CW / trainer_state.json
luyang's picture
Upload folder using huggingface_hub
9e62965 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 952,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 6.896551724137931e-07,
"loss": 2.6865,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.3793103448275862e-06,
"loss": 2.5856,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 2.0689655172413796e-06,
"loss": 2.5188,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.7586206896551725e-06,
"loss": 2.0042,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 3.448275862068966e-06,
"loss": 1.5193,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 4.137931034482759e-06,
"loss": 1.5745,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 4.8275862068965525e-06,
"loss": 1.627,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 5.517241379310345e-06,
"loss": 1.6332,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 6.206896551724138e-06,
"loss": 1.5304,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 6.896551724137932e-06,
"loss": 1.5151,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 7.586206896551724e-06,
"loss": 1.421,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 8.275862068965518e-06,
"loss": 1.4517,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 8.965517241379312e-06,
"loss": 1.3899,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 9.655172413793105e-06,
"loss": 1.4026,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 1.0344827586206898e-05,
"loss": 1.3323,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1.103448275862069e-05,
"loss": 1.2691,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 1.1724137931034483e-05,
"loss": 1.2578,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 1.2413793103448277e-05,
"loss": 1.3184,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 1.310344827586207e-05,
"loss": 1.1869,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 1.3793103448275863e-05,
"loss": 1.2355,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 1.4482758620689657e-05,
"loss": 1.2352,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 1.5172413793103448e-05,
"loss": 1.2557,
"step": 22
},
{
"epoch": 0.02,
"learning_rate": 1.586206896551724e-05,
"loss": 1.2249,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 1.6551724137931037e-05,
"loss": 1.2092,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 1.7241379310344828e-05,
"loss": 1.209,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 1.7931034482758623e-05,
"loss": 1.2161,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 1.8620689655172415e-05,
"loss": 1.1682,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 1.931034482758621e-05,
"loss": 1.2196,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 1.152,
"step": 29
},
{
"epoch": 0.03,
"learning_rate": 1.9999942075015216e-05,
"loss": 1.1849,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 1.999976830073192e-05,
"loss": 1.1177,
"step": 31
},
{
"epoch": 0.03,
"learning_rate": 1.999947867916328e-05,
"loss": 1.1997,
"step": 32
},
{
"epoch": 0.03,
"learning_rate": 1.9999073213664575e-05,
"loss": 1.1562,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 1.999855190893311e-05,
"loss": 1.1231,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 1.9997914771008205e-05,
"loss": 1.1916,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 1.99971618072711e-05,
"loss": 1.1659,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 1.999629302644487e-05,
"loss": 1.1991,
"step": 37
},
{
"epoch": 0.04,
"learning_rate": 1.999530843859435e-05,
"loss": 1.0687,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 1.9994208055125983e-05,
"loss": 1.1154,
"step": 39
},
{
"epoch": 0.04,
"learning_rate": 1.9992991888787706e-05,
"loss": 1.0185,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 1.9991659953668803e-05,
"loss": 1.0765,
"step": 41
},
{
"epoch": 0.04,
"learning_rate": 1.9990212265199738e-05,
"loss": 1.0834,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 1.998864884015198e-05,
"loss": 1.055,
"step": 43
},
{
"epoch": 0.05,
"learning_rate": 1.9986969696637798e-05,
"loss": 1.0478,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 1.9985174854110072e-05,
"loss": 1.1336,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 1.998326433336204e-05,
"loss": 1.0764,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 1.9981238156527086e-05,
"loss": 1.1182,
"step": 47
},
{
"epoch": 0.05,
"learning_rate": 1.9979096347078458e-05,
"loss": 1.0444,
"step": 48
},
{
"epoch": 0.05,
"learning_rate": 1.997683892982901e-05,
"loss": 1.0806,
"step": 49
},
{
"epoch": 0.05,
"learning_rate": 1.997446593093092e-05,
"loss": 1.0181,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 1.997197737787537e-05,
"loss": 1.1,
"step": 51
},
{
"epoch": 0.05,
"learning_rate": 1.9969373299492238e-05,
"loss": 1.0381,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 1.9966653725949765e-05,
"loss": 1.0936,
"step": 53
},
{
"epoch": 0.06,
"learning_rate": 1.9963818688754202e-05,
"loss": 1.0006,
"step": 54
},
{
"epoch": 0.06,
"learning_rate": 1.996086822074945e-05,
"loss": 1.1007,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 1.9957802356116665e-05,
"loss": 1.0053,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 1.995462113037389e-05,
"loss": 1.0866,
"step": 57
},
{
"epoch": 0.06,
"learning_rate": 1.9951324580375604e-05,
"loss": 1.0326,
"step": 58
},
{
"epoch": 0.06,
"learning_rate": 1.9947912744312332e-05,
"loss": 1.0619,
"step": 59
},
{
"epoch": 0.06,
"learning_rate": 1.994438566171019e-05,
"loss": 1.0664,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 1.994074337343041e-05,
"loss": 1.0161,
"step": 61
},
{
"epoch": 0.07,
"learning_rate": 1.99369859216689e-05,
"loss": 1.0444,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 1.9933113349955727e-05,
"loss": 0.9842,
"step": 63
},
{
"epoch": 0.07,
"learning_rate": 1.9929125703154613e-05,
"loss": 0.9941,
"step": 64
},
{
"epoch": 0.07,
"learning_rate": 1.9925023027462437e-05,
"loss": 1.0807,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 1.9920805370408695e-05,
"loss": 1.0402,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 1.9916472780854915e-05,
"loss": 1.0176,
"step": 67
},
{
"epoch": 0.07,
"learning_rate": 1.9912025308994146e-05,
"loss": 1.0598,
"step": 68
},
{
"epoch": 0.07,
"learning_rate": 1.9907463006350332e-05,
"loss": 1.0026,
"step": 69
},
{
"epoch": 0.07,
"learning_rate": 1.9902785925777735e-05,
"loss": 1.0755,
"step": 70
},
{
"epoch": 0.07,
"learning_rate": 1.9897994121460322e-05,
"loss": 0.9637,
"step": 71
},
{
"epoch": 0.08,
"learning_rate": 1.9893087648911126e-05,
"loss": 1.0536,
"step": 72
},
{
"epoch": 0.08,
"learning_rate": 1.988806656497162e-05,
"loss": 1.067,
"step": 73
},
{
"epoch": 0.08,
"learning_rate": 1.9882930927811045e-05,
"loss": 1.0523,
"step": 74
},
{
"epoch": 0.08,
"learning_rate": 1.9877680796925744e-05,
"loss": 0.9823,
"step": 75
},
{
"epoch": 0.08,
"learning_rate": 1.9872316233138463e-05,
"loss": 1.0136,
"step": 76
},
{
"epoch": 0.08,
"learning_rate": 1.9866837298597663e-05,
"loss": 0.9881,
"step": 77
},
{
"epoch": 0.08,
"learning_rate": 1.9861244056776777e-05,
"loss": 0.948,
"step": 78
},
{
"epoch": 0.08,
"learning_rate": 1.98555365724735e-05,
"loss": 1.0239,
"step": 79
},
{
"epoch": 0.08,
"learning_rate": 1.9849714911809022e-05,
"loss": 1.0191,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 1.9843779142227258e-05,
"loss": 1.0028,
"step": 81
},
{
"epoch": 0.09,
"learning_rate": 1.9837729332494084e-05,
"loss": 1.0013,
"step": 82
},
{
"epoch": 0.09,
"learning_rate": 1.9831565552696526e-05,
"loss": 1.0179,
"step": 83
},
{
"epoch": 0.09,
"learning_rate": 1.9825287874241955e-05,
"loss": 0.9747,
"step": 84
},
{
"epoch": 0.09,
"learning_rate": 1.9818896369857258e-05,
"loss": 0.9979,
"step": 85
},
{
"epoch": 0.09,
"learning_rate": 1.981239111358799e-05,
"loss": 0.9899,
"step": 86
},
{
"epoch": 0.09,
"learning_rate": 1.980577218079753e-05,
"loss": 0.9538,
"step": 87
},
{
"epoch": 0.09,
"learning_rate": 1.979903964816619e-05,
"loss": 1.0888,
"step": 88
},
{
"epoch": 0.09,
"learning_rate": 1.9792193593690344e-05,
"loss": 0.9661,
"step": 89
},
{
"epoch": 0.09,
"learning_rate": 1.9785234096681507e-05,
"loss": 1.0725,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 1.9778161237765438e-05,
"loss": 1.0257,
"step": 91
},
{
"epoch": 0.1,
"learning_rate": 1.977097509888118e-05,
"loss": 0.9723,
"step": 92
},
{
"epoch": 0.1,
"learning_rate": 1.976367576328013e-05,
"loss": 1.0031,
"step": 93
},
{
"epoch": 0.1,
"learning_rate": 1.975626331552507e-05,
"loss": 1.0288,
"step": 94
},
{
"epoch": 0.1,
"learning_rate": 1.974873784148919e-05,
"loss": 0.9661,
"step": 95
},
{
"epoch": 0.1,
"learning_rate": 1.9741099428355075e-05,
"loss": 1.0029,
"step": 96
},
{
"epoch": 0.1,
"learning_rate": 1.9733348164613722e-05,
"loss": 0.9721,
"step": 97
},
{
"epoch": 0.1,
"learning_rate": 1.97254841400635e-05,
"loss": 0.9733,
"step": 98
},
{
"epoch": 0.1,
"learning_rate": 1.9717507445809105e-05,
"loss": 0.9711,
"step": 99
},
{
"epoch": 0.11,
"learning_rate": 1.9709418174260523e-05,
"loss": 1.0235,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 1.9701216419131934e-05,
"loss": 0.9064,
"step": 101
},
{
"epoch": 0.11,
"learning_rate": 1.969290227544064e-05,
"loss": 0.9361,
"step": 102
},
{
"epoch": 0.11,
"learning_rate": 1.9684475839505988e-05,
"loss": 1.0215,
"step": 103
},
{
"epoch": 0.11,
"learning_rate": 1.96759372089482e-05,
"loss": 1.0029,
"step": 104
},
{
"epoch": 0.11,
"learning_rate": 1.9667286482687284e-05,
"loss": 0.8913,
"step": 105
},
{
"epoch": 0.11,
"learning_rate": 1.9658523760941882e-05,
"loss": 0.9695,
"step": 106
},
{
"epoch": 0.11,
"learning_rate": 1.96496491452281e-05,
"loss": 0.9173,
"step": 107
},
{
"epoch": 0.11,
"learning_rate": 1.964066273835833e-05,
"loss": 0.9118,
"step": 108
},
{
"epoch": 0.11,
"learning_rate": 1.9631564644440073e-05,
"loss": 0.9991,
"step": 109
},
{
"epoch": 0.12,
"learning_rate": 1.9622354968874714e-05,
"loss": 1.0287,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 1.9613033818356322e-05,
"loss": 0.9955,
"step": 111
},
{
"epoch": 0.12,
"learning_rate": 1.9603601300870388e-05,
"loss": 0.9678,
"step": 112
},
{
"epoch": 0.12,
"learning_rate": 1.959405752569261e-05,
"loss": 0.9185,
"step": 113
},
{
"epoch": 0.12,
"learning_rate": 1.9584402603387586e-05,
"loss": 0.9803,
"step": 114
},
{
"epoch": 0.12,
"learning_rate": 1.9574636645807568e-05,
"loss": 0.9759,
"step": 115
},
{
"epoch": 0.12,
"learning_rate": 1.956475976609114e-05,
"loss": 0.9055,
"step": 116
},
{
"epoch": 0.12,
"learning_rate": 1.955477207866192e-05,
"loss": 0.9712,
"step": 117
},
{
"epoch": 0.12,
"learning_rate": 1.954467369922725e-05,
"loss": 1.0039,
"step": 118
},
{
"epoch": 0.12,
"learning_rate": 1.953446474477681e-05,
"loss": 0.9425,
"step": 119
},
{
"epoch": 0.13,
"learning_rate": 1.9524145333581315e-05,
"loss": 0.9171,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 1.951371558519111e-05,
"loss": 0.9699,
"step": 121
},
{
"epoch": 0.13,
"learning_rate": 1.9503175620434796e-05,
"loss": 0.9545,
"step": 122
},
{
"epoch": 0.13,
"learning_rate": 1.9492525561417837e-05,
"loss": 0.9922,
"step": 123
},
{
"epoch": 0.13,
"learning_rate": 1.9481765531521134e-05,
"loss": 0.9744,
"step": 124
},
{
"epoch": 0.13,
"learning_rate": 1.9470895655399596e-05,
"loss": 0.9779,
"step": 125
},
{
"epoch": 0.13,
"learning_rate": 1.9459916058980707e-05,
"loss": 0.9519,
"step": 126
},
{
"epoch": 0.13,
"learning_rate": 1.944882686946306e-05,
"loss": 0.97,
"step": 127
},
{
"epoch": 0.13,
"learning_rate": 1.9437628215314882e-05,
"loss": 0.9483,
"step": 128
},
{
"epoch": 0.14,
"learning_rate": 1.9426320226272545e-05,
"loss": 1.0,
"step": 129
},
{
"epoch": 0.14,
"learning_rate": 1.9414903033339065e-05,
"loss": 0.9841,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 1.9403376768782592e-05,
"loss": 0.9309,
"step": 131
},
{
"epoch": 0.14,
"learning_rate": 1.939174156613487e-05,
"loss": 0.9162,
"step": 132
},
{
"epoch": 0.14,
"learning_rate": 1.9379997560189677e-05,
"loss": 0.9923,
"step": 133
},
{
"epoch": 0.14,
"learning_rate": 1.936814488700129e-05,
"loss": 0.9975,
"step": 134
},
{
"epoch": 0.14,
"learning_rate": 1.9356183683882892e-05,
"loss": 0.9559,
"step": 135
},
{
"epoch": 0.14,
"learning_rate": 1.9344114089404983e-05,
"loss": 0.9919,
"step": 136
},
{
"epoch": 0.14,
"learning_rate": 1.9331936243393785e-05,
"loss": 0.9359,
"step": 137
},
{
"epoch": 0.14,
"learning_rate": 1.9319650286929596e-05,
"loss": 0.9411,
"step": 138
},
{
"epoch": 0.15,
"learning_rate": 1.930725636234519e-05,
"loss": 1.018,
"step": 139
},
{
"epoch": 0.15,
"learning_rate": 1.929475461322415e-05,
"loss": 0.9347,
"step": 140
},
{
"epoch": 0.15,
"learning_rate": 1.9282145184399197e-05,
"loss": 0.9309,
"step": 141
},
{
"epoch": 0.15,
"learning_rate": 1.9269428221950525e-05,
"loss": 0.9389,
"step": 142
},
{
"epoch": 0.15,
"learning_rate": 1.9256603873204107e-05,
"loss": 0.9795,
"step": 143
},
{
"epoch": 0.15,
"learning_rate": 1.924367228672998e-05,
"loss": 0.9358,
"step": 144
},
{
"epoch": 0.15,
"learning_rate": 1.923063361234054e-05,
"loss": 0.9655,
"step": 145
},
{
"epoch": 0.15,
"learning_rate": 1.9217488001088784e-05,
"loss": 0.9613,
"step": 146
},
{
"epoch": 0.15,
"learning_rate": 1.9204235605266587e-05,
"loss": 0.8496,
"step": 147
},
{
"epoch": 0.16,
"learning_rate": 1.9190876578402906e-05,
"loss": 0.9389,
"step": 148
},
{
"epoch": 0.16,
"learning_rate": 1.917741107526203e-05,
"loss": 0.9755,
"step": 149
},
{
"epoch": 0.16,
"learning_rate": 1.916383925184177e-05,
"loss": 0.891,
"step": 150
},
{
"epoch": 0.16,
"learning_rate": 1.9150161265371663e-05,
"loss": 0.9577,
"step": 151
},
{
"epoch": 0.16,
"learning_rate": 1.9136377274311138e-05,
"loss": 0.894,
"step": 152
},
{
"epoch": 0.16,
"learning_rate": 1.9122487438347688e-05,
"loss": 0.9864,
"step": 153
},
{
"epoch": 0.16,
"learning_rate": 1.9108491918395023e-05,
"loss": 1.0523,
"step": 154
},
{
"epoch": 0.16,
"learning_rate": 1.90943908765912e-05,
"loss": 0.9433,
"step": 155
},
{
"epoch": 0.16,
"learning_rate": 1.908018447629674e-05,
"loss": 0.9405,
"step": 156
},
{
"epoch": 0.16,
"learning_rate": 1.9065872882092752e-05,
"loss": 0.9067,
"step": 157
},
{
"epoch": 0.17,
"learning_rate": 1.905145625977901e-05,
"loss": 1.0175,
"step": 158
},
{
"epoch": 0.17,
"learning_rate": 1.903693477637204e-05,
"loss": 1.0003,
"step": 159
},
{
"epoch": 0.17,
"learning_rate": 1.9022308600103183e-05,
"loss": 0.9609,
"step": 160
},
{
"epoch": 0.17,
"learning_rate": 1.9007577900416648e-05,
"loss": 0.927,
"step": 161
},
{
"epoch": 0.17,
"learning_rate": 1.899274284796754e-05,
"loss": 0.9313,
"step": 162
},
{
"epoch": 0.17,
"learning_rate": 1.89778036146199e-05,
"loss": 0.9373,
"step": 163
},
{
"epoch": 0.17,
"learning_rate": 1.896276037344471e-05,
"loss": 0.966,
"step": 164
},
{
"epoch": 0.17,
"learning_rate": 1.8947613298717858e-05,
"loss": 0.9123,
"step": 165
},
{
"epoch": 0.17,
"learning_rate": 1.8932362565918167e-05,
"loss": 0.9456,
"step": 166
},
{
"epoch": 0.18,
"learning_rate": 1.891700835172533e-05,
"loss": 0.878,
"step": 167
},
{
"epoch": 0.18,
"learning_rate": 1.890155083401787e-05,
"loss": 0.9495,
"step": 168
},
{
"epoch": 0.18,
"learning_rate": 1.8885990191871083e-05,
"loss": 0.9561,
"step": 169
},
{
"epoch": 0.18,
"learning_rate": 1.887032660555496e-05,
"loss": 0.927,
"step": 170
},
{
"epoch": 0.18,
"learning_rate": 1.8854560256532098e-05,
"loss": 0.9389,
"step": 171
},
{
"epoch": 0.18,
"learning_rate": 1.883869132745561e-05,
"loss": 0.9555,
"step": 172
},
{
"epoch": 0.18,
"learning_rate": 1.882272000216699e-05,
"loss": 0.9624,
"step": 173
},
{
"epoch": 0.18,
"learning_rate": 1.8806646465693988e-05,
"loss": 0.9367,
"step": 174
},
{
"epoch": 0.18,
"learning_rate": 1.8790470904248478e-05,
"loss": 0.8885,
"step": 175
},
{
"epoch": 0.18,
"learning_rate": 1.877419350522429e-05,
"loss": 0.9453,
"step": 176
},
{
"epoch": 0.19,
"learning_rate": 1.8757814457195036e-05,
"loss": 0.9202,
"step": 177
},
{
"epoch": 0.19,
"learning_rate": 1.8741333949911946e-05,
"loss": 0.9501,
"step": 178
},
{
"epoch": 0.19,
"learning_rate": 1.8724752174301643e-05,
"loss": 0.9386,
"step": 179
},
{
"epoch": 0.19,
"learning_rate": 1.8708069322463952e-05,
"loss": 0.9236,
"step": 180
},
{
"epoch": 0.19,
"learning_rate": 1.869128558766965e-05,
"loss": 0.9617,
"step": 181
},
{
"epoch": 0.19,
"learning_rate": 1.8674401164358268e-05,
"loss": 0.9531,
"step": 182
},
{
"epoch": 0.19,
"learning_rate": 1.8657416248135787e-05,
"loss": 0.9944,
"step": 183
},
{
"epoch": 0.19,
"learning_rate": 1.8640331035772414e-05,
"loss": 0.9333,
"step": 184
},
{
"epoch": 0.19,
"learning_rate": 1.862314572520028e-05,
"loss": 0.9314,
"step": 185
},
{
"epoch": 0.2,
"learning_rate": 1.8605860515511158e-05,
"loss": 0.9735,
"step": 186
},
{
"epoch": 0.2,
"learning_rate": 1.8588475606954152e-05,
"loss": 0.9559,
"step": 187
},
{
"epoch": 0.2,
"learning_rate": 1.8570991200933367e-05,
"loss": 0.9605,
"step": 188
},
{
"epoch": 0.2,
"learning_rate": 1.8553407500005602e-05,
"loss": 0.9338,
"step": 189
},
{
"epoch": 0.2,
"learning_rate": 1.8535724707877975e-05,
"loss": 0.9046,
"step": 190
},
{
"epoch": 0.2,
"learning_rate": 1.8517943029405577e-05,
"loss": 0.8963,
"step": 191
},
{
"epoch": 0.2,
"learning_rate": 1.8500062670589102e-05,
"loss": 0.9495,
"step": 192
},
{
"epoch": 0.2,
"learning_rate": 1.8482083838572454e-05,
"loss": 0.8765,
"step": 193
},
{
"epoch": 0.2,
"learning_rate": 1.8464006741640342e-05,
"loss": 0.8931,
"step": 194
},
{
"epoch": 0.2,
"learning_rate": 1.8445831589215885e-05,
"loss": 0.9428,
"step": 195
},
{
"epoch": 0.21,
"learning_rate": 1.8427558591858164e-05,
"loss": 0.9104,
"step": 196
},
{
"epoch": 0.21,
"learning_rate": 1.8409187961259797e-05,
"loss": 0.9256,
"step": 197
},
{
"epoch": 0.21,
"learning_rate": 1.8390719910244487e-05,
"loss": 0.9027,
"step": 198
},
{
"epoch": 0.21,
"learning_rate": 1.837215465276455e-05,
"loss": 0.914,
"step": 199
},
{
"epoch": 0.21,
"learning_rate": 1.8353492403898433e-05,
"loss": 0.9298,
"step": 200
},
{
"epoch": 0.21,
"learning_rate": 1.833473337984823e-05,
"loss": 0.9389,
"step": 201
},
{
"epoch": 0.21,
"learning_rate": 1.831587779793719e-05,
"loss": 0.9743,
"step": 202
},
{
"epoch": 0.21,
"learning_rate": 1.829692587660716e-05,
"loss": 0.8875,
"step": 203
},
{
"epoch": 0.21,
"learning_rate": 1.8277877835416094e-05,
"loss": 0.9121,
"step": 204
},
{
"epoch": 0.22,
"learning_rate": 1.8258733895035492e-05,
"loss": 0.8945,
"step": 205
},
{
"epoch": 0.22,
"learning_rate": 1.823949427724785e-05,
"loss": 0.9177,
"step": 206
},
{
"epoch": 0.22,
"learning_rate": 1.822015920494407e-05,
"loss": 0.9673,
"step": 207
},
{
"epoch": 0.22,
"learning_rate": 1.8200728902120914e-05,
"loss": 0.9161,
"step": 208
},
{
"epoch": 0.22,
"learning_rate": 1.8181203593878384e-05,
"loss": 0.9406,
"step": 209
},
{
"epoch": 0.22,
"learning_rate": 1.8161583506417105e-05,
"loss": 0.9551,
"step": 210
},
{
"epoch": 0.22,
"learning_rate": 1.8141868867035745e-05,
"loss": 0.9376,
"step": 211
},
{
"epoch": 0.22,
"learning_rate": 1.812205990412833e-05,
"loss": 0.907,
"step": 212
},
{
"epoch": 0.22,
"learning_rate": 1.810215684718164e-05,
"loss": 0.9105,
"step": 213
},
{
"epoch": 0.22,
"learning_rate": 1.8082159926772526e-05,
"loss": 0.9241,
"step": 214
},
{
"epoch": 0.23,
"learning_rate": 1.8062069374565253e-05,
"loss": 0.9413,
"step": 215
},
{
"epoch": 0.23,
"learning_rate": 1.8041885423308808e-05,
"loss": 0.9467,
"step": 216
},
{
"epoch": 0.23,
"learning_rate": 1.80216083068342e-05,
"loss": 0.9574,
"step": 217
},
{
"epoch": 0.23,
"learning_rate": 1.800123826005177e-05,
"loss": 0.8931,
"step": 218
},
{
"epoch": 0.23,
"learning_rate": 1.798077551894844e-05,
"loss": 0.9007,
"step": 219
},
{
"epoch": 0.23,
"learning_rate": 1.7960220320585005e-05,
"loss": 0.8983,
"step": 220
},
{
"epoch": 0.23,
"learning_rate": 1.7939572903093383e-05,
"loss": 0.9347,
"step": 221
},
{
"epoch": 0.23,
"learning_rate": 1.791883350567383e-05,
"loss": 0.9514,
"step": 222
},
{
"epoch": 0.23,
"learning_rate": 1.7898002368592214e-05,
"loss": 0.9095,
"step": 223
},
{
"epoch": 0.24,
"learning_rate": 1.7877079733177185e-05,
"loss": 0.9066,
"step": 224
},
{
"epoch": 0.24,
"learning_rate": 1.7856065841817417e-05,
"loss": 0.9108,
"step": 225
},
{
"epoch": 0.24,
"learning_rate": 1.7834960937958775e-05,
"loss": 0.9109,
"step": 226
},
{
"epoch": 0.24,
"learning_rate": 1.7813765266101505e-05,
"loss": 0.8514,
"step": 227
},
{
"epoch": 0.24,
"learning_rate": 1.7792479071797405e-05,
"loss": 0.8785,
"step": 228
},
{
"epoch": 0.24,
"learning_rate": 1.7771102601646966e-05,
"loss": 0.8933,
"step": 229
},
{
"epoch": 0.24,
"learning_rate": 1.7749636103296534e-05,
"loss": 0.9003,
"step": 230
},
{
"epoch": 0.24,
"learning_rate": 1.7728079825435426e-05,
"loss": 0.9373,
"step": 231
},
{
"epoch": 0.24,
"learning_rate": 1.7706434017793052e-05,
"loss": 0.89,
"step": 232
},
{
"epoch": 0.24,
"learning_rate": 1.7684698931136036e-05,
"loss": 0.8478,
"step": 233
},
{
"epoch": 0.25,
"learning_rate": 1.7662874817265278e-05,
"loss": 0.9047,
"step": 234
},
{
"epoch": 0.25,
"learning_rate": 1.7640961929013085e-05,
"loss": 0.9102,
"step": 235
},
{
"epoch": 0.25,
"learning_rate": 1.761896052024019e-05,
"loss": 0.9216,
"step": 236
},
{
"epoch": 0.25,
"learning_rate": 1.759687084583285e-05,
"loss": 0.9322,
"step": 237
},
{
"epoch": 0.25,
"learning_rate": 1.7574693161699878e-05,
"loss": 0.8983,
"step": 238
},
{
"epoch": 0.25,
"learning_rate": 1.7552427724769676e-05,
"loss": 0.9111,
"step": 239
},
{
"epoch": 0.25,
"learning_rate": 1.753007479298726e-05,
"loss": 0.9103,
"step": 240
},
{
"epoch": 0.25,
"learning_rate": 1.7507634625311283e-05,
"loss": 0.9133,
"step": 241
},
{
"epoch": 0.25,
"learning_rate": 1.7485107481711014e-05,
"loss": 0.8663,
"step": 242
},
{
"epoch": 0.26,
"learning_rate": 1.746249362316334e-05,
"loss": 0.9425,
"step": 243
},
{
"epoch": 0.26,
"learning_rate": 1.7439793311649757e-05,
"loss": 0.856,
"step": 244
},
{
"epoch": 0.26,
"learning_rate": 1.741700681015329e-05,
"loss": 0.9201,
"step": 245
},
{
"epoch": 0.26,
"learning_rate": 1.7394134382655496e-05,
"loss": 0.9108,
"step": 246
},
{
"epoch": 0.26,
"learning_rate": 1.7371176294133375e-05,
"loss": 0.9271,
"step": 247
},
{
"epoch": 0.26,
"learning_rate": 1.734813281055632e-05,
"loss": 0.8706,
"step": 248
},
{
"epoch": 0.26,
"learning_rate": 1.732500419888301e-05,
"loss": 0.8828,
"step": 249
},
{
"epoch": 0.26,
"learning_rate": 1.7301790727058344e-05,
"loss": 0.9019,
"step": 250
},
{
"epoch": 0.26,
"learning_rate": 1.7278492664010326e-05,
"loss": 0.9354,
"step": 251
},
{
"epoch": 0.26,
"learning_rate": 1.7255110279646936e-05,
"loss": 0.9256,
"step": 252
},
{
"epoch": 0.27,
"learning_rate": 1.7231643844853034e-05,
"loss": 0.8796,
"step": 253
},
{
"epoch": 0.27,
"learning_rate": 1.7208093631487195e-05,
"loss": 0.9543,
"step": 254
},
{
"epoch": 0.27,
"learning_rate": 1.7184459912378567e-05,
"loss": 0.8633,
"step": 255
},
{
"epoch": 0.27,
"learning_rate": 1.7160742961323714e-05,
"loss": 0.9601,
"step": 256
},
{
"epoch": 0.27,
"learning_rate": 1.7136943053083442e-05,
"loss": 0.8766,
"step": 257
},
{
"epoch": 0.27,
"learning_rate": 1.7113060463379617e-05,
"loss": 0.9089,
"step": 258
},
{
"epoch": 0.27,
"learning_rate": 1.7089095468891966e-05,
"loss": 0.9268,
"step": 259
},
{
"epoch": 0.27,
"learning_rate": 1.7065048347254877e-05,
"loss": 0.9208,
"step": 260
},
{
"epoch": 0.27,
"learning_rate": 1.7040919377054182e-05,
"loss": 0.8861,
"step": 261
},
{
"epoch": 0.28,
"learning_rate": 1.701670883782393e-05,
"loss": 0.9,
"step": 262
},
{
"epoch": 0.28,
"learning_rate": 1.6992417010043144e-05,
"loss": 0.9024,
"step": 263
},
{
"epoch": 0.28,
"learning_rate": 1.6968044175132567e-05,
"loss": 0.8625,
"step": 264
},
{
"epoch": 0.28,
"learning_rate": 1.6943590615451426e-05,
"loss": 0.8684,
"step": 265
},
{
"epoch": 0.28,
"learning_rate": 1.6919056614294133e-05,
"loss": 0.8816,
"step": 266
},
{
"epoch": 0.28,
"learning_rate": 1.6894442455887014e-05,
"loss": 0.9099,
"step": 267
},
{
"epoch": 0.28,
"learning_rate": 1.6869748425385025e-05,
"loss": 0.8963,
"step": 268
},
{
"epoch": 0.28,
"learning_rate": 1.684497480886843e-05,
"loss": 0.9324,
"step": 269
},
{
"epoch": 0.28,
"learning_rate": 1.68201218933395e-05,
"loss": 0.9152,
"step": 270
},
{
"epoch": 0.28,
"learning_rate": 1.6795189966719182e-05,
"loss": 0.8749,
"step": 271
},
{
"epoch": 0.29,
"learning_rate": 1.6770179317843784e-05,
"loss": 0.9109,
"step": 272
},
{
"epoch": 0.29,
"learning_rate": 1.6745090236461586e-05,
"loss": 0.9372,
"step": 273
},
{
"epoch": 0.29,
"learning_rate": 1.671992301322952e-05,
"loss": 0.8972,
"step": 274
},
{
"epoch": 0.29,
"learning_rate": 1.6694677939709795e-05,
"loss": 0.9365,
"step": 275
},
{
"epoch": 0.29,
"learning_rate": 1.666935530836651e-05,
"loss": 0.8834,
"step": 276
},
{
"epoch": 0.29,
"learning_rate": 1.664395541256227e-05,
"loss": 0.9331,
"step": 277
},
{
"epoch": 0.29,
"learning_rate": 1.661847854655479e-05,
"loss": 0.9192,
"step": 278
},
{
"epoch": 0.29,
"learning_rate": 1.6592925005493486e-05,
"loss": 0.8907,
"step": 279
},
{
"epoch": 0.29,
"learning_rate": 1.6567295085416052e-05,
"loss": 0.9057,
"step": 280
},
{
"epoch": 0.3,
"learning_rate": 1.654158908324504e-05,
"loss": 0.8884,
"step": 281
},
{
"epoch": 0.3,
"learning_rate": 1.65158072967844e-05,
"loss": 0.9434,
"step": 282
},
{
"epoch": 0.3,
"learning_rate": 1.6489950024716055e-05,
"loss": 0.9613,
"step": 283
},
{
"epoch": 0.3,
"learning_rate": 1.6464017566596422e-05,
"loss": 0.8904,
"step": 284
},
{
"epoch": 0.3,
"learning_rate": 1.6438010222852944e-05,
"loss": 0.9161,
"step": 285
},
{
"epoch": 0.3,
"learning_rate": 1.6411928294780626e-05,
"loss": 0.9234,
"step": 286
},
{
"epoch": 0.3,
"learning_rate": 1.638577208453852e-05,
"loss": 0.9097,
"step": 287
},
{
"epoch": 0.3,
"learning_rate": 1.635954189514625e-05,
"loss": 0.9281,
"step": 288
},
{
"epoch": 0.3,
"learning_rate": 1.6333238030480473e-05,
"loss": 0.9161,
"step": 289
},
{
"epoch": 0.3,
"learning_rate": 1.630686079527138e-05,
"loss": 0.9015,
"step": 290
},
{
"epoch": 0.31,
"learning_rate": 1.6280410495099165e-05,
"loss": 0.8613,
"step": 291
},
{
"epoch": 0.31,
"learning_rate": 1.6253887436390478e-05,
"loss": 0.8884,
"step": 292
},
{
"epoch": 0.31,
"learning_rate": 1.6227291926414864e-05,
"loss": 0.8982,
"step": 293
},
{
"epoch": 0.31,
"learning_rate": 1.6200624273281236e-05,
"loss": 0.8504,
"step": 294
},
{
"epoch": 0.31,
"learning_rate": 1.6173884785934263e-05,
"loss": 0.8968,
"step": 295
},
{
"epoch": 0.31,
"learning_rate": 1.6147073774150834e-05,
"loss": 0.8117,
"step": 296
},
{
"epoch": 0.31,
"learning_rate": 1.6120191548536433e-05,
"loss": 0.9001,
"step": 297
},
{
"epoch": 0.31,
"learning_rate": 1.609323842052157e-05,
"loss": 0.8795,
"step": 298
},
{
"epoch": 0.31,
"learning_rate": 1.606621470235814e-05,
"loss": 0.8916,
"step": 299
},
{
"epoch": 0.32,
"learning_rate": 1.6039120707115845e-05,
"loss": 0.8816,
"step": 300
},
{
"epoch": 0.32,
"learning_rate": 1.601195674867853e-05,
"loss": 0.9301,
"step": 301
},
{
"epoch": 0.32,
"learning_rate": 1.5984723141740578e-05,
"loss": 0.9071,
"step": 302
},
{
"epoch": 0.32,
"learning_rate": 1.5957420201803234e-05,
"loss": 0.839,
"step": 303
},
{
"epoch": 0.32,
"learning_rate": 1.5930048245170982e-05,
"loss": 0.8712,
"step": 304
},
{
"epoch": 0.32,
"learning_rate": 1.590260758894785e-05,
"loss": 0.821,
"step": 305
},
{
"epoch": 0.32,
"learning_rate": 1.5875098551033765e-05,
"loss": 0.8387,
"step": 306
},
{
"epoch": 0.32,
"learning_rate": 1.584752145012084e-05,
"loss": 0.8785,
"step": 307
},
{
"epoch": 0.32,
"learning_rate": 1.581987660568971e-05,
"loss": 0.8529,
"step": 308
},
{
"epoch": 0.32,
"learning_rate": 1.5792164338005807e-05,
"loss": 0.9314,
"step": 309
},
{
"epoch": 0.33,
"learning_rate": 1.5764384968115674e-05,
"loss": 0.8868,
"step": 310
},
{
"epoch": 0.33,
"learning_rate": 1.5736538817843228e-05,
"loss": 0.8737,
"step": 311
},
{
"epoch": 0.33,
"learning_rate": 1.5708626209786027e-05,
"loss": 0.8192,
"step": 312
},
{
"epoch": 0.33,
"learning_rate": 1.568064746731156e-05,
"loss": 0.861,
"step": 313
},
{
"epoch": 0.33,
"learning_rate": 1.5652602914553466e-05,
"loss": 0.8321,
"step": 314
},
{
"epoch": 0.33,
"learning_rate": 1.562449287640781e-05,
"loss": 0.8735,
"step": 315
},
{
"epoch": 0.33,
"learning_rate": 1.559631767852929e-05,
"loss": 0.8363,
"step": 316
},
{
"epoch": 0.33,
"learning_rate": 1.5568077647327493e-05,
"loss": 0.9441,
"step": 317
},
{
"epoch": 0.33,
"learning_rate": 1.5539773109963097e-05,
"loss": 0.8607,
"step": 318
},
{
"epoch": 0.34,
"learning_rate": 1.5511404394344072e-05,
"loss": 0.821,
"step": 319
},
{
"epoch": 0.34,
"learning_rate": 1.5482971829121915e-05,
"loss": 0.8955,
"step": 320
},
{
"epoch": 0.34,
"learning_rate": 1.54544757436878e-05,
"loss": 0.8664,
"step": 321
},
{
"epoch": 0.34,
"learning_rate": 1.542591646816879e-05,
"loss": 0.8808,
"step": 322
},
{
"epoch": 0.34,
"learning_rate": 1.5397294333424006e-05,
"loss": 0.9032,
"step": 323
},
{
"epoch": 0.34,
"learning_rate": 1.536860967104079e-05,
"loss": 0.8748,
"step": 324
},
{
"epoch": 0.34,
"learning_rate": 1.5339862813330873e-05,
"loss": 0.8615,
"step": 325
},
{
"epoch": 0.34,
"learning_rate": 1.5311054093326508e-05,
"loss": 0.8064,
"step": 326
},
{
"epoch": 0.34,
"learning_rate": 1.5282183844776632e-05,
"loss": 0.9026,
"step": 327
},
{
"epoch": 0.34,
"learning_rate": 1.5253252402142989e-05,
"loss": 0.909,
"step": 328
},
{
"epoch": 0.35,
"learning_rate": 1.5224260100596252e-05,
"loss": 0.8778,
"step": 329
},
{
"epoch": 0.35,
"learning_rate": 1.5195207276012143e-05,
"loss": 0.8479,
"step": 330
},
{
"epoch": 0.35,
"learning_rate": 1.5166094264967553e-05,
"loss": 0.879,
"step": 331
},
{
"epoch": 0.35,
"learning_rate": 1.513692140473662e-05,
"loss": 0.8777,
"step": 332
},
{
"epoch": 0.35,
"learning_rate": 1.510768903328684e-05,
"loss": 0.8688,
"step": 333
},
{
"epoch": 0.35,
"learning_rate": 1.5078397489275154e-05,
"loss": 0.8563,
"step": 334
},
{
"epoch": 0.35,
"learning_rate": 1.5049047112044007e-05,
"loss": 0.8966,
"step": 335
},
{
"epoch": 0.35,
"learning_rate": 1.5019638241617429e-05,
"loss": 0.8504,
"step": 336
},
{
"epoch": 0.35,
"learning_rate": 1.4990171218697098e-05,
"loss": 0.8725,
"step": 337
},
{
"epoch": 0.36,
"learning_rate": 1.4960646384658381e-05,
"loss": 0.8331,
"step": 338
},
{
"epoch": 0.36,
"learning_rate": 1.493106408154639e-05,
"loss": 0.8984,
"step": 339
},
{
"epoch": 0.36,
"learning_rate": 1.490142465207202e-05,
"loss": 0.9068,
"step": 340
},
{
"epoch": 0.36,
"learning_rate": 1.4871728439607967e-05,
"loss": 0.8716,
"step": 341
},
{
"epoch": 0.36,
"learning_rate": 1.4841975788184765e-05,
"loss": 0.88,
"step": 342
},
{
"epoch": 0.36,
"learning_rate": 1.4812167042486791e-05,
"loss": 0.8779,
"step": 343
},
{
"epoch": 0.36,
"learning_rate": 1.478230254784827e-05,
"loss": 0.8658,
"step": 344
},
{
"epoch": 0.36,
"learning_rate": 1.4752382650249288e-05,
"loss": 0.8428,
"step": 345
},
{
"epoch": 0.36,
"learning_rate": 1.472240769631176e-05,
"loss": 0.8984,
"step": 346
},
{
"epoch": 0.36,
"learning_rate": 1.469237803329544e-05,
"loss": 0.8511,
"step": 347
},
{
"epoch": 0.37,
"learning_rate": 1.466229400909388e-05,
"loss": 0.8555,
"step": 348
},
{
"epoch": 0.37,
"learning_rate": 1.4632155972230413e-05,
"loss": 0.8795,
"step": 349
},
{
"epoch": 0.37,
"learning_rate": 1.4601964271854101e-05,
"loss": 0.8681,
"step": 350
},
{
"epoch": 0.37,
"learning_rate": 1.4571719257735702e-05,
"loss": 0.8766,
"step": 351
},
{
"epoch": 0.37,
"learning_rate": 1.4541421280263612e-05,
"loss": 0.8336,
"step": 352
},
{
"epoch": 0.37,
"learning_rate": 1.451107069043981e-05,
"loss": 0.8642,
"step": 353
},
{
"epoch": 0.37,
"learning_rate": 1.4480667839875786e-05,
"loss": 0.8722,
"step": 354
},
{
"epoch": 0.37,
"learning_rate": 1.4450213080788471e-05,
"loss": 0.8755,
"step": 355
},
{
"epoch": 0.37,
"learning_rate": 1.4419706765996153e-05,
"loss": 0.8365,
"step": 356
},
{
"epoch": 0.38,
"learning_rate": 1.43891492489144e-05,
"loss": 0.8457,
"step": 357
},
{
"epoch": 0.38,
"learning_rate": 1.4358540883551952e-05,
"loss": 0.8167,
"step": 358
},
{
"epoch": 0.38,
"learning_rate": 1.4327882024506635e-05,
"loss": 0.8481,
"step": 359
},
{
"epoch": 0.38,
"learning_rate": 1.4297173026961229e-05,
"loss": 0.8263,
"step": 360
},
{
"epoch": 0.38,
"learning_rate": 1.4266414246679379e-05,
"loss": 0.8246,
"step": 361
},
{
"epoch": 0.38,
"learning_rate": 1.4235606040001466e-05,
"loss": 0.8795,
"step": 362
},
{
"epoch": 0.38,
"learning_rate": 1.4204748763840466e-05,
"loss": 0.8709,
"step": 363
},
{
"epoch": 0.38,
"learning_rate": 1.4173842775677833e-05,
"loss": 0.8665,
"step": 364
},
{
"epoch": 0.38,
"learning_rate": 1.4142888433559339e-05,
"loss": 0.888,
"step": 365
},
{
"epoch": 0.38,
"learning_rate": 1.4111886096090953e-05,
"loss": 0.8559,
"step": 366
},
{
"epoch": 0.39,
"learning_rate": 1.408083612243465e-05,
"loss": 0.8037,
"step": 367
},
{
"epoch": 0.39,
"learning_rate": 1.4049738872304288e-05,
"loss": 0.8201,
"step": 368
},
{
"epoch": 0.39,
"learning_rate": 1.4018594705961413e-05,
"loss": 0.8128,
"step": 369
},
{
"epoch": 0.39,
"learning_rate": 1.39874039842111e-05,
"loss": 0.847,
"step": 370
},
{
"epoch": 0.39,
"learning_rate": 1.3956167068397756e-05,
"loss": 0.8115,
"step": 371
},
{
"epoch": 0.39,
"learning_rate": 1.3924884320400969e-05,
"loss": 0.8649,
"step": 372
},
{
"epoch": 0.39,
"learning_rate": 1.3893556102631267e-05,
"loss": 0.8968,
"step": 373
},
{
"epoch": 0.39,
"learning_rate": 1.3862182778025966e-05,
"loss": 0.8421,
"step": 374
},
{
"epoch": 0.39,
"learning_rate": 1.383076471004493e-05,
"loss": 0.8949,
"step": 375
},
{
"epoch": 0.39,
"learning_rate": 1.3799302262666388e-05,
"loss": 0.8447,
"step": 376
},
{
"epoch": 0.4,
"learning_rate": 1.3767795800382691e-05,
"loss": 0.864,
"step": 377
},
{
"epoch": 0.4,
"learning_rate": 1.3736245688196115e-05,
"loss": 0.8157,
"step": 378
},
{
"epoch": 0.4,
"learning_rate": 1.3704652291614604e-05,
"loss": 0.8933,
"step": 379
},
{
"epoch": 0.4,
"learning_rate": 1.367301597664757e-05,
"loss": 0.8436,
"step": 380
},
{
"epoch": 0.4,
"learning_rate": 1.364133710980162e-05,
"loss": 0.8061,
"step": 381
},
{
"epoch": 0.4,
"learning_rate": 1.3609616058076336e-05,
"loss": 0.84,
"step": 382
},
{
"epoch": 0.4,
"learning_rate": 1.3577853188960002e-05,
"loss": 0.8512,
"step": 383
},
{
"epoch": 0.4,
"learning_rate": 1.3546048870425356e-05,
"loss": 0.8776,
"step": 384
},
{
"epoch": 0.4,
"learning_rate": 1.351420347092534e-05,
"loss": 0.8784,
"step": 385
},
{
"epoch": 0.41,
"learning_rate": 1.3482317359388806e-05,
"loss": 0.8616,
"step": 386
},
{
"epoch": 0.41,
"learning_rate": 1.3450390905216259e-05,
"loss": 0.8844,
"step": 387
},
{
"epoch": 0.41,
"learning_rate": 1.341842447827557e-05,
"loss": 0.8451,
"step": 388
},
{
"epoch": 0.41,
"learning_rate": 1.3386418448897706e-05,
"loss": 0.8468,
"step": 389
},
{
"epoch": 0.41,
"learning_rate": 1.3354373187872414e-05,
"loss": 0.8309,
"step": 390
},
{
"epoch": 0.41,
"learning_rate": 1.3322289066443947e-05,
"loss": 0.8436,
"step": 391
},
{
"epoch": 0.41,
"learning_rate": 1.3290166456306754e-05,
"loss": 0.8432,
"step": 392
},
{
"epoch": 0.41,
"learning_rate": 1.3258005729601178e-05,
"loss": 0.8447,
"step": 393
},
{
"epoch": 0.41,
"learning_rate": 1.3225807258909136e-05,
"loss": 0.8346,
"step": 394
},
{
"epoch": 0.41,
"learning_rate": 1.3193571417249813e-05,
"loss": 0.8498,
"step": 395
},
{
"epoch": 0.42,
"learning_rate": 1.316129857807534e-05,
"loss": 0.8276,
"step": 396
},
{
"epoch": 0.42,
"learning_rate": 1.312898911526646e-05,
"loss": 0.8488,
"step": 397
},
{
"epoch": 0.42,
"learning_rate": 1.3096643403128198e-05,
"loss": 0.8441,
"step": 398
},
{
"epoch": 0.42,
"learning_rate": 1.3064261816385533e-05,
"loss": 0.8244,
"step": 399
},
{
"epoch": 0.42,
"learning_rate": 1.3031844730179048e-05,
"loss": 0.8455,
"step": 400
},
{
"epoch": 0.42,
"learning_rate": 1.2999392520060594e-05,
"loss": 0.8678,
"step": 401
},
{
"epoch": 0.42,
"learning_rate": 1.2966905561988918e-05,
"loss": 0.893,
"step": 402
},
{
"epoch": 0.42,
"learning_rate": 1.2934384232325336e-05,
"loss": 0.8447,
"step": 403
},
{
"epoch": 0.42,
"learning_rate": 1.2901828907829348e-05,
"loss": 0.8354,
"step": 404
},
{
"epoch": 0.43,
"learning_rate": 1.2869239965654294e-05,
"loss": 0.8657,
"step": 405
},
{
"epoch": 0.43,
"learning_rate": 1.2836617783342968e-05,
"loss": 0.8215,
"step": 406
},
{
"epoch": 0.43,
"learning_rate": 1.2803962738823252e-05,
"loss": 0.8883,
"step": 407
},
{
"epoch": 0.43,
"learning_rate": 1.2771275210403742e-05,
"loss": 0.8516,
"step": 408
},
{
"epoch": 0.43,
"learning_rate": 1.2738555576769349e-05,
"loss": 0.881,
"step": 409
},
{
"epoch": 0.43,
"learning_rate": 1.2705804216976931e-05,
"loss": 0.8464,
"step": 410
},
{
"epoch": 0.43,
"learning_rate": 1.2673021510450893e-05,
"loss": 0.8429,
"step": 411
},
{
"epoch": 0.43,
"learning_rate": 1.264020783697879e-05,
"loss": 0.8324,
"step": 412
},
{
"epoch": 0.43,
"learning_rate": 1.260736357670693e-05,
"loss": 0.8555,
"step": 413
},
{
"epoch": 0.43,
"learning_rate": 1.2574489110135968e-05,
"loss": 0.7723,
"step": 414
},
{
"epoch": 0.44,
"learning_rate": 1.2541584818116494e-05,
"loss": 0.8034,
"step": 415
},
{
"epoch": 0.44,
"learning_rate": 1.250865108184464e-05,
"loss": 0.8547,
"step": 416
},
{
"epoch": 0.44,
"learning_rate": 1.2475688282857634e-05,
"loss": 0.8518,
"step": 417
},
{
"epoch": 0.44,
"learning_rate": 1.2442696803029405e-05,
"loss": 0.8465,
"step": 418
},
{
"epoch": 0.44,
"learning_rate": 1.2409677024566145e-05,
"loss": 0.8582,
"step": 419
},
{
"epoch": 0.44,
"learning_rate": 1.2376629330001889e-05,
"loss": 0.8725,
"step": 420
},
{
"epoch": 0.44,
"learning_rate": 1.2343554102194073e-05,
"loss": 0.8843,
"step": 421
},
{
"epoch": 0.44,
"learning_rate": 1.2310451724319116e-05,
"loss": 0.8218,
"step": 422
},
{
"epoch": 0.44,
"learning_rate": 1.2277322579867961e-05,
"loss": 0.8572,
"step": 423
},
{
"epoch": 0.45,
"learning_rate": 1.2244167052641651e-05,
"loss": 0.8322,
"step": 424
},
{
"epoch": 0.45,
"learning_rate": 1.2210985526746862e-05,
"loss": 0.889,
"step": 425
},
{
"epoch": 0.45,
"learning_rate": 1.2177778386591475e-05,
"loss": 0.8754,
"step": 426
},
{
"epoch": 0.45,
"learning_rate": 1.2144546016880104e-05,
"loss": 0.8597,
"step": 427
},
{
"epoch": 0.45,
"learning_rate": 1.2111288802609653e-05,
"loss": 0.8294,
"step": 428
},
{
"epoch": 0.45,
"learning_rate": 1.2078007129064846e-05,
"loss": 0.8287,
"step": 429
},
{
"epoch": 0.45,
"learning_rate": 1.2044701381813775e-05,
"loss": 0.8463,
"step": 430
},
{
"epoch": 0.45,
"learning_rate": 1.2011371946703416e-05,
"loss": 0.8706,
"step": 431
},
{
"epoch": 0.45,
"learning_rate": 1.1978019209855174e-05,
"loss": 0.8289,
"step": 432
},
{
"epoch": 0.45,
"learning_rate": 1.1944643557660404e-05,
"loss": 0.8511,
"step": 433
},
{
"epoch": 0.46,
"learning_rate": 1.1911245376775937e-05,
"loss": 0.86,
"step": 434
},
{
"epoch": 0.46,
"learning_rate": 1.1877825054119596e-05,
"loss": 0.8405,
"step": 435
},
{
"epoch": 0.46,
"learning_rate": 1.1844382976865714e-05,
"loss": 0.8384,
"step": 436
},
{
"epoch": 0.46,
"learning_rate": 1.181091953244066e-05,
"loss": 0.8417,
"step": 437
},
{
"epoch": 0.46,
"learning_rate": 1.177743510851833e-05,
"loss": 0.866,
"step": 438
},
{
"epoch": 0.46,
"learning_rate": 1.1743930093015676e-05,
"loss": 0.8308,
"step": 439
},
{
"epoch": 0.46,
"learning_rate": 1.1710404874088204e-05,
"loss": 0.8339,
"step": 440
},
{
"epoch": 0.46,
"learning_rate": 1.1676859840125468e-05,
"loss": 0.819,
"step": 441
},
{
"epoch": 0.46,
"learning_rate": 1.1643295379746587e-05,
"loss": 0.862,
"step": 442
},
{
"epoch": 0.47,
"learning_rate": 1.1609711881795732e-05,
"loss": 0.8523,
"step": 443
},
{
"epoch": 0.47,
"learning_rate": 1.1576109735337622e-05,
"loss": 0.8362,
"step": 444
},
{
"epoch": 0.47,
"learning_rate": 1.1542489329653024e-05,
"loss": 0.8549,
"step": 445
},
{
"epoch": 0.47,
"learning_rate": 1.1508851054234236e-05,
"loss": 0.8595,
"step": 446
},
{
"epoch": 0.47,
"learning_rate": 1.1475195298780577e-05,
"loss": 0.836,
"step": 447
},
{
"epoch": 0.47,
"learning_rate": 1.144152245319387e-05,
"loss": 0.828,
"step": 448
},
{
"epoch": 0.47,
"learning_rate": 1.140783290757393e-05,
"loss": 0.8365,
"step": 449
},
{
"epoch": 0.47,
"learning_rate": 1.1374127052214037e-05,
"loss": 0.8796,
"step": 450
},
{
"epoch": 0.47,
"learning_rate": 1.1340405277596427e-05,
"loss": 0.8377,
"step": 451
},
{
"epoch": 0.47,
"learning_rate": 1.1306667974387752e-05,
"loss": 0.8142,
"step": 452
},
{
"epoch": 0.48,
"learning_rate": 1.1272915533434572e-05,
"loss": 0.8453,
"step": 453
},
{
"epoch": 0.48,
"learning_rate": 1.123914834575881e-05,
"loss": 0.8779,
"step": 454
},
{
"epoch": 0.48,
"learning_rate": 1.1205366802553231e-05,
"loss": 0.8371,
"step": 455
},
{
"epoch": 0.48,
"learning_rate": 1.1171571295176915e-05,
"loss": 0.8313,
"step": 456
},
{
"epoch": 0.48,
"learning_rate": 1.1137762215150707e-05,
"loss": 0.8824,
"step": 457
},
{
"epoch": 0.48,
"learning_rate": 1.11039399541527e-05,
"loss": 0.8107,
"step": 458
},
{
"epoch": 0.48,
"learning_rate": 1.107010490401368e-05,
"loss": 0.7822,
"step": 459
},
{
"epoch": 0.48,
"learning_rate": 1.1036257456712607e-05,
"loss": 0.8537,
"step": 460
},
{
"epoch": 0.48,
"learning_rate": 1.1002398004372048e-05,
"loss": 0.8011,
"step": 461
},
{
"epoch": 0.49,
"learning_rate": 1.096852693925366e-05,
"loss": 0.8544,
"step": 462
},
{
"epoch": 0.49,
"learning_rate": 1.0934644653753626e-05,
"loss": 0.7755,
"step": 463
},
{
"epoch": 0.49,
"learning_rate": 1.0900751540398127e-05,
"loss": 0.8552,
"step": 464
},
{
"epoch": 0.49,
"learning_rate": 1.0866847991838767e-05,
"loss": 0.743,
"step": 465
},
{
"epoch": 0.49,
"learning_rate": 1.0832934400848063e-05,
"loss": 0.8419,
"step": 466
},
{
"epoch": 0.49,
"learning_rate": 1.0799011160314856e-05,
"loss": 0.8303,
"step": 467
},
{
"epoch": 0.49,
"learning_rate": 1.0765078663239792e-05,
"loss": 0.8581,
"step": 468
},
{
"epoch": 0.49,
"learning_rate": 1.0731137302730738e-05,
"loss": 0.8176,
"step": 469
},
{
"epoch": 0.49,
"learning_rate": 1.069718747199826e-05,
"loss": 0.8296,
"step": 470
},
{
"epoch": 0.49,
"learning_rate": 1.066322956435104e-05,
"loss": 0.8114,
"step": 471
},
{
"epoch": 0.5,
"learning_rate": 1.0629263973191338e-05,
"loss": 0.7989,
"step": 472
},
{
"epoch": 0.5,
"learning_rate": 1.0595291092010416e-05,
"loss": 0.83,
"step": 473
},
{
"epoch": 0.5,
"learning_rate": 1.0561311314384007e-05,
"loss": 0.8857,
"step": 474
},
{
"epoch": 0.5,
"learning_rate": 1.0527325033967725e-05,
"loss": 0.8505,
"step": 475
},
{
"epoch": 0.5,
"learning_rate": 1.0493332644492534e-05,
"loss": 0.8672,
"step": 476
},
{
"epoch": 0.5,
"learning_rate": 1.0459334539760156e-05,
"loss": 0.8119,
"step": 477
},
{
"epoch": 0.5,
"learning_rate": 1.0425331113638528e-05,
"loss": 0.8186,
"step": 478
},
{
"epoch": 0.5,
"learning_rate": 1.039132276005725e-05,
"loss": 0.877,
"step": 479
},
{
"epoch": 0.5,
"learning_rate": 1.0357309873002984e-05,
"loss": 0.8155,
"step": 480
},
{
"epoch": 0.51,
"learning_rate": 1.0323292846514927e-05,
"loss": 0.7974,
"step": 481
},
{
"epoch": 0.51,
"learning_rate": 1.0289272074680225e-05,
"loss": 0.8595,
"step": 482
},
{
"epoch": 0.51,
"learning_rate": 1.0255247951629419e-05,
"loss": 0.8408,
"step": 483
},
{
"epoch": 0.51,
"learning_rate": 1.022122087153187e-05,
"loss": 0.8401,
"step": 484
},
{
"epoch": 0.51,
"learning_rate": 1.0187191228591197e-05,
"loss": 0.8336,
"step": 485
},
{
"epoch": 0.51,
"learning_rate": 1.015315941704071e-05,
"loss": 0.8418,
"step": 486
},
{
"epoch": 0.51,
"learning_rate": 1.0119125831138848e-05,
"loss": 0.8316,
"step": 487
},
{
"epoch": 0.51,
"learning_rate": 1.0085090865164589e-05,
"loss": 0.8007,
"step": 488
},
{
"epoch": 0.51,
"learning_rate": 1.0051054913412919e-05,
"loss": 0.7921,
"step": 489
},
{
"epoch": 0.51,
"learning_rate": 1.0017018370190229e-05,
"loss": 0.8221,
"step": 490
},
{
"epoch": 0.52,
"learning_rate": 9.982981629809776e-06,
"loss": 0.7997,
"step": 491
},
{
"epoch": 0.52,
"learning_rate": 9.948945086587088e-06,
"loss": 0.8091,
"step": 492
},
{
"epoch": 0.52,
"learning_rate": 9.914909134835416e-06,
"loss": 0.8277,
"step": 493
},
{
"epoch": 0.52,
"learning_rate": 9.880874168861157e-06,
"loss": 0.7936,
"step": 494
},
{
"epoch": 0.52,
"learning_rate": 9.846840582959292e-06,
"loss": 0.795,
"step": 495
},
{
"epoch": 0.52,
"learning_rate": 9.812808771408804e-06,
"loss": 0.8259,
"step": 496
},
{
"epoch": 0.52,
"learning_rate": 9.778779128468133e-06,
"loss": 0.8109,
"step": 497
},
{
"epoch": 0.52,
"learning_rate": 9.744752048370583e-06,
"loss": 0.7941,
"step": 498
},
{
"epoch": 0.52,
"learning_rate": 9.710727925319778e-06,
"loss": 0.7929,
"step": 499
},
{
"epoch": 0.53,
"learning_rate": 9.676707153485076e-06,
"loss": 0.8219,
"step": 500
},
{
"epoch": 0.53,
"learning_rate": 9.64269012699702e-06,
"loss": 0.819,
"step": 501
},
{
"epoch": 0.53,
"learning_rate": 9.608677239942754e-06,
"loss": 0.8312,
"step": 502
},
{
"epoch": 0.53,
"learning_rate": 9.57466888636147e-06,
"loss": 0.8053,
"step": 503
},
{
"epoch": 0.53,
"learning_rate": 9.540665460239849e-06,
"loss": 0.8275,
"step": 504
},
{
"epoch": 0.53,
"learning_rate": 9.506667355507468e-06,
"loss": 0.7918,
"step": 505
},
{
"epoch": 0.53,
"learning_rate": 9.472674966032276e-06,
"loss": 0.8565,
"step": 506
},
{
"epoch": 0.53,
"learning_rate": 9.438688685616e-06,
"loss": 0.8018,
"step": 507
},
{
"epoch": 0.53,
"learning_rate": 9.404708907989589e-06,
"loss": 0.8031,
"step": 508
},
{
"epoch": 0.53,
"learning_rate": 9.370736026808669e-06,
"loss": 0.7691,
"step": 509
},
{
"epoch": 0.54,
"learning_rate": 9.336770435648963e-06,
"loss": 0.8393,
"step": 510
},
{
"epoch": 0.54,
"learning_rate": 9.302812528001741e-06,
"loss": 0.7475,
"step": 511
},
{
"epoch": 0.54,
"learning_rate": 9.268862697269263e-06,
"loss": 0.8163,
"step": 512
},
{
"epoch": 0.54,
"learning_rate": 9.234921336760211e-06,
"loss": 0.8269,
"step": 513
},
{
"epoch": 0.54,
"learning_rate": 9.200988839685146e-06,
"loss": 0.8131,
"step": 514
},
{
"epoch": 0.54,
"learning_rate": 9.16706559915194e-06,
"loss": 0.7913,
"step": 515
},
{
"epoch": 0.54,
"learning_rate": 9.133152008161235e-06,
"loss": 0.8114,
"step": 516
},
{
"epoch": 0.54,
"learning_rate": 9.099248459601877e-06,
"loss": 0.7985,
"step": 517
},
{
"epoch": 0.54,
"learning_rate": 9.065355346246376e-06,
"loss": 0.8249,
"step": 518
},
{
"epoch": 0.55,
"learning_rate": 9.031473060746341e-06,
"loss": 0.8301,
"step": 519
},
{
"epoch": 0.55,
"learning_rate": 8.997601995627952e-06,
"loss": 0.8373,
"step": 520
},
{
"epoch": 0.55,
"learning_rate": 8.963742543287397e-06,
"loss": 0.7947,
"step": 521
},
{
"epoch": 0.55,
"learning_rate": 8.929895095986324e-06,
"loss": 0.8167,
"step": 522
},
{
"epoch": 0.55,
"learning_rate": 8.896060045847305e-06,
"loss": 0.7894,
"step": 523
},
{
"epoch": 0.55,
"learning_rate": 8.862237784849298e-06,
"loss": 0.8054,
"step": 524
},
{
"epoch": 0.55,
"learning_rate": 8.828428704823088e-06,
"loss": 0.8087,
"step": 525
},
{
"epoch": 0.55,
"learning_rate": 8.79463319744677e-06,
"loss": 0.8025,
"step": 526
},
{
"epoch": 0.55,
"learning_rate": 8.760851654241193e-06,
"loss": 0.8394,
"step": 527
},
{
"epoch": 0.55,
"learning_rate": 8.72708446656543e-06,
"loss": 0.8013,
"step": 528
},
{
"epoch": 0.56,
"learning_rate": 8.693332025612251e-06,
"loss": 0.8488,
"step": 529
},
{
"epoch": 0.56,
"learning_rate": 8.659594722403577e-06,
"loss": 0.8512,
"step": 530
},
{
"epoch": 0.56,
"learning_rate": 8.625872947785968e-06,
"loss": 0.819,
"step": 531
},
{
"epoch": 0.56,
"learning_rate": 8.592167092426074e-06,
"loss": 0.7762,
"step": 532
},
{
"epoch": 0.56,
"learning_rate": 8.558477546806132e-06,
"loss": 0.8136,
"step": 533
},
{
"epoch": 0.56,
"learning_rate": 8.524804701219423e-06,
"loss": 0.7847,
"step": 534
},
{
"epoch": 0.56,
"learning_rate": 8.491148945765764e-06,
"loss": 0.7729,
"step": 535
},
{
"epoch": 0.56,
"learning_rate": 8.457510670346976e-06,
"loss": 0.8582,
"step": 536
},
{
"epoch": 0.56,
"learning_rate": 8.42389026466238e-06,
"loss": 0.8775,
"step": 537
},
{
"epoch": 0.57,
"learning_rate": 8.390288118204275e-06,
"loss": 0.8378,
"step": 538
},
{
"epoch": 0.57,
"learning_rate": 8.35670462025342e-06,
"loss": 0.8636,
"step": 539
},
{
"epoch": 0.57,
"learning_rate": 8.323140159874536e-06,
"loss": 0.8145,
"step": 540
},
{
"epoch": 0.57,
"learning_rate": 8.2895951259118e-06,
"loss": 0.824,
"step": 541
},
{
"epoch": 0.57,
"learning_rate": 8.256069906984325e-06,
"loss": 0.797,
"step": 542
},
{
"epoch": 0.57,
"learning_rate": 8.222564891481675e-06,
"loss": 0.8032,
"step": 543
},
{
"epoch": 0.57,
"learning_rate": 8.189080467559344e-06,
"loss": 0.7925,
"step": 544
},
{
"epoch": 0.57,
"learning_rate": 8.15561702313429e-06,
"loss": 0.7643,
"step": 545
},
{
"epoch": 0.57,
"learning_rate": 8.122174945880409e-06,
"loss": 0.8497,
"step": 546
},
{
"epoch": 0.57,
"learning_rate": 8.088754623224066e-06,
"loss": 0.7635,
"step": 547
},
{
"epoch": 0.58,
"learning_rate": 8.0553564423396e-06,
"loss": 0.7996,
"step": 548
},
{
"epoch": 0.58,
"learning_rate": 8.021980790144828e-06,
"loss": 0.8162,
"step": 549
},
{
"epoch": 0.58,
"learning_rate": 7.988628053296587e-06,
"loss": 0.7731,
"step": 550
},
{
"epoch": 0.58,
"learning_rate": 7.955298618186227e-06,
"loss": 0.7893,
"step": 551
},
{
"epoch": 0.58,
"learning_rate": 7.921992870935154e-06,
"loss": 0.8463,
"step": 552
},
{
"epoch": 0.58,
"learning_rate": 7.888711197390349e-06,
"loss": 0.7943,
"step": 553
},
{
"epoch": 0.58,
"learning_rate": 7.855453983119901e-06,
"loss": 0.7759,
"step": 554
},
{
"epoch": 0.58,
"learning_rate": 7.82222161340853e-06,
"loss": 0.7992,
"step": 555
},
{
"epoch": 0.58,
"learning_rate": 7.78901447325314e-06,
"loss": 0.8094,
"step": 556
},
{
"epoch": 0.59,
"learning_rate": 7.755832947358352e-06,
"loss": 0.783,
"step": 557
},
{
"epoch": 0.59,
"learning_rate": 7.722677420132042e-06,
"loss": 0.8027,
"step": 558
},
{
"epoch": 0.59,
"learning_rate": 7.689548275680887e-06,
"loss": 0.7855,
"step": 559
},
{
"epoch": 0.59,
"learning_rate": 7.65644589780593e-06,
"loss": 0.7889,
"step": 560
},
{
"epoch": 0.59,
"learning_rate": 7.623370669998115e-06,
"loss": 0.8369,
"step": 561
},
{
"epoch": 0.59,
"learning_rate": 7.590322975433857e-06,
"loss": 0.8021,
"step": 562
},
{
"epoch": 0.59,
"learning_rate": 7.557303196970595e-06,
"loss": 0.8077,
"step": 563
},
{
"epoch": 0.59,
"learning_rate": 7.524311717142368e-06,
"loss": 0.8196,
"step": 564
},
{
"epoch": 0.59,
"learning_rate": 7.4913489181553615e-06,
"loss": 0.7782,
"step": 565
},
{
"epoch": 0.59,
"learning_rate": 7.458415181883506e-06,
"loss": 0.7863,
"step": 566
},
{
"epoch": 0.6,
"learning_rate": 7.425510889864036e-06,
"loss": 0.7778,
"step": 567
},
{
"epoch": 0.6,
"learning_rate": 7.3926364232930715e-06,
"loss": 0.7774,
"step": 568
},
{
"epoch": 0.6,
"learning_rate": 7.359792163021213e-06,
"loss": 0.8353,
"step": 569
},
{
"epoch": 0.6,
"learning_rate": 7.32697848954911e-06,
"loss": 0.8393,
"step": 570
},
{
"epoch": 0.6,
"learning_rate": 7.294195783023072e-06,
"loss": 0.8085,
"step": 571
},
{
"epoch": 0.6,
"learning_rate": 7.261444423230656e-06,
"loss": 0.7916,
"step": 572
},
{
"epoch": 0.6,
"learning_rate": 7.228724789596262e-06,
"loss": 0.7942,
"step": 573
},
{
"epoch": 0.6,
"learning_rate": 7.196037261176749e-06,
"loss": 0.8389,
"step": 574
},
{
"epoch": 0.6,
"learning_rate": 7.163382216657033e-06,
"loss": 0.7917,
"step": 575
},
{
"epoch": 0.61,
"learning_rate": 7.130760034345708e-06,
"loss": 0.8008,
"step": 576
},
{
"epoch": 0.61,
"learning_rate": 7.098171092170655e-06,
"loss": 0.7941,
"step": 577
},
{
"epoch": 0.61,
"learning_rate": 7.0656157676746675e-06,
"loss": 0.7928,
"step": 578
},
{
"epoch": 0.61,
"learning_rate": 7.033094438011084e-06,
"loss": 0.811,
"step": 579
},
{
"epoch": 0.61,
"learning_rate": 7.000607479939408e-06,
"loss": 0.8007,
"step": 580
},
{
"epoch": 0.61,
"learning_rate": 6.968155269820951e-06,
"loss": 0.7568,
"step": 581
},
{
"epoch": 0.61,
"learning_rate": 6.935738183614467e-06,
"loss": 0.8556,
"step": 582
},
{
"epoch": 0.61,
"learning_rate": 6.903356596871804e-06,
"loss": 0.819,
"step": 583
},
{
"epoch": 0.61,
"learning_rate": 6.8710108847335424e-06,
"loss": 0.8194,
"step": 584
},
{
"epoch": 0.61,
"learning_rate": 6.838701421924665e-06,
"loss": 0.7956,
"step": 585
},
{
"epoch": 0.62,
"learning_rate": 6.806428582750191e-06,
"loss": 0.7802,
"step": 586
},
{
"epoch": 0.62,
"learning_rate": 6.774192741090871e-06,
"loss": 0.8087,
"step": 587
},
{
"epoch": 0.62,
"learning_rate": 6.741994270398826e-06,
"loss": 0.7939,
"step": 588
},
{
"epoch": 0.62,
"learning_rate": 6.709833543693249e-06,
"loss": 0.8262,
"step": 589
},
{
"epoch": 0.62,
"learning_rate": 6.6777109335560545e-06,
"loss": 0.7782,
"step": 590
},
{
"epoch": 0.62,
"learning_rate": 6.645626812127588e-06,
"loss": 0.8571,
"step": 591
},
{
"epoch": 0.62,
"learning_rate": 6.613581551102295e-06,
"loss": 0.8077,
"step": 592
},
{
"epoch": 0.62,
"learning_rate": 6.58157552172443e-06,
"loss": 0.8019,
"step": 593
},
{
"epoch": 0.62,
"learning_rate": 6.549609094783744e-06,
"loss": 0.7748,
"step": 594
},
{
"epoch": 0.62,
"learning_rate": 6.517682640611196e-06,
"loss": 0.8003,
"step": 595
},
{
"epoch": 0.63,
"learning_rate": 6.485796529074662e-06,
"loss": 0.7943,
"step": 596
},
{
"epoch": 0.63,
"learning_rate": 6.453951129574644e-06,
"loss": 0.7831,
"step": 597
},
{
"epoch": 0.63,
"learning_rate": 6.422146811040002e-06,
"loss": 0.8134,
"step": 598
},
{
"epoch": 0.63,
"learning_rate": 6.390383941923666e-06,
"loss": 0.7987,
"step": 599
},
{
"epoch": 0.63,
"learning_rate": 6.358662890198379e-06,
"loss": 0.8115,
"step": 600
},
{
"epoch": 0.63,
"learning_rate": 6.326984023352435e-06,
"loss": 0.8447,
"step": 601
},
{
"epoch": 0.63,
"learning_rate": 6.295347708385399e-06,
"loss": 0.8526,
"step": 602
},
{
"epoch": 0.63,
"learning_rate": 6.263754311803891e-06,
"loss": 0.7649,
"step": 603
},
{
"epoch": 0.63,
"learning_rate": 6.232204199617313e-06,
"loss": 0.7528,
"step": 604
},
{
"epoch": 0.64,
"learning_rate": 6.200697737333615e-06,
"loss": 0.7861,
"step": 605
},
{
"epoch": 0.64,
"learning_rate": 6.169235289955073e-06,
"loss": 0.8455,
"step": 606
},
{
"epoch": 0.64,
"learning_rate": 6.1378172219740375e-06,
"loss": 0.7976,
"step": 607
},
{
"epoch": 0.64,
"learning_rate": 6.106443897368737e-06,
"loss": 0.8238,
"step": 608
},
{
"epoch": 0.64,
"learning_rate": 6.0751156795990356e-06,
"loss": 0.7804,
"step": 609
},
{
"epoch": 0.64,
"learning_rate": 6.043832931602244e-06,
"loss": 0.7915,
"step": 610
},
{
"epoch": 0.64,
"learning_rate": 6.012596015788903e-06,
"loss": 0.81,
"step": 611
},
{
"epoch": 0.64,
"learning_rate": 5.981405294038588e-06,
"loss": 0.8264,
"step": 612
},
{
"epoch": 0.64,
"learning_rate": 5.950261127695711e-06,
"loss": 0.7947,
"step": 613
},
{
"epoch": 0.64,
"learning_rate": 5.919163877565351e-06,
"loss": 0.7725,
"step": 614
},
{
"epoch": 0.65,
"learning_rate": 5.8881139039090516e-06,
"loss": 0.8564,
"step": 615
},
{
"epoch": 0.65,
"learning_rate": 5.8571115664406655e-06,
"loss": 0.8267,
"step": 616
},
{
"epoch": 0.65,
"learning_rate": 5.826157224322173e-06,
"loss": 0.7965,
"step": 617
},
{
"epoch": 0.65,
"learning_rate": 5.795251236159538e-06,
"loss": 0.8019,
"step": 618
},
{
"epoch": 0.65,
"learning_rate": 5.76439395999854e-06,
"loss": 0.8606,
"step": 619
},
{
"epoch": 0.65,
"learning_rate": 5.733585753320623e-06,
"loss": 0.8314,
"step": 620
},
{
"epoch": 0.65,
"learning_rate": 5.702826973038776e-06,
"loss": 0.7428,
"step": 621
},
{
"epoch": 0.65,
"learning_rate": 5.6721179754933695e-06,
"loss": 0.7841,
"step": 622
},
{
"epoch": 0.65,
"learning_rate": 5.6414591164480495e-06,
"loss": 0.7545,
"step": 623
},
{
"epoch": 0.66,
"learning_rate": 5.610850751085603e-06,
"loss": 0.73,
"step": 624
},
{
"epoch": 0.66,
"learning_rate": 5.5802932340038485e-06,
"loss": 0.7598,
"step": 625
},
{
"epoch": 0.66,
"learning_rate": 5.549786919211532e-06,
"loss": 0.8192,
"step": 626
},
{
"epoch": 0.66,
"learning_rate": 5.519332160124215e-06,
"loss": 0.7913,
"step": 627
},
{
"epoch": 0.66,
"learning_rate": 5.488929309560192e-06,
"loss": 0.7636,
"step": 628
},
{
"epoch": 0.66,
"learning_rate": 5.458578719736387e-06,
"loss": 0.821,
"step": 629
},
{
"epoch": 0.66,
"learning_rate": 5.428280742264298e-06,
"loss": 0.7761,
"step": 630
},
{
"epoch": 0.66,
"learning_rate": 5.3980357281459e-06,
"loss": 0.8316,
"step": 631
},
{
"epoch": 0.66,
"learning_rate": 5.367844027769593e-06,
"loss": 0.8268,
"step": 632
},
{
"epoch": 0.66,
"learning_rate": 5.3377059909061225e-06,
"loss": 0.7493,
"step": 633
},
{
"epoch": 0.67,
"learning_rate": 5.307621966704564e-06,
"loss": 0.7504,
"step": 634
},
{
"epoch": 0.67,
"learning_rate": 5.2775923036882446e-06,
"loss": 0.7969,
"step": 635
},
{
"epoch": 0.67,
"learning_rate": 5.247617349750717e-06,
"loss": 0.7982,
"step": 636
},
{
"epoch": 0.67,
"learning_rate": 5.217697452151729e-06,
"loss": 0.7528,
"step": 637
},
{
"epoch": 0.67,
"learning_rate": 5.18783295751321e-06,
"loss": 0.8039,
"step": 638
},
{
"epoch": 0.67,
"learning_rate": 5.158024211815238e-06,
"loss": 0.7615,
"step": 639
},
{
"epoch": 0.67,
"learning_rate": 5.128271560392037e-06,
"loss": 0.8113,
"step": 640
},
{
"epoch": 0.67,
"learning_rate": 5.0985753479279824e-06,
"loss": 0.7893,
"step": 641
},
{
"epoch": 0.67,
"learning_rate": 5.068935918453612e-06,
"loss": 0.7665,
"step": 642
},
{
"epoch": 0.68,
"learning_rate": 5.039353615341622e-06,
"loss": 0.7452,
"step": 643
},
{
"epoch": 0.68,
"learning_rate": 5.009828781302906e-06,
"loss": 0.8034,
"step": 644
},
{
"epoch": 0.68,
"learning_rate": 4.980361758382573e-06,
"loss": 0.7867,
"step": 645
},
{
"epoch": 0.68,
"learning_rate": 4.950952887955992e-06,
"loss": 0.8103,
"step": 646
},
{
"epoch": 0.68,
"learning_rate": 4.92160251072485e-06,
"loss": 0.7684,
"step": 647
},
{
"epoch": 0.68,
"learning_rate": 4.892310966713164e-06,
"loss": 0.7814,
"step": 648
},
{
"epoch": 0.68,
"learning_rate": 4.8630785952633845e-06,
"loss": 0.7614,
"step": 649
},
{
"epoch": 0.68,
"learning_rate": 4.833905735032451e-06,
"loss": 0.7557,
"step": 650
},
{
"epoch": 0.68,
"learning_rate": 4.80479272398786e-06,
"loss": 0.7658,
"step": 651
},
{
"epoch": 0.68,
"learning_rate": 4.7757398994037525e-06,
"loss": 0.7733,
"step": 652
},
{
"epoch": 0.69,
"learning_rate": 4.746747597857014e-06,
"loss": 0.7483,
"step": 653
},
{
"epoch": 0.69,
"learning_rate": 4.717816155223368e-06,
"loss": 0.7261,
"step": 654
},
{
"epoch": 0.69,
"learning_rate": 4.688945906673494e-06,
"loss": 0.8251,
"step": 655
},
{
"epoch": 0.69,
"learning_rate": 4.660137186669131e-06,
"loss": 0.7426,
"step": 656
},
{
"epoch": 0.69,
"learning_rate": 4.631390328959213e-06,
"loss": 0.8215,
"step": 657
},
{
"epoch": 0.69,
"learning_rate": 4.602705666575995e-06,
"loss": 0.7854,
"step": 658
},
{
"epoch": 0.69,
"learning_rate": 4.574083531831212e-06,
"loss": 0.7843,
"step": 659
},
{
"epoch": 0.69,
"learning_rate": 4.545524256312202e-06,
"loss": 0.8117,
"step": 660
},
{
"epoch": 0.69,
"learning_rate": 4.5170281708780865e-06,
"loss": 0.7718,
"step": 661
},
{
"epoch": 0.7,
"learning_rate": 4.488595605655927e-06,
"loss": 0.8086,
"step": 662
},
{
"epoch": 0.7,
"learning_rate": 4.460226890036907e-06,
"loss": 0.7513,
"step": 663
},
{
"epoch": 0.7,
"learning_rate": 4.43192235267251e-06,
"loss": 0.7575,
"step": 664
},
{
"epoch": 0.7,
"learning_rate": 4.4036823214707144e-06,
"loss": 0.7645,
"step": 665
},
{
"epoch": 0.7,
"learning_rate": 4.375507123592194e-06,
"loss": 0.7651,
"step": 666
},
{
"epoch": 0.7,
"learning_rate": 4.347397085446537e-06,
"loss": 0.8218,
"step": 667
},
{
"epoch": 0.7,
"learning_rate": 4.319352532688444e-06,
"loss": 0.8144,
"step": 668
},
{
"epoch": 0.7,
"learning_rate": 4.291373790213975e-06,
"loss": 0.7774,
"step": 669
},
{
"epoch": 0.7,
"learning_rate": 4.263461182156777e-06,
"loss": 0.759,
"step": 670
},
{
"epoch": 0.7,
"learning_rate": 4.235615031884326e-06,
"loss": 0.7323,
"step": 671
},
{
"epoch": 0.71,
"learning_rate": 4.207835661994195e-06,
"loss": 0.7652,
"step": 672
},
{
"epoch": 0.71,
"learning_rate": 4.180123394310294e-06,
"loss": 0.7781,
"step": 673
},
{
"epoch": 0.71,
"learning_rate": 4.152478549879164e-06,
"loss": 0.7693,
"step": 674
},
{
"epoch": 0.71,
"learning_rate": 4.124901448966236e-06,
"loss": 0.7745,
"step": 675
},
{
"epoch": 0.71,
"learning_rate": 4.097392411052149e-06,
"loss": 0.803,
"step": 676
},
{
"epoch": 0.71,
"learning_rate": 4.06995175482902e-06,
"loss": 0.8066,
"step": 677
},
{
"epoch": 0.71,
"learning_rate": 4.042579798196768e-06,
"loss": 0.7811,
"step": 678
},
{
"epoch": 0.71,
"learning_rate": 4.015276858259427e-06,
"loss": 0.7734,
"step": 679
},
{
"epoch": 0.71,
"learning_rate": 3.988043251321474e-06,
"loss": 0.8184,
"step": 680
},
{
"epoch": 0.72,
"learning_rate": 3.9608792928841596e-06,
"loss": 0.7621,
"step": 681
},
{
"epoch": 0.72,
"learning_rate": 3.933785297641864e-06,
"loss": 0.7728,
"step": 682
},
{
"epoch": 0.72,
"learning_rate": 3.906761579478432e-06,
"loss": 0.777,
"step": 683
},
{
"epoch": 0.72,
"learning_rate": 3.879808451463566e-06,
"loss": 0.7806,
"step": 684
},
{
"epoch": 0.72,
"learning_rate": 3.852926225849167e-06,
"loss": 0.8012,
"step": 685
},
{
"epoch": 0.72,
"learning_rate": 3.826115214065739e-06,
"loss": 0.7978,
"step": 686
},
{
"epoch": 0.72,
"learning_rate": 3.7993757267187657e-06,
"loss": 0.7909,
"step": 687
},
{
"epoch": 0.72,
"learning_rate": 3.7727080735851353e-06,
"loss": 0.7785,
"step": 688
},
{
"epoch": 0.72,
"learning_rate": 3.746112563609524e-06,
"loss": 0.7404,
"step": 689
},
{
"epoch": 0.72,
"learning_rate": 3.7195895049008356e-06,
"loss": 0.7872,
"step": 690
},
{
"epoch": 0.73,
"learning_rate": 3.693139204728623e-06,
"loss": 0.7729,
"step": 691
},
{
"epoch": 0.73,
"learning_rate": 3.6667619695195287e-06,
"loss": 0.721,
"step": 692
},
{
"epoch": 0.73,
"learning_rate": 3.6404581048537522e-06,
"loss": 0.752,
"step": 693
},
{
"epoch": 0.73,
"learning_rate": 3.6142279154614832e-06,
"loss": 0.7235,
"step": 694
},
{
"epoch": 0.73,
"learning_rate": 3.588071705219377e-06,
"loss": 0.8177,
"step": 695
},
{
"epoch": 0.73,
"learning_rate": 3.561989777147059e-06,
"loss": 0.7329,
"step": 696
},
{
"epoch": 0.73,
"learning_rate": 3.5359824334035843e-06,
"loss": 0.7705,
"step": 697
},
{
"epoch": 0.73,
"learning_rate": 3.510049975283949e-06,
"loss": 0.8517,
"step": 698
},
{
"epoch": 0.73,
"learning_rate": 3.4841927032156033e-06,
"loss": 0.7825,
"step": 699
},
{
"epoch": 0.74,
"learning_rate": 3.4584109167549617e-06,
"loss": 0.7846,
"step": 700
},
{
"epoch": 0.74,
"learning_rate": 3.4327049145839496e-06,
"loss": 0.7851,
"step": 701
},
{
"epoch": 0.74,
"learning_rate": 3.4070749945065186e-06,
"loss": 0.7798,
"step": 702
},
{
"epoch": 0.74,
"learning_rate": 3.3815214534452157e-06,
"loss": 0.7855,
"step": 703
},
{
"epoch": 0.74,
"learning_rate": 3.3560445874377324e-06,
"loss": 0.7482,
"step": 704
},
{
"epoch": 0.74,
"learning_rate": 3.330644691633492e-06,
"loss": 0.7842,
"step": 705
},
{
"epoch": 0.74,
"learning_rate": 3.3053220602902057e-06,
"loss": 0.7836,
"step": 706
},
{
"epoch": 0.74,
"learning_rate": 3.2800769867704805e-06,
"loss": 0.7779,
"step": 707
},
{
"epoch": 0.74,
"learning_rate": 3.2549097635384177e-06,
"loss": 0.7858,
"step": 708
},
{
"epoch": 0.74,
"learning_rate": 3.2298206821562173e-06,
"loss": 0.7535,
"step": 709
},
{
"epoch": 0.75,
"learning_rate": 3.2048100332808195e-06,
"loss": 0.7866,
"step": 710
},
{
"epoch": 0.75,
"learning_rate": 3.1798781066605076e-06,
"loss": 0.7473,
"step": 711
},
{
"epoch": 0.75,
"learning_rate": 3.1550251911315754e-06,
"loss": 0.7914,
"step": 712
},
{
"epoch": 0.75,
"learning_rate": 3.1302515746149796e-06,
"loss": 0.7531,
"step": 713
},
{
"epoch": 0.75,
"learning_rate": 3.1055575441129892e-06,
"loss": 0.7663,
"step": 714
},
{
"epoch": 0.75,
"learning_rate": 3.0809433857058713e-06,
"loss": 0.7665,
"step": 715
},
{
"epoch": 0.75,
"learning_rate": 3.056409384548575e-06,
"loss": 0.7531,
"step": 716
},
{
"epoch": 0.75,
"learning_rate": 3.031955824867434e-06,
"loss": 0.7424,
"step": 717
},
{
"epoch": 0.75,
"learning_rate": 3.00758298995686e-06,
"loss": 0.7785,
"step": 718
},
{
"epoch": 0.76,
"learning_rate": 2.9832911621760717e-06,
"loss": 0.8011,
"step": 719
},
{
"epoch": 0.76,
"learning_rate": 2.959080622945819e-06,
"loss": 0.7762,
"step": 720
},
{
"epoch": 0.76,
"learning_rate": 2.934951652745123e-06,
"loss": 0.7517,
"step": 721
},
{
"epoch": 0.76,
"learning_rate": 2.9109045311080352e-06,
"loss": 0.7417,
"step": 722
},
{
"epoch": 0.76,
"learning_rate": 2.8869395366203857e-06,
"loss": 0.7692,
"step": 723
},
{
"epoch": 0.76,
"learning_rate": 2.8630569469165604e-06,
"loss": 0.7373,
"step": 724
},
{
"epoch": 0.76,
"learning_rate": 2.8392570386762862e-06,
"loss": 0.7246,
"step": 725
},
{
"epoch": 0.76,
"learning_rate": 2.8155400876214365e-06,
"loss": 0.802,
"step": 726
},
{
"epoch": 0.76,
"learning_rate": 2.791906368512809e-06,
"loss": 0.7956,
"step": 727
},
{
"epoch": 0.76,
"learning_rate": 2.7683561551469695e-06,
"loss": 0.7633,
"step": 728
},
{
"epoch": 0.77,
"learning_rate": 2.7448897203530655e-06,
"loss": 0.7778,
"step": 729
},
{
"epoch": 0.77,
"learning_rate": 2.7215073359896794e-06,
"loss": 0.7592,
"step": 730
},
{
"epoch": 0.77,
"learning_rate": 2.698209272941659e-06,
"loss": 0.735,
"step": 731
},
{
"epoch": 0.77,
"learning_rate": 2.674995801116994e-06,
"loss": 0.7995,
"step": 732
},
{
"epoch": 0.77,
"learning_rate": 2.651867189443682e-06,
"loss": 0.7107,
"step": 733
},
{
"epoch": 0.77,
"learning_rate": 2.6288237058666253e-06,
"loss": 0.7491,
"step": 734
},
{
"epoch": 0.77,
"learning_rate": 2.6058656173445074e-06,
"loss": 0.7655,
"step": 735
},
{
"epoch": 0.77,
"learning_rate": 2.5829931898467143e-06,
"loss": 0.8165,
"step": 736
},
{
"epoch": 0.77,
"learning_rate": 2.5602066883502487e-06,
"loss": 0.7469,
"step": 737
},
{
"epoch": 0.78,
"learning_rate": 2.537506376836658e-06,
"loss": 0.7515,
"step": 738
},
{
"epoch": 0.78,
"learning_rate": 2.514892518288988e-06,
"loss": 0.7807,
"step": 739
},
{
"epoch": 0.78,
"learning_rate": 2.49236537468872e-06,
"loss": 0.791,
"step": 740
},
{
"epoch": 0.78,
"learning_rate": 2.469925207012741e-06,
"loss": 0.7471,
"step": 741
},
{
"epoch": 0.78,
"learning_rate": 2.4475722752303265e-06,
"loss": 0.7402,
"step": 742
},
{
"epoch": 0.78,
"learning_rate": 2.4253068383001244e-06,
"loss": 0.7498,
"step": 743
},
{
"epoch": 0.78,
"learning_rate": 2.403129154167153e-06,
"loss": 0.792,
"step": 744
},
{
"epoch": 0.78,
"learning_rate": 2.3810394797598147e-06,
"loss": 0.7582,
"step": 745
},
{
"epoch": 0.78,
"learning_rate": 2.3590380709869175e-06,
"loss": 0.7801,
"step": 746
},
{
"epoch": 0.78,
"learning_rate": 2.337125182734722e-06,
"loss": 0.7573,
"step": 747
},
{
"epoch": 0.79,
"learning_rate": 2.3153010688639687e-06,
"loss": 0.7612,
"step": 748
},
{
"epoch": 0.79,
"learning_rate": 2.29356598220695e-06,
"loss": 0.789,
"step": 749
},
{
"epoch": 0.79,
"learning_rate": 2.2719201745645758e-06,
"loss": 0.723,
"step": 750
},
{
"epoch": 0.79,
"learning_rate": 2.2503638967034668e-06,
"loss": 0.7822,
"step": 751
},
{
"epoch": 0.79,
"learning_rate": 2.228897398353035e-06,
"loss": 0.7635,
"step": 752
},
{
"epoch": 0.79,
"learning_rate": 2.207520928202599e-06,
"loss": 0.7445,
"step": 753
},
{
"epoch": 0.79,
"learning_rate": 2.1862347338984945e-06,
"loss": 0.8166,
"step": 754
},
{
"epoch": 0.79,
"learning_rate": 2.1650390620412264e-06,
"loss": 0.7509,
"step": 755
},
{
"epoch": 0.79,
"learning_rate": 2.1439341581825855e-06,
"loss": 0.783,
"step": 756
},
{
"epoch": 0.8,
"learning_rate": 2.1229202668228197e-06,
"loss": 0.7458,
"step": 757
},
{
"epoch": 0.8,
"learning_rate": 2.1019976314077904e-06,
"loss": 0.6907,
"step": 758
},
{
"epoch": 0.8,
"learning_rate": 2.0811664943261724e-06,
"loss": 0.7477,
"step": 759
},
{
"epoch": 0.8,
"learning_rate": 2.060427096906622e-06,
"loss": 0.7419,
"step": 760
},
{
"epoch": 0.8,
"learning_rate": 2.039779679414996e-06,
"loss": 0.7237,
"step": 761
},
{
"epoch": 0.8,
"learning_rate": 2.0192244810515604e-06,
"loss": 0.7198,
"step": 762
},
{
"epoch": 0.8,
"learning_rate": 1.998761739948232e-06,
"loss": 0.7531,
"step": 763
},
{
"epoch": 0.8,
"learning_rate": 1.9783916931657997e-06,
"loss": 0.7541,
"step": 764
},
{
"epoch": 0.8,
"learning_rate": 1.958114576691195e-06,
"loss": 0.7458,
"step": 765
},
{
"epoch": 0.8,
"learning_rate": 1.9379306254347487e-06,
"loss": 0.7855,
"step": 766
},
{
"epoch": 0.81,
"learning_rate": 1.917840073227475e-06,
"loss": 0.7863,
"step": 767
},
{
"epoch": 0.81,
"learning_rate": 1.8978431528183627e-06,
"loss": 0.7432,
"step": 768
},
{
"epoch": 0.81,
"learning_rate": 1.877940095871673e-06,
"loss": 0.78,
"step": 769
},
{
"epoch": 0.81,
"learning_rate": 1.8581311329642592e-06,
"loss": 0.7406,
"step": 770
},
{
"epoch": 0.81,
"learning_rate": 1.838416493582893e-06,
"loss": 0.81,
"step": 771
},
{
"epoch": 0.81,
"learning_rate": 1.818796406121619e-06,
"loss": 0.7421,
"step": 772
},
{
"epoch": 0.81,
"learning_rate": 1.7992710978790884e-06,
"loss": 0.7581,
"step": 773
},
{
"epoch": 0.81,
"learning_rate": 1.7798407950559348e-06,
"loss": 0.7613,
"step": 774
},
{
"epoch": 0.81,
"learning_rate": 1.760505722752155e-06,
"loss": 0.7417,
"step": 775
},
{
"epoch": 0.82,
"learning_rate": 1.7412661049645097e-06,
"loss": 0.7592,
"step": 776
},
{
"epoch": 0.82,
"learning_rate": 1.7221221645839093e-06,
"loss": 0.7935,
"step": 777
},
{
"epoch": 0.82,
"learning_rate": 1.7030741233928438e-06,
"loss": 0.7737,
"step": 778
},
{
"epoch": 0.82,
"learning_rate": 1.6841222020628123e-06,
"loss": 0.7687,
"step": 779
},
{
"epoch": 0.82,
"learning_rate": 1.6652666201517686e-06,
"loss": 0.7727,
"step": 780
},
{
"epoch": 0.82,
"learning_rate": 1.6465075961015697e-06,
"loss": 0.7935,
"step": 781
},
{
"epoch": 0.82,
"learning_rate": 1.627845347235454e-06,
"loss": 0.7674,
"step": 782
},
{
"epoch": 0.82,
"learning_rate": 1.609280089755515e-06,
"loss": 0.7528,
"step": 783
},
{
"epoch": 0.82,
"learning_rate": 1.5908120387402038e-06,
"loss": 0.7437,
"step": 784
},
{
"epoch": 0.82,
"learning_rate": 1.5724414081418383e-06,
"loss": 0.7414,
"step": 785
},
{
"epoch": 0.83,
"learning_rate": 1.554168410784117e-06,
"loss": 0.7451,
"step": 786
},
{
"epoch": 0.83,
"learning_rate": 1.5359932583596594e-06,
"loss": 0.7833,
"step": 787
},
{
"epoch": 0.83,
"learning_rate": 1.5179161614275483e-06,
"loss": 0.7154,
"step": 788
},
{
"epoch": 0.83,
"learning_rate": 1.4999373294109e-06,
"loss": 0.8139,
"step": 789
},
{
"epoch": 0.83,
"learning_rate": 1.4820569705944254e-06,
"loss": 0.7605,
"step": 790
},
{
"epoch": 0.83,
"learning_rate": 1.4642752921220272e-06,
"loss": 0.7386,
"step": 791
},
{
"epoch": 0.83,
"learning_rate": 1.4465924999944004e-06,
"loss": 0.7867,
"step": 792
},
{
"epoch": 0.83,
"learning_rate": 1.4290087990666346e-06,
"loss": 0.7411,
"step": 793
},
{
"epoch": 0.83,
"learning_rate": 1.4115243930458533e-06,
"loss": 0.7553,
"step": 794
},
{
"epoch": 0.84,
"learning_rate": 1.3941394844888456e-06,
"loss": 0.7669,
"step": 795
},
{
"epoch": 0.84,
"learning_rate": 1.3768542747997215e-06,
"loss": 0.7621,
"step": 796
},
{
"epoch": 0.84,
"learning_rate": 1.3596689642275894e-06,
"loss": 0.8137,
"step": 797
},
{
"epoch": 0.84,
"learning_rate": 1.342583751864216e-06,
"loss": 0.7927,
"step": 798
},
{
"epoch": 0.84,
"learning_rate": 1.325598835641736e-06,
"loss": 0.7873,
"step": 799
},
{
"epoch": 0.84,
"learning_rate": 1.3087144123303475e-06,
"loss": 0.783,
"step": 800
},
{
"epoch": 0.84,
"learning_rate": 1.2919306775360495e-06,
"loss": 0.7628,
"step": 801
},
{
"epoch": 0.84,
"learning_rate": 1.2752478256983569e-06,
"loss": 0.7423,
"step": 802
},
{
"epoch": 0.84,
"learning_rate": 1.2586660500880554e-06,
"loss": 0.7308,
"step": 803
},
{
"epoch": 0.84,
"learning_rate": 1.2421855428049668e-06,
"loss": 0.7349,
"step": 804
},
{
"epoch": 0.85,
"learning_rate": 1.2258064947757164e-06,
"loss": 0.7861,
"step": 805
},
{
"epoch": 0.85,
"learning_rate": 1.209529095751527e-06,
"loss": 0.7546,
"step": 806
},
{
"epoch": 0.85,
"learning_rate": 1.1933535343060155e-06,
"loss": 0.7538,
"step": 807
},
{
"epoch": 0.85,
"learning_rate": 1.177279997833012e-06,
"loss": 0.7692,
"step": 808
},
{
"epoch": 0.85,
"learning_rate": 1.161308672544389e-06,
"loss": 0.7012,
"step": 809
},
{
"epoch": 0.85,
"learning_rate": 1.1454397434679022e-06,
"loss": 0.7557,
"step": 810
},
{
"epoch": 0.85,
"learning_rate": 1.1296733944450445e-06,
"loss": 0.7421,
"step": 811
},
{
"epoch": 0.85,
"learning_rate": 1.1140098081289219e-06,
"loss": 0.7634,
"step": 812
},
{
"epoch": 0.85,
"learning_rate": 1.0984491659821329e-06,
"loss": 0.7718,
"step": 813
},
{
"epoch": 0.86,
"learning_rate": 1.0829916482746716e-06,
"loss": 0.8108,
"step": 814
},
{
"epoch": 0.86,
"learning_rate": 1.067637434081834e-06,
"loss": 0.7308,
"step": 815
},
{
"epoch": 0.86,
"learning_rate": 1.0523867012821444e-06,
"loss": 0.7344,
"step": 816
},
{
"epoch": 0.86,
"learning_rate": 1.0372396265552919e-06,
"loss": 0.7146,
"step": 817
},
{
"epoch": 0.86,
"learning_rate": 1.0221963853800976e-06,
"loss": 0.7326,
"step": 818
},
{
"epoch": 0.86,
"learning_rate": 1.0072571520324613e-06,
"loss": 0.7287,
"step": 819
},
{
"epoch": 0.86,
"learning_rate": 9.924220995833578e-07,
"loss": 0.7498,
"step": 820
},
{
"epoch": 0.86,
"learning_rate": 9.776913998968196e-07,
"loss": 0.7667,
"step": 821
},
{
"epoch": 0.86,
"learning_rate": 9.630652236279626e-07,
"loss": 0.767,
"step": 822
},
{
"epoch": 0.86,
"learning_rate": 9.48543740220993e-07,
"loss": 0.7704,
"step": 823
},
{
"epoch": 0.87,
"learning_rate": 9.341271179072508e-07,
"loss": 0.755,
"step": 824
},
{
"epoch": 0.87,
"learning_rate": 9.198155237032624e-07,
"loss": 0.7713,
"step": 825
},
{
"epoch": 0.87,
"learning_rate": 9.056091234088038e-07,
"loss": 0.7079,
"step": 826
},
{
"epoch": 0.87,
"learning_rate": 8.915080816049792e-07,
"loss": 0.7939,
"step": 827
},
{
"epoch": 0.87,
"learning_rate": 8.77512561652315e-07,
"loss": 0.7867,
"step": 828
},
{
"epoch": 0.87,
"learning_rate": 8.636227256888641e-07,
"loss": 0.7545,
"step": 829
},
{
"epoch": 0.87,
"learning_rate": 8.498387346283388e-07,
"loss": 0.7576,
"step": 830
},
{
"epoch": 0.87,
"learning_rate": 8.361607481582312e-07,
"loss": 0.7097,
"step": 831
},
{
"epoch": 0.87,
"learning_rate": 8.225889247379726e-07,
"loss": 0.7715,
"step": 832
},
{
"epoch": 0.88,
"learning_rate": 8.091234215970967e-07,
"loss": 0.7607,
"step": 833
},
{
"epoch": 0.88,
"learning_rate": 7.957643947334148e-07,
"loss": 0.7521,
"step": 834
},
{
"epoch": 0.88,
"learning_rate": 7.825119989112173e-07,
"loss": 0.8057,
"step": 835
},
{
"epoch": 0.88,
"learning_rate": 7.693663876594648e-07,
"loss": 0.7575,
"step": 836
},
{
"epoch": 0.88,
"learning_rate": 7.563277132700219e-07,
"loss": 0.7654,
"step": 837
},
{
"epoch": 0.88,
"learning_rate": 7.433961267958978e-07,
"loss": 0.7981,
"step": 838
},
{
"epoch": 0.88,
"learning_rate": 7.305717780494781e-07,
"loss": 0.7415,
"step": 839
},
{
"epoch": 0.88,
"learning_rate": 7.178548156008058e-07,
"loss": 0.8021,
"step": 840
},
{
"epoch": 0.88,
"learning_rate": 7.052453867758525e-07,
"loss": 0.7361,
"step": 841
},
{
"epoch": 0.88,
"learning_rate": 6.927436376548091e-07,
"loss": 0.7563,
"step": 842
},
{
"epoch": 0.89,
"learning_rate": 6.803497130704062e-07,
"loss": 0.7382,
"step": 843
},
{
"epoch": 0.89,
"learning_rate": 6.680637566062198e-07,
"loss": 0.7326,
"step": 844
},
{
"epoch": 0.89,
"learning_rate": 6.558859105950188e-07,
"loss": 0.7692,
"step": 845
},
{
"epoch": 0.89,
"learning_rate": 6.438163161171096e-07,
"loss": 0.7112,
"step": 846
},
{
"epoch": 0.89,
"learning_rate": 6.318551129987116e-07,
"loss": 0.7677,
"step": 847
},
{
"epoch": 0.89,
"learning_rate": 6.200024398103255e-07,
"loss": 0.7181,
"step": 848
},
{
"epoch": 0.89,
"learning_rate": 6.082584338651331e-07,
"loss": 0.7607,
"step": 849
},
{
"epoch": 0.89,
"learning_rate": 5.966232312174069e-07,
"loss": 0.7794,
"step": 850
},
{
"epoch": 0.89,
"learning_rate": 5.850969666609363e-07,
"loss": 0.7408,
"step": 851
},
{
"epoch": 0.89,
"learning_rate": 5.736797737274591e-07,
"loss": 0.719,
"step": 852
},
{
"epoch": 0.9,
"learning_rate": 5.623717846851218e-07,
"loss": 0.6961,
"step": 853
},
{
"epoch": 0.9,
"learning_rate": 5.511731305369406e-07,
"loss": 0.7159,
"step": 854
},
{
"epoch": 0.9,
"learning_rate": 5.400839410192949e-07,
"loss": 0.7072,
"step": 855
},
{
"epoch": 0.9,
"learning_rate": 5.291043446004074e-07,
"loss": 0.7157,
"step": 856
},
{
"epoch": 0.9,
"learning_rate": 5.182344684788698e-07,
"loss": 0.7848,
"step": 857
},
{
"epoch": 0.9,
"learning_rate": 5.07474438582165e-07,
"loss": 0.7423,
"step": 858
},
{
"epoch": 0.9,
"learning_rate": 4.968243795652039e-07,
"loss": 0.7388,
"step": 859
},
{
"epoch": 0.9,
"learning_rate": 4.862844148088919e-07,
"loss": 0.7614,
"step": 860
},
{
"epoch": 0.9,
"learning_rate": 4.7585466641868696e-07,
"loss": 0.7436,
"step": 861
},
{
"epoch": 0.91,
"learning_rate": 4.6553525522319177e-07,
"loss": 0.7711,
"step": 862
},
{
"epoch": 0.91,
"learning_rate": 4.553263007727526e-07,
"loss": 0.7293,
"step": 863
},
{
"epoch": 0.91,
"learning_rate": 4.452279213380783e-07,
"loss": 0.7223,
"step": 864
},
{
"epoch": 0.91,
"learning_rate": 4.352402339088624e-07,
"loss": 0.7676,
"step": 865
},
{
"epoch": 0.91,
"learning_rate": 4.25363354192434e-07,
"loss": 0.7433,
"step": 866
},
{
"epoch": 0.91,
"learning_rate": 4.1559739661241384e-07,
"loss": 0.7619,
"step": 867
},
{
"epoch": 0.91,
"learning_rate": 4.059424743073914e-07,
"loss": 0.7691,
"step": 868
},
{
"epoch": 0.91,
"learning_rate": 3.9639869912961205e-07,
"loss": 0.7235,
"step": 869
},
{
"epoch": 0.91,
"learning_rate": 3.8696618164368204e-07,
"loss": 0.7734,
"step": 870
},
{
"epoch": 0.91,
"learning_rate": 3.776450311252866e-07,
"loss": 0.7223,
"step": 871
},
{
"epoch": 0.92,
"learning_rate": 3.684353555599285e-07,
"loss": 0.721,
"step": 872
},
{
"epoch": 0.92,
"learning_rate": 3.5933726164167013e-07,
"loss": 0.7072,
"step": 873
},
{
"epoch": 0.92,
"learning_rate": 3.5035085477190143e-07,
"loss": 0.7402,
"step": 874
},
{
"epoch": 0.92,
"learning_rate": 3.4147623905811723e-07,
"loss": 0.6917,
"step": 875
},
{
"epoch": 0.92,
"learning_rate": 3.3271351731271717e-07,
"loss": 0.7582,
"step": 876
},
{
"epoch": 0.92,
"learning_rate": 3.240627910518035e-07,
"loss": 0.764,
"step": 877
},
{
"epoch": 0.92,
"learning_rate": 3.1552416049401403e-07,
"loss": 0.7961,
"step": 878
},
{
"epoch": 0.92,
"learning_rate": 3.070977245593587e-07,
"loss": 0.7669,
"step": 879
},
{
"epoch": 0.92,
"learning_rate": 2.987835808680695e-07,
"loss": 0.7479,
"step": 880
},
{
"epoch": 0.93,
"learning_rate": 2.905818257394799e-07,
"loss": 0.7365,
"step": 881
},
{
"epoch": 0.93,
"learning_rate": 2.824925541908963e-07,
"loss": 0.7371,
"step": 882
},
{
"epoch": 0.93,
"learning_rate": 2.7451585993650166e-07,
"loss": 0.7789,
"step": 883
},
{
"epoch": 0.93,
"learning_rate": 2.666518353862801e-07,
"loss": 0.7264,
"step": 884
},
{
"epoch": 0.93,
"learning_rate": 2.589005716449289e-07,
"loss": 0.7798,
"step": 885
},
{
"epoch": 0.93,
"learning_rate": 2.512621585108155e-07,
"loss": 0.8341,
"step": 886
},
{
"epoch": 0.93,
"learning_rate": 2.4373668447493225e-07,
"loss": 0.7444,
"step": 887
},
{
"epoch": 0.93,
"learning_rate": 2.363242367198737e-07,
"loss": 0.7371,
"step": 888
},
{
"epoch": 0.93,
"learning_rate": 2.2902490111882502e-07,
"loss": 0.7596,
"step": 889
},
{
"epoch": 0.93,
"learning_rate": 2.2183876223456747e-07,
"loss": 0.7256,
"step": 890
},
{
"epoch": 0.94,
"learning_rate": 2.1476590331849566e-07,
"loss": 0.7461,
"step": 891
},
{
"epoch": 0.94,
"learning_rate": 2.0780640630965965e-07,
"loss": 0.7505,
"step": 892
},
{
"epoch": 0.94,
"learning_rate": 2.0096035183381214e-07,
"loss": 0.7494,
"step": 893
},
{
"epoch": 0.94,
"learning_rate": 1.9422781920247268e-07,
"loss": 0.7724,
"step": 894
},
{
"epoch": 0.94,
"learning_rate": 1.8760888641201181e-07,
"loss": 0.7263,
"step": 895
},
{
"epoch": 0.94,
"learning_rate": 1.811036301427449e-07,
"loss": 0.8224,
"step": 896
},
{
"epoch": 0.94,
"learning_rate": 1.747121257580464e-07,
"loss": 0.7341,
"step": 897
},
{
"epoch": 0.94,
"learning_rate": 1.6843444730347713e-07,
"loss": 0.7089,
"step": 898
},
{
"epoch": 0.94,
"learning_rate": 1.6227066750591935e-07,
"loss": 0.7522,
"step": 899
},
{
"epoch": 0.95,
"learning_rate": 1.562208577727442e-07,
"loss": 0.7458,
"step": 900
},
{
"epoch": 0.95,
"learning_rate": 1.502850881909801e-07,
"loss": 0.7122,
"step": 901
},
{
"epoch": 0.95,
"learning_rate": 1.444634275265e-07,
"loss": 0.7559,
"step": 902
},
{
"epoch": 0.95,
"learning_rate": 1.387559432232244e-07,
"loss": 0.719,
"step": 903
},
{
"epoch": 0.95,
"learning_rate": 1.3316270140233955e-07,
"loss": 0.7419,
"step": 904
},
{
"epoch": 0.95,
"learning_rate": 1.2768376686153827e-07,
"loss": 0.6996,
"step": 905
},
{
"epoch": 0.95,
"learning_rate": 1.2231920307425927e-07,
"loss": 0.7701,
"step": 906
},
{
"epoch": 0.95,
"learning_rate": 1.1706907218895669e-07,
"loss": 0.7615,
"step": 907
},
{
"epoch": 0.95,
"learning_rate": 1.1193343502838294e-07,
"loss": 0.749,
"step": 908
},
{
"epoch": 0.95,
"learning_rate": 1.0691235108887587e-07,
"loss": 0.7184,
"step": 909
},
{
"epoch": 0.96,
"learning_rate": 1.0200587853968047e-07,
"loss": 0.7375,
"step": 910
},
{
"epoch": 0.96,
"learning_rate": 9.721407422226492e-08,
"loss": 0.743,
"step": 911
},
{
"epoch": 0.96,
"learning_rate": 9.253699364966784e-08,
"loss": 0.7612,
"step": 912
},
{
"epoch": 0.96,
"learning_rate": 8.797469100585432e-08,
"loss": 0.7673,
"step": 913
},
{
"epoch": 0.96,
"learning_rate": 8.352721914508533e-08,
"loss": 0.7658,
"step": 914
},
{
"epoch": 0.96,
"learning_rate": 7.91946295913093e-08,
"loss": 0.7332,
"step": 915
},
{
"epoch": 0.96,
"learning_rate": 7.497697253756265e-08,
"loss": 0.7596,
"step": 916
},
{
"epoch": 0.96,
"learning_rate": 7.087429684539016e-08,
"loss": 0.7497,
"step": 917
},
{
"epoch": 0.96,
"learning_rate": 6.688665004427774e-08,
"loss": 0.7392,
"step": 918
},
{
"epoch": 0.97,
"learning_rate": 6.301407833109952e-08,
"loss": 0.7686,
"step": 919
},
{
"epoch": 0.97,
"learning_rate": 5.92566265695893e-08,
"loss": 0.6955,
"step": 920
},
{
"epoch": 0.97,
"learning_rate": 5.5614338289812216e-08,
"loss": 0.7355,
"step": 921
},
{
"epoch": 0.97,
"learning_rate": 5.208725568766837e-08,
"loss": 0.7665,
"step": 922
},
{
"epoch": 0.97,
"learning_rate": 4.867541962439881e-08,
"loss": 0.7424,
"step": 923
},
{
"epoch": 0.97,
"learning_rate": 4.537886962611371e-08,
"loss": 0.7198,
"step": 924
},
{
"epoch": 0.97,
"learning_rate": 4.2197643883334914e-08,
"loss": 0.7279,
"step": 925
},
{
"epoch": 0.97,
"learning_rate": 3.913177925055189e-08,
"loss": 0.7661,
"step": 926
},
{
"epoch": 0.97,
"learning_rate": 3.618131124579871e-08,
"loss": 0.7649,
"step": 927
},
{
"epoch": 0.97,
"learning_rate": 3.3346274050236605e-08,
"loss": 0.7669,
"step": 928
},
{
"epoch": 0.98,
"learning_rate": 3.062670050776429e-08,
"loss": 0.7836,
"step": 929
},
{
"epoch": 0.98,
"learning_rate": 2.8022622124632693e-08,
"loss": 0.764,
"step": 930
},
{
"epoch": 0.98,
"learning_rate": 2.5534069069081957e-08,
"loss": 0.7499,
"step": 931
},
{
"epoch": 0.98,
"learning_rate": 2.316107017099056e-08,
"loss": 0.7868,
"step": 932
},
{
"epoch": 0.98,
"learning_rate": 2.0903652921544505e-08,
"loss": 0.7693,
"step": 933
},
{
"epoch": 0.98,
"learning_rate": 1.876184347291532e-08,
"loss": 0.7327,
"step": 934
},
{
"epoch": 0.98,
"learning_rate": 1.6735666637960335e-08,
"loss": 0.7244,
"step": 935
},
{
"epoch": 0.98,
"learning_rate": 1.482514588993067e-08,
"loss": 0.7269,
"step": 936
},
{
"epoch": 0.98,
"learning_rate": 1.3030303362202568e-08,
"loss": 0.7383,
"step": 937
},
{
"epoch": 0.99,
"learning_rate": 1.1351159848023152e-08,
"loss": 0.7693,
"step": 938
},
{
"epoch": 0.99,
"learning_rate": 9.78773480026396e-09,
"loss": 0.747,
"step": 939
},
{
"epoch": 0.99,
"learning_rate": 8.340046331200002e-09,
"loss": 0.7752,
"step": 940
},
{
"epoch": 0.99,
"learning_rate": 7.0081112122966086e-09,
"loss": 0.7256,
"step": 941
},
{
"epoch": 0.99,
"learning_rate": 5.7919448740184626e-09,
"loss": 0.7449,
"step": 942
},
{
"epoch": 0.99,
"learning_rate": 4.691561405649747e-09,
"loss": 0.7782,
"step": 943
},
{
"epoch": 0.99,
"learning_rate": 3.7069735551298337e-09,
"loss": 0.7465,
"step": 944
},
{
"epoch": 0.99,
"learning_rate": 2.8381927289045098e-09,
"loss": 0.691,
"step": 945
},
{
"epoch": 0.99,
"learning_rate": 2.0852289917971947e-09,
"loss": 0.7392,
"step": 946
},
{
"epoch": 0.99,
"learning_rate": 1.4480910668912552e-09,
"loss": 0.8193,
"step": 947
},
{
"epoch": 1.0,
"learning_rate": 9.26786335427865e-10,
"loss": 0.765,
"step": 948
},
{
"epoch": 1.0,
"learning_rate": 5.21320836720518e-10,
"loss": 0.7459,
"step": 949
},
{
"epoch": 1.0,
"learning_rate": 2.316992680839736e-10,
"loss": 0.7614,
"step": 950
},
{
"epoch": 1.0,
"learning_rate": 5.792498478651709e-11,
"loss": 0.7253,
"step": 951
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.7587,
"step": 952
},
{
"epoch": 1.0,
"step": 952,
"total_flos": 103130886832128.0,
"train_loss": 0.8640537265719486,
"train_runtime": 3498.9342,
"train_samples_per_second": 30.469,
"train_steps_per_second": 0.272
}
],
"logging_steps": 1.0,
"max_steps": 952,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 2400,
"total_flos": 103130886832128.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}