LLAMA-2-460m / trainer_state.json
ccore's picture
Upload folder using huggingface_hub
882137d
raw
history blame
25.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9995995194233079,
"eval_steps": 500,
"global_step": 234,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0001,
"loss": 3.6446,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 6.5402,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0001,
"loss": 5.1279,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 4.647,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 4.2721,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 4.1431,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 4.0458,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 4.0124,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 3.9181,
"step": 9
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 3.9047,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 3.9171,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 3.8451,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 3.8507,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 3.7991,
"step": 14
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 3.8169,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 3.7717,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.0001,
"loss": 3.7706,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 3.6888,
"step": 18
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 3.7648,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 3.7429,
"step": 20
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 3.7368,
"step": 21
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 3.704,
"step": 22
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 3.6641,
"step": 23
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 3.6316,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 3.6546,
"step": 25
},
{
"epoch": 0.11,
"learning_rate": 0.0001,
"loss": 3.648,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 3.6295,
"step": 27
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 3.5866,
"step": 28
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 3.683,
"step": 29
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 3.5931,
"step": 30
},
{
"epoch": 0.13,
"learning_rate": 0.0001,
"loss": 3.6625,
"step": 31
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 3.5705,
"step": 32
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 3.5249,
"step": 33
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 3.5538,
"step": 34
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 3.6517,
"step": 35
},
{
"epoch": 0.15,
"learning_rate": 0.0001,
"loss": 3.5828,
"step": 36
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 3.5061,
"step": 37
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 3.5888,
"step": 38
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 3.5515,
"step": 39
},
{
"epoch": 0.17,
"learning_rate": 0.0001,
"loss": 3.5039,
"step": 40
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 3.5674,
"step": 41
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 3.543,
"step": 42
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 3.5187,
"step": 43
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 3.5273,
"step": 44
},
{
"epoch": 0.19,
"learning_rate": 0.0001,
"loss": 3.5568,
"step": 45
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 3.4998,
"step": 46
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 3.4959,
"step": 47
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 3.4999,
"step": 48
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 3.5434,
"step": 49
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 3.47,
"step": 50
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 3.5107,
"step": 51
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 3.533,
"step": 52
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 3.4785,
"step": 53
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 3.452,
"step": 54
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 3.4267,
"step": 55
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 3.4416,
"step": 56
},
{
"epoch": 0.24,
"learning_rate": 0.0001,
"loss": 3.4063,
"step": 57
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 3.4662,
"step": 58
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 3.4125,
"step": 59
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 3.4109,
"step": 60
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 3.3508,
"step": 61
},
{
"epoch": 0.26,
"learning_rate": 0.0001,
"loss": 3.3622,
"step": 62
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 3.3821,
"step": 63
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 3.3616,
"step": 64
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 3.3594,
"step": 65
},
{
"epoch": 0.28,
"learning_rate": 0.0001,
"loss": 3.3424,
"step": 66
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 3.3305,
"step": 67
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 3.3283,
"step": 68
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 3.2813,
"step": 69
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 3.3243,
"step": 70
},
{
"epoch": 0.3,
"learning_rate": 0.0001,
"loss": 3.3015,
"step": 71
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 3.2656,
"step": 72
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 3.2815,
"step": 73
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 3.251,
"step": 74
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 3.2704,
"step": 75
},
{
"epoch": 0.32,
"learning_rate": 0.0001,
"loss": 3.2934,
"step": 76
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 3.2403,
"step": 77
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 3.2308,
"step": 78
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 3.2043,
"step": 79
},
{
"epoch": 0.34,
"learning_rate": 0.0001,
"loss": 3.1788,
"step": 80
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 3.205,
"step": 81
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 3.1803,
"step": 82
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 3.2016,
"step": 83
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 3.131,
"step": 84
},
{
"epoch": 0.36,
"learning_rate": 0.0001,
"loss": 3.1249,
"step": 85
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 3.1844,
"step": 86
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 3.1567,
"step": 87
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 3.1218,
"step": 88
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 3.1267,
"step": 89
},
{
"epoch": 0.38,
"learning_rate": 0.0001,
"loss": 3.0832,
"step": 90
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 3.1017,
"step": 91
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 3.1062,
"step": 92
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 3.0567,
"step": 93
},
{
"epoch": 0.4,
"learning_rate": 0.0001,
"loss": 3.0983,
"step": 94
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 3.1293,
"step": 95
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 3.0962,
"step": 96
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 3.0518,
"step": 97
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 3.0512,
"step": 98
},
{
"epoch": 0.42,
"learning_rate": 0.0001,
"loss": 3.0493,
"step": 99
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 3.0442,
"step": 100
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 2.9817,
"step": 101
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 3.0215,
"step": 102
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 3.063,
"step": 103
},
{
"epoch": 0.44,
"learning_rate": 0.0001,
"loss": 2.9754,
"step": 104
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 3.0033,
"step": 105
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 2.9496,
"step": 106
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 3.0198,
"step": 107
},
{
"epoch": 0.46,
"learning_rate": 0.0001,
"loss": 3.0396,
"step": 108
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 2.9653,
"step": 109
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 2.9446,
"step": 110
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 2.9448,
"step": 111
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 2.9656,
"step": 112
},
{
"epoch": 0.48,
"learning_rate": 0.0001,
"loss": 2.9849,
"step": 113
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 2.9461,
"step": 114
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 2.8572,
"step": 115
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 2.9162,
"step": 116
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 2.9146,
"step": 117
},
{
"epoch": 0.5,
"learning_rate": 0.0001,
"loss": 2.8787,
"step": 118
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 2.9199,
"step": 119
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 2.9346,
"step": 120
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 2.9007,
"step": 121
},
{
"epoch": 0.52,
"learning_rate": 0.0001,
"loss": 2.9056,
"step": 122
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 2.8878,
"step": 123
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 2.8489,
"step": 124
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 2.8502,
"step": 125
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 2.8593,
"step": 126
},
{
"epoch": 0.54,
"learning_rate": 0.0001,
"loss": 2.8064,
"step": 127
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 2.8815,
"step": 128
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 2.8362,
"step": 129
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 2.8376,
"step": 130
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 2.8477,
"step": 131
},
{
"epoch": 0.56,
"learning_rate": 0.0001,
"loss": 2.7908,
"step": 132
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 2.86,
"step": 133
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 2.7842,
"step": 134
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 2.7412,
"step": 135
},
{
"epoch": 0.58,
"learning_rate": 0.0001,
"loss": 2.7729,
"step": 136
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 2.7708,
"step": 137
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 2.7162,
"step": 138
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 2.7579,
"step": 139
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 2.7572,
"step": 140
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 2.7245,
"step": 141
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 2.7325,
"step": 142
},
{
"epoch": 0.61,
"learning_rate": 0.0001,
"loss": 2.7613,
"step": 143
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 2.7442,
"step": 144
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 2.7399,
"step": 145
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 2.747,
"step": 146
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 2.7318,
"step": 147
},
{
"epoch": 0.63,
"learning_rate": 0.0001,
"loss": 2.7644,
"step": 148
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 2.765,
"step": 149
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 2.7045,
"step": 150
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 2.7082,
"step": 151
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 2.7346,
"step": 152
},
{
"epoch": 0.65,
"learning_rate": 0.0001,
"loss": 2.6992,
"step": 153
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 2.679,
"step": 154
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 2.7306,
"step": 155
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 2.6843,
"step": 156
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 2.6809,
"step": 157
},
{
"epoch": 0.67,
"learning_rate": 0.0001,
"loss": 2.6702,
"step": 158
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 2.6141,
"step": 159
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 2.679,
"step": 160
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 2.7093,
"step": 161
},
{
"epoch": 0.69,
"learning_rate": 0.0001,
"loss": 2.6653,
"step": 162
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 2.6362,
"step": 163
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 2.6647,
"step": 164
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 2.6576,
"step": 165
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 2.6108,
"step": 166
},
{
"epoch": 0.71,
"learning_rate": 0.0001,
"loss": 2.6401,
"step": 167
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 2.6776,
"step": 168
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 2.616,
"step": 169
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 2.6173,
"step": 170
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 2.6049,
"step": 171
},
{
"epoch": 0.73,
"learning_rate": 0.0001,
"loss": 2.6448,
"step": 172
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 2.6453,
"step": 173
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 2.5949,
"step": 174
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 2.6415,
"step": 175
},
{
"epoch": 0.75,
"learning_rate": 0.0001,
"loss": 2.5956,
"step": 176
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 2.5732,
"step": 177
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 2.588,
"step": 178
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 2.5918,
"step": 179
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 2.5963,
"step": 180
},
{
"epoch": 0.77,
"learning_rate": 0.0001,
"loss": 2.6073,
"step": 181
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 2.6167,
"step": 182
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 2.5766,
"step": 183
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 2.5509,
"step": 184
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 2.5583,
"step": 185
},
{
"epoch": 0.79,
"learning_rate": 0.0001,
"loss": 2.5683,
"step": 186
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 2.5381,
"step": 187
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 2.5717,
"step": 188
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 2.4957,
"step": 189
},
{
"epoch": 0.81,
"learning_rate": 0.0001,
"loss": 2.5815,
"step": 190
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 2.6002,
"step": 191
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 2.5265,
"step": 192
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 2.5229,
"step": 193
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 2.5607,
"step": 194
},
{
"epoch": 0.83,
"learning_rate": 0.0001,
"loss": 2.5452,
"step": 195
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 2.5288,
"step": 196
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 2.4955,
"step": 197
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 2.5229,
"step": 198
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 2.5293,
"step": 199
},
{
"epoch": 0.85,
"learning_rate": 0.0001,
"loss": 2.4859,
"step": 200
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 2.5187,
"step": 201
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 2.544,
"step": 202
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 2.5109,
"step": 203
},
{
"epoch": 0.87,
"learning_rate": 0.0001,
"loss": 2.4963,
"step": 204
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 2.5048,
"step": 205
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 2.4883,
"step": 206
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 2.4801,
"step": 207
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 2.5219,
"step": 208
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 2.5184,
"step": 209
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 2.4886,
"step": 210
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 2.5056,
"step": 211
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 2.5135,
"step": 212
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 2.4735,
"step": 213
},
{
"epoch": 0.91,
"learning_rate": 0.0001,
"loss": 2.4828,
"step": 214
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 2.4992,
"step": 215
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 2.4912,
"step": 216
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 2.4815,
"step": 217
},
{
"epoch": 0.93,
"learning_rate": 0.0001,
"loss": 2.4949,
"step": 218
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 2.4851,
"step": 219
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 2.5178,
"step": 220
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 2.4825,
"step": 221
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 2.4558,
"step": 222
},
{
"epoch": 0.95,
"learning_rate": 0.0001,
"loss": 2.5145,
"step": 223
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 2.4927,
"step": 224
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 2.4767,
"step": 225
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 2.4463,
"step": 226
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 2.4835,
"step": 227
},
{
"epoch": 0.97,
"learning_rate": 0.0001,
"loss": 2.473,
"step": 228
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 2.4432,
"step": 229
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 2.4499,
"step": 230
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 2.4551,
"step": 231
},
{
"epoch": 0.99,
"learning_rate": 0.0001,
"loss": 2.4642,
"step": 232
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 2.4617,
"step": 233
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 2.4561,
"step": 234
},
{
"epoch": 1.0,
"step": 234,
"total_flos": 2.668899657056256e+17,
"train_loss": 3.0363850155447283,
"train_runtime": 3285.3275,
"train_samples_per_second": 9.12,
"train_steps_per_second": 0.071
}
],
"logging_steps": 1.0,
"max_steps": 234,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 2.668899657056256e+17,
"trial_name": null,
"trial_params": null
}