Mel-Iza0's picture
Training in progress, epoch 1, checkpoint
d2d016f
raw
history blame
No virus
97.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 919,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 8.333333333333334e-06,
"loss": 3.1281,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.6666666666666667e-05,
"loss": 3.2134,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 2.5e-05,
"loss": 3.1325,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 3.3333333333333335e-05,
"loss": 3.1263,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 4.1666666666666665e-05,
"loss": 3.1569,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 5e-05,
"loss": 3.213,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 5.833333333333333e-05,
"loss": 3.2105,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 6.666666666666667e-05,
"loss": 3.1681,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 7.5e-05,
"loss": 3.1277,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 8.333333333333333e-05,
"loss": 3.1917,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 9.166666666666667e-05,
"loss": 3.0592,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 3.0844,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 0.00010833333333333334,
"loss": 2.8544,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 0.00011666666666666667,
"loss": 2.8214,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 0.000125,
"loss": 2.829,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 0.00013333333333333334,
"loss": 2.7026,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 0.00014166666666666668,
"loss": 2.6199,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 0.00015,
"loss": 2.5594,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 0.00015833333333333332,
"loss": 2.4738,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 0.00016666666666666666,
"loss": 2.4792,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 0.000175,
"loss": 2.4097,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 0.00018333333333333334,
"loss": 2.3469,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 0.00019166666666666667,
"loss": 2.2218,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 2.1477,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 0.00020833333333333335,
"loss": 2.0773,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 0.00021666666666666668,
"loss": 2.0249,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 0.00022500000000000002,
"loss": 1.913,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 0.00023333333333333333,
"loss": 1.8384,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 0.00024166666666666667,
"loss": 1.7988,
"step": 29
},
{
"epoch": 0.03,
"learning_rate": 0.00025,
"loss": 1.8328,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 0.00025833333333333334,
"loss": 1.7341,
"step": 31
},
{
"epoch": 0.03,
"learning_rate": 0.0002666666666666667,
"loss": 1.7436,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 0.000275,
"loss": 1.6803,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 0.00028333333333333335,
"loss": 1.6908,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 0.0002916666666666667,
"loss": 1.672,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.6964,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 0.00030833333333333337,
"loss": 1.6025,
"step": 37
},
{
"epoch": 0.04,
"learning_rate": 0.00031666666666666665,
"loss": 1.6053,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 0.00032500000000000004,
"loss": 1.5432,
"step": 39
},
{
"epoch": 0.04,
"learning_rate": 0.0003333333333333333,
"loss": 1.5595,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 0.00034166666666666666,
"loss": 1.5724,
"step": 41
},
{
"epoch": 0.05,
"learning_rate": 0.00035,
"loss": 1.5366,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 0.00035833333333333333,
"loss": 1.5278,
"step": 43
},
{
"epoch": 0.05,
"learning_rate": 0.00036666666666666667,
"loss": 1.5732,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 0.000375,
"loss": 1.5424,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 0.00038333333333333334,
"loss": 1.496,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 0.0003916666666666667,
"loss": 1.4984,
"step": 47
},
{
"epoch": 0.05,
"learning_rate": 0.0004,
"loss": 1.4642,
"step": 48
},
{
"epoch": 0.05,
"learning_rate": 0.00040833333333333336,
"loss": 1.4562,
"step": 49
},
{
"epoch": 0.05,
"learning_rate": 0.0004166666666666667,
"loss": 1.5446,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 0.000425,
"loss": 1.4786,
"step": 51
},
{
"epoch": 0.06,
"learning_rate": 0.00043333333333333337,
"loss": 1.4949,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 0.00044166666666666665,
"loss": 1.4503,
"step": 53
},
{
"epoch": 0.06,
"learning_rate": 0.00045000000000000004,
"loss": 1.501,
"step": 54
},
{
"epoch": 0.06,
"learning_rate": 0.0004583333333333333,
"loss": 1.4322,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 0.00046666666666666666,
"loss": 1.3982,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 0.000475,
"loss": 1.4274,
"step": 57
},
{
"epoch": 0.06,
"learning_rate": 0.00048333333333333334,
"loss": 1.4058,
"step": 58
},
{
"epoch": 0.06,
"learning_rate": 0.0004916666666666666,
"loss": 1.422,
"step": 59
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.4153,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.4575,
"step": 61
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.4206,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.4459,
"step": 63
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.4473,
"step": 64
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.4369,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.3791,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.4655,
"step": 67
},
{
"epoch": 0.07,
"learning_rate": 0.0005,
"loss": 1.3951,
"step": 68
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3741,
"step": 69
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3824,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3948,
"step": 71
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.383,
"step": 72
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3417,
"step": 73
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3329,
"step": 74
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3993,
"step": 75
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3095,
"step": 76
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3457,
"step": 77
},
{
"epoch": 0.08,
"learning_rate": 0.0005,
"loss": 1.3462,
"step": 78
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.3713,
"step": 79
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.4215,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.3378,
"step": 81
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.3221,
"step": 82
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.4079,
"step": 83
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.3724,
"step": 84
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.3094,
"step": 85
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.2731,
"step": 86
},
{
"epoch": 0.09,
"learning_rate": 0.0005,
"loss": 1.2718,
"step": 87
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.2988,
"step": 88
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.316,
"step": 89
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.2531,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.3109,
"step": 91
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.3246,
"step": 92
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.3568,
"step": 93
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.2643,
"step": 94
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.292,
"step": 95
},
{
"epoch": 0.1,
"learning_rate": 0.0005,
"loss": 1.2677,
"step": 96
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.2676,
"step": 97
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.2829,
"step": 98
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.2874,
"step": 99
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.233,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.3235,
"step": 101
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.2773,
"step": 102
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.2528,
"step": 103
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.2758,
"step": 104
},
{
"epoch": 0.11,
"learning_rate": 0.0005,
"loss": 1.241,
"step": 105
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.2566,
"step": 106
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.2811,
"step": 107
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.2691,
"step": 108
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.2337,
"step": 109
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.2259,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.3066,
"step": 111
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.297,
"step": 112
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.239,
"step": 113
},
{
"epoch": 0.12,
"learning_rate": 0.0005,
"loss": 1.2429,
"step": 114
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2376,
"step": 115
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2336,
"step": 116
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2281,
"step": 117
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2077,
"step": 118
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2819,
"step": 119
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2342,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2229,
"step": 121
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2834,
"step": 122
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2088,
"step": 123
},
{
"epoch": 0.13,
"learning_rate": 0.0005,
"loss": 1.2204,
"step": 124
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.182,
"step": 125
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.1772,
"step": 126
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.181,
"step": 127
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.2731,
"step": 128
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.2672,
"step": 129
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.238,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.2286,
"step": 131
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.1899,
"step": 132
},
{
"epoch": 0.14,
"learning_rate": 0.0005,
"loss": 1.237,
"step": 133
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.1862,
"step": 134
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.2598,
"step": 135
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.301,
"step": 136
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.2209,
"step": 137
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.2473,
"step": 138
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.1937,
"step": 139
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.1837,
"step": 140
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.2567,
"step": 141
},
{
"epoch": 0.15,
"learning_rate": 0.0005,
"loss": 1.2951,
"step": 142
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.2081,
"step": 143
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.24,
"step": 144
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.2182,
"step": 145
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.1947,
"step": 146
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.2134,
"step": 147
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.1861,
"step": 148
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.2662,
"step": 149
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.1699,
"step": 150
},
{
"epoch": 0.16,
"learning_rate": 0.0005,
"loss": 1.1974,
"step": 151
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.2301,
"step": 152
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.1921,
"step": 153
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.1531,
"step": 154
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.1716,
"step": 155
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.2362,
"step": 156
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.1793,
"step": 157
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.2342,
"step": 158
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.2101,
"step": 159
},
{
"epoch": 0.17,
"learning_rate": 0.0005,
"loss": 1.1724,
"step": 160
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.1928,
"step": 161
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.2171,
"step": 162
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.2294,
"step": 163
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.2505,
"step": 164
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.2111,
"step": 165
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.2237,
"step": 166
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.1797,
"step": 167
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.1526,
"step": 168
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.1983,
"step": 169
},
{
"epoch": 0.18,
"learning_rate": 0.0005,
"loss": 1.1987,
"step": 170
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.2492,
"step": 171
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.15,
"step": 172
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.1369,
"step": 173
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.203,
"step": 174
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.2171,
"step": 175
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.2159,
"step": 176
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.2028,
"step": 177
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.1498,
"step": 178
},
{
"epoch": 0.19,
"learning_rate": 0.0005,
"loss": 1.1855,
"step": 179
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.2133,
"step": 180
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.1798,
"step": 181
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.1597,
"step": 182
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.1383,
"step": 183
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.2074,
"step": 184
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.1202,
"step": 185
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.1667,
"step": 186
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.2343,
"step": 187
},
{
"epoch": 0.2,
"learning_rate": 0.0005,
"loss": 1.1639,
"step": 188
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.2114,
"step": 189
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.1465,
"step": 190
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.1341,
"step": 191
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.2378,
"step": 192
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.1704,
"step": 193
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.1667,
"step": 194
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.1565,
"step": 195
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.1623,
"step": 196
},
{
"epoch": 0.21,
"learning_rate": 0.0005,
"loss": 1.1766,
"step": 197
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.2176,
"step": 198
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.1777,
"step": 199
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.2673,
"step": 200
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.2108,
"step": 201
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.1591,
"step": 202
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.1441,
"step": 203
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.2305,
"step": 204
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.1417,
"step": 205
},
{
"epoch": 0.22,
"learning_rate": 0.0005,
"loss": 1.1638,
"step": 206
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.2092,
"step": 207
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.1597,
"step": 208
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.1423,
"step": 209
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.1304,
"step": 210
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.1535,
"step": 211
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.1886,
"step": 212
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.1739,
"step": 213
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.1597,
"step": 214
},
{
"epoch": 0.23,
"learning_rate": 0.0005,
"loss": 1.2508,
"step": 215
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.2121,
"step": 216
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.1698,
"step": 217
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.1392,
"step": 218
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.1906,
"step": 219
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.1481,
"step": 220
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.1912,
"step": 221
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.1583,
"step": 222
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.1819,
"step": 223
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.1733,
"step": 224
},
{
"epoch": 0.24,
"learning_rate": 0.0005,
"loss": 1.208,
"step": 225
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.1297,
"step": 226
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.1523,
"step": 227
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.1804,
"step": 228
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.1335,
"step": 229
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.1825,
"step": 230
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.1292,
"step": 231
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.1735,
"step": 232
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.2123,
"step": 233
},
{
"epoch": 0.25,
"learning_rate": 0.0005,
"loss": 1.1286,
"step": 234
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.2323,
"step": 235
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.1497,
"step": 236
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.1598,
"step": 237
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.2146,
"step": 238
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.1907,
"step": 239
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.1524,
"step": 240
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.155,
"step": 241
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.1665,
"step": 242
},
{
"epoch": 0.26,
"learning_rate": 0.0005,
"loss": 1.2103,
"step": 243
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1455,
"step": 244
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1145,
"step": 245
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1516,
"step": 246
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1471,
"step": 247
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1938,
"step": 248
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1558,
"step": 249
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1639,
"step": 250
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1371,
"step": 251
},
{
"epoch": 0.27,
"learning_rate": 0.0005,
"loss": 1.1195,
"step": 252
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1999,
"step": 253
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1647,
"step": 254
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1431,
"step": 255
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1219,
"step": 256
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1378,
"step": 257
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1689,
"step": 258
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1478,
"step": 259
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1591,
"step": 260
},
{
"epoch": 0.28,
"learning_rate": 0.0005,
"loss": 1.1389,
"step": 261
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.1746,
"step": 262
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.1305,
"step": 263
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.0773,
"step": 264
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.1679,
"step": 265
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.1133,
"step": 266
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.1807,
"step": 267
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.0736,
"step": 268
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.1416,
"step": 269
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.0843,
"step": 270
},
{
"epoch": 0.29,
"learning_rate": 0.0005,
"loss": 1.2055,
"step": 271
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.1401,
"step": 272
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.1247,
"step": 273
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.1633,
"step": 274
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.1592,
"step": 275
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.1481,
"step": 276
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.1493,
"step": 277
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.18,
"step": 278
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.152,
"step": 279
},
{
"epoch": 0.3,
"learning_rate": 0.0005,
"loss": 1.1175,
"step": 280
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.1736,
"step": 281
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.1598,
"step": 282
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.1614,
"step": 283
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.1112,
"step": 284
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.174,
"step": 285
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.1545,
"step": 286
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.1704,
"step": 287
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.1427,
"step": 288
},
{
"epoch": 0.31,
"learning_rate": 0.0005,
"loss": 1.0912,
"step": 289
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.172,
"step": 290
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.1939,
"step": 291
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.0911,
"step": 292
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.106,
"step": 293
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.1358,
"step": 294
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.0833,
"step": 295
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.1556,
"step": 296
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.1171,
"step": 297
},
{
"epoch": 0.32,
"learning_rate": 0.0005,
"loss": 1.1522,
"step": 298
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1619,
"step": 299
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1661,
"step": 300
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1426,
"step": 301
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1481,
"step": 302
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1153,
"step": 303
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1626,
"step": 304
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1958,
"step": 305
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1717,
"step": 306
},
{
"epoch": 0.33,
"learning_rate": 0.0005,
"loss": 1.1187,
"step": 307
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.0895,
"step": 308
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.1251,
"step": 309
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.1967,
"step": 310
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.1811,
"step": 311
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.1392,
"step": 312
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.1373,
"step": 313
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.1145,
"step": 314
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.1429,
"step": 315
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.075,
"step": 316
},
{
"epoch": 0.34,
"learning_rate": 0.0005,
"loss": 1.2638,
"step": 317
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.1076,
"step": 318
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.0853,
"step": 319
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.0948,
"step": 320
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.1421,
"step": 321
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.1067,
"step": 322
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.148,
"step": 323
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.1525,
"step": 324
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.1467,
"step": 325
},
{
"epoch": 0.35,
"learning_rate": 0.0005,
"loss": 1.1286,
"step": 326
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.1707,
"step": 327
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.1688,
"step": 328
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.1618,
"step": 329
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.1654,
"step": 330
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.109,
"step": 331
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.1761,
"step": 332
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.1845,
"step": 333
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.1326,
"step": 334
},
{
"epoch": 0.36,
"learning_rate": 0.0005,
"loss": 1.1221,
"step": 335
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.158,
"step": 336
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.0982,
"step": 337
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.1278,
"step": 338
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.0982,
"step": 339
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.118,
"step": 340
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.1106,
"step": 341
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.129,
"step": 342
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.1754,
"step": 343
},
{
"epoch": 0.37,
"learning_rate": 0.0005,
"loss": 1.1159,
"step": 344
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1448,
"step": 345
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1971,
"step": 346
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1513,
"step": 347
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1271,
"step": 348
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1378,
"step": 349
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1518,
"step": 350
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1008,
"step": 351
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1205,
"step": 352
},
{
"epoch": 0.38,
"learning_rate": 0.0005,
"loss": 1.1167,
"step": 353
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1011,
"step": 354
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1031,
"step": 355
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1194,
"step": 356
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1002,
"step": 357
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1156,
"step": 358
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.0899,
"step": 359
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1718,
"step": 360
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1062,
"step": 361
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1618,
"step": 362
},
{
"epoch": 0.39,
"learning_rate": 0.0005,
"loss": 1.1149,
"step": 363
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.1086,
"step": 364
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.1069,
"step": 365
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.0773,
"step": 366
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.1392,
"step": 367
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.1487,
"step": 368
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.1413,
"step": 369
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.1242,
"step": 370
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.0771,
"step": 371
},
{
"epoch": 0.4,
"learning_rate": 0.0005,
"loss": 1.137,
"step": 372
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.0734,
"step": 373
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.1305,
"step": 374
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.1169,
"step": 375
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.1674,
"step": 376
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.1103,
"step": 377
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.1433,
"step": 378
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.1344,
"step": 379
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.123,
"step": 380
},
{
"epoch": 0.41,
"learning_rate": 0.0005,
"loss": 1.1169,
"step": 381
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.1508,
"step": 382
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.1499,
"step": 383
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.1916,
"step": 384
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.1574,
"step": 385
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.0429,
"step": 386
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.0901,
"step": 387
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.095,
"step": 388
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.0851,
"step": 389
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 1.083,
"step": 390
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.1137,
"step": 391
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.1507,
"step": 392
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.1454,
"step": 393
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.0831,
"step": 394
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.119,
"step": 395
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.1277,
"step": 396
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.156,
"step": 397
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.1328,
"step": 398
},
{
"epoch": 0.43,
"learning_rate": 0.0005,
"loss": 1.1374,
"step": 399
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.1243,
"step": 400
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.1207,
"step": 401
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.1422,
"step": 402
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.1359,
"step": 403
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.1686,
"step": 404
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.1114,
"step": 405
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.1648,
"step": 406
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.0895,
"step": 407
},
{
"epoch": 0.44,
"learning_rate": 0.0005,
"loss": 1.1065,
"step": 408
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.1434,
"step": 409
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.1855,
"step": 410
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.1184,
"step": 411
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.0954,
"step": 412
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.0693,
"step": 413
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.1026,
"step": 414
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.169,
"step": 415
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.1184,
"step": 416
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.1343,
"step": 417
},
{
"epoch": 0.45,
"learning_rate": 0.0005,
"loss": 1.1433,
"step": 418
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.1394,
"step": 419
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.1908,
"step": 420
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.1084,
"step": 421
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.1292,
"step": 422
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.1276,
"step": 423
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.1821,
"step": 424
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.075,
"step": 425
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.0903,
"step": 426
},
{
"epoch": 0.46,
"learning_rate": 0.0005,
"loss": 1.0933,
"step": 427
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.1403,
"step": 428
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.1177,
"step": 429
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.0836,
"step": 430
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.0912,
"step": 431
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.1686,
"step": 432
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.1583,
"step": 433
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.1106,
"step": 434
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.1318,
"step": 435
},
{
"epoch": 0.47,
"learning_rate": 0.0005,
"loss": 1.0883,
"step": 436
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.1449,
"step": 437
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.1124,
"step": 438
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.1016,
"step": 439
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.0895,
"step": 440
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.0981,
"step": 441
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.1131,
"step": 442
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.1049,
"step": 443
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.0975,
"step": 444
},
{
"epoch": 0.48,
"learning_rate": 0.0005,
"loss": 1.1034,
"step": 445
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.1582,
"step": 446
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.1558,
"step": 447
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.1147,
"step": 448
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.1363,
"step": 449
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.1115,
"step": 450
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.1537,
"step": 451
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.138,
"step": 452
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.1728,
"step": 453
},
{
"epoch": 0.49,
"learning_rate": 0.0005,
"loss": 1.1497,
"step": 454
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.1443,
"step": 455
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.0952,
"step": 456
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.1314,
"step": 457
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.0779,
"step": 458
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.1676,
"step": 459
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.1408,
"step": 460
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.1355,
"step": 461
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.1123,
"step": 462
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.0768,
"step": 463
},
{
"epoch": 0.5,
"learning_rate": 0.0005,
"loss": 1.073,
"step": 464
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1002,
"step": 465
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1408,
"step": 466
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1524,
"step": 467
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1628,
"step": 468
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1003,
"step": 469
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1811,
"step": 470
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1205,
"step": 471
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1096,
"step": 472
},
{
"epoch": 0.51,
"learning_rate": 0.0005,
"loss": 1.1496,
"step": 473
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.1841,
"step": 474
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.1353,
"step": 475
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.0934,
"step": 476
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.1177,
"step": 477
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.1786,
"step": 478
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.1388,
"step": 479
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.1186,
"step": 480
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.1976,
"step": 481
},
{
"epoch": 0.52,
"learning_rate": 0.0005,
"loss": 1.0979,
"step": 482
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.1238,
"step": 483
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.1358,
"step": 484
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.1277,
"step": 485
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.0825,
"step": 486
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.1324,
"step": 487
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.1685,
"step": 488
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.1475,
"step": 489
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.1074,
"step": 490
},
{
"epoch": 0.53,
"learning_rate": 0.0005,
"loss": 1.1237,
"step": 491
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.1007,
"step": 492
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.0941,
"step": 493
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.171,
"step": 494
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.1143,
"step": 495
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.1332,
"step": 496
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.1109,
"step": 497
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.1606,
"step": 498
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.0875,
"step": 499
},
{
"epoch": 0.54,
"learning_rate": 0.0005,
"loss": 1.093,
"step": 500
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.1218,
"step": 501
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.1523,
"step": 502
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.0864,
"step": 503
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.1312,
"step": 504
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.1031,
"step": 505
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.0873,
"step": 506
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.1007,
"step": 507
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.1589,
"step": 508
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.1274,
"step": 509
},
{
"epoch": 0.55,
"learning_rate": 0.0005,
"loss": 1.0488,
"step": 510
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.1344,
"step": 511
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.1485,
"step": 512
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.073,
"step": 513
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.1457,
"step": 514
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.1524,
"step": 515
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.1407,
"step": 516
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.1652,
"step": 517
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.1391,
"step": 518
},
{
"epoch": 0.56,
"learning_rate": 0.0005,
"loss": 1.1251,
"step": 519
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.136,
"step": 520
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.0951,
"step": 521
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.122,
"step": 522
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.097,
"step": 523
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.1416,
"step": 524
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.0924,
"step": 525
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.1187,
"step": 526
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.1388,
"step": 527
},
{
"epoch": 0.57,
"learning_rate": 0.0005,
"loss": 1.1068,
"step": 528
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.1338,
"step": 529
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.089,
"step": 530
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.1547,
"step": 531
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.1474,
"step": 532
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.1267,
"step": 533
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.1456,
"step": 534
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.1456,
"step": 535
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.0993,
"step": 536
},
{
"epoch": 0.58,
"learning_rate": 0.0005,
"loss": 1.0625,
"step": 537
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1282,
"step": 538
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1154,
"step": 539
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1428,
"step": 540
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1507,
"step": 541
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1471,
"step": 542
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1485,
"step": 543
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1608,
"step": 544
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1688,
"step": 545
},
{
"epoch": 0.59,
"learning_rate": 0.0005,
"loss": 1.1432,
"step": 546
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.0744,
"step": 547
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.1473,
"step": 548
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.129,
"step": 549
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.0627,
"step": 550
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.119,
"step": 551
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.0922,
"step": 552
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.1226,
"step": 553
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.1088,
"step": 554
},
{
"epoch": 0.6,
"learning_rate": 0.0005,
"loss": 1.1086,
"step": 555
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.1223,
"step": 556
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.1532,
"step": 557
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.0867,
"step": 558
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.1249,
"step": 559
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.0589,
"step": 560
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.0997,
"step": 561
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.106,
"step": 562
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.1232,
"step": 563
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.15,
"step": 564
},
{
"epoch": 0.61,
"learning_rate": 0.0005,
"loss": 1.13,
"step": 565
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.1356,
"step": 566
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.0605,
"step": 567
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.1148,
"step": 568
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.0978,
"step": 569
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.1588,
"step": 570
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.1003,
"step": 571
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.134,
"step": 572
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.1209,
"step": 573
},
{
"epoch": 0.62,
"learning_rate": 0.0005,
"loss": 1.1147,
"step": 574
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.0861,
"step": 575
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.1172,
"step": 576
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.0743,
"step": 577
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.1118,
"step": 578
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.1286,
"step": 579
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.1274,
"step": 580
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.1367,
"step": 581
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.1314,
"step": 582
},
{
"epoch": 0.63,
"learning_rate": 0.0005,
"loss": 1.1111,
"step": 583
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.0931,
"step": 584
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.0855,
"step": 585
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.1351,
"step": 586
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.1783,
"step": 587
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.1478,
"step": 588
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.1735,
"step": 589
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.1211,
"step": 590
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.0519,
"step": 591
},
{
"epoch": 0.64,
"learning_rate": 0.0005,
"loss": 1.0837,
"step": 592
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.1075,
"step": 593
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.1191,
"step": 594
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.1093,
"step": 595
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.1389,
"step": 596
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.1264,
"step": 597
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.1058,
"step": 598
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.0963,
"step": 599
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.1002,
"step": 600
},
{
"epoch": 0.65,
"learning_rate": 0.0005,
"loss": 1.1513,
"step": 601
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.0723,
"step": 602
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.1105,
"step": 603
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.113,
"step": 604
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.0865,
"step": 605
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.1057,
"step": 606
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.1192,
"step": 607
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.1289,
"step": 608
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.1108,
"step": 609
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.1258,
"step": 610
},
{
"epoch": 0.66,
"learning_rate": 0.0005,
"loss": 1.1143,
"step": 611
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.1101,
"step": 612
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.1329,
"step": 613
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.1358,
"step": 614
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.1403,
"step": 615
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.1541,
"step": 616
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.127,
"step": 617
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.1154,
"step": 618
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.1153,
"step": 619
},
{
"epoch": 0.67,
"learning_rate": 0.0005,
"loss": 1.1383,
"step": 620
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.1302,
"step": 621
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.1266,
"step": 622
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.0733,
"step": 623
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.0846,
"step": 624
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.1305,
"step": 625
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.1089,
"step": 626
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.1499,
"step": 627
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.0957,
"step": 628
},
{
"epoch": 0.68,
"learning_rate": 0.0005,
"loss": 1.1104,
"step": 629
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.068,
"step": 630
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.128,
"step": 631
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.128,
"step": 632
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.1251,
"step": 633
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.0731,
"step": 634
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.1001,
"step": 635
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.122,
"step": 636
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.1294,
"step": 637
},
{
"epoch": 0.69,
"learning_rate": 0.0005,
"loss": 1.0869,
"step": 638
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.0959,
"step": 639
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.1069,
"step": 640
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.1385,
"step": 641
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.1011,
"step": 642
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.0785,
"step": 643
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.1236,
"step": 644
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.1247,
"step": 645
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.1202,
"step": 646
},
{
"epoch": 0.7,
"learning_rate": 0.0005,
"loss": 1.0821,
"step": 647
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.1,
"step": 648
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.1027,
"step": 649
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.0754,
"step": 650
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.0978,
"step": 651
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.1193,
"step": 652
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.1039,
"step": 653
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.0711,
"step": 654
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.1076,
"step": 655
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.1399,
"step": 656
},
{
"epoch": 0.71,
"learning_rate": 0.0005,
"loss": 1.1101,
"step": 657
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.0897,
"step": 658
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.1471,
"step": 659
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.0853,
"step": 660
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.1272,
"step": 661
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.1351,
"step": 662
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.0876,
"step": 663
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.0701,
"step": 664
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.1206,
"step": 665
},
{
"epoch": 0.72,
"learning_rate": 0.0005,
"loss": 1.0792,
"step": 666
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.0793,
"step": 667
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.0608,
"step": 668
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.162,
"step": 669
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.1206,
"step": 670
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.0972,
"step": 671
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.0974,
"step": 672
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.0726,
"step": 673
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.0959,
"step": 674
},
{
"epoch": 0.73,
"learning_rate": 0.0005,
"loss": 1.0941,
"step": 675
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.1039,
"step": 676
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.0615,
"step": 677
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.1342,
"step": 678
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.1919,
"step": 679
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.1385,
"step": 680
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.131,
"step": 681
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.0772,
"step": 682
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.0776,
"step": 683
},
{
"epoch": 0.74,
"learning_rate": 0.0005,
"loss": 1.0766,
"step": 684
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.0667,
"step": 685
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.1359,
"step": 686
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.0814,
"step": 687
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.0671,
"step": 688
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.1235,
"step": 689
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.0756,
"step": 690
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.1154,
"step": 691
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.1088,
"step": 692
},
{
"epoch": 0.75,
"learning_rate": 0.0005,
"loss": 1.1147,
"step": 693
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.095,
"step": 694
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.1245,
"step": 695
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.0816,
"step": 696
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.1043,
"step": 697
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.075,
"step": 698
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.0842,
"step": 699
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.1424,
"step": 700
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.1195,
"step": 701
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.1016,
"step": 702
},
{
"epoch": 0.76,
"learning_rate": 0.0005,
"loss": 1.1193,
"step": 703
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.0593,
"step": 704
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.0937,
"step": 705
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.076,
"step": 706
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.1058,
"step": 707
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.1066,
"step": 708
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.0824,
"step": 709
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.1151,
"step": 710
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.1501,
"step": 711
},
{
"epoch": 0.77,
"learning_rate": 0.0005,
"loss": 1.1372,
"step": 712
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.0637,
"step": 713
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.1195,
"step": 714
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.1021,
"step": 715
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.1089,
"step": 716
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.0846,
"step": 717
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.1233,
"step": 718
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.1031,
"step": 719
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.1211,
"step": 720
},
{
"epoch": 0.78,
"learning_rate": 0.0005,
"loss": 1.0841,
"step": 721
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.0998,
"step": 722
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.0864,
"step": 723
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.1018,
"step": 724
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.0778,
"step": 725
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.1049,
"step": 726
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.1231,
"step": 727
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.1025,
"step": 728
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.111,
"step": 729
},
{
"epoch": 0.79,
"learning_rate": 0.0005,
"loss": 1.1082,
"step": 730
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.0837,
"step": 731
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.0867,
"step": 732
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.1125,
"step": 733
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.0909,
"step": 734
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.1443,
"step": 735
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.1003,
"step": 736
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.1581,
"step": 737
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.0736,
"step": 738
},
{
"epoch": 0.8,
"learning_rate": 0.0005,
"loss": 1.0974,
"step": 739
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.0872,
"step": 740
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.1186,
"step": 741
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.0866,
"step": 742
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.1553,
"step": 743
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.078,
"step": 744
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.1081,
"step": 745
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.0674,
"step": 746
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.0973,
"step": 747
},
{
"epoch": 0.81,
"learning_rate": 0.0005,
"loss": 1.0922,
"step": 748
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.1481,
"step": 749
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.1071,
"step": 750
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.1343,
"step": 751
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.1072,
"step": 752
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.0918,
"step": 753
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.1667,
"step": 754
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.165,
"step": 755
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.131,
"step": 756
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.1252,
"step": 757
},
{
"epoch": 0.82,
"learning_rate": 0.0005,
"loss": 1.1433,
"step": 758
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.1037,
"step": 759
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.0903,
"step": 760
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.1368,
"step": 761
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.1149,
"step": 762
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.0738,
"step": 763
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.0749,
"step": 764
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.1186,
"step": 765
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.0967,
"step": 766
},
{
"epoch": 0.83,
"learning_rate": 0.0005,
"loss": 1.0909,
"step": 767
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.0847,
"step": 768
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.1469,
"step": 769
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.118,
"step": 770
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.1076,
"step": 771
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.0834,
"step": 772
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.0864,
"step": 773
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.0932,
"step": 774
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.0861,
"step": 775
},
{
"epoch": 0.84,
"learning_rate": 0.0005,
"loss": 1.0539,
"step": 776
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.1354,
"step": 777
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.1273,
"step": 778
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.1437,
"step": 779
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.1279,
"step": 780
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.0666,
"step": 781
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.1058,
"step": 782
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.1323,
"step": 783
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.1055,
"step": 784
},
{
"epoch": 0.85,
"learning_rate": 0.0005,
"loss": 1.0792,
"step": 785
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.125,
"step": 786
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.1169,
"step": 787
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.1032,
"step": 788
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.0784,
"step": 789
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.1013,
"step": 790
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.0913,
"step": 791
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.1077,
"step": 792
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.1228,
"step": 793
},
{
"epoch": 0.86,
"learning_rate": 0.0005,
"loss": 1.0615,
"step": 794
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.1173,
"step": 795
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.0966,
"step": 796
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.1056,
"step": 797
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.0328,
"step": 798
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.1116,
"step": 799
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.0858,
"step": 800
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.1091,
"step": 801
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.0493,
"step": 802
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.105,
"step": 803
},
{
"epoch": 0.87,
"learning_rate": 0.0005,
"loss": 1.1777,
"step": 804
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.1451,
"step": 805
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.0778,
"step": 806
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.0932,
"step": 807
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.1024,
"step": 808
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.111,
"step": 809
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.1229,
"step": 810
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.0897,
"step": 811
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.1202,
"step": 812
},
{
"epoch": 0.88,
"learning_rate": 0.0005,
"loss": 1.1137,
"step": 813
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.1186,
"step": 814
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.1214,
"step": 815
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.0675,
"step": 816
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.1189,
"step": 817
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.0946,
"step": 818
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.1108,
"step": 819
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.0859,
"step": 820
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.1146,
"step": 821
},
{
"epoch": 0.89,
"learning_rate": 0.0005,
"loss": 1.0901,
"step": 822
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.102,
"step": 823
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.11,
"step": 824
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.0579,
"step": 825
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.1133,
"step": 826
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.0737,
"step": 827
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.0851,
"step": 828
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.0861,
"step": 829
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.1276,
"step": 830
},
{
"epoch": 0.9,
"learning_rate": 0.0005,
"loss": 1.1065,
"step": 831
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.071,
"step": 832
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.1132,
"step": 833
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.0474,
"step": 834
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.0713,
"step": 835
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.0895,
"step": 836
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.1,
"step": 837
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.0584,
"step": 838
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.1124,
"step": 839
},
{
"epoch": 0.91,
"learning_rate": 0.0005,
"loss": 1.0842,
"step": 840
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.1105,
"step": 841
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.0448,
"step": 842
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.0846,
"step": 843
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.1041,
"step": 844
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.1228,
"step": 845
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.0668,
"step": 846
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.0761,
"step": 847
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.065,
"step": 848
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.1331,
"step": 849
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 1.068,
"step": 850
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.0584,
"step": 851
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.1088,
"step": 852
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.0701,
"step": 853
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.1073,
"step": 854
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.1508,
"step": 855
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.1345,
"step": 856
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.1011,
"step": 857
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.1197,
"step": 858
},
{
"epoch": 0.93,
"learning_rate": 0.0005,
"loss": 1.1237,
"step": 859
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.1065,
"step": 860
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.0708,
"step": 861
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.1131,
"step": 862
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.1019,
"step": 863
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.1584,
"step": 864
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.0882,
"step": 865
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.0999,
"step": 866
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.076,
"step": 867
},
{
"epoch": 0.94,
"learning_rate": 0.0005,
"loss": 1.088,
"step": 868
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.1374,
"step": 869
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.0797,
"step": 870
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.1058,
"step": 871
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.1146,
"step": 872
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.0843,
"step": 873
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.1031,
"step": 874
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.0865,
"step": 875
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.0452,
"step": 876
},
{
"epoch": 0.95,
"learning_rate": 0.0005,
"loss": 1.0778,
"step": 877
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.0756,
"step": 878
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.1474,
"step": 879
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.103,
"step": 880
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.0811,
"step": 881
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.0889,
"step": 882
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.0838,
"step": 883
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.0785,
"step": 884
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.0681,
"step": 885
},
{
"epoch": 0.96,
"learning_rate": 0.0005,
"loss": 1.0803,
"step": 886
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.059,
"step": 887
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.061,
"step": 888
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.0898,
"step": 889
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.1096,
"step": 890
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.0858,
"step": 891
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.075,
"step": 892
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.0722,
"step": 893
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.0998,
"step": 894
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.073,
"step": 895
},
{
"epoch": 0.97,
"learning_rate": 0.0005,
"loss": 1.132,
"step": 896
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.1191,
"step": 897
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.0656,
"step": 898
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.0935,
"step": 899
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.0748,
"step": 900
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.1,
"step": 901
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.0594,
"step": 902
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.1052,
"step": 903
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.0865,
"step": 904
},
{
"epoch": 0.98,
"learning_rate": 0.0005,
"loss": 1.1092,
"step": 905
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.0992,
"step": 906
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.0669,
"step": 907
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.0876,
"step": 908
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.0512,
"step": 909
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.0696,
"step": 910
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.1406,
"step": 911
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.113,
"step": 912
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.1111,
"step": 913
},
{
"epoch": 0.99,
"learning_rate": 0.0005,
"loss": 1.1172,
"step": 914
},
{
"epoch": 1.0,
"learning_rate": 0.0005,
"loss": 1.0936,
"step": 915
},
{
"epoch": 1.0,
"learning_rate": 0.0005,
"loss": 1.0646,
"step": 916
},
{
"epoch": 1.0,
"learning_rate": 0.0005,
"loss": 1.0913,
"step": 917
},
{
"epoch": 1.0,
"learning_rate": 0.0005,
"loss": 1.1158,
"step": 918
},
{
"epoch": 1.0,
"learning_rate": 0.0005,
"loss": 1.2066,
"step": 919
}
],
"logging_steps": 1,
"max_steps": 2000,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 2.320438859784192e+17,
"trial_name": null,
"trial_params": null
}