M4_MLM_cross / checkpoint-393 /trainer_state.json
S2312dal's picture
End of training
cdc7489
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"global_step": 393,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.5e-06,
"loss": 0.3281,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 0.3522,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 7.500000000000001e-06,
"loss": 0.2372,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 1e-05,
"loss": 0.2043,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 1.25e-05,
"loss": 0.3516,
"step": 5
},
{
"epoch": 0.05,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.2391,
"step": 6
},
{
"epoch": 0.05,
"learning_rate": 1.7500000000000002e-05,
"loss": 0.1406,
"step": 7
},
{
"epoch": 0.06,
"learning_rate": 2e-05,
"loss": 0.1592,
"step": 8
},
{
"epoch": 0.07,
"learning_rate": 1.994805194805195e-05,
"loss": 0.2057,
"step": 9
},
{
"epoch": 0.08,
"learning_rate": 1.98961038961039e-05,
"loss": 0.2209,
"step": 10
},
{
"epoch": 0.08,
"learning_rate": 1.9844155844155846e-05,
"loss": 0.2098,
"step": 11
},
{
"epoch": 0.09,
"learning_rate": 1.9792207792207794e-05,
"loss": 0.2233,
"step": 12
},
{
"epoch": 0.1,
"learning_rate": 1.974025974025974e-05,
"loss": 0.1877,
"step": 13
},
{
"epoch": 0.11,
"learning_rate": 1.968831168831169e-05,
"loss": 0.2094,
"step": 14
},
{
"epoch": 0.11,
"learning_rate": 1.963636363636364e-05,
"loss": 0.1608,
"step": 15
},
{
"epoch": 0.12,
"learning_rate": 1.9584415584415586e-05,
"loss": 0.1873,
"step": 16
},
{
"epoch": 0.13,
"learning_rate": 1.9532467532467533e-05,
"loss": 0.2251,
"step": 17
},
{
"epoch": 0.14,
"learning_rate": 1.9480519480519483e-05,
"loss": 0.2143,
"step": 18
},
{
"epoch": 0.15,
"learning_rate": 1.942857142857143e-05,
"loss": 0.179,
"step": 19
},
{
"epoch": 0.15,
"learning_rate": 1.9376623376623377e-05,
"loss": 0.2063,
"step": 20
},
{
"epoch": 0.16,
"learning_rate": 1.9324675324675325e-05,
"loss": 0.1789,
"step": 21
},
{
"epoch": 0.17,
"learning_rate": 1.9272727272727275e-05,
"loss": 0.1918,
"step": 22
},
{
"epoch": 0.18,
"learning_rate": 1.9220779220779222e-05,
"loss": 0.1587,
"step": 23
},
{
"epoch": 0.18,
"learning_rate": 1.916883116883117e-05,
"loss": 0.1268,
"step": 24
},
{
"epoch": 0.19,
"learning_rate": 1.9116883116883117e-05,
"loss": 0.1884,
"step": 25
},
{
"epoch": 0.2,
"learning_rate": 1.9064935064935067e-05,
"loss": 0.2015,
"step": 26
},
{
"epoch": 0.21,
"learning_rate": 1.9012987012987014e-05,
"loss": 0.1141,
"step": 27
},
{
"epoch": 0.21,
"learning_rate": 1.896103896103896e-05,
"loss": 0.2242,
"step": 28
},
{
"epoch": 0.22,
"learning_rate": 1.8909090909090912e-05,
"loss": 0.1462,
"step": 29
},
{
"epoch": 0.23,
"learning_rate": 1.885714285714286e-05,
"loss": 0.1986,
"step": 30
},
{
"epoch": 0.24,
"learning_rate": 1.8805194805194806e-05,
"loss": 0.1237,
"step": 31
},
{
"epoch": 0.24,
"learning_rate": 1.8753246753246753e-05,
"loss": 0.1657,
"step": 32
},
{
"epoch": 0.25,
"learning_rate": 1.8701298701298704e-05,
"loss": 0.1336,
"step": 33
},
{
"epoch": 0.26,
"learning_rate": 1.864935064935065e-05,
"loss": 0.1469,
"step": 34
},
{
"epoch": 0.27,
"learning_rate": 1.8597402597402598e-05,
"loss": 0.1352,
"step": 35
},
{
"epoch": 0.27,
"learning_rate": 1.8545454545454545e-05,
"loss": 0.1617,
"step": 36
},
{
"epoch": 0.28,
"learning_rate": 1.8493506493506496e-05,
"loss": 0.1403,
"step": 37
},
{
"epoch": 0.29,
"learning_rate": 1.8441558441558443e-05,
"loss": 0.1255,
"step": 38
},
{
"epoch": 0.3,
"learning_rate": 1.838961038961039e-05,
"loss": 0.102,
"step": 39
},
{
"epoch": 0.31,
"learning_rate": 1.8337662337662337e-05,
"loss": 0.1318,
"step": 40
},
{
"epoch": 0.31,
"learning_rate": 1.8285714285714288e-05,
"loss": 0.117,
"step": 41
},
{
"epoch": 0.32,
"learning_rate": 1.8233766233766235e-05,
"loss": 0.0931,
"step": 42
},
{
"epoch": 0.33,
"learning_rate": 1.8181818181818182e-05,
"loss": 0.0899,
"step": 43
},
{
"epoch": 0.34,
"learning_rate": 1.812987012987013e-05,
"loss": 0.1517,
"step": 44
},
{
"epoch": 0.34,
"learning_rate": 1.807792207792208e-05,
"loss": 0.1423,
"step": 45
},
{
"epoch": 0.35,
"learning_rate": 1.8025974025974027e-05,
"loss": 0.1418,
"step": 46
},
{
"epoch": 0.36,
"learning_rate": 1.7974025974025974e-05,
"loss": 0.1723,
"step": 47
},
{
"epoch": 0.37,
"learning_rate": 1.792207792207792e-05,
"loss": 0.1797,
"step": 48
},
{
"epoch": 0.37,
"learning_rate": 1.7870129870129872e-05,
"loss": 0.1365,
"step": 49
},
{
"epoch": 0.38,
"learning_rate": 1.781818181818182e-05,
"loss": 0.0738,
"step": 50
},
{
"epoch": 0.39,
"learning_rate": 1.7766233766233766e-05,
"loss": 0.0668,
"step": 51
},
{
"epoch": 0.4,
"learning_rate": 1.7714285714285717e-05,
"loss": 0.1373,
"step": 52
},
{
"epoch": 0.4,
"learning_rate": 1.7662337662337664e-05,
"loss": 0.0799,
"step": 53
},
{
"epoch": 0.41,
"learning_rate": 1.761038961038961e-05,
"loss": 0.1018,
"step": 54
},
{
"epoch": 0.42,
"learning_rate": 1.7558441558441558e-05,
"loss": 0.0802,
"step": 55
},
{
"epoch": 0.43,
"learning_rate": 1.750649350649351e-05,
"loss": 0.1481,
"step": 56
},
{
"epoch": 0.44,
"learning_rate": 1.7454545454545456e-05,
"loss": 0.0631,
"step": 57
},
{
"epoch": 0.44,
"learning_rate": 1.7402597402597403e-05,
"loss": 0.1118,
"step": 58
},
{
"epoch": 0.45,
"learning_rate": 1.735064935064935e-05,
"loss": 0.1086,
"step": 59
},
{
"epoch": 0.46,
"learning_rate": 1.72987012987013e-05,
"loss": 0.1337,
"step": 60
},
{
"epoch": 0.47,
"learning_rate": 1.7246753246753248e-05,
"loss": 0.1397,
"step": 61
},
{
"epoch": 0.47,
"learning_rate": 1.7194805194805195e-05,
"loss": 0.0519,
"step": 62
},
{
"epoch": 0.48,
"learning_rate": 1.7142857142857142e-05,
"loss": 0.1578,
"step": 63
},
{
"epoch": 0.49,
"learning_rate": 1.7090909090909092e-05,
"loss": 0.079,
"step": 64
},
{
"epoch": 0.5,
"learning_rate": 1.703896103896104e-05,
"loss": 0.1342,
"step": 65
},
{
"epoch": 0.5,
"learning_rate": 1.6987012987012987e-05,
"loss": 0.1528,
"step": 66
},
{
"epoch": 0.51,
"learning_rate": 1.6935064935064934e-05,
"loss": 0.1065,
"step": 67
},
{
"epoch": 0.52,
"learning_rate": 1.6883116883116884e-05,
"loss": 0.1988,
"step": 68
},
{
"epoch": 0.53,
"learning_rate": 1.683116883116883e-05,
"loss": 0.2357,
"step": 69
},
{
"epoch": 0.53,
"learning_rate": 1.677922077922078e-05,
"loss": 0.1789,
"step": 70
},
{
"epoch": 0.54,
"learning_rate": 1.672727272727273e-05,
"loss": 0.0914,
"step": 71
},
{
"epoch": 0.55,
"learning_rate": 1.6675324675324676e-05,
"loss": 0.1567,
"step": 72
},
{
"epoch": 0.56,
"learning_rate": 1.6623376623376627e-05,
"loss": 0.124,
"step": 73
},
{
"epoch": 0.56,
"learning_rate": 1.6571428571428574e-05,
"loss": 0.097,
"step": 74
},
{
"epoch": 0.57,
"learning_rate": 1.651948051948052e-05,
"loss": 0.087,
"step": 75
},
{
"epoch": 0.58,
"learning_rate": 1.646753246753247e-05,
"loss": 0.1105,
"step": 76
},
{
"epoch": 0.59,
"learning_rate": 1.641558441558442e-05,
"loss": 0.0719,
"step": 77
},
{
"epoch": 0.6,
"learning_rate": 1.6363636363636366e-05,
"loss": 0.0637,
"step": 78
},
{
"epoch": 0.6,
"learning_rate": 1.6311688311688313e-05,
"loss": 0.0794,
"step": 79
},
{
"epoch": 0.61,
"learning_rate": 1.6259740259740264e-05,
"loss": 0.125,
"step": 80
},
{
"epoch": 0.62,
"learning_rate": 1.620779220779221e-05,
"loss": 0.1411,
"step": 81
},
{
"epoch": 0.63,
"learning_rate": 1.6155844155844158e-05,
"loss": 0.0768,
"step": 82
},
{
"epoch": 0.63,
"learning_rate": 1.6103896103896105e-05,
"loss": 0.0986,
"step": 83
},
{
"epoch": 0.64,
"learning_rate": 1.6051948051948056e-05,
"loss": 0.0743,
"step": 84
},
{
"epoch": 0.65,
"learning_rate": 1.6000000000000003e-05,
"loss": 0.0504,
"step": 85
},
{
"epoch": 0.66,
"learning_rate": 1.594805194805195e-05,
"loss": 0.0588,
"step": 86
},
{
"epoch": 0.66,
"learning_rate": 1.5896103896103897e-05,
"loss": 0.0699,
"step": 87
},
{
"epoch": 0.67,
"learning_rate": 1.5844155844155847e-05,
"loss": 0.1118,
"step": 88
},
{
"epoch": 0.68,
"learning_rate": 1.5792207792207795e-05,
"loss": 0.0397,
"step": 89
},
{
"epoch": 0.69,
"learning_rate": 1.5740259740259742e-05,
"loss": 0.0709,
"step": 90
},
{
"epoch": 0.69,
"learning_rate": 1.568831168831169e-05,
"loss": 0.0757,
"step": 91
},
{
"epoch": 0.7,
"learning_rate": 1.563636363636364e-05,
"loss": 0.0669,
"step": 92
},
{
"epoch": 0.71,
"learning_rate": 1.5584415584415587e-05,
"loss": 0.1155,
"step": 93
},
{
"epoch": 0.72,
"learning_rate": 1.5532467532467534e-05,
"loss": 0.0716,
"step": 94
},
{
"epoch": 0.73,
"learning_rate": 1.548051948051948e-05,
"loss": 0.0836,
"step": 95
},
{
"epoch": 0.73,
"learning_rate": 1.542857142857143e-05,
"loss": 0.0805,
"step": 96
},
{
"epoch": 0.74,
"learning_rate": 1.537662337662338e-05,
"loss": 0.0519,
"step": 97
},
{
"epoch": 0.75,
"learning_rate": 1.5324675324675326e-05,
"loss": 0.0903,
"step": 98
},
{
"epoch": 0.76,
"learning_rate": 1.5272727272727276e-05,
"loss": 0.1128,
"step": 99
},
{
"epoch": 0.76,
"learning_rate": 1.5220779220779223e-05,
"loss": 0.0448,
"step": 100
},
{
"epoch": 0.77,
"learning_rate": 1.516883116883117e-05,
"loss": 0.0941,
"step": 101
},
{
"epoch": 0.78,
"learning_rate": 1.511688311688312e-05,
"loss": 0.0782,
"step": 102
},
{
"epoch": 0.79,
"learning_rate": 1.5064935064935066e-05,
"loss": 0.1422,
"step": 103
},
{
"epoch": 0.79,
"learning_rate": 1.5012987012987015e-05,
"loss": 0.1379,
"step": 104
},
{
"epoch": 0.8,
"learning_rate": 1.4961038961038962e-05,
"loss": 0.1574,
"step": 105
},
{
"epoch": 0.81,
"learning_rate": 1.4909090909090911e-05,
"loss": 0.0878,
"step": 106
},
{
"epoch": 0.82,
"learning_rate": 1.4857142857142858e-05,
"loss": 0.0585,
"step": 107
},
{
"epoch": 0.82,
"learning_rate": 1.4805194805194807e-05,
"loss": 0.0342,
"step": 108
},
{
"epoch": 0.83,
"learning_rate": 1.4753246753246754e-05,
"loss": 0.1312,
"step": 109
},
{
"epoch": 0.84,
"learning_rate": 1.4701298701298703e-05,
"loss": 0.0919,
"step": 110
},
{
"epoch": 0.85,
"learning_rate": 1.464935064935065e-05,
"loss": 0.0693,
"step": 111
},
{
"epoch": 0.85,
"learning_rate": 1.45974025974026e-05,
"loss": 0.0661,
"step": 112
},
{
"epoch": 0.86,
"learning_rate": 1.4545454545454546e-05,
"loss": 0.0699,
"step": 113
},
{
"epoch": 0.87,
"learning_rate": 1.4493506493506495e-05,
"loss": 0.0784,
"step": 114
},
{
"epoch": 0.88,
"learning_rate": 1.4441558441558442e-05,
"loss": 0.0854,
"step": 115
},
{
"epoch": 0.89,
"learning_rate": 1.4389610389610391e-05,
"loss": 0.1409,
"step": 116
},
{
"epoch": 0.89,
"learning_rate": 1.433766233766234e-05,
"loss": 0.0833,
"step": 117
},
{
"epoch": 0.9,
"learning_rate": 1.4285714285714287e-05,
"loss": 0.068,
"step": 118
},
{
"epoch": 0.91,
"learning_rate": 1.4233766233766236e-05,
"loss": 0.0484,
"step": 119
},
{
"epoch": 0.92,
"learning_rate": 1.4181818181818183e-05,
"loss": 0.1664,
"step": 120
},
{
"epoch": 0.92,
"learning_rate": 1.4129870129870132e-05,
"loss": 0.1496,
"step": 121
},
{
"epoch": 0.93,
"learning_rate": 1.4077922077922079e-05,
"loss": 0.0956,
"step": 122
},
{
"epoch": 0.94,
"learning_rate": 1.4025974025974028e-05,
"loss": 0.0733,
"step": 123
},
{
"epoch": 0.95,
"learning_rate": 1.3974025974025975e-05,
"loss": 0.0785,
"step": 124
},
{
"epoch": 0.95,
"learning_rate": 1.3922077922077924e-05,
"loss": 0.1201,
"step": 125
},
{
"epoch": 0.96,
"learning_rate": 1.3870129870129871e-05,
"loss": 0.0393,
"step": 126
},
{
"epoch": 0.97,
"learning_rate": 1.381818181818182e-05,
"loss": 0.1055,
"step": 127
},
{
"epoch": 0.98,
"learning_rate": 1.3766233766233767e-05,
"loss": 0.0835,
"step": 128
},
{
"epoch": 0.98,
"learning_rate": 1.3714285714285716e-05,
"loss": 0.043,
"step": 129
},
{
"epoch": 0.99,
"learning_rate": 1.3662337662337663e-05,
"loss": 0.2135,
"step": 130
},
{
"epoch": 1.0,
"learning_rate": 1.3610389610389612e-05,
"loss": 0.0353,
"step": 131
},
{
"epoch": 1.0,
"eval_loss": 0.0589701272547245,
"eval_pearson": 0.8326156177710631,
"eval_runtime": 3.859,
"eval_samples_per_second": 60.119,
"eval_spearmanr": 0.8224932979448152,
"eval_steps_per_second": 3.887,
"step": 131
},
{
"epoch": 1.01,
"learning_rate": 1.3558441558441559e-05,
"loss": 0.0296,
"step": 132
},
{
"epoch": 1.02,
"learning_rate": 1.3506493506493508e-05,
"loss": 0.0956,
"step": 133
},
{
"epoch": 1.02,
"learning_rate": 1.3454545454545455e-05,
"loss": 0.0395,
"step": 134
},
{
"epoch": 1.03,
"learning_rate": 1.3402597402597404e-05,
"loss": 0.0647,
"step": 135
},
{
"epoch": 1.04,
"learning_rate": 1.3350649350649351e-05,
"loss": 0.0594,
"step": 136
},
{
"epoch": 1.05,
"learning_rate": 1.32987012987013e-05,
"loss": 0.0355,
"step": 137
},
{
"epoch": 1.05,
"learning_rate": 1.3246753246753249e-05,
"loss": 0.1092,
"step": 138
},
{
"epoch": 1.06,
"learning_rate": 1.3194805194805196e-05,
"loss": 0.0696,
"step": 139
},
{
"epoch": 1.07,
"learning_rate": 1.3142857142857145e-05,
"loss": 0.0688,
"step": 140
},
{
"epoch": 1.08,
"learning_rate": 1.3090909090909092e-05,
"loss": 0.0557,
"step": 141
},
{
"epoch": 1.08,
"learning_rate": 1.303896103896104e-05,
"loss": 0.0349,
"step": 142
},
{
"epoch": 1.09,
"learning_rate": 1.2987012987012988e-05,
"loss": 0.0834,
"step": 143
},
{
"epoch": 1.1,
"learning_rate": 1.2935064935064937e-05,
"loss": 0.0609,
"step": 144
},
{
"epoch": 1.11,
"learning_rate": 1.2883116883116884e-05,
"loss": 0.0893,
"step": 145
},
{
"epoch": 1.11,
"learning_rate": 1.2831168831168832e-05,
"loss": 0.0558,
"step": 146
},
{
"epoch": 1.12,
"learning_rate": 1.277922077922078e-05,
"loss": 0.026,
"step": 147
},
{
"epoch": 1.13,
"learning_rate": 1.2727272727272728e-05,
"loss": 0.0391,
"step": 148
},
{
"epoch": 1.14,
"learning_rate": 1.2675324675324676e-05,
"loss": 0.0347,
"step": 149
},
{
"epoch": 1.15,
"learning_rate": 1.2623376623376624e-05,
"loss": 0.0587,
"step": 150
},
{
"epoch": 1.15,
"learning_rate": 1.2571428571428572e-05,
"loss": 0.0304,
"step": 151
},
{
"epoch": 1.16,
"learning_rate": 1.251948051948052e-05,
"loss": 0.0639,
"step": 152
},
{
"epoch": 1.17,
"learning_rate": 1.2467532467532468e-05,
"loss": 0.0583,
"step": 153
},
{
"epoch": 1.18,
"learning_rate": 1.2415584415584416e-05,
"loss": 0.123,
"step": 154
},
{
"epoch": 1.18,
"learning_rate": 1.2363636363636364e-05,
"loss": 0.0623,
"step": 155
},
{
"epoch": 1.19,
"learning_rate": 1.2311688311688312e-05,
"loss": 0.0276,
"step": 156
},
{
"epoch": 1.2,
"learning_rate": 1.2259740259740261e-05,
"loss": 0.032,
"step": 157
},
{
"epoch": 1.21,
"learning_rate": 1.2207792207792208e-05,
"loss": 0.0449,
"step": 158
},
{
"epoch": 1.21,
"learning_rate": 1.2155844155844157e-05,
"loss": 0.0714,
"step": 159
},
{
"epoch": 1.22,
"learning_rate": 1.2103896103896104e-05,
"loss": 0.0722,
"step": 160
},
{
"epoch": 1.23,
"learning_rate": 1.2051948051948053e-05,
"loss": 0.0407,
"step": 161
},
{
"epoch": 1.24,
"learning_rate": 1.2e-05,
"loss": 0.0308,
"step": 162
},
{
"epoch": 1.24,
"learning_rate": 1.1948051948051949e-05,
"loss": 0.0235,
"step": 163
},
{
"epoch": 1.25,
"learning_rate": 1.1896103896103896e-05,
"loss": 0.0852,
"step": 164
},
{
"epoch": 1.26,
"learning_rate": 1.1844155844155845e-05,
"loss": 0.0386,
"step": 165
},
{
"epoch": 1.27,
"learning_rate": 1.1792207792207792e-05,
"loss": 0.0358,
"step": 166
},
{
"epoch": 1.27,
"learning_rate": 1.1740259740259741e-05,
"loss": 0.1125,
"step": 167
},
{
"epoch": 1.28,
"learning_rate": 1.1688311688311688e-05,
"loss": 0.052,
"step": 168
},
{
"epoch": 1.29,
"learning_rate": 1.1636363636363637e-05,
"loss": 0.0377,
"step": 169
},
{
"epoch": 1.3,
"learning_rate": 1.1584415584415584e-05,
"loss": 0.0505,
"step": 170
},
{
"epoch": 1.31,
"learning_rate": 1.1532467532467533e-05,
"loss": 0.044,
"step": 171
},
{
"epoch": 1.31,
"learning_rate": 1.148051948051948e-05,
"loss": 0.0426,
"step": 172
},
{
"epoch": 1.32,
"learning_rate": 1.1428571428571429e-05,
"loss": 0.0364,
"step": 173
},
{
"epoch": 1.33,
"learning_rate": 1.1376623376623376e-05,
"loss": 0.0389,
"step": 174
},
{
"epoch": 1.34,
"learning_rate": 1.1324675324675325e-05,
"loss": 0.0569,
"step": 175
},
{
"epoch": 1.34,
"learning_rate": 1.1272727272727272e-05,
"loss": 0.0392,
"step": 176
},
{
"epoch": 1.35,
"learning_rate": 1.1220779220779221e-05,
"loss": 0.0828,
"step": 177
},
{
"epoch": 1.36,
"learning_rate": 1.116883116883117e-05,
"loss": 0.0564,
"step": 178
},
{
"epoch": 1.37,
"learning_rate": 1.1116883116883117e-05,
"loss": 0.0628,
"step": 179
},
{
"epoch": 1.37,
"learning_rate": 1.1064935064935066e-05,
"loss": 0.0632,
"step": 180
},
{
"epoch": 1.38,
"learning_rate": 1.1012987012987013e-05,
"loss": 0.074,
"step": 181
},
{
"epoch": 1.39,
"learning_rate": 1.0961038961038962e-05,
"loss": 0.0342,
"step": 182
},
{
"epoch": 1.4,
"learning_rate": 1.0909090909090909e-05,
"loss": 0.1477,
"step": 183
},
{
"epoch": 1.4,
"learning_rate": 1.0857142857142858e-05,
"loss": 0.0523,
"step": 184
},
{
"epoch": 1.41,
"learning_rate": 1.0805194805194805e-05,
"loss": 0.0695,
"step": 185
},
{
"epoch": 1.42,
"learning_rate": 1.0753246753246754e-05,
"loss": 0.0299,
"step": 186
},
{
"epoch": 1.43,
"learning_rate": 1.0701298701298701e-05,
"loss": 0.0528,
"step": 187
},
{
"epoch": 1.44,
"learning_rate": 1.064935064935065e-05,
"loss": 0.0393,
"step": 188
},
{
"epoch": 1.44,
"learning_rate": 1.0597402597402597e-05,
"loss": 0.0349,
"step": 189
},
{
"epoch": 1.45,
"learning_rate": 1.0545454545454546e-05,
"loss": 0.0496,
"step": 190
},
{
"epoch": 1.46,
"learning_rate": 1.0493506493506493e-05,
"loss": 0.0342,
"step": 191
},
{
"epoch": 1.47,
"learning_rate": 1.0441558441558442e-05,
"loss": 0.0352,
"step": 192
},
{
"epoch": 1.47,
"learning_rate": 1.0389610389610389e-05,
"loss": 0.1237,
"step": 193
},
{
"epoch": 1.48,
"learning_rate": 1.0337662337662338e-05,
"loss": 0.026,
"step": 194
},
{
"epoch": 1.49,
"learning_rate": 1.0285714285714285e-05,
"loss": 0.0519,
"step": 195
},
{
"epoch": 1.5,
"learning_rate": 1.0233766233766234e-05,
"loss": 0.0343,
"step": 196
},
{
"epoch": 1.5,
"learning_rate": 1.0181818181818182e-05,
"loss": 0.1232,
"step": 197
},
{
"epoch": 1.51,
"learning_rate": 1.012987012987013e-05,
"loss": 0.0244,
"step": 198
},
{
"epoch": 1.52,
"learning_rate": 1.0077922077922078e-05,
"loss": 0.0435,
"step": 199
},
{
"epoch": 1.53,
"learning_rate": 1.0025974025974026e-05,
"loss": 0.0394,
"step": 200
},
{
"epoch": 1.53,
"learning_rate": 9.974025974025974e-06,
"loss": 0.0504,
"step": 201
},
{
"epoch": 1.54,
"learning_rate": 9.922077922077923e-06,
"loss": 0.0303,
"step": 202
},
{
"epoch": 1.55,
"learning_rate": 9.87012987012987e-06,
"loss": 0.035,
"step": 203
},
{
"epoch": 1.56,
"learning_rate": 9.81818181818182e-06,
"loss": 0.0338,
"step": 204
},
{
"epoch": 1.56,
"learning_rate": 9.766233766233766e-06,
"loss": 0.0388,
"step": 205
},
{
"epoch": 1.57,
"learning_rate": 9.714285714285715e-06,
"loss": 0.0204,
"step": 206
},
{
"epoch": 1.58,
"learning_rate": 9.662337662337662e-06,
"loss": 0.0424,
"step": 207
},
{
"epoch": 1.59,
"learning_rate": 9.610389610389611e-06,
"loss": 0.1209,
"step": 208
},
{
"epoch": 1.6,
"learning_rate": 9.558441558441558e-06,
"loss": 0.039,
"step": 209
},
{
"epoch": 1.6,
"learning_rate": 9.506493506493507e-06,
"loss": 0.0532,
"step": 210
},
{
"epoch": 1.61,
"learning_rate": 9.454545454545456e-06,
"loss": 0.0427,
"step": 211
},
{
"epoch": 1.62,
"learning_rate": 9.402597402597403e-06,
"loss": 0.0528,
"step": 212
},
{
"epoch": 1.63,
"learning_rate": 9.350649350649352e-06,
"loss": 0.063,
"step": 213
},
{
"epoch": 1.63,
"learning_rate": 9.298701298701299e-06,
"loss": 0.0272,
"step": 214
},
{
"epoch": 1.64,
"learning_rate": 9.246753246753248e-06,
"loss": 0.0436,
"step": 215
},
{
"epoch": 1.65,
"learning_rate": 9.194805194805195e-06,
"loss": 0.0317,
"step": 216
},
{
"epoch": 1.66,
"learning_rate": 9.142857142857144e-06,
"loss": 0.0459,
"step": 217
},
{
"epoch": 1.66,
"learning_rate": 9.090909090909091e-06,
"loss": 0.0465,
"step": 218
},
{
"epoch": 1.67,
"learning_rate": 9.03896103896104e-06,
"loss": 0.0398,
"step": 219
},
{
"epoch": 1.68,
"learning_rate": 8.987012987012987e-06,
"loss": 0.0361,
"step": 220
},
{
"epoch": 1.69,
"learning_rate": 8.935064935064936e-06,
"loss": 0.0452,
"step": 221
},
{
"epoch": 1.69,
"learning_rate": 8.883116883116883e-06,
"loss": 0.0308,
"step": 222
},
{
"epoch": 1.7,
"learning_rate": 8.831168831168832e-06,
"loss": 0.0434,
"step": 223
},
{
"epoch": 1.71,
"learning_rate": 8.779220779220779e-06,
"loss": 0.0484,
"step": 224
},
{
"epoch": 1.72,
"learning_rate": 8.727272727272728e-06,
"loss": 0.0371,
"step": 225
},
{
"epoch": 1.73,
"learning_rate": 8.675324675324675e-06,
"loss": 0.028,
"step": 226
},
{
"epoch": 1.73,
"learning_rate": 8.623376623376624e-06,
"loss": 0.0625,
"step": 227
},
{
"epoch": 1.74,
"learning_rate": 8.571428571428571e-06,
"loss": 0.0986,
"step": 228
},
{
"epoch": 1.75,
"learning_rate": 8.51948051948052e-06,
"loss": 0.0389,
"step": 229
},
{
"epoch": 1.76,
"learning_rate": 8.467532467532467e-06,
"loss": 0.0575,
"step": 230
},
{
"epoch": 1.76,
"learning_rate": 8.415584415584416e-06,
"loss": 0.0304,
"step": 231
},
{
"epoch": 1.77,
"learning_rate": 8.363636363636365e-06,
"loss": 0.0548,
"step": 232
},
{
"epoch": 1.78,
"learning_rate": 8.311688311688313e-06,
"loss": 0.0157,
"step": 233
},
{
"epoch": 1.79,
"learning_rate": 8.25974025974026e-06,
"loss": 0.0265,
"step": 234
},
{
"epoch": 1.79,
"learning_rate": 8.20779220779221e-06,
"loss": 0.042,
"step": 235
},
{
"epoch": 1.8,
"learning_rate": 8.155844155844157e-06,
"loss": 0.0515,
"step": 236
},
{
"epoch": 1.81,
"learning_rate": 8.103896103896105e-06,
"loss": 0.0408,
"step": 237
},
{
"epoch": 1.82,
"learning_rate": 8.051948051948052e-06,
"loss": 0.0163,
"step": 238
},
{
"epoch": 1.82,
"learning_rate": 8.000000000000001e-06,
"loss": 0.0286,
"step": 239
},
{
"epoch": 1.83,
"learning_rate": 7.948051948051948e-06,
"loss": 0.0437,
"step": 240
},
{
"epoch": 1.84,
"learning_rate": 7.896103896103897e-06,
"loss": 0.0407,
"step": 241
},
{
"epoch": 1.85,
"learning_rate": 7.844155844155844e-06,
"loss": 0.046,
"step": 242
},
{
"epoch": 1.85,
"learning_rate": 7.792207792207793e-06,
"loss": 0.0162,
"step": 243
},
{
"epoch": 1.86,
"learning_rate": 7.74025974025974e-06,
"loss": 0.0498,
"step": 244
},
{
"epoch": 1.87,
"learning_rate": 7.68831168831169e-06,
"loss": 0.0766,
"step": 245
},
{
"epoch": 1.88,
"learning_rate": 7.636363636363638e-06,
"loss": 0.0149,
"step": 246
},
{
"epoch": 1.89,
"learning_rate": 7.584415584415585e-06,
"loss": 0.0431,
"step": 247
},
{
"epoch": 1.89,
"learning_rate": 7.532467532467533e-06,
"loss": 0.0107,
"step": 248
},
{
"epoch": 1.9,
"learning_rate": 7.480519480519481e-06,
"loss": 0.0189,
"step": 249
},
{
"epoch": 1.91,
"learning_rate": 7.428571428571429e-06,
"loss": 0.0355,
"step": 250
},
{
"epoch": 1.92,
"learning_rate": 7.376623376623377e-06,
"loss": 0.0275,
"step": 251
},
{
"epoch": 1.92,
"learning_rate": 7.324675324675325e-06,
"loss": 0.0337,
"step": 252
},
{
"epoch": 1.93,
"learning_rate": 7.272727272727273e-06,
"loss": 0.0262,
"step": 253
},
{
"epoch": 1.94,
"learning_rate": 7.220779220779221e-06,
"loss": 0.012,
"step": 254
},
{
"epoch": 1.95,
"learning_rate": 7.16883116883117e-06,
"loss": 0.0682,
"step": 255
},
{
"epoch": 1.95,
"learning_rate": 7.116883116883118e-06,
"loss": 0.0455,
"step": 256
},
{
"epoch": 1.96,
"learning_rate": 7.064935064935066e-06,
"loss": 0.0277,
"step": 257
},
{
"epoch": 1.97,
"learning_rate": 7.012987012987014e-06,
"loss": 0.059,
"step": 258
},
{
"epoch": 1.98,
"learning_rate": 6.961038961038962e-06,
"loss": 0.0511,
"step": 259
},
{
"epoch": 1.98,
"learning_rate": 6.90909090909091e-06,
"loss": 0.0355,
"step": 260
},
{
"epoch": 1.99,
"learning_rate": 6.857142857142858e-06,
"loss": 0.0559,
"step": 261
},
{
"epoch": 2.0,
"learning_rate": 6.805194805194806e-06,
"loss": 0.0478,
"step": 262
},
{
"epoch": 2.0,
"eval_loss": 0.036842476576566696,
"eval_pearson": 0.9234436553897939,
"eval_runtime": 3.2412,
"eval_samples_per_second": 71.578,
"eval_spearmanr": 0.889384223771582,
"eval_steps_per_second": 4.628,
"step": 262
},
{
"epoch": 2.01,
"learning_rate": 6.753246753246754e-06,
"loss": 0.0161,
"step": 263
},
{
"epoch": 2.02,
"learning_rate": 6.701298701298702e-06,
"loss": 0.0284,
"step": 264
},
{
"epoch": 2.02,
"learning_rate": 6.64935064935065e-06,
"loss": 0.0214,
"step": 265
},
{
"epoch": 2.03,
"learning_rate": 6.597402597402598e-06,
"loss": 0.0182,
"step": 266
},
{
"epoch": 2.04,
"learning_rate": 6.545454545454546e-06,
"loss": 0.0219,
"step": 267
},
{
"epoch": 2.05,
"learning_rate": 6.493506493506494e-06,
"loss": 0.0238,
"step": 268
},
{
"epoch": 2.05,
"learning_rate": 6.441558441558442e-06,
"loss": 0.0067,
"step": 269
},
{
"epoch": 2.06,
"learning_rate": 6.38961038961039e-06,
"loss": 0.0102,
"step": 270
},
{
"epoch": 2.07,
"learning_rate": 6.337662337662338e-06,
"loss": 0.0617,
"step": 271
},
{
"epoch": 2.08,
"learning_rate": 6.285714285714286e-06,
"loss": 0.02,
"step": 272
},
{
"epoch": 2.08,
"learning_rate": 6.233766233766234e-06,
"loss": 0.072,
"step": 273
},
{
"epoch": 2.09,
"learning_rate": 6.181818181818182e-06,
"loss": 0.0175,
"step": 274
},
{
"epoch": 2.1,
"learning_rate": 6.129870129870131e-06,
"loss": 0.0222,
"step": 275
},
{
"epoch": 2.11,
"learning_rate": 6.077922077922079e-06,
"loss": 0.0139,
"step": 276
},
{
"epoch": 2.11,
"learning_rate": 6.025974025974027e-06,
"loss": 0.0141,
"step": 277
},
{
"epoch": 2.12,
"learning_rate": 5.9740259740259746e-06,
"loss": 0.0287,
"step": 278
},
{
"epoch": 2.13,
"learning_rate": 5.9220779220779226e-06,
"loss": 0.0309,
"step": 279
},
{
"epoch": 2.14,
"learning_rate": 5.8701298701298705e-06,
"loss": 0.0202,
"step": 280
},
{
"epoch": 2.15,
"learning_rate": 5.8181818181818185e-06,
"loss": 0.0287,
"step": 281
},
{
"epoch": 2.15,
"learning_rate": 5.7662337662337665e-06,
"loss": 0.0191,
"step": 282
},
{
"epoch": 2.16,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.0159,
"step": 283
},
{
"epoch": 2.17,
"learning_rate": 5.6623376623376625e-06,
"loss": 0.0166,
"step": 284
},
{
"epoch": 2.18,
"learning_rate": 5.6103896103896105e-06,
"loss": 0.0159,
"step": 285
},
{
"epoch": 2.18,
"learning_rate": 5.5584415584415585e-06,
"loss": 0.0225,
"step": 286
},
{
"epoch": 2.19,
"learning_rate": 5.5064935064935065e-06,
"loss": 0.0401,
"step": 287
},
{
"epoch": 2.2,
"learning_rate": 5.4545454545454545e-06,
"loss": 0.0174,
"step": 288
},
{
"epoch": 2.21,
"learning_rate": 5.4025974025974024e-06,
"loss": 0.0245,
"step": 289
},
{
"epoch": 2.21,
"learning_rate": 5.3506493506493504e-06,
"loss": 0.0041,
"step": 290
},
{
"epoch": 2.22,
"learning_rate": 5.298701298701298e-06,
"loss": 0.042,
"step": 291
},
{
"epoch": 2.23,
"learning_rate": 5.246753246753246e-06,
"loss": 0.0181,
"step": 292
},
{
"epoch": 2.24,
"learning_rate": 5.194805194805194e-06,
"loss": 0.0214,
"step": 293
},
{
"epoch": 2.24,
"learning_rate": 5.142857142857142e-06,
"loss": 0.0181,
"step": 294
},
{
"epoch": 2.25,
"learning_rate": 5.090909090909091e-06,
"loss": 0.0206,
"step": 295
},
{
"epoch": 2.26,
"learning_rate": 5.038961038961039e-06,
"loss": 0.0281,
"step": 296
},
{
"epoch": 2.27,
"learning_rate": 4.987012987012987e-06,
"loss": 0.0257,
"step": 297
},
{
"epoch": 2.27,
"learning_rate": 4.935064935064935e-06,
"loss": 0.0253,
"step": 298
},
{
"epoch": 2.28,
"learning_rate": 4.883116883116883e-06,
"loss": 0.0874,
"step": 299
},
{
"epoch": 2.29,
"learning_rate": 4.831168831168831e-06,
"loss": 0.0167,
"step": 300
},
{
"epoch": 2.3,
"learning_rate": 4.779220779220779e-06,
"loss": 0.0159,
"step": 301
},
{
"epoch": 2.31,
"learning_rate": 4.727272727272728e-06,
"loss": 0.0232,
"step": 302
},
{
"epoch": 2.31,
"learning_rate": 4.675324675324676e-06,
"loss": 0.015,
"step": 303
},
{
"epoch": 2.32,
"learning_rate": 4.623376623376624e-06,
"loss": 0.0248,
"step": 304
},
{
"epoch": 2.33,
"learning_rate": 4.571428571428572e-06,
"loss": 0.033,
"step": 305
},
{
"epoch": 2.34,
"learning_rate": 4.51948051948052e-06,
"loss": 0.0153,
"step": 306
},
{
"epoch": 2.34,
"learning_rate": 4.467532467532468e-06,
"loss": 0.0087,
"step": 307
},
{
"epoch": 2.35,
"learning_rate": 4.415584415584416e-06,
"loss": 0.0622,
"step": 308
},
{
"epoch": 2.36,
"learning_rate": 4.363636363636364e-06,
"loss": 0.02,
"step": 309
},
{
"epoch": 2.37,
"learning_rate": 4.311688311688312e-06,
"loss": 0.0434,
"step": 310
},
{
"epoch": 2.37,
"learning_rate": 4.25974025974026e-06,
"loss": 0.0118,
"step": 311
},
{
"epoch": 2.38,
"learning_rate": 4.207792207792208e-06,
"loss": 0.0527,
"step": 312
},
{
"epoch": 2.39,
"learning_rate": 4.155844155844157e-06,
"loss": 0.012,
"step": 313
},
{
"epoch": 2.4,
"learning_rate": 4.103896103896105e-06,
"loss": 0.0136,
"step": 314
},
{
"epoch": 2.4,
"learning_rate": 4.051948051948053e-06,
"loss": 0.0072,
"step": 315
},
{
"epoch": 2.41,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0309,
"step": 316
},
{
"epoch": 2.42,
"learning_rate": 3.948051948051949e-06,
"loss": 0.0141,
"step": 317
},
{
"epoch": 2.43,
"learning_rate": 3.896103896103897e-06,
"loss": 0.0372,
"step": 318
},
{
"epoch": 2.44,
"learning_rate": 3.844155844155845e-06,
"loss": 0.0052,
"step": 319
},
{
"epoch": 2.44,
"learning_rate": 3.7922077922077926e-06,
"loss": 0.0354,
"step": 320
},
{
"epoch": 2.45,
"learning_rate": 3.7402597402597406e-06,
"loss": 0.0295,
"step": 321
},
{
"epoch": 2.46,
"learning_rate": 3.6883116883116886e-06,
"loss": 0.0083,
"step": 322
},
{
"epoch": 2.47,
"learning_rate": 3.6363636363636366e-06,
"loss": 0.012,
"step": 323
},
{
"epoch": 2.47,
"learning_rate": 3.584415584415585e-06,
"loss": 0.0414,
"step": 324
},
{
"epoch": 2.48,
"learning_rate": 3.532467532467533e-06,
"loss": 0.0368,
"step": 325
},
{
"epoch": 2.49,
"learning_rate": 3.480519480519481e-06,
"loss": 0.0187,
"step": 326
},
{
"epoch": 2.5,
"learning_rate": 3.428571428571429e-06,
"loss": 0.0699,
"step": 327
},
{
"epoch": 2.5,
"learning_rate": 3.376623376623377e-06,
"loss": 0.0115,
"step": 328
},
{
"epoch": 2.51,
"learning_rate": 3.324675324675325e-06,
"loss": 0.0456,
"step": 329
},
{
"epoch": 2.52,
"learning_rate": 3.272727272727273e-06,
"loss": 0.0257,
"step": 330
},
{
"epoch": 2.53,
"learning_rate": 3.220779220779221e-06,
"loss": 0.0106,
"step": 331
},
{
"epoch": 2.53,
"learning_rate": 3.168831168831169e-06,
"loss": 0.0229,
"step": 332
},
{
"epoch": 2.54,
"learning_rate": 3.116883116883117e-06,
"loss": 0.0115,
"step": 333
},
{
"epoch": 2.55,
"learning_rate": 3.0649350649350653e-06,
"loss": 0.023,
"step": 334
},
{
"epoch": 2.56,
"learning_rate": 3.0129870129870133e-06,
"loss": 0.03,
"step": 335
},
{
"epoch": 2.56,
"learning_rate": 2.9610389610389613e-06,
"loss": 0.0634,
"step": 336
},
{
"epoch": 2.57,
"learning_rate": 2.9090909090909093e-06,
"loss": 0.0905,
"step": 337
},
{
"epoch": 2.58,
"learning_rate": 2.8571428571428573e-06,
"loss": 0.0162,
"step": 338
},
{
"epoch": 2.59,
"learning_rate": 2.8051948051948052e-06,
"loss": 0.0322,
"step": 339
},
{
"epoch": 2.6,
"learning_rate": 2.7532467532467532e-06,
"loss": 0.0158,
"step": 340
},
{
"epoch": 2.6,
"learning_rate": 2.7012987012987012e-06,
"loss": 0.0178,
"step": 341
},
{
"epoch": 2.61,
"learning_rate": 2.649350649350649e-06,
"loss": 0.0344,
"step": 342
},
{
"epoch": 2.62,
"learning_rate": 2.597402597402597e-06,
"loss": 0.0182,
"step": 343
},
{
"epoch": 2.63,
"learning_rate": 2.5454545454545456e-06,
"loss": 0.0236,
"step": 344
},
{
"epoch": 2.63,
"learning_rate": 2.4935064935064936e-06,
"loss": 0.0245,
"step": 345
},
{
"epoch": 2.64,
"learning_rate": 2.4415584415584416e-06,
"loss": 0.0112,
"step": 346
},
{
"epoch": 2.65,
"learning_rate": 2.3896103896103896e-06,
"loss": 0.0205,
"step": 347
},
{
"epoch": 2.66,
"learning_rate": 2.337662337662338e-06,
"loss": 0.0217,
"step": 348
},
{
"epoch": 2.66,
"learning_rate": 2.285714285714286e-06,
"loss": 0.0483,
"step": 349
},
{
"epoch": 2.67,
"learning_rate": 2.233766233766234e-06,
"loss": 0.015,
"step": 350
},
{
"epoch": 2.68,
"learning_rate": 2.181818181818182e-06,
"loss": 0.0103,
"step": 351
},
{
"epoch": 2.69,
"learning_rate": 2.12987012987013e-06,
"loss": 0.0184,
"step": 352
},
{
"epoch": 2.69,
"learning_rate": 2.0779220779220784e-06,
"loss": 0.0181,
"step": 353
},
{
"epoch": 2.7,
"learning_rate": 2.0259740259740263e-06,
"loss": 0.0097,
"step": 354
},
{
"epoch": 2.71,
"learning_rate": 1.9740259740259743e-06,
"loss": 0.0229,
"step": 355
},
{
"epoch": 2.72,
"learning_rate": 1.9220779220779223e-06,
"loss": 0.0394,
"step": 356
},
{
"epoch": 2.73,
"learning_rate": 1.8701298701298703e-06,
"loss": 0.0297,
"step": 357
},
{
"epoch": 2.73,
"learning_rate": 1.8181818181818183e-06,
"loss": 0.0257,
"step": 358
},
{
"epoch": 2.74,
"learning_rate": 1.7662337662337665e-06,
"loss": 0.0123,
"step": 359
},
{
"epoch": 2.75,
"learning_rate": 1.7142857142857145e-06,
"loss": 0.0098,
"step": 360
},
{
"epoch": 2.76,
"learning_rate": 1.6623376623376625e-06,
"loss": 0.0228,
"step": 361
},
{
"epoch": 2.76,
"learning_rate": 1.6103896103896105e-06,
"loss": 0.0182,
"step": 362
},
{
"epoch": 2.77,
"learning_rate": 1.5584415584415584e-06,
"loss": 0.0077,
"step": 363
},
{
"epoch": 2.78,
"learning_rate": 1.5064935064935066e-06,
"loss": 0.0261,
"step": 364
},
{
"epoch": 2.79,
"learning_rate": 1.4545454545454546e-06,
"loss": 0.0182,
"step": 365
},
{
"epoch": 2.79,
"learning_rate": 1.4025974025974026e-06,
"loss": 0.0062,
"step": 366
},
{
"epoch": 2.8,
"learning_rate": 1.3506493506493506e-06,
"loss": 0.0135,
"step": 367
},
{
"epoch": 2.81,
"learning_rate": 1.2987012987012986e-06,
"loss": 0.0131,
"step": 368
},
{
"epoch": 2.82,
"learning_rate": 1.2467532467532468e-06,
"loss": 0.0332,
"step": 369
},
{
"epoch": 2.82,
"learning_rate": 1.1948051948051948e-06,
"loss": 0.0161,
"step": 370
},
{
"epoch": 2.83,
"learning_rate": 1.142857142857143e-06,
"loss": 0.0069,
"step": 371
},
{
"epoch": 2.84,
"learning_rate": 1.090909090909091e-06,
"loss": 0.0213,
"step": 372
},
{
"epoch": 2.85,
"learning_rate": 1.0389610389610392e-06,
"loss": 0.0074,
"step": 373
},
{
"epoch": 2.85,
"learning_rate": 9.870129870129872e-07,
"loss": 0.0036,
"step": 374
},
{
"epoch": 2.86,
"learning_rate": 9.350649350649352e-07,
"loss": 0.0075,
"step": 375
},
{
"epoch": 2.87,
"learning_rate": 8.831168831168832e-07,
"loss": 0.016,
"step": 376
},
{
"epoch": 2.88,
"learning_rate": 8.311688311688312e-07,
"loss": 0.0126,
"step": 377
},
{
"epoch": 2.89,
"learning_rate": 7.792207792207792e-07,
"loss": 0.0098,
"step": 378
},
{
"epoch": 2.89,
"learning_rate": 7.272727272727273e-07,
"loss": 0.0056,
"step": 379
},
{
"epoch": 2.9,
"learning_rate": 6.753246753246753e-07,
"loss": 0.0272,
"step": 380
},
{
"epoch": 2.91,
"learning_rate": 6.233766233766234e-07,
"loss": 0.0129,
"step": 381
},
{
"epoch": 2.92,
"learning_rate": 5.714285714285715e-07,
"loss": 0.0293,
"step": 382
},
{
"epoch": 2.92,
"learning_rate": 5.194805194805196e-07,
"loss": 0.0155,
"step": 383
},
{
"epoch": 2.93,
"learning_rate": 4.675324675324676e-07,
"loss": 0.0056,
"step": 384
},
{
"epoch": 2.94,
"learning_rate": 4.155844155844156e-07,
"loss": 0.0071,
"step": 385
},
{
"epoch": 2.95,
"learning_rate": 3.6363636363636366e-07,
"loss": 0.0096,
"step": 386
},
{
"epoch": 2.95,
"learning_rate": 3.116883116883117e-07,
"loss": 0.033,
"step": 387
},
{
"epoch": 2.96,
"learning_rate": 2.597402597402598e-07,
"loss": 0.0117,
"step": 388
},
{
"epoch": 2.97,
"learning_rate": 2.077922077922078e-07,
"loss": 0.0159,
"step": 389
},
{
"epoch": 2.98,
"learning_rate": 1.5584415584415585e-07,
"loss": 0.0092,
"step": 390
},
{
"epoch": 2.98,
"learning_rate": 1.038961038961039e-07,
"loss": 0.0129,
"step": 391
},
{
"epoch": 2.99,
"learning_rate": 5.194805194805195e-08,
"loss": 0.0184,
"step": 392
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.0256,
"step": 393
},
{
"epoch": 3.0,
"eval_loss": 0.022193333134055138,
"eval_pearson": 0.9471585477998739,
"eval_runtime": 3.2624,
"eval_samples_per_second": 71.114,
"eval_spearmanr": 0.8983049279132507,
"eval_steps_per_second": 4.598,
"step": 393
}
],
"max_steps": 393,
"num_train_epochs": 3,
"total_flos": 827587732806432.0,
"trial_name": null,
"trial_params": null
}