mistralic-expert-31 / checkpoint-200 /trainer_state.json
pharaouk's picture
Training in progress, step 200, checkpoint
90d3092
raw
history blame
25.3 kB
{
"best_metric": 0.9499853253364563,
"best_model_checkpoint": "experts/mistralic-expert-31/checkpoint-200",
"epoch": 0.061709348966368406,
"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": 0.997,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.0488,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.9417,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.0655,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.9966,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.1248,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.0554,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.1163,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.9191,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.1657,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.9985,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.0346,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.8882,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.0175,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.877,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 0.8384,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0233,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0147,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.1521,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9418,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.1608,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9631,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0209,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0619,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.2694,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9997,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9234,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9679,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9442,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9708,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0319,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0278,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0284,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.8464,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9889,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.3341,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0814,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.9036,
"step": 38
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.1541,
"step": 39
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.1549,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0072,
"step": 41
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0638,
"step": 42
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0451,
"step": 43
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.1216,
"step": 44
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0063,
"step": 45
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.8003,
"step": 46
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 1.0479,
"step": 47
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.7849,
"step": 48
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.0547,
"step": 49
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9508,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.033,
"step": 51
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.7773,
"step": 52
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.887,
"step": 53
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.8354,
"step": 54
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9288,
"step": 55
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.1684,
"step": 56
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.0553,
"step": 57
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.8693,
"step": 58
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.8337,
"step": 59
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9965,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9892,
"step": 61
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9308,
"step": 62
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.7772,
"step": 63
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.0411,
"step": 64
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.7696,
"step": 65
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.7961,
"step": 66
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.8911,
"step": 67
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.0532,
"step": 68
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.0721,
"step": 69
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.7499,
"step": 70
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9293,
"step": 71
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.8478,
"step": 72
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.02,
"step": 73
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.2677,
"step": 74
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9836,
"step": 75
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.1115,
"step": 76
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.1138,
"step": 77
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.8705,
"step": 78
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 0.9836,
"step": 79
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.068,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 0.0002,
"loss": 1.043,
"step": 81
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.0843,
"step": 82
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.974,
"step": 83
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9724,
"step": 84
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.8375,
"step": 85
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.1525,
"step": 86
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9822,
"step": 87
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.0685,
"step": 88
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.2392,
"step": 89
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9015,
"step": 90
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.8264,
"step": 91
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.1202,
"step": 92
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.0901,
"step": 93
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.1147,
"step": 94
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.858,
"step": 95
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.1012,
"step": 96
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9222,
"step": 97
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.0704,
"step": 98
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.1067,
"step": 99
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.8698,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.2041,
"step": 101
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.8054,
"step": 102
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.0614,
"step": 103
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9635,
"step": 104
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.0252,
"step": 105
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.962,
"step": 106
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9954,
"step": 107
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9895,
"step": 108
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9363,
"step": 109
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9849,
"step": 110
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.0117,
"step": 111
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 1.0286,
"step": 112
},
{
"epoch": 0.03,
"learning_rate": 0.0002,
"loss": 0.9685,
"step": 113
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9529,
"step": 114
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0492,
"step": 115
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.7994,
"step": 116
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.757,
"step": 117
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9638,
"step": 118
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0389,
"step": 119
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9388,
"step": 120
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9704,
"step": 121
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.8574,
"step": 122
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.1912,
"step": 123
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0663,
"step": 124
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0062,
"step": 125
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0792,
"step": 126
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.8519,
"step": 127
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.913,
"step": 128
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0731,
"step": 129
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0924,
"step": 130
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9461,
"step": 131
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0235,
"step": 132
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.8753,
"step": 133
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9494,
"step": 134
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0812,
"step": 135
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9319,
"step": 136
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9457,
"step": 137
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9424,
"step": 138
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0331,
"step": 139
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.0472,
"step": 140
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.998,
"step": 141
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9577,
"step": 142
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.1829,
"step": 143
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 1.049,
"step": 144
},
{
"epoch": 0.04,
"learning_rate": 0.0002,
"loss": 0.9152,
"step": 145
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0662,
"step": 146
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9938,
"step": 147
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9318,
"step": 148
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.3438,
"step": 149
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9698,
"step": 150
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9604,
"step": 151
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8512,
"step": 152
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8416,
"step": 153
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0059,
"step": 154
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.883,
"step": 155
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.2187,
"step": 156
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8645,
"step": 157
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0157,
"step": 158
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0114,
"step": 159
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9243,
"step": 160
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9201,
"step": 161
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.1389,
"step": 162
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9449,
"step": 163
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0677,
"step": 164
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0569,
"step": 165
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9678,
"step": 166
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0145,
"step": 167
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0152,
"step": 168
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.016,
"step": 169
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8583,
"step": 170
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.073,
"step": 171
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8966,
"step": 172
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8771,
"step": 173
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.075,
"step": 174
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.9856,
"step": 175
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8457,
"step": 176
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 1.0132,
"step": 177
},
{
"epoch": 0.05,
"learning_rate": 0.0002,
"loss": 0.8739,
"step": 178
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.965,
"step": 179
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.9579,
"step": 180
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0677,
"step": 181
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0182,
"step": 182
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.7834,
"step": 183
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.1045,
"step": 184
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.8176,
"step": 185
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.7513,
"step": 186
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.7464,
"step": 187
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0779,
"step": 188
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.9206,
"step": 189
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.8617,
"step": 190
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0357,
"step": 191
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0274,
"step": 192
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.9239,
"step": 193
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0465,
"step": 194
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.9282,
"step": 195
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0537,
"step": 196
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.1715,
"step": 197
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.9823,
"step": 198
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 1.0934,
"step": 199
},
{
"epoch": 0.06,
"learning_rate": 0.0002,
"loss": 0.8832,
"step": 200
},
{
"epoch": 0.06,
"eval_loss": 0.9499853253364563,
"eval_runtime": 90.0334,
"eval_samples_per_second": 11.107,
"eval_steps_per_second": 5.553,
"step": 200
},
{
"epoch": 0.06,
"mmlu_eval_accuracy": 0.583239780938983,
"mmlu_eval_accuracy_abstract_algebra": 0.18181818181818182,
"mmlu_eval_accuracy_anatomy": 0.5,
"mmlu_eval_accuracy_astronomy": 0.6875,
"mmlu_eval_accuracy_business_ethics": 0.6363636363636364,
"mmlu_eval_accuracy_clinical_knowledge": 0.5517241379310345,
"mmlu_eval_accuracy_college_biology": 0.625,
"mmlu_eval_accuracy_college_chemistry": 0.25,
"mmlu_eval_accuracy_college_computer_science": 0.45454545454545453,
"mmlu_eval_accuracy_college_mathematics": 0.6363636363636364,
"mmlu_eval_accuracy_college_medicine": 0.5909090909090909,
"mmlu_eval_accuracy_college_physics": 0.36363636363636365,
"mmlu_eval_accuracy_computer_security": 0.5454545454545454,
"mmlu_eval_accuracy_conceptual_physics": 0.5384615384615384,
"mmlu_eval_accuracy_econometrics": 0.5,
"mmlu_eval_accuracy_electrical_engineering": 0.625,
"mmlu_eval_accuracy_elementary_mathematics": 0.43902439024390244,
"mmlu_eval_accuracy_formal_logic": 0.21428571428571427,
"mmlu_eval_accuracy_global_facts": 0.4,
"mmlu_eval_accuracy_high_school_biology": 0.53125,
"mmlu_eval_accuracy_high_school_chemistry": 0.36363636363636365,
"mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
"mmlu_eval_accuracy_high_school_european_history": 0.7777777777777778,
"mmlu_eval_accuracy_high_school_geography": 0.7727272727272727,
"mmlu_eval_accuracy_high_school_government_and_politics": 0.7142857142857143,
"mmlu_eval_accuracy_high_school_macroeconomics": 0.5813953488372093,
"mmlu_eval_accuracy_high_school_mathematics": 0.3448275862068966,
"mmlu_eval_accuracy_high_school_microeconomics": 0.5769230769230769,
"mmlu_eval_accuracy_high_school_physics": 0.11764705882352941,
"mmlu_eval_accuracy_high_school_psychology": 0.85,
"mmlu_eval_accuracy_high_school_statistics": 0.34782608695652173,
"mmlu_eval_accuracy_high_school_us_history": 0.7272727272727273,
"mmlu_eval_accuracy_high_school_world_history": 0.6538461538461539,
"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": 0.45454545454545453,
"mmlu_eval_accuracy_logical_fallacies": 0.6111111111111112,
"mmlu_eval_accuracy_machine_learning": 0.45454545454545453,
"mmlu_eval_accuracy_management": 0.9090909090909091,
"mmlu_eval_accuracy_marketing": 0.92,
"mmlu_eval_accuracy_medical_genetics": 0.9090909090909091,
"mmlu_eval_accuracy_miscellaneous": 0.7674418604651163,
"mmlu_eval_accuracy_moral_disputes": 0.5526315789473685,
"mmlu_eval_accuracy_moral_scenarios": 0.28,
"mmlu_eval_accuracy_nutrition": 0.6666666666666666,
"mmlu_eval_accuracy_philosophy": 0.7647058823529411,
"mmlu_eval_accuracy_prehistory": 0.45714285714285713,
"mmlu_eval_accuracy_professional_accounting": 0.5806451612903226,
"mmlu_eval_accuracy_professional_law": 0.3941176470588235,
"mmlu_eval_accuracy_professional_medicine": 0.6129032258064516,
"mmlu_eval_accuracy_professional_psychology": 0.6521739130434783,
"mmlu_eval_accuracy_public_relations": 0.5,
"mmlu_eval_accuracy_security_studies": 0.6666666666666666,
"mmlu_eval_accuracy_sociology": 0.8636363636363636,
"mmlu_eval_accuracy_us_foreign_policy": 0.8181818181818182,
"mmlu_eval_accuracy_virology": 0.5555555555555556,
"mmlu_eval_accuracy_world_religions": 0.8421052631578947,
"mmlu_loss": 1.5736223915227088,
"step": 200
}
],
"logging_steps": 1,
"max_steps": 9723,
"num_train_epochs": 3,
"save_steps": 200,
"total_flos": 2.219788751162573e+16,
"trial_name": null,
"trial_params": null
}