core-350 / trainer_state.json
ccore's picture
Upload folder using huggingface_hub
cb54067
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.959654178674352,
"eval_steps": 500,
"global_step": 2160,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0001,
"loss": 0.9676,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 0.984,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 0.9972,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.7676,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.8397,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 0.9377,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 0.9696,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.7991,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.8041,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.7569,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.8154,
"step": 11
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.9037,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.8435,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.898,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 0.766,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 0.9003,
"step": 16
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 1.0274,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 0.8301,
"step": 18
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 0.8955,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 0.7742,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.7537,
"step": 21
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.7349,
"step": 22
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 0.8877,
"step": 23
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 0.8331,
"step": 24
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.7666,
"step": 25
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.8962,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.8609,
"step": 27
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.8964,
"step": 28
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.7768,
"step": 29
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.8596,
"step": 30
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.7721,
"step": 31
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 0.8878,
"step": 32
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 0.7284,
"step": 33
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.8328,
"step": 34
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.8429,
"step": 35
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 0.8448,
"step": 36
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 0.7671,
"step": 37
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.7308,
"step": 38
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.7853,
"step": 39
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.9482,
"step": 40
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 0.8009,
"step": 41
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 0.868,
"step": 42
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 0.7897,
"step": 43
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 0.8714,
"step": 44
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.9657,
"step": 45
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.6454,
"step": 46
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.7253,
"step": 47
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.8628,
"step": 48
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.8246,
"step": 49
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.8561,
"step": 50
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 0.9077,
"step": 51
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 0.8367,
"step": 52
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 0.6432,
"step": 53
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.7554,
"step": 54
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.7791,
"step": 55
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 0.6147,
"step": 56
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 0.8167,
"step": 57
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.799,
"step": 58
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.8401,
"step": 59
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 0.8526,
"step": 60
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 0.7959,
"step": 61
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.8322,
"step": 62
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.8143,
"step": 63
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.9124,
"step": 64
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.9136,
"step": 65
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.66,
"step": 66
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.7623,
"step": 67
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.8536,
"step": 68
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 0.861,
"step": 69
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 0.7515,
"step": 70
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.9016,
"step": 71
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.7602,
"step": 72
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 0.7922,
"step": 73
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 0.7904,
"step": 74
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.8212,
"step": 75
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.9254,
"step": 76
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.8227,
"step": 77
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.8176,
"step": 78
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.8689,
"step": 79
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.8448,
"step": 80
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.7981,
"step": 81
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 0.9025,
"step": 82
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 0.9171,
"step": 83
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.7892,
"step": 84
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.7796,
"step": 85
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.6473,
"step": 86
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.7714,
"step": 87
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.8859,
"step": 88
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.865,
"step": 89
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.7903,
"step": 90
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 0.8456,
"step": 91
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 0.8748,
"step": 92
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.7083,
"step": 93
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.8524,
"step": 94
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 0.8066,
"step": 95
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 0.8477,
"step": 96
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.8123,
"step": 97
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.8744,
"step": 98
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 0.7072,
"step": 99
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 0.8777,
"step": 100
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.7469,
"step": 101
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.8014,
"step": 102
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.9208,
"step": 103
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 0.7975,
"step": 104
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 0.8179,
"step": 105
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.9535,
"step": 106
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.8673,
"step": 107
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 0.9145,
"step": 108
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 0.85,
"step": 109
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.8655,
"step": 110
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.9255,
"step": 111
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 0.8388,
"step": 112
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 0.8188,
"step": 113
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.7234,
"step": 114
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.7082,
"step": 115
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 1.0244,
"step": 116
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 0.8967,
"step": 117
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 0.9149,
"step": 118
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.846,
"step": 119
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.7465,
"step": 120
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 0.7559,
"step": 121
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 0.8759,
"step": 122
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.8799,
"step": 123
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.8252,
"step": 124
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 0.7316,
"step": 125
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 0.9244,
"step": 126
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.8405,
"step": 127
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.7695,
"step": 128
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.9441,
"step": 129
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.8565,
"step": 130
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.7499,
"step": 131
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 0.6813,
"step": 132
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 0.7008,
"step": 133
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.9203,
"step": 134
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.879,
"step": 135
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 0.7201,
"step": 136
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 0.7224,
"step": 137
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.9708,
"step": 138
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.8975,
"step": 139
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.8079,
"step": 140
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.903,
"step": 141
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.7281,
"step": 142
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.8719,
"step": 143
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.7554,
"step": 144
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 0.8348,
"step": 145
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 0.8446,
"step": 146
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.8102,
"step": 147
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.7993,
"step": 148
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 0.9064,
"step": 149
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 0.7543,
"step": 150
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.9233,
"step": 151
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.7603,
"step": 152
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 0.8448,
"step": 153
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 0.7701,
"step": 154
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 0.7125,
"step": 155
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.9714,
"step": 156
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.6506,
"step": 157
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 0.8068,
"step": 158
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 0.8426,
"step": 159
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.8681,
"step": 160
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.7896,
"step": 161
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.9349,
"step": 162
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.7542,
"step": 163
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.9205,
"step": 164
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.7033,
"step": 165
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.8871,
"step": 166
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.7618,
"step": 167
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.6737,
"step": 168
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.7924,
"step": 169
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.7196,
"step": 170
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 0.7699,
"step": 171
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 0.7409,
"step": 172
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.8456,
"step": 173
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.8473,
"step": 174
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 0.7191,
"step": 175
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 0.7176,
"step": 176
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.8811,
"step": 177
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.8907,
"step": 178
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.7996,
"step": 179
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.8114,
"step": 180
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.8665,
"step": 181
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.8563,
"step": 182
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.7947,
"step": 183
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 0.834,
"step": 184
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 0.7452,
"step": 185
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.8456,
"step": 186
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.9828,
"step": 187
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.8402,
"step": 188
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.7954,
"step": 189
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.847,
"step": 190
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.802,
"step": 191
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.7945,
"step": 192
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.8923,
"step": 193
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.7464,
"step": 194
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.7628,
"step": 195
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.9398,
"step": 196
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 0.8046,
"step": 197
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 0.9456,
"step": 198
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.6363,
"step": 199
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.7987,
"step": 200
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.8442,
"step": 201
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.7261,
"step": 202
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.8117,
"step": 203
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.9202,
"step": 204
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.8849,
"step": 205
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.7932,
"step": 206
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.808,
"step": 207
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.888,
"step": 208
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.7703,
"step": 209
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 0.8071,
"step": 210
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 0.7929,
"step": 211
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.8726,
"step": 212
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.7442,
"step": 213
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 0.8444,
"step": 214
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 0.918,
"step": 215
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.8186,
"step": 216
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.8403,
"step": 217
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.6137,
"step": 218
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.8166,
"step": 219
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.7287,
"step": 220
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.6183,
"step": 221
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.4999,
"step": 222
},
{
"epoch": 1.03,
"learning_rate": 0.0001,
"loss": 0.6258,
"step": 223
},
{
"epoch": 1.03,
"learning_rate": 0.0001,
"loss": 0.5283,
"step": 224
},
{
"epoch": 1.04,
"learning_rate": 0.0001,
"loss": 0.6338,
"step": 225
},
{
"epoch": 1.04,
"learning_rate": 0.0001,
"loss": 0.644,
"step": 226
},
{
"epoch": 1.05,
"learning_rate": 0.0001,
"loss": 0.6705,
"step": 227
},
{
"epoch": 1.05,
"learning_rate": 0.0001,
"loss": 0.6377,
"step": 228
},
{
"epoch": 1.06,
"learning_rate": 0.0001,
"loss": 0.6374,
"step": 229
},
{
"epoch": 1.06,
"learning_rate": 0.0001,
"loss": 0.7175,
"step": 230
},
{
"epoch": 1.07,
"learning_rate": 0.0001,
"loss": 0.6294,
"step": 231
},
{
"epoch": 1.07,
"learning_rate": 0.0001,
"loss": 0.6403,
"step": 232
},
{
"epoch": 1.07,
"learning_rate": 0.0001,
"loss": 0.637,
"step": 233
},
{
"epoch": 1.08,
"learning_rate": 0.0001,
"loss": 0.6534,
"step": 234
},
{
"epoch": 1.08,
"learning_rate": 0.0001,
"loss": 0.6896,
"step": 235
},
{
"epoch": 1.09,
"learning_rate": 0.0001,
"loss": 0.6255,
"step": 236
},
{
"epoch": 1.09,
"learning_rate": 0.0001,
"loss": 0.5834,
"step": 237
},
{
"epoch": 1.1,
"learning_rate": 0.0001,
"loss": 0.5789,
"step": 238
},
{
"epoch": 1.1,
"learning_rate": 0.0001,
"loss": 0.6068,
"step": 239
},
{
"epoch": 1.11,
"learning_rate": 0.0001,
"loss": 0.6659,
"step": 240
},
{
"epoch": 1.11,
"learning_rate": 0.0001,
"loss": 0.593,
"step": 241
},
{
"epoch": 1.12,
"learning_rate": 0.0001,
"loss": 0.7278,
"step": 242
},
{
"epoch": 1.12,
"learning_rate": 0.0001,
"loss": 0.6249,
"step": 243
},
{
"epoch": 1.13,
"learning_rate": 0.0001,
"loss": 0.6226,
"step": 244
},
{
"epoch": 1.13,
"learning_rate": 0.0001,
"loss": 0.6055,
"step": 245
},
{
"epoch": 1.13,
"learning_rate": 0.0001,
"loss": 0.6842,
"step": 246
},
{
"epoch": 1.14,
"learning_rate": 0.0001,
"loss": 0.5725,
"step": 247
},
{
"epoch": 1.14,
"learning_rate": 0.0001,
"loss": 0.8079,
"step": 248
},
{
"epoch": 1.15,
"learning_rate": 0.0001,
"loss": 0.7518,
"step": 249
},
{
"epoch": 1.15,
"learning_rate": 0.0001,
"loss": 0.6706,
"step": 250
},
{
"epoch": 1.16,
"learning_rate": 0.0001,
"loss": 0.7217,
"step": 251
},
{
"epoch": 1.16,
"learning_rate": 0.0001,
"loss": 0.6161,
"step": 252
},
{
"epoch": 1.17,
"learning_rate": 0.0001,
"loss": 0.6734,
"step": 253
},
{
"epoch": 1.17,
"learning_rate": 0.0001,
"loss": 0.6245,
"step": 254
},
{
"epoch": 1.18,
"learning_rate": 0.0001,
"loss": 0.6444,
"step": 255
},
{
"epoch": 1.18,
"learning_rate": 0.0001,
"loss": 0.7256,
"step": 256
},
{
"epoch": 1.19,
"learning_rate": 0.0001,
"loss": 0.6081,
"step": 257
},
{
"epoch": 1.19,
"learning_rate": 0.0001,
"loss": 0.5902,
"step": 258
},
{
"epoch": 1.19,
"learning_rate": 0.0001,
"loss": 0.6157,
"step": 259
},
{
"epoch": 1.2,
"learning_rate": 0.0001,
"loss": 0.629,
"step": 260
},
{
"epoch": 1.2,
"learning_rate": 0.0001,
"loss": 0.7013,
"step": 261
},
{
"epoch": 1.21,
"learning_rate": 0.0001,
"loss": 0.5679,
"step": 262
},
{
"epoch": 1.21,
"learning_rate": 0.0001,
"loss": 0.6971,
"step": 263
},
{
"epoch": 1.22,
"learning_rate": 0.0001,
"loss": 0.6464,
"step": 264
},
{
"epoch": 1.22,
"learning_rate": 0.0001,
"loss": 0.6777,
"step": 265
},
{
"epoch": 1.23,
"learning_rate": 0.0001,
"loss": 0.687,
"step": 266
},
{
"epoch": 1.23,
"learning_rate": 0.0001,
"loss": 0.6545,
"step": 267
},
{
"epoch": 1.24,
"learning_rate": 0.0001,
"loss": 0.5822,
"step": 268
},
{
"epoch": 1.24,
"learning_rate": 0.0001,
"loss": 0.7351,
"step": 269
},
{
"epoch": 1.24,
"learning_rate": 0.0001,
"loss": 0.6112,
"step": 270
},
{
"epoch": 1.25,
"learning_rate": 0.0001,
"loss": 0.591,
"step": 271
},
{
"epoch": 1.25,
"learning_rate": 0.0001,
"loss": 0.7036,
"step": 272
},
{
"epoch": 1.26,
"learning_rate": 0.0001,
"loss": 0.7542,
"step": 273
},
{
"epoch": 1.26,
"learning_rate": 0.0001,
"loss": 0.6237,
"step": 274
},
{
"epoch": 1.27,
"learning_rate": 0.0001,
"loss": 0.6694,
"step": 275
},
{
"epoch": 1.27,
"learning_rate": 0.0001,
"loss": 0.6096,
"step": 276
},
{
"epoch": 1.28,
"learning_rate": 0.0001,
"loss": 0.6693,
"step": 277
},
{
"epoch": 1.28,
"learning_rate": 0.0001,
"loss": 0.6809,
"step": 278
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 0.6654,
"step": 279
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 0.6434,
"step": 280
},
{
"epoch": 1.3,
"learning_rate": 0.0001,
"loss": 0.5619,
"step": 281
},
{
"epoch": 1.3,
"learning_rate": 0.0001,
"loss": 0.7082,
"step": 282
},
{
"epoch": 1.3,
"learning_rate": 0.0001,
"loss": 0.7005,
"step": 283
},
{
"epoch": 1.31,
"learning_rate": 0.0001,
"loss": 0.7207,
"step": 284
},
{
"epoch": 1.31,
"learning_rate": 0.0001,
"loss": 0.7008,
"step": 285
},
{
"epoch": 1.32,
"learning_rate": 0.0001,
"loss": 0.7613,
"step": 286
},
{
"epoch": 1.32,
"learning_rate": 0.0001,
"loss": 0.6583,
"step": 287
},
{
"epoch": 1.33,
"learning_rate": 0.0001,
"loss": 0.6438,
"step": 288
},
{
"epoch": 1.33,
"learning_rate": 0.0001,
"loss": 0.642,
"step": 289
},
{
"epoch": 1.34,
"learning_rate": 0.0001,
"loss": 0.6378,
"step": 290
},
{
"epoch": 1.34,
"learning_rate": 0.0001,
"loss": 0.7052,
"step": 291
},
{
"epoch": 1.35,
"learning_rate": 0.0001,
"loss": 0.6238,
"step": 292
},
{
"epoch": 1.35,
"learning_rate": 0.0001,
"loss": 0.645,
"step": 293
},
{
"epoch": 1.36,
"learning_rate": 0.0001,
"loss": 0.6267,
"step": 294
},
{
"epoch": 1.36,
"learning_rate": 0.0001,
"loss": 0.6701,
"step": 295
},
{
"epoch": 1.36,
"learning_rate": 0.0001,
"loss": 0.577,
"step": 296
},
{
"epoch": 1.37,
"learning_rate": 0.0001,
"loss": 0.6614,
"step": 297
},
{
"epoch": 1.37,
"learning_rate": 0.0001,
"loss": 0.7007,
"step": 298
},
{
"epoch": 1.38,
"learning_rate": 0.0001,
"loss": 0.5506,
"step": 299
},
{
"epoch": 1.38,
"learning_rate": 0.0001,
"loss": 0.5637,
"step": 300
},
{
"epoch": 1.39,
"learning_rate": 0.0001,
"loss": 0.5992,
"step": 301
},
{
"epoch": 1.39,
"learning_rate": 0.0001,
"loss": 0.6314,
"step": 302
},
{
"epoch": 1.4,
"learning_rate": 0.0001,
"loss": 0.7354,
"step": 303
},
{
"epoch": 1.4,
"learning_rate": 0.0001,
"loss": 0.7406,
"step": 304
},
{
"epoch": 1.41,
"learning_rate": 0.0001,
"loss": 0.6475,
"step": 305
},
{
"epoch": 1.41,
"learning_rate": 0.0001,
"loss": 0.8124,
"step": 306
},
{
"epoch": 1.42,
"learning_rate": 0.0001,
"loss": 0.6359,
"step": 307
},
{
"epoch": 1.42,
"learning_rate": 0.0001,
"loss": 0.6932,
"step": 308
},
{
"epoch": 1.42,
"learning_rate": 0.0001,
"loss": 0.6507,
"step": 309
},
{
"epoch": 1.43,
"learning_rate": 0.0001,
"loss": 0.6154,
"step": 310
},
{
"epoch": 1.43,
"learning_rate": 0.0001,
"loss": 0.7067,
"step": 311
},
{
"epoch": 1.44,
"learning_rate": 0.0001,
"loss": 0.7607,
"step": 312
},
{
"epoch": 1.44,
"learning_rate": 0.0001,
"loss": 0.529,
"step": 313
},
{
"epoch": 1.45,
"learning_rate": 0.0001,
"loss": 0.5931,
"step": 314
},
{
"epoch": 1.45,
"learning_rate": 0.0001,
"loss": 0.6802,
"step": 315
},
{
"epoch": 1.46,
"learning_rate": 0.0001,
"loss": 0.6431,
"step": 316
},
{
"epoch": 1.46,
"learning_rate": 0.0001,
"loss": 0.6294,
"step": 317
},
{
"epoch": 1.47,
"learning_rate": 0.0001,
"loss": 0.664,
"step": 318
},
{
"epoch": 1.47,
"learning_rate": 0.0001,
"loss": 0.6324,
"step": 319
},
{
"epoch": 1.48,
"learning_rate": 0.0001,
"loss": 0.6428,
"step": 320
},
{
"epoch": 1.48,
"learning_rate": 0.0001,
"loss": 0.6894,
"step": 321
},
{
"epoch": 1.48,
"learning_rate": 0.0001,
"loss": 0.7039,
"step": 322
},
{
"epoch": 1.49,
"learning_rate": 0.0001,
"loss": 0.7251,
"step": 323
},
{
"epoch": 1.49,
"learning_rate": 0.0001,
"loss": 0.6487,
"step": 324
},
{
"epoch": 1.5,
"learning_rate": 0.0001,
"loss": 0.7712,
"step": 325
},
{
"epoch": 1.5,
"learning_rate": 0.0001,
"loss": 0.5498,
"step": 326
},
{
"epoch": 1.51,
"learning_rate": 0.0001,
"loss": 0.7846,
"step": 327
},
{
"epoch": 1.51,
"learning_rate": 0.0001,
"loss": 0.6807,
"step": 328
},
{
"epoch": 1.52,
"learning_rate": 0.0001,
"loss": 0.6535,
"step": 329
},
{
"epoch": 1.52,
"learning_rate": 0.0001,
"loss": 0.6623,
"step": 330
},
{
"epoch": 1.53,
"learning_rate": 0.0001,
"loss": 0.5785,
"step": 331
},
{
"epoch": 1.53,
"learning_rate": 0.0001,
"loss": 0.5555,
"step": 332
},
{
"epoch": 1.54,
"learning_rate": 0.0001,
"loss": 0.7261,
"step": 333
},
{
"epoch": 1.54,
"learning_rate": 0.0001,
"loss": 0.6072,
"step": 334
},
{
"epoch": 1.54,
"learning_rate": 0.0001,
"loss": 0.5498,
"step": 335
},
{
"epoch": 1.55,
"learning_rate": 0.0001,
"loss": 0.5894,
"step": 336
},
{
"epoch": 1.55,
"learning_rate": 0.0001,
"loss": 0.6853,
"step": 337
},
{
"epoch": 1.56,
"learning_rate": 0.0001,
"loss": 0.6072,
"step": 338
},
{
"epoch": 1.56,
"learning_rate": 0.0001,
"loss": 0.7072,
"step": 339
},
{
"epoch": 1.57,
"learning_rate": 0.0001,
"loss": 0.7131,
"step": 340
},
{
"epoch": 1.57,
"learning_rate": 0.0001,
"loss": 0.6687,
"step": 341
},
{
"epoch": 1.58,
"learning_rate": 0.0001,
"loss": 0.6753,
"step": 342
},
{
"epoch": 1.58,
"learning_rate": 0.0001,
"loss": 0.6804,
"step": 343
},
{
"epoch": 1.59,
"learning_rate": 0.0001,
"loss": 0.6072,
"step": 344
},
{
"epoch": 1.59,
"learning_rate": 0.0001,
"loss": 0.6172,
"step": 345
},
{
"epoch": 1.6,
"learning_rate": 0.0001,
"loss": 0.6871,
"step": 346
},
{
"epoch": 1.6,
"learning_rate": 0.0001,
"loss": 0.6944,
"step": 347
},
{
"epoch": 1.6,
"learning_rate": 0.0001,
"loss": 0.7855,
"step": 348
},
{
"epoch": 1.61,
"learning_rate": 0.0001,
"loss": 0.6763,
"step": 349
},
{
"epoch": 1.61,
"learning_rate": 0.0001,
"loss": 0.5914,
"step": 350
},
{
"epoch": 1.62,
"learning_rate": 0.0001,
"loss": 0.7289,
"step": 351
},
{
"epoch": 1.62,
"learning_rate": 0.0001,
"loss": 0.723,
"step": 352
},
{
"epoch": 1.63,
"learning_rate": 0.0001,
"loss": 0.5951,
"step": 353
},
{
"epoch": 1.63,
"learning_rate": 0.0001,
"loss": 0.7577,
"step": 354
},
{
"epoch": 1.64,
"learning_rate": 0.0001,
"loss": 0.654,
"step": 355
},
{
"epoch": 1.64,
"learning_rate": 0.0001,
"loss": 0.7728,
"step": 356
},
{
"epoch": 1.65,
"learning_rate": 0.0001,
"loss": 0.7034,
"step": 357
},
{
"epoch": 1.65,
"learning_rate": 0.0001,
"loss": 0.5899,
"step": 358
},
{
"epoch": 1.66,
"learning_rate": 0.0001,
"loss": 0.593,
"step": 359
},
{
"epoch": 1.66,
"learning_rate": 0.0001,
"loss": 0.6177,
"step": 360
},
{
"epoch": 1.66,
"learning_rate": 0.0001,
"loss": 0.6663,
"step": 361
},
{
"epoch": 1.67,
"learning_rate": 0.0001,
"loss": 0.7218,
"step": 362
},
{
"epoch": 1.67,
"learning_rate": 0.0001,
"loss": 0.6242,
"step": 363
},
{
"epoch": 1.68,
"learning_rate": 0.0001,
"loss": 0.6186,
"step": 364
},
{
"epoch": 1.68,
"learning_rate": 0.0001,
"loss": 0.6433,
"step": 365
},
{
"epoch": 1.69,
"learning_rate": 0.0001,
"loss": 0.7404,
"step": 366
},
{
"epoch": 1.69,
"learning_rate": 0.0001,
"loss": 0.6969,
"step": 367
},
{
"epoch": 1.7,
"learning_rate": 0.0001,
"loss": 0.7676,
"step": 368
},
{
"epoch": 1.7,
"learning_rate": 0.0001,
"loss": 0.6662,
"step": 369
},
{
"epoch": 1.71,
"learning_rate": 0.0001,
"loss": 0.6613,
"step": 370
},
{
"epoch": 1.71,
"learning_rate": 0.0001,
"loss": 0.6178,
"step": 371
},
{
"epoch": 1.72,
"learning_rate": 0.0001,
"loss": 0.7499,
"step": 372
},
{
"epoch": 1.72,
"learning_rate": 0.0001,
"loss": 0.6115,
"step": 373
},
{
"epoch": 1.72,
"learning_rate": 0.0001,
"loss": 0.6445,
"step": 374
},
{
"epoch": 1.73,
"learning_rate": 0.0001,
"loss": 0.642,
"step": 375
},
{
"epoch": 1.73,
"learning_rate": 0.0001,
"loss": 0.746,
"step": 376
},
{
"epoch": 1.74,
"learning_rate": 0.0001,
"loss": 0.7365,
"step": 377
},
{
"epoch": 1.74,
"learning_rate": 0.0001,
"loss": 0.6638,
"step": 378
},
{
"epoch": 1.75,
"learning_rate": 0.0001,
"loss": 0.6216,
"step": 379
},
{
"epoch": 1.75,
"learning_rate": 0.0001,
"loss": 0.6778,
"step": 380
},
{
"epoch": 1.76,
"learning_rate": 0.0001,
"loss": 0.5489,
"step": 381
},
{
"epoch": 1.76,
"learning_rate": 0.0001,
"loss": 0.7153,
"step": 382
},
{
"epoch": 1.77,
"learning_rate": 0.0001,
"loss": 0.7111,
"step": 383
},
{
"epoch": 1.77,
"learning_rate": 0.0001,
"loss": 0.7295,
"step": 384
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 0.5958,
"step": 385
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 0.6377,
"step": 386
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 0.8041,
"step": 387
},
{
"epoch": 1.79,
"learning_rate": 0.0001,
"loss": 0.7251,
"step": 388
},
{
"epoch": 1.79,
"learning_rate": 0.0001,
"loss": 0.7077,
"step": 389
},
{
"epoch": 1.8,
"learning_rate": 0.0001,
"loss": 0.7009,
"step": 390
},
{
"epoch": 1.8,
"learning_rate": 0.0001,
"loss": 0.6496,
"step": 391
},
{
"epoch": 1.81,
"learning_rate": 0.0001,
"loss": 0.6797,
"step": 392
},
{
"epoch": 1.81,
"learning_rate": 0.0001,
"loss": 0.7035,
"step": 393
},
{
"epoch": 1.82,
"learning_rate": 0.0001,
"loss": 0.654,
"step": 394
},
{
"epoch": 1.82,
"learning_rate": 0.0001,
"loss": 0.7618,
"step": 395
},
{
"epoch": 1.83,
"learning_rate": 0.0001,
"loss": 0.6227,
"step": 396
},
{
"epoch": 1.83,
"learning_rate": 0.0001,
"loss": 0.7315,
"step": 397
},
{
"epoch": 1.84,
"learning_rate": 0.0001,
"loss": 0.6905,
"step": 398
},
{
"epoch": 1.84,
"learning_rate": 0.0001,
"loss": 0.7865,
"step": 399
},
{
"epoch": 1.84,
"learning_rate": 0.0001,
"loss": 0.6356,
"step": 400
},
{
"epoch": 1.85,
"learning_rate": 0.0001,
"loss": 0.6958,
"step": 401
},
{
"epoch": 1.85,
"learning_rate": 0.0001,
"loss": 0.7246,
"step": 402
},
{
"epoch": 1.86,
"learning_rate": 0.0001,
"loss": 0.7012,
"step": 403
},
{
"epoch": 1.86,
"learning_rate": 0.0001,
"loss": 0.6993,
"step": 404
},
{
"epoch": 1.87,
"learning_rate": 0.0001,
"loss": 0.723,
"step": 405
},
{
"epoch": 1.87,
"learning_rate": 0.0001,
"loss": 0.636,
"step": 406
},
{
"epoch": 1.88,
"learning_rate": 0.0001,
"loss": 0.6851,
"step": 407
},
{
"epoch": 1.88,
"learning_rate": 0.0001,
"loss": 0.6449,
"step": 408
},
{
"epoch": 1.89,
"learning_rate": 0.0001,
"loss": 0.7362,
"step": 409
},
{
"epoch": 1.89,
"learning_rate": 0.0001,
"loss": 0.693,
"step": 410
},
{
"epoch": 1.9,
"learning_rate": 0.0001,
"loss": 0.6946,
"step": 411
},
{
"epoch": 1.9,
"learning_rate": 0.0001,
"loss": 0.5793,
"step": 412
},
{
"epoch": 1.9,
"learning_rate": 0.0001,
"loss": 0.7573,
"step": 413
},
{
"epoch": 1.91,
"learning_rate": 0.0001,
"loss": 0.6653,
"step": 414
},
{
"epoch": 1.91,
"learning_rate": 0.0001,
"loss": 0.7473,
"step": 415
},
{
"epoch": 1.92,
"learning_rate": 0.0001,
"loss": 0.7211,
"step": 416
},
{
"epoch": 1.92,
"learning_rate": 0.0001,
"loss": 0.5664,
"step": 417
},
{
"epoch": 1.93,
"learning_rate": 0.0001,
"loss": 0.5799,
"step": 418
},
{
"epoch": 1.93,
"learning_rate": 0.0001,
"loss": 0.6756,
"step": 419
},
{
"epoch": 1.94,
"learning_rate": 0.0001,
"loss": 0.6642,
"step": 420
},
{
"epoch": 1.94,
"learning_rate": 0.0001,
"loss": 0.5908,
"step": 421
},
{
"epoch": 1.95,
"learning_rate": 0.0001,
"loss": 0.6554,
"step": 422
},
{
"epoch": 1.95,
"learning_rate": 0.0001,
"loss": 0.6958,
"step": 423
},
{
"epoch": 1.96,
"learning_rate": 0.0001,
"loss": 0.7597,
"step": 424
},
{
"epoch": 1.96,
"learning_rate": 0.0001,
"loss": 0.7445,
"step": 425
},
{
"epoch": 1.96,
"learning_rate": 0.0001,
"loss": 0.5941,
"step": 426
},
{
"epoch": 1.97,
"learning_rate": 0.0001,
"loss": 0.7157,
"step": 427
},
{
"epoch": 1.97,
"learning_rate": 0.0001,
"loss": 0.6083,
"step": 428
},
{
"epoch": 1.98,
"learning_rate": 0.0001,
"loss": 0.6114,
"step": 429
},
{
"epoch": 1.98,
"learning_rate": 0.0001,
"loss": 0.6649,
"step": 430
},
{
"epoch": 1.99,
"learning_rate": 0.0001,
"loss": 0.5742,
"step": 431
},
{
"epoch": 1.99,
"learning_rate": 0.0001,
"loss": 0.6051,
"step": 432
},
{
"epoch": 2.0,
"learning_rate": 0.0001,
"loss": 0.6522,
"step": 433
},
{
"epoch": 2.0,
"learning_rate": 0.0001,
"loss": 0.7171,
"step": 434
},
{
"epoch": 2.01,
"learning_rate": 0.0001,
"loss": 0.5784,
"step": 435
},
{
"epoch": 2.01,
"learning_rate": 0.0001,
"loss": 0.6043,
"step": 436
},
{
"epoch": 2.01,
"learning_rate": 0.0001,
"loss": 0.6822,
"step": 437
},
{
"epoch": 2.02,
"learning_rate": 0.0001,
"loss": 0.5115,
"step": 438
},
{
"epoch": 2.02,
"learning_rate": 0.0001,
"loss": 0.5174,
"step": 439
},
{
"epoch": 2.03,
"learning_rate": 0.0001,
"loss": 0.5836,
"step": 440
},
{
"epoch": 2.03,
"learning_rate": 0.0001,
"loss": 0.4882,
"step": 441
},
{
"epoch": 2.04,
"learning_rate": 0.0001,
"loss": 0.5273,
"step": 442
},
{
"epoch": 2.04,
"learning_rate": 0.0001,
"loss": 0.4797,
"step": 443
},
{
"epoch": 2.05,
"learning_rate": 0.0001,
"loss": 0.6402,
"step": 444
},
{
"epoch": 2.05,
"learning_rate": 0.0001,
"loss": 0.5577,
"step": 445
},
{
"epoch": 2.06,
"learning_rate": 0.0001,
"loss": 0.6539,
"step": 446
},
{
"epoch": 2.06,
"learning_rate": 0.0001,
"loss": 0.5801,
"step": 447
},
{
"epoch": 2.07,
"learning_rate": 0.0001,
"loss": 0.5787,
"step": 448
},
{
"epoch": 2.07,
"learning_rate": 0.0001,
"loss": 0.4301,
"step": 449
},
{
"epoch": 2.07,
"learning_rate": 0.0001,
"loss": 0.5789,
"step": 450
},
{
"epoch": 2.08,
"learning_rate": 0.0001,
"loss": 0.5213,
"step": 451
},
{
"epoch": 2.08,
"learning_rate": 0.0001,
"loss": 0.5083,
"step": 452
},
{
"epoch": 2.09,
"learning_rate": 0.0001,
"loss": 0.5447,
"step": 453
},
{
"epoch": 2.09,
"learning_rate": 0.0001,
"loss": 0.4971,
"step": 454
},
{
"epoch": 2.1,
"learning_rate": 0.0001,
"loss": 0.5127,
"step": 455
},
{
"epoch": 2.1,
"learning_rate": 0.0001,
"loss": 0.5226,
"step": 456
},
{
"epoch": 2.11,
"learning_rate": 0.0001,
"loss": 0.5689,
"step": 457
},
{
"epoch": 2.11,
"learning_rate": 0.0001,
"loss": 0.5621,
"step": 458
},
{
"epoch": 2.12,
"learning_rate": 0.0001,
"loss": 0.5344,
"step": 459
},
{
"epoch": 2.12,
"learning_rate": 0.0001,
"loss": 0.5392,
"step": 460
},
{
"epoch": 2.13,
"learning_rate": 0.0001,
"loss": 0.5541,
"step": 461
},
{
"epoch": 2.13,
"learning_rate": 0.0001,
"loss": 0.5743,
"step": 462
},
{
"epoch": 2.13,
"learning_rate": 0.0001,
"loss": 0.5277,
"step": 463
},
{
"epoch": 2.14,
"learning_rate": 0.0001,
"loss": 0.6927,
"step": 464
},
{
"epoch": 2.14,
"learning_rate": 0.0001,
"loss": 0.61,
"step": 465
},
{
"epoch": 2.15,
"learning_rate": 0.0001,
"loss": 0.4522,
"step": 466
},
{
"epoch": 2.15,
"learning_rate": 0.0001,
"loss": 0.5356,
"step": 467
},
{
"epoch": 2.16,
"learning_rate": 0.0001,
"loss": 0.5526,
"step": 468
},
{
"epoch": 2.16,
"learning_rate": 0.0001,
"loss": 0.51,
"step": 469
},
{
"epoch": 2.17,
"learning_rate": 0.0001,
"loss": 0.5567,
"step": 470
},
{
"epoch": 2.17,
"learning_rate": 0.0001,
"loss": 0.5595,
"step": 471
},
{
"epoch": 2.18,
"learning_rate": 0.0001,
"loss": 0.4792,
"step": 472
},
{
"epoch": 2.18,
"learning_rate": 0.0001,
"loss": 0.582,
"step": 473
},
{
"epoch": 2.19,
"learning_rate": 0.0001,
"loss": 0.5474,
"step": 474
},
{
"epoch": 2.19,
"learning_rate": 0.0001,
"loss": 0.5337,
"step": 475
},
{
"epoch": 2.19,
"learning_rate": 0.0001,
"loss": 0.5361,
"step": 476
},
{
"epoch": 2.2,
"learning_rate": 0.0001,
"loss": 0.5598,
"step": 477
},
{
"epoch": 2.2,
"learning_rate": 0.0001,
"loss": 0.5874,
"step": 478
},
{
"epoch": 2.21,
"learning_rate": 0.0001,
"loss": 0.5207,
"step": 479
},
{
"epoch": 2.21,
"learning_rate": 0.0001,
"loss": 0.5333,
"step": 480
},
{
"epoch": 2.22,
"learning_rate": 0.0001,
"loss": 0.5637,
"step": 481
},
{
"epoch": 2.22,
"learning_rate": 0.0001,
"loss": 0.4818,
"step": 482
},
{
"epoch": 2.23,
"learning_rate": 0.0001,
"loss": 0.4904,
"step": 483
},
{
"epoch": 2.23,
"learning_rate": 0.0001,
"loss": 0.583,
"step": 484
},
{
"epoch": 2.24,
"learning_rate": 0.0001,
"loss": 0.5657,
"step": 485
},
{
"epoch": 2.24,
"learning_rate": 0.0001,
"loss": 0.613,
"step": 486
},
{
"epoch": 2.25,
"learning_rate": 0.0001,
"loss": 0.4933,
"step": 487
},
{
"epoch": 2.25,
"learning_rate": 0.0001,
"loss": 0.5251,
"step": 488
},
{
"epoch": 2.25,
"learning_rate": 0.0001,
"loss": 0.5978,
"step": 489
},
{
"epoch": 2.26,
"learning_rate": 0.0001,
"loss": 0.5938,
"step": 490
},
{
"epoch": 2.26,
"learning_rate": 0.0001,
"loss": 0.4796,
"step": 491
},
{
"epoch": 2.27,
"learning_rate": 0.0001,
"loss": 0.5186,
"step": 492
},
{
"epoch": 2.27,
"learning_rate": 0.0001,
"loss": 0.6017,
"step": 493
},
{
"epoch": 2.28,
"learning_rate": 0.0001,
"loss": 0.6055,
"step": 494
},
{
"epoch": 2.28,
"learning_rate": 0.0001,
"loss": 0.481,
"step": 495
},
{
"epoch": 2.29,
"learning_rate": 0.0001,
"loss": 0.6311,
"step": 496
},
{
"epoch": 2.29,
"learning_rate": 0.0001,
"loss": 0.6992,
"step": 497
},
{
"epoch": 2.3,
"learning_rate": 0.0001,
"loss": 0.6206,
"step": 498
},
{
"epoch": 2.3,
"learning_rate": 0.0001,
"loss": 0.5451,
"step": 499
},
{
"epoch": 2.31,
"learning_rate": 0.0001,
"loss": 0.548,
"step": 500
},
{
"epoch": 2.31,
"learning_rate": 0.0001,
"loss": 0.5582,
"step": 501
},
{
"epoch": 2.31,
"learning_rate": 0.0001,
"loss": 0.4262,
"step": 502
},
{
"epoch": 2.32,
"learning_rate": 0.0001,
"loss": 0.5329,
"step": 503
},
{
"epoch": 2.32,
"learning_rate": 0.0001,
"loss": 0.6002,
"step": 504
},
{
"epoch": 2.33,
"learning_rate": 0.0001,
"loss": 0.498,
"step": 505
},
{
"epoch": 2.33,
"learning_rate": 0.0001,
"loss": 0.6312,
"step": 506
},
{
"epoch": 2.34,
"learning_rate": 0.0001,
"loss": 0.5681,
"step": 507
},
{
"epoch": 2.34,
"learning_rate": 0.0001,
"loss": 0.6037,
"step": 508
},
{
"epoch": 2.35,
"learning_rate": 0.0001,
"loss": 0.5297,
"step": 509
},
{
"epoch": 2.35,
"learning_rate": 0.0001,
"loss": 0.603,
"step": 510
},
{
"epoch": 2.36,
"learning_rate": 0.0001,
"loss": 0.5382,
"step": 511
},
{
"epoch": 2.36,
"learning_rate": 0.0001,
"loss": 0.5958,
"step": 512
},
{
"epoch": 2.37,
"learning_rate": 0.0001,
"loss": 0.5855,
"step": 513
},
{
"epoch": 2.37,
"learning_rate": 0.0001,
"loss": 0.637,
"step": 514
},
{
"epoch": 2.37,
"learning_rate": 0.0001,
"loss": 0.5787,
"step": 515
},
{
"epoch": 2.38,
"learning_rate": 0.0001,
"loss": 0.5993,
"step": 516
},
{
"epoch": 2.38,
"learning_rate": 0.0001,
"loss": 0.5512,
"step": 517
},
{
"epoch": 2.39,
"learning_rate": 0.0001,
"loss": 0.6567,
"step": 518
},
{
"epoch": 2.39,
"learning_rate": 0.0001,
"loss": 0.519,
"step": 519
},
{
"epoch": 2.4,
"learning_rate": 0.0001,
"loss": 0.5498,
"step": 520
},
{
"epoch": 2.4,
"learning_rate": 0.0001,
"loss": 0.6337,
"step": 521
},
{
"epoch": 2.41,
"learning_rate": 0.0001,
"loss": 0.5809,
"step": 522
},
{
"epoch": 2.41,
"learning_rate": 0.0001,
"loss": 0.7162,
"step": 523
},
{
"epoch": 2.42,
"learning_rate": 0.0001,
"loss": 0.6183,
"step": 524
},
{
"epoch": 2.42,
"learning_rate": 0.0001,
"loss": 0.6151,
"step": 525
},
{
"epoch": 2.43,
"learning_rate": 0.0001,
"loss": 0.636,
"step": 526
},
{
"epoch": 2.43,
"learning_rate": 0.0001,
"loss": 0.6183,
"step": 527
},
{
"epoch": 2.43,
"learning_rate": 0.0001,
"loss": 0.5784,
"step": 528
},
{
"epoch": 2.44,
"learning_rate": 0.0001,
"loss": 0.6717,
"step": 529
},
{
"epoch": 2.44,
"learning_rate": 0.0001,
"loss": 0.5503,
"step": 530
},
{
"epoch": 2.45,
"learning_rate": 0.0001,
"loss": 0.6335,
"step": 531
},
{
"epoch": 2.45,
"learning_rate": 0.0001,
"loss": 0.6748,
"step": 532
},
{
"epoch": 2.46,
"learning_rate": 0.0001,
"loss": 0.5883,
"step": 533
},
{
"epoch": 2.46,
"learning_rate": 0.0001,
"loss": 0.607,
"step": 534
},
{
"epoch": 2.47,
"learning_rate": 0.0001,
"loss": 0.6416,
"step": 535
},
{
"epoch": 2.47,
"learning_rate": 0.0001,
"loss": 0.5203,
"step": 536
},
{
"epoch": 2.48,
"learning_rate": 0.0001,
"loss": 0.5925,
"step": 537
},
{
"epoch": 2.48,
"learning_rate": 0.0001,
"loss": 0.5951,
"step": 538
},
{
"epoch": 2.49,
"learning_rate": 0.0001,
"loss": 0.5141,
"step": 539
},
{
"epoch": 2.49,
"learning_rate": 0.0001,
"loss": 0.6534,
"step": 540
},
{
"epoch": 2.49,
"learning_rate": 0.0001,
"loss": 0.5258,
"step": 541
},
{
"epoch": 2.5,
"learning_rate": 0.0001,
"loss": 0.5685,
"step": 542
},
{
"epoch": 2.5,
"learning_rate": 0.0001,
"loss": 0.5615,
"step": 543
},
{
"epoch": 2.51,
"learning_rate": 0.0001,
"loss": 0.584,
"step": 544
},
{
"epoch": 2.51,
"learning_rate": 0.0001,
"loss": 0.5456,
"step": 545
},
{
"epoch": 2.52,
"learning_rate": 0.0001,
"loss": 0.5486,
"step": 546
},
{
"epoch": 2.52,
"learning_rate": 0.0001,
"loss": 0.5528,
"step": 547
},
{
"epoch": 2.53,
"learning_rate": 0.0001,
"loss": 0.6388,
"step": 548
},
{
"epoch": 2.53,
"learning_rate": 0.0001,
"loss": 0.6193,
"step": 549
},
{
"epoch": 2.54,
"learning_rate": 0.0001,
"loss": 0.5921,
"step": 550
},
{
"epoch": 2.54,
"learning_rate": 0.0001,
"loss": 0.6807,
"step": 551
},
{
"epoch": 2.55,
"learning_rate": 0.0001,
"loss": 0.6297,
"step": 552
},
{
"epoch": 2.55,
"learning_rate": 0.0001,
"loss": 0.4916,
"step": 553
},
{
"epoch": 2.55,
"learning_rate": 0.0001,
"loss": 0.5864,
"step": 554
},
{
"epoch": 2.56,
"learning_rate": 0.0001,
"loss": 0.523,
"step": 555
},
{
"epoch": 2.56,
"learning_rate": 0.0001,
"loss": 0.5867,
"step": 556
},
{
"epoch": 2.57,
"learning_rate": 0.0001,
"loss": 0.5952,
"step": 557
},
{
"epoch": 2.57,
"learning_rate": 0.0001,
"loss": 0.5503,
"step": 558
},
{
"epoch": 2.58,
"learning_rate": 0.0001,
"loss": 0.5736,
"step": 559
},
{
"epoch": 2.58,
"learning_rate": 0.0001,
"loss": 0.5896,
"step": 560
},
{
"epoch": 2.59,
"learning_rate": 0.0001,
"loss": 0.5927,
"step": 561
},
{
"epoch": 2.59,
"learning_rate": 0.0001,
"loss": 0.5783,
"step": 562
},
{
"epoch": 2.6,
"learning_rate": 0.0001,
"loss": 0.6549,
"step": 563
},
{
"epoch": 2.6,
"learning_rate": 0.0001,
"loss": 0.565,
"step": 564
},
{
"epoch": 2.61,
"learning_rate": 0.0001,
"loss": 0.502,
"step": 565
},
{
"epoch": 2.61,
"learning_rate": 0.0001,
"loss": 0.6322,
"step": 566
},
{
"epoch": 2.61,
"learning_rate": 0.0001,
"loss": 0.6772,
"step": 567
},
{
"epoch": 2.62,
"learning_rate": 0.0001,
"loss": 0.6054,
"step": 568
},
{
"epoch": 2.62,
"learning_rate": 0.0001,
"loss": 0.5686,
"step": 569
},
{
"epoch": 2.63,
"learning_rate": 0.0001,
"loss": 0.6374,
"step": 570
},
{
"epoch": 2.63,
"learning_rate": 0.0001,
"loss": 0.5653,
"step": 571
},
{
"epoch": 2.64,
"learning_rate": 0.0001,
"loss": 0.5637,
"step": 572
},
{
"epoch": 2.64,
"learning_rate": 0.0001,
"loss": 0.5493,
"step": 573
},
{
"epoch": 2.65,
"learning_rate": 0.0001,
"loss": 0.5929,
"step": 574
},
{
"epoch": 2.65,
"learning_rate": 0.0001,
"loss": 0.5497,
"step": 575
},
{
"epoch": 2.66,
"learning_rate": 0.0001,
"loss": 0.5704,
"step": 576
},
{
"epoch": 2.66,
"learning_rate": 0.0001,
"loss": 0.5515,
"step": 577
},
{
"epoch": 2.67,
"learning_rate": 0.0001,
"loss": 0.5366,
"step": 578
},
{
"epoch": 2.67,
"learning_rate": 0.0001,
"loss": 0.5751,
"step": 579
},
{
"epoch": 2.67,
"learning_rate": 0.0001,
"loss": 0.5327,
"step": 580
},
{
"epoch": 2.68,
"learning_rate": 0.0001,
"loss": 0.5508,
"step": 581
},
{
"epoch": 2.68,
"learning_rate": 0.0001,
"loss": 0.5768,
"step": 582
},
{
"epoch": 2.69,
"learning_rate": 0.0001,
"loss": 0.5747,
"step": 583
},
{
"epoch": 2.69,
"learning_rate": 0.0001,
"loss": 0.5094,
"step": 584
},
{
"epoch": 2.7,
"learning_rate": 0.0001,
"loss": 0.5311,
"step": 585
},
{
"epoch": 2.7,
"learning_rate": 0.0001,
"loss": 0.6218,
"step": 586
},
{
"epoch": 2.71,
"learning_rate": 0.0001,
"loss": 0.6563,
"step": 587
},
{
"epoch": 2.71,
"learning_rate": 0.0001,
"loss": 0.5566,
"step": 588
},
{
"epoch": 2.72,
"learning_rate": 0.0001,
"loss": 0.5497,
"step": 589
},
{
"epoch": 2.72,
"learning_rate": 0.0001,
"loss": 0.5101,
"step": 590
},
{
"epoch": 2.73,
"learning_rate": 0.0001,
"loss": 0.6579,
"step": 591
},
{
"epoch": 2.73,
"learning_rate": 0.0001,
"loss": 0.6058,
"step": 592
},
{
"epoch": 2.73,
"learning_rate": 0.0001,
"loss": 0.5393,
"step": 593
},
{
"epoch": 2.74,
"learning_rate": 0.0001,
"loss": 0.628,
"step": 594
},
{
"epoch": 2.74,
"learning_rate": 0.0001,
"loss": 0.5434,
"step": 595
},
{
"epoch": 2.75,
"learning_rate": 0.0001,
"loss": 0.608,
"step": 596
},
{
"epoch": 2.75,
"learning_rate": 0.0001,
"loss": 0.6001,
"step": 597
},
{
"epoch": 2.76,
"learning_rate": 0.0001,
"loss": 0.6087,
"step": 598
},
{
"epoch": 2.76,
"learning_rate": 0.0001,
"loss": 0.5888,
"step": 599
},
{
"epoch": 2.77,
"learning_rate": 0.0001,
"loss": 0.5842,
"step": 600
},
{
"epoch": 2.77,
"learning_rate": 0.0001,
"loss": 0.5113,
"step": 601
},
{
"epoch": 2.78,
"learning_rate": 0.0001,
"loss": 0.633,
"step": 602
},
{
"epoch": 2.78,
"learning_rate": 0.0001,
"loss": 0.621,
"step": 603
},
{
"epoch": 2.79,
"learning_rate": 0.0001,
"loss": 0.6824,
"step": 604
},
{
"epoch": 2.79,
"learning_rate": 0.0001,
"loss": 0.5712,
"step": 605
},
{
"epoch": 2.79,
"learning_rate": 0.0001,
"loss": 0.718,
"step": 606
},
{
"epoch": 2.8,
"learning_rate": 0.0001,
"loss": 0.5894,
"step": 607
},
{
"epoch": 2.8,
"learning_rate": 0.0001,
"loss": 0.6673,
"step": 608
},
{
"epoch": 2.81,
"learning_rate": 0.0001,
"loss": 0.5916,
"step": 609
},
{
"epoch": 2.81,
"learning_rate": 0.0001,
"loss": 0.5643,
"step": 610
},
{
"epoch": 2.82,
"learning_rate": 0.0001,
"loss": 0.6081,
"step": 611
},
{
"epoch": 2.82,
"learning_rate": 0.0001,
"loss": 0.5177,
"step": 612
},
{
"epoch": 2.83,
"learning_rate": 0.0001,
"loss": 0.5989,
"step": 613
},
{
"epoch": 2.83,
"learning_rate": 0.0001,
"loss": 0.6654,
"step": 614
},
{
"epoch": 2.84,
"learning_rate": 0.0001,
"loss": 0.5382,
"step": 615
},
{
"epoch": 2.84,
"learning_rate": 0.0001,
"loss": 0.5933,
"step": 616
},
{
"epoch": 2.84,
"learning_rate": 0.0001,
"loss": 0.5929,
"step": 617
},
{
"epoch": 2.85,
"learning_rate": 0.0001,
"loss": 0.6498,
"step": 618
},
{
"epoch": 2.85,
"learning_rate": 0.0001,
"loss": 0.5897,
"step": 619
},
{
"epoch": 2.86,
"learning_rate": 0.0001,
"loss": 0.544,
"step": 620
},
{
"epoch": 2.86,
"learning_rate": 0.0001,
"loss": 0.5002,
"step": 621
},
{
"epoch": 2.87,
"learning_rate": 0.0001,
"loss": 0.5259,
"step": 622
},
{
"epoch": 2.87,
"learning_rate": 0.0001,
"loss": 0.5501,
"step": 623
},
{
"epoch": 2.88,
"learning_rate": 0.0001,
"loss": 0.7178,
"step": 624
},
{
"epoch": 2.88,
"learning_rate": 0.0001,
"loss": 0.5832,
"step": 625
},
{
"epoch": 2.89,
"learning_rate": 0.0001,
"loss": 0.6234,
"step": 626
},
{
"epoch": 2.89,
"learning_rate": 0.0001,
"loss": 0.5878,
"step": 627
},
{
"epoch": 2.9,
"learning_rate": 0.0001,
"loss": 0.6238,
"step": 628
},
{
"epoch": 2.9,
"learning_rate": 0.0001,
"loss": 0.6326,
"step": 629
},
{
"epoch": 2.9,
"learning_rate": 0.0001,
"loss": 0.6848,
"step": 630
},
{
"epoch": 2.91,
"learning_rate": 0.0001,
"loss": 0.6201,
"step": 631
},
{
"epoch": 2.91,
"learning_rate": 0.0001,
"loss": 0.6097,
"step": 632
},
{
"epoch": 2.92,
"learning_rate": 0.0001,
"loss": 0.4877,
"step": 633
},
{
"epoch": 2.92,
"learning_rate": 0.0001,
"loss": 0.5574,
"step": 634
},
{
"epoch": 2.93,
"learning_rate": 0.0001,
"loss": 0.563,
"step": 635
},
{
"epoch": 2.93,
"learning_rate": 0.0001,
"loss": 0.7033,
"step": 636
},
{
"epoch": 2.94,
"learning_rate": 0.0001,
"loss": 0.605,
"step": 637
},
{
"epoch": 2.94,
"learning_rate": 0.0001,
"loss": 0.6107,
"step": 638
},
{
"epoch": 2.95,
"learning_rate": 0.0001,
"loss": 0.5807,
"step": 639
},
{
"epoch": 2.95,
"learning_rate": 0.0001,
"loss": 0.6146,
"step": 640
},
{
"epoch": 2.96,
"learning_rate": 0.0001,
"loss": 0.6576,
"step": 641
},
{
"epoch": 2.96,
"learning_rate": 0.0001,
"loss": 0.5242,
"step": 642
},
{
"epoch": 2.96,
"learning_rate": 0.0001,
"loss": 0.6723,
"step": 643
},
{
"epoch": 2.97,
"learning_rate": 0.0001,
"loss": 0.5884,
"step": 644
},
{
"epoch": 2.97,
"learning_rate": 0.0001,
"loss": 0.6287,
"step": 645
},
{
"epoch": 2.98,
"learning_rate": 0.0001,
"loss": 0.5493,
"step": 646
},
{
"epoch": 2.98,
"learning_rate": 0.0001,
"loss": 0.6382,
"step": 647
},
{
"epoch": 2.99,
"learning_rate": 0.0001,
"loss": 0.5993,
"step": 648
},
{
"epoch": 2.99,
"learning_rate": 0.0001,
"loss": 0.5698,
"step": 649
},
{
"epoch": 3.0,
"learning_rate": 0.0001,
"loss": 0.5211,
"step": 650
},
{
"epoch": 3.0,
"learning_rate": 0.0001,
"loss": 0.5188,
"step": 651
},
{
"epoch": 3.01,
"learning_rate": 0.0001,
"loss": 0.491,
"step": 652
},
{
"epoch": 3.01,
"learning_rate": 0.0001,
"loss": 0.5423,
"step": 653
},
{
"epoch": 3.02,
"learning_rate": 0.0001,
"loss": 0.476,
"step": 654
},
{
"epoch": 3.02,
"learning_rate": 0.0001,
"loss": 0.4751,
"step": 655
},
{
"epoch": 3.02,
"learning_rate": 0.0001,
"loss": 0.5192,
"step": 656
},
{
"epoch": 3.03,
"learning_rate": 0.0001,
"loss": 0.4827,
"step": 657
},
{
"epoch": 3.03,
"learning_rate": 0.0001,
"loss": 0.4959,
"step": 658
},
{
"epoch": 3.04,
"learning_rate": 0.0001,
"loss": 0.5321,
"step": 659
},
{
"epoch": 3.04,
"learning_rate": 0.0001,
"loss": 0.4667,
"step": 660
},
{
"epoch": 3.05,
"learning_rate": 0.0001,
"loss": 0.4873,
"step": 661
},
{
"epoch": 3.05,
"learning_rate": 0.0001,
"loss": 0.457,
"step": 662
},
{
"epoch": 3.06,
"learning_rate": 0.0001,
"loss": 0.4783,
"step": 663
},
{
"epoch": 3.06,
"learning_rate": 0.0001,
"loss": 0.5017,
"step": 664
},
{
"epoch": 3.07,
"learning_rate": 0.0001,
"loss": 0.4006,
"step": 665
},
{
"epoch": 3.07,
"learning_rate": 0.0001,
"loss": 0.472,
"step": 666
},
{
"epoch": 3.08,
"learning_rate": 0.0001,
"loss": 0.4481,
"step": 667
},
{
"epoch": 3.08,
"learning_rate": 0.0001,
"loss": 0.4189,
"step": 668
},
{
"epoch": 3.08,
"learning_rate": 0.0001,
"loss": 0.5147,
"step": 669
},
{
"epoch": 3.09,
"learning_rate": 0.0001,
"loss": 0.4312,
"step": 670
},
{
"epoch": 3.09,
"learning_rate": 0.0001,
"loss": 0.47,
"step": 671
},
{
"epoch": 3.1,
"learning_rate": 0.0001,
"loss": 0.4682,
"step": 672
},
{
"epoch": 3.1,
"learning_rate": 0.0001,
"loss": 0.4788,
"step": 673
},
{
"epoch": 3.11,
"learning_rate": 0.0001,
"loss": 0.4698,
"step": 674
},
{
"epoch": 3.11,
"learning_rate": 0.0001,
"loss": 0.4365,
"step": 675
},
{
"epoch": 3.12,
"learning_rate": 0.0001,
"loss": 0.4804,
"step": 676
},
{
"epoch": 3.12,
"learning_rate": 0.0001,
"loss": 0.4591,
"step": 677
},
{
"epoch": 3.13,
"learning_rate": 0.0001,
"loss": 0.4487,
"step": 678
},
{
"epoch": 3.13,
"learning_rate": 0.0001,
"loss": 0.4528,
"step": 679
},
{
"epoch": 3.14,
"learning_rate": 0.0001,
"loss": 0.4959,
"step": 680
},
{
"epoch": 3.14,
"learning_rate": 0.0001,
"loss": 0.5261,
"step": 681
},
{
"epoch": 3.14,
"learning_rate": 0.0001,
"loss": 0.4893,
"step": 682
},
{
"epoch": 3.15,
"learning_rate": 0.0001,
"loss": 0.4648,
"step": 683
},
{
"epoch": 3.15,
"learning_rate": 0.0001,
"loss": 0.5435,
"step": 684
},
{
"epoch": 3.16,
"learning_rate": 0.0001,
"loss": 0.4874,
"step": 685
},
{
"epoch": 3.16,
"learning_rate": 0.0001,
"loss": 0.4305,
"step": 686
},
{
"epoch": 3.17,
"learning_rate": 0.0001,
"loss": 0.4885,
"step": 687
},
{
"epoch": 3.17,
"learning_rate": 0.0001,
"loss": 0.4383,
"step": 688
},
{
"epoch": 3.18,
"learning_rate": 0.0001,
"loss": 0.538,
"step": 689
},
{
"epoch": 3.18,
"learning_rate": 0.0001,
"loss": 0.4431,
"step": 690
},
{
"epoch": 3.19,
"learning_rate": 0.0001,
"loss": 0.508,
"step": 691
},
{
"epoch": 3.19,
"learning_rate": 0.0001,
"loss": 0.4146,
"step": 692
},
{
"epoch": 3.2,
"learning_rate": 0.0001,
"loss": 0.4325,
"step": 693
},
{
"epoch": 3.2,
"learning_rate": 0.0001,
"loss": 0.5244,
"step": 694
},
{
"epoch": 3.2,
"learning_rate": 0.0001,
"loss": 0.4835,
"step": 695
},
{
"epoch": 3.21,
"learning_rate": 0.0001,
"loss": 0.5351,
"step": 696
},
{
"epoch": 3.21,
"learning_rate": 0.0001,
"loss": 0.4245,
"step": 697
},
{
"epoch": 3.22,
"learning_rate": 0.0001,
"loss": 0.5557,
"step": 698
},
{
"epoch": 3.22,
"learning_rate": 0.0001,
"loss": 0.4517,
"step": 699
},
{
"epoch": 3.23,
"learning_rate": 0.0001,
"loss": 0.4212,
"step": 700
},
{
"epoch": 3.23,
"learning_rate": 0.0001,
"loss": 0.5004,
"step": 701
},
{
"epoch": 3.24,
"learning_rate": 0.0001,
"loss": 0.5622,
"step": 702
},
{
"epoch": 3.24,
"learning_rate": 0.0001,
"loss": 0.5129,
"step": 703
},
{
"epoch": 3.25,
"learning_rate": 0.0001,
"loss": 0.4876,
"step": 704
},
{
"epoch": 3.25,
"learning_rate": 0.0001,
"loss": 0.4576,
"step": 705
},
{
"epoch": 3.26,
"learning_rate": 0.0001,
"loss": 0.5873,
"step": 706
},
{
"epoch": 3.26,
"learning_rate": 0.0001,
"loss": 0.5452,
"step": 707
},
{
"epoch": 3.26,
"learning_rate": 0.0001,
"loss": 0.4409,
"step": 708
},
{
"epoch": 3.27,
"learning_rate": 0.0001,
"loss": 0.456,
"step": 709
},
{
"epoch": 3.27,
"learning_rate": 0.0001,
"loss": 0.4994,
"step": 710
},
{
"epoch": 3.28,
"learning_rate": 0.0001,
"loss": 0.4909,
"step": 711
},
{
"epoch": 3.28,
"learning_rate": 0.0001,
"loss": 0.4766,
"step": 712
},
{
"epoch": 3.29,
"learning_rate": 0.0001,
"loss": 0.5597,
"step": 713
},
{
"epoch": 3.29,
"learning_rate": 0.0001,
"loss": 0.4261,
"step": 714
},
{
"epoch": 3.3,
"learning_rate": 0.0001,
"loss": 0.5078,
"step": 715
},
{
"epoch": 3.3,
"learning_rate": 0.0001,
"loss": 0.5292,
"step": 716
},
{
"epoch": 3.31,
"learning_rate": 0.0001,
"loss": 0.56,
"step": 717
},
{
"epoch": 3.31,
"learning_rate": 0.0001,
"loss": 0.514,
"step": 718
},
{
"epoch": 3.32,
"learning_rate": 0.0001,
"loss": 0.4874,
"step": 719
},
{
"epoch": 3.32,
"learning_rate": 0.0001,
"loss": 0.5423,
"step": 720
},
{
"epoch": 3.32,
"learning_rate": 0.0001,
"loss": 0.5329,
"step": 721
},
{
"epoch": 3.33,
"learning_rate": 0.0001,
"loss": 0.4387,
"step": 722
},
{
"epoch": 3.33,
"learning_rate": 0.0001,
"loss": 0.4976,
"step": 723
},
{
"epoch": 3.34,
"learning_rate": 0.0001,
"loss": 0.485,
"step": 724
},
{
"epoch": 3.34,
"learning_rate": 0.0001,
"loss": 0.5222,
"step": 725
},
{
"epoch": 3.35,
"learning_rate": 0.0001,
"loss": 0.513,
"step": 726
},
{
"epoch": 3.35,
"learning_rate": 0.0001,
"loss": 0.3953,
"step": 727
},
{
"epoch": 3.36,
"learning_rate": 0.0001,
"loss": 0.4565,
"step": 728
},
{
"epoch": 3.36,
"learning_rate": 0.0001,
"loss": 0.5427,
"step": 729
},
{
"epoch": 3.37,
"learning_rate": 0.0001,
"loss": 0.5467,
"step": 730
},
{
"epoch": 3.37,
"learning_rate": 0.0001,
"loss": 0.5211,
"step": 731
},
{
"epoch": 3.38,
"learning_rate": 0.0001,
"loss": 0.4616,
"step": 732
},
{
"epoch": 3.38,
"learning_rate": 0.0001,
"loss": 0.5719,
"step": 733
},
{
"epoch": 3.38,
"learning_rate": 0.0001,
"loss": 0.5017,
"step": 734
},
{
"epoch": 3.39,
"learning_rate": 0.0001,
"loss": 0.5065,
"step": 735
},
{
"epoch": 3.39,
"learning_rate": 0.0001,
"loss": 0.465,
"step": 736
},
{
"epoch": 3.4,
"learning_rate": 0.0001,
"loss": 0.5661,
"step": 737
},
{
"epoch": 3.4,
"learning_rate": 0.0001,
"loss": 0.5142,
"step": 738
},
{
"epoch": 3.41,
"learning_rate": 0.0001,
"loss": 0.5288,
"step": 739
},
{
"epoch": 3.41,
"learning_rate": 0.0001,
"loss": 0.5895,
"step": 740
},
{
"epoch": 3.42,
"learning_rate": 0.0001,
"loss": 0.469,
"step": 741
},
{
"epoch": 3.42,
"learning_rate": 0.0001,
"loss": 0.5326,
"step": 742
},
{
"epoch": 3.43,
"learning_rate": 0.0001,
"loss": 0.525,
"step": 743
},
{
"epoch": 3.43,
"learning_rate": 0.0001,
"loss": 0.4647,
"step": 744
},
{
"epoch": 3.44,
"learning_rate": 0.0001,
"loss": 0.5065,
"step": 745
},
{
"epoch": 3.44,
"learning_rate": 0.0001,
"loss": 0.4653,
"step": 746
},
{
"epoch": 3.44,
"learning_rate": 0.0001,
"loss": 0.5207,
"step": 747
},
{
"epoch": 3.45,
"learning_rate": 0.0001,
"loss": 0.4627,
"step": 748
},
{
"epoch": 3.45,
"learning_rate": 0.0001,
"loss": 0.509,
"step": 749
},
{
"epoch": 3.46,
"learning_rate": 0.0001,
"loss": 0.6253,
"step": 750
},
{
"epoch": 3.46,
"learning_rate": 0.0001,
"loss": 0.5472,
"step": 751
},
{
"epoch": 3.47,
"learning_rate": 0.0001,
"loss": 0.5021,
"step": 752
},
{
"epoch": 3.47,
"learning_rate": 0.0001,
"loss": 0.4551,
"step": 753
},
{
"epoch": 3.48,
"learning_rate": 0.0001,
"loss": 0.5597,
"step": 754
},
{
"epoch": 3.48,
"learning_rate": 0.0001,
"loss": 0.5121,
"step": 755
},
{
"epoch": 3.49,
"learning_rate": 0.0001,
"loss": 0.5333,
"step": 756
},
{
"epoch": 3.49,
"learning_rate": 0.0001,
"loss": 0.5087,
"step": 757
},
{
"epoch": 3.5,
"learning_rate": 0.0001,
"loss": 0.6004,
"step": 758
},
{
"epoch": 3.5,
"learning_rate": 0.0001,
"loss": 0.444,
"step": 759
},
{
"epoch": 3.5,
"learning_rate": 0.0001,
"loss": 0.5174,
"step": 760
},
{
"epoch": 3.51,
"learning_rate": 0.0001,
"loss": 0.5541,
"step": 761
},
{
"epoch": 3.51,
"learning_rate": 0.0001,
"loss": 0.4545,
"step": 762
},
{
"epoch": 3.52,
"learning_rate": 0.0001,
"loss": 0.4762,
"step": 763
},
{
"epoch": 3.52,
"learning_rate": 0.0001,
"loss": 0.4861,
"step": 764
},
{
"epoch": 3.53,
"learning_rate": 0.0001,
"loss": 0.4846,
"step": 765
},
{
"epoch": 3.53,
"learning_rate": 0.0001,
"loss": 0.4226,
"step": 766
},
{
"epoch": 3.54,
"learning_rate": 0.0001,
"loss": 0.4961,
"step": 767
},
{
"epoch": 3.54,
"learning_rate": 0.0001,
"loss": 0.5681,
"step": 768
},
{
"epoch": 3.55,
"learning_rate": 0.0001,
"loss": 0.4447,
"step": 769
},
{
"epoch": 3.55,
"learning_rate": 0.0001,
"loss": 0.5785,
"step": 770
},
{
"epoch": 3.56,
"learning_rate": 0.0001,
"loss": 0.4368,
"step": 771
},
{
"epoch": 3.56,
"learning_rate": 0.0001,
"loss": 0.5584,
"step": 772
},
{
"epoch": 3.56,
"learning_rate": 0.0001,
"loss": 0.5499,
"step": 773
},
{
"epoch": 3.57,
"learning_rate": 0.0001,
"loss": 0.4927,
"step": 774
},
{
"epoch": 3.57,
"learning_rate": 0.0001,
"loss": 0.4541,
"step": 775
},
{
"epoch": 3.58,
"learning_rate": 0.0001,
"loss": 0.5428,
"step": 776
},
{
"epoch": 3.58,
"learning_rate": 0.0001,
"loss": 0.4988,
"step": 777
},
{
"epoch": 3.59,
"learning_rate": 0.0001,
"loss": 0.5349,
"step": 778
},
{
"epoch": 3.59,
"learning_rate": 0.0001,
"loss": 0.5812,
"step": 779
},
{
"epoch": 3.6,
"learning_rate": 0.0001,
"loss": 0.5687,
"step": 780
},
{
"epoch": 3.6,
"learning_rate": 0.0001,
"loss": 0.5687,
"step": 781
},
{
"epoch": 3.61,
"learning_rate": 0.0001,
"loss": 0.4678,
"step": 782
},
{
"epoch": 3.61,
"learning_rate": 0.0001,
"loss": 0.5327,
"step": 783
},
{
"epoch": 3.61,
"learning_rate": 0.0001,
"loss": 0.5786,
"step": 784
},
{
"epoch": 3.62,
"learning_rate": 0.0001,
"loss": 0.5559,
"step": 785
},
{
"epoch": 3.62,
"learning_rate": 0.0001,
"loss": 0.5963,
"step": 786
},
{
"epoch": 3.63,
"learning_rate": 0.0001,
"loss": 0.5076,
"step": 787
},
{
"epoch": 3.63,
"learning_rate": 0.0001,
"loss": 0.5192,
"step": 788
},
{
"epoch": 3.64,
"learning_rate": 0.0001,
"loss": 0.4855,
"step": 789
},
{
"epoch": 3.64,
"learning_rate": 0.0001,
"loss": 0.5255,
"step": 790
},
{
"epoch": 3.65,
"learning_rate": 0.0001,
"loss": 0.5554,
"step": 791
},
{
"epoch": 3.65,
"learning_rate": 0.0001,
"loss": 0.5336,
"step": 792
},
{
"epoch": 3.66,
"learning_rate": 0.0001,
"loss": 0.4838,
"step": 793
},
{
"epoch": 3.66,
"learning_rate": 0.0001,
"loss": 0.597,
"step": 794
},
{
"epoch": 3.67,
"learning_rate": 0.0001,
"loss": 0.5989,
"step": 795
},
{
"epoch": 3.67,
"learning_rate": 0.0001,
"loss": 0.5069,
"step": 796
},
{
"epoch": 3.67,
"learning_rate": 0.0001,
"loss": 0.486,
"step": 797
},
{
"epoch": 3.68,
"learning_rate": 0.0001,
"loss": 0.4808,
"step": 798
},
{
"epoch": 3.68,
"learning_rate": 0.0001,
"loss": 0.492,
"step": 799
},
{
"epoch": 3.69,
"learning_rate": 0.0001,
"loss": 0.6082,
"step": 800
},
{
"epoch": 3.69,
"learning_rate": 0.0001,
"loss": 0.4829,
"step": 801
},
{
"epoch": 3.7,
"learning_rate": 0.0001,
"loss": 0.493,
"step": 802
},
{
"epoch": 3.7,
"learning_rate": 0.0001,
"loss": 0.5048,
"step": 803
},
{
"epoch": 3.71,
"learning_rate": 0.0001,
"loss": 0.5452,
"step": 804
},
{
"epoch": 3.71,
"learning_rate": 0.0001,
"loss": 0.5268,
"step": 805
},
{
"epoch": 3.72,
"learning_rate": 0.0001,
"loss": 0.45,
"step": 806
},
{
"epoch": 3.72,
"learning_rate": 0.0001,
"loss": 0.5527,
"step": 807
},
{
"epoch": 3.73,
"learning_rate": 0.0001,
"loss": 0.5064,
"step": 808
},
{
"epoch": 3.73,
"learning_rate": 0.0001,
"loss": 0.537,
"step": 809
},
{
"epoch": 3.73,
"learning_rate": 0.0001,
"loss": 0.5325,
"step": 810
},
{
"epoch": 3.74,
"learning_rate": 0.0001,
"loss": 0.5779,
"step": 811
},
{
"epoch": 3.74,
"learning_rate": 0.0001,
"loss": 0.4395,
"step": 812
},
{
"epoch": 3.75,
"learning_rate": 0.0001,
"loss": 0.5951,
"step": 813
},
{
"epoch": 3.75,
"learning_rate": 0.0001,
"loss": 0.5785,
"step": 814
},
{
"epoch": 3.76,
"learning_rate": 0.0001,
"loss": 0.5703,
"step": 815
},
{
"epoch": 3.76,
"learning_rate": 0.0001,
"loss": 0.5706,
"step": 816
},
{
"epoch": 3.77,
"learning_rate": 0.0001,
"loss": 0.4387,
"step": 817
},
{
"epoch": 3.77,
"learning_rate": 0.0001,
"loss": 0.6215,
"step": 818
},
{
"epoch": 3.78,
"learning_rate": 0.0001,
"loss": 0.5701,
"step": 819
},
{
"epoch": 3.78,
"learning_rate": 0.0001,
"loss": 0.5087,
"step": 820
},
{
"epoch": 3.79,
"learning_rate": 0.0001,
"loss": 0.5329,
"step": 821
},
{
"epoch": 3.79,
"learning_rate": 0.0001,
"loss": 0.5446,
"step": 822
},
{
"epoch": 3.79,
"learning_rate": 0.0001,
"loss": 0.5629,
"step": 823
},
{
"epoch": 3.8,
"learning_rate": 0.0001,
"loss": 0.5667,
"step": 824
},
{
"epoch": 3.8,
"learning_rate": 0.0001,
"loss": 0.4845,
"step": 825
},
{
"epoch": 3.81,
"learning_rate": 0.0001,
"loss": 0.5186,
"step": 826
},
{
"epoch": 3.81,
"learning_rate": 0.0001,
"loss": 0.439,
"step": 827
},
{
"epoch": 3.82,
"learning_rate": 0.0001,
"loss": 0.4773,
"step": 828
},
{
"epoch": 3.82,
"learning_rate": 0.0001,
"loss": 0.5428,
"step": 829
},
{
"epoch": 3.83,
"learning_rate": 0.0001,
"loss": 0.4654,
"step": 830
},
{
"epoch": 3.83,
"learning_rate": 0.0001,
"loss": 0.517,
"step": 831
},
{
"epoch": 3.84,
"learning_rate": 0.0001,
"loss": 0.4865,
"step": 832
},
{
"epoch": 3.84,
"learning_rate": 0.0001,
"loss": 0.5061,
"step": 833
},
{
"epoch": 3.85,
"learning_rate": 0.0001,
"loss": 0.5156,
"step": 834
},
{
"epoch": 3.85,
"learning_rate": 0.0001,
"loss": 0.5497,
"step": 835
},
{
"epoch": 3.85,
"learning_rate": 0.0001,
"loss": 0.5321,
"step": 836
},
{
"epoch": 3.86,
"learning_rate": 0.0001,
"loss": 0.5402,
"step": 837
},
{
"epoch": 3.86,
"learning_rate": 0.0001,
"loss": 0.4953,
"step": 838
},
{
"epoch": 3.87,
"learning_rate": 0.0001,
"loss": 0.5019,
"step": 839
},
{
"epoch": 3.87,
"learning_rate": 0.0001,
"loss": 0.6373,
"step": 840
},
{
"epoch": 3.88,
"learning_rate": 0.0001,
"loss": 0.5,
"step": 841
},
{
"epoch": 3.88,
"learning_rate": 0.0001,
"loss": 0.6032,
"step": 842
},
{
"epoch": 3.89,
"learning_rate": 0.0001,
"loss": 0.5724,
"step": 843
},
{
"epoch": 3.89,
"learning_rate": 0.0001,
"loss": 0.5303,
"step": 844
},
{
"epoch": 3.9,
"learning_rate": 0.0001,
"loss": 0.5221,
"step": 845
},
{
"epoch": 3.9,
"learning_rate": 0.0001,
"loss": 0.537,
"step": 846
},
{
"epoch": 3.91,
"learning_rate": 0.0001,
"loss": 0.5188,
"step": 847
},
{
"epoch": 3.91,
"learning_rate": 0.0001,
"loss": 0.5642,
"step": 848
},
{
"epoch": 3.91,
"learning_rate": 0.0001,
"loss": 0.4661,
"step": 849
},
{
"epoch": 3.92,
"learning_rate": 0.0001,
"loss": 0.5169,
"step": 850
},
{
"epoch": 3.92,
"learning_rate": 0.0001,
"loss": 0.5458,
"step": 851
},
{
"epoch": 3.93,
"learning_rate": 0.0001,
"loss": 0.5364,
"step": 852
},
{
"epoch": 3.93,
"learning_rate": 0.0001,
"loss": 0.5428,
"step": 853
},
{
"epoch": 3.94,
"learning_rate": 0.0001,
"loss": 0.4755,
"step": 854
},
{
"epoch": 3.94,
"learning_rate": 0.0001,
"loss": 0.5226,
"step": 855
},
{
"epoch": 3.95,
"learning_rate": 0.0001,
"loss": 0.6281,
"step": 856
},
{
"epoch": 3.95,
"learning_rate": 0.0001,
"loss": 0.5396,
"step": 857
},
{
"epoch": 3.96,
"learning_rate": 0.0001,
"loss": 0.5287,
"step": 858
},
{
"epoch": 3.96,
"learning_rate": 0.0001,
"loss": 0.5032,
"step": 859
},
{
"epoch": 3.97,
"learning_rate": 0.0001,
"loss": 0.4741,
"step": 860
},
{
"epoch": 3.97,
"learning_rate": 0.0001,
"loss": 0.5515,
"step": 861
},
{
"epoch": 3.97,
"learning_rate": 0.0001,
"loss": 0.5167,
"step": 862
},
{
"epoch": 3.98,
"learning_rate": 0.0001,
"loss": 0.5864,
"step": 863
},
{
"epoch": 3.98,
"learning_rate": 0.0001,
"loss": 0.5506,
"step": 864
},
{
"epoch": 3.99,
"learning_rate": 0.0001,
"loss": 0.5919,
"step": 865
},
{
"epoch": 3.99,
"learning_rate": 0.0001,
"loss": 0.5208,
"step": 866
},
{
"epoch": 4.0,
"learning_rate": 0.0001,
"loss": 0.5448,
"step": 867
},
{
"epoch": 4.0,
"learning_rate": 0.0001,
"loss": 0.4156,
"step": 868
},
{
"epoch": 4.01,
"learning_rate": 0.0001,
"loss": 0.3873,
"step": 869
},
{
"epoch": 4.01,
"learning_rate": 0.0001,
"loss": 0.4549,
"step": 870
},
{
"epoch": 4.02,
"learning_rate": 0.0001,
"loss": 0.3804,
"step": 871
},
{
"epoch": 4.02,
"learning_rate": 0.0001,
"loss": 0.4467,
"step": 872
},
{
"epoch": 4.03,
"learning_rate": 0.0001,
"loss": 0.3893,
"step": 873
},
{
"epoch": 4.03,
"learning_rate": 0.0001,
"loss": 0.4394,
"step": 874
},
{
"epoch": 4.03,
"learning_rate": 0.0001,
"loss": 0.5049,
"step": 875
},
{
"epoch": 4.04,
"learning_rate": 0.0001,
"loss": 0.4286,
"step": 876
},
{
"epoch": 4.04,
"learning_rate": 0.0001,
"loss": 0.4518,
"step": 877
},
{
"epoch": 4.05,
"learning_rate": 0.0001,
"loss": 0.4385,
"step": 878
},
{
"epoch": 4.05,
"learning_rate": 0.0001,
"loss": 0.4175,
"step": 879
},
{
"epoch": 4.06,
"learning_rate": 0.0001,
"loss": 0.4459,
"step": 880
},
{
"epoch": 4.06,
"learning_rate": 0.0001,
"loss": 0.4225,
"step": 881
},
{
"epoch": 4.07,
"learning_rate": 0.0001,
"loss": 0.4528,
"step": 882
},
{
"epoch": 4.07,
"learning_rate": 0.0001,
"loss": 0.4547,
"step": 883
},
{
"epoch": 4.08,
"learning_rate": 0.0001,
"loss": 0.413,
"step": 884
},
{
"epoch": 4.08,
"learning_rate": 0.0001,
"loss": 0.4415,
"step": 885
},
{
"epoch": 4.09,
"learning_rate": 0.0001,
"loss": 0.4858,
"step": 886
},
{
"epoch": 4.09,
"learning_rate": 0.0001,
"loss": 0.4178,
"step": 887
},
{
"epoch": 4.09,
"learning_rate": 0.0001,
"loss": 0.4465,
"step": 888
},
{
"epoch": 4.1,
"learning_rate": 0.0001,
"loss": 0.3692,
"step": 889
},
{
"epoch": 4.1,
"learning_rate": 0.0001,
"loss": 0.4847,
"step": 890
},
{
"epoch": 4.11,
"learning_rate": 0.0001,
"loss": 0.4554,
"step": 891
},
{
"epoch": 4.11,
"learning_rate": 0.0001,
"loss": 0.4192,
"step": 892
},
{
"epoch": 4.12,
"learning_rate": 0.0001,
"loss": 0.4471,
"step": 893
},
{
"epoch": 4.12,
"learning_rate": 0.0001,
"loss": 0.4413,
"step": 894
},
{
"epoch": 4.13,
"learning_rate": 0.0001,
"loss": 0.442,
"step": 895
},
{
"epoch": 4.13,
"learning_rate": 0.0001,
"loss": 0.4456,
"step": 896
},
{
"epoch": 4.14,
"learning_rate": 0.0001,
"loss": 0.4206,
"step": 897
},
{
"epoch": 4.14,
"learning_rate": 0.0001,
"loss": 0.4292,
"step": 898
},
{
"epoch": 4.15,
"learning_rate": 0.0001,
"loss": 0.4032,
"step": 899
},
{
"epoch": 4.15,
"learning_rate": 0.0001,
"loss": 0.4402,
"step": 900
},
{
"epoch": 4.15,
"learning_rate": 0.0001,
"loss": 0.4197,
"step": 901
},
{
"epoch": 4.16,
"learning_rate": 0.0001,
"loss": 0.4255,
"step": 902
},
{
"epoch": 4.16,
"learning_rate": 0.0001,
"loss": 0.4459,
"step": 903
},
{
"epoch": 4.17,
"learning_rate": 0.0001,
"loss": 0.4864,
"step": 904
},
{
"epoch": 4.17,
"learning_rate": 0.0001,
"loss": 0.4416,
"step": 905
},
{
"epoch": 4.18,
"learning_rate": 0.0001,
"loss": 0.4329,
"step": 906
},
{
"epoch": 4.18,
"learning_rate": 0.0001,
"loss": 0.4928,
"step": 907
},
{
"epoch": 4.19,
"learning_rate": 0.0001,
"loss": 0.4636,
"step": 908
},
{
"epoch": 4.19,
"learning_rate": 0.0001,
"loss": 0.45,
"step": 909
},
{
"epoch": 4.2,
"learning_rate": 0.0001,
"loss": 0.4461,
"step": 910
},
{
"epoch": 4.2,
"learning_rate": 0.0001,
"loss": 0.3916,
"step": 911
},
{
"epoch": 4.21,
"learning_rate": 0.0001,
"loss": 0.3841,
"step": 912
},
{
"epoch": 4.21,
"learning_rate": 0.0001,
"loss": 0.3894,
"step": 913
},
{
"epoch": 4.21,
"learning_rate": 0.0001,
"loss": 0.4272,
"step": 914
},
{
"epoch": 4.22,
"learning_rate": 0.0001,
"loss": 0.4377,
"step": 915
},
{
"epoch": 4.22,
"learning_rate": 0.0001,
"loss": 0.4712,
"step": 916
},
{
"epoch": 4.23,
"learning_rate": 0.0001,
"loss": 0.3879,
"step": 917
},
{
"epoch": 4.23,
"learning_rate": 0.0001,
"loss": 0.4125,
"step": 918
},
{
"epoch": 4.24,
"learning_rate": 0.0001,
"loss": 0.4168,
"step": 919
},
{
"epoch": 4.24,
"learning_rate": 0.0001,
"loss": 0.452,
"step": 920
},
{
"epoch": 4.25,
"learning_rate": 0.0001,
"loss": 0.4367,
"step": 921
},
{
"epoch": 4.25,
"learning_rate": 0.0001,
"loss": 0.4757,
"step": 922
},
{
"epoch": 4.26,
"learning_rate": 0.0001,
"loss": 0.3492,
"step": 923
},
{
"epoch": 4.26,
"learning_rate": 0.0001,
"loss": 0.4325,
"step": 924
},
{
"epoch": 4.27,
"learning_rate": 0.0001,
"loss": 0.4593,
"step": 925
},
{
"epoch": 4.27,
"learning_rate": 0.0001,
"loss": 0.472,
"step": 926
},
{
"epoch": 4.27,
"learning_rate": 0.0001,
"loss": 0.3736,
"step": 927
},
{
"epoch": 4.28,
"learning_rate": 0.0001,
"loss": 0.56,
"step": 928
},
{
"epoch": 4.28,
"learning_rate": 0.0001,
"loss": 0.4464,
"step": 929
},
{
"epoch": 4.29,
"learning_rate": 0.0001,
"loss": 0.4698,
"step": 930
},
{
"epoch": 4.29,
"learning_rate": 0.0001,
"loss": 0.4519,
"step": 931
},
{
"epoch": 4.3,
"learning_rate": 0.0001,
"loss": 0.5072,
"step": 932
},
{
"epoch": 4.3,
"learning_rate": 0.0001,
"loss": 0.444,
"step": 933
},
{
"epoch": 4.31,
"learning_rate": 0.0001,
"loss": 0.4001,
"step": 934
},
{
"epoch": 4.31,
"learning_rate": 0.0001,
"loss": 0.4447,
"step": 935
},
{
"epoch": 4.32,
"learning_rate": 0.0001,
"loss": 0.5098,
"step": 936
},
{
"epoch": 4.32,
"learning_rate": 0.0001,
"loss": 0.3643,
"step": 937
},
{
"epoch": 4.33,
"learning_rate": 0.0001,
"loss": 0.4307,
"step": 938
},
{
"epoch": 4.33,
"learning_rate": 0.0001,
"loss": 0.4368,
"step": 939
},
{
"epoch": 4.33,
"learning_rate": 0.0001,
"loss": 0.4716,
"step": 940
},
{
"epoch": 4.34,
"learning_rate": 0.0001,
"loss": 0.4254,
"step": 941
},
{
"epoch": 4.34,
"learning_rate": 0.0001,
"loss": 0.3533,
"step": 942
},
{
"epoch": 4.35,
"learning_rate": 0.0001,
"loss": 0.4147,
"step": 943
},
{
"epoch": 4.35,
"learning_rate": 0.0001,
"loss": 0.4525,
"step": 944
},
{
"epoch": 4.36,
"learning_rate": 0.0001,
"loss": 0.5042,
"step": 945
},
{
"epoch": 4.36,
"learning_rate": 0.0001,
"loss": 0.4583,
"step": 946
},
{
"epoch": 4.37,
"learning_rate": 0.0001,
"loss": 0.4476,
"step": 947
},
{
"epoch": 4.37,
"learning_rate": 0.0001,
"loss": 0.4228,
"step": 948
},
{
"epoch": 4.38,
"learning_rate": 0.0001,
"loss": 0.4981,
"step": 949
},
{
"epoch": 4.38,
"learning_rate": 0.0001,
"loss": 0.3752,
"step": 950
},
{
"epoch": 4.39,
"learning_rate": 0.0001,
"loss": 0.4829,
"step": 951
},
{
"epoch": 4.39,
"learning_rate": 0.0001,
"loss": 0.3926,
"step": 952
},
{
"epoch": 4.39,
"learning_rate": 0.0001,
"loss": 0.4282,
"step": 953
},
{
"epoch": 4.4,
"learning_rate": 0.0001,
"loss": 0.4561,
"step": 954
},
{
"epoch": 4.4,
"learning_rate": 0.0001,
"loss": 0.3597,
"step": 955
},
{
"epoch": 4.41,
"learning_rate": 0.0001,
"loss": 0.4341,
"step": 956
},
{
"epoch": 4.41,
"learning_rate": 0.0001,
"loss": 0.4747,
"step": 957
},
{
"epoch": 4.42,
"learning_rate": 0.0001,
"loss": 0.5216,
"step": 958
},
{
"epoch": 4.42,
"learning_rate": 0.0001,
"loss": 0.3748,
"step": 959
},
{
"epoch": 4.43,
"learning_rate": 0.0001,
"loss": 0.4683,
"step": 960
},
{
"epoch": 4.43,
"learning_rate": 0.0001,
"loss": 0.441,
"step": 961
},
{
"epoch": 4.44,
"learning_rate": 0.0001,
"loss": 0.4655,
"step": 962
},
{
"epoch": 4.44,
"learning_rate": 0.0001,
"loss": 0.4194,
"step": 963
},
{
"epoch": 4.44,
"learning_rate": 0.0001,
"loss": 0.4614,
"step": 964
},
{
"epoch": 4.45,
"learning_rate": 0.0001,
"loss": 0.4552,
"step": 965
},
{
"epoch": 4.45,
"learning_rate": 0.0001,
"loss": 0.4616,
"step": 966
},
{
"epoch": 4.46,
"learning_rate": 0.0001,
"loss": 0.4457,
"step": 967
},
{
"epoch": 4.46,
"learning_rate": 0.0001,
"loss": 0.4765,
"step": 968
},
{
"epoch": 4.47,
"learning_rate": 0.0001,
"loss": 0.4841,
"step": 969
},
{
"epoch": 4.47,
"learning_rate": 0.0001,
"loss": 0.4248,
"step": 970
},
{
"epoch": 4.48,
"learning_rate": 0.0001,
"loss": 0.455,
"step": 971
},
{
"epoch": 4.48,
"learning_rate": 0.0001,
"loss": 0.5031,
"step": 972
},
{
"epoch": 4.49,
"learning_rate": 0.0001,
"loss": 0.4151,
"step": 973
},
{
"epoch": 4.49,
"learning_rate": 0.0001,
"loss": 0.4205,
"step": 974
},
{
"epoch": 4.5,
"learning_rate": 0.0001,
"loss": 0.4535,
"step": 975
},
{
"epoch": 4.5,
"learning_rate": 0.0001,
"loss": 0.5306,
"step": 976
},
{
"epoch": 4.5,
"learning_rate": 0.0001,
"loss": 0.463,
"step": 977
},
{
"epoch": 4.51,
"learning_rate": 0.0001,
"loss": 0.4637,
"step": 978
},
{
"epoch": 4.51,
"learning_rate": 0.0001,
"loss": 0.4689,
"step": 979
},
{
"epoch": 4.52,
"learning_rate": 0.0001,
"loss": 0.5244,
"step": 980
},
{
"epoch": 4.52,
"learning_rate": 0.0001,
"loss": 0.4013,
"step": 981
},
{
"epoch": 4.53,
"learning_rate": 0.0001,
"loss": 0.3879,
"step": 982
},
{
"epoch": 4.53,
"learning_rate": 0.0001,
"loss": 0.3769,
"step": 983
},
{
"epoch": 4.54,
"learning_rate": 0.0001,
"loss": 0.4048,
"step": 984
},
{
"epoch": 4.54,
"learning_rate": 0.0001,
"loss": 0.43,
"step": 985
},
{
"epoch": 4.55,
"learning_rate": 0.0001,
"loss": 0.4394,
"step": 986
},
{
"epoch": 4.55,
"learning_rate": 0.0001,
"loss": 0.3966,
"step": 987
},
{
"epoch": 4.56,
"learning_rate": 0.0001,
"loss": 0.4349,
"step": 988
},
{
"epoch": 4.56,
"learning_rate": 0.0001,
"loss": 0.5134,
"step": 989
},
{
"epoch": 4.56,
"learning_rate": 0.0001,
"loss": 0.4889,
"step": 990
},
{
"epoch": 4.57,
"learning_rate": 0.0001,
"loss": 0.4844,
"step": 991
},
{
"epoch": 4.57,
"learning_rate": 0.0001,
"loss": 0.5023,
"step": 992
},
{
"epoch": 4.58,
"learning_rate": 0.0001,
"loss": 0.493,
"step": 993
},
{
"epoch": 4.58,
"learning_rate": 0.0001,
"loss": 0.5257,
"step": 994
},
{
"epoch": 4.59,
"learning_rate": 0.0001,
"loss": 0.4866,
"step": 995
},
{
"epoch": 4.59,
"learning_rate": 0.0001,
"loss": 0.4662,
"step": 996
},
{
"epoch": 4.6,
"learning_rate": 0.0001,
"loss": 0.4743,
"step": 997
},
{
"epoch": 4.6,
"learning_rate": 0.0001,
"loss": 0.4529,
"step": 998
},
{
"epoch": 4.61,
"learning_rate": 0.0001,
"loss": 0.4281,
"step": 999
},
{
"epoch": 4.61,
"learning_rate": 0.0001,
"loss": 0.4638,
"step": 1000
},
{
"epoch": 4.62,
"learning_rate": 0.0001,
"loss": 0.4773,
"step": 1001
},
{
"epoch": 4.62,
"learning_rate": 0.0001,
"loss": 0.4227,
"step": 1002
},
{
"epoch": 4.62,
"learning_rate": 0.0001,
"loss": 0.4302,
"step": 1003
},
{
"epoch": 4.63,
"learning_rate": 0.0001,
"loss": 0.4727,
"step": 1004
},
{
"epoch": 4.63,
"learning_rate": 0.0001,
"loss": 0.4171,
"step": 1005
},
{
"epoch": 4.64,
"learning_rate": 0.0001,
"loss": 0.4578,
"step": 1006
},
{
"epoch": 4.64,
"learning_rate": 0.0001,
"loss": 0.464,
"step": 1007
},
{
"epoch": 4.65,
"learning_rate": 0.0001,
"loss": 0.4665,
"step": 1008
},
{
"epoch": 4.65,
"learning_rate": 0.0001,
"loss": 0.3951,
"step": 1009
},
{
"epoch": 4.66,
"learning_rate": 0.0001,
"loss": 0.4828,
"step": 1010
},
{
"epoch": 4.66,
"learning_rate": 0.0001,
"loss": 0.4208,
"step": 1011
},
{
"epoch": 4.67,
"learning_rate": 0.0001,
"loss": 0.4535,
"step": 1012
},
{
"epoch": 4.67,
"learning_rate": 0.0001,
"loss": 0.4496,
"step": 1013
},
{
"epoch": 4.68,
"learning_rate": 0.0001,
"loss": 0.4483,
"step": 1014
},
{
"epoch": 4.68,
"learning_rate": 0.0001,
"loss": 0.4263,
"step": 1015
},
{
"epoch": 4.68,
"learning_rate": 0.0001,
"loss": 0.4466,
"step": 1016
},
{
"epoch": 4.69,
"learning_rate": 0.0001,
"loss": 0.4464,
"step": 1017
},
{
"epoch": 4.69,
"learning_rate": 0.0001,
"loss": 0.5433,
"step": 1018
},
{
"epoch": 4.7,
"learning_rate": 0.0001,
"loss": 0.4372,
"step": 1019
},
{
"epoch": 4.7,
"learning_rate": 0.0001,
"loss": 0.4834,
"step": 1020
},
{
"epoch": 4.71,
"learning_rate": 0.0001,
"loss": 0.4387,
"step": 1021
},
{
"epoch": 4.71,
"learning_rate": 0.0001,
"loss": 0.4355,
"step": 1022
},
{
"epoch": 4.72,
"learning_rate": 0.0001,
"loss": 0.5251,
"step": 1023
},
{
"epoch": 4.72,
"learning_rate": 0.0001,
"loss": 0.4833,
"step": 1024
},
{
"epoch": 4.73,
"learning_rate": 0.0001,
"loss": 0.4546,
"step": 1025
},
{
"epoch": 4.73,
"learning_rate": 0.0001,
"loss": 0.4326,
"step": 1026
},
{
"epoch": 4.74,
"learning_rate": 0.0001,
"loss": 0.4083,
"step": 1027
},
{
"epoch": 4.74,
"learning_rate": 0.0001,
"loss": 0.4795,
"step": 1028
},
{
"epoch": 4.74,
"learning_rate": 0.0001,
"loss": 0.5251,
"step": 1029
},
{
"epoch": 4.75,
"learning_rate": 0.0001,
"loss": 0.4464,
"step": 1030
},
{
"epoch": 4.75,
"learning_rate": 0.0001,
"loss": 0.4644,
"step": 1031
},
{
"epoch": 4.76,
"learning_rate": 0.0001,
"loss": 0.4609,
"step": 1032
},
{
"epoch": 4.76,
"learning_rate": 0.0001,
"loss": 0.4697,
"step": 1033
},
{
"epoch": 4.77,
"learning_rate": 0.0001,
"loss": 0.4247,
"step": 1034
},
{
"epoch": 4.77,
"learning_rate": 0.0001,
"loss": 0.4044,
"step": 1035
},
{
"epoch": 4.78,
"learning_rate": 0.0001,
"loss": 0.416,
"step": 1036
},
{
"epoch": 4.78,
"learning_rate": 0.0001,
"loss": 0.3857,
"step": 1037
},
{
"epoch": 4.79,
"learning_rate": 0.0001,
"loss": 0.4604,
"step": 1038
},
{
"epoch": 4.79,
"learning_rate": 0.0001,
"loss": 0.4225,
"step": 1039
},
{
"epoch": 4.8,
"learning_rate": 0.0001,
"loss": 0.4288,
"step": 1040
},
{
"epoch": 4.8,
"learning_rate": 0.0001,
"loss": 0.4309,
"step": 1041
},
{
"epoch": 4.8,
"learning_rate": 0.0001,
"loss": 0.5033,
"step": 1042
},
{
"epoch": 4.81,
"learning_rate": 0.0001,
"loss": 0.4724,
"step": 1043
},
{
"epoch": 4.81,
"learning_rate": 0.0001,
"loss": 0.4456,
"step": 1044
},
{
"epoch": 4.82,
"learning_rate": 0.0001,
"loss": 0.416,
"step": 1045
},
{
"epoch": 4.82,
"learning_rate": 0.0001,
"loss": 0.5923,
"step": 1046
},
{
"epoch": 4.83,
"learning_rate": 0.0001,
"loss": 0.4464,
"step": 1047
},
{
"epoch": 4.83,
"learning_rate": 0.0001,
"loss": 0.4783,
"step": 1048
},
{
"epoch": 4.84,
"learning_rate": 0.0001,
"loss": 0.5102,
"step": 1049
},
{
"epoch": 4.84,
"learning_rate": 0.0001,
"loss": 0.4885,
"step": 1050
},
{
"epoch": 4.85,
"learning_rate": 0.0001,
"loss": 0.4956,
"step": 1051
},
{
"epoch": 4.85,
"learning_rate": 0.0001,
"loss": 0.4797,
"step": 1052
},
{
"epoch": 4.86,
"learning_rate": 0.0001,
"loss": 0.4457,
"step": 1053
},
{
"epoch": 4.86,
"learning_rate": 0.0001,
"loss": 0.4644,
"step": 1054
},
{
"epoch": 4.86,
"learning_rate": 0.0001,
"loss": 0.448,
"step": 1055
},
{
"epoch": 4.87,
"learning_rate": 0.0001,
"loss": 0.4446,
"step": 1056
},
{
"epoch": 4.87,
"learning_rate": 0.0001,
"loss": 0.4895,
"step": 1057
},
{
"epoch": 4.88,
"learning_rate": 0.0001,
"loss": 0.469,
"step": 1058
},
{
"epoch": 4.88,
"learning_rate": 0.0001,
"loss": 0.532,
"step": 1059
},
{
"epoch": 4.89,
"learning_rate": 0.0001,
"loss": 0.4976,
"step": 1060
},
{
"epoch": 4.89,
"learning_rate": 0.0001,
"loss": 0.5087,
"step": 1061
},
{
"epoch": 4.9,
"learning_rate": 0.0001,
"loss": 0.4445,
"step": 1062
},
{
"epoch": 4.9,
"learning_rate": 0.0001,
"loss": 0.4614,
"step": 1063
},
{
"epoch": 4.91,
"learning_rate": 0.0001,
"loss": 0.4902,
"step": 1064
},
{
"epoch": 4.91,
"learning_rate": 0.0001,
"loss": 0.449,
"step": 1065
},
{
"epoch": 4.92,
"learning_rate": 0.0001,
"loss": 0.4969,
"step": 1066
},
{
"epoch": 4.92,
"learning_rate": 0.0001,
"loss": 0.5204,
"step": 1067
},
{
"epoch": 4.92,
"learning_rate": 0.0001,
"loss": 0.4606,
"step": 1068
},
{
"epoch": 4.93,
"learning_rate": 0.0001,
"loss": 0.4424,
"step": 1069
},
{
"epoch": 4.93,
"learning_rate": 0.0001,
"loss": 0.437,
"step": 1070
},
{
"epoch": 4.94,
"learning_rate": 0.0001,
"loss": 0.4754,
"step": 1071
},
{
"epoch": 4.94,
"learning_rate": 0.0001,
"loss": 0.512,
"step": 1072
},
{
"epoch": 4.95,
"learning_rate": 0.0001,
"loss": 0.5002,
"step": 1073
},
{
"epoch": 4.95,
"learning_rate": 0.0001,
"loss": 0.4793,
"step": 1074
},
{
"epoch": 4.96,
"learning_rate": 0.0001,
"loss": 0.4653,
"step": 1075
},
{
"epoch": 4.96,
"learning_rate": 0.0001,
"loss": 0.4381,
"step": 1076
},
{
"epoch": 4.97,
"learning_rate": 0.0001,
"loss": 0.5128,
"step": 1077
},
{
"epoch": 4.97,
"learning_rate": 0.0001,
"loss": 0.462,
"step": 1078
},
{
"epoch": 4.98,
"learning_rate": 0.0001,
"loss": 0.4879,
"step": 1079
},
{
"epoch": 4.98,
"learning_rate": 0.0001,
"loss": 0.5166,
"step": 1080
},
{
"epoch": 4.98,
"learning_rate": 0.0001,
"loss": 0.4966,
"step": 1081
},
{
"epoch": 4.99,
"learning_rate": 0.0001,
"loss": 0.4562,
"step": 1082
},
{
"epoch": 4.99,
"learning_rate": 0.0001,
"loss": 0.4986,
"step": 1083
},
{
"epoch": 5.0,
"learning_rate": 0.0001,
"loss": 0.4768,
"step": 1084
},
{
"epoch": 5.0,
"learning_rate": 0.0001,
"loss": 0.3818,
"step": 1085
},
{
"epoch": 5.01,
"learning_rate": 0.0001,
"loss": 0.3732,
"step": 1086
},
{
"epoch": 5.01,
"learning_rate": 0.0001,
"loss": 0.3471,
"step": 1087
},
{
"epoch": 5.02,
"learning_rate": 0.0001,
"loss": 0.3977,
"step": 1088
},
{
"epoch": 5.02,
"learning_rate": 0.0001,
"loss": 0.3787,
"step": 1089
},
{
"epoch": 5.03,
"learning_rate": 0.0001,
"loss": 0.3452,
"step": 1090
},
{
"epoch": 5.03,
"learning_rate": 0.0001,
"loss": 0.3645,
"step": 1091
},
{
"epoch": 5.04,
"learning_rate": 0.0001,
"loss": 0.3444,
"step": 1092
},
{
"epoch": 5.04,
"learning_rate": 0.0001,
"loss": 0.3778,
"step": 1093
},
{
"epoch": 5.04,
"learning_rate": 0.0001,
"loss": 0.352,
"step": 1094
},
{
"epoch": 5.05,
"learning_rate": 0.0001,
"loss": 0.3627,
"step": 1095
},
{
"epoch": 5.05,
"learning_rate": 0.0001,
"loss": 0.4292,
"step": 1096
},
{
"epoch": 5.06,
"learning_rate": 0.0001,
"loss": 0.3232,
"step": 1097
},
{
"epoch": 5.06,
"learning_rate": 0.0001,
"loss": 0.3763,
"step": 1098
},
{
"epoch": 5.07,
"learning_rate": 0.0001,
"loss": 0.3565,
"step": 1099
},
{
"epoch": 5.07,
"learning_rate": 0.0001,
"loss": 0.4417,
"step": 1100
},
{
"epoch": 5.08,
"learning_rate": 0.0001,
"loss": 0.3911,
"step": 1101
},
{
"epoch": 5.08,
"learning_rate": 0.0001,
"loss": 0.3526,
"step": 1102
},
{
"epoch": 5.09,
"learning_rate": 0.0001,
"loss": 0.4132,
"step": 1103
},
{
"epoch": 5.09,
"learning_rate": 0.0001,
"loss": 0.3949,
"step": 1104
},
{
"epoch": 5.1,
"learning_rate": 0.0001,
"loss": 0.3996,
"step": 1105
},
{
"epoch": 5.1,
"learning_rate": 0.0001,
"loss": 0.3448,
"step": 1106
},
{
"epoch": 5.1,
"learning_rate": 0.0001,
"loss": 0.3455,
"step": 1107
},
{
"epoch": 5.11,
"learning_rate": 0.0001,
"loss": 0.3858,
"step": 1108
},
{
"epoch": 5.11,
"learning_rate": 0.0001,
"loss": 0.3697,
"step": 1109
},
{
"epoch": 5.12,
"learning_rate": 0.0001,
"loss": 0.3698,
"step": 1110
},
{
"epoch": 5.12,
"learning_rate": 0.0001,
"loss": 0.3921,
"step": 1111
},
{
"epoch": 5.13,
"learning_rate": 0.0001,
"loss": 0.3421,
"step": 1112
},
{
"epoch": 5.13,
"learning_rate": 0.0001,
"loss": 0.3739,
"step": 1113
},
{
"epoch": 5.14,
"learning_rate": 0.0001,
"loss": 0.3722,
"step": 1114
},
{
"epoch": 5.14,
"learning_rate": 0.0001,
"loss": 0.383,
"step": 1115
},
{
"epoch": 5.15,
"learning_rate": 0.0001,
"loss": 0.3597,
"step": 1116
},
{
"epoch": 5.15,
"learning_rate": 0.0001,
"loss": 0.3719,
"step": 1117
},
{
"epoch": 5.16,
"learning_rate": 0.0001,
"loss": 0.3716,
"step": 1118
},
{
"epoch": 5.16,
"learning_rate": 0.0001,
"loss": 0.3529,
"step": 1119
},
{
"epoch": 5.16,
"learning_rate": 0.0001,
"loss": 0.3721,
"step": 1120
},
{
"epoch": 5.17,
"learning_rate": 0.0001,
"loss": 0.3494,
"step": 1121
},
{
"epoch": 5.17,
"learning_rate": 0.0001,
"loss": 0.3532,
"step": 1122
},
{
"epoch": 5.18,
"learning_rate": 0.0001,
"loss": 0.4008,
"step": 1123
},
{
"epoch": 5.18,
"learning_rate": 0.0001,
"loss": 0.4083,
"step": 1124
},
{
"epoch": 5.19,
"learning_rate": 0.0001,
"loss": 0.4103,
"step": 1125
},
{
"epoch": 5.19,
"learning_rate": 0.0001,
"loss": 0.3673,
"step": 1126
},
{
"epoch": 5.2,
"learning_rate": 0.0001,
"loss": 0.3874,
"step": 1127
},
{
"epoch": 5.2,
"learning_rate": 0.0001,
"loss": 0.4431,
"step": 1128
},
{
"epoch": 5.21,
"learning_rate": 0.0001,
"loss": 0.4019,
"step": 1129
},
{
"epoch": 5.21,
"learning_rate": 0.0001,
"loss": 0.4245,
"step": 1130
},
{
"epoch": 5.21,
"learning_rate": 0.0001,
"loss": 0.4173,
"step": 1131
},
{
"epoch": 5.22,
"learning_rate": 0.0001,
"loss": 0.3634,
"step": 1132
},
{
"epoch": 5.22,
"learning_rate": 0.0001,
"loss": 0.4129,
"step": 1133
},
{
"epoch": 5.23,
"learning_rate": 0.0001,
"loss": 0.3827,
"step": 1134
},
{
"epoch": 5.23,
"learning_rate": 0.0001,
"loss": 0.3951,
"step": 1135
},
{
"epoch": 5.24,
"learning_rate": 0.0001,
"loss": 0.449,
"step": 1136
},
{
"epoch": 5.24,
"learning_rate": 0.0001,
"loss": 0.3908,
"step": 1137
},
{
"epoch": 5.25,
"learning_rate": 0.0001,
"loss": 0.3736,
"step": 1138
},
{
"epoch": 5.25,
"learning_rate": 0.0001,
"loss": 0.4422,
"step": 1139
},
{
"epoch": 5.26,
"learning_rate": 0.0001,
"loss": 0.3228,
"step": 1140
},
{
"epoch": 5.26,
"learning_rate": 0.0001,
"loss": 0.3771,
"step": 1141
},
{
"epoch": 5.27,
"learning_rate": 0.0001,
"loss": 0.4184,
"step": 1142
},
{
"epoch": 5.27,
"learning_rate": 0.0001,
"loss": 0.3962,
"step": 1143
},
{
"epoch": 5.27,
"learning_rate": 0.0001,
"loss": 0.4202,
"step": 1144
},
{
"epoch": 5.28,
"learning_rate": 0.0001,
"loss": 0.3697,
"step": 1145
},
{
"epoch": 5.28,
"learning_rate": 0.0001,
"loss": 0.4038,
"step": 1146
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 0.4018,
"step": 1147
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 0.3746,
"step": 1148
},
{
"epoch": 5.3,
"learning_rate": 0.0001,
"loss": 0.3466,
"step": 1149
},
{
"epoch": 5.3,
"learning_rate": 0.0001,
"loss": 0.3726,
"step": 1150
},
{
"epoch": 5.31,
"learning_rate": 0.0001,
"loss": 0.3833,
"step": 1151
},
{
"epoch": 5.31,
"learning_rate": 0.0001,
"loss": 0.4469,
"step": 1152
},
{
"epoch": 5.32,
"learning_rate": 0.0001,
"loss": 0.3803,
"step": 1153
},
{
"epoch": 5.32,
"learning_rate": 0.0001,
"loss": 0.3577,
"step": 1154
},
{
"epoch": 5.33,
"learning_rate": 0.0001,
"loss": 0.3994,
"step": 1155
},
{
"epoch": 5.33,
"learning_rate": 0.0001,
"loss": 0.3652,
"step": 1156
},
{
"epoch": 5.33,
"learning_rate": 0.0001,
"loss": 0.422,
"step": 1157
},
{
"epoch": 5.34,
"learning_rate": 0.0001,
"loss": 0.4257,
"step": 1158
},
{
"epoch": 5.34,
"learning_rate": 0.0001,
"loss": 0.4263,
"step": 1159
},
{
"epoch": 5.35,
"learning_rate": 0.0001,
"loss": 0.3509,
"step": 1160
},
{
"epoch": 5.35,
"learning_rate": 0.0001,
"loss": 0.3752,
"step": 1161
},
{
"epoch": 5.36,
"learning_rate": 0.0001,
"loss": 0.3921,
"step": 1162
},
{
"epoch": 5.36,
"learning_rate": 0.0001,
"loss": 0.3913,
"step": 1163
},
{
"epoch": 5.37,
"learning_rate": 0.0001,
"loss": 0.3837,
"step": 1164
},
{
"epoch": 5.37,
"learning_rate": 0.0001,
"loss": 0.4197,
"step": 1165
},
{
"epoch": 5.38,
"learning_rate": 0.0001,
"loss": 0.3898,
"step": 1166
},
{
"epoch": 5.38,
"learning_rate": 0.0001,
"loss": 0.3526,
"step": 1167
},
{
"epoch": 5.39,
"learning_rate": 0.0001,
"loss": 0.3696,
"step": 1168
},
{
"epoch": 5.39,
"learning_rate": 0.0001,
"loss": 0.5303,
"step": 1169
},
{
"epoch": 5.39,
"learning_rate": 0.0001,
"loss": 0.3846,
"step": 1170
},
{
"epoch": 5.4,
"learning_rate": 0.0001,
"loss": 0.3293,
"step": 1171
},
{
"epoch": 5.4,
"learning_rate": 0.0001,
"loss": 0.4397,
"step": 1172
},
{
"epoch": 5.41,
"learning_rate": 0.0001,
"loss": 0.4007,
"step": 1173
},
{
"epoch": 5.41,
"learning_rate": 0.0001,
"loss": 0.446,
"step": 1174
},
{
"epoch": 5.42,
"learning_rate": 0.0001,
"loss": 0.3791,
"step": 1175
},
{
"epoch": 5.42,
"learning_rate": 0.0001,
"loss": 0.3979,
"step": 1176
},
{
"epoch": 5.43,
"learning_rate": 0.0001,
"loss": 0.3734,
"step": 1177
},
{
"epoch": 5.43,
"learning_rate": 0.0001,
"loss": 0.3524,
"step": 1178
},
{
"epoch": 5.44,
"learning_rate": 0.0001,
"loss": 0.37,
"step": 1179
},
{
"epoch": 5.44,
"learning_rate": 0.0001,
"loss": 0.4341,
"step": 1180
},
{
"epoch": 5.45,
"learning_rate": 0.0001,
"loss": 0.3842,
"step": 1181
},
{
"epoch": 5.45,
"learning_rate": 0.0001,
"loss": 0.4215,
"step": 1182
},
{
"epoch": 5.45,
"learning_rate": 0.0001,
"loss": 0.4244,
"step": 1183
},
{
"epoch": 5.46,
"learning_rate": 0.0001,
"loss": 0.3697,
"step": 1184
},
{
"epoch": 5.46,
"learning_rate": 0.0001,
"loss": 0.4106,
"step": 1185
},
{
"epoch": 5.47,
"learning_rate": 0.0001,
"loss": 0.3465,
"step": 1186
},
{
"epoch": 5.47,
"learning_rate": 0.0001,
"loss": 0.3764,
"step": 1187
},
{
"epoch": 5.48,
"learning_rate": 0.0001,
"loss": 0.3403,
"step": 1188
},
{
"epoch": 5.48,
"learning_rate": 0.0001,
"loss": 0.4396,
"step": 1189
},
{
"epoch": 5.49,
"learning_rate": 0.0001,
"loss": 0.4044,
"step": 1190
},
{
"epoch": 5.49,
"learning_rate": 0.0001,
"loss": 0.4164,
"step": 1191
},
{
"epoch": 5.5,
"learning_rate": 0.0001,
"loss": 0.4514,
"step": 1192
},
{
"epoch": 5.5,
"learning_rate": 0.0001,
"loss": 0.4156,
"step": 1193
},
{
"epoch": 5.51,
"learning_rate": 0.0001,
"loss": 0.3447,
"step": 1194
},
{
"epoch": 5.51,
"learning_rate": 0.0001,
"loss": 0.424,
"step": 1195
},
{
"epoch": 5.51,
"learning_rate": 0.0001,
"loss": 0.3262,
"step": 1196
},
{
"epoch": 5.52,
"learning_rate": 0.0001,
"loss": 0.4279,
"step": 1197
},
{
"epoch": 5.52,
"learning_rate": 0.0001,
"loss": 0.4627,
"step": 1198
},
{
"epoch": 5.53,
"learning_rate": 0.0001,
"loss": 0.4195,
"step": 1199
},
{
"epoch": 5.53,
"learning_rate": 0.0001,
"loss": 0.4419,
"step": 1200
},
{
"epoch": 5.54,
"learning_rate": 0.0001,
"loss": 0.4312,
"step": 1201
},
{
"epoch": 5.54,
"learning_rate": 0.0001,
"loss": 0.4452,
"step": 1202
},
{
"epoch": 5.55,
"learning_rate": 0.0001,
"loss": 0.4419,
"step": 1203
},
{
"epoch": 5.55,
"learning_rate": 0.0001,
"loss": 0.4412,
"step": 1204
},
{
"epoch": 5.56,
"learning_rate": 0.0001,
"loss": 0.4742,
"step": 1205
},
{
"epoch": 5.56,
"learning_rate": 0.0001,
"loss": 0.3854,
"step": 1206
},
{
"epoch": 5.57,
"learning_rate": 0.0001,
"loss": 0.4193,
"step": 1207
},
{
"epoch": 5.57,
"learning_rate": 0.0001,
"loss": 0.4003,
"step": 1208
},
{
"epoch": 5.57,
"learning_rate": 0.0001,
"loss": 0.4197,
"step": 1209
},
{
"epoch": 5.58,
"learning_rate": 0.0001,
"loss": 0.43,
"step": 1210
},
{
"epoch": 5.58,
"learning_rate": 0.0001,
"loss": 0.4022,
"step": 1211
},
{
"epoch": 5.59,
"learning_rate": 0.0001,
"loss": 0.388,
"step": 1212
},
{
"epoch": 5.59,
"learning_rate": 0.0001,
"loss": 0.4268,
"step": 1213
},
{
"epoch": 5.6,
"learning_rate": 0.0001,
"loss": 0.4085,
"step": 1214
},
{
"epoch": 5.6,
"learning_rate": 0.0001,
"loss": 0.4223,
"step": 1215
},
{
"epoch": 5.61,
"learning_rate": 0.0001,
"loss": 0.3465,
"step": 1216
},
{
"epoch": 5.61,
"learning_rate": 0.0001,
"loss": 0.4532,
"step": 1217
},
{
"epoch": 5.62,
"learning_rate": 0.0001,
"loss": 0.4407,
"step": 1218
},
{
"epoch": 5.62,
"learning_rate": 0.0001,
"loss": 0.4025,
"step": 1219
},
{
"epoch": 5.63,
"learning_rate": 0.0001,
"loss": 0.4266,
"step": 1220
},
{
"epoch": 5.63,
"learning_rate": 0.0001,
"loss": 0.3781,
"step": 1221
},
{
"epoch": 5.63,
"learning_rate": 0.0001,
"loss": 0.3637,
"step": 1222
},
{
"epoch": 5.64,
"learning_rate": 0.0001,
"loss": 0.413,
"step": 1223
},
{
"epoch": 5.64,
"learning_rate": 0.0001,
"loss": 0.3631,
"step": 1224
},
{
"epoch": 5.65,
"learning_rate": 0.0001,
"loss": 0.3849,
"step": 1225
},
{
"epoch": 5.65,
"learning_rate": 0.0001,
"loss": 0.4033,
"step": 1226
},
{
"epoch": 5.66,
"learning_rate": 0.0001,
"loss": 0.386,
"step": 1227
},
{
"epoch": 5.66,
"learning_rate": 0.0001,
"loss": 0.4143,
"step": 1228
},
{
"epoch": 5.67,
"learning_rate": 0.0001,
"loss": 0.4583,
"step": 1229
},
{
"epoch": 5.67,
"learning_rate": 0.0001,
"loss": 0.3756,
"step": 1230
},
{
"epoch": 5.68,
"learning_rate": 0.0001,
"loss": 0.3979,
"step": 1231
},
{
"epoch": 5.68,
"learning_rate": 0.0001,
"loss": 0.4216,
"step": 1232
},
{
"epoch": 5.69,
"learning_rate": 0.0001,
"loss": 0.4266,
"step": 1233
},
{
"epoch": 5.69,
"learning_rate": 0.0001,
"loss": 0.3968,
"step": 1234
},
{
"epoch": 5.69,
"learning_rate": 0.0001,
"loss": 0.3783,
"step": 1235
},
{
"epoch": 5.7,
"learning_rate": 0.0001,
"loss": 0.3943,
"step": 1236
},
{
"epoch": 5.7,
"learning_rate": 0.0001,
"loss": 0.4469,
"step": 1237
},
{
"epoch": 5.71,
"learning_rate": 0.0001,
"loss": 0.4149,
"step": 1238
},
{
"epoch": 5.71,
"learning_rate": 0.0001,
"loss": 0.4103,
"step": 1239
},
{
"epoch": 5.72,
"learning_rate": 0.0001,
"loss": 0.4383,
"step": 1240
},
{
"epoch": 5.72,
"learning_rate": 0.0001,
"loss": 0.3615,
"step": 1241
},
{
"epoch": 5.73,
"learning_rate": 0.0001,
"loss": 0.4217,
"step": 1242
},
{
"epoch": 5.73,
"learning_rate": 0.0001,
"loss": 0.4267,
"step": 1243
},
{
"epoch": 5.74,
"learning_rate": 0.0001,
"loss": 0.448,
"step": 1244
},
{
"epoch": 5.74,
"learning_rate": 0.0001,
"loss": 0.4376,
"step": 1245
},
{
"epoch": 5.75,
"learning_rate": 0.0001,
"loss": 0.3928,
"step": 1246
},
{
"epoch": 5.75,
"learning_rate": 0.0001,
"loss": 0.3956,
"step": 1247
},
{
"epoch": 5.75,
"learning_rate": 0.0001,
"loss": 0.4113,
"step": 1248
},
{
"epoch": 5.76,
"learning_rate": 0.0001,
"loss": 0.4185,
"step": 1249
},
{
"epoch": 5.76,
"learning_rate": 0.0001,
"loss": 0.4234,
"step": 1250
},
{
"epoch": 5.77,
"learning_rate": 0.0001,
"loss": 0.4351,
"step": 1251
},
{
"epoch": 5.77,
"learning_rate": 0.0001,
"loss": 0.4736,
"step": 1252
},
{
"epoch": 5.78,
"learning_rate": 0.0001,
"loss": 0.4373,
"step": 1253
},
{
"epoch": 5.78,
"learning_rate": 0.0001,
"loss": 0.3402,
"step": 1254
},
{
"epoch": 5.79,
"learning_rate": 0.0001,
"loss": 0.3647,
"step": 1255
},
{
"epoch": 5.79,
"learning_rate": 0.0001,
"loss": 0.3324,
"step": 1256
},
{
"epoch": 5.8,
"learning_rate": 0.0001,
"loss": 0.4593,
"step": 1257
},
{
"epoch": 5.8,
"learning_rate": 0.0001,
"loss": 0.4373,
"step": 1258
},
{
"epoch": 5.81,
"learning_rate": 0.0001,
"loss": 0.4108,
"step": 1259
},
{
"epoch": 5.81,
"learning_rate": 0.0001,
"loss": 0.4491,
"step": 1260
},
{
"epoch": 5.81,
"learning_rate": 0.0001,
"loss": 0.4248,
"step": 1261
},
{
"epoch": 5.82,
"learning_rate": 0.0001,
"loss": 0.3992,
"step": 1262
},
{
"epoch": 5.82,
"learning_rate": 0.0001,
"loss": 0.412,
"step": 1263
},
{
"epoch": 5.83,
"learning_rate": 0.0001,
"loss": 0.4497,
"step": 1264
},
{
"epoch": 5.83,
"learning_rate": 0.0001,
"loss": 0.399,
"step": 1265
},
{
"epoch": 5.84,
"learning_rate": 0.0001,
"loss": 0.418,
"step": 1266
},
{
"epoch": 5.84,
"learning_rate": 0.0001,
"loss": 0.3919,
"step": 1267
},
{
"epoch": 5.85,
"learning_rate": 0.0001,
"loss": 0.4016,
"step": 1268
},
{
"epoch": 5.85,
"learning_rate": 0.0001,
"loss": 0.3892,
"step": 1269
},
{
"epoch": 5.86,
"learning_rate": 0.0001,
"loss": 0.4069,
"step": 1270
},
{
"epoch": 5.86,
"learning_rate": 0.0001,
"loss": 0.409,
"step": 1271
},
{
"epoch": 5.87,
"learning_rate": 0.0001,
"loss": 0.4321,
"step": 1272
},
{
"epoch": 5.87,
"learning_rate": 0.0001,
"loss": 0.4009,
"step": 1273
},
{
"epoch": 5.87,
"learning_rate": 0.0001,
"loss": 0.5217,
"step": 1274
},
{
"epoch": 5.88,
"learning_rate": 0.0001,
"loss": 0.3772,
"step": 1275
},
{
"epoch": 5.88,
"learning_rate": 0.0001,
"loss": 0.4201,
"step": 1276
},
{
"epoch": 5.89,
"learning_rate": 0.0001,
"loss": 0.3931,
"step": 1277
},
{
"epoch": 5.89,
"learning_rate": 0.0001,
"loss": 0.3651,
"step": 1278
},
{
"epoch": 5.9,
"learning_rate": 0.0001,
"loss": 0.3834,
"step": 1279
},
{
"epoch": 5.9,
"learning_rate": 0.0001,
"loss": 0.3925,
"step": 1280
},
{
"epoch": 5.91,
"learning_rate": 0.0001,
"loss": 0.4462,
"step": 1281
},
{
"epoch": 5.91,
"learning_rate": 0.0001,
"loss": 0.4243,
"step": 1282
},
{
"epoch": 5.92,
"learning_rate": 0.0001,
"loss": 0.4924,
"step": 1283
},
{
"epoch": 5.92,
"learning_rate": 0.0001,
"loss": 0.4627,
"step": 1284
},
{
"epoch": 5.93,
"learning_rate": 0.0001,
"loss": 0.436,
"step": 1285
},
{
"epoch": 5.93,
"learning_rate": 0.0001,
"loss": 0.4744,
"step": 1286
},
{
"epoch": 5.93,
"learning_rate": 0.0001,
"loss": 0.4422,
"step": 1287
},
{
"epoch": 5.94,
"learning_rate": 0.0001,
"loss": 0.4178,
"step": 1288
},
{
"epoch": 5.94,
"learning_rate": 0.0001,
"loss": 0.4224,
"step": 1289
},
{
"epoch": 5.95,
"learning_rate": 0.0001,
"loss": 0.4108,
"step": 1290
},
{
"epoch": 5.95,
"learning_rate": 0.0001,
"loss": 0.3924,
"step": 1291
},
{
"epoch": 5.96,
"learning_rate": 0.0001,
"loss": 0.379,
"step": 1292
},
{
"epoch": 5.96,
"learning_rate": 0.0001,
"loss": 0.443,
"step": 1293
},
{
"epoch": 5.97,
"learning_rate": 0.0001,
"loss": 0.4305,
"step": 1294
},
{
"epoch": 5.97,
"learning_rate": 0.0001,
"loss": 0.4153,
"step": 1295
},
{
"epoch": 5.98,
"learning_rate": 0.0001,
"loss": 0.4109,
"step": 1296
},
{
"epoch": 5.98,
"learning_rate": 0.0001,
"loss": 0.4399,
"step": 1297
},
{
"epoch": 5.99,
"learning_rate": 0.0001,
"loss": 0.4581,
"step": 1298
},
{
"epoch": 5.99,
"learning_rate": 0.0001,
"loss": 0.4739,
"step": 1299
},
{
"epoch": 5.99,
"learning_rate": 0.0001,
"loss": 0.4292,
"step": 1300
},
{
"epoch": 6.0,
"learning_rate": 0.0001,
"loss": 0.4209,
"step": 1301
},
{
"epoch": 6.0,
"learning_rate": 0.0001,
"loss": 0.4074,
"step": 1302
},
{
"epoch": 6.01,
"learning_rate": 0.0001,
"loss": 0.4001,
"step": 1303
},
{
"epoch": 6.01,
"learning_rate": 0.0001,
"loss": 0.3543,
"step": 1304
},
{
"epoch": 6.02,
"learning_rate": 0.0001,
"loss": 0.3156,
"step": 1305
},
{
"epoch": 6.02,
"learning_rate": 0.0001,
"loss": 0.3244,
"step": 1306
},
{
"epoch": 6.03,
"learning_rate": 0.0001,
"loss": 0.3151,
"step": 1307
},
{
"epoch": 6.03,
"learning_rate": 0.0001,
"loss": 0.3235,
"step": 1308
},
{
"epoch": 6.04,
"learning_rate": 0.0001,
"loss": 0.334,
"step": 1309
},
{
"epoch": 6.04,
"learning_rate": 0.0001,
"loss": 0.3177,
"step": 1310
},
{
"epoch": 6.04,
"learning_rate": 0.0001,
"loss": 0.3065,
"step": 1311
},
{
"epoch": 6.05,
"learning_rate": 0.0001,
"loss": 0.334,
"step": 1312
},
{
"epoch": 6.05,
"learning_rate": 0.0001,
"loss": 0.3209,
"step": 1313
},
{
"epoch": 6.06,
"learning_rate": 0.0001,
"loss": 0.3014,
"step": 1314
},
{
"epoch": 6.06,
"learning_rate": 0.0001,
"loss": 0.2754,
"step": 1315
},
{
"epoch": 6.07,
"learning_rate": 0.0001,
"loss": 0.3072,
"step": 1316
},
{
"epoch": 6.07,
"learning_rate": 0.0001,
"loss": 0.377,
"step": 1317
},
{
"epoch": 6.08,
"learning_rate": 0.0001,
"loss": 0.3231,
"step": 1318
},
{
"epoch": 6.08,
"learning_rate": 0.0001,
"loss": 0.2605,
"step": 1319
},
{
"epoch": 6.09,
"learning_rate": 0.0001,
"loss": 0.3337,
"step": 1320
},
{
"epoch": 6.09,
"learning_rate": 0.0001,
"loss": 0.3348,
"step": 1321
},
{
"epoch": 6.1,
"learning_rate": 0.0001,
"loss": 0.3166,
"step": 1322
},
{
"epoch": 6.1,
"learning_rate": 0.0001,
"loss": 0.3319,
"step": 1323
},
{
"epoch": 6.1,
"learning_rate": 0.0001,
"loss": 0.3794,
"step": 1324
},
{
"epoch": 6.11,
"learning_rate": 0.0001,
"loss": 0.3103,
"step": 1325
},
{
"epoch": 6.11,
"learning_rate": 0.0001,
"loss": 0.3402,
"step": 1326
},
{
"epoch": 6.12,
"learning_rate": 0.0001,
"loss": 0.3259,
"step": 1327
},
{
"epoch": 6.12,
"learning_rate": 0.0001,
"loss": 0.3104,
"step": 1328
},
{
"epoch": 6.13,
"learning_rate": 0.0001,
"loss": 0.3333,
"step": 1329
},
{
"epoch": 6.13,
"learning_rate": 0.0001,
"loss": 0.3444,
"step": 1330
},
{
"epoch": 6.14,
"learning_rate": 0.0001,
"loss": 0.2962,
"step": 1331
},
{
"epoch": 6.14,
"learning_rate": 0.0001,
"loss": 0.3042,
"step": 1332
},
{
"epoch": 6.15,
"learning_rate": 0.0001,
"loss": 0.3487,
"step": 1333
},
{
"epoch": 6.15,
"learning_rate": 0.0001,
"loss": 0.3039,
"step": 1334
},
{
"epoch": 6.16,
"learning_rate": 0.0001,
"loss": 0.3308,
"step": 1335
},
{
"epoch": 6.16,
"learning_rate": 0.0001,
"loss": 0.3493,
"step": 1336
},
{
"epoch": 6.16,
"learning_rate": 0.0001,
"loss": 0.3318,
"step": 1337
},
{
"epoch": 6.17,
"learning_rate": 0.0001,
"loss": 0.3212,
"step": 1338
},
{
"epoch": 6.17,
"learning_rate": 0.0001,
"loss": 0.3185,
"step": 1339
},
{
"epoch": 6.18,
"learning_rate": 0.0001,
"loss": 0.3421,
"step": 1340
},
{
"epoch": 6.18,
"learning_rate": 0.0001,
"loss": 0.3069,
"step": 1341
},
{
"epoch": 6.19,
"learning_rate": 0.0001,
"loss": 0.3342,
"step": 1342
},
{
"epoch": 6.19,
"learning_rate": 0.0001,
"loss": 0.3329,
"step": 1343
},
{
"epoch": 6.2,
"learning_rate": 0.0001,
"loss": 0.3185,
"step": 1344
},
{
"epoch": 6.2,
"learning_rate": 0.0001,
"loss": 0.3823,
"step": 1345
},
{
"epoch": 6.21,
"learning_rate": 0.0001,
"loss": 0.3265,
"step": 1346
},
{
"epoch": 6.21,
"learning_rate": 0.0001,
"loss": 0.3627,
"step": 1347
},
{
"epoch": 6.22,
"learning_rate": 0.0001,
"loss": 0.338,
"step": 1348
},
{
"epoch": 6.22,
"learning_rate": 0.0001,
"loss": 0.3901,
"step": 1349
},
{
"epoch": 6.22,
"learning_rate": 0.0001,
"loss": 0.3426,
"step": 1350
},
{
"epoch": 6.23,
"learning_rate": 0.0001,
"loss": 0.3057,
"step": 1351
},
{
"epoch": 6.23,
"learning_rate": 0.0001,
"loss": 0.4107,
"step": 1352
},
{
"epoch": 6.24,
"learning_rate": 0.0001,
"loss": 0.3455,
"step": 1353
},
{
"epoch": 6.24,
"learning_rate": 0.0001,
"loss": 0.3168,
"step": 1354
},
{
"epoch": 6.25,
"learning_rate": 0.0001,
"loss": 0.3045,
"step": 1355
},
{
"epoch": 6.25,
"learning_rate": 0.0001,
"loss": 0.3513,
"step": 1356
},
{
"epoch": 6.26,
"learning_rate": 0.0001,
"loss": 0.3394,
"step": 1357
},
{
"epoch": 6.26,
"learning_rate": 0.0001,
"loss": 0.3266,
"step": 1358
},
{
"epoch": 6.27,
"learning_rate": 0.0001,
"loss": 0.4103,
"step": 1359
},
{
"epoch": 6.27,
"learning_rate": 0.0001,
"loss": 0.3109,
"step": 1360
},
{
"epoch": 6.28,
"learning_rate": 0.0001,
"loss": 0.3473,
"step": 1361
},
{
"epoch": 6.28,
"learning_rate": 0.0001,
"loss": 0.3149,
"step": 1362
},
{
"epoch": 6.28,
"learning_rate": 0.0001,
"loss": 0.3126,
"step": 1363
},
{
"epoch": 6.29,
"learning_rate": 0.0001,
"loss": 0.3431,
"step": 1364
},
{
"epoch": 6.29,
"learning_rate": 0.0001,
"loss": 0.3004,
"step": 1365
},
{
"epoch": 6.3,
"learning_rate": 0.0001,
"loss": 0.3881,
"step": 1366
},
{
"epoch": 6.3,
"learning_rate": 0.0001,
"loss": 0.3433,
"step": 1367
},
{
"epoch": 6.31,
"learning_rate": 0.0001,
"loss": 0.3629,
"step": 1368
},
{
"epoch": 6.31,
"learning_rate": 0.0001,
"loss": 0.3834,
"step": 1369
},
{
"epoch": 6.32,
"learning_rate": 0.0001,
"loss": 0.3164,
"step": 1370
},
{
"epoch": 6.32,
"learning_rate": 0.0001,
"loss": 0.3557,
"step": 1371
},
{
"epoch": 6.33,
"learning_rate": 0.0001,
"loss": 0.3176,
"step": 1372
},
{
"epoch": 6.33,
"learning_rate": 0.0001,
"loss": 0.3773,
"step": 1373
},
{
"epoch": 6.34,
"learning_rate": 0.0001,
"loss": 0.3202,
"step": 1374
},
{
"epoch": 6.34,
"learning_rate": 0.0001,
"loss": 0.3024,
"step": 1375
},
{
"epoch": 6.34,
"learning_rate": 0.0001,
"loss": 0.3445,
"step": 1376
},
{
"epoch": 6.35,
"learning_rate": 0.0001,
"loss": 0.3459,
"step": 1377
},
{
"epoch": 6.35,
"learning_rate": 0.0001,
"loss": 0.3733,
"step": 1378
},
{
"epoch": 6.36,
"learning_rate": 0.0001,
"loss": 0.3591,
"step": 1379
},
{
"epoch": 6.36,
"learning_rate": 0.0001,
"loss": 0.3494,
"step": 1380
},
{
"epoch": 6.37,
"learning_rate": 0.0001,
"loss": 0.3679,
"step": 1381
},
{
"epoch": 6.37,
"learning_rate": 0.0001,
"loss": 0.3532,
"step": 1382
},
{
"epoch": 6.38,
"learning_rate": 0.0001,
"loss": 0.4127,
"step": 1383
},
{
"epoch": 6.38,
"learning_rate": 0.0001,
"loss": 0.3646,
"step": 1384
},
{
"epoch": 6.39,
"learning_rate": 0.0001,
"loss": 0.359,
"step": 1385
},
{
"epoch": 6.39,
"learning_rate": 0.0001,
"loss": 0.3792,
"step": 1386
},
{
"epoch": 6.4,
"learning_rate": 0.0001,
"loss": 0.3483,
"step": 1387
},
{
"epoch": 6.4,
"learning_rate": 0.0001,
"loss": 0.3478,
"step": 1388
},
{
"epoch": 6.4,
"learning_rate": 0.0001,
"loss": 0.3776,
"step": 1389
},
{
"epoch": 6.41,
"learning_rate": 0.0001,
"loss": 0.381,
"step": 1390
},
{
"epoch": 6.41,
"learning_rate": 0.0001,
"loss": 0.339,
"step": 1391
},
{
"epoch": 6.42,
"learning_rate": 0.0001,
"loss": 0.3565,
"step": 1392
},
{
"epoch": 6.42,
"learning_rate": 0.0001,
"loss": 0.3469,
"step": 1393
},
{
"epoch": 6.43,
"learning_rate": 0.0001,
"loss": 0.3605,
"step": 1394
},
{
"epoch": 6.43,
"learning_rate": 0.0001,
"loss": 0.3212,
"step": 1395
},
{
"epoch": 6.44,
"learning_rate": 0.0001,
"loss": 0.3603,
"step": 1396
},
{
"epoch": 6.44,
"learning_rate": 0.0001,
"loss": 0.3503,
"step": 1397
},
{
"epoch": 6.45,
"learning_rate": 0.0001,
"loss": 0.4115,
"step": 1398
},
{
"epoch": 6.45,
"learning_rate": 0.0001,
"loss": 0.3386,
"step": 1399
},
{
"epoch": 6.46,
"learning_rate": 0.0001,
"loss": 0.3982,
"step": 1400
},
{
"epoch": 6.46,
"learning_rate": 0.0001,
"loss": 0.4033,
"step": 1401
},
{
"epoch": 6.46,
"learning_rate": 0.0001,
"loss": 0.3424,
"step": 1402
},
{
"epoch": 6.47,
"learning_rate": 0.0001,
"loss": 0.3531,
"step": 1403
},
{
"epoch": 6.47,
"learning_rate": 0.0001,
"loss": 0.3573,
"step": 1404
},
{
"epoch": 6.48,
"learning_rate": 0.0001,
"loss": 0.3323,
"step": 1405
},
{
"epoch": 6.48,
"learning_rate": 0.0001,
"loss": 0.3198,
"step": 1406
},
{
"epoch": 6.49,
"learning_rate": 0.0001,
"loss": 0.3807,
"step": 1407
},
{
"epoch": 6.49,
"learning_rate": 0.0001,
"loss": 0.3641,
"step": 1408
},
{
"epoch": 6.5,
"learning_rate": 0.0001,
"loss": 0.3634,
"step": 1409
},
{
"epoch": 6.5,
"learning_rate": 0.0001,
"loss": 0.3739,
"step": 1410
},
{
"epoch": 6.51,
"learning_rate": 0.0001,
"loss": 0.3698,
"step": 1411
},
{
"epoch": 6.51,
"learning_rate": 0.0001,
"loss": 0.3755,
"step": 1412
},
{
"epoch": 6.52,
"learning_rate": 0.0001,
"loss": 0.3498,
"step": 1413
},
{
"epoch": 6.52,
"learning_rate": 0.0001,
"loss": 0.3562,
"step": 1414
},
{
"epoch": 6.52,
"learning_rate": 0.0001,
"loss": 0.391,
"step": 1415
},
{
"epoch": 6.53,
"learning_rate": 0.0001,
"loss": 0.3743,
"step": 1416
},
{
"epoch": 6.53,
"learning_rate": 0.0001,
"loss": 0.3183,
"step": 1417
},
{
"epoch": 6.54,
"learning_rate": 0.0001,
"loss": 0.376,
"step": 1418
},
{
"epoch": 6.54,
"learning_rate": 0.0001,
"loss": 0.3452,
"step": 1419
},
{
"epoch": 6.55,
"learning_rate": 0.0001,
"loss": 0.3655,
"step": 1420
},
{
"epoch": 6.55,
"learning_rate": 0.0001,
"loss": 0.3486,
"step": 1421
},
{
"epoch": 6.56,
"learning_rate": 0.0001,
"loss": 0.3771,
"step": 1422
},
{
"epoch": 6.56,
"learning_rate": 0.0001,
"loss": 0.3896,
"step": 1423
},
{
"epoch": 6.57,
"learning_rate": 0.0001,
"loss": 0.3729,
"step": 1424
},
{
"epoch": 6.57,
"learning_rate": 0.0001,
"loss": 0.3771,
"step": 1425
},
{
"epoch": 6.58,
"learning_rate": 0.0001,
"loss": 0.3825,
"step": 1426
},
{
"epoch": 6.58,
"learning_rate": 0.0001,
"loss": 0.3593,
"step": 1427
},
{
"epoch": 6.58,
"learning_rate": 0.0001,
"loss": 0.3538,
"step": 1428
},
{
"epoch": 6.59,
"learning_rate": 0.0001,
"loss": 0.4044,
"step": 1429
},
{
"epoch": 6.59,
"learning_rate": 0.0001,
"loss": 0.4008,
"step": 1430
},
{
"epoch": 6.6,
"learning_rate": 0.0001,
"loss": 0.4121,
"step": 1431
},
{
"epoch": 6.6,
"learning_rate": 0.0001,
"loss": 0.3473,
"step": 1432
},
{
"epoch": 6.61,
"learning_rate": 0.0001,
"loss": 0.3678,
"step": 1433
},
{
"epoch": 6.61,
"learning_rate": 0.0001,
"loss": 0.3351,
"step": 1434
},
{
"epoch": 6.62,
"learning_rate": 0.0001,
"loss": 0.3844,
"step": 1435
},
{
"epoch": 6.62,
"learning_rate": 0.0001,
"loss": 0.3231,
"step": 1436
},
{
"epoch": 6.63,
"learning_rate": 0.0001,
"loss": 0.3699,
"step": 1437
},
{
"epoch": 6.63,
"learning_rate": 0.0001,
"loss": 0.407,
"step": 1438
},
{
"epoch": 6.64,
"learning_rate": 0.0001,
"loss": 0.3241,
"step": 1439
},
{
"epoch": 6.64,
"learning_rate": 0.0001,
"loss": 0.365,
"step": 1440
},
{
"epoch": 6.64,
"learning_rate": 0.0001,
"loss": 0.3581,
"step": 1441
},
{
"epoch": 6.65,
"learning_rate": 0.0001,
"loss": 0.3564,
"step": 1442
},
{
"epoch": 6.65,
"learning_rate": 0.0001,
"loss": 0.4109,
"step": 1443
},
{
"epoch": 6.66,
"learning_rate": 0.0001,
"loss": 0.4354,
"step": 1444
},
{
"epoch": 6.66,
"learning_rate": 0.0001,
"loss": 0.3435,
"step": 1445
},
{
"epoch": 6.67,
"learning_rate": 0.0001,
"loss": 0.3691,
"step": 1446
},
{
"epoch": 6.67,
"learning_rate": 0.0001,
"loss": 0.3845,
"step": 1447
},
{
"epoch": 6.68,
"learning_rate": 0.0001,
"loss": 0.394,
"step": 1448
},
{
"epoch": 6.68,
"learning_rate": 0.0001,
"loss": 0.3843,
"step": 1449
},
{
"epoch": 6.69,
"learning_rate": 0.0001,
"loss": 0.3368,
"step": 1450
},
{
"epoch": 6.69,
"learning_rate": 0.0001,
"loss": 0.3854,
"step": 1451
},
{
"epoch": 6.7,
"learning_rate": 0.0001,
"loss": 0.4093,
"step": 1452
},
{
"epoch": 6.7,
"learning_rate": 0.0001,
"loss": 0.4375,
"step": 1453
},
{
"epoch": 6.7,
"learning_rate": 0.0001,
"loss": 0.3779,
"step": 1454
},
{
"epoch": 6.71,
"learning_rate": 0.0001,
"loss": 0.3994,
"step": 1455
},
{
"epoch": 6.71,
"learning_rate": 0.0001,
"loss": 0.4371,
"step": 1456
},
{
"epoch": 6.72,
"learning_rate": 0.0001,
"loss": 0.3971,
"step": 1457
},
{
"epoch": 6.72,
"learning_rate": 0.0001,
"loss": 0.3544,
"step": 1458
},
{
"epoch": 6.73,
"learning_rate": 0.0001,
"loss": 0.3828,
"step": 1459
},
{
"epoch": 6.73,
"learning_rate": 0.0001,
"loss": 0.3705,
"step": 1460
},
{
"epoch": 6.74,
"learning_rate": 0.0001,
"loss": 0.3735,
"step": 1461
},
{
"epoch": 6.74,
"learning_rate": 0.0001,
"loss": 0.3559,
"step": 1462
},
{
"epoch": 6.75,
"learning_rate": 0.0001,
"loss": 0.361,
"step": 1463
},
{
"epoch": 6.75,
"learning_rate": 0.0001,
"loss": 0.3925,
"step": 1464
},
{
"epoch": 6.76,
"learning_rate": 0.0001,
"loss": 0.3749,
"step": 1465
},
{
"epoch": 6.76,
"learning_rate": 0.0001,
"loss": 0.3661,
"step": 1466
},
{
"epoch": 6.76,
"learning_rate": 0.0001,
"loss": 0.3407,
"step": 1467
},
{
"epoch": 6.77,
"learning_rate": 0.0001,
"loss": 0.3816,
"step": 1468
},
{
"epoch": 6.77,
"learning_rate": 0.0001,
"loss": 0.3196,
"step": 1469
},
{
"epoch": 6.78,
"learning_rate": 0.0001,
"loss": 0.3676,
"step": 1470
},
{
"epoch": 6.78,
"learning_rate": 0.0001,
"loss": 0.3958,
"step": 1471
},
{
"epoch": 6.79,
"learning_rate": 0.0001,
"loss": 0.3897,
"step": 1472
},
{
"epoch": 6.79,
"learning_rate": 0.0001,
"loss": 0.3844,
"step": 1473
},
{
"epoch": 6.8,
"learning_rate": 0.0001,
"loss": 0.3769,
"step": 1474
},
{
"epoch": 6.8,
"learning_rate": 0.0001,
"loss": 0.3522,
"step": 1475
},
{
"epoch": 6.81,
"learning_rate": 0.0001,
"loss": 0.4271,
"step": 1476
},
{
"epoch": 6.81,
"learning_rate": 0.0001,
"loss": 0.3735,
"step": 1477
},
{
"epoch": 6.81,
"learning_rate": 0.0001,
"loss": 0.3528,
"step": 1478
},
{
"epoch": 6.82,
"learning_rate": 0.0001,
"loss": 0.3415,
"step": 1479
},
{
"epoch": 6.82,
"learning_rate": 0.0001,
"loss": 0.3945,
"step": 1480
},
{
"epoch": 6.83,
"learning_rate": 0.0001,
"loss": 0.4009,
"step": 1481
},
{
"epoch": 6.83,
"learning_rate": 0.0001,
"loss": 0.3436,
"step": 1482
},
{
"epoch": 6.84,
"learning_rate": 0.0001,
"loss": 0.3477,
"step": 1483
},
{
"epoch": 6.84,
"learning_rate": 0.0001,
"loss": 0.3866,
"step": 1484
},
{
"epoch": 6.85,
"learning_rate": 0.0001,
"loss": 0.3713,
"step": 1485
},
{
"epoch": 6.85,
"learning_rate": 0.0001,
"loss": 0.3713,
"step": 1486
},
{
"epoch": 6.86,
"learning_rate": 0.0001,
"loss": 0.3716,
"step": 1487
},
{
"epoch": 6.86,
"learning_rate": 0.0001,
"loss": 0.3703,
"step": 1488
},
{
"epoch": 6.87,
"learning_rate": 0.0001,
"loss": 0.3521,
"step": 1489
},
{
"epoch": 6.87,
"learning_rate": 0.0001,
"loss": 0.3939,
"step": 1490
},
{
"epoch": 6.87,
"learning_rate": 0.0001,
"loss": 0.347,
"step": 1491
},
{
"epoch": 6.88,
"learning_rate": 0.0001,
"loss": 0.3591,
"step": 1492
},
{
"epoch": 6.88,
"learning_rate": 0.0001,
"loss": 0.3987,
"step": 1493
},
{
"epoch": 6.89,
"learning_rate": 0.0001,
"loss": 0.3337,
"step": 1494
},
{
"epoch": 6.89,
"learning_rate": 0.0001,
"loss": 0.4649,
"step": 1495
},
{
"epoch": 6.9,
"learning_rate": 0.0001,
"loss": 0.3953,
"step": 1496
},
{
"epoch": 6.9,
"learning_rate": 0.0001,
"loss": 0.366,
"step": 1497
},
{
"epoch": 6.91,
"learning_rate": 0.0001,
"loss": 0.4247,
"step": 1498
},
{
"epoch": 6.91,
"learning_rate": 0.0001,
"loss": 0.3533,
"step": 1499
},
{
"epoch": 6.92,
"learning_rate": 0.0001,
"loss": 0.4125,
"step": 1500
},
{
"epoch": 6.92,
"learning_rate": 0.0001,
"loss": 0.3597,
"step": 1501
},
{
"epoch": 6.93,
"learning_rate": 0.0001,
"loss": 0.3799,
"step": 1502
},
{
"epoch": 6.93,
"learning_rate": 0.0001,
"loss": 0.3474,
"step": 1503
},
{
"epoch": 6.93,
"learning_rate": 0.0001,
"loss": 0.3815,
"step": 1504
},
{
"epoch": 6.94,
"learning_rate": 0.0001,
"loss": 0.3961,
"step": 1505
},
{
"epoch": 6.94,
"learning_rate": 0.0001,
"loss": 0.3578,
"step": 1506
},
{
"epoch": 6.95,
"learning_rate": 0.0001,
"loss": 0.3375,
"step": 1507
},
{
"epoch": 6.95,
"learning_rate": 0.0001,
"loss": 0.3491,
"step": 1508
},
{
"epoch": 6.96,
"learning_rate": 0.0001,
"loss": 0.3873,
"step": 1509
},
{
"epoch": 6.96,
"learning_rate": 0.0001,
"loss": 0.4148,
"step": 1510
},
{
"epoch": 6.97,
"learning_rate": 0.0001,
"loss": 0.3893,
"step": 1511
},
{
"epoch": 6.97,
"learning_rate": 0.0001,
"loss": 0.3838,
"step": 1512
},
{
"epoch": 6.98,
"learning_rate": 0.0001,
"loss": 0.3759,
"step": 1513
},
{
"epoch": 6.98,
"learning_rate": 0.0001,
"loss": 0.3808,
"step": 1514
},
{
"epoch": 6.99,
"learning_rate": 0.0001,
"loss": 0.3898,
"step": 1515
},
{
"epoch": 6.99,
"learning_rate": 0.0001,
"loss": 0.4296,
"step": 1516
},
{
"epoch": 6.99,
"learning_rate": 0.0001,
"loss": 0.3425,
"step": 1517
},
{
"epoch": 7.0,
"learning_rate": 0.0001,
"loss": 0.3799,
"step": 1518
},
{
"epoch": 7.0,
"learning_rate": 0.0001,
"loss": 0.309,
"step": 1519
},
{
"epoch": 7.01,
"learning_rate": 0.0001,
"loss": 0.2927,
"step": 1520
},
{
"epoch": 7.01,
"learning_rate": 0.0001,
"loss": 0.2768,
"step": 1521
},
{
"epoch": 7.02,
"learning_rate": 0.0001,
"loss": 0.3285,
"step": 1522
},
{
"epoch": 7.02,
"learning_rate": 0.0001,
"loss": 0.3043,
"step": 1523
},
{
"epoch": 7.03,
"learning_rate": 0.0001,
"loss": 0.297,
"step": 1524
},
{
"epoch": 7.03,
"learning_rate": 0.0001,
"loss": 0.2863,
"step": 1525
},
{
"epoch": 7.04,
"learning_rate": 0.0001,
"loss": 0.2855,
"step": 1526
},
{
"epoch": 7.04,
"learning_rate": 0.0001,
"loss": 0.2844,
"step": 1527
},
{
"epoch": 7.05,
"learning_rate": 0.0001,
"loss": 0.2917,
"step": 1528
},
{
"epoch": 7.05,
"learning_rate": 0.0001,
"loss": 0.2999,
"step": 1529
},
{
"epoch": 7.05,
"learning_rate": 0.0001,
"loss": 0.2758,
"step": 1530
},
{
"epoch": 7.06,
"learning_rate": 0.0001,
"loss": 0.2997,
"step": 1531
},
{
"epoch": 7.06,
"learning_rate": 0.0001,
"loss": 0.2994,
"step": 1532
},
{
"epoch": 7.07,
"learning_rate": 0.0001,
"loss": 0.3151,
"step": 1533
},
{
"epoch": 7.07,
"learning_rate": 0.0001,
"loss": 0.3036,
"step": 1534
},
{
"epoch": 7.08,
"learning_rate": 0.0001,
"loss": 0.3224,
"step": 1535
},
{
"epoch": 7.08,
"learning_rate": 0.0001,
"loss": 0.3277,
"step": 1536
},
{
"epoch": 7.09,
"learning_rate": 0.0001,
"loss": 0.3192,
"step": 1537
},
{
"epoch": 7.09,
"learning_rate": 0.0001,
"loss": 0.2811,
"step": 1538
},
{
"epoch": 7.1,
"learning_rate": 0.0001,
"loss": 0.2786,
"step": 1539
},
{
"epoch": 7.1,
"learning_rate": 0.0001,
"loss": 0.323,
"step": 1540
},
{
"epoch": 7.11,
"learning_rate": 0.0001,
"loss": 0.3168,
"step": 1541
},
{
"epoch": 7.11,
"learning_rate": 0.0001,
"loss": 0.3194,
"step": 1542
},
{
"epoch": 7.11,
"learning_rate": 0.0001,
"loss": 0.2507,
"step": 1543
},
{
"epoch": 7.12,
"learning_rate": 0.0001,
"loss": 0.3337,
"step": 1544
},
{
"epoch": 7.12,
"learning_rate": 0.0001,
"loss": 0.3051,
"step": 1545
},
{
"epoch": 7.13,
"learning_rate": 0.0001,
"loss": 0.2833,
"step": 1546
},
{
"epoch": 7.13,
"learning_rate": 0.0001,
"loss": 0.2725,
"step": 1547
},
{
"epoch": 7.14,
"learning_rate": 0.0001,
"loss": 0.2956,
"step": 1548
},
{
"epoch": 7.14,
"learning_rate": 0.0001,
"loss": 0.3181,
"step": 1549
},
{
"epoch": 7.15,
"learning_rate": 0.0001,
"loss": 0.2878,
"step": 1550
},
{
"epoch": 7.15,
"learning_rate": 0.0001,
"loss": 0.3075,
"step": 1551
},
{
"epoch": 7.16,
"learning_rate": 0.0001,
"loss": 0.3265,
"step": 1552
},
{
"epoch": 7.16,
"learning_rate": 0.0001,
"loss": 0.3173,
"step": 1553
},
{
"epoch": 7.17,
"learning_rate": 0.0001,
"loss": 0.2878,
"step": 1554
},
{
"epoch": 7.17,
"learning_rate": 0.0001,
"loss": 0.3044,
"step": 1555
},
{
"epoch": 7.17,
"learning_rate": 0.0001,
"loss": 0.264,
"step": 1556
},
{
"epoch": 7.18,
"learning_rate": 0.0001,
"loss": 0.2759,
"step": 1557
},
{
"epoch": 7.18,
"learning_rate": 0.0001,
"loss": 0.2586,
"step": 1558
},
{
"epoch": 7.19,
"learning_rate": 0.0001,
"loss": 0.2975,
"step": 1559
},
{
"epoch": 7.19,
"learning_rate": 0.0001,
"loss": 0.2863,
"step": 1560
},
{
"epoch": 7.2,
"learning_rate": 0.0001,
"loss": 0.3014,
"step": 1561
},
{
"epoch": 7.2,
"learning_rate": 0.0001,
"loss": 0.3316,
"step": 1562
},
{
"epoch": 7.21,
"learning_rate": 0.0001,
"loss": 0.3081,
"step": 1563
},
{
"epoch": 7.21,
"learning_rate": 0.0001,
"loss": 0.3313,
"step": 1564
},
{
"epoch": 7.22,
"learning_rate": 0.0001,
"loss": 0.3297,
"step": 1565
},
{
"epoch": 7.22,
"learning_rate": 0.0001,
"loss": 0.2662,
"step": 1566
},
{
"epoch": 7.23,
"learning_rate": 0.0001,
"loss": 0.3024,
"step": 1567
},
{
"epoch": 7.23,
"learning_rate": 0.0001,
"loss": 0.3171,
"step": 1568
},
{
"epoch": 7.23,
"learning_rate": 0.0001,
"loss": 0.3232,
"step": 1569
},
{
"epoch": 7.24,
"learning_rate": 0.0001,
"loss": 0.3238,
"step": 1570
},
{
"epoch": 7.24,
"learning_rate": 0.0001,
"loss": 0.2826,
"step": 1571
},
{
"epoch": 7.25,
"learning_rate": 0.0001,
"loss": 0.3394,
"step": 1572
},
{
"epoch": 7.25,
"learning_rate": 0.0001,
"loss": 0.2849,
"step": 1573
},
{
"epoch": 7.26,
"learning_rate": 0.0001,
"loss": 0.2734,
"step": 1574
},
{
"epoch": 7.26,
"learning_rate": 0.0001,
"loss": 0.2852,
"step": 1575
},
{
"epoch": 7.27,
"learning_rate": 0.0001,
"loss": 0.2974,
"step": 1576
},
{
"epoch": 7.27,
"learning_rate": 0.0001,
"loss": 0.3513,
"step": 1577
},
{
"epoch": 7.28,
"learning_rate": 0.0001,
"loss": 0.3234,
"step": 1578
},
{
"epoch": 7.28,
"learning_rate": 0.0001,
"loss": 0.3373,
"step": 1579
},
{
"epoch": 7.29,
"learning_rate": 0.0001,
"loss": 0.3406,
"step": 1580
},
{
"epoch": 7.29,
"learning_rate": 0.0001,
"loss": 0.3136,
"step": 1581
},
{
"epoch": 7.29,
"learning_rate": 0.0001,
"loss": 0.3037,
"step": 1582
},
{
"epoch": 7.3,
"learning_rate": 0.0001,
"loss": 0.3088,
"step": 1583
},
{
"epoch": 7.3,
"learning_rate": 0.0001,
"loss": 0.3129,
"step": 1584
},
{
"epoch": 7.31,
"learning_rate": 0.0001,
"loss": 0.3407,
"step": 1585
},
{
"epoch": 7.31,
"learning_rate": 0.0001,
"loss": 0.3123,
"step": 1586
},
{
"epoch": 7.32,
"learning_rate": 0.0001,
"loss": 0.3204,
"step": 1587
},
{
"epoch": 7.32,
"learning_rate": 0.0001,
"loss": 0.2987,
"step": 1588
},
{
"epoch": 7.33,
"learning_rate": 0.0001,
"loss": 0.2619,
"step": 1589
},
{
"epoch": 7.33,
"learning_rate": 0.0001,
"loss": 0.2884,
"step": 1590
},
{
"epoch": 7.34,
"learning_rate": 0.0001,
"loss": 0.2667,
"step": 1591
},
{
"epoch": 7.34,
"learning_rate": 0.0001,
"loss": 0.281,
"step": 1592
},
{
"epoch": 7.35,
"learning_rate": 0.0001,
"loss": 0.3181,
"step": 1593
},
{
"epoch": 7.35,
"learning_rate": 0.0001,
"loss": 0.2739,
"step": 1594
},
{
"epoch": 7.35,
"learning_rate": 0.0001,
"loss": 0.3274,
"step": 1595
},
{
"epoch": 7.36,
"learning_rate": 0.0001,
"loss": 0.3156,
"step": 1596
},
{
"epoch": 7.36,
"learning_rate": 0.0001,
"loss": 0.3105,
"step": 1597
},
{
"epoch": 7.37,
"learning_rate": 0.0001,
"loss": 0.3572,
"step": 1598
},
{
"epoch": 7.37,
"learning_rate": 0.0001,
"loss": 0.3606,
"step": 1599
},
{
"epoch": 7.38,
"learning_rate": 0.0001,
"loss": 0.3434,
"step": 1600
},
{
"epoch": 7.38,
"learning_rate": 0.0001,
"loss": 0.3203,
"step": 1601
},
{
"epoch": 7.39,
"learning_rate": 0.0001,
"loss": 0.3069,
"step": 1602
},
{
"epoch": 7.39,
"learning_rate": 0.0001,
"loss": 0.331,
"step": 1603
},
{
"epoch": 7.4,
"learning_rate": 0.0001,
"loss": 0.36,
"step": 1604
},
{
"epoch": 7.4,
"learning_rate": 0.0001,
"loss": 0.3383,
"step": 1605
},
{
"epoch": 7.41,
"learning_rate": 0.0001,
"loss": 0.3178,
"step": 1606
},
{
"epoch": 7.41,
"learning_rate": 0.0001,
"loss": 0.2704,
"step": 1607
},
{
"epoch": 7.41,
"learning_rate": 0.0001,
"loss": 0.3175,
"step": 1608
},
{
"epoch": 7.42,
"learning_rate": 0.0001,
"loss": 0.3236,
"step": 1609
},
{
"epoch": 7.42,
"learning_rate": 0.0001,
"loss": 0.3159,
"step": 1610
},
{
"epoch": 7.43,
"learning_rate": 0.0001,
"loss": 0.3285,
"step": 1611
},
{
"epoch": 7.43,
"learning_rate": 0.0001,
"loss": 0.3224,
"step": 1612
},
{
"epoch": 7.44,
"learning_rate": 0.0001,
"loss": 0.3059,
"step": 1613
},
{
"epoch": 7.44,
"learning_rate": 0.0001,
"loss": 0.3012,
"step": 1614
},
{
"epoch": 7.45,
"learning_rate": 0.0001,
"loss": 0.3208,
"step": 1615
},
{
"epoch": 7.45,
"learning_rate": 0.0001,
"loss": 0.2969,
"step": 1616
},
{
"epoch": 7.46,
"learning_rate": 0.0001,
"loss": 0.3117,
"step": 1617
},
{
"epoch": 7.46,
"learning_rate": 0.0001,
"loss": 0.2987,
"step": 1618
},
{
"epoch": 7.47,
"learning_rate": 0.0001,
"loss": 0.3626,
"step": 1619
},
{
"epoch": 7.47,
"learning_rate": 0.0001,
"loss": 0.3215,
"step": 1620
},
{
"epoch": 7.47,
"learning_rate": 0.0001,
"loss": 0.3418,
"step": 1621
},
{
"epoch": 7.48,
"learning_rate": 0.0001,
"loss": 0.3776,
"step": 1622
},
{
"epoch": 7.48,
"learning_rate": 0.0001,
"loss": 0.3112,
"step": 1623
},
{
"epoch": 7.49,
"learning_rate": 0.0001,
"loss": 0.3191,
"step": 1624
},
{
"epoch": 7.49,
"learning_rate": 0.0001,
"loss": 0.3287,
"step": 1625
},
{
"epoch": 7.5,
"learning_rate": 0.0001,
"loss": 0.3056,
"step": 1626
},
{
"epoch": 7.5,
"learning_rate": 0.0001,
"loss": 0.339,
"step": 1627
},
{
"epoch": 7.51,
"learning_rate": 0.0001,
"loss": 0.3315,
"step": 1628
},
{
"epoch": 7.51,
"learning_rate": 0.0001,
"loss": 0.3587,
"step": 1629
},
{
"epoch": 7.52,
"learning_rate": 0.0001,
"loss": 0.3439,
"step": 1630
},
{
"epoch": 7.52,
"learning_rate": 0.0001,
"loss": 0.3166,
"step": 1631
},
{
"epoch": 7.53,
"learning_rate": 0.0001,
"loss": 0.3481,
"step": 1632
},
{
"epoch": 7.53,
"learning_rate": 0.0001,
"loss": 0.2733,
"step": 1633
},
{
"epoch": 7.53,
"learning_rate": 0.0001,
"loss": 0.3231,
"step": 1634
},
{
"epoch": 7.54,
"learning_rate": 0.0001,
"loss": 0.3636,
"step": 1635
},
{
"epoch": 7.54,
"learning_rate": 0.0001,
"loss": 0.3614,
"step": 1636
},
{
"epoch": 7.55,
"learning_rate": 0.0001,
"loss": 0.3096,
"step": 1637
},
{
"epoch": 7.55,
"learning_rate": 0.0001,
"loss": 0.2882,
"step": 1638
},
{
"epoch": 7.56,
"learning_rate": 0.0001,
"loss": 0.3557,
"step": 1639
},
{
"epoch": 7.56,
"learning_rate": 0.0001,
"loss": 0.3399,
"step": 1640
},
{
"epoch": 7.57,
"learning_rate": 0.0001,
"loss": 0.3062,
"step": 1641
},
{
"epoch": 7.57,
"learning_rate": 0.0001,
"loss": 0.3224,
"step": 1642
},
{
"epoch": 7.58,
"learning_rate": 0.0001,
"loss": 0.2981,
"step": 1643
},
{
"epoch": 7.58,
"learning_rate": 0.0001,
"loss": 0.321,
"step": 1644
},
{
"epoch": 7.59,
"learning_rate": 0.0001,
"loss": 0.3223,
"step": 1645
},
{
"epoch": 7.59,
"learning_rate": 0.0001,
"loss": 0.3191,
"step": 1646
},
{
"epoch": 7.59,
"learning_rate": 0.0001,
"loss": 0.3001,
"step": 1647
},
{
"epoch": 7.6,
"learning_rate": 0.0001,
"loss": 0.3403,
"step": 1648
},
{
"epoch": 7.6,
"learning_rate": 0.0001,
"loss": 0.3274,
"step": 1649
},
{
"epoch": 7.61,
"learning_rate": 0.0001,
"loss": 0.3224,
"step": 1650
},
{
"epoch": 7.61,
"learning_rate": 0.0001,
"loss": 0.3241,
"step": 1651
},
{
"epoch": 7.62,
"learning_rate": 0.0001,
"loss": 0.3327,
"step": 1652
},
{
"epoch": 7.62,
"learning_rate": 0.0001,
"loss": 0.3522,
"step": 1653
},
{
"epoch": 7.63,
"learning_rate": 0.0001,
"loss": 0.3416,
"step": 1654
},
{
"epoch": 7.63,
"learning_rate": 0.0001,
"loss": 0.3089,
"step": 1655
},
{
"epoch": 7.64,
"learning_rate": 0.0001,
"loss": 0.308,
"step": 1656
},
{
"epoch": 7.64,
"learning_rate": 0.0001,
"loss": 0.3183,
"step": 1657
},
{
"epoch": 7.64,
"learning_rate": 0.0001,
"loss": 0.2992,
"step": 1658
},
{
"epoch": 7.65,
"learning_rate": 0.0001,
"loss": 0.3538,
"step": 1659
},
{
"epoch": 7.65,
"learning_rate": 0.0001,
"loss": 0.3365,
"step": 1660
},
{
"epoch": 7.66,
"learning_rate": 0.0001,
"loss": 0.3057,
"step": 1661
},
{
"epoch": 7.66,
"learning_rate": 0.0001,
"loss": 0.3427,
"step": 1662
},
{
"epoch": 7.67,
"learning_rate": 0.0001,
"loss": 0.3507,
"step": 1663
},
{
"epoch": 7.67,
"learning_rate": 0.0001,
"loss": 0.325,
"step": 1664
},
{
"epoch": 7.68,
"learning_rate": 0.0001,
"loss": 0.3456,
"step": 1665
},
{
"epoch": 7.68,
"learning_rate": 0.0001,
"loss": 0.3604,
"step": 1666
},
{
"epoch": 7.69,
"learning_rate": 0.0001,
"loss": 0.3042,
"step": 1667
},
{
"epoch": 7.69,
"learning_rate": 0.0001,
"loss": 0.3297,
"step": 1668
},
{
"epoch": 7.7,
"learning_rate": 0.0001,
"loss": 0.267,
"step": 1669
},
{
"epoch": 7.7,
"learning_rate": 0.0001,
"loss": 0.3758,
"step": 1670
},
{
"epoch": 7.7,
"learning_rate": 0.0001,
"loss": 0.3123,
"step": 1671
},
{
"epoch": 7.71,
"learning_rate": 0.0001,
"loss": 0.3448,
"step": 1672
},
{
"epoch": 7.71,
"learning_rate": 0.0001,
"loss": 0.3415,
"step": 1673
},
{
"epoch": 7.72,
"learning_rate": 0.0001,
"loss": 0.315,
"step": 1674
},
{
"epoch": 7.72,
"learning_rate": 0.0001,
"loss": 0.3488,
"step": 1675
},
{
"epoch": 7.73,
"learning_rate": 0.0001,
"loss": 0.3407,
"step": 1676
},
{
"epoch": 7.73,
"learning_rate": 0.0001,
"loss": 0.2834,
"step": 1677
},
{
"epoch": 7.74,
"learning_rate": 0.0001,
"loss": 0.2846,
"step": 1678
},
{
"epoch": 7.74,
"learning_rate": 0.0001,
"loss": 0.3383,
"step": 1679
},
{
"epoch": 7.75,
"learning_rate": 0.0001,
"loss": 0.3309,
"step": 1680
},
{
"epoch": 7.75,
"learning_rate": 0.0001,
"loss": 0.3131,
"step": 1681
},
{
"epoch": 7.76,
"learning_rate": 0.0001,
"loss": 0.3532,
"step": 1682
},
{
"epoch": 7.76,
"learning_rate": 0.0001,
"loss": 0.3886,
"step": 1683
},
{
"epoch": 7.76,
"learning_rate": 0.0001,
"loss": 0.3522,
"step": 1684
},
{
"epoch": 7.77,
"learning_rate": 0.0001,
"loss": 0.3359,
"step": 1685
},
{
"epoch": 7.77,
"learning_rate": 0.0001,
"loss": 0.3518,
"step": 1686
},
{
"epoch": 7.78,
"learning_rate": 0.0001,
"loss": 0.3556,
"step": 1687
},
{
"epoch": 7.78,
"learning_rate": 0.0001,
"loss": 0.3293,
"step": 1688
},
{
"epoch": 7.79,
"learning_rate": 0.0001,
"loss": 0.3352,
"step": 1689
},
{
"epoch": 7.79,
"learning_rate": 0.0001,
"loss": 0.3746,
"step": 1690
},
{
"epoch": 7.8,
"learning_rate": 0.0001,
"loss": 0.3321,
"step": 1691
},
{
"epoch": 7.8,
"learning_rate": 0.0001,
"loss": 0.3545,
"step": 1692
},
{
"epoch": 7.81,
"learning_rate": 0.0001,
"loss": 0.3177,
"step": 1693
},
{
"epoch": 7.81,
"learning_rate": 0.0001,
"loss": 0.3392,
"step": 1694
},
{
"epoch": 7.82,
"learning_rate": 0.0001,
"loss": 0.3431,
"step": 1695
},
{
"epoch": 7.82,
"learning_rate": 0.0001,
"loss": 0.3046,
"step": 1696
},
{
"epoch": 7.82,
"learning_rate": 0.0001,
"loss": 0.3435,
"step": 1697
},
{
"epoch": 7.83,
"learning_rate": 0.0001,
"loss": 0.3407,
"step": 1698
},
{
"epoch": 7.83,
"learning_rate": 0.0001,
"loss": 0.3337,
"step": 1699
},
{
"epoch": 7.84,
"learning_rate": 0.0001,
"loss": 0.3186,
"step": 1700
},
{
"epoch": 7.84,
"learning_rate": 0.0001,
"loss": 0.3365,
"step": 1701
},
{
"epoch": 7.85,
"learning_rate": 0.0001,
"loss": 0.35,
"step": 1702
},
{
"epoch": 7.85,
"learning_rate": 0.0001,
"loss": 0.3148,
"step": 1703
},
{
"epoch": 7.86,
"learning_rate": 0.0001,
"loss": 0.3656,
"step": 1704
},
{
"epoch": 7.86,
"learning_rate": 0.0001,
"loss": 0.3427,
"step": 1705
},
{
"epoch": 7.87,
"learning_rate": 0.0001,
"loss": 0.3374,
"step": 1706
},
{
"epoch": 7.87,
"learning_rate": 0.0001,
"loss": 0.3192,
"step": 1707
},
{
"epoch": 7.88,
"learning_rate": 0.0001,
"loss": 0.3306,
"step": 1708
},
{
"epoch": 7.88,
"learning_rate": 0.0001,
"loss": 0.3067,
"step": 1709
},
{
"epoch": 7.88,
"learning_rate": 0.0001,
"loss": 0.3546,
"step": 1710
},
{
"epoch": 7.89,
"learning_rate": 0.0001,
"loss": 0.3553,
"step": 1711
},
{
"epoch": 7.89,
"learning_rate": 0.0001,
"loss": 0.3415,
"step": 1712
},
{
"epoch": 7.9,
"learning_rate": 0.0001,
"loss": 0.3717,
"step": 1713
},
{
"epoch": 7.9,
"learning_rate": 0.0001,
"loss": 0.4068,
"step": 1714
},
{
"epoch": 7.91,
"learning_rate": 0.0001,
"loss": 0.3399,
"step": 1715
},
{
"epoch": 7.91,
"learning_rate": 0.0001,
"loss": 0.3464,
"step": 1716
},
{
"epoch": 7.92,
"learning_rate": 0.0001,
"loss": 0.338,
"step": 1717
},
{
"epoch": 7.92,
"learning_rate": 0.0001,
"loss": 0.3602,
"step": 1718
},
{
"epoch": 7.93,
"learning_rate": 0.0001,
"loss": 0.336,
"step": 1719
},
{
"epoch": 7.93,
"learning_rate": 0.0001,
"loss": 0.3517,
"step": 1720
},
{
"epoch": 7.94,
"learning_rate": 0.0001,
"loss": 0.345,
"step": 1721
},
{
"epoch": 7.94,
"learning_rate": 0.0001,
"loss": 0.3259,
"step": 1722
},
{
"epoch": 7.94,
"learning_rate": 0.0001,
"loss": 0.3646,
"step": 1723
},
{
"epoch": 7.95,
"learning_rate": 0.0001,
"loss": 0.3663,
"step": 1724
},
{
"epoch": 7.95,
"learning_rate": 0.0001,
"loss": 0.3306,
"step": 1725
},
{
"epoch": 7.96,
"learning_rate": 0.0001,
"loss": 0.3434,
"step": 1726
},
{
"epoch": 7.96,
"learning_rate": 0.0001,
"loss": 0.3331,
"step": 1727
},
{
"epoch": 7.97,
"learning_rate": 0.0001,
"loss": 0.3881,
"step": 1728
},
{
"epoch": 7.97,
"learning_rate": 0.0001,
"loss": 0.3421,
"step": 1729
},
{
"epoch": 7.98,
"learning_rate": 0.0001,
"loss": 0.3504,
"step": 1730
},
{
"epoch": 7.98,
"learning_rate": 0.0001,
"loss": 0.3772,
"step": 1731
},
{
"epoch": 7.99,
"learning_rate": 0.0001,
"loss": 0.3235,
"step": 1732
},
{
"epoch": 7.99,
"learning_rate": 0.0001,
"loss": 0.3514,
"step": 1733
},
{
"epoch": 8.0,
"learning_rate": 0.0001,
"loss": 0.3959,
"step": 1734
},
{
"epoch": 8.0,
"learning_rate": 0.0001,
"loss": 0.3014,
"step": 1735
},
{
"epoch": 8.0,
"learning_rate": 0.0001,
"loss": 0.2539,
"step": 1736
},
{
"epoch": 8.01,
"learning_rate": 0.0001,
"loss": 0.2455,
"step": 1737
},
{
"epoch": 8.01,
"learning_rate": 0.0001,
"loss": 0.255,
"step": 1738
},
{
"epoch": 8.02,
"learning_rate": 0.0001,
"loss": 0.2483,
"step": 1739
},
{
"epoch": 8.02,
"learning_rate": 0.0001,
"loss": 0.2355,
"step": 1740
},
{
"epoch": 8.03,
"learning_rate": 0.0001,
"loss": 0.2538,
"step": 1741
},
{
"epoch": 8.03,
"learning_rate": 0.0001,
"loss": 0.2824,
"step": 1742
},
{
"epoch": 8.04,
"learning_rate": 0.0001,
"loss": 0.2724,
"step": 1743
},
{
"epoch": 8.04,
"learning_rate": 0.0001,
"loss": 0.2563,
"step": 1744
},
{
"epoch": 8.05,
"learning_rate": 0.0001,
"loss": 0.2549,
"step": 1745
},
{
"epoch": 8.05,
"learning_rate": 0.0001,
"loss": 0.2714,
"step": 1746
},
{
"epoch": 8.06,
"learning_rate": 0.0001,
"loss": 0.2725,
"step": 1747
},
{
"epoch": 8.06,
"learning_rate": 0.0001,
"loss": 0.2746,
"step": 1748
},
{
"epoch": 8.06,
"learning_rate": 0.0001,
"loss": 0.2815,
"step": 1749
},
{
"epoch": 8.07,
"learning_rate": 0.0001,
"loss": 0.2747,
"step": 1750
},
{
"epoch": 8.07,
"learning_rate": 0.0001,
"loss": 0.2527,
"step": 1751
},
{
"epoch": 8.08,
"learning_rate": 0.0001,
"loss": 0.2677,
"step": 1752
},
{
"epoch": 8.08,
"learning_rate": 0.0001,
"loss": 0.2529,
"step": 1753
},
{
"epoch": 8.09,
"learning_rate": 0.0001,
"loss": 0.2899,
"step": 1754
},
{
"epoch": 8.09,
"learning_rate": 0.0001,
"loss": 0.2845,
"step": 1755
},
{
"epoch": 8.1,
"learning_rate": 0.0001,
"loss": 0.2879,
"step": 1756
},
{
"epoch": 8.1,
"learning_rate": 0.0001,
"loss": 0.2659,
"step": 1757
},
{
"epoch": 8.11,
"learning_rate": 0.0001,
"loss": 0.2901,
"step": 1758
},
{
"epoch": 8.11,
"learning_rate": 0.0001,
"loss": 0.2415,
"step": 1759
},
{
"epoch": 8.12,
"learning_rate": 0.0001,
"loss": 0.2518,
"step": 1760
},
{
"epoch": 8.12,
"learning_rate": 0.0001,
"loss": 0.27,
"step": 1761
},
{
"epoch": 8.12,
"learning_rate": 0.0001,
"loss": 0.2688,
"step": 1762
},
{
"epoch": 8.13,
"learning_rate": 0.0001,
"loss": 0.2771,
"step": 1763
},
{
"epoch": 8.13,
"learning_rate": 0.0001,
"loss": 0.2579,
"step": 1764
},
{
"epoch": 8.14,
"learning_rate": 0.0001,
"loss": 0.2827,
"step": 1765
},
{
"epoch": 8.14,
"learning_rate": 0.0001,
"loss": 0.2394,
"step": 1766
},
{
"epoch": 8.15,
"learning_rate": 0.0001,
"loss": 0.2845,
"step": 1767
},
{
"epoch": 8.15,
"learning_rate": 0.0001,
"loss": 0.2843,
"step": 1768
},
{
"epoch": 8.16,
"learning_rate": 0.0001,
"loss": 0.2743,
"step": 1769
},
{
"epoch": 8.16,
"learning_rate": 0.0001,
"loss": 0.2468,
"step": 1770
},
{
"epoch": 8.17,
"learning_rate": 0.0001,
"loss": 0.2407,
"step": 1771
},
{
"epoch": 8.17,
"learning_rate": 0.0001,
"loss": 0.2372,
"step": 1772
},
{
"epoch": 8.18,
"learning_rate": 0.0001,
"loss": 0.2722,
"step": 1773
},
{
"epoch": 8.18,
"learning_rate": 0.0001,
"loss": 0.2272,
"step": 1774
},
{
"epoch": 8.18,
"learning_rate": 0.0001,
"loss": 0.2833,
"step": 1775
},
{
"epoch": 8.19,
"learning_rate": 0.0001,
"loss": 0.2715,
"step": 1776
},
{
"epoch": 8.19,
"learning_rate": 0.0001,
"loss": 0.2752,
"step": 1777
},
{
"epoch": 8.2,
"learning_rate": 0.0001,
"loss": 0.2583,
"step": 1778
},
{
"epoch": 8.2,
"learning_rate": 0.0001,
"loss": 0.2609,
"step": 1779
},
{
"epoch": 8.21,
"learning_rate": 0.0001,
"loss": 0.3051,
"step": 1780
},
{
"epoch": 8.21,
"learning_rate": 0.0001,
"loss": 0.2662,
"step": 1781
},
{
"epoch": 8.22,
"learning_rate": 0.0001,
"loss": 0.2524,
"step": 1782
},
{
"epoch": 8.22,
"learning_rate": 0.0001,
"loss": 0.3106,
"step": 1783
},
{
"epoch": 8.23,
"learning_rate": 0.0001,
"loss": 0.2867,
"step": 1784
},
{
"epoch": 8.23,
"learning_rate": 0.0001,
"loss": 0.2831,
"step": 1785
},
{
"epoch": 8.24,
"learning_rate": 0.0001,
"loss": 0.2737,
"step": 1786
},
{
"epoch": 8.24,
"learning_rate": 0.0001,
"loss": 0.2767,
"step": 1787
},
{
"epoch": 8.24,
"learning_rate": 0.0001,
"loss": 0.2713,
"step": 1788
},
{
"epoch": 8.25,
"learning_rate": 0.0001,
"loss": 0.2683,
"step": 1789
},
{
"epoch": 8.25,
"learning_rate": 0.0001,
"loss": 0.2843,
"step": 1790
},
{
"epoch": 8.26,
"learning_rate": 0.0001,
"loss": 0.2686,
"step": 1791
},
{
"epoch": 8.26,
"learning_rate": 0.0001,
"loss": 0.2913,
"step": 1792
},
{
"epoch": 8.27,
"learning_rate": 0.0001,
"loss": 0.291,
"step": 1793
},
{
"epoch": 8.27,
"learning_rate": 0.0001,
"loss": 0.3219,
"step": 1794
},
{
"epoch": 8.28,
"learning_rate": 0.0001,
"loss": 0.2536,
"step": 1795
},
{
"epoch": 8.28,
"learning_rate": 0.0001,
"loss": 0.3118,
"step": 1796
},
{
"epoch": 8.29,
"learning_rate": 0.0001,
"loss": 0.2901,
"step": 1797
},
{
"epoch": 8.29,
"learning_rate": 0.0001,
"loss": 0.259,
"step": 1798
},
{
"epoch": 8.3,
"learning_rate": 0.0001,
"loss": 0.2844,
"step": 1799
},
{
"epoch": 8.3,
"learning_rate": 0.0001,
"loss": 0.2857,
"step": 1800
},
{
"epoch": 8.3,
"learning_rate": 0.0001,
"loss": 0.2604,
"step": 1801
},
{
"epoch": 8.31,
"learning_rate": 0.0001,
"loss": 0.3145,
"step": 1802
},
{
"epoch": 8.31,
"learning_rate": 0.0001,
"loss": 0.2512,
"step": 1803
},
{
"epoch": 8.32,
"learning_rate": 0.0001,
"loss": 0.288,
"step": 1804
},
{
"epoch": 8.32,
"learning_rate": 0.0001,
"loss": 0.2946,
"step": 1805
},
{
"epoch": 8.33,
"learning_rate": 0.0001,
"loss": 0.2575,
"step": 1806
},
{
"epoch": 8.33,
"learning_rate": 0.0001,
"loss": 0.2769,
"step": 1807
},
{
"epoch": 8.34,
"learning_rate": 0.0001,
"loss": 0.3162,
"step": 1808
},
{
"epoch": 8.34,
"learning_rate": 0.0001,
"loss": 0.2976,
"step": 1809
},
{
"epoch": 8.35,
"learning_rate": 0.0001,
"loss": 0.2715,
"step": 1810
},
{
"epoch": 8.35,
"learning_rate": 0.0001,
"loss": 0.3322,
"step": 1811
},
{
"epoch": 8.36,
"learning_rate": 0.0001,
"loss": 0.2612,
"step": 1812
},
{
"epoch": 8.36,
"learning_rate": 0.0001,
"loss": 0.2801,
"step": 1813
},
{
"epoch": 8.36,
"learning_rate": 0.0001,
"loss": 0.289,
"step": 1814
},
{
"epoch": 8.37,
"learning_rate": 0.0001,
"loss": 0.2702,
"step": 1815
},
{
"epoch": 8.37,
"learning_rate": 0.0001,
"loss": 0.3045,
"step": 1816
},
{
"epoch": 8.38,
"learning_rate": 0.0001,
"loss": 0.248,
"step": 1817
},
{
"epoch": 8.38,
"learning_rate": 0.0001,
"loss": 0.292,
"step": 1818
},
{
"epoch": 8.39,
"learning_rate": 0.0001,
"loss": 0.3352,
"step": 1819
},
{
"epoch": 8.39,
"learning_rate": 0.0001,
"loss": 0.2823,
"step": 1820
},
{
"epoch": 8.4,
"learning_rate": 0.0001,
"loss": 0.3285,
"step": 1821
},
{
"epoch": 8.4,
"learning_rate": 0.0001,
"loss": 0.2823,
"step": 1822
},
{
"epoch": 8.41,
"learning_rate": 0.0001,
"loss": 0.3081,
"step": 1823
},
{
"epoch": 8.41,
"learning_rate": 0.0001,
"loss": 0.2827,
"step": 1824
},
{
"epoch": 8.41,
"learning_rate": 0.0001,
"loss": 0.3046,
"step": 1825
},
{
"epoch": 8.42,
"learning_rate": 0.0001,
"loss": 0.3041,
"step": 1826
},
{
"epoch": 8.42,
"learning_rate": 0.0001,
"loss": 0.2708,
"step": 1827
},
{
"epoch": 8.43,
"learning_rate": 0.0001,
"loss": 0.2929,
"step": 1828
},
{
"epoch": 8.43,
"learning_rate": 0.0001,
"loss": 0.2726,
"step": 1829
},
{
"epoch": 8.44,
"learning_rate": 0.0001,
"loss": 0.2851,
"step": 1830
},
{
"epoch": 8.44,
"learning_rate": 0.0001,
"loss": 0.3169,
"step": 1831
},
{
"epoch": 8.45,
"learning_rate": 0.0001,
"loss": 0.2652,
"step": 1832
},
{
"epoch": 8.45,
"learning_rate": 0.0001,
"loss": 0.2816,
"step": 1833
},
{
"epoch": 8.46,
"learning_rate": 0.0001,
"loss": 0.276,
"step": 1834
},
{
"epoch": 8.46,
"learning_rate": 0.0001,
"loss": 0.3403,
"step": 1835
},
{
"epoch": 8.47,
"learning_rate": 0.0001,
"loss": 0.288,
"step": 1836
},
{
"epoch": 8.47,
"learning_rate": 0.0001,
"loss": 0.2605,
"step": 1837
},
{
"epoch": 8.47,
"learning_rate": 0.0001,
"loss": 0.2943,
"step": 1838
},
{
"epoch": 8.48,
"learning_rate": 0.0001,
"loss": 0.2715,
"step": 1839
},
{
"epoch": 8.48,
"learning_rate": 0.0001,
"loss": 0.3302,
"step": 1840
},
{
"epoch": 8.49,
"learning_rate": 0.0001,
"loss": 0.2837,
"step": 1841
},
{
"epoch": 8.49,
"learning_rate": 0.0001,
"loss": 0.2691,
"step": 1842
},
{
"epoch": 8.5,
"learning_rate": 0.0001,
"loss": 0.2775,
"step": 1843
},
{
"epoch": 8.5,
"learning_rate": 0.0001,
"loss": 0.2728,
"step": 1844
},
{
"epoch": 8.51,
"learning_rate": 0.0001,
"loss": 0.2953,
"step": 1845
},
{
"epoch": 8.51,
"learning_rate": 0.0001,
"loss": 0.2952,
"step": 1846
},
{
"epoch": 8.52,
"learning_rate": 0.0001,
"loss": 0.2949,
"step": 1847
},
{
"epoch": 8.52,
"learning_rate": 0.0001,
"loss": 0.258,
"step": 1848
},
{
"epoch": 8.53,
"learning_rate": 0.0001,
"loss": 0.2817,
"step": 1849
},
{
"epoch": 8.53,
"learning_rate": 0.0001,
"loss": 0.2659,
"step": 1850
},
{
"epoch": 8.53,
"learning_rate": 0.0001,
"loss": 0.304,
"step": 1851
},
{
"epoch": 8.54,
"learning_rate": 0.0001,
"loss": 0.2927,
"step": 1852
},
{
"epoch": 8.54,
"learning_rate": 0.0001,
"loss": 0.3011,
"step": 1853
},
{
"epoch": 8.55,
"learning_rate": 0.0001,
"loss": 0.2932,
"step": 1854
},
{
"epoch": 8.55,
"learning_rate": 0.0001,
"loss": 0.3094,
"step": 1855
},
{
"epoch": 8.56,
"learning_rate": 0.0001,
"loss": 0.3385,
"step": 1856
},
{
"epoch": 8.56,
"learning_rate": 0.0001,
"loss": 0.3212,
"step": 1857
},
{
"epoch": 8.57,
"learning_rate": 0.0001,
"loss": 0.2713,
"step": 1858
},
{
"epoch": 8.57,
"learning_rate": 0.0001,
"loss": 0.2732,
"step": 1859
},
{
"epoch": 8.58,
"learning_rate": 0.0001,
"loss": 0.2871,
"step": 1860
},
{
"epoch": 8.58,
"learning_rate": 0.0001,
"loss": 0.2711,
"step": 1861
},
{
"epoch": 8.59,
"learning_rate": 0.0001,
"loss": 0.3125,
"step": 1862
},
{
"epoch": 8.59,
"learning_rate": 0.0001,
"loss": 0.3438,
"step": 1863
},
{
"epoch": 8.59,
"learning_rate": 0.0001,
"loss": 0.2673,
"step": 1864
},
{
"epoch": 8.6,
"learning_rate": 0.0001,
"loss": 0.3246,
"step": 1865
},
{
"epoch": 8.6,
"learning_rate": 0.0001,
"loss": 0.316,
"step": 1866
},
{
"epoch": 8.61,
"learning_rate": 0.0001,
"loss": 0.2979,
"step": 1867
},
{
"epoch": 8.61,
"learning_rate": 0.0001,
"loss": 0.2926,
"step": 1868
},
{
"epoch": 8.62,
"learning_rate": 0.0001,
"loss": 0.2796,
"step": 1869
},
{
"epoch": 8.62,
"learning_rate": 0.0001,
"loss": 0.2906,
"step": 1870
},
{
"epoch": 8.63,
"learning_rate": 0.0001,
"loss": 0.2948,
"step": 1871
},
{
"epoch": 8.63,
"learning_rate": 0.0001,
"loss": 0.3048,
"step": 1872
},
{
"epoch": 8.64,
"learning_rate": 0.0001,
"loss": 0.3226,
"step": 1873
},
{
"epoch": 8.64,
"learning_rate": 0.0001,
"loss": 0.2924,
"step": 1874
},
{
"epoch": 8.65,
"learning_rate": 0.0001,
"loss": 0.2847,
"step": 1875
},
{
"epoch": 8.65,
"learning_rate": 0.0001,
"loss": 0.3451,
"step": 1876
},
{
"epoch": 8.65,
"learning_rate": 0.0001,
"loss": 0.2951,
"step": 1877
},
{
"epoch": 8.66,
"learning_rate": 0.0001,
"loss": 0.3057,
"step": 1878
},
{
"epoch": 8.66,
"learning_rate": 0.0001,
"loss": 0.2997,
"step": 1879
},
{
"epoch": 8.67,
"learning_rate": 0.0001,
"loss": 0.2708,
"step": 1880
},
{
"epoch": 8.67,
"learning_rate": 0.0001,
"loss": 0.2776,
"step": 1881
},
{
"epoch": 8.68,
"learning_rate": 0.0001,
"loss": 0.2953,
"step": 1882
},
{
"epoch": 8.68,
"learning_rate": 0.0001,
"loss": 0.3063,
"step": 1883
},
{
"epoch": 8.69,
"learning_rate": 0.0001,
"loss": 0.2681,
"step": 1884
},
{
"epoch": 8.69,
"learning_rate": 0.0001,
"loss": 0.2694,
"step": 1885
},
{
"epoch": 8.7,
"learning_rate": 0.0001,
"loss": 0.3243,
"step": 1886
},
{
"epoch": 8.7,
"learning_rate": 0.0001,
"loss": 0.2879,
"step": 1887
},
{
"epoch": 8.71,
"learning_rate": 0.0001,
"loss": 0.3269,
"step": 1888
},
{
"epoch": 8.71,
"learning_rate": 0.0001,
"loss": 0.3117,
"step": 1889
},
{
"epoch": 8.71,
"learning_rate": 0.0001,
"loss": 0.319,
"step": 1890
},
{
"epoch": 8.72,
"learning_rate": 0.0001,
"loss": 0.3066,
"step": 1891
},
{
"epoch": 8.72,
"learning_rate": 0.0001,
"loss": 0.2779,
"step": 1892
},
{
"epoch": 8.73,
"learning_rate": 0.0001,
"loss": 0.2857,
"step": 1893
},
{
"epoch": 8.73,
"learning_rate": 0.0001,
"loss": 0.2891,
"step": 1894
},
{
"epoch": 8.74,
"learning_rate": 0.0001,
"loss": 0.3457,
"step": 1895
},
{
"epoch": 8.74,
"learning_rate": 0.0001,
"loss": 0.2751,
"step": 1896
},
{
"epoch": 8.75,
"learning_rate": 0.0001,
"loss": 0.314,
"step": 1897
},
{
"epoch": 8.75,
"learning_rate": 0.0001,
"loss": 0.3048,
"step": 1898
},
{
"epoch": 8.76,
"learning_rate": 0.0001,
"loss": 0.2978,
"step": 1899
},
{
"epoch": 8.76,
"learning_rate": 0.0001,
"loss": 0.3087,
"step": 1900
},
{
"epoch": 8.77,
"learning_rate": 0.0001,
"loss": 0.2936,
"step": 1901
},
{
"epoch": 8.77,
"learning_rate": 0.0001,
"loss": 0.2665,
"step": 1902
},
{
"epoch": 8.77,
"learning_rate": 0.0001,
"loss": 0.2973,
"step": 1903
},
{
"epoch": 8.78,
"learning_rate": 0.0001,
"loss": 0.3096,
"step": 1904
},
{
"epoch": 8.78,
"learning_rate": 0.0001,
"loss": 0.3427,
"step": 1905
},
{
"epoch": 8.79,
"learning_rate": 0.0001,
"loss": 0.2999,
"step": 1906
},
{
"epoch": 8.79,
"learning_rate": 0.0001,
"loss": 0.2761,
"step": 1907
},
{
"epoch": 8.8,
"learning_rate": 0.0001,
"loss": 0.3652,
"step": 1908
},
{
"epoch": 8.8,
"learning_rate": 0.0001,
"loss": 0.2816,
"step": 1909
},
{
"epoch": 8.81,
"learning_rate": 0.0001,
"loss": 0.3144,
"step": 1910
},
{
"epoch": 8.81,
"learning_rate": 0.0001,
"loss": 0.3216,
"step": 1911
},
{
"epoch": 8.82,
"learning_rate": 0.0001,
"loss": 0.2929,
"step": 1912
},
{
"epoch": 8.82,
"learning_rate": 0.0001,
"loss": 0.3098,
"step": 1913
},
{
"epoch": 8.83,
"learning_rate": 0.0001,
"loss": 0.2873,
"step": 1914
},
{
"epoch": 8.83,
"learning_rate": 0.0001,
"loss": 0.3262,
"step": 1915
},
{
"epoch": 8.83,
"learning_rate": 0.0001,
"loss": 0.34,
"step": 1916
},
{
"epoch": 8.84,
"learning_rate": 0.0001,
"loss": 0.3116,
"step": 1917
},
{
"epoch": 8.84,
"learning_rate": 0.0001,
"loss": 0.277,
"step": 1918
},
{
"epoch": 8.85,
"learning_rate": 0.0001,
"loss": 0.3019,
"step": 1919
},
{
"epoch": 8.85,
"learning_rate": 0.0001,
"loss": 0.319,
"step": 1920
},
{
"epoch": 8.86,
"learning_rate": 0.0001,
"loss": 0.3105,
"step": 1921
},
{
"epoch": 8.86,
"learning_rate": 0.0001,
"loss": 0.3236,
"step": 1922
},
{
"epoch": 8.87,
"learning_rate": 0.0001,
"loss": 0.2933,
"step": 1923
},
{
"epoch": 8.87,
"learning_rate": 0.0001,
"loss": 0.3004,
"step": 1924
},
{
"epoch": 8.88,
"learning_rate": 0.0001,
"loss": 0.3183,
"step": 1925
},
{
"epoch": 8.88,
"learning_rate": 0.0001,
"loss": 0.3179,
"step": 1926
},
{
"epoch": 8.89,
"learning_rate": 0.0001,
"loss": 0.325,
"step": 1927
},
{
"epoch": 8.89,
"learning_rate": 0.0001,
"loss": 0.3265,
"step": 1928
},
{
"epoch": 8.89,
"learning_rate": 0.0001,
"loss": 0.3045,
"step": 1929
},
{
"epoch": 8.9,
"learning_rate": 0.0001,
"loss": 0.2881,
"step": 1930
},
{
"epoch": 8.9,
"learning_rate": 0.0001,
"loss": 0.2784,
"step": 1931
},
{
"epoch": 8.91,
"learning_rate": 0.0001,
"loss": 0.3108,
"step": 1932
},
{
"epoch": 8.91,
"learning_rate": 0.0001,
"loss": 0.3227,
"step": 1933
},
{
"epoch": 8.92,
"learning_rate": 0.0001,
"loss": 0.3388,
"step": 1934
},
{
"epoch": 8.92,
"learning_rate": 0.0001,
"loss": 0.2967,
"step": 1935
},
{
"epoch": 8.93,
"learning_rate": 0.0001,
"loss": 0.3152,
"step": 1936
},
{
"epoch": 8.93,
"learning_rate": 0.0001,
"loss": 0.2774,
"step": 1937
},
{
"epoch": 8.94,
"learning_rate": 0.0001,
"loss": 0.3129,
"step": 1938
},
{
"epoch": 8.94,
"learning_rate": 0.0001,
"loss": 0.2956,
"step": 1939
},
{
"epoch": 8.95,
"learning_rate": 0.0001,
"loss": 0.3222,
"step": 1940
},
{
"epoch": 8.95,
"learning_rate": 0.0001,
"loss": 0.305,
"step": 1941
},
{
"epoch": 8.95,
"learning_rate": 0.0001,
"loss": 0.3256,
"step": 1942
},
{
"epoch": 8.96,
"learning_rate": 0.0001,
"loss": 0.3304,
"step": 1943
},
{
"epoch": 8.96,
"learning_rate": 0.0001,
"loss": 0.3308,
"step": 1944
},
{
"epoch": 8.97,
"learning_rate": 0.0001,
"loss": 0.3468,
"step": 1945
},
{
"epoch": 8.97,
"learning_rate": 0.0001,
"loss": 0.3342,
"step": 1946
},
{
"epoch": 8.98,
"learning_rate": 0.0001,
"loss": 0.2997,
"step": 1947
},
{
"epoch": 8.98,
"learning_rate": 0.0001,
"loss": 0.317,
"step": 1948
},
{
"epoch": 8.99,
"learning_rate": 0.0001,
"loss": 0.3296,
"step": 1949
},
{
"epoch": 8.99,
"learning_rate": 0.0001,
"loss": 0.2921,
"step": 1950
},
{
"epoch": 9.0,
"learning_rate": 0.0001,
"loss": 0.3192,
"step": 1951
},
{
"epoch": 9.0,
"learning_rate": 0.0001,
"loss": 0.2841,
"step": 1952
},
{
"epoch": 9.01,
"learning_rate": 0.0001,
"loss": 0.2293,
"step": 1953
},
{
"epoch": 9.01,
"learning_rate": 0.0001,
"loss": 0.206,
"step": 1954
},
{
"epoch": 9.01,
"learning_rate": 0.0001,
"loss": 0.2286,
"step": 1955
},
{
"epoch": 9.02,
"learning_rate": 0.0001,
"loss": 0.225,
"step": 1956
},
{
"epoch": 9.02,
"learning_rate": 0.0001,
"loss": 0.2405,
"step": 1957
},
{
"epoch": 9.03,
"learning_rate": 0.0001,
"loss": 0.2657,
"step": 1958
},
{
"epoch": 9.03,
"learning_rate": 0.0001,
"loss": 0.2156,
"step": 1959
},
{
"epoch": 9.04,
"learning_rate": 0.0001,
"loss": 0.2633,
"step": 1960
},
{
"epoch": 9.04,
"learning_rate": 0.0001,
"loss": 0.227,
"step": 1961
},
{
"epoch": 9.05,
"learning_rate": 0.0001,
"loss": 0.2235,
"step": 1962
},
{
"epoch": 9.05,
"learning_rate": 0.0001,
"loss": 0.2466,
"step": 1963
},
{
"epoch": 9.06,
"learning_rate": 0.0001,
"loss": 0.207,
"step": 1964
},
{
"epoch": 9.06,
"learning_rate": 0.0001,
"loss": 0.2253,
"step": 1965
},
{
"epoch": 9.07,
"learning_rate": 0.0001,
"loss": 0.2285,
"step": 1966
},
{
"epoch": 9.07,
"learning_rate": 0.0001,
"loss": 0.2409,
"step": 1967
},
{
"epoch": 9.07,
"learning_rate": 0.0001,
"loss": 0.229,
"step": 1968
},
{
"epoch": 9.08,
"learning_rate": 0.0001,
"loss": 0.2376,
"step": 1969
},
{
"epoch": 9.08,
"learning_rate": 0.0001,
"loss": 0.2523,
"step": 1970
},
{
"epoch": 9.09,
"learning_rate": 0.0001,
"loss": 0.2738,
"step": 1971
},
{
"epoch": 9.09,
"learning_rate": 0.0001,
"loss": 0.2623,
"step": 1972
},
{
"epoch": 9.1,
"learning_rate": 0.0001,
"loss": 0.2292,
"step": 1973
},
{
"epoch": 9.1,
"learning_rate": 0.0001,
"loss": 0.2791,
"step": 1974
},
{
"epoch": 9.11,
"learning_rate": 0.0001,
"loss": 0.2353,
"step": 1975
},
{
"epoch": 9.11,
"learning_rate": 0.0001,
"loss": 0.2301,
"step": 1976
},
{
"epoch": 9.12,
"learning_rate": 0.0001,
"loss": 0.229,
"step": 1977
},
{
"epoch": 9.12,
"learning_rate": 0.0001,
"loss": 0.2884,
"step": 1978
},
{
"epoch": 9.13,
"learning_rate": 0.0001,
"loss": 0.226,
"step": 1979
},
{
"epoch": 9.13,
"learning_rate": 0.0001,
"loss": 0.2364,
"step": 1980
},
{
"epoch": 9.13,
"learning_rate": 0.0001,
"loss": 0.2342,
"step": 1981
},
{
"epoch": 9.14,
"learning_rate": 0.0001,
"loss": 0.2526,
"step": 1982
},
{
"epoch": 9.14,
"learning_rate": 0.0001,
"loss": 0.266,
"step": 1983
},
{
"epoch": 9.15,
"learning_rate": 0.0001,
"loss": 0.2522,
"step": 1984
},
{
"epoch": 9.15,
"learning_rate": 0.0001,
"loss": 0.2554,
"step": 1985
},
{
"epoch": 9.16,
"learning_rate": 0.0001,
"loss": 0.2478,
"step": 1986
},
{
"epoch": 9.16,
"learning_rate": 0.0001,
"loss": 0.2438,
"step": 1987
},
{
"epoch": 9.17,
"learning_rate": 0.0001,
"loss": 0.2623,
"step": 1988
},
{
"epoch": 9.17,
"learning_rate": 0.0001,
"loss": 0.2325,
"step": 1989
},
{
"epoch": 9.18,
"learning_rate": 0.0001,
"loss": 0.2406,
"step": 1990
},
{
"epoch": 9.18,
"learning_rate": 0.0001,
"loss": 0.2529,
"step": 1991
},
{
"epoch": 9.19,
"learning_rate": 0.0001,
"loss": 0.2191,
"step": 1992
},
{
"epoch": 9.19,
"learning_rate": 0.0001,
"loss": 0.2662,
"step": 1993
},
{
"epoch": 9.19,
"learning_rate": 0.0001,
"loss": 0.2515,
"step": 1994
},
{
"epoch": 9.2,
"learning_rate": 0.0001,
"loss": 0.2574,
"step": 1995
},
{
"epoch": 9.2,
"learning_rate": 0.0001,
"loss": 0.2525,
"step": 1996
},
{
"epoch": 9.21,
"learning_rate": 0.0001,
"loss": 0.2312,
"step": 1997
},
{
"epoch": 9.21,
"learning_rate": 0.0001,
"loss": 0.2198,
"step": 1998
},
{
"epoch": 9.22,
"learning_rate": 0.0001,
"loss": 0.2631,
"step": 1999
},
{
"epoch": 9.22,
"learning_rate": 0.0001,
"loss": 0.2329,
"step": 2000
},
{
"epoch": 9.23,
"learning_rate": 0.0001,
"loss": 0.2317,
"step": 2001
},
{
"epoch": 9.23,
"learning_rate": 0.0001,
"loss": 0.2435,
"step": 2002
},
{
"epoch": 9.24,
"learning_rate": 0.0001,
"loss": 0.2475,
"step": 2003
},
{
"epoch": 9.24,
"learning_rate": 0.0001,
"loss": 0.2303,
"step": 2004
},
{
"epoch": 9.24,
"learning_rate": 0.0001,
"loss": 0.2685,
"step": 2005
},
{
"epoch": 9.25,
"learning_rate": 0.0001,
"loss": 0.2413,
"step": 2006
},
{
"epoch": 9.25,
"learning_rate": 0.0001,
"loss": 0.2438,
"step": 2007
},
{
"epoch": 9.26,
"learning_rate": 0.0001,
"loss": 0.265,
"step": 2008
},
{
"epoch": 9.26,
"learning_rate": 0.0001,
"loss": 0.243,
"step": 2009
},
{
"epoch": 9.27,
"learning_rate": 0.0001,
"loss": 0.2837,
"step": 2010
},
{
"epoch": 9.27,
"learning_rate": 0.0001,
"loss": 0.2237,
"step": 2011
},
{
"epoch": 9.28,
"learning_rate": 0.0001,
"loss": 0.2444,
"step": 2012
},
{
"epoch": 9.28,
"learning_rate": 0.0001,
"loss": 0.2491,
"step": 2013
},
{
"epoch": 9.29,
"learning_rate": 0.0001,
"loss": 0.2392,
"step": 2014
},
{
"epoch": 9.29,
"learning_rate": 0.0001,
"loss": 0.2478,
"step": 2015
},
{
"epoch": 9.3,
"learning_rate": 0.0001,
"loss": 0.2492,
"step": 2016
},
{
"epoch": 9.3,
"learning_rate": 0.0001,
"loss": 0.2382,
"step": 2017
},
{
"epoch": 9.3,
"learning_rate": 0.0001,
"loss": 0.2572,
"step": 2018
},
{
"epoch": 9.31,
"learning_rate": 0.0001,
"loss": 0.2757,
"step": 2019
},
{
"epoch": 9.31,
"learning_rate": 0.0001,
"loss": 0.2701,
"step": 2020
},
{
"epoch": 9.32,
"learning_rate": 0.0001,
"loss": 0.2569,
"step": 2021
},
{
"epoch": 9.32,
"learning_rate": 0.0001,
"loss": 0.2589,
"step": 2022
},
{
"epoch": 9.33,
"learning_rate": 0.0001,
"loss": 0.2681,
"step": 2023
},
{
"epoch": 9.33,
"learning_rate": 0.0001,
"loss": 0.2573,
"step": 2024
},
{
"epoch": 9.34,
"learning_rate": 0.0001,
"loss": 0.263,
"step": 2025
},
{
"epoch": 9.34,
"learning_rate": 0.0001,
"loss": 0.3006,
"step": 2026
},
{
"epoch": 9.35,
"learning_rate": 0.0001,
"loss": 0.2425,
"step": 2027
},
{
"epoch": 9.35,
"learning_rate": 0.0001,
"loss": 0.28,
"step": 2028
},
{
"epoch": 9.36,
"learning_rate": 0.0001,
"loss": 0.2574,
"step": 2029
},
{
"epoch": 9.36,
"learning_rate": 0.0001,
"loss": 0.2327,
"step": 2030
},
{
"epoch": 9.36,
"learning_rate": 0.0001,
"loss": 0.2222,
"step": 2031
},
{
"epoch": 9.37,
"learning_rate": 0.0001,
"loss": 0.2637,
"step": 2032
},
{
"epoch": 9.37,
"learning_rate": 0.0001,
"loss": 0.2777,
"step": 2033
},
{
"epoch": 9.38,
"learning_rate": 0.0001,
"loss": 0.2711,
"step": 2034
},
{
"epoch": 9.38,
"learning_rate": 0.0001,
"loss": 0.2462,
"step": 2035
},
{
"epoch": 9.39,
"learning_rate": 0.0001,
"loss": 0.2505,
"step": 2036
},
{
"epoch": 9.39,
"learning_rate": 0.0001,
"loss": 0.2429,
"step": 2037
},
{
"epoch": 9.4,
"learning_rate": 0.0001,
"loss": 0.2769,
"step": 2038
},
{
"epoch": 9.4,
"learning_rate": 0.0001,
"loss": 0.2699,
"step": 2039
},
{
"epoch": 9.41,
"learning_rate": 0.0001,
"loss": 0.2506,
"step": 2040
},
{
"epoch": 9.41,
"learning_rate": 0.0001,
"loss": 0.2706,
"step": 2041
},
{
"epoch": 9.42,
"learning_rate": 0.0001,
"loss": 0.2447,
"step": 2042
},
{
"epoch": 9.42,
"learning_rate": 0.0001,
"loss": 0.2373,
"step": 2043
},
{
"epoch": 9.42,
"learning_rate": 0.0001,
"loss": 0.2769,
"step": 2044
},
{
"epoch": 9.43,
"learning_rate": 0.0001,
"loss": 0.2954,
"step": 2045
},
{
"epoch": 9.43,
"learning_rate": 0.0001,
"loss": 0.2783,
"step": 2046
},
{
"epoch": 9.44,
"learning_rate": 0.0001,
"loss": 0.2586,
"step": 2047
},
{
"epoch": 9.44,
"learning_rate": 0.0001,
"loss": 0.2713,
"step": 2048
},
{
"epoch": 9.45,
"learning_rate": 0.0001,
"loss": 0.2401,
"step": 2049
},
{
"epoch": 9.45,
"learning_rate": 0.0001,
"loss": 0.264,
"step": 2050
},
{
"epoch": 9.46,
"learning_rate": 0.0001,
"loss": 0.27,
"step": 2051
},
{
"epoch": 9.46,
"learning_rate": 0.0001,
"loss": 0.2261,
"step": 2052
},
{
"epoch": 9.47,
"learning_rate": 0.0001,
"loss": 0.2669,
"step": 2053
},
{
"epoch": 9.47,
"learning_rate": 0.0001,
"loss": 0.2753,
"step": 2054
},
{
"epoch": 9.48,
"learning_rate": 0.0001,
"loss": 0.2612,
"step": 2055
},
{
"epoch": 9.48,
"learning_rate": 0.0001,
"loss": 0.3032,
"step": 2056
},
{
"epoch": 9.48,
"learning_rate": 0.0001,
"loss": 0.2302,
"step": 2057
},
{
"epoch": 9.49,
"learning_rate": 0.0001,
"loss": 0.246,
"step": 2058
},
{
"epoch": 9.49,
"learning_rate": 0.0001,
"loss": 0.2685,
"step": 2059
},
{
"epoch": 9.5,
"learning_rate": 0.0001,
"loss": 0.2501,
"step": 2060
},
{
"epoch": 9.5,
"learning_rate": 0.0001,
"loss": 0.2736,
"step": 2061
},
{
"epoch": 9.51,
"learning_rate": 0.0001,
"loss": 0.2599,
"step": 2062
},
{
"epoch": 9.51,
"learning_rate": 0.0001,
"loss": 0.2914,
"step": 2063
},
{
"epoch": 9.52,
"learning_rate": 0.0001,
"loss": 0.2637,
"step": 2064
},
{
"epoch": 9.52,
"learning_rate": 0.0001,
"loss": 0.275,
"step": 2065
},
{
"epoch": 9.53,
"learning_rate": 0.0001,
"loss": 0.2437,
"step": 2066
},
{
"epoch": 9.53,
"learning_rate": 0.0001,
"loss": 0.254,
"step": 2067
},
{
"epoch": 9.54,
"learning_rate": 0.0001,
"loss": 0.2808,
"step": 2068
},
{
"epoch": 9.54,
"learning_rate": 0.0001,
"loss": 0.2428,
"step": 2069
},
{
"epoch": 9.54,
"learning_rate": 0.0001,
"loss": 0.2486,
"step": 2070
},
{
"epoch": 9.55,
"learning_rate": 0.0001,
"loss": 0.2749,
"step": 2071
},
{
"epoch": 9.55,
"learning_rate": 0.0001,
"loss": 0.2785,
"step": 2072
},
{
"epoch": 9.56,
"learning_rate": 0.0001,
"loss": 0.2716,
"step": 2073
},
{
"epoch": 9.56,
"learning_rate": 0.0001,
"loss": 0.2682,
"step": 2074
},
{
"epoch": 9.57,
"learning_rate": 0.0001,
"loss": 0.2623,
"step": 2075
},
{
"epoch": 9.57,
"learning_rate": 0.0001,
"loss": 0.2768,
"step": 2076
},
{
"epoch": 9.58,
"learning_rate": 0.0001,
"loss": 0.2777,
"step": 2077
},
{
"epoch": 9.58,
"learning_rate": 0.0001,
"loss": 0.2378,
"step": 2078
},
{
"epoch": 9.59,
"learning_rate": 0.0001,
"loss": 0.2837,
"step": 2079
},
{
"epoch": 9.59,
"learning_rate": 0.0001,
"loss": 0.2984,
"step": 2080
},
{
"epoch": 9.6,
"learning_rate": 0.0001,
"loss": 0.268,
"step": 2081
},
{
"epoch": 9.6,
"learning_rate": 0.0001,
"loss": 0.2788,
"step": 2082
},
{
"epoch": 9.6,
"learning_rate": 0.0001,
"loss": 0.2732,
"step": 2083
},
{
"epoch": 9.61,
"learning_rate": 0.0001,
"loss": 0.253,
"step": 2084
},
{
"epoch": 9.61,
"learning_rate": 0.0001,
"loss": 0.2579,
"step": 2085
},
{
"epoch": 9.62,
"learning_rate": 0.0001,
"loss": 0.2599,
"step": 2086
},
{
"epoch": 9.62,
"learning_rate": 0.0001,
"loss": 0.2555,
"step": 2087
},
{
"epoch": 9.63,
"learning_rate": 0.0001,
"loss": 0.2815,
"step": 2088
},
{
"epoch": 9.63,
"learning_rate": 0.0001,
"loss": 0.2505,
"step": 2089
},
{
"epoch": 9.64,
"learning_rate": 0.0001,
"loss": 0.2529,
"step": 2090
},
{
"epoch": 9.64,
"learning_rate": 0.0001,
"loss": 0.2947,
"step": 2091
},
{
"epoch": 9.65,
"learning_rate": 0.0001,
"loss": 0.2837,
"step": 2092
},
{
"epoch": 9.65,
"learning_rate": 0.0001,
"loss": 0.2545,
"step": 2093
},
{
"epoch": 9.66,
"learning_rate": 0.0001,
"loss": 0.2711,
"step": 2094
},
{
"epoch": 9.66,
"learning_rate": 0.0001,
"loss": 0.2809,
"step": 2095
},
{
"epoch": 9.66,
"learning_rate": 0.0001,
"loss": 0.228,
"step": 2096
},
{
"epoch": 9.67,
"learning_rate": 0.0001,
"loss": 0.2468,
"step": 2097
},
{
"epoch": 9.67,
"learning_rate": 0.0001,
"loss": 0.2817,
"step": 2098
},
{
"epoch": 9.68,
"learning_rate": 0.0001,
"loss": 0.2689,
"step": 2099
},
{
"epoch": 9.68,
"learning_rate": 0.0001,
"loss": 0.2626,
"step": 2100
},
{
"epoch": 9.69,
"learning_rate": 0.0001,
"loss": 0.3184,
"step": 2101
},
{
"epoch": 9.69,
"learning_rate": 0.0001,
"loss": 0.2626,
"step": 2102
},
{
"epoch": 9.7,
"learning_rate": 0.0001,
"loss": 0.2687,
"step": 2103
},
{
"epoch": 9.7,
"learning_rate": 0.0001,
"loss": 0.2656,
"step": 2104
},
{
"epoch": 9.71,
"learning_rate": 0.0001,
"loss": 0.2657,
"step": 2105
},
{
"epoch": 9.71,
"learning_rate": 0.0001,
"loss": 0.2822,
"step": 2106
},
{
"epoch": 9.72,
"learning_rate": 0.0001,
"loss": 0.2478,
"step": 2107
},
{
"epoch": 9.72,
"learning_rate": 0.0001,
"loss": 0.278,
"step": 2108
},
{
"epoch": 9.72,
"learning_rate": 0.0001,
"loss": 0.2695,
"step": 2109
},
{
"epoch": 9.73,
"learning_rate": 0.0001,
"loss": 0.2756,
"step": 2110
},
{
"epoch": 9.73,
"learning_rate": 0.0001,
"loss": 0.2747,
"step": 2111
},
{
"epoch": 9.74,
"learning_rate": 0.0001,
"loss": 0.3124,
"step": 2112
},
{
"epoch": 9.74,
"learning_rate": 0.0001,
"loss": 0.2865,
"step": 2113
},
{
"epoch": 9.75,
"learning_rate": 0.0001,
"loss": 0.2882,
"step": 2114
},
{
"epoch": 9.75,
"learning_rate": 0.0001,
"loss": 0.2564,
"step": 2115
},
{
"epoch": 9.76,
"learning_rate": 0.0001,
"loss": 0.271,
"step": 2116
},
{
"epoch": 9.76,
"learning_rate": 0.0001,
"loss": 0.2728,
"step": 2117
},
{
"epoch": 9.77,
"learning_rate": 0.0001,
"loss": 0.2803,
"step": 2118
},
{
"epoch": 9.77,
"learning_rate": 0.0001,
"loss": 0.2873,
"step": 2119
},
{
"epoch": 9.78,
"learning_rate": 0.0001,
"loss": 0.2841,
"step": 2120
},
{
"epoch": 9.78,
"learning_rate": 0.0001,
"loss": 0.2665,
"step": 2121
},
{
"epoch": 9.78,
"learning_rate": 0.0001,
"loss": 0.2817,
"step": 2122
},
{
"epoch": 9.79,
"learning_rate": 0.0001,
"loss": 0.2853,
"step": 2123
},
{
"epoch": 9.79,
"learning_rate": 0.0001,
"loss": 0.2657,
"step": 2124
},
{
"epoch": 9.8,
"learning_rate": 0.0001,
"loss": 0.2601,
"step": 2125
},
{
"epoch": 9.8,
"learning_rate": 0.0001,
"loss": 0.2939,
"step": 2126
},
{
"epoch": 9.81,
"learning_rate": 0.0001,
"loss": 0.2811,
"step": 2127
},
{
"epoch": 9.81,
"learning_rate": 0.0001,
"loss": 0.3025,
"step": 2128
},
{
"epoch": 9.82,
"learning_rate": 0.0001,
"loss": 0.2363,
"step": 2129
},
{
"epoch": 9.82,
"learning_rate": 0.0001,
"loss": 0.2887,
"step": 2130
},
{
"epoch": 9.83,
"learning_rate": 0.0001,
"loss": 0.2631,
"step": 2131
},
{
"epoch": 9.83,
"learning_rate": 0.0001,
"loss": 0.2664,
"step": 2132
},
{
"epoch": 9.84,
"learning_rate": 0.0001,
"loss": 0.2799,
"step": 2133
},
{
"epoch": 9.84,
"learning_rate": 0.0001,
"loss": 0.2717,
"step": 2134
},
{
"epoch": 9.84,
"learning_rate": 0.0001,
"loss": 0.2828,
"step": 2135
},
{
"epoch": 9.85,
"learning_rate": 0.0001,
"loss": 0.2737,
"step": 2136
},
{
"epoch": 9.85,
"learning_rate": 0.0001,
"loss": 0.2679,
"step": 2137
},
{
"epoch": 9.86,
"learning_rate": 0.0001,
"loss": 0.2911,
"step": 2138
},
{
"epoch": 9.86,
"learning_rate": 0.0001,
"loss": 0.2687,
"step": 2139
},
{
"epoch": 9.87,
"learning_rate": 0.0001,
"loss": 0.2772,
"step": 2140
},
{
"epoch": 9.87,
"learning_rate": 0.0001,
"loss": 0.2836,
"step": 2141
},
{
"epoch": 9.88,
"learning_rate": 0.0001,
"loss": 0.254,
"step": 2142
},
{
"epoch": 9.88,
"learning_rate": 0.0001,
"loss": 0.2906,
"step": 2143
},
{
"epoch": 9.89,
"learning_rate": 0.0001,
"loss": 0.2702,
"step": 2144
},
{
"epoch": 9.89,
"learning_rate": 0.0001,
"loss": 0.2866,
"step": 2145
},
{
"epoch": 9.9,
"learning_rate": 0.0001,
"loss": 0.2949,
"step": 2146
},
{
"epoch": 9.9,
"learning_rate": 0.0001,
"loss": 0.3086,
"step": 2147
},
{
"epoch": 9.9,
"learning_rate": 0.0001,
"loss": 0.3205,
"step": 2148
},
{
"epoch": 9.91,
"learning_rate": 0.0001,
"loss": 0.2874,
"step": 2149
},
{
"epoch": 9.91,
"learning_rate": 0.0001,
"loss": 0.2537,
"step": 2150
},
{
"epoch": 9.92,
"learning_rate": 0.0001,
"loss": 0.2853,
"step": 2151
},
{
"epoch": 9.92,
"learning_rate": 0.0001,
"loss": 0.3141,
"step": 2152
},
{
"epoch": 9.93,
"learning_rate": 0.0001,
"loss": 0.2758,
"step": 2153
},
{
"epoch": 9.93,
"learning_rate": 0.0001,
"loss": 0.2877,
"step": 2154
},
{
"epoch": 9.94,
"learning_rate": 0.0001,
"loss": 0.2654,
"step": 2155
},
{
"epoch": 9.94,
"learning_rate": 0.0001,
"loss": 0.2886,
"step": 2156
},
{
"epoch": 9.95,
"learning_rate": 0.0001,
"loss": 0.3399,
"step": 2157
},
{
"epoch": 9.95,
"learning_rate": 0.0001,
"loss": 0.2914,
"step": 2158
},
{
"epoch": 9.96,
"learning_rate": 0.0001,
"loss": 0.2732,
"step": 2159
},
{
"epoch": 9.96,
"learning_rate": 0.0001,
"loss": 0.2531,
"step": 2160
},
{
"epoch": 9.96,
"step": 2160,
"total_flos": 2.5763925849853133e+17,
"train_loss": 0.46730201305062685,
"train_runtime": 11414.299,
"train_samples_per_second": 12.159,
"train_steps_per_second": 0.189
}
],
"logging_steps": 1.0,
"max_steps": 2160,
"num_train_epochs": 10,
"save_steps": 1500,
"total_flos": 2.5763925849853133e+17,
"trial_name": null,
"trial_params": null
}