{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1171875,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.765625e-05,
      "grad_norm": 13.125093460083008,
      "learning_rate": 1.6666666666666669e-06,
      "loss": 6.0473,
      "step": 1
    },
    {
      "epoch": 0.0001953125,
      "grad_norm": 13.109691619873047,
      "learning_rate": 3.3333333333333337e-06,
      "loss": 6.0151,
      "step": 2
    },
    {
      "epoch": 0.00029296875,
      "grad_norm": 12.975897789001465,
      "learning_rate": 5e-06,
      "loss": 6.0374,
      "step": 3
    },
    {
      "epoch": 0.000390625,
      "grad_norm": 12.861470222473145,
      "learning_rate": 6.6666666666666675e-06,
      "loss": 5.9534,
      "step": 4
    },
    {
      "epoch": 0.00048828125,
      "grad_norm": 11.551366806030273,
      "learning_rate": 8.333333333333334e-06,
      "loss": 5.7805,
      "step": 5
    },
    {
      "epoch": 0.0005859375,
      "grad_norm": 7.968364238739014,
      "learning_rate": 1e-05,
      "loss": 5.5664,
      "step": 6
    },
    {
      "epoch": 0.00068359375,
      "grad_norm": 6.854646682739258,
      "learning_rate": 1.1666666666666668e-05,
      "loss": 5.4982,
      "step": 7
    },
    {
      "epoch": 0.00078125,
      "grad_norm": 3.759798049926758,
      "learning_rate": 1.3333333333333335e-05,
      "loss": 5.1824,
      "step": 8
    },
    {
      "epoch": 0.00087890625,
      "grad_norm": 3.48822283744812,
      "learning_rate": 1.5e-05,
      "loss": 5.0667,
      "step": 9
    },
    {
      "epoch": 0.0009765625,
      "grad_norm": 3.1011886596679688,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 5.0028,
      "step": 10
    },
    {
      "epoch": 0.00107421875,
      "grad_norm": 2.5868849754333496,
      "learning_rate": 1.8333333333333333e-05,
      "loss": 4.7787,
      "step": 11
    },
    {
      "epoch": 0.001171875,
      "grad_norm": 2.378497838973999,
      "learning_rate": 2e-05,
      "loss": 4.6855,
      "step": 12
    },
    {
      "epoch": 0.00126953125,
      "grad_norm": 2.2101738452911377,
      "learning_rate": 2.1666666666666667e-05,
      "loss": 4.6042,
      "step": 13
    },
    {
      "epoch": 0.0013671875,
      "grad_norm": 1.9938961267471313,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 4.3843,
      "step": 14
    },
    {
      "epoch": 0.00146484375,
      "grad_norm": 1.9345463514328003,
      "learning_rate": 2.5e-05,
      "loss": 4.2548,
      "step": 15
    },
    {
      "epoch": 0.0015625,
      "grad_norm": 1.7730776071548462,
      "learning_rate": 2.666666666666667e-05,
      "loss": 4.1363,
      "step": 16
    },
    {
      "epoch": 0.00166015625,
      "grad_norm": 1.58334481716156,
      "learning_rate": 2.8333333333333332e-05,
      "loss": 3.9704,
      "step": 17
    },
    {
      "epoch": 0.0017578125,
      "grad_norm": 1.4827001094818115,
      "learning_rate": 3e-05,
      "loss": 3.81,
      "step": 18
    },
    {
      "epoch": 0.00185546875,
      "grad_norm": 1.4140430688858032,
      "learning_rate": 3.166666666666667e-05,
      "loss": 3.7305,
      "step": 19
    },
    {
      "epoch": 0.001953125,
      "grad_norm": 1.3934496641159058,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.5375,
      "step": 20
    },
    {
      "epoch": 0.00205078125,
      "grad_norm": 1.3384771347045898,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 3.5217,
      "step": 21
    },
    {
      "epoch": 0.0021484375,
      "grad_norm": 1.2228978872299194,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 3.3742,
      "step": 22
    },
    {
      "epoch": 0.00224609375,
      "grad_norm": 1.1775028705596924,
      "learning_rate": 3.8333333333333334e-05,
      "loss": 3.2626,
      "step": 23
    },
    {
      "epoch": 0.00234375,
      "grad_norm": 1.0886842012405396,
      "learning_rate": 4e-05,
      "loss": 3.1864,
      "step": 24
    },
    {
      "epoch": 0.00244140625,
      "grad_norm": 1.0981535911560059,
      "learning_rate": 4.1666666666666665e-05,
      "loss": 3.0962,
      "step": 25
    },
    {
      "epoch": 0.0025390625,
      "grad_norm": 1.009294867515564,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 3.0507,
      "step": 26
    },
    {
      "epoch": 0.00263671875,
      "grad_norm": 0.9390103816986084,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 2.9579,
      "step": 27
    },
    {
      "epoch": 0.002734375,
      "grad_norm": 0.8647847175598145,
      "learning_rate": 4.666666666666667e-05,
      "loss": 2.8166,
      "step": 28
    },
    {
      "epoch": 0.00283203125,
      "grad_norm": 0.8606237769126892,
      "learning_rate": 4.8333333333333334e-05,
      "loss": 2.7919,
      "step": 29
    },
    {
      "epoch": 0.0029296875,
      "grad_norm": 0.8069576025009155,
      "learning_rate": 5e-05,
      "loss": 2.7426,
      "step": 30
    },
    {
      "epoch": 0.00302734375,
      "grad_norm": 0.7007808685302734,
      "learning_rate": 5.1666666666666664e-05,
      "loss": 2.6926,
      "step": 31
    },
    {
      "epoch": 0.003125,
      "grad_norm": 0.6825646162033081,
      "learning_rate": 5.333333333333334e-05,
      "loss": 2.6783,
      "step": 32
    },
    {
      "epoch": 0.00322265625,
      "grad_norm": 0.7054751515388489,
      "learning_rate": 5.5e-05,
      "loss": 2.6239,
      "step": 33
    },
    {
      "epoch": 0.0033203125,
      "grad_norm": 0.7101700305938721,
      "learning_rate": 5.6666666666666664e-05,
      "loss": 2.5993,
      "step": 34
    },
    {
      "epoch": 0.00341796875,
      "grad_norm": 0.56828773021698,
      "learning_rate": 5.833333333333333e-05,
      "loss": 2.5258,
      "step": 35
    },
    {
      "epoch": 0.003515625,
      "grad_norm": 0.5513983368873596,
      "learning_rate": 6e-05,
      "loss": 2.5018,
      "step": 36
    },
    {
      "epoch": 0.00361328125,
      "grad_norm": 0.573391318321228,
      "learning_rate": 6.166666666666667e-05,
      "loss": 2.4881,
      "step": 37
    },
    {
      "epoch": 0.0037109375,
      "grad_norm": 0.4520920515060425,
      "learning_rate": 6.333333333333335e-05,
      "loss": 2.4489,
      "step": 38
    },
    {
      "epoch": 0.00380859375,
      "grad_norm": 0.43038809299468994,
      "learning_rate": 6.500000000000001e-05,
      "loss": 2.4387,
      "step": 39
    },
    {
      "epoch": 0.00390625,
      "grad_norm": 0.4071808457374573,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.4261,
      "step": 40
    },
    {
      "epoch": 0.00400390625,
      "grad_norm": 0.3631410300731659,
      "learning_rate": 6.833333333333333e-05,
      "loss": 2.3656,
      "step": 41
    },
    {
      "epoch": 0.0041015625,
      "grad_norm": 0.33457818627357483,
      "learning_rate": 7.000000000000001e-05,
      "loss": 2.4011,
      "step": 42
    },
    {
      "epoch": 0.00419921875,
      "grad_norm": 0.3582305610179901,
      "learning_rate": 7.166666666666667e-05,
      "loss": 2.3662,
      "step": 43
    },
    {
      "epoch": 0.004296875,
      "grad_norm": 0.4090467691421509,
      "learning_rate": 7.333333333333333e-05,
      "loss": 2.3282,
      "step": 44
    },
    {
      "epoch": 0.00439453125,
      "grad_norm": 0.34438556432724,
      "learning_rate": 7.5e-05,
      "loss": 2.2991,
      "step": 45
    },
    {
      "epoch": 0.0044921875,
      "grad_norm": 0.29381102323532104,
      "learning_rate": 7.666666666666667e-05,
      "loss": 2.2506,
      "step": 46
    },
    {
      "epoch": 0.00458984375,
      "grad_norm": 0.4019562304019928,
      "learning_rate": 7.833333333333334e-05,
      "loss": 2.2494,
      "step": 47
    },
    {
      "epoch": 0.0046875,
      "grad_norm": 0.3183911144733429,
      "learning_rate": 8e-05,
      "loss": 2.2853,
      "step": 48
    },
    {
      "epoch": 0.00478515625,
      "grad_norm": 0.33041393756866455,
      "learning_rate": 8.166666666666667e-05,
      "loss": 2.2251,
      "step": 49
    },
    {
      "epoch": 0.0048828125,
      "grad_norm": 0.28936123847961426,
      "learning_rate": 8.333333333333333e-05,
      "loss": 2.2308,
      "step": 50
    },
    {
      "epoch": 0.00498046875,
      "grad_norm": 0.36125779151916504,
      "learning_rate": 8.5e-05,
      "loss": 2.2473,
      "step": 51
    },
    {
      "epoch": 0.005078125,
      "grad_norm": 0.2832348942756653,
      "learning_rate": 8.666666666666667e-05,
      "loss": 2.201,
      "step": 52
    },
    {
      "epoch": 0.00517578125,
      "grad_norm": 0.3250133693218231,
      "learning_rate": 8.833333333333333e-05,
      "loss": 2.1596,
      "step": 53
    },
    {
      "epoch": 0.0052734375,
      "grad_norm": 0.31502828001976013,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.2183,
      "step": 54
    },
    {
      "epoch": 0.00537109375,
      "grad_norm": 0.33068645000457764,
      "learning_rate": 9.166666666666667e-05,
      "loss": 2.2254,
      "step": 55
    },
    {
      "epoch": 0.00546875,
      "grad_norm": 0.30684661865234375,
      "learning_rate": 9.333333333333334e-05,
      "loss": 2.2572,
      "step": 56
    },
    {
      "epoch": 0.00556640625,
      "grad_norm": 0.31540846824645996,
      "learning_rate": 9.5e-05,
      "loss": 2.1594,
      "step": 57
    },
    {
      "epoch": 0.0056640625,
      "grad_norm": 0.23259752988815308,
      "learning_rate": 9.666666666666667e-05,
      "loss": 2.172,
      "step": 58
    },
    {
      "epoch": 0.00576171875,
      "grad_norm": 0.26666638255119324,
      "learning_rate": 9.833333333333333e-05,
      "loss": 2.1961,
      "step": 59
    },
    {
      "epoch": 0.005859375,
      "grad_norm": 0.26295527815818787,
      "learning_rate": 0.0001,
      "loss": 2.1811,
      "step": 60
    },
    {
      "epoch": 0.00595703125,
      "grad_norm": 0.2302207201719284,
      "learning_rate": 0.00010166666666666667,
      "loss": 2.1431,
      "step": 61
    },
    {
      "epoch": 0.0060546875,
      "grad_norm": 0.468537837266922,
      "learning_rate": 0.00010333333333333333,
      "loss": 2.133,
      "step": 62
    },
    {
      "epoch": 0.00615234375,
      "grad_norm": 0.27946797013282776,
      "learning_rate": 0.000105,
      "loss": 2.1917,
      "step": 63
    },
    {
      "epoch": 0.00625,
      "grad_norm": 0.26789286732673645,
      "learning_rate": 0.00010666666666666668,
      "loss": 2.1417,
      "step": 64
    },
    {
      "epoch": 0.00634765625,
      "grad_norm": 0.22977805137634277,
      "learning_rate": 0.00010833333333333334,
      "loss": 2.1371,
      "step": 65
    },
    {
      "epoch": 0.0064453125,
      "grad_norm": 0.2590682804584503,
      "learning_rate": 0.00011,
      "loss": 2.113,
      "step": 66
    },
    {
      "epoch": 0.00654296875,
      "grad_norm": 0.2660805583000183,
      "learning_rate": 0.00011166666666666667,
      "loss": 2.1346,
      "step": 67
    },
    {
      "epoch": 0.006640625,
      "grad_norm": 0.24538874626159668,
      "learning_rate": 0.00011333333333333333,
      "loss": 2.1078,
      "step": 68
    },
    {
      "epoch": 0.00673828125,
      "grad_norm": 0.2986001968383789,
      "learning_rate": 0.000115,
      "loss": 2.1048,
      "step": 69
    },
    {
      "epoch": 0.0068359375,
      "grad_norm": 0.30193910002708435,
      "learning_rate": 0.00011666666666666667,
      "loss": 2.135,
      "step": 70
    },
    {
      "epoch": 0.00693359375,
      "grad_norm": 0.25153177976608276,
      "learning_rate": 0.00011833333333333334,
      "loss": 2.1101,
      "step": 71
    },
    {
      "epoch": 0.00703125,
      "grad_norm": 0.7685809135437012,
      "learning_rate": 0.00012,
      "loss": 2.0833,
      "step": 72
    },
    {
      "epoch": 0.00712890625,
      "grad_norm": 0.24468126893043518,
      "learning_rate": 0.00012166666666666668,
      "loss": 2.1409,
      "step": 73
    },
    {
      "epoch": 0.0072265625,
      "grad_norm": 0.3070752024650574,
      "learning_rate": 0.00012333333333333334,
      "loss": 2.1402,
      "step": 74
    },
    {
      "epoch": 0.00732421875,
      "grad_norm": 0.352273553609848,
      "learning_rate": 0.000125,
      "loss": 2.171,
      "step": 75
    },
    {
      "epoch": 0.007421875,
      "grad_norm": 0.34806111454963684,
      "learning_rate": 0.0001266666666666667,
      "loss": 2.1155,
      "step": 76
    },
    {
      "epoch": 0.00751953125,
      "grad_norm": 0.317414253950119,
      "learning_rate": 0.00012833333333333333,
      "loss": 2.0812,
      "step": 77
    },
    {
      "epoch": 0.0076171875,
      "grad_norm": 0.3320539891719818,
      "learning_rate": 0.00013000000000000002,
      "loss": 2.0987,
      "step": 78
    },
    {
      "epoch": 0.00771484375,
      "grad_norm": 0.3315901756286621,
      "learning_rate": 0.00013166666666666665,
      "loss": 2.1025,
      "step": 79
    },
    {
      "epoch": 0.0078125,
      "grad_norm": 0.29021286964416504,
      "learning_rate": 0.00013333333333333334,
      "loss": 2.1474,
      "step": 80
    },
    {
      "epoch": 0.00791015625,
      "grad_norm": 0.2593044936656952,
      "learning_rate": 0.000135,
      "loss": 2.0667,
      "step": 81
    },
    {
      "epoch": 0.0080078125,
      "grad_norm": 0.3192054033279419,
      "learning_rate": 0.00013666666666666666,
      "loss": 2.0764,
      "step": 82
    },
    {
      "epoch": 0.00810546875,
      "grad_norm": 0.26053664088249207,
      "learning_rate": 0.00013833333333333333,
      "loss": 2.0698,
      "step": 83
    },
    {
      "epoch": 0.008203125,
      "grad_norm": 0.24790963530540466,
      "learning_rate": 0.00014000000000000001,
      "loss": 2.124,
      "step": 84
    },
    {
      "epoch": 0.00830078125,
      "grad_norm": 0.2546316087245941,
      "learning_rate": 0.00014166666666666668,
      "loss": 2.1025,
      "step": 85
    },
    {
      "epoch": 0.0083984375,
      "grad_norm": 0.22275258600711823,
      "learning_rate": 0.00014333333333333334,
      "loss": 2.0778,
      "step": 86
    },
    {
      "epoch": 0.00849609375,
      "grad_norm": 0.22855599224567413,
      "learning_rate": 0.000145,
      "loss": 2.1113,
      "step": 87
    },
    {
      "epoch": 0.00859375,
      "grad_norm": 0.2456902116537094,
      "learning_rate": 0.00014666666666666666,
      "loss": 2.1399,
      "step": 88
    },
    {
      "epoch": 0.00869140625,
      "grad_norm": 0.22144420444965363,
      "learning_rate": 0.00014833333333333335,
      "loss": 2.0211,
      "step": 89
    },
    {
      "epoch": 0.0087890625,
      "grad_norm": 0.254894495010376,
      "learning_rate": 0.00015,
      "loss": 2.1382,
      "step": 90
    },
    {
      "epoch": 0.00888671875,
      "grad_norm": 0.2729082703590393,
      "learning_rate": 0.00015166666666666668,
      "loss": 2.1271,
      "step": 91
    },
    {
      "epoch": 0.008984375,
      "grad_norm": 0.2564642131328583,
      "learning_rate": 0.00015333333333333334,
      "loss": 2.0423,
      "step": 92
    },
    {
      "epoch": 0.00908203125,
      "grad_norm": 0.24927419424057007,
      "learning_rate": 0.000155,
      "loss": 2.0603,
      "step": 93
    },
    {
      "epoch": 0.0091796875,
      "grad_norm": 0.2591923475265503,
      "learning_rate": 0.0001566666666666667,
      "loss": 2.0522,
      "step": 94
    },
    {
      "epoch": 0.00927734375,
      "grad_norm": 0.3350547254085541,
      "learning_rate": 0.00015833333333333332,
      "loss": 2.1095,
      "step": 95
    },
    {
      "epoch": 0.009375,
      "grad_norm": 0.30227839946746826,
      "learning_rate": 0.00016,
      "loss": 2.121,
      "step": 96
    },
    {
      "epoch": 0.00947265625,
      "grad_norm": 0.3027198314666748,
      "learning_rate": 0.00016166666666666665,
      "loss": 2.0288,
      "step": 97
    },
    {
      "epoch": 0.0095703125,
      "grad_norm": 0.29791951179504395,
      "learning_rate": 0.00016333333333333334,
      "loss": 2.0471,
      "step": 98
    },
    {
      "epoch": 0.00966796875,
      "grad_norm": 0.30918803811073303,
      "learning_rate": 0.000165,
      "loss": 2.1036,
      "step": 99
    },
    {
      "epoch": 0.009765625,
      "grad_norm": 0.2510216534137726,
      "learning_rate": 0.00016666666666666666,
      "loss": 2.0217,
      "step": 100
    },
    {
      "epoch": 0.00986328125,
      "grad_norm": 0.288231760263443,
      "learning_rate": 0.00016833333333333335,
      "loss": 2.0178,
      "step": 101
    },
    {
      "epoch": 0.0099609375,
      "grad_norm": 0.3326691687107086,
      "learning_rate": 0.00017,
      "loss": 2.0947,
      "step": 102
    },
    {
      "epoch": 0.01005859375,
      "grad_norm": 0.3552946150302887,
      "learning_rate": 0.00017166666666666667,
      "loss": 1.9953,
      "step": 103
    },
    {
      "epoch": 0.01015625,
      "grad_norm": 0.34882935881614685,
      "learning_rate": 0.00017333333333333334,
      "loss": 2.1223,
      "step": 104
    },
    {
      "epoch": 0.01025390625,
      "grad_norm": 0.35487979650497437,
      "learning_rate": 0.000175,
      "loss": 2.0599,
      "step": 105
    },
    {
      "epoch": 0.0103515625,
      "grad_norm": 0.33561578392982483,
      "learning_rate": 0.00017666666666666666,
      "loss": 2.0398,
      "step": 106
    },
    {
      "epoch": 0.01044921875,
      "grad_norm": 0.27415409684181213,
      "learning_rate": 0.00017833333333333335,
      "loss": 2.0982,
      "step": 107
    },
    {
      "epoch": 0.010546875,
      "grad_norm": 0.28592920303344727,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.0571,
      "step": 108
    },
    {
      "epoch": 0.01064453125,
      "grad_norm": 0.3228552043437958,
      "learning_rate": 0.00018166666666666667,
      "loss": 1.9923,
      "step": 109
    },
    {
      "epoch": 0.0107421875,
      "grad_norm": 0.29005661606788635,
      "learning_rate": 0.00018333333333333334,
      "loss": 2.0394,
      "step": 110
    },
    {
      "epoch": 0.01083984375,
      "grad_norm": 0.36677825450897217,
      "learning_rate": 0.000185,
      "loss": 2.0153,
      "step": 111
    },
    {
      "epoch": 0.0109375,
      "grad_norm": 0.2562806308269501,
      "learning_rate": 0.0001866666666666667,
      "loss": 2.05,
      "step": 112
    },
    {
      "epoch": 0.01103515625,
      "grad_norm": 0.2748093008995056,
      "learning_rate": 0.00018833333333333332,
      "loss": 2.0449,
      "step": 113
    },
    {
      "epoch": 0.0111328125,
      "grad_norm": 0.3924459218978882,
      "learning_rate": 0.00019,
      "loss": 2.0409,
      "step": 114
    },
    {
      "epoch": 0.01123046875,
      "grad_norm": 0.4368191063404083,
      "learning_rate": 0.00019166666666666667,
      "loss": 2.0178,
      "step": 115
    },
    {
      "epoch": 0.011328125,
      "grad_norm": 0.4236035943031311,
      "learning_rate": 0.00019333333333333333,
      "loss": 2.0518,
      "step": 116
    },
    {
      "epoch": 0.01142578125,
      "grad_norm": 0.28912851214408875,
      "learning_rate": 0.00019500000000000002,
      "loss": 2.0058,
      "step": 117
    },
    {
      "epoch": 0.0115234375,
      "grad_norm": 0.38847798109054565,
      "learning_rate": 0.00019666666666666666,
      "loss": 2.0818,
      "step": 118
    },
    {
      "epoch": 0.01162109375,
      "grad_norm": 0.29429811239242554,
      "learning_rate": 0.00019833333333333335,
      "loss": 2.004,
      "step": 119
    },
    {
      "epoch": 0.01171875,
      "grad_norm": 0.2969271242618561,
      "learning_rate": 0.0002,
      "loss": 2.046,
      "step": 120
    },
    {
      "epoch": 0.01181640625,
      "grad_norm": 0.297894150018692,
      "learning_rate": 0.00020166666666666667,
      "loss": 2.0204,
      "step": 121
    },
    {
      "epoch": 0.0119140625,
      "grad_norm": 0.28794237971305847,
      "learning_rate": 0.00020333333333333333,
      "loss": 2.0663,
      "step": 122
    },
    {
      "epoch": 0.01201171875,
      "grad_norm": 0.2766033411026001,
      "learning_rate": 0.000205,
      "loss": 2.0399,
      "step": 123
    },
    {
      "epoch": 0.012109375,
      "grad_norm": 0.3516612648963928,
      "learning_rate": 0.00020666666666666666,
      "loss": 2.0389,
      "step": 124
    },
    {
      "epoch": 0.01220703125,
      "grad_norm": 0.28204381465911865,
      "learning_rate": 0.00020833333333333335,
      "loss": 2.0084,
      "step": 125
    },
    {
      "epoch": 0.0123046875,
      "grad_norm": 0.3306240737438202,
      "learning_rate": 0.00021,
      "loss": 2.013,
      "step": 126
    },
    {
      "epoch": 0.01240234375,
      "grad_norm": 0.3221111595630646,
      "learning_rate": 0.00021166666666666667,
      "loss": 2.0312,
      "step": 127
    },
    {
      "epoch": 0.0125,
      "grad_norm": 0.2742249071598053,
      "learning_rate": 0.00021333333333333336,
      "loss": 2.0375,
      "step": 128
    },
    {
      "epoch": 0.01259765625,
      "grad_norm": 0.2785228490829468,
      "learning_rate": 0.000215,
      "loss": 2.0449,
      "step": 129
    },
    {
      "epoch": 0.0126953125,
      "grad_norm": 0.2666397988796234,
      "learning_rate": 0.00021666666666666668,
      "loss": 2.0355,
      "step": 130
    },
    {
      "epoch": 0.01279296875,
      "grad_norm": 0.22522135078907013,
      "learning_rate": 0.00021833333333333332,
      "loss": 1.9693,
      "step": 131
    },
    {
      "epoch": 0.012890625,
      "grad_norm": 0.2724483013153076,
      "learning_rate": 0.00022,
      "loss": 2.0671,
      "step": 132
    },
    {
      "epoch": 0.01298828125,
      "grad_norm": 0.2655040919780731,
      "learning_rate": 0.00022166666666666667,
      "loss": 1.9805,
      "step": 133
    },
    {
      "epoch": 0.0130859375,
      "grad_norm": 0.3194504678249359,
      "learning_rate": 0.00022333333333333333,
      "loss": 2.067,
      "step": 134
    },
    {
      "epoch": 0.01318359375,
      "grad_norm": 0.25511813163757324,
      "learning_rate": 0.00022500000000000002,
      "loss": 2.0141,
      "step": 135
    },
    {
      "epoch": 0.01328125,
      "grad_norm": 0.3995087444782257,
      "learning_rate": 0.00022666666666666666,
      "loss": 2.0278,
      "step": 136
    },
    {
      "epoch": 0.01337890625,
      "grad_norm": 0.2623380422592163,
      "learning_rate": 0.00022833333333333334,
      "loss": 1.9751,
      "step": 137
    },
    {
      "epoch": 0.0134765625,
      "grad_norm": 0.23814889788627625,
      "learning_rate": 0.00023,
      "loss": 1.969,
      "step": 138
    },
    {
      "epoch": 0.01357421875,
      "grad_norm": 0.23566491901874542,
      "learning_rate": 0.00023166666666666667,
      "loss": 2.0135,
      "step": 139
    },
    {
      "epoch": 0.013671875,
      "grad_norm": 0.2437373697757721,
      "learning_rate": 0.00023333333333333333,
      "loss": 2.0044,
      "step": 140
    },
    {
      "epoch": 0.01376953125,
      "grad_norm": 0.2861543595790863,
      "learning_rate": 0.000235,
      "loss": 2.0378,
      "step": 141
    },
    {
      "epoch": 0.0138671875,
      "grad_norm": 0.318050354719162,
      "learning_rate": 0.00023666666666666668,
      "loss": 2.0857,
      "step": 142
    },
    {
      "epoch": 0.01396484375,
      "grad_norm": 0.39669227600097656,
      "learning_rate": 0.00023833333333333334,
      "loss": 2.0535,
      "step": 143
    },
    {
      "epoch": 0.0140625,
      "grad_norm": 0.4359401762485504,
      "learning_rate": 0.00024,
      "loss": 2.0432,
      "step": 144
    },
    {
      "epoch": 0.01416015625,
      "grad_norm": 0.4532039165496826,
      "learning_rate": 0.00024166666666666667,
      "loss": 1.9909,
      "step": 145
    },
    {
      "epoch": 0.0142578125,
      "grad_norm": 0.4570695161819458,
      "learning_rate": 0.00024333333333333336,
      "loss": 2.0123,
      "step": 146
    },
    {
      "epoch": 0.01435546875,
      "grad_norm": 0.36623403429985046,
      "learning_rate": 0.000245,
      "loss": 2.0179,
      "step": 147
    },
    {
      "epoch": 0.014453125,
      "grad_norm": 0.3069714307785034,
      "learning_rate": 0.0002466666666666667,
      "loss": 2.0014,
      "step": 148
    },
    {
      "epoch": 0.01455078125,
      "grad_norm": 0.3980304002761841,
      "learning_rate": 0.0002483333333333333,
      "loss": 2.0489,
      "step": 149
    },
    {
      "epoch": 0.0146484375,
      "grad_norm": 0.31907564401626587,
      "learning_rate": 0.00025,
      "loss": 2.013,
      "step": 150
    },
    {
      "epoch": 0.01474609375,
      "grad_norm": 0.2952549159526825,
      "learning_rate": 0.00025166666666666664,
      "loss": 2.0709,
      "step": 151
    },
    {
      "epoch": 0.01484375,
      "grad_norm": 0.29451197385787964,
      "learning_rate": 0.0002533333333333334,
      "loss": 1.9613,
      "step": 152
    },
    {
      "epoch": 0.01494140625,
      "grad_norm": 0.2893507778644562,
      "learning_rate": 0.000255,
      "loss": 2.0048,
      "step": 153
    },
    {
      "epoch": 0.0150390625,
      "grad_norm": 0.24850639700889587,
      "learning_rate": 0.00025666666666666665,
      "loss": 2.0198,
      "step": 154
    },
    {
      "epoch": 0.01513671875,
      "grad_norm": 0.24297639727592468,
      "learning_rate": 0.00025833333333333334,
      "loss": 2.0561,
      "step": 155
    },
    {
      "epoch": 0.015234375,
      "grad_norm": 0.2777438461780548,
      "learning_rate": 0.00026000000000000003,
      "loss": 2.0206,
      "step": 156
    },
    {
      "epoch": 0.01533203125,
      "grad_norm": 0.28714093565940857,
      "learning_rate": 0.00026166666666666667,
      "loss": 1.9891,
      "step": 157
    },
    {
      "epoch": 0.0154296875,
      "grad_norm": 0.25796255469322205,
      "learning_rate": 0.0002633333333333333,
      "loss": 2.0369,
      "step": 158
    },
    {
      "epoch": 0.01552734375,
      "grad_norm": 0.2391008883714676,
      "learning_rate": 0.00026500000000000004,
      "loss": 2.0015,
      "step": 159
    },
    {
      "epoch": 0.015625,
      "grad_norm": 0.3203892409801483,
      "learning_rate": 0.0002666666666666667,
      "loss": 2.0213,
      "step": 160
    },
    {
      "epoch": 0.01572265625,
      "grad_norm": 0.3396870791912079,
      "learning_rate": 0.0002683333333333333,
      "loss": 2.0333,
      "step": 161
    },
    {
      "epoch": 0.0158203125,
      "grad_norm": 0.315060555934906,
      "learning_rate": 0.00027,
      "loss": 2.0195,
      "step": 162
    },
    {
      "epoch": 0.01591796875,
      "grad_norm": 0.2672436535358429,
      "learning_rate": 0.0002716666666666667,
      "loss": 1.9946,
      "step": 163
    },
    {
      "epoch": 0.016015625,
      "grad_norm": 0.2996402382850647,
      "learning_rate": 0.00027333333333333333,
      "loss": 2.0112,
      "step": 164
    },
    {
      "epoch": 0.01611328125,
      "grad_norm": 0.2894189953804016,
      "learning_rate": 0.000275,
      "loss": 2.0157,
      "step": 165
    },
    {
      "epoch": 0.0162109375,
      "grad_norm": 0.26241254806518555,
      "learning_rate": 0.00027666666666666665,
      "loss": 2.0177,
      "step": 166
    },
    {
      "epoch": 0.01630859375,
      "grad_norm": 0.22900305688381195,
      "learning_rate": 0.00027833333333333334,
      "loss": 1.9834,
      "step": 167
    },
    {
      "epoch": 0.01640625,
      "grad_norm": 0.2373427301645279,
      "learning_rate": 0.00028000000000000003,
      "loss": 1.9792,
      "step": 168
    },
    {
      "epoch": 0.01650390625,
      "grad_norm": 0.2663004696369171,
      "learning_rate": 0.00028166666666666666,
      "loss": 2.0203,
      "step": 169
    },
    {
      "epoch": 0.0166015625,
      "grad_norm": 0.31653544306755066,
      "learning_rate": 0.00028333333333333335,
      "loss": 2.0216,
      "step": 170
    },
    {
      "epoch": 0.01669921875,
      "grad_norm": 0.3077234923839569,
      "learning_rate": 0.000285,
      "loss": 2.0361,
      "step": 171
    },
    {
      "epoch": 0.016796875,
      "grad_norm": 0.25555703043937683,
      "learning_rate": 0.0002866666666666667,
      "loss": 2.0102,
      "step": 172
    },
    {
      "epoch": 0.01689453125,
      "grad_norm": 0.29817435145378113,
      "learning_rate": 0.0002883333333333333,
      "loss": 1.972,
      "step": 173
    },
    {
      "epoch": 0.0169921875,
      "grad_norm": 0.3075692355632782,
      "learning_rate": 0.00029,
      "loss": 2.0195,
      "step": 174
    },
    {
      "epoch": 0.01708984375,
      "grad_norm": 0.29917964339256287,
      "learning_rate": 0.0002916666666666667,
      "loss": 1.9972,
      "step": 175
    },
    {
      "epoch": 0.0171875,
      "grad_norm": 0.32018229365348816,
      "learning_rate": 0.0002933333333333333,
      "loss": 1.9895,
      "step": 176
    },
    {
      "epoch": 0.01728515625,
      "grad_norm": 0.2907097339630127,
      "learning_rate": 0.000295,
      "loss": 1.9777,
      "step": 177
    },
    {
      "epoch": 0.0173828125,
      "grad_norm": 0.22390642762184143,
      "learning_rate": 0.0002966666666666667,
      "loss": 1.9961,
      "step": 178
    },
    {
      "epoch": 0.01748046875,
      "grad_norm": 0.25350186228752136,
      "learning_rate": 0.00029833333333333334,
      "loss": 1.9875,
      "step": 179
    },
    {
      "epoch": 0.017578125,
      "grad_norm": 0.22856706380844116,
      "learning_rate": 0.0003,
      "loss": 2.0169,
      "step": 180
    },
    {
      "epoch": 0.01767578125,
      "grad_norm": 0.2288493812084198,
      "learning_rate": 0.0003016666666666667,
      "loss": 2.0238,
      "step": 181
    },
    {
      "epoch": 0.0177734375,
      "grad_norm": 0.27326855063438416,
      "learning_rate": 0.00030333333333333335,
      "loss": 2.0134,
      "step": 182
    },
    {
      "epoch": 0.01787109375,
      "grad_norm": 0.2447524517774582,
      "learning_rate": 0.000305,
      "loss": 1.9852,
      "step": 183
    },
    {
      "epoch": 0.01796875,
      "grad_norm": 0.4363366663455963,
      "learning_rate": 0.0003066666666666667,
      "loss": 1.9921,
      "step": 184
    },
    {
      "epoch": 0.01806640625,
      "grad_norm": 0.4569666385650635,
      "learning_rate": 0.00030833333333333337,
      "loss": 1.9997,
      "step": 185
    },
    {
      "epoch": 0.0181640625,
      "grad_norm": 0.43348655104637146,
      "learning_rate": 0.00031,
      "loss": 2.0584,
      "step": 186
    },
    {
      "epoch": 0.01826171875,
      "grad_norm": 0.3844921588897705,
      "learning_rate": 0.00031166666666666663,
      "loss": 2.0035,
      "step": 187
    },
    {
      "epoch": 0.018359375,
      "grad_norm": 0.3427641987800598,
      "learning_rate": 0.0003133333333333334,
      "loss": 1.9536,
      "step": 188
    },
    {
      "epoch": 0.01845703125,
      "grad_norm": 0.33557865023612976,
      "learning_rate": 0.000315,
      "loss": 1.972,
      "step": 189
    },
    {
      "epoch": 0.0185546875,
      "grad_norm": 0.4006612300872803,
      "learning_rate": 0.00031666666666666665,
      "loss": 2.0652,
      "step": 190
    },
    {
      "epoch": 0.01865234375,
      "grad_norm": 0.3158099055290222,
      "learning_rate": 0.00031833333333333334,
      "loss": 2.0516,
      "step": 191
    },
    {
      "epoch": 0.01875,
      "grad_norm": 0.3799190819263458,
      "learning_rate": 0.00032,
      "loss": 2.011,
      "step": 192
    },
    {
      "epoch": 0.01884765625,
      "grad_norm": 0.2948876619338989,
      "learning_rate": 0.00032166666666666666,
      "loss": 2.0109,
      "step": 193
    },
    {
      "epoch": 0.0189453125,
      "grad_norm": 0.24561335146427155,
      "learning_rate": 0.0003233333333333333,
      "loss": 2.0264,
      "step": 194
    },
    {
      "epoch": 0.01904296875,
      "grad_norm": 0.24896866083145142,
      "learning_rate": 0.00032500000000000004,
      "loss": 1.9726,
      "step": 195
    },
    {
      "epoch": 0.019140625,
      "grad_norm": 0.26887547969818115,
      "learning_rate": 0.0003266666666666667,
      "loss": 2.0036,
      "step": 196
    },
    {
      "epoch": 0.01923828125,
      "grad_norm": 0.3186735212802887,
      "learning_rate": 0.0003283333333333333,
      "loss": 2.0174,
      "step": 197
    },
    {
      "epoch": 0.0193359375,
      "grad_norm": 0.3317165672779083,
      "learning_rate": 0.00033,
      "loss": 2.0047,
      "step": 198
    },
    {
      "epoch": 0.01943359375,
      "grad_norm": 0.3068574070930481,
      "learning_rate": 0.0003316666666666667,
      "loss": 2.0032,
      "step": 199
    },
    {
      "epoch": 0.01953125,
      "grad_norm": 0.29292526841163635,
      "learning_rate": 0.0003333333333333333,
      "loss": 2.0533,
      "step": 200
    },
    {
      "epoch": 0.01962890625,
      "grad_norm": 0.2519834041595459,
      "learning_rate": 0.000335,
      "loss": 2.0113,
      "step": 201
    },
    {
      "epoch": 0.0197265625,
      "grad_norm": 0.25766584277153015,
      "learning_rate": 0.0003366666666666667,
      "loss": 2.0278,
      "step": 202
    },
    {
      "epoch": 0.01982421875,
      "grad_norm": 0.2704983055591583,
      "learning_rate": 0.00033833333333333334,
      "loss": 1.9725,
      "step": 203
    },
    {
      "epoch": 0.019921875,
      "grad_norm": 0.2882053256034851,
      "learning_rate": 0.00034,
      "loss": 2.0706,
      "step": 204
    },
    {
      "epoch": 0.02001953125,
      "grad_norm": 0.34524375200271606,
      "learning_rate": 0.00034166666666666666,
      "loss": 1.9868,
      "step": 205
    },
    {
      "epoch": 0.0201171875,
      "grad_norm": 0.3718552887439728,
      "learning_rate": 0.00034333333333333335,
      "loss": 1.9596,
      "step": 206
    },
    {
      "epoch": 0.02021484375,
      "grad_norm": 0.2747247815132141,
      "learning_rate": 0.000345,
      "loss": 2.0125,
      "step": 207
    },
    {
      "epoch": 0.0203125,
      "grad_norm": 0.3062858283519745,
      "learning_rate": 0.00034666666666666667,
      "loss": 2.0224,
      "step": 208
    },
    {
      "epoch": 0.02041015625,
      "grad_norm": 0.32505863904953003,
      "learning_rate": 0.00034833333333333336,
      "loss": 2.0376,
      "step": 209
    },
    {
      "epoch": 0.0205078125,
      "grad_norm": 0.35048386454582214,
      "learning_rate": 0.00035,
      "loss": 2.0268,
      "step": 210
    },
    {
      "epoch": 0.02060546875,
      "grad_norm": 0.31204426288604736,
      "learning_rate": 0.0003516666666666667,
      "loss": 2.0198,
      "step": 211
    },
    {
      "epoch": 0.020703125,
      "grad_norm": 0.24253524839878082,
      "learning_rate": 0.0003533333333333333,
      "loss": 2.028,
      "step": 212
    },
    {
      "epoch": 0.02080078125,
      "grad_norm": 0.286915123462677,
      "learning_rate": 0.000355,
      "loss": 1.9358,
      "step": 213
    },
    {
      "epoch": 0.0208984375,
      "grad_norm": 0.2800680994987488,
      "learning_rate": 0.0003566666666666667,
      "loss": 1.9905,
      "step": 214
    },
    {
      "epoch": 0.02099609375,
      "grad_norm": 0.2718358635902405,
      "learning_rate": 0.00035833333333333333,
      "loss": 1.9902,
      "step": 215
    },
    {
      "epoch": 0.02109375,
      "grad_norm": 0.28583604097366333,
      "learning_rate": 0.00035999999999999997,
      "loss": 1.991,
      "step": 216
    },
    {
      "epoch": 0.02119140625,
      "grad_norm": 0.2911478281021118,
      "learning_rate": 0.0003616666666666667,
      "loss": 1.973,
      "step": 217
    },
    {
      "epoch": 0.0212890625,
      "grad_norm": 0.3601188361644745,
      "learning_rate": 0.00036333333333333335,
      "loss": 1.9727,
      "step": 218
    },
    {
      "epoch": 0.02138671875,
      "grad_norm": 0.2888337969779968,
      "learning_rate": 0.000365,
      "loss": 1.988,
      "step": 219
    },
    {
      "epoch": 0.021484375,
      "grad_norm": 0.25628700852394104,
      "learning_rate": 0.00036666666666666667,
      "loss": 1.9984,
      "step": 220
    },
    {
      "epoch": 0.02158203125,
      "grad_norm": 0.2637641429901123,
      "learning_rate": 0.00036833333333333336,
      "loss": 2.0229,
      "step": 221
    },
    {
      "epoch": 0.0216796875,
      "grad_norm": 0.23845899105072021,
      "learning_rate": 0.00037,
      "loss": 1.9985,
      "step": 222
    },
    {
      "epoch": 0.02177734375,
      "grad_norm": 0.28519535064697266,
      "learning_rate": 0.00037166666666666663,
      "loss": 2.0061,
      "step": 223
    },
    {
      "epoch": 0.021875,
      "grad_norm": 0.31845173239707947,
      "learning_rate": 0.0003733333333333334,
      "loss": 2.0081,
      "step": 224
    },
    {
      "epoch": 0.02197265625,
      "grad_norm": 0.3725838363170624,
      "learning_rate": 0.000375,
      "loss": 2.0032,
      "step": 225
    },
    {
      "epoch": 0.0220703125,
      "grad_norm": 0.49783870577812195,
      "learning_rate": 0.00037666666666666664,
      "loss": 2.0404,
      "step": 226
    },
    {
      "epoch": 0.02216796875,
      "grad_norm": 0.5059479475021362,
      "learning_rate": 0.0003783333333333334,
      "loss": 2.0498,
      "step": 227
    },
    {
      "epoch": 0.022265625,
      "grad_norm": 0.461291640996933,
      "learning_rate": 0.00038,
      "loss": 2.0078,
      "step": 228
    },
    {
      "epoch": 0.02236328125,
      "grad_norm": 0.3970203399658203,
      "learning_rate": 0.00038166666666666666,
      "loss": 1.9966,
      "step": 229
    },
    {
      "epoch": 0.0224609375,
      "grad_norm": 0.3155679404735565,
      "learning_rate": 0.00038333333333333334,
      "loss": 2.0263,
      "step": 230
    },
    {
      "epoch": 0.02255859375,
      "grad_norm": 0.32979920506477356,
      "learning_rate": 0.00038500000000000003,
      "loss": 1.9967,
      "step": 231
    },
    {
      "epoch": 0.02265625,
      "grad_norm": 0.27470117807388306,
      "learning_rate": 0.00038666666666666667,
      "loss": 2.0461,
      "step": 232
    },
    {
      "epoch": 0.02275390625,
      "grad_norm": 0.2981088161468506,
      "learning_rate": 0.0003883333333333333,
      "loss": 1.9944,
      "step": 233
    },
    {
      "epoch": 0.0228515625,
      "grad_norm": 0.3496599495410919,
      "learning_rate": 0.00039000000000000005,
      "loss": 1.9907,
      "step": 234
    },
    {
      "epoch": 0.02294921875,
      "grad_norm": 0.3318106532096863,
      "learning_rate": 0.0003916666666666667,
      "loss": 2.0576,
      "step": 235
    },
    {
      "epoch": 0.023046875,
      "grad_norm": 0.29498377442359924,
      "learning_rate": 0.0003933333333333333,
      "loss": 2.0242,
      "step": 236
    },
    {
      "epoch": 0.02314453125,
      "grad_norm": 0.2970214784145355,
      "learning_rate": 0.000395,
      "loss": 2.0087,
      "step": 237
    },
    {
      "epoch": 0.0232421875,
      "grad_norm": 0.37431418895721436,
      "learning_rate": 0.0003966666666666667,
      "loss": 2.0657,
      "step": 238
    },
    {
      "epoch": 0.02333984375,
      "grad_norm": 0.30095174908638,
      "learning_rate": 0.00039833333333333333,
      "loss": 2.0217,
      "step": 239
    },
    {
      "epoch": 0.0234375,
      "grad_norm": 0.24695053696632385,
      "learning_rate": 0.0004,
      "loss": 1.9833,
      "step": 240
    },
    {
      "epoch": 0.02353515625,
      "grad_norm": 0.2923540771007538,
      "learning_rate": 0.00040166666666666665,
      "loss": 2.0272,
      "step": 241
    },
    {
      "epoch": 0.0236328125,
      "grad_norm": 0.2788209915161133,
      "learning_rate": 0.00040333333333333334,
      "loss": 2.0104,
      "step": 242
    },
    {
      "epoch": 0.02373046875,
      "grad_norm": 0.2529614567756653,
      "learning_rate": 0.00040500000000000003,
      "loss": 2.003,
      "step": 243
    },
    {
      "epoch": 0.023828125,
      "grad_norm": 0.2551966905593872,
      "learning_rate": 0.00040666666666666667,
      "loss": 2.001,
      "step": 244
    },
    {
      "epoch": 0.02392578125,
      "grad_norm": 0.2613292634487152,
      "learning_rate": 0.00040833333333333336,
      "loss": 1.9822,
      "step": 245
    },
    {
      "epoch": 0.0240234375,
      "grad_norm": 0.3060430884361267,
      "learning_rate": 0.00041,
      "loss": 2.0024,
      "step": 246
    },
    {
      "epoch": 0.02412109375,
      "grad_norm": 0.33755916357040405,
      "learning_rate": 0.0004116666666666667,
      "loss": 2.0023,
      "step": 247
    },
    {
      "epoch": 0.02421875,
      "grad_norm": 0.33021774888038635,
      "learning_rate": 0.0004133333333333333,
      "loss": 1.9086,
      "step": 248
    },
    {
      "epoch": 0.02431640625,
      "grad_norm": 0.26662060618400574,
      "learning_rate": 0.000415,
      "loss": 2.009,
      "step": 249
    },
    {
      "epoch": 0.0244140625,
      "grad_norm": 0.27698251605033875,
      "learning_rate": 0.0004166666666666667,
      "loss": 2.0183,
      "step": 250
    },
    {
      "epoch": 0.02451171875,
      "grad_norm": 0.2582184970378876,
      "learning_rate": 0.00041833333333333333,
      "loss": 1.9932,
      "step": 251
    },
    {
      "epoch": 0.024609375,
      "grad_norm": 0.28684699535369873,
      "learning_rate": 0.00042,
      "loss": 2.0021,
      "step": 252
    },
    {
      "epoch": 0.02470703125,
      "grad_norm": 0.33535540103912354,
      "learning_rate": 0.0004216666666666667,
      "loss": 2.0387,
      "step": 253
    },
    {
      "epoch": 0.0248046875,
      "grad_norm": 0.3330588638782501,
      "learning_rate": 0.00042333333333333334,
      "loss": 1.9776,
      "step": 254
    },
    {
      "epoch": 0.02490234375,
      "grad_norm": 0.27919256687164307,
      "learning_rate": 0.000425,
      "loss": 2.0111,
      "step": 255
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.25296416878700256,
      "learning_rate": 0.0004266666666666667,
      "loss": 1.9755,
      "step": 256
    },
    {
      "epoch": 0.02509765625,
      "grad_norm": 0.31288138031959534,
      "learning_rate": 0.00042833333333333335,
      "loss": 2.032,
      "step": 257
    },
    {
      "epoch": 0.0251953125,
      "grad_norm": 0.3360923230648041,
      "learning_rate": 0.00043,
      "loss": 2.0837,
      "step": 258
    },
    {
      "epoch": 0.02529296875,
      "grad_norm": 0.36317816376686096,
      "learning_rate": 0.0004316666666666667,
      "loss": 1.9696,
      "step": 259
    },
    {
      "epoch": 0.025390625,
      "grad_norm": 0.366953581571579,
      "learning_rate": 0.00043333333333333337,
      "loss": 2.031,
      "step": 260
    },
    {
      "epoch": 0.02548828125,
      "grad_norm": 0.34289368987083435,
      "learning_rate": 0.000435,
      "loss": 1.9968,
      "step": 261
    },
    {
      "epoch": 0.0255859375,
      "grad_norm": 0.35170793533325195,
      "learning_rate": 0.00043666666666666664,
      "loss": 1.9963,
      "step": 262
    },
    {
      "epoch": 0.02568359375,
      "grad_norm": 0.28625521063804626,
      "learning_rate": 0.0004383333333333334,
      "loss": 1.9932,
      "step": 263
    },
    {
      "epoch": 0.02578125,
      "grad_norm": 0.2861610949039459,
      "learning_rate": 0.00044,
      "loss": 2.0297,
      "step": 264
    },
    {
      "epoch": 0.02587890625,
      "grad_norm": 0.30467647314071655,
      "learning_rate": 0.00044166666666666665,
      "loss": 1.992,
      "step": 265
    },
    {
      "epoch": 0.0259765625,
      "grad_norm": 0.31711357831954956,
      "learning_rate": 0.00044333333333333334,
      "loss": 2.0135,
      "step": 266
    },
    {
      "epoch": 0.02607421875,
      "grad_norm": 0.341530978679657,
      "learning_rate": 0.00044500000000000003,
      "loss": 1.983,
      "step": 267
    },
    {
      "epoch": 0.026171875,
      "grad_norm": 0.373901903629303,
      "learning_rate": 0.00044666666666666666,
      "loss": 2.0048,
      "step": 268
    },
    {
      "epoch": 0.02626953125,
      "grad_norm": 0.3105134665966034,
      "learning_rate": 0.0004483333333333333,
      "loss": 2.0368,
      "step": 269
    },
    {
      "epoch": 0.0263671875,
      "grad_norm": 0.29363134503364563,
      "learning_rate": 0.00045000000000000004,
      "loss": 1.978,
      "step": 270
    },
    {
      "epoch": 0.02646484375,
      "grad_norm": 0.3060167133808136,
      "learning_rate": 0.0004516666666666667,
      "loss": 1.9479,
      "step": 271
    },
    {
      "epoch": 0.0265625,
      "grad_norm": 0.30803290009498596,
      "learning_rate": 0.0004533333333333333,
      "loss": 1.9662,
      "step": 272
    },
    {
      "epoch": 0.02666015625,
      "grad_norm": 0.3324045240879059,
      "learning_rate": 0.000455,
      "loss": 2.0299,
      "step": 273
    },
    {
      "epoch": 0.0267578125,
      "grad_norm": 0.39051148295402527,
      "learning_rate": 0.0004566666666666667,
      "loss": 1.9856,
      "step": 274
    },
    {
      "epoch": 0.02685546875,
      "grad_norm": 0.4288715124130249,
      "learning_rate": 0.0004583333333333333,
      "loss": 2.0264,
      "step": 275
    },
    {
      "epoch": 0.026953125,
      "grad_norm": 0.34478962421417236,
      "learning_rate": 0.00046,
      "loss": 1.9824,
      "step": 276
    },
    {
      "epoch": 0.02705078125,
      "grad_norm": 0.2766290009021759,
      "learning_rate": 0.0004616666666666667,
      "loss": 2.0066,
      "step": 277
    },
    {
      "epoch": 0.0271484375,
      "grad_norm": 0.2508682608604431,
      "learning_rate": 0.00046333333333333334,
      "loss": 1.9663,
      "step": 278
    },
    {
      "epoch": 0.02724609375,
      "grad_norm": 0.26924827694892883,
      "learning_rate": 0.000465,
      "loss": 1.9903,
      "step": 279
    },
    {
      "epoch": 0.02734375,
      "grad_norm": 0.27668496966362,
      "learning_rate": 0.00046666666666666666,
      "loss": 2.0097,
      "step": 280
    },
    {
      "epoch": 0.02744140625,
      "grad_norm": 0.25026220083236694,
      "learning_rate": 0.00046833333333333335,
      "loss": 2.0583,
      "step": 281
    },
    {
      "epoch": 0.0275390625,
      "grad_norm": 0.2158055454492569,
      "learning_rate": 0.00047,
      "loss": 2.0137,
      "step": 282
    },
    {
      "epoch": 0.02763671875,
      "grad_norm": 0.22540244460105896,
      "learning_rate": 0.0004716666666666667,
      "loss": 1.994,
      "step": 283
    },
    {
      "epoch": 0.027734375,
      "grad_norm": 0.26405519247055054,
      "learning_rate": 0.00047333333333333336,
      "loss": 2.0221,
      "step": 284
    },
    {
      "epoch": 0.02783203125,
      "grad_norm": 0.2979099452495575,
      "learning_rate": 0.000475,
      "loss": 2.0047,
      "step": 285
    },
    {
      "epoch": 0.0279296875,
      "grad_norm": 0.34131935238838196,
      "learning_rate": 0.0004766666666666667,
      "loss": 1.9907,
      "step": 286
    },
    {
      "epoch": 0.02802734375,
      "grad_norm": 0.37178686261177063,
      "learning_rate": 0.0004783333333333333,
      "loss": 1.9806,
      "step": 287
    },
    {
      "epoch": 0.028125,
      "grad_norm": 0.36835598945617676,
      "learning_rate": 0.00048,
      "loss": 2.0134,
      "step": 288
    },
    {
      "epoch": 0.02822265625,
      "grad_norm": 0.29690125584602356,
      "learning_rate": 0.0004816666666666667,
      "loss": 2.0261,
      "step": 289
    },
    {
      "epoch": 0.0283203125,
      "grad_norm": 0.2690771818161011,
      "learning_rate": 0.00048333333333333334,
      "loss": 1.9718,
      "step": 290
    },
    {
      "epoch": 0.02841796875,
      "grad_norm": 0.3377201557159424,
      "learning_rate": 0.00048499999999999997,
      "loss": 1.99,
      "step": 291
    },
    {
      "epoch": 0.028515625,
      "grad_norm": 0.34973010420799255,
      "learning_rate": 0.0004866666666666667,
      "loss": 1.9721,
      "step": 292
    },
    {
      "epoch": 0.02861328125,
      "grad_norm": 0.3172457218170166,
      "learning_rate": 0.0004883333333333333,
      "loss": 1.9928,
      "step": 293
    },
    {
      "epoch": 0.0287109375,
      "grad_norm": 0.34357598423957825,
      "learning_rate": 0.00049,
      "loss": 1.9995,
      "step": 294
    },
    {
      "epoch": 0.02880859375,
      "grad_norm": 0.3824540376663208,
      "learning_rate": 0.0004916666666666666,
      "loss": 1.9772,
      "step": 295
    },
    {
      "epoch": 0.02890625,
      "grad_norm": 0.3704535663127899,
      "learning_rate": 0.0004933333333333334,
      "loss": 1.9829,
      "step": 296
    },
    {
      "epoch": 0.02900390625,
      "grad_norm": 0.2571757733821869,
      "learning_rate": 0.000495,
      "loss": 1.9966,
      "step": 297
    },
    {
      "epoch": 0.0291015625,
      "grad_norm": 0.3970927894115448,
      "learning_rate": 0.0004966666666666666,
      "loss": 1.9841,
      "step": 298
    },
    {
      "epoch": 0.02919921875,
      "grad_norm": 0.3420144319534302,
      "learning_rate": 0.0004983333333333334,
      "loss": 1.9747,
      "step": 299
    },
    {
      "epoch": 0.029296875,
      "grad_norm": 0.30147823691368103,
      "learning_rate": 0.0005,
      "loss": 1.9999,
      "step": 300
    },
    {
      "epoch": 0.02939453125,
      "grad_norm": 0.33727970719337463,
      "learning_rate": 0.0004999999887622467,
      "loss": 2.0084,
      "step": 301
    },
    {
      "epoch": 0.0294921875,
      "grad_norm": 0.29407384991645813,
      "learning_rate": 0.0004999999550489878,
      "loss": 2.0144,
      "step": 302
    },
    {
      "epoch": 0.02958984375,
      "grad_norm": 0.3489755094051361,
      "learning_rate": 0.0004999998988602267,
      "loss": 2.0058,
      "step": 303
    },
    {
      "epoch": 0.0296875,
      "grad_norm": 0.3327770233154297,
      "learning_rate": 0.0004999998201959691,
      "loss": 2.0166,
      "step": 304
    },
    {
      "epoch": 0.02978515625,
      "grad_norm": 0.2923370599746704,
      "learning_rate": 0.0004999997190562227,
      "loss": 2.0148,
      "step": 305
    },
    {
      "epoch": 0.0298828125,
      "grad_norm": 0.31616437435150146,
      "learning_rate": 0.0004999995954409976,
      "loss": 1.9772,
      "step": 306
    },
    {
      "epoch": 0.02998046875,
      "grad_norm": 0.22982288897037506,
      "learning_rate": 0.0004999994493503064,
      "loss": 2.0584,
      "step": 307
    },
    {
      "epoch": 0.030078125,
      "grad_norm": 0.2886744737625122,
      "learning_rate": 0.0004999992807841634,
      "loss": 2.0114,
      "step": 308
    },
    {
      "epoch": 0.03017578125,
      "grad_norm": 0.3027271032333374,
      "learning_rate": 0.0004999990897425856,
      "loss": 2.011,
      "step": 309
    },
    {
      "epoch": 0.0302734375,
      "grad_norm": 0.3191162645816803,
      "learning_rate": 0.0004999988762255922,
      "loss": 1.9962,
      "step": 310
    },
    {
      "epoch": 0.03037109375,
      "grad_norm": 0.34986981749534607,
      "learning_rate": 0.0004999986402332042,
      "loss": 1.9612,
      "step": 311
    },
    {
      "epoch": 0.03046875,
      "grad_norm": 0.36431390047073364,
      "learning_rate": 0.0004999983817654454,
      "loss": 2.045,
      "step": 312
    },
    {
      "epoch": 0.03056640625,
      "grad_norm": 0.4198042154312134,
      "learning_rate": 0.0004999981008223416,
      "loss": 2.0132,
      "step": 313
    },
    {
      "epoch": 0.0306640625,
      "grad_norm": 0.43374890089035034,
      "learning_rate": 0.0004999977974039207,
      "loss": 2.0578,
      "step": 314
    },
    {
      "epoch": 0.03076171875,
      "grad_norm": 0.3654812276363373,
      "learning_rate": 0.0004999974715102132,
      "loss": 1.9721,
      "step": 315
    },
    {
      "epoch": 0.030859375,
      "grad_norm": 0.29420921206474304,
      "learning_rate": 0.0004999971231412517,
      "loss": 2.0296,
      "step": 316
    },
    {
      "epoch": 0.03095703125,
      "grad_norm": 0.31979072093963623,
      "learning_rate": 0.0004999967522970708,
      "loss": 1.9623,
      "step": 317
    },
    {
      "epoch": 0.0310546875,
      "grad_norm": 0.3570129871368408,
      "learning_rate": 0.0004999963589777076,
      "loss": 1.9966,
      "step": 318
    },
    {
      "epoch": 0.03115234375,
      "grad_norm": 0.29743143916130066,
      "learning_rate": 0.0004999959431832016,
      "loss": 1.9535,
      "step": 319
    },
    {
      "epoch": 0.03125,
      "grad_norm": 0.23641493916511536,
      "learning_rate": 0.000499995504913594,
      "loss": 2.0304,
      "step": 320
    },
    {
      "epoch": 0.03134765625,
      "grad_norm": 0.3556622564792633,
      "learning_rate": 0.0004999950441689288,
      "loss": 1.971,
      "step": 321
    },
    {
      "epoch": 0.0314453125,
      "grad_norm": 0.323939710855484,
      "learning_rate": 0.0004999945609492519,
      "loss": 2.0153,
      "step": 322
    },
    {
      "epoch": 0.03154296875,
      "grad_norm": 0.22797244787216187,
      "learning_rate": 0.0004999940552546118,
      "loss": 1.9807,
      "step": 323
    },
    {
      "epoch": 0.031640625,
      "grad_norm": 0.2641647458076477,
      "learning_rate": 0.0004999935270850587,
      "loss": 1.9988,
      "step": 324
    },
    {
      "epoch": 0.03173828125,
      "grad_norm": 0.25289344787597656,
      "learning_rate": 0.0004999929764406455,
      "loss": 1.9748,
      "step": 325
    },
    {
      "epoch": 0.0318359375,
      "grad_norm": 0.2377796769142151,
      "learning_rate": 0.0004999924033214274,
      "loss": 1.9983,
      "step": 326
    },
    {
      "epoch": 0.03193359375,
      "grad_norm": 0.2711915671825409,
      "learning_rate": 0.0004999918077274612,
      "loss": 1.9643,
      "step": 327
    },
    {
      "epoch": 0.03203125,
      "grad_norm": 0.2866462767124176,
      "learning_rate": 0.0004999911896588068,
      "loss": 2.0196,
      "step": 328
    },
    {
      "epoch": 0.03212890625,
      "grad_norm": 0.25075578689575195,
      "learning_rate": 0.0004999905491155257,
      "loss": 2.0426,
      "step": 329
    },
    {
      "epoch": 0.0322265625,
      "grad_norm": 0.266648530960083,
      "learning_rate": 0.000499989886097682,
      "loss": 2.0318,
      "step": 330
    },
    {
      "epoch": 0.03232421875,
      "grad_norm": 0.22494247555732727,
      "learning_rate": 0.0004999892006053421,
      "loss": 1.9839,
      "step": 331
    },
    {
      "epoch": 0.032421875,
      "grad_norm": 0.3179854452610016,
      "learning_rate": 0.0004999884926385741,
      "loss": 1.9981,
      "step": 332
    },
    {
      "epoch": 0.03251953125,
      "grad_norm": 0.2754990756511688,
      "learning_rate": 0.000499987762197449,
      "loss": 1.9879,
      "step": 333
    },
    {
      "epoch": 0.0326171875,
      "grad_norm": 0.2669137418270111,
      "learning_rate": 0.0004999870092820395,
      "loss": 2.0083,
      "step": 334
    },
    {
      "epoch": 0.03271484375,
      "grad_norm": 0.31376007199287415,
      "learning_rate": 0.0004999862338924212,
      "loss": 2.0166,
      "step": 335
    },
    {
      "epoch": 0.0328125,
      "grad_norm": 0.32645899057388306,
      "learning_rate": 0.0004999854360286712,
      "loss": 2.0019,
      "step": 336
    },
    {
      "epoch": 0.03291015625,
      "grad_norm": 0.3550071120262146,
      "learning_rate": 0.0004999846156908692,
      "loss": 1.9744,
      "step": 337
    },
    {
      "epoch": 0.0330078125,
      "grad_norm": 0.30171769857406616,
      "learning_rate": 0.0004999837728790975,
      "loss": 2.0231,
      "step": 338
    },
    {
      "epoch": 0.03310546875,
      "grad_norm": 0.23128142952919006,
      "learning_rate": 0.00049998290759344,
      "loss": 2.001,
      "step": 339
    },
    {
      "epoch": 0.033203125,
      "grad_norm": 0.2433364987373352,
      "learning_rate": 0.0004999820198339832,
      "loss": 1.9945,
      "step": 340
    },
    {
      "epoch": 0.03330078125,
      "grad_norm": 0.30562201142311096,
      "learning_rate": 0.0004999811096008159,
      "loss": 2.0228,
      "step": 341
    },
    {
      "epoch": 0.0333984375,
      "grad_norm": 0.33020487427711487,
      "learning_rate": 0.0004999801768940287,
      "loss": 1.9691,
      "step": 342
    },
    {
      "epoch": 0.03349609375,
      "grad_norm": 0.3125375807285309,
      "learning_rate": 0.0004999792217137151,
      "loss": 1.9728,
      "step": 343
    },
    {
      "epoch": 0.03359375,
      "grad_norm": 0.26769348978996277,
      "learning_rate": 0.0004999782440599702,
      "loss": 2.0066,
      "step": 344
    },
    {
      "epoch": 0.03369140625,
      "grad_norm": 0.3596431314945221,
      "learning_rate": 0.0004999772439328921,
      "loss": 2.0426,
      "step": 345
    },
    {
      "epoch": 0.0337890625,
      "grad_norm": 0.34117281436920166,
      "learning_rate": 0.0004999762213325803,
      "loss": 1.9985,
      "step": 346
    },
    {
      "epoch": 0.03388671875,
      "grad_norm": 0.2922564148902893,
      "learning_rate": 0.0004999751762591371,
      "loss": 2.0346,
      "step": 347
    },
    {
      "epoch": 0.033984375,
      "grad_norm": 0.2813419997692108,
      "learning_rate": 0.0004999741087126669,
      "loss": 2.0573,
      "step": 348
    },
    {
      "epoch": 0.03408203125,
      "grad_norm": 0.27346089482307434,
      "learning_rate": 0.0004999730186932764,
      "loss": 1.9655,
      "step": 349
    },
    {
      "epoch": 0.0341796875,
      "grad_norm": 0.24704065918922424,
      "learning_rate": 0.0004999719062010745,
      "loss": 1.9542,
      "step": 350
    },
    {
      "epoch": 0.03427734375,
      "grad_norm": 0.24761976301670074,
      "learning_rate": 0.000499970771236172,
      "loss": 1.9526,
      "step": 351
    },
    {
      "epoch": 0.034375,
      "grad_norm": 0.2508860230445862,
      "learning_rate": 0.0004999696137986826,
      "loss": 2.0119,
      "step": 352
    },
    {
      "epoch": 0.03447265625,
      "grad_norm": 0.24160990118980408,
      "learning_rate": 0.0004999684338887219,
      "loss": 2.0148,
      "step": 353
    },
    {
      "epoch": 0.0345703125,
      "grad_norm": 0.2879098355770111,
      "learning_rate": 0.0004999672315064076,
      "loss": 2.0206,
      "step": 354
    },
    {
      "epoch": 0.03466796875,
      "grad_norm": 0.28366580605506897,
      "learning_rate": 0.0004999660066518601,
      "loss": 2.0737,
      "step": 355
    },
    {
      "epoch": 0.034765625,
      "grad_norm": 0.3401612937450409,
      "learning_rate": 0.0004999647593252013,
      "loss": 1.9868,
      "step": 356
    },
    {
      "epoch": 0.03486328125,
      "grad_norm": 0.4696269631385803,
      "learning_rate": 0.0004999634895265562,
      "loss": 2.0079,
      "step": 357
    },
    {
      "epoch": 0.0349609375,
      "grad_norm": 0.596168041229248,
      "learning_rate": 0.0004999621972560515,
      "loss": 2.0084,
      "step": 358
    },
    {
      "epoch": 0.03505859375,
      "grad_norm": 0.5319205522537231,
      "learning_rate": 0.0004999608825138162,
      "loss": 2.0084,
      "step": 359
    },
    {
      "epoch": 0.03515625,
      "grad_norm": 0.24298223853111267,
      "learning_rate": 0.0004999595452999818,
      "loss": 1.9183,
      "step": 360
    },
    {
      "epoch": 0.03525390625,
      "grad_norm": 0.39650923013687134,
      "learning_rate": 0.0004999581856146817,
      "loss": 1.9886,
      "step": 361
    },
    {
      "epoch": 0.0353515625,
      "grad_norm": 0.3819667100906372,
      "learning_rate": 0.0004999568034580518,
      "loss": 2.0047,
      "step": 362
    },
    {
      "epoch": 0.03544921875,
      "grad_norm": 0.3298279345035553,
      "learning_rate": 0.0004999553988302303,
      "loss": 1.9466,
      "step": 363
    },
    {
      "epoch": 0.035546875,
      "grad_norm": 0.2343115359544754,
      "learning_rate": 0.0004999539717313573,
      "loss": 1.9828,
      "step": 364
    },
    {
      "epoch": 0.03564453125,
      "grad_norm": 0.31238943338394165,
      "learning_rate": 0.0004999525221615755,
      "loss": 2.0721,
      "step": 365
    },
    {
      "epoch": 0.0357421875,
      "grad_norm": 0.27481910586357117,
      "learning_rate": 0.0004999510501210295,
      "loss": 2.0106,
      "step": 366
    },
    {
      "epoch": 0.03583984375,
      "grad_norm": 0.24870915710926056,
      "learning_rate": 0.0004999495556098666,
      "loss": 1.9846,
      "step": 367
    },
    {
      "epoch": 0.0359375,
      "grad_norm": 0.2666539251804352,
      "learning_rate": 0.0004999480386282359,
      "loss": 1.9988,
      "step": 368
    },
    {
      "epoch": 0.03603515625,
      "grad_norm": 0.23231451213359833,
      "learning_rate": 0.000499946499176289,
      "loss": 2.0235,
      "step": 369
    },
    {
      "epoch": 0.0361328125,
      "grad_norm": 0.19276577234268188,
      "learning_rate": 0.0004999449372541798,
      "loss": 1.9832,
      "step": 370
    },
    {
      "epoch": 0.03623046875,
      "grad_norm": 0.23545822501182556,
      "learning_rate": 0.000499943352862064,
      "loss": 1.9879,
      "step": 371
    },
    {
      "epoch": 0.036328125,
      "grad_norm": 0.2608807384967804,
      "learning_rate": 0.0004999417460001002,
      "loss": 2.047,
      "step": 372
    },
    {
      "epoch": 0.03642578125,
      "grad_norm": 0.27395492792129517,
      "learning_rate": 0.0004999401166684487,
      "loss": 1.9496,
      "step": 373
    },
    {
      "epoch": 0.0365234375,
      "grad_norm": 0.24661333858966827,
      "learning_rate": 0.0004999384648672724,
      "loss": 1.9924,
      "step": 374
    },
    {
      "epoch": 0.03662109375,
      "grad_norm": 0.23559828102588654,
      "learning_rate": 0.0004999367905967362,
      "loss": 1.979,
      "step": 375
    },
    {
      "epoch": 0.03671875,
      "grad_norm": 0.2556357681751251,
      "learning_rate": 0.0004999350938570074,
      "loss": 1.9793,
      "step": 376
    },
    {
      "epoch": 0.03681640625,
      "grad_norm": 0.29081088304519653,
      "learning_rate": 0.0004999333746482555,
      "loss": 1.962,
      "step": 377
    },
    {
      "epoch": 0.0369140625,
      "grad_norm": 0.2583800256252289,
      "learning_rate": 0.0004999316329706521,
      "loss": 1.9765,
      "step": 378
    },
    {
      "epoch": 0.03701171875,
      "grad_norm": 0.2506580054759979,
      "learning_rate": 0.0004999298688243714,
      "loss": 2.0302,
      "step": 379
    },
    {
      "epoch": 0.037109375,
      "grad_norm": 0.289530485868454,
      "learning_rate": 0.0004999280822095895,
      "loss": 1.9514,
      "step": 380
    },
    {
      "epoch": 0.03720703125,
      "grad_norm": 0.24479152262210846,
      "learning_rate": 0.0004999262731264848,
      "loss": 1.9742,
      "step": 381
    },
    {
      "epoch": 0.0373046875,
      "grad_norm": 0.23676550388336182,
      "learning_rate": 0.0004999244415752381,
      "loss": 2.0161,
      "step": 382
    },
    {
      "epoch": 0.03740234375,
      "grad_norm": 0.2447502315044403,
      "learning_rate": 0.0004999225875560323,
      "loss": 2.0114,
      "step": 383
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.20993874967098236,
      "learning_rate": 0.0004999207110690528,
      "loss": 1.9786,
      "step": 384
    },
    {
      "epoch": 0.03759765625,
      "grad_norm": 0.23405557870864868,
      "learning_rate": 0.0004999188121144867,
      "loss": 2.0004,
      "step": 385
    },
    {
      "epoch": 0.0376953125,
      "grad_norm": 0.2310025990009308,
      "learning_rate": 0.0004999168906925238,
      "loss": 1.924,
      "step": 386
    },
    {
      "epoch": 0.03779296875,
      "grad_norm": 0.2507460117340088,
      "learning_rate": 0.0004999149468033564,
      "loss": 2.0301,
      "step": 387
    },
    {
      "epoch": 0.037890625,
      "grad_norm": 0.30916762351989746,
      "learning_rate": 0.0004999129804471782,
      "loss": 1.9948,
      "step": 388
    },
    {
      "epoch": 0.03798828125,
      "grad_norm": 0.42094507813453674,
      "learning_rate": 0.0004999109916241858,
      "loss": 2.0128,
      "step": 389
    },
    {
      "epoch": 0.0380859375,
      "grad_norm": 0.5398088693618774,
      "learning_rate": 0.0004999089803345779,
      "loss": 1.9866,
      "step": 390
    },
    {
      "epoch": 0.03818359375,
      "grad_norm": 0.4601620137691498,
      "learning_rate": 0.0004999069465785554,
      "loss": 1.9807,
      "step": 391
    },
    {
      "epoch": 0.03828125,
      "grad_norm": 0.24873095750808716,
      "learning_rate": 0.0004999048903563213,
      "loss": 1.9225,
      "step": 392
    },
    {
      "epoch": 0.03837890625,
      "grad_norm": 0.37363573908805847,
      "learning_rate": 0.0004999028116680814,
      "loss": 2.0212,
      "step": 393
    },
    {
      "epoch": 0.0384765625,
      "grad_norm": 0.27399107813835144,
      "learning_rate": 0.0004999007105140428,
      "loss": 1.9797,
      "step": 394
    },
    {
      "epoch": 0.03857421875,
      "grad_norm": 0.2717953622341156,
      "learning_rate": 0.0004998985868944158,
      "loss": 2.0119,
      "step": 395
    },
    {
      "epoch": 0.038671875,
      "grad_norm": 0.2766648530960083,
      "learning_rate": 0.0004998964408094124,
      "loss": 1.9936,
      "step": 396
    },
    {
      "epoch": 0.03876953125,
      "grad_norm": 0.2989843487739563,
      "learning_rate": 0.0004998942722592469,
      "loss": 2.0261,
      "step": 397
    },
    {
      "epoch": 0.0388671875,
      "grad_norm": 0.31954097747802734,
      "learning_rate": 0.000499892081244136,
      "loss": 1.9713,
      "step": 398
    },
    {
      "epoch": 0.03896484375,
      "grad_norm": 0.31199777126312256,
      "learning_rate": 0.0004998898677642987,
      "loss": 1.9548,
      "step": 399
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 0.2475418746471405,
      "learning_rate": 0.0004998876318199557,
      "loss": 1.9878,
      "step": 400
    },
    {
      "epoch": 0.03916015625,
      "grad_norm": 0.25001809000968933,
      "learning_rate": 0.0004998853734113308,
      "loss": 1.991,
      "step": 401
    },
    {
      "epoch": 0.0392578125,
      "grad_norm": 0.2468329817056656,
      "learning_rate": 0.0004998830925386492,
      "loss": 1.9988,
      "step": 402
    },
    {
      "epoch": 0.03935546875,
      "grad_norm": 0.23273305594921112,
      "learning_rate": 0.000499880789202139,
      "loss": 2.0138,
      "step": 403
    },
    {
      "epoch": 0.039453125,
      "grad_norm": 0.21512626111507416,
      "learning_rate": 0.0004998784634020303,
      "loss": 1.9326,
      "step": 404
    },
    {
      "epoch": 0.03955078125,
      "grad_norm": 0.2123369723558426,
      "learning_rate": 0.0004998761151385554,
      "loss": 1.9954,
      "step": 405
    },
    {
      "epoch": 0.0396484375,
      "grad_norm": 0.20985403656959534,
      "learning_rate": 0.0004998737444119488,
      "loss": 1.996,
      "step": 406
    },
    {
      "epoch": 0.03974609375,
      "grad_norm": 0.19709332287311554,
      "learning_rate": 0.0004998713512224473,
      "loss": 1.9642,
      "step": 407
    },
    {
      "epoch": 0.03984375,
      "grad_norm": 0.21997478604316711,
      "learning_rate": 0.00049986893557029,
      "loss": 1.9925,
      "step": 408
    },
    {
      "epoch": 0.03994140625,
      "grad_norm": 0.2419801503419876,
      "learning_rate": 0.0004998664974557182,
      "loss": 2.0262,
      "step": 409
    },
    {
      "epoch": 0.0400390625,
      "grad_norm": 0.2527197003364563,
      "learning_rate": 0.0004998640368789754,
      "loss": 2.0011,
      "step": 410
    },
    {
      "epoch": 0.04013671875,
      "grad_norm": 0.2539777159690857,
      "learning_rate": 0.0004998615538403074,
      "loss": 1.9799,
      "step": 411
    },
    {
      "epoch": 0.040234375,
      "grad_norm": 0.2419251948595047,
      "learning_rate": 0.0004998590483399623,
      "loss": 2.0035,
      "step": 412
    },
    {
      "epoch": 0.04033203125,
      "grad_norm": 0.26659199595451355,
      "learning_rate": 0.0004998565203781904,
      "loss": 1.9743,
      "step": 413
    },
    {
      "epoch": 0.0404296875,
      "grad_norm": 0.3216726779937744,
      "learning_rate": 0.0004998539699552441,
      "loss": 1.979,
      "step": 414
    },
    {
      "epoch": 0.04052734375,
      "grad_norm": 0.2780512571334839,
      "learning_rate": 0.0004998513970713783,
      "loss": 1.9892,
      "step": 415
    },
    {
      "epoch": 0.040625,
      "grad_norm": 0.2947809100151062,
      "learning_rate": 0.00049984880172685,
      "loss": 1.9836,
      "step": 416
    },
    {
      "epoch": 0.04072265625,
      "grad_norm": 0.33937209844589233,
      "learning_rate": 0.0004998461839219182,
      "loss": 2.0007,
      "step": 417
    },
    {
      "epoch": 0.0408203125,
      "grad_norm": 0.3530365228652954,
      "learning_rate": 0.0004998435436568446,
      "loss": 1.9462,
      "step": 418
    },
    {
      "epoch": 0.04091796875,
      "grad_norm": 0.34433260560035706,
      "learning_rate": 0.000499840880931893,
      "loss": 1.9733,
      "step": 419
    },
    {
      "epoch": 0.041015625,
      "grad_norm": 0.323081910610199,
      "learning_rate": 0.0004998381957473293,
      "loss": 1.9522,
      "step": 420
    },
    {
      "epoch": 0.04111328125,
      "grad_norm": 0.22895868122577667,
      "learning_rate": 0.0004998354881034217,
      "loss": 1.9672,
      "step": 421
    },
    {
      "epoch": 0.0412109375,
      "grad_norm": 0.2543105185031891,
      "learning_rate": 0.0004998327580004408,
      "loss": 1.9429,
      "step": 422
    },
    {
      "epoch": 0.04130859375,
      "grad_norm": 0.2795581519603729,
      "learning_rate": 0.0004998300054386591,
      "loss": 1.9902,
      "step": 423
    },
    {
      "epoch": 0.04140625,
      "grad_norm": 0.2201048880815506,
      "learning_rate": 0.0004998272304183517,
      "loss": 1.9365,
      "step": 424
    },
    {
      "epoch": 0.04150390625,
      "grad_norm": 0.26653197407722473,
      "learning_rate": 0.0004998244329397958,
      "loss": 2.0178,
      "step": 425
    },
    {
      "epoch": 0.0416015625,
      "grad_norm": 0.26959821581840515,
      "learning_rate": 0.0004998216130032708,
      "loss": 1.9625,
      "step": 426
    },
    {
      "epoch": 0.04169921875,
      "grad_norm": 0.2673629820346832,
      "learning_rate": 0.0004998187706090584,
      "loss": 1.995,
      "step": 427
    },
    {
      "epoch": 0.041796875,
      "grad_norm": 0.3190925121307373,
      "learning_rate": 0.0004998159057574426,
      "loss": 2.0094,
      "step": 428
    },
    {
      "epoch": 0.04189453125,
      "grad_norm": 0.3376927673816681,
      "learning_rate": 0.0004998130184487094,
      "loss": 2.0535,
      "step": 429
    },
    {
      "epoch": 0.0419921875,
      "grad_norm": 0.35333067178726196,
      "learning_rate": 0.0004998101086831474,
      "loss": 2.0256,
      "step": 430
    },
    {
      "epoch": 0.04208984375,
      "grad_norm": 0.3051585853099823,
      "learning_rate": 0.0004998071764610471,
      "loss": 1.9798,
      "step": 431
    },
    {
      "epoch": 0.0421875,
      "grad_norm": 0.21881523728370667,
      "learning_rate": 0.0004998042217827015,
      "loss": 1.9726,
      "step": 432
    },
    {
      "epoch": 0.04228515625,
      "grad_norm": 0.2296576052904129,
      "learning_rate": 0.0004998012446484057,
      "loss": 1.9675,
      "step": 433
    },
    {
      "epoch": 0.0423828125,
      "grad_norm": 0.24055050313472748,
      "learning_rate": 0.0004997982450584572,
      "loss": 1.9488,
      "step": 434
    },
    {
      "epoch": 0.04248046875,
      "grad_norm": 0.22267191112041473,
      "learning_rate": 0.0004997952230131555,
      "loss": 1.9617,
      "step": 435
    },
    {
      "epoch": 0.042578125,
      "grad_norm": 0.2590855658054352,
      "learning_rate": 0.0004997921785128026,
      "loss": 1.9745,
      "step": 436
    },
    {
      "epoch": 0.04267578125,
      "grad_norm": 0.2995806336402893,
      "learning_rate": 0.0004997891115577025,
      "loss": 1.9667,
      "step": 437
    },
    {
      "epoch": 0.0427734375,
      "grad_norm": 0.3083277642726898,
      "learning_rate": 0.0004997860221481616,
      "loss": 1.9661,
      "step": 438
    },
    {
      "epoch": 0.04287109375,
      "grad_norm": 0.31743094325065613,
      "learning_rate": 0.0004997829102844885,
      "loss": 2.0172,
      "step": 439
    },
    {
      "epoch": 0.04296875,
      "grad_norm": 0.37507855892181396,
      "learning_rate": 0.0004997797759669941,
      "loss": 2.0211,
      "step": 440
    },
    {
      "epoch": 0.04306640625,
      "grad_norm": 0.35785287618637085,
      "learning_rate": 0.0004997766191959914,
      "loss": 2.038,
      "step": 441
    },
    {
      "epoch": 0.0431640625,
      "grad_norm": 0.3099903166294098,
      "learning_rate": 0.0004997734399717958,
      "loss": 1.9879,
      "step": 442
    },
    {
      "epoch": 0.04326171875,
      "grad_norm": 0.32211577892303467,
      "learning_rate": 0.0004997702382947248,
      "loss": 1.987,
      "step": 443
    },
    {
      "epoch": 0.043359375,
      "grad_norm": 0.24999700486660004,
      "learning_rate": 0.0004997670141650984,
      "loss": 1.9765,
      "step": 444
    },
    {
      "epoch": 0.04345703125,
      "grad_norm": 0.23301391303539276,
      "learning_rate": 0.0004997637675832386,
      "loss": 1.9592,
      "step": 445
    },
    {
      "epoch": 0.0435546875,
      "grad_norm": 0.22780932486057281,
      "learning_rate": 0.0004997604985494694,
      "loss": 1.9762,
      "step": 446
    },
    {
      "epoch": 0.04365234375,
      "grad_norm": 0.2347191423177719,
      "learning_rate": 0.0004997572070641178,
      "loss": 1.9791,
      "step": 447
    },
    {
      "epoch": 0.04375,
      "grad_norm": 0.3288608193397522,
      "learning_rate": 0.0004997538931275123,
      "loss": 1.9664,
      "step": 448
    },
    {
      "epoch": 0.04384765625,
      "grad_norm": 0.29897212982177734,
      "learning_rate": 0.000499750556739984,
      "loss": 1.9876,
      "step": 449
    },
    {
      "epoch": 0.0439453125,
      "grad_norm": 0.24389693140983582,
      "learning_rate": 0.0004997471979018663,
      "loss": 1.9742,
      "step": 450
    },
    {
      "epoch": 0.04404296875,
      "grad_norm": 0.3172384798526764,
      "learning_rate": 0.0004997438166134945,
      "loss": 1.969,
      "step": 451
    },
    {
      "epoch": 0.044140625,
      "grad_norm": 0.22951611876487732,
      "learning_rate": 0.0004997404128752065,
      "loss": 1.9832,
      "step": 452
    },
    {
      "epoch": 0.04423828125,
      "grad_norm": 0.2356499582529068,
      "learning_rate": 0.0004997369866873423,
      "loss": 2.0236,
      "step": 453
    },
    {
      "epoch": 0.0443359375,
      "grad_norm": 0.2687929570674896,
      "learning_rate": 0.000499733538050244,
      "loss": 1.9521,
      "step": 454
    },
    {
      "epoch": 0.04443359375,
      "grad_norm": 0.2512679398059845,
      "learning_rate": 0.0004997300669642564,
      "loss": 1.9754,
      "step": 455
    },
    {
      "epoch": 0.04453125,
      "grad_norm": 0.22110989689826965,
      "learning_rate": 0.0004997265734297259,
      "loss": 1.9931,
      "step": 456
    },
    {
      "epoch": 0.04462890625,
      "grad_norm": 0.2548464834690094,
      "learning_rate": 0.0004997230574470017,
      "loss": 2.001,
      "step": 457
    },
    {
      "epoch": 0.0447265625,
      "grad_norm": 0.3107970356941223,
      "learning_rate": 0.0004997195190164349,
      "loss": 1.9855,
      "step": 458
    },
    {
      "epoch": 0.04482421875,
      "grad_norm": 0.2989678680896759,
      "learning_rate": 0.0004997159581383789,
      "loss": 1.9646,
      "step": 459
    },
    {
      "epoch": 0.044921875,
      "grad_norm": 0.3651764690876007,
      "learning_rate": 0.0004997123748131896,
      "loss": 1.9865,
      "step": 460
    },
    {
      "epoch": 0.04501953125,
      "grad_norm": 0.41693389415740967,
      "learning_rate": 0.0004997087690412248,
      "loss": 1.9756,
      "step": 461
    },
    {
      "epoch": 0.0451171875,
      "grad_norm": 0.425959974527359,
      "learning_rate": 0.0004997051408228447,
      "loss": 1.9887,
      "step": 462
    },
    {
      "epoch": 0.04521484375,
      "grad_norm": 0.38966843485832214,
      "learning_rate": 0.0004997014901584118,
      "loss": 1.9532,
      "step": 463
    },
    {
      "epoch": 0.0453125,
      "grad_norm": 0.29931432008743286,
      "learning_rate": 0.0004996978170482906,
      "loss": 1.9806,
      "step": 464
    },
    {
      "epoch": 0.04541015625,
      "grad_norm": 0.23077397048473358,
      "learning_rate": 0.0004996941214928482,
      "loss": 2.0258,
      "step": 465
    },
    {
      "epoch": 0.0455078125,
      "grad_norm": 0.32101985812187195,
      "learning_rate": 0.0004996904034924536,
      "loss": 2.0023,
      "step": 466
    },
    {
      "epoch": 0.04560546875,
      "grad_norm": 0.3225870430469513,
      "learning_rate": 0.0004996866630474783,
      "loss": 1.9385,
      "step": 467
    },
    {
      "epoch": 0.045703125,
      "grad_norm": 0.2592551112174988,
      "learning_rate": 0.0004996829001582959,
      "loss": 2.0176,
      "step": 468
    },
    {
      "epoch": 0.04580078125,
      "grad_norm": 0.24367393553256989,
      "learning_rate": 0.0004996791148252824,
      "loss": 1.9844,
      "step": 469
    },
    {
      "epoch": 0.0458984375,
      "grad_norm": 0.26423218846321106,
      "learning_rate": 0.0004996753070488156,
      "loss": 1.9675,
      "step": 470
    },
    {
      "epoch": 0.04599609375,
      "grad_norm": 0.27801692485809326,
      "learning_rate": 0.0004996714768292762,
      "loss": 1.9265,
      "step": 471
    },
    {
      "epoch": 0.04609375,
      "grad_norm": 0.3210003077983856,
      "learning_rate": 0.0004996676241670467,
      "loss": 1.9937,
      "step": 472
    },
    {
      "epoch": 0.04619140625,
      "grad_norm": 0.3082759380340576,
      "learning_rate": 0.0004996637490625118,
      "loss": 1.9997,
      "step": 473
    },
    {
      "epoch": 0.0462890625,
      "grad_norm": 0.2486785650253296,
      "learning_rate": 0.0004996598515160589,
      "loss": 2.0687,
      "step": 474
    },
    {
      "epoch": 0.04638671875,
      "grad_norm": 0.31927499175071716,
      "learning_rate": 0.000499655931528077,
      "loss": 1.9853,
      "step": 475
    },
    {
      "epoch": 0.046484375,
      "grad_norm": 0.2736678123474121,
      "learning_rate": 0.0004996519890989578,
      "loss": 1.9916,
      "step": 476
    },
    {
      "epoch": 0.04658203125,
      "grad_norm": 0.29522353410720825,
      "learning_rate": 0.0004996480242290952,
      "loss": 1.9554,
      "step": 477
    },
    {
      "epoch": 0.0466796875,
      "grad_norm": 0.26841938495635986,
      "learning_rate": 0.0004996440369188851,
      "loss": 1.9275,
      "step": 478
    },
    {
      "epoch": 0.04677734375,
      "grad_norm": 0.2695488929748535,
      "learning_rate": 0.0004996400271687259,
      "loss": 1.9898,
      "step": 479
    },
    {
      "epoch": 0.046875,
      "grad_norm": 0.36634454131126404,
      "learning_rate": 0.0004996359949790181,
      "loss": 1.9799,
      "step": 480
    },
    {
      "epoch": 0.04697265625,
      "grad_norm": 0.37612974643707275,
      "learning_rate": 0.0004996319403501647,
      "loss": 1.9645,
      "step": 481
    },
    {
      "epoch": 0.0470703125,
      "grad_norm": 0.29007261991500854,
      "learning_rate": 0.0004996278632825703,
      "loss": 1.9486,
      "step": 482
    },
    {
      "epoch": 0.04716796875,
      "grad_norm": 0.30373314023017883,
      "learning_rate": 0.0004996237637766424,
      "loss": 1.9913,
      "step": 483
    },
    {
      "epoch": 0.047265625,
      "grad_norm": 0.2949075400829315,
      "learning_rate": 0.0004996196418327906,
      "loss": 1.9894,
      "step": 484
    },
    {
      "epoch": 0.04736328125,
      "grad_norm": 0.30601680278778076,
      "learning_rate": 0.0004996154974514264,
      "loss": 1.9835,
      "step": 485
    },
    {
      "epoch": 0.0474609375,
      "grad_norm": 0.2896345853805542,
      "learning_rate": 0.000499611330632964,
      "loss": 2.0043,
      "step": 486
    },
    {
      "epoch": 0.04755859375,
      "grad_norm": 0.3836851418018341,
      "learning_rate": 0.0004996071413778195,
      "loss": 1.9782,
      "step": 487
    },
    {
      "epoch": 0.04765625,
      "grad_norm": 0.4167245626449585,
      "learning_rate": 0.0004996029296864114,
      "loss": 1.9792,
      "step": 488
    },
    {
      "epoch": 0.04775390625,
      "grad_norm": 0.3247157335281372,
      "learning_rate": 0.0004995986955591606,
      "loss": 1.9548,
      "step": 489
    },
    {
      "epoch": 0.0478515625,
      "grad_norm": 0.36726462841033936,
      "learning_rate": 0.0004995944389964897,
      "loss": 1.9844,
      "step": 490
    },
    {
      "epoch": 0.04794921875,
      "grad_norm": 0.27440258860588074,
      "learning_rate": 0.0004995901599988241,
      "loss": 1.9608,
      "step": 491
    },
    {
      "epoch": 0.048046875,
      "grad_norm": 0.271771103143692,
      "learning_rate": 0.0004995858585665912,
      "loss": 2.022,
      "step": 492
    },
    {
      "epoch": 0.04814453125,
      "grad_norm": 0.3079121708869934,
      "learning_rate": 0.0004995815347002208,
      "loss": 1.9804,
      "step": 493
    },
    {
      "epoch": 0.0482421875,
      "grad_norm": 0.2976233661174774,
      "learning_rate": 0.0004995771884001445,
      "loss": 1.9679,
      "step": 494
    },
    {
      "epoch": 0.04833984375,
      "grad_norm": 0.31318438053131104,
      "learning_rate": 0.0004995728196667969,
      "loss": 2.0342,
      "step": 495
    },
    {
      "epoch": 0.0484375,
      "grad_norm": 0.2397848516702652,
      "learning_rate": 0.0004995684285006139,
      "loss": 1.9801,
      "step": 496
    },
    {
      "epoch": 0.04853515625,
      "grad_norm": 0.2205589860677719,
      "learning_rate": 0.0004995640149020346,
      "loss": 2.0088,
      "step": 497
    },
    {
      "epoch": 0.0486328125,
      "grad_norm": 0.23892101645469666,
      "learning_rate": 0.0004995595788714995,
      "loss": 1.9888,
      "step": 498
    },
    {
      "epoch": 0.04873046875,
      "grad_norm": 0.2999497354030609,
      "learning_rate": 0.000499555120409452,
      "loss": 1.9896,
      "step": 499
    },
    {
      "epoch": 0.048828125,
      "grad_norm": 0.3309103548526764,
      "learning_rate": 0.0004995506395163372,
      "loss": 1.9394,
      "step": 500
    },
    {
      "epoch": 0.04892578125,
      "grad_norm": 0.36243122816085815,
      "learning_rate": 0.000499546136192603,
      "loss": 1.9604,
      "step": 501
    },
    {
      "epoch": 0.0490234375,
      "grad_norm": 0.3052852153778076,
      "learning_rate": 0.0004995416104386991,
      "loss": 1.9887,
      "step": 502
    },
    {
      "epoch": 0.04912109375,
      "grad_norm": 0.2957259714603424,
      "learning_rate": 0.0004995370622550775,
      "loss": 1.9876,
      "step": 503
    },
    {
      "epoch": 0.04921875,
      "grad_norm": 0.3991003632545471,
      "learning_rate": 0.0004995324916421926,
      "loss": 1.9932,
      "step": 504
    },
    {
      "epoch": 0.04931640625,
      "grad_norm": 0.27617356181144714,
      "learning_rate": 0.000499527898600501,
      "loss": 1.9387,
      "step": 505
    },
    {
      "epoch": 0.0494140625,
      "grad_norm": 0.2820669412612915,
      "learning_rate": 0.0004995232831304614,
      "loss": 2.012,
      "step": 506
    },
    {
      "epoch": 0.04951171875,
      "grad_norm": 0.3026665449142456,
      "learning_rate": 0.0004995186452325351,
      "loss": 1.9709,
      "step": 507
    },
    {
      "epoch": 0.049609375,
      "grad_norm": 0.2331731766462326,
      "learning_rate": 0.000499513984907185,
      "loss": 1.9617,
      "step": 508
    },
    {
      "epoch": 0.04970703125,
      "grad_norm": 0.2791639268398285,
      "learning_rate": 0.0004995093021548768,
      "loss": 1.9635,
      "step": 509
    },
    {
      "epoch": 0.0498046875,
      "grad_norm": 0.257519006729126,
      "learning_rate": 0.0004995045969760785,
      "loss": 1.8908,
      "step": 510
    },
    {
      "epoch": 0.04990234375,
      "grad_norm": 0.26278433203697205,
      "learning_rate": 0.0004994998693712598,
      "loss": 1.9418,
      "step": 511
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.2534024715423584,
      "learning_rate": 0.0004994951193408929,
      "loss": 1.9821,
      "step": 512
    },
    {
      "epoch": 0.05009765625,
      "grad_norm": 0.272348552942276,
      "learning_rate": 0.0004994903468854527,
      "loss": 1.982,
      "step": 513
    },
    {
      "epoch": 0.0501953125,
      "grad_norm": 0.23883765935897827,
      "learning_rate": 0.0004994855520054154,
      "loss": 2.006,
      "step": 514
    },
    {
      "epoch": 0.05029296875,
      "grad_norm": 0.25627830624580383,
      "learning_rate": 0.0004994807347012603,
      "loss": 2.0008,
      "step": 515
    },
    {
      "epoch": 0.050390625,
      "grad_norm": 0.33997049927711487,
      "learning_rate": 0.0004994758949734686,
      "loss": 2.0339,
      "step": 516
    },
    {
      "epoch": 0.05048828125,
      "grad_norm": 0.4115971028804779,
      "learning_rate": 0.0004994710328225236,
      "loss": 1.9982,
      "step": 517
    },
    {
      "epoch": 0.0505859375,
      "grad_norm": 0.4417625069618225,
      "learning_rate": 0.000499466148248911,
      "loss": 1.9742,
      "step": 518
    },
    {
      "epoch": 0.05068359375,
      "grad_norm": 0.4123833477497101,
      "learning_rate": 0.0004994612412531189,
      "loss": 2.0148,
      "step": 519
    },
    {
      "epoch": 0.05078125,
      "grad_norm": 0.2234133630990982,
      "learning_rate": 0.0004994563118356373,
      "loss": 1.9679,
      "step": 520
    },
    {
      "epoch": 0.05087890625,
      "grad_norm": 0.35439473390579224,
      "learning_rate": 0.0004994513599969586,
      "loss": 1.9602,
      "step": 521
    },
    {
      "epoch": 0.0509765625,
      "grad_norm": 0.32346996665000916,
      "learning_rate": 0.0004994463857375776,
      "loss": 2.0106,
      "step": 522
    },
    {
      "epoch": 0.05107421875,
      "grad_norm": 0.24506594240665436,
      "learning_rate": 0.000499441389057991,
      "loss": 1.993,
      "step": 523
    },
    {
      "epoch": 0.051171875,
      "grad_norm": 0.26808494329452515,
      "learning_rate": 0.000499436369958698,
      "loss": 1.9764,
      "step": 524
    },
    {
      "epoch": 0.05126953125,
      "grad_norm": 0.21936193108558655,
      "learning_rate": 0.0004994313284401999,
      "loss": 1.9619,
      "step": 525
    },
    {
      "epoch": 0.0513671875,
      "grad_norm": 0.2545083165168762,
      "learning_rate": 0.0004994262645030005,
      "loss": 1.9825,
      "step": 526
    },
    {
      "epoch": 0.05146484375,
      "grad_norm": 0.26330727338790894,
      "learning_rate": 0.0004994211781476055,
      "loss": 1.9512,
      "step": 527
    },
    {
      "epoch": 0.0515625,
      "grad_norm": 0.2708059549331665,
      "learning_rate": 0.0004994160693745229,
      "loss": 1.9761,
      "step": 528
    },
    {
      "epoch": 0.05166015625,
      "grad_norm": 0.2882954478263855,
      "learning_rate": 0.0004994109381842632,
      "loss": 2.0223,
      "step": 529
    },
    {
      "epoch": 0.0517578125,
      "grad_norm": 0.25243133306503296,
      "learning_rate": 0.0004994057845773389,
      "loss": 1.976,
      "step": 530
    },
    {
      "epoch": 0.05185546875,
      "grad_norm": 0.23666390776634216,
      "learning_rate": 0.0004994006085542648,
      "loss": 1.9729,
      "step": 531
    },
    {
      "epoch": 0.051953125,
      "grad_norm": 0.24242763221263885,
      "learning_rate": 0.0004993954101155578,
      "loss": 1.9452,
      "step": 532
    },
    {
      "epoch": 0.05205078125,
      "grad_norm": 0.259750634431839,
      "learning_rate": 0.0004993901892617373,
      "loss": 1.9582,
      "step": 533
    },
    {
      "epoch": 0.0521484375,
      "grad_norm": 0.28516751527786255,
      "learning_rate": 0.0004993849459933249,
      "loss": 1.9367,
      "step": 534
    },
    {
      "epoch": 0.05224609375,
      "grad_norm": 0.26534441113471985,
      "learning_rate": 0.0004993796803108442,
      "loss": 2.0137,
      "step": 535
    },
    {
      "epoch": 0.05234375,
      "grad_norm": 0.28771716356277466,
      "learning_rate": 0.0004993743922148213,
      "loss": 1.927,
      "step": 536
    },
    {
      "epoch": 0.05244140625,
      "grad_norm": 0.2747785449028015,
      "learning_rate": 0.0004993690817057844,
      "loss": 1.9729,
      "step": 537
    },
    {
      "epoch": 0.0525390625,
      "grad_norm": 0.29758942127227783,
      "learning_rate": 0.0004993637487842639,
      "loss": 1.9713,
      "step": 538
    },
    {
      "epoch": 0.05263671875,
      "grad_norm": 0.3059535026550293,
      "learning_rate": 0.0004993583934507927,
      "loss": 2.0313,
      "step": 539
    },
    {
      "epoch": 0.052734375,
      "grad_norm": 0.36820656061172485,
      "learning_rate": 0.0004993530157059056,
      "loss": 1.9476,
      "step": 540
    },
    {
      "epoch": 0.05283203125,
      "grad_norm": 0.39971432089805603,
      "learning_rate": 0.0004993476155501396,
      "loss": 2.0238,
      "step": 541
    },
    {
      "epoch": 0.0529296875,
      "grad_norm": 0.3369678854942322,
      "learning_rate": 0.0004993421929840346,
      "loss": 1.9502,
      "step": 542
    },
    {
      "epoch": 0.05302734375,
      "grad_norm": 0.3733840882778168,
      "learning_rate": 0.000499336748008132,
      "loss": 2.0114,
      "step": 543
    },
    {
      "epoch": 0.053125,
      "grad_norm": 0.3251579999923706,
      "learning_rate": 0.0004993312806229757,
      "loss": 1.964,
      "step": 544
    },
    {
      "epoch": 0.05322265625,
      "grad_norm": 0.4093327522277832,
      "learning_rate": 0.0004993257908291117,
      "loss": 1.9853,
      "step": 545
    },
    {
      "epoch": 0.0533203125,
      "grad_norm": 0.26201343536376953,
      "learning_rate": 0.0004993202786270888,
      "loss": 2.0297,
      "step": 546
    },
    {
      "epoch": 0.05341796875,
      "grad_norm": 0.27842357754707336,
      "learning_rate": 0.0004993147440174572,
      "loss": 2.003,
      "step": 547
    },
    {
      "epoch": 0.053515625,
      "grad_norm": 0.2930687367916107,
      "learning_rate": 0.00049930918700077,
      "loss": 1.9634,
      "step": 548
    },
    {
      "epoch": 0.05361328125,
      "grad_norm": 0.2799973785877228,
      "learning_rate": 0.0004993036075775821,
      "loss": 2.0023,
      "step": 549
    },
    {
      "epoch": 0.0537109375,
      "grad_norm": 0.35084354877471924,
      "learning_rate": 0.000499298005748451,
      "loss": 2.0508,
      "step": 550
    },
    {
      "epoch": 0.05380859375,
      "grad_norm": 0.2895161211490631,
      "learning_rate": 0.0004992923815139362,
      "loss": 2.0074,
      "step": 551
    },
    {
      "epoch": 0.05390625,
      "grad_norm": 0.2637045979499817,
      "learning_rate": 0.0004992867348745997,
      "loss": 1.9559,
      "step": 552
    },
    {
      "epoch": 0.05400390625,
      "grad_norm": 0.2837629020214081,
      "learning_rate": 0.0004992810658310052,
      "loss": 1.9603,
      "step": 553
    },
    {
      "epoch": 0.0541015625,
      "grad_norm": 0.2644243836402893,
      "learning_rate": 0.0004992753743837193,
      "loss": 1.9767,
      "step": 554
    },
    {
      "epoch": 0.05419921875,
      "grad_norm": 0.21815134584903717,
      "learning_rate": 0.0004992696605333103,
      "loss": 1.9684,
      "step": 555
    },
    {
      "epoch": 0.054296875,
      "grad_norm": 0.28167852759361267,
      "learning_rate": 0.0004992639242803492,
      "loss": 1.97,
      "step": 556
    },
    {
      "epoch": 0.05439453125,
      "grad_norm": 0.26942357420921326,
      "learning_rate": 0.0004992581656254087,
      "loss": 1.9825,
      "step": 557
    },
    {
      "epoch": 0.0544921875,
      "grad_norm": 0.25316697359085083,
      "learning_rate": 0.0004992523845690644,
      "loss": 1.9698,
      "step": 558
    },
    {
      "epoch": 0.05458984375,
      "grad_norm": 0.29587239027023315,
      "learning_rate": 0.0004992465811118934,
      "loss": 2.0063,
      "step": 559
    },
    {
      "epoch": 0.0546875,
      "grad_norm": 0.3209396004676819,
      "learning_rate": 0.0004992407552544757,
      "loss": 2.0002,
      "step": 560
    },
    {
      "epoch": 0.05478515625,
      "grad_norm": 0.2541654109954834,
      "learning_rate": 0.0004992349069973931,
      "loss": 2.0039,
      "step": 561
    },
    {
      "epoch": 0.0548828125,
      "grad_norm": 0.34102505445480347,
      "learning_rate": 0.0004992290363412298,
      "loss": 1.9181,
      "step": 562
    },
    {
      "epoch": 0.05498046875,
      "grad_norm": 0.36123788356781006,
      "learning_rate": 0.0004992231432865723,
      "loss": 2.042,
      "step": 563
    },
    {
      "epoch": 0.055078125,
      "grad_norm": 0.27344051003456116,
      "learning_rate": 0.0004992172278340093,
      "loss": 2.0236,
      "step": 564
    },
    {
      "epoch": 0.05517578125,
      "grad_norm": 0.34781453013420105,
      "learning_rate": 0.0004992112899841315,
      "loss": 2.0017,
      "step": 565
    },
    {
      "epoch": 0.0552734375,
      "grad_norm": 0.2822319567203522,
      "learning_rate": 0.0004992053297375322,
      "loss": 1.9607,
      "step": 566
    },
    {
      "epoch": 0.05537109375,
      "grad_norm": 0.27945882081985474,
      "learning_rate": 0.0004991993470948066,
      "loss": 1.9707,
      "step": 567
    },
    {
      "epoch": 0.05546875,
      "grad_norm": 0.31535595655441284,
      "learning_rate": 0.0004991933420565527,
      "loss": 1.9708,
      "step": 568
    },
    {
      "epoch": 0.05556640625,
      "grad_norm": 0.2658466398715973,
      "learning_rate": 0.00049918731462337,
      "loss": 1.9763,
      "step": 569
    },
    {
      "epoch": 0.0556640625,
      "grad_norm": 0.3618657886981964,
      "learning_rate": 0.0004991812647958607,
      "loss": 2.0154,
      "step": 570
    },
    {
      "epoch": 0.05576171875,
      "grad_norm": 0.34552058577537537,
      "learning_rate": 0.000499175192574629,
      "loss": 1.978,
      "step": 571
    },
    {
      "epoch": 0.055859375,
      "grad_norm": 0.32903313636779785,
      "learning_rate": 0.0004991690979602817,
      "loss": 1.9762,
      "step": 572
    },
    {
      "epoch": 0.05595703125,
      "grad_norm": 0.30814382433891296,
      "learning_rate": 0.0004991629809534275,
      "loss": 1.9944,
      "step": 573
    },
    {
      "epoch": 0.0560546875,
      "grad_norm": 0.21156492829322815,
      "learning_rate": 0.0004991568415546775,
      "loss": 1.9919,
      "step": 574
    },
    {
      "epoch": 0.05615234375,
      "grad_norm": 0.32283446192741394,
      "learning_rate": 0.0004991506797646446,
      "loss": 1.9697,
      "step": 575
    },
    {
      "epoch": 0.05625,
      "grad_norm": 0.2915102541446686,
      "learning_rate": 0.0004991444955839447,
      "loss": 1.9736,
      "step": 576
    },
    {
      "epoch": 0.05634765625,
      "grad_norm": 0.28996148705482483,
      "learning_rate": 0.0004991382890131955,
      "loss": 2.002,
      "step": 577
    },
    {
      "epoch": 0.0564453125,
      "grad_norm": 0.3859401345252991,
      "learning_rate": 0.0004991320600530168,
      "loss": 1.9753,
      "step": 578
    },
    {
      "epoch": 0.05654296875,
      "grad_norm": 0.28169432282447815,
      "learning_rate": 0.0004991258087040312,
      "loss": 1.9798,
      "step": 579
    },
    {
      "epoch": 0.056640625,
      "grad_norm": 0.30669984221458435,
      "learning_rate": 0.0004991195349668626,
      "loss": 2.0007,
      "step": 580
    },
    {
      "epoch": 0.05673828125,
      "grad_norm": 0.26832297444343567,
      "learning_rate": 0.000499113238842138,
      "loss": 2.0146,
      "step": 581
    },
    {
      "epoch": 0.0568359375,
      "grad_norm": 0.25695785880088806,
      "learning_rate": 0.0004991069203304865,
      "loss": 1.9814,
      "step": 582
    },
    {
      "epoch": 0.05693359375,
      "grad_norm": 0.25700533390045166,
      "learning_rate": 0.0004991005794325389,
      "loss": 1.9623,
      "step": 583
    },
    {
      "epoch": 0.05703125,
      "grad_norm": 0.20786869525909424,
      "learning_rate": 0.0004990942161489288,
      "loss": 1.9728,
      "step": 584
    },
    {
      "epoch": 0.05712890625,
      "grad_norm": 0.23988646268844604,
      "learning_rate": 0.0004990878304802918,
      "loss": 1.9749,
      "step": 585
    },
    {
      "epoch": 0.0572265625,
      "grad_norm": 0.2418268769979477,
      "learning_rate": 0.0004990814224272658,
      "loss": 1.928,
      "step": 586
    },
    {
      "epoch": 0.05732421875,
      "grad_norm": 0.27739882469177246,
      "learning_rate": 0.0004990749919904909,
      "loss": 1.964,
      "step": 587
    },
    {
      "epoch": 0.057421875,
      "grad_norm": 0.2773842513561249,
      "learning_rate": 0.0004990685391706094,
      "loss": 1.9589,
      "step": 588
    },
    {
      "epoch": 0.05751953125,
      "grad_norm": 0.24483682215213776,
      "learning_rate": 0.0004990620639682659,
      "loss": 1.9965,
      "step": 589
    },
    {
      "epoch": 0.0576171875,
      "grad_norm": 0.27345889806747437,
      "learning_rate": 0.0004990555663841071,
      "loss": 1.9444,
      "step": 590
    },
    {
      "epoch": 0.05771484375,
      "grad_norm": 0.26006460189819336,
      "learning_rate": 0.0004990490464187824,
      "loss": 1.9391,
      "step": 591
    },
    {
      "epoch": 0.0578125,
      "grad_norm": 0.1935306191444397,
      "learning_rate": 0.0004990425040729427,
      "loss": 1.9679,
      "step": 592
    },
    {
      "epoch": 0.05791015625,
      "grad_norm": 0.26823100447654724,
      "learning_rate": 0.0004990359393472418,
      "loss": 2.0055,
      "step": 593
    },
    {
      "epoch": 0.0580078125,
      "grad_norm": 0.2706959545612335,
      "learning_rate": 0.0004990293522423352,
      "loss": 1.9853,
      "step": 594
    },
    {
      "epoch": 0.05810546875,
      "grad_norm": 0.2099694162607193,
      "learning_rate": 0.0004990227427588811,
      "loss": 1.959,
      "step": 595
    },
    {
      "epoch": 0.058203125,
      "grad_norm": 0.22345881164073944,
      "learning_rate": 0.0004990161108975398,
      "loss": 1.9867,
      "step": 596
    },
    {
      "epoch": 0.05830078125,
      "grad_norm": 0.34050315618515015,
      "learning_rate": 0.0004990094566589734,
      "loss": 1.9555,
      "step": 597
    },
    {
      "epoch": 0.0583984375,
      "grad_norm": 0.5298358798027039,
      "learning_rate": 0.0004990027800438468,
      "loss": 1.9824,
      "step": 598
    },
    {
      "epoch": 0.05849609375,
      "grad_norm": 0.6408056616783142,
      "learning_rate": 0.0004989960810528271,
      "loss": 1.9647,
      "step": 599
    },
    {
      "epoch": 0.05859375,
      "grad_norm": 0.4058885872364044,
      "learning_rate": 0.0004989893596865833,
      "loss": 1.9564,
      "step": 600
    },
    {
      "epoch": 0.05869140625,
      "grad_norm": 0.2911423146724701,
      "learning_rate": 0.0004989826159457869,
      "loss": 1.9485,
      "step": 601
    },
    {
      "epoch": 0.0587890625,
      "grad_norm": 0.40600210428237915,
      "learning_rate": 0.0004989758498311114,
      "loss": 1.993,
      "step": 602
    },
    {
      "epoch": 0.05888671875,
      "grad_norm": 0.3920167088508606,
      "learning_rate": 0.0004989690613432327,
      "loss": 2.0188,
      "step": 603
    },
    {
      "epoch": 0.058984375,
      "grad_norm": 0.2924116551876068,
      "learning_rate": 0.0004989622504828291,
      "loss": 1.9749,
      "step": 604
    },
    {
      "epoch": 0.05908203125,
      "grad_norm": 0.33497628569602966,
      "learning_rate": 0.0004989554172505807,
      "loss": 1.9358,
      "step": 605
    },
    {
      "epoch": 0.0591796875,
      "grad_norm": 0.31751033663749695,
      "learning_rate": 0.0004989485616471702,
      "loss": 1.9886,
      "step": 606
    },
    {
      "epoch": 0.05927734375,
      "grad_norm": 0.2204602211713791,
      "learning_rate": 0.0004989416836732825,
      "loss": 1.9715,
      "step": 607
    },
    {
      "epoch": 0.059375,
      "grad_norm": 0.2980511784553528,
      "learning_rate": 0.0004989347833296044,
      "loss": 1.9479,
      "step": 608
    },
    {
      "epoch": 0.05947265625,
      "grad_norm": 0.2874164879322052,
      "learning_rate": 0.0004989278606168253,
      "loss": 1.9717,
      "step": 609
    },
    {
      "epoch": 0.0595703125,
      "grad_norm": 0.2526591718196869,
      "learning_rate": 0.0004989209155356368,
      "loss": 2.0009,
      "step": 610
    },
    {
      "epoch": 0.05966796875,
      "grad_norm": 0.2890442907810211,
      "learning_rate": 0.0004989139480867327,
      "loss": 1.9862,
      "step": 611
    },
    {
      "epoch": 0.059765625,
      "grad_norm": 0.26463401317596436,
      "learning_rate": 0.0004989069582708088,
      "loss": 2.0143,
      "step": 612
    },
    {
      "epoch": 0.05986328125,
      "grad_norm": 0.19906644523143768,
      "learning_rate": 0.0004988999460885634,
      "loss": 1.9845,
      "step": 613
    },
    {
      "epoch": 0.0599609375,
      "grad_norm": 0.28752684593200684,
      "learning_rate": 0.000498892911540697,
      "loss": 1.9421,
      "step": 614
    },
    {
      "epoch": 0.06005859375,
      "grad_norm": 0.2739415466785431,
      "learning_rate": 0.0004988858546279123,
      "loss": 1.967,
      "step": 615
    },
    {
      "epoch": 0.06015625,
      "grad_norm": 0.27040478587150574,
      "learning_rate": 0.000498878775350914,
      "loss": 2.0001,
      "step": 616
    },
    {
      "epoch": 0.06025390625,
      "grad_norm": 0.28345200419425964,
      "learning_rate": 0.0004988716737104096,
      "loss": 1.9637,
      "step": 617
    },
    {
      "epoch": 0.0603515625,
      "grad_norm": 0.2515316903591156,
      "learning_rate": 0.0004988645497071082,
      "loss": 1.9511,
      "step": 618
    },
    {
      "epoch": 0.06044921875,
      "grad_norm": 0.22784312069416046,
      "learning_rate": 0.0004988574033417216,
      "loss": 1.9752,
      "step": 619
    },
    {
      "epoch": 0.060546875,
      "grad_norm": 0.23128612339496613,
      "learning_rate": 0.0004988502346149636,
      "loss": 1.9803,
      "step": 620
    },
    {
      "epoch": 0.06064453125,
      "grad_norm": 0.22022667527198792,
      "learning_rate": 0.0004988430435275503,
      "loss": 1.9592,
      "step": 621
    },
    {
      "epoch": 0.0607421875,
      "grad_norm": 0.2470719963312149,
      "learning_rate": 0.0004988358300802,
      "loss": 2.0063,
      "step": 622
    },
    {
      "epoch": 0.06083984375,
      "grad_norm": 0.22507692873477936,
      "learning_rate": 0.0004988285942736332,
      "loss": 1.9873,
      "step": 623
    },
    {
      "epoch": 0.0609375,
      "grad_norm": 0.2285120040178299,
      "learning_rate": 0.0004988213361085729,
      "loss": 1.973,
      "step": 624
    },
    {
      "epoch": 0.06103515625,
      "grad_norm": 0.2436297982931137,
      "learning_rate": 0.000498814055585744,
      "loss": 1.9786,
      "step": 625
    },
    {
      "epoch": 0.0611328125,
      "grad_norm": 0.2736089825630188,
      "learning_rate": 0.0004988067527058737,
      "loss": 1.9552,
      "step": 626
    },
    {
      "epoch": 0.06123046875,
      "grad_norm": 0.2813490033149719,
      "learning_rate": 0.0004987994274696917,
      "loss": 2.0173,
      "step": 627
    },
    {
      "epoch": 0.061328125,
      "grad_norm": 0.3024250864982605,
      "learning_rate": 0.0004987920798779294,
      "loss": 1.9232,
      "step": 628
    },
    {
      "epoch": 0.06142578125,
      "grad_norm": 0.22795617580413818,
      "learning_rate": 0.000498784709931321,
      "loss": 1.9981,
      "step": 629
    },
    {
      "epoch": 0.0615234375,
      "grad_norm": 0.2585217356681824,
      "learning_rate": 0.0004987773176306026,
      "loss": 2.0197,
      "step": 630
    },
    {
      "epoch": 0.06162109375,
      "grad_norm": 0.27120688557624817,
      "learning_rate": 0.0004987699029765127,
      "loss": 1.961,
      "step": 631
    },
    {
      "epoch": 0.06171875,
      "grad_norm": 0.23527094721794128,
      "learning_rate": 0.000498762465969792,
      "loss": 1.9996,
      "step": 632
    },
    {
      "epoch": 0.06181640625,
      "grad_norm": 0.2519530653953552,
      "learning_rate": 0.0004987550066111832,
      "loss": 1.9926,
      "step": 633
    },
    {
      "epoch": 0.0619140625,
      "grad_norm": 0.3199564218521118,
      "learning_rate": 0.0004987475249014315,
      "loss": 2.0066,
      "step": 634
    },
    {
      "epoch": 0.06201171875,
      "grad_norm": 0.3830641806125641,
      "learning_rate": 0.0004987400208412843,
      "loss": 1.9368,
      "step": 635
    },
    {
      "epoch": 0.062109375,
      "grad_norm": 0.3777483403682709,
      "learning_rate": 0.0004987324944314913,
      "loss": 1.9792,
      "step": 636
    },
    {
      "epoch": 0.06220703125,
      "grad_norm": 0.420107901096344,
      "learning_rate": 0.0004987249456728041,
      "loss": 1.9765,
      "step": 637
    },
    {
      "epoch": 0.0623046875,
      "grad_norm": 0.3748738467693329,
      "learning_rate": 0.0004987173745659768,
      "loss": 1.9826,
      "step": 638
    },
    {
      "epoch": 0.06240234375,
      "grad_norm": 0.3142974078655243,
      "learning_rate": 0.0004987097811117658,
      "loss": 1.9393,
      "step": 639
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.24331647157669067,
      "learning_rate": 0.0004987021653109296,
      "loss": 1.9305,
      "step": 640
    },
    {
      "epoch": 0.06259765625,
      "grad_norm": 0.2792535424232483,
      "learning_rate": 0.0004986945271642289,
      "loss": 1.9437,
      "step": 641
    },
    {
      "epoch": 0.0626953125,
      "grad_norm": 0.24984711408615112,
      "learning_rate": 0.0004986868666724267,
      "loss": 1.9838,
      "step": 642
    },
    {
      "epoch": 0.06279296875,
      "grad_norm": 0.2477482557296753,
      "learning_rate": 0.0004986791838362881,
      "loss": 1.9981,
      "step": 643
    },
    {
      "epoch": 0.062890625,
      "grad_norm": 0.3012976348400116,
      "learning_rate": 0.0004986714786565807,
      "loss": 1.9963,
      "step": 644
    },
    {
      "epoch": 0.06298828125,
      "grad_norm": 0.2480735331773758,
      "learning_rate": 0.0004986637511340742,
      "loss": 1.9567,
      "step": 645
    },
    {
      "epoch": 0.0630859375,
      "grad_norm": 0.20119979977607727,
      "learning_rate": 0.0004986560012695403,
      "loss": 2.0012,
      "step": 646
    },
    {
      "epoch": 0.06318359375,
      "grad_norm": 0.27725833654403687,
      "learning_rate": 0.0004986482290637535,
      "loss": 1.9751,
      "step": 647
    },
    {
      "epoch": 0.06328125,
      "grad_norm": 0.27348190546035767,
      "learning_rate": 0.0004986404345174898,
      "loss": 1.976,
      "step": 648
    },
    {
      "epoch": 0.06337890625,
      "grad_norm": 0.29639676213264465,
      "learning_rate": 0.000498632617631528,
      "loss": 1.9835,
      "step": 649
    },
    {
      "epoch": 0.0634765625,
      "grad_norm": 0.2911996841430664,
      "learning_rate": 0.000498624778406649,
      "loss": 2.0107,
      "step": 650
    },
    {
      "epoch": 0.06357421875,
      "grad_norm": 0.30200451612472534,
      "learning_rate": 0.0004986169168436355,
      "loss": 1.9433,
      "step": 651
    },
    {
      "epoch": 0.063671875,
      "grad_norm": 0.288396954536438,
      "learning_rate": 0.0004986090329432734,
      "loss": 1.9759,
      "step": 652
    },
    {
      "epoch": 0.06376953125,
      "grad_norm": 0.26006969809532166,
      "learning_rate": 0.0004986011267063497,
      "loss": 1.977,
      "step": 653
    },
    {
      "epoch": 0.0638671875,
      "grad_norm": 0.2467355877161026,
      "learning_rate": 0.0004985931981336544,
      "loss": 1.9892,
      "step": 654
    },
    {
      "epoch": 0.06396484375,
      "grad_norm": 0.2180376946926117,
      "learning_rate": 0.0004985852472259797,
      "loss": 2.0012,
      "step": 655
    },
    {
      "epoch": 0.0640625,
      "grad_norm": 0.23811106383800507,
      "learning_rate": 0.0004985772739841193,
      "loss": 1.969,
      "step": 656
    },
    {
      "epoch": 0.06416015625,
      "grad_norm": 0.2517051696777344,
      "learning_rate": 0.00049856927840887,
      "loss": 1.9607,
      "step": 657
    },
    {
      "epoch": 0.0642578125,
      "grad_norm": 0.2900746464729309,
      "learning_rate": 0.0004985612605010305,
      "loss": 1.9865,
      "step": 658
    },
    {
      "epoch": 0.06435546875,
      "grad_norm": 0.2779560983181,
      "learning_rate": 0.0004985532202614017,
      "loss": 1.9787,
      "step": 659
    },
    {
      "epoch": 0.064453125,
      "grad_norm": 0.2686167061328888,
      "learning_rate": 0.0004985451576907865,
      "loss": 1.9279,
      "step": 660
    },
    {
      "epoch": 0.06455078125,
      "grad_norm": 0.25136813521385193,
      "learning_rate": 0.0004985370727899907,
      "loss": 1.9502,
      "step": 661
    },
    {
      "epoch": 0.0646484375,
      "grad_norm": 0.26508840918540955,
      "learning_rate": 0.0004985289655598216,
      "loss": 1.9588,
      "step": 662
    },
    {
      "epoch": 0.06474609375,
      "grad_norm": 0.2178860753774643,
      "learning_rate": 0.000498520836001089,
      "loss": 1.9445,
      "step": 663
    },
    {
      "epoch": 0.06484375,
      "grad_norm": 0.21833141148090363,
      "learning_rate": 0.0004985126841146052,
      "loss": 1.9963,
      "step": 664
    },
    {
      "epoch": 0.06494140625,
      "grad_norm": 0.21572785079479218,
      "learning_rate": 0.0004985045099011844,
      "loss": 1.9789,
      "step": 665
    },
    {
      "epoch": 0.0650390625,
      "grad_norm": 0.23386414349079132,
      "learning_rate": 0.0004984963133616432,
      "loss": 1.9829,
      "step": 666
    },
    {
      "epoch": 0.06513671875,
      "grad_norm": 0.25145047903060913,
      "learning_rate": 0.0004984880944968003,
      "loss": 2.0106,
      "step": 667
    },
    {
      "epoch": 0.065234375,
      "grad_norm": 0.23240795731544495,
      "learning_rate": 0.0004984798533074767,
      "loss": 1.999,
      "step": 668
    },
    {
      "epoch": 0.06533203125,
      "grad_norm": 0.22223520278930664,
      "learning_rate": 0.0004984715897944954,
      "loss": 1.9872,
      "step": 669
    },
    {
      "epoch": 0.0654296875,
      "grad_norm": 0.2768714725971222,
      "learning_rate": 0.0004984633039586823,
      "loss": 1.9656,
      "step": 670
    },
    {
      "epoch": 0.06552734375,
      "grad_norm": 0.35761523246765137,
      "learning_rate": 0.0004984549958008646,
      "loss": 1.9984,
      "step": 671
    },
    {
      "epoch": 0.065625,
      "grad_norm": 0.4054514169692993,
      "learning_rate": 0.0004984466653218726,
      "loss": 1.9406,
      "step": 672
    },
    {
      "epoch": 0.06572265625,
      "grad_norm": 0.40501922369003296,
      "learning_rate": 0.0004984383125225383,
      "loss": 1.9682,
      "step": 673
    },
    {
      "epoch": 0.0658203125,
      "grad_norm": 0.31225842237472534,
      "learning_rate": 0.0004984299374036961,
      "loss": 1.9833,
      "step": 674
    },
    {
      "epoch": 0.06591796875,
      "grad_norm": 0.24159114062786102,
      "learning_rate": 0.0004984215399661825,
      "loss": 1.9634,
      "step": 675
    },
    {
      "epoch": 0.066015625,
      "grad_norm": 0.2537291944026947,
      "learning_rate": 0.0004984131202108364,
      "loss": 1.9563,
      "step": 676
    },
    {
      "epoch": 0.06611328125,
      "grad_norm": 0.29919305443763733,
      "learning_rate": 0.0004984046781384988,
      "loss": 1.9594,
      "step": 677
    },
    {
      "epoch": 0.0662109375,
      "grad_norm": 0.28458645939826965,
      "learning_rate": 0.0004983962137500133,
      "loss": 1.9313,
      "step": 678
    },
    {
      "epoch": 0.06630859375,
      "grad_norm": 0.2523960471153259,
      "learning_rate": 0.0004983877270462249,
      "loss": 1.9616,
      "step": 679
    },
    {
      "epoch": 0.06640625,
      "grad_norm": 0.2605716288089752,
      "learning_rate": 0.0004983792180279816,
      "loss": 1.9631,
      "step": 680
    },
    {
      "epoch": 0.06650390625,
      "grad_norm": 0.280000239610672,
      "learning_rate": 0.0004983706866961335,
      "loss": 1.9945,
      "step": 681
    },
    {
      "epoch": 0.0666015625,
      "grad_norm": 0.2881770730018616,
      "learning_rate": 0.0004983621330515326,
      "loss": 1.9639,
      "step": 682
    },
    {
      "epoch": 0.06669921875,
      "grad_norm": 0.27240094542503357,
      "learning_rate": 0.0004983535570950334,
      "loss": 1.9226,
      "step": 683
    },
    {
      "epoch": 0.066796875,
      "grad_norm": 0.2580428123474121,
      "learning_rate": 0.0004983449588274926,
      "loss": 1.9625,
      "step": 684
    },
    {
      "epoch": 0.06689453125,
      "grad_norm": 0.2719865143299103,
      "learning_rate": 0.0004983363382497692,
      "loss": 1.9941,
      "step": 685
    },
    {
      "epoch": 0.0669921875,
      "grad_norm": 0.2593652904033661,
      "learning_rate": 0.000498327695362724,
      "loss": 1.9558,
      "step": 686
    },
    {
      "epoch": 0.06708984375,
      "grad_norm": 0.2575826346874237,
      "learning_rate": 0.0004983190301672207,
      "loss": 2.0188,
      "step": 687
    },
    {
      "epoch": 0.0671875,
      "grad_norm": 0.23726949095726013,
      "learning_rate": 0.0004983103426641246,
      "loss": 1.9568,
      "step": 688
    },
    {
      "epoch": 0.06728515625,
      "grad_norm": 0.3027707040309906,
      "learning_rate": 0.0004983016328543037,
      "loss": 1.9708,
      "step": 689
    },
    {
      "epoch": 0.0673828125,
      "grad_norm": 0.29431256651878357,
      "learning_rate": 0.0004982929007386279,
      "loss": 1.9668,
      "step": 690
    },
    {
      "epoch": 0.06748046875,
      "grad_norm": 0.24073566496372223,
      "learning_rate": 0.0004982841463179694,
      "loss": 1.9746,
      "step": 691
    },
    {
      "epoch": 0.067578125,
      "grad_norm": 0.27540677785873413,
      "learning_rate": 0.000498275369593203,
      "loss": 1.868,
      "step": 692
    },
    {
      "epoch": 0.06767578125,
      "grad_norm": 0.2665644884109497,
      "learning_rate": 0.0004982665705652052,
      "loss": 1.9528,
      "step": 693
    },
    {
      "epoch": 0.0677734375,
      "grad_norm": 0.2117265909910202,
      "learning_rate": 0.0004982577492348549,
      "loss": 1.9977,
      "step": 694
    },
    {
      "epoch": 0.06787109375,
      "grad_norm": 0.30092543363571167,
      "learning_rate": 0.0004982489056030334,
      "loss": 1.9636,
      "step": 695
    },
    {
      "epoch": 0.06796875,
      "grad_norm": 0.2956363558769226,
      "learning_rate": 0.0004982400396706239,
      "loss": 1.9519,
      "step": 696
    },
    {
      "epoch": 0.06806640625,
      "grad_norm": 0.3209246098995209,
      "learning_rate": 0.0004982311514385124,
      "loss": 1.9761,
      "step": 697
    },
    {
      "epoch": 0.0681640625,
      "grad_norm": 0.4527253806591034,
      "learning_rate": 0.0004982222409075863,
      "loss": 1.9405,
      "step": 698
    },
    {
      "epoch": 0.06826171875,
      "grad_norm": 0.4838014245033264,
      "learning_rate": 0.000498213308078736,
      "loss": 1.9434,
      "step": 699
    },
    {
      "epoch": 0.068359375,
      "grad_norm": 0.4865509569644928,
      "learning_rate": 0.0004982043529528536,
      "loss": 1.9706,
      "step": 700
    },
    {
      "epoch": 0.06845703125,
      "grad_norm": 0.38092029094696045,
      "learning_rate": 0.0004981953755308339,
      "loss": 1.9168,
      "step": 701
    },
    {
      "epoch": 0.0685546875,
      "grad_norm": 0.24092066287994385,
      "learning_rate": 0.0004981863758135735,
      "loss": 1.9693,
      "step": 702
    },
    {
      "epoch": 0.06865234375,
      "grad_norm": 0.3893338143825531,
      "learning_rate": 0.0004981773538019714,
      "loss": 1.9812,
      "step": 703
    },
    {
      "epoch": 0.06875,
      "grad_norm": 0.3019930422306061,
      "learning_rate": 0.0004981683094969287,
      "loss": 1.9207,
      "step": 704
    },
    {
      "epoch": 0.06884765625,
      "grad_norm": 0.2746503949165344,
      "learning_rate": 0.0004981592428993492,
      "loss": 1.9416,
      "step": 705
    },
    {
      "epoch": 0.0689453125,
      "grad_norm": 0.2998049557209015,
      "learning_rate": 0.0004981501540101382,
      "loss": 1.9685,
      "step": 706
    },
    {
      "epoch": 0.06904296875,
      "grad_norm": 0.2986246645450592,
      "learning_rate": 0.0004981410428302037,
      "loss": 1.9827,
      "step": 707
    },
    {
      "epoch": 0.069140625,
      "grad_norm": 0.28714433312416077,
      "learning_rate": 0.000498131909360456,
      "loss": 1.904,
      "step": 708
    },
    {
      "epoch": 0.06923828125,
      "grad_norm": 0.21930216252803802,
      "learning_rate": 0.0004981227536018073,
      "loss": 1.966,
      "step": 709
    },
    {
      "epoch": 0.0693359375,
      "grad_norm": 0.2309812754392624,
      "learning_rate": 0.0004981135755551722,
      "loss": 1.9983,
      "step": 710
    },
    {
      "epoch": 0.06943359375,
      "grad_norm": 0.2016872614622116,
      "learning_rate": 0.0004981043752214674,
      "loss": 1.9382,
      "step": 711
    },
    {
      "epoch": 0.06953125,
      "grad_norm": 0.235287606716156,
      "learning_rate": 0.0004980951526016122,
      "loss": 1.9914,
      "step": 712
    },
    {
      "epoch": 0.06962890625,
      "grad_norm": 0.23780131340026855,
      "learning_rate": 0.0004980859076965276,
      "loss": 1.9404,
      "step": 713
    },
    {
      "epoch": 0.0697265625,
      "grad_norm": 0.2195412665605545,
      "learning_rate": 0.0004980766405071372,
      "loss": 1.9526,
      "step": 714
    },
    {
      "epoch": 0.06982421875,
      "grad_norm": 0.2391882836818695,
      "learning_rate": 0.0004980673510343668,
      "loss": 1.9179,
      "step": 715
    },
    {
      "epoch": 0.069921875,
      "grad_norm": 0.27623385190963745,
      "learning_rate": 0.000498058039279144,
      "loss": 1.9519,
      "step": 716
    },
    {
      "epoch": 0.07001953125,
      "grad_norm": 0.27679604291915894,
      "learning_rate": 0.0004980487052423994,
      "loss": 2.0292,
      "step": 717
    },
    {
      "epoch": 0.0701171875,
      "grad_norm": 0.2968669533729553,
      "learning_rate": 0.0004980393489250651,
      "loss": 1.9162,
      "step": 718
    },
    {
      "epoch": 0.07021484375,
      "grad_norm": 0.2479199320077896,
      "learning_rate": 0.0004980299703280758,
      "loss": 1.9544,
      "step": 719
    },
    {
      "epoch": 0.0703125,
      "grad_norm": 0.2597293555736542,
      "learning_rate": 0.0004980205694523682,
      "loss": 1.9273,
      "step": 720
    },
    {
      "epoch": 0.07041015625,
      "grad_norm": 0.23868051171302795,
      "learning_rate": 0.0004980111462988817,
      "loss": 1.9527,
      "step": 721
    },
    {
      "epoch": 0.0705078125,
      "grad_norm": 0.28150075674057007,
      "learning_rate": 0.0004980017008685573,
      "loss": 1.9523,
      "step": 722
    },
    {
      "epoch": 0.07060546875,
      "grad_norm": 0.3689873516559601,
      "learning_rate": 0.0004979922331623387,
      "loss": 1.9167,
      "step": 723
    },
    {
      "epoch": 0.070703125,
      "grad_norm": 0.380206823348999,
      "learning_rate": 0.0004979827431811713,
      "loss": 1.9025,
      "step": 724
    },
    {
      "epoch": 0.07080078125,
      "grad_norm": 0.2919938266277313,
      "learning_rate": 0.0004979732309260036,
      "loss": 1.9996,
      "step": 725
    },
    {
      "epoch": 0.0708984375,
      "grad_norm": 0.302680104970932,
      "learning_rate": 0.0004979636963977853,
      "loss": 1.95,
      "step": 726
    },
    {
      "epoch": 0.07099609375,
      "grad_norm": 0.25307831168174744,
      "learning_rate": 0.0004979541395974691,
      "loss": 1.9723,
      "step": 727
    },
    {
      "epoch": 0.07109375,
      "grad_norm": 0.304147869348526,
      "learning_rate": 0.0004979445605260096,
      "loss": 2.0359,
      "step": 728
    },
    {
      "epoch": 0.07119140625,
      "grad_norm": 0.35432276129722595,
      "learning_rate": 0.0004979349591843635,
      "loss": 1.9384,
      "step": 729
    },
    {
      "epoch": 0.0712890625,
      "grad_norm": 0.23866906762123108,
      "learning_rate": 0.00049792533557349,
      "loss": 1.9341,
      "step": 730
    },
    {
      "epoch": 0.07138671875,
      "grad_norm": 0.30183711647987366,
      "learning_rate": 0.0004979156896943504,
      "loss": 1.9603,
      "step": 731
    },
    {
      "epoch": 0.071484375,
      "grad_norm": 0.30881768465042114,
      "learning_rate": 0.0004979060215479083,
      "loss": 1.982,
      "step": 732
    },
    {
      "epoch": 0.07158203125,
      "grad_norm": 0.2996484041213989,
      "learning_rate": 0.0004978963311351295,
      "loss": 1.9536,
      "step": 733
    },
    {
      "epoch": 0.0716796875,
      "grad_norm": 0.33594587445259094,
      "learning_rate": 0.0004978866184569818,
      "loss": 1.9813,
      "step": 734
    },
    {
      "epoch": 0.07177734375,
      "grad_norm": 0.30377864837646484,
      "learning_rate": 0.0004978768835144355,
      "loss": 1.9417,
      "step": 735
    },
    {
      "epoch": 0.071875,
      "grad_norm": 0.34858009219169617,
      "learning_rate": 0.0004978671263084631,
      "loss": 1.9368,
      "step": 736
    },
    {
      "epoch": 0.07197265625,
      "grad_norm": 0.28119683265686035,
      "learning_rate": 0.0004978573468400392,
      "loss": 1.9223,
      "step": 737
    },
    {
      "epoch": 0.0720703125,
      "grad_norm": 0.2478085160255432,
      "learning_rate": 0.0004978475451101408,
      "loss": 1.9744,
      "step": 738
    },
    {
      "epoch": 0.07216796875,
      "grad_norm": 0.2461906224489212,
      "learning_rate": 0.0004978377211197466,
      "loss": 1.961,
      "step": 739
    },
    {
      "epoch": 0.072265625,
      "grad_norm": 0.2495601922273636,
      "learning_rate": 0.0004978278748698385,
      "loss": 1.9602,
      "step": 740
    },
    {
      "epoch": 0.07236328125,
      "grad_norm": 0.3028644323348999,
      "learning_rate": 0.0004978180063613997,
      "loss": 1.95,
      "step": 741
    },
    {
      "epoch": 0.0724609375,
      "grad_norm": 0.3690338730812073,
      "learning_rate": 0.000497808115595416,
      "loss": 1.9625,
      "step": 742
    },
    {
      "epoch": 0.07255859375,
      "grad_norm": 0.3791324198246002,
      "learning_rate": 0.0004977982025728755,
      "loss": 1.9747,
      "step": 743
    },
    {
      "epoch": 0.07265625,
      "grad_norm": 0.29515188932418823,
      "learning_rate": 0.0004977882672947683,
      "loss": 1.9774,
      "step": 744
    },
    {
      "epoch": 0.07275390625,
      "grad_norm": 0.29207196831703186,
      "learning_rate": 0.000497778309762087,
      "loss": 1.9704,
      "step": 745
    },
    {
      "epoch": 0.0728515625,
      "grad_norm": 0.23698067665100098,
      "learning_rate": 0.0004977683299758262,
      "loss": 1.978,
      "step": 746
    },
    {
      "epoch": 0.07294921875,
      "grad_norm": 0.2712165415287018,
      "learning_rate": 0.0004977583279369827,
      "loss": 1.9524,
      "step": 747
    },
    {
      "epoch": 0.073046875,
      "grad_norm": 0.32161638140678406,
      "learning_rate": 0.0004977483036465558,
      "loss": 1.9532,
      "step": 748
    },
    {
      "epoch": 0.07314453125,
      "grad_norm": 0.25917574763298035,
      "learning_rate": 0.0004977382571055467,
      "loss": 1.9307,
      "step": 749
    },
    {
      "epoch": 0.0732421875,
      "grad_norm": 0.27562615275382996,
      "learning_rate": 0.000497728188314959,
      "loss": 1.9842,
      "step": 750
    },
    {
      "epoch": 0.07333984375,
      "grad_norm": 0.23242716491222382,
      "learning_rate": 0.0004977180972757986,
      "loss": 1.9097,
      "step": 751
    },
    {
      "epoch": 0.0734375,
      "grad_norm": 0.3111313283443451,
      "learning_rate": 0.0004977079839890732,
      "loss": 1.9812,
      "step": 752
    },
    {
      "epoch": 0.07353515625,
      "grad_norm": 0.3295767605304718,
      "learning_rate": 0.0004976978484557933,
      "loss": 1.9206,
      "step": 753
    },
    {
      "epoch": 0.0736328125,
      "grad_norm": 0.3592395782470703,
      "learning_rate": 0.0004976876906769713,
      "loss": 1.9817,
      "step": 754
    },
    {
      "epoch": 0.07373046875,
      "grad_norm": 0.3530953824520111,
      "learning_rate": 0.0004976775106536218,
      "loss": 1.9831,
      "step": 755
    },
    {
      "epoch": 0.073828125,
      "grad_norm": 0.3064524829387665,
      "learning_rate": 0.0004976673083867617,
      "loss": 1.9207,
      "step": 756
    },
    {
      "epoch": 0.07392578125,
      "grad_norm": 0.281597763299942,
      "learning_rate": 0.0004976570838774102,
      "loss": 1.9781,
      "step": 757
    },
    {
      "epoch": 0.0740234375,
      "grad_norm": 0.296041876077652,
      "learning_rate": 0.0004976468371265886,
      "loss": 1.9708,
      "step": 758
    },
    {
      "epoch": 0.07412109375,
      "grad_norm": 0.3518696427345276,
      "learning_rate": 0.0004976365681353203,
      "loss": 1.9333,
      "step": 759
    },
    {
      "epoch": 0.07421875,
      "grad_norm": 0.21943148970603943,
      "learning_rate": 0.0004976262769046313,
      "loss": 1.9416,
      "step": 760
    },
    {
      "epoch": 0.07431640625,
      "grad_norm": 0.2540123760700226,
      "learning_rate": 0.0004976159634355495,
      "loss": 1.989,
      "step": 761
    },
    {
      "epoch": 0.0744140625,
      "grad_norm": 0.3120715320110321,
      "learning_rate": 0.0004976056277291053,
      "loss": 1.95,
      "step": 762
    },
    {
      "epoch": 0.07451171875,
      "grad_norm": 0.23797550797462463,
      "learning_rate": 0.0004975952697863308,
      "loss": 1.9534,
      "step": 763
    },
    {
      "epoch": 0.074609375,
      "grad_norm": 0.30815449357032776,
      "learning_rate": 0.000497584889608261,
      "loss": 2.0283,
      "step": 764
    },
    {
      "epoch": 0.07470703125,
      "grad_norm": 0.37625932693481445,
      "learning_rate": 0.0004975744871959327,
      "loss": 1.9658,
      "step": 765
    },
    {
      "epoch": 0.0748046875,
      "grad_norm": 0.27407678961753845,
      "learning_rate": 0.0004975640625503848,
      "loss": 1.9458,
      "step": 766
    },
    {
      "epoch": 0.07490234375,
      "grad_norm": 0.26577049493789673,
      "learning_rate": 0.000497553615672659,
      "loss": 1.9667,
      "step": 767
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.29821062088012695,
      "learning_rate": 0.0004975431465637983,
      "loss": 1.9805,
      "step": 768
    },
    {
      "epoch": 0.07509765625,
      "grad_norm": 0.2582527995109558,
      "learning_rate": 0.0004975326552248491,
      "loss": 1.9904,
      "step": 769
    },
    {
      "epoch": 0.0751953125,
      "grad_norm": 0.2533649802207947,
      "learning_rate": 0.0004975221416568591,
      "loss": 1.9383,
      "step": 770
    },
    {
      "epoch": 0.07529296875,
      "grad_norm": 0.253592312335968,
      "learning_rate": 0.0004975116058608784,
      "loss": 1.9855,
      "step": 771
    },
    {
      "epoch": 0.075390625,
      "grad_norm": 0.2658921182155609,
      "learning_rate": 0.0004975010478379596,
      "loss": 1.9845,
      "step": 772
    },
    {
      "epoch": 0.07548828125,
      "grad_norm": 0.25861868262290955,
      "learning_rate": 0.0004974904675891573,
      "loss": 1.9776,
      "step": 773
    },
    {
      "epoch": 0.0755859375,
      "grad_norm": 0.272682249546051,
      "learning_rate": 0.0004974798651155284,
      "loss": 1.9357,
      "step": 774
    },
    {
      "epoch": 0.07568359375,
      "grad_norm": 0.2574002742767334,
      "learning_rate": 0.0004974692404181319,
      "loss": 1.9677,
      "step": 775
    },
    {
      "epoch": 0.07578125,
      "grad_norm": 0.3008319139480591,
      "learning_rate": 0.0004974585934980293,
      "loss": 1.983,
      "step": 776
    },
    {
      "epoch": 0.07587890625,
      "grad_norm": 0.3242790699005127,
      "learning_rate": 0.0004974479243562839,
      "loss": 1.9846,
      "step": 777
    },
    {
      "epoch": 0.0759765625,
      "grad_norm": 0.29044070839881897,
      "learning_rate": 0.0004974372329939617,
      "loss": 2.0012,
      "step": 778
    },
    {
      "epoch": 0.07607421875,
      "grad_norm": 0.32275035977363586,
      "learning_rate": 0.0004974265194121303,
      "loss": 1.9842,
      "step": 779
    },
    {
      "epoch": 0.076171875,
      "grad_norm": 0.31752893328666687,
      "learning_rate": 0.0004974157836118604,
      "loss": 1.9368,
      "step": 780
    },
    {
      "epoch": 0.07626953125,
      "grad_norm": 0.27947962284088135,
      "learning_rate": 0.0004974050255942239,
      "loss": 1.9794,
      "step": 781
    },
    {
      "epoch": 0.0763671875,
      "grad_norm": 0.29937905073165894,
      "learning_rate": 0.000497394245360296,
      "loss": 1.9597,
      "step": 782
    },
    {
      "epoch": 0.07646484375,
      "grad_norm": 0.2969702482223511,
      "learning_rate": 0.0004973834429111529,
      "loss": 1.945,
      "step": 783
    },
    {
      "epoch": 0.0765625,
      "grad_norm": 0.3729354441165924,
      "learning_rate": 0.0004973726182478741,
      "loss": 1.9032,
      "step": 784
    },
    {
      "epoch": 0.07666015625,
      "grad_norm": 0.32856106758117676,
      "learning_rate": 0.0004973617713715408,
      "loss": 1.9551,
      "step": 785
    },
    {
      "epoch": 0.0767578125,
      "grad_norm": 0.23239392042160034,
      "learning_rate": 0.0004973509022832364,
      "loss": 1.9632,
      "step": 786
    },
    {
      "epoch": 0.07685546875,
      "grad_norm": 0.23353087902069092,
      "learning_rate": 0.000497340010984047,
      "loss": 1.9514,
      "step": 787
    },
    {
      "epoch": 0.076953125,
      "grad_norm": 0.23280592262744904,
      "learning_rate": 0.00049732909747506,
      "loss": 1.9696,
      "step": 788
    },
    {
      "epoch": 0.07705078125,
      "grad_norm": 0.2193138748407364,
      "learning_rate": 0.0004973181617573658,
      "loss": 1.9734,
      "step": 789
    },
    {
      "epoch": 0.0771484375,
      "grad_norm": 0.3234734833240509,
      "learning_rate": 0.0004973072038320569,
      "loss": 1.9874,
      "step": 790
    },
    {
      "epoch": 0.07724609375,
      "grad_norm": 0.35144004225730896,
      "learning_rate": 0.0004972962237002278,
      "loss": 1.9331,
      "step": 791
    },
    {
      "epoch": 0.07734375,
      "grad_norm": 0.37716230750083923,
      "learning_rate": 0.0004972852213629753,
      "loss": 1.9731,
      "step": 792
    },
    {
      "epoch": 0.07744140625,
      "grad_norm": 0.3221200108528137,
      "learning_rate": 0.0004972741968213985,
      "loss": 2.0043,
      "step": 793
    },
    {
      "epoch": 0.0775390625,
      "grad_norm": 0.23167745769023895,
      "learning_rate": 0.0004972631500765985,
      "loss": 1.9634,
      "step": 794
    },
    {
      "epoch": 0.07763671875,
      "grad_norm": 0.4177049398422241,
      "learning_rate": 0.0004972520811296789,
      "loss": 1.9533,
      "step": 795
    },
    {
      "epoch": 0.077734375,
      "grad_norm": 0.39038336277008057,
      "learning_rate": 0.0004972409899817455,
      "loss": 1.9508,
      "step": 796
    },
    {
      "epoch": 0.07783203125,
      "grad_norm": 0.4033074676990509,
      "learning_rate": 0.0004972298766339061,
      "loss": 1.965,
      "step": 797
    },
    {
      "epoch": 0.0779296875,
      "grad_norm": 0.3271097242832184,
      "learning_rate": 0.0004972187410872707,
      "loss": 1.9893,
      "step": 798
    },
    {
      "epoch": 0.07802734375,
      "grad_norm": 0.30553460121154785,
      "learning_rate": 0.0004972075833429516,
      "loss": 1.9735,
      "step": 799
    },
    {
      "epoch": 0.078125,
      "grad_norm": 0.28286099433898926,
      "learning_rate": 0.0004971964034020637,
      "loss": 1.9704,
      "step": 800
    },
    {
      "epoch": 0.07822265625,
      "grad_norm": 0.28064650297164917,
      "learning_rate": 0.0004971852012657235,
      "loss": 1.9452,
      "step": 801
    },
    {
      "epoch": 0.0783203125,
      "grad_norm": 0.2370154857635498,
      "learning_rate": 0.0004971739769350502,
      "loss": 2.0068,
      "step": 802
    },
    {
      "epoch": 0.07841796875,
      "grad_norm": 0.26157453656196594,
      "learning_rate": 0.0004971627304111648,
      "loss": 1.9209,
      "step": 803
    },
    {
      "epoch": 0.078515625,
      "grad_norm": 0.2244575023651123,
      "learning_rate": 0.0004971514616951908,
      "loss": 1.9952,
      "step": 804
    },
    {
      "epoch": 0.07861328125,
      "grad_norm": 0.241064190864563,
      "learning_rate": 0.0004971401707882538,
      "loss": 1.9616,
      "step": 805
    },
    {
      "epoch": 0.0787109375,
      "grad_norm": 0.23037207126617432,
      "learning_rate": 0.0004971288576914819,
      "loss": 1.9792,
      "step": 806
    },
    {
      "epoch": 0.07880859375,
      "grad_norm": 0.2162441909313202,
      "learning_rate": 0.0004971175224060049,
      "loss": 1.9556,
      "step": 807
    },
    {
      "epoch": 0.07890625,
      "grad_norm": 0.2614160180091858,
      "learning_rate": 0.0004971061649329551,
      "loss": 1.9247,
      "step": 808
    },
    {
      "epoch": 0.07900390625,
      "grad_norm": 0.22268271446228027,
      "learning_rate": 0.0004970947852734672,
      "loss": 1.9596,
      "step": 809
    },
    {
      "epoch": 0.0791015625,
      "grad_norm": 0.26265689730644226,
      "learning_rate": 0.0004970833834286779,
      "loss": 1.9722,
      "step": 810
    },
    {
      "epoch": 0.07919921875,
      "grad_norm": 0.29413190484046936,
      "learning_rate": 0.000497071959399726,
      "loss": 1.9808,
      "step": 811
    },
    {
      "epoch": 0.079296875,
      "grad_norm": 0.3389902114868164,
      "learning_rate": 0.0004970605131877527,
      "loss": 1.9986,
      "step": 812
    },
    {
      "epoch": 0.07939453125,
      "grad_norm": 0.3456060290336609,
      "learning_rate": 0.0004970490447939016,
      "loss": 1.9556,
      "step": 813
    },
    {
      "epoch": 0.0794921875,
      "grad_norm": 0.3039393126964569,
      "learning_rate": 0.0004970375542193179,
      "loss": 1.9359,
      "step": 814
    },
    {
      "epoch": 0.07958984375,
      "grad_norm": 0.46128201484680176,
      "learning_rate": 0.0004970260414651497,
      "loss": 1.935,
      "step": 815
    },
    {
      "epoch": 0.0796875,
      "grad_norm": 0.5321182608604431,
      "learning_rate": 0.000497014506532547,
      "loss": 1.9767,
      "step": 816
    },
    {
      "epoch": 0.07978515625,
      "grad_norm": 0.39562714099884033,
      "learning_rate": 0.0004970029494226618,
      "loss": 1.9803,
      "step": 817
    },
    {
      "epoch": 0.0798828125,
      "grad_norm": 0.2717466950416565,
      "learning_rate": 0.0004969913701366488,
      "loss": 1.9675,
      "step": 818
    },
    {
      "epoch": 0.07998046875,
      "grad_norm": 0.32809481024742126,
      "learning_rate": 0.0004969797686756646,
      "loss": 1.9869,
      "step": 819
    },
    {
      "epoch": 0.080078125,
      "grad_norm": 0.3525324761867523,
      "learning_rate": 0.0004969681450408681,
      "loss": 1.9858,
      "step": 820
    },
    {
      "epoch": 0.08017578125,
      "grad_norm": 0.30448198318481445,
      "learning_rate": 0.0004969564992334202,
      "loss": 2.0067,
      "step": 821
    },
    {
      "epoch": 0.0802734375,
      "grad_norm": 0.27088144421577454,
      "learning_rate": 0.0004969448312544845,
      "loss": 2.0068,
      "step": 822
    },
    {
      "epoch": 0.08037109375,
      "grad_norm": 0.26881691813468933,
      "learning_rate": 0.0004969331411052265,
      "loss": 1.9418,
      "step": 823
    },
    {
      "epoch": 0.08046875,
      "grad_norm": 0.31323063373565674,
      "learning_rate": 0.0004969214287868138,
      "loss": 1.9662,
      "step": 824
    },
    {
      "epoch": 0.08056640625,
      "grad_norm": 0.25669077038764954,
      "learning_rate": 0.0004969096943004163,
      "loss": 1.9733,
      "step": 825
    },
    {
      "epoch": 0.0806640625,
      "grad_norm": 0.27999046444892883,
      "learning_rate": 0.0004968979376472065,
      "loss": 1.9611,
      "step": 826
    },
    {
      "epoch": 0.08076171875,
      "grad_norm": 0.35361799597740173,
      "learning_rate": 0.0004968861588283584,
      "loss": 1.9035,
      "step": 827
    },
    {
      "epoch": 0.080859375,
      "grad_norm": 0.290341317653656,
      "learning_rate": 0.0004968743578450489,
      "loss": 2.0007,
      "step": 828
    },
    {
      "epoch": 0.08095703125,
      "grad_norm": 0.29945844411849976,
      "learning_rate": 0.0004968625346984565,
      "loss": 1.9724,
      "step": 829
    },
    {
      "epoch": 0.0810546875,
      "grad_norm": 0.2630455493927002,
      "learning_rate": 0.0004968506893897626,
      "loss": 1.9765,
      "step": 830
    },
    {
      "epoch": 0.08115234375,
      "grad_norm": 0.2183736264705658,
      "learning_rate": 0.0004968388219201501,
      "loss": 1.9414,
      "step": 831
    },
    {
      "epoch": 0.08125,
      "grad_norm": 0.24703919887542725,
      "learning_rate": 0.0004968269322908046,
      "loss": 1.9725,
      "step": 832
    },
    {
      "epoch": 0.08134765625,
      "grad_norm": 0.22808632254600525,
      "learning_rate": 0.0004968150205029139,
      "loss": 1.9121,
      "step": 833
    },
    {
      "epoch": 0.0814453125,
      "grad_norm": 0.18958304822444916,
      "learning_rate": 0.0004968030865576677,
      "loss": 1.971,
      "step": 834
    },
    {
      "epoch": 0.08154296875,
      "grad_norm": 0.22013933956623077,
      "learning_rate": 0.0004967911304562581,
      "loss": 1.9703,
      "step": 835
    },
    {
      "epoch": 0.081640625,
      "grad_norm": 0.21636781096458435,
      "learning_rate": 0.0004967791521998795,
      "loss": 1.992,
      "step": 836
    },
    {
      "epoch": 0.08173828125,
      "grad_norm": 0.20808343589305878,
      "learning_rate": 0.0004967671517897284,
      "loss": 1.9881,
      "step": 837
    },
    {
      "epoch": 0.0818359375,
      "grad_norm": 0.23455387353897095,
      "learning_rate": 0.0004967551292270034,
      "loss": 1.9635,
      "step": 838
    },
    {
      "epoch": 0.08193359375,
      "grad_norm": 0.2605065703392029,
      "learning_rate": 0.0004967430845129057,
      "loss": 1.8877,
      "step": 839
    },
    {
      "epoch": 0.08203125,
      "grad_norm": 0.30832260847091675,
      "learning_rate": 0.0004967310176486382,
      "loss": 1.9557,
      "step": 840
    },
    {
      "epoch": 0.08212890625,
      "grad_norm": 0.32088643312454224,
      "learning_rate": 0.0004967189286354066,
      "loss": 1.9352,
      "step": 841
    },
    {
      "epoch": 0.0822265625,
      "grad_norm": 0.3073631823062897,
      "learning_rate": 0.0004967068174744181,
      "loss": 1.9487,
      "step": 842
    },
    {
      "epoch": 0.08232421875,
      "grad_norm": 0.23467223346233368,
      "learning_rate": 0.0004966946841668828,
      "loss": 1.9514,
      "step": 843
    },
    {
      "epoch": 0.082421875,
      "grad_norm": 0.2447347342967987,
      "learning_rate": 0.0004966825287140125,
      "loss": 1.9435,
      "step": 844
    },
    {
      "epoch": 0.08251953125,
      "grad_norm": 0.2715449631214142,
      "learning_rate": 0.0004966703511170215,
      "loss": 1.9591,
      "step": 845
    },
    {
      "epoch": 0.0826171875,
      "grad_norm": 0.28944098949432373,
      "learning_rate": 0.0004966581513771263,
      "loss": 1.952,
      "step": 846
    },
    {
      "epoch": 0.08271484375,
      "grad_norm": 0.25582170486450195,
      "learning_rate": 0.0004966459294955455,
      "loss": 1.9486,
      "step": 847
    },
    {
      "epoch": 0.0828125,
      "grad_norm": 0.305513858795166,
      "learning_rate": 0.0004966336854734999,
      "loss": 1.9416,
      "step": 848
    },
    {
      "epoch": 0.08291015625,
      "grad_norm": 0.28799137473106384,
      "learning_rate": 0.0004966214193122127,
      "loss": 1.9417,
      "step": 849
    },
    {
      "epoch": 0.0830078125,
      "grad_norm": 0.22209681570529938,
      "learning_rate": 0.000496609131012909,
      "loss": 1.9641,
      "step": 850
    },
    {
      "epoch": 0.08310546875,
      "grad_norm": 0.35411134362220764,
      "learning_rate": 0.0004965968205768165,
      "loss": 1.9497,
      "step": 851
    },
    {
      "epoch": 0.083203125,
      "grad_norm": 0.2821413576602936,
      "learning_rate": 0.0004965844880051647,
      "loss": 1.9398,
      "step": 852
    },
    {
      "epoch": 0.08330078125,
      "grad_norm": 0.31592175364494324,
      "learning_rate": 0.0004965721332991856,
      "loss": 1.9407,
      "step": 853
    },
    {
      "epoch": 0.0833984375,
      "grad_norm": 0.3579123318195343,
      "learning_rate": 0.0004965597564601134,
      "loss": 1.9767,
      "step": 854
    },
    {
      "epoch": 0.08349609375,
      "grad_norm": 0.3371833860874176,
      "learning_rate": 0.0004965473574891845,
      "loss": 2.0025,
      "step": 855
    },
    {
      "epoch": 0.08359375,
      "grad_norm": 0.39282771944999695,
      "learning_rate": 0.0004965349363876371,
      "loss": 1.9303,
      "step": 856
    },
    {
      "epoch": 0.08369140625,
      "grad_norm": 0.34869179129600525,
      "learning_rate": 0.0004965224931567122,
      "loss": 1.9613,
      "step": 857
    },
    {
      "epoch": 0.0837890625,
      "grad_norm": 0.2918208837509155,
      "learning_rate": 0.0004965100277976528,
      "loss": 1.9242,
      "step": 858
    },
    {
      "epoch": 0.08388671875,
      "grad_norm": 0.25440847873687744,
      "learning_rate": 0.0004964975403117041,
      "loss": 1.9223,
      "step": 859
    },
    {
      "epoch": 0.083984375,
      "grad_norm": 0.27069318294525146,
      "learning_rate": 0.0004964850307001132,
      "loss": 1.9711,
      "step": 860
    },
    {
      "epoch": 0.08408203125,
      "grad_norm": 0.27405187487602234,
      "learning_rate": 0.0004964724989641301,
      "loss": 1.9646,
      "step": 861
    },
    {
      "epoch": 0.0841796875,
      "grad_norm": 0.3116970956325531,
      "learning_rate": 0.0004964599451050064,
      "loss": 1.9231,
      "step": 862
    },
    {
      "epoch": 0.08427734375,
      "grad_norm": 0.3815697729587555,
      "learning_rate": 0.000496447369123996,
      "loss": 1.9773,
      "step": 863
    },
    {
      "epoch": 0.084375,
      "grad_norm": 0.32103797793388367,
      "learning_rate": 0.0004964347710223555,
      "loss": 1.936,
      "step": 864
    },
    {
      "epoch": 0.08447265625,
      "grad_norm": 0.42826011776924133,
      "learning_rate": 0.0004964221508013429,
      "loss": 1.9315,
      "step": 865
    },
    {
      "epoch": 0.0845703125,
      "grad_norm": 0.3091580271720886,
      "learning_rate": 0.0004964095084622192,
      "loss": 1.9362,
      "step": 866
    },
    {
      "epoch": 0.08466796875,
      "grad_norm": 0.2816343605518341,
      "learning_rate": 0.0004963968440062471,
      "loss": 2.0076,
      "step": 867
    },
    {
      "epoch": 0.084765625,
      "grad_norm": 0.35303476452827454,
      "learning_rate": 0.0004963841574346917,
      "loss": 1.9399,
      "step": 868
    },
    {
      "epoch": 0.08486328125,
      "grad_norm": 0.27021846175193787,
      "learning_rate": 0.0004963714487488202,
      "loss": 1.9556,
      "step": 869
    },
    {
      "epoch": 0.0849609375,
      "grad_norm": 0.28174805641174316,
      "learning_rate": 0.0004963587179499021,
      "loss": 1.9749,
      "step": 870
    },
    {
      "epoch": 0.08505859375,
      "grad_norm": 0.2774275243282318,
      "learning_rate": 0.0004963459650392093,
      "loss": 1.9457,
      "step": 871
    },
    {
      "epoch": 0.08515625,
      "grad_norm": 0.2178190052509308,
      "learning_rate": 0.0004963331900180154,
      "loss": 2.0192,
      "step": 872
    },
    {
      "epoch": 0.08525390625,
      "grad_norm": 0.2983119487762451,
      "learning_rate": 0.0004963203928875967,
      "loss": 1.9659,
      "step": 873
    },
    {
      "epoch": 0.0853515625,
      "grad_norm": 0.2878938913345337,
      "learning_rate": 0.0004963075736492315,
      "loss": 1.9581,
      "step": 874
    },
    {
      "epoch": 0.08544921875,
      "grad_norm": 0.19974899291992188,
      "learning_rate": 0.0004962947323042002,
      "loss": 1.9898,
      "step": 875
    },
    {
      "epoch": 0.085546875,
      "grad_norm": 0.31860581040382385,
      "learning_rate": 0.0004962818688537857,
      "loss": 1.9737,
      "step": 876
    },
    {
      "epoch": 0.08564453125,
      "grad_norm": 0.2651256322860718,
      "learning_rate": 0.0004962689832992729,
      "loss": 1.9977,
      "step": 877
    },
    {
      "epoch": 0.0857421875,
      "grad_norm": 0.286821573972702,
      "learning_rate": 0.0004962560756419489,
      "loss": 1.9317,
      "step": 878
    },
    {
      "epoch": 0.08583984375,
      "grad_norm": 0.3837340772151947,
      "learning_rate": 0.0004962431458831032,
      "loss": 1.9419,
      "step": 879
    },
    {
      "epoch": 0.0859375,
      "grad_norm": 0.32222527265548706,
      "learning_rate": 0.0004962301940240272,
      "loss": 1.9603,
      "step": 880
    },
    {
      "epoch": 0.08603515625,
      "grad_norm": 0.33181512355804443,
      "learning_rate": 0.0004962172200660146,
      "loss": 1.9646,
      "step": 881
    },
    {
      "epoch": 0.0861328125,
      "grad_norm": 0.2813611626625061,
      "learning_rate": 0.0004962042240103617,
      "loss": 1.9706,
      "step": 882
    },
    {
      "epoch": 0.08623046875,
      "grad_norm": 0.2933270335197449,
      "learning_rate": 0.0004961912058583664,
      "loss": 1.9529,
      "step": 883
    },
    {
      "epoch": 0.086328125,
      "grad_norm": 0.31641921401023865,
      "learning_rate": 0.0004961781656113292,
      "loss": 1.9437,
      "step": 884
    },
    {
      "epoch": 0.08642578125,
      "grad_norm": 0.39271247386932373,
      "learning_rate": 0.0004961651032705528,
      "loss": 1.957,
      "step": 885
    },
    {
      "epoch": 0.0865234375,
      "grad_norm": 0.3720405697822571,
      "learning_rate": 0.000496152018837342,
      "loss": 1.9393,
      "step": 886
    },
    {
      "epoch": 0.08662109375,
      "grad_norm": 0.27104172110557556,
      "learning_rate": 0.0004961389123130037,
      "loss": 1.9547,
      "step": 887
    },
    {
      "epoch": 0.08671875,
      "grad_norm": 0.24182896316051483,
      "learning_rate": 0.0004961257836988472,
      "loss": 1.9456,
      "step": 888
    },
    {
      "epoch": 0.08681640625,
      "grad_norm": 0.22501450777053833,
      "learning_rate": 0.0004961126329961838,
      "loss": 1.9336,
      "step": 889
    },
    {
      "epoch": 0.0869140625,
      "grad_norm": 0.2969515323638916,
      "learning_rate": 0.0004960994602063273,
      "loss": 1.9415,
      "step": 890
    },
    {
      "epoch": 0.08701171875,
      "grad_norm": 0.3117569386959076,
      "learning_rate": 0.0004960862653305934,
      "loss": 1.8993,
      "step": 891
    },
    {
      "epoch": 0.087109375,
      "grad_norm": 0.32299551367759705,
      "learning_rate": 0.0004960730483703004,
      "loss": 1.9879,
      "step": 892
    },
    {
      "epoch": 0.08720703125,
      "grad_norm": 0.335592657327652,
      "learning_rate": 0.0004960598093267682,
      "loss": 1.9665,
      "step": 893
    },
    {
      "epoch": 0.0873046875,
      "grad_norm": 0.21160855889320374,
      "learning_rate": 0.0004960465482013197,
      "loss": 1.8927,
      "step": 894
    },
    {
      "epoch": 0.08740234375,
      "grad_norm": 0.30621418356895447,
      "learning_rate": 0.0004960332649952792,
      "loss": 1.9828,
      "step": 895
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.3541114330291748,
      "learning_rate": 0.0004960199597099737,
      "loss": 1.9478,
      "step": 896
    },
    {
      "epoch": 0.08759765625,
      "grad_norm": 0.31596067547798157,
      "learning_rate": 0.0004960066323467323,
      "loss": 1.9355,
      "step": 897
    },
    {
      "epoch": 0.0876953125,
      "grad_norm": 0.3170725107192993,
      "learning_rate": 0.0004959932829068863,
      "loss": 1.9501,
      "step": 898
    },
    {
      "epoch": 0.08779296875,
      "grad_norm": 0.26953962445259094,
      "learning_rate": 0.0004959799113917691,
      "loss": 1.9488,
      "step": 899
    },
    {
      "epoch": 0.087890625,
      "grad_norm": 0.23792020976543427,
      "learning_rate": 0.0004959665178027165,
      "loss": 1.941,
      "step": 900
    },
    {
      "epoch": 0.08798828125,
      "grad_norm": 0.2375611513853073,
      "learning_rate": 0.0004959531021410664,
      "loss": 1.9133,
      "step": 901
    },
    {
      "epoch": 0.0880859375,
      "grad_norm": 0.20919479429721832,
      "learning_rate": 0.0004959396644081588,
      "loss": 1.9624,
      "step": 902
    },
    {
      "epoch": 0.08818359375,
      "grad_norm": 0.22488316893577576,
      "learning_rate": 0.0004959262046053361,
      "loss": 1.9408,
      "step": 903
    },
    {
      "epoch": 0.08828125,
      "grad_norm": 0.2249651849269867,
      "learning_rate": 0.0004959127227339427,
      "loss": 2.0022,
      "step": 904
    },
    {
      "epoch": 0.08837890625,
      "grad_norm": 0.19234181940555573,
      "learning_rate": 0.0004958992187953256,
      "loss": 1.9221,
      "step": 905
    },
    {
      "epoch": 0.0884765625,
      "grad_norm": 0.21266022324562073,
      "learning_rate": 0.0004958856927908334,
      "loss": 1.9796,
      "step": 906
    },
    {
      "epoch": 0.08857421875,
      "grad_norm": 0.22636987268924713,
      "learning_rate": 0.0004958721447218174,
      "loss": 1.9799,
      "step": 907
    },
    {
      "epoch": 0.088671875,
      "grad_norm": 0.21743637323379517,
      "learning_rate": 0.0004958585745896308,
      "loss": 1.9156,
      "step": 908
    },
    {
      "epoch": 0.08876953125,
      "grad_norm": 0.316840797662735,
      "learning_rate": 0.0004958449823956294,
      "loss": 1.9856,
      "step": 909
    },
    {
      "epoch": 0.0888671875,
      "grad_norm": 0.2583603262901306,
      "learning_rate": 0.0004958313681411706,
      "loss": 1.9601,
      "step": 910
    },
    {
      "epoch": 0.08896484375,
      "grad_norm": 0.2872125208377838,
      "learning_rate": 0.0004958177318276146,
      "loss": 1.9526,
      "step": 911
    },
    {
      "epoch": 0.0890625,
      "grad_norm": 0.37896475195884705,
      "learning_rate": 0.0004958040734563235,
      "loss": 1.9465,
      "step": 912
    },
    {
      "epoch": 0.08916015625,
      "grad_norm": 0.3056401014328003,
      "learning_rate": 0.0004957903930286616,
      "loss": 1.9344,
      "step": 913
    },
    {
      "epoch": 0.0892578125,
      "grad_norm": 0.35092082619667053,
      "learning_rate": 0.0004957766905459953,
      "loss": 1.9294,
      "step": 914
    },
    {
      "epoch": 0.08935546875,
      "grad_norm": 0.2681847810745239,
      "learning_rate": 0.0004957629660096937,
      "loss": 1.9436,
      "step": 915
    },
    {
      "epoch": 0.089453125,
      "grad_norm": 0.25762611627578735,
      "learning_rate": 0.0004957492194211275,
      "loss": 1.931,
      "step": 916
    },
    {
      "epoch": 0.08955078125,
      "grad_norm": 0.24634388089179993,
      "learning_rate": 0.00049573545078167,
      "loss": 1.9373,
      "step": 917
    },
    {
      "epoch": 0.0896484375,
      "grad_norm": 0.27374333143234253,
      "learning_rate": 0.0004957216600926965,
      "loss": 2.046,
      "step": 918
    },
    {
      "epoch": 0.08974609375,
      "grad_norm": 0.338375061750412,
      "learning_rate": 0.0004957078473555845,
      "loss": 2.0259,
      "step": 919
    },
    {
      "epoch": 0.08984375,
      "grad_norm": 0.27678367495536804,
      "learning_rate": 0.0004956940125717139,
      "loss": 1.9947,
      "step": 920
    },
    {
      "epoch": 0.08994140625,
      "grad_norm": 0.266079306602478,
      "learning_rate": 0.0004956801557424666,
      "loss": 2.0097,
      "step": 921
    },
    {
      "epoch": 0.0900390625,
      "grad_norm": 0.28650638461112976,
      "learning_rate": 0.0004956662768692268,
      "loss": 1.9893,
      "step": 922
    },
    {
      "epoch": 0.09013671875,
      "grad_norm": 0.2717742323875427,
      "learning_rate": 0.0004956523759533809,
      "loss": 1.976,
      "step": 923
    },
    {
      "epoch": 0.090234375,
      "grad_norm": 0.3267741799354553,
      "learning_rate": 0.0004956384529963174,
      "loss": 1.9803,
      "step": 924
    },
    {
      "epoch": 0.09033203125,
      "grad_norm": 0.32973724603652954,
      "learning_rate": 0.0004956245079994272,
      "loss": 1.942,
      "step": 925
    },
    {
      "epoch": 0.0904296875,
      "grad_norm": 0.3257177770137787,
      "learning_rate": 0.0004956105409641031,
      "loss": 1.9584,
      "step": 926
    },
    {
      "epoch": 0.09052734375,
      "grad_norm": 0.31881803274154663,
      "learning_rate": 0.0004955965518917405,
      "loss": 1.9386,
      "step": 927
    },
    {
      "epoch": 0.090625,
      "grad_norm": 0.2814694046974182,
      "learning_rate": 0.0004955825407837365,
      "loss": 1.9114,
      "step": 928
    },
    {
      "epoch": 0.09072265625,
      "grad_norm": 0.24232172966003418,
      "learning_rate": 0.000495568507641491,
      "loss": 1.954,
      "step": 929
    },
    {
      "epoch": 0.0908203125,
      "grad_norm": 0.2062203288078308,
      "learning_rate": 0.0004955544524664056,
      "loss": 1.9682,
      "step": 930
    },
    {
      "epoch": 0.09091796875,
      "grad_norm": 0.2777712047100067,
      "learning_rate": 0.0004955403752598844,
      "loss": 1.983,
      "step": 931
    },
    {
      "epoch": 0.091015625,
      "grad_norm": 0.31253954768180847,
      "learning_rate": 0.0004955262760233335,
      "loss": 1.9211,
      "step": 932
    },
    {
      "epoch": 0.09111328125,
      "grad_norm": 0.292059987783432,
      "learning_rate": 0.0004955121547581613,
      "loss": 1.9745,
      "step": 933
    },
    {
      "epoch": 0.0912109375,
      "grad_norm": 0.309123694896698,
      "learning_rate": 0.0004954980114657783,
      "loss": 1.966,
      "step": 934
    },
    {
      "epoch": 0.09130859375,
      "grad_norm": 0.2765352129936218,
      "learning_rate": 0.0004954838461475975,
      "loss": 1.9535,
      "step": 935
    },
    {
      "epoch": 0.09140625,
      "grad_norm": 0.2576250731945038,
      "learning_rate": 0.0004954696588050338,
      "loss": 1.9002,
      "step": 936
    },
    {
      "epoch": 0.09150390625,
      "grad_norm": 0.3167097866535187,
      "learning_rate": 0.0004954554494395044,
      "loss": 1.9249,
      "step": 937
    },
    {
      "epoch": 0.0916015625,
      "grad_norm": 0.32505497336387634,
      "learning_rate": 0.0004954412180524285,
      "loss": 1.9669,
      "step": 938
    },
    {
      "epoch": 0.09169921875,
      "grad_norm": 0.3114219307899475,
      "learning_rate": 0.000495426964645228,
      "loss": 1.9276,
      "step": 939
    },
    {
      "epoch": 0.091796875,
      "grad_norm": 0.2786170542240143,
      "learning_rate": 0.0004954126892193264,
      "loss": 1.965,
      "step": 940
    },
    {
      "epoch": 0.09189453125,
      "grad_norm": 0.2753596901893616,
      "learning_rate": 0.00049539839177615,
      "loss": 1.9925,
      "step": 941
    },
    {
      "epoch": 0.0919921875,
      "grad_norm": 0.29401320219039917,
      "learning_rate": 0.0004953840723171268,
      "loss": 1.9772,
      "step": 942
    },
    {
      "epoch": 0.09208984375,
      "grad_norm": 0.3157658278942108,
      "learning_rate": 0.0004953697308436871,
      "loss": 2.0019,
      "step": 943
    },
    {
      "epoch": 0.0921875,
      "grad_norm": 0.29067566990852356,
      "learning_rate": 0.0004953553673572636,
      "loss": 1.9753,
      "step": 944
    },
    {
      "epoch": 0.09228515625,
      "grad_norm": 0.28693830966949463,
      "learning_rate": 0.0004953409818592911,
      "loss": 1.9436,
      "step": 945
    },
    {
      "epoch": 0.0923828125,
      "grad_norm": 0.2536534070968628,
      "learning_rate": 0.0004953265743512065,
      "loss": 1.9801,
      "step": 946
    },
    {
      "epoch": 0.09248046875,
      "grad_norm": 0.3041675090789795,
      "learning_rate": 0.000495312144834449,
      "loss": 1.9378,
      "step": 947
    },
    {
      "epoch": 0.092578125,
      "grad_norm": 0.3237321376800537,
      "learning_rate": 0.0004952976933104602,
      "loss": 1.9781,
      "step": 948
    },
    {
      "epoch": 0.09267578125,
      "grad_norm": 0.25767290592193604,
      "learning_rate": 0.0004952832197806835,
      "loss": 1.9031,
      "step": 949
    },
    {
      "epoch": 0.0927734375,
      "grad_norm": 0.25587791204452515,
      "learning_rate": 0.0004952687242465645,
      "loss": 1.9405,
      "step": 950
    },
    {
      "epoch": 0.09287109375,
      "grad_norm": 0.2901047468185425,
      "learning_rate": 0.0004952542067095515,
      "loss": 1.9567,
      "step": 951
    },
    {
      "epoch": 0.09296875,
      "grad_norm": 0.31517183780670166,
      "learning_rate": 0.0004952396671710945,
      "loss": 1.9464,
      "step": 952
    },
    {
      "epoch": 0.09306640625,
      "grad_norm": 0.30896711349487305,
      "learning_rate": 0.0004952251056326458,
      "loss": 1.9096,
      "step": 953
    },
    {
      "epoch": 0.0931640625,
      "grad_norm": 0.26281988620758057,
      "learning_rate": 0.0004952105220956602,
      "loss": 1.9616,
      "step": 954
    },
    {
      "epoch": 0.09326171875,
      "grad_norm": 0.23971204459667206,
      "learning_rate": 0.0004951959165615942,
      "loss": 1.9928,
      "step": 955
    },
    {
      "epoch": 0.093359375,
      "grad_norm": 0.22277623414993286,
      "learning_rate": 0.000495181289031907,
      "loss": 1.9652,
      "step": 956
    },
    {
      "epoch": 0.09345703125,
      "grad_norm": 0.26211845874786377,
      "learning_rate": 0.0004951666395080596,
      "loss": 1.9617,
      "step": 957
    },
    {
      "epoch": 0.0935546875,
      "grad_norm": 0.24874535202980042,
      "learning_rate": 0.0004951519679915155,
      "loss": 1.9509,
      "step": 958
    },
    {
      "epoch": 0.09365234375,
      "grad_norm": 0.21750757098197937,
      "learning_rate": 0.0004951372744837401,
      "loss": 1.966,
      "step": 959
    },
    {
      "epoch": 0.09375,
      "grad_norm": 0.2798830270767212,
      "learning_rate": 0.0004951225589862012,
      "loss": 1.9574,
      "step": 960
    },
    {
      "epoch": 0.09384765625,
      "grad_norm": 0.33166754245758057,
      "learning_rate": 0.0004951078215003688,
      "loss": 1.9672,
      "step": 961
    },
    {
      "epoch": 0.0939453125,
      "grad_norm": 0.3122573792934418,
      "learning_rate": 0.0004950930620277149,
      "loss": 1.9205,
      "step": 962
    },
    {
      "epoch": 0.09404296875,
      "grad_norm": 0.233395054936409,
      "learning_rate": 0.0004950782805697141,
      "loss": 1.9389,
      "step": 963
    },
    {
      "epoch": 0.094140625,
      "grad_norm": 0.2523380219936371,
      "learning_rate": 0.0004950634771278427,
      "loss": 1.9643,
      "step": 964
    },
    {
      "epoch": 0.09423828125,
      "grad_norm": 0.2774633765220642,
      "learning_rate": 0.0004950486517035796,
      "loss": 1.9467,
      "step": 965
    },
    {
      "epoch": 0.0943359375,
      "grad_norm": 0.2782750129699707,
      "learning_rate": 0.0004950338042984056,
      "loss": 1.9296,
      "step": 966
    },
    {
      "epoch": 0.09443359375,
      "grad_norm": 0.3408234417438507,
      "learning_rate": 0.0004950189349138039,
      "loss": 1.9705,
      "step": 967
    },
    {
      "epoch": 0.09453125,
      "grad_norm": 0.27266553044319153,
      "learning_rate": 0.0004950040435512598,
      "loss": 1.9292,
      "step": 968
    },
    {
      "epoch": 0.09462890625,
      "grad_norm": 0.2276991307735443,
      "learning_rate": 0.0004949891302122607,
      "loss": 1.9793,
      "step": 969
    },
    {
      "epoch": 0.0947265625,
      "grad_norm": 0.23914872109889984,
      "learning_rate": 0.0004949741948982965,
      "loss": 1.9632,
      "step": 970
    },
    {
      "epoch": 0.09482421875,
      "grad_norm": 0.24836085736751556,
      "learning_rate": 0.000494959237610859,
      "loss": 1.9304,
      "step": 971
    },
    {
      "epoch": 0.094921875,
      "grad_norm": 0.1932704746723175,
      "learning_rate": 0.0004949442583514425,
      "loss": 1.9483,
      "step": 972
    },
    {
      "epoch": 0.09501953125,
      "grad_norm": 0.27378395199775696,
      "learning_rate": 0.0004949292571215429,
      "loss": 1.9687,
      "step": 973
    },
    {
      "epoch": 0.0951171875,
      "grad_norm": 0.3175489008426666,
      "learning_rate": 0.0004949142339226591,
      "loss": 2.0036,
      "step": 974
    },
    {
      "epoch": 0.09521484375,
      "grad_norm": 0.34563618898391724,
      "learning_rate": 0.0004948991887562914,
      "loss": 1.9429,
      "step": 975
    },
    {
      "epoch": 0.0953125,
      "grad_norm": 0.2931719720363617,
      "learning_rate": 0.000494884121623943,
      "loss": 1.9424,
      "step": 976
    },
    {
      "epoch": 0.09541015625,
      "grad_norm": 0.29774370789527893,
      "learning_rate": 0.0004948690325271188,
      "loss": 1.9297,
      "step": 977
    },
    {
      "epoch": 0.0955078125,
      "grad_norm": 0.31513288617134094,
      "learning_rate": 0.0004948539214673261,
      "loss": 1.9917,
      "step": 978
    },
    {
      "epoch": 0.09560546875,
      "grad_norm": 0.2150924950838089,
      "learning_rate": 0.0004948387884460744,
      "loss": 1.9529,
      "step": 979
    },
    {
      "epoch": 0.095703125,
      "grad_norm": 0.27547362446784973,
      "learning_rate": 0.0004948236334648753,
      "loss": 1.9885,
      "step": 980
    },
    {
      "epoch": 0.09580078125,
      "grad_norm": 0.3271898925304413,
      "learning_rate": 0.0004948084565252427,
      "loss": 1.9232,
      "step": 981
    },
    {
      "epoch": 0.0958984375,
      "grad_norm": 0.2923772931098938,
      "learning_rate": 0.0004947932576286928,
      "loss": 1.9429,
      "step": 982
    },
    {
      "epoch": 0.09599609375,
      "grad_norm": 0.2936458885669708,
      "learning_rate": 0.0004947780367767434,
      "loss": 1.9773,
      "step": 983
    },
    {
      "epoch": 0.09609375,
      "grad_norm": 0.29706791043281555,
      "learning_rate": 0.0004947627939709153,
      "loss": 1.9284,
      "step": 984
    },
    {
      "epoch": 0.09619140625,
      "grad_norm": 0.22721995413303375,
      "learning_rate": 0.000494747529212731,
      "loss": 1.9281,
      "step": 985
    },
    {
      "epoch": 0.0962890625,
      "grad_norm": 0.27041006088256836,
      "learning_rate": 0.0004947322425037152,
      "loss": 1.9735,
      "step": 986
    },
    {
      "epoch": 0.09638671875,
      "grad_norm": 0.26037418842315674,
      "learning_rate": 0.0004947169338453952,
      "loss": 1.9426,
      "step": 987
    },
    {
      "epoch": 0.096484375,
      "grad_norm": 0.23383264243602753,
      "learning_rate": 0.0004947016032392999,
      "loss": 1.923,
      "step": 988
    },
    {
      "epoch": 0.09658203125,
      "grad_norm": 0.29238423705101013,
      "learning_rate": 0.0004946862506869609,
      "loss": 1.9803,
      "step": 989
    },
    {
      "epoch": 0.0966796875,
      "grad_norm": 0.223761647939682,
      "learning_rate": 0.0004946708761899116,
      "loss": 1.9377,
      "step": 990
    },
    {
      "epoch": 0.09677734375,
      "grad_norm": 0.2669995427131653,
      "learning_rate": 0.0004946554797496881,
      "loss": 1.9694,
      "step": 991
    },
    {
      "epoch": 0.096875,
      "grad_norm": 0.2847992181777954,
      "learning_rate": 0.0004946400613678279,
      "loss": 1.9501,
      "step": 992
    },
    {
      "epoch": 0.09697265625,
      "grad_norm": 0.25099360942840576,
      "learning_rate": 0.0004946246210458715,
      "loss": 1.9707,
      "step": 993
    },
    {
      "epoch": 0.0970703125,
      "grad_norm": 0.23306165635585785,
      "learning_rate": 0.0004946091587853611,
      "loss": 1.9174,
      "step": 994
    },
    {
      "epoch": 0.09716796875,
      "grad_norm": 0.2907635569572449,
      "learning_rate": 0.0004945936745878414,
      "loss": 1.9521,
      "step": 995
    },
    {
      "epoch": 0.097265625,
      "grad_norm": 0.3234463334083557,
      "learning_rate": 0.0004945781684548591,
      "loss": 1.9667,
      "step": 996
    },
    {
      "epoch": 0.09736328125,
      "grad_norm": 0.36099013686180115,
      "learning_rate": 0.0004945626403879629,
      "loss": 1.9257,
      "step": 997
    },
    {
      "epoch": 0.0974609375,
      "grad_norm": 0.3735397160053253,
      "learning_rate": 0.0004945470903887041,
      "loss": 1.9512,
      "step": 998
    },
    {
      "epoch": 0.09755859375,
      "grad_norm": 0.3653644025325775,
      "learning_rate": 0.0004945315184586359,
      "loss": 1.9664,
      "step": 999
    },
    {
      "epoch": 0.09765625,
      "grad_norm": 0.2931279242038727,
      "learning_rate": 0.000494515924599314,
      "loss": 1.9209,
      "step": 1000
    },
    {
      "epoch": 0.09775390625,
      "grad_norm": 0.31677475571632385,
      "learning_rate": 0.000494500308812296,
      "loss": 1.9989,
      "step": 1001
    },
    {
      "epoch": 0.0978515625,
      "grad_norm": 0.2640211582183838,
      "learning_rate": 0.0004944846710991416,
      "loss": 1.8792,
      "step": 1002
    },
    {
      "epoch": 0.09794921875,
      "grad_norm": 0.3207566738128662,
      "learning_rate": 0.0004944690114614132,
      "loss": 1.955,
      "step": 1003
    },
    {
      "epoch": 0.098046875,
      "grad_norm": 0.29306915402412415,
      "learning_rate": 0.0004944533299006749,
      "loss": 1.9264,
      "step": 1004
    },
    {
      "epoch": 0.09814453125,
      "grad_norm": 0.2783614993095398,
      "learning_rate": 0.000494437626418493,
      "loss": 1.9341,
      "step": 1005
    },
    {
      "epoch": 0.0982421875,
      "grad_norm": 0.346975713968277,
      "learning_rate": 0.0004944219010164361,
      "loss": 1.9599,
      "step": 1006
    },
    {
      "epoch": 0.09833984375,
      "grad_norm": 0.2799683213233948,
      "learning_rate": 0.0004944061536960755,
      "loss": 1.9201,
      "step": 1007
    },
    {
      "epoch": 0.0984375,
      "grad_norm": 0.27122223377227783,
      "learning_rate": 0.0004943903844589837,
      "loss": 1.9685,
      "step": 1008
    },
    {
      "epoch": 0.09853515625,
      "grad_norm": 0.34742453694343567,
      "learning_rate": 0.0004943745933067362,
      "loss": 1.9533,
      "step": 1009
    },
    {
      "epoch": 0.0986328125,
      "grad_norm": 0.2686299681663513,
      "learning_rate": 0.0004943587802409103,
      "loss": 1.9149,
      "step": 1010
    },
    {
      "epoch": 0.09873046875,
      "grad_norm": 0.3223266303539276,
      "learning_rate": 0.0004943429452630856,
      "loss": 1.8887,
      "step": 1011
    },
    {
      "epoch": 0.098828125,
      "grad_norm": 0.2767395079135895,
      "learning_rate": 0.0004943270883748439,
      "loss": 1.9756,
      "step": 1012
    },
    {
      "epoch": 0.09892578125,
      "grad_norm": 0.2761443257331848,
      "learning_rate": 0.0004943112095777691,
      "loss": 1.981,
      "step": 1013
    },
    {
      "epoch": 0.0990234375,
      "grad_norm": 0.22587864100933075,
      "learning_rate": 0.0004942953088734474,
      "loss": 1.939,
      "step": 1014
    },
    {
      "epoch": 0.09912109375,
      "grad_norm": 0.2596238851547241,
      "learning_rate": 0.0004942793862634671,
      "loss": 1.9546,
      "step": 1015
    },
    {
      "epoch": 0.09921875,
      "grad_norm": 0.3035464584827423,
      "learning_rate": 0.0004942634417494188,
      "loss": 2.0001,
      "step": 1016
    },
    {
      "epoch": 0.09931640625,
      "grad_norm": 0.32868078351020813,
      "learning_rate": 0.0004942474753328952,
      "loss": 1.9248,
      "step": 1017
    },
    {
      "epoch": 0.0994140625,
      "grad_norm": 0.34833693504333496,
      "learning_rate": 0.000494231487015491,
      "loss": 1.9148,
      "step": 1018
    },
    {
      "epoch": 0.09951171875,
      "grad_norm": 0.2557753920555115,
      "learning_rate": 0.0004942154767988037,
      "loss": 1.9585,
      "step": 1019
    },
    {
      "epoch": 0.099609375,
      "grad_norm": 0.25750526785850525,
      "learning_rate": 0.0004941994446844321,
      "loss": 2.0257,
      "step": 1020
    },
    {
      "epoch": 0.09970703125,
      "grad_norm": 0.22088824212551117,
      "learning_rate": 0.000494183390673978,
      "loss": 1.9373,
      "step": 1021
    },
    {
      "epoch": 0.0998046875,
      "grad_norm": 0.23292425274848938,
      "learning_rate": 0.000494167314769045,
      "loss": 1.9462,
      "step": 1022
    },
    {
      "epoch": 0.09990234375,
      "grad_norm": 0.24202801287174225,
      "learning_rate": 0.0004941512169712389,
      "loss": 2.0237,
      "step": 1023
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.28507405519485474,
      "learning_rate": 0.0004941350972821678,
      "loss": 1.9373,
      "step": 1024
    },
    {
      "epoch": 0.10009765625,
      "grad_norm": 0.22370004653930664,
      "learning_rate": 0.0004941189557034417,
      "loss": 1.9332,
      "step": 1025
    },
    {
      "epoch": 0.1001953125,
      "grad_norm": 0.2707929313182831,
      "learning_rate": 0.0004941027922366732,
      "loss": 1.9908,
      "step": 1026
    },
    {
      "epoch": 0.10029296875,
      "grad_norm": 0.29618075489997864,
      "learning_rate": 0.0004940866068834769,
      "loss": 1.9317,
      "step": 1027
    },
    {
      "epoch": 0.100390625,
      "grad_norm": 0.27780136466026306,
      "learning_rate": 0.0004940703996454695,
      "loss": 1.9225,
      "step": 1028
    },
    {
      "epoch": 0.10048828125,
      "grad_norm": 0.33955708146095276,
      "learning_rate": 0.0004940541705242698,
      "loss": 1.9232,
      "step": 1029
    },
    {
      "epoch": 0.1005859375,
      "grad_norm": 0.3132137954235077,
      "learning_rate": 0.0004940379195214992,
      "loss": 1.976,
      "step": 1030
    },
    {
      "epoch": 0.10068359375,
      "grad_norm": 0.2742595076560974,
      "learning_rate": 0.000494021646638781,
      "loss": 1.9138,
      "step": 1031
    },
    {
      "epoch": 0.10078125,
      "grad_norm": 0.2921305298805237,
      "learning_rate": 0.0004940053518777406,
      "loss": 1.9178,
      "step": 1032
    },
    {
      "epoch": 0.10087890625,
      "grad_norm": 0.2586468458175659,
      "learning_rate": 0.0004939890352400058,
      "loss": 1.9385,
      "step": 1033
    },
    {
      "epoch": 0.1009765625,
      "grad_norm": 0.30906325578689575,
      "learning_rate": 0.0004939726967272064,
      "loss": 1.9368,
      "step": 1034
    },
    {
      "epoch": 0.10107421875,
      "grad_norm": 0.3483060300350189,
      "learning_rate": 0.0004939563363409745,
      "loss": 1.9922,
      "step": 1035
    },
    {
      "epoch": 0.101171875,
      "grad_norm": 0.3559792637825012,
      "learning_rate": 0.0004939399540829445,
      "loss": 1.9564,
      "step": 1036
    },
    {
      "epoch": 0.10126953125,
      "grad_norm": 0.33506283164024353,
      "learning_rate": 0.0004939235499547526,
      "loss": 1.9784,
      "step": 1037
    },
    {
      "epoch": 0.1013671875,
      "grad_norm": 0.23956939578056335,
      "learning_rate": 0.0004939071239580377,
      "loss": 1.9755,
      "step": 1038
    },
    {
      "epoch": 0.10146484375,
      "grad_norm": 0.33348920941352844,
      "learning_rate": 0.0004938906760944403,
      "loss": 1.9128,
      "step": 1039
    },
    {
      "epoch": 0.1015625,
      "grad_norm": 0.2843862771987915,
      "learning_rate": 0.0004938742063656036,
      "loss": 1.9297,
      "step": 1040
    },
    {
      "epoch": 0.10166015625,
      "grad_norm": 0.2671546936035156,
      "learning_rate": 0.0004938577147731727,
      "loss": 1.9391,
      "step": 1041
    },
    {
      "epoch": 0.1017578125,
      "grad_norm": 0.2899993360042572,
      "learning_rate": 0.000493841201318795,
      "loss": 1.9198,
      "step": 1042
    },
    {
      "epoch": 0.10185546875,
      "grad_norm": 0.20722518861293793,
      "learning_rate": 0.0004938246660041201,
      "loss": 1.9295,
      "step": 1043
    },
    {
      "epoch": 0.101953125,
      "grad_norm": 0.22667360305786133,
      "learning_rate": 0.0004938081088307997,
      "loss": 1.9371,
      "step": 1044
    },
    {
      "epoch": 0.10205078125,
      "grad_norm": 0.275579035282135,
      "learning_rate": 0.0004937915298004877,
      "loss": 1.9383,
      "step": 1045
    },
    {
      "epoch": 0.1021484375,
      "grad_norm": 0.2900732159614563,
      "learning_rate": 0.0004937749289148401,
      "loss": 1.9805,
      "step": 1046
    },
    {
      "epoch": 0.10224609375,
      "grad_norm": 0.26479572057724,
      "learning_rate": 0.0004937583061755153,
      "loss": 1.911,
      "step": 1047
    },
    {
      "epoch": 0.10234375,
      "grad_norm": 0.2967575490474701,
      "learning_rate": 0.0004937416615841739,
      "loss": 1.9654,
      "step": 1048
    },
    {
      "epoch": 0.10244140625,
      "grad_norm": 0.2840502858161926,
      "learning_rate": 0.0004937249951424782,
      "loss": 1.9332,
      "step": 1049
    },
    {
      "epoch": 0.1025390625,
      "grad_norm": 0.2664666175842285,
      "learning_rate": 0.0004937083068520931,
      "loss": 1.973,
      "step": 1050
    },
    {
      "epoch": 0.10263671875,
      "grad_norm": 0.2535867989063263,
      "learning_rate": 0.000493691596714686,
      "loss": 1.9421,
      "step": 1051
    },
    {
      "epoch": 0.102734375,
      "grad_norm": 0.3005189895629883,
      "learning_rate": 0.0004936748647319256,
      "loss": 1.9434,
      "step": 1052
    },
    {
      "epoch": 0.10283203125,
      "grad_norm": 0.2663765549659729,
      "learning_rate": 0.0004936581109054837,
      "loss": 1.9947,
      "step": 1053
    },
    {
      "epoch": 0.1029296875,
      "grad_norm": 0.29048940539360046,
      "learning_rate": 0.0004936413352370335,
      "loss": 1.9737,
      "step": 1054
    },
    {
      "epoch": 0.10302734375,
      "grad_norm": 0.2594558596611023,
      "learning_rate": 0.000493624537728251,
      "loss": 1.9601,
      "step": 1055
    },
    {
      "epoch": 0.103125,
      "grad_norm": 0.27011555433273315,
      "learning_rate": 0.000493607718380814,
      "loss": 1.9459,
      "step": 1056
    },
    {
      "epoch": 0.10322265625,
      "grad_norm": 0.3043757677078247,
      "learning_rate": 0.0004935908771964026,
      "loss": 1.9494,
      "step": 1057
    },
    {
      "epoch": 0.1033203125,
      "grad_norm": 0.26345208287239075,
      "learning_rate": 0.0004935740141766991,
      "loss": 1.896,
      "step": 1058
    },
    {
      "epoch": 0.10341796875,
      "grad_norm": 0.20400577783584595,
      "learning_rate": 0.000493557129323388,
      "loss": 1.9276,
      "step": 1059
    },
    {
      "epoch": 0.103515625,
      "grad_norm": 0.2836177349090576,
      "learning_rate": 0.0004935402226381558,
      "loss": 1.921,
      "step": 1060
    },
    {
      "epoch": 0.10361328125,
      "grad_norm": 0.2904714047908783,
      "learning_rate": 0.0004935232941226916,
      "loss": 1.9631,
      "step": 1061
    },
    {
      "epoch": 0.1037109375,
      "grad_norm": 0.25980454683303833,
      "learning_rate": 0.0004935063437786863,
      "loss": 1.9757,
      "step": 1062
    },
    {
      "epoch": 0.10380859375,
      "grad_norm": 0.27394455671310425,
      "learning_rate": 0.0004934893716078329,
      "loss": 1.9647,
      "step": 1063
    },
    {
      "epoch": 0.10390625,
      "grad_norm": 0.23419839143753052,
      "learning_rate": 0.000493472377611827,
      "loss": 1.962,
      "step": 1064
    },
    {
      "epoch": 0.10400390625,
      "grad_norm": 0.2323913723230362,
      "learning_rate": 0.0004934553617923661,
      "loss": 1.9759,
      "step": 1065
    },
    {
      "epoch": 0.1041015625,
      "grad_norm": 0.2700064778327942,
      "learning_rate": 0.0004934383241511498,
      "loss": 1.9206,
      "step": 1066
    },
    {
      "epoch": 0.10419921875,
      "grad_norm": 0.3530958294868469,
      "learning_rate": 0.0004934212646898802,
      "loss": 1.979,
      "step": 1067
    },
    {
      "epoch": 0.104296875,
      "grad_norm": 0.30405712127685547,
      "learning_rate": 0.0004934041834102612,
      "loss": 1.951,
      "step": 1068
    },
    {
      "epoch": 0.10439453125,
      "grad_norm": 0.2923583984375,
      "learning_rate": 0.0004933870803139992,
      "loss": 2.0158,
      "step": 1069
    },
    {
      "epoch": 0.1044921875,
      "grad_norm": 0.23782993853092194,
      "learning_rate": 0.0004933699554028027,
      "loss": 1.896,
      "step": 1070
    },
    {
      "epoch": 0.10458984375,
      "grad_norm": 0.3045034110546112,
      "learning_rate": 0.0004933528086783821,
      "loss": 1.9555,
      "step": 1071
    },
    {
      "epoch": 0.1046875,
      "grad_norm": 0.40851131081581116,
      "learning_rate": 0.0004933356401424505,
      "loss": 1.9108,
      "step": 1072
    },
    {
      "epoch": 0.10478515625,
      "grad_norm": 0.39787429571151733,
      "learning_rate": 0.0004933184497967226,
      "loss": 1.9472,
      "step": 1073
    },
    {
      "epoch": 0.1048828125,
      "grad_norm": 0.24665354192256927,
      "learning_rate": 0.0004933012376429158,
      "loss": 1.9617,
      "step": 1074
    },
    {
      "epoch": 0.10498046875,
      "grad_norm": 0.28025394678115845,
      "learning_rate": 0.0004932840036827492,
      "loss": 1.898,
      "step": 1075
    },
    {
      "epoch": 0.105078125,
      "grad_norm": 0.3374732434749603,
      "learning_rate": 0.0004932667479179445,
      "loss": 1.9323,
      "step": 1076
    },
    {
      "epoch": 0.10517578125,
      "grad_norm": 0.2941461503505707,
      "learning_rate": 0.0004932494703502254,
      "loss": 1.964,
      "step": 1077
    },
    {
      "epoch": 0.1052734375,
      "grad_norm": 0.2827446758747101,
      "learning_rate": 0.0004932321709813177,
      "loss": 1.9554,
      "step": 1078
    },
    {
      "epoch": 0.10537109375,
      "grad_norm": 0.32132452726364136,
      "learning_rate": 0.0004932148498129495,
      "loss": 1.9333,
      "step": 1079
    },
    {
      "epoch": 0.10546875,
      "grad_norm": 0.2732277810573578,
      "learning_rate": 0.000493197506846851,
      "loss": 1.932,
      "step": 1080
    },
    {
      "epoch": 0.10556640625,
      "grad_norm": 0.2594139575958252,
      "learning_rate": 0.0004931801420847545,
      "loss": 1.9447,
      "step": 1081
    },
    {
      "epoch": 0.1056640625,
      "grad_norm": 0.24399201571941376,
      "learning_rate": 0.0004931627555283948,
      "loss": 1.9163,
      "step": 1082
    },
    {
      "epoch": 0.10576171875,
      "grad_norm": 0.22696708142757416,
      "learning_rate": 0.0004931453471795087,
      "loss": 1.9734,
      "step": 1083
    },
    {
      "epoch": 0.105859375,
      "grad_norm": 0.25717827677726746,
      "learning_rate": 0.0004931279170398349,
      "loss": 1.9767,
      "step": 1084
    },
    {
      "epoch": 0.10595703125,
      "grad_norm": 0.23899690806865692,
      "learning_rate": 0.0004931104651111146,
      "loss": 1.9519,
      "step": 1085
    },
    {
      "epoch": 0.1060546875,
      "grad_norm": 0.27689501643180847,
      "learning_rate": 0.0004930929913950911,
      "loss": 1.9582,
      "step": 1086
    },
    {
      "epoch": 0.10615234375,
      "grad_norm": 0.23959669470787048,
      "learning_rate": 0.00049307549589351,
      "loss": 1.9369,
      "step": 1087
    },
    {
      "epoch": 0.10625,
      "grad_norm": 0.25673651695251465,
      "learning_rate": 0.0004930579786081188,
      "loss": 1.9711,
      "step": 1088
    },
    {
      "epoch": 0.10634765625,
      "grad_norm": 0.30868396162986755,
      "learning_rate": 0.0004930404395406674,
      "loss": 1.9539,
      "step": 1089
    },
    {
      "epoch": 0.1064453125,
      "grad_norm": 0.2462042272090912,
      "learning_rate": 0.0004930228786929076,
      "loss": 1.9061,
      "step": 1090
    },
    {
      "epoch": 0.10654296875,
      "grad_norm": 0.24275164306163788,
      "learning_rate": 0.0004930052960665938,
      "loss": 1.8992,
      "step": 1091
    },
    {
      "epoch": 0.106640625,
      "grad_norm": 0.27242550253868103,
      "learning_rate": 0.0004929876916634823,
      "loss": 1.8997,
      "step": 1092
    },
    {
      "epoch": 0.10673828125,
      "grad_norm": 0.2655372619628906,
      "learning_rate": 0.0004929700654853316,
      "loss": 1.8905,
      "step": 1093
    },
    {
      "epoch": 0.1068359375,
      "grad_norm": 0.27779421210289,
      "learning_rate": 0.0004929524175339024,
      "loss": 1.9485,
      "step": 1094
    },
    {
      "epoch": 0.10693359375,
      "grad_norm": 0.3308311402797699,
      "learning_rate": 0.0004929347478109576,
      "loss": 1.896,
      "step": 1095
    },
    {
      "epoch": 0.10703125,
      "grad_norm": 0.2988120913505554,
      "learning_rate": 0.0004929170563182621,
      "loss": 1.9508,
      "step": 1096
    },
    {
      "epoch": 0.10712890625,
      "grad_norm": 0.24604608118534088,
      "learning_rate": 0.0004928993430575834,
      "loss": 1.9912,
      "step": 1097
    },
    {
      "epoch": 0.1072265625,
      "grad_norm": 0.31434887647628784,
      "learning_rate": 0.0004928816080306906,
      "loss": 1.9592,
      "step": 1098
    },
    {
      "epoch": 0.10732421875,
      "grad_norm": 0.21227046847343445,
      "learning_rate": 0.0004928638512393555,
      "loss": 1.9523,
      "step": 1099
    },
    {
      "epoch": 0.107421875,
      "grad_norm": 0.26643091440200806,
      "learning_rate": 0.0004928460726853518,
      "loss": 1.9506,
      "step": 1100
    },
    {
      "epoch": 0.10751953125,
      "grad_norm": 0.2661186754703522,
      "learning_rate": 0.0004928282723704554,
      "loss": 1.9425,
      "step": 1101
    },
    {
      "epoch": 0.1076171875,
      "grad_norm": 0.25391289591789246,
      "learning_rate": 0.0004928104502964442,
      "loss": 1.9551,
      "step": 1102
    },
    {
      "epoch": 0.10771484375,
      "grad_norm": 0.276909202337265,
      "learning_rate": 0.0004927926064650988,
      "loss": 1.9416,
      "step": 1103
    },
    {
      "epoch": 0.1078125,
      "grad_norm": 0.25135815143585205,
      "learning_rate": 0.0004927747408782014,
      "loss": 1.9197,
      "step": 1104
    },
    {
      "epoch": 0.10791015625,
      "grad_norm": 0.2529551684856415,
      "learning_rate": 0.0004927568535375368,
      "loss": 1.9561,
      "step": 1105
    },
    {
      "epoch": 0.1080078125,
      "grad_norm": 0.2697699964046478,
      "learning_rate": 0.0004927389444448915,
      "loss": 1.9369,
      "step": 1106
    },
    {
      "epoch": 0.10810546875,
      "grad_norm": 0.2805427014827728,
      "learning_rate": 0.0004927210136020548,
      "loss": 1.9535,
      "step": 1107
    },
    {
      "epoch": 0.108203125,
      "grad_norm": 0.33747565746307373,
      "learning_rate": 0.0004927030610108176,
      "loss": 1.9582,
      "step": 1108
    },
    {
      "epoch": 0.10830078125,
      "grad_norm": 0.30215132236480713,
      "learning_rate": 0.0004926850866729734,
      "loss": 1.9245,
      "step": 1109
    },
    {
      "epoch": 0.1083984375,
      "grad_norm": 0.3483729064464569,
      "learning_rate": 0.0004926670905903174,
      "loss": 1.9959,
      "step": 1110
    },
    {
      "epoch": 0.10849609375,
      "grad_norm": 0.23263247311115265,
      "learning_rate": 0.0004926490727646476,
      "loss": 1.9224,
      "step": 1111
    },
    {
      "epoch": 0.10859375,
      "grad_norm": 0.3023853898048401,
      "learning_rate": 0.0004926310331977633,
      "loss": 1.9493,
      "step": 1112
    },
    {
      "epoch": 0.10869140625,
      "grad_norm": 0.3592170774936676,
      "learning_rate": 0.0004926129718914672,
      "loss": 1.9082,
      "step": 1113
    },
    {
      "epoch": 0.1087890625,
      "grad_norm": 0.29466864466667175,
      "learning_rate": 0.0004925948888475628,
      "loss": 2.016,
      "step": 1114
    },
    {
      "epoch": 0.10888671875,
      "grad_norm": 0.3136419355869293,
      "learning_rate": 0.0004925767840678569,
      "loss": 1.9592,
      "step": 1115
    },
    {
      "epoch": 0.108984375,
      "grad_norm": 0.21686695516109467,
      "learning_rate": 0.0004925586575541578,
      "loss": 1.9081,
      "step": 1116
    },
    {
      "epoch": 0.10908203125,
      "grad_norm": 0.2520851790904999,
      "learning_rate": 0.0004925405093082761,
      "loss": 1.9418,
      "step": 1117
    },
    {
      "epoch": 0.1091796875,
      "grad_norm": 0.28278669714927673,
      "learning_rate": 0.0004925223393320247,
      "loss": 1.9815,
      "step": 1118
    },
    {
      "epoch": 0.10927734375,
      "grad_norm": 0.2773968577384949,
      "learning_rate": 0.0004925041476272189,
      "loss": 1.8888,
      "step": 1119
    },
    {
      "epoch": 0.109375,
      "grad_norm": 0.24399970471858978,
      "learning_rate": 0.0004924859341956755,
      "loss": 1.9548,
      "step": 1120
    },
    {
      "epoch": 0.10947265625,
      "grad_norm": 0.26073598861694336,
      "learning_rate": 0.0004924676990392141,
      "loss": 1.9112,
      "step": 1121
    },
    {
      "epoch": 0.1095703125,
      "grad_norm": 0.24541547894477844,
      "learning_rate": 0.0004924494421596562,
      "loss": 1.914,
      "step": 1122
    },
    {
      "epoch": 0.10966796875,
      "grad_norm": 0.21719145774841309,
      "learning_rate": 0.0004924311635588254,
      "loss": 1.9204,
      "step": 1123
    },
    {
      "epoch": 0.109765625,
      "grad_norm": 0.295460045337677,
      "learning_rate": 0.0004924128632385476,
      "loss": 1.9545,
      "step": 1124
    },
    {
      "epoch": 0.10986328125,
      "grad_norm": 0.3058072626590729,
      "learning_rate": 0.0004923945412006509,
      "loss": 1.9048,
      "step": 1125
    },
    {
      "epoch": 0.1099609375,
      "grad_norm": 0.19512003660202026,
      "learning_rate": 0.0004923761974469655,
      "loss": 1.9581,
      "step": 1126
    },
    {
      "epoch": 0.11005859375,
      "grad_norm": 0.21684713661670685,
      "learning_rate": 0.0004923578319793237,
      "loss": 1.8765,
      "step": 1127
    },
    {
      "epoch": 0.11015625,
      "grad_norm": 0.2229132503271103,
      "learning_rate": 0.0004923394447995601,
      "loss": 1.8599,
      "step": 1128
    },
    {
      "epoch": 0.11025390625,
      "grad_norm": 0.20479273796081543,
      "learning_rate": 0.0004923210359095115,
      "loss": 1.938,
      "step": 1129
    },
    {
      "epoch": 0.1103515625,
      "grad_norm": 0.2477833479642868,
      "learning_rate": 0.0004923026053110167,
      "loss": 1.9655,
      "step": 1130
    },
    {
      "epoch": 0.11044921875,
      "grad_norm": 0.23927846550941467,
      "learning_rate": 0.0004922841530059167,
      "loss": 1.9461,
      "step": 1131
    },
    {
      "epoch": 0.110546875,
      "grad_norm": 0.24189342558383942,
      "learning_rate": 0.0004922656789960547,
      "loss": 1.9338,
      "step": 1132
    },
    {
      "epoch": 0.11064453125,
      "grad_norm": 0.20208942890167236,
      "learning_rate": 0.0004922471832832763,
      "loss": 1.973,
      "step": 1133
    },
    {
      "epoch": 0.1107421875,
      "grad_norm": 0.20967181026935577,
      "learning_rate": 0.0004922286658694289,
      "loss": 1.9391,
      "step": 1134
    },
    {
      "epoch": 0.11083984375,
      "grad_norm": 0.2538667917251587,
      "learning_rate": 0.0004922101267563622,
      "loss": 1.9159,
      "step": 1135
    },
    {
      "epoch": 0.1109375,
      "grad_norm": 0.2945930063724518,
      "learning_rate": 0.0004921915659459281,
      "loss": 1.915,
      "step": 1136
    },
    {
      "epoch": 0.11103515625,
      "grad_norm": 0.3631344437599182,
      "learning_rate": 0.0004921729834399808,
      "loss": 1.9926,
      "step": 1137
    },
    {
      "epoch": 0.1111328125,
      "grad_norm": 0.32187792658805847,
      "learning_rate": 0.0004921543792403765,
      "loss": 1.9137,
      "step": 1138
    },
    {
      "epoch": 0.11123046875,
      "grad_norm": 0.276929646730423,
      "learning_rate": 0.0004921357533489734,
      "loss": 1.9427,
      "step": 1139
    },
    {
      "epoch": 0.111328125,
      "grad_norm": 0.20455695688724518,
      "learning_rate": 0.0004921171057676323,
      "loss": 1.9118,
      "step": 1140
    },
    {
      "epoch": 0.11142578125,
      "grad_norm": 0.2824450731277466,
      "learning_rate": 0.0004920984364982157,
      "loss": 1.9471,
      "step": 1141
    },
    {
      "epoch": 0.1115234375,
      "grad_norm": 0.2931687831878662,
      "learning_rate": 0.0004920797455425887,
      "loss": 1.9546,
      "step": 1142
    },
    {
      "epoch": 0.11162109375,
      "grad_norm": 0.31234028935432434,
      "learning_rate": 0.0004920610329026181,
      "loss": 1.9466,
      "step": 1143
    },
    {
      "epoch": 0.11171875,
      "grad_norm": 0.39190223813056946,
      "learning_rate": 0.0004920422985801735,
      "loss": 1.9394,
      "step": 1144
    },
    {
      "epoch": 0.11181640625,
      "grad_norm": 0.26808232069015503,
      "learning_rate": 0.0004920235425771261,
      "loss": 1.9278,
      "step": 1145
    },
    {
      "epoch": 0.1119140625,
      "grad_norm": 0.22590310871601105,
      "learning_rate": 0.0004920047648953493,
      "loss": 1.9467,
      "step": 1146
    },
    {
      "epoch": 0.11201171875,
      "grad_norm": 0.2531168758869171,
      "learning_rate": 0.0004919859655367192,
      "loss": 1.958,
      "step": 1147
    },
    {
      "epoch": 0.112109375,
      "grad_norm": 0.207502081990242,
      "learning_rate": 0.0004919671445031132,
      "loss": 2.0148,
      "step": 1148
    },
    {
      "epoch": 0.11220703125,
      "grad_norm": 0.23596623539924622,
      "learning_rate": 0.0004919483017964118,
      "loss": 1.9617,
      "step": 1149
    },
    {
      "epoch": 0.1123046875,
      "grad_norm": 0.25810694694519043,
      "learning_rate": 0.000491929437418497,
      "loss": 2.0262,
      "step": 1150
    },
    {
      "epoch": 0.11240234375,
      "grad_norm": 0.27257680892944336,
      "learning_rate": 0.0004919105513712533,
      "loss": 1.9285,
      "step": 1151
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.2861190736293793,
      "learning_rate": 0.000491891643656567,
      "loss": 1.965,
      "step": 1152
    },
    {
      "epoch": 0.11259765625,
      "grad_norm": 0.2790696620941162,
      "learning_rate": 0.0004918727142763271,
      "loss": 1.9572,
      "step": 1153
    },
    {
      "epoch": 0.1126953125,
      "grad_norm": 0.35226336121559143,
      "learning_rate": 0.0004918537632324243,
      "loss": 1.9338,
      "step": 1154
    },
    {
      "epoch": 0.11279296875,
      "grad_norm": 0.2735171616077423,
      "learning_rate": 0.0004918347905267517,
      "loss": 1.9304,
      "step": 1155
    },
    {
      "epoch": 0.112890625,
      "grad_norm": 0.2629276514053345,
      "learning_rate": 0.0004918157961612046,
      "loss": 1.9383,
      "step": 1156
    },
    {
      "epoch": 0.11298828125,
      "grad_norm": 0.3583827614784241,
      "learning_rate": 0.0004917967801376802,
      "loss": 1.9448,
      "step": 1157
    },
    {
      "epoch": 0.1130859375,
      "grad_norm": 0.2546387016773224,
      "learning_rate": 0.0004917777424580781,
      "loss": 1.9506,
      "step": 1158
    },
    {
      "epoch": 0.11318359375,
      "grad_norm": 0.35346466302871704,
      "learning_rate": 0.0004917586831243001,
      "loss": 1.9207,
      "step": 1159
    },
    {
      "epoch": 0.11328125,
      "grad_norm": 0.2943922281265259,
      "learning_rate": 0.0004917396021382499,
      "loss": 1.961,
      "step": 1160
    },
    {
      "epoch": 0.11337890625,
      "grad_norm": 0.24972833693027496,
      "learning_rate": 0.0004917204995018336,
      "loss": 1.9271,
      "step": 1161
    },
    {
      "epoch": 0.1134765625,
      "grad_norm": 0.31200850009918213,
      "learning_rate": 0.0004917013752169594,
      "loss": 1.9444,
      "step": 1162
    },
    {
      "epoch": 0.11357421875,
      "grad_norm": 0.3580279052257538,
      "learning_rate": 0.0004916822292855375,
      "loss": 1.9132,
      "step": 1163
    },
    {
      "epoch": 0.113671875,
      "grad_norm": 0.31269049644470215,
      "learning_rate": 0.0004916630617094807,
      "loss": 1.9283,
      "step": 1164
    },
    {
      "epoch": 0.11376953125,
      "grad_norm": 0.25159773230552673,
      "learning_rate": 0.0004916438724907033,
      "loss": 1.9018,
      "step": 1165
    },
    {
      "epoch": 0.1138671875,
      "grad_norm": 0.22316916286945343,
      "learning_rate": 0.0004916246616311225,
      "loss": 1.8821,
      "step": 1166
    },
    {
      "epoch": 0.11396484375,
      "grad_norm": 0.31150946021080017,
      "learning_rate": 0.0004916054291326571,
      "loss": 1.9565,
      "step": 1167
    },
    {
      "epoch": 0.1140625,
      "grad_norm": 0.29112792015075684,
      "learning_rate": 0.0004915861749972281,
      "loss": 1.9582,
      "step": 1168
    },
    {
      "epoch": 0.11416015625,
      "grad_norm": 0.26860764622688293,
      "learning_rate": 0.0004915668992267593,
      "loss": 1.9299,
      "step": 1169
    },
    {
      "epoch": 0.1142578125,
      "grad_norm": 0.24470628798007965,
      "learning_rate": 0.0004915476018231757,
      "loss": 1.9131,
      "step": 1170
    },
    {
      "epoch": 0.11435546875,
      "grad_norm": 0.26279789209365845,
      "learning_rate": 0.0004915282827884051,
      "loss": 1.9055,
      "step": 1171
    },
    {
      "epoch": 0.114453125,
      "grad_norm": 0.21272587776184082,
      "learning_rate": 0.0004915089421243773,
      "loss": 1.9694,
      "step": 1172
    },
    {
      "epoch": 0.11455078125,
      "grad_norm": 0.21711157262325287,
      "learning_rate": 0.0004914895798330244,
      "loss": 1.9644,
      "step": 1173
    },
    {
      "epoch": 0.1146484375,
      "grad_norm": 0.21599583327770233,
      "learning_rate": 0.0004914701959162803,
      "loss": 1.9528,
      "step": 1174
    },
    {
      "epoch": 0.11474609375,
      "grad_norm": 0.22919407486915588,
      "learning_rate": 0.0004914507903760814,
      "loss": 1.9353,
      "step": 1175
    },
    {
      "epoch": 0.11484375,
      "grad_norm": 0.22974969446659088,
      "learning_rate": 0.0004914313632143661,
      "loss": 1.9148,
      "step": 1176
    },
    {
      "epoch": 0.11494140625,
      "grad_norm": 0.2370641529560089,
      "learning_rate": 0.000491411914433075,
      "loss": 1.9056,
      "step": 1177
    },
    {
      "epoch": 0.1150390625,
      "grad_norm": 0.27402329444885254,
      "learning_rate": 0.000491392444034151,
      "loss": 1.9483,
      "step": 1178
    },
    {
      "epoch": 0.11513671875,
      "grad_norm": 0.2953847050666809,
      "learning_rate": 0.0004913729520195388,
      "loss": 1.9553,
      "step": 1179
    },
    {
      "epoch": 0.115234375,
      "grad_norm": 0.26085543632507324,
      "learning_rate": 0.0004913534383911857,
      "loss": 1.9307,
      "step": 1180
    },
    {
      "epoch": 0.11533203125,
      "grad_norm": 0.2782340943813324,
      "learning_rate": 0.0004913339031510408,
      "loss": 1.9733,
      "step": 1181
    },
    {
      "epoch": 0.1154296875,
      "grad_norm": 0.2568228244781494,
      "learning_rate": 0.0004913143463010554,
      "loss": 1.9402,
      "step": 1182
    },
    {
      "epoch": 0.11552734375,
      "grad_norm": 0.2584892809391022,
      "learning_rate": 0.0004912947678431833,
      "loss": 1.9254,
      "step": 1183
    },
    {
      "epoch": 0.115625,
      "grad_norm": 0.2621140778064728,
      "learning_rate": 0.00049127516777938,
      "loss": 1.9323,
      "step": 1184
    },
    {
      "epoch": 0.11572265625,
      "grad_norm": 0.28239843249320984,
      "learning_rate": 0.0004912555461116035,
      "loss": 1.9447,
      "step": 1185
    },
    {
      "epoch": 0.1158203125,
      "grad_norm": 0.3147210478782654,
      "learning_rate": 0.0004912359028418138,
      "loss": 1.8867,
      "step": 1186
    },
    {
      "epoch": 0.11591796875,
      "grad_norm": 0.25541990995407104,
      "learning_rate": 0.0004912162379719731,
      "loss": 1.871,
      "step": 1187
    },
    {
      "epoch": 0.116015625,
      "grad_norm": 0.24328139424324036,
      "learning_rate": 0.0004911965515040457,
      "loss": 1.9316,
      "step": 1188
    },
    {
      "epoch": 0.11611328125,
      "grad_norm": 0.20230042934417725,
      "learning_rate": 0.0004911768434399981,
      "loss": 1.9298,
      "step": 1189
    },
    {
      "epoch": 0.1162109375,
      "grad_norm": 0.32389941811561584,
      "learning_rate": 0.0004911571137817991,
      "loss": 1.8941,
      "step": 1190
    },
    {
      "epoch": 0.11630859375,
      "grad_norm": 0.3173327147960663,
      "learning_rate": 0.0004911373625314194,
      "loss": 1.9222,
      "step": 1191
    },
    {
      "epoch": 0.11640625,
      "grad_norm": 0.32637453079223633,
      "learning_rate": 0.0004911175896908319,
      "loss": 1.9273,
      "step": 1192
    },
    {
      "epoch": 0.11650390625,
      "grad_norm": 0.307746022939682,
      "learning_rate": 0.0004910977952620119,
      "loss": 1.9352,
      "step": 1193
    },
    {
      "epoch": 0.1166015625,
      "grad_norm": 0.21165402233600616,
      "learning_rate": 0.0004910779792469365,
      "loss": 1.8867,
      "step": 1194
    },
    {
      "epoch": 0.11669921875,
      "grad_norm": 0.3059009909629822,
      "learning_rate": 0.0004910581416475854,
      "loss": 1.9187,
      "step": 1195
    },
    {
      "epoch": 0.116796875,
      "grad_norm": 0.2690452039241791,
      "learning_rate": 0.00049103828246594,
      "loss": 1.9723,
      "step": 1196
    },
    {
      "epoch": 0.11689453125,
      "grad_norm": 0.25487321615219116,
      "learning_rate": 0.0004910184017039841,
      "loss": 1.9525,
      "step": 1197
    },
    {
      "epoch": 0.1169921875,
      "grad_norm": 0.33227404952049255,
      "learning_rate": 0.0004909984993637036,
      "loss": 1.9062,
      "step": 1198
    },
    {
      "epoch": 0.11708984375,
      "grad_norm": 0.32993388175964355,
      "learning_rate": 0.0004909785754470866,
      "loss": 1.9327,
      "step": 1199
    },
    {
      "epoch": 0.1171875,
      "grad_norm": 0.28574901819229126,
      "learning_rate": 0.0004909586299561233,
      "loss": 1.9481,
      "step": 1200
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 10240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 7.347007134262886e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}