xzuyn's picture
Upload folder using huggingface_hub
614990f
raw
history blame
No virus
44.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.598058252427185,
"global_step": 369,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 2.631578947368421e-06,
"loss": 1.9044,
"step": 1
},
{
"epoch": 0.05,
"learning_rate": 5.263157894736842e-06,
"loss": 2.018,
"step": 2
},
{
"epoch": 0.07,
"learning_rate": 7.894736842105263e-06,
"loss": 2.0221,
"step": 3
},
{
"epoch": 0.09,
"learning_rate": 1.0526315789473684e-05,
"loss": 1.8884,
"step": 4
},
{
"epoch": 0.12,
"learning_rate": 1.3157894736842106e-05,
"loss": 1.9326,
"step": 5
},
{
"epoch": 0.14,
"learning_rate": 1.5789473684210526e-05,
"loss": 2.1193,
"step": 6
},
{
"epoch": 0.16,
"learning_rate": 1.8421052631578947e-05,
"loss": 2.0827,
"step": 7
},
{
"epoch": 0.19,
"learning_rate": 2.105263157894737e-05,
"loss": 1.8846,
"step": 8
},
{
"epoch": 0.21,
"learning_rate": 2.368421052631579e-05,
"loss": 2.0943,
"step": 9
},
{
"epoch": 0.23,
"learning_rate": 2.6315789473684212e-05,
"loss": 2.0881,
"step": 10
},
{
"epoch": 0.26,
"learning_rate": 2.8947368421052634e-05,
"loss": 1.9275,
"step": 11
},
{
"epoch": 0.28,
"learning_rate": 3.157894736842105e-05,
"loss": 1.6874,
"step": 12
},
{
"epoch": 0.3,
"learning_rate": 3.421052631578947e-05,
"loss": 1.9874,
"step": 13
},
{
"epoch": 0.33,
"learning_rate": 3.6842105263157895e-05,
"loss": 1.8901,
"step": 14
},
{
"epoch": 0.35,
"learning_rate": 3.9473684210526316e-05,
"loss": 1.7683,
"step": 15
},
{
"epoch": 0.37,
"learning_rate": 4.210526315789474e-05,
"loss": 2.0108,
"step": 16
},
{
"epoch": 0.4,
"learning_rate": 4.473684210526316e-05,
"loss": 1.6579,
"step": 17
},
{
"epoch": 0.42,
"learning_rate": 4.736842105263158e-05,
"loss": 1.9758,
"step": 18
},
{
"epoch": 0.44,
"learning_rate": 5e-05,
"loss": 1.9118,
"step": 19
},
{
"epoch": 0.47,
"learning_rate": 5.2631578947368424e-05,
"loss": 1.8964,
"step": 20
},
{
"epoch": 0.49,
"learning_rate": 5.526315789473685e-05,
"loss": 1.9288,
"step": 21
},
{
"epoch": 0.51,
"learning_rate": 5.789473684210527e-05,
"loss": 1.8706,
"step": 22
},
{
"epoch": 0.54,
"learning_rate": 6.052631578947369e-05,
"loss": 1.8604,
"step": 23
},
{
"epoch": 0.56,
"learning_rate": 6.31578947368421e-05,
"loss": 1.9001,
"step": 24
},
{
"epoch": 0.58,
"learning_rate": 6.578947368421054e-05,
"loss": 1.8254,
"step": 25
},
{
"epoch": 0.61,
"learning_rate": 6.842105263157895e-05,
"loss": 1.8111,
"step": 26
},
{
"epoch": 0.63,
"learning_rate": 7.105263157894737e-05,
"loss": 1.7496,
"step": 27
},
{
"epoch": 0.65,
"learning_rate": 7.368421052631579e-05,
"loss": 1.7604,
"step": 28
},
{
"epoch": 0.68,
"learning_rate": 7.631578947368422e-05,
"loss": 1.6285,
"step": 29
},
{
"epoch": 0.7,
"learning_rate": 7.894736842105263e-05,
"loss": 1.7226,
"step": 30
},
{
"epoch": 0.72,
"learning_rate": 8.157894736842105e-05,
"loss": 1.9689,
"step": 31
},
{
"epoch": 0.75,
"learning_rate": 8.421052631578948e-05,
"loss": 1.7737,
"step": 32
},
{
"epoch": 0.77,
"learning_rate": 8.68421052631579e-05,
"loss": 1.8093,
"step": 33
},
{
"epoch": 0.79,
"learning_rate": 8.947368421052632e-05,
"loss": 1.6292,
"step": 34
},
{
"epoch": 0.82,
"learning_rate": 9.210526315789474e-05,
"loss": 1.8351,
"step": 35
},
{
"epoch": 0.84,
"learning_rate": 9.473684210526316e-05,
"loss": 1.918,
"step": 36
},
{
"epoch": 0.86,
"learning_rate": 9.736842105263158e-05,
"loss": 1.8161,
"step": 37
},
{
"epoch": 0.89,
"learning_rate": 0.0001,
"loss": 1.8184,
"step": 38
},
{
"epoch": 0.91,
"learning_rate": 9.983108108108109e-05,
"loss": 1.5839,
"step": 39
},
{
"epoch": 0.93,
"learning_rate": 9.966216216216217e-05,
"loss": 1.8736,
"step": 40
},
{
"epoch": 0.96,
"learning_rate": 9.949324324324325e-05,
"loss": 1.77,
"step": 41
},
{
"epoch": 0.98,
"learning_rate": 9.932432432432433e-05,
"loss": 1.7912,
"step": 42
},
{
"epoch": 1.0,
"learning_rate": 9.915540540540541e-05,
"loss": 1.6989,
"step": 43
},
{
"epoch": 1.03,
"learning_rate": 9.89864864864865e-05,
"loss": 1.7327,
"step": 44
},
{
"epoch": 1.05,
"learning_rate": 9.881756756756757e-05,
"loss": 1.7799,
"step": 45
},
{
"epoch": 1.07,
"learning_rate": 9.864864864864865e-05,
"loss": 1.8298,
"step": 46
},
{
"epoch": 1.1,
"learning_rate": 9.847972972972973e-05,
"loss": 1.8616,
"step": 47
},
{
"epoch": 1.12,
"learning_rate": 9.831081081081081e-05,
"loss": 1.7984,
"step": 48
},
{
"epoch": 1.14,
"learning_rate": 9.81418918918919e-05,
"loss": 1.7626,
"step": 49
},
{
"epoch": 1.17,
"learning_rate": 9.797297297297297e-05,
"loss": 1.8424,
"step": 50
},
{
"epoch": 1.19,
"learning_rate": 9.780405405405407e-05,
"loss": 1.6436,
"step": 51
},
{
"epoch": 1.21,
"learning_rate": 9.763513513513513e-05,
"loss": 1.6303,
"step": 52
},
{
"epoch": 1.23,
"learning_rate": 9.746621621621623e-05,
"loss": 1.7199,
"step": 53
},
{
"epoch": 1.26,
"learning_rate": 9.729729729729731e-05,
"loss": 1.6789,
"step": 54
},
{
"epoch": 1.28,
"learning_rate": 9.712837837837838e-05,
"loss": 1.8519,
"step": 55
},
{
"epoch": 1.3,
"learning_rate": 9.695945945945947e-05,
"loss": 1.7961,
"step": 56
},
{
"epoch": 1.33,
"learning_rate": 9.679054054054054e-05,
"loss": 1.6725,
"step": 57
},
{
"epoch": 1.35,
"learning_rate": 9.662162162162163e-05,
"loss": 1.7249,
"step": 58
},
{
"epoch": 1.37,
"learning_rate": 9.64527027027027e-05,
"loss": 1.5996,
"step": 59
},
{
"epoch": 1.4,
"learning_rate": 9.628378378378379e-05,
"loss": 1.7033,
"step": 60
},
{
"epoch": 1.42,
"learning_rate": 9.611486486486487e-05,
"loss": 1.7387,
"step": 61
},
{
"epoch": 1.44,
"learning_rate": 9.594594594594595e-05,
"loss": 1.7804,
"step": 62
},
{
"epoch": 1.47,
"learning_rate": 9.577702702702703e-05,
"loss": 1.7484,
"step": 63
},
{
"epoch": 1.49,
"learning_rate": 9.56081081081081e-05,
"loss": 1.7526,
"step": 64
},
{
"epoch": 1.51,
"learning_rate": 9.54391891891892e-05,
"loss": 1.7247,
"step": 65
},
{
"epoch": 1.54,
"learning_rate": 9.527027027027028e-05,
"loss": 1.6276,
"step": 66
},
{
"epoch": 1.56,
"learning_rate": 9.510135135135136e-05,
"loss": 1.8279,
"step": 67
},
{
"epoch": 1.58,
"learning_rate": 9.493243243243244e-05,
"loss": 1.7067,
"step": 68
},
{
"epoch": 1.61,
"learning_rate": 9.476351351351352e-05,
"loss": 1.7865,
"step": 69
},
{
"epoch": 1.63,
"learning_rate": 9.45945945945946e-05,
"loss": 1.6693,
"step": 70
},
{
"epoch": 1.65,
"learning_rate": 9.442567567567568e-05,
"loss": 1.6939,
"step": 71
},
{
"epoch": 1.68,
"learning_rate": 9.425675675675676e-05,
"loss": 1.8667,
"step": 72
},
{
"epoch": 1.7,
"learning_rate": 9.408783783783784e-05,
"loss": 1.746,
"step": 73
},
{
"epoch": 1.72,
"learning_rate": 9.391891891891892e-05,
"loss": 1.6951,
"step": 74
},
{
"epoch": 1.75,
"learning_rate": 9.375e-05,
"loss": 1.6749,
"step": 75
},
{
"epoch": 1.77,
"learning_rate": 9.35810810810811e-05,
"loss": 1.8773,
"step": 76
},
{
"epoch": 1.79,
"learning_rate": 9.341216216216216e-05,
"loss": 1.8064,
"step": 77
},
{
"epoch": 1.82,
"learning_rate": 9.324324324324324e-05,
"loss": 1.6596,
"step": 78
},
{
"epoch": 1.84,
"learning_rate": 9.307432432432432e-05,
"loss": 1.7321,
"step": 79
},
{
"epoch": 1.86,
"learning_rate": 9.29054054054054e-05,
"loss": 1.7029,
"step": 80
},
{
"epoch": 1.89,
"learning_rate": 9.27364864864865e-05,
"loss": 1.7392,
"step": 81
},
{
"epoch": 1.91,
"learning_rate": 9.256756756756757e-05,
"loss": 1.7904,
"step": 82
},
{
"epoch": 1.93,
"learning_rate": 9.239864864864866e-05,
"loss": 1.6794,
"step": 83
},
{
"epoch": 1.96,
"learning_rate": 9.222972972972973e-05,
"loss": 1.8827,
"step": 84
},
{
"epoch": 1.98,
"learning_rate": 9.206081081081082e-05,
"loss": 1.7051,
"step": 85
},
{
"epoch": 2.0,
"learning_rate": 9.18918918918919e-05,
"loss": 1.7069,
"step": 86
},
{
"epoch": 2.03,
"learning_rate": 9.172297297297297e-05,
"loss": 1.8051,
"step": 87
},
{
"epoch": 2.05,
"learning_rate": 9.155405405405406e-05,
"loss": 1.6665,
"step": 88
},
{
"epoch": 2.07,
"learning_rate": 9.138513513513513e-05,
"loss": 1.6218,
"step": 89
},
{
"epoch": 2.1,
"learning_rate": 9.121621621621623e-05,
"loss": 1.5848,
"step": 90
},
{
"epoch": 2.12,
"learning_rate": 9.10472972972973e-05,
"loss": 1.7544,
"step": 91
},
{
"epoch": 2.14,
"learning_rate": 9.087837837837839e-05,
"loss": 1.6454,
"step": 92
},
{
"epoch": 2.17,
"learning_rate": 9.070945945945947e-05,
"loss": 1.8591,
"step": 93
},
{
"epoch": 2.19,
"learning_rate": 9.054054054054055e-05,
"loss": 1.7025,
"step": 94
},
{
"epoch": 2.21,
"learning_rate": 9.037162162162163e-05,
"loss": 1.7824,
"step": 95
},
{
"epoch": 2.24,
"learning_rate": 9.02027027027027e-05,
"loss": 1.6049,
"step": 96
},
{
"epoch": 2.26,
"learning_rate": 9.003378378378379e-05,
"loss": 1.6961,
"step": 97
},
{
"epoch": 2.28,
"learning_rate": 8.986486486486487e-05,
"loss": 1.8705,
"step": 98
},
{
"epoch": 2.31,
"learning_rate": 8.969594594594595e-05,
"loss": 1.4498,
"step": 99
},
{
"epoch": 2.33,
"learning_rate": 8.952702702702703e-05,
"loss": 1.6967,
"step": 100
},
{
"epoch": 2.35,
"learning_rate": 8.935810810810811e-05,
"loss": 1.6345,
"step": 101
},
{
"epoch": 2.38,
"learning_rate": 8.918918918918919e-05,
"loss": 1.8037,
"step": 102
},
{
"epoch": 2.4,
"learning_rate": 8.902027027027027e-05,
"loss": 1.7896,
"step": 103
},
{
"epoch": 2.42,
"learning_rate": 8.885135135135135e-05,
"loss": 1.751,
"step": 104
},
{
"epoch": 2.45,
"learning_rate": 8.868243243243243e-05,
"loss": 1.482,
"step": 105
},
{
"epoch": 2.47,
"learning_rate": 8.851351351351352e-05,
"loss": 1.6049,
"step": 106
},
{
"epoch": 2.49,
"learning_rate": 8.83445945945946e-05,
"loss": 1.6029,
"step": 107
},
{
"epoch": 2.52,
"learning_rate": 8.817567567567569e-05,
"loss": 1.875,
"step": 108
},
{
"epoch": 2.54,
"learning_rate": 8.800675675675676e-05,
"loss": 1.5798,
"step": 109
},
{
"epoch": 2.56,
"learning_rate": 8.783783783783784e-05,
"loss": 1.4883,
"step": 110
},
{
"epoch": 2.59,
"learning_rate": 8.766891891891892e-05,
"loss": 1.7249,
"step": 111
},
{
"epoch": 2.61,
"learning_rate": 8.75e-05,
"loss": 1.5086,
"step": 112
},
{
"epoch": 2.63,
"learning_rate": 8.73310810810811e-05,
"loss": 1.39,
"step": 113
},
{
"epoch": 2.66,
"learning_rate": 8.716216216216216e-05,
"loss": 1.7481,
"step": 114
},
{
"epoch": 2.68,
"learning_rate": 8.699324324324325e-05,
"loss": 1.6514,
"step": 115
},
{
"epoch": 2.7,
"learning_rate": 8.682432432432432e-05,
"loss": 1.8731,
"step": 116
},
{
"epoch": 2.73,
"learning_rate": 8.665540540540542e-05,
"loss": 1.6415,
"step": 117
},
{
"epoch": 2.75,
"learning_rate": 8.64864864864865e-05,
"loss": 1.7659,
"step": 118
},
{
"epoch": 2.77,
"learning_rate": 8.631756756756756e-05,
"loss": 1.5691,
"step": 119
},
{
"epoch": 2.8,
"learning_rate": 8.614864864864866e-05,
"loss": 1.6315,
"step": 120
},
{
"epoch": 2.82,
"learning_rate": 8.597972972972972e-05,
"loss": 1.367,
"step": 121
},
{
"epoch": 2.84,
"learning_rate": 8.581081081081082e-05,
"loss": 1.6088,
"step": 122
},
{
"epoch": 2.87,
"learning_rate": 8.56418918918919e-05,
"loss": 1.7598,
"step": 123
},
{
"epoch": 2.89,
"learning_rate": 8.547297297297298e-05,
"loss": 1.6255,
"step": 124
},
{
"epoch": 2.91,
"learning_rate": 8.530405405405406e-05,
"loss": 1.5739,
"step": 125
},
{
"epoch": 2.94,
"learning_rate": 8.513513513513514e-05,
"loss": 1.5542,
"step": 126
},
{
"epoch": 2.96,
"learning_rate": 8.496621621621622e-05,
"loss": 1.5758,
"step": 127
},
{
"epoch": 2.98,
"learning_rate": 8.47972972972973e-05,
"loss": 1.668,
"step": 128
},
{
"epoch": 3.01,
"learning_rate": 8.462837837837838e-05,
"loss": 1.6283,
"step": 129
},
{
"epoch": 3.03,
"learning_rate": 8.445945945945946e-05,
"loss": 1.6111,
"step": 130
},
{
"epoch": 3.05,
"learning_rate": 8.429054054054054e-05,
"loss": 1.8061,
"step": 131
},
{
"epoch": 3.08,
"learning_rate": 8.412162162162163e-05,
"loss": 1.4882,
"step": 132
},
{
"epoch": 3.1,
"learning_rate": 8.39527027027027e-05,
"loss": 1.592,
"step": 133
},
{
"epoch": 3.12,
"learning_rate": 8.378378378378379e-05,
"loss": 1.638,
"step": 134
},
{
"epoch": 3.15,
"learning_rate": 8.361486486486487e-05,
"loss": 1.5036,
"step": 135
},
{
"epoch": 3.17,
"learning_rate": 8.344594594594595e-05,
"loss": 1.6721,
"step": 136
},
{
"epoch": 3.19,
"learning_rate": 8.327702702702703e-05,
"loss": 1.7742,
"step": 137
},
{
"epoch": 3.22,
"learning_rate": 8.310810810810811e-05,
"loss": 1.484,
"step": 138
},
{
"epoch": 3.24,
"learning_rate": 8.293918918918919e-05,
"loss": 1.3698,
"step": 139
},
{
"epoch": 3.26,
"learning_rate": 8.277027027027028e-05,
"loss": 1.5644,
"step": 140
},
{
"epoch": 3.29,
"learning_rate": 8.260135135135135e-05,
"loss": 1.6195,
"step": 141
},
{
"epoch": 3.31,
"learning_rate": 8.243243243243243e-05,
"loss": 1.5031,
"step": 142
},
{
"epoch": 3.33,
"learning_rate": 8.226351351351351e-05,
"loss": 1.5403,
"step": 143
},
{
"epoch": 3.36,
"learning_rate": 8.209459459459459e-05,
"loss": 1.57,
"step": 144
},
{
"epoch": 3.38,
"learning_rate": 8.192567567567569e-05,
"loss": 1.6454,
"step": 145
},
{
"epoch": 3.4,
"learning_rate": 8.175675675675675e-05,
"loss": 1.5069,
"step": 146
},
{
"epoch": 3.43,
"learning_rate": 8.158783783783785e-05,
"loss": 1.3782,
"step": 147
},
{
"epoch": 3.45,
"learning_rate": 8.141891891891892e-05,
"loss": 1.4296,
"step": 148
},
{
"epoch": 3.47,
"learning_rate": 8.125000000000001e-05,
"loss": 1.4303,
"step": 149
},
{
"epoch": 3.5,
"learning_rate": 8.108108108108109e-05,
"loss": 1.6368,
"step": 150
},
{
"epoch": 3.52,
"learning_rate": 8.091216216216216e-05,
"loss": 1.5951,
"step": 151
},
{
"epoch": 3.54,
"learning_rate": 8.074324324324325e-05,
"loss": 1.5769,
"step": 152
},
{
"epoch": 3.57,
"learning_rate": 8.057432432432432e-05,
"loss": 1.482,
"step": 153
},
{
"epoch": 3.59,
"learning_rate": 8.040540540540541e-05,
"loss": 1.5415,
"step": 154
},
{
"epoch": 3.61,
"learning_rate": 8.02364864864865e-05,
"loss": 1.6084,
"step": 155
},
{
"epoch": 3.63,
"learning_rate": 8.006756756756757e-05,
"loss": 1.5483,
"step": 156
},
{
"epoch": 3.66,
"learning_rate": 7.989864864864865e-05,
"loss": 1.4329,
"step": 157
},
{
"epoch": 3.68,
"learning_rate": 7.972972972972974e-05,
"loss": 1.6068,
"step": 158
},
{
"epoch": 3.7,
"learning_rate": 7.956081081081082e-05,
"loss": 1.5519,
"step": 159
},
{
"epoch": 3.73,
"learning_rate": 7.93918918918919e-05,
"loss": 1.7387,
"step": 160
},
{
"epoch": 3.75,
"learning_rate": 7.922297297297298e-05,
"loss": 1.5583,
"step": 161
},
{
"epoch": 3.77,
"learning_rate": 7.905405405405406e-05,
"loss": 1.5003,
"step": 162
},
{
"epoch": 3.8,
"learning_rate": 7.888513513513514e-05,
"loss": 1.5025,
"step": 163
},
{
"epoch": 3.82,
"learning_rate": 7.871621621621622e-05,
"loss": 1.5322,
"step": 164
},
{
"epoch": 3.84,
"learning_rate": 7.85472972972973e-05,
"loss": 1.6915,
"step": 165
},
{
"epoch": 3.87,
"learning_rate": 7.837837837837838e-05,
"loss": 1.4906,
"step": 166
},
{
"epoch": 3.89,
"learning_rate": 7.820945945945946e-05,
"loss": 1.4796,
"step": 167
},
{
"epoch": 3.91,
"learning_rate": 7.804054054054054e-05,
"loss": 1.5712,
"step": 168
},
{
"epoch": 3.94,
"learning_rate": 7.787162162162162e-05,
"loss": 1.459,
"step": 169
},
{
"epoch": 3.96,
"learning_rate": 7.77027027027027e-05,
"loss": 1.4917,
"step": 170
},
{
"epoch": 3.98,
"learning_rate": 7.753378378378378e-05,
"loss": 1.5149,
"step": 171
},
{
"epoch": 4.01,
"learning_rate": 7.736486486486488e-05,
"loss": 1.4344,
"step": 172
},
{
"epoch": 4.03,
"learning_rate": 7.719594594594595e-05,
"loss": 1.4152,
"step": 173
},
{
"epoch": 4.05,
"learning_rate": 7.702702702702703e-05,
"loss": 1.3729,
"step": 174
},
{
"epoch": 4.08,
"learning_rate": 7.68581081081081e-05,
"loss": 1.4462,
"step": 175
},
{
"epoch": 4.1,
"learning_rate": 7.668918918918919e-05,
"loss": 1.5449,
"step": 176
},
{
"epoch": 4.12,
"learning_rate": 7.652027027027028e-05,
"loss": 1.2145,
"step": 177
},
{
"epoch": 4.15,
"learning_rate": 7.635135135135135e-05,
"loss": 1.4754,
"step": 178
},
{
"epoch": 4.17,
"learning_rate": 7.618243243243244e-05,
"loss": 1.3256,
"step": 179
},
{
"epoch": 4.19,
"learning_rate": 7.601351351351351e-05,
"loss": 1.3754,
"step": 180
},
{
"epoch": 4.22,
"learning_rate": 7.58445945945946e-05,
"loss": 1.4267,
"step": 181
},
{
"epoch": 4.24,
"learning_rate": 7.567567567567568e-05,
"loss": 1.4389,
"step": 182
},
{
"epoch": 4.26,
"learning_rate": 7.550675675675675e-05,
"loss": 1.4266,
"step": 183
},
{
"epoch": 4.29,
"learning_rate": 7.533783783783785e-05,
"loss": 1.4098,
"step": 184
},
{
"epoch": 4.31,
"learning_rate": 7.516891891891891e-05,
"loss": 1.0715,
"step": 185
},
{
"epoch": 4.33,
"learning_rate": 7.500000000000001e-05,
"loss": 1.4547,
"step": 186
},
{
"epoch": 4.36,
"learning_rate": 7.483108108108109e-05,
"loss": 1.5758,
"step": 187
},
{
"epoch": 4.38,
"learning_rate": 7.466216216216217e-05,
"loss": 1.3765,
"step": 188
},
{
"epoch": 4.4,
"learning_rate": 7.449324324324325e-05,
"loss": 1.4207,
"step": 189
},
{
"epoch": 4.43,
"learning_rate": 7.432432432432433e-05,
"loss": 1.4264,
"step": 190
},
{
"epoch": 4.45,
"learning_rate": 7.415540540540541e-05,
"loss": 1.2975,
"step": 191
},
{
"epoch": 4.47,
"learning_rate": 7.398648648648649e-05,
"loss": 1.5207,
"step": 192
},
{
"epoch": 4.5,
"learning_rate": 7.381756756756757e-05,
"loss": 1.5805,
"step": 193
},
{
"epoch": 4.52,
"learning_rate": 7.364864864864865e-05,
"loss": 1.3546,
"step": 194
},
{
"epoch": 4.54,
"learning_rate": 7.347972972972973e-05,
"loss": 1.6047,
"step": 195
},
{
"epoch": 4.57,
"learning_rate": 7.331081081081081e-05,
"loss": 1.4313,
"step": 196
},
{
"epoch": 4.59,
"learning_rate": 7.31418918918919e-05,
"loss": 1.371,
"step": 197
},
{
"epoch": 4.61,
"learning_rate": 7.297297297297297e-05,
"loss": 1.4083,
"step": 198
},
{
"epoch": 4.64,
"learning_rate": 7.280405405405406e-05,
"loss": 1.6423,
"step": 199
},
{
"epoch": 4.66,
"learning_rate": 7.263513513513514e-05,
"loss": 1.4229,
"step": 200
},
{
"epoch": 4.68,
"learning_rate": 7.246621621621622e-05,
"loss": 1.4711,
"step": 201
},
{
"epoch": 4.71,
"learning_rate": 7.229729729729731e-05,
"loss": 1.3806,
"step": 202
},
{
"epoch": 4.73,
"learning_rate": 7.212837837837838e-05,
"loss": 1.4641,
"step": 203
},
{
"epoch": 4.75,
"learning_rate": 7.195945945945947e-05,
"loss": 1.6534,
"step": 204
},
{
"epoch": 4.78,
"learning_rate": 7.179054054054054e-05,
"loss": 1.3054,
"step": 205
},
{
"epoch": 4.8,
"learning_rate": 7.162162162162162e-05,
"loss": 1.4058,
"step": 206
},
{
"epoch": 4.82,
"learning_rate": 7.14527027027027e-05,
"loss": 1.5076,
"step": 207
},
{
"epoch": 4.85,
"learning_rate": 7.128378378378378e-05,
"loss": 1.5715,
"step": 208
},
{
"epoch": 4.87,
"learning_rate": 7.111486486486488e-05,
"loss": 1.4723,
"step": 209
},
{
"epoch": 4.89,
"learning_rate": 7.094594594594594e-05,
"loss": 1.3515,
"step": 210
},
{
"epoch": 4.92,
"learning_rate": 7.077702702702704e-05,
"loss": 1.2815,
"step": 211
},
{
"epoch": 4.94,
"learning_rate": 7.06081081081081e-05,
"loss": 1.2335,
"step": 212
},
{
"epoch": 4.96,
"learning_rate": 7.04391891891892e-05,
"loss": 1.2843,
"step": 213
},
{
"epoch": 4.99,
"learning_rate": 7.027027027027028e-05,
"loss": 1.518,
"step": 214
},
{
"epoch": 5.01,
"learning_rate": 7.010135135135135e-05,
"loss": 1.3281,
"step": 215
},
{
"epoch": 5.03,
"learning_rate": 6.993243243243244e-05,
"loss": 1.3571,
"step": 216
},
{
"epoch": 5.06,
"learning_rate": 6.97635135135135e-05,
"loss": 1.2656,
"step": 217
},
{
"epoch": 5.08,
"learning_rate": 6.95945945945946e-05,
"loss": 1.3251,
"step": 218
},
{
"epoch": 5.1,
"learning_rate": 6.942567567567568e-05,
"loss": 1.2875,
"step": 219
},
{
"epoch": 5.13,
"learning_rate": 6.925675675675676e-05,
"loss": 1.4429,
"step": 220
},
{
"epoch": 5.15,
"learning_rate": 6.908783783783784e-05,
"loss": 1.1838,
"step": 221
},
{
"epoch": 5.17,
"learning_rate": 6.891891891891892e-05,
"loss": 1.1694,
"step": 222
},
{
"epoch": 5.2,
"learning_rate": 6.875e-05,
"loss": 1.2747,
"step": 223
},
{
"epoch": 5.22,
"learning_rate": 6.858108108108108e-05,
"loss": 1.3806,
"step": 224
},
{
"epoch": 5.24,
"learning_rate": 6.841216216216217e-05,
"loss": 1.1208,
"step": 225
},
{
"epoch": 5.27,
"learning_rate": 6.824324324324325e-05,
"loss": 1.4053,
"step": 226
},
{
"epoch": 5.29,
"learning_rate": 6.807432432432433e-05,
"loss": 1.3146,
"step": 227
},
{
"epoch": 5.31,
"learning_rate": 6.790540540540541e-05,
"loss": 1.3767,
"step": 228
},
{
"epoch": 5.34,
"learning_rate": 6.773648648648649e-05,
"loss": 1.2501,
"step": 229
},
{
"epoch": 5.36,
"learning_rate": 6.756756756756757e-05,
"loss": 1.3812,
"step": 230
},
{
"epoch": 5.38,
"learning_rate": 6.739864864864865e-05,
"loss": 1.1772,
"step": 231
},
{
"epoch": 5.41,
"learning_rate": 6.722972972972973e-05,
"loss": 1.3066,
"step": 232
},
{
"epoch": 5.43,
"learning_rate": 6.706081081081081e-05,
"loss": 1.3026,
"step": 233
},
{
"epoch": 5.45,
"learning_rate": 6.68918918918919e-05,
"loss": 1.2601,
"step": 234
},
{
"epoch": 5.48,
"learning_rate": 6.672297297297297e-05,
"loss": 1.1287,
"step": 235
},
{
"epoch": 5.5,
"learning_rate": 6.655405405405407e-05,
"loss": 1.4575,
"step": 236
},
{
"epoch": 5.52,
"learning_rate": 6.638513513513513e-05,
"loss": 1.2495,
"step": 237
},
{
"epoch": 5.55,
"learning_rate": 6.621621621621621e-05,
"loss": 1.1763,
"step": 238
},
{
"epoch": 5.57,
"learning_rate": 6.604729729729731e-05,
"loss": 1.2768,
"step": 239
},
{
"epoch": 5.59,
"learning_rate": 6.587837837837837e-05,
"loss": 1.3268,
"step": 240
},
{
"epoch": 5.62,
"learning_rate": 6.570945945945947e-05,
"loss": 1.2082,
"step": 241
},
{
"epoch": 5.64,
"learning_rate": 6.554054054054054e-05,
"loss": 1.3312,
"step": 242
},
{
"epoch": 5.66,
"learning_rate": 6.537162162162163e-05,
"loss": 1.3582,
"step": 243
},
{
"epoch": 5.69,
"learning_rate": 6.52027027027027e-05,
"loss": 1.4009,
"step": 244
},
{
"epoch": 5.71,
"learning_rate": 6.503378378378379e-05,
"loss": 1.3129,
"step": 245
},
{
"epoch": 5.73,
"learning_rate": 6.486486486486487e-05,
"loss": 1.0997,
"step": 246
},
{
"epoch": 5.76,
"learning_rate": 6.469594594594594e-05,
"loss": 1.3952,
"step": 247
},
{
"epoch": 5.78,
"learning_rate": 6.452702702702703e-05,
"loss": 1.328,
"step": 248
},
{
"epoch": 5.8,
"learning_rate": 6.43581081081081e-05,
"loss": 1.3402,
"step": 249
},
{
"epoch": 5.83,
"learning_rate": 6.41891891891892e-05,
"loss": 1.6361,
"step": 250
},
{
"epoch": 5.85,
"learning_rate": 6.402027027027028e-05,
"loss": 1.2595,
"step": 251
},
{
"epoch": 5.87,
"learning_rate": 6.385135135135136e-05,
"loss": 1.2653,
"step": 252
},
{
"epoch": 5.9,
"learning_rate": 6.368243243243244e-05,
"loss": 1.2824,
"step": 253
},
{
"epoch": 5.92,
"learning_rate": 6.351351351351352e-05,
"loss": 1.3233,
"step": 254
},
{
"epoch": 5.94,
"learning_rate": 6.33445945945946e-05,
"loss": 1.1506,
"step": 255
},
{
"epoch": 5.97,
"learning_rate": 6.317567567567568e-05,
"loss": 1.1696,
"step": 256
},
{
"epoch": 5.99,
"learning_rate": 6.300675675675676e-05,
"loss": 1.3595,
"step": 257
},
{
"epoch": 6.01,
"learning_rate": 6.283783783783784e-05,
"loss": 1.2825,
"step": 258
},
{
"epoch": 6.03,
"learning_rate": 6.266891891891892e-05,
"loss": 1.4051,
"step": 259
},
{
"epoch": 6.06,
"learning_rate": 6.25e-05,
"loss": 1.2085,
"step": 260
},
{
"epoch": 6.08,
"learning_rate": 6.233108108108108e-05,
"loss": 1.2621,
"step": 261
},
{
"epoch": 6.1,
"learning_rate": 6.216216216216216e-05,
"loss": 1.293,
"step": 262
},
{
"epoch": 6.13,
"learning_rate": 6.199324324324324e-05,
"loss": 1.2971,
"step": 263
},
{
"epoch": 6.15,
"learning_rate": 6.182432432432432e-05,
"loss": 1.0583,
"step": 264
},
{
"epoch": 6.17,
"learning_rate": 6.16554054054054e-05,
"loss": 1.225,
"step": 265
},
{
"epoch": 6.2,
"learning_rate": 6.14864864864865e-05,
"loss": 1.0673,
"step": 266
},
{
"epoch": 6.22,
"learning_rate": 6.131756756756757e-05,
"loss": 1.1158,
"step": 267
},
{
"epoch": 6.24,
"learning_rate": 6.114864864864866e-05,
"loss": 1.1983,
"step": 268
},
{
"epoch": 6.27,
"learning_rate": 6.097972972972973e-05,
"loss": 1.1234,
"step": 269
},
{
"epoch": 6.29,
"learning_rate": 6.0810810810810814e-05,
"loss": 1.2147,
"step": 270
},
{
"epoch": 6.31,
"learning_rate": 6.06418918918919e-05,
"loss": 1.0961,
"step": 271
},
{
"epoch": 6.34,
"learning_rate": 6.0472972972972976e-05,
"loss": 1.2271,
"step": 272
},
{
"epoch": 6.36,
"learning_rate": 6.030405405405406e-05,
"loss": 0.8272,
"step": 273
},
{
"epoch": 6.38,
"learning_rate": 6.013513513513514e-05,
"loss": 1.0314,
"step": 274
},
{
"epoch": 6.41,
"learning_rate": 5.996621621621622e-05,
"loss": 1.172,
"step": 275
},
{
"epoch": 6.43,
"learning_rate": 5.9797297297297305e-05,
"loss": 1.1037,
"step": 276
},
{
"epoch": 6.45,
"learning_rate": 5.962837837837838e-05,
"loss": 1.0629,
"step": 277
},
{
"epoch": 6.48,
"learning_rate": 5.9459459459459466e-05,
"loss": 1.1261,
"step": 278
},
{
"epoch": 6.5,
"learning_rate": 5.929054054054054e-05,
"loss": 1.2574,
"step": 279
},
{
"epoch": 6.52,
"learning_rate": 5.912162162162163e-05,
"loss": 1.3313,
"step": 280
},
{
"epoch": 6.55,
"learning_rate": 5.89527027027027e-05,
"loss": 0.924,
"step": 281
},
{
"epoch": 6.57,
"learning_rate": 5.878378378378379e-05,
"loss": 1.1797,
"step": 282
},
{
"epoch": 6.59,
"learning_rate": 5.861486486486487e-05,
"loss": 1.1554,
"step": 283
},
{
"epoch": 6.62,
"learning_rate": 5.8445945945945943e-05,
"loss": 1.2582,
"step": 284
},
{
"epoch": 6.64,
"learning_rate": 5.827702702702703e-05,
"loss": 1.2177,
"step": 285
},
{
"epoch": 6.66,
"learning_rate": 5.8108108108108105e-05,
"loss": 1.1448,
"step": 286
},
{
"epoch": 6.69,
"learning_rate": 5.793918918918919e-05,
"loss": 1.1025,
"step": 287
},
{
"epoch": 6.71,
"learning_rate": 5.777027027027028e-05,
"loss": 1.1173,
"step": 288
},
{
"epoch": 6.73,
"learning_rate": 5.760135135135135e-05,
"loss": 1.1789,
"step": 289
},
{
"epoch": 6.76,
"learning_rate": 5.7432432432432434e-05,
"loss": 1.3601,
"step": 290
},
{
"epoch": 6.78,
"learning_rate": 5.7263513513513515e-05,
"loss": 1.2766,
"step": 291
},
{
"epoch": 6.8,
"learning_rate": 5.7094594594594595e-05,
"loss": 1.2541,
"step": 292
},
{
"epoch": 6.83,
"learning_rate": 5.692567567567568e-05,
"loss": 1.2084,
"step": 293
},
{
"epoch": 6.85,
"learning_rate": 5.6756756756756757e-05,
"loss": 1.3129,
"step": 294
},
{
"epoch": 6.87,
"learning_rate": 5.6587837837837844e-05,
"loss": 1.1758,
"step": 295
},
{
"epoch": 6.9,
"learning_rate": 5.641891891891892e-05,
"loss": 1.341,
"step": 296
},
{
"epoch": 6.92,
"learning_rate": 5.6250000000000005e-05,
"loss": 1.3618,
"step": 297
},
{
"epoch": 6.94,
"learning_rate": 5.6081081081081086e-05,
"loss": 1.0368,
"step": 298
},
{
"epoch": 6.97,
"learning_rate": 5.591216216216216e-05,
"loss": 1.1718,
"step": 299
},
{
"epoch": 6.99,
"learning_rate": 5.574324324324325e-05,
"loss": 1.1364,
"step": 300
},
{
"epoch": 7.01,
"learning_rate": 5.557432432432432e-05,
"loss": 1.1075,
"step": 301
},
{
"epoch": 7.04,
"learning_rate": 5.540540540540541e-05,
"loss": 1.2325,
"step": 302
},
{
"epoch": 7.06,
"learning_rate": 5.5236486486486496e-05,
"loss": 0.8635,
"step": 303
},
{
"epoch": 7.08,
"learning_rate": 5.506756756756757e-05,
"loss": 0.7712,
"step": 304
},
{
"epoch": 7.11,
"learning_rate": 5.489864864864866e-05,
"loss": 0.9811,
"step": 305
},
{
"epoch": 7.13,
"learning_rate": 5.472972972972973e-05,
"loss": 1.1597,
"step": 306
},
{
"epoch": 7.15,
"learning_rate": 5.456081081081081e-05,
"loss": 0.9311,
"step": 307
},
{
"epoch": 7.18,
"learning_rate": 5.43918918918919e-05,
"loss": 1.1239,
"step": 308
},
{
"epoch": 7.2,
"learning_rate": 5.422297297297297e-05,
"loss": 1.2107,
"step": 309
},
{
"epoch": 7.22,
"learning_rate": 5.405405405405406e-05,
"loss": 1.2178,
"step": 310
},
{
"epoch": 7.25,
"learning_rate": 5.3885135135135134e-05,
"loss": 1.1905,
"step": 311
},
{
"epoch": 7.27,
"learning_rate": 5.371621621621622e-05,
"loss": 1.2219,
"step": 312
},
{
"epoch": 7.29,
"learning_rate": 5.35472972972973e-05,
"loss": 1.0516,
"step": 313
},
{
"epoch": 7.32,
"learning_rate": 5.337837837837838e-05,
"loss": 1.0192,
"step": 314
},
{
"epoch": 7.34,
"learning_rate": 5.3209459459459463e-05,
"loss": 0.9752,
"step": 315
},
{
"epoch": 7.36,
"learning_rate": 5.304054054054054e-05,
"loss": 0.9826,
"step": 316
},
{
"epoch": 7.39,
"learning_rate": 5.2871621621621625e-05,
"loss": 1.3142,
"step": 317
},
{
"epoch": 7.41,
"learning_rate": 5.27027027027027e-05,
"loss": 1.1342,
"step": 318
},
{
"epoch": 7.43,
"learning_rate": 5.2533783783783786e-05,
"loss": 1.1025,
"step": 319
},
{
"epoch": 7.46,
"learning_rate": 5.2364864864864873e-05,
"loss": 1.2068,
"step": 320
},
{
"epoch": 7.48,
"learning_rate": 5.219594594594595e-05,
"loss": 1.0683,
"step": 321
},
{
"epoch": 7.5,
"learning_rate": 5.202702702702703e-05,
"loss": 0.859,
"step": 322
},
{
"epoch": 7.53,
"learning_rate": 5.185810810810811e-05,
"loss": 1.0902,
"step": 323
},
{
"epoch": 7.55,
"learning_rate": 5.168918918918919e-05,
"loss": 1.0506,
"step": 324
},
{
"epoch": 7.57,
"learning_rate": 5.152027027027028e-05,
"loss": 1.019,
"step": 325
},
{
"epoch": 7.6,
"learning_rate": 5.135135135135135e-05,
"loss": 0.6924,
"step": 326
},
{
"epoch": 7.62,
"learning_rate": 5.118243243243244e-05,
"loss": 1.1495,
"step": 327
},
{
"epoch": 7.64,
"learning_rate": 5.101351351351351e-05,
"loss": 1.0561,
"step": 328
},
{
"epoch": 7.67,
"learning_rate": 5.08445945945946e-05,
"loss": 1.1057,
"step": 329
},
{
"epoch": 7.69,
"learning_rate": 5.067567567567568e-05,
"loss": 1.0621,
"step": 330
},
{
"epoch": 7.71,
"learning_rate": 5.0506756756756754e-05,
"loss": 1.0147,
"step": 331
},
{
"epoch": 7.74,
"learning_rate": 5.033783783783784e-05,
"loss": 1.0904,
"step": 332
},
{
"epoch": 7.76,
"learning_rate": 5.0168918918918915e-05,
"loss": 1.1281,
"step": 333
},
{
"epoch": 7.78,
"learning_rate": 5e-05,
"loss": 1.0421,
"step": 334
},
{
"epoch": 7.81,
"learning_rate": 4.983108108108108e-05,
"loss": 1.1218,
"step": 335
},
{
"epoch": 7.83,
"learning_rate": 4.9662162162162164e-05,
"loss": 1.0854,
"step": 336
},
{
"epoch": 7.85,
"learning_rate": 4.949324324324325e-05,
"loss": 1.1577,
"step": 337
},
{
"epoch": 7.88,
"learning_rate": 4.9324324324324325e-05,
"loss": 1.078,
"step": 338
},
{
"epoch": 7.9,
"learning_rate": 4.9155405405405406e-05,
"loss": 1.1829,
"step": 339
},
{
"epoch": 7.92,
"learning_rate": 4.8986486486486486e-05,
"loss": 1.09,
"step": 340
},
{
"epoch": 7.95,
"learning_rate": 4.881756756756757e-05,
"loss": 0.9816,
"step": 341
},
{
"epoch": 7.97,
"learning_rate": 4.8648648648648654e-05,
"loss": 0.9653,
"step": 342
},
{
"epoch": 7.99,
"learning_rate": 4.8479729729729735e-05,
"loss": 1.1243,
"step": 343
},
{
"epoch": 8.02,
"learning_rate": 4.8310810810810816e-05,
"loss": 0.9883,
"step": 344
},
{
"epoch": 8.04,
"learning_rate": 4.8141891891891896e-05,
"loss": 0.8322,
"step": 345
},
{
"epoch": 8.06,
"learning_rate": 4.797297297297298e-05,
"loss": 0.9729,
"step": 346
},
{
"epoch": 8.09,
"learning_rate": 4.780405405405405e-05,
"loss": 1.0465,
"step": 347
},
{
"epoch": 8.11,
"learning_rate": 4.763513513513514e-05,
"loss": 0.8629,
"step": 348
},
{
"epoch": 8.13,
"learning_rate": 4.746621621621622e-05,
"loss": 1.15,
"step": 349
},
{
"epoch": 8.16,
"learning_rate": 4.72972972972973e-05,
"loss": 0.9984,
"step": 350
},
{
"epoch": 8.18,
"learning_rate": 4.712837837837838e-05,
"loss": 0.939,
"step": 351
},
{
"epoch": 8.2,
"learning_rate": 4.695945945945946e-05,
"loss": 0.9231,
"step": 352
},
{
"epoch": 8.23,
"learning_rate": 4.679054054054055e-05,
"loss": 1.1219,
"step": 353
},
{
"epoch": 8.25,
"learning_rate": 4.662162162162162e-05,
"loss": 1.1236,
"step": 354
},
{
"epoch": 8.27,
"learning_rate": 4.64527027027027e-05,
"loss": 0.9729,
"step": 355
},
{
"epoch": 8.3,
"learning_rate": 4.628378378378378e-05,
"loss": 1.0206,
"step": 356
},
{
"epoch": 8.32,
"learning_rate": 4.6114864864864864e-05,
"loss": 1.1789,
"step": 357
},
{
"epoch": 8.34,
"learning_rate": 4.594594594594595e-05,
"loss": 0.9932,
"step": 358
},
{
"epoch": 8.37,
"learning_rate": 4.577702702702703e-05,
"loss": 1.0049,
"step": 359
},
{
"epoch": 8.39,
"learning_rate": 4.560810810810811e-05,
"loss": 1.0889,
"step": 360
},
{
"epoch": 8.41,
"learning_rate": 4.543918918918919e-05,
"loss": 0.8475,
"step": 361
},
{
"epoch": 8.43,
"learning_rate": 4.5270270270270274e-05,
"loss": 1.0319,
"step": 362
},
{
"epoch": 8.46,
"learning_rate": 4.510135135135135e-05,
"loss": 0.9336,
"step": 363
},
{
"epoch": 8.48,
"learning_rate": 4.4932432432432435e-05,
"loss": 0.9678,
"step": 364
},
{
"epoch": 8.5,
"learning_rate": 4.4763513513513516e-05,
"loss": 0.8758,
"step": 365
},
{
"epoch": 8.53,
"learning_rate": 4.4594594594594596e-05,
"loss": 0.9342,
"step": 366
},
{
"epoch": 8.55,
"learning_rate": 4.442567567567568e-05,
"loss": 1.1054,
"step": 367
},
{
"epoch": 8.57,
"learning_rate": 4.425675675675676e-05,
"loss": 0.8595,
"step": 368
},
{
"epoch": 8.6,
"learning_rate": 4.4087837837837845e-05,
"loss": 0.9209,
"step": 369
}
],
"max_steps": 630,
"num_train_epochs": 15,
"total_flos": 1.3361056070290637e+17,
"trial_name": null,
"trial_params": null
}