mistralic-expert-23 / checkpoint-200 /trainer_state.json
pharaouk's picture
Training in progress, step 200, checkpoint
6f9ee79
raw
history blame
25.3 kB
{
"best_metric": 0.600193977355957,
"best_model_checkpoint": "experts/mistralic-expert-23/checkpoint-200",
"epoch": 0.046734431592475756,
"eval_steps": 200,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.6926,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.6169,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.539,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.5802,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.5176,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.6371,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.5969,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.6545,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.7967,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.5244,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.9098,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.7216,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.5279,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.784,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.9971,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.5255,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.6404,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.8234,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.529,
"step": 19
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.5078,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.4981,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.8841,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5563,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5759,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5739,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5891,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.454,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5685,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5723,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.516,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.7419,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.7529,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.6331,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.7149,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.7413,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5488,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.8207,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5589,
"step": 38
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5907,
"step": 39
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.6014,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5317,
"step": 41
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5762,
"step": 42
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5986,
"step": 43
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5758,
"step": 44
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.7376,
"step": 45
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.6161,
"step": 46
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5554,
"step": 47
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5997,
"step": 48
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5616,
"step": 49
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5376,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.6303,
"step": 51
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5722,
"step": 52
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5588,
"step": 53
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5734,
"step": 54
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5353,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5713,
"step": 56
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.6006,
"step": 57
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.7782,
"step": 58
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5286,
"step": 59
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.6655,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.6916,
"step": 61
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.8167,
"step": 62
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5933,
"step": 63
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.5054,
"step": 64
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5764,
"step": 65
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.4551,
"step": 66
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6122,
"step": 67
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6257,
"step": 68
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6027,
"step": 69
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5796,
"step": 70
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6817,
"step": 71
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5495,
"step": 72
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5997,
"step": 73
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.837,
"step": 74
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5642,
"step": 75
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5644,
"step": 76
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5589,
"step": 77
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6021,
"step": 78
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6688,
"step": 79
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5716,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.75,
"step": 81
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6068,
"step": 82
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5987,
"step": 83
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.7231,
"step": 84
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5786,
"step": 85
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6502,
"step": 86
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6702,
"step": 87
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6432,
"step": 88
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5064,
"step": 89
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5188,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9853,
"step": 91
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5188,
"step": 92
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.8395,
"step": 93
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5267,
"step": 94
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5357,
"step": 95
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5574,
"step": 96
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5883,
"step": 97
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6675,
"step": 98
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5527,
"step": 99
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6302,
"step": 100
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.8618,
"step": 101
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6703,
"step": 102
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.5242,
"step": 103
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.653,
"step": 104
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.6386,
"step": 105
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.7444,
"step": 106
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5107,
"step": 107
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6885,
"step": 108
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5642,
"step": 109
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6477,
"step": 110
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6824,
"step": 111
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5575,
"step": 112
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5927,
"step": 113
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5312,
"step": 114
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.63,
"step": 115
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.4778,
"step": 116
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5675,
"step": 117
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.4322,
"step": 118
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5693,
"step": 119
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6603,
"step": 120
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.4729,
"step": 121
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.8347,
"step": 122
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6119,
"step": 123
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.7242,
"step": 124
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5018,
"step": 125
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.7959,
"step": 126
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.606,
"step": 127
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5727,
"step": 128
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6316,
"step": 129
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6095,
"step": 130
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5735,
"step": 131
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.4528,
"step": 132
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5352,
"step": 133
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6042,
"step": 134
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.76,
"step": 135
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.4522,
"step": 136
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5826,
"step": 137
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5408,
"step": 138
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5659,
"step": 139
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.551,
"step": 140
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5766,
"step": 141
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5377,
"step": 142
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.8203,
"step": 143
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5066,
"step": 144
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5001,
"step": 145
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.5727,
"step": 146
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6109,
"step": 147
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6467,
"step": 148
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.6917,
"step": 149
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6373,
"step": 150
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6928,
"step": 151
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5866,
"step": 152
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.659,
"step": 153
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5483,
"step": 154
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5335,
"step": 155
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.7856,
"step": 156
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5694,
"step": 157
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.8404,
"step": 158
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.575,
"step": 159
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6436,
"step": 160
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.4149,
"step": 161
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6085,
"step": 162
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5949,
"step": 163
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6294,
"step": 164
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5303,
"step": 165
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.7256,
"step": 166
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6095,
"step": 167
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.7129,
"step": 168
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6088,
"step": 169
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.4735,
"step": 170
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.4963,
"step": 171
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.8293,
"step": 172
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6143,
"step": 173
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5835,
"step": 174
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.7986,
"step": 175
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6569,
"step": 176
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6295,
"step": 177
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.4927,
"step": 178
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5401,
"step": 179
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6203,
"step": 180
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5045,
"step": 181
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5779,
"step": 182
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5386,
"step": 183
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.4483,
"step": 184
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5543,
"step": 185
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0266,
"step": 186
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5621,
"step": 187
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5884,
"step": 188
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5395,
"step": 189
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6764,
"step": 190
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.5938,
"step": 191
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.6306,
"step": 192
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8946,
"step": 193
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.6613,
"step": 194
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.4926,
"step": 195
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.4874,
"step": 196
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.6966,
"step": 197
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.7493,
"step": 198
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.62,
"step": 199
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8005,
"step": 200
},
{
"epoch": 0.05,
"eval_loss": 0.600193977355957,
"eval_runtime": 156.5363,
"eval_samples_per_second": 6.388,
"eval_steps_per_second": 3.194,
"step": 200
},
{
"epoch": 0.05,
"mmlu_eval_accuracy": 0.6110525160674652,
"mmlu_eval_accuracy_abstract_algebra": 0.2727272727272727,
"mmlu_eval_accuracy_anatomy": 0.5714285714285714,
"mmlu_eval_accuracy_astronomy": 0.75,
"mmlu_eval_accuracy_business_ethics": 0.6363636363636364,
"mmlu_eval_accuracy_clinical_knowledge": 0.5862068965517241,
"mmlu_eval_accuracy_college_biology": 0.625,
"mmlu_eval_accuracy_college_chemistry": 0.375,
"mmlu_eval_accuracy_college_computer_science": 0.45454545454545453,
"mmlu_eval_accuracy_college_mathematics": 0.45454545454545453,
"mmlu_eval_accuracy_college_medicine": 0.6818181818181818,
"mmlu_eval_accuracy_college_physics": 0.5454545454545454,
"mmlu_eval_accuracy_computer_security": 0.6363636363636364,
"mmlu_eval_accuracy_conceptual_physics": 0.5,
"mmlu_eval_accuracy_econometrics": 0.5,
"mmlu_eval_accuracy_electrical_engineering": 0.625,
"mmlu_eval_accuracy_elementary_mathematics": 0.3902439024390244,
"mmlu_eval_accuracy_formal_logic": 0.21428571428571427,
"mmlu_eval_accuracy_global_facts": 0.3,
"mmlu_eval_accuracy_high_school_biology": 0.625,
"mmlu_eval_accuracy_high_school_chemistry": 0.4090909090909091,
"mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
"mmlu_eval_accuracy_high_school_european_history": 0.8333333333333334,
"mmlu_eval_accuracy_high_school_geography": 0.8181818181818182,
"mmlu_eval_accuracy_high_school_government_and_politics": 0.7619047619047619,
"mmlu_eval_accuracy_high_school_macroeconomics": 0.6046511627906976,
"mmlu_eval_accuracy_high_school_mathematics": 0.3103448275862069,
"mmlu_eval_accuracy_high_school_microeconomics": 0.6538461538461539,
"mmlu_eval_accuracy_high_school_physics": 0.23529411764705882,
"mmlu_eval_accuracy_high_school_psychology": 0.8666666666666667,
"mmlu_eval_accuracy_high_school_statistics": 0.43478260869565216,
"mmlu_eval_accuracy_high_school_us_history": 0.7727272727272727,
"mmlu_eval_accuracy_high_school_world_history": 0.6153846153846154,
"mmlu_eval_accuracy_human_aging": 0.7391304347826086,
"mmlu_eval_accuracy_human_sexuality": 0.5833333333333334,
"mmlu_eval_accuracy_international_law": 0.9230769230769231,
"mmlu_eval_accuracy_jurisprudence": 0.6363636363636364,
"mmlu_eval_accuracy_logical_fallacies": 0.6111111111111112,
"mmlu_eval_accuracy_machine_learning": 0.5454545454545454,
"mmlu_eval_accuracy_management": 0.9090909090909091,
"mmlu_eval_accuracy_marketing": 0.92,
"mmlu_eval_accuracy_medical_genetics": 0.9090909090909091,
"mmlu_eval_accuracy_miscellaneous": 0.7325581395348837,
"mmlu_eval_accuracy_moral_disputes": 0.5263157894736842,
"mmlu_eval_accuracy_moral_scenarios": 0.37,
"mmlu_eval_accuracy_nutrition": 0.7272727272727273,
"mmlu_eval_accuracy_philosophy": 0.7352941176470589,
"mmlu_eval_accuracy_prehistory": 0.6,
"mmlu_eval_accuracy_professional_accounting": 0.5161290322580645,
"mmlu_eval_accuracy_professional_law": 0.4,
"mmlu_eval_accuracy_professional_medicine": 0.6774193548387096,
"mmlu_eval_accuracy_professional_psychology": 0.6231884057971014,
"mmlu_eval_accuracy_public_relations": 0.5,
"mmlu_eval_accuracy_security_studies": 0.7407407407407407,
"mmlu_eval_accuracy_sociology": 0.9090909090909091,
"mmlu_eval_accuracy_us_foreign_policy": 0.8181818181818182,
"mmlu_eval_accuracy_virology": 0.5555555555555556,
"mmlu_eval_accuracy_world_religions": 0.8947368421052632,
"mmlu_loss": 1.4672958862532524,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 12837,
"num_train_epochs": 3,
"save_steps": 200,
"total_flos": 4.930732762909901e+16,
"trial_name": null,
"trial_params": null
}