M4_MLM_cross / checkpoint-131 /trainer_state.json
S2312dal's picture
Training in progress, epoch 1
0d242d5
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 131,
"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
}
],
"max_steps": 393,
"num_train_epochs": 3,
"total_flos": 275792205551616.0,
"trial_name": null,
"trial_params": null
}