zephyr-convsearch-7b / trainer_state.json
erbacher's picture
Model save
33adfe6
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.620551090700344,
"eval_steps": 500,
"global_step": 344,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.9999830768577445e-05,
"loss": 0.7381,
"step": 1
},
{
"epoch": 0.04,
"learning_rate": 1.9999323080037623e-05,
"loss": 0.7407,
"step": 2
},
{
"epoch": 0.06,
"learning_rate": 1.9998476951563914e-05,
"loss": 0.7359,
"step": 3
},
{
"epoch": 0.07,
"learning_rate": 1.999729241179462e-05,
"loss": 0.7298,
"step": 4
},
{
"epoch": 0.09,
"learning_rate": 1.9995769500822007e-05,
"loss": 0.7305,
"step": 5
},
{
"epoch": 0.11,
"learning_rate": 1.999390827019096e-05,
"loss": 0.7124,
"step": 6
},
{
"epoch": 0.13,
"learning_rate": 1.9991708782897214e-05,
"loss": 0.7076,
"step": 7
},
{
"epoch": 0.15,
"learning_rate": 1.998917111338525e-05,
"loss": 0.6927,
"step": 8
},
{
"epoch": 0.17,
"learning_rate": 1.9986295347545738e-05,
"loss": 0.6858,
"step": 9
},
{
"epoch": 0.18,
"learning_rate": 1.9983081582712684e-05,
"loss": 0.6812,
"step": 10
},
{
"epoch": 0.2,
"learning_rate": 1.9979529927660076e-05,
"loss": 0.6788,
"step": 11
},
{
"epoch": 0.22,
"learning_rate": 1.9975640502598243e-05,
"loss": 0.6633,
"step": 12
},
{
"epoch": 0.24,
"learning_rate": 1.9971413439169777e-05,
"loss": 0.6589,
"step": 13
},
{
"epoch": 0.26,
"learning_rate": 1.996684888044506e-05,
"loss": 0.6471,
"step": 14
},
{
"epoch": 0.28,
"learning_rate": 1.9961946980917457e-05,
"loss": 0.6474,
"step": 15
},
{
"epoch": 0.29,
"learning_rate": 1.9956707906498046e-05,
"loss": 0.6419,
"step": 16
},
{
"epoch": 0.31,
"learning_rate": 1.9951131834510034e-05,
"loss": 0.6345,
"step": 17
},
{
"epoch": 0.33,
"learning_rate": 1.9945218953682736e-05,
"loss": 0.635,
"step": 18
},
{
"epoch": 0.35,
"learning_rate": 1.99389694641452e-05,
"loss": 0.6309,
"step": 19
},
{
"epoch": 0.37,
"learning_rate": 1.9932383577419432e-05,
"loss": 0.619,
"step": 20
},
{
"epoch": 0.39,
"learning_rate": 1.9925461516413224e-05,
"loss": 0.6184,
"step": 21
},
{
"epoch": 0.4,
"learning_rate": 1.9918203515412616e-05,
"loss": 0.6127,
"step": 22
},
{
"epoch": 0.42,
"learning_rate": 1.9910609820073986e-05,
"loss": 0.6108,
"step": 23
},
{
"epoch": 0.44,
"learning_rate": 1.9902680687415704e-05,
"loss": 0.6138,
"step": 24
},
{
"epoch": 0.46,
"learning_rate": 1.9894416385809444e-05,
"loss": 0.6039,
"step": 25
},
{
"epoch": 0.48,
"learning_rate": 1.9885817194971116e-05,
"loss": 0.6123,
"step": 26
},
{
"epoch": 0.5,
"learning_rate": 1.9876883405951378e-05,
"loss": 0.5973,
"step": 27
},
{
"epoch": 0.51,
"learning_rate": 1.9867615321125796e-05,
"loss": 0.6002,
"step": 28
},
{
"epoch": 0.53,
"learning_rate": 1.9858013254184597e-05,
"loss": 0.5908,
"step": 29
},
{
"epoch": 0.55,
"learning_rate": 1.9848077530122083e-05,
"loss": 0.596,
"step": 30
},
{
"epoch": 0.57,
"learning_rate": 1.983780848522559e-05,
"loss": 0.5886,
"step": 31
},
{
"epoch": 0.59,
"learning_rate": 1.9827206467064133e-05,
"loss": 0.5908,
"step": 32
},
{
"epoch": 0.61,
"learning_rate": 1.9816271834476642e-05,
"loss": 0.5821,
"step": 33
},
{
"epoch": 0.62,
"learning_rate": 1.9805004957559795e-05,
"loss": 0.5796,
"step": 34
},
{
"epoch": 0.62,
"eval_loss": 0.5779749751091003,
"eval_runtime": 24.4017,
"eval_samples_per_second": 8.196,
"eval_steps_per_second": 0.533,
"step": 34
},
{
"epoch": 1.01,
"learning_rate": 1.9793406217655516e-05,
"loss": 0.5719,
"step": 35
},
{
"epoch": 1.03,
"learning_rate": 1.9781476007338058e-05,
"loss": 0.5771,
"step": 36
},
{
"epoch": 1.05,
"learning_rate": 1.976921473040071e-05,
"loss": 0.5709,
"step": 37
},
{
"epoch": 1.06,
"learning_rate": 1.9756622801842144e-05,
"loss": 0.567,
"step": 38
},
{
"epoch": 1.08,
"learning_rate": 1.9743700647852356e-05,
"loss": 0.5746,
"step": 39
},
{
"epoch": 1.1,
"learning_rate": 1.973044870579824e-05,
"loss": 0.5651,
"step": 40
},
{
"epoch": 1.12,
"learning_rate": 1.9716867424208805e-05,
"loss": 0.5621,
"step": 41
},
{
"epoch": 1.14,
"learning_rate": 1.9702957262759964e-05,
"loss": 0.5581,
"step": 42
},
{
"epoch": 1.16,
"learning_rate": 1.9688718692259007e-05,
"loss": 0.5555,
"step": 43
},
{
"epoch": 1.18,
"learning_rate": 1.967415219462864e-05,
"loss": 0.5512,
"step": 44
},
{
"epoch": 1.19,
"learning_rate": 1.9659258262890683e-05,
"loss": 0.554,
"step": 45
},
{
"epoch": 1.21,
"learning_rate": 1.964403740114939e-05,
"loss": 0.5507,
"step": 46
},
{
"epoch": 1.23,
"learning_rate": 1.962849012457438e-05,
"loss": 0.5482,
"step": 47
},
{
"epoch": 1.25,
"learning_rate": 1.961261695938319e-05,
"loss": 0.5439,
"step": 48
},
{
"epoch": 1.27,
"learning_rate": 1.9596418442823495e-05,
"loss": 0.5387,
"step": 49
},
{
"epoch": 1.29,
"learning_rate": 1.957989512315489e-05,
"loss": 0.5434,
"step": 50
},
{
"epoch": 1.3,
"learning_rate": 1.9563047559630356e-05,
"loss": 0.5388,
"step": 51
},
{
"epoch": 1.32,
"learning_rate": 1.954587632247732e-05,
"loss": 0.5385,
"step": 52
},
{
"epoch": 1.34,
"learning_rate": 1.9528381992878362e-05,
"loss": 0.5364,
"step": 53
},
{
"epoch": 1.36,
"learning_rate": 1.9510565162951538e-05,
"loss": 0.535,
"step": 54
},
{
"epoch": 1.38,
"learning_rate": 1.949242643573034e-05,
"loss": 0.5253,
"step": 55
},
{
"epoch": 1.4,
"learning_rate": 1.9473966425143292e-05,
"loss": 0.5278,
"step": 56
},
{
"epoch": 1.41,
"learning_rate": 1.945518575599317e-05,
"loss": 0.5316,
"step": 57
},
{
"epoch": 1.43,
"learning_rate": 1.9436085063935837e-05,
"loss": 0.5267,
"step": 58
},
{
"epoch": 1.45,
"learning_rate": 1.9416664995458756e-05,
"loss": 0.5265,
"step": 59
},
{
"epoch": 1.47,
"learning_rate": 1.9396926207859085e-05,
"loss": 0.5235,
"step": 60
},
{
"epoch": 1.49,
"learning_rate": 1.937686936922145e-05,
"loss": 0.5217,
"step": 61
},
{
"epoch": 1.51,
"learning_rate": 1.9356495158395317e-05,
"loss": 0.5243,
"step": 62
},
{
"epoch": 1.52,
"learning_rate": 1.9335804264972018e-05,
"loss": 0.5189,
"step": 63
},
{
"epoch": 1.54,
"learning_rate": 1.9314797389261426e-05,
"loss": 0.5193,
"step": 64
},
{
"epoch": 1.56,
"learning_rate": 1.9293475242268224e-05,
"loss": 0.5182,
"step": 65
},
{
"epoch": 1.58,
"learning_rate": 1.9271838545667876e-05,
"loss": 0.5222,
"step": 66
},
{
"epoch": 1.6,
"learning_rate": 1.924988803178216e-05,
"loss": 0.516,
"step": 67
},
{
"epoch": 1.62,
"learning_rate": 1.9227624443554425e-05,
"loss": 0.5119,
"step": 68
},
{
"epoch": 1.62,
"eval_loss": 0.5121633410453796,
"eval_runtime": 23.8105,
"eval_samples_per_second": 8.4,
"eval_steps_per_second": 0.546,
"step": 68
},
{
"epoch": 2.0,
"learning_rate": 1.9205048534524405e-05,
"loss": 0.5095,
"step": 69
},
{
"epoch": 2.02,
"learning_rate": 1.9182161068802742e-05,
"loss": 0.5091,
"step": 70
},
{
"epoch": 2.04,
"learning_rate": 1.9158962821045113e-05,
"loss": 0.5086,
"step": 71
},
{
"epoch": 2.06,
"learning_rate": 1.913545457642601e-05,
"loss": 0.507,
"step": 72
},
{
"epoch": 2.07,
"learning_rate": 1.9111637130612172e-05,
"loss": 0.5096,
"step": 73
},
{
"epoch": 2.09,
"learning_rate": 1.9087511289735646e-05,
"loss": 0.5124,
"step": 74
},
{
"epoch": 2.11,
"learning_rate": 1.9063077870366504e-05,
"loss": 0.5013,
"step": 75
},
{
"epoch": 2.13,
"learning_rate": 1.9038337699485207e-05,
"loss": 0.5048,
"step": 76
},
{
"epoch": 2.15,
"learning_rate": 1.9013291614454622e-05,
"loss": 0.4988,
"step": 77
},
{
"epoch": 2.17,
"learning_rate": 1.8987940462991673e-05,
"loss": 0.502,
"step": 78
},
{
"epoch": 2.18,
"learning_rate": 1.8962285103138637e-05,
"loss": 0.4969,
"step": 79
},
{
"epoch": 2.2,
"learning_rate": 1.8936326403234125e-05,
"loss": 0.503,
"step": 80
},
{
"epoch": 2.22,
"learning_rate": 1.891006524188368e-05,
"loss": 0.4978,
"step": 81
},
{
"epoch": 2.24,
"learning_rate": 1.8883502507930044e-05,
"loss": 0.4954,
"step": 82
},
{
"epoch": 2.26,
"learning_rate": 1.8856639100423062e-05,
"loss": 0.4939,
"step": 83
},
{
"epoch": 2.28,
"learning_rate": 1.8829475928589272e-05,
"loss": 0.4942,
"step": 84
},
{
"epoch": 2.3,
"learning_rate": 1.880201391180111e-05,
"loss": 0.4933,
"step": 85
},
{
"epoch": 2.31,
"learning_rate": 1.877425397954582e-05,
"loss": 0.4946,
"step": 86
},
{
"epoch": 2.33,
"learning_rate": 1.874619707139396e-05,
"loss": 0.4939,
"step": 87
},
{
"epoch": 2.35,
"learning_rate": 1.8717844136967626e-05,
"loss": 0.4922,
"step": 88
},
{
"epoch": 2.37,
"learning_rate": 1.8689196135908303e-05,
"loss": 0.4925,
"step": 89
},
{
"epoch": 2.39,
"learning_rate": 1.866025403784439e-05,
"loss": 0.4902,
"step": 90
},
{
"epoch": 2.41,
"learning_rate": 1.8631018822358363e-05,
"loss": 0.4866,
"step": 91
},
{
"epoch": 2.42,
"learning_rate": 1.860149147895366e-05,
"loss": 0.4937,
"step": 92
},
{
"epoch": 2.44,
"learning_rate": 1.8571673007021124e-05,
"loss": 0.4897,
"step": 93
},
{
"epoch": 2.46,
"learning_rate": 1.854156441580526e-05,
"loss": 0.4879,
"step": 94
},
{
"epoch": 2.48,
"learning_rate": 1.8511166724369997e-05,
"loss": 0.4888,
"step": 95
},
{
"epoch": 2.5,
"learning_rate": 1.848048096156426e-05,
"loss": 0.4908,
"step": 96
},
{
"epoch": 2.52,
"learning_rate": 1.8449508165987106e-05,
"loss": 0.4856,
"step": 97
},
{
"epoch": 2.53,
"learning_rate": 1.8418249385952575e-05,
"loss": 0.4842,
"step": 98
},
{
"epoch": 2.55,
"learning_rate": 1.8386705679454243e-05,
"loss": 0.4877,
"step": 99
},
{
"epoch": 2.57,
"learning_rate": 1.8354878114129368e-05,
"loss": 0.491,
"step": 100
},
{
"epoch": 2.59,
"learning_rate": 1.832276776722278e-05,
"loss": 0.4877,
"step": 101
},
{
"epoch": 2.61,
"learning_rate": 1.8290375725550417e-05,
"loss": 0.4863,
"step": 102
},
{
"epoch": 2.63,
"learning_rate": 1.8257703085462542e-05,
"loss": 0.4799,
"step": 103
},
{
"epoch": 2.63,
"eval_loss": 0.4830611050128937,
"eval_runtime": 23.8066,
"eval_samples_per_second": 8.401,
"eval_steps_per_second": 0.546,
"step": 103
},
{
"epoch": 3.01,
"learning_rate": 1.8224750952806626e-05,
"loss": 0.4797,
"step": 104
},
{
"epoch": 3.03,
"learning_rate": 1.819152044288992e-05,
"loss": 0.4833,
"step": 105
},
{
"epoch": 3.05,
"learning_rate": 1.8158012680441723e-05,
"loss": 0.4833,
"step": 106
},
{
"epoch": 3.07,
"learning_rate": 1.8124228799575295e-05,
"loss": 0.4818,
"step": 107
},
{
"epoch": 3.08,
"learning_rate": 1.8090169943749477e-05,
"loss": 0.4885,
"step": 108
},
{
"epoch": 3.1,
"learning_rate": 1.8055837265729996e-05,
"loss": 0.4785,
"step": 109
},
{
"epoch": 3.12,
"learning_rate": 1.802123192755044e-05,
"loss": 0.4789,
"step": 110
},
{
"epoch": 3.14,
"learning_rate": 1.798635510047293e-05,
"loss": 0.4795,
"step": 111
},
{
"epoch": 3.16,
"learning_rate": 1.795120796494848e-05,
"loss": 0.478,
"step": 112
},
{
"epoch": 3.18,
"learning_rate": 1.7915791710577035e-05,
"loss": 0.477,
"step": 113
},
{
"epoch": 3.19,
"learning_rate": 1.788010753606722e-05,
"loss": 0.4746,
"step": 114
},
{
"epoch": 3.21,
"learning_rate": 1.784415664919576e-05,
"loss": 0.4811,
"step": 115
},
{
"epoch": 3.23,
"learning_rate": 1.7807940266766595e-05,
"loss": 0.477,
"step": 116
},
{
"epoch": 3.25,
"learning_rate": 1.777145961456971e-05,
"loss": 0.4744,
"step": 117
},
{
"epoch": 3.27,
"learning_rate": 1.7734715927339642e-05,
"loss": 0.4753,
"step": 118
},
{
"epoch": 3.29,
"learning_rate": 1.769771044871368e-05,
"loss": 0.4754,
"step": 119
},
{
"epoch": 3.3,
"learning_rate": 1.766044443118978e-05,
"loss": 0.4773,
"step": 120
},
{
"epoch": 3.32,
"learning_rate": 1.7622919136084183e-05,
"loss": 0.4743,
"step": 121
},
{
"epoch": 3.34,
"learning_rate": 1.7585135833488692e-05,
"loss": 0.479,
"step": 122
},
{
"epoch": 3.36,
"learning_rate": 1.7547095802227723e-05,
"loss": 0.4747,
"step": 123
},
{
"epoch": 3.38,
"learning_rate": 1.7508800329814993e-05,
"loss": 0.4763,
"step": 124
},
{
"epoch": 3.4,
"learning_rate": 1.7470250712409963e-05,
"loss": 0.47,
"step": 125
},
{
"epoch": 3.42,
"learning_rate": 1.7431448254773943e-05,
"loss": 0.4741,
"step": 126
},
{
"epoch": 3.43,
"learning_rate": 1.739239427022596e-05,
"loss": 0.4753,
"step": 127
},
{
"epoch": 3.45,
"learning_rate": 1.735309008059829e-05,
"loss": 0.4738,
"step": 128
},
{
"epoch": 3.47,
"learning_rate": 1.7313537016191706e-05,
"loss": 0.4769,
"step": 129
},
{
"epoch": 3.49,
"learning_rate": 1.7273736415730488e-05,
"loss": 0.4749,
"step": 130
},
{
"epoch": 3.51,
"learning_rate": 1.723368962631708e-05,
"loss": 0.4703,
"step": 131
},
{
"epoch": 3.53,
"learning_rate": 1.7193398003386514e-05,
"loss": 0.4722,
"step": 132
},
{
"epoch": 3.54,
"learning_rate": 1.7152862910660516e-05,
"loss": 0.474,
"step": 133
},
{
"epoch": 3.56,
"learning_rate": 1.711208572010137e-05,
"loss": 0.4721,
"step": 134
},
{
"epoch": 3.58,
"learning_rate": 1.7071067811865477e-05,
"loss": 0.4755,
"step": 135
},
{
"epoch": 3.6,
"learning_rate": 1.702981057425662e-05,
"loss": 0.4717,
"step": 136
},
{
"epoch": 3.62,
"learning_rate": 1.6988315403679e-05,
"loss": 0.4712,
"step": 137
},
{
"epoch": 3.62,
"eval_loss": 0.470627099275589,
"eval_runtime": 23.8372,
"eval_samples_per_second": 8.39,
"eval_steps_per_second": 0.545,
"step": 137
},
{
"epoch": 4.0,
"learning_rate": 1.6946583704589973e-05,
"loss": 0.4679,
"step": 138
},
{
"epoch": 4.02,
"learning_rate": 1.6904616889452497e-05,
"loss": 0.4707,
"step": 139
},
{
"epoch": 4.04,
"learning_rate": 1.686241637868734e-05,
"loss": 0.4683,
"step": 140
},
{
"epoch": 4.06,
"learning_rate": 1.6819983600624986e-05,
"loss": 0.4715,
"step": 141
},
{
"epoch": 4.08,
"learning_rate": 1.6777319991457325e-05,
"loss": 0.4721,
"step": 142
},
{
"epoch": 4.09,
"learning_rate": 1.6734426995189003e-05,
"loss": 0.4719,
"step": 143
},
{
"epoch": 4.11,
"learning_rate": 1.6691306063588583e-05,
"loss": 0.4662,
"step": 144
},
{
"epoch": 4.13,
"learning_rate": 1.6647958656139377e-05,
"loss": 0.4684,
"step": 145
},
{
"epoch": 4.15,
"learning_rate": 1.6604386239990077e-05,
"loss": 0.4671,
"step": 146
},
{
"epoch": 4.17,
"learning_rate": 1.6560590289905074e-05,
"loss": 0.4671,
"step": 147
},
{
"epoch": 4.19,
"learning_rate": 1.6516572288214555e-05,
"loss": 0.4642,
"step": 148
},
{
"epoch": 4.2,
"learning_rate": 1.6472333724764326e-05,
"loss": 0.468,
"step": 149
},
{
"epoch": 4.22,
"learning_rate": 1.6427876096865394e-05,
"loss": 0.4699,
"step": 150
},
{
"epoch": 4.24,
"learning_rate": 1.6383200909243285e-05,
"loss": 0.4646,
"step": 151
},
{
"epoch": 4.26,
"learning_rate": 1.63383096739871e-05,
"loss": 0.4626,
"step": 152
},
{
"epoch": 4.28,
"learning_rate": 1.6293203910498375e-05,
"loss": 0.4665,
"step": 153
},
{
"epoch": 4.3,
"learning_rate": 1.6247885145439602e-05,
"loss": 0.4654,
"step": 154
},
{
"epoch": 4.31,
"learning_rate": 1.6202354912682602e-05,
"loss": 0.4695,
"step": 155
},
{
"epoch": 4.33,
"learning_rate": 1.6156614753256583e-05,
"loss": 0.4646,
"step": 156
},
{
"epoch": 4.35,
"learning_rate": 1.6110666215296e-05,
"loss": 0.4686,
"step": 157
},
{
"epoch": 4.37,
"learning_rate": 1.6064510853988137e-05,
"loss": 0.4635,
"step": 158
},
{
"epoch": 4.39,
"learning_rate": 1.6018150231520486e-05,
"loss": 0.4638,
"step": 159
},
{
"epoch": 4.41,
"learning_rate": 1.5971585917027864e-05,
"loss": 0.4666,
"step": 160
},
{
"epoch": 4.42,
"learning_rate": 1.592481948653931e-05,
"loss": 0.4668,
"step": 161
},
{
"epoch": 4.44,
"learning_rate": 1.5877852522924733e-05,
"loss": 0.4656,
"step": 162
},
{
"epoch": 4.46,
"learning_rate": 1.5830686615841348e-05,
"loss": 0.4652,
"step": 163
},
{
"epoch": 4.48,
"learning_rate": 1.5783323361679865e-05,
"loss": 0.4651,
"step": 164
},
{
"epoch": 4.5,
"learning_rate": 1.573576436351046e-05,
"loss": 0.4657,
"step": 165
},
{
"epoch": 4.52,
"learning_rate": 1.568801123102852e-05,
"loss": 0.4654,
"step": 166
},
{
"epoch": 4.54,
"learning_rate": 1.5640065580500146e-05,
"loss": 0.4633,
"step": 167
},
{
"epoch": 4.55,
"learning_rate": 1.5591929034707468e-05,
"loss": 0.4628,
"step": 168
},
{
"epoch": 4.57,
"learning_rate": 1.5543603222893718e-05,
"loss": 0.4691,
"step": 169
},
{
"epoch": 4.59,
"learning_rate": 1.5495089780708062e-05,
"loss": 0.4644,
"step": 170
},
{
"epoch": 4.61,
"learning_rate": 1.5446390350150272e-05,
"loss": 0.4633,
"step": 171
},
{
"epoch": 4.63,
"learning_rate": 1.539750657951513e-05,
"loss": 0.4615,
"step": 172
},
{
"epoch": 4.63,
"eval_loss": 0.4630681276321411,
"eval_runtime": 23.8164,
"eval_samples_per_second": 8.398,
"eval_steps_per_second": 0.546,
"step": 172
},
{
"epoch": 5.01,
"learning_rate": 1.5348440123336647e-05,
"loss": 0.4604,
"step": 173
},
{
"epoch": 5.03,
"learning_rate": 1.529919264233205e-05,
"loss": 0.4624,
"step": 174
},
{
"epoch": 5.05,
"learning_rate": 1.5249765803345602e-05,
"loss": 0.4629,
"step": 175
},
{
"epoch": 5.07,
"learning_rate": 1.5200161279292154e-05,
"loss": 0.4616,
"step": 176
},
{
"epoch": 5.09,
"learning_rate": 1.5150380749100545e-05,
"loss": 0.4681,
"step": 177
},
{
"epoch": 5.1,
"learning_rate": 1.5100425897656754e-05,
"loss": 0.4653,
"step": 178
},
{
"epoch": 5.12,
"learning_rate": 1.5050298415746903e-05,
"loss": 0.459,
"step": 179
},
{
"epoch": 5.14,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.4589,
"step": 180
},
{
"epoch": 5.16,
"learning_rate": 1.4949532352830543e-05,
"loss": 0.4627,
"step": 181
},
{
"epoch": 5.18,
"learning_rate": 1.4898897182380872e-05,
"loss": 0.4579,
"step": 182
},
{
"epoch": 5.2,
"learning_rate": 1.4848096202463373e-05,
"loss": 0.4612,
"step": 183
},
{
"epoch": 5.21,
"learning_rate": 1.4797131132502464e-05,
"loss": 0.4598,
"step": 184
},
{
"epoch": 5.23,
"learning_rate": 1.4746003697476406e-05,
"loss": 0.4615,
"step": 185
},
{
"epoch": 5.25,
"learning_rate": 1.469471562785891e-05,
"loss": 0.4571,
"step": 186
},
{
"epoch": 5.27,
"learning_rate": 1.4643268659560571e-05,
"loss": 0.4589,
"step": 187
},
{
"epoch": 5.29,
"learning_rate": 1.4591664533870118e-05,
"loss": 0.4608,
"step": 188
},
{
"epoch": 5.31,
"learning_rate": 1.4539904997395468e-05,
"loss": 0.4606,
"step": 189
},
{
"epoch": 5.32,
"learning_rate": 1.4487991802004625e-05,
"loss": 0.4607,
"step": 190
},
{
"epoch": 5.34,
"learning_rate": 1.4435926704766364e-05,
"loss": 0.4605,
"step": 191
},
{
"epoch": 5.36,
"learning_rate": 1.4383711467890776e-05,
"loss": 0.4598,
"step": 192
},
{
"epoch": 5.38,
"learning_rate": 1.4331347858669631e-05,
"loss": 0.4588,
"step": 193
},
{
"epoch": 5.4,
"learning_rate": 1.4278837649416543e-05,
"loss": 0.4575,
"step": 194
},
{
"epoch": 5.42,
"learning_rate": 1.4226182617406996e-05,
"loss": 0.46,
"step": 195
},
{
"epoch": 5.43,
"learning_rate": 1.417338454481818e-05,
"loss": 0.4605,
"step": 196
},
{
"epoch": 5.45,
"learning_rate": 1.4120445218668687e-05,
"loss": 0.4606,
"step": 197
},
{
"epoch": 5.47,
"learning_rate": 1.4067366430758004e-05,
"loss": 0.4584,
"step": 198
},
{
"epoch": 5.49,
"learning_rate": 1.4014149977605893e-05,
"loss": 0.4623,
"step": 199
},
{
"epoch": 5.51,
"learning_rate": 1.396079766039157e-05,
"loss": 0.4586,
"step": 200
},
{
"epoch": 5.53,
"learning_rate": 1.3907311284892737e-05,
"loss": 0.457,
"step": 201
},
{
"epoch": 5.54,
"learning_rate": 1.3853692661424485e-05,
"loss": 0.4577,
"step": 202
},
{
"epoch": 5.56,
"learning_rate": 1.3799943604777993e-05,
"loss": 0.4604,
"step": 203
},
{
"epoch": 5.58,
"learning_rate": 1.3746065934159123e-05,
"loss": 0.4603,
"step": 204
},
{
"epoch": 5.6,
"learning_rate": 1.3692061473126845e-05,
"loss": 0.46,
"step": 205
},
{
"epoch": 5.62,
"learning_rate": 1.3637932049531517e-05,
"loss": 0.4584,
"step": 206
},
{
"epoch": 5.62,
"eval_loss": 0.4574292004108429,
"eval_runtime": 23.8087,
"eval_samples_per_second": 8.4,
"eval_steps_per_second": 0.546,
"step": 206
},
{
"epoch": 6.0,
"learning_rate": 1.3583679495453e-05,
"loss": 0.4533,
"step": 207
},
{
"epoch": 6.02,
"learning_rate": 1.3529305647138689e-05,
"loss": 0.456,
"step": 208
},
{
"epoch": 6.04,
"learning_rate": 1.3474812344941315e-05,
"loss": 0.4592,
"step": 209
},
{
"epoch": 6.06,
"learning_rate": 1.342020143325669e-05,
"loss": 0.4559,
"step": 210
},
{
"epoch": 6.08,
"learning_rate": 1.3365474760461265e-05,
"loss": 0.4606,
"step": 211
},
{
"epoch": 6.1,
"learning_rate": 1.3310634178849583e-05,
"loss": 0.4607,
"step": 212
},
{
"epoch": 6.11,
"learning_rate": 1.3255681544571568e-05,
"loss": 0.4557,
"step": 213
},
{
"epoch": 6.13,
"learning_rate": 1.3200618717569716e-05,
"loss": 0.4549,
"step": 214
},
{
"epoch": 6.15,
"learning_rate": 1.3145447561516138e-05,
"loss": 0.4555,
"step": 215
},
{
"epoch": 6.17,
"learning_rate": 1.3090169943749475e-05,
"loss": 0.4557,
"step": 216
},
{
"epoch": 6.19,
"learning_rate": 1.3034787735211708e-05,
"loss": 0.4536,
"step": 217
},
{
"epoch": 6.21,
"learning_rate": 1.297930281038482e-05,
"loss": 0.459,
"step": 218
},
{
"epoch": 6.22,
"learning_rate": 1.2923717047227368e-05,
"loss": 0.4543,
"step": 219
},
{
"epoch": 6.24,
"learning_rate": 1.2868032327110904e-05,
"loss": 0.4528,
"step": 220
},
{
"epoch": 6.26,
"learning_rate": 1.2812250534756307e-05,
"loss": 0.4574,
"step": 221
},
{
"epoch": 6.28,
"learning_rate": 1.2756373558169992e-05,
"loss": 0.4533,
"step": 222
},
{
"epoch": 6.3,
"learning_rate": 1.270040328858001e-05,
"loss": 0.4558,
"step": 223
},
{
"epoch": 6.32,
"learning_rate": 1.2644341620372025e-05,
"loss": 0.4584,
"step": 224
},
{
"epoch": 6.33,
"learning_rate": 1.2588190451025209e-05,
"loss": 0.4547,
"step": 225
},
{
"epoch": 6.35,
"learning_rate": 1.253195168104802e-05,
"loss": 0.4568,
"step": 226
},
{
"epoch": 6.37,
"learning_rate": 1.2475627213913861e-05,
"loss": 0.4547,
"step": 227
},
{
"epoch": 6.39,
"learning_rate": 1.2419218955996677e-05,
"loss": 0.4523,
"step": 228
},
{
"epoch": 6.41,
"learning_rate": 1.2362728816506418e-05,
"loss": 0.4556,
"step": 229
},
{
"epoch": 6.43,
"learning_rate": 1.2306158707424402e-05,
"loss": 0.4561,
"step": 230
},
{
"epoch": 6.44,
"learning_rate": 1.2249510543438652e-05,
"loss": 0.4548,
"step": 231
},
{
"epoch": 6.46,
"learning_rate": 1.2192786241879033e-05,
"loss": 0.4569,
"step": 232
},
{
"epoch": 6.48,
"learning_rate": 1.2135987722652403e-05,
"loss": 0.4561,
"step": 233
},
{
"epoch": 6.5,
"learning_rate": 1.2079116908177592e-05,
"loss": 0.4535,
"step": 234
},
{
"epoch": 6.52,
"learning_rate": 1.2022175723320382e-05,
"loss": 0.4538,
"step": 235
},
{
"epoch": 6.54,
"learning_rate": 1.1965166095328302e-05,
"loss": 0.454,
"step": 236
},
{
"epoch": 6.55,
"learning_rate": 1.190808995376545e-05,
"loss": 0.4555,
"step": 237
},
{
"epoch": 6.57,
"learning_rate": 1.1850949230447146e-05,
"loss": 0.4567,
"step": 238
},
{
"epoch": 6.59,
"learning_rate": 1.1793745859374575e-05,
"loss": 0.4571,
"step": 239
},
{
"epoch": 6.61,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.4535,
"step": 240
},
{
"epoch": 6.63,
"learning_rate": 1.1679158920507773e-05,
"loss": 0.4524,
"step": 241
},
{
"epoch": 6.63,
"eval_loss": 0.45291438698768616,
"eval_runtime": 23.8049,
"eval_samples_per_second": 8.402,
"eval_steps_per_second": 0.546,
"step": 241
},
{
"epoch": 7.01,
"learning_rate": 1.1621779231055677e-05,
"loss": 0.4501,
"step": 242
},
{
"epoch": 7.03,
"learning_rate": 1.156434465040231e-05,
"loss": 0.4529,
"step": 243
},
{
"epoch": 7.05,
"learning_rate": 1.1506857122494832e-05,
"loss": 0.4559,
"step": 244
},
{
"epoch": 7.07,
"learning_rate": 1.1449318593072468e-05,
"loss": 0.4523,
"step": 245
},
{
"epoch": 7.09,
"learning_rate": 1.1391731009600655e-05,
"loss": 0.4572,
"step": 246
},
{
"epoch": 7.11,
"learning_rate": 1.1334096321205129e-05,
"loss": 0.4543,
"step": 247
},
{
"epoch": 7.12,
"learning_rate": 1.127641647860595e-05,
"loss": 0.452,
"step": 248
},
{
"epoch": 7.14,
"learning_rate": 1.1218693434051475e-05,
"loss": 0.4529,
"step": 249
},
{
"epoch": 7.16,
"learning_rate": 1.1160929141252303e-05,
"loss": 0.4528,
"step": 250
},
{
"epoch": 7.18,
"learning_rate": 1.110312555531512e-05,
"loss": 0.4505,
"step": 251
},
{
"epoch": 7.2,
"learning_rate": 1.1045284632676535e-05,
"loss": 0.4491,
"step": 252
},
{
"epoch": 7.22,
"learning_rate": 1.0987408331036879e-05,
"loss": 0.4544,
"step": 253
},
{
"epoch": 7.23,
"learning_rate": 1.0929498609293925e-05,
"loss": 0.4509,
"step": 254
},
{
"epoch": 7.25,
"learning_rate": 1.0871557427476585e-05,
"loss": 0.4517,
"step": 255
},
{
"epoch": 7.27,
"learning_rate": 1.0813586746678584e-05,
"loss": 0.4505,
"step": 256
},
{
"epoch": 7.29,
"learning_rate": 1.0755588528992082e-05,
"loss": 0.4508,
"step": 257
},
{
"epoch": 7.31,
"learning_rate": 1.0697564737441254e-05,
"loss": 0.4537,
"step": 258
},
{
"epoch": 7.33,
"learning_rate": 1.0639517335915857e-05,
"loss": 0.4543,
"step": 259
},
{
"epoch": 7.34,
"learning_rate": 1.0581448289104759e-05,
"loss": 0.4532,
"step": 260
},
{
"epoch": 7.36,
"learning_rate": 1.0523359562429441e-05,
"loss": 0.4532,
"step": 261
},
{
"epoch": 7.38,
"learning_rate": 1.046525312197747e-05,
"loss": 0.4507,
"step": 262
},
{
"epoch": 7.4,
"learning_rate": 1.040713093443596e-05,
"loss": 0.4494,
"step": 263
},
{
"epoch": 7.42,
"learning_rate": 1.0348994967025012e-05,
"loss": 0.4531,
"step": 264
},
{
"epoch": 7.44,
"learning_rate": 1.0290847187431115e-05,
"loss": 0.4525,
"step": 265
},
{
"epoch": 7.45,
"learning_rate": 1.0232689563740563e-05,
"loss": 0.452,
"step": 266
},
{
"epoch": 7.47,
"learning_rate": 1.0174524064372837e-05,
"loss": 0.4527,
"step": 267
},
{
"epoch": 7.49,
"learning_rate": 1.0116352658013973e-05,
"loss": 0.4532,
"step": 268
},
{
"epoch": 7.51,
"learning_rate": 1.005817731354994e-05,
"loss": 0.4507,
"step": 269
},
{
"epoch": 7.53,
"learning_rate": 1e-05,
"loss": 0.4504,
"step": 270
},
{
"epoch": 7.55,
"learning_rate": 9.941822686450061e-06,
"loss": 0.4536,
"step": 271
},
{
"epoch": 7.56,
"learning_rate": 9.883647341986032e-06,
"loss": 0.4515,
"step": 272
},
{
"epoch": 7.58,
"learning_rate": 9.825475935627165e-06,
"loss": 0.4537,
"step": 273
},
{
"epoch": 7.6,
"learning_rate": 9.767310436259438e-06,
"loss": 0.4527,
"step": 274
},
{
"epoch": 7.62,
"learning_rate": 9.709152812568886e-06,
"loss": 0.4507,
"step": 275
},
{
"epoch": 7.62,
"eval_loss": 0.4502379596233368,
"eval_runtime": 23.8128,
"eval_samples_per_second": 8.399,
"eval_steps_per_second": 0.546,
"step": 275
},
{
"epoch": 8.0,
"learning_rate": 9.651005032974994e-06,
"loss": 0.4474,
"step": 276
},
{
"epoch": 8.02,
"learning_rate": 9.592869065564043e-06,
"loss": 0.4489,
"step": 277
},
{
"epoch": 8.04,
"learning_rate": 9.534746878022533e-06,
"loss": 0.4527,
"step": 278
},
{
"epoch": 8.06,
"learning_rate": 9.476640437570562e-06,
"loss": 0.4495,
"step": 279
},
{
"epoch": 8.08,
"learning_rate": 9.418551710895243e-06,
"loss": 0.4567,
"step": 280
},
{
"epoch": 8.1,
"learning_rate": 9.360482664084144e-06,
"loss": 0.4523,
"step": 281
},
{
"epoch": 8.11,
"learning_rate": 9.302435262558748e-06,
"loss": 0.4485,
"step": 282
},
{
"epoch": 8.13,
"learning_rate": 9.244411471007923e-06,
"loss": 0.4492,
"step": 283
},
{
"epoch": 8.15,
"learning_rate": 9.18641325332142e-06,
"loss": 0.4508,
"step": 284
},
{
"epoch": 8.17,
"learning_rate": 9.128442572523418e-06,
"loss": 0.4486,
"step": 285
},
{
"epoch": 8.19,
"learning_rate": 9.07050139070608e-06,
"loss": 0.4495,
"step": 286
},
{
"epoch": 8.21,
"learning_rate": 9.012591668963123e-06,
"loss": 0.4521,
"step": 287
},
{
"epoch": 8.23,
"learning_rate": 8.954715367323468e-06,
"loss": 0.4472,
"step": 288
},
{
"epoch": 8.24,
"learning_rate": 8.896874444684882e-06,
"loss": 0.4494,
"step": 289
},
{
"epoch": 8.26,
"learning_rate": 8.839070858747697e-06,
"loss": 0.4482,
"step": 290
},
{
"epoch": 8.28,
"learning_rate": 8.781306565948528e-06,
"loss": 0.4488,
"step": 291
},
{
"epoch": 8.3,
"learning_rate": 8.723583521394054e-06,
"loss": 0.4527,
"step": 292
},
{
"epoch": 8.32,
"learning_rate": 8.665903678794873e-06,
"loss": 0.4499,
"step": 293
},
{
"epoch": 8.34,
"learning_rate": 8.60826899039935e-06,
"loss": 0.4511,
"step": 294
},
{
"epoch": 8.35,
"learning_rate": 8.550681406927534e-06,
"loss": 0.4528,
"step": 295
},
{
"epoch": 8.37,
"learning_rate": 8.49314287750517e-06,
"loss": 0.4465,
"step": 296
},
{
"epoch": 8.39,
"learning_rate": 8.43565534959769e-06,
"loss": 0.4467,
"step": 297
},
{
"epoch": 8.41,
"learning_rate": 8.378220768944328e-06,
"loss": 0.4519,
"step": 298
},
{
"epoch": 8.43,
"learning_rate": 8.32084107949223e-06,
"loss": 0.4517,
"step": 299
},
{
"epoch": 8.45,
"learning_rate": 8.263518223330698e-06,
"loss": 0.4487,
"step": 300
},
{
"epoch": 8.46,
"learning_rate": 8.206254140625425e-06,
"loss": 0.4514,
"step": 301
},
{
"epoch": 8.48,
"learning_rate": 8.149050769552856e-06,
"loss": 0.4524,
"step": 302
},
{
"epoch": 8.5,
"learning_rate": 8.091910046234552e-06,
"loss": 0.4493,
"step": 303
},
{
"epoch": 8.52,
"learning_rate": 8.034833904671698e-06,
"loss": 0.4495,
"step": 304
},
{
"epoch": 8.54,
"learning_rate": 7.977824276679623e-06,
"loss": 0.4501,
"step": 305
},
{
"epoch": 8.56,
"learning_rate": 7.92088309182241e-06,
"loss": 0.4482,
"step": 306
},
{
"epoch": 8.57,
"learning_rate": 7.864012277347602e-06,
"loss": 0.4539,
"step": 307
},
{
"epoch": 8.59,
"learning_rate": 7.807213758120965e-06,
"loss": 0.449,
"step": 308
},
{
"epoch": 8.61,
"learning_rate": 7.750489456561351e-06,
"loss": 0.4486,
"step": 309
},
{
"epoch": 8.63,
"learning_rate": 7.6938412925756e-06,
"loss": 0.4478,
"step": 310
},
{
"epoch": 8.63,
"eval_loss": 0.4479629397392273,
"eval_runtime": 23.8304,
"eval_samples_per_second": 8.393,
"eval_steps_per_second": 0.546,
"step": 310
},
{
"epoch": 9.01,
"learning_rate": 7.637271183493587e-06,
"loss": 0.4482,
"step": 311
},
{
"epoch": 9.03,
"learning_rate": 7.580781044003324e-06,
"loss": 0.4462,
"step": 312
},
{
"epoch": 9.05,
"learning_rate": 7.524372786086143e-06,
"loss": 0.4488,
"step": 313
},
{
"epoch": 9.07,
"learning_rate": 7.468048318951983e-06,
"loss": 0.4521,
"step": 314
},
{
"epoch": 9.09,
"learning_rate": 7.411809548974792e-06,
"loss": 0.4528,
"step": 315
},
{
"epoch": 9.11,
"learning_rate": 7.355658379627981e-06,
"loss": 0.4497,
"step": 316
},
{
"epoch": 9.12,
"learning_rate": 7.299596711419994e-06,
"loss": 0.447,
"step": 317
},
{
"epoch": 9.14,
"learning_rate": 7.243626441830009e-06,
"loss": 0.4488,
"step": 318
},
{
"epoch": 9.16,
"learning_rate": 7.187749465243694e-06,
"loss": 0.4473,
"step": 319
},
{
"epoch": 9.18,
"learning_rate": 7.131967672889101e-06,
"loss": 0.4494,
"step": 320
},
{
"epoch": 9.2,
"learning_rate": 7.076282952772634e-06,
"loss": 0.4461,
"step": 321
},
{
"epoch": 9.22,
"learning_rate": 7.02069718961518e-06,
"loss": 0.4505,
"step": 322
},
{
"epoch": 9.23,
"learning_rate": 6.9652122647882966e-06,
"loss": 0.4476,
"step": 323
},
{
"epoch": 9.25,
"learning_rate": 6.909830056250527e-06,
"loss": 0.445,
"step": 324
},
{
"epoch": 9.27,
"learning_rate": 6.854552438483866e-06,
"loss": 0.4494,
"step": 325
},
{
"epoch": 9.29,
"learning_rate": 6.799381282430284e-06,
"loss": 0.4464,
"step": 326
},
{
"epoch": 9.31,
"learning_rate": 6.744318455428436e-06,
"loss": 0.4503,
"step": 327
},
{
"epoch": 9.33,
"learning_rate": 6.689365821150421e-06,
"loss": 0.4503,
"step": 328
},
{
"epoch": 9.35,
"learning_rate": 6.634525239538736e-06,
"loss": 0.4485,
"step": 329
},
{
"epoch": 9.36,
"learning_rate": 6.579798566743314e-06,
"loss": 0.4492,
"step": 330
},
{
"epoch": 9.38,
"learning_rate": 6.525187655058687e-06,
"loss": 0.4462,
"step": 331
},
{
"epoch": 9.4,
"learning_rate": 6.4706943528613135e-06,
"loss": 0.4499,
"step": 332
},
{
"epoch": 9.42,
"learning_rate": 6.4163205045469975e-06,
"loss": 0.4478,
"step": 333
},
{
"epoch": 9.44,
"learning_rate": 6.362067950468489e-06,
"loss": 0.4491,
"step": 334
},
{
"epoch": 9.46,
"learning_rate": 6.3079385268731575e-06,
"loss": 0.4481,
"step": 335
},
{
"epoch": 9.47,
"learning_rate": 6.25393406584088e-06,
"loss": 0.4509,
"step": 336
},
{
"epoch": 9.49,
"learning_rate": 6.200056395222012e-06,
"loss": 0.4489,
"step": 337
},
{
"epoch": 9.51,
"learning_rate": 6.146307338575519e-06,
"loss": 0.4469,
"step": 338
},
{
"epoch": 9.53,
"learning_rate": 6.092688715107265e-06,
"loss": 0.4472,
"step": 339
},
{
"epoch": 9.55,
"learning_rate": 6.039202339608432e-06,
"loss": 0.4499,
"step": 340
},
{
"epoch": 9.57,
"learning_rate": 5.9858500223941066e-06,
"loss": 0.4483,
"step": 341
},
{
"epoch": 9.58,
"learning_rate": 5.932633569242e-06,
"loss": 0.4494,
"step": 342
},
{
"epoch": 9.6,
"learning_rate": 5.879554781331317e-06,
"loss": 0.4528,
"step": 343
},
{
"epoch": 9.62,
"learning_rate": 5.8266154551818225e-06,
"loss": 0.4467,
"step": 344
},
{
"epoch": 9.62,
"eval_loss": 0.4474964439868927,
"eval_runtime": 23.8091,
"eval_samples_per_second": 8.4,
"eval_steps_per_second": 0.546,
"step": 344
},
{
"epoch": 9.62,
"step": 344,
"total_flos": 6.414434999835034e+16,
"train_loss": 0.4900048969443454,
"train_runtime": 108147.3514,
"train_samples_per_second": 2.577,
"train_steps_per_second": 0.005
}
],
"logging_steps": 1,
"max_steps": 540,
"num_train_epochs": 10,
"save_steps": 500,
"total_flos": 6.414434999835034e+16,
"trial_name": null,
"trial_params": null
}