{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05859375,
  "eval_steps": 500,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.765625e-05,
      "grad_norm": 79.3869857788086,
      "learning_rate": 3.3333333333333337e-06,
      "loss": 7.7773,
      "step": 1
    },
    {
      "epoch": 0.0001953125,
      "grad_norm": 80.6998291015625,
      "learning_rate": 6.6666666666666675e-06,
      "loss": 7.7617,
      "step": 2
    },
    {
      "epoch": 0.00029296875,
      "grad_norm": 67.86173248291016,
      "learning_rate": 1e-05,
      "loss": 7.6523,
      "step": 3
    },
    {
      "epoch": 0.000390625,
      "grad_norm": 31.295886993408203,
      "learning_rate": 1.3333333333333335e-05,
      "loss": 7.3242,
      "step": 4
    },
    {
      "epoch": 0.00048828125,
      "grad_norm": 27.488962173461914,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 7.2773,
      "step": 5
    },
    {
      "epoch": 0.0005859375,
      "grad_norm": 16.267820358276367,
      "learning_rate": 2e-05,
      "loss": 7.1641,
      "step": 6
    },
    {
      "epoch": 0.00068359375,
      "grad_norm": 37.23747253417969,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 7.2812,
      "step": 7
    },
    {
      "epoch": 0.00078125,
      "grad_norm": 17.467384338378906,
      "learning_rate": 2.666666666666667e-05,
      "loss": 7.0508,
      "step": 8
    },
    {
      "epoch": 0.00087890625,
      "grad_norm": 9.459285736083984,
      "learning_rate": 3e-05,
      "loss": 6.9375,
      "step": 9
    },
    {
      "epoch": 0.0009765625,
      "grad_norm": 8.56839656829834,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 6.8789,
      "step": 10
    },
    {
      "epoch": 0.00107421875,
      "grad_norm": 24.074443817138672,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 6.8672,
      "step": 11
    },
    {
      "epoch": 0.001171875,
      "grad_norm": 11.778696060180664,
      "learning_rate": 4e-05,
      "loss": 6.7969,
      "step": 12
    },
    {
      "epoch": 0.00126953125,
      "grad_norm": 14.282492637634277,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 6.8047,
      "step": 13
    },
    {
      "epoch": 0.0013671875,
      "grad_norm": 8.801307678222656,
      "learning_rate": 4.666666666666667e-05,
      "loss": 6.7188,
      "step": 14
    },
    {
      "epoch": 0.00146484375,
      "grad_norm": 8.514760971069336,
      "learning_rate": 5e-05,
      "loss": 6.7148,
      "step": 15
    },
    {
      "epoch": 0.0015625,
      "grad_norm": 9.48074722290039,
      "learning_rate": 5.333333333333334e-05,
      "loss": 6.6641,
      "step": 16
    },
    {
      "epoch": 0.00166015625,
      "grad_norm": 7.557260036468506,
      "learning_rate": 5.6666666666666664e-05,
      "loss": 6.6172,
      "step": 17
    },
    {
      "epoch": 0.0017578125,
      "grad_norm": 6.613265037536621,
      "learning_rate": 6e-05,
      "loss": 6.5977,
      "step": 18
    },
    {
      "epoch": 0.00185546875,
      "grad_norm": 13.777167320251465,
      "learning_rate": 6.333333333333335e-05,
      "loss": 6.6328,
      "step": 19
    },
    {
      "epoch": 0.001953125,
      "grad_norm": 6.775121688842773,
      "learning_rate": 6.666666666666667e-05,
      "loss": 6.5391,
      "step": 20
    },
    {
      "epoch": 0.00205078125,
      "grad_norm": 9.053375244140625,
      "learning_rate": 7.000000000000001e-05,
      "loss": 6.543,
      "step": 21
    },
    {
      "epoch": 0.0021484375,
      "grad_norm": 5.147669792175293,
      "learning_rate": 7.333333333333333e-05,
      "loss": 6.5039,
      "step": 22
    },
    {
      "epoch": 0.00224609375,
      "grad_norm": 9.595170974731445,
      "learning_rate": 7.666666666666667e-05,
      "loss": 6.5,
      "step": 23
    },
    {
      "epoch": 0.00234375,
      "grad_norm": 6.9720964431762695,
      "learning_rate": 8e-05,
      "loss": 6.4883,
      "step": 24
    },
    {
      "epoch": 0.00244140625,
      "grad_norm": 9.805245399475098,
      "learning_rate": 8.333333333333333e-05,
      "loss": 6.4414,
      "step": 25
    },
    {
      "epoch": 0.0025390625,
      "grad_norm": 5.9478044509887695,
      "learning_rate": 8.666666666666667e-05,
      "loss": 6.4297,
      "step": 26
    },
    {
      "epoch": 0.00263671875,
      "grad_norm": 8.962249755859375,
      "learning_rate": 8.999999999999999e-05,
      "loss": 6.4297,
      "step": 27
    },
    {
      "epoch": 0.002734375,
      "grad_norm": 5.202462673187256,
      "learning_rate": 9.333333333333334e-05,
      "loss": 6.375,
      "step": 28
    },
    {
      "epoch": 0.00283203125,
      "grad_norm": 5.034671306610107,
      "learning_rate": 9.666666666666667e-05,
      "loss": 6.3555,
      "step": 29
    },
    {
      "epoch": 0.0029296875,
      "grad_norm": 7.446832656860352,
      "learning_rate": 0.0001,
      "loss": 6.3477,
      "step": 30
    },
    {
      "epoch": 0.00302734375,
      "grad_norm": 5.554169654846191,
      "learning_rate": 0.00010333333333333333,
      "loss": 6.3086,
      "step": 31
    },
    {
      "epoch": 0.003125,
      "grad_norm": 5.340260028839111,
      "learning_rate": 0.00010666666666666668,
      "loss": 6.293,
      "step": 32
    },
    {
      "epoch": 0.00322265625,
      "grad_norm": 6.529757976531982,
      "learning_rate": 0.00011,
      "loss": 6.2812,
      "step": 33
    },
    {
      "epoch": 0.0033203125,
      "grad_norm": 8.140447616577148,
      "learning_rate": 0.00011333333333333333,
      "loss": 6.2656,
      "step": 34
    },
    {
      "epoch": 0.00341796875,
      "grad_norm": 5.15455961227417,
      "learning_rate": 0.00011666666666666667,
      "loss": 6.2266,
      "step": 35
    },
    {
      "epoch": 0.003515625,
      "grad_norm": 7.219542980194092,
      "learning_rate": 0.00012,
      "loss": 6.2539,
      "step": 36
    },
    {
      "epoch": 0.00361328125,
      "grad_norm": 5.522006988525391,
      "learning_rate": 0.00012333333333333334,
      "loss": 6.2305,
      "step": 37
    },
    {
      "epoch": 0.0037109375,
      "grad_norm": 4.108240127563477,
      "learning_rate": 0.0001266666666666667,
      "loss": 6.2109,
      "step": 38
    },
    {
      "epoch": 0.00380859375,
      "grad_norm": 5.117391586303711,
      "learning_rate": 0.00013000000000000002,
      "loss": 6.1992,
      "step": 39
    },
    {
      "epoch": 0.00390625,
      "grad_norm": 9.84037971496582,
      "learning_rate": 0.00013333333333333334,
      "loss": 6.2227,
      "step": 40
    },
    {
      "epoch": 0.00400390625,
      "grad_norm": 5.794247150421143,
      "learning_rate": 0.00013666666666666666,
      "loss": 6.1953,
      "step": 41
    },
    {
      "epoch": 0.0041015625,
      "grad_norm": 5.9350810050964355,
      "learning_rate": 0.00014000000000000001,
      "loss": 6.1836,
      "step": 42
    },
    {
      "epoch": 0.00419921875,
      "grad_norm": 6.219013214111328,
      "learning_rate": 0.00014333333333333334,
      "loss": 6.168,
      "step": 43
    },
    {
      "epoch": 0.004296875,
      "grad_norm": 4.501729488372803,
      "learning_rate": 0.00014666666666666666,
      "loss": 6.1055,
      "step": 44
    },
    {
      "epoch": 0.00439453125,
      "grad_norm": 6.2689948081970215,
      "learning_rate": 0.00015,
      "loss": 6.1328,
      "step": 45
    },
    {
      "epoch": 0.0044921875,
      "grad_norm": 4.54839563369751,
      "learning_rate": 0.00015333333333333334,
      "loss": 6.1055,
      "step": 46
    },
    {
      "epoch": 0.00458984375,
      "grad_norm": 4.619740009307861,
      "learning_rate": 0.0001566666666666667,
      "loss": 6.082,
      "step": 47
    },
    {
      "epoch": 0.0046875,
      "grad_norm": 7.260074615478516,
      "learning_rate": 0.00016,
      "loss": 6.0938,
      "step": 48
    },
    {
      "epoch": 0.00478515625,
      "grad_norm": 5.270298480987549,
      "learning_rate": 0.00016333333333333334,
      "loss": 6.0859,
      "step": 49
    },
    {
      "epoch": 0.0048828125,
      "grad_norm": 6.634472846984863,
      "learning_rate": 0.00016666666666666666,
      "loss": 6.0625,
      "step": 50
    },
    {
      "epoch": 0.00498046875,
      "grad_norm": 4.172934532165527,
      "learning_rate": 0.00017,
      "loss": 6.0469,
      "step": 51
    },
    {
      "epoch": 0.005078125,
      "grad_norm": 5.719873905181885,
      "learning_rate": 0.00017333333333333334,
      "loss": 6.0273,
      "step": 52
    },
    {
      "epoch": 0.00517578125,
      "grad_norm": 4.851602554321289,
      "learning_rate": 0.00017666666666666666,
      "loss": 6.0234,
      "step": 53
    },
    {
      "epoch": 0.0052734375,
      "grad_norm": 4.784290313720703,
      "learning_rate": 0.00017999999999999998,
      "loss": 5.9883,
      "step": 54
    },
    {
      "epoch": 0.00537109375,
      "grad_norm": 5.738783359527588,
      "learning_rate": 0.00018333333333333334,
      "loss": 6.0078,
      "step": 55
    },
    {
      "epoch": 0.00546875,
      "grad_norm": 4.525517463684082,
      "learning_rate": 0.0001866666666666667,
      "loss": 5.9844,
      "step": 56
    },
    {
      "epoch": 0.00556640625,
      "grad_norm": 5.545010566711426,
      "learning_rate": 0.00019,
      "loss": 6.0078,
      "step": 57
    },
    {
      "epoch": 0.0056640625,
      "grad_norm": 5.725442409515381,
      "learning_rate": 0.00019333333333333333,
      "loss": 5.9688,
      "step": 58
    },
    {
      "epoch": 0.00576171875,
      "grad_norm": 4.413902282714844,
      "learning_rate": 0.00019666666666666666,
      "loss": 5.9414,
      "step": 59
    },
    {
      "epoch": 0.005859375,
      "grad_norm": 4.734899520874023,
      "learning_rate": 0.0002,
      "loss": 5.9609,
      "step": 60
    },
    {
      "epoch": 0.00595703125,
      "grad_norm": 4.493259906768799,
      "learning_rate": 0.00020333333333333333,
      "loss": 5.9648,
      "step": 61
    },
    {
      "epoch": 0.0060546875,
      "grad_norm": 4.654330253601074,
      "learning_rate": 0.00020666666666666666,
      "loss": 5.957,
      "step": 62
    },
    {
      "epoch": 0.00615234375,
      "grad_norm": 5.410141944885254,
      "learning_rate": 0.00021,
      "loss": 5.9766,
      "step": 63
    },
    {
      "epoch": 0.00625,
      "grad_norm": 3.376593589782715,
      "learning_rate": 0.00021333333333333336,
      "loss": 5.9062,
      "step": 64
    },
    {
      "epoch": 0.00634765625,
      "grad_norm": 5.334528923034668,
      "learning_rate": 0.00021666666666666668,
      "loss": 5.9141,
      "step": 65
    },
    {
      "epoch": 0.0064453125,
      "grad_norm": 4.844014644622803,
      "learning_rate": 0.00022,
      "loss": 5.9062,
      "step": 66
    },
    {
      "epoch": 0.00654296875,
      "grad_norm": 4.3729939460754395,
      "learning_rate": 0.00022333333333333333,
      "loss": 5.9023,
      "step": 67
    },
    {
      "epoch": 0.006640625,
      "grad_norm": 6.744809627532959,
      "learning_rate": 0.00022666666666666666,
      "loss": 5.9648,
      "step": 68
    },
    {
      "epoch": 0.00673828125,
      "grad_norm": 4.010498046875,
      "learning_rate": 0.00023,
      "loss": 5.8945,
      "step": 69
    },
    {
      "epoch": 0.0068359375,
      "grad_norm": 5.671877384185791,
      "learning_rate": 0.00023333333333333333,
      "loss": 5.9414,
      "step": 70
    },
    {
      "epoch": 0.00693359375,
      "grad_norm": 3.9647581577301025,
      "learning_rate": 0.00023666666666666668,
      "loss": 5.8672,
      "step": 71
    },
    {
      "epoch": 0.00703125,
      "grad_norm": 4.879064083099365,
      "learning_rate": 0.00024,
      "loss": 5.8672,
      "step": 72
    },
    {
      "epoch": 0.00712890625,
      "grad_norm": 5.130377292633057,
      "learning_rate": 0.00024333333333333336,
      "loss": 5.8711,
      "step": 73
    },
    {
      "epoch": 0.0072265625,
      "grad_norm": 5.8605122566223145,
      "learning_rate": 0.0002466666666666667,
      "loss": 5.875,
      "step": 74
    },
    {
      "epoch": 0.00732421875,
      "grad_norm": 5.346503257751465,
      "learning_rate": 0.00025,
      "loss": 5.9023,
      "step": 75
    },
    {
      "epoch": 0.007421875,
      "grad_norm": 5.273228645324707,
      "learning_rate": 0.0002533333333333334,
      "loss": 5.8867,
      "step": 76
    },
    {
      "epoch": 0.00751953125,
      "grad_norm": 3.8530828952789307,
      "learning_rate": 0.00025666666666666665,
      "loss": 5.8477,
      "step": 77
    },
    {
      "epoch": 0.0076171875,
      "grad_norm": 5.188773155212402,
      "learning_rate": 0.00026000000000000003,
      "loss": 5.8633,
      "step": 78
    },
    {
      "epoch": 0.00771484375,
      "grad_norm": 3.4620485305786133,
      "learning_rate": 0.0002633333333333333,
      "loss": 5.8398,
      "step": 79
    },
    {
      "epoch": 0.0078125,
      "grad_norm": 4.68696403503418,
      "learning_rate": 0.0002666666666666667,
      "loss": 5.8359,
      "step": 80
    },
    {
      "epoch": 0.00791015625,
      "grad_norm": 4.243693828582764,
      "learning_rate": 0.00027,
      "loss": 5.8555,
      "step": 81
    },
    {
      "epoch": 0.0080078125,
      "grad_norm": 5.6479363441467285,
      "learning_rate": 0.00027333333333333333,
      "loss": 5.832,
      "step": 82
    },
    {
      "epoch": 0.00810546875,
      "grad_norm": 3.7417171001434326,
      "learning_rate": 0.00027666666666666665,
      "loss": 5.8281,
      "step": 83
    },
    {
      "epoch": 0.008203125,
      "grad_norm": 4.857771873474121,
      "learning_rate": 0.00028000000000000003,
      "loss": 5.8086,
      "step": 84
    },
    {
      "epoch": 0.00830078125,
      "grad_norm": 4.6594085693359375,
      "learning_rate": 0.00028333333333333335,
      "loss": 5.832,
      "step": 85
    },
    {
      "epoch": 0.0083984375,
      "grad_norm": 4.48290491104126,
      "learning_rate": 0.0002866666666666667,
      "loss": 5.8164,
      "step": 86
    },
    {
      "epoch": 0.00849609375,
      "grad_norm": 6.183064937591553,
      "learning_rate": 0.00029,
      "loss": 5.8398,
      "step": 87
    },
    {
      "epoch": 0.00859375,
      "grad_norm": 4.494201183319092,
      "learning_rate": 0.0002933333333333333,
      "loss": 5.7969,
      "step": 88
    },
    {
      "epoch": 0.00869140625,
      "grad_norm": 5.650720596313477,
      "learning_rate": 0.0002966666666666667,
      "loss": 5.8438,
      "step": 89
    },
    {
      "epoch": 0.0087890625,
      "grad_norm": 5.558387756347656,
      "learning_rate": 0.0003,
      "loss": 5.8555,
      "step": 90
    },
    {
      "epoch": 0.00888671875,
      "grad_norm": 5.16208553314209,
      "learning_rate": 0.00030333333333333335,
      "loss": 5.8086,
      "step": 91
    },
    {
      "epoch": 0.008984375,
      "grad_norm": 6.598042964935303,
      "learning_rate": 0.0003066666666666667,
      "loss": 5.8516,
      "step": 92
    },
    {
      "epoch": 0.00908203125,
      "grad_norm": 4.591591835021973,
      "learning_rate": 0.00031,
      "loss": 5.8555,
      "step": 93
    },
    {
      "epoch": 0.0091796875,
      "grad_norm": 4.879761695861816,
      "learning_rate": 0.0003133333333333334,
      "loss": 5.8203,
      "step": 94
    },
    {
      "epoch": 0.00927734375,
      "grad_norm": 5.21987771987915,
      "learning_rate": 0.00031666666666666665,
      "loss": 5.8203,
      "step": 95
    },
    {
      "epoch": 0.009375,
      "grad_norm": 4.257232666015625,
      "learning_rate": 0.00032,
      "loss": 5.8047,
      "step": 96
    },
    {
      "epoch": 0.00947265625,
      "grad_norm": 6.07011604309082,
      "learning_rate": 0.0003233333333333333,
      "loss": 5.8359,
      "step": 97
    },
    {
      "epoch": 0.0095703125,
      "grad_norm": 5.662813186645508,
      "learning_rate": 0.0003266666666666667,
      "loss": 5.8633,
      "step": 98
    },
    {
      "epoch": 0.00966796875,
      "grad_norm": 4.59433650970459,
      "learning_rate": 0.00033,
      "loss": 5.8086,
      "step": 99
    },
    {
      "epoch": 0.009765625,
      "grad_norm": 4.295780181884766,
      "learning_rate": 0.0003333333333333333,
      "loss": 5.8008,
      "step": 100
    },
    {
      "epoch": 0.00986328125,
      "grad_norm": 4.587396144866943,
      "learning_rate": 0.0003366666666666667,
      "loss": 5.8008,
      "step": 101
    },
    {
      "epoch": 0.0099609375,
      "grad_norm": 4.299502849578857,
      "learning_rate": 0.00034,
      "loss": 5.7773,
      "step": 102
    },
    {
      "epoch": 0.01005859375,
      "grad_norm": 4.284260272979736,
      "learning_rate": 0.00034333333333333335,
      "loss": 5.793,
      "step": 103
    },
    {
      "epoch": 0.01015625,
      "grad_norm": 6.048828601837158,
      "learning_rate": 0.00034666666666666667,
      "loss": 5.8008,
      "step": 104
    },
    {
      "epoch": 0.01025390625,
      "grad_norm": 4.235161304473877,
      "learning_rate": 0.00035,
      "loss": 5.7656,
      "step": 105
    },
    {
      "epoch": 0.0103515625,
      "grad_norm": 5.187899589538574,
      "learning_rate": 0.0003533333333333333,
      "loss": 5.8125,
      "step": 106
    },
    {
      "epoch": 0.01044921875,
      "grad_norm": 4.133037567138672,
      "learning_rate": 0.0003566666666666667,
      "loss": 5.8047,
      "step": 107
    },
    {
      "epoch": 0.010546875,
      "grad_norm": 5.822926044464111,
      "learning_rate": 0.00035999999999999997,
      "loss": 5.8281,
      "step": 108
    },
    {
      "epoch": 0.01064453125,
      "grad_norm": 4.3357672691345215,
      "learning_rate": 0.00036333333333333335,
      "loss": 5.7734,
      "step": 109
    },
    {
      "epoch": 0.0107421875,
      "grad_norm": 4.930606842041016,
      "learning_rate": 0.00036666666666666667,
      "loss": 5.7812,
      "step": 110
    },
    {
      "epoch": 0.01083984375,
      "grad_norm": 4.797028064727783,
      "learning_rate": 0.00037,
      "loss": 5.7695,
      "step": 111
    },
    {
      "epoch": 0.0109375,
      "grad_norm": 3.1973586082458496,
      "learning_rate": 0.0003733333333333334,
      "loss": 5.7539,
      "step": 112
    },
    {
      "epoch": 0.01103515625,
      "grad_norm": 4.5399980545043945,
      "learning_rate": 0.00037666666666666664,
      "loss": 5.7852,
      "step": 113
    },
    {
      "epoch": 0.0111328125,
      "grad_norm": 4.550619602203369,
      "learning_rate": 0.00038,
      "loss": 5.7773,
      "step": 114
    },
    {
      "epoch": 0.01123046875,
      "grad_norm": 5.377904415130615,
      "learning_rate": 0.00038333333333333334,
      "loss": 5.7891,
      "step": 115
    },
    {
      "epoch": 0.011328125,
      "grad_norm": 4.06483268737793,
      "learning_rate": 0.00038666666666666667,
      "loss": 5.6992,
      "step": 116
    },
    {
      "epoch": 0.01142578125,
      "grad_norm": 3.8046791553497314,
      "learning_rate": 0.00039000000000000005,
      "loss": 5.7344,
      "step": 117
    },
    {
      "epoch": 0.0115234375,
      "grad_norm": 4.709420204162598,
      "learning_rate": 0.0003933333333333333,
      "loss": 5.7461,
      "step": 118
    },
    {
      "epoch": 0.01162109375,
      "grad_norm": 4.36158561706543,
      "learning_rate": 0.0003966666666666667,
      "loss": 5.75,
      "step": 119
    },
    {
      "epoch": 0.01171875,
      "grad_norm": 4.972657680511475,
      "learning_rate": 0.0004,
      "loss": 5.7188,
      "step": 120
    },
    {
      "epoch": 0.01181640625,
      "grad_norm": 3.862230062484741,
      "learning_rate": 0.00040333333333333334,
      "loss": 5.7617,
      "step": 121
    },
    {
      "epoch": 0.0119140625,
      "grad_norm": 6.694273948669434,
      "learning_rate": 0.00040666666666666667,
      "loss": 5.7734,
      "step": 122
    },
    {
      "epoch": 0.01201171875,
      "grad_norm": 4.289857864379883,
      "learning_rate": 0.00041,
      "loss": 5.7539,
      "step": 123
    },
    {
      "epoch": 0.012109375,
      "grad_norm": 4.241764545440674,
      "learning_rate": 0.0004133333333333333,
      "loss": 5.7422,
      "step": 124
    },
    {
      "epoch": 0.01220703125,
      "grad_norm": 5.350276947021484,
      "learning_rate": 0.0004166666666666667,
      "loss": 5.7578,
      "step": 125
    },
    {
      "epoch": 0.0123046875,
      "grad_norm": 4.058553695678711,
      "learning_rate": 0.00042,
      "loss": 5.6992,
      "step": 126
    },
    {
      "epoch": 0.01240234375,
      "grad_norm": 4.70885705947876,
      "learning_rate": 0.00042333333333333334,
      "loss": 5.7383,
      "step": 127
    },
    {
      "epoch": 0.0125,
      "grad_norm": 4.190490245819092,
      "learning_rate": 0.0004266666666666667,
      "loss": 5.7305,
      "step": 128
    },
    {
      "epoch": 0.01259765625,
      "grad_norm": 6.176610469818115,
      "learning_rate": 0.00043,
      "loss": 5.7344,
      "step": 129
    },
    {
      "epoch": 0.0126953125,
      "grad_norm": 4.583580017089844,
      "learning_rate": 0.00043333333333333337,
      "loss": 5.7266,
      "step": 130
    },
    {
      "epoch": 0.01279296875,
      "grad_norm": 3.8871593475341797,
      "learning_rate": 0.00043666666666666664,
      "loss": 5.7422,
      "step": 131
    },
    {
      "epoch": 0.012890625,
      "grad_norm": 6.952763557434082,
      "learning_rate": 0.00044,
      "loss": 5.7812,
      "step": 132
    },
    {
      "epoch": 0.01298828125,
      "grad_norm": 4.236309051513672,
      "learning_rate": 0.00044333333333333334,
      "loss": 5.75,
      "step": 133
    },
    {
      "epoch": 0.0130859375,
      "grad_norm": 7.308345794677734,
      "learning_rate": 0.00044666666666666666,
      "loss": 5.8125,
      "step": 134
    },
    {
      "epoch": 0.01318359375,
      "grad_norm": 8.599268913269043,
      "learning_rate": 0.00045000000000000004,
      "loss": 5.918,
      "step": 135
    },
    {
      "epoch": 0.01328125,
      "grad_norm": 4.937841415405273,
      "learning_rate": 0.0004533333333333333,
      "loss": 5.8242,
      "step": 136
    },
    {
      "epoch": 0.01337890625,
      "grad_norm": 4.781856536865234,
      "learning_rate": 0.0004566666666666667,
      "loss": 5.7891,
      "step": 137
    },
    {
      "epoch": 0.0134765625,
      "grad_norm": 7.261330604553223,
      "learning_rate": 0.00046,
      "loss": 5.8203,
      "step": 138
    },
    {
      "epoch": 0.01357421875,
      "grad_norm": 5.891605854034424,
      "learning_rate": 0.00046333333333333334,
      "loss": 5.875,
      "step": 139
    },
    {
      "epoch": 0.013671875,
      "grad_norm": 7.775816440582275,
      "learning_rate": 0.00046666666666666666,
      "loss": 5.8672,
      "step": 140
    },
    {
      "epoch": 0.01376953125,
      "grad_norm": 3.8871777057647705,
      "learning_rate": 0.00047,
      "loss": 5.8359,
      "step": 141
    },
    {
      "epoch": 0.0138671875,
      "grad_norm": 5.772259712219238,
      "learning_rate": 0.00047333333333333336,
      "loss": 5.8477,
      "step": 142
    },
    {
      "epoch": 0.01396484375,
      "grad_norm": 4.485783100128174,
      "learning_rate": 0.0004766666666666667,
      "loss": 5.793,
      "step": 143
    },
    {
      "epoch": 0.0140625,
      "grad_norm": 4.418201446533203,
      "learning_rate": 0.00048,
      "loss": 5.7812,
      "step": 144
    },
    {
      "epoch": 0.01416015625,
      "grad_norm": 7.3408074378967285,
      "learning_rate": 0.00048333333333333334,
      "loss": 5.8516,
      "step": 145
    },
    {
      "epoch": 0.0142578125,
      "grad_norm": 5.989964962005615,
      "learning_rate": 0.0004866666666666667,
      "loss": 5.8945,
      "step": 146
    },
    {
      "epoch": 0.01435546875,
      "grad_norm": 4.477835655212402,
      "learning_rate": 0.00049,
      "loss": 5.8477,
      "step": 147
    },
    {
      "epoch": 0.014453125,
      "grad_norm": 6.493783950805664,
      "learning_rate": 0.0004933333333333334,
      "loss": 5.8594,
      "step": 148
    },
    {
      "epoch": 0.01455078125,
      "grad_norm": 6.190314292907715,
      "learning_rate": 0.0004966666666666666,
      "loss": 5.8906,
      "step": 149
    },
    {
      "epoch": 0.0146484375,
      "grad_norm": 6.708803653717041,
      "learning_rate": 0.0005,
      "loss": 5.8711,
      "step": 150
    },
    {
      "epoch": 0.01474609375,
      "grad_norm": 5.7710113525390625,
      "learning_rate": 0.0004999999890938886,
      "loss": 5.8633,
      "step": 151
    },
    {
      "epoch": 0.01484375,
      "grad_norm": 5.553577899932861,
      "learning_rate": 0.0004999999563755552,
      "loss": 5.8594,
      "step": 152
    },
    {
      "epoch": 0.01494140625,
      "grad_norm": 4.852464199066162,
      "learning_rate": 0.0004999999018450032,
      "loss": 5.8555,
      "step": 153
    },
    {
      "epoch": 0.0150390625,
      "grad_norm": 4.127274990081787,
      "learning_rate": 0.0004999998255022377,
      "loss": 5.793,
      "step": 154
    },
    {
      "epoch": 0.01513671875,
      "grad_norm": 5.139339923858643,
      "learning_rate": 0.0004999997273472664,
      "loss": 5.8398,
      "step": 155
    },
    {
      "epoch": 0.015234375,
      "grad_norm": 3.9165873527526855,
      "learning_rate": 0.0004999996073800985,
      "loss": 5.7852,
      "step": 156
    },
    {
      "epoch": 0.01533203125,
      "grad_norm": 4.544178485870361,
      "learning_rate": 0.0004999994656007457,
      "loss": 5.8125,
      "step": 157
    },
    {
      "epoch": 0.0154296875,
      "grad_norm": 4.998808860778809,
      "learning_rate": 0.0004999993020092219,
      "loss": 5.8359,
      "step": 158
    },
    {
      "epoch": 0.01552734375,
      "grad_norm": 5.184920787811279,
      "learning_rate": 0.0004999991166055426,
      "loss": 5.8281,
      "step": 159
    },
    {
      "epoch": 0.015625,
      "grad_norm": 3.716250419616699,
      "learning_rate": 0.0004999989093897262,
      "loss": 5.7969,
      "step": 160
    },
    {
      "epoch": 0.01572265625,
      "grad_norm": 3.8317952156066895,
      "learning_rate": 0.0004999986803617926,
      "loss": 5.7617,
      "step": 161
    },
    {
      "epoch": 0.0158203125,
      "grad_norm": 4.461795330047607,
      "learning_rate": 0.0004999984295217641,
      "loss": 5.8047,
      "step": 162
    },
    {
      "epoch": 0.01591796875,
      "grad_norm": 3.0825703144073486,
      "learning_rate": 0.0004999981568696648,
      "loss": 5.7656,
      "step": 163
    },
    {
      "epoch": 0.016015625,
      "grad_norm": 4.151459217071533,
      "learning_rate": 0.0004999978624055212,
      "loss": 5.7617,
      "step": 164
    },
    {
      "epoch": 0.01611328125,
      "grad_norm": 3.66987681388855,
      "learning_rate": 0.0004999975461293621,
      "loss": 5.7461,
      "step": 165
    },
    {
      "epoch": 0.0162109375,
      "grad_norm": 4.092290878295898,
      "learning_rate": 0.0004999972080412177,
      "loss": 5.75,
      "step": 166
    },
    {
      "epoch": 0.01630859375,
      "grad_norm": 4.104146480560303,
      "learning_rate": 0.0004999968481411212,
      "loss": 5.7656,
      "step": 167
    },
    {
      "epoch": 0.01640625,
      "grad_norm": 4.437919616699219,
      "learning_rate": 0.0004999964664291073,
      "loss": 5.7812,
      "step": 168
    },
    {
      "epoch": 0.01650390625,
      "grad_norm": 7.200653553009033,
      "learning_rate": 0.0004999960629052131,
      "loss": 5.7578,
      "step": 169
    },
    {
      "epoch": 0.0166015625,
      "grad_norm": 2.731268882751465,
      "learning_rate": 0.0004999956375694776,
      "loss": 5.707,
      "step": 170
    },
    {
      "epoch": 0.01669921875,
      "grad_norm": 5.332357406616211,
      "learning_rate": 0.0004999951904219421,
      "loss": 5.7461,
      "step": 171
    },
    {
      "epoch": 0.016796875,
      "grad_norm": 3.130514144897461,
      "learning_rate": 0.0004999947214626501,
      "loss": 5.7109,
      "step": 172
    },
    {
      "epoch": 0.01689453125,
      "grad_norm": 3.6535258293151855,
      "learning_rate": 0.0004999942306916466,
      "loss": 5.7344,
      "step": 173
    },
    {
      "epoch": 0.0169921875,
      "grad_norm": 3.5438027381896973,
      "learning_rate": 0.0004999937181089796,
      "loss": 5.6953,
      "step": 174
    },
    {
      "epoch": 0.01708984375,
      "grad_norm": 4.228607177734375,
      "learning_rate": 0.0004999931837146987,
      "loss": 5.7031,
      "step": 175
    },
    {
      "epoch": 0.0171875,
      "grad_norm": 3.217113971710205,
      "learning_rate": 0.0004999926275088556,
      "loss": 5.7148,
      "step": 176
    },
    {
      "epoch": 0.01728515625,
      "grad_norm": 4.9072041511535645,
      "learning_rate": 0.0004999920494915043,
      "loss": 5.75,
      "step": 177
    },
    {
      "epoch": 0.0173828125,
      "grad_norm": 2.8025128841400146,
      "learning_rate": 0.0004999914496627009,
      "loss": 5.7148,
      "step": 178
    },
    {
      "epoch": 0.01748046875,
      "grad_norm": 2.481431245803833,
      "learning_rate": 0.0004999908280225035,
      "loss": 5.6445,
      "step": 179
    },
    {
      "epoch": 0.017578125,
      "grad_norm": 3.0694146156311035,
      "learning_rate": 0.0004999901845709722,
      "loss": 5.6602,
      "step": 180
    },
    {
      "epoch": 0.01767578125,
      "grad_norm": 2.6255242824554443,
      "learning_rate": 0.0004999895193081698,
      "loss": 5.6523,
      "step": 181
    },
    {
      "epoch": 0.0177734375,
      "grad_norm": 3.0787289142608643,
      "learning_rate": 0.0004999888322341602,
      "loss": 5.6367,
      "step": 182
    },
    {
      "epoch": 0.01787109375,
      "grad_norm": 3.5675113201141357,
      "learning_rate": 0.0004999881233490104,
      "loss": 5.6875,
      "step": 183
    },
    {
      "epoch": 0.01796875,
      "grad_norm": 3.278024673461914,
      "learning_rate": 0.0004999873926527891,
      "loss": 5.6406,
      "step": 184
    },
    {
      "epoch": 0.01806640625,
      "grad_norm": 3.4470205307006836,
      "learning_rate": 0.0004999866401455671,
      "loss": 5.6328,
      "step": 185
    },
    {
      "epoch": 0.0181640625,
      "grad_norm": 2.537705659866333,
      "learning_rate": 0.0004999858658274172,
      "loss": 5.625,
      "step": 186
    },
    {
      "epoch": 0.01826171875,
      "grad_norm": 3.446849822998047,
      "learning_rate": 0.0004999850696984147,
      "loss": 5.6367,
      "step": 187
    },
    {
      "epoch": 0.018359375,
      "grad_norm": 2.9557571411132812,
      "learning_rate": 0.0004999842517586367,
      "loss": 5.6523,
      "step": 188
    },
    {
      "epoch": 0.01845703125,
      "grad_norm": 2.224954605102539,
      "learning_rate": 0.0004999834120081624,
      "loss": 5.6133,
      "step": 189
    },
    {
      "epoch": 0.0185546875,
      "grad_norm": 2.847534418106079,
      "learning_rate": 0.0004999825504470732,
      "loss": 5.5977,
      "step": 190
    },
    {
      "epoch": 0.01865234375,
      "grad_norm": 3.08176851272583,
      "learning_rate": 0.0004999816670754527,
      "loss": 5.6094,
      "step": 191
    },
    {
      "epoch": 0.01875,
      "grad_norm": 2.509631872177124,
      "learning_rate": 0.0004999807618933866,
      "loss": 5.582,
      "step": 192
    },
    {
      "epoch": 0.01884765625,
      "grad_norm": 2.551470994949341,
      "learning_rate": 0.0004999798349009626,
      "loss": 5.582,
      "step": 193
    },
    {
      "epoch": 0.0189453125,
      "grad_norm": 2.8080625534057617,
      "learning_rate": 0.0004999788860982706,
      "loss": 5.5898,
      "step": 194
    },
    {
      "epoch": 0.01904296875,
      "grad_norm": 2.784714698791504,
      "learning_rate": 0.0004999779154854024,
      "loss": 5.6016,
      "step": 195
    },
    {
      "epoch": 0.019140625,
      "grad_norm": 2.6262359619140625,
      "learning_rate": 0.0004999769230624524,
      "loss": 5.5664,
      "step": 196
    },
    {
      "epoch": 0.01923828125,
      "grad_norm": 2.2458934783935547,
      "learning_rate": 0.0004999759088295165,
      "loss": 5.5508,
      "step": 197
    },
    {
      "epoch": 0.0193359375,
      "grad_norm": 2.5689525604248047,
      "learning_rate": 0.0004999748727866932,
      "loss": 5.5625,
      "step": 198
    },
    {
      "epoch": 0.01943359375,
      "grad_norm": 2.44174861907959,
      "learning_rate": 0.0004999738149340828,
      "loss": 5.5352,
      "step": 199
    },
    {
      "epoch": 0.01953125,
      "grad_norm": 2.5862767696380615,
      "learning_rate": 0.000499972735271788,
      "loss": 5.5234,
      "step": 200
    },
    {
      "epoch": 0.01962890625,
      "grad_norm": 2.2569644451141357,
      "learning_rate": 0.0004999716337999135,
      "loss": 5.5078,
      "step": 201
    },
    {
      "epoch": 0.0197265625,
      "grad_norm": 2.5576300621032715,
      "learning_rate": 0.0004999705105185659,
      "loss": 5.5391,
      "step": 202
    },
    {
      "epoch": 0.01982421875,
      "grad_norm": 2.7671685218811035,
      "learning_rate": 0.0004999693654278542,
      "loss": 5.5234,
      "step": 203
    },
    {
      "epoch": 0.019921875,
      "grad_norm": 1.9716945886611938,
      "learning_rate": 0.0004999681985278894,
      "loss": 5.4961,
      "step": 204
    },
    {
      "epoch": 0.02001953125,
      "grad_norm": 2.345658302307129,
      "learning_rate": 0.0004999670098187846,
      "loss": 5.4961,
      "step": 205
    },
    {
      "epoch": 0.0201171875,
      "grad_norm": 2.1516318321228027,
      "learning_rate": 0.0004999657993006551,
      "loss": 5.5078,
      "step": 206
    },
    {
      "epoch": 0.02021484375,
      "grad_norm": 2.983196258544922,
      "learning_rate": 0.0004999645669736181,
      "loss": 5.5273,
      "step": 207
    },
    {
      "epoch": 0.0203125,
      "grad_norm": 2.5061614513397217,
      "learning_rate": 0.0004999633128377932,
      "loss": 5.5195,
      "step": 208
    },
    {
      "epoch": 0.02041015625,
      "grad_norm": 1.7015206813812256,
      "learning_rate": 0.000499962036893302,
      "loss": 5.4961,
      "step": 209
    },
    {
      "epoch": 0.0205078125,
      "grad_norm": 2.2488410472869873,
      "learning_rate": 0.0004999607391402681,
      "loss": 5.4258,
      "step": 210
    },
    {
      "epoch": 0.02060546875,
      "grad_norm": 2.7714498043060303,
      "learning_rate": 0.0004999594195788175,
      "loss": 5.5039,
      "step": 211
    },
    {
      "epoch": 0.020703125,
      "grad_norm": 2.1639745235443115,
      "learning_rate": 0.0004999580782090778,
      "loss": 5.4922,
      "step": 212
    },
    {
      "epoch": 0.02080078125,
      "grad_norm": 1.9490896463394165,
      "learning_rate": 0.0004999567150311793,
      "loss": 5.4492,
      "step": 213
    },
    {
      "epoch": 0.0208984375,
      "grad_norm": 2.291276454925537,
      "learning_rate": 0.0004999553300452541,
      "loss": 5.4648,
      "step": 214
    },
    {
      "epoch": 0.02099609375,
      "grad_norm": 2.4977705478668213,
      "learning_rate": 0.0004999539232514363,
      "loss": 5.4688,
      "step": 215
    },
    {
      "epoch": 0.02109375,
      "grad_norm": 2.013157367706299,
      "learning_rate": 0.0004999524946498624,
      "loss": 5.4727,
      "step": 216
    },
    {
      "epoch": 0.02119140625,
      "grad_norm": 2.35416579246521,
      "learning_rate": 0.000499951044240671,
      "loss": 5.457,
      "step": 217
    },
    {
      "epoch": 0.0212890625,
      "grad_norm": 1.7172154188156128,
      "learning_rate": 0.0004999495720240027,
      "loss": 5.4531,
      "step": 218
    },
    {
      "epoch": 0.02138671875,
      "grad_norm": 2.345547676086426,
      "learning_rate": 0.000499948078,
      "loss": 5.4609,
      "step": 219
    },
    {
      "epoch": 0.021484375,
      "grad_norm": 2.2435221672058105,
      "learning_rate": 0.0004999465621688078,
      "loss": 5.4453,
      "step": 220
    },
    {
      "epoch": 0.02158203125,
      "grad_norm": 2.306879997253418,
      "learning_rate": 0.0004999450245305732,
      "loss": 5.4414,
      "step": 221
    },
    {
      "epoch": 0.0216796875,
      "grad_norm": 2.2427804470062256,
      "learning_rate": 0.0004999434650854452,
      "loss": 5.4531,
      "step": 222
    },
    {
      "epoch": 0.02177734375,
      "grad_norm": 1.790202260017395,
      "learning_rate": 0.000499941883833575,
      "loss": 5.457,
      "step": 223
    },
    {
      "epoch": 0.021875,
      "grad_norm": 1.838149070739746,
      "learning_rate": 0.0004999402807751157,
      "loss": 5.4297,
      "step": 224
    },
    {
      "epoch": 0.02197265625,
      "grad_norm": 2.016653299331665,
      "learning_rate": 0.000499938655910223,
      "loss": 5.4141,
      "step": 225
    },
    {
      "epoch": 0.0220703125,
      "grad_norm": 2.0161890983581543,
      "learning_rate": 0.0004999370092390541,
      "loss": 5.3906,
      "step": 226
    },
    {
      "epoch": 0.02216796875,
      "grad_norm": 2.036649465560913,
      "learning_rate": 0.0004999353407617689,
      "loss": 5.4297,
      "step": 227
    },
    {
      "epoch": 0.022265625,
      "grad_norm": 1.5296927690505981,
      "learning_rate": 0.000499933650478529,
      "loss": 5.4023,
      "step": 228
    },
    {
      "epoch": 0.02236328125,
      "grad_norm": 1.713457703590393,
      "learning_rate": 0.0004999319383894985,
      "loss": 5.4219,
      "step": 229
    },
    {
      "epoch": 0.0224609375,
      "grad_norm": 2.3026342391967773,
      "learning_rate": 0.000499930204494843,
      "loss": 5.4453,
      "step": 230
    },
    {
      "epoch": 0.02255859375,
      "grad_norm": 2.2491424083709717,
      "learning_rate": 0.0004999284487947308,
      "loss": 5.4219,
      "step": 231
    },
    {
      "epoch": 0.02265625,
      "grad_norm": 2.2838447093963623,
      "learning_rate": 0.0004999266712893322,
      "loss": 5.4336,
      "step": 232
    },
    {
      "epoch": 0.02275390625,
      "grad_norm": 1.7964040040969849,
      "learning_rate": 0.0004999248719788193,
      "loss": 5.4141,
      "step": 233
    },
    {
      "epoch": 0.0228515625,
      "grad_norm": 2.0387890338897705,
      "learning_rate": 0.0004999230508633667,
      "loss": 5.4102,
      "step": 234
    },
    {
      "epoch": 0.02294921875,
      "grad_norm": 2.3577651977539062,
      "learning_rate": 0.0004999212079431507,
      "loss": 5.4297,
      "step": 235
    },
    {
      "epoch": 0.023046875,
      "grad_norm": 1.8143409490585327,
      "learning_rate": 0.0004999193432183504,
      "loss": 5.4023,
      "step": 236
    },
    {
      "epoch": 0.02314453125,
      "grad_norm": 1.6521782875061035,
      "learning_rate": 0.0004999174566891461,
      "loss": 5.3906,
      "step": 237
    },
    {
      "epoch": 0.0232421875,
      "grad_norm": 1.8481347560882568,
      "learning_rate": 0.000499915548355721,
      "loss": 5.3984,
      "step": 238
    },
    {
      "epoch": 0.02333984375,
      "grad_norm": 2.1952035427093506,
      "learning_rate": 0.0004999136182182601,
      "loss": 5.3984,
      "step": 239
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 2.0808660984039307,
      "learning_rate": 0.0004999116662769502,
      "loss": 5.3945,
      "step": 240
    },
    {
      "epoch": 0.02353515625,
      "grad_norm": 2.293430805206299,
      "learning_rate": 0.0004999096925319808,
      "loss": 5.4102,
      "step": 241
    },
    {
      "epoch": 0.0236328125,
      "grad_norm": 1.6741044521331787,
      "learning_rate": 0.0004999076969835432,
      "loss": 5.4062,
      "step": 242
    },
    {
      "epoch": 0.02373046875,
      "grad_norm": 1.95404851436615,
      "learning_rate": 0.0004999056796318308,
      "loss": 5.3672,
      "step": 243
    },
    {
      "epoch": 0.023828125,
      "grad_norm": 1.8848334550857544,
      "learning_rate": 0.0004999036404770391,
      "loss": 5.375,
      "step": 244
    },
    {
      "epoch": 0.02392578125,
      "grad_norm": 1.6347148418426514,
      "learning_rate": 0.0004999015795193661,
      "loss": 5.3711,
      "step": 245
    },
    {
      "epoch": 0.0240234375,
      "grad_norm": 2.3380987644195557,
      "learning_rate": 0.0004998994967590113,
      "loss": 5.4023,
      "step": 246
    },
    {
      "epoch": 0.02412109375,
      "grad_norm": 1.4733819961547852,
      "learning_rate": 0.0004998973921961767,
      "loss": 5.3711,
      "step": 247
    },
    {
      "epoch": 0.02421875,
      "grad_norm": 2.443174362182617,
      "learning_rate": 0.0004998952658310662,
      "loss": 5.3633,
      "step": 248
    },
    {
      "epoch": 0.02431640625,
      "grad_norm": 1.9105093479156494,
      "learning_rate": 0.0004998931176638861,
      "loss": 5.375,
      "step": 249
    },
    {
      "epoch": 0.0244140625,
      "grad_norm": 2.14117431640625,
      "learning_rate": 0.0004998909476948446,
      "loss": 5.3672,
      "step": 250
    },
    {
      "epoch": 0.02451171875,
      "grad_norm": 1.5175701379776,
      "learning_rate": 0.0004998887559241521,
      "loss": 5.3711,
      "step": 251
    },
    {
      "epoch": 0.024609375,
      "grad_norm": 1.7954213619232178,
      "learning_rate": 0.000499886542352021,
      "loss": 5.3359,
      "step": 252
    },
    {
      "epoch": 0.02470703125,
      "grad_norm": 2.0219264030456543,
      "learning_rate": 0.0004998843069786659,
      "loss": 5.3516,
      "step": 253
    },
    {
      "epoch": 0.0248046875,
      "grad_norm": 2.42618465423584,
      "learning_rate": 0.0004998820498043036,
      "loss": 5.3594,
      "step": 254
    },
    {
      "epoch": 0.02490234375,
      "grad_norm": 2.4111266136169434,
      "learning_rate": 0.0004998797708291528,
      "loss": 5.3477,
      "step": 255
    },
    {
      "epoch": 0.025,
      "grad_norm": 1.6236835718154907,
      "learning_rate": 0.0004998774700534346,
      "loss": 5.3516,
      "step": 256
    },
    {
      "epoch": 0.02509765625,
      "grad_norm": 2.249431610107422,
      "learning_rate": 0.0004998751474773718,
      "loss": 5.3789,
      "step": 257
    },
    {
      "epoch": 0.0251953125,
      "grad_norm": 1.878957986831665,
      "learning_rate": 0.0004998728031011897,
      "loss": 5.3359,
      "step": 258
    },
    {
      "epoch": 0.02529296875,
      "grad_norm": 1.7500239610671997,
      "learning_rate": 0.0004998704369251156,
      "loss": 5.3086,
      "step": 259
    },
    {
      "epoch": 0.025390625,
      "grad_norm": 1.5108247995376587,
      "learning_rate": 0.0004998680489493788,
      "loss": 5.3008,
      "step": 260
    },
    {
      "epoch": 0.02548828125,
      "grad_norm": 1.8362010717391968,
      "learning_rate": 0.0004998656391742108,
      "loss": 5.3398,
      "step": 261
    },
    {
      "epoch": 0.0255859375,
      "grad_norm": 1.7218053340911865,
      "learning_rate": 0.0004998632075998453,
      "loss": 5.3633,
      "step": 262
    },
    {
      "epoch": 0.02568359375,
      "grad_norm": 1.8602724075317383,
      "learning_rate": 0.000499860754226518,
      "loss": 5.3477,
      "step": 263
    },
    {
      "epoch": 0.02578125,
      "grad_norm": 1.3672821521759033,
      "learning_rate": 0.0004998582790544667,
      "loss": 5.3047,
      "step": 264
    },
    {
      "epoch": 0.02587890625,
      "grad_norm": 1.5733098983764648,
      "learning_rate": 0.0004998557820839313,
      "loss": 5.3203,
      "step": 265
    },
    {
      "epoch": 0.0259765625,
      "grad_norm": 1.547677993774414,
      "learning_rate": 0.0004998532633151539,
      "loss": 5.3203,
      "step": 266
    },
    {
      "epoch": 0.02607421875,
      "grad_norm": 1.8635348081588745,
      "learning_rate": 0.0004998507227483789,
      "loss": 5.332,
      "step": 267
    },
    {
      "epoch": 0.026171875,
      "grad_norm": 1.7884019613265991,
      "learning_rate": 0.0004998481603838523,
      "loss": 5.3281,
      "step": 268
    },
    {
      "epoch": 0.02626953125,
      "grad_norm": 1.6009703874588013,
      "learning_rate": 0.0004998455762218225,
      "loss": 5.3125,
      "step": 269
    },
    {
      "epoch": 0.0263671875,
      "grad_norm": 1.79560387134552,
      "learning_rate": 0.0004998429702625401,
      "loss": 5.3125,
      "step": 270
    },
    {
      "epoch": 0.02646484375,
      "grad_norm": 2.2909066677093506,
      "learning_rate": 0.0004998403425062579,
      "loss": 5.3242,
      "step": 271
    },
    {
      "epoch": 0.0265625,
      "grad_norm": 1.209547758102417,
      "learning_rate": 0.0004998376929532305,
      "loss": 5.3164,
      "step": 272
    },
    {
      "epoch": 0.02666015625,
      "grad_norm": 1.811440110206604,
      "learning_rate": 0.0004998350216037146,
      "loss": 5.3047,
      "step": 273
    },
    {
      "epoch": 0.0267578125,
      "grad_norm": 1.956322193145752,
      "learning_rate": 0.0004998323284579694,
      "loss": 5.3086,
      "step": 274
    },
    {
      "epoch": 0.02685546875,
      "grad_norm": 2.4985668659210205,
      "learning_rate": 0.000499829613516256,
      "loss": 5.3047,
      "step": 275
    },
    {
      "epoch": 0.026953125,
      "grad_norm": 2.2196872234344482,
      "learning_rate": 0.0004998268767788373,
      "loss": 5.3125,
      "step": 276
    },
    {
      "epoch": 0.02705078125,
      "grad_norm": 2.2135283946990967,
      "learning_rate": 0.0004998241182459789,
      "loss": 5.3242,
      "step": 277
    },
    {
      "epoch": 0.0271484375,
      "grad_norm": 1.4025847911834717,
      "learning_rate": 0.0004998213379179481,
      "loss": 5.3398,
      "step": 278
    },
    {
      "epoch": 0.02724609375,
      "grad_norm": 2.832472801208496,
      "learning_rate": 0.0004998185357950144,
      "loss": 5.3047,
      "step": 279
    },
    {
      "epoch": 0.02734375,
      "grad_norm": 1.4372154474258423,
      "learning_rate": 0.0004998157118774496,
      "loss": 5.3047,
      "step": 280
    },
    {
      "epoch": 0.02744140625,
      "grad_norm": 2.209719657897949,
      "learning_rate": 0.0004998128661655274,
      "loss": 5.3008,
      "step": 281
    },
    {
      "epoch": 0.0275390625,
      "grad_norm": 2.680424928665161,
      "learning_rate": 0.0004998099986595235,
      "loss": 5.3047,
      "step": 282
    },
    {
      "epoch": 0.02763671875,
      "grad_norm": 2.1611225605010986,
      "learning_rate": 0.0004998071093597162,
      "loss": 5.3008,
      "step": 283
    },
    {
      "epoch": 0.027734375,
      "grad_norm": 1.9571424722671509,
      "learning_rate": 0.0004998041982663851,
      "loss": 5.2891,
      "step": 284
    },
    {
      "epoch": 0.02783203125,
      "grad_norm": 1.3447707891464233,
      "learning_rate": 0.000499801265379813,
      "loss": 5.2852,
      "step": 285
    },
    {
      "epoch": 0.0279296875,
      "grad_norm": 2.0131936073303223,
      "learning_rate": 0.0004997983107002838,
      "loss": 5.3086,
      "step": 286
    },
    {
      "epoch": 0.02802734375,
      "grad_norm": 1.1873258352279663,
      "learning_rate": 0.0004997953342280843,
      "loss": 5.2656,
      "step": 287
    },
    {
      "epoch": 0.028125,
      "grad_norm": 2.239952564239502,
      "learning_rate": 0.0004997923359635027,
      "loss": 5.2773,
      "step": 288
    },
    {
      "epoch": 0.02822265625,
      "grad_norm": 1.3604589700698853,
      "learning_rate": 0.0004997893159068297,
      "loss": 5.2773,
      "step": 289
    },
    {
      "epoch": 0.0283203125,
      "grad_norm": 1.888407826423645,
      "learning_rate": 0.0004997862740583584,
      "loss": 5.2852,
      "step": 290
    },
    {
      "epoch": 0.02841796875,
      "grad_norm": 1.8944205045700073,
      "learning_rate": 0.0004997832104183833,
      "loss": 5.2812,
      "step": 291
    },
    {
      "epoch": 0.028515625,
      "grad_norm": 1.1297378540039062,
      "learning_rate": 0.0004997801249872016,
      "loss": 5.25,
      "step": 292
    },
    {
      "epoch": 0.02861328125,
      "grad_norm": 1.6378464698791504,
      "learning_rate": 0.0004997770177651123,
      "loss": 5.2461,
      "step": 293
    },
    {
      "epoch": 0.0287109375,
      "grad_norm": 1.3006982803344727,
      "learning_rate": 0.0004997738887524168,
      "loss": 5.2578,
      "step": 294
    },
    {
      "epoch": 0.02880859375,
      "grad_norm": 1.8940247297286987,
      "learning_rate": 0.0004997707379494183,
      "loss": 5.2773,
      "step": 295
    },
    {
      "epoch": 0.02890625,
      "grad_norm": 1.5350399017333984,
      "learning_rate": 0.0004997675653564223,
      "loss": 5.2656,
      "step": 296
    },
    {
      "epoch": 0.02900390625,
      "grad_norm": 1.58504056930542,
      "learning_rate": 0.0004997643709737363,
      "loss": 5.2695,
      "step": 297
    },
    {
      "epoch": 0.0291015625,
      "grad_norm": 1.5148996114730835,
      "learning_rate": 0.0004997611548016699,
      "loss": 5.2734,
      "step": 298
    },
    {
      "epoch": 0.02919921875,
      "grad_norm": 1.2484545707702637,
      "learning_rate": 0.0004997579168405352,
      "loss": 5.25,
      "step": 299
    },
    {
      "epoch": 0.029296875,
      "grad_norm": 1.4745291471481323,
      "learning_rate": 0.0004997546570906458,
      "loss": 5.2773,
      "step": 300
    },
    {
      "epoch": 0.02939453125,
      "grad_norm": 1.0975582599639893,
      "learning_rate": 0.0004997513755523179,
      "loss": 5.2344,
      "step": 301
    },
    {
      "epoch": 0.0294921875,
      "grad_norm": 1.4826176166534424,
      "learning_rate": 0.0004997480722258694,
      "loss": 5.2617,
      "step": 302
    },
    {
      "epoch": 0.02958984375,
      "grad_norm": 1.3512847423553467,
      "learning_rate": 0.0004997447471116207,
      "loss": 5.2422,
      "step": 303
    },
    {
      "epoch": 0.0296875,
      "grad_norm": 1.2088016271591187,
      "learning_rate": 0.0004997414002098941,
      "loss": 5.2539,
      "step": 304
    },
    {
      "epoch": 0.02978515625,
      "grad_norm": 1.3594310283660889,
      "learning_rate": 0.0004997380315210142,
      "loss": 5.2695,
      "step": 305
    },
    {
      "epoch": 0.0298828125,
      "grad_norm": 1.6119142770767212,
      "learning_rate": 0.0004997346410453074,
      "loss": 5.2383,
      "step": 306
    },
    {
      "epoch": 0.02998046875,
      "grad_norm": 1.2976305484771729,
      "learning_rate": 0.0004997312287831024,
      "loss": 5.2773,
      "step": 307
    },
    {
      "epoch": 0.030078125,
      "grad_norm": 1.1194605827331543,
      "learning_rate": 0.00049972779473473,
      "loss": 5.2656,
      "step": 308
    },
    {
      "epoch": 0.03017578125,
      "grad_norm": 1.244971752166748,
      "learning_rate": 0.0004997243389005232,
      "loss": 5.2383,
      "step": 309
    },
    {
      "epoch": 0.0302734375,
      "grad_norm": 1.1144415140151978,
      "learning_rate": 0.0004997208612808168,
      "loss": 5.2188,
      "step": 310
    },
    {
      "epoch": 0.03037109375,
      "grad_norm": 1.1849431991577148,
      "learning_rate": 0.0004997173618759482,
      "loss": 5.2422,
      "step": 311
    },
    {
      "epoch": 0.03046875,
      "grad_norm": 1.3395856618881226,
      "learning_rate": 0.0004997138406862565,
      "loss": 5.2422,
      "step": 312
    },
    {
      "epoch": 0.03056640625,
      "grad_norm": 1.1774636507034302,
      "learning_rate": 0.0004997102977120832,
      "loss": 5.2188,
      "step": 313
    },
    {
      "epoch": 0.0306640625,
      "grad_norm": 1.4251941442489624,
      "learning_rate": 0.0004997067329537714,
      "loss": 5.2578,
      "step": 314
    },
    {
      "epoch": 0.03076171875,
      "grad_norm": 1.4117344617843628,
      "learning_rate": 0.0004997031464116672,
      "loss": 5.207,
      "step": 315
    },
    {
      "epoch": 0.030859375,
      "grad_norm": 1.3700896501541138,
      "learning_rate": 0.0004996995380861178,
      "loss": 5.2305,
      "step": 316
    },
    {
      "epoch": 0.03095703125,
      "grad_norm": 1.682862401008606,
      "learning_rate": 0.0004996959079774734,
      "loss": 5.25,
      "step": 317
    },
    {
      "epoch": 0.0310546875,
      "grad_norm": 1.1571077108383179,
      "learning_rate": 0.0004996922560860856,
      "loss": 5.2109,
      "step": 318
    },
    {
      "epoch": 0.03115234375,
      "grad_norm": 1.1706202030181885,
      "learning_rate": 0.0004996885824123087,
      "loss": 5.2344,
      "step": 319
    },
    {
      "epoch": 0.03125,
      "grad_norm": 1.116774082183838,
      "learning_rate": 0.0004996848869564986,
      "loss": 5.2227,
      "step": 320
    },
    {
      "epoch": 0.03134765625,
      "grad_norm": 1.3174951076507568,
      "learning_rate": 0.0004996811697190137,
      "loss": 5.207,
      "step": 321
    },
    {
      "epoch": 0.0314453125,
      "grad_norm": 1.7159594297409058,
      "learning_rate": 0.0004996774307002142,
      "loss": 5.2305,
      "step": 322
    },
    {
      "epoch": 0.03154296875,
      "grad_norm": 1.1668405532836914,
      "learning_rate": 0.0004996736699004628,
      "loss": 5.2344,
      "step": 323
    },
    {
      "epoch": 0.031640625,
      "grad_norm": 1.4254777431488037,
      "learning_rate": 0.000499669887320124,
      "loss": 5.2188,
      "step": 324
    },
    {
      "epoch": 0.03173828125,
      "grad_norm": 1.4150874614715576,
      "learning_rate": 0.0004996660829595643,
      "loss": 5.2461,
      "step": 325
    },
    {
      "epoch": 0.0318359375,
      "grad_norm": 1.4464291334152222,
      "learning_rate": 0.0004996622568191529,
      "loss": 5.207,
      "step": 326
    },
    {
      "epoch": 0.03193359375,
      "grad_norm": 1.3123974800109863,
      "learning_rate": 0.0004996584088992603,
      "loss": 5.2227,
      "step": 327
    },
    {
      "epoch": 0.03203125,
      "grad_norm": 1.2821930646896362,
      "learning_rate": 0.0004996545392002597,
      "loss": 5.2344,
      "step": 328
    },
    {
      "epoch": 0.03212890625,
      "grad_norm": 1.6003687381744385,
      "learning_rate": 0.0004996506477225264,
      "loss": 5.1836,
      "step": 329
    },
    {
      "epoch": 0.0322265625,
      "grad_norm": 1.305853009223938,
      "learning_rate": 0.0004996467344664374,
      "loss": 5.2266,
      "step": 330
    },
    {
      "epoch": 0.03232421875,
      "grad_norm": 1.6081973314285278,
      "learning_rate": 0.0004996427994323723,
      "loss": 5.2031,
      "step": 331
    },
    {
      "epoch": 0.032421875,
      "grad_norm": 1.0995270013809204,
      "learning_rate": 0.0004996388426207123,
      "loss": 5.1797,
      "step": 332
    },
    {
      "epoch": 0.03251953125,
      "grad_norm": 1.1569955348968506,
      "learning_rate": 0.0004996348640318412,
      "loss": 5.2305,
      "step": 333
    },
    {
      "epoch": 0.0326171875,
      "grad_norm": 1.3775110244750977,
      "learning_rate": 0.0004996308636661447,
      "loss": 5.2266,
      "step": 334
    },
    {
      "epoch": 0.03271484375,
      "grad_norm": 1.2185978889465332,
      "learning_rate": 0.0004996268415240104,
      "loss": 5.1641,
      "step": 335
    },
    {
      "epoch": 0.0328125,
      "grad_norm": 1.349692702293396,
      "learning_rate": 0.0004996227976058285,
      "loss": 5.1914,
      "step": 336
    },
    {
      "epoch": 0.03291015625,
      "grad_norm": 0.9755382537841797,
      "learning_rate": 0.0004996187319119908,
      "loss": 5.1914,
      "step": 337
    },
    {
      "epoch": 0.0330078125,
      "grad_norm": 1.187360405921936,
      "learning_rate": 0.0004996146444428916,
      "loss": 5.1875,
      "step": 338
    },
    {
      "epoch": 0.03310546875,
      "grad_norm": 1.2067431211471558,
      "learning_rate": 0.000499610535198927,
      "loss": 5.2109,
      "step": 339
    },
    {
      "epoch": 0.033203125,
      "grad_norm": 1.2557358741760254,
      "learning_rate": 0.0004996064041804956,
      "loss": 5.1953,
      "step": 340
    },
    {
      "epoch": 0.03330078125,
      "grad_norm": 1.191425085067749,
      "learning_rate": 0.0004996022513879977,
      "loss": 5.1719,
      "step": 341
    },
    {
      "epoch": 0.0333984375,
      "grad_norm": 0.985287606716156,
      "learning_rate": 0.0004995980768218358,
      "loss": 5.1719,
      "step": 342
    },
    {
      "epoch": 0.03349609375,
      "grad_norm": 2.132200002670288,
      "learning_rate": 0.0004995938804824146,
      "loss": 5.2109,
      "step": 343
    },
    {
      "epoch": 0.03359375,
      "grad_norm": 0.8363533616065979,
      "learning_rate": 0.0004995896623701412,
      "loss": 5.1914,
      "step": 344
    },
    {
      "epoch": 0.03369140625,
      "grad_norm": 1.090147614479065,
      "learning_rate": 0.0004995854224854243,
      "loss": 5.2031,
      "step": 345
    },
    {
      "epoch": 0.0337890625,
      "grad_norm": 1.313947319984436,
      "learning_rate": 0.000499581160828675,
      "loss": 5.1523,
      "step": 346
    },
    {
      "epoch": 0.03388671875,
      "grad_norm": 1.3441343307495117,
      "learning_rate": 0.0004995768774003062,
      "loss": 5.1797,
      "step": 347
    },
    {
      "epoch": 0.033984375,
      "grad_norm": 1.4852529764175415,
      "learning_rate": 0.0004995725722007335,
      "loss": 5.2031,
      "step": 348
    },
    {
      "epoch": 0.03408203125,
      "grad_norm": 1.9018231630325317,
      "learning_rate": 0.0004995682452303741,
      "loss": 5.1797,
      "step": 349
    },
    {
      "epoch": 0.0341796875,
      "grad_norm": 0.8266469836235046,
      "learning_rate": 0.0004995638964896475,
      "loss": 5.1758,
      "step": 350
    },
    {
      "epoch": 0.03427734375,
      "grad_norm": 0.971101701259613,
      "learning_rate": 0.0004995595259789752,
      "loss": 5.168,
      "step": 351
    },
    {
      "epoch": 0.034375,
      "grad_norm": 1.2720019817352295,
      "learning_rate": 0.0004995551336987809,
      "loss": 5.1914,
      "step": 352
    },
    {
      "epoch": 0.03447265625,
      "grad_norm": 1.524877667427063,
      "learning_rate": 0.0004995507196494905,
      "loss": 5.1836,
      "step": 353
    },
    {
      "epoch": 0.0345703125,
      "grad_norm": 1.155196189880371,
      "learning_rate": 0.0004995462838315319,
      "loss": 5.1484,
      "step": 354
    },
    {
      "epoch": 0.03466796875,
      "grad_norm": 1.2725322246551514,
      "learning_rate": 0.0004995418262453351,
      "loss": 5.1562,
      "step": 355
    },
    {
      "epoch": 0.034765625,
      "grad_norm": 1.064315915107727,
      "learning_rate": 0.000499537346891332,
      "loss": 5.1641,
      "step": 356
    },
    {
      "epoch": 0.03486328125,
      "grad_norm": 1.1174203157424927,
      "learning_rate": 0.0004995328457699573,
      "loss": 5.1289,
      "step": 357
    },
    {
      "epoch": 0.0349609375,
      "grad_norm": 1.5893704891204834,
      "learning_rate": 0.000499528322881647,
      "loss": 5.1523,
      "step": 358
    },
    {
      "epoch": 0.03505859375,
      "grad_norm": 1.3740280866622925,
      "learning_rate": 0.0004995237782268397,
      "loss": 5.1289,
      "step": 359
    },
    {
      "epoch": 0.03515625,
      "grad_norm": 1.560889720916748,
      "learning_rate": 0.000499519211805976,
      "loss": 5.1875,
      "step": 360
    },
    {
      "epoch": 0.03525390625,
      "grad_norm": 1.1352694034576416,
      "learning_rate": 0.0004995146236194984,
      "loss": 5.1758,
      "step": 361
    },
    {
      "epoch": 0.0353515625,
      "grad_norm": 1.4046801328659058,
      "learning_rate": 0.0004995100136678519,
      "loss": 5.1758,
      "step": 362
    },
    {
      "epoch": 0.03544921875,
      "grad_norm": 1.10200035572052,
      "learning_rate": 0.0004995053819514834,
      "loss": 5.1523,
      "step": 363
    },
    {
      "epoch": 0.035546875,
      "grad_norm": 1.179033875465393,
      "learning_rate": 0.0004995007284708418,
      "loss": 5.1367,
      "step": 364
    },
    {
      "epoch": 0.03564453125,
      "grad_norm": 1.1701732873916626,
      "learning_rate": 0.0004994960532263782,
      "loss": 5.1406,
      "step": 365
    },
    {
      "epoch": 0.0357421875,
      "grad_norm": 1.096832513809204,
      "learning_rate": 0.000499491356218546,
      "loss": 5.1484,
      "step": 366
    },
    {
      "epoch": 0.03583984375,
      "grad_norm": 1.4660563468933105,
      "learning_rate": 0.0004994866374478003,
      "loss": 5.1562,
      "step": 367
    },
    {
      "epoch": 0.0359375,
      "grad_norm": 1.2725329399108887,
      "learning_rate": 0.0004994818969145989,
      "loss": 5.1719,
      "step": 368
    },
    {
      "epoch": 0.03603515625,
      "grad_norm": 1.5378856658935547,
      "learning_rate": 0.000499477134619401,
      "loss": 5.1758,
      "step": 369
    },
    {
      "epoch": 0.0361328125,
      "grad_norm": 1.0054930448532104,
      "learning_rate": 0.0004994723505626685,
      "loss": 5.2031,
      "step": 370
    },
    {
      "epoch": 0.03623046875,
      "grad_norm": 1.3905240297317505,
      "learning_rate": 0.0004994675447448651,
      "loss": 5.1562,
      "step": 371
    },
    {
      "epoch": 0.036328125,
      "grad_norm": 1.2946956157684326,
      "learning_rate": 0.0004994627171664565,
      "loss": 5.1641,
      "step": 372
    },
    {
      "epoch": 0.03642578125,
      "grad_norm": 0.8594855070114136,
      "learning_rate": 0.0004994578678279112,
      "loss": 5.1133,
      "step": 373
    },
    {
      "epoch": 0.0365234375,
      "grad_norm": 1.0982156991958618,
      "learning_rate": 0.0004994529967296989,
      "loss": 5.1445,
      "step": 374
    },
    {
      "epoch": 0.03662109375,
      "grad_norm": 1.197832703590393,
      "learning_rate": 0.0004994481038722919,
      "loss": 5.1875,
      "step": 375
    },
    {
      "epoch": 0.03671875,
      "grad_norm": 0.903097927570343,
      "learning_rate": 0.0004994431892561646,
      "loss": 5.1523,
      "step": 376
    },
    {
      "epoch": 0.03681640625,
      "grad_norm": 1.064278483390808,
      "learning_rate": 0.0004994382528817935,
      "loss": 5.1602,
      "step": 377
    },
    {
      "epoch": 0.0369140625,
      "grad_norm": 1.0776413679122925,
      "learning_rate": 0.0004994332947496568,
      "loss": 5.1406,
      "step": 378
    },
    {
      "epoch": 0.03701171875,
      "grad_norm": 0.99156254529953,
      "learning_rate": 0.0004994283148602357,
      "loss": 5.1484,
      "step": 379
    },
    {
      "epoch": 0.037109375,
      "grad_norm": 1.25286066532135,
      "learning_rate": 0.0004994233132140125,
      "loss": 5.1367,
      "step": 380
    },
    {
      "epoch": 0.03720703125,
      "grad_norm": 0.9926852583885193,
      "learning_rate": 0.0004994182898114722,
      "loss": 5.1328,
      "step": 381
    },
    {
      "epoch": 0.0373046875,
      "grad_norm": 1.0031254291534424,
      "learning_rate": 0.0004994132446531019,
      "loss": 5.125,
      "step": 382
    },
    {
      "epoch": 0.03740234375,
      "grad_norm": 1.1352587938308716,
      "learning_rate": 0.0004994081777393907,
      "loss": 5.1719,
      "step": 383
    },
    {
      "epoch": 0.0375,
      "grad_norm": 1.145836591720581,
      "learning_rate": 0.0004994030890708297,
      "loss": 5.1211,
      "step": 384
    },
    {
      "epoch": 0.03759765625,
      "grad_norm": 1.125534176826477,
      "learning_rate": 0.0004993979786479121,
      "loss": 5.125,
      "step": 385
    },
    {
      "epoch": 0.0376953125,
      "grad_norm": 0.9138064384460449,
      "learning_rate": 0.0004993928464711337,
      "loss": 5.1289,
      "step": 386
    },
    {
      "epoch": 0.03779296875,
      "grad_norm": 1.0376123189926147,
      "learning_rate": 0.0004993876925409917,
      "loss": 5.1328,
      "step": 387
    },
    {
      "epoch": 0.037890625,
      "grad_norm": 1.0181726217269897,
      "learning_rate": 0.0004993825168579857,
      "loss": 5.1289,
      "step": 388
    },
    {
      "epoch": 0.03798828125,
      "grad_norm": 1.191735029220581,
      "learning_rate": 0.0004993773194226178,
      "loss": 5.1172,
      "step": 389
    },
    {
      "epoch": 0.0380859375,
      "grad_norm": 1.0628931522369385,
      "learning_rate": 0.0004993721002353915,
      "loss": 5.1133,
      "step": 390
    },
    {
      "epoch": 0.03818359375,
      "grad_norm": 1.2050843238830566,
      "learning_rate": 0.0004993668592968129,
      "loss": 5.1172,
      "step": 391
    },
    {
      "epoch": 0.03828125,
      "grad_norm": 0.8847583532333374,
      "learning_rate": 0.0004993615966073902,
      "loss": 5.1328,
      "step": 392
    },
    {
      "epoch": 0.03837890625,
      "grad_norm": 0.9037215709686279,
      "learning_rate": 0.0004993563121676332,
      "loss": 5.1406,
      "step": 393
    },
    {
      "epoch": 0.0384765625,
      "grad_norm": 0.8788461685180664,
      "learning_rate": 0.0004993510059780546,
      "loss": 5.1523,
      "step": 394
    },
    {
      "epoch": 0.03857421875,
      "grad_norm": 0.788327693939209,
      "learning_rate": 0.0004993456780391686,
      "loss": 5.1016,
      "step": 395
    },
    {
      "epoch": 0.038671875,
      "grad_norm": 0.874692440032959,
      "learning_rate": 0.0004993403283514919,
      "loss": 5.0938,
      "step": 396
    },
    {
      "epoch": 0.03876953125,
      "grad_norm": 1.0633156299591064,
      "learning_rate": 0.0004993349569155428,
      "loss": 5.1289,
      "step": 397
    },
    {
      "epoch": 0.0388671875,
      "grad_norm": 1.076167106628418,
      "learning_rate": 0.0004993295637318423,
      "loss": 5.1172,
      "step": 398
    },
    {
      "epoch": 0.03896484375,
      "grad_norm": 0.9785029292106628,
      "learning_rate": 0.0004993241488009131,
      "loss": 5.0977,
      "step": 399
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 1.0597959756851196,
      "learning_rate": 0.0004993187121232801,
      "loss": 5.1094,
      "step": 400
    },
    {
      "epoch": 0.03916015625,
      "grad_norm": 1.2436349391937256,
      "learning_rate": 0.0004993132536994705,
      "loss": 5.1289,
      "step": 401
    },
    {
      "epoch": 0.0392578125,
      "grad_norm": 1.0709871053695679,
      "learning_rate": 0.0004993077735300133,
      "loss": 5.1328,
      "step": 402
    },
    {
      "epoch": 0.03935546875,
      "grad_norm": 1.018754005432129,
      "learning_rate": 0.0004993022716154399,
      "loss": 5.1094,
      "step": 403
    },
    {
      "epoch": 0.039453125,
      "grad_norm": 0.8745573163032532,
      "learning_rate": 0.0004992967479562836,
      "loss": 5.1172,
      "step": 404
    },
    {
      "epoch": 0.03955078125,
      "grad_norm": 0.8379338979721069,
      "learning_rate": 0.0004992912025530799,
      "loss": 5.1406,
      "step": 405
    },
    {
      "epoch": 0.0396484375,
      "grad_norm": 0.8244563341140747,
      "learning_rate": 0.0004992856354063663,
      "loss": 5.1328,
      "step": 406
    },
    {
      "epoch": 0.03974609375,
      "grad_norm": 1.0282996892929077,
      "learning_rate": 0.0004992800465166826,
      "loss": 5.1016,
      "step": 407
    },
    {
      "epoch": 0.03984375,
      "grad_norm": 0.8590074777603149,
      "learning_rate": 0.0004992744358845707,
      "loss": 5.1094,
      "step": 408
    },
    {
      "epoch": 0.03994140625,
      "grad_norm": 0.7324565052986145,
      "learning_rate": 0.0004992688035105744,
      "loss": 5.1094,
      "step": 409
    },
    {
      "epoch": 0.0400390625,
      "grad_norm": 0.8005876541137695,
      "learning_rate": 0.0004992631493952395,
      "loss": 5.1094,
      "step": 410
    },
    {
      "epoch": 0.04013671875,
      "grad_norm": 1.217882513999939,
      "learning_rate": 0.0004992574735391144,
      "loss": 5.0938,
      "step": 411
    },
    {
      "epoch": 0.040234375,
      "grad_norm": 1.186151385307312,
      "learning_rate": 0.0004992517759427494,
      "loss": 5.1094,
      "step": 412
    },
    {
      "epoch": 0.04033203125,
      "grad_norm": 0.851876974105835,
      "learning_rate": 0.0004992460566066967,
      "loss": 5.0781,
      "step": 413
    },
    {
      "epoch": 0.0404296875,
      "grad_norm": 0.8220931887626648,
      "learning_rate": 0.0004992403155315107,
      "loss": 5.0977,
      "step": 414
    },
    {
      "epoch": 0.04052734375,
      "grad_norm": 0.848565399646759,
      "learning_rate": 0.0004992345527177482,
      "loss": 5.0898,
      "step": 415
    },
    {
      "epoch": 0.040625,
      "grad_norm": 1.1592659950256348,
      "learning_rate": 0.0004992287681659676,
      "loss": 5.0781,
      "step": 416
    },
    {
      "epoch": 0.04072265625,
      "grad_norm": 1.0059559345245361,
      "learning_rate": 0.0004992229618767298,
      "loss": 5.0781,
      "step": 417
    },
    {
      "epoch": 0.0408203125,
      "grad_norm": 0.9418927431106567,
      "learning_rate": 0.0004992171338505975,
      "loss": 5.0898,
      "step": 418
    },
    {
      "epoch": 0.04091796875,
      "grad_norm": 0.8450960516929626,
      "learning_rate": 0.0004992112840881359,
      "loss": 5.0898,
      "step": 419
    },
    {
      "epoch": 0.041015625,
      "grad_norm": 0.739745557308197,
      "learning_rate": 0.0004992054125899122,
      "loss": 5.0625,
      "step": 420
    },
    {
      "epoch": 0.04111328125,
      "grad_norm": 0.6499938368797302,
      "learning_rate": 0.0004991995193564953,
      "loss": 5.0742,
      "step": 421
    },
    {
      "epoch": 0.0412109375,
      "grad_norm": 0.5470448136329651,
      "learning_rate": 0.0004991936043884566,
      "loss": 5.0859,
      "step": 422
    },
    {
      "epoch": 0.04130859375,
      "grad_norm": 0.582874059677124,
      "learning_rate": 0.0004991876676863697,
      "loss": 5.0664,
      "step": 423
    },
    {
      "epoch": 0.04140625,
      "grad_norm": 0.61722731590271,
      "learning_rate": 0.0004991817092508099,
      "loss": 5.0898,
      "step": 424
    },
    {
      "epoch": 0.04150390625,
      "grad_norm": 0.6884714365005493,
      "learning_rate": 0.0004991757290823548,
      "loss": 5.0703,
      "step": 425
    },
    {
      "epoch": 0.0416015625,
      "grad_norm": 0.8316398859024048,
      "learning_rate": 0.0004991697271815845,
      "loss": 5.1367,
      "step": 426
    },
    {
      "epoch": 0.04169921875,
      "grad_norm": 0.9839829802513123,
      "learning_rate": 0.0004991637035490805,
      "loss": 5.0703,
      "step": 427
    },
    {
      "epoch": 0.041796875,
      "grad_norm": 1.0404824018478394,
      "learning_rate": 0.0004991576581854267,
      "loss": 5.0586,
      "step": 428
    },
    {
      "epoch": 0.04189453125,
      "grad_norm": 0.8250628709793091,
      "learning_rate": 0.0004991515910912095,
      "loss": 5.0625,
      "step": 429
    },
    {
      "epoch": 0.0419921875,
      "grad_norm": 0.7997605204582214,
      "learning_rate": 0.0004991455022670168,
      "loss": 5.0938,
      "step": 430
    },
    {
      "epoch": 0.04208984375,
      "grad_norm": 0.6865594983100891,
      "learning_rate": 0.0004991393917134388,
      "loss": 5.0781,
      "step": 431
    },
    {
      "epoch": 0.0421875,
      "grad_norm": 0.6902148723602295,
      "learning_rate": 0.0004991332594310682,
      "loss": 5.0586,
      "step": 432
    },
    {
      "epoch": 0.04228515625,
      "grad_norm": 0.6424334645271301,
      "learning_rate": 0.0004991271054204992,
      "loss": 5.0742,
      "step": 433
    },
    {
      "epoch": 0.0423828125,
      "grad_norm": 0.6057596802711487,
      "learning_rate": 0.0004991209296823285,
      "loss": 5.0625,
      "step": 434
    },
    {
      "epoch": 0.04248046875,
      "grad_norm": 0.6817944645881653,
      "learning_rate": 0.0004991147322171548,
      "loss": 5.082,
      "step": 435
    },
    {
      "epoch": 0.042578125,
      "grad_norm": 0.7707593441009521,
      "learning_rate": 0.0004991085130255789,
      "loss": 5.0586,
      "step": 436
    },
    {
      "epoch": 0.04267578125,
      "grad_norm": 0.9107893109321594,
      "learning_rate": 0.0004991022721082037,
      "loss": 5.0898,
      "step": 437
    },
    {
      "epoch": 0.0427734375,
      "grad_norm": 1.1807111501693726,
      "learning_rate": 0.0004990960094656342,
      "loss": 5.0195,
      "step": 438
    },
    {
      "epoch": 0.04287109375,
      "grad_norm": 1.1950851678848267,
      "learning_rate": 0.0004990897250984774,
      "loss": 5.0469,
      "step": 439
    },
    {
      "epoch": 0.04296875,
      "grad_norm": 0.7908074855804443,
      "learning_rate": 0.0004990834190073428,
      "loss": 5.1016,
      "step": 440
    },
    {
      "epoch": 0.04306640625,
      "grad_norm": 0.7892453670501709,
      "learning_rate": 0.0004990770911928416,
      "loss": 5.0938,
      "step": 441
    },
    {
      "epoch": 0.0431640625,
      "grad_norm": 0.7331576347351074,
      "learning_rate": 0.0004990707416555871,
      "loss": 5.0508,
      "step": 442
    },
    {
      "epoch": 0.04326171875,
      "grad_norm": 0.7229627966880798,
      "learning_rate": 0.000499064370396195,
      "loss": 5.0234,
      "step": 443
    },
    {
      "epoch": 0.043359375,
      "grad_norm": 0.8491083979606628,
      "learning_rate": 0.000499057977415283,
      "loss": 5.0859,
      "step": 444
    },
    {
      "epoch": 0.04345703125,
      "grad_norm": 1.1333506107330322,
      "learning_rate": 0.0004990515627134706,
      "loss": 5.0859,
      "step": 445
    },
    {
      "epoch": 0.0435546875,
      "grad_norm": 1.0400718450546265,
      "learning_rate": 0.00049904512629138,
      "loss": 5.0703,
      "step": 446
    },
    {
      "epoch": 0.04365234375,
      "grad_norm": 0.8677104115486145,
      "learning_rate": 0.000499038668149635,
      "loss": 5.0273,
      "step": 447
    },
    {
      "epoch": 0.04375,
      "grad_norm": 1.0702966451644897,
      "learning_rate": 0.0004990321882888617,
      "loss": 5.0664,
      "step": 448
    },
    {
      "epoch": 0.04384765625,
      "grad_norm": 0.9019585847854614,
      "learning_rate": 0.0004990256867096881,
      "loss": 5.0352,
      "step": 449
    },
    {
      "epoch": 0.0439453125,
      "grad_norm": 0.7547096014022827,
      "learning_rate": 0.0004990191634127448,
      "loss": 5.0664,
      "step": 450
    },
    {
      "epoch": 0.04404296875,
      "grad_norm": 0.6731748580932617,
      "learning_rate": 0.0004990126183986639,
      "loss": 5.0625,
      "step": 451
    },
    {
      "epoch": 0.044140625,
      "grad_norm": 0.738862931728363,
      "learning_rate": 0.0004990060516680802,
      "loss": 5.082,
      "step": 452
    },
    {
      "epoch": 0.04423828125,
      "grad_norm": 0.7783480286598206,
      "learning_rate": 0.00049899946322163,
      "loss": 5.0703,
      "step": 453
    },
    {
      "epoch": 0.0443359375,
      "grad_norm": 0.7385779023170471,
      "learning_rate": 0.0004989928530599521,
      "loss": 5.0547,
      "step": 454
    },
    {
      "epoch": 0.04443359375,
      "grad_norm": 1.394942283630371,
      "learning_rate": 0.0004989862211836873,
      "loss": 5.0547,
      "step": 455
    },
    {
      "epoch": 0.04453125,
      "grad_norm": 0.5369975566864014,
      "learning_rate": 0.0004989795675934787,
      "loss": 5.0781,
      "step": 456
    },
    {
      "epoch": 0.04462890625,
      "grad_norm": 0.6641459465026855,
      "learning_rate": 0.0004989728922899712,
      "loss": 5.0117,
      "step": 457
    },
    {
      "epoch": 0.0447265625,
      "grad_norm": 0.7093449831008911,
      "learning_rate": 0.0004989661952738118,
      "loss": 5.0586,
      "step": 458
    },
    {
      "epoch": 0.04482421875,
      "grad_norm": 0.8085068464279175,
      "learning_rate": 0.0004989594765456498,
      "loss": 5.0508,
      "step": 459
    },
    {
      "epoch": 0.044921875,
      "grad_norm": 1.188184142112732,
      "learning_rate": 0.0004989527361061366,
      "loss": 5.0391,
      "step": 460
    },
    {
      "epoch": 0.04501953125,
      "grad_norm": 0.9588766098022461,
      "learning_rate": 0.0004989459739559257,
      "loss": 5.0195,
      "step": 461
    },
    {
      "epoch": 0.0451171875,
      "grad_norm": 0.8630503416061401,
      "learning_rate": 0.0004989391900956725,
      "loss": 5.0195,
      "step": 462
    },
    {
      "epoch": 0.04521484375,
      "grad_norm": 0.8916110396385193,
      "learning_rate": 0.0004989323845260346,
      "loss": 5.0586,
      "step": 463
    },
    {
      "epoch": 0.0453125,
      "grad_norm": 0.8974289298057556,
      "learning_rate": 0.0004989255572476719,
      "loss": 5.0547,
      "step": 464
    },
    {
      "epoch": 0.04541015625,
      "grad_norm": 0.9970776438713074,
      "learning_rate": 0.0004989187082612462,
      "loss": 5.0469,
      "step": 465
    },
    {
      "epoch": 0.0455078125,
      "grad_norm": 0.885099470615387,
      "learning_rate": 0.0004989118375674216,
      "loss": 5.043,
      "step": 466
    },
    {
      "epoch": 0.04560546875,
      "grad_norm": 0.659532368183136,
      "learning_rate": 0.0004989049451668639,
      "loss": 5.0547,
      "step": 467
    },
    {
      "epoch": 0.045703125,
      "grad_norm": 0.8999412655830383,
      "learning_rate": 0.0004988980310602415,
      "loss": 5.0117,
      "step": 468
    },
    {
      "epoch": 0.04580078125,
      "grad_norm": 0.7855193018913269,
      "learning_rate": 0.0004988910952482246,
      "loss": 5.0859,
      "step": 469
    },
    {
      "epoch": 0.0458984375,
      "grad_norm": 0.9827584028244019,
      "learning_rate": 0.0004988841377314855,
      "loss": 5.0586,
      "step": 470
    },
    {
      "epoch": 0.04599609375,
      "grad_norm": 1.13511323928833,
      "learning_rate": 0.0004988771585106988,
      "loss": 5.0547,
      "step": 471
    },
    {
      "epoch": 0.04609375,
      "grad_norm": 0.8385241627693176,
      "learning_rate": 0.000498870157586541,
      "loss": 5.0586,
      "step": 472
    },
    {
      "epoch": 0.04619140625,
      "grad_norm": 0.7410266995429993,
      "learning_rate": 0.0004988631349596909,
      "loss": 5.0664,
      "step": 473
    },
    {
      "epoch": 0.0462890625,
      "grad_norm": 0.6939350962638855,
      "learning_rate": 0.0004988560906308291,
      "loss": 5.043,
      "step": 474
    },
    {
      "epoch": 0.04638671875,
      "grad_norm": 0.7858873605728149,
      "learning_rate": 0.0004988490246006388,
      "loss": 5.0469,
      "step": 475
    },
    {
      "epoch": 0.046484375,
      "grad_norm": 1.0619468688964844,
      "learning_rate": 0.0004988419368698047,
      "loss": 5.0234,
      "step": 476
    },
    {
      "epoch": 0.04658203125,
      "grad_norm": 1.3020342588424683,
      "learning_rate": 0.0004988348274390141,
      "loss": 5.0469,
      "step": 477
    },
    {
      "epoch": 0.0466796875,
      "grad_norm": 0.7949604988098145,
      "learning_rate": 0.0004988276963089561,
      "loss": 5.0391,
      "step": 478
    },
    {
      "epoch": 0.04677734375,
      "grad_norm": 0.8782525658607483,
      "learning_rate": 0.0004988205434803222,
      "loss": 5.043,
      "step": 479
    },
    {
      "epoch": 0.046875,
      "grad_norm": 0.9638606309890747,
      "learning_rate": 0.0004988133689538055,
      "loss": 5.0703,
      "step": 480
    },
    {
      "epoch": 0.04697265625,
      "grad_norm": 0.8633697032928467,
      "learning_rate": 0.0004988061727301019,
      "loss": 5.0,
      "step": 481
    },
    {
      "epoch": 0.0470703125,
      "grad_norm": 0.719272255897522,
      "learning_rate": 0.0004987989548099087,
      "loss": 5.043,
      "step": 482
    },
    {
      "epoch": 0.04716796875,
      "grad_norm": 0.7947590947151184,
      "learning_rate": 0.0004987917151939257,
      "loss": 5.0273,
      "step": 483
    },
    {
      "epoch": 0.047265625,
      "grad_norm": 0.8721004128456116,
      "learning_rate": 0.000498784453882855,
      "loss": 5.0469,
      "step": 484
    },
    {
      "epoch": 0.04736328125,
      "grad_norm": 0.840782880783081,
      "learning_rate": 0.0004987771708774001,
      "loss": 5.0273,
      "step": 485
    },
    {
      "epoch": 0.0474609375,
      "grad_norm": 0.6539798974990845,
      "learning_rate": 0.0004987698661782674,
      "loss": 5.0273,
      "step": 486
    },
    {
      "epoch": 0.04755859375,
      "grad_norm": 0.6629400253295898,
      "learning_rate": 0.0004987625397861649,
      "loss": 5.0273,
      "step": 487
    },
    {
      "epoch": 0.04765625,
      "grad_norm": 0.69793301820755,
      "learning_rate": 0.0004987551917018028,
      "loss": 4.9961,
      "step": 488
    },
    {
      "epoch": 0.04775390625,
      "grad_norm": 0.8525344133377075,
      "learning_rate": 0.0004987478219258936,
      "loss": 5.0508,
      "step": 489
    },
    {
      "epoch": 0.0478515625,
      "grad_norm": 0.9601410627365112,
      "learning_rate": 0.0004987404304591514,
      "loss": 5.0391,
      "step": 490
    },
    {
      "epoch": 0.04794921875,
      "grad_norm": 0.8520921468734741,
      "learning_rate": 0.0004987330173022932,
      "loss": 5.0273,
      "step": 491
    },
    {
      "epoch": 0.048046875,
      "grad_norm": 0.8635746240615845,
      "learning_rate": 0.0004987255824560374,
      "loss": 5.0234,
      "step": 492
    },
    {
      "epoch": 0.04814453125,
      "grad_norm": 0.998202383518219,
      "learning_rate": 0.0004987181259211048,
      "loss": 5.0273,
      "step": 493
    },
    {
      "epoch": 0.0482421875,
      "grad_norm": 1.2011066675186157,
      "learning_rate": 0.0004987106476982184,
      "loss": 5.0312,
      "step": 494
    },
    {
      "epoch": 0.04833984375,
      "grad_norm": 0.7638375163078308,
      "learning_rate": 0.0004987031477881029,
      "loss": 5.0312,
      "step": 495
    },
    {
      "epoch": 0.0484375,
      "grad_norm": 0.70158451795578,
      "learning_rate": 0.0004986956261914856,
      "loss": 5.0156,
      "step": 496
    },
    {
      "epoch": 0.04853515625,
      "grad_norm": 0.7986351847648621,
      "learning_rate": 0.0004986880829090954,
      "loss": 5.0234,
      "step": 497
    },
    {
      "epoch": 0.0486328125,
      "grad_norm": 0.8812294006347656,
      "learning_rate": 0.0004986805179416638,
      "loss": 5.0156,
      "step": 498
    },
    {
      "epoch": 0.04873046875,
      "grad_norm": 0.8842159509658813,
      "learning_rate": 0.0004986729312899242,
      "loss": 5.0156,
      "step": 499
    },
    {
      "epoch": 0.048828125,
      "grad_norm": 0.8196664452552795,
      "learning_rate": 0.000498665322954612,
      "loss": 5.0078,
      "step": 500
    },
    {
      "epoch": 0.04892578125,
      "grad_norm": 0.774849534034729,
      "learning_rate": 0.0004986576929364646,
      "loss": 5.0273,
      "step": 501
    },
    {
      "epoch": 0.0490234375,
      "grad_norm": 0.6376418471336365,
      "learning_rate": 0.0004986500412362219,
      "loss": 5.0234,
      "step": 502
    },
    {
      "epoch": 0.04912109375,
      "grad_norm": 0.49704745411872864,
      "learning_rate": 0.0004986423678546257,
      "loss": 4.9922,
      "step": 503
    },
    {
      "epoch": 0.04921875,
      "grad_norm": 0.49575215578079224,
      "learning_rate": 0.0004986346727924197,
      "loss": 5.0234,
      "step": 504
    },
    {
      "epoch": 0.04931640625,
      "grad_norm": 0.5091367363929749,
      "learning_rate": 0.0004986269560503501,
      "loss": 4.9961,
      "step": 505
    },
    {
      "epoch": 0.0494140625,
      "grad_norm": 0.7224910855293274,
      "learning_rate": 0.0004986192176291647,
      "loss": 4.9922,
      "step": 506
    },
    {
      "epoch": 0.04951171875,
      "grad_norm": 0.8590059280395508,
      "learning_rate": 0.0004986114575296141,
      "loss": 5.0234,
      "step": 507
    },
    {
      "epoch": 0.049609375,
      "grad_norm": 0.7906845808029175,
      "learning_rate": 0.0004986036757524501,
      "loss": 5.0195,
      "step": 508
    },
    {
      "epoch": 0.04970703125,
      "grad_norm": 0.6573899388313293,
      "learning_rate": 0.0004985958722984275,
      "loss": 5.0117,
      "step": 509
    },
    {
      "epoch": 0.0498046875,
      "grad_norm": 0.5708054900169373,
      "learning_rate": 0.0004985880471683026,
      "loss": 5.0,
      "step": 510
    },
    {
      "epoch": 0.04990234375,
      "grad_norm": 0.6391012668609619,
      "learning_rate": 0.000498580200362834,
      "loss": 5.0156,
      "step": 511
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.6893157362937927,
      "learning_rate": 0.0004985723318827824,
      "loss": 5.0078,
      "step": 512
    },
    {
      "epoch": 0.05009765625,
      "grad_norm": 0.7473337054252625,
      "learning_rate": 0.0004985644417289107,
      "loss": 5.0352,
      "step": 513
    },
    {
      "epoch": 0.0501953125,
      "grad_norm": 0.6992818713188171,
      "learning_rate": 0.0004985565299019836,
      "loss": 4.9766,
      "step": 514
    },
    {
      "epoch": 0.05029296875,
      "grad_norm": 0.5503939986228943,
      "learning_rate": 0.0004985485964027682,
      "loss": 5.0156,
      "step": 515
    },
    {
      "epoch": 0.050390625,
      "grad_norm": 0.5531403422355652,
      "learning_rate": 0.0004985406412320337,
      "loss": 5.0234,
      "step": 516
    },
    {
      "epoch": 0.05048828125,
      "grad_norm": 0.5232397317886353,
      "learning_rate": 0.0004985326643905511,
      "loss": 4.9922,
      "step": 517
    },
    {
      "epoch": 0.0505859375,
      "grad_norm": 0.5153787732124329,
      "learning_rate": 0.0004985246658790939,
      "loss": 4.9922,
      "step": 518
    },
    {
      "epoch": 0.05068359375,
      "grad_norm": 0.7395737767219543,
      "learning_rate": 0.0004985166456984375,
      "loss": 4.9961,
      "step": 519
    },
    {
      "epoch": 0.05078125,
      "grad_norm": 0.7297258973121643,
      "learning_rate": 0.0004985086038493591,
      "loss": 5.0195,
      "step": 520
    },
    {
      "epoch": 0.05087890625,
      "grad_norm": 0.8792772889137268,
      "learning_rate": 0.0004985005403326387,
      "loss": 5.0195,
      "step": 521
    },
    {
      "epoch": 0.0509765625,
      "grad_norm": 0.8485317230224609,
      "learning_rate": 0.0004984924551490577,
      "loss": 5.0039,
      "step": 522
    },
    {
      "epoch": 0.05107421875,
      "grad_norm": 0.7504170536994934,
      "learning_rate": 0.0004984843482994001,
      "loss": 5.0391,
      "step": 523
    },
    {
      "epoch": 0.051171875,
      "grad_norm": 0.6931923031806946,
      "learning_rate": 0.0004984762197844516,
      "loss": 4.9883,
      "step": 524
    },
    {
      "epoch": 0.05126953125,
      "grad_norm": 0.7201303839683533,
      "learning_rate": 0.0004984680696050004,
      "loss": 4.9844,
      "step": 525
    },
    {
      "epoch": 0.0513671875,
      "grad_norm": 0.8321727514266968,
      "learning_rate": 0.0004984598977618366,
      "loss": 5.0234,
      "step": 526
    },
    {
      "epoch": 0.05146484375,
      "grad_norm": 1.0283933877944946,
      "learning_rate": 0.0004984517042557523,
      "loss": 5.0156,
      "step": 527
    },
    {
      "epoch": 0.0515625,
      "grad_norm": 1.3810787200927734,
      "learning_rate": 0.0004984434890875417,
      "loss": 5.0273,
      "step": 528
    },
    {
      "epoch": 0.05166015625,
      "grad_norm": 0.75733482837677,
      "learning_rate": 0.0004984352522580015,
      "loss": 4.9844,
      "step": 529
    },
    {
      "epoch": 0.0517578125,
      "grad_norm": 0.7140693068504333,
      "learning_rate": 0.0004984269937679301,
      "loss": 4.9961,
      "step": 530
    },
    {
      "epoch": 0.05185546875,
      "grad_norm": 0.9317624568939209,
      "learning_rate": 0.000498418713618128,
      "loss": 4.9805,
      "step": 531
    },
    {
      "epoch": 0.051953125,
      "grad_norm": 0.8527510762214661,
      "learning_rate": 0.0004984104118093979,
      "loss": 4.9961,
      "step": 532
    },
    {
      "epoch": 0.05205078125,
      "grad_norm": 0.8085970878601074,
      "learning_rate": 0.0004984020883425447,
      "loss": 4.9883,
      "step": 533
    },
    {
      "epoch": 0.0521484375,
      "grad_norm": 0.8414132595062256,
      "learning_rate": 0.0004983937432183754,
      "loss": 4.9727,
      "step": 534
    },
    {
      "epoch": 0.05224609375,
      "grad_norm": 0.7883987426757812,
      "learning_rate": 0.0004983853764376987,
      "loss": 4.9766,
      "step": 535
    },
    {
      "epoch": 0.05234375,
      "grad_norm": 0.8301931619644165,
      "learning_rate": 0.000498376988001326,
      "loss": 4.9688,
      "step": 536
    },
    {
      "epoch": 0.05244140625,
      "grad_norm": 0.815565288066864,
      "learning_rate": 0.0004983685779100702,
      "loss": 5.0273,
      "step": 537
    },
    {
      "epoch": 0.0525390625,
      "grad_norm": 0.7249122262001038,
      "learning_rate": 0.0004983601461647469,
      "loss": 5.0234,
      "step": 538
    },
    {
      "epoch": 0.05263671875,
      "grad_norm": 0.6938775181770325,
      "learning_rate": 0.0004983516927661733,
      "loss": 4.9805,
      "step": 539
    },
    {
      "epoch": 0.052734375,
      "grad_norm": 0.6271894574165344,
      "learning_rate": 0.0004983432177151691,
      "loss": 4.9922,
      "step": 540
    },
    {
      "epoch": 0.05283203125,
      "grad_norm": 0.5879946351051331,
      "learning_rate": 0.0004983347210125558,
      "loss": 4.9883,
      "step": 541
    },
    {
      "epoch": 0.0529296875,
      "grad_norm": 0.6193601489067078,
      "learning_rate": 0.0004983262026591569,
      "loss": 4.9688,
      "step": 542
    },
    {
      "epoch": 0.05302734375,
      "grad_norm": 0.7117279767990112,
      "learning_rate": 0.0004983176626557986,
      "loss": 5.0195,
      "step": 543
    },
    {
      "epoch": 0.053125,
      "grad_norm": 0.6014550924301147,
      "learning_rate": 0.0004983091010033083,
      "loss": 5.0,
      "step": 544
    },
    {
      "epoch": 0.05322265625,
      "grad_norm": 0.5970187783241272,
      "learning_rate": 0.0004983005177025164,
      "loss": 4.9688,
      "step": 545
    },
    {
      "epoch": 0.0533203125,
      "grad_norm": 0.602258563041687,
      "learning_rate": 0.0004982919127542549,
      "loss": 5.0156,
      "step": 546
    },
    {
      "epoch": 0.05341796875,
      "grad_norm": 0.5443257689476013,
      "learning_rate": 0.0004982832861593579,
      "loss": 4.9805,
      "step": 547
    },
    {
      "epoch": 0.053515625,
      "grad_norm": 0.5458142161369324,
      "learning_rate": 0.0004982746379186616,
      "loss": 4.9531,
      "step": 548
    },
    {
      "epoch": 0.05361328125,
      "grad_norm": 0.5225309729576111,
      "learning_rate": 0.0004982659680330047,
      "loss": 5.0039,
      "step": 549
    },
    {
      "epoch": 0.0537109375,
      "grad_norm": 0.5642147660255432,
      "learning_rate": 0.0004982572765032275,
      "loss": 4.9961,
      "step": 550
    },
    {
      "epoch": 0.05380859375,
      "grad_norm": 0.6520267724990845,
      "learning_rate": 0.0004982485633301725,
      "loss": 5.0078,
      "step": 551
    },
    {
      "epoch": 0.05390625,
      "grad_norm": 0.7051550149917603,
      "learning_rate": 0.0004982398285146846,
      "loss": 5.0,
      "step": 552
    },
    {
      "epoch": 0.05400390625,
      "grad_norm": 0.6687464714050293,
      "learning_rate": 0.0004982310720576103,
      "loss": 4.9766,
      "step": 553
    },
    {
      "epoch": 0.0541015625,
      "grad_norm": 0.60595703125,
      "learning_rate": 0.0004982222939597989,
      "loss": 4.957,
      "step": 554
    },
    {
      "epoch": 0.05419921875,
      "grad_norm": 0.5594586133956909,
      "learning_rate": 0.0004982134942221009,
      "loss": 4.9883,
      "step": 555
    },
    {
      "epoch": 0.054296875,
      "grad_norm": 0.5148446559906006,
      "learning_rate": 0.0004982046728453696,
      "loss": 4.9844,
      "step": 556
    },
    {
      "epoch": 0.05439453125,
      "grad_norm": 0.5946763753890991,
      "learning_rate": 0.0004981958298304602,
      "loss": 5.0156,
      "step": 557
    },
    {
      "epoch": 0.0544921875,
      "grad_norm": 0.716316282749176,
      "learning_rate": 0.0004981869651782299,
      "loss": 4.9805,
      "step": 558
    },
    {
      "epoch": 0.05458984375,
      "grad_norm": 0.794476330280304,
      "learning_rate": 0.0004981780788895382,
      "loss": 5.0117,
      "step": 559
    },
    {
      "epoch": 0.0546875,
      "grad_norm": 0.7105295658111572,
      "learning_rate": 0.0004981691709652464,
      "loss": 4.9766,
      "step": 560
    },
    {
      "epoch": 0.05478515625,
      "grad_norm": 0.5912784337997437,
      "learning_rate": 0.0004981602414062181,
      "loss": 4.9414,
      "step": 561
    },
    {
      "epoch": 0.0548828125,
      "grad_norm": 0.5801540613174438,
      "learning_rate": 0.000498151290213319,
      "loss": 4.9883,
      "step": 562
    },
    {
      "epoch": 0.05498046875,
      "grad_norm": 0.6369305849075317,
      "learning_rate": 0.0004981423173874169,
      "loss": 5.0039,
      "step": 563
    },
    {
      "epoch": 0.055078125,
      "grad_norm": 0.6735507845878601,
      "learning_rate": 0.0004981333229293816,
      "loss": 4.9648,
      "step": 564
    },
    {
      "epoch": 0.05517578125,
      "grad_norm": 0.6315239667892456,
      "learning_rate": 0.000498124306840085,
      "loss": 5.0078,
      "step": 565
    },
    {
      "epoch": 0.0552734375,
      "grad_norm": 0.710253119468689,
      "learning_rate": 0.0004981152691204011,
      "loss": 4.9844,
      "step": 566
    },
    {
      "epoch": 0.05537109375,
      "grad_norm": 0.6913606524467468,
      "learning_rate": 0.0004981062097712064,
      "loss": 4.9766,
      "step": 567
    },
    {
      "epoch": 0.05546875,
      "grad_norm": 0.5899546146392822,
      "learning_rate": 0.0004980971287933787,
      "loss": 4.9688,
      "step": 568
    },
    {
      "epoch": 0.05556640625,
      "grad_norm": 0.5400623083114624,
      "learning_rate": 0.0004980880261877986,
      "loss": 4.9805,
      "step": 569
    },
    {
      "epoch": 0.0556640625,
      "grad_norm": 0.5193256139755249,
      "learning_rate": 0.0004980789019553484,
      "loss": 4.9453,
      "step": 570
    },
    {
      "epoch": 0.05576171875,
      "grad_norm": 0.5622848272323608,
      "learning_rate": 0.0004980697560969127,
      "loss": 4.957,
      "step": 571
    },
    {
      "epoch": 0.055859375,
      "grad_norm": 0.6163820028305054,
      "learning_rate": 0.0004980605886133782,
      "loss": 4.9766,
      "step": 572
    },
    {
      "epoch": 0.05595703125,
      "grad_norm": 0.6021759510040283,
      "learning_rate": 0.0004980513995056334,
      "loss": 4.957,
      "step": 573
    },
    {
      "epoch": 0.0560546875,
      "grad_norm": 0.5321788191795349,
      "learning_rate": 0.0004980421887745695,
      "loss": 4.9805,
      "step": 574
    },
    {
      "epoch": 0.05615234375,
      "grad_norm": 0.4939315617084503,
      "learning_rate": 0.0004980329564210792,
      "loss": 5.0195,
      "step": 575
    },
    {
      "epoch": 0.05625,
      "grad_norm": 0.4567241370677948,
      "learning_rate": 0.0004980237024460573,
      "loss": 4.9648,
      "step": 576
    },
    {
      "epoch": 0.05634765625,
      "grad_norm": 0.44762229919433594,
      "learning_rate": 0.0004980144268504012,
      "loss": 4.9961,
      "step": 577
    },
    {
      "epoch": 0.0564453125,
      "grad_norm": 0.5556433200836182,
      "learning_rate": 0.00049800512963501,
      "loss": 4.9844,
      "step": 578
    },
    {
      "epoch": 0.05654296875,
      "grad_norm": 0.6940642595291138,
      "learning_rate": 0.0004979958108007851,
      "loss": 4.9844,
      "step": 579
    },
    {
      "epoch": 0.056640625,
      "grad_norm": 0.7792614102363586,
      "learning_rate": 0.0004979864703486297,
      "loss": 4.9648,
      "step": 580
    },
    {
      "epoch": 0.05673828125,
      "grad_norm": 0.8071824908256531,
      "learning_rate": 0.0004979771082794495,
      "loss": 4.9727,
      "step": 581
    },
    {
      "epoch": 0.0568359375,
      "grad_norm": 0.9120080471038818,
      "learning_rate": 0.0004979677245941519,
      "loss": 4.9883,
      "step": 582
    },
    {
      "epoch": 0.05693359375,
      "grad_norm": 0.9239040017127991,
      "learning_rate": 0.0004979583192936468,
      "loss": 4.9609,
      "step": 583
    },
    {
      "epoch": 0.05703125,
      "grad_norm": 1.002406120300293,
      "learning_rate": 0.0004979488923788459,
      "loss": 4.9766,
      "step": 584
    },
    {
      "epoch": 0.05712890625,
      "grad_norm": 0.8661404848098755,
      "learning_rate": 0.0004979394438506629,
      "loss": 5.0,
      "step": 585
    },
    {
      "epoch": 0.0572265625,
      "grad_norm": 0.6225184798240662,
      "learning_rate": 0.000497929973710014,
      "loss": 4.9727,
      "step": 586
    },
    {
      "epoch": 0.05732421875,
      "grad_norm": 0.5944101810455322,
      "learning_rate": 0.0004979204819578172,
      "loss": 4.9414,
      "step": 587
    },
    {
      "epoch": 0.057421875,
      "grad_norm": 0.5297685265541077,
      "learning_rate": 0.0004979109685949926,
      "loss": 4.9844,
      "step": 588
    },
    {
      "epoch": 0.05751953125,
      "grad_norm": 0.43607059121131897,
      "learning_rate": 0.0004979014336224625,
      "loss": 4.9961,
      "step": 589
    },
    {
      "epoch": 0.0576171875,
      "grad_norm": 0.48334574699401855,
      "learning_rate": 0.0004978918770411513,
      "loss": 4.9648,
      "step": 590
    },
    {
      "epoch": 0.05771484375,
      "grad_norm": 0.5257386565208435,
      "learning_rate": 0.0004978822988519853,
      "loss": 4.9766,
      "step": 591
    },
    {
      "epoch": 0.0578125,
      "grad_norm": 0.6425731182098389,
      "learning_rate": 0.0004978726990558931,
      "loss": 4.9492,
      "step": 592
    },
    {
      "epoch": 0.05791015625,
      "grad_norm": 1.0080450773239136,
      "learning_rate": 0.0004978630776538056,
      "loss": 4.9727,
      "step": 593
    },
    {
      "epoch": 0.0580078125,
      "grad_norm": 1.2617547512054443,
      "learning_rate": 0.000497853434646655,
      "loss": 5.0156,
      "step": 594
    },
    {
      "epoch": 0.05810546875,
      "grad_norm": 0.8185104727745056,
      "learning_rate": 0.0004978437700353766,
      "loss": 4.9648,
      "step": 595
    },
    {
      "epoch": 0.058203125,
      "grad_norm": 0.996583104133606,
      "learning_rate": 0.0004978340838209071,
      "loss": 4.9336,
      "step": 596
    },
    {
      "epoch": 0.05830078125,
      "grad_norm": 0.8999793529510498,
      "learning_rate": 0.0004978243760041855,
      "loss": 4.9805,
      "step": 597
    },
    {
      "epoch": 0.0583984375,
      "grad_norm": 0.7666017413139343,
      "learning_rate": 0.0004978146465861531,
      "loss": 4.918,
      "step": 598
    },
    {
      "epoch": 0.05849609375,
      "grad_norm": 0.7835460901260376,
      "learning_rate": 0.0004978048955677529,
      "loss": 4.9766,
      "step": 599
    },
    {
      "epoch": 0.05859375,
      "grad_norm": 0.7298296689987183,
      "learning_rate": 0.0004977951229499302,
      "loss": 4.9648,
      "step": 600
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 10240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.673503567131443e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}