pharaouk's picture
a
0af3fe6
{
"best_metric": 0.36855557560920715,
"best_model_checkpoint": "./output_v2/34bCodellama_CodeLlama-34b-Python-hf_unnatural-instructions_standardized/checkpoint-400",
"epoch": 0.024444274692536856,
"global_step": 400,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1006,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 1.2792,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.3465,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4367,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1706,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.632,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1233,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4661,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1672,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.0641,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.3908,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.505,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.7672,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2875,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4619,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4586,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.7159,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.207,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4808,
"step": 19
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.104,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.5561,
"step": 21
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4114,
"step": 22
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.3656,
"step": 23
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6222,
"step": 24
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.502,
"step": 25
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.3339,
"step": 26
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6282,
"step": 27
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.104,
"step": 28
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.7241,
"step": 29
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.7388,
"step": 30
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1877,
"step": 31
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.5733,
"step": 32
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6204,
"step": 33
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.9779,
"step": 34
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 1.0215,
"step": 35
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2895,
"step": 36
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.3081,
"step": 37
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6799,
"step": 38
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6704,
"step": 39
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6087,
"step": 40
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.8191,
"step": 41
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.307,
"step": 42
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.431,
"step": 43
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2427,
"step": 44
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.8054,
"step": 45
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 1.0238,
"step": 46
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4241,
"step": 47
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1145,
"step": 48
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 1.069,
"step": 49
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 1.0728,
"step": 50
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.108,
"step": 51
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2927,
"step": 52
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2443,
"step": 53
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.0006,
"step": 54
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2178,
"step": 55
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2221,
"step": 56
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.0375,
"step": 57
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1756,
"step": 58
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4141,
"step": 59
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.154,
"step": 60
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1159,
"step": 61
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2163,
"step": 62
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.3193,
"step": 63
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.3983,
"step": 64
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.7675,
"step": 65
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.395,
"step": 66
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.4137,
"step": 67
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1585,
"step": 68
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.0744,
"step": 69
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2868,
"step": 70
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6288,
"step": 71
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2539,
"step": 72
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.9,
"step": 73
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.5689,
"step": 74
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1503,
"step": 75
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6418,
"step": 76
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.2353,
"step": 77
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.8223,
"step": 78
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1297,
"step": 79
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.6385,
"step": 80
},
{
"epoch": 0.0,
"learning_rate": 0.0004,
"loss": 0.1623,
"step": 81
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3846,
"step": 82
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3152,
"step": 83
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1425,
"step": 84
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.6978,
"step": 85
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 1.0012,
"step": 86
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1544,
"step": 87
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7167,
"step": 88
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5173,
"step": 89
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4471,
"step": 90
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4159,
"step": 91
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.697,
"step": 92
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2301,
"step": 93
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.9655,
"step": 94
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2113,
"step": 95
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 1.5099,
"step": 96
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.6587,
"step": 97
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.677,
"step": 98
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.8563,
"step": 99
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 1.6579,
"step": 100
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2976,
"step": 101
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4181,
"step": 102
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3141,
"step": 103
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1189,
"step": 104
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0589,
"step": 105
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.533,
"step": 106
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4562,
"step": 107
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2835,
"step": 108
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5246,
"step": 109
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2345,
"step": 110
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1858,
"step": 111
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5243,
"step": 112
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3014,
"step": 113
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0783,
"step": 114
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1369,
"step": 115
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1517,
"step": 116
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4089,
"step": 117
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.184,
"step": 118
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.218,
"step": 119
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2696,
"step": 120
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0955,
"step": 121
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3469,
"step": 122
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2769,
"step": 123
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2437,
"step": 124
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2283,
"step": 125
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5484,
"step": 126
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3495,
"step": 127
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7042,
"step": 128
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3839,
"step": 129
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3892,
"step": 130
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2422,
"step": 131
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3934,
"step": 132
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4136,
"step": 133
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0939,
"step": 134
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.508,
"step": 135
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3331,
"step": 136
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.377,
"step": 137
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.8366,
"step": 138
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2068,
"step": 139
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.484,
"step": 140
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.8796,
"step": 141
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4984,
"step": 142
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5241,
"step": 143
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4839,
"step": 144
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2773,
"step": 145
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5004,
"step": 146
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3029,
"step": 147
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.9682,
"step": 148
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3496,
"step": 149
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.462,
"step": 150
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1464,
"step": 151
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1177,
"step": 152
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3903,
"step": 153
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2373,
"step": 154
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1732,
"step": 155
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5158,
"step": 156
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3224,
"step": 157
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2082,
"step": 158
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2307,
"step": 159
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1758,
"step": 160
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2339,
"step": 161
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0613,
"step": 162
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1142,
"step": 163
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3177,
"step": 164
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4358,
"step": 165
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 1.3582,
"step": 166
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5703,
"step": 167
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3477,
"step": 168
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4394,
"step": 169
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3481,
"step": 170
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1735,
"step": 171
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0878,
"step": 172
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0659,
"step": 173
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3527,
"step": 174
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1819,
"step": 175
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.379,
"step": 176
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2146,
"step": 177
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.133,
"step": 178
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5217,
"step": 179
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3077,
"step": 180
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0022,
"step": 181
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1031,
"step": 182
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.681,
"step": 183
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7839,
"step": 184
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.6465,
"step": 185
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2607,
"step": 186
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7913,
"step": 187
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4266,
"step": 188
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2851,
"step": 189
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.6628,
"step": 190
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.8151,
"step": 191
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3577,
"step": 192
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4329,
"step": 193
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1639,
"step": 194
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1394,
"step": 195
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3146,
"step": 196
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2623,
"step": 197
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 1.3405,
"step": 198
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.6208,
"step": 199
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7118,
"step": 200
},
{
"epoch": 0.01,
"eval_loss": 0.3938411474227905,
"eval_runtime": 219.0899,
"eval_samples_per_second": 2.282,
"eval_steps_per_second": 1.141,
"step": 200
},
{
"epoch": 0.01,
"mmlu_eval_accuracy": 0.3485764968358423,
"mmlu_eval_accuracy_abstract_algebra": 0.36363636363636365,
"mmlu_eval_accuracy_anatomy": 0.35714285714285715,
"mmlu_eval_accuracy_astronomy": 0.5,
"mmlu_eval_accuracy_business_ethics": 0.2727272727272727,
"mmlu_eval_accuracy_clinical_knowledge": 0.41379310344827586,
"mmlu_eval_accuracy_college_biology": 0.4375,
"mmlu_eval_accuracy_college_chemistry": 0.25,
"mmlu_eval_accuracy_college_computer_science": 0.36363636363636365,
"mmlu_eval_accuracy_college_mathematics": 0.36363636363636365,
"mmlu_eval_accuracy_college_medicine": 0.4090909090909091,
"mmlu_eval_accuracy_college_physics": 0.2727272727272727,
"mmlu_eval_accuracy_computer_security": 0.45454545454545453,
"mmlu_eval_accuracy_conceptual_physics": 0.34615384615384615,
"mmlu_eval_accuracy_econometrics": 0.25,
"mmlu_eval_accuracy_electrical_engineering": 0.25,
"mmlu_eval_accuracy_elementary_mathematics": 0.34146341463414637,
"mmlu_eval_accuracy_formal_logic": 0.21428571428571427,
"mmlu_eval_accuracy_global_facts": 0.0,
"mmlu_eval_accuracy_high_school_biology": 0.3125,
"mmlu_eval_accuracy_high_school_chemistry": 0.18181818181818182,
"mmlu_eval_accuracy_high_school_computer_science": 0.5555555555555556,
"mmlu_eval_accuracy_high_school_european_history": 0.5555555555555556,
"mmlu_eval_accuracy_high_school_geography": 0.7272727272727273,
"mmlu_eval_accuracy_high_school_government_and_politics": 0.2857142857142857,
"mmlu_eval_accuracy_high_school_macroeconomics": 0.5116279069767442,
"mmlu_eval_accuracy_high_school_mathematics": 0.20689655172413793,
"mmlu_eval_accuracy_high_school_microeconomics": 0.21428571428571427,
"mmlu_loss": 0.783768397025764,
"step": 200
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.9429,
"step": 201
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1329,
"step": 202
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1037,
"step": 203
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1569,
"step": 204
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1435,
"step": 205
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1809,
"step": 206
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3113,
"step": 207
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5093,
"step": 208
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3999,
"step": 209
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2678,
"step": 210
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3196,
"step": 211
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.6502,
"step": 212
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2296,
"step": 213
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5807,
"step": 214
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1532,
"step": 215
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4757,
"step": 216
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.228,
"step": 217
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.9191,
"step": 218
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1239,
"step": 219
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.6583,
"step": 220
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1169,
"step": 221
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4391,
"step": 222
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.2499,
"step": 223
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3765,
"step": 224
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3311,
"step": 225
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.4432,
"step": 226
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.273,
"step": 227
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0578,
"step": 228
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7053,
"step": 229
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.724,
"step": 230
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.0928,
"step": 231
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.903,
"step": 232
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7901,
"step": 233
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7745,
"step": 234
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3911,
"step": 235
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.1124,
"step": 236
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.6872,
"step": 237
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3603,
"step": 238
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7547,
"step": 239
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5801,
"step": 240
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.565,
"step": 241
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.5144,
"step": 242
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7707,
"step": 243
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.3473,
"step": 244
},
{
"epoch": 0.01,
"learning_rate": 0.0004,
"loss": 0.7117,
"step": 245
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.2869,
"step": 246
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.835,
"step": 247
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.023,
"step": 248
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3017,
"step": 249
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.5144,
"step": 250
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2024,
"step": 251
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1079,
"step": 252
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2874,
"step": 253
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0762,
"step": 254
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0513,
"step": 255
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.6924,
"step": 256
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3838,
"step": 257
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2467,
"step": 258
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3778,
"step": 259
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1238,
"step": 260
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.336,
"step": 261
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.1311,
"step": 262
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3756,
"step": 263
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2104,
"step": 264
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2373,
"step": 265
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3603,
"step": 266
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1986,
"step": 267
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1257,
"step": 268
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.7065,
"step": 269
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.148,
"step": 270
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0937,
"step": 271
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4194,
"step": 272
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5164,
"step": 273
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1585,
"step": 274
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4005,
"step": 275
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2115,
"step": 276
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0974,
"step": 277
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2902,
"step": 278
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5665,
"step": 279
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4776,
"step": 280
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4144,
"step": 281
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2455,
"step": 282
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1699,
"step": 283
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1421,
"step": 284
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1625,
"step": 285
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1451,
"step": 286
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2915,
"step": 287
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5279,
"step": 288
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3336,
"step": 289
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2865,
"step": 290
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3335,
"step": 291
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5623,
"step": 292
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4999,
"step": 293
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3863,
"step": 294
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.8553,
"step": 295
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5907,
"step": 296
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.411,
"step": 297
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.8062,
"step": 298
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.6118,
"step": 299
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.9868,
"step": 300
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.4436,
"step": 301
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0785,
"step": 302
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0027,
"step": 303
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0584,
"step": 304
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4422,
"step": 305
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4163,
"step": 306
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0861,
"step": 307
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1849,
"step": 308
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2862,
"step": 309
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1654,
"step": 310
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0498,
"step": 311
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2044,
"step": 312
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1615,
"step": 313
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3443,
"step": 314
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1133,
"step": 315
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.9935,
"step": 316
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0738,
"step": 317
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.7676,
"step": 318
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5102,
"step": 319
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3776,
"step": 320
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.6596,
"step": 321
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3674,
"step": 322
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2252,
"step": 323
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2687,
"step": 324
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4756,
"step": 325
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1923,
"step": 326
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4282,
"step": 327
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0104,
"step": 328
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1326,
"step": 329
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.9252,
"step": 330
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5622,
"step": 331
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.6532,
"step": 332
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1987,
"step": 333
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3073,
"step": 334
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.7015,
"step": 335
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4761,
"step": 336
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4269,
"step": 337
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.988,
"step": 338
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3558,
"step": 339
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1494,
"step": 340
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.1602,
"step": 341
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.8131,
"step": 342
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1298,
"step": 343
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3267,
"step": 344
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.9548,
"step": 345
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.62,
"step": 346
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.9897,
"step": 347
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.546,
"step": 348
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.8286,
"step": 349
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.0614,
"step": 350
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0516,
"step": 351
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4044,
"step": 352
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1558,
"step": 353
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.149,
"step": 354
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2533,
"step": 355
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4241,
"step": 356
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0167,
"step": 357
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2235,
"step": 358
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0712,
"step": 359
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4779,
"step": 360
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0887,
"step": 361
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0534,
"step": 362
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1561,
"step": 363
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2777,
"step": 364
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.202,
"step": 365
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.002,
"step": 366
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.4045,
"step": 367
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.6756,
"step": 368
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2138,
"step": 369
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.6403,
"step": 370
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.0688,
"step": 371
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2767,
"step": 372
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.0905,
"step": 373
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1871,
"step": 374
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2342,
"step": 375
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.559,
"step": 376
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1791,
"step": 377
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.311,
"step": 378
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.39,
"step": 379
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.7051,
"step": 380
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.2912,
"step": 381
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1762,
"step": 382
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5241,
"step": 383
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5655,
"step": 384
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1796,
"step": 385
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.9497,
"step": 386
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5626,
"step": 387
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3157,
"step": 388
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5506,
"step": 389
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.7158,
"step": 390
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.7723,
"step": 391
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3411,
"step": 392
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.3612,
"step": 393
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.9484,
"step": 394
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.7988,
"step": 395
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.6859,
"step": 396
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.1707,
"step": 397
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.5727,
"step": 398
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 0.7488,
"step": 399
},
{
"epoch": 0.02,
"learning_rate": 0.0004,
"loss": 1.3428,
"step": 400
},
{
"epoch": 0.02,
"eval_loss": 0.36855557560920715,
"eval_runtime": 218.1575,
"eval_samples_per_second": 2.292,
"eval_steps_per_second": 1.146,
"step": 400
},
{
"epoch": 0.02,
"mmlu_eval_accuracy": 0.37785769008166176,
"mmlu_eval_accuracy_abstract_algebra": 0.2727272727272727,
"mmlu_eval_accuracy_anatomy": 0.5,
"mmlu_eval_accuracy_astronomy": 0.375,
"mmlu_eval_accuracy_business_ethics": 0.45454545454545453,
"mmlu_eval_accuracy_clinical_knowledge": 0.4827586206896552,
"mmlu_eval_accuracy_college_biology": 0.25,
"mmlu_eval_accuracy_college_chemistry": 0.125,
"mmlu_eval_accuracy_college_computer_science": 0.2727272727272727,
"mmlu_eval_accuracy_college_mathematics": 0.18181818181818182,
"mmlu_eval_accuracy_college_medicine": 0.5909090909090909,
"mmlu_eval_accuracy_college_physics": 0.5454545454545454,
"mmlu_eval_accuracy_computer_security": 0.45454545454545453,
"mmlu_eval_accuracy_conceptual_physics": 0.4230769230769231,
"mmlu_eval_accuracy_econometrics": 0.25,
"mmlu_eval_accuracy_electrical_engineering": 0.1875,
"mmlu_eval_accuracy_elementary_mathematics": 0.34146341463414637,
"mmlu_eval_accuracy_formal_logic": 0.14285714285714285,
"mmlu_eval_accuracy_global_facts": 0.3,
"mmlu_eval_accuracy_high_school_biology": 0.4375,
"mmlu_eval_accuracy_high_school_chemistry": 0.22727272727272727,
"mmlu_eval_accuracy_high_school_computer_science": 0.6666666666666666,
"mmlu_eval_accuracy_high_school_european_history": 0.5,
"mmlu_eval_accuracy_high_school_geography": 0.7727272727272727,
"mmlu_eval_accuracy_high_school_government_and_politics": 0.47619047619047616,
"mmlu_eval_accuracy_high_school_macroeconomics": 0.4418604651162791,
"mmlu_eval_accuracy_high_school_mathematics": 0.1724137931034483,
"mmlu_eval_accuracy_high_school_microeconomics": 0.35714285714285715,
"mmlu_loss": 0.7700759556740523,
"step": 400
}
],
"max_steps": 5000,
"num_train_epochs": 1,
"total_flos": 5.810756599893197e+16,
"trial_name": null,
"trial_params": null
}