Muennighoff's picture
Upload folder using huggingface_hub
4c13437
Raw
History Blame Contribute Delete
120 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.7980845969672785,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.263157894736843e-07,
"loss": 0.7396,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.0526315789473685e-06,
"loss": 0.6635,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.5789473684210526e-06,
"loss": 0.7036,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.105263157894737e-06,
"loss": 0.6616,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 2.631578947368421e-06,
"loss": 0.7004,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 3.157894736842105e-06,
"loss": 0.637,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 3.6842105263157896e-06,
"loss": 0.6202,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 4.210526315789474e-06,
"loss": 0.6074,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 4.736842105263158e-06,
"loss": 0.6147,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 5.263157894736842e-06,
"loss": 0.6723,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 5.789473684210527e-06,
"loss": 0.6024,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 6.31578947368421e-06,
"loss": 0.6143,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 6.842105263157896e-06,
"loss": 0.6261,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 7.368421052631579e-06,
"loss": 0.6334,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 7.894736842105265e-06,
"loss": 0.6041,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 8.421052631578948e-06,
"loss": 0.6071,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 8.947368421052632e-06,
"loss": 0.6264,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 9.473684210526315e-06,
"loss": 0.5899,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 0.628,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 1.0526315789473684e-05,
"loss": 0.6481,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 1.105263157894737e-05,
"loss": 0.5854,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 1.1578947368421053e-05,
"loss": 0.5735,
"step": 22
},
{
"epoch": 0.02,
"learning_rate": 1.2105263157894737e-05,
"loss": 0.6635,
"step": 23
},
{
"epoch": 0.02,
"learning_rate": 1.263157894736842e-05,
"loss": 0.5895,
"step": 24
},
{
"epoch": 0.02,
"learning_rate": 1.3157894736842108e-05,
"loss": 0.6014,
"step": 25
},
{
"epoch": 0.02,
"learning_rate": 1.3684210526315791e-05,
"loss": 0.623,
"step": 26
},
{
"epoch": 0.02,
"learning_rate": 1.4210526315789475e-05,
"loss": 0.5791,
"step": 27
},
{
"epoch": 0.02,
"learning_rate": 1.4736842105263159e-05,
"loss": 0.6215,
"step": 28
},
{
"epoch": 0.02,
"learning_rate": 1.5263157894736846e-05,
"loss": 0.6359,
"step": 29
},
{
"epoch": 0.02,
"learning_rate": 1.578947368421053e-05,
"loss": 0.6282,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 1.6315789473684213e-05,
"loss": 0.644,
"step": 31
},
{
"epoch": 0.03,
"learning_rate": 1.6842105263157896e-05,
"loss": 0.6252,
"step": 32
},
{
"epoch": 0.03,
"learning_rate": 1.736842105263158e-05,
"loss": 0.6518,
"step": 33
},
{
"epoch": 0.03,
"learning_rate": 1.7894736842105264e-05,
"loss": 0.6346,
"step": 34
},
{
"epoch": 0.03,
"learning_rate": 1.8421052631578947e-05,
"loss": 0.6537,
"step": 35
},
{
"epoch": 0.03,
"learning_rate": 1.894736842105263e-05,
"loss": 0.5812,
"step": 36
},
{
"epoch": 0.03,
"learning_rate": 1.9473684210526318e-05,
"loss": 0.6329,
"step": 37
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 0.6777,
"step": 38
},
{
"epoch": 0.03,
"learning_rate": 1.9983498349834986e-05,
"loss": 0.6258,
"step": 39
},
{
"epoch": 0.03,
"learning_rate": 1.996699669966997e-05,
"loss": 0.6399,
"step": 40
},
{
"epoch": 0.03,
"learning_rate": 1.9950495049504954e-05,
"loss": 0.6712,
"step": 41
},
{
"epoch": 0.03,
"learning_rate": 1.9933993399339934e-05,
"loss": 0.6586,
"step": 42
},
{
"epoch": 0.03,
"learning_rate": 1.9917491749174918e-05,
"loss": 0.6319,
"step": 43
},
{
"epoch": 0.04,
"learning_rate": 1.9900990099009902e-05,
"loss": 0.6588,
"step": 44
},
{
"epoch": 0.04,
"learning_rate": 1.9884488448844886e-05,
"loss": 0.6542,
"step": 45
},
{
"epoch": 0.04,
"learning_rate": 1.986798679867987e-05,
"loss": 0.6493,
"step": 46
},
{
"epoch": 0.04,
"learning_rate": 1.9851485148514854e-05,
"loss": 0.624,
"step": 47
},
{
"epoch": 0.04,
"learning_rate": 1.9834983498349835e-05,
"loss": 0.6032,
"step": 48
},
{
"epoch": 0.04,
"learning_rate": 1.9818481848184822e-05,
"loss": 0.6462,
"step": 49
},
{
"epoch": 0.04,
"learning_rate": 1.9801980198019803e-05,
"loss": 0.6265,
"step": 50
},
{
"epoch": 0.04,
"learning_rate": 1.9785478547854787e-05,
"loss": 0.667,
"step": 51
},
{
"epoch": 0.04,
"learning_rate": 1.976897689768977e-05,
"loss": 0.7015,
"step": 52
},
{
"epoch": 0.04,
"learning_rate": 1.9752475247524755e-05,
"loss": 0.667,
"step": 53
},
{
"epoch": 0.04,
"learning_rate": 1.9735973597359735e-05,
"loss": 0.6689,
"step": 54
},
{
"epoch": 0.04,
"learning_rate": 1.9719471947194723e-05,
"loss": 0.6587,
"step": 55
},
{
"epoch": 0.04,
"learning_rate": 1.9702970297029703e-05,
"loss": 0.6549,
"step": 56
},
{
"epoch": 0.05,
"learning_rate": 1.9686468646864687e-05,
"loss": 0.697,
"step": 57
},
{
"epoch": 0.05,
"learning_rate": 1.966996699669967e-05,
"loss": 0.6115,
"step": 58
},
{
"epoch": 0.05,
"learning_rate": 1.9653465346534655e-05,
"loss": 0.6558,
"step": 59
},
{
"epoch": 0.05,
"learning_rate": 1.963696369636964e-05,
"loss": 0.6415,
"step": 60
},
{
"epoch": 0.05,
"learning_rate": 1.9620462046204623e-05,
"loss": 0.6442,
"step": 61
},
{
"epoch": 0.05,
"learning_rate": 1.9603960396039604e-05,
"loss": 0.62,
"step": 62
},
{
"epoch": 0.05,
"learning_rate": 1.9587458745874588e-05,
"loss": 0.6786,
"step": 63
},
{
"epoch": 0.05,
"learning_rate": 1.957095709570957e-05,
"loss": 0.6905,
"step": 64
},
{
"epoch": 0.05,
"learning_rate": 1.9554455445544556e-05,
"loss": 0.6507,
"step": 65
},
{
"epoch": 0.05,
"learning_rate": 1.953795379537954e-05,
"loss": 0.6649,
"step": 66
},
{
"epoch": 0.05,
"learning_rate": 1.9521452145214524e-05,
"loss": 0.6098,
"step": 67
},
{
"epoch": 0.05,
"learning_rate": 1.9504950495049508e-05,
"loss": 0.5978,
"step": 68
},
{
"epoch": 0.06,
"learning_rate": 1.948844884488449e-05,
"loss": 0.6344,
"step": 69
},
{
"epoch": 0.06,
"learning_rate": 1.9471947194719475e-05,
"loss": 0.6606,
"step": 70
},
{
"epoch": 0.06,
"learning_rate": 1.9455445544554456e-05,
"loss": 0.6793,
"step": 71
},
{
"epoch": 0.06,
"learning_rate": 1.943894389438944e-05,
"loss": 0.6635,
"step": 72
},
{
"epoch": 0.06,
"learning_rate": 1.9422442244224424e-05,
"loss": 0.6407,
"step": 73
},
{
"epoch": 0.06,
"learning_rate": 1.9405940594059408e-05,
"loss": 0.6476,
"step": 74
},
{
"epoch": 0.06,
"learning_rate": 1.9389438943894392e-05,
"loss": 0.6434,
"step": 75
},
{
"epoch": 0.06,
"learning_rate": 1.9372937293729376e-05,
"loss": 0.6561,
"step": 76
},
{
"epoch": 0.06,
"learning_rate": 1.9356435643564357e-05,
"loss": 0.6489,
"step": 77
},
{
"epoch": 0.06,
"learning_rate": 1.9339933993399344e-05,
"loss": 0.6775,
"step": 78
},
{
"epoch": 0.06,
"learning_rate": 1.9323432343234325e-05,
"loss": 0.63,
"step": 79
},
{
"epoch": 0.06,
"learning_rate": 1.930693069306931e-05,
"loss": 0.6778,
"step": 80
},
{
"epoch": 0.06,
"learning_rate": 1.9290429042904292e-05,
"loss": 0.6809,
"step": 81
},
{
"epoch": 0.07,
"learning_rate": 1.9273927392739276e-05,
"loss": 0.6401,
"step": 82
},
{
"epoch": 0.07,
"learning_rate": 1.9257425742574257e-05,
"loss": 0.6388,
"step": 83
},
{
"epoch": 0.07,
"learning_rate": 1.9240924092409244e-05,
"loss": 0.6422,
"step": 84
},
{
"epoch": 0.07,
"learning_rate": 1.9224422442244225e-05,
"loss": 0.5752,
"step": 85
},
{
"epoch": 0.07,
"learning_rate": 1.920792079207921e-05,
"loss": 0.6527,
"step": 86
},
{
"epoch": 0.07,
"learning_rate": 1.9191419141914193e-05,
"loss": 0.683,
"step": 87
},
{
"epoch": 0.07,
"learning_rate": 1.9174917491749177e-05,
"loss": 0.6494,
"step": 88
},
{
"epoch": 0.07,
"learning_rate": 1.9158415841584158e-05,
"loss": 0.6725,
"step": 89
},
{
"epoch": 0.07,
"learning_rate": 1.9141914191419145e-05,
"loss": 0.6538,
"step": 90
},
{
"epoch": 0.07,
"learning_rate": 1.9125412541254126e-05,
"loss": 0.6121,
"step": 91
},
{
"epoch": 0.07,
"learning_rate": 1.910891089108911e-05,
"loss": 0.6573,
"step": 92
},
{
"epoch": 0.07,
"learning_rate": 1.9092409240924093e-05,
"loss": 0.6869,
"step": 93
},
{
"epoch": 0.08,
"learning_rate": 1.9075907590759077e-05,
"loss": 0.6573,
"step": 94
},
{
"epoch": 0.08,
"learning_rate": 1.905940594059406e-05,
"loss": 0.6516,
"step": 95
},
{
"epoch": 0.08,
"learning_rate": 1.9042904290429045e-05,
"loss": 0.6857,
"step": 96
},
{
"epoch": 0.08,
"learning_rate": 1.902640264026403e-05,
"loss": 0.6865,
"step": 97
},
{
"epoch": 0.08,
"learning_rate": 1.900990099009901e-05,
"loss": 0.6181,
"step": 98
},
{
"epoch": 0.08,
"learning_rate": 1.8993399339933994e-05,
"loss": 0.6548,
"step": 99
},
{
"epoch": 0.08,
"learning_rate": 1.8976897689768978e-05,
"loss": 0.714,
"step": 100
},
{
"epoch": 0.08,
"learning_rate": 1.8960396039603962e-05,
"loss": 0.6515,
"step": 101
},
{
"epoch": 0.08,
"learning_rate": 1.8943894389438946e-05,
"loss": 0.6421,
"step": 102
},
{
"epoch": 0.08,
"learning_rate": 1.892739273927393e-05,
"loss": 0.6284,
"step": 103
},
{
"epoch": 0.08,
"learning_rate": 1.891089108910891e-05,
"loss": 0.7068,
"step": 104
},
{
"epoch": 0.08,
"learning_rate": 1.8894389438943898e-05,
"loss": 0.7048,
"step": 105
},
{
"epoch": 0.08,
"learning_rate": 1.887788778877888e-05,
"loss": 0.6819,
"step": 106
},
{
"epoch": 0.09,
"learning_rate": 1.8861386138613862e-05,
"loss": 0.6773,
"step": 107
},
{
"epoch": 0.09,
"learning_rate": 1.8844884488448846e-05,
"loss": 0.6911,
"step": 108
},
{
"epoch": 0.09,
"learning_rate": 1.882838283828383e-05,
"loss": 0.6353,
"step": 109
},
{
"epoch": 0.09,
"learning_rate": 1.881188118811881e-05,
"loss": 0.6425,
"step": 110
},
{
"epoch": 0.09,
"learning_rate": 1.87953795379538e-05,
"loss": 0.5878,
"step": 111
},
{
"epoch": 0.09,
"learning_rate": 1.877887788778878e-05,
"loss": 0.6712,
"step": 112
},
{
"epoch": 0.09,
"learning_rate": 1.8762376237623763e-05,
"loss": 0.6068,
"step": 113
},
{
"epoch": 0.09,
"learning_rate": 1.8745874587458747e-05,
"loss": 0.6573,
"step": 114
},
{
"epoch": 0.09,
"learning_rate": 1.872937293729373e-05,
"loss": 0.6677,
"step": 115
},
{
"epoch": 0.09,
"learning_rate": 1.8712871287128715e-05,
"loss": 0.6443,
"step": 116
},
{
"epoch": 0.09,
"learning_rate": 1.86963696369637e-05,
"loss": 0.6311,
"step": 117
},
{
"epoch": 0.09,
"learning_rate": 1.867986798679868e-05,
"loss": 0.7183,
"step": 118
},
{
"epoch": 0.09,
"learning_rate": 1.8663366336633667e-05,
"loss": 0.6484,
"step": 119
},
{
"epoch": 0.1,
"learning_rate": 1.8646864686468647e-05,
"loss": 0.6561,
"step": 120
},
{
"epoch": 0.1,
"learning_rate": 1.863036303630363e-05,
"loss": 0.6085,
"step": 121
},
{
"epoch": 0.1,
"learning_rate": 1.8613861386138615e-05,
"loss": 0.6587,
"step": 122
},
{
"epoch": 0.1,
"learning_rate": 1.85973597359736e-05,
"loss": 0.6274,
"step": 123
},
{
"epoch": 0.1,
"learning_rate": 1.8580858085808583e-05,
"loss": 0.6347,
"step": 124
},
{
"epoch": 0.1,
"learning_rate": 1.8564356435643567e-05,
"loss": 0.6464,
"step": 125
},
{
"epoch": 0.1,
"learning_rate": 1.8547854785478548e-05,
"loss": 0.636,
"step": 126
},
{
"epoch": 0.1,
"learning_rate": 1.8531353135313532e-05,
"loss": 0.6038,
"step": 127
},
{
"epoch": 0.1,
"learning_rate": 1.8514851485148516e-05,
"loss": 0.6457,
"step": 128
},
{
"epoch": 0.1,
"learning_rate": 1.84983498349835e-05,
"loss": 0.6406,
"step": 129
},
{
"epoch": 0.1,
"learning_rate": 1.8481848184818484e-05,
"loss": 0.6365,
"step": 130
},
{
"epoch": 0.1,
"learning_rate": 1.8465346534653468e-05,
"loss": 0.628,
"step": 131
},
{
"epoch": 0.11,
"learning_rate": 1.8448844884488452e-05,
"loss": 0.6738,
"step": 132
},
{
"epoch": 0.11,
"learning_rate": 1.8432343234323432e-05,
"loss": 0.6525,
"step": 133
},
{
"epoch": 0.11,
"learning_rate": 1.841584158415842e-05,
"loss": 0.635,
"step": 134
},
{
"epoch": 0.11,
"learning_rate": 1.83993399339934e-05,
"loss": 0.6527,
"step": 135
},
{
"epoch": 0.11,
"learning_rate": 1.8382838283828384e-05,
"loss": 0.6939,
"step": 136
},
{
"epoch": 0.11,
"learning_rate": 1.8366336633663368e-05,
"loss": 0.6522,
"step": 137
},
{
"epoch": 0.11,
"learning_rate": 1.8349834983498352e-05,
"loss": 0.6485,
"step": 138
},
{
"epoch": 0.11,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.6562,
"step": 139
},
{
"epoch": 0.11,
"learning_rate": 1.831683168316832e-05,
"loss": 0.626,
"step": 140
},
{
"epoch": 0.11,
"learning_rate": 1.83003300330033e-05,
"loss": 0.6433,
"step": 141
},
{
"epoch": 0.11,
"learning_rate": 1.8283828382838285e-05,
"loss": 0.6408,
"step": 142
},
{
"epoch": 0.11,
"learning_rate": 1.826732673267327e-05,
"loss": 0.57,
"step": 143
},
{
"epoch": 0.11,
"learning_rate": 1.8250825082508253e-05,
"loss": 0.6462,
"step": 144
},
{
"epoch": 0.12,
"learning_rate": 1.8234323432343233e-05,
"loss": 0.5984,
"step": 145
},
{
"epoch": 0.12,
"learning_rate": 1.821782178217822e-05,
"loss": 0.6415,
"step": 146
},
{
"epoch": 0.12,
"learning_rate": 1.82013201320132e-05,
"loss": 0.6493,
"step": 147
},
{
"epoch": 0.12,
"learning_rate": 1.8184818481848185e-05,
"loss": 0.6246,
"step": 148
},
{
"epoch": 0.12,
"learning_rate": 1.816831683168317e-05,
"loss": 0.6273,
"step": 149
},
{
"epoch": 0.12,
"learning_rate": 1.8151815181518153e-05,
"loss": 0.6823,
"step": 150
},
{
"epoch": 0.12,
"learning_rate": 1.8135313531353137e-05,
"loss": 0.6246,
"step": 151
},
{
"epoch": 0.12,
"learning_rate": 1.811881188118812e-05,
"loss": 0.6132,
"step": 152
},
{
"epoch": 0.12,
"learning_rate": 1.8102310231023105e-05,
"loss": 0.6466,
"step": 153
},
{
"epoch": 0.12,
"learning_rate": 1.8085808580858086e-05,
"loss": 0.6547,
"step": 154
},
{
"epoch": 0.12,
"learning_rate": 1.806930693069307e-05,
"loss": 0.6246,
"step": 155
},
{
"epoch": 0.12,
"learning_rate": 1.8052805280528054e-05,
"loss": 0.6227,
"step": 156
},
{
"epoch": 0.13,
"learning_rate": 1.8036303630363038e-05,
"loss": 0.5829,
"step": 157
},
{
"epoch": 0.13,
"learning_rate": 1.8019801980198022e-05,
"loss": 0.6334,
"step": 158
},
{
"epoch": 0.13,
"learning_rate": 1.8003300330033006e-05,
"loss": 0.6252,
"step": 159
},
{
"epoch": 0.13,
"learning_rate": 1.7986798679867986e-05,
"loss": 0.5979,
"step": 160
},
{
"epoch": 0.13,
"learning_rate": 1.7970297029702974e-05,
"loss": 0.6162,
"step": 161
},
{
"epoch": 0.13,
"learning_rate": 1.7953795379537954e-05,
"loss": 0.6287,
"step": 162
},
{
"epoch": 0.13,
"learning_rate": 1.7937293729372938e-05,
"loss": 0.6063,
"step": 163
},
{
"epoch": 0.13,
"learning_rate": 1.7920792079207922e-05,
"loss": 0.5693,
"step": 164
},
{
"epoch": 0.13,
"learning_rate": 1.7904290429042906e-05,
"loss": 0.6643,
"step": 165
},
{
"epoch": 0.13,
"learning_rate": 1.788778877887789e-05,
"loss": 0.6257,
"step": 166
},
{
"epoch": 0.13,
"learning_rate": 1.7871287128712874e-05,
"loss": 0.6113,
"step": 167
},
{
"epoch": 0.13,
"learning_rate": 1.7854785478547855e-05,
"loss": 0.6142,
"step": 168
},
{
"epoch": 0.13,
"learning_rate": 1.7838283828382842e-05,
"loss": 0.6252,
"step": 169
},
{
"epoch": 0.14,
"learning_rate": 1.7821782178217823e-05,
"loss": 0.6227,
"step": 170
},
{
"epoch": 0.14,
"learning_rate": 1.7805280528052807e-05,
"loss": 0.6171,
"step": 171
},
{
"epoch": 0.14,
"learning_rate": 1.778877887788779e-05,
"loss": 0.638,
"step": 172
},
{
"epoch": 0.14,
"learning_rate": 1.7772277227722775e-05,
"loss": 0.616,
"step": 173
},
{
"epoch": 0.14,
"learning_rate": 1.7755775577557755e-05,
"loss": 0.6266,
"step": 174
},
{
"epoch": 0.14,
"learning_rate": 1.7739273927392743e-05,
"loss": 0.5931,
"step": 175
},
{
"epoch": 0.14,
"learning_rate": 1.7722772277227723e-05,
"loss": 0.6347,
"step": 176
},
{
"epoch": 0.14,
"learning_rate": 1.7706270627062707e-05,
"loss": 0.669,
"step": 177
},
{
"epoch": 0.14,
"learning_rate": 1.768976897689769e-05,
"loss": 0.659,
"step": 178
},
{
"epoch": 0.14,
"learning_rate": 1.7673267326732675e-05,
"loss": 0.6111,
"step": 179
},
{
"epoch": 0.14,
"learning_rate": 1.765676567656766e-05,
"loss": 0.6475,
"step": 180
},
{
"epoch": 0.14,
"learning_rate": 1.7640264026402643e-05,
"loss": 0.6458,
"step": 181
},
{
"epoch": 0.15,
"learning_rate": 1.7623762376237624e-05,
"loss": 0.5915,
"step": 182
},
{
"epoch": 0.15,
"learning_rate": 1.7607260726072608e-05,
"loss": 0.6795,
"step": 183
},
{
"epoch": 0.15,
"learning_rate": 1.759075907590759e-05,
"loss": 0.6699,
"step": 184
},
{
"epoch": 0.15,
"learning_rate": 1.7574257425742576e-05,
"loss": 0.6135,
"step": 185
},
{
"epoch": 0.15,
"learning_rate": 1.755775577557756e-05,
"loss": 0.582,
"step": 186
},
{
"epoch": 0.15,
"learning_rate": 1.7541254125412544e-05,
"loss": 0.6012,
"step": 187
},
{
"epoch": 0.15,
"learning_rate": 1.7524752475247528e-05,
"loss": 0.6681,
"step": 188
},
{
"epoch": 0.15,
"learning_rate": 1.7508250825082508e-05,
"loss": 0.6592,
"step": 189
},
{
"epoch": 0.15,
"learning_rate": 1.7491749174917496e-05,
"loss": 0.5882,
"step": 190
},
{
"epoch": 0.15,
"learning_rate": 1.7475247524752476e-05,
"loss": 0.5977,
"step": 191
},
{
"epoch": 0.15,
"learning_rate": 1.745874587458746e-05,
"loss": 0.6002,
"step": 192
},
{
"epoch": 0.15,
"learning_rate": 1.7442244224422444e-05,
"loss": 0.6631,
"step": 193
},
{
"epoch": 0.15,
"learning_rate": 1.7425742574257428e-05,
"loss": 0.6665,
"step": 194
},
{
"epoch": 0.16,
"learning_rate": 1.740924092409241e-05,
"loss": 0.6041,
"step": 195
},
{
"epoch": 0.16,
"learning_rate": 1.7392739273927396e-05,
"loss": 0.6649,
"step": 196
},
{
"epoch": 0.16,
"learning_rate": 1.7376237623762377e-05,
"loss": 0.6451,
"step": 197
},
{
"epoch": 0.16,
"learning_rate": 1.735973597359736e-05,
"loss": 0.6347,
"step": 198
},
{
"epoch": 0.16,
"learning_rate": 1.7343234323432345e-05,
"loss": 0.652,
"step": 199
},
{
"epoch": 0.16,
"learning_rate": 1.732673267326733e-05,
"loss": 0.6621,
"step": 200
},
{
"epoch": 0.16,
"learning_rate": 1.731023102310231e-05,
"loss": 0.6536,
"step": 201
},
{
"epoch": 0.16,
"learning_rate": 1.7293729372937297e-05,
"loss": 0.6164,
"step": 202
},
{
"epoch": 0.16,
"learning_rate": 1.7277227722772277e-05,
"loss": 0.6775,
"step": 203
},
{
"epoch": 0.16,
"learning_rate": 1.726072607260726e-05,
"loss": 0.6434,
"step": 204
},
{
"epoch": 0.16,
"learning_rate": 1.7244224422442245e-05,
"loss": 0.6415,
"step": 205
},
{
"epoch": 0.16,
"learning_rate": 1.722772277227723e-05,
"loss": 0.6019,
"step": 206
},
{
"epoch": 0.17,
"learning_rate": 1.7211221122112213e-05,
"loss": 0.6241,
"step": 207
},
{
"epoch": 0.17,
"learning_rate": 1.7194719471947197e-05,
"loss": 0.6813,
"step": 208
},
{
"epoch": 0.17,
"learning_rate": 1.717821782178218e-05,
"loss": 0.6123,
"step": 209
},
{
"epoch": 0.17,
"learning_rate": 1.716171617161716e-05,
"loss": 0.6924,
"step": 210
},
{
"epoch": 0.17,
"learning_rate": 1.7145214521452146e-05,
"loss": 0.6142,
"step": 211
},
{
"epoch": 0.17,
"learning_rate": 1.712871287128713e-05,
"loss": 0.6105,
"step": 212
},
{
"epoch": 0.17,
"learning_rate": 1.7112211221122114e-05,
"loss": 0.6289,
"step": 213
},
{
"epoch": 0.17,
"learning_rate": 1.7095709570957098e-05,
"loss": 0.6449,
"step": 214
},
{
"epoch": 0.17,
"learning_rate": 1.707920792079208e-05,
"loss": 0.6199,
"step": 215
},
{
"epoch": 0.17,
"learning_rate": 1.7062706270627065e-05,
"loss": 0.6133,
"step": 216
},
{
"epoch": 0.17,
"learning_rate": 1.704620462046205e-05,
"loss": 0.6827,
"step": 217
},
{
"epoch": 0.17,
"learning_rate": 1.702970297029703e-05,
"loss": 0.6249,
"step": 218
},
{
"epoch": 0.17,
"learning_rate": 1.7013201320132014e-05,
"loss": 0.5773,
"step": 219
},
{
"epoch": 0.18,
"learning_rate": 1.6996699669966998e-05,
"loss": 0.611,
"step": 220
},
{
"epoch": 0.18,
"learning_rate": 1.6980198019801982e-05,
"loss": 0.6695,
"step": 221
},
{
"epoch": 0.18,
"learning_rate": 1.6963696369636966e-05,
"loss": 0.6275,
"step": 222
},
{
"epoch": 0.18,
"learning_rate": 1.694719471947195e-05,
"loss": 0.6499,
"step": 223
},
{
"epoch": 0.18,
"learning_rate": 1.693069306930693e-05,
"loss": 0.6483,
"step": 224
},
{
"epoch": 0.18,
"learning_rate": 1.6914191419141918e-05,
"loss": 0.6217,
"step": 225
},
{
"epoch": 0.18,
"learning_rate": 1.68976897689769e-05,
"loss": 0.6555,
"step": 226
},
{
"epoch": 0.18,
"learning_rate": 1.6881188118811882e-05,
"loss": 0.636,
"step": 227
},
{
"epoch": 0.18,
"learning_rate": 1.6864686468646866e-05,
"loss": 0.614,
"step": 228
},
{
"epoch": 0.18,
"learning_rate": 1.684818481848185e-05,
"loss": 0.6508,
"step": 229
},
{
"epoch": 0.18,
"learning_rate": 1.683168316831683e-05,
"loss": 0.5982,
"step": 230
},
{
"epoch": 0.18,
"learning_rate": 1.681518151815182e-05,
"loss": 0.6098,
"step": 231
},
{
"epoch": 0.19,
"learning_rate": 1.67986798679868e-05,
"loss": 0.6044,
"step": 232
},
{
"epoch": 0.19,
"learning_rate": 1.6782178217821783e-05,
"loss": 0.6185,
"step": 233
},
{
"epoch": 0.19,
"learning_rate": 1.6765676567656767e-05,
"loss": 0.6169,
"step": 234
},
{
"epoch": 0.19,
"learning_rate": 1.674917491749175e-05,
"loss": 0.6331,
"step": 235
},
{
"epoch": 0.19,
"learning_rate": 1.6732673267326735e-05,
"loss": 0.6002,
"step": 236
},
{
"epoch": 0.19,
"learning_rate": 1.671617161716172e-05,
"loss": 0.6199,
"step": 237
},
{
"epoch": 0.19,
"learning_rate": 1.66996699669967e-05,
"loss": 0.5983,
"step": 238
},
{
"epoch": 0.19,
"learning_rate": 1.6683168316831683e-05,
"loss": 0.6432,
"step": 239
},
{
"epoch": 0.19,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.603,
"step": 240
},
{
"epoch": 0.19,
"learning_rate": 1.665016501650165e-05,
"loss": 0.6689,
"step": 241
},
{
"epoch": 0.19,
"learning_rate": 1.6633663366336635e-05,
"loss": 0.5661,
"step": 242
},
{
"epoch": 0.19,
"learning_rate": 1.661716171617162e-05,
"loss": 0.6168,
"step": 243
},
{
"epoch": 0.19,
"learning_rate": 1.6600660066006603e-05,
"loss": 0.5778,
"step": 244
},
{
"epoch": 0.2,
"learning_rate": 1.6584158415841584e-05,
"loss": 0.569,
"step": 245
},
{
"epoch": 0.2,
"learning_rate": 1.656765676567657e-05,
"loss": 0.5578,
"step": 246
},
{
"epoch": 0.2,
"learning_rate": 1.6551155115511552e-05,
"loss": 0.5997,
"step": 247
},
{
"epoch": 0.2,
"learning_rate": 1.6534653465346536e-05,
"loss": 0.6453,
"step": 248
},
{
"epoch": 0.2,
"learning_rate": 1.651815181518152e-05,
"loss": 0.6069,
"step": 249
},
{
"epoch": 0.2,
"learning_rate": 1.6501650165016504e-05,
"loss": 0.6215,
"step": 250
},
{
"epoch": 0.2,
"learning_rate": 1.6485148514851484e-05,
"loss": 0.617,
"step": 251
},
{
"epoch": 0.2,
"learning_rate": 1.6468646864686472e-05,
"loss": 0.6192,
"step": 252
},
{
"epoch": 0.2,
"learning_rate": 1.6452145214521452e-05,
"loss": 0.6175,
"step": 253
},
{
"epoch": 0.2,
"learning_rate": 1.6435643564356436e-05,
"loss": 0.6468,
"step": 254
},
{
"epoch": 0.2,
"learning_rate": 1.641914191419142e-05,
"loss": 0.6445,
"step": 255
},
{
"epoch": 0.2,
"learning_rate": 1.6402640264026404e-05,
"loss": 0.6322,
"step": 256
},
{
"epoch": 0.21,
"learning_rate": 1.6386138613861385e-05,
"loss": 0.6014,
"step": 257
},
{
"epoch": 0.21,
"learning_rate": 1.6369636963696372e-05,
"loss": 0.6023,
"step": 258
},
{
"epoch": 0.21,
"learning_rate": 1.6353135313531353e-05,
"loss": 0.6608,
"step": 259
},
{
"epoch": 0.21,
"learning_rate": 1.6336633663366337e-05,
"loss": 0.6199,
"step": 260
},
{
"epoch": 0.21,
"learning_rate": 1.632013201320132e-05,
"loss": 0.6199,
"step": 261
},
{
"epoch": 0.21,
"learning_rate": 1.6303630363036305e-05,
"loss": 0.6059,
"step": 262
},
{
"epoch": 0.21,
"learning_rate": 1.628712871287129e-05,
"loss": 0.6056,
"step": 263
},
{
"epoch": 0.21,
"learning_rate": 1.6270627062706273e-05,
"loss": 0.6276,
"step": 264
},
{
"epoch": 0.21,
"learning_rate": 1.6254125412541253e-05,
"loss": 0.5902,
"step": 265
},
{
"epoch": 0.21,
"learning_rate": 1.623762376237624e-05,
"loss": 0.6265,
"step": 266
},
{
"epoch": 0.21,
"learning_rate": 1.622112211221122e-05,
"loss": 0.6065,
"step": 267
},
{
"epoch": 0.21,
"learning_rate": 1.6204620462046205e-05,
"loss": 0.6258,
"step": 268
},
{
"epoch": 0.21,
"learning_rate": 1.618811881188119e-05,
"loss": 0.585,
"step": 269
},
{
"epoch": 0.22,
"learning_rate": 1.6171617161716173e-05,
"loss": 0.5867,
"step": 270
},
{
"epoch": 0.22,
"learning_rate": 1.6155115511551157e-05,
"loss": 0.6345,
"step": 271
},
{
"epoch": 0.22,
"learning_rate": 1.613861386138614e-05,
"loss": 0.5722,
"step": 272
},
{
"epoch": 0.22,
"learning_rate": 1.6122112211221125e-05,
"loss": 0.6453,
"step": 273
},
{
"epoch": 0.22,
"learning_rate": 1.6105610561056106e-05,
"loss": 0.6093,
"step": 274
},
{
"epoch": 0.22,
"learning_rate": 1.608910891089109e-05,
"loss": 0.6353,
"step": 275
},
{
"epoch": 0.22,
"learning_rate": 1.6072607260726074e-05,
"loss": 0.6177,
"step": 276
},
{
"epoch": 0.22,
"learning_rate": 1.6056105610561058e-05,
"loss": 0.6442,
"step": 277
},
{
"epoch": 0.22,
"learning_rate": 1.6039603960396042e-05,
"loss": 0.6133,
"step": 278
},
{
"epoch": 0.22,
"learning_rate": 1.6023102310231026e-05,
"loss": 0.5901,
"step": 279
},
{
"epoch": 0.22,
"learning_rate": 1.6006600660066006e-05,
"loss": 0.5915,
"step": 280
},
{
"epoch": 0.22,
"learning_rate": 1.5990099009900994e-05,
"loss": 0.6012,
"step": 281
},
{
"epoch": 0.23,
"learning_rate": 1.5973597359735974e-05,
"loss": 0.5721,
"step": 282
},
{
"epoch": 0.23,
"learning_rate": 1.5957095709570958e-05,
"loss": 0.6112,
"step": 283
},
{
"epoch": 0.23,
"learning_rate": 1.5940594059405942e-05,
"loss": 0.6102,
"step": 284
},
{
"epoch": 0.23,
"learning_rate": 1.5924092409240926e-05,
"loss": 0.6079,
"step": 285
},
{
"epoch": 0.23,
"learning_rate": 1.5907590759075907e-05,
"loss": 0.6427,
"step": 286
},
{
"epoch": 0.23,
"learning_rate": 1.5891089108910894e-05,
"loss": 0.643,
"step": 287
},
{
"epoch": 0.23,
"learning_rate": 1.5874587458745875e-05,
"loss": 0.5941,
"step": 288
},
{
"epoch": 0.23,
"learning_rate": 1.585808580858086e-05,
"loss": 0.6082,
"step": 289
},
{
"epoch": 0.23,
"learning_rate": 1.5841584158415843e-05,
"loss": 0.6186,
"step": 290
},
{
"epoch": 0.23,
"learning_rate": 1.5825082508250827e-05,
"loss": 0.5935,
"step": 291
},
{
"epoch": 0.23,
"learning_rate": 1.580858085808581e-05,
"loss": 0.6275,
"step": 292
},
{
"epoch": 0.23,
"learning_rate": 1.5792079207920795e-05,
"loss": 0.6246,
"step": 293
},
{
"epoch": 0.23,
"learning_rate": 1.5775577557755775e-05,
"loss": 0.6296,
"step": 294
},
{
"epoch": 0.24,
"learning_rate": 1.575907590759076e-05,
"loss": 0.5688,
"step": 295
},
{
"epoch": 0.24,
"learning_rate": 1.5742574257425743e-05,
"loss": 0.5895,
"step": 296
},
{
"epoch": 0.24,
"learning_rate": 1.5726072607260727e-05,
"loss": 0.6286,
"step": 297
},
{
"epoch": 0.24,
"learning_rate": 1.570957095709571e-05,
"loss": 0.5989,
"step": 298
},
{
"epoch": 0.24,
"learning_rate": 1.5693069306930695e-05,
"loss": 0.5972,
"step": 299
},
{
"epoch": 0.24,
"learning_rate": 1.567656765676568e-05,
"loss": 0.6156,
"step": 300
},
{
"epoch": 0.24,
"learning_rate": 1.566006600660066e-05,
"loss": 0.6106,
"step": 301
},
{
"epoch": 0.24,
"learning_rate": 1.5643564356435644e-05,
"loss": 0.5751,
"step": 302
},
{
"epoch": 0.24,
"learning_rate": 1.5627062706270628e-05,
"loss": 0.6321,
"step": 303
},
{
"epoch": 0.24,
"learning_rate": 1.5610561056105612e-05,
"loss": 0.6577,
"step": 304
},
{
"epoch": 0.24,
"learning_rate": 1.5594059405940596e-05,
"loss": 0.6388,
"step": 305
},
{
"epoch": 0.24,
"learning_rate": 1.557755775577558e-05,
"loss": 0.5894,
"step": 306
},
{
"epoch": 0.25,
"learning_rate": 1.556105610561056e-05,
"loss": 0.5897,
"step": 307
},
{
"epoch": 0.25,
"learning_rate": 1.5544554455445548e-05,
"loss": 0.5822,
"step": 308
},
{
"epoch": 0.25,
"learning_rate": 1.5528052805280528e-05,
"loss": 0.6529,
"step": 309
},
{
"epoch": 0.25,
"learning_rate": 1.5511551155115512e-05,
"loss": 0.5884,
"step": 310
},
{
"epoch": 0.25,
"learning_rate": 1.5495049504950496e-05,
"loss": 0.5927,
"step": 311
},
{
"epoch": 0.25,
"learning_rate": 1.547854785478548e-05,
"loss": 0.6098,
"step": 312
},
{
"epoch": 0.25,
"learning_rate": 1.546204620462046e-05,
"loss": 0.6624,
"step": 313
},
{
"epoch": 0.25,
"learning_rate": 1.5445544554455448e-05,
"loss": 0.6307,
"step": 314
},
{
"epoch": 0.25,
"learning_rate": 1.542904290429043e-05,
"loss": 0.6354,
"step": 315
},
{
"epoch": 0.25,
"learning_rate": 1.5412541254125416e-05,
"loss": 0.5333,
"step": 316
},
{
"epoch": 0.25,
"learning_rate": 1.5396039603960397e-05,
"loss": 0.6148,
"step": 317
},
{
"epoch": 0.25,
"learning_rate": 1.537953795379538e-05,
"loss": 0.5703,
"step": 318
},
{
"epoch": 0.25,
"learning_rate": 1.5363036303630365e-05,
"loss": 0.5843,
"step": 319
},
{
"epoch": 0.26,
"learning_rate": 1.534653465346535e-05,
"loss": 0.5906,
"step": 320
},
{
"epoch": 0.26,
"learning_rate": 1.533003300330033e-05,
"loss": 0.5813,
"step": 321
},
{
"epoch": 0.26,
"learning_rate": 1.5313531353135317e-05,
"loss": 0.6106,
"step": 322
},
{
"epoch": 0.26,
"learning_rate": 1.5297029702970297e-05,
"loss": 0.5847,
"step": 323
},
{
"epoch": 0.26,
"learning_rate": 1.528052805280528e-05,
"loss": 0.6285,
"step": 324
},
{
"epoch": 0.26,
"learning_rate": 1.5264026402640265e-05,
"loss": 0.6288,
"step": 325
},
{
"epoch": 0.26,
"learning_rate": 1.5247524752475249e-05,
"loss": 0.5704,
"step": 326
},
{
"epoch": 0.26,
"learning_rate": 1.5231023102310231e-05,
"loss": 0.641,
"step": 327
},
{
"epoch": 0.26,
"learning_rate": 1.5214521452145217e-05,
"loss": 0.6141,
"step": 328
},
{
"epoch": 0.26,
"learning_rate": 1.51980198019802e-05,
"loss": 0.6374,
"step": 329
},
{
"epoch": 0.26,
"learning_rate": 1.5181518151815182e-05,
"loss": 0.6133,
"step": 330
},
{
"epoch": 0.26,
"learning_rate": 1.5165016501650167e-05,
"loss": 0.5784,
"step": 331
},
{
"epoch": 0.26,
"learning_rate": 1.514851485148515e-05,
"loss": 0.5831,
"step": 332
},
{
"epoch": 0.27,
"learning_rate": 1.5132013201320132e-05,
"loss": 0.6319,
"step": 333
},
{
"epoch": 0.27,
"learning_rate": 1.5115511551155118e-05,
"loss": 0.5662,
"step": 334
},
{
"epoch": 0.27,
"learning_rate": 1.50990099009901e-05,
"loss": 0.5743,
"step": 335
},
{
"epoch": 0.27,
"learning_rate": 1.5082508250825084e-05,
"loss": 0.6239,
"step": 336
},
{
"epoch": 0.27,
"learning_rate": 1.5066006600660068e-05,
"loss": 0.551,
"step": 337
},
{
"epoch": 0.27,
"learning_rate": 1.504950495049505e-05,
"loss": 0.5712,
"step": 338
},
{
"epoch": 0.27,
"learning_rate": 1.5033003300330034e-05,
"loss": 0.6283,
"step": 339
},
{
"epoch": 0.27,
"learning_rate": 1.5016501650165018e-05,
"loss": 0.5741,
"step": 340
},
{
"epoch": 0.27,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.5502,
"step": 341
},
{
"epoch": 0.27,
"learning_rate": 1.4983498349834984e-05,
"loss": 0.5688,
"step": 342
},
{
"epoch": 0.27,
"learning_rate": 1.4966996699669968e-05,
"loss": 0.6159,
"step": 343
},
{
"epoch": 0.27,
"learning_rate": 1.4950495049504952e-05,
"loss": 0.6406,
"step": 344
},
{
"epoch": 0.28,
"learning_rate": 1.4933993399339935e-05,
"loss": 0.584,
"step": 345
},
{
"epoch": 0.28,
"learning_rate": 1.4917491749174919e-05,
"loss": 0.5867,
"step": 346
},
{
"epoch": 0.28,
"learning_rate": 1.4900990099009903e-05,
"loss": 0.6106,
"step": 347
},
{
"epoch": 0.28,
"learning_rate": 1.4884488448844885e-05,
"loss": 0.6126,
"step": 348
},
{
"epoch": 0.28,
"learning_rate": 1.486798679867987e-05,
"loss": 0.5755,
"step": 349
},
{
"epoch": 0.28,
"learning_rate": 1.4851485148514853e-05,
"loss": 0.5997,
"step": 350
},
{
"epoch": 0.28,
"learning_rate": 1.4834983498349835e-05,
"loss": 0.6071,
"step": 351
},
{
"epoch": 0.28,
"learning_rate": 1.481848184818482e-05,
"loss": 0.6309,
"step": 352
},
{
"epoch": 0.28,
"learning_rate": 1.4801980198019803e-05,
"loss": 0.5608,
"step": 353
},
{
"epoch": 0.28,
"learning_rate": 1.4785478547854785e-05,
"loss": 0.6024,
"step": 354
},
{
"epoch": 0.28,
"learning_rate": 1.4768976897689771e-05,
"loss": 0.6461,
"step": 355
},
{
"epoch": 0.28,
"learning_rate": 1.4752475247524753e-05,
"loss": 0.5974,
"step": 356
},
{
"epoch": 0.28,
"learning_rate": 1.4735973597359736e-05,
"loss": 0.5963,
"step": 357
},
{
"epoch": 0.29,
"learning_rate": 1.4719471947194721e-05,
"loss": 0.5701,
"step": 358
},
{
"epoch": 0.29,
"learning_rate": 1.4702970297029704e-05,
"loss": 0.5713,
"step": 359
},
{
"epoch": 0.29,
"learning_rate": 1.4686468646864686e-05,
"loss": 0.6087,
"step": 360
},
{
"epoch": 0.29,
"learning_rate": 1.4669966996699672e-05,
"loss": 0.5479,
"step": 361
},
{
"epoch": 0.29,
"learning_rate": 1.4653465346534654e-05,
"loss": 0.5647,
"step": 362
},
{
"epoch": 0.29,
"learning_rate": 1.4636963696369638e-05,
"loss": 0.6127,
"step": 363
},
{
"epoch": 0.29,
"learning_rate": 1.4620462046204622e-05,
"loss": 0.6212,
"step": 364
},
{
"epoch": 0.29,
"learning_rate": 1.4603960396039604e-05,
"loss": 0.5675,
"step": 365
},
{
"epoch": 0.29,
"learning_rate": 1.4587458745874588e-05,
"loss": 0.5938,
"step": 366
},
{
"epoch": 0.29,
"learning_rate": 1.4570957095709572e-05,
"loss": 0.5255,
"step": 367
},
{
"epoch": 0.29,
"learning_rate": 1.4554455445544556e-05,
"loss": 0.5837,
"step": 368
},
{
"epoch": 0.29,
"learning_rate": 1.453795379537954e-05,
"loss": 0.5926,
"step": 369
},
{
"epoch": 0.3,
"learning_rate": 1.4521452145214522e-05,
"loss": 0.5825,
"step": 370
},
{
"epoch": 0.3,
"learning_rate": 1.4504950495049506e-05,
"loss": 0.5738,
"step": 371
},
{
"epoch": 0.3,
"learning_rate": 1.448844884488449e-05,
"loss": 0.5941,
"step": 372
},
{
"epoch": 0.3,
"learning_rate": 1.4471947194719474e-05,
"loss": 0.5932,
"step": 373
},
{
"epoch": 0.3,
"learning_rate": 1.4455445544554456e-05,
"loss": 0.5819,
"step": 374
},
{
"epoch": 0.3,
"learning_rate": 1.443894389438944e-05,
"loss": 0.5942,
"step": 375
},
{
"epoch": 0.3,
"learning_rate": 1.4422442244224424e-05,
"loss": 0.64,
"step": 376
},
{
"epoch": 0.3,
"learning_rate": 1.4405940594059407e-05,
"loss": 0.612,
"step": 377
},
{
"epoch": 0.3,
"learning_rate": 1.438943894389439e-05,
"loss": 0.6179,
"step": 378
},
{
"epoch": 0.3,
"learning_rate": 1.4372937293729375e-05,
"loss": 0.5963,
"step": 379
},
{
"epoch": 0.3,
"learning_rate": 1.4356435643564357e-05,
"loss": 0.61,
"step": 380
},
{
"epoch": 0.3,
"learning_rate": 1.4339933993399343e-05,
"loss": 0.5477,
"step": 381
},
{
"epoch": 0.3,
"learning_rate": 1.4323432343234325e-05,
"loss": 0.6623,
"step": 382
},
{
"epoch": 0.31,
"learning_rate": 1.4306930693069307e-05,
"loss": 0.5672,
"step": 383
},
{
"epoch": 0.31,
"learning_rate": 1.4290429042904293e-05,
"loss": 0.644,
"step": 384
},
{
"epoch": 0.31,
"learning_rate": 1.4273927392739275e-05,
"loss": 0.5575,
"step": 385
},
{
"epoch": 0.31,
"learning_rate": 1.4257425742574257e-05,
"loss": 0.5979,
"step": 386
},
{
"epoch": 0.31,
"learning_rate": 1.4240924092409243e-05,
"loss": 0.6261,
"step": 387
},
{
"epoch": 0.31,
"learning_rate": 1.4224422442244225e-05,
"loss": 0.6078,
"step": 388
},
{
"epoch": 0.31,
"learning_rate": 1.4207920792079208e-05,
"loss": 0.5697,
"step": 389
},
{
"epoch": 0.31,
"learning_rate": 1.4191419141914193e-05,
"loss": 0.6361,
"step": 390
},
{
"epoch": 0.31,
"learning_rate": 1.4174917491749176e-05,
"loss": 0.5651,
"step": 391
},
{
"epoch": 0.31,
"learning_rate": 1.4158415841584158e-05,
"loss": 0.5863,
"step": 392
},
{
"epoch": 0.31,
"learning_rate": 1.4141914191419144e-05,
"loss": 0.6279,
"step": 393
},
{
"epoch": 0.31,
"learning_rate": 1.4125412541254126e-05,
"loss": 0.6082,
"step": 394
},
{
"epoch": 0.32,
"learning_rate": 1.410891089108911e-05,
"loss": 0.6308,
"step": 395
},
{
"epoch": 0.32,
"learning_rate": 1.4092409240924094e-05,
"loss": 0.567,
"step": 396
},
{
"epoch": 0.32,
"learning_rate": 1.4075907590759076e-05,
"loss": 0.5742,
"step": 397
},
{
"epoch": 0.32,
"learning_rate": 1.405940594059406e-05,
"loss": 0.5751,
"step": 398
},
{
"epoch": 0.32,
"learning_rate": 1.4042904290429044e-05,
"loss": 0.5782,
"step": 399
},
{
"epoch": 0.32,
"learning_rate": 1.4026402640264028e-05,
"loss": 0.5713,
"step": 400
},
{
"epoch": 0.32,
"learning_rate": 1.400990099009901e-05,
"loss": 0.5917,
"step": 401
},
{
"epoch": 0.32,
"learning_rate": 1.3993399339933994e-05,
"loss": 0.6088,
"step": 402
},
{
"epoch": 0.32,
"learning_rate": 1.3976897689768978e-05,
"loss": 0.5703,
"step": 403
},
{
"epoch": 0.32,
"learning_rate": 1.396039603960396e-05,
"loss": 0.6044,
"step": 404
},
{
"epoch": 0.32,
"learning_rate": 1.3943894389438946e-05,
"loss": 0.5768,
"step": 405
},
{
"epoch": 0.32,
"learning_rate": 1.3927392739273929e-05,
"loss": 0.5817,
"step": 406
},
{
"epoch": 0.32,
"learning_rate": 1.3910891089108911e-05,
"loss": 0.6193,
"step": 407
},
{
"epoch": 0.33,
"learning_rate": 1.3894389438943897e-05,
"loss": 0.6118,
"step": 408
},
{
"epoch": 0.33,
"learning_rate": 1.3877887788778879e-05,
"loss": 0.5857,
"step": 409
},
{
"epoch": 0.33,
"learning_rate": 1.3861386138613861e-05,
"loss": 0.6479,
"step": 410
},
{
"epoch": 0.33,
"learning_rate": 1.3844884488448847e-05,
"loss": 0.6191,
"step": 411
},
{
"epoch": 0.33,
"learning_rate": 1.3828382838283829e-05,
"loss": 0.5745,
"step": 412
},
{
"epoch": 0.33,
"learning_rate": 1.3811881188118811e-05,
"loss": 0.5324,
"step": 413
},
{
"epoch": 0.33,
"learning_rate": 1.3795379537953797e-05,
"loss": 0.6109,
"step": 414
},
{
"epoch": 0.33,
"learning_rate": 1.377887788778878e-05,
"loss": 0.5768,
"step": 415
},
{
"epoch": 0.33,
"learning_rate": 1.3762376237623762e-05,
"loss": 0.5848,
"step": 416
},
{
"epoch": 0.33,
"learning_rate": 1.3745874587458747e-05,
"loss": 0.5844,
"step": 417
},
{
"epoch": 0.33,
"learning_rate": 1.372937293729373e-05,
"loss": 0.584,
"step": 418
},
{
"epoch": 0.33,
"learning_rate": 1.3712871287128715e-05,
"loss": 0.5731,
"step": 419
},
{
"epoch": 0.34,
"learning_rate": 1.3696369636963698e-05,
"loss": 0.576,
"step": 420
},
{
"epoch": 0.34,
"learning_rate": 1.367986798679868e-05,
"loss": 0.5933,
"step": 421
},
{
"epoch": 0.34,
"learning_rate": 1.3663366336633666e-05,
"loss": 0.5731,
"step": 422
},
{
"epoch": 0.34,
"learning_rate": 1.3646864686468648e-05,
"loss": 0.5282,
"step": 423
},
{
"epoch": 0.34,
"learning_rate": 1.3630363036303632e-05,
"loss": 0.55,
"step": 424
},
{
"epoch": 0.34,
"learning_rate": 1.3613861386138616e-05,
"loss": 0.7658,
"step": 425
},
{
"epoch": 0.34,
"learning_rate": 1.3597359735973598e-05,
"loss": 0.5938,
"step": 426
},
{
"epoch": 0.34,
"learning_rate": 1.3580858085808582e-05,
"loss": 0.566,
"step": 427
},
{
"epoch": 0.34,
"learning_rate": 1.3564356435643566e-05,
"loss": 0.5827,
"step": 428
},
{
"epoch": 0.34,
"learning_rate": 1.3547854785478548e-05,
"loss": 0.5589,
"step": 429
},
{
"epoch": 0.34,
"learning_rate": 1.3531353135313532e-05,
"loss": 0.6081,
"step": 430
},
{
"epoch": 0.34,
"learning_rate": 1.3514851485148516e-05,
"loss": 0.571,
"step": 431
},
{
"epoch": 0.34,
"learning_rate": 1.34983498349835e-05,
"loss": 0.6014,
"step": 432
},
{
"epoch": 0.35,
"learning_rate": 1.3481848184818483e-05,
"loss": 0.5386,
"step": 433
},
{
"epoch": 0.35,
"learning_rate": 1.3465346534653467e-05,
"loss": 0.5562,
"step": 434
},
{
"epoch": 0.35,
"learning_rate": 1.344884488448845e-05,
"loss": 0.614,
"step": 435
},
{
"epoch": 0.35,
"learning_rate": 1.3432343234323433e-05,
"loss": 0.585,
"step": 436
},
{
"epoch": 0.35,
"learning_rate": 1.3415841584158418e-05,
"loss": 0.6117,
"step": 437
},
{
"epoch": 0.35,
"learning_rate": 1.33993399339934e-05,
"loss": 0.565,
"step": 438
},
{
"epoch": 0.35,
"learning_rate": 1.3382838283828383e-05,
"loss": 0.6197,
"step": 439
},
{
"epoch": 0.35,
"learning_rate": 1.3366336633663369e-05,
"loss": 0.5808,
"step": 440
},
{
"epoch": 0.35,
"learning_rate": 1.3349834983498351e-05,
"loss": 0.5886,
"step": 441
},
{
"epoch": 0.35,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.5721,
"step": 442
},
{
"epoch": 0.35,
"learning_rate": 1.3316831683168319e-05,
"loss": 0.5888,
"step": 443
},
{
"epoch": 0.35,
"learning_rate": 1.3300330033003301e-05,
"loss": 0.587,
"step": 444
},
{
"epoch": 0.36,
"learning_rate": 1.3283828382838284e-05,
"loss": 0.6135,
"step": 445
},
{
"epoch": 0.36,
"learning_rate": 1.326732673267327e-05,
"loss": 0.597,
"step": 446
},
{
"epoch": 0.36,
"learning_rate": 1.3250825082508252e-05,
"loss": 0.5774,
"step": 447
},
{
"epoch": 0.36,
"learning_rate": 1.3234323432343234e-05,
"loss": 0.5731,
"step": 448
},
{
"epoch": 0.36,
"learning_rate": 1.321782178217822e-05,
"loss": 0.5597,
"step": 449
},
{
"epoch": 0.36,
"learning_rate": 1.3201320132013202e-05,
"loss": 0.5494,
"step": 450
},
{
"epoch": 0.36,
"learning_rate": 1.3184818481848186e-05,
"loss": 0.5836,
"step": 451
},
{
"epoch": 0.36,
"learning_rate": 1.316831683168317e-05,
"loss": 0.657,
"step": 452
},
{
"epoch": 0.36,
"learning_rate": 1.3151815181518152e-05,
"loss": 0.628,
"step": 453
},
{
"epoch": 0.36,
"learning_rate": 1.3135313531353136e-05,
"loss": 0.5776,
"step": 454
},
{
"epoch": 0.36,
"learning_rate": 1.311881188118812e-05,
"loss": 0.5562,
"step": 455
},
{
"epoch": 0.36,
"learning_rate": 1.3102310231023104e-05,
"loss": 0.5953,
"step": 456
},
{
"epoch": 0.36,
"learning_rate": 1.3085808580858086e-05,
"loss": 0.5618,
"step": 457
},
{
"epoch": 0.37,
"learning_rate": 1.306930693069307e-05,
"loss": 0.5269,
"step": 458
},
{
"epoch": 0.37,
"learning_rate": 1.3052805280528054e-05,
"loss": 0.5561,
"step": 459
},
{
"epoch": 0.37,
"learning_rate": 1.3036303630363036e-05,
"loss": 0.5658,
"step": 460
},
{
"epoch": 0.37,
"learning_rate": 1.3019801980198022e-05,
"loss": 0.6267,
"step": 461
},
{
"epoch": 0.37,
"learning_rate": 1.3003300330033004e-05,
"loss": 0.5221,
"step": 462
},
{
"epoch": 0.37,
"learning_rate": 1.2986798679867987e-05,
"loss": 0.549,
"step": 463
},
{
"epoch": 0.37,
"learning_rate": 1.2970297029702972e-05,
"loss": 0.6091,
"step": 464
},
{
"epoch": 0.37,
"learning_rate": 1.2953795379537955e-05,
"loss": 0.5349,
"step": 465
},
{
"epoch": 0.37,
"learning_rate": 1.2937293729372937e-05,
"loss": 0.5977,
"step": 466
},
{
"epoch": 0.37,
"learning_rate": 1.2920792079207923e-05,
"loss": 0.5872,
"step": 467
},
{
"epoch": 0.37,
"learning_rate": 1.2904290429042905e-05,
"loss": 0.6398,
"step": 468
},
{
"epoch": 0.37,
"learning_rate": 1.288778877887789e-05,
"loss": 0.5777,
"step": 469
},
{
"epoch": 0.38,
"learning_rate": 1.2871287128712873e-05,
"loss": 0.6078,
"step": 470
},
{
"epoch": 0.38,
"learning_rate": 1.2854785478547855e-05,
"loss": 0.5672,
"step": 471
},
{
"epoch": 0.38,
"learning_rate": 1.2838283828382841e-05,
"loss": 0.5793,
"step": 472
},
{
"epoch": 0.38,
"learning_rate": 1.2821782178217823e-05,
"loss": 0.5832,
"step": 473
},
{
"epoch": 0.38,
"learning_rate": 1.2805280528052805e-05,
"loss": 0.6152,
"step": 474
},
{
"epoch": 0.38,
"learning_rate": 1.2788778877887791e-05,
"loss": 0.553,
"step": 475
},
{
"epoch": 0.38,
"learning_rate": 1.2772277227722773e-05,
"loss": 0.566,
"step": 476
},
{
"epoch": 0.38,
"learning_rate": 1.2755775577557756e-05,
"loss": 0.5676,
"step": 477
},
{
"epoch": 0.38,
"learning_rate": 1.2739273927392741e-05,
"loss": 0.549,
"step": 478
},
{
"epoch": 0.38,
"learning_rate": 1.2722772277227724e-05,
"loss": 0.6024,
"step": 479
},
{
"epoch": 0.38,
"learning_rate": 1.2706270627062706e-05,
"loss": 0.584,
"step": 480
},
{
"epoch": 0.38,
"learning_rate": 1.2689768976897692e-05,
"loss": 0.5732,
"step": 481
},
{
"epoch": 0.38,
"learning_rate": 1.2673267326732674e-05,
"loss": 0.5964,
"step": 482
},
{
"epoch": 0.39,
"learning_rate": 1.2656765676567658e-05,
"loss": 0.6146,
"step": 483
},
{
"epoch": 0.39,
"learning_rate": 1.2640264026402642e-05,
"loss": 0.5602,
"step": 484
},
{
"epoch": 0.39,
"learning_rate": 1.2623762376237624e-05,
"loss": 0.5801,
"step": 485
},
{
"epoch": 0.39,
"learning_rate": 1.2607260726072608e-05,
"loss": 0.5555,
"step": 486
},
{
"epoch": 0.39,
"learning_rate": 1.2590759075907592e-05,
"loss": 0.5187,
"step": 487
},
{
"epoch": 0.39,
"learning_rate": 1.2574257425742576e-05,
"loss": 0.6006,
"step": 488
},
{
"epoch": 0.39,
"learning_rate": 1.2557755775577558e-05,
"loss": 0.5743,
"step": 489
},
{
"epoch": 0.39,
"learning_rate": 1.2541254125412542e-05,
"loss": 0.5775,
"step": 490
},
{
"epoch": 0.39,
"learning_rate": 1.2524752475247526e-05,
"loss": 0.6282,
"step": 491
},
{
"epoch": 0.39,
"learning_rate": 1.2508250825082509e-05,
"loss": 0.5613,
"step": 492
},
{
"epoch": 0.39,
"learning_rate": 1.2491749174917494e-05,
"loss": 0.5226,
"step": 493
},
{
"epoch": 0.39,
"learning_rate": 1.2475247524752477e-05,
"loss": 0.6239,
"step": 494
},
{
"epoch": 0.4,
"learning_rate": 1.2458745874587459e-05,
"loss": 0.6089,
"step": 495
},
{
"epoch": 0.4,
"learning_rate": 1.2442244224422445e-05,
"loss": 0.5943,
"step": 496
},
{
"epoch": 0.4,
"learning_rate": 1.2425742574257427e-05,
"loss": 0.5683,
"step": 497
},
{
"epoch": 0.4,
"learning_rate": 1.2409240924092409e-05,
"loss": 0.5771,
"step": 498
},
{
"epoch": 0.4,
"learning_rate": 1.2392739273927395e-05,
"loss": 0.5497,
"step": 499
},
{
"epoch": 0.4,
"learning_rate": 1.2376237623762377e-05,
"loss": 0.5626,
"step": 500
},
{
"epoch": 0.4,
"learning_rate": 1.235973597359736e-05,
"loss": 0.5393,
"step": 501
},
{
"epoch": 0.4,
"learning_rate": 1.2343234323432345e-05,
"loss": 0.5641,
"step": 502
},
{
"epoch": 0.4,
"learning_rate": 1.2326732673267327e-05,
"loss": 0.5101,
"step": 503
},
{
"epoch": 0.4,
"learning_rate": 1.231023102310231e-05,
"loss": 0.5399,
"step": 504
},
{
"epoch": 0.4,
"learning_rate": 1.2293729372937295e-05,
"loss": 0.5329,
"step": 505
},
{
"epoch": 0.4,
"learning_rate": 1.2277227722772278e-05,
"loss": 0.5292,
"step": 506
},
{
"epoch": 0.4,
"learning_rate": 1.2260726072607262e-05,
"loss": 0.5562,
"step": 507
},
{
"epoch": 0.41,
"learning_rate": 1.2244224422442246e-05,
"loss": 0.565,
"step": 508
},
{
"epoch": 0.41,
"learning_rate": 1.2227722772277228e-05,
"loss": 0.5755,
"step": 509
},
{
"epoch": 0.41,
"learning_rate": 1.2211221122112212e-05,
"loss": 0.5562,
"step": 510
},
{
"epoch": 0.41,
"learning_rate": 1.2194719471947196e-05,
"loss": 0.5682,
"step": 511
},
{
"epoch": 0.41,
"learning_rate": 1.217821782178218e-05,
"loss": 0.574,
"step": 512
},
{
"epoch": 0.41,
"learning_rate": 1.2161716171617162e-05,
"loss": 0.577,
"step": 513
},
{
"epoch": 0.41,
"learning_rate": 1.2145214521452146e-05,
"loss": 0.5921,
"step": 514
},
{
"epoch": 0.41,
"learning_rate": 1.212871287128713e-05,
"loss": 0.5538,
"step": 515
},
{
"epoch": 0.41,
"learning_rate": 1.2112211221122112e-05,
"loss": 0.6061,
"step": 516
},
{
"epoch": 0.41,
"learning_rate": 1.2095709570957096e-05,
"loss": 0.5833,
"step": 517
},
{
"epoch": 0.41,
"learning_rate": 1.207920792079208e-05,
"loss": 0.5189,
"step": 518
},
{
"epoch": 0.41,
"learning_rate": 1.2062706270627064e-05,
"loss": 0.5854,
"step": 519
},
{
"epoch": 0.42,
"learning_rate": 1.2046204620462048e-05,
"loss": 0.5877,
"step": 520
},
{
"epoch": 0.42,
"learning_rate": 1.202970297029703e-05,
"loss": 0.5833,
"step": 521
},
{
"epoch": 0.42,
"learning_rate": 1.2013201320132014e-05,
"loss": 0.5366,
"step": 522
},
{
"epoch": 0.42,
"learning_rate": 1.1996699669966998e-05,
"loss": 0.5533,
"step": 523
},
{
"epoch": 0.42,
"learning_rate": 1.198019801980198e-05,
"loss": 0.5593,
"step": 524
},
{
"epoch": 0.42,
"learning_rate": 1.1963696369636966e-05,
"loss": 0.5911,
"step": 525
},
{
"epoch": 0.42,
"learning_rate": 1.1947194719471949e-05,
"loss": 0.5572,
"step": 526
},
{
"epoch": 0.42,
"learning_rate": 1.1930693069306931e-05,
"loss": 0.5473,
"step": 527
},
{
"epoch": 0.42,
"learning_rate": 1.1914191419141917e-05,
"loss": 0.5136,
"step": 528
},
{
"epoch": 0.42,
"learning_rate": 1.1897689768976899e-05,
"loss": 0.5983,
"step": 529
},
{
"epoch": 0.42,
"learning_rate": 1.1881188118811881e-05,
"loss": 0.54,
"step": 530
},
{
"epoch": 0.42,
"learning_rate": 1.1864686468646867e-05,
"loss": 0.5918,
"step": 531
},
{
"epoch": 0.42,
"learning_rate": 1.184818481848185e-05,
"loss": 0.5771,
"step": 532
},
{
"epoch": 0.43,
"learning_rate": 1.1831683168316831e-05,
"loss": 0.5697,
"step": 533
},
{
"epoch": 0.43,
"learning_rate": 1.1815181518151817e-05,
"loss": 0.5683,
"step": 534
},
{
"epoch": 0.43,
"learning_rate": 1.17986798679868e-05,
"loss": 0.5565,
"step": 535
},
{
"epoch": 0.43,
"learning_rate": 1.1782178217821782e-05,
"loss": 0.5993,
"step": 536
},
{
"epoch": 0.43,
"learning_rate": 1.1765676567656767e-05,
"loss": 0.5527,
"step": 537
},
{
"epoch": 0.43,
"learning_rate": 1.174917491749175e-05,
"loss": 0.5422,
"step": 538
},
{
"epoch": 0.43,
"learning_rate": 1.1732673267326734e-05,
"loss": 0.5853,
"step": 539
},
{
"epoch": 0.43,
"learning_rate": 1.1716171617161718e-05,
"loss": 0.556,
"step": 540
},
{
"epoch": 0.43,
"learning_rate": 1.16996699669967e-05,
"loss": 0.5564,
"step": 541
},
{
"epoch": 0.43,
"learning_rate": 1.1683168316831684e-05,
"loss": 0.5859,
"step": 542
},
{
"epoch": 0.43,
"learning_rate": 1.1666666666666668e-05,
"loss": 0.538,
"step": 543
},
{
"epoch": 0.43,
"learning_rate": 1.1650165016501652e-05,
"loss": 0.5486,
"step": 544
},
{
"epoch": 0.43,
"learning_rate": 1.1633663366336634e-05,
"loss": 0.5749,
"step": 545
},
{
"epoch": 0.44,
"learning_rate": 1.1617161716171618e-05,
"loss": 0.5034,
"step": 546
},
{
"epoch": 0.44,
"learning_rate": 1.1600660066006602e-05,
"loss": 0.5916,
"step": 547
},
{
"epoch": 0.44,
"learning_rate": 1.1584158415841584e-05,
"loss": 0.5312,
"step": 548
},
{
"epoch": 0.44,
"learning_rate": 1.156765676567657e-05,
"loss": 0.5559,
"step": 549
},
{
"epoch": 0.44,
"learning_rate": 1.1551155115511552e-05,
"loss": 0.5804,
"step": 550
},
{
"epoch": 0.44,
"learning_rate": 1.1534653465346535e-05,
"loss": 0.5369,
"step": 551
},
{
"epoch": 0.44,
"learning_rate": 1.151815181518152e-05,
"loss": 0.5717,
"step": 552
},
{
"epoch": 0.44,
"learning_rate": 1.1501650165016503e-05,
"loss": 0.5791,
"step": 553
},
{
"epoch": 0.44,
"learning_rate": 1.1485148514851485e-05,
"loss": 0.5216,
"step": 554
},
{
"epoch": 0.44,
"learning_rate": 1.146864686468647e-05,
"loss": 0.5546,
"step": 555
},
{
"epoch": 0.44,
"learning_rate": 1.1452145214521453e-05,
"loss": 0.5378,
"step": 556
},
{
"epoch": 0.44,
"learning_rate": 1.1435643564356435e-05,
"loss": 0.5306,
"step": 557
},
{
"epoch": 0.45,
"learning_rate": 1.141914191419142e-05,
"loss": 0.5596,
"step": 558
},
{
"epoch": 0.45,
"learning_rate": 1.1402640264026403e-05,
"loss": 0.5718,
"step": 559
},
{
"epoch": 0.45,
"learning_rate": 1.1386138613861385e-05,
"loss": 0.6207,
"step": 560
},
{
"epoch": 0.45,
"learning_rate": 1.1369636963696371e-05,
"loss": 0.5392,
"step": 561
},
{
"epoch": 0.45,
"learning_rate": 1.1353135313531353e-05,
"loss": 0.5452,
"step": 562
},
{
"epoch": 0.45,
"learning_rate": 1.1336633663366337e-05,
"loss": 0.5588,
"step": 563
},
{
"epoch": 0.45,
"learning_rate": 1.1320132013201321e-05,
"loss": 0.5755,
"step": 564
},
{
"epoch": 0.45,
"learning_rate": 1.1303630363036304e-05,
"loss": 0.5758,
"step": 565
},
{
"epoch": 0.45,
"learning_rate": 1.1287128712871288e-05,
"loss": 0.5236,
"step": 566
},
{
"epoch": 0.45,
"learning_rate": 1.1270627062706272e-05,
"loss": 0.5726,
"step": 567
},
{
"epoch": 0.45,
"learning_rate": 1.1254125412541254e-05,
"loss": 0.5672,
"step": 568
},
{
"epoch": 0.45,
"learning_rate": 1.123762376237624e-05,
"loss": 0.5504,
"step": 569
},
{
"epoch": 0.45,
"learning_rate": 1.1221122112211222e-05,
"loss": 0.5608,
"step": 570
},
{
"epoch": 0.46,
"learning_rate": 1.1204620462046206e-05,
"loss": 0.5271,
"step": 571
},
{
"epoch": 0.46,
"learning_rate": 1.118811881188119e-05,
"loss": 0.5953,
"step": 572
},
{
"epoch": 0.46,
"learning_rate": 1.1171617161716172e-05,
"loss": 0.5576,
"step": 573
},
{
"epoch": 0.46,
"learning_rate": 1.1155115511551156e-05,
"loss": 0.584,
"step": 574
},
{
"epoch": 0.46,
"learning_rate": 1.113861386138614e-05,
"loss": 0.5025,
"step": 575
},
{
"epoch": 0.46,
"learning_rate": 1.1122112211221124e-05,
"loss": 0.5568,
"step": 576
},
{
"epoch": 0.46,
"learning_rate": 1.1105610561056106e-05,
"loss": 0.5764,
"step": 577
},
{
"epoch": 0.46,
"learning_rate": 1.108910891089109e-05,
"loss": 0.5569,
"step": 578
},
{
"epoch": 0.46,
"learning_rate": 1.1072607260726074e-05,
"loss": 0.5476,
"step": 579
},
{
"epoch": 0.46,
"learning_rate": 1.1056105610561057e-05,
"loss": 0.5626,
"step": 580
},
{
"epoch": 0.46,
"learning_rate": 1.1039603960396042e-05,
"loss": 0.5663,
"step": 581
},
{
"epoch": 0.46,
"learning_rate": 1.1023102310231025e-05,
"loss": 0.5558,
"step": 582
},
{
"epoch": 0.47,
"learning_rate": 1.1006600660066007e-05,
"loss": 0.5525,
"step": 583
},
{
"epoch": 0.47,
"learning_rate": 1.0990099009900992e-05,
"loss": 0.5032,
"step": 584
},
{
"epoch": 0.47,
"learning_rate": 1.0973597359735975e-05,
"loss": 0.5689,
"step": 585
},
{
"epoch": 0.47,
"learning_rate": 1.0957095709570957e-05,
"loss": 0.5796,
"step": 586
},
{
"epoch": 0.47,
"learning_rate": 1.0940594059405943e-05,
"loss": 0.5351,
"step": 587
},
{
"epoch": 0.47,
"learning_rate": 1.0924092409240925e-05,
"loss": 0.5108,
"step": 588
},
{
"epoch": 0.47,
"learning_rate": 1.0907590759075907e-05,
"loss": 0.5273,
"step": 589
},
{
"epoch": 0.47,
"learning_rate": 1.0891089108910893e-05,
"loss": 0.5647,
"step": 590
},
{
"epoch": 0.47,
"learning_rate": 1.0874587458745875e-05,
"loss": 0.5297,
"step": 591
},
{
"epoch": 0.47,
"learning_rate": 1.0858085808580858e-05,
"loss": 0.5854,
"step": 592
},
{
"epoch": 0.47,
"learning_rate": 1.0841584158415843e-05,
"loss": 0.5997,
"step": 593
},
{
"epoch": 0.47,
"learning_rate": 1.0825082508250826e-05,
"loss": 0.5767,
"step": 594
},
{
"epoch": 0.47,
"learning_rate": 1.080858085808581e-05,
"loss": 0.5706,
"step": 595
},
{
"epoch": 0.48,
"learning_rate": 1.0792079207920793e-05,
"loss": 0.5272,
"step": 596
},
{
"epoch": 0.48,
"learning_rate": 1.0775577557755776e-05,
"loss": 0.5405,
"step": 597
},
{
"epoch": 0.48,
"learning_rate": 1.075907590759076e-05,
"loss": 0.5068,
"step": 598
},
{
"epoch": 0.48,
"learning_rate": 1.0742574257425744e-05,
"loss": 0.5629,
"step": 599
},
{
"epoch": 0.48,
"learning_rate": 1.0726072607260728e-05,
"loss": 0.5564,
"step": 600
},
{
"epoch": 0.48,
"learning_rate": 1.070957095709571e-05,
"loss": 0.5348,
"step": 601
},
{
"epoch": 0.48,
"learning_rate": 1.0693069306930694e-05,
"loss": 0.5344,
"step": 602
},
{
"epoch": 0.48,
"learning_rate": 1.0676567656765678e-05,
"loss": 0.5614,
"step": 603
},
{
"epoch": 0.48,
"learning_rate": 1.066006600660066e-05,
"loss": 0.5229,
"step": 604
},
{
"epoch": 0.48,
"learning_rate": 1.0643564356435644e-05,
"loss": 0.5849,
"step": 605
},
{
"epoch": 0.48,
"learning_rate": 1.0627062706270628e-05,
"loss": 0.5624,
"step": 606
},
{
"epoch": 0.48,
"learning_rate": 1.061056105610561e-05,
"loss": 0.5469,
"step": 607
},
{
"epoch": 0.49,
"learning_rate": 1.0594059405940596e-05,
"loss": 0.6092,
"step": 608
},
{
"epoch": 0.49,
"learning_rate": 1.0577557755775578e-05,
"loss": 0.5748,
"step": 609
},
{
"epoch": 0.49,
"learning_rate": 1.056105610561056e-05,
"loss": 0.5553,
"step": 610
},
{
"epoch": 0.49,
"learning_rate": 1.0544554455445546e-05,
"loss": 0.5628,
"step": 611
},
{
"epoch": 0.49,
"learning_rate": 1.0528052805280529e-05,
"loss": 0.5432,
"step": 612
},
{
"epoch": 0.49,
"learning_rate": 1.0511551155115511e-05,
"loss": 0.533,
"step": 613
},
{
"epoch": 0.49,
"learning_rate": 1.0495049504950497e-05,
"loss": 0.59,
"step": 614
},
{
"epoch": 0.49,
"learning_rate": 1.0478547854785479e-05,
"loss": 0.5241,
"step": 615
},
{
"epoch": 0.49,
"learning_rate": 1.0462046204620461e-05,
"loss": 0.6021,
"step": 616
},
{
"epoch": 0.49,
"learning_rate": 1.0445544554455447e-05,
"loss": 0.5187,
"step": 617
},
{
"epoch": 0.49,
"learning_rate": 1.042904290429043e-05,
"loss": 0.55,
"step": 618
},
{
"epoch": 0.49,
"learning_rate": 1.0412541254125415e-05,
"loss": 0.5933,
"step": 619
},
{
"epoch": 0.49,
"learning_rate": 1.0396039603960397e-05,
"loss": 0.6064,
"step": 620
},
{
"epoch": 0.5,
"learning_rate": 1.037953795379538e-05,
"loss": 0.5995,
"step": 621
},
{
"epoch": 0.5,
"learning_rate": 1.0363036303630365e-05,
"loss": 0.5459,
"step": 622
},
{
"epoch": 0.5,
"learning_rate": 1.0346534653465347e-05,
"loss": 0.5385,
"step": 623
},
{
"epoch": 0.5,
"learning_rate": 1.033003300330033e-05,
"loss": 0.511,
"step": 624
},
{
"epoch": 0.5,
"learning_rate": 1.0313531353135315e-05,
"loss": 0.5146,
"step": 625
},
{
"epoch": 0.5,
"learning_rate": 1.0297029702970298e-05,
"loss": 0.5254,
"step": 626
},
{
"epoch": 0.5,
"learning_rate": 1.0280528052805282e-05,
"loss": 0.5733,
"step": 627
},
{
"epoch": 0.5,
"learning_rate": 1.0264026402640266e-05,
"loss": 0.5374,
"step": 628
},
{
"epoch": 0.5,
"learning_rate": 1.0247524752475248e-05,
"loss": 0.5395,
"step": 629
},
{
"epoch": 0.5,
"learning_rate": 1.0231023102310232e-05,
"loss": 0.5296,
"step": 630
},
{
"epoch": 0.5,
"learning_rate": 1.0214521452145216e-05,
"loss": 0.5598,
"step": 631
},
{
"epoch": 0.5,
"learning_rate": 1.01980198019802e-05,
"loss": 0.5341,
"step": 632
},
{
"epoch": 0.51,
"learning_rate": 1.0181518151815182e-05,
"loss": 0.5776,
"step": 633
},
{
"epoch": 0.51,
"learning_rate": 1.0165016501650166e-05,
"loss": 0.5276,
"step": 634
},
{
"epoch": 0.51,
"learning_rate": 1.014851485148515e-05,
"loss": 0.5322,
"step": 635
},
{
"epoch": 0.51,
"learning_rate": 1.0132013201320132e-05,
"loss": 0.547,
"step": 636
},
{
"epoch": 0.51,
"learning_rate": 1.0115511551155116e-05,
"loss": 0.5553,
"step": 637
},
{
"epoch": 0.51,
"learning_rate": 1.00990099009901e-05,
"loss": 0.5293,
"step": 638
},
{
"epoch": 0.51,
"learning_rate": 1.0082508250825083e-05,
"loss": 0.5554,
"step": 639
},
{
"epoch": 0.51,
"learning_rate": 1.0066006600660068e-05,
"loss": 0.519,
"step": 640
},
{
"epoch": 0.51,
"learning_rate": 1.004950495049505e-05,
"loss": 0.572,
"step": 641
},
{
"epoch": 0.51,
"learning_rate": 1.0033003300330033e-05,
"loss": 0.5519,
"step": 642
},
{
"epoch": 0.51,
"learning_rate": 1.0016501650165019e-05,
"loss": 0.5449,
"step": 643
},
{
"epoch": 0.51,
"learning_rate": 1e-05,
"loss": 0.6103,
"step": 644
},
{
"epoch": 0.51,
"learning_rate": 9.983498349834985e-06,
"loss": 0.5895,
"step": 645
},
{
"epoch": 0.52,
"learning_rate": 9.966996699669967e-06,
"loss": 0.5708,
"step": 646
},
{
"epoch": 0.52,
"learning_rate": 9.950495049504951e-06,
"loss": 0.5117,
"step": 647
},
{
"epoch": 0.52,
"learning_rate": 9.933993399339935e-06,
"loss": 0.5718,
"step": 648
},
{
"epoch": 0.52,
"learning_rate": 9.917491749174917e-06,
"loss": 0.5492,
"step": 649
},
{
"epoch": 0.52,
"learning_rate": 9.900990099009901e-06,
"loss": 0.5479,
"step": 650
},
{
"epoch": 0.52,
"learning_rate": 9.884488448844885e-06,
"loss": 0.5697,
"step": 651
},
{
"epoch": 0.52,
"learning_rate": 9.867986798679868e-06,
"loss": 0.5238,
"step": 652
},
{
"epoch": 0.52,
"learning_rate": 9.851485148514852e-06,
"loss": 0.5419,
"step": 653
},
{
"epoch": 0.52,
"learning_rate": 9.834983498349836e-06,
"loss": 0.5129,
"step": 654
},
{
"epoch": 0.52,
"learning_rate": 9.81848184818482e-06,
"loss": 0.4988,
"step": 655
},
{
"epoch": 0.52,
"learning_rate": 9.801980198019802e-06,
"loss": 0.5586,
"step": 656
},
{
"epoch": 0.52,
"learning_rate": 9.785478547854786e-06,
"loss": 0.522,
"step": 657
},
{
"epoch": 0.53,
"learning_rate": 9.76897689768977e-06,
"loss": 0.5896,
"step": 658
},
{
"epoch": 0.53,
"learning_rate": 9.752475247524754e-06,
"loss": 0.5542,
"step": 659
},
{
"epoch": 0.53,
"learning_rate": 9.735973597359738e-06,
"loss": 0.5944,
"step": 660
},
{
"epoch": 0.53,
"learning_rate": 9.71947194719472e-06,
"loss": 0.5701,
"step": 661
},
{
"epoch": 0.53,
"learning_rate": 9.702970297029704e-06,
"loss": 0.5555,
"step": 662
},
{
"epoch": 0.53,
"learning_rate": 9.686468646864688e-06,
"loss": 0.5392,
"step": 663
},
{
"epoch": 0.53,
"learning_rate": 9.669966996699672e-06,
"loss": 0.5642,
"step": 664
},
{
"epoch": 0.53,
"learning_rate": 9.653465346534654e-06,
"loss": 0.5159,
"step": 665
},
{
"epoch": 0.53,
"learning_rate": 9.636963696369638e-06,
"loss": 0.5746,
"step": 666
},
{
"epoch": 0.53,
"learning_rate": 9.620462046204622e-06,
"loss": 0.59,
"step": 667
},
{
"epoch": 0.53,
"learning_rate": 9.603960396039604e-06,
"loss": 0.5798,
"step": 668
},
{
"epoch": 0.53,
"learning_rate": 9.587458745874588e-06,
"loss": 0.5523,
"step": 669
},
{
"epoch": 0.53,
"learning_rate": 9.570957095709572e-06,
"loss": 0.5682,
"step": 670
},
{
"epoch": 0.54,
"learning_rate": 9.554455445544555e-06,
"loss": 0.5377,
"step": 671
},
{
"epoch": 0.54,
"learning_rate": 9.537953795379539e-06,
"loss": 0.5731,
"step": 672
},
{
"epoch": 0.54,
"learning_rate": 9.521452145214523e-06,
"loss": 0.5539,
"step": 673
},
{
"epoch": 0.54,
"learning_rate": 9.504950495049505e-06,
"loss": 0.506,
"step": 674
},
{
"epoch": 0.54,
"learning_rate": 9.488448844884489e-06,
"loss": 0.5503,
"step": 675
},
{
"epoch": 0.54,
"learning_rate": 9.471947194719473e-06,
"loss": 0.5347,
"step": 676
},
{
"epoch": 0.54,
"learning_rate": 9.455445544554455e-06,
"loss": 0.5528,
"step": 677
},
{
"epoch": 0.54,
"learning_rate": 9.43894389438944e-06,
"loss": 0.5215,
"step": 678
},
{
"epoch": 0.54,
"learning_rate": 9.422442244224423e-06,
"loss": 0.5188,
"step": 679
},
{
"epoch": 0.54,
"learning_rate": 9.405940594059405e-06,
"loss": 0.5502,
"step": 680
},
{
"epoch": 0.54,
"learning_rate": 9.38943894389439e-06,
"loss": 0.5029,
"step": 681
},
{
"epoch": 0.54,
"learning_rate": 9.372937293729373e-06,
"loss": 0.5261,
"step": 682
},
{
"epoch": 0.55,
"learning_rate": 9.356435643564357e-06,
"loss": 0.5351,
"step": 683
},
{
"epoch": 0.55,
"learning_rate": 9.33993399339934e-06,
"loss": 0.5477,
"step": 684
},
{
"epoch": 0.55,
"learning_rate": 9.323432343234324e-06,
"loss": 0.5614,
"step": 685
},
{
"epoch": 0.55,
"learning_rate": 9.306930693069308e-06,
"loss": 0.5552,
"step": 686
},
{
"epoch": 0.55,
"learning_rate": 9.290429042904292e-06,
"loss": 0.4946,
"step": 687
},
{
"epoch": 0.55,
"learning_rate": 9.273927392739274e-06,
"loss": 0.5149,
"step": 688
},
{
"epoch": 0.55,
"learning_rate": 9.257425742574258e-06,
"loss": 0.5425,
"step": 689
},
{
"epoch": 0.55,
"learning_rate": 9.240924092409242e-06,
"loss": 0.5408,
"step": 690
},
{
"epoch": 0.55,
"learning_rate": 9.224422442244226e-06,
"loss": 0.5651,
"step": 691
},
{
"epoch": 0.55,
"learning_rate": 9.20792079207921e-06,
"loss": 0.5431,
"step": 692
},
{
"epoch": 0.55,
"learning_rate": 9.191419141914192e-06,
"loss": 0.5208,
"step": 693
},
{
"epoch": 0.55,
"learning_rate": 9.174917491749176e-06,
"loss": 0.505,
"step": 694
},
{
"epoch": 0.55,
"learning_rate": 9.15841584158416e-06,
"loss": 0.5308,
"step": 695
},
{
"epoch": 0.56,
"learning_rate": 9.141914191419142e-06,
"loss": 0.5656,
"step": 696
},
{
"epoch": 0.56,
"learning_rate": 9.125412541254126e-06,
"loss": 0.5934,
"step": 697
},
{
"epoch": 0.56,
"learning_rate": 9.10891089108911e-06,
"loss": 0.5294,
"step": 698
},
{
"epoch": 0.56,
"learning_rate": 9.092409240924093e-06,
"loss": 0.518,
"step": 699
},
{
"epoch": 0.56,
"learning_rate": 9.075907590759077e-06,
"loss": 0.5413,
"step": 700
},
{
"epoch": 0.56,
"learning_rate": 9.05940594059406e-06,
"loss": 0.5235,
"step": 701
},
{
"epoch": 0.56,
"learning_rate": 9.042904290429043e-06,
"loss": 0.5348,
"step": 702
},
{
"epoch": 0.56,
"learning_rate": 9.026402640264027e-06,
"loss": 0.541,
"step": 703
},
{
"epoch": 0.56,
"learning_rate": 9.009900990099011e-06,
"loss": 0.5769,
"step": 704
},
{
"epoch": 0.56,
"learning_rate": 8.993399339933993e-06,
"loss": 0.5638,
"step": 705
},
{
"epoch": 0.56,
"learning_rate": 8.976897689768977e-06,
"loss": 0.4854,
"step": 706
},
{
"epoch": 0.56,
"learning_rate": 8.960396039603961e-06,
"loss": 0.523,
"step": 707
},
{
"epoch": 0.57,
"learning_rate": 8.943894389438945e-06,
"loss": 0.5413,
"step": 708
},
{
"epoch": 0.57,
"learning_rate": 8.927392739273927e-06,
"loss": 0.548,
"step": 709
},
{
"epoch": 0.57,
"learning_rate": 8.910891089108911e-06,
"loss": 0.5222,
"step": 710
},
{
"epoch": 0.57,
"learning_rate": 8.894389438943895e-06,
"loss": 0.5398,
"step": 711
},
{
"epoch": 0.57,
"learning_rate": 8.877887788778878e-06,
"loss": 0.5215,
"step": 712
},
{
"epoch": 0.57,
"learning_rate": 8.861386138613862e-06,
"loss": 0.5385,
"step": 713
},
{
"epoch": 0.57,
"learning_rate": 8.844884488448846e-06,
"loss": 0.5018,
"step": 714
},
{
"epoch": 0.57,
"learning_rate": 8.82838283828383e-06,
"loss": 0.5202,
"step": 715
},
{
"epoch": 0.57,
"learning_rate": 8.811881188118812e-06,
"loss": 0.5645,
"step": 716
},
{
"epoch": 0.57,
"learning_rate": 8.795379537953796e-06,
"loss": 0.5304,
"step": 717
},
{
"epoch": 0.57,
"learning_rate": 8.77887788778878e-06,
"loss": 0.539,
"step": 718
},
{
"epoch": 0.57,
"learning_rate": 8.762376237623764e-06,
"loss": 0.5037,
"step": 719
},
{
"epoch": 0.57,
"learning_rate": 8.745874587458748e-06,
"loss": 0.4562,
"step": 720
},
{
"epoch": 0.58,
"learning_rate": 8.72937293729373e-06,
"loss": 0.511,
"step": 721
},
{
"epoch": 0.58,
"learning_rate": 8.712871287128714e-06,
"loss": 0.5315,
"step": 722
},
{
"epoch": 0.58,
"learning_rate": 8.696369636963698e-06,
"loss": 0.5177,
"step": 723
},
{
"epoch": 0.58,
"learning_rate": 8.67986798679868e-06,
"loss": 0.5428,
"step": 724
},
{
"epoch": 0.58,
"learning_rate": 8.663366336633664e-06,
"loss": 0.5344,
"step": 725
},
{
"epoch": 0.58,
"learning_rate": 8.646864686468648e-06,
"loss": 0.5461,
"step": 726
},
{
"epoch": 0.58,
"learning_rate": 8.63036303630363e-06,
"loss": 0.526,
"step": 727
},
{
"epoch": 0.58,
"learning_rate": 8.613861386138615e-06,
"loss": 0.4874,
"step": 728
},
{
"epoch": 0.58,
"learning_rate": 8.597359735973599e-06,
"loss": 0.552,
"step": 729
},
{
"epoch": 0.58,
"learning_rate": 8.58085808580858e-06,
"loss": 0.4941,
"step": 730
},
{
"epoch": 0.58,
"learning_rate": 8.564356435643565e-06,
"loss": 0.5594,
"step": 731
},
{
"epoch": 0.58,
"learning_rate": 8.547854785478549e-06,
"loss": 0.5658,
"step": 732
},
{
"epoch": 0.58,
"learning_rate": 8.531353135313533e-06,
"loss": 0.525,
"step": 733
},
{
"epoch": 0.59,
"learning_rate": 8.514851485148515e-06,
"loss": 0.5423,
"step": 734
},
{
"epoch": 0.59,
"learning_rate": 8.498349834983499e-06,
"loss": 0.5081,
"step": 735
},
{
"epoch": 0.59,
"learning_rate": 8.481848184818483e-06,
"loss": 0.4847,
"step": 736
},
{
"epoch": 0.59,
"learning_rate": 8.465346534653465e-06,
"loss": 0.5757,
"step": 737
},
{
"epoch": 0.59,
"learning_rate": 8.44884488448845e-06,
"loss": 0.5371,
"step": 738
},
{
"epoch": 0.59,
"learning_rate": 8.432343234323433e-06,
"loss": 0.5271,
"step": 739
},
{
"epoch": 0.59,
"learning_rate": 8.415841584158416e-06,
"loss": 0.5045,
"step": 740
},
{
"epoch": 0.59,
"learning_rate": 8.3993399339934e-06,
"loss": 0.5246,
"step": 741
},
{
"epoch": 0.59,
"learning_rate": 8.382838283828383e-06,
"loss": 0.5451,
"step": 742
},
{
"epoch": 0.59,
"learning_rate": 8.366336633663367e-06,
"loss": 0.5785,
"step": 743
},
{
"epoch": 0.59,
"learning_rate": 8.34983498349835e-06,
"loss": 0.5336,
"step": 744
},
{
"epoch": 0.59,
"learning_rate": 8.333333333333334e-06,
"loss": 0.5427,
"step": 745
},
{
"epoch": 0.6,
"learning_rate": 8.316831683168318e-06,
"loss": 0.5793,
"step": 746
},
{
"epoch": 0.6,
"learning_rate": 8.300330033003302e-06,
"loss": 0.5419,
"step": 747
},
{
"epoch": 0.6,
"learning_rate": 8.283828382838286e-06,
"loss": 0.4903,
"step": 748
},
{
"epoch": 0.6,
"learning_rate": 8.267326732673268e-06,
"loss": 0.5921,
"step": 749
},
{
"epoch": 0.6,
"learning_rate": 8.250825082508252e-06,
"loss": 0.5009,
"step": 750
},
{
"epoch": 0.6,
"learning_rate": 8.234323432343236e-06,
"loss": 0.4896,
"step": 751
},
{
"epoch": 0.6,
"learning_rate": 8.217821782178218e-06,
"loss": 0.5422,
"step": 752
},
{
"epoch": 0.6,
"learning_rate": 8.201320132013202e-06,
"loss": 0.5286,
"step": 753
},
{
"epoch": 0.6,
"learning_rate": 8.184818481848186e-06,
"loss": 0.5029,
"step": 754
},
{
"epoch": 0.6,
"learning_rate": 8.168316831683168e-06,
"loss": 0.518,
"step": 755
},
{
"epoch": 0.6,
"learning_rate": 8.151815181518152e-06,
"loss": 0.6075,
"step": 756
},
{
"epoch": 0.6,
"learning_rate": 8.135313531353136e-06,
"loss": 0.5119,
"step": 757
},
{
"epoch": 0.6,
"learning_rate": 8.11881188118812e-06,
"loss": 0.568,
"step": 758
},
{
"epoch": 0.61,
"learning_rate": 8.102310231023103e-06,
"loss": 0.5164,
"step": 759
},
{
"epoch": 0.61,
"learning_rate": 8.085808580858087e-06,
"loss": 0.4782,
"step": 760
},
{
"epoch": 0.61,
"learning_rate": 8.06930693069307e-06,
"loss": 0.5262,
"step": 761
},
{
"epoch": 0.61,
"learning_rate": 8.052805280528053e-06,
"loss": 0.5287,
"step": 762
},
{
"epoch": 0.61,
"learning_rate": 8.036303630363037e-06,
"loss": 0.5716,
"step": 763
},
{
"epoch": 0.61,
"learning_rate": 8.019801980198021e-06,
"loss": 0.5163,
"step": 764
},
{
"epoch": 0.61,
"learning_rate": 8.003300330033003e-06,
"loss": 0.5671,
"step": 765
},
{
"epoch": 0.61,
"learning_rate": 7.986798679867987e-06,
"loss": 0.5133,
"step": 766
},
{
"epoch": 0.61,
"learning_rate": 7.970297029702971e-06,
"loss": 0.507,
"step": 767
},
{
"epoch": 0.61,
"learning_rate": 7.953795379537953e-06,
"loss": 0.5125,
"step": 768
},
{
"epoch": 0.61,
"learning_rate": 7.937293729372937e-06,
"loss": 0.5161,
"step": 769
},
{
"epoch": 0.61,
"learning_rate": 7.920792079207921e-06,
"loss": 0.4831,
"step": 770
},
{
"epoch": 0.62,
"learning_rate": 7.904290429042905e-06,
"loss": 0.5461,
"step": 771
},
{
"epoch": 0.62,
"learning_rate": 7.887788778877888e-06,
"loss": 0.5148,
"step": 772
},
{
"epoch": 0.62,
"learning_rate": 7.871287128712872e-06,
"loss": 0.5373,
"step": 773
},
{
"epoch": 0.62,
"learning_rate": 7.854785478547856e-06,
"loss": 0.525,
"step": 774
},
{
"epoch": 0.62,
"learning_rate": 7.83828382838284e-06,
"loss": 0.5572,
"step": 775
},
{
"epoch": 0.62,
"learning_rate": 7.821782178217822e-06,
"loss": 0.5546,
"step": 776
},
{
"epoch": 0.62,
"learning_rate": 7.805280528052806e-06,
"loss": 0.5288,
"step": 777
},
{
"epoch": 0.62,
"learning_rate": 7.78877887788779e-06,
"loss": 0.5498,
"step": 778
},
{
"epoch": 0.62,
"learning_rate": 7.772277227722774e-06,
"loss": 0.5608,
"step": 779
},
{
"epoch": 0.62,
"learning_rate": 7.755775577557756e-06,
"loss": 0.5596,
"step": 780
},
{
"epoch": 0.62,
"learning_rate": 7.73927392739274e-06,
"loss": 0.5609,
"step": 781
},
{
"epoch": 0.62,
"learning_rate": 7.722772277227724e-06,
"loss": 0.5061,
"step": 782
},
{
"epoch": 0.62,
"learning_rate": 7.706270627062708e-06,
"loss": 0.5036,
"step": 783
},
{
"epoch": 0.63,
"learning_rate": 7.68976897689769e-06,
"loss": 0.5344,
"step": 784
},
{
"epoch": 0.63,
"learning_rate": 7.673267326732674e-06,
"loss": 0.5631,
"step": 785
},
{
"epoch": 0.63,
"learning_rate": 7.656765676567658e-06,
"loss": 0.5485,
"step": 786
},
{
"epoch": 0.63,
"learning_rate": 7.64026402640264e-06,
"loss": 0.542,
"step": 787
},
{
"epoch": 0.63,
"learning_rate": 7.6237623762376246e-06,
"loss": 0.4833,
"step": 788
},
{
"epoch": 0.63,
"learning_rate": 7.6072607260726086e-06,
"loss": 0.4901,
"step": 789
},
{
"epoch": 0.63,
"learning_rate": 7.590759075907591e-06,
"loss": 0.5171,
"step": 790
},
{
"epoch": 0.63,
"learning_rate": 7.574257425742575e-06,
"loss": 0.5121,
"step": 791
},
{
"epoch": 0.63,
"learning_rate": 7.557755775577559e-06,
"loss": 0.4988,
"step": 792
},
{
"epoch": 0.63,
"learning_rate": 7.541254125412542e-06,
"loss": 0.5355,
"step": 793
},
{
"epoch": 0.63,
"learning_rate": 7.524752475247525e-06,
"loss": 0.5409,
"step": 794
},
{
"epoch": 0.63,
"learning_rate": 7.508250825082509e-06,
"loss": 0.5416,
"step": 795
},
{
"epoch": 0.64,
"learning_rate": 7.491749174917492e-06,
"loss": 0.5764,
"step": 796
},
{
"epoch": 0.64,
"learning_rate": 7.475247524752476e-06,
"loss": 0.5364,
"step": 797
},
{
"epoch": 0.64,
"learning_rate": 7.458745874587459e-06,
"loss": 0.5347,
"step": 798
},
{
"epoch": 0.64,
"learning_rate": 7.4422442244224424e-06,
"loss": 0.5235,
"step": 799
},
{
"epoch": 0.64,
"learning_rate": 7.425742574257426e-06,
"loss": 0.5405,
"step": 800
},
{
"epoch": 0.64,
"learning_rate": 7.40924092409241e-06,
"loss": 0.5466,
"step": 801
},
{
"epoch": 0.64,
"learning_rate": 7.392739273927393e-06,
"loss": 0.521,
"step": 802
},
{
"epoch": 0.64,
"learning_rate": 7.376237623762377e-06,
"loss": 0.5223,
"step": 803
},
{
"epoch": 0.64,
"learning_rate": 7.359735973597361e-06,
"loss": 0.5266,
"step": 804
},
{
"epoch": 0.64,
"learning_rate": 7.343234323432343e-06,
"loss": 0.504,
"step": 805
},
{
"epoch": 0.64,
"learning_rate": 7.326732673267327e-06,
"loss": 0.5502,
"step": 806
},
{
"epoch": 0.64,
"learning_rate": 7.310231023102311e-06,
"loss": 0.5317,
"step": 807
},
{
"epoch": 0.64,
"learning_rate": 7.293729372937294e-06,
"loss": 0.5268,
"step": 808
},
{
"epoch": 0.65,
"learning_rate": 7.277227722772278e-06,
"loss": 0.5207,
"step": 809
},
{
"epoch": 0.65,
"learning_rate": 7.260726072607261e-06,
"loss": 0.5464,
"step": 810
},
{
"epoch": 0.65,
"learning_rate": 7.244224422442245e-06,
"loss": 0.5014,
"step": 811
},
{
"epoch": 0.65,
"learning_rate": 7.227722772277228e-06,
"loss": 0.5227,
"step": 812
},
{
"epoch": 0.65,
"learning_rate": 7.211221122112212e-06,
"loss": 0.5729,
"step": 813
},
{
"epoch": 0.65,
"learning_rate": 7.194719471947195e-06,
"loss": 0.551,
"step": 814
},
{
"epoch": 0.65,
"learning_rate": 7.1782178217821785e-06,
"loss": 0.5016,
"step": 815
},
{
"epoch": 0.65,
"learning_rate": 7.1617161716171625e-06,
"loss": 0.4834,
"step": 816
},
{
"epoch": 0.65,
"learning_rate": 7.1452145214521465e-06,
"loss": 0.5052,
"step": 817
},
{
"epoch": 0.65,
"learning_rate": 7.128712871287129e-06,
"loss": 0.4771,
"step": 818
},
{
"epoch": 0.65,
"learning_rate": 7.112211221122113e-06,
"loss": 0.4736,
"step": 819
},
{
"epoch": 0.65,
"learning_rate": 7.095709570957097e-06,
"loss": 0.5049,
"step": 820
},
{
"epoch": 0.66,
"learning_rate": 7.079207920792079e-06,
"loss": 0.5077,
"step": 821
},
{
"epoch": 0.66,
"learning_rate": 7.062706270627063e-06,
"loss": 0.5493,
"step": 822
},
{
"epoch": 0.66,
"learning_rate": 7.046204620462047e-06,
"loss": 0.4917,
"step": 823
},
{
"epoch": 0.66,
"learning_rate": 7.02970297029703e-06,
"loss": 0.5247,
"step": 824
},
{
"epoch": 0.66,
"learning_rate": 7.013201320132014e-06,
"loss": 0.5168,
"step": 825
},
{
"epoch": 0.66,
"learning_rate": 6.996699669966997e-06,
"loss": 0.5009,
"step": 826
},
{
"epoch": 0.66,
"learning_rate": 6.98019801980198e-06,
"loss": 0.5139,
"step": 827
},
{
"epoch": 0.66,
"learning_rate": 6.963696369636964e-06,
"loss": 0.4608,
"step": 828
},
{
"epoch": 0.66,
"learning_rate": 6.947194719471948e-06,
"loss": 0.4859,
"step": 829
},
{
"epoch": 0.66,
"learning_rate": 6.930693069306931e-06,
"loss": 0.5315,
"step": 830
},
{
"epoch": 0.66,
"learning_rate": 6.9141914191419146e-06,
"loss": 0.5276,
"step": 831
},
{
"epoch": 0.66,
"learning_rate": 6.8976897689768985e-06,
"loss": 0.5472,
"step": 832
},
{
"epoch": 0.66,
"learning_rate": 6.881188118811881e-06,
"loss": 0.5368,
"step": 833
},
{
"epoch": 0.67,
"learning_rate": 6.864686468646865e-06,
"loss": 0.5019,
"step": 834
},
{
"epoch": 0.67,
"learning_rate": 6.848184818481849e-06,
"loss": 0.501,
"step": 835
},
{
"epoch": 0.67,
"learning_rate": 6.831683168316833e-06,
"loss": 0.4828,
"step": 836
},
{
"epoch": 0.67,
"learning_rate": 6.815181518151816e-06,
"loss": 0.4927,
"step": 837
},
{
"epoch": 0.67,
"learning_rate": 6.798679867986799e-06,
"loss": 0.5306,
"step": 838
},
{
"epoch": 0.67,
"learning_rate": 6.782178217821783e-06,
"loss": 0.5388,
"step": 839
},
{
"epoch": 0.67,
"learning_rate": 6.765676567656766e-06,
"loss": 0.4892,
"step": 840
},
{
"epoch": 0.67,
"learning_rate": 6.74917491749175e-06,
"loss": 0.5158,
"step": 841
},
{
"epoch": 0.67,
"learning_rate": 6.732673267326733e-06,
"loss": 0.5211,
"step": 842
},
{
"epoch": 0.67,
"learning_rate": 6.716171617161716e-06,
"loss": 0.4972,
"step": 843
},
{
"epoch": 0.67,
"learning_rate": 6.6996699669967e-06,
"loss": 0.5293,
"step": 844
},
{
"epoch": 0.67,
"learning_rate": 6.683168316831684e-06,
"loss": 0.493,
"step": 845
},
{
"epoch": 0.68,
"learning_rate": 6.666666666666667e-06,
"loss": 0.5186,
"step": 846
},
{
"epoch": 0.68,
"learning_rate": 6.650165016501651e-06,
"loss": 0.5443,
"step": 847
},
{
"epoch": 0.68,
"learning_rate": 6.633663366336635e-06,
"loss": 0.5191,
"step": 848
},
{
"epoch": 0.68,
"learning_rate": 6.617161716171617e-06,
"loss": 0.5636,
"step": 849
},
{
"epoch": 0.68,
"learning_rate": 6.600660066006601e-06,
"loss": 0.5546,
"step": 850
},
{
"epoch": 0.68,
"learning_rate": 6.584158415841585e-06,
"loss": 0.584,
"step": 851
},
{
"epoch": 0.68,
"learning_rate": 6.567656765676568e-06,
"loss": 0.5388,
"step": 852
},
{
"epoch": 0.68,
"learning_rate": 6.551155115511552e-06,
"loss": 0.4756,
"step": 853
},
{
"epoch": 0.68,
"learning_rate": 6.534653465346535e-06,
"loss": 0.4862,
"step": 854
},
{
"epoch": 0.68,
"learning_rate": 6.518151815181518e-06,
"loss": 0.4913,
"step": 855
},
{
"epoch": 0.68,
"learning_rate": 6.501650165016502e-06,
"loss": 0.5333,
"step": 856
},
{
"epoch": 0.68,
"learning_rate": 6.485148514851486e-06,
"loss": 0.5439,
"step": 857
},
{
"epoch": 0.68,
"learning_rate": 6.4686468646864685e-06,
"loss": 0.5067,
"step": 858
},
{
"epoch": 0.69,
"learning_rate": 6.4521452145214525e-06,
"loss": 0.541,
"step": 859
},
{
"epoch": 0.69,
"learning_rate": 6.4356435643564364e-06,
"loss": 0.5363,
"step": 860
},
{
"epoch": 0.69,
"learning_rate": 6.4191419141914204e-06,
"loss": 0.5208,
"step": 861
},
{
"epoch": 0.69,
"learning_rate": 6.402640264026403e-06,
"loss": 0.5333,
"step": 862
},
{
"epoch": 0.69,
"learning_rate": 6.386138613861387e-06,
"loss": 0.5048,
"step": 863
},
{
"epoch": 0.69,
"learning_rate": 6.369636963696371e-06,
"loss": 0.5428,
"step": 864
},
{
"epoch": 0.69,
"learning_rate": 6.353135313531353e-06,
"loss": 0.5751,
"step": 865
},
{
"epoch": 0.69,
"learning_rate": 6.336633663366337e-06,
"loss": 0.5046,
"step": 866
},
{
"epoch": 0.69,
"learning_rate": 6.320132013201321e-06,
"loss": 0.4954,
"step": 867
},
{
"epoch": 0.69,
"learning_rate": 6.303630363036304e-06,
"loss": 0.5376,
"step": 868
},
{
"epoch": 0.69,
"learning_rate": 6.287128712871288e-06,
"loss": 0.5353,
"step": 869
},
{
"epoch": 0.69,
"learning_rate": 6.270627062706271e-06,
"loss": 0.5156,
"step": 870
},
{
"epoch": 0.7,
"learning_rate": 6.254125412541254e-06,
"loss": 0.464,
"step": 871
},
{
"epoch": 0.7,
"learning_rate": 6.237623762376238e-06,
"loss": 0.5073,
"step": 872
},
{
"epoch": 0.7,
"learning_rate": 6.221122112211222e-06,
"loss": 0.5364,
"step": 873
},
{
"epoch": 0.7,
"learning_rate": 6.2046204620462046e-06,
"loss": 0.5324,
"step": 874
},
{
"epoch": 0.7,
"learning_rate": 6.1881188118811885e-06,
"loss": 0.5458,
"step": 875
},
{
"epoch": 0.7,
"learning_rate": 6.1716171617161725e-06,
"loss": 0.5682,
"step": 876
},
{
"epoch": 0.7,
"learning_rate": 6.155115511551155e-06,
"loss": 0.5796,
"step": 877
},
{
"epoch": 0.7,
"learning_rate": 6.138613861386139e-06,
"loss": 0.5223,
"step": 878
},
{
"epoch": 0.7,
"learning_rate": 6.122112211221123e-06,
"loss": 0.5266,
"step": 879
},
{
"epoch": 0.7,
"learning_rate": 6.105610561056106e-06,
"loss": 0.5382,
"step": 880
},
{
"epoch": 0.7,
"learning_rate": 6.08910891089109e-06,
"loss": 0.4713,
"step": 881
},
{
"epoch": 0.7,
"learning_rate": 6.072607260726073e-06,
"loss": 0.4912,
"step": 882
},
{
"epoch": 0.7,
"learning_rate": 6.056105610561056e-06,
"loss": 0.5103,
"step": 883
},
{
"epoch": 0.71,
"learning_rate": 6.03960396039604e-06,
"loss": 0.5032,
"step": 884
},
{
"epoch": 0.71,
"learning_rate": 6.023102310231024e-06,
"loss": 0.5495,
"step": 885
},
{
"epoch": 0.71,
"learning_rate": 6.006600660066007e-06,
"loss": 0.4878,
"step": 886
},
{
"epoch": 0.71,
"learning_rate": 5.99009900990099e-06,
"loss": 0.5095,
"step": 887
},
{
"epoch": 0.71,
"learning_rate": 5.973597359735974e-06,
"loss": 0.5221,
"step": 888
},
{
"epoch": 0.71,
"learning_rate": 5.957095709570958e-06,
"loss": 0.522,
"step": 889
},
{
"epoch": 0.71,
"learning_rate": 5.940594059405941e-06,
"loss": 0.512,
"step": 890
},
{
"epoch": 0.71,
"learning_rate": 5.924092409240925e-06,
"loss": 0.531,
"step": 891
},
{
"epoch": 0.71,
"learning_rate": 5.907590759075909e-06,
"loss": 0.4759,
"step": 892
},
{
"epoch": 0.71,
"learning_rate": 5.891089108910891e-06,
"loss": 0.5209,
"step": 893
},
{
"epoch": 0.71,
"learning_rate": 5.874587458745875e-06,
"loss": 0.4937,
"step": 894
},
{
"epoch": 0.71,
"learning_rate": 5.858085808580859e-06,
"loss": 0.5166,
"step": 895
},
{
"epoch": 0.72,
"learning_rate": 5.841584158415842e-06,
"loss": 0.473,
"step": 896
},
{
"epoch": 0.72,
"learning_rate": 5.825082508250826e-06,
"loss": 0.5615,
"step": 897
},
{
"epoch": 0.72,
"learning_rate": 5.808580858085809e-06,
"loss": 0.5121,
"step": 898
},
{
"epoch": 0.72,
"learning_rate": 5.792079207920792e-06,
"loss": 0.4906,
"step": 899
},
{
"epoch": 0.72,
"learning_rate": 5.775577557755776e-06,
"loss": 0.5163,
"step": 900
},
{
"epoch": 0.72,
"learning_rate": 5.75907590759076e-06,
"loss": 0.5809,
"step": 901
},
{
"epoch": 0.72,
"learning_rate": 5.7425742574257425e-06,
"loss": 0.5459,
"step": 902
},
{
"epoch": 0.72,
"learning_rate": 5.7260726072607264e-06,
"loss": 0.4919,
"step": 903
},
{
"epoch": 0.72,
"learning_rate": 5.70957095709571e-06,
"loss": 0.5123,
"step": 904
},
{
"epoch": 0.72,
"learning_rate": 5.693069306930693e-06,
"loss": 0.5309,
"step": 905
},
{
"epoch": 0.72,
"learning_rate": 5.676567656765677e-06,
"loss": 0.5496,
"step": 906
},
{
"epoch": 0.72,
"learning_rate": 5.660066006600661e-06,
"loss": 0.5144,
"step": 907
},
{
"epoch": 0.72,
"learning_rate": 5.643564356435644e-06,
"loss": 0.5126,
"step": 908
},
{
"epoch": 0.73,
"learning_rate": 5.627062706270627e-06,
"loss": 0.4796,
"step": 909
},
{
"epoch": 0.73,
"learning_rate": 5.610561056105611e-06,
"loss": 0.5417,
"step": 910
},
{
"epoch": 0.73,
"learning_rate": 5.594059405940595e-06,
"loss": 0.4922,
"step": 911
},
{
"epoch": 0.73,
"learning_rate": 5.577557755775578e-06,
"loss": 0.5188,
"step": 912
},
{
"epoch": 0.73,
"learning_rate": 5.561056105610562e-06,
"loss": 0.4676,
"step": 913
},
{
"epoch": 0.73,
"learning_rate": 5.544554455445545e-06,
"loss": 0.5076,
"step": 914
},
{
"epoch": 0.73,
"learning_rate": 5.528052805280528e-06,
"loss": 0.5256,
"step": 915
},
{
"epoch": 0.73,
"learning_rate": 5.511551155115512e-06,
"loss": 0.4906,
"step": 916
},
{
"epoch": 0.73,
"learning_rate": 5.495049504950496e-06,
"loss": 0.5268,
"step": 917
},
{
"epoch": 0.73,
"learning_rate": 5.4785478547854785e-06,
"loss": 0.5112,
"step": 918
},
{
"epoch": 0.73,
"learning_rate": 5.4620462046204625e-06,
"loss": 0.4938,
"step": 919
},
{
"epoch": 0.73,
"learning_rate": 5.4455445544554465e-06,
"loss": 0.5611,
"step": 920
},
{
"epoch": 0.74,
"learning_rate": 5.429042904290429e-06,
"loss": 0.5532,
"step": 921
},
{
"epoch": 0.74,
"learning_rate": 5.412541254125413e-06,
"loss": 0.5343,
"step": 922
},
{
"epoch": 0.74,
"learning_rate": 5.396039603960397e-06,
"loss": 0.5404,
"step": 923
},
{
"epoch": 0.74,
"learning_rate": 5.37953795379538e-06,
"loss": 0.5418,
"step": 924
},
{
"epoch": 0.74,
"learning_rate": 5.363036303630364e-06,
"loss": 0.4836,
"step": 925
},
{
"epoch": 0.74,
"learning_rate": 5.346534653465347e-06,
"loss": 0.4891,
"step": 926
},
{
"epoch": 0.74,
"learning_rate": 5.33003300330033e-06,
"loss": 0.4727,
"step": 927
},
{
"epoch": 0.74,
"learning_rate": 5.313531353135314e-06,
"loss": 0.4926,
"step": 928
},
{
"epoch": 0.74,
"learning_rate": 5.297029702970298e-06,
"loss": 0.515,
"step": 929
},
{
"epoch": 0.74,
"learning_rate": 5.28052805280528e-06,
"loss": 0.5263,
"step": 930
},
{
"epoch": 0.74,
"learning_rate": 5.264026402640264e-06,
"loss": 0.5381,
"step": 931
},
{
"epoch": 0.74,
"learning_rate": 5.247524752475248e-06,
"loss": 0.5259,
"step": 932
},
{
"epoch": 0.74,
"learning_rate": 5.231023102310231e-06,
"loss": 0.494,
"step": 933
},
{
"epoch": 0.75,
"learning_rate": 5.214521452145215e-06,
"loss": 0.5681,
"step": 934
},
{
"epoch": 0.75,
"learning_rate": 5.1980198019801986e-06,
"loss": 0.5146,
"step": 935
},
{
"epoch": 0.75,
"learning_rate": 5.1815181518151826e-06,
"loss": 0.5885,
"step": 936
},
{
"epoch": 0.75,
"learning_rate": 5.165016501650165e-06,
"loss": 0.5182,
"step": 937
},
{
"epoch": 0.75,
"learning_rate": 5.148514851485149e-06,
"loss": 0.5094,
"step": 938
},
{
"epoch": 0.75,
"learning_rate": 5.132013201320133e-06,
"loss": 0.5208,
"step": 939
},
{
"epoch": 0.75,
"learning_rate": 5.115511551155116e-06,
"loss": 0.4969,
"step": 940
},
{
"epoch": 0.75,
"learning_rate": 5.0990099009901e-06,
"loss": 0.4974,
"step": 941
},
{
"epoch": 0.75,
"learning_rate": 5.082508250825083e-06,
"loss": 0.4893,
"step": 942
},
{
"epoch": 0.75,
"learning_rate": 5.066006600660066e-06,
"loss": 0.5605,
"step": 943
},
{
"epoch": 0.75,
"learning_rate": 5.04950495049505e-06,
"loss": 0.5285,
"step": 944
},
{
"epoch": 0.75,
"learning_rate": 5.033003300330034e-06,
"loss": 0.5375,
"step": 945
},
{
"epoch": 0.75,
"learning_rate": 5.0165016501650164e-06,
"loss": 0.4906,
"step": 946
},
{
"epoch": 0.76,
"learning_rate": 5e-06,
"loss": 0.5413,
"step": 947
},
{
"epoch": 0.76,
"learning_rate": 4.9834983498349835e-06,
"loss": 0.5934,
"step": 948
},
{
"epoch": 0.76,
"learning_rate": 4.9669966996699675e-06,
"loss": 0.5093,
"step": 949
},
{
"epoch": 0.76,
"learning_rate": 4.950495049504951e-06,
"loss": 0.5305,
"step": 950
},
{
"epoch": 0.76,
"learning_rate": 4.933993399339934e-06,
"loss": 0.5534,
"step": 951
},
{
"epoch": 0.76,
"learning_rate": 4.917491749174918e-06,
"loss": 0.54,
"step": 952
},
{
"epoch": 0.76,
"learning_rate": 4.900990099009901e-06,
"loss": 0.5404,
"step": 953
},
{
"epoch": 0.76,
"learning_rate": 4.884488448844885e-06,
"loss": 0.5408,
"step": 954
},
{
"epoch": 0.76,
"learning_rate": 4.867986798679869e-06,
"loss": 0.4956,
"step": 955
},
{
"epoch": 0.76,
"learning_rate": 4.851485148514852e-06,
"loss": 0.5042,
"step": 956
},
{
"epoch": 0.76,
"learning_rate": 4.834983498349836e-06,
"loss": 0.5014,
"step": 957
},
{
"epoch": 0.76,
"learning_rate": 4.818481848184819e-06,
"loss": 0.5651,
"step": 958
},
{
"epoch": 0.77,
"learning_rate": 4.801980198019802e-06,
"loss": 0.5257,
"step": 959
},
{
"epoch": 0.77,
"learning_rate": 4.785478547854786e-06,
"loss": 0.5143,
"step": 960
},
{
"epoch": 0.77,
"learning_rate": 4.768976897689769e-06,
"loss": 0.4706,
"step": 961
},
{
"epoch": 0.77,
"learning_rate": 4.7524752475247525e-06,
"loss": 0.4911,
"step": 962
},
{
"epoch": 0.77,
"learning_rate": 4.7359735973597365e-06,
"loss": 0.4994,
"step": 963
},
{
"epoch": 0.77,
"learning_rate": 4.71947194719472e-06,
"loss": 0.5162,
"step": 964
},
{
"epoch": 0.77,
"learning_rate": 4.702970297029703e-06,
"loss": 0.4987,
"step": 965
},
{
"epoch": 0.77,
"learning_rate": 4.686468646864687e-06,
"loss": 0.4791,
"step": 966
},
{
"epoch": 0.77,
"learning_rate": 4.66996699669967e-06,
"loss": 0.5449,
"step": 967
},
{
"epoch": 0.77,
"learning_rate": 4.653465346534654e-06,
"loss": 0.4738,
"step": 968
},
{
"epoch": 0.77,
"learning_rate": 4.636963696369637e-06,
"loss": 0.5353,
"step": 969
},
{
"epoch": 0.77,
"learning_rate": 4.620462046204621e-06,
"loss": 0.5287,
"step": 970
},
{
"epoch": 0.77,
"learning_rate": 4.603960396039605e-06,
"loss": 0.5528,
"step": 971
},
{
"epoch": 0.78,
"learning_rate": 4.587458745874588e-06,
"loss": 0.5267,
"step": 972
},
{
"epoch": 0.78,
"learning_rate": 4.570957095709571e-06,
"loss": 0.4881,
"step": 973
},
{
"epoch": 0.78,
"learning_rate": 4.554455445544555e-06,
"loss": 0.5573,
"step": 974
},
{
"epoch": 0.78,
"learning_rate": 4.537953795379538e-06,
"loss": 0.52,
"step": 975
},
{
"epoch": 0.78,
"learning_rate": 4.5214521452145214e-06,
"loss": 0.503,
"step": 976
},
{
"epoch": 0.78,
"learning_rate": 4.5049504950495054e-06,
"loss": 0.5097,
"step": 977
},
{
"epoch": 0.78,
"learning_rate": 4.4884488448844886e-06,
"loss": 0.5514,
"step": 978
},
{
"epoch": 0.78,
"learning_rate": 4.4719471947194725e-06,
"loss": 0.526,
"step": 979
},
{
"epoch": 0.78,
"learning_rate": 4.455445544554456e-06,
"loss": 0.5,
"step": 980
},
{
"epoch": 0.78,
"learning_rate": 4.438943894389439e-06,
"loss": 0.4736,
"step": 981
},
{
"epoch": 0.78,
"learning_rate": 4.422442244224423e-06,
"loss": 0.4961,
"step": 982
},
{
"epoch": 0.78,
"learning_rate": 4.405940594059406e-06,
"loss": 0.5664,
"step": 983
},
{
"epoch": 0.79,
"learning_rate": 4.38943894389439e-06,
"loss": 0.5631,
"step": 984
},
{
"epoch": 0.79,
"learning_rate": 4.372937293729374e-06,
"loss": 0.494,
"step": 985
},
{
"epoch": 0.79,
"learning_rate": 4.356435643564357e-06,
"loss": 0.5277,
"step": 986
},
{
"epoch": 0.79,
"learning_rate": 4.33993399339934e-06,
"loss": 0.5417,
"step": 987
},
{
"epoch": 0.79,
"learning_rate": 4.323432343234324e-06,
"loss": 0.5174,
"step": 988
},
{
"epoch": 0.79,
"learning_rate": 4.306930693069307e-06,
"loss": 0.4929,
"step": 989
},
{
"epoch": 0.79,
"learning_rate": 4.29042904290429e-06,
"loss": 0.4719,
"step": 990
},
{
"epoch": 0.79,
"learning_rate": 4.273927392739274e-06,
"loss": 0.4924,
"step": 991
},
{
"epoch": 0.79,
"learning_rate": 4.2574257425742575e-06,
"loss": 0.4951,
"step": 992
},
{
"epoch": 0.79,
"learning_rate": 4.2409240924092415e-06,
"loss": 0.471,
"step": 993
},
{
"epoch": 0.79,
"learning_rate": 4.224422442244225e-06,
"loss": 0.5077,
"step": 994
},
{
"epoch": 0.79,
"learning_rate": 4.207920792079208e-06,
"loss": 0.5385,
"step": 995
},
{
"epoch": 0.79,
"learning_rate": 4.191419141914192e-06,
"loss": 0.504,
"step": 996
},
{
"epoch": 0.8,
"learning_rate": 4.174917491749175e-06,
"loss": 0.4735,
"step": 997
},
{
"epoch": 0.8,
"learning_rate": 4.158415841584159e-06,
"loss": 0.449,
"step": 998
},
{
"epoch": 0.8,
"learning_rate": 4.141914191419143e-06,
"loss": 0.5192,
"step": 999
},
{
"epoch": 0.8,
"learning_rate": 4.125412541254126e-06,
"loss": 0.5347,
"step": 1000
}
],
"logging_steps": 1.0,
"max_steps": 1250,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 0.0,
"trial_name": null,
"trial_params": null
}