educhat-qwen-hq / trainer_state.json
butyuhao's picture
update
c292617
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9998361998361999,
"eval_steps": 500,
"global_step": 763,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0,
"loss": 1.419,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 2.5e-06,
"loss": 1.4286,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 3.962406251802891e-06,
"loss": 1.3769,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 5e-06,
"loss": 1.3143,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 5.804820237218406e-06,
"loss": 1.3021,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 6.462406251802891e-06,
"loss": 1.3504,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 7.018387305144011e-06,
"loss": 1.322,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 7.499999999999999e-06,
"loss": 1.3809,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 7.924812503605782e-06,
"loss": 1.3668,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 8.304820237218408e-06,
"loss": 1.3955,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 8.648579046593244e-06,
"loss": 1.3302,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 8.96240625180289e-06,
"loss": 1.2661,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 9.25109929535273e-06,
"loss": 1.4107,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 9.51838730514401e-06,
"loss": 1.2451,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 9.767226489021297e-06,
"loss": 1.3415,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 1.2943,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 1.2522,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 1.2224,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 1.3191,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 1.2476,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 1.2646,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 1.3427,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 1.2767,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 1.3247,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 1.2376,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 1.3091,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 1.3247,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 1.2891,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 1.2212,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 1.1395,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 1.3225,
"step": 31
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 1.2411,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 1.2646,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 1e-05,
"loss": 1.247,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.2742,
"step": 35
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.3276,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.3118,
"step": 37
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.2362,
"step": 38
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.2002,
"step": 39
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.2544,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.2586,
"step": 41
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.2219,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.1487,
"step": 43
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.2374,
"step": 44
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.1346,
"step": 45
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.1702,
"step": 46
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.2095,
"step": 47
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.2731,
"step": 48
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 1.2282,
"step": 49
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.1828,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.2041,
"step": 51
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.1929,
"step": 52
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.1721,
"step": 53
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.1842,
"step": 54
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.2166,
"step": 55
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.1807,
"step": 56
},
{
"epoch": 0.07,
"learning_rate": 1e-05,
"loss": 1.1112,
"step": 57
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 1.2922,
"step": 58
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 1.1809,
"step": 59
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 1.1841,
"step": 60
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 1.2236,
"step": 61
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 1.2644,
"step": 62
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 1.223,
"step": 63
},
{
"epoch": 0.08,
"learning_rate": 1e-05,
"loss": 1.1729,
"step": 64
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 1.2133,
"step": 65
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 1.2487,
"step": 66
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 1.2464,
"step": 67
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 1.2267,
"step": 68
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 1.1504,
"step": 69
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 1.2984,
"step": 70
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 1.2635,
"step": 71
},
{
"epoch": 0.09,
"learning_rate": 1e-05,
"loss": 1.1728,
"step": 72
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.1855,
"step": 73
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.2193,
"step": 74
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.1411,
"step": 75
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.2151,
"step": 76
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.1246,
"step": 77
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.2639,
"step": 78
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.1682,
"step": 79
},
{
"epoch": 0.1,
"learning_rate": 1e-05,
"loss": 1.2273,
"step": 80
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.2022,
"step": 81
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.2625,
"step": 82
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.2314,
"step": 83
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.1618,
"step": 84
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.2443,
"step": 85
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.3048,
"step": 86
},
{
"epoch": 0.11,
"learning_rate": 1e-05,
"loss": 1.198,
"step": 87
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.1832,
"step": 88
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.3059,
"step": 89
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.1264,
"step": 90
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.1925,
"step": 91
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.2281,
"step": 92
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.1263,
"step": 93
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.1842,
"step": 94
},
{
"epoch": 0.12,
"learning_rate": 1e-05,
"loss": 1.1317,
"step": 95
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.3189,
"step": 96
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.1733,
"step": 97
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.2364,
"step": 98
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.191,
"step": 99
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.1974,
"step": 100
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.2286,
"step": 101
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.1647,
"step": 102
},
{
"epoch": 0.13,
"learning_rate": 1e-05,
"loss": 1.2806,
"step": 103
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.1928,
"step": 104
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.1728,
"step": 105
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.1455,
"step": 106
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.1748,
"step": 107
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.2779,
"step": 108
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.1871,
"step": 109
},
{
"epoch": 0.14,
"learning_rate": 1e-05,
"loss": 1.2795,
"step": 110
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.2084,
"step": 111
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.1314,
"step": 112
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.2351,
"step": 113
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.1762,
"step": 114
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.1904,
"step": 115
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.1552,
"step": 116
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.0961,
"step": 117
},
{
"epoch": 0.15,
"learning_rate": 1e-05,
"loss": 1.195,
"step": 118
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.1728,
"step": 119
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.125,
"step": 120
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.1861,
"step": 121
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.1536,
"step": 122
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.1977,
"step": 123
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.0763,
"step": 124
},
{
"epoch": 0.16,
"learning_rate": 1e-05,
"loss": 1.2132,
"step": 125
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.2042,
"step": 126
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.2516,
"step": 127
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.1579,
"step": 128
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.2348,
"step": 129
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.1223,
"step": 130
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.1664,
"step": 131
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.1369,
"step": 132
},
{
"epoch": 0.17,
"learning_rate": 1e-05,
"loss": 1.198,
"step": 133
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.1469,
"step": 134
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.1773,
"step": 135
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.1434,
"step": 136
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.0885,
"step": 137
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.2256,
"step": 138
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.1535,
"step": 139
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.1785,
"step": 140
},
{
"epoch": 0.18,
"learning_rate": 1e-05,
"loss": 1.1864,
"step": 141
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.1661,
"step": 142
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.167,
"step": 143
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.081,
"step": 144
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.168,
"step": 145
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.1371,
"step": 146
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.1839,
"step": 147
},
{
"epoch": 0.19,
"learning_rate": 1e-05,
"loss": 1.2448,
"step": 148
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.2198,
"step": 149
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.2014,
"step": 150
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.255,
"step": 151
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.1093,
"step": 152
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.1917,
"step": 153
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.1719,
"step": 154
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.1785,
"step": 155
},
{
"epoch": 0.2,
"learning_rate": 1e-05,
"loss": 1.2196,
"step": 156
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.2153,
"step": 157
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.1483,
"step": 158
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.2352,
"step": 159
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.1639,
"step": 160
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.1467,
"step": 161
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.0377,
"step": 162
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.1915,
"step": 163
},
{
"epoch": 0.21,
"learning_rate": 1e-05,
"loss": 1.171,
"step": 164
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.1325,
"step": 165
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.1899,
"step": 166
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.1738,
"step": 167
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.1637,
"step": 168
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.2024,
"step": 169
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.1296,
"step": 170
},
{
"epoch": 0.22,
"learning_rate": 1e-05,
"loss": 1.2399,
"step": 171
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.0746,
"step": 172
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.198,
"step": 173
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.2413,
"step": 174
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.2342,
"step": 175
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.2357,
"step": 176
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.159,
"step": 177
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.2127,
"step": 178
},
{
"epoch": 0.23,
"learning_rate": 1e-05,
"loss": 1.1189,
"step": 179
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.1645,
"step": 180
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.172,
"step": 181
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.1497,
"step": 182
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.0676,
"step": 183
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.1294,
"step": 184
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.187,
"step": 185
},
{
"epoch": 0.24,
"learning_rate": 1e-05,
"loss": 1.1007,
"step": 186
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.2878,
"step": 187
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.2019,
"step": 188
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.2057,
"step": 189
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.1091,
"step": 190
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.1311,
"step": 191
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.057,
"step": 192
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.2647,
"step": 193
},
{
"epoch": 0.25,
"learning_rate": 1e-05,
"loss": 1.1708,
"step": 194
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.1876,
"step": 195
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.2016,
"step": 196
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.1602,
"step": 197
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.0654,
"step": 198
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.2093,
"step": 199
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.2223,
"step": 200
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.2057,
"step": 201
},
{
"epoch": 0.26,
"learning_rate": 1e-05,
"loss": 1.1704,
"step": 202
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.1818,
"step": 203
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.1632,
"step": 204
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.1938,
"step": 205
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.2035,
"step": 206
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.1826,
"step": 207
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.1667,
"step": 208
},
{
"epoch": 0.27,
"learning_rate": 1e-05,
"loss": 1.1591,
"step": 209
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.1854,
"step": 210
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.1122,
"step": 211
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0791,
"step": 212
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.1404,
"step": 213
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.0595,
"step": 214
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.1264,
"step": 215
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.2122,
"step": 216
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 1.1667,
"step": 217
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.17,
"step": 218
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.1275,
"step": 219
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.1915,
"step": 220
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.1317,
"step": 221
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.1482,
"step": 222
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.1738,
"step": 223
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.1369,
"step": 224
},
{
"epoch": 0.29,
"learning_rate": 1e-05,
"loss": 1.1274,
"step": 225
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.098,
"step": 226
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.1118,
"step": 227
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.1298,
"step": 228
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.1451,
"step": 229
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.1106,
"step": 230
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.2434,
"step": 231
},
{
"epoch": 0.3,
"learning_rate": 1e-05,
"loss": 1.2448,
"step": 232
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.2178,
"step": 233
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.2108,
"step": 234
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.144,
"step": 235
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.207,
"step": 236
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.1764,
"step": 237
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.1789,
"step": 238
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.1937,
"step": 239
},
{
"epoch": 0.31,
"learning_rate": 1e-05,
"loss": 1.165,
"step": 240
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.0736,
"step": 241
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.122,
"step": 242
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.195,
"step": 243
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.1534,
"step": 244
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.0497,
"step": 245
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.22,
"step": 246
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.105,
"step": 247
},
{
"epoch": 0.32,
"learning_rate": 1e-05,
"loss": 1.1331,
"step": 248
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.1233,
"step": 249
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.1533,
"step": 250
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.0814,
"step": 251
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.1771,
"step": 252
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.1722,
"step": 253
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.1772,
"step": 254
},
{
"epoch": 0.33,
"learning_rate": 1e-05,
"loss": 1.1644,
"step": 255
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0746,
"step": 256
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.1853,
"step": 257
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.1081,
"step": 258
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.2228,
"step": 259
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.1414,
"step": 260
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.1071,
"step": 261
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.1327,
"step": 262
},
{
"epoch": 0.34,
"learning_rate": 1e-05,
"loss": 1.0866,
"step": 263
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.1377,
"step": 264
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.1854,
"step": 265
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.1462,
"step": 266
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.0672,
"step": 267
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.2539,
"step": 268
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.2115,
"step": 269
},
{
"epoch": 0.35,
"learning_rate": 1e-05,
"loss": 1.1712,
"step": 270
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.1874,
"step": 271
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.2199,
"step": 272
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.1905,
"step": 273
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.1675,
"step": 274
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.2049,
"step": 275
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.0632,
"step": 276
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.2113,
"step": 277
},
{
"epoch": 0.36,
"learning_rate": 1e-05,
"loss": 1.1781,
"step": 278
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.1979,
"step": 279
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.0251,
"step": 280
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.0963,
"step": 281
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.2862,
"step": 282
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.2339,
"step": 283
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.1541,
"step": 284
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.2246,
"step": 285
},
{
"epoch": 0.37,
"learning_rate": 1e-05,
"loss": 1.1562,
"step": 286
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.1304,
"step": 287
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.1691,
"step": 288
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.1246,
"step": 289
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.0747,
"step": 290
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.101,
"step": 291
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.1435,
"step": 292
},
{
"epoch": 0.38,
"learning_rate": 1e-05,
"loss": 1.1791,
"step": 293
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.1166,
"step": 294
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.1448,
"step": 295
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.1363,
"step": 296
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.1725,
"step": 297
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.0774,
"step": 298
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.1569,
"step": 299
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.0678,
"step": 300
},
{
"epoch": 0.39,
"learning_rate": 1e-05,
"loss": 1.1603,
"step": 301
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.0945,
"step": 302
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.1447,
"step": 303
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.213,
"step": 304
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.1232,
"step": 305
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.0816,
"step": 306
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.1605,
"step": 307
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.1522,
"step": 308
},
{
"epoch": 0.4,
"learning_rate": 1e-05,
"loss": 1.106,
"step": 309
},
{
"epoch": 0.41,
"learning_rate": 1e-05,
"loss": 1.0764,
"step": 310
},
{
"epoch": 0.41,
"learning_rate": 1e-05,
"loss": 1.1571,
"step": 311
},
{
"epoch": 0.41,
"learning_rate": 1e-05,
"loss": 1.0537,
"step": 312
},
{
"epoch": 0.41,
"learning_rate": 1e-05,
"loss": 1.1303,
"step": 313
},
{
"epoch": 0.41,
"learning_rate": 1e-05,
"loss": 1.1422,
"step": 314
},
{
"epoch": 0.41,
"learning_rate": 1e-05,
"loss": 1.2062,
"step": 315
},
{
"epoch": 0.41,
"learning_rate": 1e-05,
"loss": 1.2219,
"step": 316
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.1497,
"step": 317
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.1758,
"step": 318
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.0641,
"step": 319
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.137,
"step": 320
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.2398,
"step": 321
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.1259,
"step": 322
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.1144,
"step": 323
},
{
"epoch": 0.42,
"learning_rate": 1e-05,
"loss": 1.1751,
"step": 324
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 1.1245,
"step": 325
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 1.17,
"step": 326
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 1.0883,
"step": 327
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 1.0721,
"step": 328
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 1.2494,
"step": 329
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 1.1764,
"step": 330
},
{
"epoch": 0.43,
"learning_rate": 1e-05,
"loss": 1.1573,
"step": 331
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.1673,
"step": 332
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.1486,
"step": 333
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.1519,
"step": 334
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.0729,
"step": 335
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.1353,
"step": 336
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.1501,
"step": 337
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.1535,
"step": 338
},
{
"epoch": 0.44,
"learning_rate": 1e-05,
"loss": 1.1697,
"step": 339
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.0906,
"step": 340
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.1993,
"step": 341
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.1824,
"step": 342
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.1422,
"step": 343
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.093,
"step": 344
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.1148,
"step": 345
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.1025,
"step": 346
},
{
"epoch": 0.45,
"learning_rate": 1e-05,
"loss": 1.1931,
"step": 347
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 1.0956,
"step": 348
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 1.1995,
"step": 349
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 1.1928,
"step": 350
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 1.1257,
"step": 351
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 1.2489,
"step": 352
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 1.0889,
"step": 353
},
{
"epoch": 0.46,
"learning_rate": 1e-05,
"loss": 1.0701,
"step": 354
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.153,
"step": 355
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.1475,
"step": 356
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.1151,
"step": 357
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.1558,
"step": 358
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.1728,
"step": 359
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.1082,
"step": 360
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.0717,
"step": 361
},
{
"epoch": 0.47,
"learning_rate": 1e-05,
"loss": 1.0998,
"step": 362
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 1.0868,
"step": 363
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 1.2157,
"step": 364
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 1.023,
"step": 365
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 1.0781,
"step": 366
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 1.1602,
"step": 367
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 1.1489,
"step": 368
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 1.2046,
"step": 369
},
{
"epoch": 0.48,
"learning_rate": 1e-05,
"loss": 1.0684,
"step": 370
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 1.1471,
"step": 371
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 1.0886,
"step": 372
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 1.1701,
"step": 373
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 1.0904,
"step": 374
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 1.2215,
"step": 375
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 1.134,
"step": 376
},
{
"epoch": 0.49,
"learning_rate": 1e-05,
"loss": 1.1026,
"step": 377
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.1797,
"step": 378
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.1449,
"step": 379
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.1996,
"step": 380
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.0852,
"step": 381
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.0662,
"step": 382
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.1134,
"step": 383
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.1746,
"step": 384
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.0978,
"step": 385
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.1253,
"step": 386
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.1481,
"step": 387
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.151,
"step": 388
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.2107,
"step": 389
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.1108,
"step": 390
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.1166,
"step": 391
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.1116,
"step": 392
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 1.0886,
"step": 393
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.1247,
"step": 394
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.0827,
"step": 395
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.1228,
"step": 396
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.1126,
"step": 397
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.1113,
"step": 398
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.178,
"step": 399
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.06,
"step": 400
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.103,
"step": 401
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.0766,
"step": 402
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.1355,
"step": 403
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.1401,
"step": 404
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.0833,
"step": 405
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.1447,
"step": 406
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.0815,
"step": 407
},
{
"epoch": 0.53,
"learning_rate": 1e-05,
"loss": 1.1848,
"step": 408
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 1.0736,
"step": 409
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 1.0575,
"step": 410
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 1.0649,
"step": 411
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 1.1615,
"step": 412
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 1.1314,
"step": 413
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 1.1541,
"step": 414
},
{
"epoch": 0.54,
"learning_rate": 1e-05,
"loss": 1.0086,
"step": 415
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 1.0593,
"step": 416
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 1.0813,
"step": 417
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 1.1627,
"step": 418
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 1.0808,
"step": 419
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 1.1235,
"step": 420
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 1.1251,
"step": 421
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 1.1513,
"step": 422
},
{
"epoch": 0.55,
"learning_rate": 1e-05,
"loss": 1.1522,
"step": 423
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.058,
"step": 424
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.0659,
"step": 425
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.1449,
"step": 426
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.056,
"step": 427
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.0727,
"step": 428
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.1939,
"step": 429
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.097,
"step": 430
},
{
"epoch": 0.56,
"learning_rate": 1e-05,
"loss": 1.1245,
"step": 431
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 1.1875,
"step": 432
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 1.1237,
"step": 433
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 1.13,
"step": 434
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 1.1384,
"step": 435
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 1.0954,
"step": 436
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 1.1308,
"step": 437
},
{
"epoch": 0.57,
"learning_rate": 1e-05,
"loss": 1.177,
"step": 438
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.042,
"step": 439
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.249,
"step": 440
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.098,
"step": 441
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.0932,
"step": 442
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.2008,
"step": 443
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.1205,
"step": 444
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.1739,
"step": 445
},
{
"epoch": 0.58,
"learning_rate": 1e-05,
"loss": 1.0802,
"step": 446
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.1007,
"step": 447
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.2105,
"step": 448
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.1455,
"step": 449
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.1078,
"step": 450
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.1312,
"step": 451
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.1642,
"step": 452
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.1129,
"step": 453
},
{
"epoch": 0.59,
"learning_rate": 1e-05,
"loss": 1.121,
"step": 454
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.1408,
"step": 455
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.0623,
"step": 456
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.1354,
"step": 457
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.0905,
"step": 458
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.1315,
"step": 459
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.1072,
"step": 460
},
{
"epoch": 0.6,
"learning_rate": 1e-05,
"loss": 1.059,
"step": 461
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 1.1307,
"step": 462
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 1.2169,
"step": 463
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 1.0693,
"step": 464
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 1.0933,
"step": 465
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 1.1493,
"step": 466
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 1.076,
"step": 467
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 1.1333,
"step": 468
},
{
"epoch": 0.61,
"learning_rate": 1e-05,
"loss": 1.1087,
"step": 469
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 1.2311,
"step": 470
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 1.1785,
"step": 471
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 1.147,
"step": 472
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 1.067,
"step": 473
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 1.1096,
"step": 474
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 1.1161,
"step": 475
},
{
"epoch": 0.62,
"learning_rate": 1e-05,
"loss": 1.0665,
"step": 476
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 1.2197,
"step": 477
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 1.1278,
"step": 478
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 1.1091,
"step": 479
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 1.0789,
"step": 480
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 1.0956,
"step": 481
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 1.1117,
"step": 482
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 1.1508,
"step": 483
},
{
"epoch": 0.63,
"learning_rate": 1e-05,
"loss": 1.1839,
"step": 484
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 1.052,
"step": 485
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 1.0973,
"step": 486
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 1.067,
"step": 487
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 1.1481,
"step": 488
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 1.1636,
"step": 489
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 1.0766,
"step": 490
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 1.2124,
"step": 491
},
{
"epoch": 0.64,
"learning_rate": 1e-05,
"loss": 1.1512,
"step": 492
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.0625,
"step": 493
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.0444,
"step": 494
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.0134,
"step": 495
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.0785,
"step": 496
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.1982,
"step": 497
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.2205,
"step": 498
},
{
"epoch": 0.65,
"learning_rate": 1e-05,
"loss": 1.1091,
"step": 499
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.1838,
"step": 500
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.1055,
"step": 501
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.1933,
"step": 502
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.0714,
"step": 503
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.1622,
"step": 504
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.1007,
"step": 505
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.071,
"step": 506
},
{
"epoch": 0.66,
"learning_rate": 1e-05,
"loss": 1.0644,
"step": 507
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.19,
"step": 508
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.196,
"step": 509
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.0908,
"step": 510
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.1363,
"step": 511
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.1237,
"step": 512
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.1044,
"step": 513
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.125,
"step": 514
},
{
"epoch": 0.67,
"learning_rate": 1e-05,
"loss": 1.0984,
"step": 515
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.069,
"step": 516
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.0531,
"step": 517
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.1698,
"step": 518
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.07,
"step": 519
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.1798,
"step": 520
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.0844,
"step": 521
},
{
"epoch": 0.68,
"learning_rate": 1e-05,
"loss": 1.0588,
"step": 522
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.0756,
"step": 523
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.0595,
"step": 524
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 0.9999,
"step": 525
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.132,
"step": 526
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.1498,
"step": 527
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.0824,
"step": 528
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.189,
"step": 529
},
{
"epoch": 0.69,
"learning_rate": 1e-05,
"loss": 1.1561,
"step": 530
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 1.0432,
"step": 531
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 1.0952,
"step": 532
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 1.1779,
"step": 533
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 1.1764,
"step": 534
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 1.165,
"step": 535
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 1.032,
"step": 536
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 1.007,
"step": 537
},
{
"epoch": 0.7,
"learning_rate": 1e-05,
"loss": 1.0795,
"step": 538
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 1.1393,
"step": 539
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 1.1268,
"step": 540
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 1.1671,
"step": 541
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 1.1344,
"step": 542
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 1.0526,
"step": 543
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 1.0475,
"step": 544
},
{
"epoch": 0.71,
"learning_rate": 1e-05,
"loss": 1.1136,
"step": 545
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.0917,
"step": 546
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.1304,
"step": 547
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.1713,
"step": 548
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.1075,
"step": 549
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.0433,
"step": 550
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.1413,
"step": 551
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.1287,
"step": 552
},
{
"epoch": 0.72,
"learning_rate": 1e-05,
"loss": 1.0544,
"step": 553
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 1.0948,
"step": 554
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 1.0486,
"step": 555
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 1.0294,
"step": 556
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 1.1342,
"step": 557
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 1.1311,
"step": 558
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 1.292,
"step": 559
},
{
"epoch": 0.73,
"learning_rate": 1e-05,
"loss": 1.0462,
"step": 560
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.1373,
"step": 561
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.0422,
"step": 562
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.1323,
"step": 563
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.1583,
"step": 564
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.0488,
"step": 565
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.1455,
"step": 566
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.1454,
"step": 567
},
{
"epoch": 0.74,
"learning_rate": 1e-05,
"loss": 1.1856,
"step": 568
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.164,
"step": 569
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.1338,
"step": 570
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.1452,
"step": 571
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.105,
"step": 572
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.1738,
"step": 573
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.1409,
"step": 574
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.2128,
"step": 575
},
{
"epoch": 0.75,
"learning_rate": 1e-05,
"loss": 1.0991,
"step": 576
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 0.9785,
"step": 577
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.0146,
"step": 578
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.1587,
"step": 579
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.1499,
"step": 580
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.1695,
"step": 581
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.0072,
"step": 582
},
{
"epoch": 0.76,
"learning_rate": 1e-05,
"loss": 1.1465,
"step": 583
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.0976,
"step": 584
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.1581,
"step": 585
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.0455,
"step": 586
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.0656,
"step": 587
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.1564,
"step": 588
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.1414,
"step": 589
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.1129,
"step": 590
},
{
"epoch": 0.77,
"learning_rate": 1e-05,
"loss": 1.1502,
"step": 591
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.1551,
"step": 592
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.1153,
"step": 593
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.085,
"step": 594
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.1891,
"step": 595
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.0715,
"step": 596
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.0935,
"step": 597
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.1682,
"step": 598
},
{
"epoch": 0.78,
"learning_rate": 1e-05,
"loss": 1.1473,
"step": 599
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 1.0672,
"step": 600
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 1.0535,
"step": 601
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 0.9803,
"step": 602
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 1.0637,
"step": 603
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 1.1107,
"step": 604
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 1.016,
"step": 605
},
{
"epoch": 0.79,
"learning_rate": 1e-05,
"loss": 1.224,
"step": 606
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.0501,
"step": 607
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.0059,
"step": 608
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.0131,
"step": 609
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 0.9832,
"step": 610
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.1435,
"step": 611
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.2086,
"step": 612
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.1031,
"step": 613
},
{
"epoch": 0.8,
"learning_rate": 1e-05,
"loss": 1.1176,
"step": 614
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.1637,
"step": 615
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.0336,
"step": 616
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.0694,
"step": 617
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.0587,
"step": 618
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.1138,
"step": 619
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.2348,
"step": 620
},
{
"epoch": 0.81,
"learning_rate": 1e-05,
"loss": 1.1394,
"step": 621
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.1978,
"step": 622
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.1113,
"step": 623
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.2453,
"step": 624
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0189,
"step": 625
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0194,
"step": 626
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0692,
"step": 627
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.0821,
"step": 628
},
{
"epoch": 0.82,
"learning_rate": 1e-05,
"loss": 1.1102,
"step": 629
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.1246,
"step": 630
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.1086,
"step": 631
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.0267,
"step": 632
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.075,
"step": 633
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.209,
"step": 634
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.0182,
"step": 635
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.1436,
"step": 636
},
{
"epoch": 0.83,
"learning_rate": 1e-05,
"loss": 1.0958,
"step": 637
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 1.0123,
"step": 638
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 1.0992,
"step": 639
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 1.0386,
"step": 640
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 1.1307,
"step": 641
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 1.071,
"step": 642
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 1.1559,
"step": 643
},
{
"epoch": 0.84,
"learning_rate": 1e-05,
"loss": 1.1097,
"step": 644
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 1.1351,
"step": 645
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 1.1606,
"step": 646
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 1.1073,
"step": 647
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 1.1331,
"step": 648
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 1.0829,
"step": 649
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 1.0939,
"step": 650
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 1.0905,
"step": 651
},
{
"epoch": 0.85,
"learning_rate": 1e-05,
"loss": 1.2633,
"step": 652
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.098,
"step": 653
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.074,
"step": 654
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.1239,
"step": 655
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.1844,
"step": 656
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.0273,
"step": 657
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.1133,
"step": 658
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.1795,
"step": 659
},
{
"epoch": 0.86,
"learning_rate": 1e-05,
"loss": 1.159,
"step": 660
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.1022,
"step": 661
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.138,
"step": 662
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.1729,
"step": 663
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.1922,
"step": 664
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.1122,
"step": 665
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.1064,
"step": 666
},
{
"epoch": 0.87,
"learning_rate": 1e-05,
"loss": 1.1729,
"step": 667
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 1.2423,
"step": 668
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 1.1586,
"step": 669
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 1.1267,
"step": 670
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 1.1737,
"step": 671
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 1.1311,
"step": 672
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 1.0418,
"step": 673
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 1.1059,
"step": 674
},
{
"epoch": 0.88,
"learning_rate": 1e-05,
"loss": 1.0244,
"step": 675
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.0964,
"step": 676
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.0807,
"step": 677
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.109,
"step": 678
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.0575,
"step": 679
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.0783,
"step": 680
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 1.1035,
"step": 681
},
{
"epoch": 0.89,
"learning_rate": 1e-05,
"loss": 0.9895,
"step": 682
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 1.0588,
"step": 683
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 1.2132,
"step": 684
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 1.0925,
"step": 685
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 1.005,
"step": 686
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 1.0566,
"step": 687
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 1.1449,
"step": 688
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 1.1861,
"step": 689
},
{
"epoch": 0.9,
"learning_rate": 1e-05,
"loss": 1.1236,
"step": 690
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.1029,
"step": 691
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.1064,
"step": 692
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.1022,
"step": 693
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.0721,
"step": 694
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.0993,
"step": 695
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.232,
"step": 696
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.0639,
"step": 697
},
{
"epoch": 0.91,
"learning_rate": 1e-05,
"loss": 1.1605,
"step": 698
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 1.0583,
"step": 699
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 1.1495,
"step": 700
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 1.0219,
"step": 701
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 1.1221,
"step": 702
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 1.1241,
"step": 703
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 1.2033,
"step": 704
},
{
"epoch": 0.92,
"learning_rate": 1e-05,
"loss": 1.1577,
"step": 705
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.0877,
"step": 706
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.1729,
"step": 707
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.0328,
"step": 708
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.1185,
"step": 709
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.1177,
"step": 710
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.0357,
"step": 711
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.1044,
"step": 712
},
{
"epoch": 0.93,
"learning_rate": 1e-05,
"loss": 1.0242,
"step": 713
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 1.0319,
"step": 714
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 1.0402,
"step": 715
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 1.1038,
"step": 716
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 1.1568,
"step": 717
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 1.0341,
"step": 718
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 1.0592,
"step": 719
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 1.1089,
"step": 720
},
{
"epoch": 0.94,
"learning_rate": 1e-05,
"loss": 1.1582,
"step": 721
},
{
"epoch": 0.95,
"learning_rate": 1e-05,
"loss": 1.0815,
"step": 722
},
{
"epoch": 0.95,
"learning_rate": 1e-05,
"loss": 1.1986,
"step": 723
},
{
"epoch": 0.95,
"learning_rate": 1e-05,
"loss": 0.9891,
"step": 724
},
{
"epoch": 0.95,
"learning_rate": 1e-05,
"loss": 1.0625,
"step": 725
},
{
"epoch": 0.95,
"learning_rate": 1e-05,
"loss": 1.1619,
"step": 726
},
{
"epoch": 0.95,
"learning_rate": 1e-05,
"loss": 1.1473,
"step": 727
},
{
"epoch": 0.95,
"learning_rate": 1e-05,
"loss": 1.0042,
"step": 728
},
{
"epoch": 0.96,
"learning_rate": 1e-05,
"loss": 1.0952,
"step": 729
},
{
"epoch": 0.96,
"learning_rate": 1e-05,
"loss": 1.0996,
"step": 730
},
{
"epoch": 0.96,
"learning_rate": 1e-05,
"loss": 1.0994,
"step": 731
},
{
"epoch": 0.96,
"learning_rate": 1e-05,
"loss": 1.0666,
"step": 732
},
{
"epoch": 0.96,
"learning_rate": 1e-05,
"loss": 1.109,
"step": 733
},
{
"epoch": 0.96,
"learning_rate": 1e-05,
"loss": 1.1455,
"step": 734
},
{
"epoch": 0.96,
"learning_rate": 1e-05,
"loss": 1.0717,
"step": 735
},
{
"epoch": 0.96,
"learning_rate": 1e-05,
"loss": 1.0017,
"step": 736
},
{
"epoch": 0.97,
"learning_rate": 1e-05,
"loss": 1.0912,
"step": 737
},
{
"epoch": 0.97,
"learning_rate": 1e-05,
"loss": 1.0153,
"step": 738
},
{
"epoch": 0.97,
"learning_rate": 1e-05,
"loss": 1.1383,
"step": 739
},
{
"epoch": 0.97,
"learning_rate": 1e-05,
"loss": 1.0648,
"step": 740
},
{
"epoch": 0.97,
"learning_rate": 1e-05,
"loss": 1.0922,
"step": 741
},
{
"epoch": 0.97,
"learning_rate": 1e-05,
"loss": 1.2428,
"step": 742
},
{
"epoch": 0.97,
"learning_rate": 1e-05,
"loss": 1.0013,
"step": 743
},
{
"epoch": 0.97,
"learning_rate": 1e-05,
"loss": 1.0422,
"step": 744
},
{
"epoch": 0.98,
"learning_rate": 1e-05,
"loss": 1.0188,
"step": 745
},
{
"epoch": 0.98,
"learning_rate": 1e-05,
"loss": 1.0576,
"step": 746
},
{
"epoch": 0.98,
"learning_rate": 1e-05,
"loss": 1.0765,
"step": 747
},
{
"epoch": 0.98,
"learning_rate": 1e-05,
"loss": 1.1814,
"step": 748
},
{
"epoch": 0.98,
"learning_rate": 1e-05,
"loss": 1.0617,
"step": 749
},
{
"epoch": 0.98,
"learning_rate": 1e-05,
"loss": 1.0474,
"step": 750
},
{
"epoch": 0.98,
"learning_rate": 1e-05,
"loss": 1.005,
"step": 751
},
{
"epoch": 0.99,
"learning_rate": 1e-05,
"loss": 0.984,
"step": 752
},
{
"epoch": 0.99,
"learning_rate": 1e-05,
"loss": 1.0283,
"step": 753
},
{
"epoch": 0.99,
"learning_rate": 1e-05,
"loss": 1.0526,
"step": 754
},
{
"epoch": 0.99,
"learning_rate": 1e-05,
"loss": 1.0942,
"step": 755
},
{
"epoch": 0.99,
"learning_rate": 1e-05,
"loss": 1.1801,
"step": 756
},
{
"epoch": 0.99,
"learning_rate": 1e-05,
"loss": 1.1005,
"step": 757
},
{
"epoch": 0.99,
"learning_rate": 1e-05,
"loss": 1.1215,
"step": 758
},
{
"epoch": 0.99,
"learning_rate": 1e-05,
"loss": 1.0726,
"step": 759
},
{
"epoch": 1.0,
"learning_rate": 1e-05,
"loss": 1.1016,
"step": 760
},
{
"epoch": 1.0,
"learning_rate": 1e-05,
"loss": 1.0931,
"step": 761
},
{
"epoch": 1.0,
"learning_rate": 1e-05,
"loss": 1.1488,
"step": 762
},
{
"epoch": 1.0,
"learning_rate": 1e-05,
"loss": 1.069,
"step": 763
}
],
"logging_steps": 1.0,
"max_steps": 1526,
"num_train_epochs": 2,
"save_steps": 500,
"total_flos": 1662874904510464.0,
"trial_name": null,
"trial_params": null
}