857584902778,
      "grad_norm": 2.9266700744628906,
      "learning_rate": 0.00019999585701634224,
      "loss": 1.9574,
      "step": 485
    },
    {
      "epoch": 0.009282958322191236,
      "grad_norm": 2.743868827819824,
      "learning_rate": 0.0001999958387855395,
      "loss": 1.627,
      "step": 486
    },
    {
      "epoch": 0.009302059059479695,
      "grad_norm": 2.098435640335083,
      "learning_rate": 0.00019999582051471415,
      "loss": 1.9481,
      "step": 487
    },
    {
      "epoch": 0.009321159796768156,
      "grad_norm": 2.2296576499938965,
      "learning_rate": 0.0001999958022038662,
      "loss": 1.8036,
      "step": 488
    },
    {
      "epoch": 0.009340260534056614,
      "grad_norm": 3.6765589714050293,
      "learning_rate": 0.00019999578385299568,
      "loss": 1.9649,
      "step": 489
    },
    {
      "epoch": 0.009359361271345073,
      "grad_norm": 3.0595455169677734,
      "learning_rate": 0.00019999576546210257,
      "loss": 1.9475,
      "step": 490
    },
    {
      "epoch": 0.009378462008633534,
      "grad_norm": 2.384010076522827,
      "learning_rate": 0.0001999957470311869,
      "loss": 1.4104,
      "step": 491
    },
    {
      "epoch": 0.009397562745921993,
      "grad_norm": 2.574535369873047,
      "learning_rate": 0.00019999572856024863,
      "loss": 1.6484,
      "step": 492
    },
    {
      "epoch": 0.009416663483210451,
      "grad_norm": 2.6458804607391357,
      "learning_rate": 0.00019999571004928782,
      "loss": 1.8833,
      "step": 493
    },
    {
      "epoch": 0.009435764220498912,
      "grad_norm": 2.349950075149536,
      "learning_rate": 0.00019999569149830446,
      "loss": 2.1191,
      "step": 494
    },
    {
      "epoch": 0.00945486495778737,
      "grad_norm": 3.1498658657073975,
      "learning_rate": 0.00019999567290729855,
      "loss": 1.7071,
      "step": 495
    },
    {
      "epoch": 0.00947396569507583,
      "grad_norm": 3.2090718746185303,
      "learning_rate": 0.00019999565427627008,
      "loss": 1.6817,
      "step": 496
    },
    {
      "epoch": 0.00949306643236429,
      "grad_norm": 2.395963668823242,
      "learning_rate": 0.0001999956356052191,
      "loss": 1.33,
      "step": 497
    },
    {
      "epoch": 0.009512167169652749,
      "grad_norm": 2.325792074203491,
      "learning_rate": 0.00019999561689414561,
      "loss": 1.162,
      "step": 498
    },
    {
      "epoch": 0.009531267906941207,
      "grad_norm": 2.388033390045166,
      "learning_rate": 0.0001999955981430496,
      "loss": 1.561,
      "step": 499
    },
    {
      "epoch": 0.009550368644229668,
      "grad_norm": 2.2684884071350098,
      "learning_rate": 0.00019999557935193108,
      "loss": 1.171,
      "step": 500
    },
    {
      "epoch": 0.009569469381518127,
      "grad_norm": 2.950627565383911,
      "learning_rate": 0.00019999556052079003,
      "loss": 1.5889,
      "step": 501
    },
    {
      "epoch": 0.009588570118806585,
      "grad_norm": 2.096398115158081,
      "learning_rate": 0.0001999955416496265,
      "loss": 1.2153,
      "step": 502
    },
    {
      "epoch": 0.009607670856095046,
      "grad_norm": 2.2046103477478027,
      "learning_rate": 0.00019999552273844052,
      "loss": 1.4099,
      "step": 503
    },
    {
      "epoch": 0.009626771593383505,
      "grad_norm": 2.2452595233917236,
      "learning_rate": 0.00019999550378723202,
      "loss": 1.7303,
      "step": 504
    },
    {
      "epoch": 0.009645872330671964,
      "grad_norm": 2.4751219749450684,
      "learning_rate": 0.00019999548479600104,
      "loss": 1.2452,
      "step": 505
    },
    {
      "epoch": 0.009664973067960424,
      "grad_norm": 2.661731719970703,
      "learning_rate": 0.00019999546576474764,
      "loss": 1.6215,
      "step": 506
    },
    {
      "epoch": 0.009684073805248883,
      "grad_norm": 2.141298770904541,
      "learning_rate": 0.00019999544669347175,
      "loss": 1.754,
      "step": 507
    },
    {
      "epoch": 0.009703174542537342,
      "grad_norm": 2.6175999641418457,
      "learning_rate": 0.00019999542758217343,
      "loss": 1.853,
      "step": 508
    },
    {
      "epoch": 0.009722275279825802,
      "grad_norm": 2.7261364459991455,
      "learning_rate": 0.00019999540843085268,
      "loss": 1.5112,
      "step": 509
    },
    {
      "epoch": 0.009741376017114261,
      "grad_norm": 2.7811036109924316,
      "learning_rate": 0.00019999538923950948,
      "loss": 1.8711,
      "step": 510
    },
    {
      "epoch": 0.00976047675440272,
      "grad_norm": 3.1355984210968018,
      "learning_rate": 0.00019999537000814385,
      "loss": 1.4778,
      "step": 511
    },
    {
      "epoch": 0.009779577491691178,
      "grad_norm": 2.2926268577575684,
      "learning_rate": 0.0001999953507367558,
      "loss": 1.6349,
      "step": 512
    },
    {
      "epoch": 0.009798678228979639,
      "grad_norm": 2.6121926307678223,
      "learning_rate": 0.00019999533142534538,
      "loss": 1.9548,
      "step": 513
    },
    {
      "epoch": 0.009817778966268098,
      "grad_norm": 2.5958971977233887,
      "learning_rate": 0.00019999531207391251,
      "loss": 1.5181,
      "step": 514
    },
    {
      "epoch": 0.009836879703556557,
      "grad_norm": 1.885945200920105,
      "learning_rate": 0.00019999529268245728,
      "loss": 1.2165,
      "step": 515
    },
    {
      "epoch": 0.009855980440845017,
      "grad_norm": 2.7017934322357178,
      "learning_rate": 0.00019999527325097964,
      "loss": 2.0755,
      "step": 516
    },
    {
      "epoch": 0.009875081178133476,
      "grad_norm": 2.7641208171844482,
      "learning_rate": 0.00019999525377947962,
      "loss": 1.9842,
      "step": 517
    },
    {
      "epoch": 0.009894181915421935,
      "grad_norm": 2.2648820877075195,
      "learning_rate": 0.00019999523426795729,
      "loss": 1.5034,
      "step": 518
    },
    {
      "epoch": 0.009913282652710395,
      "grad_norm": 2.527851104736328,
      "learning_rate": 0.00019999521471641255,
      "loss": 1.8324,
      "step": 519
    },
    {
      "epoch": 0.009932383389998854,
      "grad_norm": 2.301114797592163,
      "learning_rate": 0.0001999951951248454,
      "loss": 1.7006,
      "step": 520
    },
    {
      "epoch": 0.009951484127287313,
      "grad_norm": 2.1252832412719727,
      "learning_rate": 0.00019999517549325598,
      "loss": 1.5727,
      "step": 521
    },
    {
      "epoch": 0.009970584864575773,
      "grad_norm": 2.397451877593994,
      "learning_rate": 0.0001999951558216442,
      "loss": 1.4762,
      "step": 522
    },
    {
      "epoch": 0.009989685601864232,
      "grad_norm": 3.1829490661621094,
      "learning_rate": 0.00019999513611001008,
      "loss": 1.9065,
      "step": 523
    },
    {
      "epoch": 0.01000878633915269,
      "grad_norm": 2.408437490463257,
      "learning_rate": 0.00019999511635835363,
      "loss": 1.5941,
      "step": 524
    },
    {
      "epoch": 0.010027887076441151,
      "grad_norm": 2.3365416526794434,
      "learning_rate": 0.0001999950965666749,
      "loss": 1.416,
      "step": 525
    },
    {
      "epoch": 0.01004698781372961,
      "grad_norm": 2.3885278701782227,
      "learning_rate": 0.00019999507673497383,
      "loss": 1.3723,
      "step": 526
    },
    {
      "epoch": 0.010066088551018069,
      "grad_norm": 2.562570095062256,
      "learning_rate": 0.00019999505686325048,
      "loss": 1.8526,
      "step": 527
    },
    {
      "epoch": 0.01008518928830653,
      "grad_norm": 2.801509141921997,
      "learning_rate": 0.00019999503695150483,
      "loss": 1.6393,
      "step": 528
    },
    {
      "epoch": 0.010104290025594988,
      "grad_norm": 2.9117088317871094,
      "learning_rate": 0.00019999501699973692,
      "loss": 1.41,
      "step": 529
    },
    {
      "epoch": 0.010123390762883447,
      "grad_norm": 2.109048366546631,
      "learning_rate": 0.0001999949970079467,
      "loss": 1.5962,
      "step": 530
    },
    {
      "epoch": 0.010142491500171907,
      "grad_norm": 2.446869373321533,
      "learning_rate": 0.00019999497697613424,
      "loss": 1.908,
      "step": 531
    },
    {
      "epoch": 0.010161592237460366,
      "grad_norm": 2.8916923999786377,
      "learning_rate": 0.00019999495690429947,
      "loss": 1.5868,
      "step": 532
    },
    {
      "epoch": 0.010180692974748825,
      "grad_norm": 2.7810280323028564,
      "learning_rate": 0.00019999493679244247,
      "loss": 1.7152,
      "step": 533
    },
    {
      "epoch": 0.010199793712037285,
      "grad_norm": 3.361274480819702,
      "learning_rate": 0.00019999491664056325,
      "loss": 1.9465,
      "step": 534
    },
    {
      "epoch": 0.010218894449325744,
      "grad_norm": 3.292489528656006,
      "learning_rate": 0.00019999489644866177,
      "loss": 1.9029,
      "step": 535
    },
    {
      "epoch": 0.010237995186614203,
      "grad_norm": 2.8238041400909424,
      "learning_rate": 0.00019999487621673808,
      "loss": 1.7841,
      "step": 536
    },
    {
      "epoch": 0.010257095923902664,
      "grad_norm": 3.657904863357544,
      "learning_rate": 0.00019999485594479217,
      "loss": 1.3361,
      "step": 537
    },
    {
      "epoch": 0.010276196661191122,
      "grad_norm": 3.400042772293091,
      "learning_rate": 0.00019999483563282406,
      "loss": 1.7846,
      "step": 538
    },
    {
      "epoch": 0.010295297398479581,
      "grad_norm": 2.5916669368743896,
      "learning_rate": 0.0001999948152808337,
      "loss": 1.7077,
      "step": 539
    },
    {
      "epoch": 0.01031439813576804,
      "grad_norm": 2.773420572280884,
      "learning_rate": 0.00019999479488882118,
      "loss": 1.4611,
      "step": 540
    },
    {
      "epoch": 0.0103334988730565,
      "grad_norm": 2.7768609523773193,
      "learning_rate": 0.00019999477445678648,
      "loss": 1.7089,
      "step": 541
    },
    {
      "epoch": 0.010352599610344959,
      "grad_norm": 2.1695709228515625,
      "learning_rate": 0.0001999947539847296,
      "loss": 1.4427,
      "step": 542
    },
    {
      "epoch": 0.010371700347633418,
      "grad_norm": 2.531581401824951,
      "learning_rate": 0.00019999473347265053,
      "loss": 1.4312,
      "step": 543
    },
    {
      "epoch": 0.010390801084921878,
      "grad_norm": 3.202211618423462,
      "learning_rate": 0.00019999471292054933,
      "loss": 1.4947,
      "step": 544
    },
    {
      "epoch": 0.010409901822210337,
      "grad_norm": 2.6524271965026855,
      "learning_rate": 0.00019999469232842595,
      "loss": 1.7487,
      "step": 545
    },
    {
      "epoch": 0.010429002559498796,
      "grad_norm": 3.0159459114074707,
      "learning_rate": 0.00019999467169628038,
      "loss": 1.2636,
      "step": 546
    },
    {
      "epoch": 0.010448103296787256,
      "grad_norm": 2.9119112491607666,
      "learning_rate": 0.00019999465102411273,
      "loss": 1.2444,
      "step": 547
    },
    {
      "epoch": 0.010467204034075715,
      "grad_norm": 2.456414222717285,
      "learning_rate": 0.00019999463031192293,
      "loss": 1.637,
      "step": 548
    },
    {
      "epoch": 0.010486304771364174,
      "grad_norm": 2.26185941696167,
      "learning_rate": 0.00019999460955971103,
      "loss": 2.1721,
      "step": 549
    },
    {
      "epoch": 0.010505405508652635,
      "grad_norm": 2.312927007675171,
      "learning_rate": 0.00019999458876747702,
      "loss": 1.099,
      "step": 550
    },
    {
      "epoch": 0.010524506245941093,
      "grad_norm": 2.6310036182403564,
      "learning_rate": 0.0001999945679352209,
      "loss": 1.6433,
      "step": 551
    },
    {
      "epoch": 0.010543606983229552,
      "grad_norm": 2.6065750122070312,
      "learning_rate": 0.00019999454706294266,
      "loss": 1.771,
      "step": 552
    },
    {
      "epoch": 0.010562707720518013,
      "grad_norm": 2.5609495639801025,
      "learning_rate": 0.00019999452615064237,
      "loss": 2.2705,
      "step": 553
    },
    {
      "epoch": 0.010581808457806471,
      "grad_norm": 2.9569127559661865,
      "learning_rate": 0.00019999450519831994,
      "loss": 1.8389,
      "step": 554
    },
    {
      "epoch": 0.01060090919509493,
      "grad_norm": 2.4812865257263184,
      "learning_rate": 0.0001999944842059755,
      "loss": 1.8519,
      "step": 555
    },
    {
      "epoch": 0.01062000993238339,
      "grad_norm": 3.063325881958008,
      "learning_rate": 0.000199994463173609,
      "loss": 1.6486,
      "step": 556
    },
    {
      "epoch": 0.01063911066967185,
      "grad_norm": 4.5443034172058105,
      "learning_rate": 0.0001999944421012204,
      "loss": 1.5709,
      "step": 557
    },
    {
      "epoch": 0.010658211406960308,
      "grad_norm": 2.5845296382904053,
      "learning_rate": 0.00019999442098880978,
      "loss": 1.8639,
      "step": 558
    },
    {
      "epoch": 0.010677312144248769,
      "grad_norm": 2.2224247455596924,
      "learning_rate": 0.0001999943998363771,
      "loss": 1.5837,
      "step": 559
    },
    {
      "epoch": 0.010696412881537228,
      "grad_norm": 2.829287528991699,
      "learning_rate": 0.00019999437864392242,
      "loss": 1.4475,
      "step": 560
    },
    {
      "epoch": 0.010715513618825686,
      "grad_norm": 2.479654312133789,
      "learning_rate": 0.0001999943574114457,
      "loss": 1.6639,
      "step": 561
    },
    {
      "epoch": 0.010734614356114147,
      "grad_norm": 2.687471628189087,
      "learning_rate": 0.000199994336138947,
      "loss": 1.8888,
      "step": 562
    },
    {
      "epoch": 0.010753715093402606,
      "grad_norm": 2.596912384033203,
      "learning_rate": 0.00019999431482642626,
      "loss": 1.8142,
      "step": 563
    },
    {
      "epoch": 0.010772815830691064,
      "grad_norm": 2.9020838737487793,
      "learning_rate": 0.00019999429347388354,
      "loss": 2.0703,
      "step": 564
    },
    {
      "epoch": 0.010791916567979523,
      "grad_norm": 2.944603204727173,
      "learning_rate": 0.00019999427208131884,
      "loss": 1.6916,
      "step": 565
    },
    {
      "epoch": 0.010811017305267984,
      "grad_norm": 2.8149964809417725,
      "learning_rate": 0.00019999425064873215,
      "loss": 1.4511,
      "step": 566
    },
    {
      "epoch": 0.010830118042556442,
      "grad_norm": 2.7110812664031982,
      "learning_rate": 0.00019999422917612352,
      "loss": 2.0112,
      "step": 567
    },
    {
      "epoch": 0.010849218779844901,
      "grad_norm": 2.5554158687591553,
      "learning_rate": 0.0001999942076634929,
      "loss": 1.6409,
      "step": 568
    },
    {
      "epoch": 0.010868319517133362,
      "grad_norm": 2.444139242172241,
      "learning_rate": 0.0001999941861108403,
      "loss": 1.7189,
      "step": 569
    },
    {
      "epoch": 0.01088742025442182,
      "grad_norm": 2.5485432147979736,
      "learning_rate": 0.00019999416451816582,
      "loss": 1.6837,
      "step": 570
    },
    {
      "epoch": 0.01090652099171028,
      "grad_norm": 2.6404764652252197,
      "learning_rate": 0.00019999414288546938,
      "loss": 1.396,
      "step": 571
    },
    {
      "epoch": 0.01092562172899874,
      "grad_norm": 2.8588619232177734,
      "learning_rate": 0.00019999412121275101,
      "loss": 2.4281,
      "step": 572
    },
    {
      "epoch": 0.010944722466287199,
      "grad_norm": 2.2015268802642822,
      "learning_rate": 0.00019999409950001074,
      "loss": 1.3709,
      "step": 573
    },
    {
      "epoch": 0.010963823203575657,
      "grad_norm": 2.542998790740967,
      "learning_rate": 0.00019999407774724852,
      "loss": 1.1404,
      "step": 574
    },
    {
      "epoch": 0.010982923940864118,
      "grad_norm": 2.909494638442993,
      "learning_rate": 0.00019999405595446442,
      "loss": 1.6487,
      "step": 575
    },
    {
      "epoch": 0.011002024678152577,
      "grad_norm": 2.0401461124420166,
      "learning_rate": 0.00019999403412165846,
      "loss": 1.5564,
      "step": 576
    },
    {
      "epoch": 0.011021125415441035,
      "grad_norm": 2.6978771686553955,
      "learning_rate": 0.00019999401224883058,
      "loss": 1.7273,
      "step": 577
    },
    {
      "epoch": 0.011040226152729496,
      "grad_norm": 1.9256681203842163,
      "learning_rate": 0.00019999399033598082,
      "loss": 1.7656,
      "step": 578
    },
    {
      "epoch": 0.011059326890017955,
      "grad_norm": 2.556506872177124,
      "learning_rate": 0.00019999396838310922,
      "loss": 1.0669,
      "step": 579
    },
    {
      "epoch": 0.011078427627306413,
      "grad_norm": 2.6599297523498535,
      "learning_rate": 0.00019999394639021577,
      "loss": 1.9357,
      "step": 580
    },
    {
      "epoch": 0.011097528364594874,
      "grad_norm": 2.2721431255340576,
      "learning_rate": 0.00019999392435730045,
      "loss": 1.5638,
      "step": 581
    },
    {
      "epoch": 0.011116629101883333,
      "grad_norm": 3.3910045623779297,
      "learning_rate": 0.00019999390228436333,
      "loss": 1.8197,
      "step": 582
    },
    {
      "epoch": 0.011135729839171792,
      "grad_norm": 2.4710543155670166,
      "learning_rate": 0.00019999388017140436,
      "loss": 1.4693,
      "step": 583
    },
    {
      "epoch": 0.011154830576460252,
      "grad_norm": 2.6770901679992676,
      "learning_rate": 0.00019999385801842352,
      "loss": 1.743,
      "step": 584
    },
    {
      "epoch": 0.01117393131374871,
      "grad_norm": 2.5150258541107178,
      "learning_rate": 0.00019999383582542093,
      "loss": 1.7097,
      "step": 585
    },
    {
      "epoch": 0.01119303205103717,
      "grad_norm": 3.089395761489868,
      "learning_rate": 0.0001999938135923965,
      "loss": 2.1524,
      "step": 586
    },
    {
      "epoch": 0.01121213278832563,
      "grad_norm": 2.5426809787750244,
      "learning_rate": 0.00019999379131935033,
      "loss": 1.5698,
      "step": 587
    },
    {
      "epoch": 0.011231233525614089,
      "grad_norm": 3.366891384124756,
      "learning_rate": 0.0001999937690062823,
      "loss": 1.7869,
      "step": 588
    },
    {
      "epoch": 0.011250334262902548,
      "grad_norm": 2.702518939971924,
      "learning_rate": 0.00019999374665319254,
      "loss": 1.5403,
      "step": 589
    },
    {
      "epoch": 0.011269435000191008,
      "grad_norm": 3.1196656227111816,
      "learning_rate": 0.000199993724260081,
      "loss": 1.4863,
      "step": 590
    },
    {
      "epoch": 0.011288535737479467,
      "grad_norm": 2.9855072498321533,
      "learning_rate": 0.00019999370182694772,
      "loss": 1.2492,
      "step": 591
    },
    {
      "epoch": 0.011307636474767926,
      "grad_norm": 3.178865671157837,
      "learning_rate": 0.00019999367935379268,
      "loss": 1.5056,
      "step": 592
    },
    {
      "epoch": 0.011326737212056385,
      "grad_norm": 2.533909559249878,
      "learning_rate": 0.0001999936568406159,
      "loss": 1.7882,
      "step": 593
    },
    {
      "epoch": 0.011345837949344845,
      "grad_norm": 3.1380391120910645,
      "learning_rate": 0.00019999363428741738,
      "loss": 2.0992,
      "step": 594
    },
    {
      "epoch": 0.011364938686633304,
      "grad_norm": 2.593240976333618,
      "learning_rate": 0.00019999361169419712,
      "loss": 1.6021,
      "step": 595
    },
    {
      "epoch": 0.011384039423921763,
      "grad_norm": 2.567368507385254,
      "learning_rate": 0.0001999935890609552,
      "loss": 1.4546,
      "step": 596
    },
    {
      "epoch": 0.011403140161210223,
      "grad_norm": 2.84065318107605,
      "learning_rate": 0.0001999935663876915,
      "loss": 2.0434,
      "step": 597
    },
    {
      "epoch": 0.011422240898498682,
      "grad_norm": 2.372765302658081,
      "learning_rate": 0.00019999354367440618,
      "loss": 1.9569,
      "step": 598
    },
    {
      "epoch": 0.01144134163578714,
      "grad_norm": 3.1541905403137207,
      "learning_rate": 0.00019999352092109915,
      "loss": 1.7301,
      "step": 599
    },
    {
      "epoch": 0.011460442373075601,
      "grad_norm": 2.7687268257141113,
      "learning_rate": 0.00019999349812777043,
      "loss": 1.2495,
      "step": 600
    },
    {
      "epoch": 0.011460442373075601,
      "eval_loss": 1.6057014465332031,
      "eval_runtime": 316.347,
      "eval_samples_per_second": 3.329,
      "eval_steps_per_second": 3.329,
      "step": 600
    },
    {
      "epoch": 0.01147954311036406,
      "grad_norm": 2.864779472351074,
      "learning_rate": 0.00019999347529442004,
      "loss": 1.571,
      "step": 601
    },
    {
      "epoch": 0.011498643847652519,
      "grad_norm": 2.411355495452881,
      "learning_rate": 0.000199993452421048,
      "loss": 1.7606,
      "step": 602
    },
    {
      "epoch": 0.01151774458494098,
      "grad_norm": 2.9920690059661865,
      "learning_rate": 0.0001999934295076543,
      "loss": 1.4411,
      "step": 603
    },
    {
      "epoch": 0.011536845322229438,
      "grad_norm": 2.8667569160461426,
      "learning_rate": 0.00019999340655423899,
      "loss": 1.9482,
      "step": 604
    },
    {
      "epoch": 0.011555946059517897,
      "grad_norm": 2.8687736988067627,
      "learning_rate": 0.00019999338356080202,
      "loss": 1.3954,
      "step": 605
    },
    {
      "epoch": 0.011575046796806357,
      "grad_norm": 3.2238101959228516,
      "learning_rate": 0.00019999336052734345,
      "loss": 1.6533,
      "step": 606
    },
    {
      "epoch": 0.011594147534094816,
      "grad_norm": 2.429716110229492,
      "learning_rate": 0.00019999333745386325,
      "loss": 1.4666,
      "step": 607
    },
    {
      "epoch": 0.011613248271383275,
      "grad_norm": 2.301257848739624,
      "learning_rate": 0.00019999331434036145,
      "loss": 1.6573,
      "step": 608
    },
    {
      "epoch": 0.011632349008671735,
      "grad_norm": 3.1305930614471436,
      "learning_rate": 0.00019999329118683805,
      "loss": 1.9612,
      "step": 609
    },
    {
      "epoch": 0.011651449745960194,
      "grad_norm": 2.5469961166381836,
      "learning_rate": 0.00019999326799329307,
      "loss": 1.6685,
      "step": 610
    },
    {
      "epoch": 0.011670550483248653,
      "grad_norm": 3.266101360321045,
      "learning_rate": 0.00019999324475972652,
      "loss": 1.6436,
      "step": 611
    },
    {
      "epoch": 0.011689651220537113,
      "grad_norm": 2.397834062576294,
      "learning_rate": 0.00019999322148613838,
      "loss": 1.4486,
      "step": 612
    },
    {
      "epoch": 0.011708751957825572,
      "grad_norm": 2.3775346279144287,
      "learning_rate": 0.00019999319817252871,
      "loss": 1.2804,
      "step": 613
    },
    {
      "epoch": 0.011727852695114031,
      "grad_norm": 2.231910228729248,
      "learning_rate": 0.0001999931748188975,
      "loss": 2.0634,
      "step": 614
    },
    {
      "epoch": 0.011746953432402491,
      "grad_norm": 2.4796581268310547,
      "learning_rate": 0.00019999315142524472,
      "loss": 1.6056,
      "step": 615
    },
    {
      "epoch": 0.01176605416969095,
      "grad_norm": 3.218553066253662,
      "learning_rate": 0.00019999312799157045,
      "loss": 1.7809,
      "step": 616
    },
    {
      "epoch": 0.011785154906979409,
      "grad_norm": 2.437124252319336,
      "learning_rate": 0.00019999310451787464,
      "loss": 1.3701,
      "step": 617
    },
    {
      "epoch": 0.01180425564426787,
      "grad_norm": 2.6643710136413574,
      "learning_rate": 0.0001999930810041573,
      "loss": 1.9405,
      "step": 618
    },
    {
      "epoch": 0.011823356381556328,
      "grad_norm": 3.1502201557159424,
      "learning_rate": 0.00019999305745041848,
      "loss": 1.8137,
      "step": 619
    },
    {
      "epoch": 0.011842457118844787,
      "grad_norm": 3.2663509845733643,
      "learning_rate": 0.00019999303385665815,
      "loss": 1.6637,
      "step": 620
    },
    {
      "epoch": 0.011861557856133246,
      "grad_norm": 2.316215753555298,
      "learning_rate": 0.00019999301022287637,
      "loss": 1.8888,
      "step": 621
    },
    {
      "epoch": 0.011880658593421706,
      "grad_norm": 2.502110481262207,
      "learning_rate": 0.0001999929865490731,
      "loss": 1.8574,
      "step": 622
    },
    {
      "epoch": 0.011899759330710165,
      "grad_norm": 2.652360200881958,
      "learning_rate": 0.00019999296283524837,
      "loss": 1.4807,
      "step": 623
    },
    {
      "epoch": 0.011918860067998624,
      "grad_norm": 2.557692527770996,
      "learning_rate": 0.00019999293908140218,
      "loss": 1.9732,
      "step": 624
    },
    {
      "epoch": 0.011937960805287084,
      "grad_norm": 2.14984130859375,
      "learning_rate": 0.00019999291528753453,
      "loss": 1.7349,
      "step": 625
    },
    {
      "epoch": 0.011957061542575543,
      "grad_norm": 3.0951967239379883,
      "learning_rate": 0.00019999289145364549,
      "loss": 1.9189,
      "step": 626
    },
    {
      "epoch": 0.011976162279864002,
      "grad_norm": 2.535294532775879,
      "learning_rate": 0.000199992867579735,
      "loss": 1.7201,
      "step": 627
    },
    {
      "epoch": 0.011995263017152463,
      "grad_norm": 2.547638177871704,
      "learning_rate": 0.0001999928436658031,
      "loss": 1.7049,
      "step": 628
    },
    {
      "epoch": 0.012014363754440921,
      "grad_norm": 3.340628147125244,
      "learning_rate": 0.00019999281971184977,
      "loss": 1.6626,
      "step": 629
    },
    {
      "epoch": 0.01203346449172938,
      "grad_norm": 2.68426251411438,
      "learning_rate": 0.00019999279571787505,
      "loss": 1.7096,
      "step": 630
    },
    {
      "epoch": 0.01205256522901784,
      "grad_norm": 3.0554888248443604,
      "learning_rate": 0.00019999277168387898,
      "loss": 1.3704,
      "step": 631
    },
    {
      "epoch": 0.0120716659663063,
      "grad_norm": 3.0311872959136963,
      "learning_rate": 0.0001999927476098615,
      "loss": 1.7377,
      "step": 632
    },
    {
      "epoch": 0.012090766703594758,
      "grad_norm": 2.9748988151550293,
      "learning_rate": 0.00019999272349582265,
      "loss": 1.8879,
      "step": 633
    },
    {
      "epoch": 0.012109867440883219,
      "grad_norm": 3.180656909942627,
      "learning_rate": 0.00019999269934176247,
      "loss": 1.8419,
      "step": 634
    },
    {
      "epoch": 0.012128968178171677,
      "grad_norm": 2.576258897781372,
      "learning_rate": 0.00019999267514768092,
      "loss": 1.4033,
      "step": 635
    },
    {
      "epoch": 0.012148068915460136,
      "grad_norm": 2.569373607635498,
      "learning_rate": 0.00019999265091357802,
      "loss": 1.7824,
      "step": 636
    },
    {
      "epoch": 0.012167169652748597,
      "grad_norm": 2.5161616802215576,
      "learning_rate": 0.0001999926266394538,
      "loss": 1.6731,
      "step": 637
    },
    {
      "epoch": 0.012186270390037056,
      "grad_norm": 2.3374226093292236,
      "learning_rate": 0.0001999926023253083,
      "loss": 1.7104,
      "step": 638
    },
    {
      "epoch": 0.012205371127325514,
      "grad_norm": 2.4363086223602295,
      "learning_rate": 0.00019999257797114142,
      "loss": 1.8085,
      "step": 639
    },
    {
      "epoch": 0.012224471864613975,
      "grad_norm": 2.941084861755371,
      "learning_rate": 0.0001999925535769533,
      "loss": 2.0765,
      "step": 640
    },
    {
      "epoch": 0.012243572601902434,
      "grad_norm": 2.83056640625,
      "learning_rate": 0.00019999252914274388,
      "loss": 1.8043,
      "step": 641
    },
    {
      "epoch": 0.012262673339190892,
      "grad_norm": 2.3962693214416504,
      "learning_rate": 0.00019999250466851316,
      "loss": 1.4625,
      "step": 642
    },
    {
      "epoch": 0.012281774076479353,
      "grad_norm": 2.6046390533447266,
      "learning_rate": 0.0001999924801542612,
      "loss": 1.0684,
      "step": 643
    },
    {
      "epoch": 0.012300874813767812,
      "grad_norm": 2.9064183235168457,
      "learning_rate": 0.00019999245559998796,
      "loss": 1.4994,
      "step": 644
    },
    {
      "epoch": 0.01231997555105627,
      "grad_norm": 2.9133238792419434,
      "learning_rate": 0.00019999243100569345,
      "loss": 1.6579,
      "step": 645
    },
    {
      "epoch": 0.012339076288344731,
      "grad_norm": 2.8820364475250244,
      "learning_rate": 0.0001999924063713777,
      "loss": 1.9706,
      "step": 646
    },
    {
      "epoch": 0.01235817702563319,
      "grad_norm": 2.4429101943969727,
      "learning_rate": 0.00019999238169704075,
      "loss": 1.5358,
      "step": 647
    },
    {
      "epoch": 0.012377277762921648,
      "grad_norm": 2.3884732723236084,
      "learning_rate": 0.00019999235698268258,
      "loss": 1.5619,
      "step": 648
    },
    {
      "epoch": 0.012396378500210107,
      "grad_norm": 2.282904863357544,
      "learning_rate": 0.00019999233222830318,
      "loss": 1.6431,
      "step": 649
    },
    {
      "epoch": 0.012415479237498568,
      "grad_norm": 2.6698572635650635,
      "learning_rate": 0.00019999230743390257,
      "loss": 1.4717,
      "step": 650
    },
    {
      "epoch": 0.012434579974787027,
      "grad_norm": 2.802544116973877,
      "learning_rate": 0.0001999922825994808,
      "loss": 1.8708,
      "step": 651
    },
    {
      "epoch": 0.012453680712075485,
      "grad_norm": 3.031515598297119,
      "learning_rate": 0.00019999225772503784,
      "loss": 1.9596,
      "step": 652
    },
    {
      "epoch": 0.012472781449363946,
      "grad_norm": 2.81042742729187,
      "learning_rate": 0.00019999223281057368,
      "loss": 1.7721,
      "step": 653
    },
    {
      "epoch": 0.012491882186652405,
      "grad_norm": 2.502845287322998,
      "learning_rate": 0.0001999922078560884,
      "loss": 1.601,
      "step": 654
    },
    {
      "epoch": 0.012510982923940863,
      "grad_norm": 2.882308006286621,
      "learning_rate": 0.00019999218286158193,
      "loss": 1.7559,
      "step": 655
    },
    {
      "epoch": 0.012530083661229324,
      "grad_norm": 3.1670713424682617,
      "learning_rate": 0.00019999215782705434,
      "loss": 1.8753,
      "step": 656
    },
    {
      "epoch": 0.012549184398517783,
      "grad_norm": 3.557795286178589,
      "learning_rate": 0.00019999213275250562,
      "loss": 1.8192,
      "step": 657
    },
    {
      "epoch": 0.012568285135806241,
      "grad_norm": 3.2227823734283447,
      "learning_rate": 0.00019999210763793577,
      "loss": 1.7,
      "step": 658
    },
    {
      "epoch": 0.012587385873094702,
      "grad_norm": 3.2979555130004883,
      "learning_rate": 0.00019999208248334483,
      "loss": 1.6068,
      "step": 659
    },
    {
      "epoch": 0.01260648661038316,
      "grad_norm": 2.654470682144165,
      "learning_rate": 0.00019999205728873275,
      "loss": 1.4862,
      "step": 660
    },
    {
      "epoch": 0.01262558734767162,
      "grad_norm": 2.6005117893218994,
      "learning_rate": 0.0001999920320540996,
      "loss": 1.9259,
      "step": 661
    },
    {
      "epoch": 0.01264468808496008,
      "grad_norm": 2.6312828063964844,
      "learning_rate": 0.00019999200677944535,
      "loss": 1.4842,
      "step": 662
    },
    {
      "epoch": 0.012663788822248539,
      "grad_norm": 2.927393674850464,
      "learning_rate": 0.00019999198146477008,
      "loss": 1.7834,
      "step": 663
    },
    {
      "epoch": 0.012682889559536998,
      "grad_norm": 3.496072292327881,
      "learning_rate": 0.00019999195611007368,
      "loss": 1.7548,
      "step": 664
    },
    {
      "epoch": 0.012701990296825458,
      "grad_norm": 2.8093299865722656,
      "learning_rate": 0.0001999919307153563,
      "loss": 1.5364,
      "step": 665
    },
    {
      "epoch": 0.012721091034113917,
      "grad_norm": 2.56909441947937,
      "learning_rate": 0.00019999190528061783,
      "loss": 1.6719,
      "step": 666
    },
    {
      "epoch": 0.012740191771402376,
      "grad_norm": 2.4822440147399902,
      "learning_rate": 0.00019999187980585835,
      "loss": 2.077,
      "step": 667
    },
    {
      "epoch": 0.012759292508690836,
      "grad_norm": 2.8480865955352783,
      "learning_rate": 0.00019999185429107782,
      "loss": 1.4884,
      "step": 668
    },
    {
      "epoch": 0.012778393245979295,
      "grad_norm": 2.7173736095428467,
      "learning_rate": 0.0001999918287362763,
      "loss": 1.6966,
      "step": 669
    },
    {
      "epoch": 0.012797493983267754,
      "grad_norm": 2.7146530151367188,
      "learning_rate": 0.00019999180314145382,
      "loss": 1.73,
      "step": 670
    },
    {
      "epoch": 0.012816594720556214,
      "grad_norm": 3.322645902633667,
      "learning_rate": 0.0001999917775066103,
      "loss": 2.1701,
      "step": 671
    },
    {
      "epoch": 0.012835695457844673,
      "grad_norm": 2.5913186073303223,
      "learning_rate": 0.00019999175183174584,
      "loss": 1.7808,
      "step": 672
    },
    {
      "epoch": 0.012854796195133132,
      "grad_norm": 3.885732650756836,
      "learning_rate": 0.00019999172611686035,
      "loss": 1.6411,
      "step": 673
    },
    {
      "epoch": 0.012873896932421592,
      "grad_norm": 2.3079276084899902,
      "learning_rate": 0.00019999170036195395,
      "loss": 1.3599,
      "step": 674
    },
    {
      "epoch": 0.012892997669710051,
      "grad_norm": 2.825882911682129,
      "learning_rate": 0.0001999916745670266,
      "loss": 1.5204,
      "step": 675
    },
    {
      "epoch": 0.01291209840699851,
      "grad_norm": 2.627578020095825,
      "learning_rate": 0.00019999164873207831,
      "loss": 1.9556,
      "step": 676
    },
    {
      "epoch": 0.012931199144286969,
      "grad_norm": 2.994882106781006,
      "learning_rate": 0.00019999162285710907,
      "loss": 1.5385,
      "step": 677
    },
    {
      "epoch": 0.01295029988157543,
      "grad_norm": 2.3018670082092285,
      "learning_rate": 0.00019999159694211892,
      "loss": 1.4885,
      "step": 678
    },
    {
      "epoch": 0.012969400618863888,
      "grad_norm": 2.8117122650146484,
      "learning_rate": 0.0001999915709871079,
      "loss": 1.7377,
      "step": 679
    },
    {
      "epoch": 0.012988501356152347,
      "grad_norm": 2.962376594543457,
      "learning_rate": 0.00019999154499207594,
      "loss": 1.4886,
      "step": 680
    },
    {
      "epoch": 0.013007602093440807,
      "grad_norm": 1.9343243837356567,
      "learning_rate": 0.00019999151895702314,
      "loss": 1.3736,
      "step": 681
    },
    {
      "epoch": 0.013026702830729266,
      "grad_norm": 2.432466745376587,
      "learning_rate": 0.0001999914928819494,
      "loss": 2.1578,
      "step": 682
    },
    {
      "epoch": 0.013045803568017725,
      "grad_norm": 2.202101469039917,
      "learning_rate": 0.00019999146676685483,
      "loss": 1.2948,
      "step": 683
    },
    {
      "epoch": 0.013064904305306185,
      "grad_norm": 3.549584150314331,
      "learning_rate": 0.0001999914406117394,
      "loss": 1.8424,
      "step": 684
    },
    {
      "epoch": 0.013084005042594644,
      "grad_norm": 2.5720021724700928,
      "learning_rate": 0.00019999141441660314,
      "loss": 1.7538,
      "step": 685
    },
    {
      "epoch": 0.013103105779883103,
      "grad_norm": 2.6509618759155273,
      "learning_rate": 0.00019999138818144603,
      "loss": 1.6428,
      "step": 686
    },
    {
      "epoch": 0.013122206517171563,
      "grad_norm": 2.5078060626983643,
      "learning_rate": 0.00019999136190626811,
      "loss": 1.4622,
      "step": 687
    },
    {
      "epoch": 0.013141307254460022,
      "grad_norm": 2.402911901473999,
      "learning_rate": 0.00019999133559106937,
      "loss": 1.7112,
      "step": 688
    },
    {
      "epoch": 0.013160407991748481,
      "grad_norm": 2.844231128692627,
      "learning_rate": 0.00019999130923584982,
      "loss": 1.8277,
      "step": 689
    },
    {
      "epoch": 0.013179508729036941,
      "grad_norm": 3.094304084777832,
      "learning_rate": 0.00019999128284060947,
      "loss": 1.7636,
      "step": 690
    },
    {
      "epoch": 0.0131986094663254,
      "grad_norm": 3.2131800651550293,
      "learning_rate": 0.00019999125640534837,
      "loss": 1.8747,
      "step": 691
    },
    {
      "epoch": 0.013217710203613859,
      "grad_norm": 2.424783945083618,
      "learning_rate": 0.00019999122993006647,
      "loss": 1.4385,
      "step": 692
    },
    {
      "epoch": 0.01323681094090232,
      "grad_norm": 2.238924741744995,
      "learning_rate": 0.00019999120341476382,
      "loss": 1.6293,
      "step": 693
    },
    {
      "epoch": 0.013255911678190778,
      "grad_norm": 2.055927276611328,
      "learning_rate": 0.00019999117685944043,
      "loss": 1.7289,
      "step": 694
    },
    {
      "epoch": 0.013275012415479237,
      "grad_norm": 2.728943109512329,
      "learning_rate": 0.00019999115026409628,
      "loss": 1.7285,
      "step": 695
    },
    {
      "epoch": 0.013294113152767698,
      "grad_norm": 2.6181559562683105,
      "learning_rate": 0.00019999112362873141,
      "loss": 1.2837,
      "step": 696
    },
    {
      "epoch": 0.013313213890056156,
      "grad_norm": 2.691065788269043,
      "learning_rate": 0.00019999109695334583,
      "loss": 2.0615,
      "step": 697
    },
    {
      "epoch": 0.013332314627344615,
      "grad_norm": 2.8856863975524902,
      "learning_rate": 0.00019999107023793955,
      "loss": 1.6765,
      "step": 698
    },
    {
      "epoch": 0.013351415364633076,
      "grad_norm": 2.9722166061401367,
      "learning_rate": 0.00019999104348251257,
      "loss": 1.8353,
      "step": 699
    },
    {
      "epoch": 0.013370516101921534,
      "grad_norm": 3.3637351989746094,
      "learning_rate": 0.00019999101668706493,
      "loss": 1.3809,
      "step": 700
    },
    {
      "epoch": 0.013389616839209993,
      "grad_norm": 2.9738588333129883,
      "learning_rate": 0.00019999098985159656,
      "loss": 1.5701,
      "step": 701
    },
    {
      "epoch": 0.013408717576498454,
      "grad_norm": 2.887516736984253,
      "learning_rate": 0.00019999096297610756,
      "loss": 1.6787,
      "step": 702
    },
    {
      "epoch": 0.013427818313786912,
      "grad_norm": 2.9608116149902344,
      "learning_rate": 0.00019999093606059792,
      "loss": 1.7752,
      "step": 703
    },
    {
      "epoch": 0.013446919051075371,
      "grad_norm": 2.5908451080322266,
      "learning_rate": 0.00019999090910506758,
      "loss": 2.3363,
      "step": 704
    },
    {
      "epoch": 0.01346601978836383,
      "grad_norm": 2.981342077255249,
      "learning_rate": 0.00019999088210951666,
      "loss": 1.6005,
      "step": 705
    },
    {
      "epoch": 0.01348512052565229,
      "grad_norm": 2.515554189682007,
      "learning_rate": 0.0001999908550739451,
      "loss": 1.4265,
      "step": 706
    },
    {
      "epoch": 0.01350422126294075,
      "grad_norm": 2.872626543045044,
      "learning_rate": 0.00019999082799835295,
      "loss": 1.7518,
      "step": 707
    },
    {
      "epoch": 0.013523322000229208,
      "grad_norm": 2.5680935382843018,
      "learning_rate": 0.00019999080088274016,
      "loss": 1.4029,
      "step": 708
    },
    {
      "epoch": 0.013542422737517669,
      "grad_norm": 2.821704149246216,
      "learning_rate": 0.0001999907737271068,
      "loss": 1.5423,
      "step": 709
    },
    {
      "epoch": 0.013561523474806127,
      "grad_norm": 2.3868284225463867,
      "learning_rate": 0.00019999074653145288,
      "loss": 1.1585,
      "step": 710
    },
    {
      "epoch": 0.013580624212094586,
      "grad_norm": 2.420156717300415,
      "learning_rate": 0.0001999907192957784,
      "loss": 1.402,
      "step": 711
    },
    {
      "epoch": 0.013599724949383047,
      "grad_norm": 2.2136287689208984,
      "learning_rate": 0.00019999069202008334,
      "loss": 1.2022,
      "step": 712
    },
    {
      "epoch": 0.013618825686671505,
      "grad_norm": 2.6350796222686768,
      "learning_rate": 0.00019999066470436773,
      "loss": 1.427,
      "step": 713
    },
    {
      "epoch": 0.013637926423959964,
      "grad_norm": 3.194741725921631,
      "learning_rate": 0.0001999906373486316,
      "loss": 2.1678,
      "step": 714
    },
    {
      "epoch": 0.013657027161248425,
      "grad_norm": 2.3353493213653564,
      "learning_rate": 0.00019999060995287495,
      "loss": 1.6455,
      "step": 715
    },
    {
      "epoch": 0.013676127898536884,
      "grad_norm": 3.330263376235962,
      "learning_rate": 0.00019999058251709778,
      "loss": 1.5418,
      "step": 716
    },
    {
      "epoch": 0.013695228635825342,
      "grad_norm": 2.8708808422088623,
      "learning_rate": 0.0001999905550413001,
      "loss": 1.6586,
      "step": 717
    },
    {
      "epoch": 0.013714329373113803,
      "grad_norm": 2.7450971603393555,
      "learning_rate": 0.00019999052752548194,
      "loss": 1.5343,
      "step": 718
    },
    {
      "epoch": 0.013733430110402262,
      "grad_norm": 2.234499931335449,
      "learning_rate": 0.0001999904999696433,
      "loss": 1.707,
      "step": 719
    },
    {
      "epoch": 0.01375253084769072,
      "grad_norm": 3.541503667831421,
      "learning_rate": 0.0001999904723737842,
      "loss": 1.6933,
      "step": 720
    },
    {
      "epoch": 0.013771631584979181,
      "grad_norm": 5.775755405426025,
      "learning_rate": 0.00019999044473790467,
      "loss": 1.5715,
      "step": 721
    },
    {
      "epoch": 0.01379073232226764,
      "grad_norm": 2.597992181777954,
      "learning_rate": 0.00019999041706200466,
      "loss": 1.4911,
      "step": 722
    },
    {
      "epoch": 0.013809833059556098,
      "grad_norm": 2.5736374855041504,
      "learning_rate": 0.0001999903893460842,
      "loss": 1.6861,
      "step": 723
    },
    {
      "epoch": 0.013828933796844559,
      "grad_norm": 3.8485496044158936,
      "learning_rate": 0.00019999036159014337,
      "loss": 2.0365,
      "step": 724
    },
    {
      "epoch": 0.013848034534133018,
      "grad_norm": 3.691772699356079,
      "learning_rate": 0.0001999903337941821,
      "loss": 1.7605,
      "step": 725
    },
    {
      "epoch": 0.013867135271421476,
      "grad_norm": 2.854365825653076,
      "learning_rate": 0.0001999903059582004,
      "loss": 1.6582,
      "step": 726
    },
    {
      "epoch": 0.013886236008709937,
      "grad_norm": 2.6433026790618896,
      "learning_rate": 0.00019999027808219832,
      "loss": 1.693,
      "step": 727
    },
    {
      "epoch": 0.013905336745998396,
      "grad_norm": 2.8845293521881104,
      "learning_rate": 0.0001999902501661759,
      "loss": 1.4044,
      "step": 728
    },
    {
      "epoch": 0.013924437483286855,
      "grad_norm": 2.5835039615631104,
      "learning_rate": 0.0001999902222101331,
      "loss": 1.5204,
      "step": 729
    },
    {
      "epoch": 0.013943538220575315,
      "grad_norm": 2.991536855697632,
      "learning_rate": 0.00019999019421406992,
      "loss": 1.5921,
      "step": 730
    },
    {
      "epoch": 0.013962638957863774,
      "grad_norm": 2.737752676010132,
      "learning_rate": 0.00019999016617798637,
      "loss": 1.8646,
      "step": 731
    },
    {
      "epoch": 0.013981739695152233,
      "grad_norm": 3.373857021331787,
      "learning_rate": 0.00019999013810188254,
      "loss": 1.647,
      "step": 732
    },
    {
      "epoch": 0.014000840432440691,
      "grad_norm": 4.505081653594971,
      "learning_rate": 0.00019999010998575836,
      "loss": 1.3577,
      "step": 733
    },
    {
      "epoch": 0.014019941169729152,
      "grad_norm": 3.860342502593994,
      "learning_rate": 0.00019999008182961387,
      "loss": 1.9416,
      "step": 734
    },
    {
      "epoch": 0.01403904190701761,
      "grad_norm": 2.7709474563598633,
      "learning_rate": 0.0001999900536334491,
      "loss": 1.7685,
      "step": 735
    },
    {
      "epoch": 0.01405814264430607,
      "grad_norm": 3.0130558013916016,
      "learning_rate": 0.000199990025397264,
      "loss": 1.6192,
      "step": 736
    },
    {
      "epoch": 0.01407724338159453,
      "grad_norm": 3.5610463619232178,
      "learning_rate": 0.00019998999712105863,
      "loss": 2.1094,
      "step": 737
    },
    {
      "epoch": 0.014096344118882989,
      "grad_norm": 2.6081161499023438,
      "learning_rate": 0.00019998996880483304,
      "loss": 1.0628,
      "step": 738
    },
    {
      "epoch": 0.014115444856171448,
      "grad_norm": 2.946040630340576,
      "learning_rate": 0.00019998994044858717,
      "loss": 1.7079,
      "step": 739
    },
    {
      "epoch": 0.014134545593459908,
      "grad_norm": 3.1493520736694336,
      "learning_rate": 0.00019998991205232104,
      "loss": 1.8093,
      "step": 740
    },
    {
      "epoch": 0.014153646330748367,
      "grad_norm": 2.568794012069702,
      "learning_rate": 0.00019998988361603467,
      "loss": 1.3639,
      "step": 741
    },
    {
      "epoch": 0.014172747068036826,
      "grad_norm": 3.264702558517456,
      "learning_rate": 0.00019998985513972812,
      "loss": 1.7574,
      "step": 742
    },
    {
      "epoch": 0.014191847805325286,
      "grad_norm": 2.518845558166504,
      "learning_rate": 0.00019998982662340132,
      "loss": 1.3229,
      "step": 743
    },
    {
      "epoch": 0.014210948542613745,
      "grad_norm": 2.3984932899475098,
      "learning_rate": 0.00019998979806705434,
      "loss": 1.4818,
      "step": 744
    },
    {
      "epoch": 0.014230049279902204,
      "grad_norm": 2.1911556720733643,
      "learning_rate": 0.0001999897694706872,
      "loss": 1.9382,
      "step": 745
    },
    {
      "epoch": 0.014249150017190664,
      "grad_norm": 2.5810317993164062,
      "learning_rate": 0.00019998974083429986,
      "loss": 1.537,
      "step": 746
    },
    {
      "epoch": 0.014268250754479123,
      "grad_norm": 2.338548183441162,
      "learning_rate": 0.00019998971215789234,
      "loss": 1.7498,
      "step": 747
    },
    {
      "epoch": 0.014287351491767582,
      "grad_norm": 2.710540771484375,
      "learning_rate": 0.00019998968344146466,
      "loss": 1.7325,
      "step": 748
    },
    {
      "epoch": 0.014306452229056042,
      "grad_norm": 2.6436245441436768,
      "learning_rate": 0.00019998965468501686,
      "loss": 1.0599,
      "step": 749
    },
    {
      "epoch": 0.014325552966344501,
      "grad_norm": 2.6218113899230957,
      "learning_rate": 0.00019998962588854891,
      "loss": 1.3647,
      "step": 750
    },
    {
      "epoch": 0.01434465370363296,
      "grad_norm": 2.6935341358184814,
      "learning_rate": 0.0001999895970520609,
      "loss": 1.7228,
      "step": 751
    },
    {
      "epoch": 0.01436375444092142,
      "grad_norm": 2.800276756286621,
      "learning_rate": 0.00019998956817555272,
      "loss": 1.6139,
      "step": 752
    },
    {
      "epoch": 0.014382855178209879,
      "grad_norm": 2.588927984237671,
      "learning_rate": 0.00019998953925902448,
      "loss": 1.4193,
      "step": 753
    },
    {
      "epoch": 0.014401955915498338,
      "grad_norm": 2.408782482147217,
      "learning_rate": 0.00019998951030247614,
      "loss": 1.499,
      "step": 754
    },
    {
      "epoch": 0.014421056652786798,
      "grad_norm": 3.665207624435425,
      "learning_rate": 0.00019998948130590773,
      "loss": 1.8768,
      "step": 755
    },
    {
      "epoch": 0.014440157390075257,
      "grad_norm": 2.7714574337005615,
      "learning_rate": 0.00019998945226931927,
      "loss": 1.844,
      "step": 756
    },
    {
      "epoch": 0.014459258127363716,
      "grad_norm": 2.762695074081421,
      "learning_rate": 0.00019998942319271077,
      "loss": 1.8143,
      "step": 757
    },
    {
      "epoch": 0.014478358864652175,
      "grad_norm": 2.9843015670776367,
      "learning_rate": 0.0001999893940760822,
      "loss": 1.9315,
      "step": 758
    },
    {
      "epoch": 0.014497459601940635,
      "grad_norm": 2.5618374347686768,
      "learning_rate": 0.00019998936491943362,
      "loss": 1.4166,
      "step": 759
    },
    {
      "epoch": 0.014516560339229094,
      "grad_norm": 2.5571842193603516,
      "learning_rate": 0.00019998933572276504,
      "loss": 1.7608,
      "step": 760
    },
    {
      "epoch": 0.014535661076517553,
      "grad_norm": 2.283684015274048,
      "learning_rate": 0.00019998930648607645,
      "loss": 1.6089,
      "step": 761
    },
    {
      "epoch": 0.014554761813806013,
      "grad_norm": 2.8148903846740723,
      "learning_rate": 0.0001999892772093679,
      "loss": 2.0328,
      "step": 762
    },
    {
      "epoch": 0.014573862551094472,
      "grad_norm": 1.9580574035644531,
      "learning_rate": 0.0001999892478926393,
      "loss": 2.1421,
      "step": 763
    },
    {
      "epoch": 0.01459296328838293,
      "grad_norm": 2.185143232345581,
      "learning_rate": 0.0001999892185358908,
      "loss": 1.8849,
      "step": 764
    },
    {
      "epoch": 0.014612064025671391,
      "grad_norm": 1.8924754858016968,
      "learning_rate": 0.0001999891891391223,
      "loss": 1.6162,
      "step": 765
    },
    {
      "epoch": 0.01463116476295985,
      "grad_norm": 2.555217742919922,
      "learning_rate": 0.00019998915970233388,
      "loss": 1.636,
      "step": 766
    },
    {
      "epoch": 0.014650265500248309,
      "grad_norm": 2.7078351974487305,
      "learning_rate": 0.0001999891302255255,
      "loss": 1.7432,
      "step": 767
    },
    {
      "epoch": 0.01466936623753677,
      "grad_norm": 2.237368106842041,
      "learning_rate": 0.00019998910070869724,
      "loss": 1.4121,
      "step": 768
    },
    {
      "epoch": 0.014688466974825228,
      "grad_norm": 2.7987027168273926,
      "learning_rate": 0.00019998907115184906,
      "loss": 2.0102,
      "step": 769
    },
    {
      "epoch": 0.014707567712113687,
      "grad_norm": 1.9199455976486206,
      "learning_rate": 0.000199989041554981,
      "loss": 1.253,
      "step": 770
    },
    {
      "epoch": 0.014726668449402147,
      "grad_norm": 2.3375496864318848,
      "learning_rate": 0.00019998901191809303,
      "loss": 1.4095,
      "step": 771
    },
    {
      "epoch": 0.014745769186690606,
      "grad_norm": 2.8408284187316895,
      "learning_rate": 0.00019998898224118518,
      "loss": 1.7115,
      "step": 772
    },
    {
      "epoch": 0.014764869923979065,
      "grad_norm": 2.243790864944458,
      "learning_rate": 0.00019998895252425748,
      "loss": 1.3211,
      "step": 773
    },
    {
      "epoch": 0.014783970661267526,
      "grad_norm": 3.4616260528564453,
      "learning_rate": 0.00019998892276730995,
      "loss": 1.954,
      "step": 774
    },
    {
      "epoch": 0.014803071398555984,
      "grad_norm": 3.197127103805542,
      "learning_rate": 0.00019998889297034256,
      "loss": 2.0215,
      "step": 775
    },
    {
      "epoch": 0.014822172135844443,
      "grad_norm": 2.870364189147949,
      "learning_rate": 0.00019998886313335535,
      "loss": 1.6413,
      "step": 776
    },
    {
      "epoch": 0.014841272873132904,
      "grad_norm": 2.777554512023926,
      "learning_rate": 0.00019998883325634834,
      "loss": 1.6414,
      "step": 777
    },
    {
      "epoch": 0.014860373610421362,
      "grad_norm": 2.4237184524536133,
      "learning_rate": 0.00019998880333932153,
      "loss": 1.2707,
      "step": 778
    },
    {
      "epoch": 0.014879474347709821,
      "grad_norm": 3.1750295162200928,
      "learning_rate": 0.0001999887733822749,
      "loss": 1.6912,
      "step": 779
    },
    {
      "epoch": 0.014898575084998282,
      "grad_norm": 2.8074100017547607,
      "learning_rate": 0.00019998874338520852,
      "loss": 1.7729,
      "step": 780
    },
    {
      "epoch": 0.01491767582228674,
      "grad_norm": 4.077731132507324,
      "learning_rate": 0.00019998871334812236,
      "loss": 1.8243,
      "step": 781
    },
    {
      "epoch": 0.0149367765595752,
      "grad_norm": 3.0560433864593506,
      "learning_rate": 0.00019998868327101646,
      "loss": 1.4738,
      "step": 782
    },
    {
      "epoch": 0.01495587729686366,
      "grad_norm": 2.305824041366577,
      "learning_rate": 0.00019998865315389082,
      "loss": 1.2202,
      "step": 783
    },
    {
      "epoch": 0.014974978034152119,
      "grad_norm": 3.0948402881622314,
      "learning_rate": 0.00019998862299674546,
      "loss": 1.5797,
      "step": 784
    },
    {
      "epoch": 0.014994078771440577,
      "grad_norm": 3.118197202682495,
      "learning_rate": 0.00019998859279958038,
      "loss": 1.4426,
      "step": 785
    },
    {
      "epoch": 0.015013179508729036,
      "grad_norm": 2.7309913635253906,
      "learning_rate": 0.00019998856256239558,
      "loss": 2.2082,
      "step": 786
    },
    {
      "epoch": 0.015032280246017497,
      "grad_norm": 3.408578872680664,
      "learning_rate": 0.00019998853228519109,
      "loss": 1.7374,
      "step": 787
    },
    {
      "epoch": 0.015051380983305955,
      "grad_norm": 3.5563881397247314,
      "learning_rate": 0.00019998850196796693,
      "loss": 1.7934,
      "step": 788
    },
    {
      "epoch": 0.015070481720594414,
      "grad_norm": 2.4586527347564697,
      "learning_rate": 0.00019998847161072306,
      "loss": 1.5502,
      "step": 789
    },
    {
      "epoch": 0.015089582457882875,
      "grad_norm": 2.817995309829712,
      "learning_rate": 0.0001999884412134596,
      "loss": 2.0213,
      "step": 790
    },
    {
      "epoch": 0.015108683195171333,
      "grad_norm": 3.212003469467163,
      "learning_rate": 0.00019998841077617648,
      "loss": 1.5462,
      "step": 791
    },
    {
      "epoch": 0.015127783932459792,
      "grad_norm": 2.7965571880340576,
      "learning_rate": 0.0001999883802988737,
      "loss": 1.2179,
      "step": 792
    },
    {
      "epoch": 0.015146884669748253,
      "grad_norm": 2.597515821456909,
      "learning_rate": 0.0001999883497815513,
      "loss": 1.4296,
      "step": 793
    },
    {
      "epoch": 0.015165985407036712,
      "grad_norm": 3.3041131496429443,
      "learning_rate": 0.0001999883192242093,
      "loss": 1.4494,
      "step": 794
    },
    {
      "epoch": 0.01518508614432517,
      "grad_norm": 2.613602638244629,
      "learning_rate": 0.00019998828862684772,
      "loss": 1.7081,
      "step": 795
    },
    {
      "epoch": 0.01520418688161363,
      "grad_norm": 3.0008580684661865,
      "learning_rate": 0.00019998825798946658,
      "loss": 1.8633,
      "step": 796
    },
    {
      "epoch": 0.01522328761890209,
      "grad_norm": 2.2705130577087402,
      "learning_rate": 0.0001999882273120658,
      "loss": 1.3902,
      "step": 797
    },
    {
      "epoch": 0.015242388356190548,
      "grad_norm": 4.293129920959473,
      "learning_rate": 0.00019998819659464552,
      "loss": 1.7738,
      "step": 798
    },
    {
      "epoch": 0.015261489093479009,
      "grad_norm": 3.421990394592285,
      "learning_rate": 0.00019998816583720569,
      "loss": 2.0584,
      "step": 799
    },
    {
      "epoch": 0.015280589830767468,
      "grad_norm": 2.9595751762390137,
      "learning_rate": 0.0001999881350397463,
      "loss": 1.6772,
      "step": 800
    },
    {
      "epoch": 0.015280589830767468,
      "eval_loss": 1.6139286756515503,
      "eval_runtime": 316.5229,
      "eval_samples_per_second": 3.327,
      "eval_steps_per_second": 3.327,
      "step": 800
    }
  ],
  "logging_steps": 1,
  "max_steps": 157062,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0842795665679974e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}