swift_sw / trainer_state.json
yuchenlin's picture
add swift
bf2b3df
{
"best_metric": 0.10144635289907455,
"best_model_checkpoint": "model_ckpts/flan_large_0411/checkpoint-500",
"epoch": 1.0309119010819165,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0,
"loss": 2.0859,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.0,
"loss": 1.7471,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 1.509,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 1.552,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 1.2214,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 1.1383,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 1.1124,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.9961,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.7675,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.8992,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.7213,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 0.8539,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 0.6665,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 0.6982,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 0.6082,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 0.6788,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.6445,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.5978,
"step": 18
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.6115,
"step": 19
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.5072,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 0.5304,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.4517,
"step": 22
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.4339,
"step": 23
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.6107,
"step": 24
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.4486,
"step": 25
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 0.5635,
"step": 26
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.517,
"step": 27
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.4418,
"step": 28
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.5549,
"step": 29
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.4133,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 0.4221,
"step": 31
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 0.4018,
"step": 32
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 0.445,
"step": 33
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 0.3948,
"step": 34
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 0.3131,
"step": 35
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 0.2682,
"step": 36
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 0.2656,
"step": 37
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 0.3366,
"step": 38
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 0.3304,
"step": 39
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 0.3858,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 0.3185,
"step": 41
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 0.3853,
"step": 42
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 0.3407,
"step": 43
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 0.398,
"step": 44
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 0.3724,
"step": 45
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 0.3071,
"step": 46
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.2107,
"step": 47
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.3249,
"step": 48
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.2247,
"step": 49
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.3205,
"step": 50
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 0.3112,
"step": 51
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 0.2215,
"step": 52
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 0.2689,
"step": 53
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 0.2726,
"step": 54
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 0.3124,
"step": 55
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.2395,
"step": 56
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.2271,
"step": 57
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.3099,
"step": 58
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.2904,
"step": 59
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.3311,
"step": 60
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.2102,
"step": 61
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.2088,
"step": 62
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.2664,
"step": 63
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.241,
"step": 64
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 0.2373,
"step": 65
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.215,
"step": 66
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.2384,
"step": 67
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.2232,
"step": 68
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.27,
"step": 69
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.2309,
"step": 70
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 0.2802,
"step": 71
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 0.1925,
"step": 72
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 0.2079,
"step": 73
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 0.2097,
"step": 74
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 0.2146,
"step": 75
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.1824,
"step": 76
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.2179,
"step": 77
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.203,
"step": 78
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.2314,
"step": 79
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.2374,
"step": 80
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 0.1772,
"step": 81
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 0.2744,
"step": 82
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 0.2191,
"step": 83
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 0.2669,
"step": 84
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.2578,
"step": 85
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.2093,
"step": 86
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.2495,
"step": 87
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.1716,
"step": 88
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.1964,
"step": 89
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 0.1601,
"step": 90
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 0.1921,
"step": 91
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 0.2021,
"step": 92
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 0.1933,
"step": 93
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 0.1747,
"step": 94
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 0.3239,
"step": 95
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 0.2016,
"step": 96
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 0.1786,
"step": 97
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 0.1484,
"step": 98
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 0.2085,
"step": 99
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.2037,
"step": 100
},
{
"epoch": 0.21,
"eval_loss": 0.2043856978416443,
"eval_runtime": 949.0923,
"eval_samples_per_second": 34.016,
"eval_steps_per_second": 0.267,
"step": 100
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.209,
"step": 101
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.2336,
"step": 102
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.2064,
"step": 103
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.1811,
"step": 104
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.2142,
"step": 105
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.1959,
"step": 106
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.1612,
"step": 107
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.1505,
"step": 108
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.2053,
"step": 109
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.14,
"step": 110
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.2863,
"step": 111
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.1826,
"step": 112
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.146,
"step": 113
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.1208,
"step": 114
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 0.1573,
"step": 115
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 0.2216,
"step": 116
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 0.1939,
"step": 117
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 0.1872,
"step": 118
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.1737,
"step": 119
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.1509,
"step": 120
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.1952,
"step": 121
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.1518,
"step": 122
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.1514,
"step": 123
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 0.166,
"step": 124
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 0.1327,
"step": 125
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 0.1821,
"step": 126
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 0.2404,
"step": 127
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 0.1416,
"step": 128
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.1641,
"step": 129
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.1298,
"step": 130
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.1486,
"step": 131
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.1599,
"step": 132
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.0898,
"step": 133
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 0.1458,
"step": 134
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 0.107,
"step": 135
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 0.1175,
"step": 136
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 0.1248,
"step": 137
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 0.1983,
"step": 138
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.1772,
"step": 139
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.0884,
"step": 140
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.1383,
"step": 141
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.1082,
"step": 142
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.1572,
"step": 143
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.1179,
"step": 144
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.1147,
"step": 145
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.1277,
"step": 146
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.2077,
"step": 147
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 0.1235,
"step": 148
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.1499,
"step": 149
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.1552,
"step": 150
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.1877,
"step": 151
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.1677,
"step": 152
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 0.1878,
"step": 153
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 0.1817,
"step": 154
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 0.1055,
"step": 155
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 0.162,
"step": 156
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 0.1303,
"step": 157
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.0981,
"step": 158
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.0963,
"step": 159
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.1327,
"step": 160
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.167,
"step": 161
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.1431,
"step": 162
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 0.1583,
"step": 163
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 0.1395,
"step": 164
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 0.0974,
"step": 165
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 0.2083,
"step": 166
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 0.1538,
"step": 167
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.1298,
"step": 168
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.1947,
"step": 169
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.1031,
"step": 170
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.1545,
"step": 171
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.1194,
"step": 172
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.0988,
"step": 173
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.1526,
"step": 174
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.1673,
"step": 175
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.0977,
"step": 176
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 0.1249,
"step": 177
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.1572,
"step": 178
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.1437,
"step": 179
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.1001,
"step": 180
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.1167,
"step": 181
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 0.2169,
"step": 182
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 0.1151,
"step": 183
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 0.1024,
"step": 184
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 0.144,
"step": 185
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 0.2502,
"step": 186
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.1616,
"step": 187
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.0828,
"step": 188
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.1487,
"step": 189
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.1605,
"step": 190
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.1711,
"step": 191
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.0971,
"step": 192
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.1173,
"step": 193
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.2035,
"step": 194
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.0935,
"step": 195
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 0.1642,
"step": 196
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.0919,
"step": 197
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.1287,
"step": 198
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.104,
"step": 199
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.1304,
"step": 200
},
{
"epoch": 0.41,
"eval_loss": 0.1713656336069107,
"eval_runtime": 941.1442,
"eval_samples_per_second": 34.303,
"eval_steps_per_second": 0.269,
"step": 200
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.1692,
"step": 201
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 0.1555,
"step": 202
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 0.0741,
"step": 203
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 0.0975,
"step": 204
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 0.1215,
"step": 205
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 0.1174,
"step": 206
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.1581,
"step": 207
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.16,
"step": 208
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.1579,
"step": 209
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.0981,
"step": 210
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.0843,
"step": 211
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 0.124,
"step": 212
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 0.1287,
"step": 213
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 0.1344,
"step": 214
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 0.1168,
"step": 215
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.1141,
"step": 216
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.1051,
"step": 217
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.0952,
"step": 218
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.0949,
"step": 219
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.0679,
"step": 220
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 0.1158,
"step": 221
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 0.0817,
"step": 222
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 0.1035,
"step": 223
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 0.1039,
"step": 224
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 0.1031,
"step": 225
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.1152,
"step": 226
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.0968,
"step": 227
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.0682,
"step": 228
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.0822,
"step": 229
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.1364,
"step": 230
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 0.0945,
"step": 231
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 0.1614,
"step": 232
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 0.0957,
"step": 233
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 0.1053,
"step": 234
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 0.0719,
"step": 235
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.1377,
"step": 236
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.0988,
"step": 237
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.1374,
"step": 238
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.0913,
"step": 239
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.1398,
"step": 240
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 0.1,
"step": 241
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 0.0954,
"step": 242
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 0.0851,
"step": 243
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 0.0924,
"step": 244
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 0.112,
"step": 245
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.0862,
"step": 246
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.1043,
"step": 247
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.2192,
"step": 248
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.1003,
"step": 249
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 0.0825,
"step": 250
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 0.0998,
"step": 251
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 0.1333,
"step": 252
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 0.1,
"step": 253
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 0.1085,
"step": 254
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.1291,
"step": 255
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.121,
"step": 256
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.0972,
"step": 257
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.0779,
"step": 258
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.0833,
"step": 259
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 0.0992,
"step": 260
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 0.1175,
"step": 261
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 0.1271,
"step": 262
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 0.1154,
"step": 263
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 0.0816,
"step": 264
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.0985,
"step": 265
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.1091,
"step": 266
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.114,
"step": 267
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.0989,
"step": 268
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.1541,
"step": 269
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 0.0868,
"step": 270
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 0.0645,
"step": 271
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 0.0927,
"step": 272
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 0.1146,
"step": 273
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 0.157,
"step": 274
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.0823,
"step": 275
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.1343,
"step": 276
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.1015,
"step": 277
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.0746,
"step": 278
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.0918,
"step": 279
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 0.1038,
"step": 280
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 0.1023,
"step": 281
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 0.0809,
"step": 282
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 0.0715,
"step": 283
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.0806,
"step": 284
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.0997,
"step": 285
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.0793,
"step": 286
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.0658,
"step": 287
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.1345,
"step": 288
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.0867,
"step": 289
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.0642,
"step": 290
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.09,
"step": 291
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.0836,
"step": 292
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.056,
"step": 293
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 0.1309,
"step": 294
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 0.0825,
"step": 295
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 0.1343,
"step": 296
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 0.0874,
"step": 297
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 0.1005,
"step": 298
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.0804,
"step": 299
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.0688,
"step": 300
},
{
"epoch": 0.62,
"eval_loss": 0.11704447865486145,
"eval_runtime": 967.1425,
"eval_samples_per_second": 33.381,
"eval_steps_per_second": 0.262,
"step": 300
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.0868,
"step": 301
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.0682,
"step": 302
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.1118,
"step": 303
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 0.0908,
"step": 304
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 0.0633,
"step": 305
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 0.0839,
"step": 306
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 0.0796,
"step": 307
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 0.0631,
"step": 308
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.0797,
"step": 309
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.1014,
"step": 310
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.1586,
"step": 311
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.0789,
"step": 312
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.0722,
"step": 313
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.12,
"step": 314
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.0665,
"step": 315
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.0963,
"step": 316
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 0.1095,
"step": 317
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.0728,
"step": 318
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.0795,
"step": 319
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.0729,
"step": 320
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.0599,
"step": 321
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.0803,
"step": 322
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 0.0511,
"step": 323
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 0.0783,
"step": 324
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 0.1076,
"step": 325
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 0.0917,
"step": 326
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 0.0581,
"step": 327
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.0665,
"step": 328
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.0707,
"step": 329
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.0926,
"step": 330
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.0544,
"step": 331
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.1131,
"step": 332
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 0.1424,
"step": 333
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 0.0938,
"step": 334
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 0.1193,
"step": 335
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 0.0688,
"step": 336
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 0.1052,
"step": 337
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.1174,
"step": 338
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.085,
"step": 339
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.0913,
"step": 340
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.0902,
"step": 341
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.0591,
"step": 342
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 0.0858,
"step": 343
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 0.0681,
"step": 344
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 0.0756,
"step": 345
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 0.0842,
"step": 346
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.1008,
"step": 347
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.1254,
"step": 348
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.0795,
"step": 349
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.0869,
"step": 350
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.1,
"step": 351
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 0.0925,
"step": 352
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 0.0609,
"step": 353
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 0.0579,
"step": 354
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 0.1045,
"step": 355
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 0.082,
"step": 356
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.1129,
"step": 357
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.0776,
"step": 358
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.0747,
"step": 359
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.1089,
"step": 360
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.0581,
"step": 361
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.0613,
"step": 362
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.0679,
"step": 363
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.0817,
"step": 364
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.0609,
"step": 365
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 0.0688,
"step": 366
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.126,
"step": 367
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.0956,
"step": 368
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.0566,
"step": 369
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.0407,
"step": 370
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.0685,
"step": 371
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.0404,
"step": 372
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.1011,
"step": 373
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.0549,
"step": 374
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.0562,
"step": 375
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 0.0477,
"step": 376
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.1497,
"step": 377
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.0704,
"step": 378
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.097,
"step": 379
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.0732,
"step": 380
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 0.0572,
"step": 381
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 0.0902,
"step": 382
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 0.0783,
"step": 383
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 0.1082,
"step": 384
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 0.057,
"step": 385
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.0636,
"step": 386
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.1116,
"step": 387
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.0442,
"step": 388
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.1222,
"step": 389
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.0978,
"step": 390
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 0.0529,
"step": 391
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 0.0465,
"step": 392
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 0.0378,
"step": 393
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 0.094,
"step": 394
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 0.106,
"step": 395
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.0707,
"step": 396
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.0667,
"step": 397
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.0662,
"step": 398
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.0952,
"step": 399
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.055,
"step": 400
},
{
"epoch": 0.82,
"eval_loss": 0.10834690928459167,
"eval_runtime": 964.0919,
"eval_samples_per_second": 33.486,
"eval_steps_per_second": 0.262,
"step": 400
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.088,
"step": 401
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.084,
"step": 402
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.0543,
"step": 403
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.0969,
"step": 404
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 0.0494,
"step": 405
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.1015,
"step": 406
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.0843,
"step": 407
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.0427,
"step": 408
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.0777,
"step": 409
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.0499,
"step": 410
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 0.1067,
"step": 411
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 0.1234,
"step": 412
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 0.0464,
"step": 413
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 0.0744,
"step": 414
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.1134,
"step": 415
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.0643,
"step": 416
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.0636,
"step": 417
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.0602,
"step": 418
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.0845,
"step": 419
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.0637,
"step": 420
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.0806,
"step": 421
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.1163,
"step": 422
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.0887,
"step": 423
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 0.0852,
"step": 424
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.0468,
"step": 425
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.035,
"step": 426
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.0691,
"step": 427
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.0598,
"step": 428
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.0653,
"step": 429
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.0783,
"step": 430
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.0858,
"step": 431
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.0845,
"step": 432
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.0677,
"step": 433
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 0.0609,
"step": 434
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.0679,
"step": 435
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.0898,
"step": 436
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.118,
"step": 437
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.0654,
"step": 438
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.0688,
"step": 439
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 0.0776,
"step": 440
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 0.0471,
"step": 441
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 0.0637,
"step": 442
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 0.0776,
"step": 443
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 0.0877,
"step": 444
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.0739,
"step": 445
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.0605,
"step": 446
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.0581,
"step": 447
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.0601,
"step": 448
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.0386,
"step": 449
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.0696,
"step": 450
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.1212,
"step": 451
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.1015,
"step": 452
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 0.0549,
"step": 453
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.0789,
"step": 454
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.0589,
"step": 455
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.0517,
"step": 456
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.1175,
"step": 457
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.1051,
"step": 458
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.0799,
"step": 459
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.061,
"step": 460
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.102,
"step": 461
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.076,
"step": 462
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 0.0885,
"step": 463
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.1001,
"step": 464
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.0541,
"step": 465
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.0625,
"step": 466
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.0762,
"step": 467
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.0836,
"step": 468
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 0.0593,
"step": 469
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 0.0892,
"step": 470
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 0.0841,
"step": 471
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 0.0647,
"step": 472
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 0.0566,
"step": 473
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.105,
"step": 474
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.0926,
"step": 475
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.0564,
"step": 476
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.0504,
"step": 477
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 0.0474,
"step": 478
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 0.0477,
"step": 479
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 0.0577,
"step": 480
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 0.0782,
"step": 481
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 0.059,
"step": 482
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.0467,
"step": 483
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.0392,
"step": 484
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.079,
"step": 485
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.125,
"step": 486
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.0938,
"step": 487
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.0671,
"step": 488
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.0634,
"step": 489
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.066,
"step": 490
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.0636,
"step": 491
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 0.0463,
"step": 492
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.0723,
"step": 493
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.0808,
"step": 494
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.0636,
"step": 495
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.0643,
"step": 496
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.0511,
"step": 497
},
{
"epoch": 1.03,
"learning_rate": 0.0001,
"loss": 0.0624,
"step": 498
},
{
"epoch": 1.03,
"learning_rate": 0.0001,
"loss": 0.0528,
"step": 499
},
{
"epoch": 1.03,
"learning_rate": 0.0001,
"loss": 0.046,
"step": 500
},
{
"epoch": 1.03,
"eval_loss": 0.10144635289907455,
"eval_runtime": 971.1805,
"eval_samples_per_second": 33.242,
"eval_steps_per_second": 0.261,
"step": 500
}
],
"max_steps": 4850,
"num_train_epochs": 10,
"total_flos": 2.229441347410985e+17,
"trial_name": null,
"trial_params": null
}