{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06666666666666667,
  "global_step": 400,
  "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": 4.0598,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 3.9538,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.4e-05,
      "loss": 4.0434,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 4.0516,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 4e-05,
      "loss": 3.998,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.8e-05,
      "loss": 4.0225,
      "step": 6
    },
    {
      "epoch": 0.0,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 3.904,
      "step": 7
    },
    {
      "epoch": 0.0,
      "learning_rate": 6.400000000000001e-05,
      "loss": 3.792,
      "step": 8
    },
    {
      "epoch": 0.0,
      "learning_rate": 7.2e-05,
      "loss": 3.5984,
      "step": 9
    },
    {
      "epoch": 0.0,
      "learning_rate": 8e-05,
      "loss": 3.4579,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.800000000000001e-05,
      "loss": 3.6368,
      "step": 11
    },
    {
      "epoch": 0.0,
      "learning_rate": 9.6e-05,
      "loss": 3.4327,
      "step": 12
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00010400000000000001,
      "loss": 3.3701,
      "step": 13
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00011200000000000001,
      "loss": 3.2466,
      "step": 14
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012,
      "loss": 3.2952,
      "step": 15
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00012800000000000002,
      "loss": 3.1374,
      "step": 16
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00013600000000000003,
      "loss": 3.139,
      "step": 17
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000144,
      "loss": 3.0374,
      "step": 18
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000152,
      "loss": 3.0814,
      "step": 19
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00016,
      "loss": 3.0121,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000168,
      "loss": 3.0238,
      "step": 21
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00017600000000000002,
      "loss": 2.84,
      "step": 22
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00018400000000000003,
      "loss": 2.8892,
      "step": 23
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000192,
      "loss": 2.8234,
      "step": 24
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.0002,
      "loss": 2.8687,
      "step": 25
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00020800000000000001,
      "loss": 2.7765,
      "step": 26
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00021600000000000002,
      "loss": 2.7827,
      "step": 27
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.00022400000000000002,
      "loss": 2.8096,
      "step": 28
    },
    {
      "epoch": 0.0,
      "learning_rate": 0.000232,
      "loss": 2.7986,
      "step": 29
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00024,
      "loss": 2.7335,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000248,
      "loss": 2.7041,
      "step": 31
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00025600000000000004,
      "loss": 2.6543,
      "step": 32
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000264,
      "loss": 2.6889,
      "step": 33
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00027200000000000005,
      "loss": 2.7073,
      "step": 34
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00028,
      "loss": 2.7532,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000288,
      "loss": 2.5479,
      "step": 36
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000296,
      "loss": 2.5846,
      "step": 37
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000304,
      "loss": 2.5425,
      "step": 38
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00031200000000000005,
      "loss": 2.6203,
      "step": 39
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00032,
      "loss": 2.578,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000328,
      "loss": 2.6235,
      "step": 41
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000336,
      "loss": 2.5181,
      "step": 42
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000344,
      "loss": 2.5592,
      "step": 43
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00035200000000000005,
      "loss": 2.4978,
      "step": 44
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00036,
      "loss": 2.5523,
      "step": 45
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00036800000000000005,
      "loss": 2.5996,
      "step": 46
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000376,
      "loss": 2.5497,
      "step": 47
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000384,
      "loss": 2.5293,
      "step": 48
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000392,
      "loss": 2.417,
      "step": 49
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0004,
      "loss": 2.4453,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00040800000000000005,
      "loss": 2.4302,
      "step": 51
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00041600000000000003,
      "loss": 2.3976,
      "step": 52
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00042400000000000006,
      "loss": 2.5218,
      "step": 53
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00043200000000000004,
      "loss": 2.4465,
      "step": 54
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00044000000000000007,
      "loss": 2.4865,
      "step": 55
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00044800000000000005,
      "loss": 2.5155,
      "step": 56
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00045599999999999997,
      "loss": 2.502,
      "step": 57
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000464,
      "loss": 2.4115,
      "step": 58
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000472,
      "loss": 2.4561,
      "step": 59
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00048,
      "loss": 2.4581,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000488,
      "loss": 2.4264,
      "step": 61
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000496,
      "loss": 2.4441,
      "step": 62
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000504,
      "loss": 2.4781,
      "step": 63
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005120000000000001,
      "loss": 2.3868,
      "step": 64
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005200000000000001,
      "loss": 2.4542,
      "step": 65
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000528,
      "loss": 2.4437,
      "step": 66
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000536,
      "loss": 2.4007,
      "step": 67
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0005440000000000001,
      "loss": 2.4116,
      "step": 68
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000552,
      "loss": 2.4022,
      "step": 69
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00056,
      "loss": 2.3727,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000568,
      "loss": 2.38,
      "step": 71
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000576,
      "loss": 2.3938,
      "step": 72
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000584,
      "loss": 2.4948,
      "step": 73
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000592,
      "loss": 2.3133,
      "step": 74
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006000000000000001,
      "loss": 2.4094,
      "step": 75
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000608,
      "loss": 2.3753,
      "step": 76
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000616,
      "loss": 2.4388,
      "step": 77
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006240000000000001,
      "loss": 2.4028,
      "step": 78
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0006320000000000001,
      "loss": 2.3912,
      "step": 79
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00064,
      "loss": 2.3202,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000648,
      "loss": 2.404,
      "step": 81
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000656,
      "loss": 2.3694,
      "step": 82
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000664,
      "loss": 2.3869,
      "step": 83
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000672,
      "loss": 2.3976,
      "step": 84
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00068,
      "loss": 2.3407,
      "step": 85
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000688,
      "loss": 2.35,
      "step": 86
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.000696,
      "loss": 2.3244,
      "step": 87
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007040000000000001,
      "loss": 2.2987,
      "step": 88
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0007120000000000001,
      "loss": 2.403,
      "step": 89
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.00072,
      "loss": 2.4228,
      "step": 90
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000728,
      "loss": 2.3729,
      "step": 91
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007360000000000001,
      "loss": 2.2986,
      "step": 92
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007440000000000001,
      "loss": 2.3624,
      "step": 93
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000752,
      "loss": 2.3393,
      "step": 94
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00076,
      "loss": 2.3151,
      "step": 95
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000768,
      "loss": 2.3513,
      "step": 96
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000776,
      "loss": 2.2885,
      "step": 97
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000784,
      "loss": 2.3285,
      "step": 98
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007920000000000001,
      "loss": 2.3709,
      "step": 99
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0008,
      "loss": 2.4014,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000799864406779661,
      "loss": 2.3282,
      "step": 101
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007997288135593221,
      "loss": 2.3529,
      "step": 102
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007995932203389831,
      "loss": 2.3502,
      "step": 103
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007994576271186441,
      "loss": 2.2684,
      "step": 104
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.000799322033898305,
      "loss": 2.3121,
      "step": 105
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007991864406779661,
      "loss": 2.2489,
      "step": 106
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007990508474576271,
      "loss": 2.2469,
      "step": 107
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007989152542372882,
      "loss": 2.3522,
      "step": 108
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007987796610169492,
      "loss": 2.2518,
      "step": 109
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007986440677966103,
      "loss": 2.3545,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007985084745762711,
      "loss": 2.3159,
      "step": 111
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007983728813559322,
      "loss": 2.3242,
      "step": 112
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007982372881355932,
      "loss": 2.3071,
      "step": 113
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007981016949152543,
      "loss": 2.3003,
      "step": 114
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007979661016949153,
      "loss": 2.2448,
      "step": 115
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007978305084745764,
      "loss": 2.3383,
      "step": 116
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007976949152542374,
      "loss": 2.2184,
      "step": 117
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007975593220338983,
      "loss": 2.3312,
      "step": 118
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007974237288135593,
      "loss": 2.3349,
      "step": 119
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007972881355932204,
      "loss": 2.3324,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007971525423728814,
      "loss": 2.3189,
      "step": 121
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007970169491525424,
      "loss": 2.2545,
      "step": 122
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007968813559322035,
      "loss": 2.3608,
      "step": 123
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007967457627118644,
      "loss": 2.2787,
      "step": 124
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007966101694915254,
      "loss": 2.3173,
      "step": 125
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007964745762711864,
      "loss": 2.2544,
      "step": 126
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007963389830508475,
      "loss": 2.3787,
      "step": 127
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007962033898305085,
      "loss": 2.2431,
      "step": 128
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007960677966101696,
      "loss": 2.2985,
      "step": 129
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007959322033898305,
      "loss": 2.255,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007957966101694916,
      "loss": 2.2984,
      "step": 131
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007956610169491526,
      "loss": 2.2976,
      "step": 132
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007955254237288136,
      "loss": 2.2816,
      "step": 133
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007953898305084746,
      "loss": 2.2662,
      "step": 134
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007952542372881357,
      "loss": 2.2066,
      "step": 135
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007951186440677966,
      "loss": 2.2509,
      "step": 136
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007949830508474577,
      "loss": 2.2874,
      "step": 137
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007948474576271187,
      "loss": 2.2304,
      "step": 138
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007947118644067797,
      "loss": 2.2438,
      "step": 139
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007945762711864407,
      "loss": 2.293,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007944406779661018,
      "loss": 2.2882,
      "step": 141
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007943050847457627,
      "loss": 2.2687,
      "step": 142
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007941694915254237,
      "loss": 2.2579,
      "step": 143
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007940338983050848,
      "loss": 2.2091,
      "step": 144
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007938983050847458,
      "loss": 2.3201,
      "step": 145
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007937627118644069,
      "loss": 2.1964,
      "step": 146
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007936271186440678,
      "loss": 2.2587,
      "step": 147
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007934915254237288,
      "loss": 2.2987,
      "step": 148
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0007933559322033898,
      "loss": 2.1963,
      "step": 149
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007932203389830509,
      "loss": 2.2045,
      "step": 150
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007930847457627119,
      "loss": 2.3174,
      "step": 151
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000792949152542373,
      "loss": 2.3348,
      "step": 152
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000792813559322034,
      "loss": 2.2241,
      "step": 153
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007926779661016949,
      "loss": 2.2472,
      "step": 154
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007925423728813559,
      "loss": 2.2352,
      "step": 155
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000792406779661017,
      "loss": 2.2351,
      "step": 156
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000792271186440678,
      "loss": 2.2205,
      "step": 157
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007921355932203391,
      "loss": 2.1175,
      "step": 158
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007920000000000001,
      "loss": 2.1801,
      "step": 159
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000791864406779661,
      "loss": 2.2301,
      "step": 160
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.000791728813559322,
      "loss": 2.2605,
      "step": 161
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007915932203389831,
      "loss": 2.2462,
      "step": 162
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007914576271186441,
      "loss": 2.2029,
      "step": 163
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007913220338983051,
      "loss": 2.2551,
      "step": 164
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007911864406779662,
      "loss": 2.2825,
      "step": 165
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007910508474576271,
      "loss": 2.2582,
      "step": 166
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007909152542372882,
      "loss": 2.2453,
      "step": 167
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007907796610169492,
      "loss": 2.2599,
      "step": 168
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007906440677966102,
      "loss": 2.2336,
      "step": 169
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007905084745762712,
      "loss": 2.1311,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007903728813559323,
      "loss": 2.2047,
      "step": 171
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007902372881355932,
      "loss": 2.2847,
      "step": 172
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007901016949152543,
      "loss": 2.1759,
      "step": 173
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007899661016949153,
      "loss": 2.1877,
      "step": 174
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007898305084745763,
      "loss": 2.2365,
      "step": 175
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007896949152542373,
      "loss": 2.1855,
      "step": 176
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007895593220338984,
      "loss": 2.2359,
      "step": 177
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007894237288135593,
      "loss": 2.2366,
      "step": 178
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007892881355932204,
      "loss": 2.2493,
      "step": 179
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007891525423728814,
      "loss": 2.2278,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007890169491525425,
      "loss": 2.2498,
      "step": 181
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007888813559322034,
      "loss": 2.2337,
      "step": 182
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007887457627118645,
      "loss": 2.2675,
      "step": 183
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007886101694915254,
      "loss": 2.2142,
      "step": 184
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007884745762711864,
      "loss": 2.2686,
      "step": 185
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007883389830508475,
      "loss": 2.1442,
      "step": 186
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007882033898305085,
      "loss": 2.2155,
      "step": 187
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007880677966101696,
      "loss": 2.2874,
      "step": 188
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007879322033898306,
      "loss": 2.1709,
      "step": 189
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007877966101694915,
      "loss": 2.2595,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007876610169491525,
      "loss": 2.2017,
      "step": 191
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007875254237288136,
      "loss": 2.1778,
      "step": 192
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007873898305084746,
      "loss": 2.2272,
      "step": 193
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007872542372881357,
      "loss": 2.2734,
      "step": 194
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007871186440677967,
      "loss": 2.1794,
      "step": 195
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007869830508474576,
      "loss": 2.2155,
      "step": 196
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007868474576271186,
      "loss": 2.2478,
      "step": 197
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007867118644067797,
      "loss": 2.1717,
      "step": 198
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007865762711864407,
      "loss": 2.2421,
      "step": 199
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007864406779661018,
      "loss": 2.2584,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007863050847457628,
      "loss": 2.2263,
      "step": 201
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007861694915254239,
      "loss": 2.1951,
      "step": 202
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007860338983050848,
      "loss": 2.1717,
      "step": 203
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007858983050847457,
      "loss": 2.1705,
      "step": 204
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007857627118644068,
      "loss": 2.199,
      "step": 205
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007856271186440678,
      "loss": 2.3078,
      "step": 206
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007854915254237289,
      "loss": 2.1449,
      "step": 207
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007853559322033898,
      "loss": 2.1788,
      "step": 208
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0007852203389830509,
      "loss": 2.1998,
      "step": 209
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007850847457627119,
      "loss": 2.2799,
      "step": 210
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007849491525423729,
      "loss": 2.2501,
      "step": 211
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007848135593220339,
      "loss": 2.2081,
      "step": 212
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000784677966101695,
      "loss": 2.1697,
      "step": 213
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007845423728813559,
      "loss": 2.1713,
      "step": 214
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000784406779661017,
      "loss": 2.2226,
      "step": 215
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000784271186440678,
      "loss": 2.2084,
      "step": 216
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007841355932203391,
      "loss": 2.1771,
      "step": 217
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000784,
      "loss": 2.2013,
      "step": 218
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007838644067796611,
      "loss": 2.248,
      "step": 219
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.000783728813559322,
      "loss": 2.2238,
      "step": 220
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007835932203389831,
      "loss": 2.1268,
      "step": 221
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007834576271186441,
      "loss": 2.161,
      "step": 222
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007833220338983052,
      "loss": 2.1049,
      "step": 223
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007831864406779662,
      "loss": 2.1929,
      "step": 224
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007830508474576272,
      "loss": 2.2978,
      "step": 225
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007829152542372881,
      "loss": 2.175,
      "step": 226
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007827796610169491,
      "loss": 2.2298,
      "step": 227
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007826440677966102,
      "loss": 2.1707,
      "step": 228
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007825084745762712,
      "loss": 2.1759,
      "step": 229
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007823728813559323,
      "loss": 2.182,
      "step": 230
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007822372881355933,
      "loss": 2.219,
      "step": 231
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007821016949152542,
      "loss": 2.2042,
      "step": 232
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007819661016949152,
      "loss": 2.1706,
      "step": 233
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007818305084745763,
      "loss": 2.171,
      "step": 234
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007816949152542373,
      "loss": 2.0928,
      "step": 235
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007815593220338984,
      "loss": 2.2218,
      "step": 236
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007814237288135594,
      "loss": 2.1285,
      "step": 237
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007812881355932205,
      "loss": 2.2702,
      "step": 238
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007811525423728813,
      "loss": 2.2371,
      "step": 239
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007810169491525424,
      "loss": 2.1952,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007808813559322034,
      "loss": 2.228,
      "step": 241
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007807457627118645,
      "loss": 2.0863,
      "step": 242
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007806101694915255,
      "loss": 2.1102,
      "step": 243
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007804745762711866,
      "loss": 2.0992,
      "step": 244
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007803389830508475,
      "loss": 2.231,
      "step": 245
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007802033898305085,
      "loss": 2.1459,
      "step": 246
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007800677966101695,
      "loss": 2.2173,
      "step": 247
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007799322033898305,
      "loss": 2.1938,
      "step": 248
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007797966101694916,
      "loss": 2.1128,
      "step": 249
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007796610169491525,
      "loss": 2.1401,
      "step": 250
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007795254237288136,
      "loss": 2.1503,
      "step": 251
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007793898305084746,
      "loss": 2.0771,
      "step": 252
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007792542372881356,
      "loss": 2.0993,
      "step": 253
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007791186440677966,
      "loss": 2.24,
      "step": 254
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007789830508474577,
      "loss": 2.154,
      "step": 255
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007788474576271186,
      "loss": 2.1774,
      "step": 256
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007787118644067797,
      "loss": 2.0888,
      "step": 257
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007785762711864407,
      "loss": 2.216,
      "step": 258
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007784406779661018,
      "loss": 2.1042,
      "step": 259
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007783050847457628,
      "loss": 2.2299,
      "step": 260
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007781694915254238,
      "loss": 2.201,
      "step": 261
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007780338983050847,
      "loss": 2.1315,
      "step": 262
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007778983050847458,
      "loss": 2.1977,
      "step": 263
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007777627118644068,
      "loss": 2.2053,
      "step": 264
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007776271186440679,
      "loss": 2.1809,
      "step": 265
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007774915254237289,
      "loss": 2.2412,
      "step": 266
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007773559322033899,
      "loss": 2.2178,
      "step": 267
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007772203389830508,
      "loss": 2.2615,
      "step": 268
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007770847457627118,
      "loss": 2.128,
      "step": 269
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0007769491525423729,
      "loss": 2.2243,
      "step": 270
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007768135593220339,
      "loss": 2.1416,
      "step": 271
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000776677966101695,
      "loss": 2.1921,
      "step": 272
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000776542372881356,
      "loss": 2.1748,
      "step": 273
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007764067796610171,
      "loss": 2.1006,
      "step": 274
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007762711864406779,
      "loss": 2.1855,
      "step": 275
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000776135593220339,
      "loss": 2.0681,
      "step": 276
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000776,
      "loss": 2.2588,
      "step": 277
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007758644067796611,
      "loss": 2.1486,
      "step": 278
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007757288135593221,
      "loss": 2.206,
      "step": 279
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007755932203389832,
      "loss": 2.0873,
      "step": 280
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007754576271186441,
      "loss": 2.149,
      "step": 281
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007753220338983051,
      "loss": 2.1717,
      "step": 282
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007751864406779661,
      "loss": 2.1944,
      "step": 283
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007750508474576272,
      "loss": 2.1323,
      "step": 284
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007749152542372882,
      "loss": 2.2031,
      "step": 285
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007747796610169493,
      "loss": 2.1541,
      "step": 286
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007746440677966102,
      "loss": 2.1012,
      "step": 287
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007745084745762712,
      "loss": 2.1111,
      "step": 288
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007743728813559322,
      "loss": 2.1989,
      "step": 289
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007742372881355932,
      "loss": 2.1702,
      "step": 290
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007741016949152543,
      "loss": 2.095,
      "step": 291
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007739661016949152,
      "loss": 2.2087,
      "step": 292
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007738305084745763,
      "loss": 2.1621,
      "step": 293
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007736949152542373,
      "loss": 2.1102,
      "step": 294
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007735593220338984,
      "loss": 2.1092,
      "step": 295
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007734237288135594,
      "loss": 2.0995,
      "step": 296
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007732881355932204,
      "loss": 2.0985,
      "step": 297
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007731525423728813,
      "loss": 2.1749,
      "step": 298
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007730169491525424,
      "loss": 2.1833,
      "step": 299
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007728813559322034,
      "loss": 2.1927,
      "step": 300
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007727457627118645,
      "loss": 2.0672,
      "step": 301
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007726101694915255,
      "loss": 2.2456,
      "step": 302
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007724745762711865,
      "loss": 2.1152,
      "step": 303
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007723389830508474,
      "loss": 2.1347,
      "step": 304
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007722033898305085,
      "loss": 2.113,
      "step": 305
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007720677966101695,
      "loss": 2.1097,
      "step": 306
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007719322033898306,
      "loss": 2.1361,
      "step": 307
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007717966101694916,
      "loss": 2.1015,
      "step": 308
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007716610169491526,
      "loss": 2.1516,
      "step": 309
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007715254237288135,
      "loss": 2.1099,
      "step": 310
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007713898305084745,
      "loss": 2.1754,
      "step": 311
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007712542372881356,
      "loss": 2.1101,
      "step": 312
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007711186440677966,
      "loss": 2.1652,
      "step": 313
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007709830508474577,
      "loss": 2.0852,
      "step": 314
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007708474576271187,
      "loss": 2.0926,
      "step": 315
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007707118644067798,
      "loss": 2.1592,
      "step": 316
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007705762711864407,
      "loss": 2.2111,
      "step": 317
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007704406779661017,
      "loss": 2.08,
      "step": 318
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007703050847457627,
      "loss": 2.1532,
      "step": 319
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007701694915254238,
      "loss": 2.1141,
      "step": 320
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007700338983050848,
      "loss": 2.0578,
      "step": 321
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007698983050847459,
      "loss": 2.1405,
      "step": 322
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007697627118644068,
      "loss": 2.0921,
      "step": 323
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007696271186440678,
      "loss": 2.1161,
      "step": 324
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007694915254237288,
      "loss": 2.118,
      "step": 325
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007693559322033899,
      "loss": 2.054,
      "step": 326
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007692203389830509,
      "loss": 2.0837,
      "step": 327
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.000769084745762712,
      "loss": 2.1788,
      "step": 328
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0007689491525423729,
      "loss": 2.1688,
      "step": 329
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007688135593220339,
      "loss": 2.1397,
      "step": 330
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768677966101695,
      "loss": 2.0973,
      "step": 331
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007685423728813559,
      "loss": 2.1558,
      "step": 332
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768406779661017,
      "loss": 2.0784,
      "step": 333
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768271186440678,
      "loss": 2.0901,
      "step": 334
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768135593220339,
      "loss": 2.083,
      "step": 335
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000768,
      "loss": 2.0883,
      "step": 336
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007678644067796611,
      "loss": 2.1707,
      "step": 337
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007677288135593221,
      "loss": 2.1467,
      "step": 338
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007675932203389831,
      "loss": 2.0778,
      "step": 339
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000767457627118644,
      "loss": 2.158,
      "step": 340
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007673220338983051,
      "loss": 2.1849,
      "step": 341
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007671864406779661,
      "loss": 2.132,
      "step": 342
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007670508474576272,
      "loss": 2.1017,
      "step": 343
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007669152542372882,
      "loss": 2.1146,
      "step": 344
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007667796610169493,
      "loss": 2.0731,
      "step": 345
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007666440677966102,
      "loss": 2.1342,
      "step": 346
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007665084745762712,
      "loss": 2.1694,
      "step": 347
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007663728813559322,
      "loss": 2.0779,
      "step": 348
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007662372881355933,
      "loss": 2.151,
      "step": 349
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007661016949152543,
      "loss": 2.121,
      "step": 350
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007659661016949153,
      "loss": 2.0767,
      "step": 351
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007658305084745764,
      "loss": 2.1442,
      "step": 352
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007656949152542373,
      "loss": 2.1636,
      "step": 353
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007655593220338983,
      "loss": 2.168,
      "step": 354
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007654237288135593,
      "loss": 2.1254,
      "step": 355
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007652881355932204,
      "loss": 2.1253,
      "step": 356
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007651525423728814,
      "loss": 2.0905,
      "step": 357
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007650169491525425,
      "loss": 2.0981,
      "step": 358
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007648813559322034,
      "loss": 2.1296,
      "step": 359
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007647457627118644,
      "loss": 2.1614,
      "step": 360
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007646101694915254,
      "loss": 2.0396,
      "step": 361
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007644745762711865,
      "loss": 2.1202,
      "step": 362
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007643389830508475,
      "loss": 2.083,
      "step": 363
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007642033898305086,
      "loss": 2.1423,
      "step": 364
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007640677966101695,
      "loss": 2.2048,
      "step": 365
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007639322033898306,
      "loss": 2.1045,
      "step": 366
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007637966101694915,
      "loss": 2.0007,
      "step": 367
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007636610169491526,
      "loss": 2.1807,
      "step": 368
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007635254237288136,
      "loss": 2.1266,
      "step": 369
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007633898305084747,
      "loss": 2.1566,
      "step": 370
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007632542372881356,
      "loss": 1.9788,
      "step": 371
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007631186440677966,
      "loss": 2.1346,
      "step": 372
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007629830508474577,
      "loss": 2.1011,
      "step": 373
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007628474576271187,
      "loss": 2.1045,
      "step": 374
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007627118644067797,
      "loss": 2.0789,
      "step": 375
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007625762711864407,
      "loss": 2.1627,
      "step": 376
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007624406779661017,
      "loss": 2.1348,
      "step": 377
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007623050847457627,
      "loss": 2.0705,
      "step": 378
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007621694915254238,
      "loss": 2.1322,
      "step": 379
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007620338983050848,
      "loss": 2.0468,
      "step": 380
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007618983050847458,
      "loss": 2.0707,
      "step": 381
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007617627118644068,
      "loss": 2.1316,
      "step": 382
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007616271186440678,
      "loss": 2.115,
      "step": 383
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007614915254237288,
      "loss": 2.1173,
      "step": 384
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007613559322033899,
      "loss": 2.1069,
      "step": 385
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007612203389830509,
      "loss": 2.1525,
      "step": 386
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000761084745762712,
      "loss": 2.1556,
      "step": 387
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.000760949152542373,
      "loss": 2.1647,
      "step": 388
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0007608135593220339,
      "loss": 2.0778,
      "step": 389
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007606779661016949,
      "loss": 2.1567,
      "step": 390
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007605423728813559,
      "loss": 2.0568,
      "step": 391
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000760406779661017,
      "loss": 2.0702,
      "step": 392
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000760271186440678,
      "loss": 2.1035,
      "step": 393
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007601355932203391,
      "loss": 2.1456,
      "step": 394
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00076,
      "loss": 2.0825,
      "step": 395
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000759864406779661,
      "loss": 2.1152,
      "step": 396
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.000759728813559322,
      "loss": 2.0893,
      "step": 397
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007595932203389831,
      "loss": 2.1312,
      "step": 398
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007594576271186441,
      "loss": 2.1767,
      "step": 399
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0007593220338983052,
      "loss": 2.1467,
      "step": 400
    }
  ],
  "max_steps": 6000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 2.066289917184e+17,
  "trial_name": null,
  "trial_params": null
}