denverbaumgartner's picture
Upload trainer_state.json with huggingface_hub
15d739a verified
{
"best_metric": 0.35135135135135137,
"best_model_checkpoint": "/train_synth_kaggle_sampled_all_base_00_run_01_train_rerun/checkpoint-357",
"epoch": 6.995121951219512,
"global_step": 357,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 0.0001,
"loss": 3.3759,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 2.0536,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 1.3874,
"step": 3
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 1.1731,
"step": 4
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.9834,
"step": 5
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.8546,
"step": 6
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.7398,
"step": 7
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.7305,
"step": 8
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.7271,
"step": 9
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 1.0761,
"step": 10
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.553,
"step": 11
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.6037,
"step": 12
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.7828,
"step": 13
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.4642,
"step": 14
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.462,
"step": 15
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.4447,
"step": 16
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.5029,
"step": 17
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.4575,
"step": 18
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.4271,
"step": 19
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.41,
"step": 20
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.466,
"step": 21
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.3523,
"step": 22
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.4639,
"step": 23
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.3086,
"step": 24
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.3207,
"step": 25
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.3158,
"step": 26
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.3489,
"step": 27
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.3118,
"step": 28
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.3525,
"step": 29
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.3663,
"step": 30
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.2651,
"step": 31
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.403,
"step": 32
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.2569,
"step": 33
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.2629,
"step": 34
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.4017,
"step": 35
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.2565,
"step": 36
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.2578,
"step": 37
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.2865,
"step": 38
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.2865,
"step": 39
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.2676,
"step": 40
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.3189,
"step": 41
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.3188,
"step": 42
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.3004,
"step": 43
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.2068,
"step": 44
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.3131,
"step": 45
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.229,
"step": 46
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.2169,
"step": 47
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.2326,
"step": 48
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.3634,
"step": 49
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.2743,
"step": 50
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.1879,
"step": 51
},
{
"epoch": 1.0,
"eval_exact_match": 0.16216216216216217,
"eval_exec": 0.2756756756756757,
"eval_loss": 0.7464725971221924,
"eval_runtime": 367.6462,
"eval_samples_per_second": 0.503,
"step": 51
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.2133,
"step": 52
},
{
"epoch": 1.04,
"learning_rate": 0.0001,
"loss": 0.192,
"step": 53
},
{
"epoch": 1.06,
"learning_rate": 0.0001,
"loss": 0.2053,
"step": 54
},
{
"epoch": 1.08,
"learning_rate": 0.0001,
"loss": 0.1848,
"step": 55
},
{
"epoch": 1.1,
"learning_rate": 0.0001,
"loss": 0.2142,
"step": 56
},
{
"epoch": 1.12,
"learning_rate": 0.0001,
"loss": 0.1977,
"step": 57
},
{
"epoch": 1.14,
"learning_rate": 0.0001,
"loss": 0.2133,
"step": 58
},
{
"epoch": 1.16,
"learning_rate": 0.0001,
"loss": 0.1428,
"step": 59
},
{
"epoch": 1.18,
"learning_rate": 0.0001,
"loss": 0.1575,
"step": 60
},
{
"epoch": 1.2,
"learning_rate": 0.0001,
"loss": 0.1775,
"step": 61
},
{
"epoch": 1.21,
"learning_rate": 0.0001,
"loss": 0.2035,
"step": 62
},
{
"epoch": 1.23,
"learning_rate": 0.0001,
"loss": 0.2387,
"step": 63
},
{
"epoch": 1.25,
"learning_rate": 0.0001,
"loss": 0.1371,
"step": 64
},
{
"epoch": 1.27,
"learning_rate": 0.0001,
"loss": 0.2074,
"step": 65
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 0.1563,
"step": 66
},
{
"epoch": 1.31,
"learning_rate": 0.0001,
"loss": 0.1514,
"step": 67
},
{
"epoch": 1.33,
"learning_rate": 0.0001,
"loss": 0.1018,
"step": 68
},
{
"epoch": 1.35,
"learning_rate": 0.0001,
"loss": 0.1714,
"step": 69
},
{
"epoch": 1.37,
"learning_rate": 0.0001,
"loss": 0.3015,
"step": 70
},
{
"epoch": 1.39,
"learning_rate": 0.0001,
"loss": 0.2506,
"step": 71
},
{
"epoch": 1.41,
"learning_rate": 0.0001,
"loss": 0.2401,
"step": 72
},
{
"epoch": 1.43,
"learning_rate": 0.0001,
"loss": 0.1393,
"step": 73
},
{
"epoch": 1.45,
"learning_rate": 0.0001,
"loss": 0.1521,
"step": 74
},
{
"epoch": 1.47,
"learning_rate": 0.0001,
"loss": 0.1903,
"step": 75
},
{
"epoch": 1.49,
"learning_rate": 0.0001,
"loss": 0.2181,
"step": 76
},
{
"epoch": 1.51,
"learning_rate": 0.0001,
"loss": 0.2115,
"step": 77
},
{
"epoch": 1.53,
"learning_rate": 0.0001,
"loss": 0.2493,
"step": 78
},
{
"epoch": 1.55,
"learning_rate": 0.0001,
"loss": 0.202,
"step": 79
},
{
"epoch": 1.57,
"learning_rate": 0.0001,
"loss": 0.2105,
"step": 80
},
{
"epoch": 1.59,
"learning_rate": 0.0001,
"loss": 0.1555,
"step": 81
},
{
"epoch": 1.6,
"learning_rate": 0.0001,
"loss": 0.1505,
"step": 82
},
{
"epoch": 1.62,
"learning_rate": 0.0001,
"loss": 0.2083,
"step": 83
},
{
"epoch": 1.64,
"learning_rate": 0.0001,
"loss": 0.1621,
"step": 84
},
{
"epoch": 1.66,
"learning_rate": 0.0001,
"loss": 0.1271,
"step": 85
},
{
"epoch": 1.68,
"learning_rate": 0.0001,
"loss": 0.1622,
"step": 86
},
{
"epoch": 1.7,
"learning_rate": 0.0001,
"loss": 0.1225,
"step": 87
},
{
"epoch": 1.72,
"learning_rate": 0.0001,
"loss": 0.1872,
"step": 88
},
{
"epoch": 1.74,
"learning_rate": 0.0001,
"loss": 0.1493,
"step": 89
},
{
"epoch": 1.76,
"learning_rate": 0.0001,
"loss": 0.1685,
"step": 90
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 0.1341,
"step": 91
},
{
"epoch": 1.8,
"learning_rate": 0.0001,
"loss": 0.1919,
"step": 92
},
{
"epoch": 1.82,
"learning_rate": 0.0001,
"loss": 0.1806,
"step": 93
},
{
"epoch": 1.84,
"learning_rate": 0.0001,
"loss": 0.179,
"step": 94
},
{
"epoch": 1.86,
"learning_rate": 0.0001,
"loss": 0.1838,
"step": 95
},
{
"epoch": 1.88,
"learning_rate": 0.0001,
"loss": 0.1367,
"step": 96
},
{
"epoch": 1.9,
"learning_rate": 0.0001,
"loss": 0.1353,
"step": 97
},
{
"epoch": 1.92,
"learning_rate": 0.0001,
"loss": 0.198,
"step": 98
},
{
"epoch": 1.94,
"learning_rate": 0.0001,
"loss": 0.1512,
"step": 99
},
{
"epoch": 1.96,
"learning_rate": 0.0001,
"loss": 0.1563,
"step": 100
},
{
"epoch": 1.98,
"learning_rate": 0.0001,
"loss": 0.2044,
"step": 101
},
{
"epoch": 2.0,
"learning_rate": 0.0001,
"loss": 0.1437,
"step": 102
},
{
"epoch": 2.0,
"eval_exact_match": 0.12972972972972974,
"eval_exec": 0.32432432432432434,
"eval_loss": 0.7133980393409729,
"eval_runtime": 382.7403,
"eval_samples_per_second": 0.483,
"step": 102
},
{
"epoch": 2.02,
"learning_rate": 0.0001,
"loss": 0.2096,
"step": 103
},
{
"epoch": 2.04,
"learning_rate": 0.0001,
"loss": 0.1244,
"step": 104
},
{
"epoch": 2.06,
"learning_rate": 0.0001,
"loss": 0.1031,
"step": 105
},
{
"epoch": 2.08,
"learning_rate": 0.0001,
"loss": 0.1223,
"step": 106
},
{
"epoch": 2.1,
"learning_rate": 0.0001,
"loss": 0.1207,
"step": 107
},
{
"epoch": 2.12,
"learning_rate": 0.0001,
"loss": 0.0939,
"step": 108
},
{
"epoch": 2.14,
"learning_rate": 0.0001,
"loss": 0.1211,
"step": 109
},
{
"epoch": 2.16,
"learning_rate": 0.0001,
"loss": 0.0974,
"step": 110
},
{
"epoch": 2.18,
"learning_rate": 0.0001,
"loss": 0.2096,
"step": 111
},
{
"epoch": 2.2,
"learning_rate": 0.0001,
"loss": 0.1407,
"step": 112
},
{
"epoch": 2.21,
"learning_rate": 0.0001,
"loss": 0.1,
"step": 113
},
{
"epoch": 2.23,
"learning_rate": 0.0001,
"loss": 0.1496,
"step": 114
},
{
"epoch": 2.25,
"learning_rate": 0.0001,
"loss": 0.1266,
"step": 115
},
{
"epoch": 2.27,
"learning_rate": 0.0001,
"loss": 0.1363,
"step": 116
},
{
"epoch": 2.29,
"learning_rate": 0.0001,
"loss": 0.1647,
"step": 117
},
{
"epoch": 2.31,
"learning_rate": 0.0001,
"loss": 0.1231,
"step": 118
},
{
"epoch": 2.33,
"learning_rate": 0.0001,
"loss": 0.1421,
"step": 119
},
{
"epoch": 2.35,
"learning_rate": 0.0001,
"loss": 0.1862,
"step": 120
},
{
"epoch": 2.37,
"learning_rate": 0.0001,
"loss": 0.078,
"step": 121
},
{
"epoch": 2.39,
"learning_rate": 0.0001,
"loss": 0.1083,
"step": 122
},
{
"epoch": 2.41,
"learning_rate": 0.0001,
"loss": 0.0885,
"step": 123
},
{
"epoch": 2.43,
"learning_rate": 0.0001,
"loss": 0.1104,
"step": 124
},
{
"epoch": 2.45,
"learning_rate": 0.0001,
"loss": 0.1276,
"step": 125
},
{
"epoch": 2.47,
"learning_rate": 0.0001,
"loss": 0.1461,
"step": 126
},
{
"epoch": 2.49,
"learning_rate": 0.0001,
"loss": 0.1373,
"step": 127
},
{
"epoch": 2.51,
"learning_rate": 0.0001,
"loss": 0.1443,
"step": 128
},
{
"epoch": 2.53,
"learning_rate": 0.0001,
"loss": 0.1285,
"step": 129
},
{
"epoch": 2.55,
"learning_rate": 0.0001,
"loss": 0.09,
"step": 130
},
{
"epoch": 2.57,
"learning_rate": 0.0001,
"loss": 0.1002,
"step": 131
},
{
"epoch": 2.59,
"learning_rate": 0.0001,
"loss": 0.0969,
"step": 132
},
{
"epoch": 2.6,
"learning_rate": 0.0001,
"loss": 0.1384,
"step": 133
},
{
"epoch": 2.62,
"learning_rate": 0.0001,
"loss": 0.1253,
"step": 134
},
{
"epoch": 2.64,
"learning_rate": 0.0001,
"loss": 0.1151,
"step": 135
},
{
"epoch": 2.66,
"learning_rate": 0.0001,
"loss": 0.1213,
"step": 136
},
{
"epoch": 2.68,
"learning_rate": 0.0001,
"loss": 0.1261,
"step": 137
},
{
"epoch": 2.7,
"learning_rate": 0.0001,
"loss": 0.1078,
"step": 138
},
{
"epoch": 2.72,
"learning_rate": 0.0001,
"loss": 0.093,
"step": 139
},
{
"epoch": 2.74,
"learning_rate": 0.0001,
"loss": 0.1167,
"step": 140
},
{
"epoch": 2.76,
"learning_rate": 0.0001,
"loss": 0.127,
"step": 141
},
{
"epoch": 2.78,
"learning_rate": 0.0001,
"loss": 0.1336,
"step": 142
},
{
"epoch": 2.8,
"learning_rate": 0.0001,
"loss": 0.1276,
"step": 143
},
{
"epoch": 2.82,
"learning_rate": 0.0001,
"loss": 0.1152,
"step": 144
},
{
"epoch": 2.84,
"learning_rate": 0.0001,
"loss": 0.1591,
"step": 145
},
{
"epoch": 2.86,
"learning_rate": 0.0001,
"loss": 0.0968,
"step": 146
},
{
"epoch": 2.88,
"learning_rate": 0.0001,
"loss": 0.0911,
"step": 147
},
{
"epoch": 2.9,
"learning_rate": 0.0001,
"loss": 0.1135,
"step": 148
},
{
"epoch": 2.92,
"learning_rate": 0.0001,
"loss": 0.0811,
"step": 149
},
{
"epoch": 2.94,
"learning_rate": 0.0001,
"loss": 0.1472,
"step": 150
},
{
"epoch": 2.96,
"learning_rate": 0.0001,
"loss": 0.1302,
"step": 151
},
{
"epoch": 2.98,
"learning_rate": 0.0001,
"loss": 0.1385,
"step": 152
},
{
"epoch": 3.0,
"learning_rate": 0.0001,
"loss": 0.1673,
"step": 153
},
{
"epoch": 3.0,
"eval_exact_match": 0.10810810810810811,
"eval_exec": 0.3081081081081081,
"eval_loss": 0.7153419256210327,
"eval_runtime": 1791.616,
"eval_samples_per_second": 0.103,
"step": 153
},
{
"epoch": 3.02,
"learning_rate": 0.0001,
"loss": 0.1139,
"step": 154
},
{
"epoch": 3.04,
"learning_rate": 0.0001,
"loss": 0.0709,
"step": 155
},
{
"epoch": 3.06,
"learning_rate": 0.0001,
"loss": 0.0947,
"step": 156
},
{
"epoch": 3.08,
"learning_rate": 0.0001,
"loss": 0.077,
"step": 157
},
{
"epoch": 3.1,
"learning_rate": 0.0001,
"loss": 0.082,
"step": 158
},
{
"epoch": 3.12,
"learning_rate": 0.0001,
"loss": 0.0855,
"step": 159
},
{
"epoch": 3.14,
"learning_rate": 0.0001,
"loss": 0.0727,
"step": 160
},
{
"epoch": 3.16,
"learning_rate": 0.0001,
"loss": 0.0751,
"step": 161
},
{
"epoch": 3.18,
"learning_rate": 0.0001,
"loss": 0.1084,
"step": 162
},
{
"epoch": 3.2,
"learning_rate": 0.0001,
"loss": 0.074,
"step": 163
},
{
"epoch": 3.21,
"learning_rate": 0.0001,
"loss": 0.067,
"step": 164
},
{
"epoch": 3.23,
"learning_rate": 0.0001,
"loss": 0.0883,
"step": 165
},
{
"epoch": 3.25,
"learning_rate": 0.0001,
"loss": 0.0852,
"step": 166
},
{
"epoch": 3.27,
"learning_rate": 0.0001,
"loss": 0.0585,
"step": 167
},
{
"epoch": 3.29,
"learning_rate": 0.0001,
"loss": 0.0955,
"step": 168
},
{
"epoch": 3.31,
"learning_rate": 0.0001,
"loss": 0.0983,
"step": 169
},
{
"epoch": 3.33,
"learning_rate": 0.0001,
"loss": 0.096,
"step": 170
},
{
"epoch": 3.35,
"learning_rate": 0.0001,
"loss": 0.1348,
"step": 171
},
{
"epoch": 3.37,
"learning_rate": 0.0001,
"loss": 0.1121,
"step": 172
},
{
"epoch": 3.39,
"learning_rate": 0.0001,
"loss": 0.1438,
"step": 173
},
{
"epoch": 3.41,
"learning_rate": 0.0001,
"loss": 0.1388,
"step": 174
},
{
"epoch": 3.43,
"learning_rate": 0.0001,
"loss": 0.0888,
"step": 175
},
{
"epoch": 3.45,
"learning_rate": 0.0001,
"loss": 0.0781,
"step": 176
},
{
"epoch": 3.47,
"learning_rate": 0.0001,
"loss": 0.0962,
"step": 177
},
{
"epoch": 3.49,
"learning_rate": 0.0001,
"loss": 0.0831,
"step": 178
},
{
"epoch": 3.51,
"learning_rate": 0.0001,
"loss": 0.081,
"step": 179
},
{
"epoch": 3.53,
"learning_rate": 0.0001,
"loss": 0.1494,
"step": 180
},
{
"epoch": 3.55,
"learning_rate": 0.0001,
"loss": 0.0967,
"step": 181
},
{
"epoch": 3.57,
"learning_rate": 0.0001,
"loss": 0.1005,
"step": 182
},
{
"epoch": 3.59,
"learning_rate": 0.0001,
"loss": 0.1517,
"step": 183
},
{
"epoch": 3.6,
"learning_rate": 0.0001,
"loss": 0.1001,
"step": 184
},
{
"epoch": 3.62,
"learning_rate": 0.0001,
"loss": 0.0884,
"step": 185
},
{
"epoch": 3.64,
"learning_rate": 0.0001,
"loss": 0.1104,
"step": 186
},
{
"epoch": 3.66,
"learning_rate": 0.0001,
"loss": 0.0923,
"step": 187
},
{
"epoch": 3.68,
"learning_rate": 0.0001,
"loss": 0.0881,
"step": 188
},
{
"epoch": 3.7,
"learning_rate": 0.0001,
"loss": 0.0757,
"step": 189
},
{
"epoch": 3.72,
"learning_rate": 0.0001,
"loss": 0.1063,
"step": 190
},
{
"epoch": 3.74,
"learning_rate": 0.0001,
"loss": 0.1155,
"step": 191
},
{
"epoch": 3.76,
"learning_rate": 0.0001,
"loss": 0.079,
"step": 192
},
{
"epoch": 3.78,
"learning_rate": 0.0001,
"loss": 0.1092,
"step": 193
},
{
"epoch": 3.8,
"learning_rate": 0.0001,
"loss": 0.0885,
"step": 194
},
{
"epoch": 3.82,
"learning_rate": 0.0001,
"loss": 0.0957,
"step": 195
},
{
"epoch": 3.84,
"learning_rate": 0.0001,
"loss": 0.0767,
"step": 196
},
{
"epoch": 3.86,
"learning_rate": 0.0001,
"loss": 0.1115,
"step": 197
},
{
"epoch": 3.88,
"learning_rate": 0.0001,
"loss": 0.0678,
"step": 198
},
{
"epoch": 3.9,
"learning_rate": 0.0001,
"loss": 0.0866,
"step": 199
},
{
"epoch": 3.92,
"learning_rate": 0.0001,
"loss": 0.1096,
"step": 200
},
{
"epoch": 3.94,
"learning_rate": 0.0001,
"loss": 0.0851,
"step": 201
},
{
"epoch": 3.96,
"learning_rate": 0.0001,
"loss": 0.1017,
"step": 202
},
{
"epoch": 3.98,
"learning_rate": 0.0001,
"loss": 0.0999,
"step": 203
},
{
"epoch": 4.0,
"learning_rate": 0.0001,
"loss": 0.1149,
"step": 204
},
{
"epoch": 4.0,
"eval_exact_match": 0.1783783783783784,
"eval_exec": 0.31351351351351353,
"eval_loss": 0.717568576335907,
"eval_runtime": 347.1085,
"eval_samples_per_second": 0.533,
"step": 204
},
{
"epoch": 4.02,
"learning_rate": 0.0001,
"loss": 0.1412,
"step": 205
},
{
"epoch": 4.04,
"learning_rate": 0.0001,
"loss": 0.0757,
"step": 206
},
{
"epoch": 4.06,
"learning_rate": 0.0001,
"loss": 0.0709,
"step": 207
},
{
"epoch": 4.08,
"learning_rate": 0.0001,
"loss": 0.0705,
"step": 208
},
{
"epoch": 4.1,
"learning_rate": 0.0001,
"loss": 0.0839,
"step": 209
},
{
"epoch": 4.12,
"learning_rate": 0.0001,
"loss": 0.0658,
"step": 210
},
{
"epoch": 4.14,
"learning_rate": 0.0001,
"loss": 0.0725,
"step": 211
},
{
"epoch": 4.16,
"learning_rate": 0.0001,
"loss": 0.0701,
"step": 212
},
{
"epoch": 4.18,
"learning_rate": 0.0001,
"loss": 0.0628,
"step": 213
},
{
"epoch": 4.2,
"learning_rate": 0.0001,
"loss": 0.0673,
"step": 214
},
{
"epoch": 4.21,
"learning_rate": 0.0001,
"loss": 0.0847,
"step": 215
},
{
"epoch": 4.23,
"learning_rate": 0.0001,
"loss": 0.1081,
"step": 216
},
{
"epoch": 4.25,
"learning_rate": 0.0001,
"loss": 0.1022,
"step": 217
},
{
"epoch": 4.27,
"learning_rate": 0.0001,
"loss": 0.0912,
"step": 218
},
{
"epoch": 4.29,
"learning_rate": 0.0001,
"loss": 0.0854,
"step": 219
},
{
"epoch": 4.31,
"learning_rate": 0.0001,
"loss": 0.0623,
"step": 220
},
{
"epoch": 4.33,
"learning_rate": 0.0001,
"loss": 0.0852,
"step": 221
},
{
"epoch": 4.35,
"learning_rate": 0.0001,
"loss": 0.0818,
"step": 222
},
{
"epoch": 4.37,
"learning_rate": 0.0001,
"loss": 0.0563,
"step": 223
},
{
"epoch": 4.39,
"learning_rate": 0.0001,
"loss": 0.0868,
"step": 224
},
{
"epoch": 4.41,
"learning_rate": 0.0001,
"loss": 0.0816,
"step": 225
},
{
"epoch": 4.43,
"learning_rate": 0.0001,
"loss": 0.0784,
"step": 226
},
{
"epoch": 4.45,
"learning_rate": 0.0001,
"loss": 0.0943,
"step": 227
},
{
"epoch": 4.47,
"learning_rate": 0.0001,
"loss": 0.1,
"step": 228
},
{
"epoch": 4.49,
"learning_rate": 0.0001,
"loss": 0.0542,
"step": 229
},
{
"epoch": 4.51,
"learning_rate": 0.0001,
"loss": 0.0657,
"step": 230
},
{
"epoch": 4.53,
"learning_rate": 0.0001,
"loss": 0.0755,
"step": 231
},
{
"epoch": 4.55,
"learning_rate": 0.0001,
"loss": 0.0884,
"step": 232
},
{
"epoch": 4.57,
"learning_rate": 0.0001,
"loss": 0.0897,
"step": 233
},
{
"epoch": 4.59,
"learning_rate": 0.0001,
"loss": 0.0916,
"step": 234
},
{
"epoch": 4.6,
"learning_rate": 0.0001,
"loss": 0.0687,
"step": 235
},
{
"epoch": 4.62,
"learning_rate": 0.0001,
"loss": 0.0646,
"step": 236
},
{
"epoch": 4.64,
"learning_rate": 0.0001,
"loss": 0.085,
"step": 237
},
{
"epoch": 4.66,
"learning_rate": 0.0001,
"loss": 0.0887,
"step": 238
},
{
"epoch": 4.68,
"learning_rate": 0.0001,
"loss": 0.0517,
"step": 239
},
{
"epoch": 4.7,
"learning_rate": 0.0001,
"loss": 0.0558,
"step": 240
},
{
"epoch": 4.72,
"learning_rate": 0.0001,
"loss": 0.0712,
"step": 241
},
{
"epoch": 4.74,
"learning_rate": 0.0001,
"loss": 0.0791,
"step": 242
},
{
"epoch": 4.76,
"learning_rate": 0.0001,
"loss": 0.1257,
"step": 243
},
{
"epoch": 4.78,
"learning_rate": 0.0001,
"loss": 0.0589,
"step": 244
},
{
"epoch": 4.8,
"learning_rate": 0.0001,
"loss": 0.0713,
"step": 245
},
{
"epoch": 4.82,
"learning_rate": 0.0001,
"loss": 0.0893,
"step": 246
},
{
"epoch": 4.84,
"learning_rate": 0.0001,
"loss": 0.0832,
"step": 247
},
{
"epoch": 4.86,
"learning_rate": 0.0001,
"loss": 0.0849,
"step": 248
},
{
"epoch": 4.88,
"learning_rate": 0.0001,
"loss": 0.071,
"step": 249
},
{
"epoch": 4.9,
"learning_rate": 0.0001,
"loss": 0.0751,
"step": 250
},
{
"epoch": 4.92,
"learning_rate": 0.0001,
"loss": 0.0704,
"step": 251
},
{
"epoch": 4.94,
"learning_rate": 0.0001,
"loss": 0.0749,
"step": 252
},
{
"epoch": 4.96,
"learning_rate": 0.0001,
"loss": 0.0827,
"step": 253
},
{
"epoch": 4.98,
"learning_rate": 0.0001,
"loss": 0.057,
"step": 254
},
{
"epoch": 5.0,
"learning_rate": 0.0001,
"loss": 0.0717,
"step": 255
},
{
"epoch": 5.0,
"eval_exact_match": 0.12972972972972974,
"eval_exec": 0.2918918918918919,
"eval_loss": 0.822371780872345,
"eval_runtime": 328.0785,
"eval_samples_per_second": 0.564,
"step": 255
},
{
"epoch": 5.02,
"learning_rate": 0.0001,
"loss": 0.0833,
"step": 256
},
{
"epoch": 5.04,
"learning_rate": 0.0001,
"loss": 0.0711,
"step": 257
},
{
"epoch": 5.06,
"learning_rate": 0.0001,
"loss": 0.0769,
"step": 258
},
{
"epoch": 5.08,
"learning_rate": 0.0001,
"loss": 0.054,
"step": 259
},
{
"epoch": 5.1,
"learning_rate": 0.0001,
"loss": 0.0365,
"step": 260
},
{
"epoch": 5.12,
"learning_rate": 0.0001,
"loss": 0.0509,
"step": 261
},
{
"epoch": 5.14,
"learning_rate": 0.0001,
"loss": 0.0718,
"step": 262
},
{
"epoch": 5.16,
"learning_rate": 0.0001,
"loss": 0.04,
"step": 263
},
{
"epoch": 5.18,
"learning_rate": 0.0001,
"loss": 0.053,
"step": 264
},
{
"epoch": 5.2,
"learning_rate": 0.0001,
"loss": 0.0508,
"step": 265
},
{
"epoch": 5.21,
"learning_rate": 0.0001,
"loss": 0.043,
"step": 266
},
{
"epoch": 5.23,
"learning_rate": 0.0001,
"loss": 0.0672,
"step": 267
},
{
"epoch": 5.25,
"learning_rate": 0.0001,
"loss": 0.0971,
"step": 268
},
{
"epoch": 5.27,
"learning_rate": 0.0001,
"loss": 0.0468,
"step": 269
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 0.0761,
"step": 270
},
{
"epoch": 5.31,
"learning_rate": 0.0001,
"loss": 0.0684,
"step": 271
},
{
"epoch": 5.33,
"learning_rate": 0.0001,
"loss": 0.0593,
"step": 272
},
{
"epoch": 5.35,
"learning_rate": 0.0001,
"loss": 0.0727,
"step": 273
},
{
"epoch": 5.37,
"learning_rate": 0.0001,
"loss": 0.0939,
"step": 274
},
{
"epoch": 5.39,
"learning_rate": 0.0001,
"loss": 0.0739,
"step": 275
},
{
"epoch": 5.41,
"learning_rate": 0.0001,
"loss": 0.048,
"step": 276
},
{
"epoch": 5.43,
"learning_rate": 0.0001,
"loss": 0.0579,
"step": 277
},
{
"epoch": 5.45,
"learning_rate": 0.0001,
"loss": 0.0904,
"step": 278
},
{
"epoch": 5.47,
"learning_rate": 0.0001,
"loss": 0.0628,
"step": 279
},
{
"epoch": 5.49,
"learning_rate": 0.0001,
"loss": 0.0778,
"step": 280
},
{
"epoch": 5.51,
"learning_rate": 0.0001,
"loss": 0.0491,
"step": 281
},
{
"epoch": 5.53,
"learning_rate": 0.0001,
"loss": 0.0641,
"step": 282
},
{
"epoch": 5.55,
"learning_rate": 0.0001,
"loss": 0.0508,
"step": 283
},
{
"epoch": 5.57,
"learning_rate": 0.0001,
"loss": 0.062,
"step": 284
},
{
"epoch": 5.59,
"learning_rate": 0.0001,
"loss": 0.0786,
"step": 285
},
{
"epoch": 5.6,
"learning_rate": 0.0001,
"loss": 0.048,
"step": 286
},
{
"epoch": 5.62,
"learning_rate": 0.0001,
"loss": 0.0516,
"step": 287
},
{
"epoch": 5.64,
"learning_rate": 0.0001,
"loss": 0.0515,
"step": 288
},
{
"epoch": 5.66,
"learning_rate": 0.0001,
"loss": 0.0889,
"step": 289
},
{
"epoch": 5.68,
"learning_rate": 0.0001,
"loss": 0.0989,
"step": 290
},
{
"epoch": 5.7,
"learning_rate": 0.0001,
"loss": 0.0844,
"step": 291
},
{
"epoch": 5.72,
"learning_rate": 0.0001,
"loss": 0.0843,
"step": 292
},
{
"epoch": 5.74,
"learning_rate": 0.0001,
"loss": 0.0601,
"step": 293
},
{
"epoch": 5.76,
"learning_rate": 0.0001,
"loss": 0.0604,
"step": 294
},
{
"epoch": 5.78,
"learning_rate": 0.0001,
"loss": 0.0791,
"step": 295
},
{
"epoch": 5.8,
"learning_rate": 0.0001,
"loss": 0.0727,
"step": 296
},
{
"epoch": 5.82,
"learning_rate": 0.0001,
"loss": 0.0617,
"step": 297
},
{
"epoch": 5.84,
"learning_rate": 0.0001,
"loss": 0.0587,
"step": 298
},
{
"epoch": 5.86,
"learning_rate": 0.0001,
"loss": 0.0627,
"step": 299
},
{
"epoch": 5.88,
"learning_rate": 0.0001,
"loss": 0.078,
"step": 300
},
{
"epoch": 5.9,
"learning_rate": 0.0001,
"loss": 0.0656,
"step": 301
},
{
"epoch": 5.92,
"learning_rate": 0.0001,
"loss": 0.0443,
"step": 302
},
{
"epoch": 5.94,
"learning_rate": 0.0001,
"loss": 0.0703,
"step": 303
},
{
"epoch": 5.96,
"learning_rate": 0.0001,
"loss": 0.067,
"step": 304
},
{
"epoch": 5.98,
"learning_rate": 0.0001,
"loss": 0.0745,
"step": 305
},
{
"epoch": 6.0,
"learning_rate": 0.0001,
"loss": 0.0639,
"step": 306
},
{
"epoch": 6.0,
"eval_exact_match": 0.10270270270270271,
"eval_exec": 0.31351351351351353,
"eval_loss": 0.8198407292366028,
"eval_runtime": 314.0983,
"eval_samples_per_second": 0.589,
"step": 306
},
{
"epoch": 6.02,
"learning_rate": 0.0001,
"loss": 0.0544,
"step": 307
},
{
"epoch": 6.04,
"learning_rate": 0.0001,
"loss": 0.0427,
"step": 308
},
{
"epoch": 6.06,
"learning_rate": 0.0001,
"loss": 0.0408,
"step": 309
},
{
"epoch": 6.08,
"learning_rate": 0.0001,
"loss": 0.0527,
"step": 310
},
{
"epoch": 6.1,
"learning_rate": 0.0001,
"loss": 0.0541,
"step": 311
},
{
"epoch": 6.12,
"learning_rate": 0.0001,
"loss": 0.0392,
"step": 312
},
{
"epoch": 6.14,
"learning_rate": 0.0001,
"loss": 0.0585,
"step": 313
},
{
"epoch": 6.16,
"learning_rate": 0.0001,
"loss": 0.0813,
"step": 314
},
{
"epoch": 6.18,
"learning_rate": 0.0001,
"loss": 0.0497,
"step": 315
},
{
"epoch": 6.2,
"learning_rate": 0.0001,
"loss": 0.0629,
"step": 316
},
{
"epoch": 6.21,
"learning_rate": 0.0001,
"loss": 0.0457,
"step": 317
},
{
"epoch": 6.23,
"learning_rate": 0.0001,
"loss": 0.0519,
"step": 318
},
{
"epoch": 6.25,
"learning_rate": 0.0001,
"loss": 0.0647,
"step": 319
},
{
"epoch": 6.27,
"learning_rate": 0.0001,
"loss": 0.0391,
"step": 320
},
{
"epoch": 6.29,
"learning_rate": 0.0001,
"loss": 0.0464,
"step": 321
},
{
"epoch": 6.31,
"learning_rate": 0.0001,
"loss": 0.0398,
"step": 322
},
{
"epoch": 6.33,
"learning_rate": 0.0001,
"loss": 0.0425,
"step": 323
},
{
"epoch": 6.35,
"learning_rate": 0.0001,
"loss": 0.0491,
"step": 324
},
{
"epoch": 6.37,
"learning_rate": 0.0001,
"loss": 0.0528,
"step": 325
},
{
"epoch": 6.39,
"learning_rate": 0.0001,
"loss": 0.0605,
"step": 326
},
{
"epoch": 6.41,
"learning_rate": 0.0001,
"loss": 0.0568,
"step": 327
},
{
"epoch": 6.43,
"learning_rate": 0.0001,
"loss": 0.0547,
"step": 328
},
{
"epoch": 6.45,
"learning_rate": 0.0001,
"loss": 0.0861,
"step": 329
},
{
"epoch": 6.47,
"learning_rate": 0.0001,
"loss": 0.0467,
"step": 330
},
{
"epoch": 6.49,
"learning_rate": 0.0001,
"loss": 0.0375,
"step": 331
},
{
"epoch": 6.51,
"learning_rate": 0.0001,
"loss": 0.0965,
"step": 332
},
{
"epoch": 6.53,
"learning_rate": 0.0001,
"loss": 0.0476,
"step": 333
},
{
"epoch": 6.55,
"learning_rate": 0.0001,
"loss": 0.0557,
"step": 334
},
{
"epoch": 6.57,
"learning_rate": 0.0001,
"loss": 0.0592,
"step": 335
},
{
"epoch": 6.59,
"learning_rate": 0.0001,
"loss": 0.052,
"step": 336
},
{
"epoch": 6.6,
"learning_rate": 0.0001,
"loss": 0.0681,
"step": 337
},
{
"epoch": 6.62,
"learning_rate": 0.0001,
"loss": 0.0526,
"step": 338
},
{
"epoch": 6.64,
"learning_rate": 0.0001,
"loss": 0.0734,
"step": 339
},
{
"epoch": 6.66,
"learning_rate": 0.0001,
"loss": 0.0687,
"step": 340
},
{
"epoch": 6.68,
"learning_rate": 0.0001,
"loss": 0.0584,
"step": 341
},
{
"epoch": 6.7,
"learning_rate": 0.0001,
"loss": 0.0679,
"step": 342
},
{
"epoch": 6.72,
"learning_rate": 0.0001,
"loss": 0.0834,
"step": 343
},
{
"epoch": 6.74,
"learning_rate": 0.0001,
"loss": 0.054,
"step": 344
},
{
"epoch": 6.76,
"learning_rate": 0.0001,
"loss": 0.0618,
"step": 345
},
{
"epoch": 6.78,
"learning_rate": 0.0001,
"loss": 0.0813,
"step": 346
},
{
"epoch": 6.8,
"learning_rate": 0.0001,
"loss": 0.0359,
"step": 347
},
{
"epoch": 6.82,
"learning_rate": 0.0001,
"loss": 0.0622,
"step": 348
},
{
"epoch": 6.84,
"learning_rate": 0.0001,
"loss": 0.0734,
"step": 349
},
{
"epoch": 6.86,
"learning_rate": 0.0001,
"loss": 0.086,
"step": 350
},
{
"epoch": 6.88,
"learning_rate": 0.0001,
"loss": 0.0816,
"step": 351
},
{
"epoch": 6.9,
"learning_rate": 0.0001,
"loss": 0.073,
"step": 352
},
{
"epoch": 6.92,
"learning_rate": 0.0001,
"loss": 0.065,
"step": 353
},
{
"epoch": 6.94,
"learning_rate": 0.0001,
"loss": 0.0725,
"step": 354
},
{
"epoch": 6.96,
"learning_rate": 0.0001,
"loss": 0.05,
"step": 355
},
{
"epoch": 6.98,
"learning_rate": 0.0001,
"loss": 0.0421,
"step": 356
},
{
"epoch": 7.0,
"learning_rate": 0.0001,
"loss": 0.0657,
"step": 357
},
{
"epoch": 7.0,
"eval_exact_match": 0.10810810810810811,
"eval_exec": 0.35135135135135137,
"eval_loss": 0.8267735838890076,
"eval_runtime": 335.9131,
"eval_samples_per_second": 0.551,
"step": 357
}
],
"max_steps": 1275,
"num_train_epochs": 25,
"total_flos": 4.52971520232407e+16,
"trial_name": null,
"trial_params": null
}