denverbaumgartner's picture
Upload trainer_state.json with huggingface_hub
29fa852 verified
{
"best_metric": 0.35135135135135137,
"best_model_checkpoint": "/train_synth_kaggle_sampled_all_base_00_run_00_train_rerun/checkpoint-306",
"epoch": 5.995121951219512,
"global_step": 306,
"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": 3.3739,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 0.0001,
"loss": 2.053,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 0.0001,
"loss": 1.3787,
"step": 3
},
{
"epoch": 0.08,
"learning_rate": 0.0001,
"loss": 1.2049,
"step": 4
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 0.9958,
"step": 5
},
{
"epoch": 0.12,
"learning_rate": 0.0001,
"loss": 0.9045,
"step": 6
},
{
"epoch": 0.14,
"learning_rate": 0.0001,
"loss": 0.7612,
"step": 7
},
{
"epoch": 0.16,
"learning_rate": 0.0001,
"loss": 0.7243,
"step": 8
},
{
"epoch": 0.18,
"learning_rate": 0.0001,
"loss": 0.7789,
"step": 9
},
{
"epoch": 0.2,
"learning_rate": 0.0001,
"loss": 1.0047,
"step": 10
},
{
"epoch": 0.21,
"learning_rate": 0.0001,
"loss": 0.5055,
"step": 11
},
{
"epoch": 0.23,
"learning_rate": 0.0001,
"loss": 0.5152,
"step": 12
},
{
"epoch": 0.25,
"learning_rate": 0.0001,
"loss": 0.6686,
"step": 13
},
{
"epoch": 0.27,
"learning_rate": 0.0001,
"loss": 0.4896,
"step": 14
},
{
"epoch": 0.29,
"learning_rate": 0.0001,
"loss": 0.533,
"step": 15
},
{
"epoch": 0.31,
"learning_rate": 0.0001,
"loss": 0.452,
"step": 16
},
{
"epoch": 0.33,
"learning_rate": 0.0001,
"loss": 0.4648,
"step": 17
},
{
"epoch": 0.35,
"learning_rate": 0.0001,
"loss": 0.4912,
"step": 18
},
{
"epoch": 0.37,
"learning_rate": 0.0001,
"loss": 0.447,
"step": 19
},
{
"epoch": 0.39,
"learning_rate": 0.0001,
"loss": 0.3661,
"step": 20
},
{
"epoch": 0.41,
"learning_rate": 0.0001,
"loss": 0.5228,
"step": 21
},
{
"epoch": 0.43,
"learning_rate": 0.0001,
"loss": 0.3719,
"step": 22
},
{
"epoch": 0.45,
"learning_rate": 0.0001,
"loss": 0.4539,
"step": 23
},
{
"epoch": 0.47,
"learning_rate": 0.0001,
"loss": 0.3439,
"step": 24
},
{
"epoch": 0.49,
"learning_rate": 0.0001,
"loss": 0.3345,
"step": 25
},
{
"epoch": 0.51,
"learning_rate": 0.0001,
"loss": 0.3321,
"step": 26
},
{
"epoch": 0.53,
"learning_rate": 0.0001,
"loss": 0.3633,
"step": 27
},
{
"epoch": 0.55,
"learning_rate": 0.0001,
"loss": 0.2942,
"step": 28
},
{
"epoch": 0.57,
"learning_rate": 0.0001,
"loss": 0.2946,
"step": 29
},
{
"epoch": 0.59,
"learning_rate": 0.0001,
"loss": 0.3659,
"step": 30
},
{
"epoch": 0.6,
"learning_rate": 0.0001,
"loss": 0.2755,
"step": 31
},
{
"epoch": 0.62,
"learning_rate": 0.0001,
"loss": 0.3928,
"step": 32
},
{
"epoch": 0.64,
"learning_rate": 0.0001,
"loss": 0.2506,
"step": 33
},
{
"epoch": 0.66,
"learning_rate": 0.0001,
"loss": 0.2949,
"step": 34
},
{
"epoch": 0.68,
"learning_rate": 0.0001,
"loss": 0.3995,
"step": 35
},
{
"epoch": 0.7,
"learning_rate": 0.0001,
"loss": 0.2582,
"step": 36
},
{
"epoch": 0.72,
"learning_rate": 0.0001,
"loss": 0.2683,
"step": 37
},
{
"epoch": 0.74,
"learning_rate": 0.0001,
"loss": 0.2896,
"step": 38
},
{
"epoch": 0.76,
"learning_rate": 0.0001,
"loss": 0.2714,
"step": 39
},
{
"epoch": 0.78,
"learning_rate": 0.0001,
"loss": 0.2823,
"step": 40
},
{
"epoch": 0.8,
"learning_rate": 0.0001,
"loss": 0.284,
"step": 41
},
{
"epoch": 0.82,
"learning_rate": 0.0001,
"loss": 0.2682,
"step": 42
},
{
"epoch": 0.84,
"learning_rate": 0.0001,
"loss": 0.303,
"step": 43
},
{
"epoch": 0.86,
"learning_rate": 0.0001,
"loss": 0.2127,
"step": 44
},
{
"epoch": 0.88,
"learning_rate": 0.0001,
"loss": 0.3182,
"step": 45
},
{
"epoch": 0.9,
"learning_rate": 0.0001,
"loss": 0.2551,
"step": 46
},
{
"epoch": 0.92,
"learning_rate": 0.0001,
"loss": 0.1895,
"step": 47
},
{
"epoch": 0.94,
"learning_rate": 0.0001,
"loss": 0.2146,
"step": 48
},
{
"epoch": 0.96,
"learning_rate": 0.0001,
"loss": 0.3238,
"step": 49
},
{
"epoch": 0.98,
"learning_rate": 0.0001,
"loss": 0.3389,
"step": 50
},
{
"epoch": 1.0,
"learning_rate": 0.0001,
"loss": 0.1857,
"step": 51
},
{
"epoch": 1.0,
"eval_exact_match": 0.15675675675675677,
"eval_exec": 0.2972972972972973,
"eval_loss": 0.7331372499465942,
"eval_runtime": 378.3205,
"eval_samples_per_second": 0.489,
"step": 51
},
{
"epoch": 1.02,
"learning_rate": 0.0001,
"loss": 0.2577,
"step": 52
},
{
"epoch": 1.04,
"learning_rate": 0.0001,
"loss": 0.5961,
"step": 53
},
{
"epoch": 1.06,
"learning_rate": 0.0001,
"loss": 0.6639,
"step": 54
},
{
"epoch": 1.08,
"learning_rate": 0.0001,
"loss": 0.2215,
"step": 55
},
{
"epoch": 1.1,
"learning_rate": 0.0001,
"loss": 0.2199,
"step": 56
},
{
"epoch": 1.12,
"learning_rate": 0.0001,
"loss": 0.3201,
"step": 57
},
{
"epoch": 1.14,
"learning_rate": 0.0001,
"loss": 0.2378,
"step": 58
},
{
"epoch": 1.16,
"learning_rate": 0.0001,
"loss": 0.1577,
"step": 59
},
{
"epoch": 1.18,
"learning_rate": 0.0001,
"loss": 0.1754,
"step": 60
},
{
"epoch": 1.2,
"learning_rate": 0.0001,
"loss": 0.1828,
"step": 61
},
{
"epoch": 1.21,
"learning_rate": 0.0001,
"loss": 0.2188,
"step": 62
},
{
"epoch": 1.23,
"learning_rate": 0.0001,
"loss": 0.2262,
"step": 63
},
{
"epoch": 1.25,
"learning_rate": 0.0001,
"loss": 0.1318,
"step": 64
},
{
"epoch": 1.27,
"learning_rate": 0.0001,
"loss": 0.2077,
"step": 65
},
{
"epoch": 1.29,
"learning_rate": 0.0001,
"loss": 0.1643,
"step": 66
},
{
"epoch": 1.31,
"learning_rate": 0.0001,
"loss": 0.1509,
"step": 67
},
{
"epoch": 1.33,
"learning_rate": 0.0001,
"loss": 0.1061,
"step": 68
},
{
"epoch": 1.35,
"learning_rate": 0.0001,
"loss": 0.1732,
"step": 69
},
{
"epoch": 1.37,
"learning_rate": 0.0001,
"loss": 0.182,
"step": 70
},
{
"epoch": 1.39,
"learning_rate": 0.0001,
"loss": 0.2668,
"step": 71
},
{
"epoch": 1.41,
"learning_rate": 0.0001,
"loss": 0.2236,
"step": 72
},
{
"epoch": 1.43,
"learning_rate": 0.0001,
"loss": 0.1395,
"step": 73
},
{
"epoch": 1.45,
"learning_rate": 0.0001,
"loss": 0.1643,
"step": 74
},
{
"epoch": 1.47,
"learning_rate": 0.0001,
"loss": 0.2129,
"step": 75
},
{
"epoch": 1.49,
"learning_rate": 0.0001,
"loss": 0.1919,
"step": 76
},
{
"epoch": 1.51,
"learning_rate": 0.0001,
"loss": 0.2123,
"step": 77
},
{
"epoch": 1.53,
"learning_rate": 0.0001,
"loss": 0.2473,
"step": 78
},
{
"epoch": 1.55,
"learning_rate": 0.0001,
"loss": 0.2185,
"step": 79
},
{
"epoch": 1.57,
"learning_rate": 0.0001,
"loss": 0.2158,
"step": 80
},
{
"epoch": 1.59,
"learning_rate": 0.0001,
"loss": 0.1674,
"step": 81
},
{
"epoch": 1.6,
"learning_rate": 0.0001,
"loss": 0.1353,
"step": 82
},
{
"epoch": 1.62,
"learning_rate": 0.0001,
"loss": 0.1918,
"step": 83
},
{
"epoch": 1.64,
"learning_rate": 0.0001,
"loss": 0.1678,
"step": 84
},
{
"epoch": 1.66,
"learning_rate": 0.0001,
"loss": 0.1434,
"step": 85
},
{
"epoch": 1.68,
"learning_rate": 0.0001,
"loss": 0.1522,
"step": 86
},
{
"epoch": 1.7,
"learning_rate": 0.0001,
"loss": 0.1487,
"step": 87
},
{
"epoch": 1.72,
"learning_rate": 0.0001,
"loss": 0.199,
"step": 88
},
{
"epoch": 1.74,
"learning_rate": 0.0001,
"loss": 0.1497,
"step": 89
},
{
"epoch": 1.76,
"learning_rate": 0.0001,
"loss": 0.1836,
"step": 90
},
{
"epoch": 1.78,
"learning_rate": 0.0001,
"loss": 0.1529,
"step": 91
},
{
"epoch": 1.8,
"learning_rate": 0.0001,
"loss": 0.1945,
"step": 92
},
{
"epoch": 1.82,
"learning_rate": 0.0001,
"loss": 0.182,
"step": 93
},
{
"epoch": 1.84,
"learning_rate": 0.0001,
"loss": 0.1741,
"step": 94
},
{
"epoch": 1.86,
"learning_rate": 0.0001,
"loss": 0.1903,
"step": 95
},
{
"epoch": 1.88,
"learning_rate": 0.0001,
"loss": 0.1286,
"step": 96
},
{
"epoch": 1.9,
"learning_rate": 0.0001,
"loss": 0.1435,
"step": 97
},
{
"epoch": 1.92,
"learning_rate": 0.0001,
"loss": 0.1931,
"step": 98
},
{
"epoch": 1.94,
"learning_rate": 0.0001,
"loss": 0.1429,
"step": 99
},
{
"epoch": 1.96,
"learning_rate": 0.0001,
"loss": 0.144,
"step": 100
},
{
"epoch": 1.98,
"learning_rate": 0.0001,
"loss": 0.1924,
"step": 101
},
{
"epoch": 2.0,
"learning_rate": 0.0001,
"loss": 0.1605,
"step": 102
},
{
"epoch": 2.0,
"eval_exact_match": 0.10810810810810811,
"eval_exec": 0.31891891891891894,
"eval_loss": 0.7565640807151794,
"eval_runtime": 1626.5882,
"eval_samples_per_second": 0.114,
"step": 102
},
{
"epoch": 2.02,
"learning_rate": 0.0001,
"loss": 0.2484,
"step": 103
},
{
"epoch": 2.04,
"learning_rate": 0.0001,
"loss": 0.1149,
"step": 104
},
{
"epoch": 2.06,
"learning_rate": 0.0001,
"loss": 0.1124,
"step": 105
},
{
"epoch": 2.08,
"learning_rate": 0.0001,
"loss": 0.1127,
"step": 106
},
{
"epoch": 2.1,
"learning_rate": 0.0001,
"loss": 0.1088,
"step": 107
},
{
"epoch": 2.12,
"learning_rate": 0.0001,
"loss": 0.0897,
"step": 108
},
{
"epoch": 2.14,
"learning_rate": 0.0001,
"loss": 0.1282,
"step": 109
},
{
"epoch": 2.16,
"learning_rate": 0.0001,
"loss": 0.0893,
"step": 110
},
{
"epoch": 2.18,
"learning_rate": 0.0001,
"loss": 0.2047,
"step": 111
},
{
"epoch": 2.2,
"learning_rate": 0.0001,
"loss": 0.1573,
"step": 112
},
{
"epoch": 2.21,
"learning_rate": 0.0001,
"loss": 0.0947,
"step": 113
},
{
"epoch": 2.23,
"learning_rate": 0.0001,
"loss": 0.1456,
"step": 114
},
{
"epoch": 2.25,
"learning_rate": 0.0001,
"loss": 0.1307,
"step": 115
},
{
"epoch": 2.27,
"learning_rate": 0.0001,
"loss": 0.1663,
"step": 116
},
{
"epoch": 2.29,
"learning_rate": 0.0001,
"loss": 0.1487,
"step": 117
},
{
"epoch": 2.31,
"learning_rate": 0.0001,
"loss": 0.1328,
"step": 118
},
{
"epoch": 2.33,
"learning_rate": 0.0001,
"loss": 0.1246,
"step": 119
},
{
"epoch": 2.35,
"learning_rate": 0.0001,
"loss": 0.1446,
"step": 120
},
{
"epoch": 2.37,
"learning_rate": 0.0001,
"loss": 0.0852,
"step": 121
},
{
"epoch": 2.39,
"learning_rate": 0.0001,
"loss": 0.1233,
"step": 122
},
{
"epoch": 2.41,
"learning_rate": 0.0001,
"loss": 0.0996,
"step": 123
},
{
"epoch": 2.43,
"learning_rate": 0.0001,
"loss": 0.1164,
"step": 124
},
{
"epoch": 2.45,
"learning_rate": 0.0001,
"loss": 0.1287,
"step": 125
},
{
"epoch": 2.47,
"learning_rate": 0.0001,
"loss": 0.1372,
"step": 126
},
{
"epoch": 2.49,
"learning_rate": 0.0001,
"loss": 0.1441,
"step": 127
},
{
"epoch": 2.51,
"learning_rate": 0.0001,
"loss": 0.1405,
"step": 128
},
{
"epoch": 2.53,
"learning_rate": 0.0001,
"loss": 0.1305,
"step": 129
},
{
"epoch": 2.55,
"learning_rate": 0.0001,
"loss": 0.0996,
"step": 130
},
{
"epoch": 2.57,
"learning_rate": 0.0001,
"loss": 0.1044,
"step": 131
},
{
"epoch": 2.59,
"learning_rate": 0.0001,
"loss": 0.0887,
"step": 132
},
{
"epoch": 2.6,
"learning_rate": 0.0001,
"loss": 0.1352,
"step": 133
},
{
"epoch": 2.62,
"learning_rate": 0.0001,
"loss": 0.1144,
"step": 134
},
{
"epoch": 2.64,
"learning_rate": 0.0001,
"loss": 0.1142,
"step": 135
},
{
"epoch": 2.66,
"learning_rate": 0.0001,
"loss": 0.1245,
"step": 136
},
{
"epoch": 2.68,
"learning_rate": 0.0001,
"loss": 0.1326,
"step": 137
},
{
"epoch": 2.7,
"learning_rate": 0.0001,
"loss": 0.1386,
"step": 138
},
{
"epoch": 2.72,
"learning_rate": 0.0001,
"loss": 0.0956,
"step": 139
},
{
"epoch": 2.74,
"learning_rate": 0.0001,
"loss": 0.0978,
"step": 140
},
{
"epoch": 2.76,
"learning_rate": 0.0001,
"loss": 0.1338,
"step": 141
},
{
"epoch": 2.78,
"learning_rate": 0.0001,
"loss": 0.1524,
"step": 142
},
{
"epoch": 2.8,
"learning_rate": 0.0001,
"loss": 0.127,
"step": 143
},
{
"epoch": 2.82,
"learning_rate": 0.0001,
"loss": 0.1274,
"step": 144
},
{
"epoch": 2.84,
"learning_rate": 0.0001,
"loss": 0.1334,
"step": 145
},
{
"epoch": 2.86,
"learning_rate": 0.0001,
"loss": 0.0926,
"step": 146
},
{
"epoch": 2.88,
"learning_rate": 0.0001,
"loss": 0.0996,
"step": 147
},
{
"epoch": 2.9,
"learning_rate": 0.0001,
"loss": 0.1072,
"step": 148
},
{
"epoch": 2.92,
"learning_rate": 0.0001,
"loss": 0.0736,
"step": 149
},
{
"epoch": 2.94,
"learning_rate": 0.0001,
"loss": 0.1177,
"step": 150
},
{
"epoch": 2.96,
"learning_rate": 0.0001,
"loss": 0.1236,
"step": 151
},
{
"epoch": 2.98,
"learning_rate": 0.0001,
"loss": 0.1319,
"step": 152
},
{
"epoch": 3.0,
"learning_rate": 0.0001,
"loss": 0.1997,
"step": 153
},
{
"epoch": 3.0,
"eval_exact_match": 0.0972972972972973,
"eval_exec": 0.34594594594594597,
"eval_loss": 0.6917403936386108,
"eval_runtime": 400.7428,
"eval_samples_per_second": 0.462,
"step": 153
},
{
"epoch": 3.02,
"learning_rate": 0.0001,
"loss": 0.1149,
"step": 154
},
{
"epoch": 3.04,
"learning_rate": 0.0001,
"loss": 0.067,
"step": 155
},
{
"epoch": 3.06,
"learning_rate": 0.0001,
"loss": 0.0891,
"step": 156
},
{
"epoch": 3.08,
"learning_rate": 0.0001,
"loss": 0.0678,
"step": 157
},
{
"epoch": 3.1,
"learning_rate": 0.0001,
"loss": 0.0943,
"step": 158
},
{
"epoch": 3.12,
"learning_rate": 0.0001,
"loss": 0.0866,
"step": 159
},
{
"epoch": 3.14,
"learning_rate": 0.0001,
"loss": 0.0655,
"step": 160
},
{
"epoch": 3.16,
"learning_rate": 0.0001,
"loss": 0.073,
"step": 161
},
{
"epoch": 3.18,
"learning_rate": 0.0001,
"loss": 0.09,
"step": 162
},
{
"epoch": 3.2,
"learning_rate": 0.0001,
"loss": 0.0666,
"step": 163
},
{
"epoch": 3.21,
"learning_rate": 0.0001,
"loss": 0.0757,
"step": 164
},
{
"epoch": 3.23,
"learning_rate": 0.0001,
"loss": 0.0843,
"step": 165
},
{
"epoch": 3.25,
"learning_rate": 0.0001,
"loss": 0.0795,
"step": 166
},
{
"epoch": 3.27,
"learning_rate": 0.0001,
"loss": 0.0637,
"step": 167
},
{
"epoch": 3.29,
"learning_rate": 0.0001,
"loss": 0.1107,
"step": 168
},
{
"epoch": 3.31,
"learning_rate": 0.0001,
"loss": 0.0992,
"step": 169
},
{
"epoch": 3.33,
"learning_rate": 0.0001,
"loss": 0.1207,
"step": 170
},
{
"epoch": 3.35,
"learning_rate": 0.0001,
"loss": 0.1326,
"step": 171
},
{
"epoch": 3.37,
"learning_rate": 0.0001,
"loss": 0.1245,
"step": 172
},
{
"epoch": 3.39,
"learning_rate": 0.0001,
"loss": 0.1015,
"step": 173
},
{
"epoch": 3.41,
"learning_rate": 0.0001,
"loss": 0.1348,
"step": 174
},
{
"epoch": 3.43,
"learning_rate": 0.0001,
"loss": 0.0924,
"step": 175
},
{
"epoch": 3.45,
"learning_rate": 0.0001,
"loss": 0.0754,
"step": 176
},
{
"epoch": 3.47,
"learning_rate": 0.0001,
"loss": 0.0845,
"step": 177
},
{
"epoch": 3.49,
"learning_rate": 0.0001,
"loss": 0.0932,
"step": 178
},
{
"epoch": 3.51,
"learning_rate": 0.0001,
"loss": 0.0724,
"step": 179
},
{
"epoch": 3.53,
"learning_rate": 0.0001,
"loss": 0.1453,
"step": 180
},
{
"epoch": 3.55,
"learning_rate": 0.0001,
"loss": 0.085,
"step": 181
},
{
"epoch": 3.57,
"learning_rate": 0.0001,
"loss": 0.1064,
"step": 182
},
{
"epoch": 3.59,
"learning_rate": 0.0001,
"loss": 0.1342,
"step": 183
},
{
"epoch": 3.6,
"learning_rate": 0.0001,
"loss": 0.0963,
"step": 184
},
{
"epoch": 3.62,
"learning_rate": 0.0001,
"loss": 0.0947,
"step": 185
},
{
"epoch": 3.64,
"learning_rate": 0.0001,
"loss": 0.0943,
"step": 186
},
{
"epoch": 3.66,
"learning_rate": 0.0001,
"loss": 0.0976,
"step": 187
},
{
"epoch": 3.68,
"learning_rate": 0.0001,
"loss": 0.1203,
"step": 188
},
{
"epoch": 3.7,
"learning_rate": 0.0001,
"loss": 0.0834,
"step": 189
},
{
"epoch": 3.72,
"learning_rate": 0.0001,
"loss": 0.0934,
"step": 190
},
{
"epoch": 3.74,
"learning_rate": 0.0001,
"loss": 0.1072,
"step": 191
},
{
"epoch": 3.76,
"learning_rate": 0.0001,
"loss": 0.0937,
"step": 192
},
{
"epoch": 3.78,
"learning_rate": 0.0001,
"loss": 0.1134,
"step": 193
},
{
"epoch": 3.8,
"learning_rate": 0.0001,
"loss": 0.0863,
"step": 194
},
{
"epoch": 3.82,
"learning_rate": 0.0001,
"loss": 0.0844,
"step": 195
},
{
"epoch": 3.84,
"learning_rate": 0.0001,
"loss": 0.0777,
"step": 196
},
{
"epoch": 3.86,
"learning_rate": 0.0001,
"loss": 0.1058,
"step": 197
},
{
"epoch": 3.88,
"learning_rate": 0.0001,
"loss": 0.0681,
"step": 198
},
{
"epoch": 3.9,
"learning_rate": 0.0001,
"loss": 0.104,
"step": 199
},
{
"epoch": 3.92,
"learning_rate": 0.0001,
"loss": 0.1114,
"step": 200
},
{
"epoch": 3.94,
"learning_rate": 0.0001,
"loss": 0.0856,
"step": 201
},
{
"epoch": 3.96,
"learning_rate": 0.0001,
"loss": 0.1004,
"step": 202
},
{
"epoch": 3.98,
"learning_rate": 0.0001,
"loss": 0.0996,
"step": 203
},
{
"epoch": 4.0,
"learning_rate": 0.0001,
"loss": 0.106,
"step": 204
},
{
"epoch": 4.0,
"eval_exact_match": 0.0972972972972973,
"eval_exec": 0.32432432432432434,
"eval_loss": 0.7120223045349121,
"eval_runtime": 449.0317,
"eval_samples_per_second": 0.412,
"step": 204
},
{
"epoch": 4.02,
"learning_rate": 0.0001,
"loss": 0.1297,
"step": 205
},
{
"epoch": 4.04,
"learning_rate": 0.0001,
"loss": 0.0774,
"step": 206
},
{
"epoch": 4.06,
"learning_rate": 0.0001,
"loss": 0.0659,
"step": 207
},
{
"epoch": 4.08,
"learning_rate": 0.0001,
"loss": 0.0792,
"step": 208
},
{
"epoch": 4.1,
"learning_rate": 0.0001,
"loss": 0.0985,
"step": 209
},
{
"epoch": 4.12,
"learning_rate": 0.0001,
"loss": 0.0514,
"step": 210
},
{
"epoch": 4.14,
"learning_rate": 0.0001,
"loss": 0.0604,
"step": 211
},
{
"epoch": 4.16,
"learning_rate": 0.0001,
"loss": 0.0675,
"step": 212
},
{
"epoch": 4.18,
"learning_rate": 0.0001,
"loss": 0.0576,
"step": 213
},
{
"epoch": 4.2,
"learning_rate": 0.0001,
"loss": 0.078,
"step": 214
},
{
"epoch": 4.21,
"learning_rate": 0.0001,
"loss": 0.0805,
"step": 215
},
{
"epoch": 4.23,
"learning_rate": 0.0001,
"loss": 0.0904,
"step": 216
},
{
"epoch": 4.25,
"learning_rate": 0.0001,
"loss": 0.0967,
"step": 217
},
{
"epoch": 4.27,
"learning_rate": 0.0001,
"loss": 0.0942,
"step": 218
},
{
"epoch": 4.29,
"learning_rate": 0.0001,
"loss": 0.0799,
"step": 219
},
{
"epoch": 4.31,
"learning_rate": 0.0001,
"loss": 0.0671,
"step": 220
},
{
"epoch": 4.33,
"learning_rate": 0.0001,
"loss": 0.1034,
"step": 221
},
{
"epoch": 4.35,
"learning_rate": 0.0001,
"loss": 0.0911,
"step": 222
},
{
"epoch": 4.37,
"learning_rate": 0.0001,
"loss": 0.0774,
"step": 223
},
{
"epoch": 4.39,
"learning_rate": 0.0001,
"loss": 0.1119,
"step": 224
},
{
"epoch": 4.41,
"learning_rate": 0.0001,
"loss": 0.0818,
"step": 225
},
{
"epoch": 4.43,
"learning_rate": 0.0001,
"loss": 0.0773,
"step": 226
},
{
"epoch": 4.45,
"learning_rate": 0.0001,
"loss": 0.0968,
"step": 227
},
{
"epoch": 4.47,
"learning_rate": 0.0001,
"loss": 0.1008,
"step": 228
},
{
"epoch": 4.49,
"learning_rate": 0.0001,
"loss": 0.0574,
"step": 229
},
{
"epoch": 4.51,
"learning_rate": 0.0001,
"loss": 0.061,
"step": 230
},
{
"epoch": 4.53,
"learning_rate": 0.0001,
"loss": 0.0786,
"step": 231
},
{
"epoch": 4.55,
"learning_rate": 0.0001,
"loss": 0.0886,
"step": 232
},
{
"epoch": 4.57,
"learning_rate": 0.0001,
"loss": 0.0954,
"step": 233
},
{
"epoch": 4.59,
"learning_rate": 0.0001,
"loss": 0.108,
"step": 234
},
{
"epoch": 4.6,
"learning_rate": 0.0001,
"loss": 0.0719,
"step": 235
},
{
"epoch": 4.62,
"learning_rate": 0.0001,
"loss": 0.0765,
"step": 236
},
{
"epoch": 4.64,
"learning_rate": 0.0001,
"loss": 0.0851,
"step": 237
},
{
"epoch": 4.66,
"learning_rate": 0.0001,
"loss": 0.096,
"step": 238
},
{
"epoch": 4.68,
"learning_rate": 0.0001,
"loss": 0.0511,
"step": 239
},
{
"epoch": 4.7,
"learning_rate": 0.0001,
"loss": 0.0501,
"step": 240
},
{
"epoch": 4.72,
"learning_rate": 0.0001,
"loss": 0.0679,
"step": 241
},
{
"epoch": 4.74,
"learning_rate": 0.0001,
"loss": 0.093,
"step": 242
},
{
"epoch": 4.76,
"learning_rate": 0.0001,
"loss": 0.1083,
"step": 243
},
{
"epoch": 4.78,
"learning_rate": 0.0001,
"loss": 0.0522,
"step": 244
},
{
"epoch": 4.8,
"learning_rate": 0.0001,
"loss": 0.0776,
"step": 245
},
{
"epoch": 4.82,
"learning_rate": 0.0001,
"loss": 0.0966,
"step": 246
},
{
"epoch": 4.84,
"learning_rate": 0.0001,
"loss": 0.0802,
"step": 247
},
{
"epoch": 4.86,
"learning_rate": 0.0001,
"loss": 0.09,
"step": 248
},
{
"epoch": 4.88,
"learning_rate": 0.0001,
"loss": 0.0712,
"step": 249
},
{
"epoch": 4.9,
"learning_rate": 0.0001,
"loss": 0.0799,
"step": 250
},
{
"epoch": 4.92,
"learning_rate": 0.0001,
"loss": 0.0656,
"step": 251
},
{
"epoch": 4.94,
"learning_rate": 0.0001,
"loss": 0.0866,
"step": 252
},
{
"epoch": 4.96,
"learning_rate": 0.0001,
"loss": 0.08,
"step": 253
},
{
"epoch": 4.98,
"learning_rate": 0.0001,
"loss": 0.0672,
"step": 254
},
{
"epoch": 5.0,
"learning_rate": 0.0001,
"loss": 0.0688,
"step": 255
},
{
"epoch": 5.0,
"eval_exact_match": 0.14054054054054055,
"eval_exec": 0.34054054054054056,
"eval_loss": 0.741645872592926,
"eval_runtime": 306.251,
"eval_samples_per_second": 0.604,
"step": 255
},
{
"epoch": 5.02,
"learning_rate": 0.0001,
"loss": 0.0818,
"step": 256
},
{
"epoch": 5.04,
"learning_rate": 0.0001,
"loss": 0.0692,
"step": 257
},
{
"epoch": 5.06,
"learning_rate": 0.0001,
"loss": 0.0737,
"step": 258
},
{
"epoch": 5.08,
"learning_rate": 0.0001,
"loss": 0.0571,
"step": 259
},
{
"epoch": 5.1,
"learning_rate": 0.0001,
"loss": 0.0441,
"step": 260
},
{
"epoch": 5.12,
"learning_rate": 0.0001,
"loss": 0.0562,
"step": 261
},
{
"epoch": 5.14,
"learning_rate": 0.0001,
"loss": 0.0673,
"step": 262
},
{
"epoch": 5.16,
"learning_rate": 0.0001,
"loss": 0.0446,
"step": 263
},
{
"epoch": 5.18,
"learning_rate": 0.0001,
"loss": 0.0542,
"step": 264
},
{
"epoch": 5.2,
"learning_rate": 0.0001,
"loss": 0.048,
"step": 265
},
{
"epoch": 5.21,
"learning_rate": 0.0001,
"loss": 0.0445,
"step": 266
},
{
"epoch": 5.23,
"learning_rate": 0.0001,
"loss": 0.0651,
"step": 267
},
{
"epoch": 5.25,
"learning_rate": 0.0001,
"loss": 0.082,
"step": 268
},
{
"epoch": 5.27,
"learning_rate": 0.0001,
"loss": 0.0466,
"step": 269
},
{
"epoch": 5.29,
"learning_rate": 0.0001,
"loss": 0.0723,
"step": 270
},
{
"epoch": 5.31,
"learning_rate": 0.0001,
"loss": 0.0717,
"step": 271
},
{
"epoch": 5.33,
"learning_rate": 0.0001,
"loss": 0.0536,
"step": 272
},
{
"epoch": 5.35,
"learning_rate": 0.0001,
"loss": 0.0645,
"step": 273
},
{
"epoch": 5.37,
"learning_rate": 0.0001,
"loss": 0.1053,
"step": 274
},
{
"epoch": 5.39,
"learning_rate": 0.0001,
"loss": 0.056,
"step": 275
},
{
"epoch": 5.41,
"learning_rate": 0.0001,
"loss": 0.0411,
"step": 276
},
{
"epoch": 5.43,
"learning_rate": 0.0001,
"loss": 0.0595,
"step": 277
},
{
"epoch": 5.45,
"learning_rate": 0.0001,
"loss": 0.0866,
"step": 278
},
{
"epoch": 5.47,
"learning_rate": 0.0001,
"loss": 0.084,
"step": 279
},
{
"epoch": 5.49,
"learning_rate": 0.0001,
"loss": 0.0783,
"step": 280
},
{
"epoch": 5.51,
"learning_rate": 0.0001,
"loss": 0.0582,
"step": 281
},
{
"epoch": 5.53,
"learning_rate": 0.0001,
"loss": 0.0664,
"step": 282
},
{
"epoch": 5.55,
"learning_rate": 0.0001,
"loss": 0.0602,
"step": 283
},
{
"epoch": 5.57,
"learning_rate": 0.0001,
"loss": 0.0694,
"step": 284
},
{
"epoch": 5.59,
"learning_rate": 0.0001,
"loss": 0.0631,
"step": 285
},
{
"epoch": 5.6,
"learning_rate": 0.0001,
"loss": 0.0511,
"step": 286
},
{
"epoch": 5.62,
"learning_rate": 0.0001,
"loss": 0.0687,
"step": 287
},
{
"epoch": 5.64,
"learning_rate": 0.0001,
"loss": 0.0535,
"step": 288
},
{
"epoch": 5.66,
"learning_rate": 0.0001,
"loss": 0.0716,
"step": 289
},
{
"epoch": 5.68,
"learning_rate": 0.0001,
"loss": 0.1022,
"step": 290
},
{
"epoch": 5.7,
"learning_rate": 0.0001,
"loss": 0.085,
"step": 291
},
{
"epoch": 5.72,
"learning_rate": 0.0001,
"loss": 0.0902,
"step": 292
},
{
"epoch": 5.74,
"learning_rate": 0.0001,
"loss": 0.0569,
"step": 293
},
{
"epoch": 5.76,
"learning_rate": 0.0001,
"loss": 0.0672,
"step": 294
},
{
"epoch": 5.78,
"learning_rate": 0.0001,
"loss": 0.079,
"step": 295
},
{
"epoch": 5.8,
"learning_rate": 0.0001,
"loss": 0.0684,
"step": 296
},
{
"epoch": 5.82,
"learning_rate": 0.0001,
"loss": 0.0623,
"step": 297
},
{
"epoch": 5.84,
"learning_rate": 0.0001,
"loss": 0.0619,
"step": 298
},
{
"epoch": 5.86,
"learning_rate": 0.0001,
"loss": 0.0588,
"step": 299
},
{
"epoch": 5.88,
"learning_rate": 0.0001,
"loss": 0.0775,
"step": 300
},
{
"epoch": 5.9,
"learning_rate": 0.0001,
"loss": 0.0496,
"step": 301
},
{
"epoch": 5.92,
"learning_rate": 0.0001,
"loss": 0.053,
"step": 302
},
{
"epoch": 5.94,
"learning_rate": 0.0001,
"loss": 0.0694,
"step": 303
},
{
"epoch": 5.96,
"learning_rate": 0.0001,
"loss": 0.0668,
"step": 304
},
{
"epoch": 5.98,
"learning_rate": 0.0001,
"loss": 0.0718,
"step": 305
},
{
"epoch": 6.0,
"learning_rate": 0.0001,
"loss": 0.0778,
"step": 306
},
{
"epoch": 6.0,
"eval_exact_match": 0.11891891891891893,
"eval_exec": 0.35135135135135137,
"eval_loss": 0.7917532324790955,
"eval_runtime": 308.0693,
"eval_samples_per_second": 0.601,
"step": 306
}
],
"max_steps": 1275,
"num_train_epochs": 25,
"total_flos": 3.882472417839514e+16,
"trial_name": null,
"trial_params": null
}