{
  "best_metric": 2.2723255157470703,
  "best_model_checkpoint": "output/checkpoint-500",
  "epoch": 0.08333333333333333,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 5.1377,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 5.1144,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.4e-05,
      "loss": 5.2944,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 5.277,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 4.7688,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.8e-05,
      "loss": 4.7068,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 4.905,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.400000000000001e-05,
      "loss": 4.6467,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.2e-05,
      "loss": 4.4809,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 4.4408,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.800000000000001e-05,
      "loss": 4.2903,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.6e-05,
      "loss": 4.2546,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00010400000000000001,
      "loss": 4.1372,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00011200000000000001,
      "loss": 4.1673,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 3.8483,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012800000000000002,
      "loss": 3.7866,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00013600000000000003,
      "loss": 3.7765,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000144,
      "loss": 3.61,
      "step": 18
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000152,
      "loss": 3.5922,
      "step": 19
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 3.5748,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000168,
      "loss": 3.462,
      "step": 21
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017600000000000002,
      "loss": 3.5482,
      "step": 22
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018400000000000003,
      "loss": 3.3806,
      "step": 23
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000192,
      "loss": 3.375,
      "step": 24
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 3.4461,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00020800000000000001,
      "loss": 3.3302,
      "step": 26
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00021600000000000002,
      "loss": 3.2568,
      "step": 27
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00022400000000000002,
      "loss": 3.1755,
      "step": 28
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000232,
      "loss": 3.1303,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00024,
      "loss": 3.1867,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000248,
      "loss": 3.086,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00025600000000000004,
      "loss": 3.0142,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000264,
      "loss": 2.9919,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00027200000000000005,
      "loss": 2.9977,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00028,
      "loss": 3.0582,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000288,
      "loss": 3.0244,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000296,
      "loss": 3.0201,
      "step": 37
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000304,
      "loss": 3.0081,
      "step": 38
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00031200000000000005,
      "loss": 3.0072,
      "step": 39
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00032,
      "loss": 3.0163,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000328,
      "loss": 2.9476,
      "step": 41
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000336,
      "loss": 2.9289,
      "step": 42
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000344,
      "loss": 2.8889,
      "step": 43
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00035200000000000005,
      "loss": 2.9479,
      "step": 44
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00036,
      "loss": 2.913,
      "step": 45
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00036800000000000005,
      "loss": 2.8848,
      "step": 46
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000376,
      "loss": 2.9424,
      "step": 47
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000384,
      "loss": 2.8967,
      "step": 48
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000392,
      "loss": 2.8882,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 2.783,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00040800000000000005,
      "loss": 2.9005,
      "step": 51
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00041600000000000003,
      "loss": 2.8624,
      "step": 52
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00042400000000000006,
      "loss": 2.8651,
      "step": 53
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00043200000000000004,
      "loss": 2.9019,
      "step": 54
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00044000000000000007,
      "loss": 2.9397,
      "step": 55
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00044800000000000005,
      "loss": 2.9143,
      "step": 56
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00045599999999999997,
      "loss": 2.816,
      "step": 57
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000464,
      "loss": 2.7941,
      "step": 58
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000472,
      "loss": 2.7889,
      "step": 59
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00048,
      "loss": 2.816,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000488,
      "loss": 2.7483,
      "step": 61
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000496,
      "loss": 2.8676,
      "step": 62
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000504,
      "loss": 2.7342,
      "step": 63
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005120000000000001,
      "loss": 2.8743,
      "step": 64
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005200000000000001,
      "loss": 2.7635,
      "step": 65
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000528,
      "loss": 2.8303,
      "step": 66
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000536,
      "loss": 2.8751,
      "step": 67
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005440000000000001,
      "loss": 2.7702,
      "step": 68
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000552,
      "loss": 2.7697,
      "step": 69
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00056,
      "loss": 2.7656,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000568,
      "loss": 2.6676,
      "step": 71
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000576,
      "loss": 2.7541,
      "step": 72
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000584,
      "loss": 2.7413,
      "step": 73
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000592,
      "loss": 2.655,
      "step": 74
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006000000000000001,
      "loss": 2.7992,
      "step": 75
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000608,
      "loss": 2.7969,
      "step": 76
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000616,
      "loss": 2.8561,
      "step": 77
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006240000000000001,
      "loss": 2.7182,
      "step": 78
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006320000000000001,
      "loss": 2.7121,
      "step": 79
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00064,
      "loss": 2.7505,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000648,
      "loss": 2.7664,
      "step": 81
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000656,
      "loss": 2.7699,
      "step": 82
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000664,
      "loss": 2.687,
      "step": 83
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000672,
      "loss": 2.6854,
      "step": 84
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00068,
      "loss": 2.7284,
      "step": 85
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000688,
      "loss": 2.7535,
      "step": 86
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000696,
      "loss": 2.7291,
      "step": 87
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007040000000000001,
      "loss": 2.6795,
      "step": 88
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007120000000000001,
      "loss": 2.6847,
      "step": 89
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00072,
      "loss": 2.8037,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000728,
      "loss": 2.7104,
      "step": 91
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007360000000000001,
      "loss": 2.7022,
      "step": 92
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007440000000000001,
      "loss": 2.6876,
      "step": 93
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000752,
      "loss": 2.7657,
      "step": 94
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00076,
      "loss": 2.6784,
      "step": 95
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000768,
      "loss": 2.7005,
      "step": 96
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000776,
      "loss": 2.6969,
      "step": 97
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000784,
      "loss": 2.727,
      "step": 98
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007920000000000001,
      "loss": 2.6475,
      "step": 99
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0008,
      "loss": 2.7626,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000799864406779661,
      "loss": 2.7642,
      "step": 101
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007997288135593221,
      "loss": 2.6881,
      "step": 102
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007995932203389831,
      "loss": 2.722,
      "step": 103
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007994576271186441,
      "loss": 2.761,
      "step": 104
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000799322033898305,
      "loss": 2.6431,
      "step": 105
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007991864406779661,
      "loss": 2.6869,
      "step": 106
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007990508474576271,
      "loss": 2.6963,
      "step": 107
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007989152542372882,
      "loss": 2.8242,
      "step": 108
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007987796610169492,
      "loss": 2.6418,
      "step": 109
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007986440677966103,
      "loss": 2.7597,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007985084745762711,
      "loss": 2.7569,
      "step": 111
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007983728813559322,
      "loss": 2.7329,
      "step": 112
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007982372881355932,
      "loss": 2.6758,
      "step": 113
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007981016949152543,
      "loss": 2.7202,
      "step": 114
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007979661016949153,
      "loss": 2.6658,
      "step": 115
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007978305084745764,
      "loss": 2.6372,
      "step": 116
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007976949152542374,
      "loss": 2.665,
      "step": 117
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007975593220338983,
      "loss": 2.717,
      "step": 118
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007974237288135593,
      "loss": 2.8033,
      "step": 119
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007972881355932204,
      "loss": 2.6871,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007971525423728814,
      "loss": 2.7634,
      "step": 121
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007970169491525424,
      "loss": 2.6665,
      "step": 122
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007968813559322035,
      "loss": 2.6286,
      "step": 123
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007967457627118644,
      "loss": 2.7076,
      "step": 124
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007966101694915254,
      "loss": 2.6828,
      "step": 125
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007964745762711864,
      "loss": 2.6324,
      "step": 126
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007963389830508475,
      "loss": 2.6649,
      "step": 127
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007962033898305085,
      "loss": 2.692,
      "step": 128
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007960677966101696,
      "loss": 2.6541,
      "step": 129
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007959322033898305,
      "loss": 2.6768,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007957966101694916,
      "loss": 2.7182,
      "step": 131
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007956610169491526,
      "loss": 2.7264,
      "step": 132
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007955254237288136,
      "loss": 2.6101,
      "step": 133
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007953898305084746,
      "loss": 2.7315,
      "step": 134
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007952542372881357,
      "loss": 2.7184,
      "step": 135
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007951186440677966,
      "loss": 2.7155,
      "step": 136
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007949830508474577,
      "loss": 2.6894,
      "step": 137
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007948474576271187,
      "loss": 2.6394,
      "step": 138
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007947118644067797,
      "loss": 2.6448,
      "step": 139
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007945762711864407,
      "loss": 2.6805,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007944406779661018,
      "loss": 2.6213,
      "step": 141
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007943050847457627,
      "loss": 2.6665,
      "step": 142
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007941694915254237,
      "loss": 2.5491,
      "step": 143
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007940338983050848,
      "loss": 2.7293,
      "step": 144
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007938983050847458,
      "loss": 2.6627,
      "step": 145
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007937627118644069,
      "loss": 2.6717,
      "step": 146
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007936271186440678,
      "loss": 2.6122,
      "step": 147
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007934915254237288,
      "loss": 2.6305,
      "step": 148
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007933559322033898,
      "loss": 2.6266,
      "step": 149
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007932203389830509,
      "loss": 2.6781,
      "step": 150
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007930847457627119,
      "loss": 2.6851,
      "step": 151
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000792949152542373,
      "loss": 2.6379,
      "step": 152
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000792813559322034,
      "loss": 2.6714,
      "step": 153
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007926779661016949,
      "loss": 2.7392,
      "step": 154
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007925423728813559,
      "loss": 2.6727,
      "step": 155
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000792406779661017,
      "loss": 2.7512,
      "step": 156
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000792271186440678,
      "loss": 2.731,
      "step": 157
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007921355932203391,
      "loss": 2.7441,
      "step": 158
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007920000000000001,
      "loss": 2.638,
      "step": 159
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000791864406779661,
      "loss": 2.6419,
      "step": 160
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000791728813559322,
      "loss": 2.582,
      "step": 161
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007915932203389831,
      "loss": 2.724,
      "step": 162
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007914576271186441,
      "loss": 2.7238,
      "step": 163
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007913220338983051,
      "loss": 2.7242,
      "step": 164
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007911864406779662,
      "loss": 2.6581,
      "step": 165
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007910508474576271,
      "loss": 2.6638,
      "step": 166
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007909152542372882,
      "loss": 2.6857,
      "step": 167
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007907796610169492,
      "loss": 2.6805,
      "step": 168
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007906440677966102,
      "loss": 2.5892,
      "step": 169
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007905084745762712,
      "loss": 2.6294,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007903728813559323,
      "loss": 2.7016,
      "step": 171
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007902372881355932,
      "loss": 2.6009,
      "step": 172
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007901016949152543,
      "loss": 2.6274,
      "step": 173
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007899661016949153,
      "loss": 2.6633,
      "step": 174
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007898305084745763,
      "loss": 2.6486,
      "step": 175
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007896949152542373,
      "loss": 2.5538,
      "step": 176
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007895593220338984,
      "loss": 2.6583,
      "step": 177
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007894237288135593,
      "loss": 2.6365,
      "step": 178
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007892881355932204,
      "loss": 2.6217,
      "step": 179
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007891525423728814,
      "loss": 2.6431,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007890169491525425,
      "loss": 2.6859,
      "step": 181
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007888813559322034,
      "loss": 2.5771,
      "step": 182
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007887457627118645,
      "loss": 2.6483,
      "step": 183
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007886101694915254,
      "loss": 2.6999,
      "step": 184
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007884745762711864,
      "loss": 2.7057,
      "step": 185
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007883389830508475,
      "loss": 2.6446,
      "step": 186
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007882033898305085,
      "loss": 2.7161,
      "step": 187
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007880677966101696,
      "loss": 2.6047,
      "step": 188
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007879322033898306,
      "loss": 2.6412,
      "step": 189
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007877966101694915,
      "loss": 2.631,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007876610169491525,
      "loss": 2.6807,
      "step": 191
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007875254237288136,
      "loss": 2.6596,
      "step": 192
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007873898305084746,
      "loss": 2.6051,
      "step": 193
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007872542372881357,
      "loss": 2.6938,
      "step": 194
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007871186440677967,
      "loss": 2.7125,
      "step": 195
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007869830508474576,
      "loss": 2.664,
      "step": 196
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007868474576271186,
      "loss": 2.6355,
      "step": 197
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007867118644067797,
      "loss": 2.6469,
      "step": 198
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007865762711864407,
      "loss": 2.6451,
      "step": 199
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007864406779661018,
      "loss": 2.6577,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007863050847457628,
      "loss": 2.6677,
      "step": 201
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007861694915254239,
      "loss": 2.6208,
      "step": 202
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007860338983050848,
      "loss": 2.5922,
      "step": 203
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007858983050847457,
      "loss": 2.633,
      "step": 204
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007857627118644068,
      "loss": 2.6587,
      "step": 205
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007856271186440678,
      "loss": 2.6327,
      "step": 206
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007854915254237289,
      "loss": 2.6015,
      "step": 207
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007853559322033898,
      "loss": 2.6667,
      "step": 208
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007852203389830509,
      "loss": 2.6262,
      "step": 209
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007850847457627119,
      "loss": 2.7435,
      "step": 210
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007849491525423729,
      "loss": 2.4698,
      "step": 211
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007848135593220339,
      "loss": 2.5554,
      "step": 212
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000784677966101695,
      "loss": 2.5718,
      "step": 213
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007845423728813559,
      "loss": 2.5544,
      "step": 214
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000784406779661017,
      "loss": 2.6508,
      "step": 215
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000784271186440678,
      "loss": 2.613,
      "step": 216
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007841355932203391,
      "loss": 2.5898,
      "step": 217
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000784,
      "loss": 2.5876,
      "step": 218
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007838644067796611,
      "loss": 2.5573,
      "step": 219
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000783728813559322,
      "loss": 2.624,
      "step": 220
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007835932203389831,
      "loss": 2.5814,
      "step": 221
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007834576271186441,
      "loss": 2.6656,
      "step": 222
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007833220338983052,
      "loss": 2.6862,
      "step": 223
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007831864406779662,
      "loss": 2.8027,
      "step": 224
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007830508474576272,
      "loss": 2.8105,
      "step": 225
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007829152542372881,
      "loss": 2.7149,
      "step": 226
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007827796610169491,
      "loss": 2.8449,
      "step": 227
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007826440677966102,
      "loss": 2.9684,
      "step": 228
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007825084745762712,
      "loss": 2.9016,
      "step": 229
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007823728813559323,
      "loss": 2.8576,
      "step": 230
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007822372881355933,
      "loss": 2.9106,
      "step": 231
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007821016949152542,
      "loss": 2.826,
      "step": 232
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007819661016949152,
      "loss": 2.9042,
      "step": 233
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007818305084745763,
      "loss": 2.8738,
      "step": 234
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007816949152542373,
      "loss": 2.9855,
      "step": 235
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007815593220338984,
      "loss": 2.9692,
      "step": 236
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007814237288135594,
      "loss": 3.199,
      "step": 237
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007812881355932205,
      "loss": 3.0884,
      "step": 238
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007811525423728813,
      "loss": 3.042,
      "step": 239
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007810169491525424,
      "loss": 3.1018,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007808813559322034,
      "loss": 3.0346,
      "step": 241
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007807457627118645,
      "loss": 3.0977,
      "step": 242
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007806101694915255,
      "loss": 3.115,
      "step": 243
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007804745762711866,
      "loss": 3.2372,
      "step": 244
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007803389830508475,
      "loss": 3.2689,
      "step": 245
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007802033898305085,
      "loss": 3.1267,
      "step": 246
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007800677966101695,
      "loss": 3.0774,
      "step": 247
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007799322033898305,
      "loss": 3.0283,
      "step": 248
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007797966101694916,
      "loss": 3.0163,
      "step": 249
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007796610169491525,
      "loss": 2.9164,
      "step": 250
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007795254237288136,
      "loss": 2.8825,
      "step": 251
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007793898305084746,
      "loss": 2.9542,
      "step": 252
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007792542372881356,
      "loss": 2.9018,
      "step": 253
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007791186440677966,
      "loss": 2.9929,
      "step": 254
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007789830508474577,
      "loss": 3.0326,
      "step": 255
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007788474576271186,
      "loss": 2.9234,
      "step": 256
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007787118644067797,
      "loss": 3.0114,
      "step": 257
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007785762711864407,
      "loss": 3.0775,
      "step": 258
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007784406779661018,
      "loss": 2.9171,
      "step": 259
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007783050847457628,
      "loss": 3.0288,
      "step": 260
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007781694915254238,
      "loss": 2.9062,
      "step": 261
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007780338983050847,
      "loss": 3.092,
      "step": 262
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007778983050847458,
      "loss": 2.9368,
      "step": 263
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007777627118644068,
      "loss": 2.9572,
      "step": 264
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007776271186440679,
      "loss": 2.936,
      "step": 265
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007774915254237289,
      "loss": 2.9461,
      "step": 266
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007773559322033899,
      "loss": 3.0886,
      "step": 267
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007772203389830508,
      "loss": 2.8941,
      "step": 268
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007770847457627118,
      "loss": 2.8142,
      "step": 269
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007769491525423729,
      "loss": 2.777,
      "step": 270
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007768135593220339,
      "loss": 2.8028,
      "step": 271
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000776677966101695,
      "loss": 2.6842,
      "step": 272
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000776542372881356,
      "loss": 2.7688,
      "step": 273
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007764067796610171,
      "loss": 2.6817,
      "step": 274
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007762711864406779,
      "loss": 2.6677,
      "step": 275
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000776135593220339,
      "loss": 2.6759,
      "step": 276
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000776,
      "loss": 2.7113,
      "step": 277
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007758644067796611,
      "loss": 2.5817,
      "step": 278
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007757288135593221,
      "loss": 2.6208,
      "step": 279
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007755932203389832,
      "loss": 2.6325,
      "step": 280
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007754576271186441,
      "loss": 2.7245,
      "step": 281
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007753220338983051,
      "loss": 2.7362,
      "step": 282
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007751864406779661,
      "loss": 2.5645,
      "step": 283
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007750508474576272,
      "loss": 2.6167,
      "step": 284
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007749152542372882,
      "loss": 2.6517,
      "step": 285
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007747796610169493,
      "loss": 2.6042,
      "step": 286
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007746440677966102,
      "loss": 2.652,
      "step": 287
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007745084745762712,
      "loss": 2.619,
      "step": 288
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007743728813559322,
      "loss": 2.5819,
      "step": 289
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007742372881355932,
      "loss": 2.6991,
      "step": 290
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007741016949152543,
      "loss": 2.6854,
      "step": 291
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007739661016949152,
      "loss": 2.6002,
      "step": 292
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007738305084745763,
      "loss": 2.6408,
      "step": 293
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007736949152542373,
      "loss": 2.6261,
      "step": 294
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007735593220338984,
      "loss": 2.5894,
      "step": 295
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007734237288135594,
      "loss": 2.6171,
      "step": 296
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007732881355932204,
      "loss": 2.6116,
      "step": 297
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007731525423728813,
      "loss": 2.6656,
      "step": 298
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007730169491525424,
      "loss": 2.6228,
      "step": 299
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007728813559322034,
      "loss": 2.608,
      "step": 300
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007727457627118645,
      "loss": 2.5309,
      "step": 301
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007726101694915255,
      "loss": 2.6226,
      "step": 302
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007724745762711865,
      "loss": 2.5953,
      "step": 303
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007723389830508474,
      "loss": 2.6025,
      "step": 304
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007722033898305085,
      "loss": 2.5493,
      "step": 305
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007720677966101695,
      "loss": 2.6022,
      "step": 306
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007719322033898306,
      "loss": 2.5399,
      "step": 307
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007717966101694916,
      "loss": 2.5497,
      "step": 308
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007716610169491526,
      "loss": 2.6287,
      "step": 309
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007715254237288135,
      "loss": 2.6215,
      "step": 310
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007713898305084745,
      "loss": 2.6294,
      "step": 311
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007712542372881356,
      "loss": 2.6212,
      "step": 312
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007711186440677966,
      "loss": 2.5755,
      "step": 313
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007709830508474577,
      "loss": 2.5396,
      "step": 314
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007708474576271187,
      "loss": 2.642,
      "step": 315
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007707118644067798,
      "loss": 2.5289,
      "step": 316
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007705762711864407,
      "loss": 2.5519,
      "step": 317
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007704406779661017,
      "loss": 2.586,
      "step": 318
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007703050847457627,
      "loss": 2.594,
      "step": 319
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007701694915254238,
      "loss": 2.5997,
      "step": 320
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007700338983050848,
      "loss": 2.5599,
      "step": 321
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007698983050847459,
      "loss": 2.603,
      "step": 322
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007697627118644068,
      "loss": 2.5505,
      "step": 323
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007696271186440678,
      "loss": 2.5184,
      "step": 324
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007694915254237288,
      "loss": 2.6093,
      "step": 325
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007693559322033899,
      "loss": 2.6121,
      "step": 326
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007692203389830509,
      "loss": 2.587,
      "step": 327
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000769084745762712,
      "loss": 2.555,
      "step": 328
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007689491525423729,
      "loss": 2.5838,
      "step": 329
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007688135593220339,
      "loss": 2.4801,
      "step": 330
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768677966101695,
      "loss": 2.6102,
      "step": 331
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007685423728813559,
      "loss": 2.5922,
      "step": 332
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768406779661017,
      "loss": 2.5824,
      "step": 333
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768271186440678,
      "loss": 2.6137,
      "step": 334
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768135593220339,
      "loss": 2.5511,
      "step": 335
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768,
      "loss": 2.5406,
      "step": 336
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007678644067796611,
      "loss": 2.5357,
      "step": 337
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007677288135593221,
      "loss": 2.4895,
      "step": 338
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007675932203389831,
      "loss": 2.6371,
      "step": 339
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000767457627118644,
      "loss": 2.5476,
      "step": 340
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007673220338983051,
      "loss": 2.5362,
      "step": 341
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007671864406779661,
      "loss": 2.5852,
      "step": 342
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007670508474576272,
      "loss": 2.5826,
      "step": 343
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007669152542372882,
      "loss": 2.4969,
      "step": 344
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007667796610169493,
      "loss": 2.5199,
      "step": 345
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007666440677966102,
      "loss": 2.5435,
      "step": 346
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007665084745762712,
      "loss": 2.5403,
      "step": 347
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007663728813559322,
      "loss": 2.6631,
      "step": 348
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007662372881355933,
      "loss": 2.6509,
      "step": 349
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007661016949152543,
      "loss": 2.5466,
      "step": 350
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007659661016949153,
      "loss": 2.6346,
      "step": 351
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007658305084745764,
      "loss": 2.6195,
      "step": 352
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007656949152542373,
      "loss": 2.5258,
      "step": 353
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007655593220338983,
      "loss": 2.562,
      "step": 354
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007654237288135593,
      "loss": 2.5812,
      "step": 355
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007652881355932204,
      "loss": 2.5627,
      "step": 356
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007651525423728814,
      "loss": 2.5146,
      "step": 357
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007650169491525425,
      "loss": 2.518,
      "step": 358
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007648813559322034,
      "loss": 2.5651,
      "step": 359
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007647457627118644,
      "loss": 2.5486,
      "step": 360
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007646101694915254,
      "loss": 2.5635,
      "step": 361
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007644745762711865,
      "loss": 2.5231,
      "step": 362
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007643389830508475,
      "loss": 2.5416,
      "step": 363
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007642033898305086,
      "loss": 2.4828,
      "step": 364
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007640677966101695,
      "loss": 2.5094,
      "step": 365
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007639322033898306,
      "loss": 2.5963,
      "step": 366
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007637966101694915,
      "loss": 2.5987,
      "step": 367
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007636610169491526,
      "loss": 2.4665,
      "step": 368
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007635254237288136,
      "loss": 2.5982,
      "step": 369
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007633898305084747,
      "loss": 2.4934,
      "step": 370
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007632542372881356,
      "loss": 2.5585,
      "step": 371
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007631186440677966,
      "loss": 2.595,
      "step": 372
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007629830508474577,
      "loss": 2.5229,
      "step": 373
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007628474576271187,
      "loss": 2.5127,
      "step": 374
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007627118644067797,
      "loss": 2.5398,
      "step": 375
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007625762711864407,
      "loss": 2.4711,
      "step": 376
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007624406779661017,
      "loss": 2.5616,
      "step": 377
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007623050847457627,
      "loss": 2.4629,
      "step": 378
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007621694915254238,
      "loss": 2.4795,
      "step": 379
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007620338983050848,
      "loss": 2.4815,
      "step": 380
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007618983050847458,
      "loss": 2.5178,
      "step": 381
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007617627118644068,
      "loss": 2.535,
      "step": 382
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007616271186440678,
      "loss": 2.5254,
      "step": 383
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007614915254237288,
      "loss": 2.543,
      "step": 384
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007613559322033899,
      "loss": 2.5363,
      "step": 385
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007612203389830509,
      "loss": 2.5608,
      "step": 386
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000761084745762712,
      "loss": 2.5059,
      "step": 387
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000760949152542373,
      "loss": 2.4691,
      "step": 388
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007608135593220339,
      "loss": 2.5462,
      "step": 389
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007606779661016949,
      "loss": 2.5665,
      "step": 390
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007605423728813559,
      "loss": 2.4889,
      "step": 391
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000760406779661017,
      "loss": 2.4813,
      "step": 392
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000760271186440678,
      "loss": 2.5234,
      "step": 393
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007601355932203391,
      "loss": 2.4285,
      "step": 394
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00076,
      "loss": 2.484,
      "step": 395
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000759864406779661,
      "loss": 2.517,
      "step": 396
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000759728813559322,
      "loss": 2.5167,
      "step": 397
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007595932203389831,
      "loss": 2.5136,
      "step": 398
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007594576271186441,
      "loss": 2.4747,
      "step": 399
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007593220338983052,
      "loss": 2.4998,
      "step": 400
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007591864406779661,
      "loss": 2.5182,
      "step": 401
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007590508474576272,
      "loss": 2.4585,
      "step": 402
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007589152542372881,
      "loss": 2.5584,
      "step": 403
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007587796610169492,
      "loss": 2.4856,
      "step": 404
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007586440677966102,
      "loss": 2.4919,
      "step": 405
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007585084745762713,
      "loss": 2.5149,
      "step": 406
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007583728813559322,
      "loss": 2.522,
      "step": 407
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007582372881355933,
      "loss": 2.4943,
      "step": 408
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007581016949152543,
      "loss": 2.5093,
      "step": 409
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007579661016949153,
      "loss": 2.517,
      "step": 410
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007578305084745763,
      "loss": 2.4795,
      "step": 411
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007576949152542373,
      "loss": 2.5078,
      "step": 412
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007575593220338983,
      "loss": 2.5792,
      "step": 413
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007574237288135593,
      "loss": 2.5151,
      "step": 414
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007572881355932204,
      "loss": 2.4612,
      "step": 415
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007571525423728814,
      "loss": 2.4582,
      "step": 416
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007570169491525424,
      "loss": 2.5092,
      "step": 417
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007568813559322034,
      "loss": 2.4834,
      "step": 418
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007567457627118644,
      "loss": 2.5014,
      "step": 419
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007566101694915254,
      "loss": 2.4331,
      "step": 420
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007564745762711865,
      "loss": 2.5328,
      "step": 421
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007563389830508475,
      "loss": 2.4425,
      "step": 422
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007562033898305086,
      "loss": 2.4065,
      "step": 423
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007560677966101696,
      "loss": 2.4847,
      "step": 424
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007559322033898305,
      "loss": 2.5003,
      "step": 425
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007557966101694915,
      "loss": 2.5485,
      "step": 426
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007556610169491526,
      "loss": 2.5025,
      "step": 427
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007555254237288136,
      "loss": 2.4961,
      "step": 428
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007553898305084747,
      "loss": 2.5246,
      "step": 429
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007552542372881357,
      "loss": 2.4668,
      "step": 430
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007551186440677966,
      "loss": 2.5051,
      "step": 431
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007549830508474576,
      "loss": 2.4929,
      "step": 432
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007548474576271186,
      "loss": 2.4197,
      "step": 433
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007547118644067797,
      "loss": 2.5754,
      "step": 434
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007545762711864407,
      "loss": 2.4829,
      "step": 435
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007544406779661018,
      "loss": 2.4313,
      "step": 436
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007543050847457627,
      "loss": 2.4745,
      "step": 437
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007541694915254237,
      "loss": 2.4724,
      "step": 438
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007540338983050847,
      "loss": 2.4648,
      "step": 439
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007538983050847458,
      "loss": 2.4234,
      "step": 440
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007537627118644068,
      "loss": 2.4681,
      "step": 441
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007536271186440679,
      "loss": 2.4547,
      "step": 442
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007534915254237288,
      "loss": 2.4622,
      "step": 443
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007533559322033899,
      "loss": 2.5777,
      "step": 444
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007532203389830509,
      "loss": 2.4368,
      "step": 445
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007530847457627119,
      "loss": 2.5213,
      "step": 446
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007529491525423729,
      "loss": 2.4985,
      "step": 447
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000752813559322034,
      "loss": 2.4489,
      "step": 448
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007526779661016949,
      "loss": 2.5418,
      "step": 449
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000752542372881356,
      "loss": 2.4771,
      "step": 450
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000752406779661017,
      "loss": 2.5463,
      "step": 451
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000752271186440678,
      "loss": 2.4252,
      "step": 452
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000752135593220339,
      "loss": 2.5508,
      "step": 453
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000752,
      "loss": 2.506,
      "step": 454
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000751864406779661,
      "loss": 2.484,
      "step": 455
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.000751728813559322,
      "loss": 2.4426,
      "step": 456
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007515932203389831,
      "loss": 2.5205,
      "step": 457
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007514576271186441,
      "loss": 2.4948,
      "step": 458
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007513220338983052,
      "loss": 2.4423,
      "step": 459
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007511864406779661,
      "loss": 2.522,
      "step": 460
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007510508474576271,
      "loss": 2.5116,
      "step": 461
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007509152542372881,
      "loss": 2.4785,
      "step": 462
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007507796610169492,
      "loss": 2.5521,
      "step": 463
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007506440677966102,
      "loss": 2.52,
      "step": 464
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007505084745762713,
      "loss": 2.5449,
      "step": 465
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007503728813559323,
      "loss": 2.4744,
      "step": 466
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007502372881355932,
      "loss": 2.5192,
      "step": 467
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007501016949152542,
      "loss": 2.4494,
      "step": 468
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007499661016949153,
      "loss": 2.5145,
      "step": 469
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007498305084745763,
      "loss": 2.4541,
      "step": 470
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007496949152542374,
      "loss": 2.563,
      "step": 471
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007495593220338984,
      "loss": 2.4924,
      "step": 472
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007494237288135595,
      "loss": 2.5099,
      "step": 473
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007492881355932203,
      "loss": 2.6177,
      "step": 474
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007491525423728813,
      "loss": 2.5639,
      "step": 475
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007490169491525424,
      "loss": 2.4748,
      "step": 476
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007488813559322034,
      "loss": 2.4668,
      "step": 477
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007487457627118645,
      "loss": 2.6352,
      "step": 478
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007486101694915254,
      "loss": 2.5874,
      "step": 479
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007484745762711865,
      "loss": 2.5707,
      "step": 480
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007483389830508475,
      "loss": 2.5545,
      "step": 481
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007482033898305085,
      "loss": 2.5301,
      "step": 482
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007480677966101695,
      "loss": 2.5508,
      "step": 483
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007479322033898306,
      "loss": 2.5526,
      "step": 484
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007477966101694915,
      "loss": 2.4831,
      "step": 485
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007476610169491526,
      "loss": 2.4991,
      "step": 486
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007475254237288136,
      "loss": 2.4024,
      "step": 487
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007473898305084746,
      "loss": 2.5339,
      "step": 488
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007472542372881356,
      "loss": 2.5592,
      "step": 489
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007471186440677967,
      "loss": 2.4575,
      "step": 490
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007469830508474576,
      "loss": 2.4742,
      "step": 491
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007468474576271187,
      "loss": 2.4736,
      "step": 492
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007467118644067797,
      "loss": 2.4658,
      "step": 493
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007465762711864408,
      "loss": 2.5223,
      "step": 494
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007464406779661017,
      "loss": 2.4854,
      "step": 495
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007463050847457627,
      "loss": 2.4874,
      "step": 496
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007461694915254237,
      "loss": 2.5765,
      "step": 497
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007460338983050847,
      "loss": 2.5211,
      "step": 498
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007458983050847458,
      "loss": 2.5138,
      "step": 499
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0007457627118644068,
      "loss": 2.4739,
      "step": 500
    },
    {
      "epoch": 0.08,
      "eval_gen_len": 19.0,
      "eval_loss": 2.2723255157470703,
      "eval_rouge1": 0.2537,
      "eval_rouge2": 0.0882,
      "eval_rougeL": 0.2125,
      "eval_rougeLsum": 0.2111,
      "eval_runtime": 18.6819,
      "eval_samples_per_second": 2.676,
      "eval_steps_per_second": 0.375,
      "step": 500
    }
  ],
  "max_steps": 6000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 4.762543607571456e+17,
  "trial_name": null,
  "trial_params": null
}