{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00909090909090909,
      "grad_norm": 5.665040969848633,
      "learning_rate": 0.001,
      "loss": 3.2237,
      "step": 1
    },
    {
      "epoch": 0.01818181818181818,
      "grad_norm": 4.213883399963379,
      "learning_rate": 0.000996969696969697,
      "loss": 2.7254,
      "step": 2
    },
    {
      "epoch": 0.02727272727272727,
      "grad_norm": 3.3348634243011475,
      "learning_rate": 0.000993939393939394,
      "loss": 2.6316,
      "step": 3
    },
    {
      "epoch": 0.03636363636363636,
      "grad_norm": 4.175114154815674,
      "learning_rate": 0.000990909090909091,
      "loss": 2.5194,
      "step": 4
    },
    {
      "epoch": 0.045454545454545456,
      "grad_norm": 3.9401752948760986,
      "learning_rate": 0.000987878787878788,
      "loss": 2.7733,
      "step": 5
    },
    {
      "epoch": 0.05454545454545454,
      "grad_norm": 3.072375774383545,
      "learning_rate": 0.000984848484848485,
      "loss": 2.6526,
      "step": 6
    },
    {
      "epoch": 0.06363636363636363,
      "grad_norm": 2.7777438163757324,
      "learning_rate": 0.0009818181818181818,
      "loss": 1.8668,
      "step": 7
    },
    {
      "epoch": 0.07272727272727272,
      "grad_norm": 3.6554815769195557,
      "learning_rate": 0.0009787878787878787,
      "loss": 2.806,
      "step": 8
    },
    {
      "epoch": 0.08181818181818182,
      "grad_norm": 3.1596930027008057,
      "learning_rate": 0.0009757575757575757,
      "loss": 2.3411,
      "step": 9
    },
    {
      "epoch": 0.09090909090909091,
      "grad_norm": 3.395393133163452,
      "learning_rate": 0.0009727272727272728,
      "loss": 2.1094,
      "step": 10
    },
    {
      "epoch": 0.1,
      "grad_norm": 3.1888489723205566,
      "learning_rate": 0.0009696969696969698,
      "loss": 2.4204,
      "step": 11
    },
    {
      "epoch": 0.10909090909090909,
      "grad_norm": 3.4513046741485596,
      "learning_rate": 0.0009666666666666667,
      "loss": 2.4544,
      "step": 12
    },
    {
      "epoch": 0.11818181818181818,
      "grad_norm": 2.7531213760375977,
      "learning_rate": 0.0009636363636363637,
      "loss": 2.1506,
      "step": 13
    },
    {
      "epoch": 0.12727272727272726,
      "grad_norm": 3.208503246307373,
      "learning_rate": 0.0009606060606060606,
      "loss": 2.3214,
      "step": 14
    },
    {
      "epoch": 0.13636363636363635,
      "grad_norm": 3.3703765869140625,
      "learning_rate": 0.0009575757575757576,
      "loss": 2.391,
      "step": 15
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": 3.4211888313293457,
      "learning_rate": 0.0009545454545454546,
      "loss": 2.11,
      "step": 16
    },
    {
      "epoch": 0.15454545454545454,
      "grad_norm": 3.6409544944763184,
      "learning_rate": 0.0009515151515151516,
      "loss": 2.1259,
      "step": 17
    },
    {
      "epoch": 0.16363636363636364,
      "grad_norm": 2.8954989910125732,
      "learning_rate": 0.0009484848484848486,
      "loss": 2.355,
      "step": 18
    },
    {
      "epoch": 0.17272727272727273,
      "grad_norm": 3.888411045074463,
      "learning_rate": 0.0009454545454545454,
      "loss": 2.4117,
      "step": 19
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.7836341857910156,
      "learning_rate": 0.0009424242424242424,
      "loss": 2.3758,
      "step": 20
    },
    {
      "epoch": 0.19090909090909092,
      "grad_norm": 2.7203328609466553,
      "learning_rate": 0.0009393939393939394,
      "loss": 2.1513,
      "step": 21
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.068617582321167,
      "learning_rate": 0.0009363636363636364,
      "loss": 2.2397,
      "step": 22
    },
    {
      "epoch": 0.20909090909090908,
      "grad_norm": 3.331226110458374,
      "learning_rate": 0.0009333333333333333,
      "loss": 2.2208,
      "step": 23
    },
    {
      "epoch": 0.21818181818181817,
      "grad_norm": 2.6493046283721924,
      "learning_rate": 0.0009303030303030303,
      "loss": 1.7146,
      "step": 24
    },
    {
      "epoch": 0.22727272727272727,
      "grad_norm": 3.1719207763671875,
      "learning_rate": 0.0009272727272727273,
      "loss": 1.9304,
      "step": 25
    },
    {
      "epoch": 0.23636363636363636,
      "grad_norm": 2.7667529582977295,
      "learning_rate": 0.0009242424242424242,
      "loss": 1.9621,
      "step": 26
    },
    {
      "epoch": 0.24545454545454545,
      "grad_norm": 3.3443210124969482,
      "learning_rate": 0.0009212121212121213,
      "loss": 2.4454,
      "step": 27
    },
    {
      "epoch": 0.2545454545454545,
      "grad_norm": 3.644787311553955,
      "learning_rate": 0.0009181818181818182,
      "loss": 2.7365,
      "step": 28
    },
    {
      "epoch": 0.2636363636363636,
      "grad_norm": 3.105468988418579,
      "learning_rate": 0.0009151515151515152,
      "loss": 2.4995,
      "step": 29
    },
    {
      "epoch": 0.2727272727272727,
      "grad_norm": 2.935793876647949,
      "learning_rate": 0.0009121212121212121,
      "loss": 2.3143,
      "step": 30
    },
    {
      "epoch": 0.2818181818181818,
      "grad_norm": 2.8935372829437256,
      "learning_rate": 0.0009090909090909091,
      "loss": 2.1376,
      "step": 31
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": 2.6549243927001953,
      "learning_rate": 0.000906060606060606,
      "loss": 2.2932,
      "step": 32
    },
    {
      "epoch": 0.3,
      "grad_norm": 3.13305926322937,
      "learning_rate": 0.0009030303030303031,
      "loss": 2.1224,
      "step": 33
    },
    {
      "epoch": 0.3090909090909091,
      "grad_norm": 2.6850459575653076,
      "learning_rate": 0.0009000000000000001,
      "loss": 2.3033,
      "step": 34
    },
    {
      "epoch": 0.3181818181818182,
      "grad_norm": 2.9505958557128906,
      "learning_rate": 0.000896969696969697,
      "loss": 2.2389,
      "step": 35
    },
    {
      "epoch": 0.32727272727272727,
      "grad_norm": 3.228408098220825,
      "learning_rate": 0.000893939393939394,
      "loss": 1.9583,
      "step": 36
    },
    {
      "epoch": 0.33636363636363636,
      "grad_norm": 3.032721757888794,
      "learning_rate": 0.0008909090909090909,
      "loss": 2.2626,
      "step": 37
    },
    {
      "epoch": 0.34545454545454546,
      "grad_norm": 3.150395631790161,
      "learning_rate": 0.000887878787878788,
      "loss": 2.5744,
      "step": 38
    },
    {
      "epoch": 0.35454545454545455,
      "grad_norm": 2.4964640140533447,
      "learning_rate": 0.0008848484848484849,
      "loss": 2.0985,
      "step": 39
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.5252561569213867,
      "learning_rate": 0.0008818181818181819,
      "loss": 1.7968,
      "step": 40
    },
    {
      "epoch": 0.37272727272727274,
      "grad_norm": 3.1341795921325684,
      "learning_rate": 0.0008787878787878789,
      "loss": 2.3209,
      "step": 41
    },
    {
      "epoch": 0.38181818181818183,
      "grad_norm": 2.343937397003174,
      "learning_rate": 0.0008757575757575757,
      "loss": 2.5445,
      "step": 42
    },
    {
      "epoch": 0.39090909090909093,
      "grad_norm": 2.7909810543060303,
      "learning_rate": 0.0008727272727272727,
      "loss": 2.192,
      "step": 43
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.5907089710235596,
      "learning_rate": 0.0008696969696969697,
      "loss": 1.7104,
      "step": 44
    },
    {
      "epoch": 0.4090909090909091,
      "grad_norm": 2.5267434120178223,
      "learning_rate": 0.0008666666666666667,
      "loss": 1.8205,
      "step": 45
    },
    {
      "epoch": 0.41818181818181815,
      "grad_norm": 2.3627917766571045,
      "learning_rate": 0.0008636363636363636,
      "loss": 1.8828,
      "step": 46
    },
    {
      "epoch": 0.42727272727272725,
      "grad_norm": 3.309234142303467,
      "learning_rate": 0.0008606060606060606,
      "loss": 2.3486,
      "step": 47
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": 2.6482889652252197,
      "learning_rate": 0.0008575757575757575,
      "loss": 1.9503,
      "step": 48
    },
    {
      "epoch": 0.44545454545454544,
      "grad_norm": 2.395134687423706,
      "learning_rate": 0.0008545454545454545,
      "loss": 1.7914,
      "step": 49
    },
    {
      "epoch": 0.45454545454545453,
      "grad_norm": 2.543719530105591,
      "learning_rate": 0.0008515151515151516,
      "loss": 2.3357,
      "step": 50
    },
    {
      "epoch": 0.4636363636363636,
      "grad_norm": 3.097923517227173,
      "learning_rate": 0.0008484848484848485,
      "loss": 2.3008,
      "step": 51
    },
    {
      "epoch": 0.4727272727272727,
      "grad_norm": 2.509481191635132,
      "learning_rate": 0.0008454545454545455,
      "loss": 2.3587,
      "step": 52
    },
    {
      "epoch": 0.4818181818181818,
      "grad_norm": 2.7688727378845215,
      "learning_rate": 0.0008424242424242424,
      "loss": 2.1728,
      "step": 53
    },
    {
      "epoch": 0.4909090909090909,
      "grad_norm": 2.68802547454834,
      "learning_rate": 0.0008393939393939394,
      "loss": 2.2718,
      "step": 54
    },
    {
      "epoch": 0.5,
      "grad_norm": 2.38201904296875,
      "learning_rate": 0.0008363636363636363,
      "loss": 1.932,
      "step": 55
    },
    {
      "epoch": 0.509090909090909,
      "grad_norm": 2.4522223472595215,
      "learning_rate": 0.0008333333333333334,
      "loss": 1.7194,
      "step": 56
    },
    {
      "epoch": 0.5181818181818182,
      "grad_norm": 3.0071616172790527,
      "learning_rate": 0.0008303030303030304,
      "loss": 2.3589,
      "step": 57
    },
    {
      "epoch": 0.5272727272727272,
      "grad_norm": 2.3861336708068848,
      "learning_rate": 0.0008272727272727273,
      "loss": 2.1155,
      "step": 58
    },
    {
      "epoch": 0.5363636363636364,
      "grad_norm": 2.8061254024505615,
      "learning_rate": 0.0008242424242424243,
      "loss": 2.1691,
      "step": 59
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 2.481740951538086,
      "learning_rate": 0.0008212121212121212,
      "loss": 1.8603,
      "step": 60
    },
    {
      "epoch": 0.5545454545454546,
      "grad_norm": 2.681589365005493,
      "learning_rate": 0.0008181818181818183,
      "loss": 2.3706,
      "step": 61
    },
    {
      "epoch": 0.5636363636363636,
      "grad_norm": 2.509098768234253,
      "learning_rate": 0.0008151515151515152,
      "loss": 1.8332,
      "step": 62
    },
    {
      "epoch": 0.5727272727272728,
      "grad_norm": 2.8032596111297607,
      "learning_rate": 0.0008121212121212122,
      "loss": 2.0156,
      "step": 63
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": 2.3624141216278076,
      "learning_rate": 0.0008090909090909092,
      "loss": 1.7122,
      "step": 64
    },
    {
      "epoch": 0.5909090909090909,
      "grad_norm": 2.6861467361450195,
      "learning_rate": 0.000806060606060606,
      "loss": 1.8449,
      "step": 65
    },
    {
      "epoch": 0.6,
      "grad_norm": 2.547766923904419,
      "learning_rate": 0.000803030303030303,
      "loss": 1.9611,
      "step": 66
    },
    {
      "epoch": 0.6090909090909091,
      "grad_norm": 3.040510416030884,
      "learning_rate": 0.0008,
      "loss": 2.6715,
      "step": 67
    },
    {
      "epoch": 0.6181818181818182,
      "grad_norm": 3.57930064201355,
      "learning_rate": 0.000796969696969697,
      "loss": 2.0624,
      "step": 68
    },
    {
      "epoch": 0.6272727272727273,
      "grad_norm": 3.1566851139068604,
      "learning_rate": 0.0007939393939393939,
      "loss": 2.0065,
      "step": 69
    },
    {
      "epoch": 0.6363636363636364,
      "grad_norm": 2.6310720443725586,
      "learning_rate": 0.0007909090909090909,
      "loss": 1.5961,
      "step": 70
    },
    {
      "epoch": 0.6454545454545455,
      "grad_norm": 2.786461591720581,
      "learning_rate": 0.0007878787878787878,
      "loss": 1.9295,
      "step": 71
    },
    {
      "epoch": 0.6545454545454545,
      "grad_norm": 2.86108136177063,
      "learning_rate": 0.0007848484848484848,
      "loss": 2.0496,
      "step": 72
    },
    {
      "epoch": 0.6636363636363637,
      "grad_norm": 3.1573517322540283,
      "learning_rate": 0.0007818181818181819,
      "loss": 2.0882,
      "step": 73
    },
    {
      "epoch": 0.6727272727272727,
      "grad_norm": 3.606954336166382,
      "learning_rate": 0.0007787878787878788,
      "loss": 2.1405,
      "step": 74
    },
    {
      "epoch": 0.6818181818181818,
      "grad_norm": 2.636775255203247,
      "learning_rate": 0.0007757575757575758,
      "loss": 2.121,
      "step": 75
    },
    {
      "epoch": 0.6909090909090909,
      "grad_norm": 2.7421998977661133,
      "learning_rate": 0.0007727272727272727,
      "loss": 1.8807,
      "step": 76
    },
    {
      "epoch": 0.7,
      "grad_norm": 3.12371826171875,
      "learning_rate": 0.0007696969696969697,
      "loss": 2.0103,
      "step": 77
    },
    {
      "epoch": 0.7090909090909091,
      "grad_norm": 3.1188058853149414,
      "learning_rate": 0.0007666666666666667,
      "loss": 2.013,
      "step": 78
    },
    {
      "epoch": 0.7181818181818181,
      "grad_norm": 2.4656403064727783,
      "learning_rate": 0.0007636363636363637,
      "loss": 2.0458,
      "step": 79
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 2.941725969314575,
      "learning_rate": 0.0007606060606060607,
      "loss": 1.773,
      "step": 80
    },
    {
      "epoch": 0.7363636363636363,
      "grad_norm": 2.9364752769470215,
      "learning_rate": 0.0007575757575757576,
      "loss": 2.0031,
      "step": 81
    },
    {
      "epoch": 0.7454545454545455,
      "grad_norm": 2.4230921268463135,
      "learning_rate": 0.0007545454545454546,
      "loss": 2.0012,
      "step": 82
    },
    {
      "epoch": 0.7545454545454545,
      "grad_norm": 3.1850976943969727,
      "learning_rate": 0.0007515151515151515,
      "loss": 2.3248,
      "step": 83
    },
    {
      "epoch": 0.7636363636363637,
      "grad_norm": 3.167229175567627,
      "learning_rate": 0.0007484848484848486,
      "loss": 1.9262,
      "step": 84
    },
    {
      "epoch": 0.7727272727272727,
      "grad_norm": 2.4680087566375732,
      "learning_rate": 0.0007454545454545455,
      "loss": 1.6246,
      "step": 85
    },
    {
      "epoch": 0.7818181818181819,
      "grad_norm": 2.7406013011932373,
      "learning_rate": 0.0007424242424242425,
      "loss": 2.381,
      "step": 86
    },
    {
      "epoch": 0.7909090909090909,
      "grad_norm": 2.7593629360198975,
      "learning_rate": 0.0007393939393939393,
      "loss": 2.0615,
      "step": 87
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.1164543628692627,
      "learning_rate": 0.0007363636363636363,
      "loss": 2.6717,
      "step": 88
    },
    {
      "epoch": 0.8090909090909091,
      "grad_norm": 2.6316466331481934,
      "learning_rate": 0.0007333333333333333,
      "loss": 2.317,
      "step": 89
    },
    {
      "epoch": 0.8181818181818182,
      "grad_norm": 3.0438151359558105,
      "learning_rate": 0.0007303030303030303,
      "loss": 2.0723,
      "step": 90
    },
    {
      "epoch": 0.8272727272727273,
      "grad_norm": 2.9584133625030518,
      "learning_rate": 0.0007272727272727273,
      "loss": 2.1763,
      "step": 91
    },
    {
      "epoch": 0.8363636363636363,
      "grad_norm": 2.3147857189178467,
      "learning_rate": 0.0007242424242424242,
      "loss": 1.8736,
      "step": 92
    },
    {
      "epoch": 0.8454545454545455,
      "grad_norm": 4.842822551727295,
      "learning_rate": 0.0007212121212121212,
      "loss": 1.9492,
      "step": 93
    },
    {
      "epoch": 0.8545454545454545,
      "grad_norm": 2.4618189334869385,
      "learning_rate": 0.0007181818181818181,
      "loss": 1.7265,
      "step": 94
    },
    {
      "epoch": 0.8636363636363636,
      "grad_norm": 2.5660629272460938,
      "learning_rate": 0.0007151515151515152,
      "loss": 1.6217,
      "step": 95
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": 2.756845474243164,
      "learning_rate": 0.0007121212121212122,
      "loss": 1.7652,
      "step": 96
    },
    {
      "epoch": 0.8818181818181818,
      "grad_norm": 3.031113386154175,
      "learning_rate": 0.0007090909090909091,
      "loss": 1.7428,
      "step": 97
    },
    {
      "epoch": 0.8909090909090909,
      "grad_norm": 2.649324893951416,
      "learning_rate": 0.0007060606060606061,
      "loss": 2.1218,
      "step": 98
    },
    {
      "epoch": 0.9,
      "grad_norm": 3.04146409034729,
      "learning_rate": 0.000703030303030303,
      "loss": 1.9781,
      "step": 99
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 3.3008482456207275,
      "learning_rate": 0.0007,
      "loss": 1.8574,
      "step": 100
    },
    {
      "epoch": 0.9181818181818182,
      "grad_norm": 3.4236679077148438,
      "learning_rate": 0.000696969696969697,
      "loss": 1.8579,
      "step": 101
    },
    {
      "epoch": 0.9272727272727272,
      "grad_norm": 2.5228774547576904,
      "learning_rate": 0.000693939393939394,
      "loss": 2.0507,
      "step": 102
    },
    {
      "epoch": 0.9363636363636364,
      "grad_norm": 2.8307383060455322,
      "learning_rate": 0.0006909090909090909,
      "loss": 1.8925,
      "step": 103
    },
    {
      "epoch": 0.9454545454545454,
      "grad_norm": 2.4877798557281494,
      "learning_rate": 0.0006878787878787879,
      "loss": 1.8905,
      "step": 104
    },
    {
      "epoch": 0.9545454545454546,
      "grad_norm": 2.250138282775879,
      "learning_rate": 0.0006848484848484849,
      "loss": 1.7955,
      "step": 105
    },
    {
      "epoch": 0.9636363636363636,
      "grad_norm": 3.187009811401367,
      "learning_rate": 0.0006818181818181818,
      "loss": 1.8573,
      "step": 106
    },
    {
      "epoch": 0.9727272727272728,
      "grad_norm": 2.1931631565093994,
      "learning_rate": 0.0006787878787878789,
      "loss": 1.5388,
      "step": 107
    },
    {
      "epoch": 0.9818181818181818,
      "grad_norm": 3.110795259475708,
      "learning_rate": 0.0006757575757575758,
      "loss": 1.6931,
      "step": 108
    },
    {
      "epoch": 0.990909090909091,
      "grad_norm": 3.2352283000946045,
      "learning_rate": 0.0006727272727272728,
      "loss": 2.3059,
      "step": 109
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.837517499923706,
      "learning_rate": 0.0006696969696969696,
      "loss": 2.1023,
      "step": 110
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.8843,
      "eval_gen_len": 48.7,
      "eval_loss": 1.877951741218567,
      "eval_precision": 0.8815,
      "eval_recall": 0.8873,
      "eval_rouge1": 0.424,
      "eval_rouge2": 0.1972,
      "eval_rougeL": 0.3628,
      "eval_rougeLsum": 0.3926,
      "eval_runtime": 92.4178,
      "eval_samples_per_second": 1.19,
      "eval_steps_per_second": 0.151,
      "step": 110
    },
    {
      "epoch": 1.009090909090909,
      "grad_norm": 2.3287570476531982,
      "learning_rate": 0.0006666666666666666,
      "loss": 1.9052,
      "step": 111
    },
    {
      "epoch": 1.018181818181818,
      "grad_norm": 2.0073699951171875,
      "learning_rate": 0.0006636363636363638,
      "loss": 1.446,
      "step": 112
    },
    {
      "epoch": 1.0272727272727273,
      "grad_norm": 2.168977737426758,
      "learning_rate": 0.0006606060606060606,
      "loss": 1.8199,
      "step": 113
    },
    {
      "epoch": 1.0363636363636364,
      "grad_norm": 2.858215808868408,
      "learning_rate": 0.0006575757575757576,
      "loss": 2.2367,
      "step": 114
    },
    {
      "epoch": 1.0454545454545454,
      "grad_norm": 2.29089617729187,
      "learning_rate": 0.0006545454545454545,
      "loss": 1.6473,
      "step": 115
    },
    {
      "epoch": 1.0545454545454545,
      "grad_norm": 3.0102224349975586,
      "learning_rate": 0.0006515151515151515,
      "loss": 1.9845,
      "step": 116
    },
    {
      "epoch": 1.0636363636363637,
      "grad_norm": 2.2177374362945557,
      "learning_rate": 0.0006484848484848484,
      "loss": 1.3654,
      "step": 117
    },
    {
      "epoch": 1.0727272727272728,
      "grad_norm": 2.297360420227051,
      "learning_rate": 0.0006454545454545455,
      "loss": 1.7296,
      "step": 118
    },
    {
      "epoch": 1.0818181818181818,
      "grad_norm": 2.1550073623657227,
      "learning_rate": 0.0006424242424242425,
      "loss": 1.9423,
      "step": 119
    },
    {
      "epoch": 1.0909090909090908,
      "grad_norm": 2.4641056060791016,
      "learning_rate": 0.0006393939393939394,
      "loss": 2.2135,
      "step": 120
    },
    {
      "epoch": 1.1,
      "grad_norm": 5.603208541870117,
      "learning_rate": 0.0006363636363636364,
      "loss": 1.676,
      "step": 121
    },
    {
      "epoch": 1.1090909090909091,
      "grad_norm": 2.7538461685180664,
      "learning_rate": 0.0006333333333333333,
      "loss": 1.7354,
      "step": 122
    },
    {
      "epoch": 1.1181818181818182,
      "grad_norm": 2.825066328048706,
      "learning_rate": 0.0006303030303030303,
      "loss": 2.0684,
      "step": 123
    },
    {
      "epoch": 1.1272727272727272,
      "grad_norm": 2.937466621398926,
      "learning_rate": 0.0006272727272727273,
      "loss": 2.0502,
      "step": 124
    },
    {
      "epoch": 1.1363636363636362,
      "grad_norm": 2.2857277393341064,
      "learning_rate": 0.0006242424242424243,
      "loss": 1.8194,
      "step": 125
    },
    {
      "epoch": 1.1454545454545455,
      "grad_norm": 2.6627023220062256,
      "learning_rate": 0.0006212121212121212,
      "loss": 1.8175,
      "step": 126
    },
    {
      "epoch": 1.1545454545454545,
      "grad_norm": 2.040328025817871,
      "learning_rate": 0.0006181818181818182,
      "loss": 1.7328,
      "step": 127
    },
    {
      "epoch": 1.1636363636363636,
      "grad_norm": 2.9272687435150146,
      "learning_rate": 0.0006151515151515152,
      "loss": 1.8226,
      "step": 128
    },
    {
      "epoch": 1.1727272727272728,
      "grad_norm": 2.5650229454040527,
      "learning_rate": 0.0006121212121212121,
      "loss": 2.0747,
      "step": 129
    },
    {
      "epoch": 1.1818181818181819,
      "grad_norm": 2.527750015258789,
      "learning_rate": 0.0006090909090909092,
      "loss": 2.0068,
      "step": 130
    },
    {
      "epoch": 1.190909090909091,
      "grad_norm": 2.1396644115448,
      "learning_rate": 0.0006060606060606061,
      "loss": 1.7381,
      "step": 131
    },
    {
      "epoch": 1.2,
      "grad_norm": 2.3363115787506104,
      "learning_rate": 0.0006030303030303031,
      "loss": 1.831,
      "step": 132
    },
    {
      "epoch": 1.209090909090909,
      "grad_norm": 2.6562187671661377,
      "learning_rate": 0.0006,
      "loss": 1.6173,
      "step": 133
    },
    {
      "epoch": 1.2181818181818183,
      "grad_norm": 2.5438387393951416,
      "learning_rate": 0.0005969696969696969,
      "loss": 1.8259,
      "step": 134
    },
    {
      "epoch": 1.2272727272727273,
      "grad_norm": 2.9491357803344727,
      "learning_rate": 0.000593939393939394,
      "loss": 2.0777,
      "step": 135
    },
    {
      "epoch": 1.2363636363636363,
      "grad_norm": 2.413816213607788,
      "learning_rate": 0.0005909090909090909,
      "loss": 1.9164,
      "step": 136
    },
    {
      "epoch": 1.2454545454545454,
      "grad_norm": 2.3370840549468994,
      "learning_rate": 0.0005878787878787879,
      "loss": 1.3178,
      "step": 137
    },
    {
      "epoch": 1.2545454545454544,
      "grad_norm": 2.3356008529663086,
      "learning_rate": 0.0005848484848484848,
      "loss": 1.5996,
      "step": 138
    },
    {
      "epoch": 1.2636363636363637,
      "grad_norm": 2.4713988304138184,
      "learning_rate": 0.0005818181818181818,
      "loss": 1.8534,
      "step": 139
    },
    {
      "epoch": 1.2727272727272727,
      "grad_norm": 2.606344699859619,
      "learning_rate": 0.0005787878787878787,
      "loss": 1.9943,
      "step": 140
    },
    {
      "epoch": 1.2818181818181817,
      "grad_norm": 3.592637300491333,
      "learning_rate": 0.0005757575757575758,
      "loss": 1.9167,
      "step": 141
    },
    {
      "epoch": 1.290909090909091,
      "grad_norm": 2.4633491039276123,
      "learning_rate": 0.0005727272727272727,
      "loss": 1.5882,
      "step": 142
    },
    {
      "epoch": 1.3,
      "grad_norm": 2.452533721923828,
      "learning_rate": 0.0005696969696969697,
      "loss": 1.9909,
      "step": 143
    },
    {
      "epoch": 1.309090909090909,
      "grad_norm": 2.186228036880493,
      "learning_rate": 0.0005666666666666667,
      "loss": 1.5457,
      "step": 144
    },
    {
      "epoch": 1.3181818181818181,
      "grad_norm": 2.7401318550109863,
      "learning_rate": 0.0005636363636363636,
      "loss": 2.1097,
      "step": 145
    },
    {
      "epoch": 1.3272727272727272,
      "grad_norm": 2.6180741786956787,
      "learning_rate": 0.0005606060606060606,
      "loss": 1.8567,
      "step": 146
    },
    {
      "epoch": 1.3363636363636364,
      "grad_norm": 2.243070602416992,
      "learning_rate": 0.0005575757575757576,
      "loss": 1.7541,
      "step": 147
    },
    {
      "epoch": 1.3454545454545455,
      "grad_norm": 3.5008132457733154,
      "learning_rate": 0.0005545454545454546,
      "loss": 2.0835,
      "step": 148
    },
    {
      "epoch": 1.3545454545454545,
      "grad_norm": 3.4842278957366943,
      "learning_rate": 0.0005515151515151515,
      "loss": 1.6775,
      "step": 149
    },
    {
      "epoch": 1.3636363636363638,
      "grad_norm": 2.3027610778808594,
      "learning_rate": 0.0005484848484848485,
      "loss": 1.6217,
      "step": 150
    },
    {
      "epoch": 1.3727272727272728,
      "grad_norm": 2.6352574825286865,
      "learning_rate": 0.0005454545454545455,
      "loss": 1.9762,
      "step": 151
    },
    {
      "epoch": 1.3818181818181818,
      "grad_norm": 2.128300666809082,
      "learning_rate": 0.0005424242424242425,
      "loss": 1.7913,
      "step": 152
    },
    {
      "epoch": 1.3909090909090909,
      "grad_norm": 2.380162239074707,
      "learning_rate": 0.0005393939393939395,
      "loss": 1.7805,
      "step": 153
    },
    {
      "epoch": 1.4,
      "grad_norm": 2.393587350845337,
      "learning_rate": 0.0005363636363636364,
      "loss": 1.9058,
      "step": 154
    },
    {
      "epoch": 1.4090909090909092,
      "grad_norm": 2.346465587615967,
      "learning_rate": 0.0005333333333333334,
      "loss": 1.8443,
      "step": 155
    },
    {
      "epoch": 1.4181818181818182,
      "grad_norm": 2.5013091564178467,
      "learning_rate": 0.0005303030303030302,
      "loss": 1.8411,
      "step": 156
    },
    {
      "epoch": 1.4272727272727272,
      "grad_norm": 2.590817451477051,
      "learning_rate": 0.0005272727272727272,
      "loss": 1.4564,
      "step": 157
    },
    {
      "epoch": 1.4363636363636363,
      "grad_norm": 2.522027015686035,
      "learning_rate": 0.0005242424242424244,
      "loss": 1.8682,
      "step": 158
    },
    {
      "epoch": 1.4454545454545453,
      "grad_norm": 2.5325217247009277,
      "learning_rate": 0.0005212121212121212,
      "loss": 1.7599,
      "step": 159
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 4.200484275817871,
      "learning_rate": 0.0005181818181818182,
      "loss": 2.0001,
      "step": 160
    },
    {
      "epoch": 1.4636363636363636,
      "grad_norm": 2.63664174079895,
      "learning_rate": 0.0005151515151515151,
      "loss": 1.8449,
      "step": 161
    },
    {
      "epoch": 1.4727272727272727,
      "grad_norm": 2.3978261947631836,
      "learning_rate": 0.0005121212121212121,
      "loss": 1.4752,
      "step": 162
    },
    {
      "epoch": 1.481818181818182,
      "grad_norm": 3.072042226791382,
      "learning_rate": 0.000509090909090909,
      "loss": 2.2647,
      "step": 163
    },
    {
      "epoch": 1.490909090909091,
      "grad_norm": 2.5624783039093018,
      "learning_rate": 0.0005060606060606061,
      "loss": 1.7171,
      "step": 164
    },
    {
      "epoch": 1.5,
      "grad_norm": 2.568311929702759,
      "learning_rate": 0.000503030303030303,
      "loss": 1.4561,
      "step": 165
    },
    {
      "epoch": 1.509090909090909,
      "grad_norm": 3.0943450927734375,
      "learning_rate": 0.0005,
      "loss": 1.9923,
      "step": 166
    },
    {
      "epoch": 1.518181818181818,
      "grad_norm": 2.704014301300049,
      "learning_rate": 0.000496969696969697,
      "loss": 1.9129,
      "step": 167
    },
    {
      "epoch": 1.5272727272727273,
      "grad_norm": 2.179574728012085,
      "learning_rate": 0.000493939393939394,
      "loss": 1.4398,
      "step": 168
    },
    {
      "epoch": 1.5363636363636364,
      "grad_norm": 2.764063596725464,
      "learning_rate": 0.0004909090909090909,
      "loss": 1.8727,
      "step": 169
    },
    {
      "epoch": 1.5454545454545454,
      "grad_norm": 2.14660382270813,
      "learning_rate": 0.00048787878787878784,
      "loss": 1.4661,
      "step": 170
    },
    {
      "epoch": 1.5545454545454547,
      "grad_norm": 2.8891947269439697,
      "learning_rate": 0.0004848484848484849,
      "loss": 1.828,
      "step": 171
    },
    {
      "epoch": 1.5636363636363635,
      "grad_norm": 2.541154384613037,
      "learning_rate": 0.00048181818181818184,
      "loss": 1.707,
      "step": 172
    },
    {
      "epoch": 1.5727272727272728,
      "grad_norm": 2.3288965225219727,
      "learning_rate": 0.0004787878787878788,
      "loss": 1.5946,
      "step": 173
    },
    {
      "epoch": 1.5818181818181818,
      "grad_norm": 2.395747661590576,
      "learning_rate": 0.0004757575757575758,
      "loss": 1.8755,
      "step": 174
    },
    {
      "epoch": 1.5909090909090908,
      "grad_norm": 2.5431134700775146,
      "learning_rate": 0.0004727272727272727,
      "loss": 1.8194,
      "step": 175
    },
    {
      "epoch": 1.6,
      "grad_norm": 2.811426877975464,
      "learning_rate": 0.0004696969696969697,
      "loss": 2.0278,
      "step": 176
    },
    {
      "epoch": 1.6090909090909091,
      "grad_norm": 2.861673355102539,
      "learning_rate": 0.00046666666666666666,
      "loss": 1.6279,
      "step": 177
    },
    {
      "epoch": 1.6181818181818182,
      "grad_norm": 2.6865475177764893,
      "learning_rate": 0.00046363636363636366,
      "loss": 1.7717,
      "step": 178
    },
    {
      "epoch": 1.6272727272727274,
      "grad_norm": 2.3562960624694824,
      "learning_rate": 0.00046060606060606066,
      "loss": 1.7969,
      "step": 179
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 2.477825880050659,
      "learning_rate": 0.0004575757575757576,
      "loss": 1.8108,
      "step": 180
    },
    {
      "epoch": 1.6454545454545455,
      "grad_norm": 2.505647659301758,
      "learning_rate": 0.00045454545454545455,
      "loss": 1.7048,
      "step": 181
    },
    {
      "epoch": 1.6545454545454545,
      "grad_norm": 2.1108808517456055,
      "learning_rate": 0.00045151515151515154,
      "loss": 1.3949,
      "step": 182
    },
    {
      "epoch": 1.6636363636363636,
      "grad_norm": 2.241442918777466,
      "learning_rate": 0.0004484848484848485,
      "loss": 1.5959,
      "step": 183
    },
    {
      "epoch": 1.6727272727272728,
      "grad_norm": 2.6187334060668945,
      "learning_rate": 0.00044545454545454543,
      "loss": 2.1715,
      "step": 184
    },
    {
      "epoch": 1.6818181818181817,
      "grad_norm": 2.8887858390808105,
      "learning_rate": 0.00044242424242424243,
      "loss": 1.9389,
      "step": 185
    },
    {
      "epoch": 1.690909090909091,
      "grad_norm": 2.5965023040771484,
      "learning_rate": 0.0004393939393939394,
      "loss": 1.7985,
      "step": 186
    },
    {
      "epoch": 1.7,
      "grad_norm": 2.331174612045288,
      "learning_rate": 0.00043636363636363637,
      "loss": 1.7063,
      "step": 187
    },
    {
      "epoch": 1.709090909090909,
      "grad_norm": 2.7674190998077393,
      "learning_rate": 0.00043333333333333337,
      "loss": 1.8718,
      "step": 188
    },
    {
      "epoch": 1.7181818181818183,
      "grad_norm": 2.5106184482574463,
      "learning_rate": 0.0004303030303030303,
      "loss": 1.4466,
      "step": 189
    },
    {
      "epoch": 1.7272727272727273,
      "grad_norm": 3.3343894481658936,
      "learning_rate": 0.00042727272727272726,
      "loss": 1.7985,
      "step": 190
    },
    {
      "epoch": 1.7363636363636363,
      "grad_norm": 2.390157699584961,
      "learning_rate": 0.00042424242424242425,
      "loss": 1.6776,
      "step": 191
    },
    {
      "epoch": 1.7454545454545456,
      "grad_norm": 2.7473723888397217,
      "learning_rate": 0.0004212121212121212,
      "loss": 1.8325,
      "step": 192
    },
    {
      "epoch": 1.7545454545454544,
      "grad_norm": 2.471184253692627,
      "learning_rate": 0.00041818181818181814,
      "loss": 1.7526,
      "step": 193
    },
    {
      "epoch": 1.7636363636363637,
      "grad_norm": 2.483290433883667,
      "learning_rate": 0.0004151515151515152,
      "loss": 2.1073,
      "step": 194
    },
    {
      "epoch": 1.7727272727272727,
      "grad_norm": 2.5065691471099854,
      "learning_rate": 0.00041212121212121214,
      "loss": 1.7606,
      "step": 195
    },
    {
      "epoch": 1.7818181818181817,
      "grad_norm": 2.5545785427093506,
      "learning_rate": 0.00040909090909090913,
      "loss": 2.1015,
      "step": 196
    },
    {
      "epoch": 1.790909090909091,
      "grad_norm": 3.050154447555542,
      "learning_rate": 0.0004060606060606061,
      "loss": 1.4343,
      "step": 197
    },
    {
      "epoch": 1.8,
      "grad_norm": 2.7478559017181396,
      "learning_rate": 0.000403030303030303,
      "loss": 1.9771,
      "step": 198
    },
    {
      "epoch": 1.809090909090909,
      "grad_norm": 2.5995945930480957,
      "learning_rate": 0.0004,
      "loss": 1.926,
      "step": 199
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 2.290558338165283,
      "learning_rate": 0.00039696969696969696,
      "loss": 1.8709,
      "step": 200
    },
    {
      "epoch": 1.8272727272727272,
      "grad_norm": 2.3791120052337646,
      "learning_rate": 0.0003939393939393939,
      "loss": 1.7667,
      "step": 201
    },
    {
      "epoch": 1.8363636363636364,
      "grad_norm": 2.6796791553497314,
      "learning_rate": 0.00039090909090909096,
      "loss": 1.7274,
      "step": 202
    },
    {
      "epoch": 1.8454545454545455,
      "grad_norm": 2.2967612743377686,
      "learning_rate": 0.0003878787878787879,
      "loss": 1.5935,
      "step": 203
    },
    {
      "epoch": 1.8545454545454545,
      "grad_norm": 2.1105916500091553,
      "learning_rate": 0.00038484848484848485,
      "loss": 1.6592,
      "step": 204
    },
    {
      "epoch": 1.8636363636363638,
      "grad_norm": 2.29516863822937,
      "learning_rate": 0.00038181818181818184,
      "loss": 1.5718,
      "step": 205
    },
    {
      "epoch": 1.8727272727272726,
      "grad_norm": 2.2299954891204834,
      "learning_rate": 0.0003787878787878788,
      "loss": 1.7402,
      "step": 206
    },
    {
      "epoch": 1.8818181818181818,
      "grad_norm": 2.6776788234710693,
      "learning_rate": 0.00037575757575757573,
      "loss": 1.6508,
      "step": 207
    },
    {
      "epoch": 1.8909090909090909,
      "grad_norm": 2.6130335330963135,
      "learning_rate": 0.00037272727272727273,
      "loss": 1.7602,
      "step": 208
    },
    {
      "epoch": 1.9,
      "grad_norm": 2.5121042728424072,
      "learning_rate": 0.00036969696969696967,
      "loss": 1.7763,
      "step": 209
    },
    {
      "epoch": 1.9090909090909092,
      "grad_norm": 2.6164438724517822,
      "learning_rate": 0.00036666666666666667,
      "loss": 1.7072,
      "step": 210
    },
    {
      "epoch": 1.9181818181818182,
      "grad_norm": 2.4708261489868164,
      "learning_rate": 0.00036363636363636367,
      "loss": 1.6395,
      "step": 211
    },
    {
      "epoch": 1.9272727272727272,
      "grad_norm": 2.2297871112823486,
      "learning_rate": 0.0003606060606060606,
      "loss": 1.8522,
      "step": 212
    },
    {
      "epoch": 1.9363636363636365,
      "grad_norm": 2.4121155738830566,
      "learning_rate": 0.0003575757575757576,
      "loss": 1.7713,
      "step": 213
    },
    {
      "epoch": 1.9454545454545453,
      "grad_norm": 2.429016351699829,
      "learning_rate": 0.00035454545454545455,
      "loss": 1.7839,
      "step": 214
    },
    {
      "epoch": 1.9545454545454546,
      "grad_norm": 2.6120107173919678,
      "learning_rate": 0.0003515151515151515,
      "loss": 1.8366,
      "step": 215
    },
    {
      "epoch": 1.9636363636363636,
      "grad_norm": 2.9374547004699707,
      "learning_rate": 0.0003484848484848485,
      "loss": 1.9741,
      "step": 216
    },
    {
      "epoch": 1.9727272727272727,
      "grad_norm": 2.2528085708618164,
      "learning_rate": 0.00034545454545454544,
      "loss": 1.6823,
      "step": 217
    },
    {
      "epoch": 1.981818181818182,
      "grad_norm": 2.1785707473754883,
      "learning_rate": 0.00034242424242424244,
      "loss": 1.4632,
      "step": 218
    },
    {
      "epoch": 1.990909090909091,
      "grad_norm": 2.4691455364227295,
      "learning_rate": 0.00033939393939393943,
      "loss": 2.1426,
      "step": 219
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.7157750129699707,
      "learning_rate": 0.0003363636363636364,
      "loss": 1.7351,
      "step": 220
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.8907,
      "eval_gen_len": 49.1909,
      "eval_loss": 1.8108986616134644,
      "eval_precision": 0.8879,
      "eval_recall": 0.8937,
      "eval_rouge1": 0.4494,
      "eval_rouge2": 0.2109,
      "eval_rougeL": 0.3799,
      "eval_rougeLsum": 0.4135,
      "eval_runtime": 34.4599,
      "eval_samples_per_second": 3.192,
      "eval_steps_per_second": 0.406,
      "step": 220
    },
    {
      "epoch": 2.0090909090909093,
      "grad_norm": 2.1249160766601562,
      "learning_rate": 0.0003333333333333333,
      "loss": 1.3421,
      "step": 221
    },
    {
      "epoch": 2.018181818181818,
      "grad_norm": 1.9582439661026,
      "learning_rate": 0.0003303030303030303,
      "loss": 1.6079,
      "step": 222
    },
    {
      "epoch": 2.0272727272727273,
      "grad_norm": 2.3376898765563965,
      "learning_rate": 0.00032727272727272726,
      "loss": 1.6966,
      "step": 223
    },
    {
      "epoch": 2.036363636363636,
      "grad_norm": 2.4100501537323,
      "learning_rate": 0.0003242424242424242,
      "loss": 1.5984,
      "step": 224
    },
    {
      "epoch": 2.0454545454545454,
      "grad_norm": 2.425031900405884,
      "learning_rate": 0.00032121212121212126,
      "loss": 1.7891,
      "step": 225
    },
    {
      "epoch": 2.0545454545454547,
      "grad_norm": 2.7900376319885254,
      "learning_rate": 0.0003181818181818182,
      "loss": 2.1962,
      "step": 226
    },
    {
      "epoch": 2.0636363636363635,
      "grad_norm": 2.1523351669311523,
      "learning_rate": 0.00031515151515151515,
      "loss": 1.5468,
      "step": 227
    },
    {
      "epoch": 2.0727272727272728,
      "grad_norm": 1.9378288984298706,
      "learning_rate": 0.00031212121212121214,
      "loss": 1.6581,
      "step": 228
    },
    {
      "epoch": 2.081818181818182,
      "grad_norm": 1.946201205253601,
      "learning_rate": 0.0003090909090909091,
      "loss": 1.393,
      "step": 229
    },
    {
      "epoch": 2.090909090909091,
      "grad_norm": 3.224222421646118,
      "learning_rate": 0.00030606060606060603,
      "loss": 1.6511,
      "step": 230
    },
    {
      "epoch": 2.1,
      "grad_norm": 2.397679567337036,
      "learning_rate": 0.00030303030303030303,
      "loss": 1.4755,
      "step": 231
    },
    {
      "epoch": 2.109090909090909,
      "grad_norm": 2.2537128925323486,
      "learning_rate": 0.0003,
      "loss": 1.3588,
      "step": 232
    },
    {
      "epoch": 2.118181818181818,
      "grad_norm": 2.4279613494873047,
      "learning_rate": 0.000296969696969697,
      "loss": 1.5448,
      "step": 233
    },
    {
      "epoch": 2.1272727272727274,
      "grad_norm": 2.3873281478881836,
      "learning_rate": 0.00029393939393939397,
      "loss": 1.3447,
      "step": 234
    },
    {
      "epoch": 2.1363636363636362,
      "grad_norm": NaN,
      "learning_rate": 0.0002909090909090909,
      "loss": 1.3727,
      "step": 235
    },
    {
      "epoch": 2.1454545454545455,
      "grad_norm": 2.3502180576324463,
      "learning_rate": 0.0002878787878787879,
      "loss": 1.8046,
      "step": 236
    },
    {
      "epoch": 2.1545454545454543,
      "grad_norm": 3.139299154281616,
      "learning_rate": 0.00028484848484848485,
      "loss": 1.4736,
      "step": 237
    },
    {
      "epoch": 2.1636363636363636,
      "grad_norm": 2.6550652980804443,
      "learning_rate": 0.0002818181818181818,
      "loss": 1.6793,
      "step": 238
    },
    {
      "epoch": 2.172727272727273,
      "grad_norm": 2.3589141368865967,
      "learning_rate": 0.0002787878787878788,
      "loss": 1.6814,
      "step": 239
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 2.702759265899658,
      "learning_rate": 0.00027575757575757574,
      "loss": 2.0298,
      "step": 240
    },
    {
      "epoch": 2.190909090909091,
      "grad_norm": 3.7319226264953613,
      "learning_rate": 0.00027272727272727274,
      "loss": 1.399,
      "step": 241
    },
    {
      "epoch": 2.2,
      "grad_norm": 2.0268139839172363,
      "learning_rate": 0.00026969696969696974,
      "loss": 1.0498,
      "step": 242
    },
    {
      "epoch": 2.209090909090909,
      "grad_norm": 2.8383145332336426,
      "learning_rate": 0.0002666666666666667,
      "loss": 2.1721,
      "step": 243
    },
    {
      "epoch": 2.2181818181818183,
      "grad_norm": 2.6691808700561523,
      "learning_rate": 0.0002636363636363636,
      "loss": 1.7675,
      "step": 244
    },
    {
      "epoch": 2.227272727272727,
      "grad_norm": 3.2594199180603027,
      "learning_rate": 0.0002606060606060606,
      "loss": 1.6253,
      "step": 245
    },
    {
      "epoch": 2.2363636363636363,
      "grad_norm": 2.6453161239624023,
      "learning_rate": 0.00025757575757575756,
      "loss": 1.9321,
      "step": 246
    },
    {
      "epoch": 2.2454545454545456,
      "grad_norm": 2.9281351566314697,
      "learning_rate": 0.0002545454545454545,
      "loss": 1.7218,
      "step": 247
    },
    {
      "epoch": 2.2545454545454544,
      "grad_norm": 3.0768837928771973,
      "learning_rate": 0.0002515151515151515,
      "loss": 1.668,
      "step": 248
    },
    {
      "epoch": 2.2636363636363637,
      "grad_norm": 2.6963603496551514,
      "learning_rate": 0.0002484848484848485,
      "loss": 1.8747,
      "step": 249
    },
    {
      "epoch": 2.2727272727272725,
      "grad_norm": 2.636838436126709,
      "learning_rate": 0.00024545454545454545,
      "loss": 2.0157,
      "step": 250
    },
    {
      "epoch": 2.2818181818181817,
      "grad_norm": 1.9459854364395142,
      "learning_rate": 0.00024242424242424245,
      "loss": 1.2909,
      "step": 251
    },
    {
      "epoch": 2.290909090909091,
      "grad_norm": 2.016514301300049,
      "learning_rate": 0.0002393939393939394,
      "loss": 1.2945,
      "step": 252
    },
    {
      "epoch": 2.3,
      "grad_norm": 3.083578109741211,
      "learning_rate": 0.00023636363636363636,
      "loss": 1.651,
      "step": 253
    },
    {
      "epoch": 2.309090909090909,
      "grad_norm": 2.4212188720703125,
      "learning_rate": 0.00023333333333333333,
      "loss": 1.8318,
      "step": 254
    },
    {
      "epoch": 2.3181818181818183,
      "grad_norm": 2.3662185668945312,
      "learning_rate": 0.00023030303030303033,
      "loss": 1.6034,
      "step": 255
    },
    {
      "epoch": 2.327272727272727,
      "grad_norm": 2.8802566528320312,
      "learning_rate": 0.00022727272727272727,
      "loss": 1.6308,
      "step": 256
    },
    {
      "epoch": 2.3363636363636364,
      "grad_norm": 2.5055510997772217,
      "learning_rate": 0.00022424242424242424,
      "loss": 1.969,
      "step": 257
    },
    {
      "epoch": 2.3454545454545457,
      "grad_norm": 2.2045178413391113,
      "learning_rate": 0.00022121212121212121,
      "loss": 1.4335,
      "step": 258
    },
    {
      "epoch": 2.3545454545454545,
      "grad_norm": 2.2642455101013184,
      "learning_rate": 0.00021818181818181818,
      "loss": 1.6836,
      "step": 259
    },
    {
      "epoch": 2.3636363636363638,
      "grad_norm": 2.2562596797943115,
      "learning_rate": 0.00021515151515151516,
      "loss": 1.7615,
      "step": 260
    },
    {
      "epoch": 2.3727272727272726,
      "grad_norm": 2.346268892288208,
      "learning_rate": 0.00021212121212121213,
      "loss": 1.4159,
      "step": 261
    },
    {
      "epoch": 2.381818181818182,
      "grad_norm": 2.380128860473633,
      "learning_rate": 0.00020909090909090907,
      "loss": 1.5036,
      "step": 262
    },
    {
      "epoch": 2.390909090909091,
      "grad_norm": 2.918025493621826,
      "learning_rate": 0.00020606060606060607,
      "loss": 1.2163,
      "step": 263
    },
    {
      "epoch": 2.4,
      "grad_norm": 2.3654491901397705,
      "learning_rate": 0.00020303030303030304,
      "loss": 1.7327,
      "step": 264
    },
    {
      "epoch": 2.409090909090909,
      "grad_norm": 2.0867059230804443,
      "learning_rate": 0.0002,
      "loss": 1.4487,
      "step": 265
    },
    {
      "epoch": 2.418181818181818,
      "grad_norm": 1.782357931137085,
      "learning_rate": 0.00019696969696969695,
      "loss": 1.4284,
      "step": 266
    },
    {
      "epoch": 2.4272727272727272,
      "grad_norm": 2.770702600479126,
      "learning_rate": 0.00019393939393939395,
      "loss": 1.8376,
      "step": 267
    },
    {
      "epoch": 2.4363636363636365,
      "grad_norm": 2.3309333324432373,
      "learning_rate": 0.00019090909090909092,
      "loss": 1.4546,
      "step": 268
    },
    {
      "epoch": 2.4454545454545453,
      "grad_norm": 2.347947835922241,
      "learning_rate": 0.00018787878787878787,
      "loss": 1.651,
      "step": 269
    },
    {
      "epoch": 2.4545454545454546,
      "grad_norm": 2.440192222595215,
      "learning_rate": 0.00018484848484848484,
      "loss": 1.7113,
      "step": 270
    },
    {
      "epoch": 2.463636363636364,
      "grad_norm": 2.800288200378418,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.587,
      "step": 271
    },
    {
      "epoch": 2.4727272727272727,
      "grad_norm": 2.5269834995269775,
      "learning_rate": 0.0001787878787878788,
      "loss": 1.3436,
      "step": 272
    },
    {
      "epoch": 2.481818181818182,
      "grad_norm": 2.5719213485717773,
      "learning_rate": 0.00017575757575757575,
      "loss": 1.455,
      "step": 273
    },
    {
      "epoch": 2.4909090909090907,
      "grad_norm": 2.989320755004883,
      "learning_rate": 0.00017272727272727272,
      "loss": 1.7098,
      "step": 274
    },
    {
      "epoch": 2.5,
      "grad_norm": 2.680875539779663,
      "learning_rate": 0.00016969696969696972,
      "loss": 1.7441,
      "step": 275
    },
    {
      "epoch": 2.509090909090909,
      "grad_norm": 2.5206220149993896,
      "learning_rate": 0.00016666666666666666,
      "loss": 1.4399,
      "step": 276
    },
    {
      "epoch": 2.518181818181818,
      "grad_norm": NaN,
      "learning_rate": 0.00016363636363636363,
      "loss": 1.5653,
      "step": 277
    },
    {
      "epoch": 2.5272727272727273,
      "grad_norm": 2.3463797569274902,
      "learning_rate": 0.00016060606060606063,
      "loss": 1.718,
      "step": 278
    },
    {
      "epoch": 2.536363636363636,
      "grad_norm": 2.494494915008545,
      "learning_rate": 0.00015757575757575757,
      "loss": 1.8038,
      "step": 279
    },
    {
      "epoch": 2.5454545454545454,
      "grad_norm": 2.3026742935180664,
      "learning_rate": 0.00015454545454545454,
      "loss": 1.5355,
      "step": 280
    },
    {
      "epoch": 2.5545454545454547,
      "grad_norm": 2.641831636428833,
      "learning_rate": 0.00015151515151515152,
      "loss": 1.4931,
      "step": 281
    },
    {
      "epoch": 2.5636363636363635,
      "grad_norm": 2.6526780128479004,
      "learning_rate": 0.0001484848484848485,
      "loss": 1.435,
      "step": 282
    },
    {
      "epoch": 2.5727272727272728,
      "grad_norm": 2.48811936378479,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.4271,
      "step": 283
    },
    {
      "epoch": 2.581818181818182,
      "grad_norm": 2.8319783210754395,
      "learning_rate": 0.00014242424242424243,
      "loss": 1.655,
      "step": 284
    },
    {
      "epoch": 2.590909090909091,
      "grad_norm": 2.399517297744751,
      "learning_rate": 0.0001393939393939394,
      "loss": 1.6801,
      "step": 285
    },
    {
      "epoch": 2.6,
      "grad_norm": 2.204937696456909,
      "learning_rate": 0.00013636363636363637,
      "loss": 1.4153,
      "step": 286
    },
    {
      "epoch": 2.6090909090909093,
      "grad_norm": 2.2615416049957275,
      "learning_rate": 0.00013333333333333334,
      "loss": 1.5112,
      "step": 287
    },
    {
      "epoch": 2.618181818181818,
      "grad_norm": 2.5197913646698,
      "learning_rate": 0.0001303030303030303,
      "loss": 1.6922,
      "step": 288
    },
    {
      "epoch": 2.6272727272727274,
      "grad_norm": 2.1603517532348633,
      "learning_rate": 0.00012727272727272725,
      "loss": 1.4442,
      "step": 289
    },
    {
      "epoch": 2.6363636363636362,
      "grad_norm": NaN,
      "learning_rate": 0.00012424242424242425,
      "loss": 0.0,
      "step": 290
    },
    {
      "epoch": 2.6454545454545455,
      "grad_norm": 2.9369215965270996,
      "learning_rate": 0.00012121212121212122,
      "loss": 1.6885,
      "step": 291
    },
    {
      "epoch": 2.6545454545454543,
      "grad_norm": 2.6513493061065674,
      "learning_rate": 0.00011818181818181818,
      "loss": 2.1636,
      "step": 292
    },
    {
      "epoch": 2.6636363636363636,
      "grad_norm": 2.744880437850952,
      "learning_rate": 0.00011515151515151516,
      "loss": 1.6039,
      "step": 293
    },
    {
      "epoch": 2.672727272727273,
      "grad_norm": 2.202091932296753,
      "learning_rate": 0.00011212121212121212,
      "loss": 1.5977,
      "step": 294
    },
    {
      "epoch": 2.6818181818181817,
      "grad_norm": 2.5491065979003906,
      "learning_rate": 0.00010909090909090909,
      "loss": 2.0341,
      "step": 295
    },
    {
      "epoch": 2.690909090909091,
      "grad_norm": 2.4479360580444336,
      "learning_rate": 0.00010606060606060606,
      "loss": 1.7084,
      "step": 296
    },
    {
      "epoch": 2.7,
      "grad_norm": 2.3855769634246826,
      "learning_rate": 0.00010303030303030303,
      "loss": 1.6035,
      "step": 297
    },
    {
      "epoch": 2.709090909090909,
      "grad_norm": 3.228444814682007,
      "learning_rate": 0.0001,
      "loss": 1.4157,
      "step": 298
    },
    {
      "epoch": 2.7181818181818183,
      "grad_norm": 2.0895612239837646,
      "learning_rate": 9.696969696969698e-05,
      "loss": 1.3353,
      "step": 299
    },
    {
      "epoch": 2.7272727272727275,
      "grad_norm": 2.8420956134796143,
      "learning_rate": 9.393939393939393e-05,
      "loss": 2.02,
      "step": 300
    },
    {
      "epoch": 2.7363636363636363,
      "grad_norm": 2.3535358905792236,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.4193,
      "step": 301
    },
    {
      "epoch": 2.7454545454545456,
      "grad_norm": 2.5961458683013916,
      "learning_rate": 8.787878787878787e-05,
      "loss": 1.483,
      "step": 302
    },
    {
      "epoch": 2.7545454545454544,
      "grad_norm": 2.8026998043060303,
      "learning_rate": 8.484848484848486e-05,
      "loss": 1.4553,
      "step": 303
    },
    {
      "epoch": 2.7636363636363637,
      "grad_norm": 2.504908800125122,
      "learning_rate": 8.181818181818182e-05,
      "loss": 1.4092,
      "step": 304
    },
    {
      "epoch": 2.7727272727272725,
      "grad_norm": 2.252107620239258,
      "learning_rate": 7.878787878787879e-05,
      "loss": 1.2563,
      "step": 305
    },
    {
      "epoch": 2.7818181818181817,
      "grad_norm": 2.343602418899536,
      "learning_rate": 7.575757575757576e-05,
      "loss": 1.6098,
      "step": 306
    },
    {
      "epoch": 2.790909090909091,
      "grad_norm": 2.638190746307373,
      "learning_rate": 7.272727272727273e-05,
      "loss": 1.7983,
      "step": 307
    },
    {
      "epoch": 2.8,
      "grad_norm": 2.359740734100342,
      "learning_rate": 6.96969696969697e-05,
      "loss": 1.5149,
      "step": 308
    },
    {
      "epoch": 2.809090909090909,
      "grad_norm": 2.869689702987671,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.0222,
      "step": 309
    },
    {
      "epoch": 2.8181818181818183,
      "grad_norm": 2.1919660568237305,
      "learning_rate": 6.363636363636363e-05,
      "loss": 1.4945,
      "step": 310
    },
    {
      "epoch": 2.827272727272727,
      "grad_norm": 2.4785120487213135,
      "learning_rate": 6.060606060606061e-05,
      "loss": 1.9861,
      "step": 311
    },
    {
      "epoch": 2.8363636363636364,
      "grad_norm": 2.384038209915161,
      "learning_rate": 5.757575757575758e-05,
      "loss": 1.6079,
      "step": 312
    },
    {
      "epoch": 2.8454545454545457,
      "grad_norm": 2.6744563579559326,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 1.698,
      "step": 313
    },
    {
      "epoch": 2.8545454545454545,
      "grad_norm": 2.787661552429199,
      "learning_rate": 5.151515151515152e-05,
      "loss": 1.568,
      "step": 314
    },
    {
      "epoch": 2.8636363636363638,
      "grad_norm": 2.107388973236084,
      "learning_rate": 4.848484848484849e-05,
      "loss": 1.2982,
      "step": 315
    },
    {
      "epoch": 2.8727272727272726,
      "grad_norm": 2.4389491081237793,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.6659,
      "step": 316
    },
    {
      "epoch": 2.881818181818182,
      "grad_norm": 2.5721840858459473,
      "learning_rate": 4.242424242424243e-05,
      "loss": 1.5628,
      "step": 317
    },
    {
      "epoch": 2.8909090909090907,
      "grad_norm": 2.5818939208984375,
      "learning_rate": 3.939393939393939e-05,
      "loss": 1.8823,
      "step": 318
    },
    {
      "epoch": 2.9,
      "grad_norm": 3.1052472591400146,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 2.012,
      "step": 319
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 2.4920005798339844,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3315,
      "step": 320
    },
    {
      "epoch": 2.918181818181818,
      "grad_norm": 2.6718740463256836,
      "learning_rate": 3.0303030303030306e-05,
      "loss": 1.8997,
      "step": 321
    },
    {
      "epoch": 2.9272727272727272,
      "grad_norm": 2.8918116092681885,
      "learning_rate": 2.7272727272727273e-05,
      "loss": 1.2294,
      "step": 322
    },
    {
      "epoch": 2.9363636363636365,
      "grad_norm": 2.3522236347198486,
      "learning_rate": 2.4242424242424244e-05,
      "loss": 1.5485,
      "step": 323
    },
    {
      "epoch": 2.9454545454545453,
      "grad_norm": 3.1940016746520996,
      "learning_rate": 2.1212121212121215e-05,
      "loss": 1.7361,
      "step": 324
    },
    {
      "epoch": 2.9545454545454546,
      "grad_norm": 2.333925247192383,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 1.5913,
      "step": 325
    },
    {
      "epoch": 2.963636363636364,
      "grad_norm": 2.5500593185424805,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 1.8166,
      "step": 326
    },
    {
      "epoch": 2.9727272727272727,
      "grad_norm": 2.1785731315612793,
      "learning_rate": 1.2121212121212122e-05,
      "loss": 1.3214,
      "step": 327
    },
    {
      "epoch": 2.981818181818182,
      "grad_norm": 2.3469910621643066,
      "learning_rate": 9.090909090909091e-06,
      "loss": 1.4537,
      "step": 328
    },
    {
      "epoch": 2.990909090909091,
      "grad_norm": 2.3071048259735107,
      "learning_rate": 6.060606060606061e-06,
      "loss": 1.3383,
      "step": 329
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.35412335395813,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 1.5234,
      "step": 330
    },
    {
      "epoch": 3.0,
      "eval_f1": 0.8888,
      "eval_gen_len": 47.8545,
      "eval_loss": 1.8115006685256958,
      "eval_precision": 0.8854,
      "eval_recall": 0.8924,
      "eval_rouge1": 0.4407,
      "eval_rouge2": 0.2025,
      "eval_rougeL": 0.368,
      "eval_rougeLsum": 0.4049,
      "eval_runtime": 34.0252,
      "eval_samples_per_second": 3.233,
      "eval_steps_per_second": 0.411,
      "step": 330
    },
    {
      "epoch": 3.0,
      "step": 330,
      "total_flos": 2506179136462848.0,
      "train_loss": 1.8389299175956033,
      "train_runtime": 453.2247,
      "train_samples_per_second": 5.818,
      "train_steps_per_second": 0.728
    }
  ],
  "logging_steps": 1,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2506179136462848.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}