{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 200,
  "global_step": 1215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 2.8335,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 2.752,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 2.7803,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 2.5798,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0001,
      "loss": 2.7038,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00012,
      "loss": 2.1478,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014,
      "loss": 1.7468,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00016,
      "loss": 1.6426,
      "step": 8
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00018,
      "loss": 0.9787,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 0.7736,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999997902092877,
      "loss": 0.5849,
      "step": 11
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999991608372393,
      "loss": 0.4335,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999981118841182,
      "loss": 0.3929,
      "step": 13
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019999966433503652,
      "loss": 0.1443,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019999947552365961,
      "loss": 0.1243,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001999992447543603,
      "loss": 0.4306,
      "step": 16
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019999897202723545,
      "loss": 0.2558,
      "step": 17
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019999865734239946,
      "loss": 0.1647,
      "step": 18
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001999983006999844,
      "loss": 0.191,
      "step": 19
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019999790210013988,
      "loss": 0.259,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019999746154303317,
      "loss": 0.0401,
      "step": 21
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001999969790288491,
      "loss": 0.0613,
      "step": 22
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019999645455779014,
      "loss": 0.2135,
      "step": 23
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019999588813007633,
      "loss": 0.0816,
      "step": 24
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001999952797459453,
      "loss": 0.0543,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019999462940565243,
      "loss": 0.1945,
      "step": 26
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001999939371094705,
      "loss": 0.0461,
      "step": 27
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019999320285769,
      "loss": 0.1266,
      "step": 28
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000199992426650619,
      "loss": 0.0274,
      "step": 29
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001999916084885832,
      "loss": 0.1039,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019999074837192589,
      "loss": 0.0169,
      "step": 31
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019998984630100792,
      "loss": 0.1045,
      "step": 32
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019998890227620783,
      "loss": 0.0236,
      "step": 33
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001999879162979217,
      "loss": 0.0125,
      "step": 34
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998688836656323,
      "loss": 0.0317,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001999858184825637,
      "loss": 0.0216,
      "step": 36
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998470664637203,
      "loss": 0.0583,
      "step": 37
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00019998355285845475,
      "loss": 0.0534,
      "step": 38
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001999823571192959,
      "loss": 0.1213,
      "step": 39
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001999811194293973,
      "loss": 0.2095,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019997983978927813,
      "loss": 0.0122,
      "step": 41
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019997851819947537,
      "loss": 0.2262,
      "step": 42
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019997715466054357,
      "loss": 0.0329,
      "step": 43
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019997574917305478,
      "loss": 0.0907,
      "step": 44
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019997430173759875,
      "loss": 0.0111,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019997281235478278,
      "loss": 0.1297,
      "step": 46
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019997128102523183,
      "loss": 0.0805,
      "step": 47
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019996970774958836,
      "loss": 0.0527,
      "step": 48
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019996809252851251,
      "loss": 0.0117,
      "step": 49
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019996643536268204,
      "loss": 0.0287,
      "step": 50
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001999647362527922,
      "loss": 0.0106,
      "step": 51
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001999629951995559,
      "loss": 0.0564,
      "step": 52
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019996121220370374,
      "loss": 0.0318,
      "step": 53
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019995938726598373,
      "loss": 0.0829,
      "step": 54
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019995752038716168,
      "loss": 0.0564,
      "step": 55
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019995561156802079,
      "loss": 0.0852,
      "step": 56
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019995366080936204,
      "loss": 0.0146,
      "step": 57
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001999516681120039,
      "loss": 0.0446,
      "step": 58
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019994963347678247,
      "loss": 0.0103,
      "step": 59
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019994755690455152,
      "loss": 0.0147,
      "step": 60
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019994543839618221,
      "loss": 0.0479,
      "step": 61
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001999432779525635,
      "loss": 0.0028,
      "step": 62
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001999410755746019,
      "loss": 0.0316,
      "step": 63
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001999388312632214,
      "loss": 0.113,
      "step": 64
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001999365450193638,
      "loss": 0.0148,
      "step": 65
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019993421684398824,
      "loss": 0.0437,
      "step": 66
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019993184673807162,
      "loss": 0.0287,
      "step": 67
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019992943470260844,
      "loss": 0.0088,
      "step": 68
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019992698073861064,
      "loss": 0.0971,
      "step": 69
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019992448484710797,
      "loss": 0.0557,
      "step": 70
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999219470291476,
      "loss": 0.0609,
      "step": 71
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019991936728579437,
      "loss": 0.0033,
      "step": 72
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001999167456181307,
      "loss": 0.0853,
      "step": 73
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019991408202725655,
      "loss": 0.0019,
      "step": 74
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019991137651428957,
      "loss": 0.0121,
      "step": 75
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001999086290803649,
      "loss": 0.016,
      "step": 76
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019990583972663534,
      "loss": 0.0014,
      "step": 77
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019990300845427125,
      "loss": 0.1069,
      "step": 78
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019990013526446056,
      "loss": 0.0157,
      "step": 79
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001998972201584088,
      "loss": 0.0891,
      "step": 80
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001998942631373391,
      "loss": 0.0495,
      "step": 81
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019989126420249221,
      "loss": 0.0441,
      "step": 82
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019988822335512637,
      "loss": 0.079,
      "step": 83
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019988514059651752,
      "loss": 0.0699,
      "step": 84
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001998820159279591,
      "loss": 0.0009,
      "step": 85
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019987884935076213,
      "loss": 0.0007,
      "step": 86
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001998756408662553,
      "loss": 0.061,
      "step": 87
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019987239047578482,
      "loss": 0.0012,
      "step": 88
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019986909818071446,
      "loss": 0.0657,
      "step": 89
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019986576398242566,
      "loss": 0.0024,
      "step": 90
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019986238788231733,
      "loss": 0.0411,
      "step": 91
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019985896988180605,
      "loss": 0.0813,
      "step": 92
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019985550998232596,
      "loss": 0.0013,
      "step": 93
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019985200818532875,
      "loss": 0.1736,
      "step": 94
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0001998484644922837,
      "loss": 0.0006,
      "step": 95
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001998448789046777,
      "loss": 0.0013,
      "step": 96
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001998412514240152,
      "loss": 0.0813,
      "step": 97
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019983758205181822,
      "loss": 0.0002,
      "step": 98
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019983387078962631,
      "loss": 0.0006,
      "step": 99
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019983011763899673,
      "loss": 0.1275,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019982632260150417,
      "loss": 0.0737,
      "step": 101
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019982248567874098,
      "loss": 0.162,
      "step": 102
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019981860687231706,
      "loss": 0.2331,
      "step": 103
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019981468618385988,
      "loss": 0.0005,
      "step": 104
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001998107236150145,
      "loss": 0.001,
      "step": 105
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019980671916744352,
      "loss": 0.0136,
      "step": 106
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019980267284282717,
      "loss": 0.1149,
      "step": 107
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019979858464286317,
      "loss": 0.1266,
      "step": 108
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019979445456926688,
      "loss": 0.0724,
      "step": 109
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019979028262377118,
      "loss": 0.1143,
      "step": 110
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019978606880812657,
      "loss": 0.0084,
      "step": 111
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019978181312410104,
      "loss": 0.0657,
      "step": 112
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019977751557348025,
      "loss": 0.1512,
      "step": 113
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019977317615806737,
      "loss": 0.0051,
      "step": 114
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001997687948796831,
      "loss": 0.0093,
      "step": 115
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019976437174016573,
      "loss": 0.0067,
      "step": 116
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001997599067413712,
      "loss": 0.0949,
      "step": 117
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019975539988517288,
      "loss": 0.0393,
      "step": 118
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019975085117346177,
      "loss": 0.0364,
      "step": 119
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019974626060814647,
      "loss": 0.1306,
      "step": 120
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019974162819115306,
      "loss": 0.0019,
      "step": 121
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001997369539244252,
      "loss": 0.0029,
      "step": 122
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019973223780992414,
      "loss": 0.0159,
      "step": 123
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001997274798496287,
      "loss": 0.0019,
      "step": 124
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001997226800455352,
      "loss": 0.0194,
      "step": 125
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019971783839965756,
      "loss": 0.0037,
      "step": 126
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019971295491402725,
      "loss": 0.0442,
      "step": 127
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019970802959069328,
      "loss": 0.003,
      "step": 128
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019970306243172222,
      "loss": 0.0023,
      "step": 129
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019969805343919821,
      "loss": 0.0198,
      "step": 130
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019969300261522293,
      "loss": 0.0025,
      "step": 131
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001996879099619156,
      "loss": 0.0574,
      "step": 132
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019968277548141302,
      "loss": 0.0796,
      "step": 133
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019967759917586953,
      "loss": 0.0326,
      "step": 134
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019967238104745696,
      "loss": 0.0021,
      "step": 135
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019966712109836476,
      "loss": 0.0008,
      "step": 136
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019966181933079997,
      "loss": 0.0943,
      "step": 137
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.000199656475746987,
      "loss": 0.002,
      "step": 138
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019965109034916808,
      "loss": 0.0451,
      "step": 139
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019964566313960264,
      "loss": 0.0485,
      "step": 140
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.000199640194120568,
      "loss": 0.0186,
      "step": 141
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001996346832943587,
      "loss": 0.0305,
      "step": 142
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001996291306632871,
      "loss": 0.0625,
      "step": 143
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019962353622968295,
      "loss": 0.0183,
      "step": 144
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019961789999589356,
      "loss": 0.0043,
      "step": 145
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019961222196428378,
      "loss": 0.0493,
      "step": 146
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019960650213723602,
      "loss": 0.1198,
      "step": 147
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001996007405171502,
      "loss": 0.0005,
      "step": 148
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019959493710644384,
      "loss": 0.0006,
      "step": 149
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019958909190755187,
      "loss": 0.1201,
      "step": 150
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019958320492292686,
      "loss": 0.0012,
      "step": 151
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019957727615503888,
      "loss": 0.0025,
      "step": 152
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019957130560637552,
      "loss": 0.1595,
      "step": 153
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019956529327944198,
      "loss": 0.0003,
      "step": 154
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001995592391767608,
      "loss": 0.0014,
      "step": 155
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019955314330087225,
      "loss": 0.1316,
      "step": 156
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019954700565433405,
      "loss": 0.0015,
      "step": 157
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019954082623972142,
      "loss": 0.0015,
      "step": 158
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001995346050596271,
      "loss": 0.0018,
      "step": 159
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001995283421166614,
      "loss": 0.0638,
      "step": 160
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019952203741345218,
      "loss": 0.0283,
      "step": 161
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00019951569095264473,
      "loss": 0.0005,
      "step": 162
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001995093027369019,
      "loss": 0.0013,
      "step": 163
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001995028727689041,
      "loss": 0.0828,
      "step": 164
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019949640105134918,
      "loss": 0.0007,
      "step": 165
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019948988758695263,
      "loss": 0.0588,
      "step": 166
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019948333237844733,
      "loss": 0.0166,
      "step": 167
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019947673542858367,
      "loss": 0.2658,
      "step": 168
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019947009674012973,
      "loss": 0.0063,
      "step": 169
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019946341631587087,
      "loss": 0.053,
      "step": 170
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001994566941586101,
      "loss": 0.0007,
      "step": 171
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019944993027116797,
      "loss": 0.0009,
      "step": 172
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001994431246563824,
      "loss": 0.0003,
      "step": 173
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019943627731710897,
      "loss": 0.0008,
      "step": 174
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019942938825622065,
      "loss": 0.0834,
      "step": 175
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019942245747660796,
      "loss": 0.0174,
      "step": 176
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019941548498117896,
      "loss": 0.0963,
      "step": 177
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019940847077285916,
      "loss": 0.0361,
      "step": 178
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001994014148545916,
      "loss": 0.0408,
      "step": 179
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001993943172293368,
      "loss": 0.0011,
      "step": 180
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001993871779000728,
      "loss": 0.0801,
      "step": 181
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001993799968697951,
      "loss": 0.1176,
      "step": 182
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019937277414151677,
      "loss": 0.1212,
      "step": 183
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019936550971826834,
      "loss": 0.0458,
      "step": 184
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019935820360309777,
      "loss": 0.0543,
      "step": 185
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019935085579907063,
      "loss": 0.0518,
      "step": 186
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001993434663092699,
      "loss": 0.0015,
      "step": 187
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019933603513679605,
      "loss": 0.0704,
      "step": 188
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019932856228476706,
      "loss": 0.0628,
      "step": 189
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019932104775631846,
      "loss": 0.0602,
      "step": 190
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019931349155460315,
      "loss": 0.0025,
      "step": 191
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001993058936827916,
      "loss": 0.0032,
      "step": 192
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019929825414407172,
      "loss": 0.1927,
      "step": 193
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019929057294164893,
      "loss": 0.003,
      "step": 194
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001992828500787461,
      "loss": 0.0027,
      "step": 195
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001992750855586036,
      "loss": 0.0225,
      "step": 196
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019926727938447933,
      "loss": 0.0018,
      "step": 197
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019925943155964856,
      "loss": 0.0019,
      "step": 198
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001992515420874041,
      "loss": 0.0015,
      "step": 199
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019924361097105623,
      "loss": 0.0411,
      "step": 200
    },
    {
      "epoch": 0.49,
      "eval_loss": 0.02292541041970253,
      "eval_runtime": 126.0288,
      "eval_samples_per_second": 1.016,
      "eval_steps_per_second": 0.341,
      "step": 200
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001992356382139327,
      "loss": 0.0512,
      "step": 201
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019922762381937878,
      "loss": 0.0013,
      "step": 202
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019921956779075708,
      "loss": 0.0022,
      "step": 203
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001992114701314478,
      "loss": 0.0513,
      "step": 204
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019920333084484857,
      "loss": 0.0621,
      "step": 205
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019919514993437445,
      "loss": 0.0032,
      "step": 206
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019918692740345802,
      "loss": 0.0048,
      "step": 207
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019917866325554938,
      "loss": 0.001,
      "step": 208
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019917035749411586,
      "loss": 0.0006,
      "step": 209
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019916201012264254,
      "loss": 0.0666,
      "step": 210
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019915362114463172,
      "loss": 0.049,
      "step": 211
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001991451905636033,
      "loss": 0.0005,
      "step": 212
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019913671838309464,
      "loss": 0.0025,
      "step": 213
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019912820460666044,
      "loss": 0.0006,
      "step": 214
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019911964923787295,
      "loss": 0.062,
      "step": 215
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019911105228032186,
      "loss": 0.0012,
      "step": 216
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019910241373761426,
      "loss": 0.0817,
      "step": 217
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019909373361337476,
      "loss": 0.0003,
      "step": 218
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00019908501191124534,
      "loss": 0.0002,
      "step": 219
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001990762486348855,
      "loss": 0.0434,
      "step": 220
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019906744378797212,
      "loss": 0.0994,
      "step": 221
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019905859737419956,
      "loss": 0.0506,
      "step": 222
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019904970939727963,
      "loss": 0.059,
      "step": 223
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00019904077986094152,
      "loss": 0.0042,
      "step": 224
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019903180876893194,
      "loss": 0.0667,
      "step": 225
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019902279612501493,
      "loss": 0.002,
      "step": 226
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019901374193297212,
      "loss": 0.0003,
      "step": 227
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0001990046461966024,
      "loss": 0.0003,
      "step": 228
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019899550891972222,
      "loss": 0.0002,
      "step": 229
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019898633010616542,
      "loss": 0.0025,
      "step": 230
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019897710975978321,
      "loss": 0.1237,
      "step": 231
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001989678478844443,
      "loss": 0.0625,
      "step": 232
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019895854448403482,
      "loss": 0.0569,
      "step": 233
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019894919956245824,
      "loss": 0.001,
      "step": 234
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019893981312363562,
      "loss": 0.0846,
      "step": 235
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00019893038517150525,
      "loss": 0.0325,
      "step": 236
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019892091571002297,
      "loss": 0.0696,
      "step": 237
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019891140474316194,
      "loss": 0.0006,
      "step": 238
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019890185227491283,
      "loss": 0.0002,
      "step": 239
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019889225830928365,
      "loss": 0.0002,
      "step": 240
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019888262285029987,
      "loss": 0.0008,
      "step": 241
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019887294590200435,
      "loss": 0.0013,
      "step": 242
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019886322746845737,
      "loss": 0.0006,
      "step": 243
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019885346755373656,
      "loss": 0.0004,
      "step": 244
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019884366616193706,
      "loss": 0.0468,
      "step": 245
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019883382329717128,
      "loss": 0.0017,
      "step": 246
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019882393896356913,
      "loss": 0.0741,
      "step": 247
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019881401316527793,
      "loss": 0.0004,
      "step": 248
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019880404590646232,
      "loss": 0.1221,
      "step": 249
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001987940371913044,
      "loss": 0.0582,
      "step": 250
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019878398702400364,
      "loss": 0.0689,
      "step": 251
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00019877389540877687,
      "loss": 0.1289,
      "step": 252
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001987637623498584,
      "loss": 0.0026,
      "step": 253
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001987535878514998,
      "loss": 0.0419,
      "step": 254
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001987433719179702,
      "loss": 0.001,
      "step": 255
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0001987331145535559,
      "loss": 0.0003,
      "step": 256
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00019872281576256077,
      "loss": 0.0004,
      "step": 257
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.000198712475549306,
      "loss": 0.0006,
      "step": 258
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019870209391813012,
      "loss": 0.0495,
      "step": 259
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00019869167087338907,
      "loss": 0.1258,
      "step": 260
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001986812064194562,
      "loss": 0.0003,
      "step": 261
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019867070056072214,
      "loss": 0.069,
      "step": 262
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019866015330159505,
      "loss": 0.1022,
      "step": 263
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019864956464650025,
      "loss": 0.0012,
      "step": 264
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00019863893459988062,
      "loss": 0.1075,
      "step": 265
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019862826316619628,
      "loss": 0.0002,
      "step": 266
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00019861755034992484,
      "loss": 0.0004,
      "step": 267
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001986067961555611,
      "loss": 0.0006,
      "step": 268
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001985960005876174,
      "loss": 0.0541,
      "step": 269
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019858516365062334,
      "loss": 0.1308,
      "step": 270
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019857428534912587,
      "loss": 0.0062,
      "step": 271
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019856336568768935,
      "loss": 0.0382,
      "step": 272
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00019855240467089543,
      "loss": 0.0003,
      "step": 273
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019854140230334322,
      "loss": 0.0043,
      "step": 274
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019853035858964906,
      "loss": 0.0373,
      "step": 275
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0001985192735344467,
      "loss": 0.0516,
      "step": 276
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00019850814714238716,
      "loss": 0.0004,
      "step": 277
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019849697941813898,
      "loss": 0.1028,
      "step": 278
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019848577036638788,
      "loss": 0.2622,
      "step": 279
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019847451999183694,
      "loss": 0.0004,
      "step": 280
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00019846322829920662,
      "loss": 0.0006,
      "step": 281
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019845189529323475,
      "loss": 0.1482,
      "step": 282
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019844052097867638,
      "loss": 0.038,
      "step": 283
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019842910536030403,
      "loss": 0.0107,
      "step": 284
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00019841764844290744,
      "loss": 0.035,
      "step": 285
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019840615023129372,
      "loss": 0.035,
      "step": 286
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019839461073028732,
      "loss": 0.0033,
      "step": 287
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019838302994472997,
      "loss": 0.0442,
      "step": 288
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00019837140787948082,
      "loss": 0.0135,
      "step": 289
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001983597445394162,
      "loss": 0.0014,
      "step": 290
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019834803992942987,
      "loss": 0.1629,
      "step": 291
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019833629405443284,
      "loss": 0.0867,
      "step": 292
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00019832450691935352,
      "loss": 0.0388,
      "step": 293
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001983126785291375,
      "loss": 0.0014,
      "step": 294
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019830080888874778,
      "loss": 0.0028,
      "step": 295
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00019828889800316466,
      "loss": 0.1433,
      "step": 296
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0001982769458773857,
      "loss": 0.1458,
      "step": 297
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019826495251642578,
      "loss": 0.0005,
      "step": 298
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019825291792531716,
      "loss": 0.0114,
      "step": 299
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00019824084210910925,
      "loss": 0.0508,
      "step": 300
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001982287250728689,
      "loss": 0.0006,
      "step": 301
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019821656682168012,
      "loss": 0.0377,
      "step": 302
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019820436736064435,
      "loss": 0.0383,
      "step": 303
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019819212669488026,
      "loss": 0.0052,
      "step": 304
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00019817984482952376,
      "loss": 0.0008,
      "step": 305
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019816752176972813,
      "loss": 0.0619,
      "step": 306
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019815515752066387,
      "loss": 0.0866,
      "step": 307
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001981427520875188,
      "loss": 0.002,
      "step": 308
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00019813030547549803,
      "loss": 0.0405,
      "step": 309
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001981178176898239,
      "loss": 0.0656,
      "step": 310
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019810528873573607,
      "loss": 0.0043,
      "step": 311
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019809271861849145,
      "loss": 0.0045,
      "step": 312
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00019808010734336423,
      "loss": 0.0021,
      "step": 313
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019806745491564586,
      "loss": 0.001,
      "step": 314
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00019805476134064507,
      "loss": 0.09,
      "step": 315
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001980420266236878,
      "loss": 0.0011,
      "step": 316
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001980292507701174,
      "loss": 0.0013,
      "step": 317
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0001980164337852943,
      "loss": 0.0007,
      "step": 318
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019800357567459633,
      "loss": 0.1487,
      "step": 319
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019799067644341844,
      "loss": 0.098,
      "step": 320
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00019797773609717297,
      "loss": 0.0006,
      "step": 321
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019796475464128942,
      "loss": 0.0469,
      "step": 322
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019795173208121458,
      "loss": 0.0003,
      "step": 323
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019793866842241243,
      "loss": 0.0424,
      "step": 324
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019792556367036432,
      "loss": 0.0003,
      "step": 325
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00019791241783056874,
      "loss": 0.0003,
      "step": 326
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019789923090854136,
      "loss": 0.0243,
      "step": 327
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019788600290981525,
      "loss": 0.0383,
      "step": 328
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00019787273383994062,
      "loss": 0.0005,
      "step": 329
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001978594237044849,
      "loss": 0.0329,
      "step": 330
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019784607250903277,
      "loss": 0.0013,
      "step": 331
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001978326802591862,
      "loss": 0.0363,
      "step": 332
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019781924696056426,
      "loss": 0.1015,
      "step": 333
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00019780577261880336,
      "loss": 0.0383,
      "step": 334
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019779225723955707,
      "loss": 0.001,
      "step": 335
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0001977787008284962,
      "loss": 0.0498,
      "step": 336
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019776510339130873,
      "loss": 0.095,
      "step": 337
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00019775146493369994,
      "loss": 0.0004,
      "step": 338
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019773778546139227,
      "loss": 0.0002,
      "step": 339
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001977240649801253,
      "loss": 0.0003,
      "step": 340
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.000197710303495656,
      "loss": 0.0011,
      "step": 341
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00019769650101375837,
      "loss": 0.0017,
      "step": 342
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019768265754022365,
      "loss": 0.0576,
      "step": 343
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019766877308086036,
      "loss": 0.0002,
      "step": 344
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019765484764149415,
      "loss": 0.0175,
      "step": 345
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00019764088122796783,
      "loss": 0.0002,
      "step": 346
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001976268738461415,
      "loss": 0.0008,
      "step": 347
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001976128255018924,
      "loss": 0.0006,
      "step": 348
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001975987362011149,
      "loss": 0.1749,
      "step": 349
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00019758460594972068,
      "loss": 0.0748,
      "step": 350
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019757043475363847,
      "loss": 0.0698,
      "step": 351
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019755622261881427,
      "loss": 0.0002,
      "step": 352
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019754196955121123,
      "loss": 0.0004,
      "step": 353
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00019752767555680968,
      "loss": 0.0491,
      "step": 354
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00019751334064160706,
      "loss": 0.0708,
      "step": 355
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00019749896481161808,
      "loss": 0.0673,
      "step": 356
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00019748454807287457,
      "loss": 0.0002,
      "step": 357
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00019747009043142555,
      "loss": 0.0689,
      "step": 358
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001974555918933371,
      "loss": 0.001,
      "step": 359
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019744105246469263,
      "loss": 0.0496,
      "step": 360
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019742647215159254,
      "loss": 0.0034,
      "step": 361
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00019741185096015448,
      "loss": 0.0498,
      "step": 362
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019739718889651327,
      "loss": 0.02,
      "step": 363
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019738248596682078,
      "loss": 0.0358,
      "step": 364
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00019736774217724614,
      "loss": 0.0929,
      "step": 365
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001973529575339755,
      "loss": 0.0001,
      "step": 366
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019733813204321233,
      "loss": 0.0018,
      "step": 367
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019732326571117703,
      "loss": 0.0017,
      "step": 368
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019730835854410726,
      "loss": 0.0001,
      "step": 369
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00019729341054825782,
      "loss": 0.0688,
      "step": 370
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0001972784217299006,
      "loss": 0.0004,
      "step": 371
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00019726339209532462,
      "loss": 0.0652,
      "step": 372
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00019724832165083603,
      "loss": 0.002,
      "step": 373
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00019723321040275815,
      "loss": 0.0565,
      "step": 374
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00019721805835743134,
      "loss": 0.0345,
      "step": 375
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001972028655212131,
      "loss": 0.0005,
      "step": 376
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00019718763190047808,
      "loss": 0.0726,
      "step": 377
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00019717235750161806,
      "loss": 0.08,
      "step": 378
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00019715704233104185,
      "loss": 0.0486,
      "step": 379
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00019714168639517544,
      "loss": 0.0006,
      "step": 380
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00019712628970046189,
      "loss": 0.0001,
      "step": 381
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00019711085225336132,
      "loss": 0.0653,
      "step": 382
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00019709537406035105,
      "loss": 0.1022,
      "step": 383
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00019707985512792543,
      "loss": 0.0005,
      "step": 384
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00019706429546259593,
      "loss": 0.0345,
      "step": 385
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00019704869507089105,
      "loss": 0.0003,
      "step": 386
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00019703305395935648,
      "loss": 0.0231,
      "step": 387
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001970173721345549,
      "loss": 0.2725,
      "step": 388
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00019700164960306614,
      "loss": 0.0806,
      "step": 389
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00019698588637148703,
      "loss": 0.086,
      "step": 390
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001969700824464316,
      "loss": 0.0044,
      "step": 391
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00019695423783453088,
      "loss": 0.0033,
      "step": 392
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00019693835254243287,
      "loss": 0.0028,
      "step": 393
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00019692242657680286,
      "loss": 0.0513,
      "step": 394
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00019690645994432305,
      "loss": 0.0038,
      "step": 395
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00019689045265169273,
      "loss": 0.0032,
      "step": 396
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001968744047056283,
      "loss": 0.0026,
      "step": 397
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001968583161128631,
      "loss": 0.0099,
      "step": 398
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00019684218688014772,
      "loss": 0.0675,
      "step": 399
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001968260170142496,
      "loss": 0.0425,
      "step": 400
    },
    {
      "epoch": 0.99,
      "eval_loss": 0.019980641081929207,
      "eval_runtime": 126.04,
      "eval_samples_per_second": 1.016,
      "eval_steps_per_second": 0.341,
      "step": 400
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00019680980652195333,
      "loss": 0.0016,
      "step": 401
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00019679355541006054,
      "loss": 0.0017,
      "step": 402
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001967772636853899,
      "loss": 0.0009,
      "step": 403
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019676093135477713,
      "loss": 0.095,
      "step": 404
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019674455842507492,
      "loss": 0.0646,
      "step": 405
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001967281449031531,
      "loss": 0.0014,
      "step": 406
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00019671169079589848,
      "loss": 0.001,
      "step": 407
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019669519611021486,
      "loss": 0.0223,
      "step": 408
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019667866085302312,
      "loss": 0.0006,
      "step": 409
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019666208503126112,
      "loss": 0.0609,
      "step": 410
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00019664546865188386,
      "loss": 0.1217,
      "step": 411
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019662881172186313,
      "loss": 0.0006,
      "step": 412
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019661211424818798,
      "loss": 0.0005,
      "step": 413
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019659537623786428,
      "loss": 0.0518,
      "step": 414
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00019657859769791505,
      "loss": 0.0364,
      "step": 415
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00019656177863538026,
      "loss": 0.0003,
      "step": 416
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001965449190573168,
      "loss": 0.0604,
      "step": 417
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00019652801897079869,
      "loss": 0.0569,
      "step": 418
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001965110783829169,
      "loss": 0.0875,
      "step": 419
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00019649409730077935,
      "loss": 0.0554,
      "step": 420
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00019647707573151098,
      "loss": 0.0004,
      "step": 421
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00019646001368225382,
      "loss": 0.035,
      "step": 422
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00019644291116016667,
      "loss": 0.0007,
      "step": 423
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001964257681724255,
      "loss": 0.0064,
      "step": 424
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00019640858472622316,
      "loss": 0.0008,
      "step": 425
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00019639136082876953,
      "loss": 0.0009,
      "step": 426
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001963740964872914,
      "loss": 0.0027,
      "step": 427
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00019635679170903258,
      "loss": 0.0356,
      "step": 428
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00019633944650125388,
      "loss": 0.0013,
      "step": 429
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00019632206087123296,
      "loss": 0.0179,
      "step": 430
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00019630463482626454,
      "loss": 0.0477,
      "step": 431
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019628716837366027,
      "loss": 0.0004,
      "step": 432
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019626966152074874,
      "loss": 0.0795,
      "step": 433
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019625211427487548,
      "loss": 0.1192,
      "step": 434
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00019623452664340306,
      "loss": 0.0606,
      "step": 435
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00019621689863371083,
      "loss": 0.0004,
      "step": 436
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001961992302531952,
      "loss": 0.1189,
      "step": 437
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00019618152150926955,
      "loss": 0.0015,
      "step": 438
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00019616377240936407,
      "loss": 0.0004,
      "step": 439
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000196145982960926,
      "loss": 0.0004,
      "step": 440
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00019612815317141945,
      "loss": 0.0003,
      "step": 441
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00019611028304832546,
      "loss": 0.0003,
      "step": 442
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.000196092372599142,
      "loss": 0.0153,
      "step": 443
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.000196074421831384,
      "loss": 0.0725,
      "step": 444
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00019605643075258321,
      "loss": 0.0005,
      "step": 445
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00019603839937028838,
      "loss": 0.0005,
      "step": 446
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00019602032769206517,
      "loss": 0.0003,
      "step": 447
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00019600221572549606,
      "loss": 0.0416,
      "step": 448
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00019598406347818054,
      "loss": 0.0712,
      "step": 449
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00019596587095773495,
      "loss": 0.0005,
      "step": 450
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00019594763817179254,
      "loss": 0.0095,
      "step": 451
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00019592936512800342,
      "loss": 0.0294,
      "step": 452
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00019591105183403462,
      "loss": 0.0164,
      "step": 453
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00019589269829757008,
      "loss": 0.0021,
      "step": 454
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001958743045263106,
      "loss": 0.0017,
      "step": 455
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00019585587052797389,
      "loss": 0.0439,
      "step": 456
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00019583739631029445,
      "loss": 0.0014,
      "step": 457
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00019581888188102375,
      "loss": 0.0944,
      "step": 458
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0001958003272479301,
      "loss": 0.0444,
      "step": 459
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00019578173241879872,
      "loss": 0.0063,
      "step": 460
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001957630974014316,
      "loss": 0.0054,
      "step": 461
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00019574442220364767,
      "loss": 0.0567,
      "step": 462
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.0001957257068332827,
      "loss": 0.0019,
      "step": 463
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00019570695129818926,
      "loss": 0.0355,
      "step": 464
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001956881556062369,
      "loss": 0.0891,
      "step": 465
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001956693197653119,
      "loss": 0.0026,
      "step": 466
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00019565044378331745,
      "loss": 0.0609,
      "step": 467
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00019563152766817354,
      "loss": 0.1015,
      "step": 468
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00019561257142781705,
      "loss": 0.0434,
      "step": 469
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00019559357507020162,
      "loss": 0.0016,
      "step": 470
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001955745386032978,
      "loss": 0.0339,
      "step": 471
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019555546203509297,
      "loss": 0.0305,
      "step": 472
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019553634537359122,
      "loss": 0.0003,
      "step": 473
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019551718862681364,
      "loss": 0.001,
      "step": 474
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00019549799180279792,
      "loss": 0.0016,
      "step": 475
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00019547875490959885,
      "loss": 0.0265,
      "step": 476
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00019545947795528777,
      "loss": 0.0248,
      "step": 477
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00019544016094795295,
      "loss": 0.0443,
      "step": 478
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.00019542080389569946,
      "loss": 0.0005,
      "step": 479
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019540140680664913,
      "loss": 0.0005,
      "step": 480
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019538196968894067,
      "loss": 0.0001,
      "step": 481
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019536249255072948,
      "loss": 0.0002,
      "step": 482
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00019534297540018785,
      "loss": 0.0002,
      "step": 483
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00019532341824550479,
      "loss": 0.0526,
      "step": 484
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001953038210948861,
      "loss": 0.0002,
      "step": 485
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001952841839565544,
      "loss": 0.0631,
      "step": 486
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001952645068387491,
      "loss": 0.0252,
      "step": 487
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.0001952447897497263,
      "loss": 0.0002,
      "step": 488
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019522503269775899,
      "loss": 0.056,
      "step": 489
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019520523569113677,
      "loss": 0.0001,
      "step": 490
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019518539873816617,
      "loss": 0.0591,
      "step": 491
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00019516552184717037,
      "loss": 0.0257,
      "step": 492
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00019514560502648936,
      "loss": 0.0989,
      "step": 493
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00019512564828447988,
      "loss": 0.0679,
      "step": 494
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.0002,
      "step": 495
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.0001950856150699861,
      "loss": 0.0662,
      "step": 496
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00019506553861429898,
      "loss": 0.0004,
      "step": 497
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001950454222708778,
      "loss": 0.0464,
      "step": 498
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00019502526604816295,
      "loss": 0.0657,
      "step": 499
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0001950050699546116,
      "loss": 0.0001,
      "step": 500
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00019498483399869767,
      "loss": 0.0327,
      "step": 501
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.0001949645581889118,
      "loss": 0.0701,
      "step": 502
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00019494424253376134,
      "loss": 0.0003,
      "step": 503
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00019492388704177036,
      "loss": 0.0001,
      "step": 504
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019490349172147963,
      "loss": 0.0002,
      "step": 505
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019488305658144667,
      "loss": 0.0633,
      "step": 506
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019486258163024567,
      "loss": 0.0066,
      "step": 507
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.00019484206687646753,
      "loss": 0.0001,
      "step": 508
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.0001948215123287199,
      "loss": 0.0001,
      "step": 509
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00019480091799562704,
      "loss": 0.003,
      "step": 510
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00019478028388583,
      "loss": 0.0005,
      "step": 511
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00019475961000798645,
      "loss": 0.0002,
      "step": 512
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00019473889637077073,
      "loss": 0.0002,
      "step": 513
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001947181429828739,
      "loss": 0.0594,
      "step": 514
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00019469734985300371,
      "loss": 0.0003,
      "step": 515
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00019467651698988462,
      "loss": 0.0012,
      "step": 516
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00019465564440225767,
      "loss": 0.0003,
      "step": 517
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.0001946347320988806,
      "loss": 0.0001,
      "step": 518
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00019461378008852785,
      "loss": 0.0029,
      "step": 519
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00019459278837999046,
      "loss": 0.0017,
      "step": 520
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0001945717569820762,
      "loss": 0.009,
      "step": 521
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00019455068590360942,
      "loss": 0.0014,
      "step": 522
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00019452957515343118,
      "loss": 0.0007,
      "step": 523
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00019450842474039913,
      "loss": 0.0011,
      "step": 524
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00019448723467338763,
      "loss": 0.0279,
      "step": 525
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00019446600496128758,
      "loss": 0.0443,
      "step": 526
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00019444473561300668,
      "loss": 0.0261,
      "step": 527
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00019442342663746902,
      "loss": 0.06,
      "step": 528
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00019440207804361553,
      "loss": 0.0002,
      "step": 529
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00019438068984040365,
      "loss": 0.0514,
      "step": 530
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0001943592620368075,
      "loss": 0.0004,
      "step": 531
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00019433779464181778,
      "loss": 0.0593,
      "step": 532
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00019431628766444182,
      "loss": 0.0122,
      "step": 533
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00019429474111370352,
      "loss": 0.0393,
      "step": 534
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00019427315499864344,
      "loss": 0.062,
      "step": 535
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001942515293283187,
      "loss": 0.0549,
      "step": 536
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.000194229864111803,
      "loss": 0.0005,
      "step": 537
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00019420815935818672,
      "loss": 0.0004,
      "step": 538
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00019418641507657673,
      "loss": 0.0561,
      "step": 539
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00019416463127609656,
      "loss": 0.0574,
      "step": 540
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00019414280796588624,
      "loss": 0.0573,
      "step": 541
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00019412094515510248,
      "loss": 0.0012,
      "step": 542
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.0001940990428529185,
      "loss": 0.0064,
      "step": 543
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00019407710106852404,
      "loss": 0.0661,
      "step": 544
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0001940551198111255,
      "loss": 0.0512,
      "step": 545
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00019403309908994586,
      "loss": 0.001,
      "step": 546
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00019401103891422455,
      "loss": 0.042,
      "step": 547
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00019398893929321761,
      "loss": 0.0537,
      "step": 548
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00019396680023619765,
      "loss": 0.2087,
      "step": 549
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00019394462175245381,
      "loss": 0.0287,
      "step": 550
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00019392240385129173,
      "loss": 0.0028,
      "step": 551
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00019390014654203369,
      "loss": 0.0006,
      "step": 552
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00019387784983401838,
      "loss": 0.0008,
      "step": 553
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001938555137366011,
      "loss": 0.0403,
      "step": 554
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0001938331382591537,
      "loss": 0.0014,
      "step": 555
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.00019381072341106452,
      "loss": 0.001,
      "step": 556
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00019378826920173837,
      "loss": 0.0037,
      "step": 557
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001937657756405966,
      "loss": 0.0008,
      "step": 558
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00019374324273707715,
      "loss": 0.0008,
      "step": 559
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00019372067050063438,
      "loss": 0.0675,
      "step": 560
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00019369805894073919,
      "loss": 0.041,
      "step": 561
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00019367540806687893,
      "loss": 0.0299,
      "step": 562
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00019365271788855757,
      "loss": 0.0006,
      "step": 563
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0001936299884152954,
      "loss": 0.0125,
      "step": 564
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00019360721965662933,
      "loss": 0.032,
      "step": 565
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0001935844116221127,
      "loss": 0.0252,
      "step": 566
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00019356156432131534,
      "loss": 0.0639,
      "step": 567
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00019353867776382354,
      "loss": 0.0005,
      "step": 568
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.00019351575195924013,
      "loss": 0.0014,
      "step": 569
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00019349278691718427,
      "loss": 0.0019,
      "step": 570
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00019346978264729172,
      "loss": 0.1464,
      "step": 571
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0001934467391592146,
      "loss": 0.0019,
      "step": 572
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00019342365646262156,
      "loss": 0.0376,
      "step": 573
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00019340053456719768,
      "loss": 0.0007,
      "step": 574
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00019337737348264447,
      "loss": 0.0007,
      "step": 575
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00019335417321867987,
      "loss": 0.001,
      "step": 576
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.0001933309337850383,
      "loss": 0.0108,
      "step": 577
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001933076551914706,
      "loss": 0.0225,
      "step": 578
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.000193284337447744,
      "loss": 0.063,
      "step": 579
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00019326098056364222,
      "loss": 0.0476,
      "step": 580
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00019323758454896538,
      "loss": 0.0011,
      "step": 581
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00019321414941353003,
      "loss": 0.0003,
      "step": 582
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001931906751671691,
      "loss": 0.0262,
      "step": 583
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00019316716181973188,
      "loss": 0.0005,
      "step": 584
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.00019314360938108425,
      "loss": 0.084,
      "step": 585
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00019312001786110828,
      "loss": 0.0512,
      "step": 586
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0001930963872697026,
      "loss": 0.0235,
      "step": 587
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00019307271761678213,
      "loss": 0.0002,
      "step": 588
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00019304900891227824,
      "loss": 0.0004,
      "step": 589
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00019302526116613864,
      "loss": 0.0491,
      "step": 590
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00019300147438832744,
      "loss": 0.0595,
      "step": 591
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00019297764858882514,
      "loss": 0.0005,
      "step": 592
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00019295378377762862,
      "loss": 0.0693,
      "step": 593
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00019292987996475113,
      "loss": 0.0024,
      "step": 594
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00019290593716022217,
      "loss": 0.001,
      "step": 595
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0001928819553740878,
      "loss": 0.0134,
      "step": 596
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00019285793461641028,
      "loss": 0.0295,
      "step": 597
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00019283387489726827,
      "loss": 0.0006,
      "step": 598
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.0001928097762267568,
      "loss": 0.0009,
      "step": 599
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00019278563861498723,
      "loss": 0.0465,
      "step": 600
    },
    {
      "epoch": 1.48,
      "eval_loss": 0.017965465784072876,
      "eval_runtime": 126.0107,
      "eval_samples_per_second": 1.016,
      "eval_steps_per_second": 0.341,
      "step": 600
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.00019276146207208728,
      "loss": 0.039,
      "step": 601
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00019273724660820088,
      "loss": 0.0005,
      "step": 602
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00019271299223348848,
      "loss": 0.071,
      "step": 603
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00019268869895812672,
      "loss": 0.0007,
      "step": 604
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.00019266436679230865,
      "loss": 0.1072,
      "step": 605
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00019263999574624355,
      "loss": 0.0503,
      "step": 606
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00019261558583015707,
      "loss": 0.0451,
      "step": 607
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001925911370542912,
      "loss": 0.0005,
      "step": 608
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00019256664942890413,
      "loss": 0.0202,
      "step": 609
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00019254212296427044,
      "loss": 0.0401,
      "step": 610
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00019251755767068097,
      "loss": 0.1015,
      "step": 611
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00019249295355844285,
      "loss": 0.0009,
      "step": 612
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00019246831063787957,
      "loss": 0.0007,
      "step": 613
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00019244362891933077,
      "loss": 0.0007,
      "step": 614
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00019241890841315248,
      "loss": 0.0726,
      "step": 615
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.00019239414912971696,
      "loss": 0.0022,
      "step": 616
    },
    {
      "epoch": 1.52,
      "learning_rate": 0.0001923693510794127,
      "loss": 0.1312,
      "step": 617
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001923445142726446,
      "loss": 0.0742,
      "step": 618
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00019231963871983366,
      "loss": 0.043,
      "step": 619
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0001922947244314172,
      "loss": 0.0899,
      "step": 620
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00019226977141784875,
      "loss": 0.0004,
      "step": 621
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001922447796895982,
      "loss": 0.0003,
      "step": 622
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001922197492571516,
      "loss": 0.0003,
      "step": 623
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.00019219468013101124,
      "loss": 0.0015,
      "step": 624
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001921695723216957,
      "loss": 0.0003,
      "step": 625
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00019214442583973966,
      "loss": 0.001,
      "step": 626
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0001921192406956942,
      "loss": 0.0004,
      "step": 627
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00019209401690012653,
      "loss": 0.0651,
      "step": 628
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00019206875446362001,
      "loss": 0.0938,
      "step": 629
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00019204345339677442,
      "loss": 0.0486,
      "step": 630
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001920181137102055,
      "loss": 0.0281,
      "step": 631
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.00019199273541454538,
      "loss": 0.0003,
      "step": 632
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001919673185204423,
      "loss": 0.0001,
      "step": 633
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019194186303856067,
      "loss": 0.0002,
      "step": 634
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019191636897958122,
      "loss": 0.0003,
      "step": 635
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019189083635420075,
      "loss": 0.0004,
      "step": 636
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00019186526517313225,
      "loss": 0.0003,
      "step": 637
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019183965544710495,
      "loss": 0.0611,
      "step": 638
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.0001918140071868642,
      "loss": 0.0528,
      "step": 639
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019178832040317155,
      "loss": 0.0948,
      "step": 640
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.00019176259510680463,
      "loss": 0.0002,
      "step": 641
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001917368313085574,
      "loss": 0.0003,
      "step": 642
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001917110290192398,
      "loss": 0.0005,
      "step": 643
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.00019168518824967795,
      "loss": 0.0415,
      "step": 644
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0001916593090107143,
      "loss": 0.0259,
      "step": 645
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019163339131320718,
      "loss": 0.0261,
      "step": 646
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.0001916074351680312,
      "loss": 0.0001,
      "step": 647
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019158144058607708,
      "loss": 0.0001,
      "step": 648
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019155540757825168,
      "loss": 0.0002,
      "step": 649
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00019152933615547798,
      "loss": 0.031,
      "step": 650
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019150322632869497,
      "loss": 0.0002,
      "step": 651
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.000191477078108858,
      "loss": 0.0405,
      "step": 652
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019145089150693822,
      "loss": 0.0651,
      "step": 653
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00019142466653392318,
      "loss": 0.0001,
      "step": 654
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001913984032008163,
      "loss": 0.0903,
      "step": 655
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001913721015186372,
      "loss": 0.0001,
      "step": 656
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.00019134576149842163,
      "loss": 0.0271,
      "step": 657
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001913193831512213,
      "loss": 0.0002,
      "step": 658
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019129296648810412,
      "loss": 0.0406,
      "step": 659
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019126651152015403,
      "loss": 0.0484,
      "step": 660
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.00019124001825847103,
      "loss": 0.0004,
      "step": 661
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0001912134867141712,
      "loss": 0.0509,
      "step": 662
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.00019118691689838668,
      "loss": 0.0436,
      "step": 663
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001911603088222657,
      "loss": 0.0358,
      "step": 664
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001911336624969725,
      "loss": 0.0447,
      "step": 665
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.0001911069779336873,
      "loss": 0.0439,
      "step": 666
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00019108025514360662,
      "loss": 0.0617,
      "step": 667
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00019105349413794272,
      "loss": 0.0001,
      "step": 668
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00019102669492792405,
      "loss": 0.0001,
      "step": 669
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00019099985752479506,
      "loss": 0.0001,
      "step": 670
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00019097298193981624,
      "loss": 0.0224,
      "step": 671
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00019094606818426403,
      "loss": 0.0407,
      "step": 672
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00019091911626943102,
      "loss": 0.0632,
      "step": 673
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00019089212620662568,
      "loss": 0.0505,
      "step": 674
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00019086509800717258,
      "loss": 0.0001,
      "step": 675
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00019083803168241223,
      "loss": 0.0465,
      "step": 676
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00019081092724370114,
      "loss": 0.0001,
      "step": 677
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.00019078378470241183,
      "loss": 0.0312,
      "step": 678
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00019075660406993284,
      "loss": 0.0892,
      "step": 679
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00019072938535766865,
      "loss": 0.0007,
      "step": 680
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00019070212857703967,
      "loss": 0.0002,
      "step": 681
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00019067483373948243,
      "loss": 0.0005,
      "step": 682
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00019064750085644926,
      "loss": 0.0545,
      "step": 683
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00019062012993940859,
      "loss": 0.0501,
      "step": 684
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001905927209998447,
      "loss": 0.0001,
      "step": 685
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00019056527404925789,
      "loss": 0.1453,
      "step": 686
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00019053778909916438,
      "loss": 0.0001,
      "step": 687
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00019051026616109638,
      "loss": 0.0962,
      "step": 688
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00019048270524660196,
      "loss": 0.0436,
      "step": 689
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.0001904551063672452,
      "loss": 0.1079,
      "step": 690
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00019042746953460606,
      "loss": 0.0687,
      "step": 691
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00019039979476028043,
      "loss": 0.0853,
      "step": 692
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.00019037208205588017,
      "loss": 0.0943,
      "step": 693
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.000190344331433033,
      "loss": 0.0001,
      "step": 694
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00019031654290338254,
      "loss": 0.0375,
      "step": 695
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00019028871647858834,
      "loss": 0.0001,
      "step": 696
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00019026085217032593,
      "loss": 0.0001,
      "step": 697
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00019023294999028653,
      "loss": 0.1158,
      "step": 698
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00019020500995017747,
      "loss": 0.0398,
      "step": 699
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00019017703206172185,
      "loss": 0.0001,
      "step": 700
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.00019014901633665867,
      "loss": 0.0001,
      "step": 701
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0001901209627867428,
      "loss": 0.0473,
      "step": 702
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.000190092871423745,
      "loss": 0.0528,
      "step": 703
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001900647422594519,
      "loss": 0.0581,
      "step": 704
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001900365753056659,
      "loss": 0.0434,
      "step": 705
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0001900083705742054,
      "loss": 0.0001,
      "step": 706
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00018998012807690457,
      "loss": 0.0886,
      "step": 707
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00018995184782561345,
      "loss": 0.0391,
      "step": 708
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00018992352983219785,
      "loss": 0.0006,
      "step": 709
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.00018989517410853955,
      "loss": 0.0002,
      "step": 710
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00018986678066653601,
      "loss": 0.0001,
      "step": 711
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.0001898383495181007,
      "loss": 0.0006,
      "step": 712
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00018980988067516266,
      "loss": 0.0539,
      "step": 713
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00018978137414966698,
      "loss": 0.0211,
      "step": 714
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00018975282995357446,
      "loss": 0.0355,
      "step": 715
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001897242480988617,
      "loss": 0.0532,
      "step": 716
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0001896956285975211,
      "loss": 0.0354,
      "step": 717
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.00018966697146156092,
      "loss": 0.0004,
      "step": 718
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001896382767030051,
      "loss": 0.0418,
      "step": 719
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00018960954433389345,
      "loss": 0.0502,
      "step": 720
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00018958077436628158,
      "loss": 0.0004,
      "step": 721
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.0001895519668122408,
      "loss": 0.0001,
      "step": 722
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00018952312168385823,
      "loss": 0.0509,
      "step": 723
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0001894942389932367,
      "loss": 0.0003,
      "step": 724
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00018946531875249493,
      "loss": 0.0006,
      "step": 725
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.00018943636097376726,
      "loss": 0.019,
      "step": 726
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00018940736566920387,
      "loss": 0.0002,
      "step": 727
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00018937833285097066,
      "loss": 0.0004,
      "step": 728
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00018934926253124921,
      "loss": 0.0258,
      "step": 729
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00018932015472223693,
      "loss": 0.0001,
      "step": 730
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.0001892910094361469,
      "loss": 0.0008,
      "step": 731
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00018926182668520792,
      "loss": 0.0479,
      "step": 732
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00018923260648166457,
      "loss": 0.0008,
      "step": 733
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0001892033488377771,
      "loss": 0.1391,
      "step": 734
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.00018917405376582145,
      "loss": 0.0029,
      "step": 735
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001891447212780893,
      "loss": 0.0002,
      "step": 736
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00018911535138688802,
      "loss": 0.0002,
      "step": 737
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001890859441045407,
      "loss": 0.0877,
      "step": 738
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.00018905649944338598,
      "loss": 0.0014,
      "step": 739
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0001890270174157784,
      "loss": 0.0006,
      "step": 740
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00018899749803408806,
      "loss": 0.1397,
      "step": 741
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00018896794131070073,
      "loss": 0.1003,
      "step": 742
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00018893834725801782,
      "loss": 0.0558,
      "step": 743
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001889087158884565,
      "loss": 0.0016,
      "step": 744
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00018887904721444953,
      "loss": 0.0328,
      "step": 745
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00018884934124844532,
      "loss": 0.0359,
      "step": 746
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00018881959800290797,
      "loss": 0.0856,
      "step": 747
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00018878981749031716,
      "loss": 0.0639,
      "step": 748
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00018875999972316825,
      "loss": 0.0152,
      "step": 749
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00018873014471397224,
      "loss": 0.0043,
      "step": 750
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0001887002524752557,
      "loss": 0.0024,
      "step": 751
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00018867032301956088,
      "loss": 0.0007,
      "step": 752
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00018864035635944562,
      "loss": 0.0005,
      "step": 753
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00018861035250748343,
      "loss": 0.0556,
      "step": 754
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00018858031147626325,
      "loss": 0.0383,
      "step": 755
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00018855023327838983,
      "loss": 0.0003,
      "step": 756
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0001885201179264834,
      "loss": 0.0006,
      "step": 757
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00018848996543317982,
      "loss": 0.0033,
      "step": 758
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00018845977581113046,
      "loss": 0.0003,
      "step": 759
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00018842954907300236,
      "loss": 0.0507,
      "step": 760
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00018839928523147812,
      "loss": 0.181,
      "step": 761
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00018836898429925585,
      "loss": 0.0007,
      "step": 762
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.0001883386462890493,
      "loss": 0.0371,
      "step": 763
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001883082712135877,
      "loss": 0.0005,
      "step": 764
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00018827785908561584,
      "loss": 0.0009,
      "step": 765
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00018824740991789415,
      "loss": 0.0009,
      "step": 766
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0001882169237231985,
      "loss": 0.0014,
      "step": 767
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00018818640051432035,
      "loss": 0.0451,
      "step": 768
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.00018815584030406664,
      "loss": 0.0006,
      "step": 769
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001881252431052599,
      "loss": 0.0046,
      "step": 770
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001880946089307381,
      "loss": 0.0058,
      "step": 771
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00018806393779335483,
      "loss": 0.0002,
      "step": 772
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00018803322970597908,
      "loss": 0.0012,
      "step": 773
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00018800248468149543,
      "loss": 0.1054,
      "step": 774
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00018797170273280388,
      "loss": 0.0132,
      "step": 775
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00018794088387282,
      "loss": 0.0526,
      "step": 776
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00018791002811447481,
      "loss": 0.0004,
      "step": 777
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00018787913547071484,
      "loss": 0.0421,
      "step": 778
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00018784820595450197,
      "loss": 0.0585,
      "step": 779
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00018781723957881372,
      "loss": 0.0561,
      "step": 780
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00018778623635664303,
      "loss": 0.0618,
      "step": 781
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0001877551963009982,
      "loss": 0.0473,
      "step": 782
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00018772411942490313,
      "loss": 0.0004,
      "step": 783
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001876930057413971,
      "loss": 0.001,
      "step": 784
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001876618552635348,
      "loss": 0.0439,
      "step": 785
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00018763066800438636,
      "loss": 0.068,
      "step": 786
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00018759944397703747,
      "loss": 0.035,
      "step": 787
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00018756818319458907,
      "loss": 0.0005,
      "step": 788
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001875368856701576,
      "loss": 0.0472,
      "step": 789
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.000187505551416875,
      "loss": 0.0495,
      "step": 790
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00018747418044788846,
      "loss": 0.0657,
      "step": 791
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001874427727763607,
      "loss": 0.0005,
      "step": 792
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001874113284154698,
      "loss": 0.076,
      "step": 793
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.0001873798473784092,
      "loss": 0.0581,
      "step": 794
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00018734832967838775,
      "loss": 0.0007,
      "step": 795
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00018731677532862976,
      "loss": 0.0363,
      "step": 796
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00018728518434237473,
      "loss": 0.0651,
      "step": 797
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.00018725355673287778,
      "loss": 0.0649,
      "step": 798
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0001872218925134092,
      "loss": 0.0004,
      "step": 799
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00018719019169725472,
      "loss": 0.0002,
      "step": 800
    },
    {
      "epoch": 1.98,
      "eval_loss": 0.014746900647878647,
      "eval_runtime": 126.097,
      "eval_samples_per_second": 1.015,
      "eval_steps_per_second": 0.341,
      "step": 800
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001871584542977154,
      "loss": 0.0467,
      "step": 801
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00018712668032810768,
      "loss": 0.0519,
      "step": 802
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001870948698017633,
      "loss": 0.0105,
      "step": 803
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00018706302273202943,
      "loss": 0.0003,
      "step": 804
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00018703113913226847,
      "loss": 0.0297,
      "step": 805
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00018699921901585813,
      "loss": 0.1403,
      "step": 806
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0001869672623961916,
      "loss": 0.0525,
      "step": 807
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.0001869352692866772,
      "loss": 0.0691,
      "step": 808
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00018690323970073873,
      "loss": 0.0535,
      "step": 809
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00018687117365181512,
      "loss": 0.0336,
      "step": 810
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00018683907115336074,
      "loss": 0.0262,
      "step": 811
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00018680693221884517,
      "loss": 0.0004,
      "step": 812
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00018677475686175338,
      "loss": 0.0003,
      "step": 813
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00018674254509558544,
      "loss": 0.0402,
      "step": 814
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0001867102969338569,
      "loss": 0.0004,
      "step": 815
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.00018667801239009846,
      "loss": 0.0005,
      "step": 816
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00018664569147785613,
      "loss": 0.005,
      "step": 817
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00018661333421069113,
      "loss": 0.0008,
      "step": 818
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00018658094060217999,
      "loss": 0.0608,
      "step": 819
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.00018654851066591448,
      "loss": 0.031,
      "step": 820
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00018651604441550154,
      "loss": 0.0024,
      "step": 821
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00018648354186456348,
      "loss": 0.0726,
      "step": 822
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00018645100302673774,
      "loss": 0.0463,
      "step": 823
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.000186418427915677,
      "loss": 0.0032,
      "step": 824
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001863858165450492,
      "loss": 0.0004,
      "step": 825
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00018635316892853741,
      "loss": 0.0196,
      "step": 826
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00018632048507984,
      "loss": 0.022,
      "step": 827
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.00018628776501267052,
      "loss": 0.0009,
      "step": 828
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001862550087407577,
      "loss": 0.1024,
      "step": 829
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001862222162778454,
      "loss": 0.0796,
      "step": 830
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.00018618938763769282,
      "loss": 0.0004,
      "step": 831
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0001861565228340742,
      "loss": 0.0004,
      "step": 832
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00018612362188077898,
      "loss": 0.1187,
      "step": 833
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00018609068479161182,
      "loss": 0.002,
      "step": 834
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00018605771158039253,
      "loss": 0.0931,
      "step": 835
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00018602470226095603,
      "loss": 0.1085,
      "step": 836
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001859916568471524,
      "loss": 0.0022,
      "step": 837
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00018595857535284692,
      "loss": 0.0291,
      "step": 838
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0001859254577919199,
      "loss": 0.032,
      "step": 839
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.00018589230417826697,
      "loss": 0.0046,
      "step": 840
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001858591145257987,
      "loss": 0.0018,
      "step": 841
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00018582588884844084,
      "loss": 0.1096,
      "step": 842
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001857926271601343,
      "loss": 0.0547,
      "step": 843
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00018575932947483502,
      "loss": 0.0151,
      "step": 844
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00018572599580651415,
      "loss": 0.071,
      "step": 845
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00018569262616915784,
      "loss": 0.0062,
      "step": 846
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00018565922057676737,
      "loss": 0.0039,
      "step": 847
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.00018562577904335912,
      "loss": 0.0017,
      "step": 848
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00018559230158296454,
      "loss": 0.0013,
      "step": 849
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00018555878820963013,
      "loss": 0.0011,
      "step": 850
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00018552523893741748,
      "loss": 0.0013,
      "step": 851
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00018549165378040327,
      "loss": 0.005,
      "step": 852
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0001854580327526792,
      "loss": 0.0379,
      "step": 853
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00018542437586835202,
      "loss": 0.0847,
      "step": 854
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00018539068314154354,
      "loss": 0.0017,
      "step": 855
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00018535695458639056,
      "loss": 0.0721,
      "step": 856
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.000185323190217045,
      "loss": 0.0006,
      "step": 857
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00018528939004767376,
      "loss": 0.0003,
      "step": 858
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00018525555409245877,
      "loss": 0.0005,
      "step": 859
    },
    {
      "epoch": 2.12,
      "learning_rate": 0.00018522168236559695,
      "loss": 0.0008,
      "step": 860
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00018518777488130023,
      "loss": 0.0466,
      "step": 861
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001851538316537956,
      "loss": 0.0372,
      "step": 862
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00018511985269732497,
      "loss": 0.038,
      "step": 863
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0001850858380261453,
      "loss": 0.0013,
      "step": 864
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00018505178765452853,
      "loss": 0.0304,
      "step": 865
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00018501770159676156,
      "loss": 0.0465,
      "step": 866
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00018498357986714622,
      "loss": 0.0424,
      "step": 867
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.0001849494224799994,
      "loss": 0.0705,
      "step": 868
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001849152294496529,
      "loss": 0.0002,
      "step": 869
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00018488100079045344,
      "loss": 0.0009,
      "step": 870
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.00018484673651676282,
      "loss": 0.0002,
      "step": 871
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001848124366429576,
      "loss": 0.0455,
      "step": 872
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001847781011834294,
      "loss": 0.0505,
      "step": 873
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00018474373015258473,
      "loss": 0.0386,
      "step": 874
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.00018470932356484508,
      "loss": 0.0509,
      "step": 875
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.0001846748814346468,
      "loss": 0.0003,
      "step": 876
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0001846404037764411,
      "loss": 0.0351,
      "step": 877
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00018460589060469425,
      "loss": 0.0003,
      "step": 878
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0001845713419338873,
      "loss": 0.0002,
      "step": 879
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00018453675777851627,
      "loss": 0.0037,
      "step": 880
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00018450213815309198,
      "loss": 0.0442,
      "step": 881
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00018446748307214019,
      "loss": 0.035,
      "step": 882
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.00018443279255020152,
      "loss": 0.0875,
      "step": 883
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.0001843980666018315,
      "loss": 0.0418,
      "step": 884
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00018436330524160047,
      "loss": 0.0009,
      "step": 885
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00018432850848409363,
      "loss": 0.0089,
      "step": 886
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00018429367634391114,
      "loss": 0.0017,
      "step": 887
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00018425880883566782,
      "loss": 0.0004,
      "step": 888
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00018422390597399349,
      "loss": 0.0464,
      "step": 889
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.0001841889677735327,
      "loss": 0.0027,
      "step": 890
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00018415399424894492,
      "loss": 0.0004,
      "step": 891
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00018411898541490434,
      "loss": 0.0928,
      "step": 892
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.00018408394128610001,
      "loss": 0.0042,
      "step": 893
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001840488618772359,
      "loss": 0.002,
      "step": 894
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00018401374720303056,
      "loss": 0.0002,
      "step": 895
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00018397859727821748,
      "loss": 0.0004,
      "step": 896
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00018394341211754495,
      "loss": 0.0987,
      "step": 897
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00018390819173577598,
      "loss": 0.0004,
      "step": 898
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.0001838729361476884,
      "loss": 0.0002,
      "step": 899
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00018383764536807485,
      "loss": 0.0002,
      "step": 900
    },
    {
      "epoch": 2.22,
      "learning_rate": 0.00018380231941174258,
      "loss": 0.0422,
      "step": 901
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00018376695829351377,
      "loss": 0.0004,
      "step": 902
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001837315620282253,
      "loss": 0.0007,
      "step": 903
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.00018369613063072874,
      "loss": 0.0231,
      "step": 904
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001836606641158905,
      "loss": 0.053,
      "step": 905
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00018362516249859163,
      "loss": 0.0003,
      "step": 906
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00018358962579372796,
      "loss": 0.0403,
      "step": 907
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.00018355405401621001,
      "loss": 0.0319,
      "step": 908
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.0001835184471809631,
      "loss": 0.0402,
      "step": 909
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00018348280530292713,
      "loss": 0.0628,
      "step": 910
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0001834471283970568,
      "loss": 0.0937,
      "step": 911
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00018341141647832147,
      "loss": 0.0005,
      "step": 912
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00018337566956170523,
      "loss": 0.05,
      "step": 913
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00018333988766220676,
      "loss": 0.0202,
      "step": 914
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00018330407079483952,
      "loss": 0.0008,
      "step": 915
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.0001832682189746316,
      "loss": 0.0003,
      "step": 916
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.00018323233221662573,
      "loss": 0.0037,
      "step": 917
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.00018319641053587938,
      "loss": 0.0417,
      "step": 918
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001831604539474646,
      "loss": 0.0269,
      "step": 919
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001831244624664681,
      "loss": 0.048,
      "step": 920
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001830884361079912,
      "loss": 0.0801,
      "step": 921
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00018305237488714995,
      "loss": 0.0001,
      "step": 922
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00018301627881907494,
      "loss": 0.0425,
      "step": 923
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00018298014791891137,
      "loss": 0.0323,
      "step": 924
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00018294398220181917,
      "loss": 0.0631,
      "step": 925
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00018290778168297277,
      "loss": 0.0005,
      "step": 926
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00018287154637756125,
      "loss": 0.0007,
      "step": 927
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00018283527630078825,
      "loss": 0.0237,
      "step": 928
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.00018279897146787204,
      "loss": 0.0605,
      "step": 929
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.0001827626318940454,
      "loss": 0.0871,
      "step": 930
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00018272625759455582,
      "loss": 0.003,
      "step": 931
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00018268984858466522,
      "loss": 0.0001,
      "step": 932
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00018265340487965017,
      "loss": 0.0586,
      "step": 933
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00018261692649480175,
      "loss": 0.0459,
      "step": 934
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00018258041344542566,
      "loss": 0.0005,
      "step": 935
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00018254386574684204,
      "loss": 0.027,
      "step": 936
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.00018250728341438568,
      "loss": 0.0001,
      "step": 937
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001824706664634058,
      "loss": 0.0824,
      "step": 938
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001824340149092662,
      "loss": 0.0112,
      "step": 939
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00018239732876734527,
      "loss": 0.0007,
      "step": 940
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001823606080530357,
      "loss": 0.0004,
      "step": 941
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0001823238527817449,
      "loss": 0.1245,
      "step": 942
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0001822870629688947,
      "loss": 0.0796,
      "step": 943
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00018225023862992142,
      "loss": 0.0712,
      "step": 944
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00018221337978027583,
      "loss": 0.033,
      "step": 945
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00018217648643542323,
      "loss": 0.0025,
      "step": 946
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00018213955861084343,
      "loss": 0.0002,
      "step": 947
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001821025963220306,
      "loss": 0.0015,
      "step": 948
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001820655995844935,
      "loss": 0.0024,
      "step": 949
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00018202856841375518,
      "loss": 0.0435,
      "step": 950
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00018199150282535332,
      "loss": 0.0511,
      "step": 951
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.00018195440283483988,
      "loss": 0.0627,
      "step": 952
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0001819172684577814,
      "loss": 0.0885,
      "step": 953
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.0001818800997097587,
      "loss": 0.0628,
      "step": 954
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00018184289660636715,
      "loss": 0.0008,
      "step": 955
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00018180565916321647,
      "loss": 0.0005,
      "step": 956
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00018176838739593078,
      "loss": 0.0304,
      "step": 957
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001817310813201486,
      "loss": 0.0297,
      "step": 958
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00018169374095152295,
      "loss": 0.001,
      "step": 959
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0001816563663057211,
      "loss": 0.0022,
      "step": 960
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00018161895739842476,
      "loss": 0.0411,
      "step": 961
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00018158151424533002,
      "loss": 0.0012,
      "step": 962
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001815440368621473,
      "loss": 0.0343,
      "step": 963
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00018150652526460146,
      "loss": 0.0418,
      "step": 964
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00018146897946843163,
      "loss": 0.1491,
      "step": 965
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00018143139948939137,
      "loss": 0.0002,
      "step": 966
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00018139378534324848,
      "loss": 0.0006,
      "step": 967
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00018135613704578526,
      "loss": 0.0004,
      "step": 968
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00018131845461279812,
      "loss": 0.0704,
      "step": 969
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.000181280738060098,
      "loss": 0.0002,
      "step": 970
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00018124298740351003,
      "loss": 0.0001,
      "step": 971
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00018120520265887363,
      "loss": 0.0025,
      "step": 972
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00018116738384204266,
      "loss": 0.0254,
      "step": 973
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00018112953096888516,
      "loss": 0.0003,
      "step": 974
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001810916440552835,
      "loss": 0.1252,
      "step": 975
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00018105372311713432,
      "loss": 0.0005,
      "step": 976
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001810157681703485,
      "loss": 0.0002,
      "step": 977
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0001809777792308513,
      "loss": 0.024,
      "step": 978
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00018093975631458217,
      "loss": 0.0001,
      "step": 979
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.0566,
      "step": 980
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00018086360861555706,
      "loss": 0.0003,
      "step": 981
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.0001808254838647513,
      "loss": 0.0443,
      "step": 982
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00018078732520107385,
      "loss": 0.0001,
      "step": 983
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00018074913264053545,
      "loss": 0.0002,
      "step": 984
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00018071090619916093,
      "loss": 0.0553,
      "step": 985
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00018067264589298945,
      "loss": 0.0981,
      "step": 986
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.0001806343517380743,
      "loss": 0.001,
      "step": 987
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00018059602375048293,
      "loss": 0.0004,
      "step": 988
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00018055766194629715,
      "loss": 0.0001,
      "step": 989
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00018051926634161282,
      "loss": 0.0004,
      "step": 990
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00018048083695254005,
      "loss": 0.0494,
      "step": 991
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00018044237379520305,
      "loss": 0.089,
      "step": 992
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.00018040387688574025,
      "loss": 0.0001,
      "step": 993
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0001803653462403043,
      "loss": 0.056,
      "step": 994
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00018032678187506187,
      "loss": 0.0343,
      "step": 995
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.0001802881838061939,
      "loss": 0.041,
      "step": 996
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00018024955204989538,
      "loss": 0.0631,
      "step": 997
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00018021088662237552,
      "loss": 0.0001,
      "step": 998
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001801721875398576,
      "loss": 0.0002,
      "step": 999
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00018013345481857903,
      "loss": 0.0001,
      "step": 1000
    },
    {
      "epoch": 2.47,
      "eval_loss": 0.016305094584822655,
      "eval_runtime": 126.0835,
      "eval_samples_per_second": 1.015,
      "eval_steps_per_second": 0.341,
      "step": 1000
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001800946884747913,
      "loss": 0.0365,
      "step": 1001
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00018005588852476015,
      "loss": 0.0001,
      "step": 1002
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00018001705498476523,
      "loss": 0.0412,
      "step": 1003
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.00017997818787110042,
      "loss": 0.0001,
      "step": 1004
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001799392872000736,
      "loss": 0.0001,
      "step": 1005
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001799003529880068,
      "loss": 0.0,
      "step": 1006
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00017986138525123607,
      "loss": 0.0739,
      "step": 1007
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001798223840061116,
      "loss": 0.0001,
      "step": 1008
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0001797833492689975,
      "loss": 0.0863,
      "step": 1009
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00017974428105627208,
      "loss": 0.0002,
      "step": 1010
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00017970517938432765,
      "loss": 0.0538,
      "step": 1011
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00017966604426957047,
      "loss": 0.0001,
      "step": 1012
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00017962687572842102,
      "loss": 0.034,
      "step": 1013
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00017958767377731358,
      "loss": 0.0001,
      "step": 1014
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00017954843843269664,
      "loss": 0.0001,
      "step": 1015
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00017950916971103259,
      "loss": 0.0001,
      "step": 1016
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00017946986762879785,
      "loss": 0.0002,
      "step": 1017
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00017943053220248283,
      "loss": 0.0489,
      "step": 1018
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.000179391163448592,
      "loss": 0.0002,
      "step": 1019
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.0001793517613836437,
      "loss": 0.0003,
      "step": 1020
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00017931232602417033,
      "loss": 0.0003,
      "step": 1021
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00017927285738671825,
      "loss": 0.0641,
      "step": 1022
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00017923335548784773,
      "loss": 0.0714,
      "step": 1023
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00017919382034413305,
      "loss": 0.0004,
      "step": 1024
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00017915425197216245,
      "loss": 0.0272,
      "step": 1025
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00017911465038853805,
      "loss": 0.0003,
      "step": 1026
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00017907501560987594,
      "loss": 0.0003,
      "step": 1027
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00017903534765280614,
      "loss": 0.0001,
      "step": 1028
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00017899564653397262,
      "loss": 0.0357,
      "step": 1029
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.00017895591227003315,
      "loss": 0.0015,
      "step": 1030
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00017891614487765959,
      "loss": 0.0957,
      "step": 1031
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00017887634437353754,
      "loss": 0.0,
      "step": 1032
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00017883651077436655,
      "loss": 0.0377,
      "step": 1033
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00017879664409686008,
      "loss": 0.0415,
      "step": 1034
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00017875674435774547,
      "loss": 0.0002,
      "step": 1035
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00017871681157376383,
      "loss": 0.0489,
      "step": 1036
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.0001786768457616703,
      "loss": 0.0478,
      "step": 1037
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00017863684693823374,
      "loss": 0.0675,
      "step": 1038
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00017859681512023693,
      "loss": 0.0002,
      "step": 1039
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00017855675032447648,
      "loss": 0.06,
      "step": 1040
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00017851665256776283,
      "loss": 0.1278,
      "step": 1041
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00017847652186692026,
      "loss": 0.0002,
      "step": 1042
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00017843635823878686,
      "loss": 0.0,
      "step": 1043
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00017839616170021452,
      "loss": 0.0441,
      "step": 1044
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00017835593226806903,
      "loss": 0.0,
      "step": 1045
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.00017831566995922985,
      "loss": 0.0446,
      "step": 1046
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00017827537479059026,
      "loss": 0.0006,
      "step": 1047
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0001782350467790575,
      "loss": 0.0002,
      "step": 1048
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00017819468594155232,
      "loss": 0.0002,
      "step": 1049
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00017815429229500946,
      "loss": 0.0001,
      "step": 1050
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00017811386585637727,
      "loss": 0.0392,
      "step": 1051
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00017807340664261802,
      "loss": 0.0756,
      "step": 1052
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0001780329146707076,
      "loss": 0.0001,
      "step": 1053
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00017799238995763568,
      "loss": 0.0509,
      "step": 1054
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00017795183252040567,
      "loss": 0.0,
      "step": 1055
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00017791124237603477,
      "loss": 0.1026,
      "step": 1056
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00017787061954155378,
      "loss": 0.0004,
      "step": 1057
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00017782996403400736,
      "loss": 0.0395,
      "step": 1058
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00017778927587045373,
      "loss": 0.029,
      "step": 1059
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.00017774855506796496,
      "loss": 0.0002,
      "step": 1060
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.00017770780164362665,
      "loss": 0.0211,
      "step": 1061
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001776670156145383,
      "loss": 0.0596,
      "step": 1062
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.00017762619699781287,
      "loss": 0.0001,
      "step": 1063
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00017758534581057718,
      "loss": 0.0499,
      "step": 1064
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0001775444620699715,
      "loss": 0.043,
      "step": 1065
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00017750354579315004,
      "loss": 0.0527,
      "step": 1066
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00017746259699728042,
      "loss": 0.0855,
      "step": 1067
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.00017742161569954398,
      "loss": 0.0002,
      "step": 1068
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0001773806019171358,
      "loss": 0.076,
      "step": 1069
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0001773395556672644,
      "loss": 0.03,
      "step": 1070
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.0001772984769671521,
      "loss": 0.0593,
      "step": 1071
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001772573658340347,
      "loss": 0.0493,
      "step": 1072
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001772162222851617,
      "loss": 0.0007,
      "step": 1073
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0001771750463377962,
      "loss": 0.0033,
      "step": 1074
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.00017713383800921478,
      "loss": 0.0019,
      "step": 1075
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.00017709259731670774,
      "loss": 0.0031,
      "step": 1076
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.00017705132427757895,
      "loss": 0.0028,
      "step": 1077
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.00017701001890914572,
      "loss": 0.0003,
      "step": 1078
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.00017696868122873909,
      "loss": 0.0786,
      "step": 1079
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00017692731125370354,
      "loss": 0.0496,
      "step": 1080
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00017688590900139715,
      "loss": 0.1294,
      "step": 1081
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00017684447448919154,
      "loss": 0.0002,
      "step": 1082
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0001768030077344719,
      "loss": 0.0002,
      "step": 1083
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00017676150875463686,
      "loss": 0.0001,
      "step": 1084
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00017671997756709863,
      "loss": 0.0803,
      "step": 1085
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0001766784141892829,
      "loss": 0.0232,
      "step": 1086
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00017663681863862895,
      "loss": 0.0001,
      "step": 1087
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.0001765951909325895,
      "loss": 0.0522,
      "step": 1088
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00017655353108863068,
      "loss": 0.0008,
      "step": 1089
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00017651183912423228,
      "loss": 0.0002,
      "step": 1090
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00017647011505688743,
      "loss": 0.0001,
      "step": 1091
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0001764283589041028,
      "loss": 0.0002,
      "step": 1092
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00017638657068339843,
      "loss": 0.0428,
      "step": 1093
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00017634475041230797,
      "loss": 0.0351,
      "step": 1094
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00017630289810837834,
      "loss": 0.0647,
      "step": 1095
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00017626101378917004,
      "loss": 0.0181,
      "step": 1096
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00017621909747225697,
      "loss": 0.0277,
      "step": 1097
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.0001761771491752264,
      "loss": 0.0002,
      "step": 1098
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00017613516891567906,
      "loss": 0.0001,
      "step": 1099
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0001760931567112291,
      "loss": 0.0006,
      "step": 1100
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.00017605111257950408,
      "loss": 0.0002,
      "step": 1101
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0001760090365381449,
      "loss": 0.065,
      "step": 1102
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.00017596692860480593,
      "loss": 0.0582,
      "step": 1103
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0001759247887971548,
      "loss": 0.0932,
      "step": 1104
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00017588261713287267,
      "loss": 0.0686,
      "step": 1105
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00017584041362965396,
      "loss": 0.0451,
      "step": 1106
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00017579817830520644,
      "loss": 0.0481,
      "step": 1107
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0001757559111772513,
      "loss": 0.0387,
      "step": 1108
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.00017571361226352306,
      "loss": 0.0003,
      "step": 1109
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.00017567128158176953,
      "loss": 0.0873,
      "step": 1110
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0001756289191497519,
      "loss": 0.0605,
      "step": 1111
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.0001755865249852446,
      "loss": 0.0674,
      "step": 1112
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00017554409910603552,
      "loss": 0.0238,
      "step": 1113
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00017550164152992573,
      "loss": 0.0009,
      "step": 1114
    },
    {
      "epoch": 2.75,
      "learning_rate": 0.00017545915227472965,
      "loss": 0.074,
      "step": 1115
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.00017541663135827492,
      "loss": 0.0561,
      "step": 1116
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.00017537407879840265,
      "loss": 0.0347,
      "step": 1117
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.000175331494612967,
      "loss": 0.0088,
      "step": 1118
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0001752888788198355,
      "loss": 0.0704,
      "step": 1119
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00017524623143688902,
      "loss": 0.0011,
      "step": 1120
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00017520355248202158,
      "loss": 0.1127,
      "step": 1121
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00017516084197314046,
      "loss": 0.0006,
      "step": 1122
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00017511809992816618,
      "loss": 0.0438,
      "step": 1123
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00017507532636503256,
      "loss": 0.0614,
      "step": 1124
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00017503252130168657,
      "loss": 0.0639,
      "step": 1125
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00017498968475608838,
      "loss": 0.0354,
      "step": 1126
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00017494681674621148,
      "loss": 0.027,
      "step": 1127
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00017490391729004244,
      "loss": 0.0001,
      "step": 1128
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00017486098640558107,
      "loss": 0.0002,
      "step": 1129
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00017481802411084042,
      "loss": 0.0538,
      "step": 1130
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.0001747750304238466,
      "loss": 0.0674,
      "step": 1131
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00017473200536263905,
      "loss": 0.0974,
      "step": 1132
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0001746889489452702,
      "loss": 0.0006,
      "step": 1133
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0001746458611898058,
      "loss": 0.0003,
      "step": 1134
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0001746027421143246,
      "loss": 0.0523,
      "step": 1135
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00017455959173691863,
      "loss": 0.0002,
      "step": 1136
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00017451641007569296,
      "loss": 0.0055,
      "step": 1137
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00017447319714876579,
      "loss": 0.0359,
      "step": 1138
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00017442995297426846,
      "loss": 0.0001,
      "step": 1139
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00017438667757034546,
      "loss": 0.0001,
      "step": 1140
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00017434337095515432,
      "loss": 0.0604,
      "step": 1141
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00017430003314686569,
      "loss": 0.0363,
      "step": 1142
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00017425666416366332,
      "loss": 0.0013,
      "step": 1143
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00017421326402374405,
      "loss": 0.0001,
      "step": 1144
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00017416983274531775,
      "loss": 0.1052,
      "step": 1145
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00017412637034660734,
      "loss": 0.0003,
      "step": 1146
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0001740828768458489,
      "loss": 0.0323,
      "step": 1147
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.0001740393522612915,
      "loss": 0.0317,
      "step": 1148
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.00017399579661119715,
      "loss": 0.0001,
      "step": 1149
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0001739522099138411,
      "loss": 0.0003,
      "step": 1150
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.00017390859218751142,
      "loss": 0.0001,
      "step": 1151
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.00017386494345050942,
      "loss": 0.0008,
      "step": 1152
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.0001738212637211492,
      "loss": 0.0334,
      "step": 1153
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.000173777553017758,
      "loss": 0.0001,
      "step": 1154
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00017373381135867604,
      "loss": 0.0549,
      "step": 1155
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00017369003876225642,
      "loss": 0.0469,
      "step": 1156
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00017364623524686543,
      "loss": 0.0053,
      "step": 1157
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00017360240083088213,
      "loss": 0.0833,
      "step": 1158
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00017355853553269865,
      "loss": 0.0145,
      "step": 1159
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00017351463937072004,
      "loss": 0.0002,
      "step": 1160
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00017347071236336437,
      "loss": 0.042,
      "step": 1161
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00017342675452906248,
      "loss": 0.0001,
      "step": 1162
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00017338276588625839,
      "loss": 0.002,
      "step": 1163
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00017333874645340884,
      "loss": 0.0003,
      "step": 1164
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0001732946962489836,
      "loss": 0.0416,
      "step": 1165
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0001732506152914653,
      "loss": 0.0002,
      "step": 1166
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0001732065035993495,
      "loss": 0.0005,
      "step": 1167
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00017316236119114463,
      "loss": 0.0531,
      "step": 1168
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00017311818808537206,
      "loss": 0.0492,
      "step": 1169
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00017307398430056593,
      "loss": 0.0001,
      "step": 1170
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00017302974985527344,
      "loss": 0.0001,
      "step": 1171
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00017298548476805446,
      "loss": 0.0628,
      "step": 1172
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.00017294118905748182,
      "loss": 0.0001,
      "step": 1173
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.00017289686274214118,
      "loss": 0.0185,
      "step": 1174
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.000172852505840631,
      "loss": 0.0002,
      "step": 1175
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.00017280811837156268,
      "loss": 0.0005,
      "step": 1176
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00017276370035356034,
      "loss": 0.0421,
      "step": 1177
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00017271925180526094,
      "loss": 0.0001,
      "step": 1178
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00017267477274531432,
      "loss": 0.0001,
      "step": 1179
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00017263026319238301,
      "loss": 0.0001,
      "step": 1180
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0001725857231651424,
      "loss": 0.0001,
      "step": 1181
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0001725411526822807,
      "loss": 0.0469,
      "step": 1182
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.00017249655176249882,
      "loss": 0.0001,
      "step": 1183
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0001724519204245105,
      "loss": 0.0001,
      "step": 1184
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00017240725868704218,
      "loss": 0.0003,
      "step": 1185
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0001723625665688331,
      "loss": 0.0418,
      "step": 1186
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00017231784408863532,
      "loss": 0.0004,
      "step": 1187
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00017227309126521348,
      "loss": 0.0002,
      "step": 1188
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00017222830811734502,
      "loss": 0.0245,
      "step": 1189
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00017218349466382023,
      "loss": 0.0334,
      "step": 1190
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00017213865092344187,
      "loss": 0.0004,
      "step": 1191
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00017209377691502565,
      "loss": 0.0001,
      "step": 1192
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00017204887265739977,
      "loss": 0.0459,
      "step": 1193
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0001720039381694053,
      "loss": 0.0371,
      "step": 1194
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.0001719589734698959,
      "loss": 0.0001,
      "step": 1195
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00017191397857773788,
      "loss": 0.0014,
      "step": 1196
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00017186895351181032,
      "loss": 0.0002,
      "step": 1197
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00017182389829100485,
      "loss": 0.0001,
      "step": 1198
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00017177881293422583,
      "loss": 0.0413,
      "step": 1199
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00017173369746039025,
      "loss": 0.0001,
      "step": 1200
    },
    {
      "epoch": 2.96,
      "eval_loss": 0.014002716168761253,
      "eval_runtime": 126.0996,
      "eval_samples_per_second": 1.015,
      "eval_steps_per_second": 0.341,
      "step": 1200
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00017168855188842773,
      "loss": 0.0004,
      "step": 1201
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00017164337623728045,
      "loss": 0.0012,
      "step": 1202
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.0001715981705259033,
      "loss": 0.0001,
      "step": 1203
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00017155293477326384,
      "loss": 0.0009,
      "step": 1204
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00017150766899834204,
      "loss": 0.0307,
      "step": 1205
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00017146237322013068,
      "loss": 0.024,
      "step": 1206
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00017141704745763492,
      "loss": 0.0002,
      "step": 1207
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00017137169172987268,
      "loss": 0.0417,
      "step": 1208
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00017132630605587435,
      "loss": 0.0655,
      "step": 1209
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00017128089045468294,
      "loss": 0.0002,
      "step": 1210
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00017123544494535397,
      "loss": 0.0001,
      "step": 1211
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00017118996954695553,
      "loss": 0.091,
      "step": 1212
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00017114446427856828,
      "loss": 0.0471,
      "step": 1213
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00017109892915928535,
      "loss": 0.0436,
      "step": 1214
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00017105336420821247,
      "loss": 0.0,
      "step": 1215
    }
  ],
  "logging_steps": 1,
  "max_steps": 4860,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "save_steps": 500,
  "total_flos": 1.8178730075703214e+18,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}