finetune_cs_1 / trainer_state.json
BENBENBENb's picture
End of training
2373d0c
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 150,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 4.0818,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 4.2333,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 6e-05,
"loss": 4.1542,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 8e-05,
"loss": 3.9009,
"step": 4
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 3.6789,
"step": 5
},
{
"epoch": 0.04,
"learning_rate": 9.931034482758621e-05,
"loss": 3.6293,
"step": 6
},
{
"epoch": 0.05,
"learning_rate": 9.862068965517242e-05,
"loss": 2.9873,
"step": 7
},
{
"epoch": 0.05,
"learning_rate": 9.793103448275862e-05,
"loss": 2.972,
"step": 8
},
{
"epoch": 0.06,
"learning_rate": 9.724137931034482e-05,
"loss": 2.8305,
"step": 9
},
{
"epoch": 0.07,
"learning_rate": 9.655172413793105e-05,
"loss": 2.5089,
"step": 10
},
{
"epoch": 0.07,
"learning_rate": 9.586206896551725e-05,
"loss": 2.672,
"step": 11
},
{
"epoch": 0.08,
"learning_rate": 9.586206896551725e-05,
"loss": 2.4479,
"step": 12
},
{
"epoch": 0.09,
"learning_rate": 9.517241379310345e-05,
"loss": 2.325,
"step": 13
},
{
"epoch": 0.09,
"learning_rate": 9.448275862068966e-05,
"loss": 2.3685,
"step": 14
},
{
"epoch": 0.1,
"learning_rate": 9.379310344827587e-05,
"loss": 2.1516,
"step": 15
},
{
"epoch": 0.11,
"learning_rate": 9.310344827586207e-05,
"loss": 2.0509,
"step": 16
},
{
"epoch": 0.11,
"learning_rate": 9.241379310344827e-05,
"loss": 2.1814,
"step": 17
},
{
"epoch": 0.12,
"learning_rate": 9.172413793103448e-05,
"loss": 2.0731,
"step": 18
},
{
"epoch": 0.13,
"learning_rate": 9.10344827586207e-05,
"loss": 1.9349,
"step": 19
},
{
"epoch": 0.13,
"learning_rate": 9.034482758620691e-05,
"loss": 1.9393,
"step": 20
},
{
"epoch": 0.14,
"learning_rate": 8.96551724137931e-05,
"loss": 1.7397,
"step": 21
},
{
"epoch": 0.15,
"learning_rate": 8.896551724137931e-05,
"loss": 1.8364,
"step": 22
},
{
"epoch": 0.15,
"learning_rate": 8.896551724137931e-05,
"loss": 1.7434,
"step": 23
},
{
"epoch": 0.16,
"learning_rate": 8.827586206896552e-05,
"loss": 1.8296,
"step": 24
},
{
"epoch": 0.17,
"learning_rate": 8.758620689655173e-05,
"loss": 1.7968,
"step": 25
},
{
"epoch": 0.17,
"learning_rate": 8.689655172413794e-05,
"loss": 2.0705,
"step": 26
},
{
"epoch": 0.18,
"learning_rate": 8.620689655172413e-05,
"loss": 2.0936,
"step": 27
},
{
"epoch": 0.19,
"learning_rate": 8.551724137931035e-05,
"loss": 2.1498,
"step": 28
},
{
"epoch": 0.19,
"learning_rate": 8.482758620689656e-05,
"loss": 1.5908,
"step": 29
},
{
"epoch": 0.2,
"learning_rate": 8.413793103448277e-05,
"loss": 1.9481,
"step": 30
},
{
"epoch": 0.21,
"learning_rate": 8.344827586206896e-05,
"loss": 2.0838,
"step": 31
},
{
"epoch": 0.21,
"learning_rate": 8.275862068965517e-05,
"loss": 1.9145,
"step": 32
},
{
"epoch": 0.22,
"learning_rate": 8.206896551724138e-05,
"loss": 1.8683,
"step": 33
},
{
"epoch": 0.23,
"learning_rate": 8.137931034482759e-05,
"loss": 1.8419,
"step": 34
},
{
"epoch": 0.23,
"learning_rate": 8.06896551724138e-05,
"loss": 1.8494,
"step": 35
},
{
"epoch": 0.24,
"learning_rate": 8e-05,
"loss": 1.8084,
"step": 36
},
{
"epoch": 0.25,
"learning_rate": 7.931034482758621e-05,
"loss": 1.6323,
"step": 37
},
{
"epoch": 0.25,
"learning_rate": 7.862068965517242e-05,
"loss": 1.6161,
"step": 38
},
{
"epoch": 0.26,
"learning_rate": 7.793103448275862e-05,
"loss": 1.7512,
"step": 39
},
{
"epoch": 0.27,
"learning_rate": 7.724137931034483e-05,
"loss": 1.9403,
"step": 40
},
{
"epoch": 0.27,
"learning_rate": 7.655172413793103e-05,
"loss": 1.8314,
"step": 41
},
{
"epoch": 0.28,
"learning_rate": 7.586206896551724e-05,
"loss": 1.4765,
"step": 42
},
{
"epoch": 0.29,
"learning_rate": 7.517241379310345e-05,
"loss": 2.0523,
"step": 43
},
{
"epoch": 0.29,
"learning_rate": 7.448275862068966e-05,
"loss": 1.6631,
"step": 44
},
{
"epoch": 0.3,
"learning_rate": 7.379310344827587e-05,
"loss": 1.8069,
"step": 45
},
{
"epoch": 0.31,
"learning_rate": 7.310344827586208e-05,
"loss": 1.7911,
"step": 46
},
{
"epoch": 0.31,
"learning_rate": 7.241379310344828e-05,
"loss": 1.5465,
"step": 47
},
{
"epoch": 0.32,
"learning_rate": 7.172413793103448e-05,
"loss": 1.7861,
"step": 48
},
{
"epoch": 0.33,
"learning_rate": 7.103448275862069e-05,
"loss": 1.8213,
"step": 49
},
{
"epoch": 0.33,
"learning_rate": 7.03448275862069e-05,
"loss": 1.706,
"step": 50
},
{
"epoch": 0.34,
"learning_rate": 6.96551724137931e-05,
"loss": 1.6529,
"step": 51
},
{
"epoch": 0.35,
"learning_rate": 6.896551724137931e-05,
"loss": 1.6611,
"step": 52
},
{
"epoch": 0.35,
"learning_rate": 6.827586206896552e-05,
"loss": 1.8146,
"step": 53
},
{
"epoch": 0.36,
"learning_rate": 6.758620689655173e-05,
"loss": 1.9463,
"step": 54
},
{
"epoch": 0.37,
"learning_rate": 6.689655172413794e-05,
"loss": 1.8856,
"step": 55
},
{
"epoch": 0.37,
"learning_rate": 6.620689655172415e-05,
"loss": 1.8093,
"step": 56
},
{
"epoch": 0.38,
"learning_rate": 6.551724137931034e-05,
"loss": 1.8616,
"step": 57
},
{
"epoch": 0.39,
"learning_rate": 6.482758620689655e-05,
"loss": 1.3817,
"step": 58
},
{
"epoch": 0.39,
"learning_rate": 6.413793103448276e-05,
"loss": 1.4823,
"step": 59
},
{
"epoch": 0.4,
"learning_rate": 6.344827586206897e-05,
"loss": 1.6869,
"step": 60
},
{
"epoch": 0.41,
"learning_rate": 6.275862068965517e-05,
"loss": 1.435,
"step": 61
},
{
"epoch": 0.41,
"learning_rate": 6.206896551724138e-05,
"loss": 1.747,
"step": 62
},
{
"epoch": 0.42,
"learning_rate": 6.137931034482759e-05,
"loss": 1.7569,
"step": 63
},
{
"epoch": 0.43,
"learning_rate": 6.068965517241379e-05,
"loss": 1.6538,
"step": 64
},
{
"epoch": 0.43,
"learning_rate": 6e-05,
"loss": 1.7693,
"step": 65
},
{
"epoch": 0.44,
"learning_rate": 5.93103448275862e-05,
"loss": 1.7543,
"step": 66
},
{
"epoch": 0.45,
"learning_rate": 5.862068965517241e-05,
"loss": 1.6419,
"step": 67
},
{
"epoch": 0.45,
"learning_rate": 5.7931034482758627e-05,
"loss": 1.605,
"step": 68
},
{
"epoch": 0.46,
"learning_rate": 5.7241379310344835e-05,
"loss": 1.8797,
"step": 69
},
{
"epoch": 0.47,
"learning_rate": 5.6551724137931037e-05,
"loss": 1.8213,
"step": 70
},
{
"epoch": 0.47,
"learning_rate": 5.5862068965517245e-05,
"loss": 1.7598,
"step": 71
},
{
"epoch": 0.48,
"learning_rate": 5.517241379310345e-05,
"loss": 1.6588,
"step": 72
},
{
"epoch": 0.49,
"learning_rate": 5.4482758620689655e-05,
"loss": 1.4647,
"step": 73
},
{
"epoch": 0.49,
"learning_rate": 5.379310344827586e-05,
"loss": 1.6897,
"step": 74
},
{
"epoch": 0.5,
"learning_rate": 5.3103448275862065e-05,
"loss": 1.6746,
"step": 75
},
{
"epoch": 0.51,
"learning_rate": 5.241379310344828e-05,
"loss": 1.7333,
"step": 76
},
{
"epoch": 0.51,
"learning_rate": 5.172413793103449e-05,
"loss": 1.7597,
"step": 77
},
{
"epoch": 0.52,
"learning_rate": 5.10344827586207e-05,
"loss": 1.8023,
"step": 78
},
{
"epoch": 0.53,
"learning_rate": 5.03448275862069e-05,
"loss": 1.6242,
"step": 79
},
{
"epoch": 0.53,
"learning_rate": 4.9655172413793107e-05,
"loss": 1.8235,
"step": 80
},
{
"epoch": 0.54,
"learning_rate": 4.896551724137931e-05,
"loss": 1.4698,
"step": 81
},
{
"epoch": 0.55,
"learning_rate": 4.827586206896552e-05,
"loss": 1.7668,
"step": 82
},
{
"epoch": 0.55,
"learning_rate": 4.7586206896551725e-05,
"loss": 1.7414,
"step": 83
},
{
"epoch": 0.56,
"learning_rate": 4.689655172413793e-05,
"loss": 1.6057,
"step": 84
},
{
"epoch": 0.57,
"learning_rate": 4.6206896551724135e-05,
"loss": 1.7719,
"step": 85
},
{
"epoch": 0.57,
"learning_rate": 4.551724137931035e-05,
"loss": 1.487,
"step": 86
},
{
"epoch": 0.58,
"learning_rate": 4.482758620689655e-05,
"loss": 1.6868,
"step": 87
},
{
"epoch": 0.59,
"learning_rate": 4.413793103448276e-05,
"loss": 1.3526,
"step": 88
},
{
"epoch": 0.59,
"learning_rate": 4.344827586206897e-05,
"loss": 1.599,
"step": 89
},
{
"epoch": 0.6,
"learning_rate": 4.275862068965518e-05,
"loss": 1.6426,
"step": 90
},
{
"epoch": 0.61,
"learning_rate": 4.2068965517241385e-05,
"loss": 1.8232,
"step": 91
},
{
"epoch": 0.61,
"learning_rate": 4.1379310344827587e-05,
"loss": 1.6906,
"step": 92
},
{
"epoch": 0.62,
"learning_rate": 4.0689655172413795e-05,
"loss": 1.7554,
"step": 93
},
{
"epoch": 0.63,
"learning_rate": 4e-05,
"loss": 1.3775,
"step": 94
},
{
"epoch": 0.63,
"learning_rate": 3.931034482758621e-05,
"loss": 1.6337,
"step": 95
},
{
"epoch": 0.64,
"learning_rate": 3.862068965517241e-05,
"loss": 1.7228,
"step": 96
},
{
"epoch": 0.65,
"learning_rate": 3.793103448275862e-05,
"loss": 1.6965,
"step": 97
},
{
"epoch": 0.65,
"learning_rate": 3.724137931034483e-05,
"loss": 1.6325,
"step": 98
},
{
"epoch": 0.66,
"learning_rate": 3.655172413793104e-05,
"loss": 1.7079,
"step": 99
},
{
"epoch": 0.67,
"learning_rate": 3.586206896551724e-05,
"loss": 1.7325,
"step": 100
},
{
"epoch": 0.67,
"learning_rate": 3.517241379310345e-05,
"loss": 1.691,
"step": 101
},
{
"epoch": 0.68,
"learning_rate": 3.4482758620689657e-05,
"loss": 1.581,
"step": 102
},
{
"epoch": 0.69,
"learning_rate": 3.3793103448275865e-05,
"loss": 1.5555,
"step": 103
},
{
"epoch": 0.69,
"learning_rate": 3.310344827586207e-05,
"loss": 1.888,
"step": 104
},
{
"epoch": 0.7,
"learning_rate": 3.2413793103448275e-05,
"loss": 1.7468,
"step": 105
},
{
"epoch": 0.71,
"learning_rate": 3.172413793103448e-05,
"loss": 1.517,
"step": 106
},
{
"epoch": 0.71,
"learning_rate": 3.103448275862069e-05,
"loss": 1.3428,
"step": 107
},
{
"epoch": 0.72,
"learning_rate": 3.0344827586206897e-05,
"loss": 1.6182,
"step": 108
},
{
"epoch": 0.73,
"learning_rate": 2.96551724137931e-05,
"loss": 1.5281,
"step": 109
},
{
"epoch": 0.73,
"learning_rate": 2.8965517241379313e-05,
"loss": 1.7454,
"step": 110
},
{
"epoch": 0.74,
"learning_rate": 2.8275862068965518e-05,
"loss": 1.4548,
"step": 111
},
{
"epoch": 0.75,
"learning_rate": 2.7586206896551727e-05,
"loss": 1.4244,
"step": 112
},
{
"epoch": 0.75,
"learning_rate": 2.689655172413793e-05,
"loss": 1.4889,
"step": 113
},
{
"epoch": 0.76,
"learning_rate": 2.620689655172414e-05,
"loss": 1.6355,
"step": 114
},
{
"epoch": 0.77,
"learning_rate": 2.551724137931035e-05,
"loss": 1.9701,
"step": 115
},
{
"epoch": 0.77,
"learning_rate": 2.4827586206896553e-05,
"loss": 1.5884,
"step": 116
},
{
"epoch": 0.78,
"learning_rate": 2.413793103448276e-05,
"loss": 1.7459,
"step": 117
},
{
"epoch": 0.79,
"learning_rate": 2.3448275862068967e-05,
"loss": 1.5876,
"step": 118
},
{
"epoch": 0.79,
"learning_rate": 2.2758620689655175e-05,
"loss": 1.7276,
"step": 119
},
{
"epoch": 0.8,
"learning_rate": 2.206896551724138e-05,
"loss": 1.5473,
"step": 120
},
{
"epoch": 0.81,
"learning_rate": 2.137931034482759e-05,
"loss": 1.4386,
"step": 121
},
{
"epoch": 0.81,
"learning_rate": 2.0689655172413793e-05,
"loss": 1.6739,
"step": 122
},
{
"epoch": 0.82,
"learning_rate": 2e-05,
"loss": 1.7468,
"step": 123
},
{
"epoch": 0.83,
"learning_rate": 1.9310344827586207e-05,
"loss": 1.6021,
"step": 124
},
{
"epoch": 0.83,
"learning_rate": 1.8620689655172415e-05,
"loss": 1.6122,
"step": 125
},
{
"epoch": 0.84,
"learning_rate": 1.793103448275862e-05,
"loss": 1.6383,
"step": 126
},
{
"epoch": 0.85,
"learning_rate": 1.7241379310344828e-05,
"loss": 1.5088,
"step": 127
},
{
"epoch": 0.85,
"learning_rate": 1.6551724137931037e-05,
"loss": 1.4898,
"step": 128
},
{
"epoch": 0.86,
"learning_rate": 1.586206896551724e-05,
"loss": 1.8334,
"step": 129
},
{
"epoch": 0.87,
"learning_rate": 1.5172413793103448e-05,
"loss": 1.5095,
"step": 130
},
{
"epoch": 0.87,
"learning_rate": 1.4482758620689657e-05,
"loss": 1.7406,
"step": 131
},
{
"epoch": 0.88,
"learning_rate": 1.3793103448275863e-05,
"loss": 1.4073,
"step": 132
},
{
"epoch": 0.89,
"learning_rate": 1.310344827586207e-05,
"loss": 1.6381,
"step": 133
},
{
"epoch": 0.89,
"learning_rate": 1.2413793103448277e-05,
"loss": 1.5619,
"step": 134
},
{
"epoch": 0.9,
"learning_rate": 1.1724137931034483e-05,
"loss": 1.6302,
"step": 135
},
{
"epoch": 0.91,
"learning_rate": 1.103448275862069e-05,
"loss": 1.5507,
"step": 136
},
{
"epoch": 0.91,
"learning_rate": 1.0344827586206897e-05,
"loss": 1.4098,
"step": 137
},
{
"epoch": 0.92,
"learning_rate": 9.655172413793103e-06,
"loss": 1.7283,
"step": 138
},
{
"epoch": 0.93,
"learning_rate": 8.96551724137931e-06,
"loss": 1.4632,
"step": 139
},
{
"epoch": 0.93,
"learning_rate": 8.275862068965518e-06,
"loss": 1.5798,
"step": 140
},
{
"epoch": 0.94,
"learning_rate": 7.586206896551724e-06,
"loss": 1.6579,
"step": 141
},
{
"epoch": 0.95,
"learning_rate": 6.896551724137932e-06,
"loss": 1.6255,
"step": 142
},
{
"epoch": 0.95,
"learning_rate": 6.206896551724138e-06,
"loss": 1.5473,
"step": 143
},
{
"epoch": 0.96,
"learning_rate": 5.517241379310345e-06,
"loss": 1.6416,
"step": 144
},
{
"epoch": 0.97,
"learning_rate": 4.827586206896552e-06,
"loss": 1.5112,
"step": 145
},
{
"epoch": 0.97,
"learning_rate": 4.137931034482759e-06,
"loss": 1.8943,
"step": 146
},
{
"epoch": 0.98,
"learning_rate": 3.448275862068966e-06,
"loss": 1.7169,
"step": 147
},
{
"epoch": 0.99,
"learning_rate": 2.7586206896551725e-06,
"loss": 1.5538,
"step": 148
},
{
"epoch": 0.99,
"learning_rate": 2.0689655172413796e-06,
"loss": 1.9224,
"step": 149
},
{
"epoch": 1.0,
"learning_rate": 1.3793103448275862e-06,
"loss": 1.6907,
"step": 150
},
{
"epoch": 1.0,
"eval_loss": 1.6271520853042603,
"eval_runtime": 10.0351,
"eval_samples_per_second": 19.93,
"eval_steps_per_second": 2.491,
"step": 150
},
{
"epoch": 1.0,
"step": 150,
"total_flos": 2345174699212800.0,
"train_loss": 1.8450010808308919,
"train_runtime": 149.9186,
"train_samples_per_second": 4.002,
"train_steps_per_second": 1.001
}
],
"logging_steps": 1,
"max_steps": 150,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 2345174699212800.0,
"trial_name": null,
"trial_params": null
}