InstructScore / trainer_state.json
Wenda Xu
small fix
2825b5a
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9873843566021865,
"global_step": 222,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0,
"loss": 9.0082,
"step": 1
},
{
"epoch": 0.03,
"learning_rate": 0,
"loss": 8.6216,
"step": 2
},
{
"epoch": 0.04,
"learning_rate": 0,
"loss": 8.9495,
"step": 3
},
{
"epoch": 0.05,
"learning_rate": 0,
"loss": 9.3486,
"step": 4
},
{
"epoch": 0.07,
"learning_rate": 0,
"loss": 9.1724,
"step": 5
},
{
"epoch": 0.08,
"learning_rate": 0,
"loss": 8.6433,
"step": 6
},
{
"epoch": 0.09,
"learning_rate": 0.0,
"loss": 8.872,
"step": 7
},
{
"epoch": 0.11,
"learning_rate": 0.0,
"loss": 10.083,
"step": 8
},
{
"epoch": 0.12,
"learning_rate": 0.0,
"loss": 10.3374,
"step": 9
},
{
"epoch": 0.13,
"learning_rate": 2e-05,
"loss": 9.8785,
"step": 10
},
{
"epoch": 0.15,
"learning_rate": 2e-05,
"loss": 10.5295,
"step": 11
},
{
"epoch": 0.16,
"learning_rate": 2e-05,
"loss": 7.6001,
"step": 12
},
{
"epoch": 0.17,
"learning_rate": 2e-05,
"loss": 7.0393,
"step": 13
},
{
"epoch": 0.19,
"learning_rate": 2e-05,
"loss": 6.9884,
"step": 14
},
{
"epoch": 0.2,
"learning_rate": 2e-05,
"loss": 6.9941,
"step": 15
},
{
"epoch": 0.22,
"learning_rate": 2e-05,
"loss": 7.235,
"step": 16
},
{
"epoch": 0.23,
"learning_rate": 2e-05,
"loss": 6.7456,
"step": 17
},
{
"epoch": 0.24,
"learning_rate": 2e-05,
"loss": 6.7632,
"step": 18
},
{
"epoch": 0.26,
"learning_rate": 2e-05,
"loss": 6.3373,
"step": 19
},
{
"epoch": 0.27,
"learning_rate": 2e-05,
"loss": 6.5851,
"step": 20
},
{
"epoch": 0.28,
"learning_rate": 2e-05,
"loss": 6.8799,
"step": 21
},
{
"epoch": 0.3,
"learning_rate": 2e-05,
"loss": 6.0525,
"step": 22
},
{
"epoch": 0.31,
"learning_rate": 2e-05,
"loss": 6.178,
"step": 23
},
{
"epoch": 0.32,
"learning_rate": 2e-05,
"loss": 6.6378,
"step": 24
},
{
"epoch": 0.34,
"learning_rate": 2e-05,
"loss": 6.1607,
"step": 25
},
{
"epoch": 0.35,
"learning_rate": 2e-05,
"loss": 6.2084,
"step": 26
},
{
"epoch": 0.36,
"learning_rate": 2e-05,
"loss": 5.7216,
"step": 27
},
{
"epoch": 0.38,
"learning_rate": 2e-05,
"loss": 5.5294,
"step": 28
},
{
"epoch": 0.39,
"learning_rate": 2e-05,
"loss": 5.6123,
"step": 29
},
{
"epoch": 0.4,
"learning_rate": 2e-05,
"loss": 5.3022,
"step": 30
},
{
"epoch": 0.42,
"learning_rate": 2e-05,
"loss": 5.2346,
"step": 31
},
{
"epoch": 0.43,
"learning_rate": 2e-05,
"loss": 5.268,
"step": 32
},
{
"epoch": 0.44,
"learning_rate": 2e-05,
"loss": 4.8788,
"step": 33
},
{
"epoch": 0.46,
"learning_rate": 2e-05,
"loss": 4.8944,
"step": 34
},
{
"epoch": 0.47,
"learning_rate": 2e-05,
"loss": 4.487,
"step": 35
},
{
"epoch": 0.48,
"learning_rate": 2e-05,
"loss": 4.3159,
"step": 36
},
{
"epoch": 0.5,
"learning_rate": 2e-05,
"loss": 4.1472,
"step": 37
},
{
"epoch": 0.51,
"learning_rate": 2e-05,
"loss": 4.2212,
"step": 38
},
{
"epoch": 0.52,
"learning_rate": 2e-05,
"loss": 4.1312,
"step": 39
},
{
"epoch": 0.54,
"learning_rate": 2e-05,
"loss": 3.9116,
"step": 40
},
{
"epoch": 0.55,
"learning_rate": 2e-05,
"loss": 3.8727,
"step": 41
},
{
"epoch": 0.57,
"learning_rate": 2e-05,
"loss": 3.4962,
"step": 42
},
{
"epoch": 0.58,
"learning_rate": 2e-05,
"loss": 3.2736,
"step": 43
},
{
"epoch": 0.59,
"learning_rate": 2e-05,
"loss": 3.1902,
"step": 44
},
{
"epoch": 0.61,
"learning_rate": 2e-05,
"loss": 3.0781,
"step": 45
},
{
"epoch": 0.62,
"learning_rate": 2e-05,
"loss": 2.9503,
"step": 46
},
{
"epoch": 0.63,
"learning_rate": 2e-05,
"loss": 2.6742,
"step": 47
},
{
"epoch": 0.65,
"learning_rate": 2e-05,
"loss": 2.5908,
"step": 48
},
{
"epoch": 0.66,
"learning_rate": 2e-05,
"loss": 2.4428,
"step": 49
},
{
"epoch": 0.67,
"learning_rate": 2e-05,
"loss": 2.1305,
"step": 50
},
{
"epoch": 0.69,
"learning_rate": 2e-05,
"loss": 2.0908,
"step": 51
},
{
"epoch": 0.7,
"learning_rate": 2e-05,
"loss": 1.8319,
"step": 52
},
{
"epoch": 0.71,
"learning_rate": 2e-05,
"loss": 1.6784,
"step": 53
},
{
"epoch": 0.73,
"learning_rate": 2e-05,
"loss": 1.553,
"step": 54
},
{
"epoch": 0.74,
"learning_rate": 2e-05,
"loss": 1.3679,
"step": 55
},
{
"epoch": 0.75,
"learning_rate": 2e-05,
"loss": 1.2306,
"step": 56
},
{
"epoch": 0.77,
"learning_rate": 2e-05,
"loss": 1.0531,
"step": 57
},
{
"epoch": 0.78,
"learning_rate": 2e-05,
"loss": 0.9721,
"step": 58
},
{
"epoch": 0.79,
"learning_rate": 2e-05,
"loss": 0.8153,
"step": 59
},
{
"epoch": 0.81,
"learning_rate": 2e-05,
"loss": 0.6768,
"step": 60
},
{
"epoch": 0.82,
"learning_rate": 2e-05,
"loss": 0.5962,
"step": 61
},
{
"epoch": 0.83,
"learning_rate": 2e-05,
"loss": 0.5061,
"step": 62
},
{
"epoch": 0.85,
"learning_rate": 2e-05,
"loss": 0.4319,
"step": 63
},
{
"epoch": 0.86,
"learning_rate": 2e-05,
"loss": 0.372,
"step": 64
},
{
"epoch": 0.87,
"learning_rate": 2e-05,
"loss": 0.327,
"step": 65
},
{
"epoch": 0.89,
"learning_rate": 2e-05,
"loss": 0.2799,
"step": 66
},
{
"epoch": 0.9,
"learning_rate": 2e-05,
"loss": 0.2455,
"step": 67
},
{
"epoch": 0.92,
"learning_rate": 2e-05,
"loss": 0.2267,
"step": 68
},
{
"epoch": 0.93,
"learning_rate": 2e-05,
"loss": 0.2177,
"step": 69
},
{
"epoch": 0.94,
"learning_rate": 2e-05,
"loss": 0.2029,
"step": 70
},
{
"epoch": 0.96,
"learning_rate": 2e-05,
"loss": 0.1958,
"step": 71
},
{
"epoch": 0.97,
"learning_rate": 2e-05,
"loss": 0.1748,
"step": 72
},
{
"epoch": 0.98,
"learning_rate": 2e-05,
"loss": 0.1772,
"step": 73
},
{
"epoch": 1.0,
"learning_rate": 2e-05,
"loss": 0.1639,
"step": 74
},
{
"epoch": 1.01,
"learning_rate": 2e-05,
"loss": 0.1495,
"step": 75
},
{
"epoch": 1.02,
"learning_rate": 2e-05,
"loss": 0.1595,
"step": 76
},
{
"epoch": 1.04,
"learning_rate": 2e-05,
"loss": 0.141,
"step": 77
},
{
"epoch": 1.05,
"learning_rate": 2e-05,
"loss": 0.1411,
"step": 78
},
{
"epoch": 1.06,
"learning_rate": 2e-05,
"loss": 0.1456,
"step": 79
},
{
"epoch": 1.08,
"learning_rate": 2e-05,
"loss": 0.1396,
"step": 80
},
{
"epoch": 1.09,
"learning_rate": 2e-05,
"loss": 0.1276,
"step": 81
},
{
"epoch": 1.1,
"learning_rate": 2e-05,
"loss": 0.1285,
"step": 82
},
{
"epoch": 1.12,
"learning_rate": 2e-05,
"loss": 0.1274,
"step": 83
},
{
"epoch": 1.13,
"learning_rate": 2e-05,
"loss": 0.1315,
"step": 84
},
{
"epoch": 1.14,
"learning_rate": 2e-05,
"loss": 0.1283,
"step": 85
},
{
"epoch": 1.16,
"learning_rate": 2e-05,
"loss": 0.1055,
"step": 86
},
{
"epoch": 1.17,
"learning_rate": 2e-05,
"loss": 0.1164,
"step": 87
},
{
"epoch": 1.18,
"learning_rate": 2e-05,
"loss": 0.1306,
"step": 88
},
{
"epoch": 1.2,
"learning_rate": 2e-05,
"loss": 0.121,
"step": 89
},
{
"epoch": 1.21,
"learning_rate": 2e-05,
"loss": 0.1275,
"step": 90
},
{
"epoch": 1.22,
"learning_rate": 2e-05,
"loss": 0.1081,
"step": 91
},
{
"epoch": 1.24,
"learning_rate": 2e-05,
"loss": 0.1114,
"step": 92
},
{
"epoch": 1.25,
"learning_rate": 2e-05,
"loss": 0.1186,
"step": 93
},
{
"epoch": 1.26,
"learning_rate": 2e-05,
"loss": 0.1097,
"step": 94
},
{
"epoch": 1.28,
"learning_rate": 2e-05,
"loss": 0.1163,
"step": 95
},
{
"epoch": 1.29,
"learning_rate": 2e-05,
"loss": 0.113,
"step": 96
},
{
"epoch": 1.31,
"learning_rate": 2e-05,
"loss": 0.1217,
"step": 97
},
{
"epoch": 1.32,
"learning_rate": 2e-05,
"loss": 0.1132,
"step": 98
},
{
"epoch": 1.33,
"learning_rate": 2e-05,
"loss": 0.1203,
"step": 99
},
{
"epoch": 1.35,
"learning_rate": 2e-05,
"loss": 0.1094,
"step": 100
},
{
"epoch": 1.36,
"learning_rate": 2e-05,
"loss": 0.1279,
"step": 101
},
{
"epoch": 1.37,
"learning_rate": 2e-05,
"loss": 0.1043,
"step": 102
},
{
"epoch": 1.39,
"learning_rate": 2e-05,
"loss": 0.1097,
"step": 103
},
{
"epoch": 1.4,
"learning_rate": 2e-05,
"loss": 0.1125,
"step": 104
},
{
"epoch": 1.41,
"learning_rate": 2e-05,
"loss": 0.118,
"step": 105
},
{
"epoch": 1.43,
"learning_rate": 2e-05,
"loss": 0.0962,
"step": 106
},
{
"epoch": 1.44,
"learning_rate": 2e-05,
"loss": 0.1093,
"step": 107
},
{
"epoch": 1.45,
"learning_rate": 2e-05,
"loss": 0.1219,
"step": 108
},
{
"epoch": 1.47,
"learning_rate": 2e-05,
"loss": 0.1046,
"step": 109
},
{
"epoch": 1.48,
"learning_rate": 2e-05,
"loss": 0.1017,
"step": 110
},
{
"epoch": 1.49,
"learning_rate": 2e-05,
"loss": 0.1044,
"step": 111
},
{
"epoch": 1.51,
"learning_rate": 2e-05,
"loss": 0.1084,
"step": 112
},
{
"epoch": 1.52,
"learning_rate": 2e-05,
"loss": 0.1158,
"step": 113
},
{
"epoch": 1.53,
"learning_rate": 2e-05,
"loss": 0.1074,
"step": 114
},
{
"epoch": 1.55,
"learning_rate": 2e-05,
"loss": 0.1075,
"step": 115
},
{
"epoch": 1.56,
"learning_rate": 2e-05,
"loss": 0.1052,
"step": 116
},
{
"epoch": 1.57,
"learning_rate": 2e-05,
"loss": 0.1017,
"step": 117
},
{
"epoch": 1.59,
"learning_rate": 2e-05,
"loss": 0.0992,
"step": 118
},
{
"epoch": 1.6,
"learning_rate": 2e-05,
"loss": 0.1096,
"step": 119
},
{
"epoch": 1.61,
"learning_rate": 2e-05,
"loss": 0.1272,
"step": 120
},
{
"epoch": 1.63,
"learning_rate": 2e-05,
"loss": 0.1049,
"step": 121
},
{
"epoch": 1.64,
"learning_rate": 2e-05,
"loss": 0.0998,
"step": 122
},
{
"epoch": 1.66,
"learning_rate": 2e-05,
"loss": 0.1052,
"step": 123
},
{
"epoch": 1.67,
"learning_rate": 2e-05,
"loss": 0.1177,
"step": 124
},
{
"epoch": 1.68,
"learning_rate": 2e-05,
"loss": 0.1052,
"step": 125
},
{
"epoch": 1.7,
"learning_rate": 2e-05,
"loss": 0.0997,
"step": 126
},
{
"epoch": 1.71,
"learning_rate": 2e-05,
"loss": 0.1115,
"step": 127
},
{
"epoch": 1.72,
"learning_rate": 2e-05,
"loss": 0.109,
"step": 128
},
{
"epoch": 1.74,
"learning_rate": 2e-05,
"loss": 0.1094,
"step": 129
},
{
"epoch": 1.75,
"learning_rate": 2e-05,
"loss": 0.0988,
"step": 130
},
{
"epoch": 1.76,
"learning_rate": 2e-05,
"loss": 0.1088,
"step": 131
},
{
"epoch": 1.78,
"learning_rate": 2e-05,
"loss": 0.0988,
"step": 132
},
{
"epoch": 1.79,
"learning_rate": 2e-05,
"loss": 0.0931,
"step": 133
},
{
"epoch": 1.8,
"learning_rate": 2e-05,
"loss": 0.0989,
"step": 134
},
{
"epoch": 1.82,
"learning_rate": 2e-05,
"loss": 0.1099,
"step": 135
},
{
"epoch": 1.83,
"learning_rate": 2e-05,
"loss": 0.107,
"step": 136
},
{
"epoch": 1.84,
"learning_rate": 2e-05,
"loss": 0.0991,
"step": 137
},
{
"epoch": 1.86,
"learning_rate": 2e-05,
"loss": 0.1045,
"step": 138
},
{
"epoch": 1.87,
"learning_rate": 2e-05,
"loss": 0.1112,
"step": 139
},
{
"epoch": 1.88,
"learning_rate": 2e-05,
"loss": 0.1128,
"step": 140
},
{
"epoch": 1.9,
"learning_rate": 2e-05,
"loss": 0.1106,
"step": 141
},
{
"epoch": 1.91,
"learning_rate": 2e-05,
"loss": 0.0934,
"step": 142
},
{
"epoch": 1.92,
"learning_rate": 2e-05,
"loss": 0.1105,
"step": 143
},
{
"epoch": 1.94,
"learning_rate": 2e-05,
"loss": 0.1024,
"step": 144
},
{
"epoch": 1.95,
"learning_rate": 2e-05,
"loss": 0.0985,
"step": 145
},
{
"epoch": 1.96,
"learning_rate": 2e-05,
"loss": 0.1051,
"step": 146
},
{
"epoch": 1.98,
"learning_rate": 2e-05,
"loss": 0.0955,
"step": 147
},
{
"epoch": 1.99,
"learning_rate": 2e-05,
"loss": 0.0915,
"step": 148
},
{
"epoch": 2.01,
"learning_rate": 2e-05,
"loss": 0.0985,
"step": 149
},
{
"epoch": 2.02,
"learning_rate": 2e-05,
"loss": 0.0678,
"step": 150
},
{
"epoch": 2.03,
"learning_rate": 2e-05,
"loss": 0.0667,
"step": 151
},
{
"epoch": 2.05,
"learning_rate": 2e-05,
"loss": 0.0706,
"step": 152
},
{
"epoch": 2.06,
"learning_rate": 2e-05,
"loss": 0.0689,
"step": 153
},
{
"epoch": 2.07,
"learning_rate": 2e-05,
"loss": 0.0661,
"step": 154
},
{
"epoch": 2.09,
"learning_rate": 2e-05,
"loss": 0.0705,
"step": 155
},
{
"epoch": 2.1,
"learning_rate": 2e-05,
"loss": 0.077,
"step": 156
},
{
"epoch": 2.11,
"learning_rate": 2e-05,
"loss": 0.0605,
"step": 157
},
{
"epoch": 2.13,
"learning_rate": 2e-05,
"loss": 0.0653,
"step": 158
},
{
"epoch": 2.14,
"learning_rate": 2e-05,
"loss": 0.07,
"step": 159
},
{
"epoch": 2.15,
"learning_rate": 2e-05,
"loss": 0.0694,
"step": 160
},
{
"epoch": 2.17,
"learning_rate": 2e-05,
"loss": 0.0655,
"step": 161
},
{
"epoch": 2.18,
"learning_rate": 2e-05,
"loss": 0.061,
"step": 162
},
{
"epoch": 2.19,
"learning_rate": 2e-05,
"loss": 0.0799,
"step": 163
},
{
"epoch": 2.21,
"learning_rate": 2e-05,
"loss": 0.0637,
"step": 164
},
{
"epoch": 2.22,
"learning_rate": 2e-05,
"loss": 0.0711,
"step": 165
},
{
"epoch": 2.23,
"learning_rate": 2e-05,
"loss": 0.0668,
"step": 166
},
{
"epoch": 2.25,
"learning_rate": 2e-05,
"loss": 0.0699,
"step": 167
},
{
"epoch": 2.26,
"learning_rate": 2e-05,
"loss": 0.0748,
"step": 168
},
{
"epoch": 2.27,
"learning_rate": 2e-05,
"loss": 0.0614,
"step": 169
},
{
"epoch": 2.29,
"learning_rate": 2e-05,
"loss": 0.0676,
"step": 170
},
{
"epoch": 2.3,
"learning_rate": 2e-05,
"loss": 0.0628,
"step": 171
},
{
"epoch": 2.31,
"learning_rate": 2e-05,
"loss": 0.0642,
"step": 172
},
{
"epoch": 2.33,
"learning_rate": 2e-05,
"loss": 0.0678,
"step": 173
},
{
"epoch": 2.34,
"learning_rate": 2e-05,
"loss": 0.0629,
"step": 174
},
{
"epoch": 2.35,
"learning_rate": 2e-05,
"loss": 0.0645,
"step": 175
},
{
"epoch": 2.37,
"learning_rate": 2e-05,
"loss": 0.0612,
"step": 176
},
{
"epoch": 2.38,
"learning_rate": 2e-05,
"loss": 0.0575,
"step": 177
},
{
"epoch": 2.4,
"learning_rate": 2e-05,
"loss": 0.0651,
"step": 178
},
{
"epoch": 2.41,
"learning_rate": 2e-05,
"loss": 0.0679,
"step": 179
},
{
"epoch": 2.42,
"learning_rate": 2e-05,
"loss": 0.0648,
"step": 180
},
{
"epoch": 2.44,
"learning_rate": 2e-05,
"loss": 0.0685,
"step": 181
},
{
"epoch": 2.45,
"learning_rate": 2e-05,
"loss": 0.0646,
"step": 182
},
{
"epoch": 2.46,
"learning_rate": 2e-05,
"loss": 0.0688,
"step": 183
},
{
"epoch": 2.48,
"learning_rate": 2e-05,
"loss": 0.068,
"step": 184
},
{
"epoch": 2.49,
"learning_rate": 2e-05,
"loss": 0.067,
"step": 185
},
{
"epoch": 2.5,
"learning_rate": 2e-05,
"loss": 0.0683,
"step": 186
},
{
"epoch": 2.52,
"learning_rate": 2e-05,
"loss": 0.0668,
"step": 187
},
{
"epoch": 2.53,
"learning_rate": 2e-05,
"loss": 0.0663,
"step": 188
},
{
"epoch": 2.54,
"learning_rate": 2e-05,
"loss": 0.0636,
"step": 189
},
{
"epoch": 2.56,
"learning_rate": 2e-05,
"loss": 0.0667,
"step": 190
},
{
"epoch": 2.57,
"learning_rate": 2e-05,
"loss": 0.0688,
"step": 191
},
{
"epoch": 2.58,
"learning_rate": 2e-05,
"loss": 0.0708,
"step": 192
},
{
"epoch": 2.6,
"learning_rate": 2e-05,
"loss": 0.0666,
"step": 193
},
{
"epoch": 2.61,
"learning_rate": 2e-05,
"loss": 0.0679,
"step": 194
},
{
"epoch": 2.62,
"learning_rate": 2e-05,
"loss": 0.0675,
"step": 195
},
{
"epoch": 2.64,
"learning_rate": 2e-05,
"loss": 0.0688,
"step": 196
},
{
"epoch": 2.65,
"learning_rate": 2e-05,
"loss": 0.068,
"step": 197
},
{
"epoch": 2.66,
"learning_rate": 2e-05,
"loss": 0.0665,
"step": 198
},
{
"epoch": 2.68,
"learning_rate": 2e-05,
"loss": 0.0678,
"step": 199
},
{
"epoch": 2.69,
"learning_rate": 2e-05,
"loss": 0.0674,
"step": 200
},
{
"epoch": 2.7,
"learning_rate": 2e-05,
"loss": 0.0627,
"step": 201
},
{
"epoch": 2.72,
"learning_rate": 2e-05,
"loss": 0.0676,
"step": 202
},
{
"epoch": 2.73,
"learning_rate": 2e-05,
"loss": 0.0605,
"step": 203
},
{
"epoch": 2.75,
"learning_rate": 2e-05,
"loss": 0.0656,
"step": 204
},
{
"epoch": 2.76,
"learning_rate": 2e-05,
"loss": 0.072,
"step": 205
},
{
"epoch": 2.77,
"learning_rate": 2e-05,
"loss": 0.0635,
"step": 206
},
{
"epoch": 2.79,
"learning_rate": 2e-05,
"loss": 0.0624,
"step": 207
},
{
"epoch": 2.8,
"learning_rate": 2e-05,
"loss": 0.0628,
"step": 208
},
{
"epoch": 2.81,
"learning_rate": 2e-05,
"loss": 0.0704,
"step": 209
},
{
"epoch": 2.83,
"learning_rate": 2e-05,
"loss": 0.0647,
"step": 210
},
{
"epoch": 2.84,
"learning_rate": 2e-05,
"loss": 0.0611,
"step": 211
},
{
"epoch": 2.85,
"learning_rate": 2e-05,
"loss": 0.0686,
"step": 212
},
{
"epoch": 2.87,
"learning_rate": 2e-05,
"loss": 0.0686,
"step": 213
},
{
"epoch": 2.88,
"learning_rate": 2e-05,
"loss": 0.0723,
"step": 214
},
{
"epoch": 2.89,
"learning_rate": 2e-05,
"loss": 0.0644,
"step": 215
},
{
"epoch": 2.91,
"learning_rate": 2e-05,
"loss": 0.0702,
"step": 216
},
{
"epoch": 2.92,
"learning_rate": 2e-05,
"loss": 0.0624,
"step": 217
},
{
"epoch": 2.93,
"learning_rate": 2e-05,
"loss": 0.0664,
"step": 218
},
{
"epoch": 2.95,
"learning_rate": 2e-05,
"loss": 0.0592,
"step": 219
},
{
"epoch": 2.96,
"learning_rate": 2e-05,
"loss": 0.0565,
"step": 220
},
{
"epoch": 2.97,
"learning_rate": 2e-05,
"loss": 0.0679,
"step": 221
},
{
"epoch": 2.99,
"learning_rate": 2e-05,
"loss": 0.0617,
"step": 222
}
],
"max_steps": 222,
"num_train_epochs": 3,
"total_flos": 31856813015040.0,
"trial_name": null,
"trial_params": null
}