denverbaumgartner's picture
Upload trainer_state.json with huggingface_hub
17219f4 verified
{
"best_metric": 0.35135135135135137,
"best_model_checkpoint": "/train_synth_kaggle_sampled_all_base_00_run_02_train_rerun/checkpoint-918",
"epoch": 17.995121951219513,
"global_step": 918,
"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": 3.3724,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 2.0577,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 1.3659,
"step": 3
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 1.1298,
"step": 4
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.9756,
"step": 5
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.8382,
"step": 6
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.7376,
"step": 7
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.6463,
"step": 8
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.7646,
"step": 9
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 1.1028,
"step": 10
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.5436,
"step": 11
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.5141,
"step": 12
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.7812,
"step": 13
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.4589,
"step": 14
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.4829,
"step": 15
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.5056,
"step": 16
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.4852,
"step": 17
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.5199,
"step": 18
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.4426,
"step": 19
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.4513,
"step": 20
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.5105,
"step": 21
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.3924,
"step": 22
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.4518,
"step": 23
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.3347,
"step": 24
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.3294,
"step": 25
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.2768,
"step": 26
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.3407,
"step": 27
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.3629,
"step": 28
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.3283,
"step": 29
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.3881,
"step": 30
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.2777,
"step": 31
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.4109,
"step": 32
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.2744,
"step": 33
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.2753,
"step": 34
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.4003,
"step": 35
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.238,
"step": 36
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.2943,
"step": 37
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.3306,
"step": 38
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.2671,
"step": 39
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.2849,
"step": 40
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.2639,
"step": 41
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.2803,
"step": 42
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.323,
"step": 43
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.2127,
"step": 44
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.2931,
"step": 45
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.2328,
"step": 46
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.2049,
"step": 47
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.2511,
"step": 48
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.3092,
"step": 49
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.2675,
"step": 50
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.1886,
"step": 51
},
{
"epoch": 1.0,
"eval_exact_match": 0.0972972972972973,
"eval_exec": 0.2918918918918919,
"eval_loss": 0.7343990206718445,
"eval_runtime": 396.4151,
"eval_samples_per_second": 0.467,
"step": 51
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.1938,
"step": 52
},
{
"epoch": 1.04,
"learning_rate": 0.0001,
"loss": 0.2199,
"step": 53
},
{
"epoch": 1.06,
"learning_rate": 0.0001,
"loss": 0.2215,
"step": 54
},
{
"epoch": 1.08,
"learning_rate": 0.0001,
"loss": 0.1945,
"step": 55
},
{
"epoch": 1.1,
"learning_rate": 0.0001,
"loss": 0.2126,
"step": 56
},
{
"epoch": 1.12,
"learning_rate": 0.0001,
"loss": 0.2228,
"step": 57
},
{
"epoch": 1.14,
"learning_rate": 0.0001,
"loss": 0.2291,
"step": 58
},
{
"epoch": 1.16,
"learning_rate": 0.0001,
"loss": 0.1372,
"step": 59
},
{
"epoch": 1.18,
"learning_rate": 0.0001,
"loss": 0.2073,
"step": 60
},
{
"epoch": 1.2,
"learning_rate": 0.0001,
"loss": 0.1597,
"step": 61
},
{
"epoch": 1.21,
"learning_rate": 0.0001,
"loss": 0.1917,
"step": 62
},
{
"epoch": 1.23,
"learning_rate": 0.0001,
"loss": 0.236,
"step": 63
},
{
"epoch": 1.25,
"learning_rate": 0.0001,
"loss": 0.1449,
"step": 64
},
{
"epoch": 1.27,
"learning_rate": 0.0001,
"loss": 0.233,
"step": 65
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 0.184,
"step": 66
},
{
"epoch": 1.31,
"learning_rate": 0.0001,
"loss": 0.1778,
"step": 67
},
{
"epoch": 1.33,
"learning_rate": 0.0001,
"loss": 0.0922,
"step": 68
},
{
"epoch": 1.35,
"learning_rate": 0.0001,
"loss": 0.1705,
"step": 69
},
{
"epoch": 1.37,
"learning_rate": 0.0001,
"loss": 0.1648,
"step": 70
},
{
"epoch": 1.39,
"learning_rate": 0.0001,
"loss": 0.2741,
"step": 71
},
{
"epoch": 1.41,
"learning_rate": 0.0001,
"loss": 0.2427,
"step": 72
},
{
"epoch": 1.43,
"learning_rate": 0.0001,
"loss": 0.1497,
"step": 73
},
{
"epoch": 1.45,
"learning_rate": 0.0001,
"loss": 0.1845,
"step": 74
},
{
"epoch": 1.47,
"learning_rate": 0.0001,
"loss": 0.2148,
"step": 75
},
{
"epoch": 1.49,
"learning_rate": 0.0001,
"loss": 0.2218,
"step": 76
},
{
"epoch": 1.51,
"learning_rate": 0.0001,
"loss": 0.2168,
"step": 77
},
{
"epoch": 1.53,
"learning_rate": 0.0001,
"loss": 0.2395,
"step": 78
},
{
"epoch": 1.55,
"learning_rate": 0.0001,
"loss": 0.2203,
"step": 79
},
{
"epoch": 1.57,
"learning_rate": 0.0001,
"loss": 0.223,
"step": 80
},
{
"epoch": 1.59,
"learning_rate": 0.0001,
"loss": 0.1754,
"step": 81
},
{
"epoch": 1.6,
"learning_rate": 0.0001,
"loss": 0.1542,
"step": 82
},
{
"epoch": 1.62,
"learning_rate": 0.0001,
"loss": 0.2074,
"step": 83
},
{
"epoch": 1.64,
"learning_rate": 0.0001,
"loss": 0.1599,
"step": 84
},
{
"epoch": 1.66,
"learning_rate": 0.0001,
"loss": 0.1405,
"step": 85
},
{
"epoch": 1.68,
"learning_rate": 0.0001,
"loss": 0.1893,
"step": 86
},
{
"epoch": 1.7,
"learning_rate": 0.0001,
"loss": 0.1274,
"step": 87
},
{
"epoch": 1.72,
"learning_rate": 0.0001,
"loss": 0.1902,
"step": 88
},
{
"epoch": 1.74,
"learning_rate": 0.0001,
"loss": 0.1593,
"step": 89
},
{
"epoch": 1.76,
"learning_rate": 0.0001,
"loss": 0.1728,
"step": 90
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 0.1326,
"step": 91
},
{
"epoch": 1.8,
"learning_rate": 0.0001,
"loss": 0.203,
"step": 92
},
{
"epoch": 1.82,
"learning_rate": 0.0001,
"loss": 0.1909,
"step": 93
},
{
"epoch": 1.84,
"learning_rate": 0.0001,
"loss": 0.1896,
"step": 94
},
{
"epoch": 1.86,
"learning_rate": 0.0001,
"loss": 0.1801,
"step": 95
},
{
"epoch": 1.88,
"learning_rate": 0.0001,
"loss": 0.1593,
"step": 96
},
{
"epoch": 1.9,
"learning_rate": 0.0001,
"loss": 0.1388,
"step": 97
},
{
"epoch": 1.92,
"learning_rate": 0.0001,
"loss": 0.199,
"step": 98
},
{
"epoch": 1.94,
"learning_rate": 0.0001,
"loss": 0.1421,
"step": 99
},
{
"epoch": 1.96,
"learning_rate": 0.0001,
"loss": 0.1456,
"step": 100
},
{
"epoch": 1.98,
"learning_rate": 0.0001,
"loss": 0.1965,
"step": 101
},
{
"epoch": 2.0,
"learning_rate": 0.0001,
"loss": 0.1606,
"step": 102
},
{
"epoch": 2.0,
"eval_exact_match": 0.10270270270270271,
"eval_exec": 0.3081081081081081,
"eval_loss": 0.7089210152626038,
"eval_runtime": 437.9411,
"eval_samples_per_second": 0.422,
"step": 102
},
{
"epoch": 2.02,
"learning_rate": 0.0001,
"loss": 0.2369,
"step": 103
},
{
"epoch": 2.04,
"learning_rate": 0.0001,
"loss": 0.119,
"step": 104
},
{
"epoch": 2.06,
"learning_rate": 0.0001,
"loss": 0.1102,
"step": 105
},
{
"epoch": 2.08,
"learning_rate": 0.0001,
"loss": 0.1157,
"step": 106
},
{
"epoch": 2.1,
"learning_rate": 0.0001,
"loss": 0.1204,
"step": 107
},
{
"epoch": 2.12,
"learning_rate": 0.0001,
"loss": 0.101,
"step": 108
},
{
"epoch": 2.14,
"learning_rate": 0.0001,
"loss": 0.1226,
"step": 109
},
{
"epoch": 2.16,
"learning_rate": 0.0001,
"loss": 0.091,
"step": 110
},
{
"epoch": 2.18,
"learning_rate": 0.0001,
"loss": 0.2132,
"step": 111
},
{
"epoch": 2.2,
"learning_rate": 0.0001,
"loss": 0.1655,
"step": 112
},
{
"epoch": 2.21,
"learning_rate": 0.0001,
"loss": 0.0962,
"step": 113
},
{
"epoch": 2.23,
"learning_rate": 0.0001,
"loss": 0.1668,
"step": 114
},
{
"epoch": 2.25,
"learning_rate": 0.0001,
"loss": 0.1269,
"step": 115
},
{
"epoch": 2.27,
"learning_rate": 0.0001,
"loss": 0.1594,
"step": 116
},
{
"epoch": 2.29,
"learning_rate": 0.0001,
"loss": 0.1568,
"step": 117
},
{
"epoch": 2.31,
"learning_rate": 0.0001,
"loss": 0.129,
"step": 118
},
{
"epoch": 2.33,
"learning_rate": 0.0001,
"loss": 0.1502,
"step": 119
},
{
"epoch": 2.35,
"learning_rate": 0.0001,
"loss": 0.1909,
"step": 120
},
{
"epoch": 2.37,
"learning_rate": 0.0001,
"loss": 0.0802,
"step": 121
},
{
"epoch": 2.39,
"learning_rate": 0.0001,
"loss": 0.1075,
"step": 122
},
{
"epoch": 2.41,
"learning_rate": 0.0001,
"loss": 0.0895,
"step": 123
},
{
"epoch": 2.43,
"learning_rate": 0.0001,
"loss": 0.1036,
"step": 124
},
{
"epoch": 2.45,
"learning_rate": 0.0001,
"loss": 0.1232,
"step": 125
},
{
"epoch": 2.47,
"learning_rate": 0.0001,
"loss": 0.1454,
"step": 126
},
{
"epoch": 2.49,
"learning_rate": 0.0001,
"loss": 0.1583,
"step": 127
},
{
"epoch": 2.51,
"learning_rate": 0.0001,
"loss": 0.1754,
"step": 128
},
{
"epoch": 2.53,
"learning_rate": 0.0001,
"loss": 0.1616,
"step": 129
},
{
"epoch": 2.55,
"learning_rate": 0.0001,
"loss": 0.1013,
"step": 130
},
{
"epoch": 2.57,
"learning_rate": 0.0001,
"loss": 0.1085,
"step": 131
},
{
"epoch": 2.59,
"learning_rate": 0.0001,
"loss": 0.0997,
"step": 132
},
{
"epoch": 2.6,
"learning_rate": 0.0001,
"loss": 0.1423,
"step": 133
},
{
"epoch": 2.62,
"learning_rate": 0.0001,
"loss": 0.1141,
"step": 134
},
{
"epoch": 2.64,
"learning_rate": 0.0001,
"loss": 0.1336,
"step": 135
},
{
"epoch": 2.66,
"learning_rate": 0.0001,
"loss": 0.1157,
"step": 136
},
{
"epoch": 2.68,
"learning_rate": 0.0001,
"loss": 0.1329,
"step": 137
},
{
"epoch": 2.7,
"learning_rate": 0.0001,
"loss": 0.1274,
"step": 138
},
{
"epoch": 2.72,
"learning_rate": 0.0001,
"loss": 0.1096,
"step": 139
},
{
"epoch": 2.74,
"learning_rate": 0.0001,
"loss": 0.1298,
"step": 140
},
{
"epoch": 2.76,
"learning_rate": 0.0001,
"loss": 0.1332,
"step": 141
},
{
"epoch": 2.78,
"learning_rate": 0.0001,
"loss": 0.1599,
"step": 142
},
{
"epoch": 2.8,
"learning_rate": 0.0001,
"loss": 0.1348,
"step": 143
},
{
"epoch": 2.82,
"learning_rate": 0.0001,
"loss": 0.1334,
"step": 144
},
{
"epoch": 2.84,
"learning_rate": 0.0001,
"loss": 0.1544,
"step": 145
},
{
"epoch": 2.86,
"learning_rate": 0.0001,
"loss": 0.0953,
"step": 146
},
{
"epoch": 2.88,
"learning_rate": 0.0001,
"loss": 0.1062,
"step": 147
},
{
"epoch": 2.9,
"learning_rate": 0.0001,
"loss": 0.1117,
"step": 148
},
{
"epoch": 2.92,
"learning_rate": 0.0001,
"loss": 0.0746,
"step": 149
},
{
"epoch": 2.94,
"learning_rate": 0.0001,
"loss": 0.1363,
"step": 150
},
{
"epoch": 2.96,
"learning_rate": 0.0001,
"loss": 0.1112,
"step": 151
},
{
"epoch": 2.98,
"learning_rate": 0.0001,
"loss": 0.1401,
"step": 152
},
{
"epoch": 3.0,
"learning_rate": 0.0001,
"loss": 0.178,
"step": 153
},
{
"epoch": 3.0,
"eval_exact_match": 0.12432432432432433,
"eval_exec": 0.32432432432432434,
"eval_loss": 0.6852184534072876,
"eval_runtime": 1812.0807,
"eval_samples_per_second": 0.102,
"step": 153
},
{
"epoch": 3.02,
"learning_rate": 0.0001,
"loss": 0.1231,
"step": 154
},
{
"epoch": 3.04,
"learning_rate": 0.0001,
"loss": 0.0783,
"step": 155
},
{
"epoch": 3.06,
"learning_rate": 0.0001,
"loss": 0.1089,
"step": 156
},
{
"epoch": 3.08,
"learning_rate": 0.0001,
"loss": 0.0857,
"step": 157
},
{
"epoch": 3.1,
"learning_rate": 0.0001,
"loss": 0.0958,
"step": 158
},
{
"epoch": 3.12,
"learning_rate": 0.0001,
"loss": 0.0783,
"step": 159
},
{
"epoch": 3.14,
"learning_rate": 0.0001,
"loss": 0.0665,
"step": 160
},
{
"epoch": 3.16,
"learning_rate": 0.0001,
"loss": 0.0845,
"step": 161
},
{
"epoch": 3.18,
"learning_rate": 0.0001,
"loss": 0.116,
"step": 162
},
{
"epoch": 3.2,
"learning_rate": 0.0001,
"loss": 0.0832,
"step": 163
},
{
"epoch": 3.21,
"learning_rate": 0.0001,
"loss": 0.084,
"step": 164
},
{
"epoch": 3.23,
"learning_rate": 0.0001,
"loss": 0.0941,
"step": 165
},
{
"epoch": 3.25,
"learning_rate": 0.0001,
"loss": 0.0832,
"step": 166
},
{
"epoch": 3.27,
"learning_rate": 0.0001,
"loss": 0.0617,
"step": 167
},
{
"epoch": 3.29,
"learning_rate": 0.0001,
"loss": 0.1072,
"step": 168
},
{
"epoch": 3.31,
"learning_rate": 0.0001,
"loss": 0.1153,
"step": 169
},
{
"epoch": 3.33,
"learning_rate": 0.0001,
"loss": 0.0991,
"step": 170
},
{
"epoch": 3.35,
"learning_rate": 0.0001,
"loss": 0.1333,
"step": 171
},
{
"epoch": 3.37,
"learning_rate": 0.0001,
"loss": 0.1163,
"step": 172
},
{
"epoch": 3.39,
"learning_rate": 0.0001,
"loss": 0.1239,
"step": 173
},
{
"epoch": 3.41,
"learning_rate": 0.0001,
"loss": 0.1404,
"step": 174
},
{
"epoch": 3.43,
"learning_rate": 0.0001,
"loss": 0.0938,
"step": 175
},
{
"epoch": 3.45,
"learning_rate": 0.0001,
"loss": 0.0862,
"step": 176
},
{
"epoch": 3.47,
"learning_rate": 0.0001,
"loss": 0.0917,
"step": 177
},
{
"epoch": 3.49,
"learning_rate": 0.0001,
"loss": 0.0756,
"step": 178
},
{
"epoch": 3.51,
"learning_rate": 0.0001,
"loss": 0.0711,
"step": 179
},
{
"epoch": 3.53,
"learning_rate": 0.0001,
"loss": 0.1393,
"step": 180
},
{
"epoch": 3.55,
"learning_rate": 0.0001,
"loss": 0.1023,
"step": 181
},
{
"epoch": 3.57,
"learning_rate": 0.0001,
"loss": 0.1078,
"step": 182
},
{
"epoch": 3.59,
"learning_rate": 0.0001,
"loss": 0.1317,
"step": 183
},
{
"epoch": 3.6,
"learning_rate": 0.0001,
"loss": 0.1002,
"step": 184
},
{
"epoch": 3.62,
"learning_rate": 0.0001,
"loss": 0.0969,
"step": 185
},
{
"epoch": 3.64,
"learning_rate": 0.0001,
"loss": 0.1047,
"step": 186
},
{
"epoch": 3.66,
"learning_rate": 0.0001,
"loss": 0.1075,
"step": 187
},
{
"epoch": 3.68,
"learning_rate": 0.0001,
"loss": 0.1032,
"step": 188
},
{
"epoch": 3.7,
"learning_rate": 0.0001,
"loss": 0.0822,
"step": 189
},
{
"epoch": 3.72,
"learning_rate": 0.0001,
"loss": 0.1031,
"step": 190
},
{
"epoch": 3.74,
"learning_rate": 0.0001,
"loss": 0.1133,
"step": 191
},
{
"epoch": 3.76,
"learning_rate": 0.0001,
"loss": 0.0863,
"step": 192
},
{
"epoch": 3.78,
"learning_rate": 0.0001,
"loss": 0.1136,
"step": 193
},
{
"epoch": 3.8,
"learning_rate": 0.0001,
"loss": 0.0955,
"step": 194
},
{
"epoch": 3.82,
"learning_rate": 0.0001,
"loss": 0.0947,
"step": 195
},
{
"epoch": 3.84,
"learning_rate": 0.0001,
"loss": 0.0845,
"step": 196
},
{
"epoch": 3.86,
"learning_rate": 0.0001,
"loss": 0.1069,
"step": 197
},
{
"epoch": 3.88,
"learning_rate": 0.0001,
"loss": 0.0649,
"step": 198
},
{
"epoch": 3.9,
"learning_rate": 0.0001,
"loss": 0.0915,
"step": 199
},
{
"epoch": 3.92,
"learning_rate": 0.0001,
"loss": 0.1081,
"step": 200
},
{
"epoch": 3.94,
"learning_rate": 0.0001,
"loss": 0.0874,
"step": 201
},
{
"epoch": 3.96,
"learning_rate": 0.0001,
"loss": 0.1059,
"step": 202
},
{
"epoch": 3.98,
"learning_rate": 0.0001,
"loss": 0.1045,
"step": 203
},
{
"epoch": 4.0,
"learning_rate": 0.0001,
"loss": 0.1117,
"step": 204
},
{
"epoch": 4.0,
"eval_exact_match": 0.15675675675675677,
"eval_exec": 0.33513513513513515,
"eval_loss": 0.7143957018852234,
"eval_runtime": 349.2941,
"eval_samples_per_second": 0.53,
"step": 204
},
{
"epoch": 4.02,
"learning_rate": 0.0001,
"loss": 0.1483,
"step": 205
},
{
"epoch": 4.04,
"learning_rate": 0.0001,
"loss": 0.0662,
"step": 206
},
{
"epoch": 4.06,
"learning_rate": 0.0001,
"loss": 0.0676,
"step": 207
},
{
"epoch": 4.08,
"learning_rate": 0.0001,
"loss": 0.0652,
"step": 208
},
{
"epoch": 4.1,
"learning_rate": 0.0001,
"loss": 0.0914,
"step": 209
},
{
"epoch": 4.12,
"learning_rate": 0.0001,
"loss": 0.0617,
"step": 210
},
{
"epoch": 4.14,
"learning_rate": 0.0001,
"loss": 0.0847,
"step": 211
},
{
"epoch": 4.16,
"learning_rate": 0.0001,
"loss": 0.0843,
"step": 212
},
{
"epoch": 4.18,
"learning_rate": 0.0001,
"loss": 0.0713,
"step": 213
},
{
"epoch": 4.2,
"learning_rate": 0.0001,
"loss": 0.0745,
"step": 214
},
{
"epoch": 4.21,
"learning_rate": 0.0001,
"loss": 0.0824,
"step": 215
},
{
"epoch": 4.23,
"learning_rate": 0.0001,
"loss": 0.1003,
"step": 216
},
{
"epoch": 4.25,
"learning_rate": 0.0001,
"loss": 0.0833,
"step": 217
},
{
"epoch": 4.27,
"learning_rate": 0.0001,
"loss": 0.0908,
"step": 218
},
{
"epoch": 4.29,
"learning_rate": 0.0001,
"loss": 0.0729,
"step": 219
},
{
"epoch": 4.31,
"learning_rate": 0.0001,
"loss": 0.0723,
"step": 220
},
{
"epoch": 4.33,
"learning_rate": 0.0001,
"loss": 0.0954,
"step": 221
},
{
"epoch": 4.35,
"learning_rate": 0.0001,
"loss": 0.0887,
"step": 222
},
{
"epoch": 4.37,
"learning_rate": 0.0001,
"loss": 0.0657,
"step": 223
},
{
"epoch": 4.39,
"learning_rate": 0.0001,
"loss": 0.0923,
"step": 224
},
{
"epoch": 4.41,
"learning_rate": 0.0001,
"loss": 0.0935,
"step": 225
},
{
"epoch": 4.43,
"learning_rate": 0.0001,
"loss": 0.0913,
"step": 226
},
{
"epoch": 4.45,
"learning_rate": 0.0001,
"loss": 0.0919,
"step": 227
},
{
"epoch": 4.47,
"learning_rate": 0.0001,
"loss": 0.0966,
"step": 228
},
{
"epoch": 4.49,
"learning_rate": 0.0001,
"loss": 0.0564,
"step": 229
},
{
"epoch": 4.51,
"learning_rate": 0.0001,
"loss": 0.0685,
"step": 230
},
{
"epoch": 4.53,
"learning_rate": 0.0001,
"loss": 0.0881,
"step": 231
},
{
"epoch": 4.55,
"learning_rate": 0.0001,
"loss": 0.0841,
"step": 232
},
{
"epoch": 4.57,
"learning_rate": 0.0001,
"loss": 0.0844,
"step": 233
},
{
"epoch": 4.59,
"learning_rate": 0.0001,
"loss": 0.1092,
"step": 234
},
{
"epoch": 4.6,
"learning_rate": 0.0001,
"loss": 0.0738,
"step": 235
},
{
"epoch": 4.62,
"learning_rate": 0.0001,
"loss": 0.0835,
"step": 236
},
{
"epoch": 4.64,
"learning_rate": 0.0001,
"loss": 0.0761,
"step": 237
},
{
"epoch": 4.66,
"learning_rate": 0.0001,
"loss": 0.0904,
"step": 238
},
{
"epoch": 4.68,
"learning_rate": 0.0001,
"loss": 0.0612,
"step": 239
},
{
"epoch": 4.7,
"learning_rate": 0.0001,
"loss": 0.0477,
"step": 240
},
{
"epoch": 4.72,
"learning_rate": 0.0001,
"loss": 0.0798,
"step": 241
},
{
"epoch": 4.74,
"learning_rate": 0.0001,
"loss": 0.08,
"step": 242
},
{
"epoch": 4.76,
"learning_rate": 0.0001,
"loss": 0.1122,
"step": 243
},
{
"epoch": 4.78,
"learning_rate": 0.0001,
"loss": 0.0503,
"step": 244
},
{
"epoch": 4.8,
"learning_rate": 0.0001,
"loss": 0.0767,
"step": 245
},
{
"epoch": 4.82,
"learning_rate": 0.0001,
"loss": 0.0774,
"step": 246
},
{
"epoch": 4.84,
"learning_rate": 0.0001,
"loss": 0.0825,
"step": 247
},
{
"epoch": 4.86,
"learning_rate": 0.0001,
"loss": 0.0837,
"step": 248
},
{
"epoch": 4.88,
"learning_rate": 0.0001,
"loss": 0.0862,
"step": 249
},
{
"epoch": 4.9,
"learning_rate": 0.0001,
"loss": 0.0849,
"step": 250
},
{
"epoch": 4.92,
"learning_rate": 0.0001,
"loss": 0.0776,
"step": 251
},
{
"epoch": 4.94,
"learning_rate": 0.0001,
"loss": 0.093,
"step": 252
},
{
"epoch": 4.96,
"learning_rate": 0.0001,
"loss": 0.087,
"step": 253
},
{
"epoch": 4.98,
"learning_rate": 0.0001,
"loss": 0.061,
"step": 254
},
{
"epoch": 5.0,
"learning_rate": 0.0001,
"loss": 0.0743,
"step": 255
},
{
"epoch": 5.0,
"eval_exact_match": 0.10810810810810811,
"eval_exec": 0.2972972972972973,
"eval_loss": 0.8123499155044556,
"eval_runtime": 338.5504,
"eval_samples_per_second": 0.546,
"step": 255
},
{
"epoch": 5.02,
"learning_rate": 0.0001,
"loss": 0.0863,
"step": 256
},
{
"epoch": 5.04,
"learning_rate": 0.0001,
"loss": 0.072,
"step": 257
},
{
"epoch": 5.06,
"learning_rate": 0.0001,
"loss": 0.0761,
"step": 258
},
{
"epoch": 5.08,
"learning_rate": 0.0001,
"loss": 0.0893,
"step": 259
},
{
"epoch": 5.1,
"learning_rate": 0.0001,
"loss": 0.0436,
"step": 260
},
{
"epoch": 5.12,
"learning_rate": 0.0001,
"loss": 0.0531,
"step": 261
},
{
"epoch": 5.14,
"learning_rate": 0.0001,
"loss": 0.0633,
"step": 262
},
{
"epoch": 5.16,
"learning_rate": 0.0001,
"loss": 0.0447,
"step": 263
},
{
"epoch": 5.18,
"learning_rate": 0.0001,
"loss": 0.0616,
"step": 264
},
{
"epoch": 5.2,
"learning_rate": 0.0001,
"loss": 0.054,
"step": 265
},
{
"epoch": 5.21,
"learning_rate": 0.0001,
"loss": 0.0436,
"step": 266
},
{
"epoch": 5.23,
"learning_rate": 0.0001,
"loss": 0.0656,
"step": 267
},
{
"epoch": 5.25,
"learning_rate": 0.0001,
"loss": 0.0832,
"step": 268
},
{
"epoch": 5.27,
"learning_rate": 0.0001,
"loss": 0.05,
"step": 269
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 0.0802,
"step": 270
},
{
"epoch": 5.31,
"learning_rate": 0.0001,
"loss": 0.0723,
"step": 271
},
{
"epoch": 5.33,
"learning_rate": 0.0001,
"loss": 0.053,
"step": 272
},
{
"epoch": 5.35,
"learning_rate": 0.0001,
"loss": 0.0647,
"step": 273
},
{
"epoch": 5.37,
"learning_rate": 0.0001,
"loss": 0.1065,
"step": 274
},
{
"epoch": 5.39,
"learning_rate": 0.0001,
"loss": 0.0699,
"step": 275
},
{
"epoch": 5.41,
"learning_rate": 0.0001,
"loss": 0.0565,
"step": 276
},
{
"epoch": 5.43,
"learning_rate": 0.0001,
"loss": 0.0588,
"step": 277
},
{
"epoch": 5.45,
"learning_rate": 0.0001,
"loss": 0.102,
"step": 278
},
{
"epoch": 5.47,
"learning_rate": 0.0001,
"loss": 0.0626,
"step": 279
},
{
"epoch": 5.49,
"learning_rate": 0.0001,
"loss": 0.074,
"step": 280
},
{
"epoch": 5.51,
"learning_rate": 0.0001,
"loss": 0.0585,
"step": 281
},
{
"epoch": 5.53,
"learning_rate": 0.0001,
"loss": 0.0528,
"step": 282
},
{
"epoch": 5.55,
"learning_rate": 0.0001,
"loss": 0.0449,
"step": 283
},
{
"epoch": 5.57,
"learning_rate": 0.0001,
"loss": 0.065,
"step": 284
},
{
"epoch": 5.59,
"learning_rate": 0.0001,
"loss": 0.081,
"step": 285
},
{
"epoch": 5.6,
"learning_rate": 0.0001,
"loss": 0.0508,
"step": 286
},
{
"epoch": 5.62,
"learning_rate": 0.0001,
"loss": 0.0585,
"step": 287
},
{
"epoch": 5.64,
"learning_rate": 0.0001,
"loss": 0.0638,
"step": 288
},
{
"epoch": 5.66,
"learning_rate": 0.0001,
"loss": 0.0684,
"step": 289
},
{
"epoch": 5.68,
"learning_rate": 0.0001,
"loss": 0.0937,
"step": 290
},
{
"epoch": 5.7,
"learning_rate": 0.0001,
"loss": 0.0809,
"step": 291
},
{
"epoch": 5.72,
"learning_rate": 0.0001,
"loss": 0.111,
"step": 292
},
{
"epoch": 5.74,
"learning_rate": 0.0001,
"loss": 0.0685,
"step": 293
},
{
"epoch": 5.76,
"learning_rate": 0.0001,
"loss": 0.0557,
"step": 294
},
{
"epoch": 5.78,
"learning_rate": 0.0001,
"loss": 0.0766,
"step": 295
},
{
"epoch": 5.8,
"learning_rate": 0.0001,
"loss": 0.0845,
"step": 296
},
{
"epoch": 5.82,
"learning_rate": 0.0001,
"loss": 0.0737,
"step": 297
},
{
"epoch": 5.84,
"learning_rate": 0.0001,
"loss": 0.0613,
"step": 298
},
{
"epoch": 5.86,
"learning_rate": 0.0001,
"loss": 0.0539,
"step": 299
},
{
"epoch": 5.88,
"learning_rate": 0.0001,
"loss": 0.0728,
"step": 300
},
{
"epoch": 5.9,
"learning_rate": 0.0001,
"loss": 0.0701,
"step": 301
},
{
"epoch": 5.92,
"learning_rate": 0.0001,
"loss": 0.0562,
"step": 302
},
{
"epoch": 5.94,
"learning_rate": 0.0001,
"loss": 0.0669,
"step": 303
},
{
"epoch": 5.96,
"learning_rate": 0.0001,
"loss": 0.0563,
"step": 304
},
{
"epoch": 5.98,
"learning_rate": 0.0001,
"loss": 0.074,
"step": 305
},
{
"epoch": 6.0,
"learning_rate": 0.0001,
"loss": 0.069,
"step": 306
},
{
"epoch": 6.0,
"eval_exact_match": 0.13513513513513514,
"eval_exec": 0.33513513513513515,
"eval_loss": 0.8501036167144775,
"eval_runtime": 1519.8613,
"eval_samples_per_second": 0.122,
"step": 306
},
{
"epoch": 6.02,
"learning_rate": 0.0001,
"loss": 0.0537,
"step": 307
},
{
"epoch": 6.04,
"learning_rate": 0.0001,
"loss": 0.0497,
"step": 308
},
{
"epoch": 6.06,
"learning_rate": 0.0001,
"loss": 0.0427,
"step": 309
},
{
"epoch": 6.08,
"learning_rate": 0.0001,
"loss": 0.052,
"step": 310
},
{
"epoch": 6.1,
"learning_rate": 0.0001,
"loss": 0.0474,
"step": 311
},
{
"epoch": 6.12,
"learning_rate": 0.0001,
"loss": 0.0393,
"step": 312
},
{
"epoch": 6.14,
"learning_rate": 0.0001,
"loss": 0.0645,
"step": 313
},
{
"epoch": 6.16,
"learning_rate": 0.0001,
"loss": 0.0714,
"step": 314
},
{
"epoch": 6.18,
"learning_rate": 0.0001,
"loss": 0.0482,
"step": 315
},
{
"epoch": 6.2,
"learning_rate": 0.0001,
"loss": 0.0549,
"step": 316
},
{
"epoch": 6.21,
"learning_rate": 0.0001,
"loss": 0.0428,
"step": 317
},
{
"epoch": 6.23,
"learning_rate": 0.0001,
"loss": 0.0466,
"step": 318
},
{
"epoch": 6.25,
"learning_rate": 0.0001,
"loss": 0.0678,
"step": 319
},
{
"epoch": 6.27,
"learning_rate": 0.0001,
"loss": 0.0538,
"step": 320
},
{
"epoch": 6.29,
"learning_rate": 0.0001,
"loss": 0.0489,
"step": 321
},
{
"epoch": 6.31,
"learning_rate": 0.0001,
"loss": 0.0485,
"step": 322
},
{
"epoch": 6.33,
"learning_rate": 0.0001,
"loss": 0.042,
"step": 323
},
{
"epoch": 6.35,
"learning_rate": 0.0001,
"loss": 0.0528,
"step": 324
},
{
"epoch": 6.37,
"learning_rate": 0.0001,
"loss": 0.0434,
"step": 325
},
{
"epoch": 6.39,
"learning_rate": 0.0001,
"loss": 0.0479,
"step": 326
},
{
"epoch": 6.41,
"learning_rate": 0.0001,
"loss": 0.0736,
"step": 327
},
{
"epoch": 6.43,
"learning_rate": 0.0001,
"loss": 0.0653,
"step": 328
},
{
"epoch": 6.45,
"learning_rate": 0.0001,
"loss": 0.0707,
"step": 329
},
{
"epoch": 6.47,
"learning_rate": 0.0001,
"loss": 0.0733,
"step": 330
},
{
"epoch": 6.49,
"learning_rate": 0.0001,
"loss": 0.0577,
"step": 331
},
{
"epoch": 6.51,
"learning_rate": 0.0001,
"loss": 0.0705,
"step": 332
},
{
"epoch": 6.53,
"learning_rate": 0.0001,
"loss": 0.0479,
"step": 333
},
{
"epoch": 6.55,
"learning_rate": 0.0001,
"loss": 0.0508,
"step": 334
},
{
"epoch": 6.57,
"learning_rate": 0.0001,
"loss": 0.0605,
"step": 335
},
{
"epoch": 6.59,
"learning_rate": 0.0001,
"loss": 0.0481,
"step": 336
},
{
"epoch": 6.6,
"learning_rate": 0.0001,
"loss": 0.067,
"step": 337
},
{
"epoch": 6.62,
"learning_rate": 0.0001,
"loss": 0.0542,
"step": 338
},
{
"epoch": 6.64,
"learning_rate": 0.0001,
"loss": 0.0675,
"step": 339
},
{
"epoch": 6.66,
"learning_rate": 0.0001,
"loss": 0.0712,
"step": 340
},
{
"epoch": 6.68,
"learning_rate": 0.0001,
"loss": 0.047,
"step": 341
},
{
"epoch": 6.7,
"learning_rate": 0.0001,
"loss": 0.0605,
"step": 342
},
{
"epoch": 6.72,
"learning_rate": 0.0001,
"loss": 0.0693,
"step": 343
},
{
"epoch": 6.74,
"learning_rate": 0.0001,
"loss": 0.0446,
"step": 344
},
{
"epoch": 6.76,
"learning_rate": 0.0001,
"loss": 0.0506,
"step": 345
},
{
"epoch": 6.78,
"learning_rate": 0.0001,
"loss": 0.057,
"step": 346
},
{
"epoch": 6.8,
"learning_rate": 0.0001,
"loss": 0.0466,
"step": 347
},
{
"epoch": 6.82,
"learning_rate": 0.0001,
"loss": 0.0581,
"step": 348
},
{
"epoch": 6.84,
"learning_rate": 0.0001,
"loss": 0.0767,
"step": 349
},
{
"epoch": 6.86,
"learning_rate": 0.0001,
"loss": 0.0901,
"step": 350
},
{
"epoch": 6.88,
"learning_rate": 0.0001,
"loss": 0.0677,
"step": 351
},
{
"epoch": 6.9,
"learning_rate": 0.0001,
"loss": 0.0808,
"step": 352
},
{
"epoch": 6.92,
"learning_rate": 0.0001,
"loss": 0.0956,
"step": 353
},
{
"epoch": 6.94,
"learning_rate": 0.0001,
"loss": 0.0849,
"step": 354
},
{
"epoch": 6.96,
"learning_rate": 0.0001,
"loss": 0.0601,
"step": 355
},
{
"epoch": 6.98,
"learning_rate": 0.0001,
"loss": 0.0515,
"step": 356
},
{
"epoch": 7.0,
"learning_rate": 0.0001,
"loss": 0.0757,
"step": 357
},
{
"epoch": 7.0,
"eval_exact_match": 0.14054054054054055,
"eval_exec": 0.32972972972972975,
"eval_loss": 0.9021496176719666,
"eval_runtime": 312.4965,
"eval_samples_per_second": 0.592,
"step": 357
},
{
"epoch": 7.02,
"learning_rate": 0.0001,
"loss": 0.0668,
"step": 358
},
{
"epoch": 7.04,
"learning_rate": 0.0001,
"loss": 0.0503,
"step": 359
},
{
"epoch": 7.06,
"learning_rate": 0.0001,
"loss": 0.067,
"step": 360
},
{
"epoch": 7.08,
"learning_rate": 0.0001,
"loss": 0.0533,
"step": 361
},
{
"epoch": 7.1,
"learning_rate": 0.0001,
"loss": 0.1201,
"step": 362
},
{
"epoch": 7.12,
"learning_rate": 0.0001,
"loss": 0.0584,
"step": 363
},
{
"epoch": 7.14,
"learning_rate": 0.0001,
"loss": 0.0365,
"step": 364
},
{
"epoch": 7.16,
"learning_rate": 0.0001,
"loss": 0.0595,
"step": 365
},
{
"epoch": 7.18,
"learning_rate": 0.0001,
"loss": 0.0533,
"step": 366
},
{
"epoch": 7.2,
"learning_rate": 0.0001,
"loss": 0.0596,
"step": 367
},
{
"epoch": 7.21,
"learning_rate": 0.0001,
"loss": 0.0575,
"step": 368
},
{
"epoch": 7.23,
"learning_rate": 0.0001,
"loss": 0.0344,
"step": 369
},
{
"epoch": 7.25,
"learning_rate": 0.0001,
"loss": 0.0666,
"step": 370
},
{
"epoch": 7.27,
"learning_rate": 0.0001,
"loss": 0.0566,
"step": 371
},
{
"epoch": 7.29,
"learning_rate": 0.0001,
"loss": 0.0398,
"step": 372
},
{
"epoch": 7.31,
"learning_rate": 0.0001,
"loss": 0.0357,
"step": 373
},
{
"epoch": 7.33,
"learning_rate": 0.0001,
"loss": 0.0421,
"step": 374
},
{
"epoch": 7.35,
"learning_rate": 0.0001,
"loss": 0.044,
"step": 375
},
{
"epoch": 7.37,
"learning_rate": 0.0001,
"loss": 0.0556,
"step": 376
},
{
"epoch": 7.39,
"learning_rate": 0.0001,
"loss": 0.0806,
"step": 377
},
{
"epoch": 7.41,
"learning_rate": 0.0001,
"loss": 0.0359,
"step": 378
},
{
"epoch": 7.43,
"learning_rate": 0.0001,
"loss": 0.0426,
"step": 379
},
{
"epoch": 7.45,
"learning_rate": 0.0001,
"loss": 0.0473,
"step": 380
},
{
"epoch": 7.47,
"learning_rate": 0.0001,
"loss": 0.053,
"step": 381
},
{
"epoch": 7.49,
"learning_rate": 0.0001,
"loss": 0.0444,
"step": 382
},
{
"epoch": 7.51,
"learning_rate": 0.0001,
"loss": 0.0435,
"step": 383
},
{
"epoch": 7.53,
"learning_rate": 0.0001,
"loss": 0.0634,
"step": 384
},
{
"epoch": 7.55,
"learning_rate": 0.0001,
"loss": 0.0648,
"step": 385
},
{
"epoch": 7.57,
"learning_rate": 0.0001,
"loss": 0.0493,
"step": 386
},
{
"epoch": 7.59,
"learning_rate": 0.0001,
"loss": 0.0451,
"step": 387
},
{
"epoch": 7.6,
"learning_rate": 0.0001,
"loss": 0.0397,
"step": 388
},
{
"epoch": 7.62,
"learning_rate": 0.0001,
"loss": 0.0419,
"step": 389
},
{
"epoch": 7.64,
"learning_rate": 0.0001,
"loss": 0.0652,
"step": 390
},
{
"epoch": 7.66,
"learning_rate": 0.0001,
"loss": 0.0402,
"step": 391
},
{
"epoch": 7.68,
"learning_rate": 0.0001,
"loss": 0.0633,
"step": 392
},
{
"epoch": 7.7,
"learning_rate": 0.0001,
"loss": 0.0777,
"step": 393
},
{
"epoch": 7.72,
"learning_rate": 0.0001,
"loss": 0.0343,
"step": 394
},
{
"epoch": 7.74,
"learning_rate": 0.0001,
"loss": 0.0414,
"step": 395
},
{
"epoch": 7.76,
"learning_rate": 0.0001,
"loss": 0.0611,
"step": 396
},
{
"epoch": 7.78,
"learning_rate": 0.0001,
"loss": 0.077,
"step": 397
},
{
"epoch": 7.8,
"learning_rate": 0.0001,
"loss": 0.0386,
"step": 398
},
{
"epoch": 7.82,
"learning_rate": 0.0001,
"loss": 0.0458,
"step": 399
},
{
"epoch": 7.84,
"learning_rate": 0.0001,
"loss": 0.0526,
"step": 400
},
{
"epoch": 7.86,
"learning_rate": 0.0001,
"loss": 0.0425,
"step": 401
},
{
"epoch": 7.88,
"learning_rate": 0.0001,
"loss": 0.0398,
"step": 402
},
{
"epoch": 7.9,
"learning_rate": 0.0001,
"loss": 0.0571,
"step": 403
},
{
"epoch": 7.92,
"learning_rate": 0.0001,
"loss": 0.0599,
"step": 404
},
{
"epoch": 7.94,
"learning_rate": 0.0001,
"loss": 0.0618,
"step": 405
},
{
"epoch": 7.96,
"learning_rate": 0.0001,
"loss": 0.0511,
"step": 406
},
{
"epoch": 7.98,
"learning_rate": 0.0001,
"loss": 0.0543,
"step": 407
},
{
"epoch": 8.0,
"learning_rate": 0.0001,
"loss": 0.0749,
"step": 408
},
{
"epoch": 8.0,
"eval_exact_match": 0.10810810810810811,
"eval_exec": 0.32972972972972975,
"eval_loss": 0.8674821257591248,
"eval_runtime": 368.5441,
"eval_samples_per_second": 0.502,
"step": 408
},
{
"epoch": 8.02,
"learning_rate": 0.0001,
"loss": 0.0456,
"step": 409
},
{
"epoch": 8.04,
"learning_rate": 0.0001,
"loss": 0.0526,
"step": 410
},
{
"epoch": 8.06,
"learning_rate": 0.0001,
"loss": 0.0347,
"step": 411
},
{
"epoch": 8.08,
"learning_rate": 0.0001,
"loss": 0.0592,
"step": 412
},
{
"epoch": 8.1,
"learning_rate": 0.0001,
"loss": 0.0397,
"step": 413
},
{
"epoch": 8.12,
"learning_rate": 0.0001,
"loss": 0.048,
"step": 414
},
{
"epoch": 8.14,
"learning_rate": 0.0001,
"loss": 0.0408,
"step": 415
},
{
"epoch": 8.16,
"learning_rate": 0.0001,
"loss": 0.0322,
"step": 416
},
{
"epoch": 8.18,
"learning_rate": 0.0001,
"loss": 0.0285,
"step": 417
},
{
"epoch": 8.2,
"learning_rate": 0.0001,
"loss": 0.0287,
"step": 418
},
{
"epoch": 8.21,
"learning_rate": 0.0001,
"loss": 0.0205,
"step": 419
},
{
"epoch": 8.23,
"learning_rate": 0.0001,
"loss": 0.0529,
"step": 420
},
{
"epoch": 8.25,
"learning_rate": 0.0001,
"loss": 0.0378,
"step": 421
},
{
"epoch": 8.27,
"learning_rate": 0.0001,
"loss": 0.0456,
"step": 422
},
{
"epoch": 8.29,
"learning_rate": 0.0001,
"loss": 0.025,
"step": 423
},
{
"epoch": 8.31,
"learning_rate": 0.0001,
"loss": 0.0463,
"step": 424
},
{
"epoch": 8.33,
"learning_rate": 0.0001,
"loss": 0.0374,
"step": 425
},
{
"epoch": 8.35,
"learning_rate": 0.0001,
"loss": 0.0342,
"step": 426
},
{
"epoch": 8.37,
"learning_rate": 0.0001,
"loss": 0.0459,
"step": 427
},
{
"epoch": 8.39,
"learning_rate": 0.0001,
"loss": 0.0277,
"step": 428
},
{
"epoch": 8.41,
"learning_rate": 0.0001,
"loss": 0.0339,
"step": 429
},
{
"epoch": 8.43,
"learning_rate": 0.0001,
"loss": 0.0441,
"step": 430
},
{
"epoch": 8.45,
"learning_rate": 0.0001,
"loss": 0.0517,
"step": 431
},
{
"epoch": 8.47,
"learning_rate": 0.0001,
"loss": 0.0442,
"step": 432
},
{
"epoch": 8.49,
"learning_rate": 0.0001,
"loss": 0.0444,
"step": 433
},
{
"epoch": 8.51,
"learning_rate": 0.0001,
"loss": 0.0432,
"step": 434
},
{
"epoch": 8.53,
"learning_rate": 0.0001,
"loss": 0.0239,
"step": 435
},
{
"epoch": 8.55,
"learning_rate": 0.0001,
"loss": 0.053,
"step": 436
},
{
"epoch": 8.57,
"learning_rate": 0.0001,
"loss": 0.0362,
"step": 437
},
{
"epoch": 8.59,
"learning_rate": 0.0001,
"loss": 0.0419,
"step": 438
},
{
"epoch": 8.6,
"learning_rate": 0.0001,
"loss": 0.0484,
"step": 439
},
{
"epoch": 8.62,
"learning_rate": 0.0001,
"loss": 0.0437,
"step": 440
},
{
"epoch": 8.64,
"learning_rate": 0.0001,
"loss": 0.0364,
"step": 441
},
{
"epoch": 8.66,
"learning_rate": 0.0001,
"loss": 0.0469,
"step": 442
},
{
"epoch": 8.68,
"learning_rate": 0.0001,
"loss": 0.053,
"step": 443
},
{
"epoch": 8.7,
"learning_rate": 0.0001,
"loss": 0.0433,
"step": 444
},
{
"epoch": 8.72,
"learning_rate": 0.0001,
"loss": 0.0624,
"step": 445
},
{
"epoch": 8.74,
"learning_rate": 0.0001,
"loss": 0.0528,
"step": 446
},
{
"epoch": 8.76,
"learning_rate": 0.0001,
"loss": 0.0406,
"step": 447
},
{
"epoch": 8.78,
"learning_rate": 0.0001,
"loss": 0.0657,
"step": 448
},
{
"epoch": 8.8,
"learning_rate": 0.0001,
"loss": 0.0569,
"step": 449
},
{
"epoch": 8.82,
"learning_rate": 0.0001,
"loss": 0.058,
"step": 450
},
{
"epoch": 8.84,
"learning_rate": 0.0001,
"loss": 0.0773,
"step": 451
},
{
"epoch": 8.86,
"learning_rate": 0.0001,
"loss": 0.0508,
"step": 452
},
{
"epoch": 8.88,
"learning_rate": 0.0001,
"loss": 0.0578,
"step": 453
},
{
"epoch": 8.9,
"learning_rate": 0.0001,
"loss": 0.057,
"step": 454
},
{
"epoch": 8.92,
"learning_rate": 0.0001,
"loss": 0.0436,
"step": 455
},
{
"epoch": 8.94,
"learning_rate": 0.0001,
"loss": 0.0683,
"step": 456
},
{
"epoch": 8.96,
"learning_rate": 0.0001,
"loss": 0.055,
"step": 457
},
{
"epoch": 8.98,
"learning_rate": 0.0001,
"loss": 0.0458,
"step": 458
},
{
"epoch": 9.0,
"learning_rate": 0.0001,
"loss": 0.0328,
"step": 459
},
{
"epoch": 9.0,
"eval_exact_match": 0.14594594594594595,
"eval_exec": 0.2756756756756757,
"eval_loss": 0.8724486231803894,
"eval_runtime": 400.1896,
"eval_samples_per_second": 0.462,
"step": 459
},
{
"epoch": 9.02,
"learning_rate": 0.0001,
"loss": 0.046,
"step": 460
},
{
"epoch": 9.04,
"learning_rate": 0.0001,
"loss": 0.0311,
"step": 461
},
{
"epoch": 9.06,
"learning_rate": 0.0001,
"loss": 0.0366,
"step": 462
},
{
"epoch": 9.08,
"learning_rate": 0.0001,
"loss": 0.0417,
"step": 463
},
{
"epoch": 9.1,
"learning_rate": 0.0001,
"loss": 0.0335,
"step": 464
},
{
"epoch": 9.12,
"learning_rate": 0.0001,
"loss": 0.0427,
"step": 465
},
{
"epoch": 9.14,
"learning_rate": 0.0001,
"loss": 0.0376,
"step": 466
},
{
"epoch": 9.16,
"learning_rate": 0.0001,
"loss": 0.0579,
"step": 467
},
{
"epoch": 9.18,
"learning_rate": 0.0001,
"loss": 0.0529,
"step": 468
},
{
"epoch": 9.2,
"learning_rate": 0.0001,
"loss": 0.035,
"step": 469
},
{
"epoch": 9.21,
"learning_rate": 0.0001,
"loss": 0.0299,
"step": 470
},
{
"epoch": 9.23,
"learning_rate": 0.0001,
"loss": 0.0461,
"step": 471
},
{
"epoch": 9.25,
"learning_rate": 0.0001,
"loss": 0.042,
"step": 472
},
{
"epoch": 9.27,
"learning_rate": 0.0001,
"loss": 0.0417,
"step": 473
},
{
"epoch": 9.29,
"learning_rate": 0.0001,
"loss": 0.05,
"step": 474
},
{
"epoch": 9.31,
"learning_rate": 0.0001,
"loss": 0.0348,
"step": 475
},
{
"epoch": 9.33,
"learning_rate": 0.0001,
"loss": 0.034,
"step": 476
},
{
"epoch": 9.35,
"learning_rate": 0.0001,
"loss": 0.0328,
"step": 477
},
{
"epoch": 9.37,
"learning_rate": 0.0001,
"loss": 0.0332,
"step": 478
},
{
"epoch": 9.39,
"learning_rate": 0.0001,
"loss": 0.0436,
"step": 479
},
{
"epoch": 9.41,
"learning_rate": 0.0001,
"loss": 0.0594,
"step": 480
},
{
"epoch": 9.43,
"learning_rate": 0.0001,
"loss": 0.0345,
"step": 481
},
{
"epoch": 9.45,
"learning_rate": 0.0001,
"loss": 0.0448,
"step": 482
},
{
"epoch": 9.47,
"learning_rate": 0.0001,
"loss": 0.0343,
"step": 483
},
{
"epoch": 9.49,
"learning_rate": 0.0001,
"loss": 0.0515,
"step": 484
},
{
"epoch": 9.51,
"learning_rate": 0.0001,
"loss": 0.0417,
"step": 485
},
{
"epoch": 9.53,
"learning_rate": 0.0001,
"loss": 0.0406,
"step": 486
},
{
"epoch": 9.55,
"learning_rate": 0.0001,
"loss": 0.0411,
"step": 487
},
{
"epoch": 9.57,
"learning_rate": 0.0001,
"loss": 0.0349,
"step": 488
},
{
"epoch": 9.59,
"learning_rate": 0.0001,
"loss": 0.035,
"step": 489
},
{
"epoch": 9.6,
"learning_rate": 0.0001,
"loss": 0.0606,
"step": 490
},
{
"epoch": 9.62,
"learning_rate": 0.0001,
"loss": 0.0376,
"step": 491
},
{
"epoch": 9.64,
"learning_rate": 0.0001,
"loss": 0.0422,
"step": 492
},
{
"epoch": 9.66,
"learning_rate": 0.0001,
"loss": 0.05,
"step": 493
},
{
"epoch": 9.68,
"learning_rate": 0.0001,
"loss": 0.0443,
"step": 494
},
{
"epoch": 9.7,
"learning_rate": 0.0001,
"loss": 0.0373,
"step": 495
},
{
"epoch": 9.72,
"learning_rate": 0.0001,
"loss": 0.0242,
"step": 496
},
{
"epoch": 9.74,
"learning_rate": 0.0001,
"loss": 0.0222,
"step": 497
},
{
"epoch": 9.76,
"learning_rate": 0.0001,
"loss": 0.0336,
"step": 498
},
{
"epoch": 9.78,
"learning_rate": 0.0001,
"loss": 0.0474,
"step": 499
},
{
"epoch": 9.8,
"learning_rate": 0.0001,
"loss": 0.0355,
"step": 500
},
{
"epoch": 9.82,
"learning_rate": 0.0001,
"loss": 0.0341,
"step": 501
},
{
"epoch": 9.84,
"learning_rate": 0.0001,
"loss": 0.0453,
"step": 502
},
{
"epoch": 9.86,
"learning_rate": 0.0001,
"loss": 0.0555,
"step": 503
},
{
"epoch": 9.88,
"learning_rate": 0.0001,
"loss": 0.0519,
"step": 504
},
{
"epoch": 9.9,
"learning_rate": 0.0001,
"loss": 0.0333,
"step": 505
},
{
"epoch": 9.92,
"learning_rate": 0.0001,
"loss": 0.0362,
"step": 506
},
{
"epoch": 9.94,
"learning_rate": 0.0001,
"loss": 0.0587,
"step": 507
},
{
"epoch": 9.96,
"learning_rate": 0.0001,
"loss": 0.0376,
"step": 508
},
{
"epoch": 9.98,
"learning_rate": 0.0001,
"loss": 0.0456,
"step": 509
},
{
"epoch": 10.0,
"learning_rate": 0.0001,
"loss": 0.0529,
"step": 510
},
{
"epoch": 10.0,
"eval_exact_match": 0.12972972972972974,
"eval_exec": 0.2972972972972973,
"eval_loss": 0.896236002445221,
"eval_runtime": 316.3604,
"eval_samples_per_second": 0.585,
"step": 510
},
{
"epoch": 10.02,
"learning_rate": 0.0001,
"loss": 0.0501,
"step": 511
},
{
"epoch": 10.04,
"learning_rate": 0.0001,
"loss": 0.0374,
"step": 512
},
{
"epoch": 10.06,
"learning_rate": 0.0001,
"loss": 0.0465,
"step": 513
},
{
"epoch": 10.08,
"learning_rate": 0.0001,
"loss": 0.0466,
"step": 514
},
{
"epoch": 10.1,
"learning_rate": 0.0001,
"loss": 0.0528,
"step": 515
},
{
"epoch": 10.12,
"learning_rate": 0.0001,
"loss": 0.0373,
"step": 516
},
{
"epoch": 10.14,
"learning_rate": 0.0001,
"loss": 0.044,
"step": 517
},
{
"epoch": 10.16,
"learning_rate": 0.0001,
"loss": 0.0523,
"step": 518
},
{
"epoch": 10.18,
"learning_rate": 0.0001,
"loss": 0.0296,
"step": 519
},
{
"epoch": 10.2,
"learning_rate": 0.0001,
"loss": 0.0236,
"step": 520
},
{
"epoch": 10.21,
"learning_rate": 0.0001,
"loss": 0.0427,
"step": 521
},
{
"epoch": 10.23,
"learning_rate": 0.0001,
"loss": 0.0234,
"step": 522
},
{
"epoch": 10.25,
"learning_rate": 0.0001,
"loss": 0.0477,
"step": 523
},
{
"epoch": 10.27,
"learning_rate": 0.0001,
"loss": 0.0487,
"step": 524
},
{
"epoch": 10.29,
"learning_rate": 0.0001,
"loss": 0.0269,
"step": 525
},
{
"epoch": 10.31,
"learning_rate": 0.0001,
"loss": 0.047,
"step": 526
},
{
"epoch": 10.33,
"learning_rate": 0.0001,
"loss": 0.0364,
"step": 527
},
{
"epoch": 10.35,
"learning_rate": 0.0001,
"loss": 0.0455,
"step": 528
},
{
"epoch": 10.37,
"learning_rate": 0.0001,
"loss": 0.08,
"step": 529
},
{
"epoch": 10.39,
"learning_rate": 0.0001,
"loss": 0.0421,
"step": 530
},
{
"epoch": 10.41,
"learning_rate": 0.0001,
"loss": 0.0347,
"step": 531
},
{
"epoch": 10.43,
"learning_rate": 0.0001,
"loss": 0.0491,
"step": 532
},
{
"epoch": 10.45,
"learning_rate": 0.0001,
"loss": 0.0381,
"step": 533
},
{
"epoch": 10.47,
"learning_rate": 0.0001,
"loss": 0.034,
"step": 534
},
{
"epoch": 10.49,
"learning_rate": 0.0001,
"loss": 0.04,
"step": 535
},
{
"epoch": 10.51,
"learning_rate": 0.0001,
"loss": 0.0337,
"step": 536
},
{
"epoch": 10.53,
"learning_rate": 0.0001,
"loss": 0.035,
"step": 537
},
{
"epoch": 10.55,
"learning_rate": 0.0001,
"loss": 0.0252,
"step": 538
},
{
"epoch": 10.57,
"learning_rate": 0.0001,
"loss": 0.0436,
"step": 539
},
{
"epoch": 10.59,
"learning_rate": 0.0001,
"loss": 0.0568,
"step": 540
},
{
"epoch": 10.6,
"learning_rate": 0.0001,
"loss": 0.0419,
"step": 541
},
{
"epoch": 10.62,
"learning_rate": 0.0001,
"loss": 0.0336,
"step": 542
},
{
"epoch": 10.64,
"learning_rate": 0.0001,
"loss": 0.0485,
"step": 543
},
{
"epoch": 10.66,
"learning_rate": 0.0001,
"loss": 0.0375,
"step": 544
},
{
"epoch": 10.68,
"learning_rate": 0.0001,
"loss": 0.0448,
"step": 545
},
{
"epoch": 10.7,
"learning_rate": 0.0001,
"loss": 0.0369,
"step": 546
},
{
"epoch": 10.72,
"learning_rate": 0.0001,
"loss": 0.0262,
"step": 547
},
{
"epoch": 10.74,
"learning_rate": 0.0001,
"loss": 0.0393,
"step": 548
},
{
"epoch": 10.76,
"learning_rate": 0.0001,
"loss": 0.0391,
"step": 549
},
{
"epoch": 10.78,
"learning_rate": 0.0001,
"loss": 0.0355,
"step": 550
},
{
"epoch": 10.8,
"learning_rate": 0.0001,
"loss": 0.0324,
"step": 551
},
{
"epoch": 10.82,
"learning_rate": 0.0001,
"loss": 0.0331,
"step": 552
},
{
"epoch": 10.84,
"learning_rate": 0.0001,
"loss": 0.032,
"step": 553
},
{
"epoch": 10.86,
"learning_rate": 0.0001,
"loss": 0.0583,
"step": 554
},
{
"epoch": 10.88,
"learning_rate": 0.0001,
"loss": 0.0502,
"step": 555
},
{
"epoch": 10.9,
"learning_rate": 0.0001,
"loss": 0.0329,
"step": 556
},
{
"epoch": 10.92,
"learning_rate": 0.0001,
"loss": 0.0305,
"step": 557
},
{
"epoch": 10.94,
"learning_rate": 0.0001,
"loss": 0.0455,
"step": 558
},
{
"epoch": 10.96,
"learning_rate": 0.0001,
"loss": 0.0303,
"step": 559
},
{
"epoch": 10.98,
"learning_rate": 0.0001,
"loss": 0.0447,
"step": 560
},
{
"epoch": 11.0,
"learning_rate": 0.0001,
"loss": 0.029,
"step": 561
},
{
"epoch": 11.0,
"eval_exact_match": 0.14054054054054055,
"eval_exec": 0.2972972972972973,
"eval_loss": 0.9216025471687317,
"eval_runtime": 384.0619,
"eval_samples_per_second": 0.482,
"step": 561
},
{
"epoch": 11.02,
"learning_rate": 0.0001,
"loss": 0.0334,
"step": 562
},
{
"epoch": 11.04,
"learning_rate": 0.0001,
"loss": 0.0251,
"step": 563
},
{
"epoch": 11.06,
"learning_rate": 0.0001,
"loss": 0.0257,
"step": 564
},
{
"epoch": 11.08,
"learning_rate": 0.0001,
"loss": 0.0294,
"step": 565
},
{
"epoch": 11.1,
"learning_rate": 0.0001,
"loss": 0.0315,
"step": 566
},
{
"epoch": 11.12,
"learning_rate": 0.0001,
"loss": 0.0292,
"step": 567
},
{
"epoch": 11.14,
"learning_rate": 0.0001,
"loss": 0.053,
"step": 568
},
{
"epoch": 11.16,
"learning_rate": 0.0001,
"loss": 0.0207,
"step": 569
},
{
"epoch": 11.18,
"learning_rate": 0.0001,
"loss": 0.0299,
"step": 570
},
{
"epoch": 11.2,
"learning_rate": 0.0001,
"loss": 0.0312,
"step": 571
},
{
"epoch": 11.21,
"learning_rate": 0.0001,
"loss": 0.0277,
"step": 572
},
{
"epoch": 11.23,
"learning_rate": 0.0001,
"loss": 0.0168,
"step": 573
},
{
"epoch": 11.25,
"learning_rate": 0.0001,
"loss": 0.0601,
"step": 574
},
{
"epoch": 11.27,
"learning_rate": 0.0001,
"loss": 0.0158,
"step": 575
},
{
"epoch": 11.29,
"learning_rate": 0.0001,
"loss": 0.0417,
"step": 576
},
{
"epoch": 11.31,
"learning_rate": 0.0001,
"loss": 0.0443,
"step": 577
},
{
"epoch": 11.33,
"learning_rate": 0.0001,
"loss": 0.0416,
"step": 578
},
{
"epoch": 11.35,
"learning_rate": 0.0001,
"loss": 0.0322,
"step": 579
},
{
"epoch": 11.37,
"learning_rate": 0.0001,
"loss": 0.0311,
"step": 580
},
{
"epoch": 11.39,
"learning_rate": 0.0001,
"loss": 0.0314,
"step": 581
},
{
"epoch": 11.41,
"learning_rate": 0.0001,
"loss": 0.0155,
"step": 582
},
{
"epoch": 11.43,
"learning_rate": 0.0001,
"loss": 0.038,
"step": 583
},
{
"epoch": 11.45,
"learning_rate": 0.0001,
"loss": 0.0199,
"step": 584
},
{
"epoch": 11.47,
"learning_rate": 0.0001,
"loss": 0.0171,
"step": 585
},
{
"epoch": 11.49,
"learning_rate": 0.0001,
"loss": 0.0294,
"step": 586
},
{
"epoch": 11.51,
"learning_rate": 0.0001,
"loss": 0.0518,
"step": 587
},
{
"epoch": 11.53,
"learning_rate": 0.0001,
"loss": 0.0433,
"step": 588
},
{
"epoch": 11.55,
"learning_rate": 0.0001,
"loss": 0.0344,
"step": 589
},
{
"epoch": 11.57,
"learning_rate": 0.0001,
"loss": 0.0308,
"step": 590
},
{
"epoch": 11.59,
"learning_rate": 0.0001,
"loss": 0.0227,
"step": 591
},
{
"epoch": 11.6,
"learning_rate": 0.0001,
"loss": 0.0212,
"step": 592
},
{
"epoch": 11.62,
"learning_rate": 0.0001,
"loss": 0.0274,
"step": 593
},
{
"epoch": 11.64,
"learning_rate": 0.0001,
"loss": 0.0321,
"step": 594
},
{
"epoch": 11.66,
"learning_rate": 0.0001,
"loss": 0.039,
"step": 595
},
{
"epoch": 11.68,
"learning_rate": 0.0001,
"loss": 0.0324,
"step": 596
},
{
"epoch": 11.7,
"learning_rate": 0.0001,
"loss": 0.0369,
"step": 597
},
{
"epoch": 11.72,
"learning_rate": 0.0001,
"loss": 0.0529,
"step": 598
},
{
"epoch": 11.74,
"learning_rate": 0.0001,
"loss": 0.0418,
"step": 599
},
{
"epoch": 11.76,
"learning_rate": 0.0001,
"loss": 0.048,
"step": 600
},
{
"epoch": 11.78,
"learning_rate": 0.0001,
"loss": 0.0487,
"step": 601
},
{
"epoch": 11.8,
"learning_rate": 0.0001,
"loss": 0.0352,
"step": 602
},
{
"epoch": 11.82,
"learning_rate": 0.0001,
"loss": 0.0192,
"step": 603
},
{
"epoch": 11.84,
"learning_rate": 0.0001,
"loss": 0.0515,
"step": 604
},
{
"epoch": 11.86,
"learning_rate": 0.0001,
"loss": 0.035,
"step": 605
},
{
"epoch": 11.88,
"learning_rate": 0.0001,
"loss": 0.0677,
"step": 606
},
{
"epoch": 11.9,
"learning_rate": 0.0001,
"loss": 0.0212,
"step": 607
},
{
"epoch": 11.92,
"learning_rate": 0.0001,
"loss": 0.0309,
"step": 608
},
{
"epoch": 11.94,
"learning_rate": 0.0001,
"loss": 0.0366,
"step": 609
},
{
"epoch": 11.96,
"learning_rate": 0.0001,
"loss": 0.0333,
"step": 610
},
{
"epoch": 11.98,
"learning_rate": 0.0001,
"loss": 0.0214,
"step": 611
},
{
"epoch": 12.0,
"learning_rate": 0.0001,
"loss": 0.0417,
"step": 612
},
{
"epoch": 12.0,
"eval_exact_match": 0.11351351351351352,
"eval_exec": 0.3027027027027027,
"eval_loss": 0.942590057849884,
"eval_runtime": 333.5297,
"eval_samples_per_second": 0.555,
"step": 612
},
{
"epoch": 12.02,
"learning_rate": 0.0001,
"loss": 0.0389,
"step": 613
},
{
"epoch": 12.04,
"learning_rate": 0.0001,
"loss": 0.0317,
"step": 614
},
{
"epoch": 12.06,
"learning_rate": 0.0001,
"loss": 0.0284,
"step": 615
},
{
"epoch": 12.08,
"learning_rate": 0.0001,
"loss": 0.0265,
"step": 616
},
{
"epoch": 12.1,
"learning_rate": 0.0001,
"loss": 0.0277,
"step": 617
},
{
"epoch": 12.12,
"learning_rate": 0.0001,
"loss": 0.022,
"step": 618
},
{
"epoch": 12.14,
"learning_rate": 0.0001,
"loss": 0.0232,
"step": 619
},
{
"epoch": 12.16,
"learning_rate": 0.0001,
"loss": 0.0186,
"step": 620
},
{
"epoch": 12.18,
"learning_rate": 0.0001,
"loss": 0.0345,
"step": 621
},
{
"epoch": 12.2,
"learning_rate": 0.0001,
"loss": 0.0263,
"step": 622
},
{
"epoch": 12.21,
"learning_rate": 0.0001,
"loss": 0.0134,
"step": 623
},
{
"epoch": 12.23,
"learning_rate": 0.0001,
"loss": 0.0217,
"step": 624
},
{
"epoch": 12.25,
"learning_rate": 0.0001,
"loss": 0.0393,
"step": 625
},
{
"epoch": 12.27,
"learning_rate": 0.0001,
"loss": 0.046,
"step": 626
},
{
"epoch": 12.29,
"learning_rate": 0.0001,
"loss": 0.0287,
"step": 627
},
{
"epoch": 12.31,
"learning_rate": 0.0001,
"loss": 0.0319,
"step": 628
},
{
"epoch": 12.33,
"learning_rate": 0.0001,
"loss": 0.0221,
"step": 629
},
{
"epoch": 12.35,
"learning_rate": 0.0001,
"loss": 0.0243,
"step": 630
},
{
"epoch": 12.37,
"learning_rate": 0.0001,
"loss": 0.0411,
"step": 631
},
{
"epoch": 12.39,
"learning_rate": 0.0001,
"loss": 0.0377,
"step": 632
},
{
"epoch": 12.41,
"learning_rate": 0.0001,
"loss": 0.0273,
"step": 633
},
{
"epoch": 12.43,
"learning_rate": 0.0001,
"loss": 0.0136,
"step": 634
},
{
"epoch": 12.45,
"learning_rate": 0.0001,
"loss": 0.0216,
"step": 635
},
{
"epoch": 12.47,
"learning_rate": 0.0001,
"loss": 0.0174,
"step": 636
},
{
"epoch": 12.49,
"learning_rate": 0.0001,
"loss": 0.0357,
"step": 637
},
{
"epoch": 12.51,
"learning_rate": 0.0001,
"loss": 0.0382,
"step": 638
},
{
"epoch": 12.53,
"learning_rate": 0.0001,
"loss": 0.0357,
"step": 639
},
{
"epoch": 12.55,
"learning_rate": 0.0001,
"loss": 0.0276,
"step": 640
},
{
"epoch": 12.57,
"learning_rate": 0.0001,
"loss": 0.0212,
"step": 641
},
{
"epoch": 12.59,
"learning_rate": 0.0001,
"loss": 0.0395,
"step": 642
},
{
"epoch": 12.6,
"learning_rate": 0.0001,
"loss": 0.0372,
"step": 643
},
{
"epoch": 12.62,
"learning_rate": 0.0001,
"loss": 0.0262,
"step": 644
},
{
"epoch": 12.64,
"learning_rate": 0.0001,
"loss": 0.0269,
"step": 645
},
{
"epoch": 12.66,
"learning_rate": 0.0001,
"loss": 0.046,
"step": 646
},
{
"epoch": 12.68,
"learning_rate": 0.0001,
"loss": 0.0305,
"step": 647
},
{
"epoch": 12.7,
"learning_rate": 0.0001,
"loss": 0.037,
"step": 648
},
{
"epoch": 12.72,
"learning_rate": 0.0001,
"loss": 0.0189,
"step": 649
},
{
"epoch": 12.74,
"learning_rate": 0.0001,
"loss": 0.041,
"step": 650
},
{
"epoch": 12.76,
"learning_rate": 0.0001,
"loss": 0.0353,
"step": 651
},
{
"epoch": 12.78,
"learning_rate": 0.0001,
"loss": 0.029,
"step": 652
},
{
"epoch": 12.8,
"learning_rate": 0.0001,
"loss": 0.0415,
"step": 653
},
{
"epoch": 12.82,
"learning_rate": 0.0001,
"loss": 0.0437,
"step": 654
},
{
"epoch": 12.84,
"learning_rate": 0.0001,
"loss": 0.0304,
"step": 655
},
{
"epoch": 12.86,
"learning_rate": 0.0001,
"loss": 0.0357,
"step": 656
},
{
"epoch": 12.88,
"learning_rate": 0.0001,
"loss": 0.0306,
"step": 657
},
{
"epoch": 12.9,
"learning_rate": 0.0001,
"loss": 0.0288,
"step": 658
},
{
"epoch": 12.92,
"learning_rate": 0.0001,
"loss": 0.0314,
"step": 659
},
{
"epoch": 12.94,
"learning_rate": 0.0001,
"loss": 0.0418,
"step": 660
},
{
"epoch": 12.96,
"learning_rate": 0.0001,
"loss": 0.0244,
"step": 661
},
{
"epoch": 12.98,
"learning_rate": 0.0001,
"loss": 0.044,
"step": 662
},
{
"epoch": 13.0,
"learning_rate": 0.0001,
"loss": 0.0214,
"step": 663
},
{
"epoch": 13.0,
"eval_exact_match": 0.11891891891891893,
"eval_exec": 0.32432432432432434,
"eval_loss": 1.0238938331604004,
"eval_runtime": 1525.5229,
"eval_samples_per_second": 0.121,
"step": 663
},
{
"epoch": 13.02,
"learning_rate": 0.0001,
"loss": 0.0202,
"step": 664
},
{
"epoch": 13.04,
"learning_rate": 0.0001,
"loss": 0.0164,
"step": 665
},
{
"epoch": 13.06,
"learning_rate": 0.0001,
"loss": 0.039,
"step": 666
},
{
"epoch": 13.08,
"learning_rate": 0.0001,
"loss": 0.0223,
"step": 667
},
{
"epoch": 13.1,
"learning_rate": 0.0001,
"loss": 0.0209,
"step": 668
},
{
"epoch": 13.12,
"learning_rate": 0.0001,
"loss": 0.0459,
"step": 669
},
{
"epoch": 13.14,
"learning_rate": 0.0001,
"loss": 0.0238,
"step": 670
},
{
"epoch": 13.16,
"learning_rate": 0.0001,
"loss": 0.0248,
"step": 671
},
{
"epoch": 13.18,
"learning_rate": 0.0001,
"loss": 0.0233,
"step": 672
},
{
"epoch": 13.2,
"learning_rate": 0.0001,
"loss": 0.0354,
"step": 673
},
{
"epoch": 13.21,
"learning_rate": 0.0001,
"loss": 0.0212,
"step": 674
},
{
"epoch": 13.23,
"learning_rate": 0.0001,
"loss": 0.0177,
"step": 675
},
{
"epoch": 13.25,
"learning_rate": 0.0001,
"loss": 0.0243,
"step": 676
},
{
"epoch": 13.27,
"learning_rate": 0.0001,
"loss": 0.0297,
"step": 677
},
{
"epoch": 13.29,
"learning_rate": 0.0001,
"loss": 0.0308,
"step": 678
},
{
"epoch": 13.31,
"learning_rate": 0.0001,
"loss": 0.0423,
"step": 679
},
{
"epoch": 13.33,
"learning_rate": 0.0001,
"loss": 0.029,
"step": 680
},
{
"epoch": 13.35,
"learning_rate": 0.0001,
"loss": 0.0227,
"step": 681
},
{
"epoch": 13.37,
"learning_rate": 0.0001,
"loss": 0.0284,
"step": 682
},
{
"epoch": 13.39,
"learning_rate": 0.0001,
"loss": 0.0275,
"step": 683
},
{
"epoch": 13.41,
"learning_rate": 0.0001,
"loss": 0.0292,
"step": 684
},
{
"epoch": 13.43,
"learning_rate": 0.0001,
"loss": 0.0223,
"step": 685
},
{
"epoch": 13.45,
"learning_rate": 0.0001,
"loss": 0.0311,
"step": 686
},
{
"epoch": 13.47,
"learning_rate": 0.0001,
"loss": 0.0206,
"step": 687
},
{
"epoch": 13.49,
"learning_rate": 0.0001,
"loss": 0.0173,
"step": 688
},
{
"epoch": 13.51,
"learning_rate": 0.0001,
"loss": 0.0419,
"step": 689
},
{
"epoch": 13.53,
"learning_rate": 0.0001,
"loss": 0.0279,
"step": 690
},
{
"epoch": 13.55,
"learning_rate": 0.0001,
"loss": 0.0221,
"step": 691
},
{
"epoch": 13.57,
"learning_rate": 0.0001,
"loss": 0.0269,
"step": 692
},
{
"epoch": 13.59,
"learning_rate": 0.0001,
"loss": 0.0259,
"step": 693
},
{
"epoch": 13.6,
"learning_rate": 0.0001,
"loss": 0.0179,
"step": 694
},
{
"epoch": 13.62,
"learning_rate": 0.0001,
"loss": 0.0193,
"step": 695
},
{
"epoch": 13.64,
"learning_rate": 0.0001,
"loss": 0.0249,
"step": 696
},
{
"epoch": 13.66,
"learning_rate": 0.0001,
"loss": 0.0252,
"step": 697
},
{
"epoch": 13.68,
"learning_rate": 0.0001,
"loss": 0.0214,
"step": 698
},
{
"epoch": 13.7,
"learning_rate": 0.0001,
"loss": 0.0279,
"step": 699
},
{
"epoch": 13.72,
"learning_rate": 0.0001,
"loss": 0.0287,
"step": 700
},
{
"epoch": 13.74,
"learning_rate": 0.0001,
"loss": 0.0226,
"step": 701
},
{
"epoch": 13.76,
"learning_rate": 0.0001,
"loss": 0.0231,
"step": 702
},
{
"epoch": 13.78,
"learning_rate": 0.0001,
"loss": 0.0292,
"step": 703
},
{
"epoch": 13.8,
"learning_rate": 0.0001,
"loss": 0.021,
"step": 704
},
{
"epoch": 13.82,
"learning_rate": 0.0001,
"loss": 0.0297,
"step": 705
},
{
"epoch": 13.84,
"learning_rate": 0.0001,
"loss": 0.0197,
"step": 706
},
{
"epoch": 13.86,
"learning_rate": 0.0001,
"loss": 0.0359,
"step": 707
},
{
"epoch": 13.88,
"learning_rate": 0.0001,
"loss": 0.0523,
"step": 708
},
{
"epoch": 13.9,
"learning_rate": 0.0001,
"loss": 0.0428,
"step": 709
},
{
"epoch": 13.92,
"learning_rate": 0.0001,
"loss": 0.0311,
"step": 710
},
{
"epoch": 13.94,
"learning_rate": 0.0001,
"loss": 0.0386,
"step": 711
},
{
"epoch": 13.96,
"learning_rate": 0.0001,
"loss": 0.0199,
"step": 712
},
{
"epoch": 13.98,
"learning_rate": 0.0001,
"loss": 0.0225,
"step": 713
},
{
"epoch": 14.0,
"learning_rate": 0.0001,
"loss": 0.0485,
"step": 714
},
{
"epoch": 14.0,
"eval_exact_match": 0.0918918918918919,
"eval_exec": 0.31351351351351353,
"eval_loss": 0.9727324843406677,
"eval_runtime": 315.727,
"eval_samples_per_second": 0.586,
"step": 714
},
{
"epoch": 14.02,
"learning_rate": 0.0001,
"loss": 0.0369,
"step": 715
},
{
"epoch": 14.04,
"learning_rate": 0.0001,
"loss": 0.0278,
"step": 716
},
{
"epoch": 14.06,
"learning_rate": 0.0001,
"loss": 0.021,
"step": 717
},
{
"epoch": 14.08,
"learning_rate": 0.0001,
"loss": 0.0191,
"step": 718
},
{
"epoch": 14.1,
"learning_rate": 0.0001,
"loss": 0.0506,
"step": 719
},
{
"epoch": 14.12,
"learning_rate": 0.0001,
"loss": 0.0349,
"step": 720
},
{
"epoch": 14.14,
"learning_rate": 0.0001,
"loss": 0.022,
"step": 721
},
{
"epoch": 14.16,
"learning_rate": 0.0001,
"loss": 0.0158,
"step": 722
},
{
"epoch": 14.18,
"learning_rate": 0.0001,
"loss": 0.0157,
"step": 723
},
{
"epoch": 14.2,
"learning_rate": 0.0001,
"loss": 0.0339,
"step": 724
},
{
"epoch": 14.21,
"learning_rate": 0.0001,
"loss": 0.026,
"step": 725
},
{
"epoch": 14.23,
"learning_rate": 0.0001,
"loss": 0.0177,
"step": 726
},
{
"epoch": 14.25,
"learning_rate": 0.0001,
"loss": 0.0201,
"step": 727
},
{
"epoch": 14.27,
"learning_rate": 0.0001,
"loss": 0.0211,
"step": 728
},
{
"epoch": 14.29,
"learning_rate": 0.0001,
"loss": 0.0278,
"step": 729
},
{
"epoch": 14.31,
"learning_rate": 0.0001,
"loss": 0.0201,
"step": 730
},
{
"epoch": 14.33,
"learning_rate": 0.0001,
"loss": 0.0185,
"step": 731
},
{
"epoch": 14.35,
"learning_rate": 0.0001,
"loss": 0.017,
"step": 732
},
{
"epoch": 14.37,
"learning_rate": 0.0001,
"loss": 0.0272,
"step": 733
},
{
"epoch": 14.39,
"learning_rate": 0.0001,
"loss": 0.0358,
"step": 734
},
{
"epoch": 14.41,
"learning_rate": 0.0001,
"loss": 0.0223,
"step": 735
},
{
"epoch": 14.43,
"learning_rate": 0.0001,
"loss": 0.0262,
"step": 736
},
{
"epoch": 14.45,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 737
},
{
"epoch": 14.47,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 738
},
{
"epoch": 14.49,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 739
},
{
"epoch": 14.51,
"learning_rate": 0.0001,
"loss": 0.0228,
"step": 740
},
{
"epoch": 14.53,
"learning_rate": 0.0001,
"loss": 0.0227,
"step": 741
},
{
"epoch": 14.55,
"learning_rate": 0.0001,
"loss": 0.02,
"step": 742
},
{
"epoch": 14.57,
"learning_rate": 0.0001,
"loss": 0.0172,
"step": 743
},
{
"epoch": 14.59,
"learning_rate": 0.0001,
"loss": 0.0248,
"step": 744
},
{
"epoch": 14.6,
"learning_rate": 0.0001,
"loss": 0.0236,
"step": 745
},
{
"epoch": 14.62,
"learning_rate": 0.0001,
"loss": 0.0232,
"step": 746
},
{
"epoch": 14.64,
"learning_rate": 0.0001,
"loss": 0.0171,
"step": 747
},
{
"epoch": 14.66,
"learning_rate": 0.0001,
"loss": 0.0322,
"step": 748
},
{
"epoch": 14.68,
"learning_rate": 0.0001,
"loss": 0.0187,
"step": 749
},
{
"epoch": 14.7,
"learning_rate": 0.0001,
"loss": 0.0265,
"step": 750
},
{
"epoch": 14.72,
"learning_rate": 0.0001,
"loss": 0.0207,
"step": 751
},
{
"epoch": 14.74,
"learning_rate": 0.0001,
"loss": 0.0224,
"step": 752
},
{
"epoch": 14.76,
"learning_rate": 0.0001,
"loss": 0.0202,
"step": 753
},
{
"epoch": 14.78,
"learning_rate": 0.0001,
"loss": 0.022,
"step": 754
},
{
"epoch": 14.8,
"learning_rate": 0.0001,
"loss": 0.0346,
"step": 755
},
{
"epoch": 14.82,
"learning_rate": 0.0001,
"loss": 0.0303,
"step": 756
},
{
"epoch": 14.84,
"learning_rate": 0.0001,
"loss": 0.0212,
"step": 757
},
{
"epoch": 14.86,
"learning_rate": 0.0001,
"loss": 0.0291,
"step": 758
},
{
"epoch": 14.88,
"learning_rate": 0.0001,
"loss": 0.0366,
"step": 759
},
{
"epoch": 14.9,
"learning_rate": 0.0001,
"loss": 0.0345,
"step": 760
},
{
"epoch": 14.92,
"learning_rate": 0.0001,
"loss": 0.032,
"step": 761
},
{
"epoch": 14.94,
"learning_rate": 0.0001,
"loss": 0.034,
"step": 762
},
{
"epoch": 14.96,
"learning_rate": 0.0001,
"loss": 0.0282,
"step": 763
},
{
"epoch": 14.98,
"learning_rate": 0.0001,
"loss": 0.0258,
"step": 764
},
{
"epoch": 15.0,
"learning_rate": 0.0001,
"loss": 0.0227,
"step": 765
},
{
"epoch": 15.0,
"eval_exact_match": 0.11351351351351352,
"eval_exec": 0.3081081081081081,
"eval_loss": 1.0063648223876953,
"eval_runtime": 334.6947,
"eval_samples_per_second": 0.553,
"step": 765
},
{
"epoch": 15.02,
"learning_rate": 0.0001,
"loss": 0.0181,
"step": 766
},
{
"epoch": 15.04,
"learning_rate": 0.0001,
"loss": 0.0236,
"step": 767
},
{
"epoch": 15.06,
"learning_rate": 0.0001,
"loss": 0.0125,
"step": 768
},
{
"epoch": 15.08,
"learning_rate": 0.0001,
"loss": 0.0206,
"step": 769
},
{
"epoch": 15.1,
"learning_rate": 0.0001,
"loss": 0.0193,
"step": 770
},
{
"epoch": 15.12,
"learning_rate": 0.0001,
"loss": 0.0176,
"step": 771
},
{
"epoch": 15.14,
"learning_rate": 0.0001,
"loss": 0.0195,
"step": 772
},
{
"epoch": 15.16,
"learning_rate": 0.0001,
"loss": 0.0148,
"step": 773
},
{
"epoch": 15.18,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 774
},
{
"epoch": 15.2,
"learning_rate": 0.0001,
"loss": 0.0372,
"step": 775
},
{
"epoch": 15.21,
"learning_rate": 0.0001,
"loss": 0.0308,
"step": 776
},
{
"epoch": 15.23,
"learning_rate": 0.0001,
"loss": 0.0141,
"step": 777
},
{
"epoch": 15.25,
"learning_rate": 0.0001,
"loss": 0.0202,
"step": 778
},
{
"epoch": 15.27,
"learning_rate": 0.0001,
"loss": 0.0209,
"step": 779
},
{
"epoch": 15.29,
"learning_rate": 0.0001,
"loss": 0.0265,
"step": 780
},
{
"epoch": 15.31,
"learning_rate": 0.0001,
"loss": 0.0257,
"step": 781
},
{
"epoch": 15.33,
"learning_rate": 0.0001,
"loss": 0.028,
"step": 782
},
{
"epoch": 15.35,
"learning_rate": 0.0001,
"loss": 0.0214,
"step": 783
},
{
"epoch": 15.37,
"learning_rate": 0.0001,
"loss": 0.0281,
"step": 784
},
{
"epoch": 15.39,
"learning_rate": 0.0001,
"loss": 0.017,
"step": 785
},
{
"epoch": 15.41,
"learning_rate": 0.0001,
"loss": 0.0186,
"step": 786
},
{
"epoch": 15.43,
"learning_rate": 0.0001,
"loss": 0.0277,
"step": 787
},
{
"epoch": 15.45,
"learning_rate": 0.0001,
"loss": 0.0378,
"step": 788
},
{
"epoch": 15.47,
"learning_rate": 0.0001,
"loss": 0.0163,
"step": 789
},
{
"epoch": 15.49,
"learning_rate": 0.0001,
"loss": 0.0197,
"step": 790
},
{
"epoch": 15.51,
"learning_rate": 0.0001,
"loss": 0.0224,
"step": 791
},
{
"epoch": 15.53,
"learning_rate": 0.0001,
"loss": 0.0216,
"step": 792
},
{
"epoch": 15.55,
"learning_rate": 0.0001,
"loss": 0.0325,
"step": 793
},
{
"epoch": 15.57,
"learning_rate": 0.0001,
"loss": 0.03,
"step": 794
},
{
"epoch": 15.59,
"learning_rate": 0.0001,
"loss": 0.0206,
"step": 795
},
{
"epoch": 15.6,
"learning_rate": 0.0001,
"loss": 0.0363,
"step": 796
},
{
"epoch": 15.62,
"learning_rate": 0.0001,
"loss": 0.0163,
"step": 797
},
{
"epoch": 15.64,
"learning_rate": 0.0001,
"loss": 0.0207,
"step": 798
},
{
"epoch": 15.66,
"learning_rate": 0.0001,
"loss": 0.0299,
"step": 799
},
{
"epoch": 15.68,
"learning_rate": 0.0001,
"loss": 0.0287,
"step": 800
},
{
"epoch": 15.7,
"learning_rate": 0.0001,
"loss": 0.0235,
"step": 801
},
{
"epoch": 15.72,
"learning_rate": 0.0001,
"loss": 0.0257,
"step": 802
},
{
"epoch": 15.74,
"learning_rate": 0.0001,
"loss": 0.0128,
"step": 803
},
{
"epoch": 15.76,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 804
},
{
"epoch": 15.78,
"learning_rate": 0.0001,
"loss": 0.0259,
"step": 805
},
{
"epoch": 15.8,
"learning_rate": 0.0001,
"loss": 0.0147,
"step": 806
},
{
"epoch": 15.82,
"learning_rate": 0.0001,
"loss": 0.0288,
"step": 807
},
{
"epoch": 15.84,
"learning_rate": 0.0001,
"loss": 0.0284,
"step": 808
},
{
"epoch": 15.86,
"learning_rate": 0.0001,
"loss": 0.0233,
"step": 809
},
{
"epoch": 15.88,
"learning_rate": 0.0001,
"loss": 0.0278,
"step": 810
},
{
"epoch": 15.9,
"learning_rate": 0.0001,
"loss": 0.0228,
"step": 811
},
{
"epoch": 15.92,
"learning_rate": 0.0001,
"loss": 0.0373,
"step": 812
},
{
"epoch": 15.94,
"learning_rate": 0.0001,
"loss": 0.0145,
"step": 813
},
{
"epoch": 15.96,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 814
},
{
"epoch": 15.98,
"learning_rate": 0.0001,
"loss": 0.035,
"step": 815
},
{
"epoch": 16.0,
"learning_rate": 0.0001,
"loss": 0.023,
"step": 816
},
{
"epoch": 16.0,
"eval_exact_match": 0.12432432432432433,
"eval_exec": 0.31351351351351353,
"eval_loss": 1.0441596508026123,
"eval_runtime": 1442.8355,
"eval_samples_per_second": 0.128,
"step": 816
},
{
"epoch": 16.02,
"learning_rate": 0.0001,
"loss": 0.019,
"step": 817
},
{
"epoch": 16.04,
"learning_rate": 0.0001,
"loss": 0.0151,
"step": 818
},
{
"epoch": 16.06,
"learning_rate": 0.0001,
"loss": 0.0143,
"step": 819
},
{
"epoch": 16.08,
"learning_rate": 0.0001,
"loss": 0.0321,
"step": 820
},
{
"epoch": 16.1,
"learning_rate": 0.0001,
"loss": 0.0231,
"step": 821
},
{
"epoch": 16.12,
"learning_rate": 0.0001,
"loss": 0.0192,
"step": 822
},
{
"epoch": 16.14,
"learning_rate": 0.0001,
"loss": 0.0069,
"step": 823
},
{
"epoch": 16.16,
"learning_rate": 0.0001,
"loss": 0.0267,
"step": 824
},
{
"epoch": 16.18,
"learning_rate": 0.0001,
"loss": 0.0152,
"step": 825
},
{
"epoch": 16.2,
"learning_rate": 0.0001,
"loss": 0.0178,
"step": 826
},
{
"epoch": 16.21,
"learning_rate": 0.0001,
"loss": 0.0179,
"step": 827
},
{
"epoch": 16.23,
"learning_rate": 0.0001,
"loss": 0.0243,
"step": 828
},
{
"epoch": 16.25,
"learning_rate": 0.0001,
"loss": 0.0228,
"step": 829
},
{
"epoch": 16.27,
"learning_rate": 0.0001,
"loss": 0.0217,
"step": 830
},
{
"epoch": 16.29,
"learning_rate": 0.0001,
"loss": 0.0216,
"step": 831
},
{
"epoch": 16.31,
"learning_rate": 0.0001,
"loss": 0.0248,
"step": 832
},
{
"epoch": 16.33,
"learning_rate": 0.0001,
"loss": 0.0343,
"step": 833
},
{
"epoch": 16.35,
"learning_rate": 0.0001,
"loss": 0.0196,
"step": 834
},
{
"epoch": 16.37,
"learning_rate": 0.0001,
"loss": 0.0103,
"step": 835
},
{
"epoch": 16.39,
"learning_rate": 0.0001,
"loss": 0.023,
"step": 836
},
{
"epoch": 16.41,
"learning_rate": 0.0001,
"loss": 0.0159,
"step": 837
},
{
"epoch": 16.43,
"learning_rate": 0.0001,
"loss": 0.019,
"step": 838
},
{
"epoch": 16.45,
"learning_rate": 0.0001,
"loss": 0.0203,
"step": 839
},
{
"epoch": 16.47,
"learning_rate": 0.0001,
"loss": 0.0175,
"step": 840
},
{
"epoch": 16.49,
"learning_rate": 0.0001,
"loss": 0.0143,
"step": 841
},
{
"epoch": 16.51,
"learning_rate": 0.0001,
"loss": 0.0192,
"step": 842
},
{
"epoch": 16.53,
"learning_rate": 0.0001,
"loss": 0.0135,
"step": 843
},
{
"epoch": 16.55,
"learning_rate": 0.0001,
"loss": 0.0202,
"step": 844
},
{
"epoch": 16.57,
"learning_rate": 0.0001,
"loss": 0.0203,
"step": 845
},
{
"epoch": 16.59,
"learning_rate": 0.0001,
"loss": 0.0172,
"step": 846
},
{
"epoch": 16.6,
"learning_rate": 0.0001,
"loss": 0.0121,
"step": 847
},
{
"epoch": 16.62,
"learning_rate": 0.0001,
"loss": 0.0253,
"step": 848
},
{
"epoch": 16.64,
"learning_rate": 0.0001,
"loss": 0.015,
"step": 849
},
{
"epoch": 16.66,
"learning_rate": 0.0001,
"loss": 0.013,
"step": 850
},
{
"epoch": 16.68,
"learning_rate": 0.0001,
"loss": 0.0377,
"step": 851
},
{
"epoch": 16.7,
"learning_rate": 0.0001,
"loss": 0.0139,
"step": 852
},
{
"epoch": 16.72,
"learning_rate": 0.0001,
"loss": 0.0097,
"step": 853
},
{
"epoch": 16.74,
"learning_rate": 0.0001,
"loss": 0.02,
"step": 854
},
{
"epoch": 16.76,
"learning_rate": 0.0001,
"loss": 0.0095,
"step": 855
},
{
"epoch": 16.78,
"learning_rate": 0.0001,
"loss": 0.0181,
"step": 856
},
{
"epoch": 16.8,
"learning_rate": 0.0001,
"loss": 0.0183,
"step": 857
},
{
"epoch": 16.82,
"learning_rate": 0.0001,
"loss": 0.0189,
"step": 858
},
{
"epoch": 16.84,
"learning_rate": 0.0001,
"loss": 0.0193,
"step": 859
},
{
"epoch": 16.86,
"learning_rate": 0.0001,
"loss": 0.0207,
"step": 860
},
{
"epoch": 16.88,
"learning_rate": 0.0001,
"loss": 0.0276,
"step": 861
},
{
"epoch": 16.9,
"learning_rate": 0.0001,
"loss": 0.0274,
"step": 862
},
{
"epoch": 16.92,
"learning_rate": 0.0001,
"loss": 0.0252,
"step": 863
},
{
"epoch": 16.94,
"learning_rate": 0.0001,
"loss": 0.0202,
"step": 864
},
{
"epoch": 16.96,
"learning_rate": 0.0001,
"loss": 0.02,
"step": 865
},
{
"epoch": 16.98,
"learning_rate": 0.0001,
"loss": 0.0242,
"step": 866
},
{
"epoch": 17.0,
"learning_rate": 0.0001,
"loss": 0.0327,
"step": 867
},
{
"epoch": 17.0,
"eval_exact_match": 0.15675675675675677,
"eval_exec": 0.2972972972972973,
"eval_loss": 1.0014864206314087,
"eval_runtime": 313.9782,
"eval_samples_per_second": 0.589,
"step": 867
},
{
"epoch": 17.02,
"learning_rate": 0.0001,
"loss": 0.017,
"step": 868
},
{
"epoch": 17.04,
"learning_rate": 0.0001,
"loss": 0.0086,
"step": 869
},
{
"epoch": 17.06,
"learning_rate": 0.0001,
"loss": 0.0152,
"step": 870
},
{
"epoch": 17.08,
"learning_rate": 0.0001,
"loss": 0.0379,
"step": 871
},
{
"epoch": 17.1,
"learning_rate": 0.0001,
"loss": 0.0265,
"step": 872
},
{
"epoch": 17.12,
"learning_rate": 0.0001,
"loss": 0.0245,
"step": 873
},
{
"epoch": 17.14,
"learning_rate": 0.0001,
"loss": 0.0246,
"step": 874
},
{
"epoch": 17.16,
"learning_rate": 0.0001,
"loss": 0.0232,
"step": 875
},
{
"epoch": 17.18,
"learning_rate": 0.0001,
"loss": 0.023,
"step": 876
},
{
"epoch": 17.2,
"learning_rate": 0.0001,
"loss": 0.0129,
"step": 877
},
{
"epoch": 17.21,
"learning_rate": 0.0001,
"loss": 0.0195,
"step": 878
},
{
"epoch": 17.23,
"learning_rate": 0.0001,
"loss": 0.0168,
"step": 879
},
{
"epoch": 17.25,
"learning_rate": 0.0001,
"loss": 0.023,
"step": 880
},
{
"epoch": 17.27,
"learning_rate": 0.0001,
"loss": 0.0201,
"step": 881
},
{
"epoch": 17.29,
"learning_rate": 0.0001,
"loss": 0.0135,
"step": 882
},
{
"epoch": 17.31,
"learning_rate": 0.0001,
"loss": 0.0166,
"step": 883
},
{
"epoch": 17.33,
"learning_rate": 0.0001,
"loss": 0.0164,
"step": 884
},
{
"epoch": 17.35,
"learning_rate": 0.0001,
"loss": 0.0236,
"step": 885
},
{
"epoch": 17.37,
"learning_rate": 0.0001,
"loss": 0.0313,
"step": 886
},
{
"epoch": 17.39,
"learning_rate": 0.0001,
"loss": 0.0198,
"step": 887
},
{
"epoch": 17.41,
"learning_rate": 0.0001,
"loss": 0.0243,
"step": 888
},
{
"epoch": 17.43,
"learning_rate": 0.0001,
"loss": 0.0174,
"step": 889
},
{
"epoch": 17.45,
"learning_rate": 0.0001,
"loss": 0.0474,
"step": 890
},
{
"epoch": 17.47,
"learning_rate": 0.0001,
"loss": 0.0275,
"step": 891
},
{
"epoch": 17.49,
"learning_rate": 0.0001,
"loss": 0.0213,
"step": 892
},
{
"epoch": 17.51,
"learning_rate": 0.0001,
"loss": 0.0102,
"step": 893
},
{
"epoch": 17.53,
"learning_rate": 0.0001,
"loss": 0.0285,
"step": 894
},
{
"epoch": 17.55,
"learning_rate": 0.0001,
"loss": 0.0129,
"step": 895
},
{
"epoch": 17.57,
"learning_rate": 0.0001,
"loss": 0.016,
"step": 896
},
{
"epoch": 17.59,
"learning_rate": 0.0001,
"loss": 0.0261,
"step": 897
},
{
"epoch": 17.6,
"learning_rate": 0.0001,
"loss": 0.0241,
"step": 898
},
{
"epoch": 17.62,
"learning_rate": 0.0001,
"loss": 0.0254,
"step": 899
},
{
"epoch": 17.64,
"learning_rate": 0.0001,
"loss": 0.0111,
"step": 900
},
{
"epoch": 17.66,
"learning_rate": 0.0001,
"loss": 0.0302,
"step": 901
},
{
"epoch": 17.68,
"learning_rate": 0.0001,
"loss": 0.0177,
"step": 902
},
{
"epoch": 17.7,
"learning_rate": 0.0001,
"loss": 0.0191,
"step": 903
},
{
"epoch": 17.72,
"learning_rate": 0.0001,
"loss": 0.0227,
"step": 904
},
{
"epoch": 17.74,
"learning_rate": 0.0001,
"loss": 0.0138,
"step": 905
},
{
"epoch": 17.76,
"learning_rate": 0.0001,
"loss": 0.0173,
"step": 906
},
{
"epoch": 17.78,
"learning_rate": 0.0001,
"loss": 0.0242,
"step": 907
},
{
"epoch": 17.8,
"learning_rate": 0.0001,
"loss": 0.0284,
"step": 908
},
{
"epoch": 17.82,
"learning_rate": 0.0001,
"loss": 0.0138,
"step": 909
},
{
"epoch": 17.84,
"learning_rate": 0.0001,
"loss": 0.0206,
"step": 910
},
{
"epoch": 17.86,
"learning_rate": 0.0001,
"loss": 0.0164,
"step": 911
},
{
"epoch": 17.88,
"learning_rate": 0.0001,
"loss": 0.0358,
"step": 912
},
{
"epoch": 17.9,
"learning_rate": 0.0001,
"loss": 0.0244,
"step": 913
},
{
"epoch": 17.92,
"learning_rate": 0.0001,
"loss": 0.0311,
"step": 914
},
{
"epoch": 17.94,
"learning_rate": 0.0001,
"loss": 0.0233,
"step": 915
},
{
"epoch": 17.96,
"learning_rate": 0.0001,
"loss": 0.0221,
"step": 916
},
{
"epoch": 17.98,
"learning_rate": 0.0001,
"loss": 0.0204,
"step": 917
},
{
"epoch": 18.0,
"learning_rate": 0.0001,
"loss": 0.0238,
"step": 918
},
{
"epoch": 18.0,
"eval_exact_match": 0.12972972972972974,
"eval_exec": 0.35135135135135137,
"eval_loss": 0.9965826272964478,
"eval_runtime": 310.3791,
"eval_samples_per_second": 0.596,
"step": 918
}
],
"max_steps": 1275,
"num_train_epochs": 25,
"total_flos": 1.1658274875194573e+17,
"trial_name": null,
"trial_params": null
}