{
  "best_metric": 1.9963864088058472,
  "best_model_checkpoint": "output/checkpoint-250",
  "epoch": 0.041666666666666664,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5e-06,
      "loss": 4.4985,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 4.9103,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.5e-05,
      "loss": 4.6958,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 5.0638,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.5e-05,
      "loss": 4.588,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 3e-05,
      "loss": 4.4131,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 4.9837,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 4.3112,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 4.8598,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 5e-05,
      "loss": 4.7387,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.5e-05,
      "loss": 4.5859,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-05,
      "loss": 4.958,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.500000000000001e-05,
      "loss": 4.6871,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.000000000000001e-05,
      "loss": 4.9336,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.5e-05,
      "loss": 4.6115,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 4.3188,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.5e-05,
      "loss": 4.6045,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999999999999999e-05,
      "loss": 4.0343,
      "step": 18
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.5e-05,
      "loss": 4.1379,
      "step": 19
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0001,
      "loss": 4.5752,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000105,
      "loss": 4.3199,
      "step": 21
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00011,
      "loss": 4.3148,
      "step": 22
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000115,
      "loss": 3.8599,
      "step": 23
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 4.0002,
      "step": 24
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000125,
      "loss": 3.9161,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00013000000000000002,
      "loss": 3.9049,
      "step": 26
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000135,
      "loss": 3.8149,
      "step": 27
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00014000000000000001,
      "loss": 3.6388,
      "step": 28
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000145,
      "loss": 3.4915,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00015,
      "loss": 3.4805,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000155,
      "loss": 3.3052,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00016,
      "loss": 3.1385,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000165,
      "loss": 3.121,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017,
      "loss": 3.1415,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000175,
      "loss": 3.0643,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00017999999999999998,
      "loss": 2.9809,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000185,
      "loss": 3.0295,
      "step": 37
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019,
      "loss": 3.0945,
      "step": 38
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00019500000000000002,
      "loss": 2.9501,
      "step": 39
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002,
      "loss": 2.9358,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000205,
      "loss": 2.915,
      "step": 41
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00021,
      "loss": 2.7445,
      "step": 42
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000215,
      "loss": 2.7352,
      "step": 43
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00022,
      "loss": 2.7662,
      "step": 44
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00022500000000000002,
      "loss": 2.6828,
      "step": 45
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00023,
      "loss": 2.6451,
      "step": 46
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000235,
      "loss": 2.6842,
      "step": 47
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00024,
      "loss": 2.6543,
      "step": 48
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000245,
      "loss": 2.5892,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00025,
      "loss": 2.49,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000255,
      "loss": 2.5954,
      "step": 51
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00026000000000000003,
      "loss": 2.5552,
      "step": 52
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00026500000000000004,
      "loss": 2.5406,
      "step": 53
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00027,
      "loss": 2.5237,
      "step": 54
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000275,
      "loss": 2.5773,
      "step": 55
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00028000000000000003,
      "loss": 2.5432,
      "step": 56
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000285,
      "loss": 2.4555,
      "step": 57
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00029,
      "loss": 2.4223,
      "step": 58
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000295,
      "loss": 2.4397,
      "step": 59
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 2.4535,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000305,
      "loss": 2.3823,
      "step": 61
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00031,
      "loss": 2.4813,
      "step": 62
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000315,
      "loss": 2.3828,
      "step": 63
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00032,
      "loss": 2.488,
      "step": 64
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00032500000000000004,
      "loss": 2.3947,
      "step": 65
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00033,
      "loss": 2.4411,
      "step": 66
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000335,
      "loss": 2.5039,
      "step": 67
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00034,
      "loss": 2.4039,
      "step": 68
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000345,
      "loss": 2.3924,
      "step": 69
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00035,
      "loss": 2.3745,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000355,
      "loss": 2.3098,
      "step": 71
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00035999999999999997,
      "loss": 2.3694,
      "step": 72
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000365,
      "loss": 2.3753,
      "step": 73
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00037,
      "loss": 2.2472,
      "step": 74
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000375,
      "loss": 2.402,
      "step": 75
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00038,
      "loss": 2.4102,
      "step": 76
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00038500000000000003,
      "loss": 2.459,
      "step": 77
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00039000000000000005,
      "loss": 2.3445,
      "step": 78
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000395,
      "loss": 2.3456,
      "step": 79
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 2.399,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00040500000000000003,
      "loss": 2.3885,
      "step": 81
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00041,
      "loss": 2.4083,
      "step": 82
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000415,
      "loss": 2.3559,
      "step": 83
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00042,
      "loss": 2.3256,
      "step": 84
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000425,
      "loss": 2.3741,
      "step": 85
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00043,
      "loss": 2.3922,
      "step": 86
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000435,
      "loss": 2.4278,
      "step": 87
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00044,
      "loss": 2.3309,
      "step": 88
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00044500000000000003,
      "loss": 2.3462,
      "step": 89
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00045000000000000004,
      "loss": 2.4298,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000455,
      "loss": 2.3494,
      "step": 91
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00046,
      "loss": 2.3557,
      "step": 92
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000465,
      "loss": 2.3381,
      "step": 93
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00047,
      "loss": 2.396,
      "step": 94
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000475,
      "loss": 2.3382,
      "step": 95
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00048,
      "loss": 2.3339,
      "step": 96
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00048499999999999997,
      "loss": 2.384,
      "step": 97
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00049,
      "loss": 2.3916,
      "step": 98
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000495,
      "loss": 2.2884,
      "step": 99
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0005,
      "loss": 2.4124,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004999152542372881,
      "loss": 2.4458,
      "step": 101
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004998305084745763,
      "loss": 2.3689,
      "step": 102
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004997457627118644,
      "loss": 2.3983,
      "step": 103
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004996610169491526,
      "loss": 2.4062,
      "step": 104
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004995762711864407,
      "loss": 2.3034,
      "step": 105
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004994915254237289,
      "loss": 2.3648,
      "step": 106
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004994067796610169,
      "loss": 2.3478,
      "step": 107
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004993220338983051,
      "loss": 2.4845,
      "step": 108
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004992372881355932,
      "loss": 2.3216,
      "step": 109
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004991525423728814,
      "loss": 2.433,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004990677966101695,
      "loss": 2.4103,
      "step": 111
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004989830508474577,
      "loss": 2.3842,
      "step": 112
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004988983050847458,
      "loss": 2.3335,
      "step": 113
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000498813559322034,
      "loss": 2.3887,
      "step": 114
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004987288135593221,
      "loss": 2.3307,
      "step": 115
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004986440677966102,
      "loss": 2.313,
      "step": 116
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004985593220338983,
      "loss": 2.3206,
      "step": 117
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004984745762711864,
      "loss": 2.39,
      "step": 118
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004983898305084746,
      "loss": 2.4717,
      "step": 119
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004983050847457627,
      "loss": 2.3574,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004982203389830509,
      "loss": 2.4505,
      "step": 121
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000498135593220339,
      "loss": 2.3297,
      "step": 122
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004980508474576272,
      "loss": 2.3063,
      "step": 123
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004979661016949153,
      "loss": 2.3955,
      "step": 124
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004978813559322035,
      "loss": 2.3589,
      "step": 125
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004977966101694915,
      "loss": 2.337,
      "step": 126
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004977118644067796,
      "loss": 2.3332,
      "step": 127
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004976271186440678,
      "loss": 2.3803,
      "step": 128
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004975423728813559,
      "loss": 2.3611,
      "step": 129
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004974576271186441,
      "loss": 2.3554,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004973728813559322,
      "loss": 2.4101,
      "step": 131
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004972881355932204,
      "loss": 2.4309,
      "step": 132
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004972033898305085,
      "loss": 2.28,
      "step": 133
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004971186440677967,
      "loss": 2.4093,
      "step": 134
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004970338983050847,
      "loss": 2.4303,
      "step": 135
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004969491525423728,
      "loss": 2.4194,
      "step": 136
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000496864406779661,
      "loss": 2.4032,
      "step": 137
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004967796610169491,
      "loss": 2.3526,
      "step": 138
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004966949152542373,
      "loss": 2.3505,
      "step": 139
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004966101694915254,
      "loss": 2.3653,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004965254237288136,
      "loss": 2.2969,
      "step": 141
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004964406779661017,
      "loss": 2.3262,
      "step": 142
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004963559322033899,
      "loss": 2.2601,
      "step": 143
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000496271186440678,
      "loss": 2.4252,
      "step": 144
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000496186440677966,
      "loss": 2.34,
      "step": 145
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004961016949152542,
      "loss": 2.372,
      "step": 146
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004960169491525423,
      "loss": 2.296,
      "step": 147
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004959322033898305,
      "loss": 2.2997,
      "step": 148
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0004958474576271186,
      "loss": 2.2999,
      "step": 149
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004957627118644068,
      "loss": 2.3452,
      "step": 150
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004956779661016949,
      "loss": 2.2956,
      "step": 151
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004955932203389831,
      "loss": 2.2542,
      "step": 152
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004955084745762712,
      "loss": 2.2831,
      "step": 153
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004954237288135594,
      "loss": 2.3547,
      "step": 154
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004953389830508474,
      "loss": 2.2986,
      "step": 155
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004952542372881356,
      "loss": 2.3739,
      "step": 156
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004951694915254237,
      "loss": 2.3628,
      "step": 157
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004950847457627119,
      "loss": 2.3686,
      "step": 158
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000495,
      "loss": 2.3178,
      "step": 159
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004949152542372882,
      "loss": 2.2912,
      "step": 160
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004948305084745763,
      "loss": 2.2516,
      "step": 161
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004947457627118645,
      "loss": 2.3826,
      "step": 162
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004946610169491526,
      "loss": 2.3779,
      "step": 163
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004945762711864406,
      "loss": 2.407,
      "step": 164
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004944915254237288,
      "loss": 2.3459,
      "step": 165
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004944067796610169,
      "loss": 2.3394,
      "step": 166
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004943220338983051,
      "loss": 2.3575,
      "step": 167
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004942372881355932,
      "loss": 2.337,
      "step": 168
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004941525423728814,
      "loss": 2.2534,
      "step": 169
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004940677966101695,
      "loss": 2.3056,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004939830508474577,
      "loss": 2.3595,
      "step": 171
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004938983050847458,
      "loss": 2.2519,
      "step": 172
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000493813559322034,
      "loss": 2.2968,
      "step": 173
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000493728813559322,
      "loss": 2.3444,
      "step": 174
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004936440677966102,
      "loss": 2.2988,
      "step": 175
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004935593220338983,
      "loss": 2.2193,
      "step": 176
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004934745762711865,
      "loss": 2.325,
      "step": 177
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004933898305084746,
      "loss": 2.3135,
      "step": 178
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004933050847457628,
      "loss": 2.2869,
      "step": 179
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004932203389830509,
      "loss": 2.371,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000493135593220339,
      "loss": 2.3293,
      "step": 181
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004930508474576272,
      "loss": 2.2483,
      "step": 182
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004929661016949152,
      "loss": 2.317,
      "step": 183
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004928813559322034,
      "loss": 2.3836,
      "step": 184
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004927966101694915,
      "loss": 2.3599,
      "step": 185
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004927118644067797,
      "loss": 2.2669,
      "step": 186
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004926271186440678,
      "loss": 2.3605,
      "step": 187
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000492542372881356,
      "loss": 2.2419,
      "step": 188
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004924576271186441,
      "loss": 2.3,
      "step": 189
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004923728813559322,
      "loss": 2.304,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004922881355932204,
      "loss": 2.3371,
      "step": 191
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004922033898305085,
      "loss": 2.3064,
      "step": 192
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004921186440677966,
      "loss": 2.2496,
      "step": 193
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004920338983050847,
      "loss": 2.3298,
      "step": 194
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004919491525423729,
      "loss": 2.3429,
      "step": 195
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000491864406779661,
      "loss": 2.2897,
      "step": 196
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004917796610169492,
      "loss": 2.3197,
      "step": 197
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004916949152542373,
      "loss": 2.2984,
      "step": 198
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004916101694915254,
      "loss": 2.2688,
      "step": 199
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004915254237288136,
      "loss": 2.3088,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004914406779661017,
      "loss": 2.2954,
      "step": 201
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004913559322033899,
      "loss": 2.2482,
      "step": 202
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004912711864406779,
      "loss": 2.2175,
      "step": 203
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004911864406779661,
      "loss": 2.2773,
      "step": 204
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004911016949152542,
      "loss": 2.3321,
      "step": 205
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004910169491525423,
      "loss": 2.2648,
      "step": 206
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004909322033898305,
      "loss": 2.2507,
      "step": 207
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004908474576271186,
      "loss": 2.3099,
      "step": 208
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0004907627118644068,
      "loss": 2.2771,
      "step": 209
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004906779661016949,
      "loss": 2.3824,
      "step": 210
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004905932203389831,
      "loss": 2.1398,
      "step": 211
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004905084745762711,
      "loss": 2.2114,
      "step": 212
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004904237288135593,
      "loss": 2.2262,
      "step": 213
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004903389830508474,
      "loss": 2.2057,
      "step": 214
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004902542372881356,
      "loss": 2.2878,
      "step": 215
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004901694915254237,
      "loss": 2.2418,
      "step": 216
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004900847457627119,
      "loss": 2.2456,
      "step": 217
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00049,
      "loss": 2.2267,
      "step": 218
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004899152542372882,
      "loss": 2.1876,
      "step": 219
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004898305084745763,
      "loss": 2.2439,
      "step": 220
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004897457627118645,
      "loss": 2.1952,
      "step": 221
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004896610169491525,
      "loss": 2.215,
      "step": 222
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004895762711864407,
      "loss": 2.2313,
      "step": 223
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004894915254237288,
      "loss": 2.2823,
      "step": 224
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004894067796610169,
      "loss": 2.2705,
      "step": 225
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004893220338983051,
      "loss": 2.167,
      "step": 226
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004892372881355932,
      "loss": 2.2286,
      "step": 227
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004891525423728814,
      "loss": 2.2877,
      "step": 228
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004890677966101695,
      "loss": 2.2448,
      "step": 229
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004889830508474577,
      "loss": 2.2232,
      "step": 230
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004888983050847457,
      "loss": 2.2535,
      "step": 231
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004888135593220339,
      "loss": 2.2222,
      "step": 232
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000488728813559322,
      "loss": 2.2819,
      "step": 233
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004886440677966102,
      "loss": 2.1981,
      "step": 234
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004885593220338983,
      "loss": 2.2716,
      "step": 235
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004884745762711865,
      "loss": 2.2013,
      "step": 236
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004883898305084746,
      "loss": 2.3319,
      "step": 237
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004883050847457628,
      "loss": 2.2559,
      "step": 238
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00048822033898305087,
      "loss": 2.193,
      "step": 239
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000488135593220339,
      "loss": 2.2776,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00048805084745762715,
      "loss": 2.2398,
      "step": 241
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004879661016949153,
      "loss": 2.2511,
      "step": 242
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004878813559322034,
      "loss": 2.1962,
      "step": 243
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00048779661016949157,
      "loss": 2.2218,
      "step": 244
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00048771186440677965,
      "loss": 2.1811,
      "step": 245
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004876271186440678,
      "loss": 2.2381,
      "step": 246
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00048754237288135593,
      "loss": 2.3434,
      "step": 247
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004874576271186441,
      "loss": 2.2563,
      "step": 248
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004873728813559322,
      "loss": 2.2949,
      "step": 249
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0004872881355932203,
      "loss": 2.2758,
      "step": 250
    },
    {
      "epoch": 0.04,
      "eval_gen_len": 19.0,
      "eval_loss": 1.9963864088058472,
      "eval_rouge1": 0.2486,
      "eval_rouge2": 0.0909,
      "eval_rougeL": 0.2094,
      "eval_rougeLsum": 0.2095,
      "eval_runtime": 125.5893,
      "eval_samples_per_second": 1.592,
      "eval_steps_per_second": 0.199,
      "step": 250
    }
  ],
  "max_steps": 6000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 5.876308597389558e+17,
  "trial_name": null,
  "trial_params": null
}