bart-large-test / trainer_state.json
James Briggs
Initial commit
e25338b
raw
history blame
29.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"global_step": 280,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 3.5996,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 4.9727,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 3.5352,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 3.0605,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 3.4121,
"step": 5
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 3.293,
"step": 6
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 2.9238,
"step": 7
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 2.6406,
"step": 8
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 2.6426,
"step": 9
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 2.7148,
"step": 10
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 2.3477,
"step": 11
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 2.9609,
"step": 12
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 2.1797,
"step": 13
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 1.8857,
"step": 14
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 1.8379,
"step": 15
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 2.2383,
"step": 16
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 2.0156,
"step": 17
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 2.3145,
"step": 18
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 2.209,
"step": 19
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 2.4082,
"step": 20
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 2.1113,
"step": 21
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 2.2051,
"step": 22
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 2.0898,
"step": 23
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 1.9688,
"step": 24
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 2.0098,
"step": 25
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 1.9893,
"step": 26
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 1.626,
"step": 27
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 2.0938,
"step": 28
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 1.9971,
"step": 29
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 1.7969,
"step": 30
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 2.0684,
"step": 31
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 2.1445,
"step": 32
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 1.835,
"step": 33
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 2.0312,
"step": 34
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 1.6748,
"step": 35
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 2.168,
"step": 36
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 1.6338,
"step": 37
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 1.957,
"step": 38
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 1.5664,
"step": 39
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 1.7988,
"step": 40
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 1.9775,
"step": 41
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 2.2344,
"step": 42
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 2.1465,
"step": 43
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 1.8945,
"step": 44
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 2.4668,
"step": 45
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 1.8594,
"step": 46
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 1.7832,
"step": 47
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 1.6914,
"step": 48
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 1.8164,
"step": 49
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 1.748,
"step": 50
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 1.7295,
"step": 51
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 1.6348,
"step": 52
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 1.7852,
"step": 53
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 1.3389,
"step": 54
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 1.7471,
"step": 55
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 1.7236,
"step": 56
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 2.1211,
"step": 57
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 1.8281,
"step": 58
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 1.584,
"step": 59
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 2.2324,
"step": 60
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 1.8545,
"step": 61
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 1.8682,
"step": 62
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 1.8604,
"step": 63
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 2.0215,
"step": 64
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 1.6104,
"step": 65
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 1.7539,
"step": 66
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 1.9746,
"step": 67
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 1.3779,
"step": 68
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 2.0254,
"step": 69
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 1.5674,
"step": 70
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 1.4785,
"step": 71
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 1.7217,
"step": 72
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 1.625,
"step": 73
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 1.875,
"step": 74
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 1.9883,
"step": 75
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 1.6797,
"step": 76
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 1.7686,
"step": 77
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 1.6582,
"step": 78
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 2.1855,
"step": 79
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 1.7979,
"step": 80
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 2.1035,
"step": 81
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 1.752,
"step": 82
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 1.7871,
"step": 83
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 1.3613,
"step": 84
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 1.7275,
"step": 85
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 1.7656,
"step": 86
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 1.6826,
"step": 87
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 1.8018,
"step": 88
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 1.6641,
"step": 89
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 1.6318,
"step": 90
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 1.5752,
"step": 91
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 1.3965,
"step": 92
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 1.543,
"step": 93
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 1.5459,
"step": 94
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 1.8145,
"step": 95
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 1.4121,
"step": 96
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 1.6016,
"step": 97
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 1.8262,
"step": 98
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 1.9375,
"step": 99
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 1.6953,
"step": 100
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 1.5479,
"step": 101
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 1.5684,
"step": 102
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 1.8037,
"step": 103
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 1.6963,
"step": 104
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 1.4502,
"step": 105
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 1.7285,
"step": 106
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 1.4961,
"step": 107
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 1.751,
"step": 108
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 1.8936,
"step": 109
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 1.7363,
"step": 110
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 1.6406,
"step": 111
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 1.7012,
"step": 112
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 1.7969,
"step": 113
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 1.4629,
"step": 114
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 1.4238,
"step": 115
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 1.7998,
"step": 116
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 1.8223,
"step": 117
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 1.7256,
"step": 118
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 1.7061,
"step": 119
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 1.7188,
"step": 120
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 1.7197,
"step": 121
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 1.5801,
"step": 122
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 1.5977,
"step": 123
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 1.5107,
"step": 124
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 1.5957,
"step": 125
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 1.6143,
"step": 126
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 2.0312,
"step": 127
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 1.8018,
"step": 128
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 1.5645,
"step": 129
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 1.8369,
"step": 130
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 1.3682,
"step": 131
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 1.4131,
"step": 132
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 1.916,
"step": 133
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 1.584,
"step": 134
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 1.6074,
"step": 135
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 1.6309,
"step": 136
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 1.6074,
"step": 137
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 1.8457,
"step": 138
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 1.8535,
"step": 139
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 1.5439,
"step": 140
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 1.5664,
"step": 141
},
{
"epoch": 1.01,
"learning_rate": 0.0001,
"loss": 1.5977,
"step": 142
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 1.5645,
"step": 143
},
{
"epoch": 1.03,
"learning_rate": 0.0001,
"loss": 1.1816,
"step": 144
},
{
"epoch": 1.04,
"learning_rate": 0.0001,
"loss": 1.7852,
"step": 145
},
{
"epoch": 1.04,
"learning_rate": 0.0001,
"loss": 1.2666,
"step": 146
},
{
"epoch": 1.05,
"learning_rate": 0.0001,
"loss": 1.5752,
"step": 147
},
{
"epoch": 1.06,
"learning_rate": 0.0001,
"loss": 1.7041,
"step": 148
},
{
"epoch": 1.06,
"learning_rate": 0.0001,
"loss": 1.4316,
"step": 149
},
{
"epoch": 1.07,
"learning_rate": 0.0001,
"loss": 1.3887,
"step": 150
},
{
"epoch": 1.08,
"learning_rate": 0.0001,
"loss": 1.8936,
"step": 151
},
{
"epoch": 1.09,
"learning_rate": 0.0001,
"loss": 1.498,
"step": 152
},
{
"epoch": 1.09,
"learning_rate": 0.0001,
"loss": 1.626,
"step": 153
},
{
"epoch": 1.1,
"learning_rate": 0.0001,
"loss": 1.9414,
"step": 154
},
{
"epoch": 1.11,
"learning_rate": 0.0001,
"loss": 1.6758,
"step": 155
},
{
"epoch": 1.11,
"learning_rate": 0.0001,
"loss": 1.9248,
"step": 156
},
{
"epoch": 1.12,
"learning_rate": 0.0001,
"loss": 1.624,
"step": 157
},
{
"epoch": 1.13,
"learning_rate": 0.0001,
"loss": 1.793,
"step": 158
},
{
"epoch": 1.14,
"learning_rate": 0.0001,
"loss": 1.2383,
"step": 159
},
{
"epoch": 1.14,
"learning_rate": 0.0001,
"loss": 1.585,
"step": 160
},
{
"epoch": 1.15,
"learning_rate": 0.0001,
"loss": 1.417,
"step": 161
},
{
"epoch": 1.16,
"learning_rate": 0.0001,
"loss": 1.5586,
"step": 162
},
{
"epoch": 1.16,
"learning_rate": 0.0001,
"loss": 1.5234,
"step": 163
},
{
"epoch": 1.17,
"learning_rate": 0.0001,
"loss": 1.5645,
"step": 164
},
{
"epoch": 1.18,
"learning_rate": 0.0001,
"loss": 1.3896,
"step": 165
},
{
"epoch": 1.19,
"learning_rate": 0.0001,
"loss": 1.7812,
"step": 166
},
{
"epoch": 1.19,
"learning_rate": 0.0001,
"loss": 1.7793,
"step": 167
},
{
"epoch": 1.2,
"learning_rate": 0.0001,
"loss": 1.7812,
"step": 168
},
{
"epoch": 1.21,
"learning_rate": 0.0001,
"loss": 1.9229,
"step": 169
},
{
"epoch": 1.21,
"learning_rate": 0.0001,
"loss": 1.666,
"step": 170
},
{
"epoch": 1.22,
"learning_rate": 0.0001,
"loss": 1.9746,
"step": 171
},
{
"epoch": 1.23,
"learning_rate": 0.0001,
"loss": 1.6787,
"step": 172
},
{
"epoch": 1.24,
"learning_rate": 0.0001,
"loss": 1.7773,
"step": 173
},
{
"epoch": 1.24,
"learning_rate": 0.0001,
"loss": 1.6934,
"step": 174
},
{
"epoch": 1.25,
"learning_rate": 0.0001,
"loss": 1.5186,
"step": 175
},
{
"epoch": 1.26,
"learning_rate": 0.0001,
"loss": 1.79,
"step": 176
},
{
"epoch": 1.26,
"learning_rate": 0.0001,
"loss": 1.7012,
"step": 177
},
{
"epoch": 1.27,
"learning_rate": 0.0001,
"loss": 1.2969,
"step": 178
},
{
"epoch": 1.28,
"learning_rate": 0.0001,
"loss": 1.6855,
"step": 179
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 1.6055,
"step": 180
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 1.6328,
"step": 181
},
{
"epoch": 1.3,
"learning_rate": 0.0001,
"loss": 1.6934,
"step": 182
},
{
"epoch": 1.31,
"learning_rate": 0.0001,
"loss": 1.3418,
"step": 183
},
{
"epoch": 1.31,
"learning_rate": 0.0001,
"loss": 1.7578,
"step": 184
},
{
"epoch": 1.32,
"learning_rate": 0.0001,
"loss": 1.6445,
"step": 185
},
{
"epoch": 1.33,
"learning_rate": 0.0001,
"loss": 1.4941,
"step": 186
},
{
"epoch": 1.34,
"learning_rate": 0.0001,
"loss": 1.4053,
"step": 187
},
{
"epoch": 1.34,
"learning_rate": 0.0001,
"loss": 1.5752,
"step": 188
},
{
"epoch": 1.35,
"learning_rate": 0.0001,
"loss": 1.5996,
"step": 189
},
{
"epoch": 1.36,
"learning_rate": 0.0001,
"loss": 1.4834,
"step": 190
},
{
"epoch": 1.36,
"learning_rate": 0.0001,
"loss": 1.4775,
"step": 191
},
{
"epoch": 1.37,
"learning_rate": 0.0001,
"loss": 1.7051,
"step": 192
},
{
"epoch": 1.38,
"learning_rate": 0.0001,
"loss": 1.7812,
"step": 193
},
{
"epoch": 1.39,
"learning_rate": 0.0001,
"loss": 1.4375,
"step": 194
},
{
"epoch": 1.39,
"learning_rate": 0.0001,
"loss": 1.792,
"step": 195
},
{
"epoch": 1.4,
"learning_rate": 0.0001,
"loss": 1.6436,
"step": 196
},
{
"epoch": 1.41,
"learning_rate": 0.0001,
"loss": 1.6699,
"step": 197
},
{
"epoch": 1.41,
"learning_rate": 0.0001,
"loss": 1.2744,
"step": 198
},
{
"epoch": 1.42,
"learning_rate": 0.0001,
"loss": 1.4277,
"step": 199
},
{
"epoch": 1.43,
"learning_rate": 0.0001,
"loss": 1.4316,
"step": 200
},
{
"epoch": 1.44,
"learning_rate": 0.0001,
"loss": 1.292,
"step": 201
},
{
"epoch": 1.44,
"learning_rate": 0.0001,
"loss": 1.668,
"step": 202
},
{
"epoch": 1.45,
"learning_rate": 0.0001,
"loss": 1.4512,
"step": 203
},
{
"epoch": 1.46,
"learning_rate": 0.0001,
"loss": 1.7656,
"step": 204
},
{
"epoch": 1.46,
"learning_rate": 0.0001,
"loss": 1.4053,
"step": 205
},
{
"epoch": 1.47,
"learning_rate": 0.0001,
"loss": 1.8477,
"step": 206
},
{
"epoch": 1.48,
"learning_rate": 0.0001,
"loss": 1.3828,
"step": 207
},
{
"epoch": 1.49,
"learning_rate": 0.0001,
"loss": 1.4131,
"step": 208
},
{
"epoch": 1.49,
"learning_rate": 0.0001,
"loss": 1.168,
"step": 209
},
{
"epoch": 1.5,
"learning_rate": 0.0001,
"loss": 1.792,
"step": 210
},
{
"epoch": 1.51,
"learning_rate": 0.0001,
"loss": 1.8184,
"step": 211
},
{
"epoch": 1.51,
"learning_rate": 0.0001,
"loss": 1.5586,
"step": 212
},
{
"epoch": 1.52,
"learning_rate": 0.0001,
"loss": 1.2178,
"step": 213
},
{
"epoch": 1.53,
"learning_rate": 0.0001,
"loss": 2.0156,
"step": 214
},
{
"epoch": 1.54,
"learning_rate": 0.0001,
"loss": 1.8408,
"step": 215
},
{
"epoch": 1.54,
"learning_rate": 0.0001,
"loss": 1.5859,
"step": 216
},
{
"epoch": 1.55,
"learning_rate": 0.0001,
"loss": 1.4707,
"step": 217
},
{
"epoch": 1.56,
"learning_rate": 0.0001,
"loss": 1.8301,
"step": 218
},
{
"epoch": 1.56,
"learning_rate": 0.0001,
"loss": 1.4648,
"step": 219
},
{
"epoch": 1.57,
"learning_rate": 0.0001,
"loss": 1.583,
"step": 220
},
{
"epoch": 1.58,
"learning_rate": 0.0001,
"loss": 1.8945,
"step": 221
},
{
"epoch": 1.59,
"learning_rate": 0.0001,
"loss": 1.4541,
"step": 222
},
{
"epoch": 1.59,
"learning_rate": 0.0001,
"loss": 1.7383,
"step": 223
},
{
"epoch": 1.6,
"learning_rate": 0.0001,
"loss": 2.1191,
"step": 224
},
{
"epoch": 1.61,
"learning_rate": 0.0001,
"loss": 1.8965,
"step": 225
},
{
"epoch": 1.61,
"learning_rate": 0.0001,
"loss": 1.4854,
"step": 226
},
{
"epoch": 1.62,
"learning_rate": 0.0001,
"loss": 1.5781,
"step": 227
},
{
"epoch": 1.63,
"learning_rate": 0.0001,
"loss": 1.6709,
"step": 228
},
{
"epoch": 1.64,
"learning_rate": 0.0001,
"loss": 1.5127,
"step": 229
},
{
"epoch": 1.64,
"learning_rate": 0.0001,
"loss": 1.9502,
"step": 230
},
{
"epoch": 1.65,
"learning_rate": 0.0001,
"loss": 1.5635,
"step": 231
},
{
"epoch": 1.66,
"learning_rate": 0.0001,
"loss": 1.6846,
"step": 232
},
{
"epoch": 1.66,
"learning_rate": 0.0001,
"loss": 1.2803,
"step": 233
},
{
"epoch": 1.67,
"learning_rate": 0.0001,
"loss": 1.624,
"step": 234
},
{
"epoch": 1.68,
"learning_rate": 0.0001,
"loss": 1.2988,
"step": 235
},
{
"epoch": 1.69,
"learning_rate": 0.0001,
"loss": 1.9316,
"step": 236
},
{
"epoch": 1.69,
"learning_rate": 0.0001,
"loss": 1.3828,
"step": 237
},
{
"epoch": 1.7,
"learning_rate": 0.0001,
"loss": 1.3975,
"step": 238
},
{
"epoch": 1.71,
"learning_rate": 0.0001,
"loss": 1.8467,
"step": 239
},
{
"epoch": 1.71,
"learning_rate": 0.0001,
"loss": 1.4531,
"step": 240
},
{
"epoch": 1.72,
"learning_rate": 0.0001,
"loss": 1.5137,
"step": 241
},
{
"epoch": 1.73,
"learning_rate": 0.0001,
"loss": 1.4238,
"step": 242
},
{
"epoch": 1.74,
"learning_rate": 0.0001,
"loss": 1.7539,
"step": 243
},
{
"epoch": 1.74,
"learning_rate": 0.0001,
"loss": 1.6992,
"step": 244
},
{
"epoch": 1.75,
"learning_rate": 0.0001,
"loss": 1.4238,
"step": 245
},
{
"epoch": 1.76,
"learning_rate": 0.0001,
"loss": 1.5127,
"step": 246
},
{
"epoch": 1.76,
"learning_rate": 0.0001,
"loss": 1.3877,
"step": 247
},
{
"epoch": 1.77,
"learning_rate": 0.0001,
"loss": 1.7334,
"step": 248
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 1.498,
"step": 249
},
{
"epoch": 1.79,
"learning_rate": 0.0001,
"loss": 1.8457,
"step": 250
},
{
"epoch": 1.79,
"learning_rate": 0.0001,
"loss": 1.6035,
"step": 251
},
{
"epoch": 1.8,
"learning_rate": 0.0001,
"loss": 1.6357,
"step": 252
},
{
"epoch": 1.81,
"learning_rate": 0.0001,
"loss": 1.6641,
"step": 253
},
{
"epoch": 1.81,
"learning_rate": 0.0001,
"loss": 1.5029,
"step": 254
},
{
"epoch": 1.82,
"learning_rate": 0.0001,
"loss": 1.8223,
"step": 255
},
{
"epoch": 1.83,
"learning_rate": 0.0001,
"loss": 1.6719,
"step": 256
},
{
"epoch": 1.84,
"learning_rate": 0.0001,
"loss": 1.4766,
"step": 257
},
{
"epoch": 1.84,
"learning_rate": 0.0001,
"loss": 1.4863,
"step": 258
},
{
"epoch": 1.85,
"learning_rate": 0.0001,
"loss": 1.5752,
"step": 259
},
{
"epoch": 1.86,
"learning_rate": 0.0001,
"loss": 1.8574,
"step": 260
},
{
"epoch": 1.86,
"learning_rate": 0.0001,
"loss": 1.9775,
"step": 261
},
{
"epoch": 1.87,
"learning_rate": 0.0001,
"loss": 1.5381,
"step": 262
},
{
"epoch": 1.88,
"learning_rate": 0.0001,
"loss": 1.5703,
"step": 263
},
{
"epoch": 1.89,
"learning_rate": 0.0001,
"loss": 1.3584,
"step": 264
},
{
"epoch": 1.89,
"learning_rate": 0.0001,
"loss": 1.6475,
"step": 265
},
{
"epoch": 1.9,
"learning_rate": 0.0001,
"loss": 1.6982,
"step": 266
},
{
"epoch": 1.91,
"learning_rate": 0.0001,
"loss": 1.4414,
"step": 267
},
{
"epoch": 1.91,
"learning_rate": 0.0001,
"loss": 1.3584,
"step": 268
},
{
"epoch": 1.92,
"learning_rate": 0.0001,
"loss": 1.7646,
"step": 269
},
{
"epoch": 1.93,
"learning_rate": 0.0001,
"loss": 1.7969,
"step": 270
},
{
"epoch": 1.94,
"learning_rate": 0.0001,
"loss": 1.7061,
"step": 271
},
{
"epoch": 1.94,
"learning_rate": 0.0001,
"loss": 1.5898,
"step": 272
},
{
"epoch": 1.95,
"learning_rate": 0.0001,
"loss": 1.6416,
"step": 273
},
{
"epoch": 1.96,
"learning_rate": 0.0001,
"loss": 1.6152,
"step": 274
},
{
"epoch": 1.96,
"learning_rate": 0.0001,
"loss": 1.7949,
"step": 275
},
{
"epoch": 1.97,
"learning_rate": 0.0001,
"loss": 0.9819,
"step": 276
},
{
"epoch": 1.98,
"learning_rate": 0.0001,
"loss": 1.5293,
"step": 277
},
{
"epoch": 1.99,
"learning_rate": 0.0001,
"loss": 1.627,
"step": 278
},
{
"epoch": 1.99,
"learning_rate": 0.0001,
"loss": 1.8301,
"step": 279
},
{
"epoch": 2.0,
"learning_rate": 0.0001,
"loss": 1.6055,
"step": 280
},
{
"epoch": 2.0,
"step": 280,
"total_flos": 2.5450587402958956e+21,
"train_loss": 1.75728759765625,
"train_runtime": 1388.2147,
"train_samples_per_second": 413.644,
"train_steps_per_second": 0.202
}
],
"max_steps": 280,
"num_train_epochs": 2,
"total_flos": 2.5450587402958956e+21,
"trial_name": null,
"trial_params": null
}