{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.4,
  "eval_steps": 500,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002,
      "grad_norm": 0.15426555275917053,
      "learning_rate": 4.999e-05,
      "loss": 1.05,
      "step": 1
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.12709155678749084,
      "learning_rate": 4.9980000000000006e-05,
      "loss": 1.0572,
      "step": 2
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.1603364646434784,
      "learning_rate": 4.997e-05,
      "loss": 1.0282,
      "step": 3
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.2332337498664856,
      "learning_rate": 4.996e-05,
      "loss": 1.1703,
      "step": 4
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.1483815610408783,
      "learning_rate": 4.995e-05,
      "loss": 1.1163,
      "step": 5
    },
    {
      "epoch": 0.012,
      "grad_norm": 0.12220710515975952,
      "learning_rate": 4.9940000000000006e-05,
      "loss": 0.8897,
      "step": 6
    },
    {
      "epoch": 0.014,
      "grad_norm": 0.15056240558624268,
      "learning_rate": 4.9930000000000005e-05,
      "loss": 0.8998,
      "step": 7
    },
    {
      "epoch": 0.016,
      "grad_norm": 0.13436363637447357,
      "learning_rate": 4.992e-05,
      "loss": 0.9671,
      "step": 8
    },
    {
      "epoch": 0.018,
      "grad_norm": 0.13434761762619019,
      "learning_rate": 4.991e-05,
      "loss": 0.9692,
      "step": 9
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.1641756296157837,
      "learning_rate": 4.99e-05,
      "loss": 1.0044,
      "step": 10
    },
    {
      "epoch": 0.022,
      "grad_norm": 0.19019633531570435,
      "learning_rate": 4.9890000000000005e-05,
      "loss": 0.925,
      "step": 11
    },
    {
      "epoch": 0.024,
      "grad_norm": 0.11101183295249939,
      "learning_rate": 4.9880000000000004e-05,
      "loss": 0.9182,
      "step": 12
    },
    {
      "epoch": 0.026,
      "grad_norm": 0.16728107631206512,
      "learning_rate": 4.987e-05,
      "loss": 0.9582,
      "step": 13
    },
    {
      "epoch": 0.028,
      "grad_norm": 0.13117073476314545,
      "learning_rate": 4.986e-05,
      "loss": 0.9796,
      "step": 14
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.13628996908664703,
      "learning_rate": 4.9850000000000006e-05,
      "loss": 1.0854,
      "step": 15
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.244254007935524,
      "learning_rate": 4.9840000000000004e-05,
      "loss": 0.98,
      "step": 16
    },
    {
      "epoch": 0.034,
      "grad_norm": 0.15982504189014435,
      "learning_rate": 4.983e-05,
      "loss": 1.0,
      "step": 17
    },
    {
      "epoch": 0.036,
      "grad_norm": 0.19700302183628082,
      "learning_rate": 4.982e-05,
      "loss": 0.976,
      "step": 18
    },
    {
      "epoch": 0.038,
      "grad_norm": 0.13975825905799866,
      "learning_rate": 4.981e-05,
      "loss": 0.9673,
      "step": 19
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.19986604154109955,
      "learning_rate": 4.9800000000000004e-05,
      "loss": 1.0941,
      "step": 20
    },
    {
      "epoch": 0.042,
      "grad_norm": 0.13514864444732666,
      "learning_rate": 4.979e-05,
      "loss": 0.9293,
      "step": 21
    },
    {
      "epoch": 0.044,
      "grad_norm": 0.17641392350196838,
      "learning_rate": 4.978e-05,
      "loss": 1.0845,
      "step": 22
    },
    {
      "epoch": 0.046,
      "grad_norm": 0.14343786239624023,
      "learning_rate": 4.977e-05,
      "loss": 0.9832,
      "step": 23
    },
    {
      "epoch": 0.048,
      "grad_norm": 0.19530853629112244,
      "learning_rate": 4.976e-05,
      "loss": 1.0003,
      "step": 24
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.1906237006187439,
      "learning_rate": 4.975e-05,
      "loss": 1.0535,
      "step": 25
    },
    {
      "epoch": 0.052,
      "grad_norm": 0.16383886337280273,
      "learning_rate": 4.974e-05,
      "loss": 0.9403,
      "step": 26
    },
    {
      "epoch": 0.054,
      "grad_norm": 0.18397654592990875,
      "learning_rate": 4.973000000000001e-05,
      "loss": 0.9986,
      "step": 27
    },
    {
      "epoch": 0.056,
      "grad_norm": 0.1469949334859848,
      "learning_rate": 4.972e-05,
      "loss": 0.8989,
      "step": 28
    },
    {
      "epoch": 0.058,
      "grad_norm": 0.14918571710586548,
      "learning_rate": 4.9710000000000003e-05,
      "loss": 1.0134,
      "step": 29
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.17474521696567535,
      "learning_rate": 4.97e-05,
      "loss": 0.8832,
      "step": 30
    },
    {
      "epoch": 0.062,
      "grad_norm": 0.1665133684873581,
      "learning_rate": 4.969e-05,
      "loss": 0.852,
      "step": 31
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.16474837064743042,
      "learning_rate": 4.9680000000000005e-05,
      "loss": 0.8692,
      "step": 32
    },
    {
      "epoch": 0.066,
      "grad_norm": 0.1703304797410965,
      "learning_rate": 4.967e-05,
      "loss": 0.9744,
      "step": 33
    },
    {
      "epoch": 0.068,
      "grad_norm": 0.363540917634964,
      "learning_rate": 4.966e-05,
      "loss": 0.9743,
      "step": 34
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.15182030200958252,
      "learning_rate": 4.965e-05,
      "loss": 0.8621,
      "step": 35
    },
    {
      "epoch": 0.072,
      "grad_norm": 0.18470583856105804,
      "learning_rate": 4.9640000000000006e-05,
      "loss": 0.8994,
      "step": 36
    },
    {
      "epoch": 0.074,
      "grad_norm": 0.17034071683883667,
      "learning_rate": 4.9630000000000004e-05,
      "loss": 0.8815,
      "step": 37
    },
    {
      "epoch": 0.076,
      "grad_norm": 0.1921834647655487,
      "learning_rate": 4.962e-05,
      "loss": 0.8571,
      "step": 38
    },
    {
      "epoch": 0.078,
      "grad_norm": 0.5177106857299805,
      "learning_rate": 4.961e-05,
      "loss": 0.8526,
      "step": 39
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.17441946268081665,
      "learning_rate": 4.96e-05,
      "loss": 0.9106,
      "step": 40
    },
    {
      "epoch": 0.082,
      "grad_norm": 0.1906650960445404,
      "learning_rate": 4.9590000000000005e-05,
      "loss": 0.9408,
      "step": 41
    },
    {
      "epoch": 0.084,
      "grad_norm": 0.15480925142765045,
      "learning_rate": 4.958e-05,
      "loss": 0.94,
      "step": 42
    },
    {
      "epoch": 0.086,
      "grad_norm": 0.1611844003200531,
      "learning_rate": 4.957e-05,
      "loss": 0.8976,
      "step": 43
    },
    {
      "epoch": 0.088,
      "grad_norm": 0.1564462035894394,
      "learning_rate": 4.956e-05,
      "loss": 0.8556,
      "step": 44
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.19315579533576965,
      "learning_rate": 4.9550000000000005e-05,
      "loss": 0.9154,
      "step": 45
    },
    {
      "epoch": 0.092,
      "grad_norm": 0.19190064072608948,
      "learning_rate": 4.9540000000000003e-05,
      "loss": 0.8546,
      "step": 46
    },
    {
      "epoch": 0.094,
      "grad_norm": 0.18955475091934204,
      "learning_rate": 4.953e-05,
      "loss": 0.9515,
      "step": 47
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.18206185102462769,
      "learning_rate": 4.952e-05,
      "loss": 0.9668,
      "step": 48
    },
    {
      "epoch": 0.098,
      "grad_norm": 0.17476564645767212,
      "learning_rate": 4.951e-05,
      "loss": 0.8894,
      "step": 49
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.16770018637180328,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.864,
      "step": 50
    },
    {
      "epoch": 0.102,
      "grad_norm": 0.1613185703754425,
      "learning_rate": 4.949e-05,
      "loss": 0.8604,
      "step": 51
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.18597957491874695,
      "learning_rate": 4.948000000000001e-05,
      "loss": 1.0068,
      "step": 52
    },
    {
      "epoch": 0.106,
      "grad_norm": 0.15847554802894592,
      "learning_rate": 4.947e-05,
      "loss": 0.8898,
      "step": 53
    },
    {
      "epoch": 0.108,
      "grad_norm": 0.14919398725032806,
      "learning_rate": 4.946e-05,
      "loss": 0.8268,
      "step": 54
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.15170955657958984,
      "learning_rate": 4.945e-05,
      "loss": 0.7413,
      "step": 55
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.1621982753276825,
      "learning_rate": 4.944e-05,
      "loss": 0.9099,
      "step": 56
    },
    {
      "epoch": 0.114,
      "grad_norm": 0.1732129007577896,
      "learning_rate": 4.9430000000000006e-05,
      "loss": 0.7594,
      "step": 57
    },
    {
      "epoch": 0.116,
      "grad_norm": 0.17541876435279846,
      "learning_rate": 4.942e-05,
      "loss": 0.8599,
      "step": 58
    },
    {
      "epoch": 0.118,
      "grad_norm": 0.20780043303966522,
      "learning_rate": 4.941e-05,
      "loss": 0.8937,
      "step": 59
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.15124286711215973,
      "learning_rate": 4.94e-05,
      "loss": 0.8622,
      "step": 60
    },
    {
      "epoch": 0.122,
      "grad_norm": 0.15645167231559753,
      "learning_rate": 4.939e-05,
      "loss": 0.9051,
      "step": 61
    },
    {
      "epoch": 0.124,
      "grad_norm": 0.29350391030311584,
      "learning_rate": 4.9380000000000005e-05,
      "loss": 0.8143,
      "step": 62
    },
    {
      "epoch": 0.126,
      "grad_norm": 0.21682289242744446,
      "learning_rate": 4.937e-05,
      "loss": 0.919,
      "step": 63
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.1551298350095749,
      "learning_rate": 4.936e-05,
      "loss": 0.9609,
      "step": 64
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.18353714048862457,
      "learning_rate": 4.935e-05,
      "loss": 0.8417,
      "step": 65
    },
    {
      "epoch": 0.132,
      "grad_norm": 0.16884168982505798,
      "learning_rate": 4.9340000000000005e-05,
      "loss": 0.8245,
      "step": 66
    },
    {
      "epoch": 0.134,
      "grad_norm": 0.16556158661842346,
      "learning_rate": 4.9330000000000004e-05,
      "loss": 0.861,
      "step": 67
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.1595425009727478,
      "learning_rate": 4.932e-05,
      "loss": 0.8105,
      "step": 68
    },
    {
      "epoch": 0.138,
      "grad_norm": 0.16665107011795044,
      "learning_rate": 4.931e-05,
      "loss": 0.9665,
      "step": 69
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.16219840943813324,
      "learning_rate": 4.93e-05,
      "loss": 0.8015,
      "step": 70
    },
    {
      "epoch": 0.142,
      "grad_norm": 0.17223553359508514,
      "learning_rate": 4.9290000000000004e-05,
      "loss": 0.8522,
      "step": 71
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.15540814399719238,
      "learning_rate": 4.928e-05,
      "loss": 0.6988,
      "step": 72
    },
    {
      "epoch": 0.146,
      "grad_norm": 0.17961961030960083,
      "learning_rate": 4.927000000000001e-05,
      "loss": 0.9313,
      "step": 73
    },
    {
      "epoch": 0.148,
      "grad_norm": 0.17895761132240295,
      "learning_rate": 4.926e-05,
      "loss": 0.8712,
      "step": 74
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.17795026302337646,
      "learning_rate": 4.9250000000000004e-05,
      "loss": 0.8601,
      "step": 75
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.16494092345237732,
      "learning_rate": 4.924e-05,
      "loss": 0.8595,
      "step": 76
    },
    {
      "epoch": 0.154,
      "grad_norm": 0.17727716267108917,
      "learning_rate": 4.923e-05,
      "loss": 0.7616,
      "step": 77
    },
    {
      "epoch": 0.156,
      "grad_norm": 0.1806144267320633,
      "learning_rate": 4.9220000000000006e-05,
      "loss": 0.771,
      "step": 78
    },
    {
      "epoch": 0.158,
      "grad_norm": 0.16605085134506226,
      "learning_rate": 4.921e-05,
      "loss": 0.7771,
      "step": 79
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.2618866264820099,
      "learning_rate": 4.92e-05,
      "loss": 0.9218,
      "step": 80
    },
    {
      "epoch": 0.162,
      "grad_norm": 0.20908960700035095,
      "learning_rate": 4.919e-05,
      "loss": 0.7781,
      "step": 81
    },
    {
      "epoch": 0.164,
      "grad_norm": 0.16217266023159027,
      "learning_rate": 4.918000000000001e-05,
      "loss": 0.8979,
      "step": 82
    },
    {
      "epoch": 0.166,
      "grad_norm": 0.161507248878479,
      "learning_rate": 4.9170000000000005e-05,
      "loss": 0.6754,
      "step": 83
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.17677399516105652,
      "learning_rate": 4.9160000000000004e-05,
      "loss": 0.7224,
      "step": 84
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.2032463252544403,
      "learning_rate": 4.915e-05,
      "loss": 0.7824,
      "step": 85
    },
    {
      "epoch": 0.172,
      "grad_norm": 0.18544171750545502,
      "learning_rate": 4.914e-05,
      "loss": 0.8323,
      "step": 86
    },
    {
      "epoch": 0.174,
      "grad_norm": 0.17022430896759033,
      "learning_rate": 4.9130000000000006e-05,
      "loss": 0.8678,
      "step": 87
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.16055932641029358,
      "learning_rate": 4.9120000000000004e-05,
      "loss": 0.7293,
      "step": 88
    },
    {
      "epoch": 0.178,
      "grad_norm": 0.1739533543586731,
      "learning_rate": 4.911e-05,
      "loss": 0.6897,
      "step": 89
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.17253080010414124,
      "learning_rate": 4.91e-05,
      "loss": 0.7663,
      "step": 90
    },
    {
      "epoch": 0.182,
      "grad_norm": 0.18093682825565338,
      "learning_rate": 4.9090000000000006e-05,
      "loss": 0.8966,
      "step": 91
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.39482560753822327,
      "learning_rate": 4.9080000000000004e-05,
      "loss": 0.7794,
      "step": 92
    },
    {
      "epoch": 0.186,
      "grad_norm": 0.1769993156194687,
      "learning_rate": 4.907e-05,
      "loss": 0.7503,
      "step": 93
    },
    {
      "epoch": 0.188,
      "grad_norm": 0.1584313064813614,
      "learning_rate": 4.906e-05,
      "loss": 0.7138,
      "step": 94
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.21162880957126617,
      "learning_rate": 4.905e-05,
      "loss": 0.8229,
      "step": 95
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.1863650381565094,
      "learning_rate": 4.9040000000000005e-05,
      "loss": 0.7932,
      "step": 96
    },
    {
      "epoch": 0.194,
      "grad_norm": 0.19603383541107178,
      "learning_rate": 4.903e-05,
      "loss": 0.7973,
      "step": 97
    },
    {
      "epoch": 0.196,
      "grad_norm": 0.16941046714782715,
      "learning_rate": 4.902e-05,
      "loss": 0.7216,
      "step": 98
    },
    {
      "epoch": 0.198,
      "grad_norm": 0.17508655786514282,
      "learning_rate": 4.901e-05,
      "loss": 0.6917,
      "step": 99
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.20799246430397034,
      "learning_rate": 4.9e-05,
      "loss": 0.7623,
      "step": 100
    },
    {
      "epoch": 0.202,
      "grad_norm": 0.17266519367694855,
      "learning_rate": 4.8990000000000004e-05,
      "loss": 0.7838,
      "step": 101
    },
    {
      "epoch": 0.204,
      "grad_norm": 0.15804770588874817,
      "learning_rate": 4.898e-05,
      "loss": 0.7198,
      "step": 102
    },
    {
      "epoch": 0.206,
      "grad_norm": 0.18841996788978577,
      "learning_rate": 4.897000000000001e-05,
      "loss": 0.8427,
      "step": 103
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.2060270458459854,
      "learning_rate": 4.896e-05,
      "loss": 0.732,
      "step": 104
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.16148711740970612,
      "learning_rate": 4.8950000000000004e-05,
      "loss": 0.7576,
      "step": 105
    },
    {
      "epoch": 0.212,
      "grad_norm": 0.16729658842086792,
      "learning_rate": 4.894e-05,
      "loss": 0.7049,
      "step": 106
    },
    {
      "epoch": 0.214,
      "grad_norm": 0.18130692839622498,
      "learning_rate": 4.893e-05,
      "loss": 0.7943,
      "step": 107
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.16856049001216888,
      "learning_rate": 4.8920000000000006e-05,
      "loss": 0.7507,
      "step": 108
    },
    {
      "epoch": 0.218,
      "grad_norm": 0.17912209033966064,
      "learning_rate": 4.891e-05,
      "loss": 0.7448,
      "step": 109
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.16425421833992004,
      "learning_rate": 4.89e-05,
      "loss": 0.7518,
      "step": 110
    },
    {
      "epoch": 0.222,
      "grad_norm": 0.18968652188777924,
      "learning_rate": 4.889e-05,
      "loss": 0.7387,
      "step": 111
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.18210746347904205,
      "learning_rate": 4.8880000000000006e-05,
      "loss": 0.8284,
      "step": 112
    },
    {
      "epoch": 0.226,
      "grad_norm": 0.16067589819431305,
      "learning_rate": 4.8870000000000005e-05,
      "loss": 0.7161,
      "step": 113
    },
    {
      "epoch": 0.228,
      "grad_norm": 0.21508732438087463,
      "learning_rate": 4.886e-05,
      "loss": 0.7559,
      "step": 114
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.20675824582576752,
      "learning_rate": 4.885e-05,
      "loss": 0.7717,
      "step": 115
    },
    {
      "epoch": 0.232,
      "grad_norm": 0.1855594366788864,
      "learning_rate": 4.884e-05,
      "loss": 0.7304,
      "step": 116
    },
    {
      "epoch": 0.234,
      "grad_norm": 0.17346052825450897,
      "learning_rate": 4.8830000000000005e-05,
      "loss": 0.7946,
      "step": 117
    },
    {
      "epoch": 0.236,
      "grad_norm": 0.16850675642490387,
      "learning_rate": 4.8820000000000004e-05,
      "loss": 0.8264,
      "step": 118
    },
    {
      "epoch": 0.238,
      "grad_norm": 0.17360711097717285,
      "learning_rate": 4.881e-05,
      "loss": 0.7152,
      "step": 119
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.19422297179698944,
      "learning_rate": 4.88e-05,
      "loss": 0.7704,
      "step": 120
    },
    {
      "epoch": 0.242,
      "grad_norm": 0.16386844217777252,
      "learning_rate": 4.8790000000000006e-05,
      "loss": 0.8024,
      "step": 121
    },
    {
      "epoch": 0.244,
      "grad_norm": 0.18992245197296143,
      "learning_rate": 4.8780000000000004e-05,
      "loss": 0.6937,
      "step": 122
    },
    {
      "epoch": 0.246,
      "grad_norm": 0.17040878534317017,
      "learning_rate": 4.877e-05,
      "loss": 0.7349,
      "step": 123
    },
    {
      "epoch": 0.248,
      "grad_norm": 0.187296524643898,
      "learning_rate": 4.876e-05,
      "loss": 0.6242,
      "step": 124
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.17259983718395233,
      "learning_rate": 4.875e-05,
      "loss": 0.6656,
      "step": 125
    },
    {
      "epoch": 0.252,
      "grad_norm": 0.16188134253025055,
      "learning_rate": 4.8740000000000004e-05,
      "loss": 0.7009,
      "step": 126
    },
    {
      "epoch": 0.254,
      "grad_norm": 0.17831256985664368,
      "learning_rate": 4.873e-05,
      "loss": 0.7098,
      "step": 127
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.18309949338436127,
      "learning_rate": 4.872000000000001e-05,
      "loss": 0.8171,
      "step": 128
    },
    {
      "epoch": 0.258,
      "grad_norm": 0.17562147974967957,
      "learning_rate": 4.871e-05,
      "loss": 0.7185,
      "step": 129
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.18238484859466553,
      "learning_rate": 4.87e-05,
      "loss": 0.7824,
      "step": 130
    },
    {
      "epoch": 0.262,
      "grad_norm": 0.1970655918121338,
      "learning_rate": 4.869e-05,
      "loss": 0.6794,
      "step": 131
    },
    {
      "epoch": 0.264,
      "grad_norm": 0.18091806769371033,
      "learning_rate": 4.868e-05,
      "loss": 0.7149,
      "step": 132
    },
    {
      "epoch": 0.266,
      "grad_norm": 0.16607695817947388,
      "learning_rate": 4.867000000000001e-05,
      "loss": 0.6596,
      "step": 133
    },
    {
      "epoch": 0.268,
      "grad_norm": 0.14630946516990662,
      "learning_rate": 4.866e-05,
      "loss": 0.5551,
      "step": 134
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.1951550394296646,
      "learning_rate": 4.8650000000000003e-05,
      "loss": 0.6972,
      "step": 135
    },
    {
      "epoch": 0.272,
      "grad_norm": 0.16738222539424896,
      "learning_rate": 4.864e-05,
      "loss": 0.6976,
      "step": 136
    },
    {
      "epoch": 0.274,
      "grad_norm": 0.17754323780536652,
      "learning_rate": 4.863e-05,
      "loss": 0.7231,
      "step": 137
    },
    {
      "epoch": 0.276,
      "grad_norm": 0.19366562366485596,
      "learning_rate": 4.8620000000000005e-05,
      "loss": 0.7682,
      "step": 138
    },
    {
      "epoch": 0.278,
      "grad_norm": 0.19526396691799164,
      "learning_rate": 4.861e-05,
      "loss": 0.6572,
      "step": 139
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.18090026080608368,
      "learning_rate": 4.86e-05,
      "loss": 0.7206,
      "step": 140
    },
    {
      "epoch": 0.282,
      "grad_norm": 0.17786529660224915,
      "learning_rate": 4.859e-05,
      "loss": 0.7527,
      "step": 141
    },
    {
      "epoch": 0.284,
      "grad_norm": 0.17932577431201935,
      "learning_rate": 4.8580000000000006e-05,
      "loss": 0.7523,
      "step": 142
    },
    {
      "epoch": 0.286,
      "grad_norm": 0.17716765403747559,
      "learning_rate": 4.8570000000000004e-05,
      "loss": 0.66,
      "step": 143
    },
    {
      "epoch": 0.288,
      "grad_norm": 0.19830791652202606,
      "learning_rate": 4.856e-05,
      "loss": 0.7504,
      "step": 144
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.19970470666885376,
      "learning_rate": 4.855e-05,
      "loss": 0.8374,
      "step": 145
    },
    {
      "epoch": 0.292,
      "grad_norm": 0.17745786905288696,
      "learning_rate": 4.854e-05,
      "loss": 0.7288,
      "step": 146
    },
    {
      "epoch": 0.294,
      "grad_norm": 0.16594083607196808,
      "learning_rate": 4.8530000000000005e-05,
      "loss": 0.6372,
      "step": 147
    },
    {
      "epoch": 0.296,
      "grad_norm": 0.19067466259002686,
      "learning_rate": 4.852e-05,
      "loss": 0.7761,
      "step": 148
    },
    {
      "epoch": 0.298,
      "grad_norm": 0.17589321732521057,
      "learning_rate": 4.851e-05,
      "loss": 0.7475,
      "step": 149
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.16668495535850525,
      "learning_rate": 4.85e-05,
      "loss": 0.655,
      "step": 150
    },
    {
      "epoch": 0.302,
      "grad_norm": 0.18038712441921234,
      "learning_rate": 4.8490000000000005e-05,
      "loss": 0.7447,
      "step": 151
    },
    {
      "epoch": 0.304,
      "grad_norm": 0.17747431993484497,
      "learning_rate": 4.8480000000000003e-05,
      "loss": 0.6821,
      "step": 152
    },
    {
      "epoch": 0.306,
      "grad_norm": 0.18808145821094513,
      "learning_rate": 4.847e-05,
      "loss": 0.6878,
      "step": 153
    },
    {
      "epoch": 0.308,
      "grad_norm": 0.16301684081554413,
      "learning_rate": 4.846e-05,
      "loss": 0.6687,
      "step": 154
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.1757572591304779,
      "learning_rate": 4.845e-05,
      "loss": 0.7166,
      "step": 155
    },
    {
      "epoch": 0.312,
      "grad_norm": 0.16521325707435608,
      "learning_rate": 4.8440000000000004e-05,
      "loss": 0.6626,
      "step": 156
    },
    {
      "epoch": 0.314,
      "grad_norm": 0.17104895412921906,
      "learning_rate": 4.843e-05,
      "loss": 0.694,
      "step": 157
    },
    {
      "epoch": 0.316,
      "grad_norm": 0.2105347067117691,
      "learning_rate": 4.842000000000001e-05,
      "loss": 0.7123,
      "step": 158
    },
    {
      "epoch": 0.318,
      "grad_norm": 0.1545153558254242,
      "learning_rate": 4.841e-05,
      "loss": 0.7374,
      "step": 159
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.18015415966510773,
      "learning_rate": 4.8400000000000004e-05,
      "loss": 0.8343,
      "step": 160
    },
    {
      "epoch": 0.322,
      "grad_norm": 0.1678248643875122,
      "learning_rate": 4.839e-05,
      "loss": 0.677,
      "step": 161
    },
    {
      "epoch": 0.324,
      "grad_norm": 0.2440311163663864,
      "learning_rate": 4.838e-05,
      "loss": 0.7022,
      "step": 162
    },
    {
      "epoch": 0.326,
      "grad_norm": 0.1826225370168686,
      "learning_rate": 4.8370000000000006e-05,
      "loss": 0.7169,
      "step": 163
    },
    {
      "epoch": 0.328,
      "grad_norm": 0.1914544403553009,
      "learning_rate": 4.836e-05,
      "loss": 0.745,
      "step": 164
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.18756432831287384,
      "learning_rate": 4.835e-05,
      "loss": 0.6353,
      "step": 165
    },
    {
      "epoch": 0.332,
      "grad_norm": 0.16854585707187653,
      "learning_rate": 4.834e-05,
      "loss": 0.7072,
      "step": 166
    },
    {
      "epoch": 0.334,
      "grad_norm": 0.2005048245191574,
      "learning_rate": 4.833e-05,
      "loss": 0.7651,
      "step": 167
    },
    {
      "epoch": 0.336,
      "grad_norm": 0.19548290967941284,
      "learning_rate": 4.8320000000000005e-05,
      "loss": 0.736,
      "step": 168
    },
    {
      "epoch": 0.338,
      "grad_norm": 0.17135733366012573,
      "learning_rate": 4.8309999999999997e-05,
      "loss": 0.8211,
      "step": 169
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.16657552123069763,
      "learning_rate": 4.83e-05,
      "loss": 0.7372,
      "step": 170
    },
    {
      "epoch": 0.342,
      "grad_norm": 0.17498229444026947,
      "learning_rate": 4.829e-05,
      "loss": 0.7333,
      "step": 171
    },
    {
      "epoch": 0.344,
      "grad_norm": 0.18211571872234344,
      "learning_rate": 4.8280000000000005e-05,
      "loss": 0.7547,
      "step": 172
    },
    {
      "epoch": 0.346,
      "grad_norm": 0.1906624734401703,
      "learning_rate": 4.8270000000000004e-05,
      "loss": 0.7839,
      "step": 173
    },
    {
      "epoch": 0.348,
      "grad_norm": 0.1763816624879837,
      "learning_rate": 4.826e-05,
      "loss": 0.6486,
      "step": 174
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.16783268749713898,
      "learning_rate": 4.825e-05,
      "loss": 0.6533,
      "step": 175
    },
    {
      "epoch": 0.352,
      "grad_norm": 0.17041102051734924,
      "learning_rate": 4.824e-05,
      "loss": 0.7981,
      "step": 176
    },
    {
      "epoch": 0.354,
      "grad_norm": 0.1828545331954956,
      "learning_rate": 4.8230000000000004e-05,
      "loss": 0.7116,
      "step": 177
    },
    {
      "epoch": 0.356,
      "grad_norm": 0.20127569139003754,
      "learning_rate": 4.822e-05,
      "loss": 0.7525,
      "step": 178
    },
    {
      "epoch": 0.358,
      "grad_norm": 0.1801321655511856,
      "learning_rate": 4.821e-05,
      "loss": 0.6858,
      "step": 179
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.18023674190044403,
      "learning_rate": 4.82e-05,
      "loss": 0.7719,
      "step": 180
    },
    {
      "epoch": 0.362,
      "grad_norm": 0.19391784071922302,
      "learning_rate": 4.8190000000000004e-05,
      "loss": 0.7177,
      "step": 181
    },
    {
      "epoch": 0.364,
      "grad_norm": 0.17303819954395294,
      "learning_rate": 4.818e-05,
      "loss": 0.6717,
      "step": 182
    },
    {
      "epoch": 0.366,
      "grad_norm": 0.16896046698093414,
      "learning_rate": 4.817e-05,
      "loss": 0.6847,
      "step": 183
    },
    {
      "epoch": 0.368,
      "grad_norm": 0.19223248958587646,
      "learning_rate": 4.816e-05,
      "loss": 0.6312,
      "step": 184
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.20020322501659393,
      "learning_rate": 4.815e-05,
      "loss": 0.6391,
      "step": 185
    },
    {
      "epoch": 0.372,
      "grad_norm": 0.16758307814598083,
      "learning_rate": 4.814e-05,
      "loss": 0.6659,
      "step": 186
    },
    {
      "epoch": 0.374,
      "grad_norm": 0.176300048828125,
      "learning_rate": 4.813e-05,
      "loss": 0.6823,
      "step": 187
    },
    {
      "epoch": 0.376,
      "grad_norm": 0.17282813787460327,
      "learning_rate": 4.812000000000001e-05,
      "loss": 0.6885,
      "step": 188
    },
    {
      "epoch": 0.378,
      "grad_norm": 0.1966462880373001,
      "learning_rate": 4.8110000000000005e-05,
      "loss": 0.6833,
      "step": 189
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.18239817023277283,
      "learning_rate": 4.8100000000000004e-05,
      "loss": 0.6464,
      "step": 190
    },
    {
      "epoch": 0.382,
      "grad_norm": 0.17479926347732544,
      "learning_rate": 4.809e-05,
      "loss": 0.6868,
      "step": 191
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.1797116994857788,
      "learning_rate": 4.808e-05,
      "loss": 0.612,
      "step": 192
    },
    {
      "epoch": 0.386,
      "grad_norm": 0.17411945760250092,
      "learning_rate": 4.8070000000000006e-05,
      "loss": 0.6431,
      "step": 193
    },
    {
      "epoch": 0.388,
      "grad_norm": 0.20542018115520477,
      "learning_rate": 4.8060000000000004e-05,
      "loss": 0.6994,
      "step": 194
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.18406227231025696,
      "learning_rate": 4.805e-05,
      "loss": 0.6693,
      "step": 195
    },
    {
      "epoch": 0.392,
      "grad_norm": 0.16543979942798615,
      "learning_rate": 4.804e-05,
      "loss": 0.5446,
      "step": 196
    },
    {
      "epoch": 0.394,
      "grad_norm": 0.17976847290992737,
      "learning_rate": 4.8030000000000006e-05,
      "loss": 0.6433,
      "step": 197
    },
    {
      "epoch": 0.396,
      "grad_norm": 0.26321882009506226,
      "learning_rate": 4.8020000000000004e-05,
      "loss": 0.73,
      "step": 198
    },
    {
      "epoch": 0.398,
      "grad_norm": 0.19417919218540192,
      "learning_rate": 4.801e-05,
      "loss": 0.6931,
      "step": 199
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.17781345546245575,
      "learning_rate": 4.8e-05,
      "loss": 0.6867,
      "step": 200
    },
    {
      "epoch": 0.402,
      "grad_norm": 0.188642680644989,
      "learning_rate": 4.799e-05,
      "loss": 0.6491,
      "step": 201
    },
    {
      "epoch": 0.404,
      "grad_norm": 0.18071314692497253,
      "learning_rate": 4.7980000000000005e-05,
      "loss": 0.6237,
      "step": 202
    },
    {
      "epoch": 0.406,
      "grad_norm": 0.21487824618816376,
      "learning_rate": 4.797e-05,
      "loss": 0.7617,
      "step": 203
    },
    {
      "epoch": 0.408,
      "grad_norm": 0.17277319729328156,
      "learning_rate": 4.796e-05,
      "loss": 0.5965,
      "step": 204
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.18421082198619843,
      "learning_rate": 4.795e-05,
      "loss": 0.679,
      "step": 205
    },
    {
      "epoch": 0.412,
      "grad_norm": 0.15729452669620514,
      "learning_rate": 4.794e-05,
      "loss": 0.6262,
      "step": 206
    },
    {
      "epoch": 0.414,
      "grad_norm": 0.2214370220899582,
      "learning_rate": 4.7930000000000004e-05,
      "loss": 0.6288,
      "step": 207
    },
    {
      "epoch": 0.416,
      "grad_norm": 0.17312027513980865,
      "learning_rate": 4.792e-05,
      "loss": 0.6782,
      "step": 208
    },
    {
      "epoch": 0.418,
      "grad_norm": 0.21297283470630646,
      "learning_rate": 4.791000000000001e-05,
      "loss": 0.7311,
      "step": 209
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.20006674528121948,
      "learning_rate": 4.79e-05,
      "loss": 0.7033,
      "step": 210
    },
    {
      "epoch": 0.422,
      "grad_norm": 0.19188763201236725,
      "learning_rate": 4.7890000000000004e-05,
      "loss": 0.6777,
      "step": 211
    },
    {
      "epoch": 0.424,
      "grad_norm": 0.17428816854953766,
      "learning_rate": 4.788e-05,
      "loss": 0.6487,
      "step": 212
    },
    {
      "epoch": 0.426,
      "grad_norm": 0.20363588631153107,
      "learning_rate": 4.787e-05,
      "loss": 0.8352,
      "step": 213
    },
    {
      "epoch": 0.428,
      "grad_norm": 0.171103835105896,
      "learning_rate": 4.7860000000000006e-05,
      "loss": 0.5961,
      "step": 214
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.17176367342472076,
      "learning_rate": 4.785e-05,
      "loss": 0.6979,
      "step": 215
    },
    {
      "epoch": 0.432,
      "grad_norm": 0.17316070199012756,
      "learning_rate": 4.784e-05,
      "loss": 0.592,
      "step": 216
    },
    {
      "epoch": 0.434,
      "grad_norm": 0.17615540325641632,
      "learning_rate": 4.783e-05,
      "loss": 0.7628,
      "step": 217
    },
    {
      "epoch": 0.436,
      "grad_norm": 0.1740606278181076,
      "learning_rate": 4.7820000000000006e-05,
      "loss": 0.6561,
      "step": 218
    },
    {
      "epoch": 0.438,
      "grad_norm": 0.1783115118741989,
      "learning_rate": 4.7810000000000005e-05,
      "loss": 0.6712,
      "step": 219
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.1763063669204712,
      "learning_rate": 4.78e-05,
      "loss": 0.7533,
      "step": 220
    },
    {
      "epoch": 0.442,
      "grad_norm": 0.19785965979099274,
      "learning_rate": 4.779e-05,
      "loss": 0.7371,
      "step": 221
    },
    {
      "epoch": 0.444,
      "grad_norm": 0.2079770267009735,
      "learning_rate": 4.778e-05,
      "loss": 0.7435,
      "step": 222
    },
    {
      "epoch": 0.446,
      "grad_norm": 0.18670807778835297,
      "learning_rate": 4.7770000000000005e-05,
      "loss": 0.6834,
      "step": 223
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.18333281576633453,
      "learning_rate": 4.7760000000000004e-05,
      "loss": 0.6122,
      "step": 224
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.19812564551830292,
      "learning_rate": 4.775e-05,
      "loss": 0.6303,
      "step": 225
    },
    {
      "epoch": 0.452,
      "grad_norm": 0.20050670206546783,
      "learning_rate": 4.774e-05,
      "loss": 0.769,
      "step": 226
    },
    {
      "epoch": 0.454,
      "grad_norm": 0.1639266014099121,
      "learning_rate": 4.7730000000000005e-05,
      "loss": 0.6178,
      "step": 227
    },
    {
      "epoch": 0.456,
      "grad_norm": 0.17916633188724518,
      "learning_rate": 4.7720000000000004e-05,
      "loss": 0.6541,
      "step": 228
    },
    {
      "epoch": 0.458,
      "grad_norm": 0.22116564214229584,
      "learning_rate": 4.771e-05,
      "loss": 0.7461,
      "step": 229
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.176322802901268,
      "learning_rate": 4.77e-05,
      "loss": 0.6412,
      "step": 230
    },
    {
      "epoch": 0.462,
      "grad_norm": 0.19817325472831726,
      "learning_rate": 4.769e-05,
      "loss": 0.6134,
      "step": 231
    },
    {
      "epoch": 0.464,
      "grad_norm": 0.1950073093175888,
      "learning_rate": 4.7680000000000004e-05,
      "loss": 0.6869,
      "step": 232
    },
    {
      "epoch": 0.466,
      "grad_norm": 0.1868954300880432,
      "learning_rate": 4.767e-05,
      "loss": 0.6438,
      "step": 233
    },
    {
      "epoch": 0.468,
      "grad_norm": 0.17018316686153412,
      "learning_rate": 4.766000000000001e-05,
      "loss": 0.6171,
      "step": 234
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.2001843899488449,
      "learning_rate": 4.765e-05,
      "loss": 0.6735,
      "step": 235
    },
    {
      "epoch": 0.472,
      "grad_norm": 0.17621289193630219,
      "learning_rate": 4.7640000000000005e-05,
      "loss": 0.5407,
      "step": 236
    },
    {
      "epoch": 0.474,
      "grad_norm": 0.19587376713752747,
      "learning_rate": 4.763e-05,
      "loss": 0.7755,
      "step": 237
    },
    {
      "epoch": 0.476,
      "grad_norm": 0.1757344752550125,
      "learning_rate": 4.762e-05,
      "loss": 0.6121,
      "step": 238
    },
    {
      "epoch": 0.478,
      "grad_norm": 0.19122175872325897,
      "learning_rate": 4.761000000000001e-05,
      "loss": 0.7537,
      "step": 239
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.1687469482421875,
      "learning_rate": 4.76e-05,
      "loss": 0.6598,
      "step": 240
    },
    {
      "epoch": 0.482,
      "grad_norm": 0.16485217213630676,
      "learning_rate": 4.7590000000000003e-05,
      "loss": 0.545,
      "step": 241
    },
    {
      "epoch": 0.484,
      "grad_norm": 0.1940855085849762,
      "learning_rate": 4.758e-05,
      "loss": 0.7865,
      "step": 242
    },
    {
      "epoch": 0.486,
      "grad_norm": 0.2028513252735138,
      "learning_rate": 4.757e-05,
      "loss": 0.6879,
      "step": 243
    },
    {
      "epoch": 0.488,
      "grad_norm": 0.15615610778331757,
      "learning_rate": 4.7560000000000005e-05,
      "loss": 0.559,
      "step": 244
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.18467123806476593,
      "learning_rate": 4.755e-05,
      "loss": 0.7475,
      "step": 245
    },
    {
      "epoch": 0.492,
      "grad_norm": 0.1865721493959427,
      "learning_rate": 4.754e-05,
      "loss": 0.7141,
      "step": 246
    },
    {
      "epoch": 0.494,
      "grad_norm": 0.18532711267471313,
      "learning_rate": 4.753e-05,
      "loss": 0.7313,
      "step": 247
    },
    {
      "epoch": 0.496,
      "grad_norm": 0.1919030398130417,
      "learning_rate": 4.7520000000000006e-05,
      "loss": 0.6593,
      "step": 248
    },
    {
      "epoch": 0.498,
      "grad_norm": 0.18372733891010284,
      "learning_rate": 4.7510000000000004e-05,
      "loss": 0.6839,
      "step": 249
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.18965525925159454,
      "learning_rate": 4.75e-05,
      "loss": 0.7376,
      "step": 250
    },
    {
      "epoch": 0.502,
      "grad_norm": 0.20535258948802948,
      "learning_rate": 4.749e-05,
      "loss": 0.7515,
      "step": 251
    },
    {
      "epoch": 0.504,
      "grad_norm": 0.16773927211761475,
      "learning_rate": 4.748e-05,
      "loss": 0.5974,
      "step": 252
    },
    {
      "epoch": 0.506,
      "grad_norm": 0.16834793984889984,
      "learning_rate": 4.7470000000000005e-05,
      "loss": 0.5599,
      "step": 253
    },
    {
      "epoch": 0.508,
      "grad_norm": 0.22490134835243225,
      "learning_rate": 4.746e-05,
      "loss": 0.7511,
      "step": 254
    },
    {
      "epoch": 0.51,
      "grad_norm": 0.1897481083869934,
      "learning_rate": 4.745e-05,
      "loss": 0.6008,
      "step": 255
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.21182553470134735,
      "learning_rate": 4.744e-05,
      "loss": 0.7087,
      "step": 256
    },
    {
      "epoch": 0.514,
      "grad_norm": 0.2457868903875351,
      "learning_rate": 4.7430000000000005e-05,
      "loss": 0.622,
      "step": 257
    },
    {
      "epoch": 0.516,
      "grad_norm": 0.18708348274230957,
      "learning_rate": 4.742e-05,
      "loss": 0.6574,
      "step": 258
    },
    {
      "epoch": 0.518,
      "grad_norm": 0.20146219432353973,
      "learning_rate": 4.741e-05,
      "loss": 0.6787,
      "step": 259
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.18447726964950562,
      "learning_rate": 4.74e-05,
      "loss": 0.6803,
      "step": 260
    },
    {
      "epoch": 0.522,
      "grad_norm": 0.18880298733711243,
      "learning_rate": 4.739e-05,
      "loss": 0.7279,
      "step": 261
    },
    {
      "epoch": 0.524,
      "grad_norm": 0.2038155347108841,
      "learning_rate": 4.7380000000000004e-05,
      "loss": 0.6424,
      "step": 262
    },
    {
      "epoch": 0.526,
      "grad_norm": 0.18949934840202332,
      "learning_rate": 4.737e-05,
      "loss": 0.6297,
      "step": 263
    },
    {
      "epoch": 0.528,
      "grad_norm": 0.19548696279525757,
      "learning_rate": 4.736000000000001e-05,
      "loss": 0.5877,
      "step": 264
    },
    {
      "epoch": 0.53,
      "grad_norm": 0.171523779630661,
      "learning_rate": 4.735e-05,
      "loss": 0.6716,
      "step": 265
    },
    {
      "epoch": 0.532,
      "grad_norm": 0.18637031316757202,
      "learning_rate": 4.7340000000000004e-05,
      "loss": 0.6865,
      "step": 266
    },
    {
      "epoch": 0.534,
      "grad_norm": 0.18773992359638214,
      "learning_rate": 4.733e-05,
      "loss": 0.6441,
      "step": 267
    },
    {
      "epoch": 0.536,
      "grad_norm": 0.1926441490650177,
      "learning_rate": 4.732e-05,
      "loss": 0.7257,
      "step": 268
    },
    {
      "epoch": 0.538,
      "grad_norm": 0.1823345571756363,
      "learning_rate": 4.7310000000000006e-05,
      "loss": 0.6777,
      "step": 269
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.19136260449886322,
      "learning_rate": 4.73e-05,
      "loss": 0.6748,
      "step": 270
    },
    {
      "epoch": 0.542,
      "grad_norm": 0.20468977093696594,
      "learning_rate": 4.729e-05,
      "loss": 0.6638,
      "step": 271
    },
    {
      "epoch": 0.544,
      "grad_norm": 0.18765564262866974,
      "learning_rate": 4.728e-05,
      "loss": 0.6411,
      "step": 272
    },
    {
      "epoch": 0.546,
      "grad_norm": 0.19151361286640167,
      "learning_rate": 4.7270000000000007e-05,
      "loss": 0.6509,
      "step": 273
    },
    {
      "epoch": 0.548,
      "grad_norm": 0.1872202306985855,
      "learning_rate": 4.7260000000000005e-05,
      "loss": 0.6721,
      "step": 274
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.1839660257101059,
      "learning_rate": 4.7249999999999997e-05,
      "loss": 0.5901,
      "step": 275
    },
    {
      "epoch": 0.552,
      "grad_norm": 0.17300380766391754,
      "learning_rate": 4.724e-05,
      "loss": 0.7104,
      "step": 276
    },
    {
      "epoch": 0.554,
      "grad_norm": 0.20044074952602386,
      "learning_rate": 4.723e-05,
      "loss": 0.755,
      "step": 277
    },
    {
      "epoch": 0.556,
      "grad_norm": 0.1961713582277298,
      "learning_rate": 4.7220000000000005e-05,
      "loss": 0.708,
      "step": 278
    },
    {
      "epoch": 0.558,
      "grad_norm": 0.18064777553081512,
      "learning_rate": 4.7210000000000004e-05,
      "loss": 0.6549,
      "step": 279
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.17640075087547302,
      "learning_rate": 4.72e-05,
      "loss": 0.6918,
      "step": 280
    },
    {
      "epoch": 0.562,
      "grad_norm": 0.17156340181827545,
      "learning_rate": 4.719e-05,
      "loss": 0.5443,
      "step": 281
    },
    {
      "epoch": 0.564,
      "grad_norm": 0.17006738483905792,
      "learning_rate": 4.718e-05,
      "loss": 0.731,
      "step": 282
    },
    {
      "epoch": 0.566,
      "grad_norm": 0.20639865100383759,
      "learning_rate": 4.7170000000000004e-05,
      "loss": 0.6952,
      "step": 283
    },
    {
      "epoch": 0.568,
      "grad_norm": 0.17628632485866547,
      "learning_rate": 4.716e-05,
      "loss": 0.6038,
      "step": 284
    },
    {
      "epoch": 0.57,
      "grad_norm": 0.20290911197662354,
      "learning_rate": 4.715e-05,
      "loss": 0.6803,
      "step": 285
    },
    {
      "epoch": 0.572,
      "grad_norm": 0.24859286844730377,
      "learning_rate": 4.714e-05,
      "loss": 0.6594,
      "step": 286
    },
    {
      "epoch": 0.574,
      "grad_norm": 0.18021917343139648,
      "learning_rate": 4.7130000000000004e-05,
      "loss": 0.7659,
      "step": 287
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.20608916878700256,
      "learning_rate": 4.712e-05,
      "loss": 0.7284,
      "step": 288
    },
    {
      "epoch": 0.578,
      "grad_norm": 0.17671485245227814,
      "learning_rate": 4.711e-05,
      "loss": 0.6577,
      "step": 289
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.1899622082710266,
      "learning_rate": 4.71e-05,
      "loss": 0.6012,
      "step": 290
    },
    {
      "epoch": 0.582,
      "grad_norm": 0.19019369781017303,
      "learning_rate": 4.709e-05,
      "loss": 0.6374,
      "step": 291
    },
    {
      "epoch": 0.584,
      "grad_norm": 0.19268132746219635,
      "learning_rate": 4.708e-05,
      "loss": 0.6448,
      "step": 292
    },
    {
      "epoch": 0.586,
      "grad_norm": 0.16056692600250244,
      "learning_rate": 4.707e-05,
      "loss": 0.5231,
      "step": 293
    },
    {
      "epoch": 0.588,
      "grad_norm": 0.18093591928482056,
      "learning_rate": 4.706000000000001e-05,
      "loss": 0.6451,
      "step": 294
    },
    {
      "epoch": 0.59,
      "grad_norm": 0.19243648648262024,
      "learning_rate": 4.705e-05,
      "loss": 0.6161,
      "step": 295
    },
    {
      "epoch": 0.592,
      "grad_norm": 0.17207425832748413,
      "learning_rate": 4.7040000000000004e-05,
      "loss": 0.5465,
      "step": 296
    },
    {
      "epoch": 0.594,
      "grad_norm": 0.17885583639144897,
      "learning_rate": 4.703e-05,
      "loss": 0.7451,
      "step": 297
    },
    {
      "epoch": 0.596,
      "grad_norm": 0.19622336328029633,
      "learning_rate": 4.702e-05,
      "loss": 0.6251,
      "step": 298
    },
    {
      "epoch": 0.598,
      "grad_norm": 0.19896407425403595,
      "learning_rate": 4.7010000000000006e-05,
      "loss": 0.6579,
      "step": 299
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.21171756088733673,
      "learning_rate": 4.7e-05,
      "loss": 0.6662,
      "step": 300
    },
    {
      "epoch": 0.602,
      "grad_norm": 0.18232490122318268,
      "learning_rate": 4.699e-05,
      "loss": 0.5088,
      "step": 301
    },
    {
      "epoch": 0.604,
      "grad_norm": 0.1896355003118515,
      "learning_rate": 4.698e-05,
      "loss": 0.6084,
      "step": 302
    },
    {
      "epoch": 0.606,
      "grad_norm": 0.1955353021621704,
      "learning_rate": 4.6970000000000006e-05,
      "loss": 0.6105,
      "step": 303
    },
    {
      "epoch": 0.608,
      "grad_norm": 0.22242772579193115,
      "learning_rate": 4.6960000000000004e-05,
      "loss": 0.6991,
      "step": 304
    },
    {
      "epoch": 0.61,
      "grad_norm": 0.1831687092781067,
      "learning_rate": 4.695e-05,
      "loss": 0.6907,
      "step": 305
    },
    {
      "epoch": 0.612,
      "grad_norm": 0.1904367059469223,
      "learning_rate": 4.694e-05,
      "loss": 0.6295,
      "step": 306
    },
    {
      "epoch": 0.614,
      "grad_norm": 0.1965903788805008,
      "learning_rate": 4.693e-05,
      "loss": 0.6932,
      "step": 307
    },
    {
      "epoch": 0.616,
      "grad_norm": 0.2138614058494568,
      "learning_rate": 4.6920000000000005e-05,
      "loss": 0.7003,
      "step": 308
    },
    {
      "epoch": 0.618,
      "grad_norm": 0.18636015057563782,
      "learning_rate": 4.691e-05,
      "loss": 0.6633,
      "step": 309
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.18050327897071838,
      "learning_rate": 4.69e-05,
      "loss": 0.6142,
      "step": 310
    },
    {
      "epoch": 0.622,
      "grad_norm": 0.1982421725988388,
      "learning_rate": 4.689e-05,
      "loss": 0.6773,
      "step": 311
    },
    {
      "epoch": 0.624,
      "grad_norm": 0.1651502251625061,
      "learning_rate": 4.688e-05,
      "loss": 0.565,
      "step": 312
    },
    {
      "epoch": 0.626,
      "grad_norm": 0.17334266006946564,
      "learning_rate": 4.6870000000000004e-05,
      "loss": 0.6226,
      "step": 313
    },
    {
      "epoch": 0.628,
      "grad_norm": 0.17907755076885223,
      "learning_rate": 4.686e-05,
      "loss": 0.679,
      "step": 314
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.25513723492622375,
      "learning_rate": 4.685000000000001e-05,
      "loss": 0.5717,
      "step": 315
    },
    {
      "epoch": 0.632,
      "grad_norm": 0.18325062096118927,
      "learning_rate": 4.684e-05,
      "loss": 0.6351,
      "step": 316
    },
    {
      "epoch": 0.634,
      "grad_norm": 0.20759661495685577,
      "learning_rate": 4.6830000000000004e-05,
      "loss": 0.6668,
      "step": 317
    },
    {
      "epoch": 0.636,
      "grad_norm": 0.19245915114879608,
      "learning_rate": 4.682e-05,
      "loss": 0.6529,
      "step": 318
    },
    {
      "epoch": 0.638,
      "grad_norm": 0.1865272969007492,
      "learning_rate": 4.681e-05,
      "loss": 0.5857,
      "step": 319
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.2123071849346161,
      "learning_rate": 4.6800000000000006e-05,
      "loss": 0.65,
      "step": 320
    },
    {
      "epoch": 0.642,
      "grad_norm": 0.1932321935892105,
      "learning_rate": 4.679e-05,
      "loss": 0.6381,
      "step": 321
    },
    {
      "epoch": 0.644,
      "grad_norm": 0.19530931115150452,
      "learning_rate": 4.678e-05,
      "loss": 0.7162,
      "step": 322
    },
    {
      "epoch": 0.646,
      "grad_norm": 0.17521904408931732,
      "learning_rate": 4.677e-05,
      "loss": 0.5582,
      "step": 323
    },
    {
      "epoch": 0.648,
      "grad_norm": 0.19137729704380035,
      "learning_rate": 4.6760000000000006e-05,
      "loss": 0.5357,
      "step": 324
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.19260117411613464,
      "learning_rate": 4.6750000000000005e-05,
      "loss": 0.6176,
      "step": 325
    },
    {
      "epoch": 0.652,
      "grad_norm": 0.1776568442583084,
      "learning_rate": 4.674e-05,
      "loss": 0.5889,
      "step": 326
    },
    {
      "epoch": 0.654,
      "grad_norm": 0.2181580364704132,
      "learning_rate": 4.673e-05,
      "loss": 0.557,
      "step": 327
    },
    {
      "epoch": 0.656,
      "grad_norm": 0.22205041348934174,
      "learning_rate": 4.672e-05,
      "loss": 0.6275,
      "step": 328
    },
    {
      "epoch": 0.658,
      "grad_norm": 0.18241576850414276,
      "learning_rate": 4.6710000000000005e-05,
      "loss": 0.5873,
      "step": 329
    },
    {
      "epoch": 0.66,
      "grad_norm": 0.17380136251449585,
      "learning_rate": 4.6700000000000003e-05,
      "loss": 0.5892,
      "step": 330
    },
    {
      "epoch": 0.662,
      "grad_norm": 0.16387759149074554,
      "learning_rate": 4.669e-05,
      "loss": 0.5868,
      "step": 331
    },
    {
      "epoch": 0.664,
      "grad_norm": 0.18557021021842957,
      "learning_rate": 4.668e-05,
      "loss": 0.5483,
      "step": 332
    },
    {
      "epoch": 0.666,
      "grad_norm": 0.19413799047470093,
      "learning_rate": 4.6670000000000005e-05,
      "loss": 0.6387,
      "step": 333
    },
    {
      "epoch": 0.668,
      "grad_norm": 0.17195573449134827,
      "learning_rate": 4.6660000000000004e-05,
      "loss": 0.607,
      "step": 334
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.17779302597045898,
      "learning_rate": 4.665e-05,
      "loss": 0.5974,
      "step": 335
    },
    {
      "epoch": 0.672,
      "grad_norm": 0.18037612736225128,
      "learning_rate": 4.664e-05,
      "loss": 0.5918,
      "step": 336
    },
    {
      "epoch": 0.674,
      "grad_norm": 0.1866716593503952,
      "learning_rate": 4.663e-05,
      "loss": 0.6466,
      "step": 337
    },
    {
      "epoch": 0.676,
      "grad_norm": 0.20922498404979706,
      "learning_rate": 4.6620000000000004e-05,
      "loss": 0.651,
      "step": 338
    },
    {
      "epoch": 0.678,
      "grad_norm": 0.18638573586940765,
      "learning_rate": 4.661e-05,
      "loss": 0.5522,
      "step": 339
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.2101825624704361,
      "learning_rate": 4.660000000000001e-05,
      "loss": 0.6816,
      "step": 340
    },
    {
      "epoch": 0.682,
      "grad_norm": 0.17060095071792603,
      "learning_rate": 4.659e-05,
      "loss": 0.6462,
      "step": 341
    },
    {
      "epoch": 0.684,
      "grad_norm": 0.1735481470823288,
      "learning_rate": 4.6580000000000005e-05,
      "loss": 0.6128,
      "step": 342
    },
    {
      "epoch": 0.686,
      "grad_norm": 0.1967155635356903,
      "learning_rate": 4.657e-05,
      "loss": 0.597,
      "step": 343
    },
    {
      "epoch": 0.688,
      "grad_norm": 0.18372522294521332,
      "learning_rate": 4.656e-05,
      "loss": 0.6613,
      "step": 344
    },
    {
      "epoch": 0.69,
      "grad_norm": 0.16918990015983582,
      "learning_rate": 4.655000000000001e-05,
      "loss": 0.5559,
      "step": 345
    },
    {
      "epoch": 0.692,
      "grad_norm": 0.1488986760377884,
      "learning_rate": 4.654e-05,
      "loss": 0.5447,
      "step": 346
    },
    {
      "epoch": 0.694,
      "grad_norm": 0.1725722849369049,
      "learning_rate": 4.6530000000000003e-05,
      "loss": 0.6245,
      "step": 347
    },
    {
      "epoch": 0.696,
      "grad_norm": 0.17919033765792847,
      "learning_rate": 4.652e-05,
      "loss": 0.5695,
      "step": 348
    },
    {
      "epoch": 0.698,
      "grad_norm": 0.1841966211795807,
      "learning_rate": 4.651e-05,
      "loss": 0.5604,
      "step": 349
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.22056150436401367,
      "learning_rate": 4.6500000000000005e-05,
      "loss": 0.6476,
      "step": 350
    },
    {
      "epoch": 0.702,
      "grad_norm": 0.2027232050895691,
      "learning_rate": 4.649e-05,
      "loss": 0.5757,
      "step": 351
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.18255826830863953,
      "learning_rate": 4.648e-05,
      "loss": 0.637,
      "step": 352
    },
    {
      "epoch": 0.706,
      "grad_norm": 0.19408002495765686,
      "learning_rate": 4.647e-05,
      "loss": 0.6453,
      "step": 353
    },
    {
      "epoch": 0.708,
      "grad_norm": 0.1874883621931076,
      "learning_rate": 4.6460000000000006e-05,
      "loss": 0.4938,
      "step": 354
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.20282092690467834,
      "learning_rate": 4.6450000000000004e-05,
      "loss": 0.594,
      "step": 355
    },
    {
      "epoch": 0.712,
      "grad_norm": 0.19063018262386322,
      "learning_rate": 4.644e-05,
      "loss": 0.7343,
      "step": 356
    },
    {
      "epoch": 0.714,
      "grad_norm": 0.1925002485513687,
      "learning_rate": 4.643e-05,
      "loss": 0.6524,
      "step": 357
    },
    {
      "epoch": 0.716,
      "grad_norm": 0.18297319114208221,
      "learning_rate": 4.642e-05,
      "loss": 0.6049,
      "step": 358
    },
    {
      "epoch": 0.718,
      "grad_norm": 0.17188158631324768,
      "learning_rate": 4.6410000000000005e-05,
      "loss": 0.5932,
      "step": 359
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.23126398026943207,
      "learning_rate": 4.64e-05,
      "loss": 0.7189,
      "step": 360
    },
    {
      "epoch": 0.722,
      "grad_norm": 0.21801422536373138,
      "learning_rate": 4.639e-05,
      "loss": 0.642,
      "step": 361
    },
    {
      "epoch": 0.724,
      "grad_norm": 0.19002754986286163,
      "learning_rate": 4.638e-05,
      "loss": 0.6988,
      "step": 362
    },
    {
      "epoch": 0.726,
      "grad_norm": 0.18377232551574707,
      "learning_rate": 4.6370000000000005e-05,
      "loss": 0.652,
      "step": 363
    },
    {
      "epoch": 0.728,
      "grad_norm": 0.1825602501630783,
      "learning_rate": 4.636e-05,
      "loss": 0.578,
      "step": 364
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.17906206846237183,
      "learning_rate": 4.635e-05,
      "loss": 0.5577,
      "step": 365
    },
    {
      "epoch": 0.732,
      "grad_norm": 0.17708086967468262,
      "learning_rate": 4.634e-05,
      "loss": 0.5671,
      "step": 366
    },
    {
      "epoch": 0.734,
      "grad_norm": 0.2228001058101654,
      "learning_rate": 4.633e-05,
      "loss": 0.648,
      "step": 367
    },
    {
      "epoch": 0.736,
      "grad_norm": 0.1861792653799057,
      "learning_rate": 4.6320000000000004e-05,
      "loss": 0.6291,
      "step": 368
    },
    {
      "epoch": 0.738,
      "grad_norm": 0.19840364158153534,
      "learning_rate": 4.631e-05,
      "loss": 0.5629,
      "step": 369
    },
    {
      "epoch": 0.74,
      "grad_norm": 0.204924076795578,
      "learning_rate": 4.630000000000001e-05,
      "loss": 0.7094,
      "step": 370
    },
    {
      "epoch": 0.742,
      "grad_norm": 0.18317362666130066,
      "learning_rate": 4.629e-05,
      "loss": 0.5192,
      "step": 371
    },
    {
      "epoch": 0.744,
      "grad_norm": 0.20287658274173737,
      "learning_rate": 4.6280000000000004e-05,
      "loss": 0.6877,
      "step": 372
    },
    {
      "epoch": 0.746,
      "grad_norm": 0.206755593419075,
      "learning_rate": 4.627e-05,
      "loss": 0.671,
      "step": 373
    },
    {
      "epoch": 0.748,
      "grad_norm": 0.21340832114219666,
      "learning_rate": 4.626e-05,
      "loss": 0.644,
      "step": 374
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.20817971229553223,
      "learning_rate": 4.6250000000000006e-05,
      "loss": 0.7255,
      "step": 375
    },
    {
      "epoch": 0.752,
      "grad_norm": 0.17707408964633942,
      "learning_rate": 4.624e-05,
      "loss": 0.5997,
      "step": 376
    },
    {
      "epoch": 0.754,
      "grad_norm": 0.2087557464838028,
      "learning_rate": 4.623e-05,
      "loss": 0.6961,
      "step": 377
    },
    {
      "epoch": 0.756,
      "grad_norm": 0.1889437437057495,
      "learning_rate": 4.622e-05,
      "loss": 0.5635,
      "step": 378
    },
    {
      "epoch": 0.758,
      "grad_norm": 0.17022623121738434,
      "learning_rate": 4.6210000000000006e-05,
      "loss": 0.5472,
      "step": 379
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.1839427947998047,
      "learning_rate": 4.6200000000000005e-05,
      "loss": 0.5968,
      "step": 380
    },
    {
      "epoch": 0.762,
      "grad_norm": 0.19771188497543335,
      "learning_rate": 4.619e-05,
      "loss": 0.5682,
      "step": 381
    },
    {
      "epoch": 0.764,
      "grad_norm": 0.2051680088043213,
      "learning_rate": 4.618e-05,
      "loss": 0.6268,
      "step": 382
    },
    {
      "epoch": 0.766,
      "grad_norm": 0.2551143765449524,
      "learning_rate": 4.617e-05,
      "loss": 0.6234,
      "step": 383
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.18750117719173431,
      "learning_rate": 4.6160000000000005e-05,
      "loss": 0.7146,
      "step": 384
    },
    {
      "epoch": 0.77,
      "grad_norm": 0.19697488844394684,
      "learning_rate": 4.6150000000000004e-05,
      "loss": 0.654,
      "step": 385
    },
    {
      "epoch": 0.772,
      "grad_norm": 0.20981992781162262,
      "learning_rate": 4.614e-05,
      "loss": 0.5874,
      "step": 386
    },
    {
      "epoch": 0.774,
      "grad_norm": 0.1924438178539276,
      "learning_rate": 4.613e-05,
      "loss": 0.6167,
      "step": 387
    },
    {
      "epoch": 0.776,
      "grad_norm": 0.1714833378791809,
      "learning_rate": 4.612e-05,
      "loss": 0.5145,
      "step": 388
    },
    {
      "epoch": 0.778,
      "grad_norm": 0.17212292551994324,
      "learning_rate": 4.6110000000000004e-05,
      "loss": 0.5355,
      "step": 389
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.20480036735534668,
      "learning_rate": 4.61e-05,
      "loss": 0.6193,
      "step": 390
    },
    {
      "epoch": 0.782,
      "grad_norm": 0.21422697603702545,
      "learning_rate": 4.609e-05,
      "loss": 0.6715,
      "step": 391
    },
    {
      "epoch": 0.784,
      "grad_norm": 0.2247288078069687,
      "learning_rate": 4.608e-05,
      "loss": 0.597,
      "step": 392
    },
    {
      "epoch": 0.786,
      "grad_norm": 0.1962817907333374,
      "learning_rate": 4.6070000000000004e-05,
      "loss": 0.5673,
      "step": 393
    },
    {
      "epoch": 0.788,
      "grad_norm": 0.21063271164894104,
      "learning_rate": 4.606e-05,
      "loss": 0.6286,
      "step": 394
    },
    {
      "epoch": 0.79,
      "grad_norm": 0.21100153028964996,
      "learning_rate": 4.605e-05,
      "loss": 0.6427,
      "step": 395
    },
    {
      "epoch": 0.792,
      "grad_norm": 0.1841425895690918,
      "learning_rate": 4.604e-05,
      "loss": 0.5852,
      "step": 396
    },
    {
      "epoch": 0.794,
      "grad_norm": 0.21620410680770874,
      "learning_rate": 4.603e-05,
      "loss": 0.6688,
      "step": 397
    },
    {
      "epoch": 0.796,
      "grad_norm": 0.2009444534778595,
      "learning_rate": 4.602e-05,
      "loss": 0.5766,
      "step": 398
    },
    {
      "epoch": 0.798,
      "grad_norm": 0.18764597177505493,
      "learning_rate": 4.601e-05,
      "loss": 0.5836,
      "step": 399
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.1796872466802597,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.6051,
      "step": 400
    },
    {
      "epoch": 0.802,
      "grad_norm": 0.18313618004322052,
      "learning_rate": 4.599e-05,
      "loss": 0.5459,
      "step": 401
    },
    {
      "epoch": 0.804,
      "grad_norm": 0.1805708110332489,
      "learning_rate": 4.5980000000000004e-05,
      "loss": 0.5259,
      "step": 402
    },
    {
      "epoch": 0.806,
      "grad_norm": 0.14790281653404236,
      "learning_rate": 4.597e-05,
      "loss": 0.5112,
      "step": 403
    },
    {
      "epoch": 0.808,
      "grad_norm": 0.19898934662342072,
      "learning_rate": 4.596e-05,
      "loss": 0.6487,
      "step": 404
    },
    {
      "epoch": 0.81,
      "grad_norm": 0.2173125445842743,
      "learning_rate": 4.5950000000000006e-05,
      "loss": 0.5429,
      "step": 405
    },
    {
      "epoch": 0.812,
      "grad_norm": 0.22148528695106506,
      "learning_rate": 4.594e-05,
      "loss": 0.6078,
      "step": 406
    },
    {
      "epoch": 0.814,
      "grad_norm": 0.1788310557603836,
      "learning_rate": 4.593e-05,
      "loss": 0.5902,
      "step": 407
    },
    {
      "epoch": 0.816,
      "grad_norm": 0.17214561998844147,
      "learning_rate": 4.592e-05,
      "loss": 0.6102,
      "step": 408
    },
    {
      "epoch": 0.818,
      "grad_norm": 0.20561139285564423,
      "learning_rate": 4.5910000000000006e-05,
      "loss": 0.6989,
      "step": 409
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.1942395567893982,
      "learning_rate": 4.5900000000000004e-05,
      "loss": 0.5499,
      "step": 410
    },
    {
      "epoch": 0.822,
      "grad_norm": 0.2051408886909485,
      "learning_rate": 4.589e-05,
      "loss": 0.5664,
      "step": 411
    },
    {
      "epoch": 0.824,
      "grad_norm": 0.18937014043331146,
      "learning_rate": 4.588e-05,
      "loss": 0.6156,
      "step": 412
    },
    {
      "epoch": 0.826,
      "grad_norm": 0.16688166558742523,
      "learning_rate": 4.587e-05,
      "loss": 0.5419,
      "step": 413
    },
    {
      "epoch": 0.828,
      "grad_norm": 0.15259812772274017,
      "learning_rate": 4.5860000000000005e-05,
      "loss": 0.5237,
      "step": 414
    },
    {
      "epoch": 0.83,
      "grad_norm": 0.18324361741542816,
      "learning_rate": 4.585e-05,
      "loss": 0.5555,
      "step": 415
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.20461533963680267,
      "learning_rate": 4.584e-05,
      "loss": 0.5434,
      "step": 416
    },
    {
      "epoch": 0.834,
      "grad_norm": 0.1844327300786972,
      "learning_rate": 4.583e-05,
      "loss": 0.6336,
      "step": 417
    },
    {
      "epoch": 0.836,
      "grad_norm": 0.18570420145988464,
      "learning_rate": 4.5820000000000005e-05,
      "loss": 0.5067,
      "step": 418
    },
    {
      "epoch": 0.838,
      "grad_norm": 0.21089297533035278,
      "learning_rate": 4.5810000000000004e-05,
      "loss": 0.5911,
      "step": 419
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.21014462411403656,
      "learning_rate": 4.58e-05,
      "loss": 0.6797,
      "step": 420
    },
    {
      "epoch": 0.842,
      "grad_norm": 0.20022115111351013,
      "learning_rate": 4.579e-05,
      "loss": 0.6301,
      "step": 421
    },
    {
      "epoch": 0.844,
      "grad_norm": 0.2022683173418045,
      "learning_rate": 4.578e-05,
      "loss": 0.6682,
      "step": 422
    },
    {
      "epoch": 0.846,
      "grad_norm": 0.19390150904655457,
      "learning_rate": 4.5770000000000004e-05,
      "loss": 0.6788,
      "step": 423
    },
    {
      "epoch": 0.848,
      "grad_norm": 0.18870306015014648,
      "learning_rate": 4.576e-05,
      "loss": 0.656,
      "step": 424
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.1926574409008026,
      "learning_rate": 4.575e-05,
      "loss": 0.6379,
      "step": 425
    },
    {
      "epoch": 0.852,
      "grad_norm": 0.22433732450008392,
      "learning_rate": 4.574e-05,
      "loss": 0.6082,
      "step": 426
    },
    {
      "epoch": 0.854,
      "grad_norm": 0.18340998888015747,
      "learning_rate": 4.573e-05,
      "loss": 0.5933,
      "step": 427
    },
    {
      "epoch": 0.856,
      "grad_norm": 0.19337745010852814,
      "learning_rate": 4.572e-05,
      "loss": 0.5538,
      "step": 428
    },
    {
      "epoch": 0.858,
      "grad_norm": 0.207818865776062,
      "learning_rate": 4.571e-05,
      "loss": 0.6633,
      "step": 429
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.17644749581813812,
      "learning_rate": 4.5700000000000006e-05,
      "loss": 0.6244,
      "step": 430
    },
    {
      "epoch": 0.862,
      "grad_norm": 0.19277946650981903,
      "learning_rate": 4.569e-05,
      "loss": 0.6499,
      "step": 431
    },
    {
      "epoch": 0.864,
      "grad_norm": 0.18463121354579926,
      "learning_rate": 4.568e-05,
      "loss": 0.6349,
      "step": 432
    },
    {
      "epoch": 0.866,
      "grad_norm": 0.1824328601360321,
      "learning_rate": 4.567e-05,
      "loss": 0.5354,
      "step": 433
    },
    {
      "epoch": 0.868,
      "grad_norm": 0.19813786447048187,
      "learning_rate": 4.566e-05,
      "loss": 0.6313,
      "step": 434
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.1948874592781067,
      "learning_rate": 4.5650000000000005e-05,
      "loss": 0.6559,
      "step": 435
    },
    {
      "epoch": 0.872,
      "grad_norm": 0.21239355206489563,
      "learning_rate": 4.564e-05,
      "loss": 0.7408,
      "step": 436
    },
    {
      "epoch": 0.874,
      "grad_norm": 0.19978439807891846,
      "learning_rate": 4.563e-05,
      "loss": 0.6459,
      "step": 437
    },
    {
      "epoch": 0.876,
      "grad_norm": 0.19137194752693176,
      "learning_rate": 4.562e-05,
      "loss": 0.5706,
      "step": 438
    },
    {
      "epoch": 0.878,
      "grad_norm": 0.21602730453014374,
      "learning_rate": 4.5610000000000005e-05,
      "loss": 0.7547,
      "step": 439
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.18226025998592377,
      "learning_rate": 4.5600000000000004e-05,
      "loss": 0.5271,
      "step": 440
    },
    {
      "epoch": 0.882,
      "grad_norm": 0.18746662139892578,
      "learning_rate": 4.559e-05,
      "loss": 0.6545,
      "step": 441
    },
    {
      "epoch": 0.884,
      "grad_norm": 0.19350747764110565,
      "learning_rate": 4.558e-05,
      "loss": 0.4961,
      "step": 442
    },
    {
      "epoch": 0.886,
      "grad_norm": 0.1879873424768448,
      "learning_rate": 4.557e-05,
      "loss": 0.6219,
      "step": 443
    },
    {
      "epoch": 0.888,
      "grad_norm": 0.1813156008720398,
      "learning_rate": 4.5560000000000004e-05,
      "loss": 0.5553,
      "step": 444
    },
    {
      "epoch": 0.89,
      "grad_norm": 0.19688071310520172,
      "learning_rate": 4.555e-05,
      "loss": 0.5252,
      "step": 445
    },
    {
      "epoch": 0.892,
      "grad_norm": 0.21453718841075897,
      "learning_rate": 4.554000000000001e-05,
      "loss": 0.627,
      "step": 446
    },
    {
      "epoch": 0.894,
      "grad_norm": 0.22127218544483185,
      "learning_rate": 4.553e-05,
      "loss": 0.5629,
      "step": 447
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.1822357475757599,
      "learning_rate": 4.5520000000000005e-05,
      "loss": 0.551,
      "step": 448
    },
    {
      "epoch": 0.898,
      "grad_norm": 0.1829032003879547,
      "learning_rate": 4.551e-05,
      "loss": 0.5749,
      "step": 449
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.1852453649044037,
      "learning_rate": 4.55e-05,
      "loss": 0.5672,
      "step": 450
    },
    {
      "epoch": 0.902,
      "grad_norm": 0.20939582586288452,
      "learning_rate": 4.549000000000001e-05,
      "loss": 0.6513,
      "step": 451
    },
    {
      "epoch": 0.904,
      "grad_norm": 0.18649578094482422,
      "learning_rate": 4.548e-05,
      "loss": 0.5475,
      "step": 452
    },
    {
      "epoch": 0.906,
      "grad_norm": 0.17368032038211823,
      "learning_rate": 4.5470000000000003e-05,
      "loss": 0.6117,
      "step": 453
    },
    {
      "epoch": 0.908,
      "grad_norm": 0.20324939489364624,
      "learning_rate": 4.546e-05,
      "loss": 0.4885,
      "step": 454
    },
    {
      "epoch": 0.91,
      "grad_norm": 0.19989271461963654,
      "learning_rate": 4.545000000000001e-05,
      "loss": 0.6796,
      "step": 455
    },
    {
      "epoch": 0.912,
      "grad_norm": 0.23006810247898102,
      "learning_rate": 4.5440000000000005e-05,
      "loss": 0.6818,
      "step": 456
    },
    {
      "epoch": 0.914,
      "grad_norm": 0.20702069997787476,
      "learning_rate": 4.543e-05,
      "loss": 0.6044,
      "step": 457
    },
    {
      "epoch": 0.916,
      "grad_norm": 0.20405983924865723,
      "learning_rate": 4.542e-05,
      "loss": 0.6659,
      "step": 458
    },
    {
      "epoch": 0.918,
      "grad_norm": 0.20356738567352295,
      "learning_rate": 4.541e-05,
      "loss": 0.6003,
      "step": 459
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.20328208804130554,
      "learning_rate": 4.5400000000000006e-05,
      "loss": 0.649,
      "step": 460
    },
    {
      "epoch": 0.922,
      "grad_norm": 0.198821559548378,
      "learning_rate": 4.5390000000000004e-05,
      "loss": 0.5452,
      "step": 461
    },
    {
      "epoch": 0.924,
      "grad_norm": 0.17357122898101807,
      "learning_rate": 4.538e-05,
      "loss": 0.6672,
      "step": 462
    },
    {
      "epoch": 0.926,
      "grad_norm": 0.18239179253578186,
      "learning_rate": 4.537e-05,
      "loss": 0.6415,
      "step": 463
    },
    {
      "epoch": 0.928,
      "grad_norm": 0.21714146435260773,
      "learning_rate": 4.536e-05,
      "loss": 0.6111,
      "step": 464
    },
    {
      "epoch": 0.93,
      "grad_norm": 0.19968821108341217,
      "learning_rate": 4.5350000000000005e-05,
      "loss": 0.6068,
      "step": 465
    },
    {
      "epoch": 0.932,
      "grad_norm": 0.21064497530460358,
      "learning_rate": 4.534e-05,
      "loss": 0.5667,
      "step": 466
    },
    {
      "epoch": 0.934,
      "grad_norm": 0.19035053253173828,
      "learning_rate": 4.533e-05,
      "loss": 0.608,
      "step": 467
    },
    {
      "epoch": 0.936,
      "grad_norm": 0.1872062236070633,
      "learning_rate": 4.532e-05,
      "loss": 0.4219,
      "step": 468
    },
    {
      "epoch": 0.938,
      "grad_norm": 0.21659088134765625,
      "learning_rate": 4.5310000000000005e-05,
      "loss": 0.6364,
      "step": 469
    },
    {
      "epoch": 0.94,
      "grad_norm": 0.2094154953956604,
      "learning_rate": 4.53e-05,
      "loss": 0.609,
      "step": 470
    },
    {
      "epoch": 0.942,
      "grad_norm": 0.19277390837669373,
      "learning_rate": 4.529e-05,
      "loss": 0.5491,
      "step": 471
    },
    {
      "epoch": 0.944,
      "grad_norm": 0.1932992786169052,
      "learning_rate": 4.528e-05,
      "loss": 0.6397,
      "step": 472
    },
    {
      "epoch": 0.946,
      "grad_norm": 0.18232814967632294,
      "learning_rate": 4.527e-05,
      "loss": 0.6154,
      "step": 473
    },
    {
      "epoch": 0.948,
      "grad_norm": 0.21726353466510773,
      "learning_rate": 4.5260000000000004e-05,
      "loss": 0.5741,
      "step": 474
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.1735064834356308,
      "learning_rate": 4.525e-05,
      "loss": 0.5322,
      "step": 475
    },
    {
      "epoch": 0.952,
      "grad_norm": 0.22087444365024567,
      "learning_rate": 4.524000000000001e-05,
      "loss": 0.6378,
      "step": 476
    },
    {
      "epoch": 0.954,
      "grad_norm": 0.2162839025259018,
      "learning_rate": 4.523e-05,
      "loss": 0.5818,
      "step": 477
    },
    {
      "epoch": 0.956,
      "grad_norm": 0.21821214258670807,
      "learning_rate": 4.5220000000000004e-05,
      "loss": 0.6076,
      "step": 478
    },
    {
      "epoch": 0.958,
      "grad_norm": 0.1862291395664215,
      "learning_rate": 4.521e-05,
      "loss": 0.5263,
      "step": 479
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.1847664713859558,
      "learning_rate": 4.52e-05,
      "loss": 0.5983,
      "step": 480
    },
    {
      "epoch": 0.962,
      "grad_norm": 0.18088018894195557,
      "learning_rate": 4.5190000000000006e-05,
      "loss": 0.4899,
      "step": 481
    },
    {
      "epoch": 0.964,
      "grad_norm": 0.22544273734092712,
      "learning_rate": 4.518e-05,
      "loss": 0.6154,
      "step": 482
    },
    {
      "epoch": 0.966,
      "grad_norm": 0.23055431246757507,
      "learning_rate": 4.517e-05,
      "loss": 0.6242,
      "step": 483
    },
    {
      "epoch": 0.968,
      "grad_norm": 0.20244711637496948,
      "learning_rate": 4.516e-05,
      "loss": 0.6026,
      "step": 484
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.21975699067115784,
      "learning_rate": 4.5150000000000006e-05,
      "loss": 0.6892,
      "step": 485
    },
    {
      "epoch": 0.972,
      "grad_norm": 0.18714089691638947,
      "learning_rate": 4.5140000000000005e-05,
      "loss": 0.5943,
      "step": 486
    },
    {
      "epoch": 0.974,
      "grad_norm": 0.21303005516529083,
      "learning_rate": 4.513e-05,
      "loss": 0.5504,
      "step": 487
    },
    {
      "epoch": 0.976,
      "grad_norm": 0.2207714468240738,
      "learning_rate": 4.512e-05,
      "loss": 0.6564,
      "step": 488
    },
    {
      "epoch": 0.978,
      "grad_norm": 0.17340348660945892,
      "learning_rate": 4.511e-05,
      "loss": 0.527,
      "step": 489
    },
    {
      "epoch": 0.98,
      "grad_norm": 0.20630691945552826,
      "learning_rate": 4.5100000000000005e-05,
      "loss": 0.64,
      "step": 490
    },
    {
      "epoch": 0.982,
      "grad_norm": 0.2178223878145218,
      "learning_rate": 4.5090000000000004e-05,
      "loss": 0.6673,
      "step": 491
    },
    {
      "epoch": 0.984,
      "grad_norm": 0.1884588748216629,
      "learning_rate": 4.508e-05,
      "loss": 0.5482,
      "step": 492
    },
    {
      "epoch": 0.986,
      "grad_norm": 0.189361572265625,
      "learning_rate": 4.507e-05,
      "loss": 0.6116,
      "step": 493
    },
    {
      "epoch": 0.988,
      "grad_norm": 0.20682279765605927,
      "learning_rate": 4.506e-05,
      "loss": 0.5871,
      "step": 494
    },
    {
      "epoch": 0.99,
      "grad_norm": 0.22821040451526642,
      "learning_rate": 4.5050000000000004e-05,
      "loss": 0.6539,
      "step": 495
    },
    {
      "epoch": 0.992,
      "grad_norm": 0.21789148449897766,
      "learning_rate": 4.504e-05,
      "loss": 0.6111,
      "step": 496
    },
    {
      "epoch": 0.994,
      "grad_norm": 0.1959594488143921,
      "learning_rate": 4.503e-05,
      "loss": 0.5606,
      "step": 497
    },
    {
      "epoch": 0.996,
      "grad_norm": 0.2024727165699005,
      "learning_rate": 4.502e-05,
      "loss": 0.5868,
      "step": 498
    },
    {
      "epoch": 0.998,
      "grad_norm": 0.2144571989774704,
      "learning_rate": 4.5010000000000004e-05,
      "loss": 0.6423,
      "step": 499
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.1946929693222046,
      "learning_rate": 4.5e-05,
      "loss": 0.6486,
      "step": 500
    },
    {
      "epoch": 1.002,
      "grad_norm": 0.22168385982513428,
      "learning_rate": 4.499e-05,
      "loss": 0.6445,
      "step": 501
    },
    {
      "epoch": 1.004,
      "grad_norm": 0.2581266462802887,
      "learning_rate": 4.498e-05,
      "loss": 0.597,
      "step": 502
    },
    {
      "epoch": 1.006,
      "grad_norm": 0.2223937064409256,
      "learning_rate": 4.497e-05,
      "loss": 0.5913,
      "step": 503
    },
    {
      "epoch": 1.008,
      "grad_norm": 0.19220681488513947,
      "learning_rate": 4.496e-05,
      "loss": 0.5636,
      "step": 504
    },
    {
      "epoch": 1.01,
      "grad_norm": 0.19889682531356812,
      "learning_rate": 4.495e-05,
      "loss": 0.5497,
      "step": 505
    },
    {
      "epoch": 1.012,
      "grad_norm": 0.19532665610313416,
      "learning_rate": 4.494000000000001e-05,
      "loss": 0.6121,
      "step": 506
    },
    {
      "epoch": 1.014,
      "grad_norm": 0.21716678142547607,
      "learning_rate": 4.493e-05,
      "loss": 0.6513,
      "step": 507
    },
    {
      "epoch": 1.016,
      "grad_norm": 0.18669895827770233,
      "learning_rate": 4.4920000000000004e-05,
      "loss": 0.5941,
      "step": 508
    },
    {
      "epoch": 1.018,
      "grad_norm": 0.18874263763427734,
      "learning_rate": 4.491e-05,
      "loss": 0.5748,
      "step": 509
    },
    {
      "epoch": 1.02,
      "grad_norm": 0.2070489227771759,
      "learning_rate": 4.49e-05,
      "loss": 0.6097,
      "step": 510
    },
    {
      "epoch": 1.022,
      "grad_norm": 0.21579885482788086,
      "learning_rate": 4.4890000000000006e-05,
      "loss": 0.5662,
      "step": 511
    },
    {
      "epoch": 1.024,
      "grad_norm": 0.18448017537593842,
      "learning_rate": 4.488e-05,
      "loss": 0.5953,
      "step": 512
    },
    {
      "epoch": 1.026,
      "grad_norm": 0.201309934258461,
      "learning_rate": 4.487e-05,
      "loss": 0.5791,
      "step": 513
    },
    {
      "epoch": 1.028,
      "grad_norm": 0.21169063448905945,
      "learning_rate": 4.486e-05,
      "loss": 0.6305,
      "step": 514
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.18058130145072937,
      "learning_rate": 4.4850000000000006e-05,
      "loss": 0.5972,
      "step": 515
    },
    {
      "epoch": 1.032,
      "grad_norm": 0.2007116824388504,
      "learning_rate": 4.4840000000000004e-05,
      "loss": 0.5788,
      "step": 516
    },
    {
      "epoch": 1.034,
      "grad_norm": 0.21135172247886658,
      "learning_rate": 4.483e-05,
      "loss": 0.62,
      "step": 517
    },
    {
      "epoch": 1.036,
      "grad_norm": 0.19215519726276398,
      "learning_rate": 4.482e-05,
      "loss": 0.5778,
      "step": 518
    },
    {
      "epoch": 1.038,
      "grad_norm": 0.1865689903497696,
      "learning_rate": 4.481e-05,
      "loss": 0.6138,
      "step": 519
    },
    {
      "epoch": 1.04,
      "grad_norm": 0.20218238234519958,
      "learning_rate": 4.4800000000000005e-05,
      "loss": 0.5906,
      "step": 520
    },
    {
      "epoch": 1.042,
      "grad_norm": 0.21387755870819092,
      "learning_rate": 4.479e-05,
      "loss": 0.5725,
      "step": 521
    },
    {
      "epoch": 1.044,
      "grad_norm": 0.19877299666404724,
      "learning_rate": 4.478e-05,
      "loss": 0.5005,
      "step": 522
    },
    {
      "epoch": 1.046,
      "grad_norm": 0.21403655409812927,
      "learning_rate": 4.477e-05,
      "loss": 0.6002,
      "step": 523
    },
    {
      "epoch": 1.048,
      "grad_norm": 0.17705759406089783,
      "learning_rate": 4.4760000000000005e-05,
      "loss": 0.6179,
      "step": 524
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.18957218527793884,
      "learning_rate": 4.4750000000000004e-05,
      "loss": 0.5991,
      "step": 525
    },
    {
      "epoch": 1.052,
      "grad_norm": 0.1773412674665451,
      "learning_rate": 4.474e-05,
      "loss": 0.591,
      "step": 526
    },
    {
      "epoch": 1.054,
      "grad_norm": 0.20133773982524872,
      "learning_rate": 4.473e-05,
      "loss": 0.5994,
      "step": 527
    },
    {
      "epoch": 1.056,
      "grad_norm": 0.20997783541679382,
      "learning_rate": 4.472e-05,
      "loss": 0.5802,
      "step": 528
    },
    {
      "epoch": 1.058,
      "grad_norm": 0.17510485649108887,
      "learning_rate": 4.4710000000000004e-05,
      "loss": 0.6102,
      "step": 529
    },
    {
      "epoch": 1.06,
      "grad_norm": 0.19752104580402374,
      "learning_rate": 4.47e-05,
      "loss": 0.7215,
      "step": 530
    },
    {
      "epoch": 1.062,
      "grad_norm": 0.2410070151090622,
      "learning_rate": 4.469e-05,
      "loss": 0.6564,
      "step": 531
    },
    {
      "epoch": 1.064,
      "grad_norm": 0.21721455454826355,
      "learning_rate": 4.468e-05,
      "loss": 0.548,
      "step": 532
    },
    {
      "epoch": 1.066,
      "grad_norm": 0.23381918668746948,
      "learning_rate": 4.467e-05,
      "loss": 0.66,
      "step": 533
    },
    {
      "epoch": 1.068,
      "grad_norm": 0.1823287308216095,
      "learning_rate": 4.466e-05,
      "loss": 0.521,
      "step": 534
    },
    {
      "epoch": 1.07,
      "grad_norm": 0.20097286999225616,
      "learning_rate": 4.465e-05,
      "loss": 0.5167,
      "step": 535
    },
    {
      "epoch": 1.072,
      "grad_norm": 0.19682855904102325,
      "learning_rate": 4.4640000000000006e-05,
      "loss": 0.5618,
      "step": 536
    },
    {
      "epoch": 1.074,
      "grad_norm": 0.2131110429763794,
      "learning_rate": 4.463e-05,
      "loss": 0.7303,
      "step": 537
    },
    {
      "epoch": 1.076,
      "grad_norm": 0.2144109010696411,
      "learning_rate": 4.462e-05,
      "loss": 0.6177,
      "step": 538
    },
    {
      "epoch": 1.078,
      "grad_norm": 0.19851645827293396,
      "learning_rate": 4.461e-05,
      "loss": 0.6451,
      "step": 539
    },
    {
      "epoch": 1.08,
      "grad_norm": 0.19800704717636108,
      "learning_rate": 4.46e-05,
      "loss": 0.6469,
      "step": 540
    },
    {
      "epoch": 1.082,
      "grad_norm": 0.19389107823371887,
      "learning_rate": 4.4590000000000005e-05,
      "loss": 0.6013,
      "step": 541
    },
    {
      "epoch": 1.084,
      "grad_norm": 0.20725345611572266,
      "learning_rate": 4.458e-05,
      "loss": 0.5639,
      "step": 542
    },
    {
      "epoch": 1.086,
      "grad_norm": 0.20398126542568207,
      "learning_rate": 4.457e-05,
      "loss": 0.7066,
      "step": 543
    },
    {
      "epoch": 1.088,
      "grad_norm": 0.23301570117473602,
      "learning_rate": 4.456e-05,
      "loss": 0.683,
      "step": 544
    },
    {
      "epoch": 1.09,
      "grad_norm": 0.18302753567695618,
      "learning_rate": 4.4550000000000005e-05,
      "loss": 0.5672,
      "step": 545
    },
    {
      "epoch": 1.092,
      "grad_norm": 0.19786565005779266,
      "learning_rate": 4.4540000000000004e-05,
      "loss": 0.6621,
      "step": 546
    },
    {
      "epoch": 1.094,
      "grad_norm": 0.19150419533252716,
      "learning_rate": 4.453e-05,
      "loss": 0.5648,
      "step": 547
    },
    {
      "epoch": 1.096,
      "grad_norm": 0.20977294445037842,
      "learning_rate": 4.452e-05,
      "loss": 0.5941,
      "step": 548
    },
    {
      "epoch": 1.098,
      "grad_norm": 0.19033905863761902,
      "learning_rate": 4.451e-05,
      "loss": 0.5862,
      "step": 549
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.17870080471038818,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.5119,
      "step": 550
    },
    {
      "epoch": 1.102,
      "grad_norm": 0.19028523564338684,
      "learning_rate": 4.449e-05,
      "loss": 0.6146,
      "step": 551
    },
    {
      "epoch": 1.104,
      "grad_norm": 0.20481224358081818,
      "learning_rate": 4.448e-05,
      "loss": 0.6182,
      "step": 552
    },
    {
      "epoch": 1.106,
      "grad_norm": 0.5263721942901611,
      "learning_rate": 4.447e-05,
      "loss": 0.6316,
      "step": 553
    },
    {
      "epoch": 1.108,
      "grad_norm": 0.20338623225688934,
      "learning_rate": 4.4460000000000005e-05,
      "loss": 0.6326,
      "step": 554
    },
    {
      "epoch": 1.11,
      "grad_norm": 0.1929793357849121,
      "learning_rate": 4.445e-05,
      "loss": 0.5357,
      "step": 555
    },
    {
      "epoch": 1.112,
      "grad_norm": 0.2107112854719162,
      "learning_rate": 4.444e-05,
      "loss": 0.6165,
      "step": 556
    },
    {
      "epoch": 1.114,
      "grad_norm": 0.2129804641008377,
      "learning_rate": 4.443e-05,
      "loss": 0.6724,
      "step": 557
    },
    {
      "epoch": 1.116,
      "grad_norm": 0.20006398856639862,
      "learning_rate": 4.442e-05,
      "loss": 0.5899,
      "step": 558
    },
    {
      "epoch": 1.1179999999999999,
      "grad_norm": 0.20823417603969574,
      "learning_rate": 4.4410000000000003e-05,
      "loss": 0.5449,
      "step": 559
    },
    {
      "epoch": 1.12,
      "grad_norm": 0.20882166922092438,
      "learning_rate": 4.44e-05,
      "loss": 0.5296,
      "step": 560
    },
    {
      "epoch": 1.1219999999999999,
      "grad_norm": 0.19584539532661438,
      "learning_rate": 4.439000000000001e-05,
      "loss": 0.5562,
      "step": 561
    },
    {
      "epoch": 1.124,
      "grad_norm": 0.19048091769218445,
      "learning_rate": 4.438e-05,
      "loss": 0.5809,
      "step": 562
    },
    {
      "epoch": 1.126,
      "grad_norm": 0.19735245406627655,
      "learning_rate": 4.4370000000000004e-05,
      "loss": 0.6672,
      "step": 563
    },
    {
      "epoch": 1.1280000000000001,
      "grad_norm": 0.20549283921718597,
      "learning_rate": 4.436e-05,
      "loss": 0.6006,
      "step": 564
    },
    {
      "epoch": 1.13,
      "grad_norm": 0.19877098500728607,
      "learning_rate": 4.435e-05,
      "loss": 0.534,
      "step": 565
    },
    {
      "epoch": 1.1320000000000001,
      "grad_norm": 0.20947475731372833,
      "learning_rate": 4.4340000000000006e-05,
      "loss": 0.5859,
      "step": 566
    },
    {
      "epoch": 1.134,
      "grad_norm": 0.18569184839725494,
      "learning_rate": 4.4330000000000004e-05,
      "loss": 0.5441,
      "step": 567
    },
    {
      "epoch": 1.1360000000000001,
      "grad_norm": 0.1995682269334793,
      "learning_rate": 4.432e-05,
      "loss": 0.5323,
      "step": 568
    },
    {
      "epoch": 1.138,
      "grad_norm": 0.22524245083332062,
      "learning_rate": 4.431e-05,
      "loss": 0.6062,
      "step": 569
    },
    {
      "epoch": 1.1400000000000001,
      "grad_norm": 0.19676834344863892,
      "learning_rate": 4.43e-05,
      "loss": 0.5421,
      "step": 570
    },
    {
      "epoch": 1.142,
      "grad_norm": 0.20001918077468872,
      "learning_rate": 4.4290000000000005e-05,
      "loss": 0.503,
      "step": 571
    },
    {
      "epoch": 1.144,
      "grad_norm": 0.19310520589351654,
      "learning_rate": 4.428e-05,
      "loss": 0.5714,
      "step": 572
    },
    {
      "epoch": 1.146,
      "grad_norm": 0.1684369444847107,
      "learning_rate": 4.427e-05,
      "loss": 0.4657,
      "step": 573
    },
    {
      "epoch": 1.148,
      "grad_norm": 0.2464480698108673,
      "learning_rate": 4.426e-05,
      "loss": 0.6095,
      "step": 574
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.21196356415748596,
      "learning_rate": 4.4250000000000005e-05,
      "loss": 0.486,
      "step": 575
    },
    {
      "epoch": 1.152,
      "grad_norm": 0.18600516021251678,
      "learning_rate": 4.424e-05,
      "loss": 0.588,
      "step": 576
    },
    {
      "epoch": 1.154,
      "grad_norm": 0.19391140341758728,
      "learning_rate": 4.423e-05,
      "loss": 0.5791,
      "step": 577
    },
    {
      "epoch": 1.156,
      "grad_norm": 0.20038722455501556,
      "learning_rate": 4.422e-05,
      "loss": 0.5251,
      "step": 578
    },
    {
      "epoch": 1.158,
      "grad_norm": 0.17348361015319824,
      "learning_rate": 4.421e-05,
      "loss": 0.5648,
      "step": 579
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.2228512465953827,
      "learning_rate": 4.4200000000000004e-05,
      "loss": 0.5741,
      "step": 580
    },
    {
      "epoch": 1.162,
      "grad_norm": 0.1962224692106247,
      "learning_rate": 4.419e-05,
      "loss": 0.5391,
      "step": 581
    },
    {
      "epoch": 1.164,
      "grad_norm": 0.20475374162197113,
      "learning_rate": 4.418000000000001e-05,
      "loss": 0.6273,
      "step": 582
    },
    {
      "epoch": 1.166,
      "grad_norm": 0.20558544993400574,
      "learning_rate": 4.417e-05,
      "loss": 0.6236,
      "step": 583
    },
    {
      "epoch": 1.168,
      "grad_norm": 0.23516933619976044,
      "learning_rate": 4.4160000000000004e-05,
      "loss": 0.5887,
      "step": 584
    },
    {
      "epoch": 1.17,
      "grad_norm": 0.20617741346359253,
      "learning_rate": 4.415e-05,
      "loss": 0.617,
      "step": 585
    },
    {
      "epoch": 1.172,
      "grad_norm": 0.216308131814003,
      "learning_rate": 4.414e-05,
      "loss": 0.6356,
      "step": 586
    },
    {
      "epoch": 1.174,
      "grad_norm": 0.19473914802074432,
      "learning_rate": 4.4130000000000006e-05,
      "loss": 0.5473,
      "step": 587
    },
    {
      "epoch": 1.176,
      "grad_norm": 0.20949441194534302,
      "learning_rate": 4.412e-05,
      "loss": 0.5388,
      "step": 588
    },
    {
      "epoch": 1.178,
      "grad_norm": 0.21411944925785065,
      "learning_rate": 4.411e-05,
      "loss": 0.6231,
      "step": 589
    },
    {
      "epoch": 1.18,
      "grad_norm": 0.18295326828956604,
      "learning_rate": 4.41e-05,
      "loss": 0.5703,
      "step": 590
    },
    {
      "epoch": 1.182,
      "grad_norm": 0.20706209540367126,
      "learning_rate": 4.4090000000000006e-05,
      "loss": 0.6102,
      "step": 591
    },
    {
      "epoch": 1.184,
      "grad_norm": 0.19791294634342194,
      "learning_rate": 4.4080000000000005e-05,
      "loss": 0.5409,
      "step": 592
    },
    {
      "epoch": 1.186,
      "grad_norm": 0.2113964557647705,
      "learning_rate": 4.407e-05,
      "loss": 0.5932,
      "step": 593
    },
    {
      "epoch": 1.188,
      "grad_norm": 0.17157748341560364,
      "learning_rate": 4.406e-05,
      "loss": 0.5442,
      "step": 594
    },
    {
      "epoch": 1.19,
      "grad_norm": 0.2267071008682251,
      "learning_rate": 4.405e-05,
      "loss": 0.6715,
      "step": 595
    },
    {
      "epoch": 1.192,
      "grad_norm": 0.22745326161384583,
      "learning_rate": 4.4040000000000005e-05,
      "loss": 0.6379,
      "step": 596
    },
    {
      "epoch": 1.194,
      "grad_norm": 0.19248466193675995,
      "learning_rate": 4.4030000000000004e-05,
      "loss": 0.5462,
      "step": 597
    },
    {
      "epoch": 1.196,
      "grad_norm": 0.1977124959230423,
      "learning_rate": 4.402e-05,
      "loss": 0.5127,
      "step": 598
    },
    {
      "epoch": 1.198,
      "grad_norm": 0.2224949151277542,
      "learning_rate": 4.401e-05,
      "loss": 0.6466,
      "step": 599
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.2159275859594345,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6082,
      "step": 600
    },
    {
      "epoch": 1.202,
      "grad_norm": 0.20515945553779602,
      "learning_rate": 4.3990000000000004e-05,
      "loss": 0.5903,
      "step": 601
    },
    {
      "epoch": 1.204,
      "grad_norm": 0.19639264047145844,
      "learning_rate": 4.398e-05,
      "loss": 0.5765,
      "step": 602
    },
    {
      "epoch": 1.206,
      "grad_norm": 0.22909431159496307,
      "learning_rate": 4.397e-05,
      "loss": 0.6025,
      "step": 603
    },
    {
      "epoch": 1.208,
      "grad_norm": 0.2259034514427185,
      "learning_rate": 4.396e-05,
      "loss": 0.6427,
      "step": 604
    },
    {
      "epoch": 1.21,
      "grad_norm": 0.19979901611804962,
      "learning_rate": 4.3950000000000004e-05,
      "loss": 0.5271,
      "step": 605
    },
    {
      "epoch": 1.212,
      "grad_norm": 0.21502630412578583,
      "learning_rate": 4.394e-05,
      "loss": 0.5954,
      "step": 606
    },
    {
      "epoch": 1.214,
      "grad_norm": 0.20371314883232117,
      "learning_rate": 4.393e-05,
      "loss": 0.5828,
      "step": 607
    },
    {
      "epoch": 1.216,
      "grad_norm": 0.21107852458953857,
      "learning_rate": 4.392e-05,
      "loss": 0.6029,
      "step": 608
    },
    {
      "epoch": 1.218,
      "grad_norm": 0.17909643054008484,
      "learning_rate": 4.391e-05,
      "loss": 0.6587,
      "step": 609
    },
    {
      "epoch": 1.22,
      "grad_norm": 0.21194545924663544,
      "learning_rate": 4.39e-05,
      "loss": 0.5606,
      "step": 610
    },
    {
      "epoch": 1.222,
      "grad_norm": 0.18832319974899292,
      "learning_rate": 4.389e-05,
      "loss": 0.5733,
      "step": 611
    },
    {
      "epoch": 1.224,
      "grad_norm": 0.21508416533470154,
      "learning_rate": 4.388000000000001e-05,
      "loss": 0.5837,
      "step": 612
    },
    {
      "epoch": 1.226,
      "grad_norm": 0.21378885209560394,
      "learning_rate": 4.387e-05,
      "loss": 0.5558,
      "step": 613
    },
    {
      "epoch": 1.228,
      "grad_norm": 0.24820692837238312,
      "learning_rate": 4.3860000000000004e-05,
      "loss": 0.6971,
      "step": 614
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.1849009394645691,
      "learning_rate": 4.385e-05,
      "loss": 0.5712,
      "step": 615
    },
    {
      "epoch": 1.232,
      "grad_norm": 0.23946769535541534,
      "learning_rate": 4.384e-05,
      "loss": 0.6747,
      "step": 616
    },
    {
      "epoch": 1.234,
      "grad_norm": 0.220892533659935,
      "learning_rate": 4.3830000000000006e-05,
      "loss": 0.6101,
      "step": 617
    },
    {
      "epoch": 1.236,
      "grad_norm": 0.18981412053108215,
      "learning_rate": 4.382e-05,
      "loss": 0.4892,
      "step": 618
    },
    {
      "epoch": 1.238,
      "grad_norm": 0.23685996234416962,
      "learning_rate": 4.381e-05,
      "loss": 0.5582,
      "step": 619
    },
    {
      "epoch": 1.24,
      "grad_norm": 0.19691988825798035,
      "learning_rate": 4.38e-05,
      "loss": 0.5823,
      "step": 620
    },
    {
      "epoch": 1.242,
      "grad_norm": 0.23621264100074768,
      "learning_rate": 4.3790000000000006e-05,
      "loss": 0.6687,
      "step": 621
    },
    {
      "epoch": 1.244,
      "grad_norm": 0.2227286845445633,
      "learning_rate": 4.3780000000000004e-05,
      "loss": 0.6677,
      "step": 622
    },
    {
      "epoch": 1.246,
      "grad_norm": 0.20094943046569824,
      "learning_rate": 4.377e-05,
      "loss": 0.5783,
      "step": 623
    },
    {
      "epoch": 1.248,
      "grad_norm": 0.2083892971277237,
      "learning_rate": 4.376e-05,
      "loss": 0.559,
      "step": 624
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.21730823814868927,
      "learning_rate": 4.375e-05,
      "loss": 0.542,
      "step": 625
    },
    {
      "epoch": 1.252,
      "grad_norm": 0.21850605309009552,
      "learning_rate": 4.3740000000000005e-05,
      "loss": 0.6211,
      "step": 626
    },
    {
      "epoch": 1.254,
      "grad_norm": 0.20119699835777283,
      "learning_rate": 4.373e-05,
      "loss": 0.5272,
      "step": 627
    },
    {
      "epoch": 1.256,
      "grad_norm": 0.23064668476581573,
      "learning_rate": 4.372e-05,
      "loss": 0.6462,
      "step": 628
    },
    {
      "epoch": 1.258,
      "grad_norm": 0.21558353304862976,
      "learning_rate": 4.371e-05,
      "loss": 0.5547,
      "step": 629
    },
    {
      "epoch": 1.26,
      "grad_norm": 0.25317391753196716,
      "learning_rate": 4.3700000000000005e-05,
      "loss": 0.6799,
      "step": 630
    },
    {
      "epoch": 1.262,
      "grad_norm": 0.1989932358264923,
      "learning_rate": 4.3690000000000004e-05,
      "loss": 0.5812,
      "step": 631
    },
    {
      "epoch": 1.264,
      "grad_norm": 0.21172182261943817,
      "learning_rate": 4.368e-05,
      "loss": 0.62,
      "step": 632
    },
    {
      "epoch": 1.266,
      "grad_norm": 0.21126477420330048,
      "learning_rate": 4.367e-05,
      "loss": 0.5217,
      "step": 633
    },
    {
      "epoch": 1.268,
      "grad_norm": 0.20479610562324524,
      "learning_rate": 4.366e-05,
      "loss": 0.6741,
      "step": 634
    },
    {
      "epoch": 1.27,
      "grad_norm": 0.2281307876110077,
      "learning_rate": 4.3650000000000004e-05,
      "loss": 0.5584,
      "step": 635
    },
    {
      "epoch": 1.272,
      "grad_norm": 0.20038704574108124,
      "learning_rate": 4.364e-05,
      "loss": 0.5471,
      "step": 636
    },
    {
      "epoch": 1.274,
      "grad_norm": 0.21315504610538483,
      "learning_rate": 4.363000000000001e-05,
      "loss": 0.5367,
      "step": 637
    },
    {
      "epoch": 1.276,
      "grad_norm": 0.20510873198509216,
      "learning_rate": 4.362e-05,
      "loss": 0.6416,
      "step": 638
    },
    {
      "epoch": 1.278,
      "grad_norm": 0.18110395967960358,
      "learning_rate": 4.361e-05,
      "loss": 0.6165,
      "step": 639
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.19763672351837158,
      "learning_rate": 4.36e-05,
      "loss": 0.548,
      "step": 640
    },
    {
      "epoch": 1.282,
      "grad_norm": 0.22199787199497223,
      "learning_rate": 4.359e-05,
      "loss": 0.5948,
      "step": 641
    },
    {
      "epoch": 1.284,
      "grad_norm": 0.21400614082813263,
      "learning_rate": 4.3580000000000006e-05,
      "loss": 0.476,
      "step": 642
    },
    {
      "epoch": 1.286,
      "grad_norm": 0.1921880692243576,
      "learning_rate": 4.357e-05,
      "loss": 0.5716,
      "step": 643
    },
    {
      "epoch": 1.288,
      "grad_norm": 0.1940234899520874,
      "learning_rate": 4.356e-05,
      "loss": 0.621,
      "step": 644
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.22476941347122192,
      "learning_rate": 4.355e-05,
      "loss": 0.586,
      "step": 645
    },
    {
      "epoch": 1.292,
      "grad_norm": 0.199696347117424,
      "learning_rate": 4.354e-05,
      "loss": 0.6177,
      "step": 646
    },
    {
      "epoch": 1.294,
      "grad_norm": 0.19897620379924774,
      "learning_rate": 4.3530000000000005e-05,
      "loss": 0.5981,
      "step": 647
    },
    {
      "epoch": 1.296,
      "grad_norm": 0.18877290189266205,
      "learning_rate": 4.352e-05,
      "loss": 0.5264,
      "step": 648
    },
    {
      "epoch": 1.298,
      "grad_norm": 0.1996156871318817,
      "learning_rate": 4.351e-05,
      "loss": 0.5537,
      "step": 649
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.19752252101898193,
      "learning_rate": 4.35e-05,
      "loss": 0.5518,
      "step": 650
    },
    {
      "epoch": 1.302,
      "grad_norm": 0.19172196090221405,
      "learning_rate": 4.3490000000000005e-05,
      "loss": 0.517,
      "step": 651
    },
    {
      "epoch": 1.304,
      "grad_norm": 0.1916598230600357,
      "learning_rate": 4.3480000000000004e-05,
      "loss": 0.6194,
      "step": 652
    },
    {
      "epoch": 1.306,
      "grad_norm": 0.2249755561351776,
      "learning_rate": 4.347e-05,
      "loss": 0.5648,
      "step": 653
    },
    {
      "epoch": 1.308,
      "grad_norm": 0.21257826685905457,
      "learning_rate": 4.346e-05,
      "loss": 0.5851,
      "step": 654
    },
    {
      "epoch": 1.31,
      "grad_norm": 0.22375406324863434,
      "learning_rate": 4.345e-05,
      "loss": 0.563,
      "step": 655
    },
    {
      "epoch": 1.312,
      "grad_norm": 0.2560722827911377,
      "learning_rate": 4.3440000000000004e-05,
      "loss": 0.7102,
      "step": 656
    },
    {
      "epoch": 1.314,
      "grad_norm": 0.2261979579925537,
      "learning_rate": 4.343e-05,
      "loss": 0.6269,
      "step": 657
    },
    {
      "epoch": 1.316,
      "grad_norm": 0.22072796523571014,
      "learning_rate": 4.342e-05,
      "loss": 0.585,
      "step": 658
    },
    {
      "epoch": 1.318,
      "grad_norm": 0.2084806263446808,
      "learning_rate": 4.341e-05,
      "loss": 0.5933,
      "step": 659
    },
    {
      "epoch": 1.32,
      "grad_norm": 0.1984473168849945,
      "learning_rate": 4.3400000000000005e-05,
      "loss": 0.5641,
      "step": 660
    },
    {
      "epoch": 1.322,
      "grad_norm": 0.20633773505687714,
      "learning_rate": 4.339e-05,
      "loss": 0.6262,
      "step": 661
    },
    {
      "epoch": 1.324,
      "grad_norm": 0.1869378536939621,
      "learning_rate": 4.338e-05,
      "loss": 0.4613,
      "step": 662
    },
    {
      "epoch": 1.326,
      "grad_norm": 0.19371822476387024,
      "learning_rate": 4.337e-05,
      "loss": 0.6016,
      "step": 663
    },
    {
      "epoch": 1.328,
      "grad_norm": 0.22572529315948486,
      "learning_rate": 4.336e-05,
      "loss": 0.6891,
      "step": 664
    },
    {
      "epoch": 1.33,
      "grad_norm": 0.19980907440185547,
      "learning_rate": 4.335e-05,
      "loss": 0.5174,
      "step": 665
    },
    {
      "epoch": 1.332,
      "grad_norm": 0.1863400638103485,
      "learning_rate": 4.334e-05,
      "loss": 0.5886,
      "step": 666
    },
    {
      "epoch": 1.334,
      "grad_norm": 0.2504555583000183,
      "learning_rate": 4.333000000000001e-05,
      "loss": 0.5608,
      "step": 667
    },
    {
      "epoch": 1.336,
      "grad_norm": 0.23737183213233948,
      "learning_rate": 4.332e-05,
      "loss": 0.6351,
      "step": 668
    },
    {
      "epoch": 1.338,
      "grad_norm": 0.24397732317447662,
      "learning_rate": 4.3310000000000004e-05,
      "loss": 0.6332,
      "step": 669
    },
    {
      "epoch": 1.34,
      "grad_norm": 0.186910942196846,
      "learning_rate": 4.33e-05,
      "loss": 0.4916,
      "step": 670
    },
    {
      "epoch": 1.342,
      "grad_norm": 0.2204650193452835,
      "learning_rate": 4.329e-05,
      "loss": 0.6193,
      "step": 671
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 0.20329062640666962,
      "learning_rate": 4.3280000000000006e-05,
      "loss": 0.6311,
      "step": 672
    },
    {
      "epoch": 1.346,
      "grad_norm": 0.17689010500907898,
      "learning_rate": 4.327e-05,
      "loss": 0.5129,
      "step": 673
    },
    {
      "epoch": 1.3479999999999999,
      "grad_norm": 0.19227999448776245,
      "learning_rate": 4.326e-05,
      "loss": 0.585,
      "step": 674
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.2173619568347931,
      "learning_rate": 4.325e-05,
      "loss": 0.5513,
      "step": 675
    },
    {
      "epoch": 1.3519999999999999,
      "grad_norm": 0.21630556881427765,
      "learning_rate": 4.324e-05,
      "loss": 0.612,
      "step": 676
    },
    {
      "epoch": 1.354,
      "grad_norm": 0.23232296109199524,
      "learning_rate": 4.3230000000000005e-05,
      "loss": 0.6401,
      "step": 677
    },
    {
      "epoch": 1.3559999999999999,
      "grad_norm": 0.2330378144979477,
      "learning_rate": 4.3219999999999996e-05,
      "loss": 0.7614,
      "step": 678
    },
    {
      "epoch": 1.358,
      "grad_norm": 0.1954951286315918,
      "learning_rate": 4.321e-05,
      "loss": 0.5531,
      "step": 679
    },
    {
      "epoch": 1.3599999999999999,
      "grad_norm": 0.1955898106098175,
      "learning_rate": 4.32e-05,
      "loss": 0.4924,
      "step": 680
    },
    {
      "epoch": 1.362,
      "grad_norm": 0.2058050036430359,
      "learning_rate": 4.3190000000000005e-05,
      "loss": 0.5021,
      "step": 681
    },
    {
      "epoch": 1.3639999999999999,
      "grad_norm": 0.263340562582016,
      "learning_rate": 4.318e-05,
      "loss": 0.567,
      "step": 682
    },
    {
      "epoch": 1.366,
      "grad_norm": 0.20733140408992767,
      "learning_rate": 4.317e-05,
      "loss": 0.6279,
      "step": 683
    },
    {
      "epoch": 1.3679999999999999,
      "grad_norm": 0.22644178569316864,
      "learning_rate": 4.316e-05,
      "loss": 0.5664,
      "step": 684
    },
    {
      "epoch": 1.37,
      "grad_norm": 0.27613282203674316,
      "learning_rate": 4.315e-05,
      "loss": 0.5829,
      "step": 685
    },
    {
      "epoch": 1.3719999999999999,
      "grad_norm": 0.19206145405769348,
      "learning_rate": 4.3140000000000004e-05,
      "loss": 0.5515,
      "step": 686
    },
    {
      "epoch": 1.374,
      "grad_norm": 0.25372427701950073,
      "learning_rate": 4.313e-05,
      "loss": 0.6937,
      "step": 687
    },
    {
      "epoch": 1.376,
      "grad_norm": 0.22427460551261902,
      "learning_rate": 4.312000000000001e-05,
      "loss": 0.6961,
      "step": 688
    },
    {
      "epoch": 1.3780000000000001,
      "grad_norm": 0.22864195704460144,
      "learning_rate": 4.311e-05,
      "loss": 0.7201,
      "step": 689
    },
    {
      "epoch": 1.38,
      "grad_norm": 0.15411259233951569,
      "learning_rate": 4.3100000000000004e-05,
      "loss": 0.3898,
      "step": 690
    },
    {
      "epoch": 1.3820000000000001,
      "grad_norm": 0.21335478127002716,
      "learning_rate": 4.309e-05,
      "loss": 0.6347,
      "step": 691
    },
    {
      "epoch": 1.384,
      "grad_norm": 0.1923125833272934,
      "learning_rate": 4.308e-05,
      "loss": 0.6299,
      "step": 692
    },
    {
      "epoch": 1.3860000000000001,
      "grad_norm": 0.20960748195648193,
      "learning_rate": 4.3070000000000006e-05,
      "loss": 0.606,
      "step": 693
    },
    {
      "epoch": 1.388,
      "grad_norm": 0.20630641281604767,
      "learning_rate": 4.306e-05,
      "loss": 0.5883,
      "step": 694
    },
    {
      "epoch": 1.3900000000000001,
      "grad_norm": 0.1649722456932068,
      "learning_rate": 4.305e-05,
      "loss": 0.4467,
      "step": 695
    },
    {
      "epoch": 1.392,
      "grad_norm": 0.21387261152267456,
      "learning_rate": 4.304e-05,
      "loss": 0.6852,
      "step": 696
    },
    {
      "epoch": 1.3940000000000001,
      "grad_norm": 0.22639335691928864,
      "learning_rate": 4.3030000000000006e-05,
      "loss": 0.542,
      "step": 697
    },
    {
      "epoch": 1.396,
      "grad_norm": 0.21238407492637634,
      "learning_rate": 4.3020000000000005e-05,
      "loss": 0.6011,
      "step": 698
    },
    {
      "epoch": 1.3980000000000001,
      "grad_norm": 0.2178695648908615,
      "learning_rate": 4.301e-05,
      "loss": 0.5566,
      "step": 699
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.1901402771472931,
      "learning_rate": 4.3e-05,
      "loss": 0.5757,
      "step": 700
    },
    {
      "epoch": 1.4020000000000001,
      "grad_norm": 0.2045552283525467,
      "learning_rate": 4.299e-05,
      "loss": 0.5678,
      "step": 701
    },
    {
      "epoch": 1.404,
      "grad_norm": 0.19475097954273224,
      "learning_rate": 4.2980000000000005e-05,
      "loss": 0.588,
      "step": 702
    },
    {
      "epoch": 1.4060000000000001,
      "grad_norm": 0.2065313756465912,
      "learning_rate": 4.2970000000000004e-05,
      "loss": 0.6748,
      "step": 703
    },
    {
      "epoch": 1.408,
      "grad_norm": 0.2813938558101654,
      "learning_rate": 4.296e-05,
      "loss": 0.601,
      "step": 704
    },
    {
      "epoch": 1.41,
      "grad_norm": 0.23802025616168976,
      "learning_rate": 4.295e-05,
      "loss": 0.7323,
      "step": 705
    },
    {
      "epoch": 1.412,
      "grad_norm": 0.23389388620853424,
      "learning_rate": 4.2940000000000006e-05,
      "loss": 0.5336,
      "step": 706
    },
    {
      "epoch": 1.414,
      "grad_norm": 0.21070720255374908,
      "learning_rate": 4.2930000000000004e-05,
      "loss": 0.6171,
      "step": 707
    },
    {
      "epoch": 1.416,
      "grad_norm": 0.21459278464317322,
      "learning_rate": 4.292e-05,
      "loss": 0.5903,
      "step": 708
    },
    {
      "epoch": 1.418,
      "grad_norm": 0.21212553977966309,
      "learning_rate": 4.291e-05,
      "loss": 0.6458,
      "step": 709
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.212654247879982,
      "learning_rate": 4.29e-05,
      "loss": 0.5955,
      "step": 710
    },
    {
      "epoch": 1.422,
      "grad_norm": 0.20657028257846832,
      "learning_rate": 4.2890000000000004e-05,
      "loss": 0.5186,
      "step": 711
    },
    {
      "epoch": 1.424,
      "grad_norm": 0.2148103266954422,
      "learning_rate": 4.288e-05,
      "loss": 0.635,
      "step": 712
    },
    {
      "epoch": 1.426,
      "grad_norm": 0.21794739365577698,
      "learning_rate": 4.287000000000001e-05,
      "loss": 0.5263,
      "step": 713
    },
    {
      "epoch": 1.428,
      "grad_norm": 0.22709821164608002,
      "learning_rate": 4.286e-05,
      "loss": 0.5933,
      "step": 714
    },
    {
      "epoch": 1.43,
      "grad_norm": 0.1945171058177948,
      "learning_rate": 4.285e-05,
      "loss": 0.5093,
      "step": 715
    },
    {
      "epoch": 1.432,
      "grad_norm": 0.2270834892988205,
      "learning_rate": 4.284e-05,
      "loss": 0.5716,
      "step": 716
    },
    {
      "epoch": 1.434,
      "grad_norm": 0.21322421729564667,
      "learning_rate": 4.283e-05,
      "loss": 0.6758,
      "step": 717
    },
    {
      "epoch": 1.436,
      "grad_norm": 0.22180742025375366,
      "learning_rate": 4.282000000000001e-05,
      "loss": 0.6433,
      "step": 718
    },
    {
      "epoch": 1.438,
      "grad_norm": 0.1959298551082611,
      "learning_rate": 4.281e-05,
      "loss": 0.6108,
      "step": 719
    },
    {
      "epoch": 1.44,
      "grad_norm": 0.21371756494045258,
      "learning_rate": 4.2800000000000004e-05,
      "loss": 0.6228,
      "step": 720
    },
    {
      "epoch": 1.442,
      "grad_norm": 0.2120112180709839,
      "learning_rate": 4.279e-05,
      "loss": 0.6034,
      "step": 721
    },
    {
      "epoch": 1.444,
      "grad_norm": 0.20808736979961395,
      "learning_rate": 4.278e-05,
      "loss": 0.6471,
      "step": 722
    },
    {
      "epoch": 1.446,
      "grad_norm": 0.20965223014354706,
      "learning_rate": 4.2770000000000006e-05,
      "loss": 0.5389,
      "step": 723
    },
    {
      "epoch": 1.448,
      "grad_norm": 0.21139630675315857,
      "learning_rate": 4.276e-05,
      "loss": 0.5244,
      "step": 724
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.19360531866550446,
      "learning_rate": 4.275e-05,
      "loss": 0.5875,
      "step": 725
    },
    {
      "epoch": 1.452,
      "grad_norm": 0.21325168013572693,
      "learning_rate": 4.274e-05,
      "loss": 0.5826,
      "step": 726
    },
    {
      "epoch": 1.454,
      "grad_norm": 0.2077636867761612,
      "learning_rate": 4.2730000000000006e-05,
      "loss": 0.6809,
      "step": 727
    },
    {
      "epoch": 1.456,
      "grad_norm": 0.20011232793331146,
      "learning_rate": 4.2720000000000004e-05,
      "loss": 0.4634,
      "step": 728
    },
    {
      "epoch": 1.458,
      "grad_norm": 0.20724835991859436,
      "learning_rate": 4.271e-05,
      "loss": 0.5878,
      "step": 729
    },
    {
      "epoch": 1.46,
      "grad_norm": 0.20728984475135803,
      "learning_rate": 4.27e-05,
      "loss": 0.4541,
      "step": 730
    },
    {
      "epoch": 1.462,
      "grad_norm": 0.23507185280323029,
      "learning_rate": 4.269e-05,
      "loss": 0.6409,
      "step": 731
    },
    {
      "epoch": 1.464,
      "grad_norm": 0.23297451436519623,
      "learning_rate": 4.2680000000000005e-05,
      "loss": 0.6633,
      "step": 732
    },
    {
      "epoch": 1.466,
      "grad_norm": 0.2090078741312027,
      "learning_rate": 4.267e-05,
      "loss": 0.6347,
      "step": 733
    },
    {
      "epoch": 1.468,
      "grad_norm": 0.20409215986728668,
      "learning_rate": 4.266e-05,
      "loss": 0.5472,
      "step": 734
    },
    {
      "epoch": 1.47,
      "grad_norm": 0.21352814137935638,
      "learning_rate": 4.265e-05,
      "loss": 0.6449,
      "step": 735
    },
    {
      "epoch": 1.472,
      "grad_norm": 0.20980428159236908,
      "learning_rate": 4.2640000000000005e-05,
      "loss": 0.6371,
      "step": 736
    },
    {
      "epoch": 1.474,
      "grad_norm": 0.1911533921957016,
      "learning_rate": 4.2630000000000004e-05,
      "loss": 0.5392,
      "step": 737
    },
    {
      "epoch": 1.476,
      "grad_norm": 0.21656915545463562,
      "learning_rate": 4.262e-05,
      "loss": 0.627,
      "step": 738
    },
    {
      "epoch": 1.478,
      "grad_norm": 0.19826734066009521,
      "learning_rate": 4.261e-05,
      "loss": 0.6034,
      "step": 739
    },
    {
      "epoch": 1.48,
      "grad_norm": 0.20627282559871674,
      "learning_rate": 4.26e-05,
      "loss": 0.5495,
      "step": 740
    },
    {
      "epoch": 1.482,
      "grad_norm": 0.24123527109622955,
      "learning_rate": 4.2590000000000004e-05,
      "loss": 0.699,
      "step": 741
    },
    {
      "epoch": 1.484,
      "grad_norm": 0.20298898220062256,
      "learning_rate": 4.258e-05,
      "loss": 0.5217,
      "step": 742
    },
    {
      "epoch": 1.486,
      "grad_norm": 0.218084916472435,
      "learning_rate": 4.257000000000001e-05,
      "loss": 0.603,
      "step": 743
    },
    {
      "epoch": 1.488,
      "grad_norm": 0.22439178824424744,
      "learning_rate": 4.256e-05,
      "loss": 0.5046,
      "step": 744
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.20961345732212067,
      "learning_rate": 4.2550000000000004e-05,
      "loss": 0.5791,
      "step": 745
    },
    {
      "epoch": 1.492,
      "grad_norm": 0.21735183894634247,
      "learning_rate": 4.254e-05,
      "loss": 0.5744,
      "step": 746
    },
    {
      "epoch": 1.494,
      "grad_norm": 0.2141823023557663,
      "learning_rate": 4.253e-05,
      "loss": 0.6365,
      "step": 747
    },
    {
      "epoch": 1.496,
      "grad_norm": 0.19389428198337555,
      "learning_rate": 4.2520000000000006e-05,
      "loss": 0.5767,
      "step": 748
    },
    {
      "epoch": 1.498,
      "grad_norm": 0.24830563366413116,
      "learning_rate": 4.251e-05,
      "loss": 0.6411,
      "step": 749
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.24806180596351624,
      "learning_rate": 4.25e-05,
      "loss": 0.641,
      "step": 750
    },
    {
      "epoch": 1.502,
      "grad_norm": 0.19207115471363068,
      "learning_rate": 4.249e-05,
      "loss": 0.4554,
      "step": 751
    },
    {
      "epoch": 1.504,
      "grad_norm": 0.21739742159843445,
      "learning_rate": 4.248e-05,
      "loss": 0.5802,
      "step": 752
    },
    {
      "epoch": 1.506,
      "grad_norm": 0.20979043841362,
      "learning_rate": 4.2470000000000005e-05,
      "loss": 0.5499,
      "step": 753
    },
    {
      "epoch": 1.508,
      "grad_norm": 0.18834327161312103,
      "learning_rate": 4.246e-05,
      "loss": 0.558,
      "step": 754
    },
    {
      "epoch": 1.51,
      "grad_norm": 0.1966605931520462,
      "learning_rate": 4.245e-05,
      "loss": 0.5573,
      "step": 755
    },
    {
      "epoch": 1.512,
      "grad_norm": 0.2214249223470688,
      "learning_rate": 4.244e-05,
      "loss": 0.5933,
      "step": 756
    },
    {
      "epoch": 1.514,
      "grad_norm": 0.20649488270282745,
      "learning_rate": 4.2430000000000005e-05,
      "loss": 0.486,
      "step": 757
    },
    {
      "epoch": 1.516,
      "grad_norm": 0.23040921986103058,
      "learning_rate": 4.2420000000000004e-05,
      "loss": 0.5451,
      "step": 758
    },
    {
      "epoch": 1.518,
      "grad_norm": 0.19081412255764008,
      "learning_rate": 4.241e-05,
      "loss": 0.6122,
      "step": 759
    },
    {
      "epoch": 1.52,
      "grad_norm": 0.20429189503192902,
      "learning_rate": 4.24e-05,
      "loss": 0.4951,
      "step": 760
    },
    {
      "epoch": 1.522,
      "grad_norm": 0.2081070989370346,
      "learning_rate": 4.239e-05,
      "loss": 0.6102,
      "step": 761
    },
    {
      "epoch": 1.524,
      "grad_norm": 0.19600601494312286,
      "learning_rate": 4.2380000000000004e-05,
      "loss": 0.5609,
      "step": 762
    },
    {
      "epoch": 1.526,
      "grad_norm": 0.22128801047801971,
      "learning_rate": 4.237e-05,
      "loss": 0.514,
      "step": 763
    },
    {
      "epoch": 1.528,
      "grad_norm": 0.21633316576480865,
      "learning_rate": 4.236e-05,
      "loss": 0.5348,
      "step": 764
    },
    {
      "epoch": 1.53,
      "grad_norm": 0.23707932233810425,
      "learning_rate": 4.235e-05,
      "loss": 0.5494,
      "step": 765
    },
    {
      "epoch": 1.532,
      "grad_norm": 0.2444704920053482,
      "learning_rate": 4.2340000000000005e-05,
      "loss": 0.5086,
      "step": 766
    },
    {
      "epoch": 1.534,
      "grad_norm": 0.2355782687664032,
      "learning_rate": 4.233e-05,
      "loss": 0.6334,
      "step": 767
    },
    {
      "epoch": 1.536,
      "grad_norm": 0.20617908239364624,
      "learning_rate": 4.232e-05,
      "loss": 0.5296,
      "step": 768
    },
    {
      "epoch": 1.538,
      "grad_norm": 0.18543358147144318,
      "learning_rate": 4.231e-05,
      "loss": 0.4944,
      "step": 769
    },
    {
      "epoch": 1.54,
      "grad_norm": 0.24593642354011536,
      "learning_rate": 4.23e-05,
      "loss": 0.6141,
      "step": 770
    },
    {
      "epoch": 1.542,
      "grad_norm": 0.21925920248031616,
      "learning_rate": 4.229e-05,
      "loss": 0.5704,
      "step": 771
    },
    {
      "epoch": 1.544,
      "grad_norm": 0.23085656762123108,
      "learning_rate": 4.228e-05,
      "loss": 0.5748,
      "step": 772
    },
    {
      "epoch": 1.546,
      "grad_norm": 0.2114836573600769,
      "learning_rate": 4.227000000000001e-05,
      "loss": 0.5582,
      "step": 773
    },
    {
      "epoch": 1.548,
      "grad_norm": 0.2578122019767761,
      "learning_rate": 4.226e-05,
      "loss": 0.5869,
      "step": 774
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.21830229461193085,
      "learning_rate": 4.2250000000000004e-05,
      "loss": 0.5825,
      "step": 775
    },
    {
      "epoch": 1.552,
      "grad_norm": 0.2558196783065796,
      "learning_rate": 4.224e-05,
      "loss": 0.6324,
      "step": 776
    },
    {
      "epoch": 1.554,
      "grad_norm": 0.19135409593582153,
      "learning_rate": 4.223e-05,
      "loss": 0.5364,
      "step": 777
    },
    {
      "epoch": 1.556,
      "grad_norm": 0.22118104994297028,
      "learning_rate": 4.2220000000000006e-05,
      "loss": 0.5579,
      "step": 778
    },
    {
      "epoch": 1.558,
      "grad_norm": 0.2239237129688263,
      "learning_rate": 4.221e-05,
      "loss": 0.5025,
      "step": 779
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.1993967741727829,
      "learning_rate": 4.22e-05,
      "loss": 0.5327,
      "step": 780
    },
    {
      "epoch": 1.562,
      "grad_norm": 0.20883196592330933,
      "learning_rate": 4.219e-05,
      "loss": 0.6594,
      "step": 781
    },
    {
      "epoch": 1.564,
      "grad_norm": 0.20599497854709625,
      "learning_rate": 4.2180000000000006e-05,
      "loss": 0.591,
      "step": 782
    },
    {
      "epoch": 1.5659999999999998,
      "grad_norm": 0.2093878537416458,
      "learning_rate": 4.2170000000000005e-05,
      "loss": 0.4834,
      "step": 783
    },
    {
      "epoch": 1.568,
      "grad_norm": 0.24116116762161255,
      "learning_rate": 4.2159999999999996e-05,
      "loss": 0.5273,
      "step": 784
    },
    {
      "epoch": 1.5699999999999998,
      "grad_norm": 0.2020028680562973,
      "learning_rate": 4.215e-05,
      "loss": 0.526,
      "step": 785
    },
    {
      "epoch": 1.572,
      "grad_norm": 0.20167556405067444,
      "learning_rate": 4.214e-05,
      "loss": 0.6276,
      "step": 786
    },
    {
      "epoch": 1.5739999999999998,
      "grad_norm": 0.2037021368741989,
      "learning_rate": 4.2130000000000005e-05,
      "loss": 0.5864,
      "step": 787
    },
    {
      "epoch": 1.576,
      "grad_norm": 0.22905926406383514,
      "learning_rate": 4.212e-05,
      "loss": 0.5766,
      "step": 788
    },
    {
      "epoch": 1.5779999999999998,
      "grad_norm": 0.21906892955303192,
      "learning_rate": 4.211e-05,
      "loss": 0.5296,
      "step": 789
    },
    {
      "epoch": 1.58,
      "grad_norm": 0.2502303421497345,
      "learning_rate": 4.21e-05,
      "loss": 0.5491,
      "step": 790
    },
    {
      "epoch": 1.5819999999999999,
      "grad_norm": 0.2179962396621704,
      "learning_rate": 4.209e-05,
      "loss": 0.6227,
      "step": 791
    },
    {
      "epoch": 1.584,
      "grad_norm": 0.2146979421377182,
      "learning_rate": 4.2080000000000004e-05,
      "loss": 0.5965,
      "step": 792
    },
    {
      "epoch": 1.5859999999999999,
      "grad_norm": 0.2131640762090683,
      "learning_rate": 4.207e-05,
      "loss": 0.615,
      "step": 793
    },
    {
      "epoch": 1.588,
      "grad_norm": 0.22561247646808624,
      "learning_rate": 4.206e-05,
      "loss": 0.4323,
      "step": 794
    },
    {
      "epoch": 1.5899999999999999,
      "grad_norm": 0.22139142453670502,
      "learning_rate": 4.205e-05,
      "loss": 0.6603,
      "step": 795
    },
    {
      "epoch": 1.592,
      "grad_norm": 0.20566140115261078,
      "learning_rate": 4.2040000000000004e-05,
      "loss": 0.5087,
      "step": 796
    },
    {
      "epoch": 1.5939999999999999,
      "grad_norm": 0.24742665886878967,
      "learning_rate": 4.203e-05,
      "loss": 0.5964,
      "step": 797
    },
    {
      "epoch": 1.596,
      "grad_norm": 0.20380236208438873,
      "learning_rate": 4.202e-05,
      "loss": 0.5487,
      "step": 798
    },
    {
      "epoch": 1.5979999999999999,
      "grad_norm": 0.20481078326702118,
      "learning_rate": 4.201e-05,
      "loss": 0.5881,
      "step": 799
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.25701841711997986,
      "learning_rate": 4.2e-05,
      "loss": 0.6234,
      "step": 800
    },
    {
      "epoch": 1.6019999999999999,
      "grad_norm": 0.1961895078420639,
      "learning_rate": 4.199e-05,
      "loss": 0.5342,
      "step": 801
    },
    {
      "epoch": 1.604,
      "grad_norm": 0.203657329082489,
      "learning_rate": 4.198e-05,
      "loss": 0.6276,
      "step": 802
    },
    {
      "epoch": 1.6059999999999999,
      "grad_norm": 0.21167868375778198,
      "learning_rate": 4.1970000000000006e-05,
      "loss": 0.5694,
      "step": 803
    },
    {
      "epoch": 1.608,
      "grad_norm": 0.2066878229379654,
      "learning_rate": 4.196e-05,
      "loss": 0.4994,
      "step": 804
    },
    {
      "epoch": 1.6099999999999999,
      "grad_norm": 0.21661029756069183,
      "learning_rate": 4.195e-05,
      "loss": 0.5586,
      "step": 805
    },
    {
      "epoch": 1.612,
      "grad_norm": 0.1986166387796402,
      "learning_rate": 4.194e-05,
      "loss": 0.4946,
      "step": 806
    },
    {
      "epoch": 1.6139999999999999,
      "grad_norm": 0.2023763805627823,
      "learning_rate": 4.193e-05,
      "loss": 0.4492,
      "step": 807
    },
    {
      "epoch": 1.616,
      "grad_norm": 0.22971948981285095,
      "learning_rate": 4.1920000000000005e-05,
      "loss": 0.5701,
      "step": 808
    },
    {
      "epoch": 1.6179999999999999,
      "grad_norm": 0.2328362613916397,
      "learning_rate": 4.191e-05,
      "loss": 0.5548,
      "step": 809
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.1914706826210022,
      "learning_rate": 4.19e-05,
      "loss": 0.5186,
      "step": 810
    },
    {
      "epoch": 1.6219999999999999,
      "grad_norm": 0.20274528861045837,
      "learning_rate": 4.189e-05,
      "loss": 0.4636,
      "step": 811
    },
    {
      "epoch": 1.624,
      "grad_norm": 0.19216802716255188,
      "learning_rate": 4.1880000000000006e-05,
      "loss": 0.5209,
      "step": 812
    },
    {
      "epoch": 1.626,
      "grad_norm": 0.2118818759918213,
      "learning_rate": 4.1870000000000004e-05,
      "loss": 0.5066,
      "step": 813
    },
    {
      "epoch": 1.6280000000000001,
      "grad_norm": 0.24689842760562897,
      "learning_rate": 4.186e-05,
      "loss": 0.6412,
      "step": 814
    },
    {
      "epoch": 1.63,
      "grad_norm": 0.2002333402633667,
      "learning_rate": 4.185e-05,
      "loss": 0.6256,
      "step": 815
    },
    {
      "epoch": 1.6320000000000001,
      "grad_norm": 0.2199128419160843,
      "learning_rate": 4.184e-05,
      "loss": 0.6407,
      "step": 816
    },
    {
      "epoch": 1.634,
      "grad_norm": 0.21204575896263123,
      "learning_rate": 4.1830000000000004e-05,
      "loss": 0.5561,
      "step": 817
    },
    {
      "epoch": 1.6360000000000001,
      "grad_norm": 0.19997568428516388,
      "learning_rate": 4.182e-05,
      "loss": 0.5599,
      "step": 818
    },
    {
      "epoch": 1.638,
      "grad_norm": 0.22140006721019745,
      "learning_rate": 4.181000000000001e-05,
      "loss": 0.5745,
      "step": 819
    },
    {
      "epoch": 1.6400000000000001,
      "grad_norm": 0.22329610586166382,
      "learning_rate": 4.18e-05,
      "loss": 0.5873,
      "step": 820
    },
    {
      "epoch": 1.642,
      "grad_norm": 0.19843119382858276,
      "learning_rate": 4.179e-05,
      "loss": 0.5501,
      "step": 821
    },
    {
      "epoch": 1.6440000000000001,
      "grad_norm": 0.2290477603673935,
      "learning_rate": 4.178e-05,
      "loss": 0.5568,
      "step": 822
    },
    {
      "epoch": 1.646,
      "grad_norm": 0.24019767343997955,
      "learning_rate": 4.177e-05,
      "loss": 0.6133,
      "step": 823
    },
    {
      "epoch": 1.6480000000000001,
      "grad_norm": 0.19814185798168182,
      "learning_rate": 4.176000000000001e-05,
      "loss": 0.5102,
      "step": 824
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.2241322547197342,
      "learning_rate": 4.175e-05,
      "loss": 0.5887,
      "step": 825
    },
    {
      "epoch": 1.6520000000000001,
      "grad_norm": 0.19099442660808563,
      "learning_rate": 4.1740000000000004e-05,
      "loss": 0.5056,
      "step": 826
    },
    {
      "epoch": 1.654,
      "grad_norm": 0.20805147290229797,
      "learning_rate": 4.173e-05,
      "loss": 0.472,
      "step": 827
    },
    {
      "epoch": 1.6560000000000001,
      "grad_norm": 0.2212725132703781,
      "learning_rate": 4.172e-05,
      "loss": 0.6282,
      "step": 828
    },
    {
      "epoch": 1.658,
      "grad_norm": 0.37296777963638306,
      "learning_rate": 4.1710000000000006e-05,
      "loss": 0.5325,
      "step": 829
    },
    {
      "epoch": 1.6600000000000001,
      "grad_norm": 0.20890404284000397,
      "learning_rate": 4.17e-05,
      "loss": 0.4846,
      "step": 830
    },
    {
      "epoch": 1.662,
      "grad_norm": 0.21045196056365967,
      "learning_rate": 4.169e-05,
      "loss": 0.4938,
      "step": 831
    },
    {
      "epoch": 1.6640000000000001,
      "grad_norm": 0.21068882942199707,
      "learning_rate": 4.168e-05,
      "loss": 0.5429,
      "step": 832
    },
    {
      "epoch": 1.666,
      "grad_norm": 0.24714180827140808,
      "learning_rate": 4.1670000000000006e-05,
      "loss": 0.6145,
      "step": 833
    },
    {
      "epoch": 1.6680000000000001,
      "grad_norm": 0.22348974645137787,
      "learning_rate": 4.1660000000000004e-05,
      "loss": 0.5867,
      "step": 834
    },
    {
      "epoch": 1.67,
      "grad_norm": 0.2049664705991745,
      "learning_rate": 4.165e-05,
      "loss": 0.5407,
      "step": 835
    },
    {
      "epoch": 1.6720000000000002,
      "grad_norm": 0.2059626579284668,
      "learning_rate": 4.164e-05,
      "loss": 0.5682,
      "step": 836
    },
    {
      "epoch": 1.674,
      "grad_norm": 0.26519888639450073,
      "learning_rate": 4.163e-05,
      "loss": 0.5899,
      "step": 837
    },
    {
      "epoch": 1.6760000000000002,
      "grad_norm": 0.2156396508216858,
      "learning_rate": 4.1620000000000005e-05,
      "loss": 0.5087,
      "step": 838
    },
    {
      "epoch": 1.678,
      "grad_norm": 0.20123973488807678,
      "learning_rate": 4.161e-05,
      "loss": 0.5533,
      "step": 839
    },
    {
      "epoch": 1.6800000000000002,
      "grad_norm": 0.22913528978824615,
      "learning_rate": 4.16e-05,
      "loss": 0.5258,
      "step": 840
    },
    {
      "epoch": 1.682,
      "grad_norm": 0.2171671986579895,
      "learning_rate": 4.159e-05,
      "loss": 0.543,
      "step": 841
    },
    {
      "epoch": 1.6840000000000002,
      "grad_norm": 0.21813921630382538,
      "learning_rate": 4.1580000000000005e-05,
      "loss": 0.5416,
      "step": 842
    },
    {
      "epoch": 1.686,
      "grad_norm": 0.22544947266578674,
      "learning_rate": 4.1570000000000003e-05,
      "loss": 0.6301,
      "step": 843
    },
    {
      "epoch": 1.688,
      "grad_norm": 0.21432709693908691,
      "learning_rate": 4.156e-05,
      "loss": 0.5973,
      "step": 844
    },
    {
      "epoch": 1.69,
      "grad_norm": 0.20817779004573822,
      "learning_rate": 4.155e-05,
      "loss": 0.5521,
      "step": 845
    },
    {
      "epoch": 1.692,
      "grad_norm": 0.22415509819984436,
      "learning_rate": 4.154e-05,
      "loss": 0.5536,
      "step": 846
    },
    {
      "epoch": 1.694,
      "grad_norm": 0.21055614948272705,
      "learning_rate": 4.1530000000000004e-05,
      "loss": 0.6203,
      "step": 847
    },
    {
      "epoch": 1.696,
      "grad_norm": 0.23882174491882324,
      "learning_rate": 4.152e-05,
      "loss": 0.5853,
      "step": 848
    },
    {
      "epoch": 1.698,
      "grad_norm": 0.20354397594928741,
      "learning_rate": 4.151000000000001e-05,
      "loss": 0.5458,
      "step": 849
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.22530478239059448,
      "learning_rate": 4.15e-05,
      "loss": 0.7185,
      "step": 850
    },
    {
      "epoch": 1.702,
      "grad_norm": 0.25041744112968445,
      "learning_rate": 4.1490000000000004e-05,
      "loss": 0.5678,
      "step": 851
    },
    {
      "epoch": 1.704,
      "grad_norm": 0.2135017216205597,
      "learning_rate": 4.148e-05,
      "loss": 0.6186,
      "step": 852
    },
    {
      "epoch": 1.706,
      "grad_norm": 0.23338288068771362,
      "learning_rate": 4.147e-05,
      "loss": 0.6402,
      "step": 853
    },
    {
      "epoch": 1.708,
      "grad_norm": 0.21697267889976501,
      "learning_rate": 4.1460000000000006e-05,
      "loss": 0.6018,
      "step": 854
    },
    {
      "epoch": 1.71,
      "grad_norm": 0.2361728698015213,
      "learning_rate": 4.145e-05,
      "loss": 0.5507,
      "step": 855
    },
    {
      "epoch": 1.712,
      "grad_norm": 0.23075933754444122,
      "learning_rate": 4.144e-05,
      "loss": 0.6301,
      "step": 856
    },
    {
      "epoch": 1.714,
      "grad_norm": 0.2399604618549347,
      "learning_rate": 4.143e-05,
      "loss": 0.5621,
      "step": 857
    },
    {
      "epoch": 1.716,
      "grad_norm": 0.22412839531898499,
      "learning_rate": 4.142000000000001e-05,
      "loss": 0.5519,
      "step": 858
    },
    {
      "epoch": 1.718,
      "grad_norm": 0.22783443331718445,
      "learning_rate": 4.1410000000000005e-05,
      "loss": 0.5019,
      "step": 859
    },
    {
      "epoch": 1.72,
      "grad_norm": 0.2074798047542572,
      "learning_rate": 4.14e-05,
      "loss": 0.5808,
      "step": 860
    },
    {
      "epoch": 1.722,
      "grad_norm": 0.21460920572280884,
      "learning_rate": 4.139e-05,
      "loss": 0.496,
      "step": 861
    },
    {
      "epoch": 1.724,
      "grad_norm": 0.2521255612373352,
      "learning_rate": 4.138e-05,
      "loss": 0.6452,
      "step": 862
    },
    {
      "epoch": 1.726,
      "grad_norm": 0.21282966434955597,
      "learning_rate": 4.1370000000000005e-05,
      "loss": 0.547,
      "step": 863
    },
    {
      "epoch": 1.728,
      "grad_norm": 0.1929510086774826,
      "learning_rate": 4.1360000000000004e-05,
      "loss": 0.5167,
      "step": 864
    },
    {
      "epoch": 1.73,
      "grad_norm": 0.21537943184375763,
      "learning_rate": 4.135e-05,
      "loss": 0.5226,
      "step": 865
    },
    {
      "epoch": 1.732,
      "grad_norm": 0.2190752625465393,
      "learning_rate": 4.134e-05,
      "loss": 0.6551,
      "step": 866
    },
    {
      "epoch": 1.734,
      "grad_norm": 0.23043037950992584,
      "learning_rate": 4.133e-05,
      "loss": 0.5818,
      "step": 867
    },
    {
      "epoch": 1.736,
      "grad_norm": 0.1956707090139389,
      "learning_rate": 4.1320000000000004e-05,
      "loss": 0.5653,
      "step": 868
    },
    {
      "epoch": 1.738,
      "grad_norm": 0.20191261172294617,
      "learning_rate": 4.131e-05,
      "loss": 0.5275,
      "step": 869
    },
    {
      "epoch": 1.74,
      "grad_norm": 0.217775359749794,
      "learning_rate": 4.13e-05,
      "loss": 0.5777,
      "step": 870
    },
    {
      "epoch": 1.742,
      "grad_norm": 0.2121749073266983,
      "learning_rate": 4.129e-05,
      "loss": 0.5817,
      "step": 871
    },
    {
      "epoch": 1.744,
      "grad_norm": 0.23671622574329376,
      "learning_rate": 4.1280000000000005e-05,
      "loss": 0.5791,
      "step": 872
    },
    {
      "epoch": 1.746,
      "grad_norm": 0.21338392794132233,
      "learning_rate": 4.127e-05,
      "loss": 0.5255,
      "step": 873
    },
    {
      "epoch": 1.748,
      "grad_norm": 0.2075783610343933,
      "learning_rate": 4.126e-05,
      "loss": 0.5348,
      "step": 874
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.21902282536029816,
      "learning_rate": 4.125e-05,
      "loss": 0.5297,
      "step": 875
    },
    {
      "epoch": 1.752,
      "grad_norm": 0.22228483855724335,
      "learning_rate": 4.124e-05,
      "loss": 0.6283,
      "step": 876
    },
    {
      "epoch": 1.754,
      "grad_norm": 0.20441770553588867,
      "learning_rate": 4.123e-05,
      "loss": 0.604,
      "step": 877
    },
    {
      "epoch": 1.756,
      "grad_norm": 0.20509788393974304,
      "learning_rate": 4.122e-05,
      "loss": 0.5171,
      "step": 878
    },
    {
      "epoch": 1.758,
      "grad_norm": 0.19927029311656952,
      "learning_rate": 4.121000000000001e-05,
      "loss": 0.5345,
      "step": 879
    },
    {
      "epoch": 1.76,
      "grad_norm": 0.22879639267921448,
      "learning_rate": 4.12e-05,
      "loss": 0.7277,
      "step": 880
    },
    {
      "epoch": 1.762,
      "grad_norm": 0.19165241718292236,
      "learning_rate": 4.1190000000000004e-05,
      "loss": 0.5839,
      "step": 881
    },
    {
      "epoch": 1.764,
      "grad_norm": 0.22788327932357788,
      "learning_rate": 4.118e-05,
      "loss": 0.5701,
      "step": 882
    },
    {
      "epoch": 1.766,
      "grad_norm": 0.24636496603488922,
      "learning_rate": 4.117e-05,
      "loss": 0.5136,
      "step": 883
    },
    {
      "epoch": 1.768,
      "grad_norm": 0.19353416562080383,
      "learning_rate": 4.1160000000000006e-05,
      "loss": 0.5419,
      "step": 884
    },
    {
      "epoch": 1.77,
      "grad_norm": 0.25121909379959106,
      "learning_rate": 4.115e-05,
      "loss": 0.5708,
      "step": 885
    },
    {
      "epoch": 1.772,
      "grad_norm": 0.19388718903064728,
      "learning_rate": 4.114e-05,
      "loss": 0.5358,
      "step": 886
    },
    {
      "epoch": 1.774,
      "grad_norm": 0.2159653753042221,
      "learning_rate": 4.113e-05,
      "loss": 0.5699,
      "step": 887
    },
    {
      "epoch": 1.776,
      "grad_norm": 0.22405487298965454,
      "learning_rate": 4.1120000000000006e-05,
      "loss": 0.5936,
      "step": 888
    },
    {
      "epoch": 1.778,
      "grad_norm": 0.23130780458450317,
      "learning_rate": 4.1110000000000005e-05,
      "loss": 0.5559,
      "step": 889
    },
    {
      "epoch": 1.78,
      "grad_norm": 0.2627403438091278,
      "learning_rate": 4.11e-05,
      "loss": 0.718,
      "step": 890
    },
    {
      "epoch": 1.782,
      "grad_norm": 0.2019093930721283,
      "learning_rate": 4.109e-05,
      "loss": 0.5455,
      "step": 891
    },
    {
      "epoch": 1.784,
      "grad_norm": 0.2051168829202652,
      "learning_rate": 4.108e-05,
      "loss": 0.5509,
      "step": 892
    },
    {
      "epoch": 1.786,
      "grad_norm": 0.2552720308303833,
      "learning_rate": 4.1070000000000005e-05,
      "loss": 0.6097,
      "step": 893
    },
    {
      "epoch": 1.788,
      "grad_norm": 0.21365538239479065,
      "learning_rate": 4.106e-05,
      "loss": 0.6256,
      "step": 894
    },
    {
      "epoch": 1.79,
      "grad_norm": 0.22518736124038696,
      "learning_rate": 4.105e-05,
      "loss": 0.5823,
      "step": 895
    },
    {
      "epoch": 1.792,
      "grad_norm": 0.22332648932933807,
      "learning_rate": 4.104e-05,
      "loss": 0.5949,
      "step": 896
    },
    {
      "epoch": 1.794,
      "grad_norm": 0.20917260646820068,
      "learning_rate": 4.103e-05,
      "loss": 0.5124,
      "step": 897
    },
    {
      "epoch": 1.796,
      "grad_norm": 0.20652370154857635,
      "learning_rate": 4.1020000000000004e-05,
      "loss": 0.5732,
      "step": 898
    },
    {
      "epoch": 1.798,
      "grad_norm": 0.22270749509334564,
      "learning_rate": 4.101e-05,
      "loss": 0.5921,
      "step": 899
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.25644269585609436,
      "learning_rate": 4.1e-05,
      "loss": 0.5824,
      "step": 900
    },
    {
      "epoch": 1.802,
      "grad_norm": 0.2324872463941574,
      "learning_rate": 4.099e-05,
      "loss": 0.6288,
      "step": 901
    },
    {
      "epoch": 1.804,
      "grad_norm": 0.2203238308429718,
      "learning_rate": 4.0980000000000004e-05,
      "loss": 0.6001,
      "step": 902
    },
    {
      "epoch": 1.806,
      "grad_norm": 0.1977611482143402,
      "learning_rate": 4.097e-05,
      "loss": 0.5367,
      "step": 903
    },
    {
      "epoch": 1.808,
      "grad_norm": 0.20962348580360413,
      "learning_rate": 4.096e-05,
      "loss": 0.5974,
      "step": 904
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.20759950578212738,
      "learning_rate": 4.095e-05,
      "loss": 0.5846,
      "step": 905
    },
    {
      "epoch": 1.812,
      "grad_norm": 0.20946946740150452,
      "learning_rate": 4.094e-05,
      "loss": 0.5357,
      "step": 906
    },
    {
      "epoch": 1.814,
      "grad_norm": 0.2401723712682724,
      "learning_rate": 4.093e-05,
      "loss": 0.6251,
      "step": 907
    },
    {
      "epoch": 1.8159999999999998,
      "grad_norm": 0.183771014213562,
      "learning_rate": 4.092e-05,
      "loss": 0.4638,
      "step": 908
    },
    {
      "epoch": 1.818,
      "grad_norm": 0.22831161320209503,
      "learning_rate": 4.0910000000000006e-05,
      "loss": 0.5606,
      "step": 909
    },
    {
      "epoch": 1.8199999999999998,
      "grad_norm": 0.2133151739835739,
      "learning_rate": 4.09e-05,
      "loss": 0.6701,
      "step": 910
    },
    {
      "epoch": 1.822,
      "grad_norm": 0.2002599835395813,
      "learning_rate": 4.089e-05,
      "loss": 0.5428,
      "step": 911
    },
    {
      "epoch": 1.8239999999999998,
      "grad_norm": 0.21106943488121033,
      "learning_rate": 4.088e-05,
      "loss": 0.5172,
      "step": 912
    },
    {
      "epoch": 1.826,
      "grad_norm": 0.22433418035507202,
      "learning_rate": 4.087e-05,
      "loss": 0.4971,
      "step": 913
    },
    {
      "epoch": 1.8279999999999998,
      "grad_norm": 0.29436904191970825,
      "learning_rate": 4.0860000000000005e-05,
      "loss": 0.4824,
      "step": 914
    },
    {
      "epoch": 1.83,
      "grad_norm": 0.2517542243003845,
      "learning_rate": 4.085e-05,
      "loss": 0.6387,
      "step": 915
    },
    {
      "epoch": 1.8319999999999999,
      "grad_norm": 0.20705367624759674,
      "learning_rate": 4.084e-05,
      "loss": 0.546,
      "step": 916
    },
    {
      "epoch": 1.834,
      "grad_norm": 0.21476560831069946,
      "learning_rate": 4.083e-05,
      "loss": 0.5628,
      "step": 917
    },
    {
      "epoch": 1.8359999999999999,
      "grad_norm": 0.2123742401599884,
      "learning_rate": 4.0820000000000006e-05,
      "loss": 0.5286,
      "step": 918
    },
    {
      "epoch": 1.838,
      "grad_norm": 0.20832893252372742,
      "learning_rate": 4.0810000000000004e-05,
      "loss": 0.5871,
      "step": 919
    },
    {
      "epoch": 1.8399999999999999,
      "grad_norm": 0.1990961730480194,
      "learning_rate": 4.08e-05,
      "loss": 0.5139,
      "step": 920
    },
    {
      "epoch": 1.842,
      "grad_norm": 0.2340562492609024,
      "learning_rate": 4.079e-05,
      "loss": 0.6197,
      "step": 921
    },
    {
      "epoch": 1.8439999999999999,
      "grad_norm": 0.18560324609279633,
      "learning_rate": 4.078e-05,
      "loss": 0.398,
      "step": 922
    },
    {
      "epoch": 1.846,
      "grad_norm": 0.2281452864408493,
      "learning_rate": 4.0770000000000004e-05,
      "loss": 0.6096,
      "step": 923
    },
    {
      "epoch": 1.8479999999999999,
      "grad_norm": 0.22291038930416107,
      "learning_rate": 4.076e-05,
      "loss": 0.5313,
      "step": 924
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.20964789390563965,
      "learning_rate": 4.075e-05,
      "loss": 0.5965,
      "step": 925
    },
    {
      "epoch": 1.8519999999999999,
      "grad_norm": 0.24047353863716125,
      "learning_rate": 4.074e-05,
      "loss": 0.6198,
      "step": 926
    },
    {
      "epoch": 1.854,
      "grad_norm": 0.23723970353603363,
      "learning_rate": 4.0730000000000005e-05,
      "loss": 0.6799,
      "step": 927
    },
    {
      "epoch": 1.8559999999999999,
      "grad_norm": 0.21580907702445984,
      "learning_rate": 4.072e-05,
      "loss": 0.5481,
      "step": 928
    },
    {
      "epoch": 1.858,
      "grad_norm": 0.2145693600177765,
      "learning_rate": 4.071e-05,
      "loss": 0.552,
      "step": 929
    },
    {
      "epoch": 1.8599999999999999,
      "grad_norm": 0.2449941337108612,
      "learning_rate": 4.07e-05,
      "loss": 0.5838,
      "step": 930
    },
    {
      "epoch": 1.862,
      "grad_norm": 0.2502371370792389,
      "learning_rate": 4.069e-05,
      "loss": 0.5497,
      "step": 931
    },
    {
      "epoch": 1.8639999999999999,
      "grad_norm": 0.18988710641860962,
      "learning_rate": 4.0680000000000004e-05,
      "loss": 0.5292,
      "step": 932
    },
    {
      "epoch": 1.866,
      "grad_norm": 0.23330973088741302,
      "learning_rate": 4.067e-05,
      "loss": 0.5252,
      "step": 933
    },
    {
      "epoch": 1.8679999999999999,
      "grad_norm": 0.2083967626094818,
      "learning_rate": 4.066e-05,
      "loss": 0.5631,
      "step": 934
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.2037411481142044,
      "learning_rate": 4.065e-05,
      "loss": 0.5596,
      "step": 935
    },
    {
      "epoch": 1.8719999999999999,
      "grad_norm": 0.22660300135612488,
      "learning_rate": 4.064e-05,
      "loss": 0.587,
      "step": 936
    },
    {
      "epoch": 1.874,
      "grad_norm": 0.24138827621936798,
      "learning_rate": 4.063e-05,
      "loss": 0.511,
      "step": 937
    },
    {
      "epoch": 1.876,
      "grad_norm": 0.23298485577106476,
      "learning_rate": 4.062e-05,
      "loss": 0.5614,
      "step": 938
    },
    {
      "epoch": 1.8780000000000001,
      "grad_norm": 0.2537238299846649,
      "learning_rate": 4.0610000000000006e-05,
      "loss": 0.5249,
      "step": 939
    },
    {
      "epoch": 1.88,
      "grad_norm": 0.23439259827136993,
      "learning_rate": 4.0600000000000004e-05,
      "loss": 0.5895,
      "step": 940
    },
    {
      "epoch": 1.8820000000000001,
      "grad_norm": 0.2297605574131012,
      "learning_rate": 4.059e-05,
      "loss": 0.5568,
      "step": 941
    },
    {
      "epoch": 1.884,
      "grad_norm": 0.22932069003582,
      "learning_rate": 4.058e-05,
      "loss": 0.6007,
      "step": 942
    },
    {
      "epoch": 1.8860000000000001,
      "grad_norm": 0.19363686442375183,
      "learning_rate": 4.057e-05,
      "loss": 0.526,
      "step": 943
    },
    {
      "epoch": 1.888,
      "grad_norm": 0.22038032114505768,
      "learning_rate": 4.0560000000000005e-05,
      "loss": 0.6154,
      "step": 944
    },
    {
      "epoch": 1.8900000000000001,
      "grad_norm": 0.20162424445152283,
      "learning_rate": 4.055e-05,
      "loss": 0.5284,
      "step": 945
    },
    {
      "epoch": 1.892,
      "grad_norm": 0.24655213952064514,
      "learning_rate": 4.054e-05,
      "loss": 0.5562,
      "step": 946
    },
    {
      "epoch": 1.8940000000000001,
      "grad_norm": 0.23588095605373383,
      "learning_rate": 4.053e-05,
      "loss": 0.7056,
      "step": 947
    },
    {
      "epoch": 1.896,
      "grad_norm": 0.21690240502357483,
      "learning_rate": 4.0520000000000005e-05,
      "loss": 0.5517,
      "step": 948
    },
    {
      "epoch": 1.8980000000000001,
      "grad_norm": 0.19915015995502472,
      "learning_rate": 4.0510000000000003e-05,
      "loss": 0.5044,
      "step": 949
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.22316230833530426,
      "learning_rate": 4.05e-05,
      "loss": 0.557,
      "step": 950
    },
    {
      "epoch": 1.9020000000000001,
      "grad_norm": 0.23766140639781952,
      "learning_rate": 4.049e-05,
      "loss": 0.5601,
      "step": 951
    },
    {
      "epoch": 1.904,
      "grad_norm": 0.25181880593299866,
      "learning_rate": 4.048e-05,
      "loss": 0.5983,
      "step": 952
    },
    {
      "epoch": 1.9060000000000001,
      "grad_norm": 0.21048982441425323,
      "learning_rate": 4.0470000000000004e-05,
      "loss": 0.5901,
      "step": 953
    },
    {
      "epoch": 1.908,
      "grad_norm": 0.19192460179328918,
      "learning_rate": 4.046e-05,
      "loss": 0.4686,
      "step": 954
    },
    {
      "epoch": 1.9100000000000001,
      "grad_norm": 0.23322626948356628,
      "learning_rate": 4.045000000000001e-05,
      "loss": 0.6613,
      "step": 955
    },
    {
      "epoch": 1.912,
      "grad_norm": 0.21661929786205292,
      "learning_rate": 4.044e-05,
      "loss": 0.5491,
      "step": 956
    },
    {
      "epoch": 1.9140000000000001,
      "grad_norm": 0.21244138479232788,
      "learning_rate": 4.0430000000000004e-05,
      "loss": 0.5141,
      "step": 957
    },
    {
      "epoch": 1.916,
      "grad_norm": 0.22383420169353485,
      "learning_rate": 4.042e-05,
      "loss": 0.5722,
      "step": 958
    },
    {
      "epoch": 1.9180000000000001,
      "grad_norm": 0.234762042760849,
      "learning_rate": 4.041e-05,
      "loss": 0.5825,
      "step": 959
    },
    {
      "epoch": 1.92,
      "grad_norm": 0.20146997272968292,
      "learning_rate": 4.0400000000000006e-05,
      "loss": 0.5272,
      "step": 960
    },
    {
      "epoch": 1.9220000000000002,
      "grad_norm": 0.22217825055122375,
      "learning_rate": 4.039e-05,
      "loss": 0.6413,
      "step": 961
    },
    {
      "epoch": 1.924,
      "grad_norm": 0.2346162497997284,
      "learning_rate": 4.038e-05,
      "loss": 0.6417,
      "step": 962
    },
    {
      "epoch": 1.9260000000000002,
      "grad_norm": 0.2526434063911438,
      "learning_rate": 4.037e-05,
      "loss": 0.5815,
      "step": 963
    },
    {
      "epoch": 1.928,
      "grad_norm": 0.22428862750530243,
      "learning_rate": 4.0360000000000007e-05,
      "loss": 0.6114,
      "step": 964
    },
    {
      "epoch": 1.9300000000000002,
      "grad_norm": 0.21866799890995026,
      "learning_rate": 4.0350000000000005e-05,
      "loss": 0.542,
      "step": 965
    },
    {
      "epoch": 1.932,
      "grad_norm": 0.22071845829486847,
      "learning_rate": 4.034e-05,
      "loss": 0.5551,
      "step": 966
    },
    {
      "epoch": 1.9340000000000002,
      "grad_norm": 0.25092819333076477,
      "learning_rate": 4.033e-05,
      "loss": 0.6824,
      "step": 967
    },
    {
      "epoch": 1.936,
      "grad_norm": 0.21841230988502502,
      "learning_rate": 4.032e-05,
      "loss": 0.604,
      "step": 968
    },
    {
      "epoch": 1.938,
      "grad_norm": 0.22759634256362915,
      "learning_rate": 4.0310000000000005e-05,
      "loss": 0.6722,
      "step": 969
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.24783313274383545,
      "learning_rate": 4.0300000000000004e-05,
      "loss": 0.5625,
      "step": 970
    },
    {
      "epoch": 1.942,
      "grad_norm": 0.22955209016799927,
      "learning_rate": 4.029e-05,
      "loss": 0.653,
      "step": 971
    },
    {
      "epoch": 1.944,
      "grad_norm": 0.2600350081920624,
      "learning_rate": 4.028e-05,
      "loss": 0.6628,
      "step": 972
    },
    {
      "epoch": 1.946,
      "grad_norm": 0.21005043387413025,
      "learning_rate": 4.027e-05,
      "loss": 0.4254,
      "step": 973
    },
    {
      "epoch": 1.948,
      "grad_norm": 0.20057177543640137,
      "learning_rate": 4.0260000000000004e-05,
      "loss": 0.5552,
      "step": 974
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.2378489077091217,
      "learning_rate": 4.025e-05,
      "loss": 0.5861,
      "step": 975
    },
    {
      "epoch": 1.952,
      "grad_norm": 0.27887988090515137,
      "learning_rate": 4.024e-05,
      "loss": 0.5742,
      "step": 976
    },
    {
      "epoch": 1.954,
      "grad_norm": 0.19681380689144135,
      "learning_rate": 4.023e-05,
      "loss": 0.5129,
      "step": 977
    },
    {
      "epoch": 1.956,
      "grad_norm": 0.21786653995513916,
      "learning_rate": 4.0220000000000005e-05,
      "loss": 0.5089,
      "step": 978
    },
    {
      "epoch": 1.958,
      "grad_norm": 0.2101248949766159,
      "learning_rate": 4.021e-05,
      "loss": 0.6421,
      "step": 979
    },
    {
      "epoch": 1.96,
      "grad_norm": 0.22144469618797302,
      "learning_rate": 4.02e-05,
      "loss": 0.5279,
      "step": 980
    },
    {
      "epoch": 1.962,
      "grad_norm": 0.2304532378911972,
      "learning_rate": 4.019e-05,
      "loss": 0.5908,
      "step": 981
    },
    {
      "epoch": 1.964,
      "grad_norm": 0.28714126348495483,
      "learning_rate": 4.018e-05,
      "loss": 0.6038,
      "step": 982
    },
    {
      "epoch": 1.966,
      "grad_norm": 0.2407093048095703,
      "learning_rate": 4.017e-05,
      "loss": 0.5684,
      "step": 983
    },
    {
      "epoch": 1.968,
      "grad_norm": 0.20832942426204681,
      "learning_rate": 4.016e-05,
      "loss": 0.5724,
      "step": 984
    },
    {
      "epoch": 1.97,
      "grad_norm": 0.20581866800785065,
      "learning_rate": 4.015000000000001e-05,
      "loss": 0.5205,
      "step": 985
    },
    {
      "epoch": 1.972,
      "grad_norm": 0.2234366089105606,
      "learning_rate": 4.014e-05,
      "loss": 0.6269,
      "step": 986
    },
    {
      "epoch": 1.974,
      "grad_norm": 0.23339971899986267,
      "learning_rate": 4.0130000000000004e-05,
      "loss": 0.5409,
      "step": 987
    },
    {
      "epoch": 1.976,
      "grad_norm": 0.21210043132305145,
      "learning_rate": 4.012e-05,
      "loss": 0.502,
      "step": 988
    },
    {
      "epoch": 1.978,
      "grad_norm": 0.2021539956331253,
      "learning_rate": 4.011e-05,
      "loss": 0.5456,
      "step": 989
    },
    {
      "epoch": 1.98,
      "grad_norm": 0.24333329498767853,
      "learning_rate": 4.0100000000000006e-05,
      "loss": 0.6098,
      "step": 990
    },
    {
      "epoch": 1.982,
      "grad_norm": 0.19317735731601715,
      "learning_rate": 4.009e-05,
      "loss": 0.4954,
      "step": 991
    },
    {
      "epoch": 1.984,
      "grad_norm": 0.28837406635284424,
      "learning_rate": 4.008e-05,
      "loss": 0.5882,
      "step": 992
    },
    {
      "epoch": 1.986,
      "grad_norm": 0.233433797955513,
      "learning_rate": 4.007e-05,
      "loss": 0.5944,
      "step": 993
    },
    {
      "epoch": 1.988,
      "grad_norm": 0.2529718577861786,
      "learning_rate": 4.0060000000000006e-05,
      "loss": 0.5822,
      "step": 994
    },
    {
      "epoch": 1.99,
      "grad_norm": 0.2050531506538391,
      "learning_rate": 4.0050000000000004e-05,
      "loss": 0.5316,
      "step": 995
    },
    {
      "epoch": 1.992,
      "grad_norm": 0.20875830948352814,
      "learning_rate": 4.004e-05,
      "loss": 0.5767,
      "step": 996
    },
    {
      "epoch": 1.994,
      "grad_norm": 0.21856260299682617,
      "learning_rate": 4.003e-05,
      "loss": 0.576,
      "step": 997
    },
    {
      "epoch": 1.996,
      "grad_norm": 0.2040548473596573,
      "learning_rate": 4.002e-05,
      "loss": 0.5035,
      "step": 998
    },
    {
      "epoch": 1.998,
      "grad_norm": 0.22710789740085602,
      "learning_rate": 4.0010000000000005e-05,
      "loss": 0.6112,
      "step": 999
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.20931439101696014,
      "learning_rate": 4e-05,
      "loss": 0.5229,
      "step": 1000
    },
    {
      "epoch": 2.002,
      "grad_norm": 0.2300502359867096,
      "learning_rate": 3.999e-05,
      "loss": 0.5785,
      "step": 1001
    },
    {
      "epoch": 2.004,
      "grad_norm": 0.22193074226379395,
      "learning_rate": 3.998e-05,
      "loss": 0.5755,
      "step": 1002
    },
    {
      "epoch": 2.006,
      "grad_norm": 0.24395062029361725,
      "learning_rate": 3.9970000000000005e-05,
      "loss": 0.5643,
      "step": 1003
    },
    {
      "epoch": 2.008,
      "grad_norm": 0.19612465798854828,
      "learning_rate": 3.9960000000000004e-05,
      "loss": 0.5181,
      "step": 1004
    },
    {
      "epoch": 2.01,
      "grad_norm": 0.2229042500257492,
      "learning_rate": 3.995e-05,
      "loss": 0.5675,
      "step": 1005
    },
    {
      "epoch": 2.012,
      "grad_norm": 0.2308545857667923,
      "learning_rate": 3.994e-05,
      "loss": 0.5175,
      "step": 1006
    },
    {
      "epoch": 2.014,
      "grad_norm": 0.22244416177272797,
      "learning_rate": 3.993e-05,
      "loss": 0.5007,
      "step": 1007
    },
    {
      "epoch": 2.016,
      "grad_norm": 0.20587439835071564,
      "learning_rate": 3.9920000000000004e-05,
      "loss": 0.5403,
      "step": 1008
    },
    {
      "epoch": 2.018,
      "grad_norm": 0.21140223741531372,
      "learning_rate": 3.991e-05,
      "loss": 0.5211,
      "step": 1009
    },
    {
      "epoch": 2.02,
      "grad_norm": 0.2223360389471054,
      "learning_rate": 3.99e-05,
      "loss": 0.701,
      "step": 1010
    },
    {
      "epoch": 2.022,
      "grad_norm": 0.22314807772636414,
      "learning_rate": 3.989e-05,
      "loss": 0.6075,
      "step": 1011
    },
    {
      "epoch": 2.024,
      "grad_norm": 0.23748956620693207,
      "learning_rate": 3.988e-05,
      "loss": 0.5044,
      "step": 1012
    },
    {
      "epoch": 2.026,
      "grad_norm": 0.23993243277072906,
      "learning_rate": 3.987e-05,
      "loss": 0.5213,
      "step": 1013
    },
    {
      "epoch": 2.028,
      "grad_norm": 0.24043142795562744,
      "learning_rate": 3.986e-05,
      "loss": 0.5525,
      "step": 1014
    },
    {
      "epoch": 2.03,
      "grad_norm": 0.23012974858283997,
      "learning_rate": 3.9850000000000006e-05,
      "loss": 0.5964,
      "step": 1015
    },
    {
      "epoch": 2.032,
      "grad_norm": 0.2021389603614807,
      "learning_rate": 3.984e-05,
      "loss": 0.5016,
      "step": 1016
    },
    {
      "epoch": 2.034,
      "grad_norm": 0.22271737456321716,
      "learning_rate": 3.983e-05,
      "loss": 0.5695,
      "step": 1017
    },
    {
      "epoch": 2.036,
      "grad_norm": 0.2237047702074051,
      "learning_rate": 3.982e-05,
      "loss": 0.5098,
      "step": 1018
    },
    {
      "epoch": 2.038,
      "grad_norm": 0.20218700170516968,
      "learning_rate": 3.981e-05,
      "loss": 0.4349,
      "step": 1019
    },
    {
      "epoch": 2.04,
      "grad_norm": 0.24619650840759277,
      "learning_rate": 3.9800000000000005e-05,
      "loss": 0.6199,
      "step": 1020
    },
    {
      "epoch": 2.042,
      "grad_norm": 0.24785549938678741,
      "learning_rate": 3.979e-05,
      "loss": 0.5889,
      "step": 1021
    },
    {
      "epoch": 2.044,
      "grad_norm": 0.22918753325939178,
      "learning_rate": 3.978e-05,
      "loss": 0.5206,
      "step": 1022
    },
    {
      "epoch": 2.046,
      "grad_norm": 0.22109267115592957,
      "learning_rate": 3.977e-05,
      "loss": 0.553,
      "step": 1023
    },
    {
      "epoch": 2.048,
      "grad_norm": 0.22089530527591705,
      "learning_rate": 3.9760000000000006e-05,
      "loss": 0.5653,
      "step": 1024
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.2215888500213623,
      "learning_rate": 3.9750000000000004e-05,
      "loss": 0.6286,
      "step": 1025
    },
    {
      "epoch": 2.052,
      "grad_norm": 0.2496936172246933,
      "learning_rate": 3.974e-05,
      "loss": 0.7117,
      "step": 1026
    },
    {
      "epoch": 2.054,
      "grad_norm": 0.20800064504146576,
      "learning_rate": 3.973e-05,
      "loss": 0.498,
      "step": 1027
    },
    {
      "epoch": 2.056,
      "grad_norm": 0.23079819977283478,
      "learning_rate": 3.972e-05,
      "loss": 0.6061,
      "step": 1028
    },
    {
      "epoch": 2.058,
      "grad_norm": 0.23401056230068207,
      "learning_rate": 3.9710000000000004e-05,
      "loss": 0.5678,
      "step": 1029
    },
    {
      "epoch": 2.06,
      "grad_norm": 0.27760186791419983,
      "learning_rate": 3.97e-05,
      "loss": 0.684,
      "step": 1030
    },
    {
      "epoch": 2.062,
      "grad_norm": 0.22640343010425568,
      "learning_rate": 3.969e-05,
      "loss": 0.5338,
      "step": 1031
    },
    {
      "epoch": 2.064,
      "grad_norm": 0.1947317123413086,
      "learning_rate": 3.968e-05,
      "loss": 0.4795,
      "step": 1032
    },
    {
      "epoch": 2.066,
      "grad_norm": 0.22717192769050598,
      "learning_rate": 3.9670000000000005e-05,
      "loss": 0.5183,
      "step": 1033
    },
    {
      "epoch": 2.068,
      "grad_norm": 0.21169620752334595,
      "learning_rate": 3.966e-05,
      "loss": 0.5641,
      "step": 1034
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.9110057950019836,
      "learning_rate": 3.965e-05,
      "loss": 0.6311,
      "step": 1035
    },
    {
      "epoch": 2.072,
      "grad_norm": 0.2137368768453598,
      "learning_rate": 3.964e-05,
      "loss": 0.5862,
      "step": 1036
    },
    {
      "epoch": 2.074,
      "grad_norm": 0.23863641917705536,
      "learning_rate": 3.963e-05,
      "loss": 0.5416,
      "step": 1037
    },
    {
      "epoch": 2.076,
      "grad_norm": 0.2136143296957016,
      "learning_rate": 3.9620000000000004e-05,
      "loss": 0.5665,
      "step": 1038
    },
    {
      "epoch": 2.078,
      "grad_norm": 0.22708338499069214,
      "learning_rate": 3.961e-05,
      "loss": 0.6251,
      "step": 1039
    },
    {
      "epoch": 2.08,
      "grad_norm": 0.24242404103279114,
      "learning_rate": 3.960000000000001e-05,
      "loss": 0.5365,
      "step": 1040
    },
    {
      "epoch": 2.082,
      "grad_norm": 0.24977032840251923,
      "learning_rate": 3.959e-05,
      "loss": 0.5447,
      "step": 1041
    },
    {
      "epoch": 2.084,
      "grad_norm": 0.24284620583057404,
      "learning_rate": 3.958e-05,
      "loss": 0.6634,
      "step": 1042
    },
    {
      "epoch": 2.086,
      "grad_norm": 0.23839087784290314,
      "learning_rate": 3.957e-05,
      "loss": 0.6501,
      "step": 1043
    },
    {
      "epoch": 2.088,
      "grad_norm": 0.213258296251297,
      "learning_rate": 3.956e-05,
      "loss": 0.5919,
      "step": 1044
    },
    {
      "epoch": 2.09,
      "grad_norm": 0.2643541097640991,
      "learning_rate": 3.9550000000000006e-05,
      "loss": 0.5912,
      "step": 1045
    },
    {
      "epoch": 2.092,
      "grad_norm": 0.24359184503555298,
      "learning_rate": 3.954e-05,
      "loss": 0.5563,
      "step": 1046
    },
    {
      "epoch": 2.094,
      "grad_norm": 0.19231514632701874,
      "learning_rate": 3.953e-05,
      "loss": 0.5082,
      "step": 1047
    },
    {
      "epoch": 2.096,
      "grad_norm": 0.20474958419799805,
      "learning_rate": 3.952e-05,
      "loss": 0.4931,
      "step": 1048
    },
    {
      "epoch": 2.098,
      "grad_norm": 0.22740337252616882,
      "learning_rate": 3.951e-05,
      "loss": 0.5513,
      "step": 1049
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.23002669215202332,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.5292,
      "step": 1050
    },
    {
      "epoch": 2.102,
      "grad_norm": 0.22021901607513428,
      "learning_rate": 3.9489999999999996e-05,
      "loss": 0.5926,
      "step": 1051
    },
    {
      "epoch": 2.104,
      "grad_norm": 0.2307133972644806,
      "learning_rate": 3.948e-05,
      "loss": 0.5864,
      "step": 1052
    },
    {
      "epoch": 2.106,
      "grad_norm": 0.2517574727535248,
      "learning_rate": 3.947e-05,
      "loss": 0.6357,
      "step": 1053
    },
    {
      "epoch": 2.108,
      "grad_norm": 0.220330610871315,
      "learning_rate": 3.9460000000000005e-05,
      "loss": 0.4541,
      "step": 1054
    },
    {
      "epoch": 2.11,
      "grad_norm": 0.24779756367206573,
      "learning_rate": 3.9450000000000003e-05,
      "loss": 0.5963,
      "step": 1055
    },
    {
      "epoch": 2.112,
      "grad_norm": 0.22897957265377045,
      "learning_rate": 3.944e-05,
      "loss": 0.4901,
      "step": 1056
    },
    {
      "epoch": 2.114,
      "grad_norm": 0.21515005826950073,
      "learning_rate": 3.943e-05,
      "loss": 0.5122,
      "step": 1057
    },
    {
      "epoch": 2.116,
      "grad_norm": 0.23861292004585266,
      "learning_rate": 3.942e-05,
      "loss": 0.5649,
      "step": 1058
    },
    {
      "epoch": 2.118,
      "grad_norm": 0.2284981906414032,
      "learning_rate": 3.9410000000000004e-05,
      "loss": 0.6206,
      "step": 1059
    },
    {
      "epoch": 2.12,
      "grad_norm": 0.2444058358669281,
      "learning_rate": 3.94e-05,
      "loss": 0.5106,
      "step": 1060
    },
    {
      "epoch": 2.122,
      "grad_norm": 0.22870151698589325,
      "learning_rate": 3.939e-05,
      "loss": 0.5614,
      "step": 1061
    },
    {
      "epoch": 2.124,
      "grad_norm": 0.22062517702579498,
      "learning_rate": 3.938e-05,
      "loss": 0.6262,
      "step": 1062
    },
    {
      "epoch": 2.126,
      "grad_norm": 0.24075838923454285,
      "learning_rate": 3.9370000000000004e-05,
      "loss": 0.5642,
      "step": 1063
    },
    {
      "epoch": 2.128,
      "grad_norm": 0.2970450222492218,
      "learning_rate": 3.936e-05,
      "loss": 0.4678,
      "step": 1064
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.21903452277183533,
      "learning_rate": 3.935e-05,
      "loss": 0.5021,
      "step": 1065
    },
    {
      "epoch": 2.132,
      "grad_norm": 0.23422181606292725,
      "learning_rate": 3.9340000000000006e-05,
      "loss": 0.519,
      "step": 1066
    },
    {
      "epoch": 2.134,
      "grad_norm": 0.2115645855665207,
      "learning_rate": 3.933e-05,
      "loss": 0.541,
      "step": 1067
    },
    {
      "epoch": 2.136,
      "grad_norm": 0.21695291996002197,
      "learning_rate": 3.932e-05,
      "loss": 0.5288,
      "step": 1068
    },
    {
      "epoch": 2.138,
      "grad_norm": 0.23118314146995544,
      "learning_rate": 3.931e-05,
      "loss": 0.6113,
      "step": 1069
    },
    {
      "epoch": 2.14,
      "grad_norm": 0.199484184384346,
      "learning_rate": 3.9300000000000007e-05,
      "loss": 0.4818,
      "step": 1070
    },
    {
      "epoch": 2.142,
      "grad_norm": 0.22116996347904205,
      "learning_rate": 3.9290000000000005e-05,
      "loss": 0.5796,
      "step": 1071
    },
    {
      "epoch": 2.144,
      "grad_norm": 0.20206792652606964,
      "learning_rate": 3.9280000000000003e-05,
      "loss": 0.4504,
      "step": 1072
    },
    {
      "epoch": 2.146,
      "grad_norm": 0.22893157601356506,
      "learning_rate": 3.927e-05,
      "loss": 0.6186,
      "step": 1073
    },
    {
      "epoch": 2.148,
      "grad_norm": 0.21714241802692413,
      "learning_rate": 3.926e-05,
      "loss": 0.4772,
      "step": 1074
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.22640830278396606,
      "learning_rate": 3.9250000000000005e-05,
      "loss": 0.5859,
      "step": 1075
    },
    {
      "epoch": 2.152,
      "grad_norm": 0.23758919537067413,
      "learning_rate": 3.9240000000000004e-05,
      "loss": 0.5819,
      "step": 1076
    },
    {
      "epoch": 2.154,
      "grad_norm": 0.22804389894008636,
      "learning_rate": 3.923e-05,
      "loss": 0.6115,
      "step": 1077
    },
    {
      "epoch": 2.156,
      "grad_norm": 0.22379794716835022,
      "learning_rate": 3.922e-05,
      "loss": 0.5003,
      "step": 1078
    },
    {
      "epoch": 2.158,
      "grad_norm": 0.21899166703224182,
      "learning_rate": 3.921e-05,
      "loss": 0.5034,
      "step": 1079
    },
    {
      "epoch": 2.16,
      "grad_norm": 0.23076632618904114,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 0.5094,
      "step": 1080
    },
    {
      "epoch": 2.162,
      "grad_norm": 0.23180313408374786,
      "learning_rate": 3.919e-05,
      "loss": 0.5651,
      "step": 1081
    },
    {
      "epoch": 2.164,
      "grad_norm": 0.22800596058368683,
      "learning_rate": 3.918e-05,
      "loss": 0.4437,
      "step": 1082
    },
    {
      "epoch": 2.166,
      "grad_norm": 0.2834121584892273,
      "learning_rate": 3.917e-05,
      "loss": 0.5514,
      "step": 1083
    },
    {
      "epoch": 2.168,
      "grad_norm": 0.21410004794597626,
      "learning_rate": 3.9160000000000005e-05,
      "loss": 0.5601,
      "step": 1084
    },
    {
      "epoch": 2.17,
      "grad_norm": 0.23435719311237335,
      "learning_rate": 3.915e-05,
      "loss": 0.4677,
      "step": 1085
    },
    {
      "epoch": 2.172,
      "grad_norm": 0.24208413064479828,
      "learning_rate": 3.914e-05,
      "loss": 0.575,
      "step": 1086
    },
    {
      "epoch": 2.174,
      "grad_norm": 0.2928978502750397,
      "learning_rate": 3.913e-05,
      "loss": 0.6441,
      "step": 1087
    },
    {
      "epoch": 2.176,
      "grad_norm": 0.24352501332759857,
      "learning_rate": 3.912e-05,
      "loss": 0.4845,
      "step": 1088
    },
    {
      "epoch": 2.178,
      "grad_norm": 0.23127582669258118,
      "learning_rate": 3.911e-05,
      "loss": 0.5877,
      "step": 1089
    },
    {
      "epoch": 2.18,
      "grad_norm": 0.2425108104944229,
      "learning_rate": 3.91e-05,
      "loss": 0.5549,
      "step": 1090
    },
    {
      "epoch": 2.182,
      "grad_norm": 0.22946766018867493,
      "learning_rate": 3.909000000000001e-05,
      "loss": 0.5377,
      "step": 1091
    },
    {
      "epoch": 2.184,
      "grad_norm": 0.22083094716072083,
      "learning_rate": 3.908e-05,
      "loss": 0.5841,
      "step": 1092
    },
    {
      "epoch": 2.186,
      "grad_norm": 0.2550792098045349,
      "learning_rate": 3.9070000000000004e-05,
      "loss": 0.5348,
      "step": 1093
    },
    {
      "epoch": 2.188,
      "grad_norm": 0.22484949231147766,
      "learning_rate": 3.906e-05,
      "loss": 0.5632,
      "step": 1094
    },
    {
      "epoch": 2.19,
      "grad_norm": 0.21601122617721558,
      "learning_rate": 3.905e-05,
      "loss": 0.5059,
      "step": 1095
    },
    {
      "epoch": 2.192,
      "grad_norm": 0.22118137776851654,
      "learning_rate": 3.9040000000000006e-05,
      "loss": 0.5811,
      "step": 1096
    },
    {
      "epoch": 2.194,
      "grad_norm": 0.26987406611442566,
      "learning_rate": 3.903e-05,
      "loss": 0.6285,
      "step": 1097
    },
    {
      "epoch": 2.196,
      "grad_norm": 0.20037396252155304,
      "learning_rate": 3.902e-05,
      "loss": 0.5504,
      "step": 1098
    },
    {
      "epoch": 2.198,
      "grad_norm": 0.2180766761302948,
      "learning_rate": 3.901e-05,
      "loss": 0.594,
      "step": 1099
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.219328373670578,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.5788,
      "step": 1100
    },
    {
      "epoch": 2.202,
      "grad_norm": 0.21294790506362915,
      "learning_rate": 3.8990000000000004e-05,
      "loss": 0.5512,
      "step": 1101
    },
    {
      "epoch": 2.204,
      "grad_norm": 0.2298852503299713,
      "learning_rate": 3.898e-05,
      "loss": 0.5362,
      "step": 1102
    },
    {
      "epoch": 2.206,
      "grad_norm": 0.22244185209274292,
      "learning_rate": 3.897e-05,
      "loss": 0.5054,
      "step": 1103
    },
    {
      "epoch": 2.208,
      "grad_norm": 0.20233727991580963,
      "learning_rate": 3.896e-05,
      "loss": 0.518,
      "step": 1104
    },
    {
      "epoch": 2.21,
      "grad_norm": 0.22405940294265747,
      "learning_rate": 3.8950000000000005e-05,
      "loss": 0.5718,
      "step": 1105
    },
    {
      "epoch": 2.212,
      "grad_norm": 0.2102762758731842,
      "learning_rate": 3.894e-05,
      "loss": 0.4936,
      "step": 1106
    },
    {
      "epoch": 2.214,
      "grad_norm": 0.19645659625530243,
      "learning_rate": 3.893e-05,
      "loss": 0.432,
      "step": 1107
    },
    {
      "epoch": 2.216,
      "grad_norm": 0.23301316797733307,
      "learning_rate": 3.892e-05,
      "loss": 0.5298,
      "step": 1108
    },
    {
      "epoch": 2.218,
      "grad_norm": 0.2393760234117508,
      "learning_rate": 3.8910000000000005e-05,
      "loss": 0.5487,
      "step": 1109
    },
    {
      "epoch": 2.22,
      "grad_norm": 0.22411087155342102,
      "learning_rate": 3.8900000000000004e-05,
      "loss": 0.5053,
      "step": 1110
    },
    {
      "epoch": 2.222,
      "grad_norm": 0.2210693508386612,
      "learning_rate": 3.889e-05,
      "loss": 0.6067,
      "step": 1111
    },
    {
      "epoch": 2.224,
      "grad_norm": 0.235130175948143,
      "learning_rate": 3.888e-05,
      "loss": 0.576,
      "step": 1112
    },
    {
      "epoch": 2.226,
      "grad_norm": 0.2377382218837738,
      "learning_rate": 3.887e-05,
      "loss": 0.5263,
      "step": 1113
    },
    {
      "epoch": 2.228,
      "grad_norm": 0.2421228140592575,
      "learning_rate": 3.8860000000000004e-05,
      "loss": 0.6216,
      "step": 1114
    },
    {
      "epoch": 2.23,
      "grad_norm": 0.24329040944576263,
      "learning_rate": 3.885e-05,
      "loss": 0.5613,
      "step": 1115
    },
    {
      "epoch": 2.232,
      "grad_norm": 0.20890939235687256,
      "learning_rate": 3.884e-05,
      "loss": 0.5432,
      "step": 1116
    },
    {
      "epoch": 2.234,
      "grad_norm": 0.24169021844863892,
      "learning_rate": 3.883e-05,
      "loss": 0.5293,
      "step": 1117
    },
    {
      "epoch": 2.2359999999999998,
      "grad_norm": 0.21673136949539185,
      "learning_rate": 3.882e-05,
      "loss": 0.5403,
      "step": 1118
    },
    {
      "epoch": 2.238,
      "grad_norm": 0.2557161748409271,
      "learning_rate": 3.881e-05,
      "loss": 0.5339,
      "step": 1119
    },
    {
      "epoch": 2.24,
      "grad_norm": 0.23125320672988892,
      "learning_rate": 3.88e-05,
      "loss": 0.592,
      "step": 1120
    },
    {
      "epoch": 2.242,
      "grad_norm": 0.20030373334884644,
      "learning_rate": 3.8790000000000006e-05,
      "loss": 0.5503,
      "step": 1121
    },
    {
      "epoch": 2.2439999999999998,
      "grad_norm": 0.24123123288154602,
      "learning_rate": 3.878e-05,
      "loss": 0.4135,
      "step": 1122
    },
    {
      "epoch": 2.246,
      "grad_norm": 0.2905665636062622,
      "learning_rate": 3.877e-05,
      "loss": 0.5786,
      "step": 1123
    },
    {
      "epoch": 2.248,
      "grad_norm": 0.2328137904405594,
      "learning_rate": 3.876e-05,
      "loss": 0.5716,
      "step": 1124
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.2417079508304596,
      "learning_rate": 3.875e-05,
      "loss": 0.5863,
      "step": 1125
    },
    {
      "epoch": 2.252,
      "grad_norm": 0.23080268502235413,
      "learning_rate": 3.8740000000000005e-05,
      "loss": 0.4844,
      "step": 1126
    },
    {
      "epoch": 2.254,
      "grad_norm": 0.21996165812015533,
      "learning_rate": 3.873e-05,
      "loss": 0.5092,
      "step": 1127
    },
    {
      "epoch": 2.2560000000000002,
      "grad_norm": 0.2577206492424011,
      "learning_rate": 3.872e-05,
      "loss": 0.5431,
      "step": 1128
    },
    {
      "epoch": 2.258,
      "grad_norm": 0.25457316637039185,
      "learning_rate": 3.871e-05,
      "loss": 0.6858,
      "step": 1129
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.2645741105079651,
      "learning_rate": 3.8700000000000006e-05,
      "loss": 0.5619,
      "step": 1130
    },
    {
      "epoch": 2.262,
      "grad_norm": 0.22185394167900085,
      "learning_rate": 3.8690000000000004e-05,
      "loss": 0.559,
      "step": 1131
    },
    {
      "epoch": 2.2640000000000002,
      "grad_norm": 0.2066442221403122,
      "learning_rate": 3.868e-05,
      "loss": 0.5291,
      "step": 1132
    },
    {
      "epoch": 2.266,
      "grad_norm": 0.2601262032985687,
      "learning_rate": 3.867e-05,
      "loss": 0.6364,
      "step": 1133
    },
    {
      "epoch": 2.268,
      "grad_norm": 0.22718307375907898,
      "learning_rate": 3.866e-05,
      "loss": 0.5746,
      "step": 1134
    },
    {
      "epoch": 2.27,
      "grad_norm": 0.2720508873462677,
      "learning_rate": 3.8650000000000004e-05,
      "loss": 0.6349,
      "step": 1135
    },
    {
      "epoch": 2.2720000000000002,
      "grad_norm": 0.22701649367809296,
      "learning_rate": 3.864e-05,
      "loss": 0.6053,
      "step": 1136
    },
    {
      "epoch": 2.274,
      "grad_norm": 0.2616439163684845,
      "learning_rate": 3.863e-05,
      "loss": 0.5182,
      "step": 1137
    },
    {
      "epoch": 2.276,
      "grad_norm": 0.27830225229263306,
      "learning_rate": 3.862e-05,
      "loss": 0.5754,
      "step": 1138
    },
    {
      "epoch": 2.278,
      "grad_norm": 0.20636102557182312,
      "learning_rate": 3.8610000000000005e-05,
      "loss": 0.5245,
      "step": 1139
    },
    {
      "epoch": 2.2800000000000002,
      "grad_norm": 0.21962614357471466,
      "learning_rate": 3.86e-05,
      "loss": 0.59,
      "step": 1140
    },
    {
      "epoch": 2.282,
      "grad_norm": 0.21946291625499725,
      "learning_rate": 3.859e-05,
      "loss": 0.5318,
      "step": 1141
    },
    {
      "epoch": 2.284,
      "grad_norm": 0.22070477902889252,
      "learning_rate": 3.858e-05,
      "loss": 0.5564,
      "step": 1142
    },
    {
      "epoch": 2.286,
      "grad_norm": 0.27207010984420776,
      "learning_rate": 3.857e-05,
      "loss": 0.5756,
      "step": 1143
    },
    {
      "epoch": 2.288,
      "grad_norm": 0.27739766240119934,
      "learning_rate": 3.8560000000000004e-05,
      "loss": 0.5278,
      "step": 1144
    },
    {
      "epoch": 2.29,
      "grad_norm": 0.22324499487876892,
      "learning_rate": 3.855e-05,
      "loss": 0.5717,
      "step": 1145
    },
    {
      "epoch": 2.292,
      "grad_norm": 0.23215104639530182,
      "learning_rate": 3.854000000000001e-05,
      "loss": 0.6419,
      "step": 1146
    },
    {
      "epoch": 2.294,
      "grad_norm": 0.20787887275218964,
      "learning_rate": 3.853e-05,
      "loss": 0.582,
      "step": 1147
    },
    {
      "epoch": 2.296,
      "grad_norm": 0.20145432651042938,
      "learning_rate": 3.8520000000000004e-05,
      "loss": 0.4721,
      "step": 1148
    },
    {
      "epoch": 2.298,
      "grad_norm": 0.23586659133434296,
      "learning_rate": 3.851e-05,
      "loss": 0.5895,
      "step": 1149
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.2162531614303589,
      "learning_rate": 3.85e-05,
      "loss": 0.4895,
      "step": 1150
    },
    {
      "epoch": 2.302,
      "grad_norm": 0.21131418645381927,
      "learning_rate": 3.8490000000000006e-05,
      "loss": 0.5607,
      "step": 1151
    },
    {
      "epoch": 2.304,
      "grad_norm": 0.21754594147205353,
      "learning_rate": 3.848e-05,
      "loss": 0.4685,
      "step": 1152
    },
    {
      "epoch": 2.306,
      "grad_norm": 0.23733021318912506,
      "learning_rate": 3.847e-05,
      "loss": 0.5187,
      "step": 1153
    },
    {
      "epoch": 2.308,
      "grad_norm": 0.22440409660339355,
      "learning_rate": 3.846e-05,
      "loss": 0.6549,
      "step": 1154
    },
    {
      "epoch": 2.31,
      "grad_norm": 0.21810773015022278,
      "learning_rate": 3.845e-05,
      "loss": 0.5227,
      "step": 1155
    },
    {
      "epoch": 2.312,
      "grad_norm": 0.22836032509803772,
      "learning_rate": 3.8440000000000005e-05,
      "loss": 0.5562,
      "step": 1156
    },
    {
      "epoch": 2.314,
      "grad_norm": 0.2178371548652649,
      "learning_rate": 3.8429999999999996e-05,
      "loss": 0.4847,
      "step": 1157
    },
    {
      "epoch": 2.316,
      "grad_norm": 0.22366905212402344,
      "learning_rate": 3.842e-05,
      "loss": 0.5684,
      "step": 1158
    },
    {
      "epoch": 2.318,
      "grad_norm": 0.21383610367774963,
      "learning_rate": 3.841e-05,
      "loss": 0.5217,
      "step": 1159
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.2699750065803528,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.5617,
      "step": 1160
    },
    {
      "epoch": 2.322,
      "grad_norm": 0.2394636571407318,
      "learning_rate": 3.8390000000000003e-05,
      "loss": 0.5369,
      "step": 1161
    },
    {
      "epoch": 2.324,
      "grad_norm": 0.22675740718841553,
      "learning_rate": 3.838e-05,
      "loss": 0.5482,
      "step": 1162
    },
    {
      "epoch": 2.326,
      "grad_norm": 0.2006162852048874,
      "learning_rate": 3.837e-05,
      "loss": 0.509,
      "step": 1163
    },
    {
      "epoch": 2.328,
      "grad_norm": 0.2551890015602112,
      "learning_rate": 3.836e-05,
      "loss": 0.488,
      "step": 1164
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.20632576942443848,
      "learning_rate": 3.8350000000000004e-05,
      "loss": 0.4869,
      "step": 1165
    },
    {
      "epoch": 2.332,
      "grad_norm": 0.20424461364746094,
      "learning_rate": 3.834e-05,
      "loss": 0.5745,
      "step": 1166
    },
    {
      "epoch": 2.334,
      "grad_norm": 0.2168879508972168,
      "learning_rate": 3.833e-05,
      "loss": 0.5208,
      "step": 1167
    },
    {
      "epoch": 2.336,
      "grad_norm": 0.2205127477645874,
      "learning_rate": 3.832e-05,
      "loss": 0.5025,
      "step": 1168
    },
    {
      "epoch": 2.338,
      "grad_norm": 0.23642250895500183,
      "learning_rate": 3.8310000000000004e-05,
      "loss": 0.5903,
      "step": 1169
    },
    {
      "epoch": 2.34,
      "grad_norm": 0.22600825130939484,
      "learning_rate": 3.83e-05,
      "loss": 0.4807,
      "step": 1170
    },
    {
      "epoch": 2.342,
      "grad_norm": 0.22957386076450348,
      "learning_rate": 3.829e-05,
      "loss": 0.5777,
      "step": 1171
    },
    {
      "epoch": 2.344,
      "grad_norm": 0.24798931181430817,
      "learning_rate": 3.828e-05,
      "loss": 0.5857,
      "step": 1172
    },
    {
      "epoch": 2.346,
      "grad_norm": 0.2501101493835449,
      "learning_rate": 3.827e-05,
      "loss": 0.5004,
      "step": 1173
    },
    {
      "epoch": 2.348,
      "grad_norm": 0.24327729642391205,
      "learning_rate": 3.826e-05,
      "loss": 0.6353,
      "step": 1174
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.26182571053504944,
      "learning_rate": 3.825e-05,
      "loss": 0.5299,
      "step": 1175
    },
    {
      "epoch": 2.352,
      "grad_norm": 0.24347805976867676,
      "learning_rate": 3.8240000000000007e-05,
      "loss": 0.6362,
      "step": 1176
    },
    {
      "epoch": 2.354,
      "grad_norm": 0.23492677509784698,
      "learning_rate": 3.823e-05,
      "loss": 0.5888,
      "step": 1177
    },
    {
      "epoch": 2.356,
      "grad_norm": 0.2524511516094208,
      "learning_rate": 3.822e-05,
      "loss": 0.6127,
      "step": 1178
    },
    {
      "epoch": 2.358,
      "grad_norm": 0.23998746275901794,
      "learning_rate": 3.821e-05,
      "loss": 0.5543,
      "step": 1179
    },
    {
      "epoch": 2.36,
      "grad_norm": 0.22162604331970215,
      "learning_rate": 3.82e-05,
      "loss": 0.58,
      "step": 1180
    },
    {
      "epoch": 2.362,
      "grad_norm": 0.21816958487033844,
      "learning_rate": 3.8190000000000005e-05,
      "loss": 0.4873,
      "step": 1181
    },
    {
      "epoch": 2.364,
      "grad_norm": 0.20614151656627655,
      "learning_rate": 3.818e-05,
      "loss": 0.5233,
      "step": 1182
    },
    {
      "epoch": 2.366,
      "grad_norm": 0.22421181201934814,
      "learning_rate": 3.817e-05,
      "loss": 0.5244,
      "step": 1183
    },
    {
      "epoch": 2.368,
      "grad_norm": 0.23380468785762787,
      "learning_rate": 3.816e-05,
      "loss": 0.4835,
      "step": 1184
    },
    {
      "epoch": 2.37,
      "grad_norm": 0.23658302426338196,
      "learning_rate": 3.8150000000000006e-05,
      "loss": 0.6125,
      "step": 1185
    },
    {
      "epoch": 2.372,
      "grad_norm": 0.2474319487810135,
      "learning_rate": 3.8140000000000004e-05,
      "loss": 0.6016,
      "step": 1186
    },
    {
      "epoch": 2.374,
      "grad_norm": 0.2601548135280609,
      "learning_rate": 3.8129999999999996e-05,
      "loss": 0.5145,
      "step": 1187
    },
    {
      "epoch": 2.376,
      "grad_norm": 0.2442774921655655,
      "learning_rate": 3.812e-05,
      "loss": 0.5756,
      "step": 1188
    },
    {
      "epoch": 2.378,
      "grad_norm": 0.2299203872680664,
      "learning_rate": 3.811e-05,
      "loss": 0.5553,
      "step": 1189
    },
    {
      "epoch": 2.38,
      "grad_norm": 0.21725517511367798,
      "learning_rate": 3.8100000000000005e-05,
      "loss": 0.5216,
      "step": 1190
    },
    {
      "epoch": 2.382,
      "grad_norm": 0.23462055623531342,
      "learning_rate": 3.809e-05,
      "loss": 0.5489,
      "step": 1191
    },
    {
      "epoch": 2.384,
      "grad_norm": 0.21845324337482452,
      "learning_rate": 3.808e-05,
      "loss": 0.5335,
      "step": 1192
    },
    {
      "epoch": 2.386,
      "grad_norm": 0.23328767716884613,
      "learning_rate": 3.807e-05,
      "loss": 0.5462,
      "step": 1193
    },
    {
      "epoch": 2.388,
      "grad_norm": 0.23643261194229126,
      "learning_rate": 3.806e-05,
      "loss": 0.5572,
      "step": 1194
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.2143084853887558,
      "learning_rate": 3.805e-05,
      "loss": 0.4858,
      "step": 1195
    },
    {
      "epoch": 2.392,
      "grad_norm": 0.21531163156032562,
      "learning_rate": 3.804e-05,
      "loss": 0.4647,
      "step": 1196
    },
    {
      "epoch": 2.394,
      "grad_norm": 0.24806390702724457,
      "learning_rate": 3.803000000000001e-05,
      "loss": 0.5758,
      "step": 1197
    },
    {
      "epoch": 2.396,
      "grad_norm": 0.24888557195663452,
      "learning_rate": 3.802e-05,
      "loss": 0.5831,
      "step": 1198
    },
    {
      "epoch": 2.398,
      "grad_norm": 0.21910586953163147,
      "learning_rate": 3.8010000000000004e-05,
      "loss": 0.5288,
      "step": 1199
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.24126410484313965,
      "learning_rate": 3.8e-05,
      "loss": 0.5372,
      "step": 1200
    }
  ],
  "logging_steps": 1,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.601053976526848e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}