medalpaca-7b / trainer_state.json
kbressem's picture
Rerun trainig with data v3
9405874
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.99904,
"global_step": 2343,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 2.8169014084507043e-07,
"loss": 1.8921,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 5.633802816901409e-07,
"loss": 1.8096,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 8.450704225352114e-07,
"loss": 1.7,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 1.1267605633802817e-06,
"loss": 1.7214,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.4084507042253523e-06,
"loss": 1.6331,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.6901408450704227e-06,
"loss": 1.6166,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 1.971830985915493e-06,
"loss": 1.6235,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 2.2535211267605635e-06,
"loss": 1.5503,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 2.535211267605634e-06,
"loss": 1.7446,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 2.8169014084507046e-06,
"loss": 1.7047,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 3.0985915492957746e-06,
"loss": 1.5921,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 3.3802816901408454e-06,
"loss": 1.6417,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 3.6619718309859158e-06,
"loss": 1.5161,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 3.943661971830986e-06,
"loss": 1.6622,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 4.225352112676057e-06,
"loss": 1.5799,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 4.507042253521127e-06,
"loss": 1.6811,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 4.788732394366197e-06,
"loss": 1.7073,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 5.070422535211268e-06,
"loss": 1.6215,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 5.352112676056338e-06,
"loss": 1.6431,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 5.633802816901409e-06,
"loss": 1.4463,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 5.915492957746479e-06,
"loss": 1.6029,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 6.197183098591549e-06,
"loss": 1.5853,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 6.478873239436621e-06,
"loss": 1.6092,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 6.760563380281691e-06,
"loss": 1.5076,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 7.042253521126761e-06,
"loss": 1.6526,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 7.3239436619718316e-06,
"loss": 1.6948,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 7.6056338028169015e-06,
"loss": 1.5392,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 7.887323943661972e-06,
"loss": 1.5999,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 8.169014084507043e-06,
"loss": 1.565,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 8.450704225352114e-06,
"loss": 1.4908,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 8.732394366197183e-06,
"loss": 1.6403,
"step": 31
},
{
"epoch": 0.04,
"learning_rate": 9.014084507042254e-06,
"loss": 1.6085,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 9.295774647887325e-06,
"loss": 1.5261,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 9.577464788732394e-06,
"loss": 1.6884,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 9.859154929577466e-06,
"loss": 1.6382,
"step": 35
},
{
"epoch": 0.05,
"learning_rate": 1.0140845070422535e-05,
"loss": 1.5463,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 1.0422535211267606e-05,
"loss": 1.6388,
"step": 37
},
{
"epoch": 0.05,
"learning_rate": 1.0704225352112675e-05,
"loss": 1.565,
"step": 38
},
{
"epoch": 0.05,
"learning_rate": 1.0985915492957748e-05,
"loss": 1.6066,
"step": 39
},
{
"epoch": 0.05,
"learning_rate": 1.1267605633802819e-05,
"loss": 1.6559,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 1.1549295774647888e-05,
"loss": 1.6585,
"step": 41
},
{
"epoch": 0.05,
"learning_rate": 1.1830985915492958e-05,
"loss": 1.6534,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 1.211267605633803e-05,
"loss": 1.5766,
"step": 43
},
{
"epoch": 0.06,
"learning_rate": 1.2394366197183098e-05,
"loss": 1.6348,
"step": 44
},
{
"epoch": 0.06,
"learning_rate": 1.2676056338028171e-05,
"loss": 1.4892,
"step": 45
},
{
"epoch": 0.06,
"learning_rate": 1.2957746478873242e-05,
"loss": 1.6072,
"step": 46
},
{
"epoch": 0.06,
"learning_rate": 1.323943661971831e-05,
"loss": 1.5432,
"step": 47
},
{
"epoch": 0.06,
"learning_rate": 1.3521126760563382e-05,
"loss": 1.5705,
"step": 48
},
{
"epoch": 0.06,
"learning_rate": 1.380281690140845e-05,
"loss": 1.5671,
"step": 49
},
{
"epoch": 0.06,
"learning_rate": 1.4084507042253522e-05,
"loss": 1.3851,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 1.4366197183098594e-05,
"loss": 1.7054,
"step": 51
},
{
"epoch": 0.07,
"learning_rate": 1.4647887323943663e-05,
"loss": 1.587,
"step": 52
},
{
"epoch": 0.07,
"learning_rate": 1.4929577464788734e-05,
"loss": 1.5249,
"step": 53
},
{
"epoch": 0.07,
"learning_rate": 1.5211267605633803e-05,
"loss": 1.5869,
"step": 54
},
{
"epoch": 0.07,
"learning_rate": 1.5492957746478872e-05,
"loss": 1.5268,
"step": 55
},
{
"epoch": 0.07,
"learning_rate": 1.5774647887323945e-05,
"loss": 1.6697,
"step": 56
},
{
"epoch": 0.07,
"learning_rate": 1.6056338028169017e-05,
"loss": 1.4727,
"step": 57
},
{
"epoch": 0.07,
"learning_rate": 1.6338028169014086e-05,
"loss": 1.5529,
"step": 58
},
{
"epoch": 0.08,
"learning_rate": 1.6619718309859155e-05,
"loss": 1.5541,
"step": 59
},
{
"epoch": 0.08,
"learning_rate": 1.6901408450704228e-05,
"loss": 1.5959,
"step": 60
},
{
"epoch": 0.08,
"learning_rate": 1.7183098591549297e-05,
"loss": 1.5616,
"step": 61
},
{
"epoch": 0.08,
"learning_rate": 1.7464788732394366e-05,
"loss": 1.6742,
"step": 62
},
{
"epoch": 0.08,
"learning_rate": 1.774647887323944e-05,
"loss": 1.64,
"step": 63
},
{
"epoch": 0.08,
"learning_rate": 1.8028169014084508e-05,
"loss": 1.5498,
"step": 64
},
{
"epoch": 0.08,
"learning_rate": 1.830985915492958e-05,
"loss": 1.5754,
"step": 65
},
{
"epoch": 0.08,
"learning_rate": 1.859154929577465e-05,
"loss": 1.5734,
"step": 66
},
{
"epoch": 0.09,
"learning_rate": 1.887323943661972e-05,
"loss": 1.5026,
"step": 67
},
{
"epoch": 0.09,
"learning_rate": 1.9154929577464788e-05,
"loss": 1.5985,
"step": 68
},
{
"epoch": 0.09,
"learning_rate": 1.943661971830986e-05,
"loss": 1.5921,
"step": 69
},
{
"epoch": 0.09,
"learning_rate": 1.9718309859154933e-05,
"loss": 1.5652,
"step": 70
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 1.6493,
"step": 71
},
{
"epoch": 0.09,
"learning_rate": 1.9999990440107112e-05,
"loss": 1.4978,
"step": 72
},
{
"epoch": 0.09,
"learning_rate": 1.9999961760446717e-05,
"loss": 1.4696,
"step": 73
},
{
"epoch": 0.09,
"learning_rate": 1.999991396107366e-05,
"loss": 1.528,
"step": 74
},
{
"epoch": 0.1,
"learning_rate": 1.999984704207932e-05,
"loss": 1.6531,
"step": 75
},
{
"epoch": 0.1,
"learning_rate": 1.9999761003591655e-05,
"loss": 1.4925,
"step": 76
},
{
"epoch": 0.1,
"learning_rate": 1.999965584577516e-05,
"loss": 1.6071,
"step": 77
},
{
"epoch": 0.1,
"learning_rate": 1.9999531568830904e-05,
"loss": 1.6808,
"step": 78
},
{
"epoch": 0.1,
"learning_rate": 1.9999388172996495e-05,
"loss": 1.569,
"step": 79
},
{
"epoch": 0.1,
"learning_rate": 1.9999225658546105e-05,
"loss": 1.616,
"step": 80
},
{
"epoch": 0.1,
"learning_rate": 1.9999044025790462e-05,
"loss": 1.534,
"step": 81
},
{
"epoch": 0.1,
"learning_rate": 1.9998843275076836e-05,
"loss": 1.5611,
"step": 82
},
{
"epoch": 0.11,
"learning_rate": 1.9998623406789065e-05,
"loss": 1.47,
"step": 83
},
{
"epoch": 0.11,
"learning_rate": 1.9998384421347525e-05,
"loss": 1.5568,
"step": 84
},
{
"epoch": 0.11,
"learning_rate": 1.999812631920916e-05,
"loss": 1.5439,
"step": 85
},
{
"epoch": 0.11,
"learning_rate": 1.999784910086745e-05,
"loss": 1.6501,
"step": 86
},
{
"epoch": 0.11,
"learning_rate": 1.9997552766852434e-05,
"loss": 1.6142,
"step": 87
},
{
"epoch": 0.11,
"learning_rate": 1.9997237317730688e-05,
"loss": 1.5881,
"step": 88
},
{
"epoch": 0.11,
"learning_rate": 1.9996902754105356e-05,
"loss": 1.5508,
"step": 89
},
{
"epoch": 0.12,
"learning_rate": 1.999654907661611e-05,
"loss": 1.5169,
"step": 90
},
{
"epoch": 0.12,
"learning_rate": 1.9996176285939174e-05,
"loss": 1.5327,
"step": 91
},
{
"epoch": 0.12,
"learning_rate": 1.9995784382787317e-05,
"loss": 1.4774,
"step": 92
},
{
"epoch": 0.12,
"learning_rate": 1.9995373367909846e-05,
"loss": 1.5419,
"step": 93
},
{
"epoch": 0.12,
"learning_rate": 1.9994943242092616e-05,
"loss": 1.6472,
"step": 94
},
{
"epoch": 0.12,
"learning_rate": 1.9994494006158018e-05,
"loss": 1.6383,
"step": 95
},
{
"epoch": 0.12,
"learning_rate": 1.9994025660964983e-05,
"loss": 1.5829,
"step": 96
},
{
"epoch": 0.12,
"learning_rate": 1.9993538207408975e-05,
"loss": 1.5911,
"step": 97
},
{
"epoch": 0.13,
"learning_rate": 1.9993031646421994e-05,
"loss": 1.4514,
"step": 98
},
{
"epoch": 0.13,
"learning_rate": 1.9992505978972575e-05,
"loss": 1.6075,
"step": 99
},
{
"epoch": 0.13,
"learning_rate": 1.9991961206065783e-05,
"loss": 1.5791,
"step": 100
},
{
"epoch": 0.13,
"learning_rate": 1.999139732874321e-05,
"loss": 1.6027,
"step": 101
},
{
"epoch": 0.13,
"learning_rate": 1.999081434808298e-05,
"loss": 1.6114,
"step": 102
},
{
"epoch": 0.13,
"learning_rate": 1.9990212265199738e-05,
"loss": 1.5659,
"step": 103
},
{
"epoch": 0.13,
"learning_rate": 1.9989591081244654e-05,
"loss": 1.5509,
"step": 104
},
{
"epoch": 0.13,
"learning_rate": 1.998895079740542e-05,
"loss": 1.6459,
"step": 105
},
{
"epoch": 0.14,
"learning_rate": 1.9988291414906243e-05,
"loss": 1.5128,
"step": 106
},
{
"epoch": 0.14,
"learning_rate": 1.9987612935007847e-05,
"loss": 1.6003,
"step": 107
},
{
"epoch": 0.14,
"learning_rate": 1.9986915359007475e-05,
"loss": 1.6368,
"step": 108
},
{
"epoch": 0.14,
"learning_rate": 1.9986198688238874e-05,
"loss": 1.5721,
"step": 109
},
{
"epoch": 0.14,
"learning_rate": 1.9985462924072305e-05,
"loss": 1.4756,
"step": 110
},
{
"epoch": 0.14,
"learning_rate": 1.9984708067914533e-05,
"loss": 1.521,
"step": 111
},
{
"epoch": 0.14,
"learning_rate": 1.9983934121208826e-05,
"loss": 1.5336,
"step": 112
},
{
"epoch": 0.14,
"learning_rate": 1.9983141085434952e-05,
"loss": 1.5823,
"step": 113
},
{
"epoch": 0.15,
"learning_rate": 1.9982328962109183e-05,
"loss": 1.4413,
"step": 114
},
{
"epoch": 0.15,
"learning_rate": 1.998149775278428e-05,
"loss": 1.4935,
"step": 115
},
{
"epoch": 0.15,
"learning_rate": 1.9980647459049494e-05,
"loss": 1.5255,
"step": 116
},
{
"epoch": 0.15,
"learning_rate": 1.9979778082530572e-05,
"loss": 1.561,
"step": 117
},
{
"epoch": 0.15,
"learning_rate": 1.997888962488974e-05,
"loss": 1.5925,
"step": 118
},
{
"epoch": 0.15,
"learning_rate": 1.9977982087825714e-05,
"loss": 1.6209,
"step": 119
},
{
"epoch": 0.15,
"learning_rate": 1.997705547307368e-05,
"loss": 1.5829,
"step": 120
},
{
"epoch": 0.15,
"learning_rate": 1.9976109782405314e-05,
"loss": 1.5361,
"step": 121
},
{
"epoch": 0.16,
"learning_rate": 1.9975145017628745e-05,
"loss": 1.528,
"step": 122
},
{
"epoch": 0.16,
"learning_rate": 1.9974161180588593e-05,
"loss": 1.5733,
"step": 123
},
{
"epoch": 0.16,
"learning_rate": 1.9973158273165925e-05,
"loss": 1.5336,
"step": 124
},
{
"epoch": 0.16,
"learning_rate": 1.9972136297278285e-05,
"loss": 1.5187,
"step": 125
},
{
"epoch": 0.16,
"learning_rate": 1.997109525487967e-05,
"loss": 1.5704,
"step": 126
},
{
"epoch": 0.16,
"learning_rate": 1.9970035147960524e-05,
"loss": 1.6741,
"step": 127
},
{
"epoch": 0.16,
"learning_rate": 1.9968955978547753e-05,
"loss": 1.5884,
"step": 128
},
{
"epoch": 0.17,
"learning_rate": 1.9967857748704705e-05,
"loss": 1.5621,
"step": 129
},
{
"epoch": 0.17,
"learning_rate": 1.9966740460531172e-05,
"loss": 1.4549,
"step": 130
},
{
"epoch": 0.17,
"learning_rate": 1.996560411616338e-05,
"loss": 1.5865,
"step": 131
},
{
"epoch": 0.17,
"learning_rate": 1.9964448717774008e-05,
"loss": 1.5352,
"step": 132
},
{
"epoch": 0.17,
"learning_rate": 1.9963274267572143e-05,
"loss": 1.4776,
"step": 133
},
{
"epoch": 0.17,
"learning_rate": 1.9962080767803303e-05,
"loss": 1.5916,
"step": 134
},
{
"epoch": 0.17,
"learning_rate": 1.996086822074945e-05,
"loss": 1.423,
"step": 135
},
{
"epoch": 0.17,
"learning_rate": 1.9959636628728938e-05,
"loss": 1.5618,
"step": 136
},
{
"epoch": 0.18,
"learning_rate": 1.9958385994096543e-05,
"loss": 1.4755,
"step": 137
},
{
"epoch": 0.18,
"learning_rate": 1.9957116319243458e-05,
"loss": 1.4957,
"step": 138
},
{
"epoch": 0.18,
"learning_rate": 1.995582760659727e-05,
"loss": 1.5618,
"step": 139
},
{
"epoch": 0.18,
"learning_rate": 1.995451985862197e-05,
"loss": 1.4713,
"step": 140
},
{
"epoch": 0.18,
"learning_rate": 1.995319307781794e-05,
"loss": 1.5717,
"step": 141
},
{
"epoch": 0.18,
"learning_rate": 1.995184726672197e-05,
"loss": 1.5397,
"step": 142
},
{
"epoch": 0.18,
"learning_rate": 1.995048242790721e-05,
"loss": 1.5383,
"step": 143
},
{
"epoch": 0.18,
"learning_rate": 1.9949098563983206e-05,
"loss": 1.5889,
"step": 144
},
{
"epoch": 0.19,
"learning_rate": 1.9947695677595877e-05,
"loss": 1.4919,
"step": 145
},
{
"epoch": 0.19,
"learning_rate": 1.994627377142751e-05,
"loss": 1.4836,
"step": 146
},
{
"epoch": 0.19,
"learning_rate": 1.9944832848196757e-05,
"loss": 1.4114,
"step": 147
},
{
"epoch": 0.19,
"learning_rate": 1.994337291065864e-05,
"loss": 1.5828,
"step": 148
},
{
"epoch": 0.19,
"learning_rate": 1.994189396160452e-05,
"loss": 1.5641,
"step": 149
},
{
"epoch": 0.19,
"learning_rate": 1.9940396003862123e-05,
"loss": 1.5425,
"step": 150
},
{
"epoch": 0.19,
"learning_rate": 1.9938879040295508e-05,
"loss": 1.5539,
"step": 151
},
{
"epoch": 0.19,
"learning_rate": 1.9937343073805078e-05,
"loss": 1.5581,
"step": 152
},
{
"epoch": 0.2,
"learning_rate": 1.9935788107327565e-05,
"loss": 1.6151,
"step": 153
},
{
"epoch": 0.2,
"learning_rate": 1.9934214143836038e-05,
"loss": 1.581,
"step": 154
},
{
"epoch": 0.2,
"learning_rate": 1.9932621186339873e-05,
"loss": 1.4626,
"step": 155
},
{
"epoch": 0.2,
"learning_rate": 1.993100923788478e-05,
"loss": 1.5291,
"step": 156
},
{
"epoch": 0.2,
"learning_rate": 1.992937830155276e-05,
"loss": 1.6632,
"step": 157
},
{
"epoch": 0.2,
"learning_rate": 1.9927728380462133e-05,
"loss": 1.5383,
"step": 158
},
{
"epoch": 0.2,
"learning_rate": 1.992605947776752e-05,
"loss": 1.5726,
"step": 159
},
{
"epoch": 0.2,
"learning_rate": 1.9924371596659816e-05,
"loss": 1.5397,
"step": 160
},
{
"epoch": 0.21,
"learning_rate": 1.992266474036622e-05,
"loss": 1.5604,
"step": 161
},
{
"epoch": 0.21,
"learning_rate": 1.99209389121502e-05,
"loss": 1.6912,
"step": 162
},
{
"epoch": 0.21,
"learning_rate": 1.9919194115311505e-05,
"loss": 1.6031,
"step": 163
},
{
"epoch": 0.21,
"learning_rate": 1.9917430353186155e-05,
"loss": 1.4782,
"step": 164
},
{
"epoch": 0.21,
"learning_rate": 1.991564762914641e-05,
"loss": 1.5983,
"step": 165
},
{
"epoch": 0.21,
"learning_rate": 1.991384594660082e-05,
"loss": 1.5054,
"step": 166
},
{
"epoch": 0.21,
"learning_rate": 1.9912025308994146e-05,
"loss": 1.5919,
"step": 167
},
{
"epoch": 0.22,
"learning_rate": 1.991018571980742e-05,
"loss": 1.5814,
"step": 168
},
{
"epoch": 0.22,
"learning_rate": 1.990832718255789e-05,
"loss": 1.6701,
"step": 169
},
{
"epoch": 0.22,
"learning_rate": 1.9906449700799045e-05,
"loss": 1.5032,
"step": 170
},
{
"epoch": 0.22,
"learning_rate": 1.9904553278120585e-05,
"loss": 1.4681,
"step": 171
},
{
"epoch": 0.22,
"learning_rate": 1.9902637918148434e-05,
"loss": 1.6125,
"step": 172
},
{
"epoch": 0.22,
"learning_rate": 1.9900703624544713e-05,
"loss": 1.5088,
"step": 173
},
{
"epoch": 0.22,
"learning_rate": 1.9898750401007755e-05,
"loss": 1.527,
"step": 174
},
{
"epoch": 0.22,
"learning_rate": 1.989677825127208e-05,
"loss": 1.554,
"step": 175
},
{
"epoch": 0.23,
"learning_rate": 1.9894787179108395e-05,
"loss": 1.5321,
"step": 176
},
{
"epoch": 0.23,
"learning_rate": 1.989277718832359e-05,
"loss": 1.584,
"step": 177
},
{
"epoch": 0.23,
"learning_rate": 1.9890748282760723e-05,
"loss": 1.6019,
"step": 178
},
{
"epoch": 0.23,
"learning_rate": 1.988870046629902e-05,
"loss": 1.5916,
"step": 179
},
{
"epoch": 0.23,
"learning_rate": 1.988663374285386e-05,
"loss": 1.5527,
"step": 180
},
{
"epoch": 0.23,
"learning_rate": 1.9884548116376767e-05,
"loss": 1.5735,
"step": 181
},
{
"epoch": 0.23,
"learning_rate": 1.9882443590855427e-05,
"loss": 1.6428,
"step": 182
},
{
"epoch": 0.23,
"learning_rate": 1.988032017031364e-05,
"loss": 1.5624,
"step": 183
},
{
"epoch": 0.24,
"learning_rate": 1.9878177858811346e-05,
"loss": 1.5176,
"step": 184
},
{
"epoch": 0.24,
"learning_rate": 1.9876016660444594e-05,
"loss": 1.4849,
"step": 185
},
{
"epoch": 0.24,
"learning_rate": 1.987383657934555e-05,
"loss": 1.5434,
"step": 186
},
{
"epoch": 0.24,
"learning_rate": 1.987163761968248e-05,
"loss": 1.5246,
"step": 187
},
{
"epoch": 0.24,
"learning_rate": 1.986941978565975e-05,
"loss": 1.346,
"step": 188
},
{
"epoch": 0.24,
"learning_rate": 1.9867183081517812e-05,
"loss": 1.604,
"step": 189
},
{
"epoch": 0.24,
"learning_rate": 1.98649275115332e-05,
"loss": 1.4752,
"step": 190
},
{
"epoch": 0.24,
"learning_rate": 1.9862653080018508e-05,
"loss": 1.5684,
"step": 191
},
{
"epoch": 0.25,
"learning_rate": 1.9860359791322403e-05,
"loss": 1.6076,
"step": 192
},
{
"epoch": 0.25,
"learning_rate": 1.9858047649829607e-05,
"loss": 1.5748,
"step": 193
},
{
"epoch": 0.25,
"learning_rate": 1.985571665996088e-05,
"loss": 1.5715,
"step": 194
},
{
"epoch": 0.25,
"learning_rate": 1.985336682617303e-05,
"loss": 1.6314,
"step": 195
},
{
"epoch": 0.25,
"learning_rate": 1.985099815295888e-05,
"loss": 1.5235,
"step": 196
},
{
"epoch": 0.25,
"learning_rate": 1.9848610644847296e-05,
"loss": 1.4343,
"step": 197
},
{
"epoch": 0.25,
"learning_rate": 1.984620430640313e-05,
"loss": 1.5752,
"step": 198
},
{
"epoch": 0.25,
"learning_rate": 1.9843779142227258e-05,
"loss": 1.5915,
"step": 199
},
{
"epoch": 0.26,
"learning_rate": 1.9841335156956535e-05,
"loss": 1.6355,
"step": 200
},
{
"epoch": 0.26,
"learning_rate": 1.9838872355263813e-05,
"loss": 1.5881,
"step": 201
},
{
"epoch": 0.26,
"learning_rate": 1.9836390741857914e-05,
"loss": 1.4578,
"step": 202
},
{
"epoch": 0.26,
"learning_rate": 1.9833890321483636e-05,
"loss": 1.6122,
"step": 203
},
{
"epoch": 0.26,
"learning_rate": 1.983137109892172e-05,
"loss": 1.4533,
"step": 204
},
{
"epoch": 0.26,
"learning_rate": 1.982883307898887e-05,
"loss": 1.6115,
"step": 205
},
{
"epoch": 0.26,
"learning_rate": 1.9826276266537726e-05,
"loss": 1.5985,
"step": 206
},
{
"epoch": 0.26,
"learning_rate": 1.9823700666456854e-05,
"loss": 1.5907,
"step": 207
},
{
"epoch": 0.27,
"learning_rate": 1.9821106283670753e-05,
"loss": 1.575,
"step": 208
},
{
"epoch": 0.27,
"learning_rate": 1.9818493123139825e-05,
"loss": 1.6302,
"step": 209
},
{
"epoch": 0.27,
"learning_rate": 1.9815861189860373e-05,
"loss": 1.5568,
"step": 210
},
{
"epoch": 0.27,
"learning_rate": 1.9813210488864604e-05,
"loss": 1.6496,
"step": 211
},
{
"epoch": 0.27,
"learning_rate": 1.9810541025220594e-05,
"loss": 1.526,
"step": 212
},
{
"epoch": 0.27,
"learning_rate": 1.9807852804032306e-05,
"loss": 1.5699,
"step": 213
},
{
"epoch": 0.27,
"learning_rate": 1.980514583043956e-05,
"loss": 1.4829,
"step": 214
},
{
"epoch": 0.28,
"learning_rate": 1.980242010961803e-05,
"loss": 1.5604,
"step": 215
},
{
"epoch": 0.28,
"learning_rate": 1.979967564677924e-05,
"loss": 1.4396,
"step": 216
},
{
"epoch": 0.28,
"learning_rate": 1.9796912447170536e-05,
"loss": 1.5015,
"step": 217
},
{
"epoch": 0.28,
"learning_rate": 1.9794130516075104e-05,
"loss": 1.563,
"step": 218
},
{
"epoch": 0.28,
"learning_rate": 1.979132985881193e-05,
"loss": 1.602,
"step": 219
},
{
"epoch": 0.28,
"learning_rate": 1.9788510480735822e-05,
"loss": 1.6708,
"step": 220
},
{
"epoch": 0.28,
"learning_rate": 1.9785672387237357e-05,
"loss": 1.443,
"step": 221
},
{
"epoch": 0.28,
"learning_rate": 1.9782815583742917e-05,
"loss": 1.6391,
"step": 222
},
{
"epoch": 0.29,
"learning_rate": 1.977994007571465e-05,
"loss": 1.4925,
"step": 223
},
{
"epoch": 0.29,
"learning_rate": 1.977704586865046e-05,
"loss": 1.5083,
"step": 224
},
{
"epoch": 0.29,
"learning_rate": 1.9774132968084013e-05,
"loss": 1.5564,
"step": 225
},
{
"epoch": 0.29,
"learning_rate": 1.977120137958471e-05,
"loss": 1.5835,
"step": 226
},
{
"epoch": 0.29,
"learning_rate": 1.976825110875769e-05,
"loss": 1.4686,
"step": 227
},
{
"epoch": 0.29,
"learning_rate": 1.9765282161243803e-05,
"loss": 1.4561,
"step": 228
},
{
"epoch": 0.29,
"learning_rate": 1.9762294542719612e-05,
"loss": 1.5031,
"step": 229
},
{
"epoch": 0.29,
"learning_rate": 1.9759288258897385e-05,
"loss": 1.5902,
"step": 230
},
{
"epoch": 0.3,
"learning_rate": 1.975626331552507e-05,
"loss": 1.6597,
"step": 231
},
{
"epoch": 0.3,
"learning_rate": 1.9753219718386293e-05,
"loss": 1.508,
"step": 232
},
{
"epoch": 0.3,
"learning_rate": 1.9750157473300346e-05,
"loss": 1.6212,
"step": 233
},
{
"epoch": 0.3,
"learning_rate": 1.9747076586122175e-05,
"loss": 1.5397,
"step": 234
},
{
"epoch": 0.3,
"learning_rate": 1.9743977062742373e-05,
"loss": 1.6058,
"step": 235
},
{
"epoch": 0.3,
"learning_rate": 1.9740858909087165e-05,
"loss": 1.5216,
"step": 236
},
{
"epoch": 0.3,
"learning_rate": 1.9737722131118385e-05,
"loss": 1.62,
"step": 237
},
{
"epoch": 0.3,
"learning_rate": 1.9734566734833492e-05,
"loss": 1.5419,
"step": 238
},
{
"epoch": 0.31,
"learning_rate": 1.9731392726265538e-05,
"loss": 1.5845,
"step": 239
},
{
"epoch": 0.31,
"learning_rate": 1.9728200111483155e-05,
"loss": 1.5045,
"step": 240
},
{
"epoch": 0.31,
"learning_rate": 1.9724988896590553e-05,
"loss": 1.5712,
"step": 241
},
{
"epoch": 0.31,
"learning_rate": 1.972175908772751e-05,
"loss": 1.5249,
"step": 242
},
{
"epoch": 0.31,
"learning_rate": 1.9718510691069352e-05,
"loss": 1.5461,
"step": 243
},
{
"epoch": 0.31,
"learning_rate": 1.9715243712826938e-05,
"loss": 1.52,
"step": 244
},
{
"epoch": 0.31,
"learning_rate": 1.9711958159246665e-05,
"loss": 1.4509,
"step": 245
},
{
"epoch": 0.31,
"learning_rate": 1.970865403661044e-05,
"loss": 1.4433,
"step": 246
},
{
"epoch": 0.32,
"learning_rate": 1.9705331351235673e-05,
"loss": 1.555,
"step": 247
},
{
"epoch": 0.32,
"learning_rate": 1.9701990109475273e-05,
"loss": 1.5605,
"step": 248
},
{
"epoch": 0.32,
"learning_rate": 1.9698630317717617e-05,
"loss": 1.6769,
"step": 249
},
{
"epoch": 0.32,
"learning_rate": 1.9695251982386553e-05,
"loss": 1.6464,
"step": 250
},
{
"epoch": 0.32,
"learning_rate": 1.9691855109941394e-05,
"loss": 1.4653,
"step": 251
},
{
"epoch": 0.32,
"learning_rate": 1.968843970687688e-05,
"loss": 1.4217,
"step": 252
},
{
"epoch": 0.32,
"learning_rate": 1.9685005779723192e-05,
"loss": 1.5234,
"step": 253
},
{
"epoch": 0.33,
"learning_rate": 1.9681553335045925e-05,
"loss": 1.5572,
"step": 254
},
{
"epoch": 0.33,
"learning_rate": 1.967808237944608e-05,
"loss": 1.4501,
"step": 255
},
{
"epoch": 0.33,
"learning_rate": 1.9674592919560046e-05,
"loss": 1.5247,
"step": 256
},
{
"epoch": 0.33,
"learning_rate": 1.9671084962059596e-05,
"loss": 1.5897,
"step": 257
},
{
"epoch": 0.33,
"learning_rate": 1.9667558513651875e-05,
"loss": 1.5331,
"step": 258
},
{
"epoch": 0.33,
"learning_rate": 1.966401358107937e-05,
"loss": 1.4277,
"step": 259
},
{
"epoch": 0.33,
"learning_rate": 1.9660450171119923e-05,
"loss": 1.6509,
"step": 260
},
{
"epoch": 0.33,
"learning_rate": 1.965686829058669e-05,
"loss": 1.469,
"step": 261
},
{
"epoch": 0.34,
"learning_rate": 1.965326794632816e-05,
"loss": 1.5032,
"step": 262
},
{
"epoch": 0.34,
"learning_rate": 1.96496491452281e-05,
"loss": 1.4701,
"step": 263
},
{
"epoch": 0.34,
"learning_rate": 1.9646011894205596e-05,
"loss": 1.6634,
"step": 264
},
{
"epoch": 0.34,
"learning_rate": 1.9642356200214977e-05,
"loss": 1.568,
"step": 265
},
{
"epoch": 0.34,
"learning_rate": 1.963868207024587e-05,
"loss": 1.6312,
"step": 266
},
{
"epoch": 0.34,
"learning_rate": 1.9634989511323118e-05,
"loss": 1.6529,
"step": 267
},
{
"epoch": 0.34,
"learning_rate": 1.9631278530506817e-05,
"loss": 1.5365,
"step": 268
},
{
"epoch": 0.34,
"learning_rate": 1.9627549134892293e-05,
"loss": 1.3881,
"step": 269
},
{
"epoch": 0.35,
"learning_rate": 1.962380133161006e-05,
"loss": 1.5303,
"step": 270
},
{
"epoch": 0.35,
"learning_rate": 1.962003512782584e-05,
"loss": 1.6535,
"step": 271
},
{
"epoch": 0.35,
"learning_rate": 1.961625053074054e-05,
"loss": 1.5175,
"step": 272
},
{
"epoch": 0.35,
"learning_rate": 1.9612447547590216e-05,
"loss": 1.6222,
"step": 273
},
{
"epoch": 0.35,
"learning_rate": 1.96086261856461e-05,
"loss": 1.5488,
"step": 274
},
{
"epoch": 0.35,
"learning_rate": 1.9604786452214554e-05,
"loss": 1.5521,
"step": 275
},
{
"epoch": 0.35,
"learning_rate": 1.9600928354637063e-05,
"loss": 1.6231,
"step": 276
},
{
"epoch": 0.35,
"learning_rate": 1.959705190029023e-05,
"loss": 1.6081,
"step": 277
},
{
"epoch": 0.36,
"learning_rate": 1.9593157096585747e-05,
"loss": 1.5731,
"step": 278
},
{
"epoch": 0.36,
"learning_rate": 1.95892439509704e-05,
"loss": 1.5925,
"step": 279
},
{
"epoch": 0.36,
"learning_rate": 1.9585312470926043e-05,
"loss": 1.4548,
"step": 280
},
{
"epoch": 0.36,
"learning_rate": 1.9581362663969572e-05,
"loss": 1.5281,
"step": 281
},
{
"epoch": 0.36,
"learning_rate": 1.957739453765294e-05,
"loss": 1.5626,
"step": 282
},
{
"epoch": 0.36,
"learning_rate": 1.957340809956312e-05,
"loss": 1.646,
"step": 283
},
{
"epoch": 0.36,
"learning_rate": 1.956940335732209e-05,
"loss": 1.4231,
"step": 284
},
{
"epoch": 0.36,
"learning_rate": 1.9565380318586838e-05,
"loss": 1.5245,
"step": 285
},
{
"epoch": 0.37,
"learning_rate": 1.9561338991049323e-05,
"loss": 1.4708,
"step": 286
},
{
"epoch": 0.37,
"learning_rate": 1.9557279382436483e-05,
"loss": 1.6048,
"step": 287
},
{
"epoch": 0.37,
"learning_rate": 1.9553201500510197e-05,
"loss": 1.5894,
"step": 288
},
{
"epoch": 0.37,
"learning_rate": 1.954910535306729e-05,
"loss": 1.4496,
"step": 289
},
{
"epoch": 0.37,
"learning_rate": 1.9544990947939504e-05,
"loss": 1.4983,
"step": 290
},
{
"epoch": 0.37,
"learning_rate": 1.95408582929935e-05,
"loss": 1.4941,
"step": 291
},
{
"epoch": 0.37,
"learning_rate": 1.9536707396130826e-05,
"loss": 1.5229,
"step": 292
},
{
"epoch": 0.38,
"learning_rate": 1.95325382652879e-05,
"loss": 1.5914,
"step": 293
},
{
"epoch": 0.38,
"learning_rate": 1.952835090843602e-05,
"loss": 1.4926,
"step": 294
},
{
"epoch": 0.38,
"learning_rate": 1.9524145333581315e-05,
"loss": 1.5251,
"step": 295
},
{
"epoch": 0.38,
"learning_rate": 1.951992154876476e-05,
"loss": 1.6215,
"step": 296
},
{
"epoch": 0.38,
"learning_rate": 1.951567956206214e-05,
"loss": 1.5768,
"step": 297
},
{
"epoch": 0.38,
"learning_rate": 1.9511419381584033e-05,
"loss": 1.5086,
"step": 298
},
{
"epoch": 0.38,
"learning_rate": 1.9507141015475828e-05,
"loss": 1.5019,
"step": 299
},
{
"epoch": 0.38,
"learning_rate": 1.950284447191766e-05,
"loss": 1.5381,
"step": 300
},
{
"epoch": 0.39,
"learning_rate": 1.949852975912443e-05,
"loss": 1.5158,
"step": 301
},
{
"epoch": 0.39,
"learning_rate": 1.949419688534578e-05,
"loss": 1.507,
"step": 302
},
{
"epoch": 0.39,
"learning_rate": 1.9489845858866066e-05,
"loss": 1.6007,
"step": 303
},
{
"epoch": 0.39,
"learning_rate": 1.948547668800436e-05,
"loss": 1.5318,
"step": 304
},
{
"epoch": 0.39,
"learning_rate": 1.9481089381114427e-05,
"loss": 1.544,
"step": 305
},
{
"epoch": 0.39,
"learning_rate": 1.94766839465847e-05,
"loss": 1.6778,
"step": 306
},
{
"epoch": 0.39,
"learning_rate": 1.9472260392838272e-05,
"loss": 1.4475,
"step": 307
},
{
"epoch": 0.39,
"learning_rate": 1.9467818728332887e-05,
"loss": 1.4946,
"step": 308
},
{
"epoch": 0.4,
"learning_rate": 1.946335896156091e-05,
"loss": 1.4903,
"step": 309
},
{
"epoch": 0.4,
"learning_rate": 1.945888110104933e-05,
"loss": 1.5962,
"step": 310
},
{
"epoch": 0.4,
"learning_rate": 1.9454385155359704e-05,
"loss": 1.4955,
"step": 311
},
{
"epoch": 0.4,
"learning_rate": 1.9449871133088197e-05,
"loss": 1.4937,
"step": 312
},
{
"epoch": 0.4,
"learning_rate": 1.9445339042865513e-05,
"loss": 1.5271,
"step": 313
},
{
"epoch": 0.4,
"learning_rate": 1.9440788893356917e-05,
"loss": 1.4787,
"step": 314
},
{
"epoch": 0.4,
"learning_rate": 1.9436220693262196e-05,
"loss": 1.5266,
"step": 315
},
{
"epoch": 0.4,
"learning_rate": 1.9431634451315656e-05,
"loss": 1.59,
"step": 316
},
{
"epoch": 0.41,
"learning_rate": 1.9427030176286084e-05,
"loss": 1.5541,
"step": 317
},
{
"epoch": 0.41,
"learning_rate": 1.942240787697676e-05,
"loss": 1.5428,
"step": 318
},
{
"epoch": 0.41,
"learning_rate": 1.9417767562225422e-05,
"loss": 1.5705,
"step": 319
},
{
"epoch": 0.41,
"learning_rate": 1.941310924090425e-05,
"loss": 1.5075,
"step": 320
},
{
"epoch": 0.41,
"learning_rate": 1.9408432921919858e-05,
"loss": 1.6058,
"step": 321
},
{
"epoch": 0.41,
"learning_rate": 1.9403738614213266e-05,
"loss": 1.5554,
"step": 322
},
{
"epoch": 0.41,
"learning_rate": 1.9399026326759886e-05,
"loss": 1.426,
"step": 323
},
{
"epoch": 0.41,
"learning_rate": 1.9394296068569517e-05,
"loss": 1.5018,
"step": 324
},
{
"epoch": 0.42,
"learning_rate": 1.938954784868631e-05,
"loss": 1.479,
"step": 325
},
{
"epoch": 0.42,
"learning_rate": 1.9384781676188756e-05,
"loss": 1.6239,
"step": 326
},
{
"epoch": 0.42,
"learning_rate": 1.9379997560189677e-05,
"loss": 1.4323,
"step": 327
},
{
"epoch": 0.42,
"learning_rate": 1.93751955098362e-05,
"loss": 1.5905,
"step": 328
},
{
"epoch": 0.42,
"learning_rate": 1.9370375534309743e-05,
"loss": 1.559,
"step": 329
},
{
"epoch": 0.42,
"learning_rate": 1.9365537642825996e-05,
"loss": 1.5472,
"step": 330
},
{
"epoch": 0.42,
"learning_rate": 1.9360681844634903e-05,
"loss": 1.4352,
"step": 331
},
{
"epoch": 0.42,
"learning_rate": 1.9355808149020645e-05,
"loss": 1.5759,
"step": 332
},
{
"epoch": 0.43,
"learning_rate": 1.935091656530163e-05,
"loss": 1.5138,
"step": 333
},
{
"epoch": 0.43,
"learning_rate": 1.934600710283045e-05,
"loss": 1.4506,
"step": 334
},
{
"epoch": 0.43,
"learning_rate": 1.93410797709939e-05,
"loss": 1.5263,
"step": 335
},
{
"epoch": 0.43,
"learning_rate": 1.9336134579212933e-05,
"loss": 1.447,
"step": 336
},
{
"epoch": 0.43,
"learning_rate": 1.933117153694265e-05,
"loss": 1.4765,
"step": 337
},
{
"epoch": 0.43,
"learning_rate": 1.9326190653672277e-05,
"loss": 1.5694,
"step": 338
},
{
"epoch": 0.43,
"learning_rate": 1.9321191938925156e-05,
"loss": 1.5056,
"step": 339
},
{
"epoch": 0.44,
"learning_rate": 1.9316175402258733e-05,
"loss": 1.53,
"step": 340
},
{
"epoch": 0.44,
"learning_rate": 1.9311141053264502e-05,
"loss": 1.5962,
"step": 341
},
{
"epoch": 0.44,
"learning_rate": 1.9306088901568047e-05,
"loss": 1.6619,
"step": 342
},
{
"epoch": 0.44,
"learning_rate": 1.9301018956828966e-05,
"loss": 1.5669,
"step": 343
},
{
"epoch": 0.44,
"learning_rate": 1.9295931228740882e-05,
"loss": 1.5196,
"step": 344
},
{
"epoch": 0.44,
"learning_rate": 1.9290825727031425e-05,
"loss": 1.5164,
"step": 345
},
{
"epoch": 0.44,
"learning_rate": 1.9285702461462204e-05,
"loss": 1.5818,
"step": 346
},
{
"epoch": 0.44,
"learning_rate": 1.9280561441828794e-05,
"loss": 1.5524,
"step": 347
},
{
"epoch": 0.45,
"learning_rate": 1.9275402677960716e-05,
"loss": 1.5758,
"step": 348
},
{
"epoch": 0.45,
"learning_rate": 1.9270226179721416e-05,
"loss": 1.4895,
"step": 349
},
{
"epoch": 0.45,
"learning_rate": 1.9265031957008243e-05,
"loss": 1.5604,
"step": 350
},
{
"epoch": 0.45,
"learning_rate": 1.9259820019752445e-05,
"loss": 1.6659,
"step": 351
},
{
"epoch": 0.45,
"learning_rate": 1.9254590377919128e-05,
"loss": 1.5113,
"step": 352
},
{
"epoch": 0.45,
"learning_rate": 1.9249343041507264e-05,
"loss": 1.492,
"step": 353
},
{
"epoch": 0.45,
"learning_rate": 1.924407802054964e-05,
"loss": 1.5277,
"step": 354
},
{
"epoch": 0.45,
"learning_rate": 1.9238795325112867e-05,
"loss": 1.5835,
"step": 355
},
{
"epoch": 0.46,
"learning_rate": 1.923349496529735e-05,
"loss": 1.5611,
"step": 356
},
{
"epoch": 0.46,
"learning_rate": 1.9228176951237252e-05,
"loss": 1.6418,
"step": 357
},
{
"epoch": 0.46,
"learning_rate": 1.922284129310051e-05,
"loss": 1.512,
"step": 358
},
{
"epoch": 0.46,
"learning_rate": 1.9217488001088784e-05,
"loss": 1.6668,
"step": 359
},
{
"epoch": 0.46,
"learning_rate": 1.921211708543746e-05,
"loss": 1.4548,
"step": 360
},
{
"epoch": 0.46,
"learning_rate": 1.9206728556415604e-05,
"loss": 1.5987,
"step": 361
},
{
"epoch": 0.46,
"learning_rate": 1.9201322424325982e-05,
"loss": 1.5106,
"step": 362
},
{
"epoch": 0.46,
"learning_rate": 1.919589869950499e-05,
"loss": 1.6269,
"step": 363
},
{
"epoch": 0.47,
"learning_rate": 1.9190457392322677e-05,
"loss": 1.5116,
"step": 364
},
{
"epoch": 0.47,
"learning_rate": 1.9184998513182705e-05,
"loss": 1.5542,
"step": 365
},
{
"epoch": 0.47,
"learning_rate": 1.917952207252234e-05,
"loss": 1.6317,
"step": 366
},
{
"epoch": 0.47,
"learning_rate": 1.9174028080812415e-05,
"loss": 1.5089,
"step": 367
},
{
"epoch": 0.47,
"learning_rate": 1.9168516548557322e-05,
"loss": 1.4765,
"step": 368
},
{
"epoch": 0.47,
"learning_rate": 1.9162987486295e-05,
"loss": 1.5436,
"step": 369
},
{
"epoch": 0.47,
"learning_rate": 1.9157440904596886e-05,
"loss": 1.536,
"step": 370
},
{
"epoch": 0.47,
"learning_rate": 1.9151876814067932e-05,
"loss": 1.6647,
"step": 371
},
{
"epoch": 0.48,
"learning_rate": 1.9146295225346566e-05,
"loss": 1.4496,
"step": 372
},
{
"epoch": 0.48,
"learning_rate": 1.9140696149104657e-05,
"loss": 1.5858,
"step": 373
},
{
"epoch": 0.48,
"learning_rate": 1.9135079596047522e-05,
"loss": 1.4961,
"step": 374
},
{
"epoch": 0.48,
"learning_rate": 1.9129445576913886e-05,
"loss": 1.5313,
"step": 375
},
{
"epoch": 0.48,
"learning_rate": 1.9123794102475884e-05,
"loss": 1.6396,
"step": 376
},
{
"epoch": 0.48,
"learning_rate": 1.9118125183539003e-05,
"loss": 1.5159,
"step": 377
},
{
"epoch": 0.48,
"learning_rate": 1.91124388309421e-05,
"loss": 1.5542,
"step": 378
},
{
"epoch": 0.49,
"learning_rate": 1.910673505555736e-05,
"loss": 1.5676,
"step": 379
},
{
"epoch": 0.49,
"learning_rate": 1.9101013868290274e-05,
"loss": 1.4897,
"step": 380
},
{
"epoch": 0.49,
"learning_rate": 1.909527528007963e-05,
"loss": 1.5595,
"step": 381
},
{
"epoch": 0.49,
"learning_rate": 1.9089519301897494e-05,
"loss": 1.528,
"step": 382
},
{
"epoch": 0.49,
"learning_rate": 1.9083745944749163e-05,
"loss": 1.4923,
"step": 383
},
{
"epoch": 0.49,
"learning_rate": 1.907795521967318e-05,
"loss": 1.4445,
"step": 384
},
{
"epoch": 0.49,
"learning_rate": 1.907214713774128e-05,
"loss": 1.3598,
"step": 385
},
{
"epoch": 0.49,
"learning_rate": 1.90663217100584e-05,
"loss": 1.5494,
"step": 386
},
{
"epoch": 0.5,
"learning_rate": 1.9060478947762625e-05,
"loss": 1.5066,
"step": 387
},
{
"epoch": 0.5,
"learning_rate": 1.9054618862025198e-05,
"loss": 1.5562,
"step": 388
},
{
"epoch": 0.5,
"learning_rate": 1.9048741464050468e-05,
"loss": 1.5286,
"step": 389
},
{
"epoch": 0.5,
"learning_rate": 1.9042846765075905e-05,
"loss": 1.5854,
"step": 390
},
{
"epoch": 0.5,
"learning_rate": 1.903693477637204e-05,
"loss": 1.6033,
"step": 391
},
{
"epoch": 0.5,
"learning_rate": 1.903100550924247e-05,
"loss": 1.5679,
"step": 392
},
{
"epoch": 0.5,
"learning_rate": 1.902505897502383e-05,
"loss": 1.5367,
"step": 393
},
{
"epoch": 0.5,
"learning_rate": 1.901909518508576e-05,
"loss": 1.5428,
"step": 394
},
{
"epoch": 0.51,
"learning_rate": 1.9013114150830904e-05,
"loss": 1.5304,
"step": 395
},
{
"epoch": 0.51,
"learning_rate": 1.9007115883694872e-05,
"loss": 1.6188,
"step": 396
},
{
"epoch": 0.51,
"learning_rate": 1.9001100395146216e-05,
"loss": 1.5219,
"step": 397
},
{
"epoch": 0.51,
"learning_rate": 1.899506769668643e-05,
"loss": 1.5169,
"step": 398
},
{
"epoch": 0.51,
"learning_rate": 1.8989017799849896e-05,
"loss": 1.3971,
"step": 399
},
{
"epoch": 0.51,
"learning_rate": 1.8982950716203888e-05,
"loss": 1.5518,
"step": 400
},
{
"epoch": 0.51,
"learning_rate": 1.8976866457348547e-05,
"loss": 1.4723,
"step": 401
},
{
"epoch": 0.51,
"learning_rate": 1.897076503491684e-05,
"loss": 1.4152,
"step": 402
},
{
"epoch": 0.52,
"learning_rate": 1.8964646460574555e-05,
"loss": 1.5079,
"step": 403
},
{
"epoch": 0.52,
"learning_rate": 1.8958510746020276e-05,
"loss": 1.5701,
"step": 404
},
{
"epoch": 0.52,
"learning_rate": 1.8952357902985363e-05,
"loss": 1.6675,
"step": 405
},
{
"epoch": 0.52,
"learning_rate": 1.894618794323391e-05,
"loss": 1.5312,
"step": 406
},
{
"epoch": 0.52,
"learning_rate": 1.8940000878562758e-05,
"loss": 1.503,
"step": 407
},
{
"epoch": 0.52,
"learning_rate": 1.8933796720801437e-05,
"loss": 1.5588,
"step": 408
},
{
"epoch": 0.52,
"learning_rate": 1.8927575481812168e-05,
"loss": 1.6306,
"step": 409
},
{
"epoch": 0.52,
"learning_rate": 1.892133717348982e-05,
"loss": 1.5523,
"step": 410
},
{
"epoch": 0.53,
"learning_rate": 1.8915081807761907e-05,
"loss": 1.489,
"step": 411
},
{
"epoch": 0.53,
"learning_rate": 1.8908809396588557e-05,
"loss": 1.4722,
"step": 412
},
{
"epoch": 0.53,
"learning_rate": 1.8902519951962483e-05,
"loss": 1.6297,
"step": 413
},
{
"epoch": 0.53,
"learning_rate": 1.889621348590897e-05,
"loss": 1.4199,
"step": 414
},
{
"epoch": 0.53,
"learning_rate": 1.8889890010485847e-05,
"loss": 1.5319,
"step": 415
},
{
"epoch": 0.53,
"learning_rate": 1.888354953778346e-05,
"loss": 1.5826,
"step": 416
},
{
"epoch": 0.53,
"learning_rate": 1.887719207992466e-05,
"loss": 1.5537,
"step": 417
},
{
"epoch": 0.54,
"learning_rate": 1.887081764906477e-05,
"loss": 1.6173,
"step": 418
},
{
"epoch": 0.54,
"learning_rate": 1.8864426257391567e-05,
"loss": 1.5516,
"step": 419
},
{
"epoch": 0.54,
"learning_rate": 1.885801791712525e-05,
"loss": 1.6347,
"step": 420
},
{
"epoch": 0.54,
"learning_rate": 1.8851592640518433e-05,
"loss": 1.4851,
"step": 421
},
{
"epoch": 0.54,
"learning_rate": 1.8845150439856102e-05,
"loss": 1.3995,
"step": 422
},
{
"epoch": 0.54,
"learning_rate": 1.883869132745561e-05,
"loss": 1.5242,
"step": 423
},
{
"epoch": 0.54,
"learning_rate": 1.8832215315666645e-05,
"loss": 1.4844,
"step": 424
},
{
"epoch": 0.54,
"learning_rate": 1.8825722416871197e-05,
"loss": 1.6318,
"step": 425
},
{
"epoch": 0.55,
"learning_rate": 1.881921264348355e-05,
"loss": 1.5529,
"step": 426
},
{
"epoch": 0.55,
"learning_rate": 1.8812686007950257e-05,
"loss": 1.571,
"step": 427
},
{
"epoch": 0.55,
"learning_rate": 1.8806142522750098e-05,
"loss": 1.481,
"step": 428
},
{
"epoch": 0.55,
"learning_rate": 1.879958220039408e-05,
"loss": 1.5949,
"step": 429
},
{
"epoch": 0.55,
"learning_rate": 1.87930050534254e-05,
"loss": 1.5699,
"step": 430
},
{
"epoch": 0.55,
"learning_rate": 1.878641109441942e-05,
"loss": 1.5897,
"step": 431
},
{
"epoch": 0.55,
"learning_rate": 1.8779800335983648e-05,
"loss": 1.4738,
"step": 432
},
{
"epoch": 0.55,
"learning_rate": 1.8773172790757713e-05,
"loss": 1.5033,
"step": 433
},
{
"epoch": 0.56,
"learning_rate": 1.876652847141334e-05,
"loss": 1.4432,
"step": 434
},
{
"epoch": 0.56,
"learning_rate": 1.8759867390654326e-05,
"loss": 1.4978,
"step": 435
},
{
"epoch": 0.56,
"learning_rate": 1.8753189561216514e-05,
"loss": 1.6507,
"step": 436
},
{
"epoch": 0.56,
"learning_rate": 1.874649499586777e-05,
"loss": 1.4505,
"step": 437
},
{
"epoch": 0.56,
"learning_rate": 1.8739783707407965e-05,
"loss": 1.5597,
"step": 438
},
{
"epoch": 0.56,
"learning_rate": 1.8733055708668928e-05,
"loss": 1.5849,
"step": 439
},
{
"epoch": 0.56,
"learning_rate": 1.872631101251446e-05,
"loss": 1.4635,
"step": 440
},
{
"epoch": 0.56,
"learning_rate": 1.8719549631840266e-05,
"loss": 1.5478,
"step": 441
},
{
"epoch": 0.57,
"learning_rate": 1.8712771579573968e-05,
"loss": 1.5115,
"step": 442
},
{
"epoch": 0.57,
"learning_rate": 1.870597686867505e-05,
"loss": 1.6138,
"step": 443
},
{
"epoch": 0.57,
"learning_rate": 1.869916551213486e-05,
"loss": 1.441,
"step": 444
},
{
"epoch": 0.57,
"learning_rate": 1.869233752297656e-05,
"loss": 1.4458,
"step": 445
},
{
"epoch": 0.57,
"learning_rate": 1.868549291425513e-05,
"loss": 1.4579,
"step": 446
},
{
"epoch": 0.57,
"learning_rate": 1.86786316990573e-05,
"loss": 1.4856,
"step": 447
},
{
"epoch": 0.57,
"learning_rate": 1.867175389050158e-05,
"loss": 1.6457,
"step": 448
},
{
"epoch": 0.57,
"learning_rate": 1.8664859501738183e-05,
"loss": 1.5344,
"step": 449
},
{
"epoch": 0.58,
"learning_rate": 1.8657948545949036e-05,
"loss": 1.4316,
"step": 450
},
{
"epoch": 0.58,
"learning_rate": 1.865102103634774e-05,
"loss": 1.6006,
"step": 451
},
{
"epoch": 0.58,
"learning_rate": 1.8644076986179543e-05,
"loss": 1.5681,
"step": 452
},
{
"epoch": 0.58,
"learning_rate": 1.8637116408721324e-05,
"loss": 1.4692,
"step": 453
},
{
"epoch": 0.58,
"learning_rate": 1.8630139317281554e-05,
"loss": 1.4087,
"step": 454
},
{
"epoch": 0.58,
"learning_rate": 1.862314572520028e-05,
"loss": 1.637,
"step": 455
},
{
"epoch": 0.58,
"learning_rate": 1.8616135645849106e-05,
"loss": 1.5485,
"step": 456
},
{
"epoch": 0.58,
"learning_rate": 1.860910909263115e-05,
"loss": 1.3215,
"step": 457
},
{
"epoch": 0.59,
"learning_rate": 1.860206607898103e-05,
"loss": 1.6119,
"step": 458
},
{
"epoch": 0.59,
"learning_rate": 1.8595006618364843e-05,
"loss": 1.582,
"step": 459
},
{
"epoch": 0.59,
"learning_rate": 1.8587930724280124e-05,
"loss": 1.5267,
"step": 460
},
{
"epoch": 0.59,
"learning_rate": 1.8580838410255825e-05,
"loss": 1.5518,
"step": 461
},
{
"epoch": 0.59,
"learning_rate": 1.8573729689852307e-05,
"loss": 1.4138,
"step": 462
},
{
"epoch": 0.59,
"learning_rate": 1.8566604576661288e-05,
"loss": 1.654,
"step": 463
},
{
"epoch": 0.59,
"learning_rate": 1.855946308430583e-05,
"loss": 1.6676,
"step": 464
},
{
"epoch": 0.6,
"learning_rate": 1.8552305226440315e-05,
"loss": 1.5533,
"step": 465
},
{
"epoch": 0.6,
"learning_rate": 1.8545131016750413e-05,
"loss": 1.6206,
"step": 466
},
{
"epoch": 0.6,
"learning_rate": 1.853794046895306e-05,
"loss": 1.5267,
"step": 467
},
{
"epoch": 0.6,
"learning_rate": 1.853073359679643e-05,
"loss": 1.4732,
"step": 468
},
{
"epoch": 0.6,
"learning_rate": 1.8523510414059903e-05,
"loss": 1.5234,
"step": 469
},
{
"epoch": 0.6,
"learning_rate": 1.851627093455406e-05,
"loss": 1.5687,
"step": 470
},
{
"epoch": 0.6,
"learning_rate": 1.850901517212062e-05,
"loss": 1.4919,
"step": 471
},
{
"epoch": 0.6,
"learning_rate": 1.8501743140632457e-05,
"loss": 1.4328,
"step": 472
},
{
"epoch": 0.61,
"learning_rate": 1.8494454853993527e-05,
"loss": 1.5762,
"step": 473
},
{
"epoch": 0.61,
"learning_rate": 1.8487150326138884e-05,
"loss": 1.5325,
"step": 474
},
{
"epoch": 0.61,
"learning_rate": 1.847982957103463e-05,
"loss": 1.5702,
"step": 475
},
{
"epoch": 0.61,
"learning_rate": 1.847249260267789e-05,
"loss": 1.5487,
"step": 476
},
{
"epoch": 0.61,
"learning_rate": 1.8465139435096787e-05,
"loss": 1.5621,
"step": 477
},
{
"epoch": 0.61,
"learning_rate": 1.8457770082350426e-05,
"loss": 1.6269,
"step": 478
},
{
"epoch": 0.61,
"learning_rate": 1.8450384558528848e-05,
"loss": 1.5245,
"step": 479
},
{
"epoch": 0.61,
"learning_rate": 1.8442982877753016e-05,
"loss": 1.4432,
"step": 480
},
{
"epoch": 0.62,
"learning_rate": 1.8435565054174792e-05,
"loss": 1.6035,
"step": 481
},
{
"epoch": 0.62,
"learning_rate": 1.8428131101976884e-05,
"loss": 1.5814,
"step": 482
},
{
"epoch": 0.62,
"learning_rate": 1.8420681035372858e-05,
"loss": 1.6586,
"step": 483
},
{
"epoch": 0.62,
"learning_rate": 1.841321486860708e-05,
"loss": 1.4699,
"step": 484
},
{
"epoch": 0.62,
"learning_rate": 1.84057326159547e-05,
"loss": 1.5394,
"step": 485
},
{
"epoch": 0.62,
"learning_rate": 1.8398234291721622e-05,
"loss": 1.5886,
"step": 486
},
{
"epoch": 0.62,
"learning_rate": 1.8390719910244487e-05,
"loss": 1.5667,
"step": 487
},
{
"epoch": 0.62,
"learning_rate": 1.8383189485890632e-05,
"loss": 1.5693,
"step": 488
},
{
"epoch": 0.63,
"learning_rate": 1.8375643033058058e-05,
"loss": 1.4013,
"step": 489
},
{
"epoch": 0.63,
"learning_rate": 1.836808056617543e-05,
"loss": 1.4577,
"step": 490
},
{
"epoch": 0.63,
"learning_rate": 1.8360502099702016e-05,
"loss": 1.4651,
"step": 491
},
{
"epoch": 0.63,
"learning_rate": 1.8352907648127688e-05,
"loss": 1.5245,
"step": 492
},
{
"epoch": 0.63,
"learning_rate": 1.8345297225972873e-05,
"loss": 1.4243,
"step": 493
},
{
"epoch": 0.63,
"learning_rate": 1.8337670847788535e-05,
"loss": 1.5857,
"step": 494
},
{
"epoch": 0.63,
"learning_rate": 1.8330028528156138e-05,
"loss": 1.5347,
"step": 495
},
{
"epoch": 0.63,
"learning_rate": 1.8322370281687644e-05,
"loss": 1.6043,
"step": 496
},
{
"epoch": 0.64,
"learning_rate": 1.8314696123025456e-05,
"loss": 1.5089,
"step": 497
},
{
"epoch": 0.64,
"learning_rate": 1.830700606684239e-05,
"loss": 1.4643,
"step": 498
},
{
"epoch": 0.64,
"learning_rate": 1.8299300127841683e-05,
"loss": 1.6145,
"step": 499
},
{
"epoch": 0.64,
"learning_rate": 1.8291578320756913e-05,
"loss": 1.4843,
"step": 500
},
{
"epoch": 0.64,
"learning_rate": 1.8283840660352017e-05,
"loss": 1.6487,
"step": 501
},
{
"epoch": 0.64,
"learning_rate": 1.8276087161421234e-05,
"loss": 1.5171,
"step": 502
},
{
"epoch": 0.64,
"learning_rate": 1.826831783878909e-05,
"loss": 1.5883,
"step": 503
},
{
"epoch": 0.65,
"learning_rate": 1.826053270731036e-05,
"loss": 1.5624,
"step": 504
},
{
"epoch": 0.65,
"learning_rate": 1.8252731781870046e-05,
"loss": 1.5277,
"step": 505
},
{
"epoch": 0.65,
"learning_rate": 1.8244915077383358e-05,
"loss": 1.4787,
"step": 506
},
{
"epoch": 0.65,
"learning_rate": 1.8237082608795664e-05,
"loss": 1.5277,
"step": 507
},
{
"epoch": 0.65,
"learning_rate": 1.8229234391082472e-05,
"loss": 1.5259,
"step": 508
},
{
"epoch": 0.65,
"learning_rate": 1.8221370439249412e-05,
"loss": 1.628,
"step": 509
},
{
"epoch": 0.65,
"learning_rate": 1.8213490768332193e-05,
"loss": 1.5003,
"step": 510
},
{
"epoch": 0.65,
"learning_rate": 1.820559539339657e-05,
"loss": 1.5083,
"step": 511
},
{
"epoch": 0.66,
"learning_rate": 1.819768432953833e-05,
"loss": 1.4897,
"step": 512
},
{
"epoch": 0.66,
"learning_rate": 1.818975759188327e-05,
"loss": 1.5501,
"step": 513
},
{
"epoch": 0.66,
"learning_rate": 1.818181519558713e-05,
"loss": 1.5783,
"step": 514
},
{
"epoch": 0.66,
"learning_rate": 1.817385715583561e-05,
"loss": 1.4158,
"step": 515
},
{
"epoch": 0.66,
"learning_rate": 1.81658834878443e-05,
"loss": 1.5979,
"step": 516
},
{
"epoch": 0.66,
"learning_rate": 1.8157894206858698e-05,
"loss": 1.5257,
"step": 517
},
{
"epoch": 0.66,
"learning_rate": 1.8149889328154123e-05,
"loss": 1.4823,
"step": 518
},
{
"epoch": 0.66,
"learning_rate": 1.8141868867035745e-05,
"loss": 1.6418,
"step": 519
},
{
"epoch": 0.67,
"learning_rate": 1.8133832838838503e-05,
"loss": 1.5138,
"step": 520
},
{
"epoch": 0.67,
"learning_rate": 1.8125781258927116e-05,
"loss": 1.5885,
"step": 521
},
{
"epoch": 0.67,
"learning_rate": 1.811771414269603e-05,
"loss": 1.412,
"step": 522
},
{
"epoch": 0.67,
"learning_rate": 1.8109631505569404e-05,
"loss": 1.5144,
"step": 523
},
{
"epoch": 0.67,
"learning_rate": 1.810153336300106e-05,
"loss": 1.6172,
"step": 524
},
{
"epoch": 0.67,
"learning_rate": 1.809341973047448e-05,
"loss": 1.6128,
"step": 525
},
{
"epoch": 0.67,
"learning_rate": 1.808529062350275e-05,
"loss": 1.4841,
"step": 526
},
{
"epoch": 0.67,
"learning_rate": 1.8077146057628547e-05,
"loss": 1.543,
"step": 527
},
{
"epoch": 0.68,
"learning_rate": 1.806898604842411e-05,
"loss": 1.5263,
"step": 528
},
{
"epoch": 0.68,
"learning_rate": 1.8060810611491203e-05,
"loss": 1.4654,
"step": 529
},
{
"epoch": 0.68,
"learning_rate": 1.8052619762461084e-05,
"loss": 1.59,
"step": 530
},
{
"epoch": 0.68,
"learning_rate": 1.8044413516994483e-05,
"loss": 1.4533,
"step": 531
},
{
"epoch": 0.68,
"learning_rate": 1.8036191890781563e-05,
"loss": 1.5751,
"step": 532
},
{
"epoch": 0.68,
"learning_rate": 1.8027954899541894e-05,
"loss": 1.5516,
"step": 533
},
{
"epoch": 0.68,
"learning_rate": 1.8019702559024437e-05,
"loss": 1.546,
"step": 534
},
{
"epoch": 0.68,
"learning_rate": 1.8011434885007482e-05,
"loss": 1.5633,
"step": 535
},
{
"epoch": 0.69,
"learning_rate": 1.8003151893298646e-05,
"loss": 1.5256,
"step": 536
},
{
"epoch": 0.69,
"learning_rate": 1.7994853599734835e-05,
"loss": 1.5775,
"step": 537
},
{
"epoch": 0.69,
"learning_rate": 1.7986540020182207e-05,
"loss": 1.4661,
"step": 538
},
{
"epoch": 0.69,
"learning_rate": 1.7978211170536145e-05,
"loss": 1.4995,
"step": 539
},
{
"epoch": 0.69,
"learning_rate": 1.7969867066721234e-05,
"loss": 1.6578,
"step": 540
},
{
"epoch": 0.69,
"learning_rate": 1.796150772469122e-05,
"loss": 1.4593,
"step": 541
},
{
"epoch": 0.69,
"learning_rate": 1.795313316042899e-05,
"loss": 1.5147,
"step": 542
},
{
"epoch": 0.7,
"learning_rate": 1.7944743389946524e-05,
"loss": 1.6462,
"step": 543
},
{
"epoch": 0.7,
"learning_rate": 1.793633842928489e-05,
"loss": 1.4628,
"step": 544
},
{
"epoch": 0.7,
"learning_rate": 1.792791829451419e-05,
"loss": 1.3819,
"step": 545
},
{
"epoch": 0.7,
"learning_rate": 1.791948300173354e-05,
"loss": 1.5975,
"step": 546
},
{
"epoch": 0.7,
"learning_rate": 1.7911032567071044e-05,
"loss": 1.5558,
"step": 547
},
{
"epoch": 0.7,
"learning_rate": 1.7902567006683747e-05,
"loss": 1.6226,
"step": 548
},
{
"epoch": 0.7,
"learning_rate": 1.7894086336757627e-05,
"loss": 1.5697,
"step": 549
},
{
"epoch": 0.7,
"learning_rate": 1.788559057350753e-05,
"loss": 1.4851,
"step": 550
},
{
"epoch": 0.71,
"learning_rate": 1.7877079733177185e-05,
"loss": 1.4857,
"step": 551
},
{
"epoch": 0.71,
"learning_rate": 1.7868553832039128e-05,
"loss": 1.4548,
"step": 552
},
{
"epoch": 0.71,
"learning_rate": 1.786001288639471e-05,
"loss": 1.5372,
"step": 553
},
{
"epoch": 0.71,
"learning_rate": 1.7851456912574022e-05,
"loss": 1.667,
"step": 554
},
{
"epoch": 0.71,
"learning_rate": 1.7842885926935917e-05,
"loss": 1.5669,
"step": 555
},
{
"epoch": 0.71,
"learning_rate": 1.7834299945867926e-05,
"loss": 1.5722,
"step": 556
},
{
"epoch": 0.71,
"learning_rate": 1.7825698985786264e-05,
"loss": 1.4489,
"step": 557
},
{
"epoch": 0.71,
"learning_rate": 1.7817083063135782e-05,
"loss": 1.4824,
"step": 558
},
{
"epoch": 0.72,
"learning_rate": 1.780845219438994e-05,
"loss": 1.5446,
"step": 559
},
{
"epoch": 0.72,
"learning_rate": 1.779980639605077e-05,
"loss": 1.5276,
"step": 560
},
{
"epoch": 0.72,
"learning_rate": 1.7791145684648864e-05,
"loss": 1.4949,
"step": 561
},
{
"epoch": 0.72,
"learning_rate": 1.778247007674331e-05,
"loss": 1.4785,
"step": 562
},
{
"epoch": 0.72,
"learning_rate": 1.777377958892168e-05,
"loss": 1.6022,
"step": 563
},
{
"epoch": 0.72,
"learning_rate": 1.776507423780001e-05,
"loss": 1.5496,
"step": 564
},
{
"epoch": 0.72,
"learning_rate": 1.7756354040022736e-05,
"loss": 1.5412,
"step": 565
},
{
"epoch": 0.72,
"learning_rate": 1.7747619012262697e-05,
"loss": 1.5029,
"step": 566
},
{
"epoch": 0.73,
"learning_rate": 1.773886917122107e-05,
"loss": 1.5501,
"step": 567
},
{
"epoch": 0.73,
"learning_rate": 1.773010453362737e-05,
"loss": 1.4715,
"step": 568
},
{
"epoch": 0.73,
"learning_rate": 1.77213251162394e-05,
"loss": 1.4653,
"step": 569
},
{
"epoch": 0.73,
"learning_rate": 1.7712530935843206e-05,
"loss": 1.4231,
"step": 570
},
{
"epoch": 0.73,
"learning_rate": 1.7703722009253084e-05,
"loss": 1.6637,
"step": 571
},
{
"epoch": 0.73,
"learning_rate": 1.769489835331151e-05,
"loss": 1.5361,
"step": 572
},
{
"epoch": 0.73,
"learning_rate": 1.7686059984889123e-05,
"loss": 1.4445,
"step": 573
},
{
"epoch": 0.73,
"learning_rate": 1.767720692088469e-05,
"loss": 1.6327,
"step": 574
},
{
"epoch": 0.74,
"learning_rate": 1.766833917822509e-05,
"loss": 1.5256,
"step": 575
},
{
"epoch": 0.74,
"learning_rate": 1.7659456773865247e-05,
"loss": 1.4394,
"step": 576
},
{
"epoch": 0.74,
"learning_rate": 1.7650559724788137e-05,
"loss": 1.5231,
"step": 577
},
{
"epoch": 0.74,
"learning_rate": 1.764164804800472e-05,
"loss": 1.5967,
"step": 578
},
{
"epoch": 0.74,
"learning_rate": 1.7632721760553935e-05,
"loss": 1.5865,
"step": 579
},
{
"epoch": 0.74,
"learning_rate": 1.762378087950265e-05,
"loss": 1.4517,
"step": 580
},
{
"epoch": 0.74,
"learning_rate": 1.7614825421945642e-05,
"loss": 1.5339,
"step": 581
},
{
"epoch": 0.74,
"learning_rate": 1.7605855405005548e-05,
"loss": 1.5612,
"step": 582
},
{
"epoch": 0.75,
"learning_rate": 1.759687084583285e-05,
"loss": 1.6679,
"step": 583
},
{
"epoch": 0.75,
"learning_rate": 1.7587871761605838e-05,
"loss": 1.5264,
"step": 584
},
{
"epoch": 0.75,
"learning_rate": 1.7578858169530565e-05,
"loss": 1.5529,
"step": 585
},
{
"epoch": 0.75,
"learning_rate": 1.756983008684082e-05,
"loss": 1.5614,
"step": 586
},
{
"epoch": 0.75,
"learning_rate": 1.756078753079811e-05,
"loss": 1.5096,
"step": 587
},
{
"epoch": 0.75,
"learning_rate": 1.7551730518691612e-05,
"loss": 1.525,
"step": 588
},
{
"epoch": 0.75,
"learning_rate": 1.7542659067838132e-05,
"loss": 1.4647,
"step": 589
},
{
"epoch": 0.76,
"learning_rate": 1.7533573195582093e-05,
"loss": 1.5689,
"step": 590
},
{
"epoch": 0.76,
"learning_rate": 1.7524472919295488e-05,
"loss": 1.5574,
"step": 591
},
{
"epoch": 0.76,
"learning_rate": 1.751535825637785e-05,
"loss": 1.4986,
"step": 592
},
{
"epoch": 0.76,
"learning_rate": 1.7506229224256216e-05,
"loss": 1.4711,
"step": 593
},
{
"epoch": 0.76,
"learning_rate": 1.7497085840385105e-05,
"loss": 1.4352,
"step": 594
},
{
"epoch": 0.76,
"learning_rate": 1.7487928122246467e-05,
"loss": 1.5839,
"step": 595
},
{
"epoch": 0.76,
"learning_rate": 1.7478756087349665e-05,
"loss": 1.3915,
"step": 596
},
{
"epoch": 0.76,
"learning_rate": 1.7469569753231436e-05,
"loss": 1.4873,
"step": 597
},
{
"epoch": 0.77,
"learning_rate": 1.7460369137455848e-05,
"loss": 1.5048,
"step": 598
},
{
"epoch": 0.77,
"learning_rate": 1.7451154257614287e-05,
"loss": 1.6288,
"step": 599
},
{
"epoch": 0.77,
"learning_rate": 1.7441925131325403e-05,
"loss": 1.3306,
"step": 600
},
{
"epoch": 0.77,
"learning_rate": 1.7432681776235085e-05,
"loss": 1.557,
"step": 601
},
{
"epoch": 0.77,
"learning_rate": 1.7423424210016438e-05,
"loss": 1.4688,
"step": 602
},
{
"epoch": 0.77,
"learning_rate": 1.741415245036972e-05,
"loss": 1.4829,
"step": 603
},
{
"epoch": 0.77,
"learning_rate": 1.7404866515022344e-05,
"loss": 1.6249,
"step": 604
},
{
"epoch": 0.77,
"learning_rate": 1.7395566421728818e-05,
"loss": 1.5846,
"step": 605
},
{
"epoch": 0.78,
"learning_rate": 1.738625218827072e-05,
"loss": 1.5239,
"step": 606
},
{
"epoch": 0.78,
"learning_rate": 1.7376923832456665e-05,
"loss": 1.4548,
"step": 607
},
{
"epoch": 0.78,
"learning_rate": 1.736758137212227e-05,
"loss": 1.5579,
"step": 608
},
{
"epoch": 0.78,
"learning_rate": 1.735822482513012e-05,
"loss": 1.5518,
"step": 609
},
{
"epoch": 0.78,
"learning_rate": 1.7348854209369733e-05,
"loss": 1.4994,
"step": 610
},
{
"epoch": 0.78,
"learning_rate": 1.7339469542757524e-05,
"loss": 1.5803,
"step": 611
},
{
"epoch": 0.78,
"learning_rate": 1.7330070843236772e-05,
"loss": 1.4356,
"step": 612
},
{
"epoch": 0.78,
"learning_rate": 1.7320658128777594e-05,
"loss": 1.5938,
"step": 613
},
{
"epoch": 0.79,
"learning_rate": 1.7311231417376894e-05,
"loss": 1.4163,
"step": 614
},
{
"epoch": 0.79,
"learning_rate": 1.7301790727058344e-05,
"loss": 1.5661,
"step": 615
},
{
"epoch": 0.79,
"learning_rate": 1.729233607587234e-05,
"loss": 1.5186,
"step": 616
},
{
"epoch": 0.79,
"learning_rate": 1.7282867481895983e-05,
"loss": 1.4679,
"step": 617
},
{
"epoch": 0.79,
"learning_rate": 1.7273384963233005e-05,
"loss": 1.5399,
"step": 618
},
{
"epoch": 0.79,
"learning_rate": 1.726388853801379e-05,
"loss": 1.5167,
"step": 619
},
{
"epoch": 0.79,
"learning_rate": 1.72543782243953e-05,
"loss": 1.3608,
"step": 620
},
{
"epoch": 0.79,
"learning_rate": 1.7244854040561042e-05,
"loss": 1.6059,
"step": 621
},
{
"epoch": 0.8,
"learning_rate": 1.7235316004721058e-05,
"loss": 1.4435,
"step": 622
},
{
"epoch": 0.8,
"learning_rate": 1.7225764135111867e-05,
"loss": 1.5231,
"step": 623
},
{
"epoch": 0.8,
"learning_rate": 1.7216198449996442e-05,
"loss": 1.4482,
"step": 624
},
{
"epoch": 0.8,
"learning_rate": 1.7206618967664162e-05,
"loss": 1.5029,
"step": 625
},
{
"epoch": 0.8,
"learning_rate": 1.7197025706430797e-05,
"loss": 1.4924,
"step": 626
},
{
"epoch": 0.8,
"learning_rate": 1.7187418684638456e-05,
"loss": 1.3754,
"step": 627
},
{
"epoch": 0.8,
"learning_rate": 1.7177797920655555e-05,
"loss": 1.6074,
"step": 628
},
{
"epoch": 0.81,
"learning_rate": 1.7168163432876796e-05,
"loss": 1.4987,
"step": 629
},
{
"epoch": 0.81,
"learning_rate": 1.7158515239723107e-05,
"loss": 1.523,
"step": 630
},
{
"epoch": 0.81,
"learning_rate": 1.7148853359641627e-05,
"loss": 1.6024,
"step": 631
},
{
"epoch": 0.81,
"learning_rate": 1.7139177811105666e-05,
"loss": 1.5471,
"step": 632
},
{
"epoch": 0.81,
"learning_rate": 1.7129488612614668e-05,
"loss": 1.4727,
"step": 633
},
{
"epoch": 0.81,
"learning_rate": 1.711978578269416e-05,
"loss": 1.5078,
"step": 634
},
{
"epoch": 0.81,
"learning_rate": 1.7110069339895764e-05,
"loss": 1.5186,
"step": 635
},
{
"epoch": 0.81,
"learning_rate": 1.71003393027971e-05,
"loss": 1.6478,
"step": 636
},
{
"epoch": 0.82,
"learning_rate": 1.709059569000179e-05,
"loss": 1.5051,
"step": 637
},
{
"epoch": 0.82,
"learning_rate": 1.7080838520139417e-05,
"loss": 1.3942,
"step": 638
},
{
"epoch": 0.82,
"learning_rate": 1.7071067811865477e-05,
"loss": 1.5837,
"step": 639
},
{
"epoch": 0.82,
"learning_rate": 1.7061283583861358e-05,
"loss": 1.5204,
"step": 640
},
{
"epoch": 0.82,
"learning_rate": 1.705148585483429e-05,
"loss": 1.5019,
"step": 641
},
{
"epoch": 0.82,
"learning_rate": 1.7041674643517322e-05,
"loss": 1.519,
"step": 642
},
{
"epoch": 0.82,
"learning_rate": 1.7031849968669287e-05,
"loss": 1.565,
"step": 643
},
{
"epoch": 0.82,
"learning_rate": 1.7022011849074745e-05,
"loss": 1.436,
"step": 644
},
{
"epoch": 0.83,
"learning_rate": 1.701216030354397e-05,
"loss": 1.4744,
"step": 645
},
{
"epoch": 0.83,
"learning_rate": 1.700229535091291e-05,
"loss": 1.4501,
"step": 646
},
{
"epoch": 0.83,
"learning_rate": 1.6992417010043144e-05,
"loss": 1.4366,
"step": 647
},
{
"epoch": 0.83,
"learning_rate": 1.698252529982184e-05,
"loss": 1.4416,
"step": 648
},
{
"epoch": 0.83,
"learning_rate": 1.6972620239161747e-05,
"loss": 1.4952,
"step": 649
},
{
"epoch": 0.83,
"learning_rate": 1.696270184700112e-05,
"loss": 1.5683,
"step": 650
},
{
"epoch": 0.83,
"learning_rate": 1.695277014230372e-05,
"loss": 1.6548,
"step": 651
},
{
"epoch": 0.83,
"learning_rate": 1.6942825144058744e-05,
"loss": 1.5788,
"step": 652
},
{
"epoch": 0.84,
"learning_rate": 1.6932866871280823e-05,
"loss": 1.4559,
"step": 653
},
{
"epoch": 0.84,
"learning_rate": 1.6922895343009963e-05,
"loss": 1.5352,
"step": 654
},
{
"epoch": 0.84,
"learning_rate": 1.6912910578311503e-05,
"loss": 1.5393,
"step": 655
},
{
"epoch": 0.84,
"learning_rate": 1.6902912596276107e-05,
"loss": 1.4919,
"step": 656
},
{
"epoch": 0.84,
"learning_rate": 1.6892901416019702e-05,
"loss": 1.5079,
"step": 657
},
{
"epoch": 0.84,
"learning_rate": 1.6882877056683446e-05,
"loss": 1.5547,
"step": 658
},
{
"epoch": 0.84,
"learning_rate": 1.6872839537433706e-05,
"loss": 1.5188,
"step": 659
},
{
"epoch": 0.84,
"learning_rate": 1.6862788877461994e-05,
"loss": 1.4864,
"step": 660
},
{
"epoch": 0.85,
"learning_rate": 1.6852725095984964e-05,
"loss": 1.5786,
"step": 661
},
{
"epoch": 0.85,
"learning_rate": 1.684264821224435e-05,
"loss": 1.5396,
"step": 662
},
{
"epoch": 0.85,
"learning_rate": 1.6832558245506937e-05,
"loss": 1.479,
"step": 663
},
{
"epoch": 0.85,
"learning_rate": 1.6822455215064522e-05,
"loss": 1.5636,
"step": 664
},
{
"epoch": 0.85,
"learning_rate": 1.681233914023389e-05,
"loss": 1.4777,
"step": 665
},
{
"epoch": 0.85,
"learning_rate": 1.6802210040356753e-05,
"loss": 1.6042,
"step": 666
},
{
"epoch": 0.85,
"learning_rate": 1.6792067934799734e-05,
"loss": 1.444,
"step": 667
},
{
"epoch": 0.86,
"learning_rate": 1.6781912842954323e-05,
"loss": 1.6779,
"step": 668
},
{
"epoch": 0.86,
"learning_rate": 1.677174478423684e-05,
"loss": 1.5744,
"step": 669
},
{
"epoch": 0.86,
"learning_rate": 1.676156377808839e-05,
"loss": 1.5028,
"step": 670
},
{
"epoch": 0.86,
"learning_rate": 1.6751369843974842e-05,
"loss": 1.5694,
"step": 671
},
{
"epoch": 0.86,
"learning_rate": 1.6741163001386783e-05,
"loss": 1.5982,
"step": 672
},
{
"epoch": 0.86,
"learning_rate": 1.673094326983947e-05,
"loss": 1.4068,
"step": 673
},
{
"epoch": 0.86,
"learning_rate": 1.6720710668872816e-05,
"loss": 1.5212,
"step": 674
},
{
"epoch": 0.86,
"learning_rate": 1.6710465218051332e-05,
"loss": 1.572,
"step": 675
},
{
"epoch": 0.87,
"learning_rate": 1.6700206936964102e-05,
"loss": 1.6098,
"step": 676
},
{
"epoch": 0.87,
"learning_rate": 1.6689935845224742e-05,
"loss": 1.5454,
"step": 677
},
{
"epoch": 0.87,
"learning_rate": 1.6679651962471356e-05,
"loss": 1.5341,
"step": 678
},
{
"epoch": 0.87,
"learning_rate": 1.666935530836651e-05,
"loss": 1.5899,
"step": 679
},
{
"epoch": 0.87,
"learning_rate": 1.665904590259718e-05,
"loss": 1.5433,
"step": 680
},
{
"epoch": 0.87,
"learning_rate": 1.6648723764874737e-05,
"loss": 1.5102,
"step": 681
},
{
"epoch": 0.87,
"learning_rate": 1.6638388914934886e-05,
"loss": 1.4966,
"step": 682
},
{
"epoch": 0.87,
"learning_rate": 1.6628041372537633e-05,
"loss": 1.5101,
"step": 683
},
{
"epoch": 0.88,
"learning_rate": 1.661768115746726e-05,
"loss": 1.494,
"step": 684
},
{
"epoch": 0.88,
"learning_rate": 1.660730828953228e-05,
"loss": 1.5223,
"step": 685
},
{
"epoch": 0.88,
"learning_rate": 1.659692278856539e-05,
"loss": 1.4483,
"step": 686
},
{
"epoch": 0.88,
"learning_rate": 1.658652467442345e-05,
"loss": 1.5636,
"step": 687
},
{
"epoch": 0.88,
"learning_rate": 1.6576113966987423e-05,
"loss": 1.4911,
"step": 688
},
{
"epoch": 0.88,
"learning_rate": 1.6565690686162365e-05,
"loss": 1.5708,
"step": 689
},
{
"epoch": 0.88,
"learning_rate": 1.6555254851877367e-05,
"loss": 1.5029,
"step": 690
},
{
"epoch": 0.88,
"learning_rate": 1.6544806484085517e-05,
"loss": 1.5355,
"step": 691
},
{
"epoch": 0.89,
"learning_rate": 1.653434560276387e-05,
"loss": 1.6601,
"step": 692
},
{
"epoch": 0.89,
"learning_rate": 1.652387222791341e-05,
"loss": 1.5048,
"step": 693
},
{
"epoch": 0.89,
"learning_rate": 1.6513386379559006e-05,
"loss": 1.4535,
"step": 694
},
{
"epoch": 0.89,
"learning_rate": 1.650288807774937e-05,
"loss": 1.4837,
"step": 695
},
{
"epoch": 0.89,
"learning_rate": 1.6492377342557036e-05,
"loss": 1.6034,
"step": 696
},
{
"epoch": 0.89,
"learning_rate": 1.64818541940783e-05,
"loss": 1.546,
"step": 697
},
{
"epoch": 0.89,
"learning_rate": 1.6471318652433198e-05,
"loss": 1.5467,
"step": 698
},
{
"epoch": 0.89,
"learning_rate": 1.6460770737765465e-05,
"loss": 1.4843,
"step": 699
},
{
"epoch": 0.9,
"learning_rate": 1.645021047024248e-05,
"loss": 1.4456,
"step": 700
},
{
"epoch": 0.9,
"learning_rate": 1.643963787005525e-05,
"loss": 1.4996,
"step": 701
},
{
"epoch": 0.9,
"learning_rate": 1.6429052957418363e-05,
"loss": 1.5743,
"step": 702
},
{
"epoch": 0.9,
"learning_rate": 1.6418455752569945e-05,
"loss": 1.5112,
"step": 703
},
{
"epoch": 0.9,
"learning_rate": 1.6407846275771625e-05,
"loss": 1.4653,
"step": 704
},
{
"epoch": 0.9,
"learning_rate": 1.639722454730849e-05,
"loss": 1.4576,
"step": 705
},
{
"epoch": 0.9,
"learning_rate": 1.638659058748906e-05,
"loss": 1.472,
"step": 706
},
{
"epoch": 0.9,
"learning_rate": 1.637594441664524e-05,
"loss": 1.5423,
"step": 707
},
{
"epoch": 0.91,
"learning_rate": 1.636528605513229e-05,
"loss": 1.5335,
"step": 708
},
{
"epoch": 0.91,
"learning_rate": 1.635461552332875e-05,
"loss": 1.5117,
"step": 709
},
{
"epoch": 0.91,
"learning_rate": 1.6343932841636455e-05,
"loss": 1.4179,
"step": 710
},
{
"epoch": 0.91,
"learning_rate": 1.6333238030480473e-05,
"loss": 1.448,
"step": 711
},
{
"epoch": 0.91,
"learning_rate": 1.632253111030904e-05,
"loss": 1.5192,
"step": 712
},
{
"epoch": 0.91,
"learning_rate": 1.631181210159357e-05,
"loss": 1.4766,
"step": 713
},
{
"epoch": 0.91,
"learning_rate": 1.630108102482857e-05,
"loss": 1.5815,
"step": 714
},
{
"epoch": 0.92,
"learning_rate": 1.6290337900531633e-05,
"loss": 1.4862,
"step": 715
},
{
"epoch": 0.92,
"learning_rate": 1.627958274924338e-05,
"loss": 1.5528,
"step": 716
},
{
"epoch": 0.92,
"learning_rate": 1.626881559152743e-05,
"loss": 1.6059,
"step": 717
},
{
"epoch": 0.92,
"learning_rate": 1.6258036447970363e-05,
"loss": 1.5849,
"step": 718
},
{
"epoch": 0.92,
"learning_rate": 1.624724533918166e-05,
"loss": 1.5834,
"step": 719
},
{
"epoch": 0.92,
"learning_rate": 1.62364422857937e-05,
"loss": 1.5903,
"step": 720
},
{
"epoch": 0.92,
"learning_rate": 1.6225627308461688e-05,
"loss": 1.5857,
"step": 721
},
{
"epoch": 0.92,
"learning_rate": 1.6214800427863626e-05,
"loss": 1.4953,
"step": 722
},
{
"epoch": 0.93,
"learning_rate": 1.6203961664700275e-05,
"loss": 1.5037,
"step": 723
},
{
"epoch": 0.93,
"learning_rate": 1.6193111039695124e-05,
"loss": 1.4149,
"step": 724
},
{
"epoch": 0.93,
"learning_rate": 1.6182248573594334e-05,
"loss": 1.5717,
"step": 725
},
{
"epoch": 0.93,
"learning_rate": 1.6171374287166708e-05,
"loss": 1.5662,
"step": 726
},
{
"epoch": 0.93,
"learning_rate": 1.6160488201203643e-05,
"loss": 1.507,
"step": 727
},
{
"epoch": 0.93,
"learning_rate": 1.614959033651911e-05,
"loss": 1.5662,
"step": 728
},
{
"epoch": 0.93,
"learning_rate": 1.613868071394959e-05,
"loss": 1.5028,
"step": 729
},
{
"epoch": 0.93,
"learning_rate": 1.6127759354354044e-05,
"loss": 1.504,
"step": 730
},
{
"epoch": 0.94,
"learning_rate": 1.6116826278613882e-05,
"loss": 1.4723,
"step": 731
},
{
"epoch": 0.94,
"learning_rate": 1.610588150763291e-05,
"loss": 1.4376,
"step": 732
},
{
"epoch": 0.94,
"learning_rate": 1.6094925062337294e-05,
"loss": 1.4708,
"step": 733
},
{
"epoch": 0.94,
"learning_rate": 1.6083956963675524e-05,
"loss": 1.55,
"step": 734
},
{
"epoch": 0.94,
"learning_rate": 1.607297723261837e-05,
"loss": 1.4513,
"step": 735
},
{
"epoch": 0.94,
"learning_rate": 1.606198589015884e-05,
"loss": 1.5062,
"step": 736
},
{
"epoch": 0.94,
"learning_rate": 1.6050982957312148e-05,
"loss": 1.4572,
"step": 737
},
{
"epoch": 0.94,
"learning_rate": 1.6039968455115666e-05,
"loss": 1.542,
"step": 738
},
{
"epoch": 0.95,
"learning_rate": 1.6028942404628886e-05,
"loss": 1.5446,
"step": 739
},
{
"epoch": 0.95,
"learning_rate": 1.6017904826933376e-05,
"loss": 1.5324,
"step": 740
},
{
"epoch": 0.95,
"learning_rate": 1.6006855743132756e-05,
"loss": 1.5279,
"step": 741
},
{
"epoch": 0.95,
"learning_rate": 1.599579517435263e-05,
"loss": 1.419,
"step": 742
},
{
"epoch": 0.95,
"learning_rate": 1.5984723141740578e-05,
"loss": 1.5599,
"step": 743
},
{
"epoch": 0.95,
"learning_rate": 1.5973639666466078e-05,
"loss": 1.5176,
"step": 744
},
{
"epoch": 0.95,
"learning_rate": 1.59625447697205e-05,
"loss": 1.6002,
"step": 745
},
{
"epoch": 0.95,
"learning_rate": 1.5951438472717055e-05,
"loss": 1.4306,
"step": 746
},
{
"epoch": 0.96,
"learning_rate": 1.5940320796690742e-05,
"loss": 1.4968,
"step": 747
},
{
"epoch": 0.96,
"learning_rate": 1.5929191762898315e-05,
"loss": 1.5079,
"step": 748
},
{
"epoch": 0.96,
"learning_rate": 1.5918051392618255e-05,
"loss": 1.5674,
"step": 749
},
{
"epoch": 0.96,
"learning_rate": 1.590689970715071e-05,
"loss": 1.5115,
"step": 750
},
{
"epoch": 0.96,
"learning_rate": 1.5895736727817457e-05,
"loss": 1.5265,
"step": 751
},
{
"epoch": 0.96,
"learning_rate": 1.588456247596188e-05,
"loss": 1.5439,
"step": 752
},
{
"epoch": 0.96,
"learning_rate": 1.5873376972948905e-05,
"loss": 1.4767,
"step": 753
},
{
"epoch": 0.97,
"learning_rate": 1.586218024016498e-05,
"loss": 1.5562,
"step": 754
},
{
"epoch": 0.97,
"learning_rate": 1.5850972299018014e-05,
"loss": 1.6845,
"step": 755
},
{
"epoch": 0.97,
"learning_rate": 1.583975317093735e-05,
"loss": 1.6212,
"step": 756
},
{
"epoch": 0.97,
"learning_rate": 1.5828522877373728e-05,
"loss": 1.5755,
"step": 757
},
{
"epoch": 0.97,
"learning_rate": 1.5817281439799215e-05,
"loss": 1.548,
"step": 758
},
{
"epoch": 0.97,
"learning_rate": 1.580602887970721e-05,
"loss": 1.451,
"step": 759
},
{
"epoch": 0.97,
"learning_rate": 1.579476521861236e-05,
"loss": 1.5423,
"step": 760
},
{
"epoch": 0.97,
"learning_rate": 1.578349047805055e-05,
"loss": 1.5677,
"step": 761
},
{
"epoch": 0.98,
"learning_rate": 1.5772204679578835e-05,
"loss": 1.5563,
"step": 762
},
{
"epoch": 0.98,
"learning_rate": 1.5760907844775428e-05,
"loss": 1.5435,
"step": 763
},
{
"epoch": 0.98,
"learning_rate": 1.574959999523963e-05,
"loss": 1.4779,
"step": 764
},
{
"epoch": 0.98,
"learning_rate": 1.573828115259181e-05,
"loss": 1.5168,
"step": 765
},
{
"epoch": 0.98,
"learning_rate": 1.572695133847335e-05,
"loss": 1.5292,
"step": 766
},
{
"epoch": 0.98,
"learning_rate": 1.5715610574546612e-05,
"loss": 1.4631,
"step": 767
},
{
"epoch": 0.98,
"learning_rate": 1.5704258882494893e-05,
"loss": 1.4746,
"step": 768
},
{
"epoch": 0.98,
"learning_rate": 1.569289628402239e-05,
"loss": 1.4808,
"step": 769
},
{
"epoch": 0.99,
"learning_rate": 1.5681522800854147e-05,
"loss": 1.5122,
"step": 770
},
{
"epoch": 0.99,
"learning_rate": 1.5670138454736012e-05,
"loss": 1.4242,
"step": 771
},
{
"epoch": 0.99,
"learning_rate": 1.565874326743462e-05,
"loss": 1.5265,
"step": 772
},
{
"epoch": 0.99,
"learning_rate": 1.564733726073732e-05,
"loss": 1.4896,
"step": 773
},
{
"epoch": 0.99,
"learning_rate": 1.5635920456452152e-05,
"loss": 1.6303,
"step": 774
},
{
"epoch": 0.99,
"learning_rate": 1.562449287640781e-05,
"loss": 1.5172,
"step": 775
},
{
"epoch": 0.99,
"learning_rate": 1.561305454245357e-05,
"loss": 1.507,
"step": 776
},
{
"epoch": 0.99,
"learning_rate": 1.560160547645929e-05,
"loss": 1.6261,
"step": 777
},
{
"epoch": 1.0,
"learning_rate": 1.5590145700315333e-05,
"loss": 1.5126,
"step": 778
},
{
"epoch": 1.0,
"learning_rate": 1.557867523593255e-05,
"loss": 1.5811,
"step": 779
},
{
"epoch": 1.0,
"learning_rate": 1.556719410524222e-05,
"loss": 1.4222,
"step": 780
},
{
"epoch": 1.0,
"learning_rate": 1.5555702330196024e-05,
"loss": 1.5278,
"step": 781
},
{
"epoch": 1.0,
"learning_rate": 1.5544199932765983e-05,
"loss": 1.3436,
"step": 782
},
{
"epoch": 1.0,
"learning_rate": 1.553268693494444e-05,
"loss": 1.2307,
"step": 783
},
{
"epoch": 1.0,
"learning_rate": 1.5521163358743998e-05,
"loss": 1.17,
"step": 784
},
{
"epoch": 1.0,
"learning_rate": 1.550962922619749e-05,
"loss": 1.225,
"step": 785
},
{
"epoch": 1.01,
"learning_rate": 1.5498084559357922e-05,
"loss": 1.2589,
"step": 786
},
{
"epoch": 1.01,
"learning_rate": 1.548652938029846e-05,
"loss": 1.2029,
"step": 787
},
{
"epoch": 1.01,
"learning_rate": 1.5474963711112354e-05,
"loss": 1.3469,
"step": 788
},
{
"epoch": 1.01,
"learning_rate": 1.5463387573912916e-05,
"loss": 1.1938,
"step": 789
},
{
"epoch": 1.01,
"learning_rate": 1.5451800990833473e-05,
"loss": 1.2913,
"step": 790
},
{
"epoch": 1.01,
"learning_rate": 1.5440203984027323e-05,
"loss": 1.3701,
"step": 791
},
{
"epoch": 1.01,
"learning_rate": 1.5428596575667697e-05,
"loss": 1.1922,
"step": 792
},
{
"epoch": 1.02,
"learning_rate": 1.5416978787947708e-05,
"loss": 1.2417,
"step": 793
},
{
"epoch": 1.02,
"learning_rate": 1.5405350643080315e-05,
"loss": 1.1946,
"step": 794
},
{
"epoch": 1.02,
"learning_rate": 1.539371216329829e-05,
"loss": 1.1704,
"step": 795
},
{
"epoch": 1.02,
"learning_rate": 1.5382063370854154e-05,
"loss": 1.3232,
"step": 796
},
{
"epoch": 1.02,
"learning_rate": 1.5370404288020142e-05,
"loss": 1.333,
"step": 797
},
{
"epoch": 1.02,
"learning_rate": 1.5358734937088174e-05,
"loss": 1.134,
"step": 798
},
{
"epoch": 1.02,
"learning_rate": 1.5347055340369806e-05,
"loss": 1.1303,
"step": 799
},
{
"epoch": 1.02,
"learning_rate": 1.533536552019617e-05,
"loss": 1.1818,
"step": 800
},
{
"epoch": 1.03,
"learning_rate": 1.532366549891795e-05,
"loss": 1.3051,
"step": 801
},
{
"epoch": 1.03,
"learning_rate": 1.5311955298905342e-05,
"loss": 1.2986,
"step": 802
},
{
"epoch": 1.03,
"learning_rate": 1.530023494254799e-05,
"loss": 1.2276,
"step": 803
},
{
"epoch": 1.03,
"learning_rate": 1.5288504452254975e-05,
"loss": 1.2336,
"step": 804
},
{
"epoch": 1.03,
"learning_rate": 1.5276763850454735e-05,
"loss": 1.1609,
"step": 805
},
{
"epoch": 1.03,
"learning_rate": 1.526501315959505e-05,
"loss": 1.3192,
"step": 806
},
{
"epoch": 1.03,
"learning_rate": 1.5253252402142989e-05,
"loss": 1.2879,
"step": 807
},
{
"epoch": 1.03,
"learning_rate": 1.5241481600584874e-05,
"loss": 1.3112,
"step": 808
},
{
"epoch": 1.04,
"learning_rate": 1.5229700777426217e-05,
"loss": 1.163,
"step": 809
},
{
"epoch": 1.04,
"learning_rate": 1.5217909955191706e-05,
"loss": 1.1871,
"step": 810
},
{
"epoch": 1.04,
"learning_rate": 1.5206109156425137e-05,
"loss": 1.1491,
"step": 811
},
{
"epoch": 1.04,
"learning_rate": 1.5194298403689386e-05,
"loss": 1.1259,
"step": 812
},
{
"epoch": 1.04,
"learning_rate": 1.518247771956636e-05,
"loss": 1.1368,
"step": 813
},
{
"epoch": 1.04,
"learning_rate": 1.517064712665695e-05,
"loss": 1.1642,
"step": 814
},
{
"epoch": 1.04,
"learning_rate": 1.5158806647581e-05,
"loss": 1.2282,
"step": 815
},
{
"epoch": 1.04,
"learning_rate": 1.5146956304977254e-05,
"loss": 1.1852,
"step": 816
},
{
"epoch": 1.05,
"learning_rate": 1.5135096121503308e-05,
"loss": 1.2004,
"step": 817
},
{
"epoch": 1.05,
"learning_rate": 1.5123226119835581e-05,
"loss": 1.1955,
"step": 818
},
{
"epoch": 1.05,
"learning_rate": 1.5111346322669262e-05,
"loss": 1.117,
"step": 819
},
{
"epoch": 1.05,
"learning_rate": 1.5099456752718266e-05,
"loss": 1.2484,
"step": 820
},
{
"epoch": 1.05,
"learning_rate": 1.5087557432715206e-05,
"loss": 1.3413,
"step": 821
},
{
"epoch": 1.05,
"learning_rate": 1.5075648385411314e-05,
"loss": 1.1343,
"step": 822
},
{
"epoch": 1.05,
"learning_rate": 1.506372963357644e-05,
"loss": 1.2481,
"step": 823
},
{
"epoch": 1.05,
"learning_rate": 1.5051801199998983e-05,
"loss": 1.2712,
"step": 824
},
{
"epoch": 1.06,
"learning_rate": 1.503986310748585e-05,
"loss": 1.1932,
"step": 825
},
{
"epoch": 1.06,
"learning_rate": 1.502791537886242e-05,
"loss": 1.2357,
"step": 826
},
{
"epoch": 1.06,
"learning_rate": 1.5015958036972488e-05,
"loss": 1.2222,
"step": 827
},
{
"epoch": 1.06,
"learning_rate": 1.5003991104678245e-05,
"loss": 1.2228,
"step": 828
},
{
"epoch": 1.06,
"learning_rate": 1.4992014604860203e-05,
"loss": 1.2384,
"step": 829
},
{
"epoch": 1.06,
"learning_rate": 1.4980028560417176e-05,
"loss": 1.2331,
"step": 830
},
{
"epoch": 1.06,
"learning_rate": 1.4968032994266224e-05,
"loss": 1.2519,
"step": 831
},
{
"epoch": 1.06,
"learning_rate": 1.4956027929342611e-05,
"loss": 1.2266,
"step": 832
},
{
"epoch": 1.07,
"learning_rate": 1.4944013388599763e-05,
"loss": 1.1775,
"step": 833
},
{
"epoch": 1.07,
"learning_rate": 1.493198939500923e-05,
"loss": 1.1914,
"step": 834
},
{
"epoch": 1.07,
"learning_rate": 1.4919955971560622e-05,
"loss": 1.1442,
"step": 835
},
{
"epoch": 1.07,
"learning_rate": 1.4907913141261591e-05,
"loss": 1.1764,
"step": 836
},
{
"epoch": 1.07,
"learning_rate": 1.4895860927137773e-05,
"loss": 1.2792,
"step": 837
},
{
"epoch": 1.07,
"learning_rate": 1.4883799352232743e-05,
"loss": 1.2952,
"step": 838
},
{
"epoch": 1.07,
"learning_rate": 1.4871728439607967e-05,
"loss": 1.2613,
"step": 839
},
{
"epoch": 1.08,
"learning_rate": 1.4859648212342778e-05,
"loss": 1.3075,
"step": 840
},
{
"epoch": 1.08,
"learning_rate": 1.4847558693534309e-05,
"loss": 1.1774,
"step": 841
},
{
"epoch": 1.08,
"learning_rate": 1.4835459906297462e-05,
"loss": 1.1291,
"step": 842
},
{
"epoch": 1.08,
"learning_rate": 1.4823351873764862e-05,
"loss": 1.2469,
"step": 843
},
{
"epoch": 1.08,
"learning_rate": 1.4811234619086802e-05,
"loss": 1.0765,
"step": 844
},
{
"epoch": 1.08,
"learning_rate": 1.4799108165431215e-05,
"loss": 1.1946,
"step": 845
},
{
"epoch": 1.08,
"learning_rate": 1.4786972535983624e-05,
"loss": 1.173,
"step": 846
},
{
"epoch": 1.08,
"learning_rate": 1.4774827753947088e-05,
"loss": 1.2652,
"step": 847
},
{
"epoch": 1.09,
"learning_rate": 1.4762673842542175e-05,
"loss": 1.1688,
"step": 848
},
{
"epoch": 1.09,
"learning_rate": 1.4750510825006898e-05,
"loss": 1.2725,
"step": 849
},
{
"epoch": 1.09,
"learning_rate": 1.4738338724596691e-05,
"loss": 1.1952,
"step": 850
},
{
"epoch": 1.09,
"learning_rate": 1.4726157564584345e-05,
"loss": 1.1522,
"step": 851
},
{
"epoch": 1.09,
"learning_rate": 1.4713967368259981e-05,
"loss": 1.178,
"step": 852
},
{
"epoch": 1.09,
"learning_rate": 1.4701768158930987e-05,
"loss": 1.2104,
"step": 853
},
{
"epoch": 1.09,
"learning_rate": 1.4689559959921995e-05,
"loss": 1.3163,
"step": 854
},
{
"epoch": 1.09,
"learning_rate": 1.4677342794574819e-05,
"loss": 1.1721,
"step": 855
},
{
"epoch": 1.1,
"learning_rate": 1.4665116686248418e-05,
"loss": 1.1627,
"step": 856
},
{
"epoch": 1.1,
"learning_rate": 1.465288165831885e-05,
"loss": 1.1635,
"step": 857
},
{
"epoch": 1.1,
"learning_rate": 1.4640637734179222e-05,
"loss": 1.1497,
"step": 858
},
{
"epoch": 1.1,
"learning_rate": 1.4628384937239659e-05,
"loss": 1.1312,
"step": 859
},
{
"epoch": 1.1,
"learning_rate": 1.4616123290927244e-05,
"loss": 1.2433,
"step": 860
},
{
"epoch": 1.1,
"learning_rate": 1.4603852818685985e-05,
"loss": 1.092,
"step": 861
},
{
"epoch": 1.1,
"learning_rate": 1.4591573543976758e-05,
"loss": 1.3162,
"step": 862
},
{
"epoch": 1.1,
"learning_rate": 1.4579285490277275e-05,
"loss": 1.1653,
"step": 863
},
{
"epoch": 1.11,
"learning_rate": 1.456698868108203e-05,
"loss": 1.2219,
"step": 864
},
{
"epoch": 1.11,
"learning_rate": 1.4554683139902262e-05,
"loss": 1.206,
"step": 865
},
{
"epoch": 1.11,
"learning_rate": 1.4542368890265901e-05,
"loss": 1.4149,
"step": 866
},
{
"epoch": 1.11,
"learning_rate": 1.4530045955717528e-05,
"loss": 1.2155,
"step": 867
},
{
"epoch": 1.11,
"learning_rate": 1.4517714359818329e-05,
"loss": 1.198,
"step": 868
},
{
"epoch": 1.11,
"learning_rate": 1.4505374126146053e-05,
"loss": 1.2839,
"step": 869
},
{
"epoch": 1.11,
"learning_rate": 1.449302527829496e-05,
"loss": 1.139,
"step": 870
},
{
"epoch": 1.11,
"learning_rate": 1.4480667839875786e-05,
"loss": 1.2797,
"step": 871
},
{
"epoch": 1.12,
"learning_rate": 1.4468301834515685e-05,
"loss": 1.1736,
"step": 872
},
{
"epoch": 1.12,
"learning_rate": 1.4455927285858196e-05,
"loss": 1.1984,
"step": 873
},
{
"epoch": 1.12,
"learning_rate": 1.444354421756319e-05,
"loss": 1.2049,
"step": 874
},
{
"epoch": 1.12,
"learning_rate": 1.4431152653306833e-05,
"loss": 1.2572,
"step": 875
},
{
"epoch": 1.12,
"learning_rate": 1.4418752616781522e-05,
"loss": 1.2538,
"step": 876
},
{
"epoch": 1.12,
"learning_rate": 1.4406344131695868e-05,
"loss": 1.2,
"step": 877
},
{
"epoch": 1.12,
"learning_rate": 1.4393927221774627e-05,
"loss": 1.1266,
"step": 878
},
{
"epoch": 1.13,
"learning_rate": 1.4381501910758662e-05,
"loss": 1.2158,
"step": 879
},
{
"epoch": 1.13,
"learning_rate": 1.4369068222404904e-05,
"loss": 1.2406,
"step": 880
},
{
"epoch": 1.13,
"learning_rate": 1.4356626180486299e-05,
"loss": 1.0863,
"step": 881
},
{
"epoch": 1.13,
"learning_rate": 1.4344175808791765e-05,
"loss": 1.2011,
"step": 882
},
{
"epoch": 1.13,
"learning_rate": 1.4331717131126142e-05,
"loss": 1.1927,
"step": 883
},
{
"epoch": 1.13,
"learning_rate": 1.4319250171310164e-05,
"loss": 1.2026,
"step": 884
},
{
"epoch": 1.13,
"learning_rate": 1.430677495318038e-05,
"loss": 1.203,
"step": 885
},
{
"epoch": 1.13,
"learning_rate": 1.4294291500589145e-05,
"loss": 1.2063,
"step": 886
},
{
"epoch": 1.14,
"learning_rate": 1.4281799837404553e-05,
"loss": 1.0684,
"step": 887
},
{
"epoch": 1.14,
"learning_rate": 1.4269299987510398e-05,
"loss": 1.3337,
"step": 888
},
{
"epoch": 1.14,
"learning_rate": 1.4256791974806122e-05,
"loss": 1.1662,
"step": 889
},
{
"epoch": 1.14,
"learning_rate": 1.4244275823206776e-05,
"loss": 1.2638,
"step": 890
},
{
"epoch": 1.14,
"learning_rate": 1.4231751556642981e-05,
"loss": 1.2312,
"step": 891
},
{
"epoch": 1.14,
"learning_rate": 1.421921919906086e-05,
"loss": 1.2843,
"step": 892
},
{
"epoch": 1.14,
"learning_rate": 1.4206678774422016e-05,
"loss": 1.2139,
"step": 893
},
{
"epoch": 1.14,
"learning_rate": 1.4194130306703467e-05,
"loss": 1.192,
"step": 894
},
{
"epoch": 1.15,
"learning_rate": 1.4181573819897618e-05,
"loss": 1.1594,
"step": 895
},
{
"epoch": 1.15,
"learning_rate": 1.4169009338012205e-05,
"loss": 1.2109,
"step": 896
},
{
"epoch": 1.15,
"learning_rate": 1.4156436885070243e-05,
"loss": 1.2549,
"step": 897
},
{
"epoch": 1.15,
"learning_rate": 1.4143856485109999e-05,
"loss": 1.2495,
"step": 898
},
{
"epoch": 1.15,
"learning_rate": 1.4131268162184921e-05,
"loss": 1.1652,
"step": 899
},
{
"epoch": 1.15,
"learning_rate": 1.4118671940363618e-05,
"loss": 1.1898,
"step": 900
},
{
"epoch": 1.15,
"learning_rate": 1.4106067843729797e-05,
"loss": 1.1882,
"step": 901
},
{
"epoch": 1.15,
"learning_rate": 1.4093455896382215e-05,
"loss": 1.3092,
"step": 902
},
{
"epoch": 1.16,
"learning_rate": 1.408083612243465e-05,
"loss": 1.2652,
"step": 903
},
{
"epoch": 1.16,
"learning_rate": 1.4068208546015838e-05,
"loss": 1.1824,
"step": 904
},
{
"epoch": 1.16,
"learning_rate": 1.4055573191269436e-05,
"loss": 1.2462,
"step": 905
},
{
"epoch": 1.16,
"learning_rate": 1.4042930082353969e-05,
"loss": 1.3578,
"step": 906
},
{
"epoch": 1.16,
"learning_rate": 1.4030279243442793e-05,
"loss": 1.178,
"step": 907
},
{
"epoch": 1.16,
"learning_rate": 1.4017620698724037e-05,
"loss": 1.2513,
"step": 908
},
{
"epoch": 1.16,
"learning_rate": 1.4004954472400574e-05,
"loss": 1.239,
"step": 909
},
{
"epoch": 1.16,
"learning_rate": 1.399228058868995e-05,
"loss": 1.1456,
"step": 910
},
{
"epoch": 1.17,
"learning_rate": 1.3979599071824363e-05,
"loss": 1.2961,
"step": 911
},
{
"epoch": 1.17,
"learning_rate": 1.3966909946050602e-05,
"loss": 1.1437,
"step": 912
},
{
"epoch": 1.17,
"learning_rate": 1.3954213235630005e-05,
"loss": 1.2119,
"step": 913
},
{
"epoch": 1.17,
"learning_rate": 1.3941508964838407e-05,
"loss": 1.3639,
"step": 914
},
{
"epoch": 1.17,
"learning_rate": 1.3928797157966098e-05,
"loss": 1.1819,
"step": 915
},
{
"epoch": 1.17,
"learning_rate": 1.391607783931779e-05,
"loss": 1.2616,
"step": 916
},
{
"epoch": 1.17,
"learning_rate": 1.3903351033212544e-05,
"loss": 1.2256,
"step": 917
},
{
"epoch": 1.18,
"learning_rate": 1.3890616763983738e-05,
"loss": 1.3166,
"step": 918
},
{
"epoch": 1.18,
"learning_rate": 1.3877875055979021e-05,
"loss": 1.2222,
"step": 919
},
{
"epoch": 1.18,
"learning_rate": 1.3865125933560272e-05,
"loss": 1.2539,
"step": 920
},
{
"epoch": 1.18,
"learning_rate": 1.3852369421103538e-05,
"loss": 1.2659,
"step": 921
},
{
"epoch": 1.18,
"learning_rate": 1.3839605542998991e-05,
"loss": 1.2749,
"step": 922
},
{
"epoch": 1.18,
"learning_rate": 1.3826834323650899e-05,
"loss": 1.1186,
"step": 923
},
{
"epoch": 1.18,
"learning_rate": 1.3814055787477558e-05,
"loss": 1.2641,
"step": 924
},
{
"epoch": 1.18,
"learning_rate": 1.3801269958911256e-05,
"loss": 1.0724,
"step": 925
},
{
"epoch": 1.19,
"learning_rate": 1.3788476862398226e-05,
"loss": 1.2218,
"step": 926
},
{
"epoch": 1.19,
"learning_rate": 1.3775676522398587e-05,
"loss": 1.241,
"step": 927
},
{
"epoch": 1.19,
"learning_rate": 1.376286896338632e-05,
"loss": 1.2912,
"step": 928
},
{
"epoch": 1.19,
"learning_rate": 1.3750054209849204e-05,
"loss": 1.2464,
"step": 929
},
{
"epoch": 1.19,
"learning_rate": 1.3737232286288773e-05,
"loss": 1.2726,
"step": 930
},
{
"epoch": 1.19,
"learning_rate": 1.3724403217220268e-05,
"loss": 1.1272,
"step": 931
},
{
"epoch": 1.19,
"learning_rate": 1.3711567027172594e-05,
"loss": 1.2658,
"step": 932
},
{
"epoch": 1.19,
"learning_rate": 1.3698723740688275e-05,
"loss": 1.2059,
"step": 933
},
{
"epoch": 1.2,
"learning_rate": 1.3685873382323398e-05,
"loss": 1.2691,
"step": 934
},
{
"epoch": 1.2,
"learning_rate": 1.367301597664757e-05,
"loss": 1.1836,
"step": 935
},
{
"epoch": 1.2,
"learning_rate": 1.3660151548243879e-05,
"loss": 1.2218,
"step": 936
},
{
"epoch": 1.2,
"learning_rate": 1.3647280121708835e-05,
"loss": 1.2973,
"step": 937
},
{
"epoch": 1.2,
"learning_rate": 1.363440172165233e-05,
"loss": 1.1976,
"step": 938
},
{
"epoch": 1.2,
"learning_rate": 1.3621516372697587e-05,
"loss": 1.1687,
"step": 939
},
{
"epoch": 1.2,
"learning_rate": 1.360862409948112e-05,
"loss": 1.2191,
"step": 940
},
{
"epoch": 1.2,
"learning_rate": 1.3595724926652679e-05,
"loss": 1.076,
"step": 941
},
{
"epoch": 1.21,
"learning_rate": 1.3582818878875209e-05,
"loss": 1.2148,
"step": 942
},
{
"epoch": 1.21,
"learning_rate": 1.3569905980824789e-05,
"loss": 1.1488,
"step": 943
},
{
"epoch": 1.21,
"learning_rate": 1.3556986257190608e-05,
"loss": 1.1193,
"step": 944
},
{
"epoch": 1.21,
"learning_rate": 1.35440597326749e-05,
"loss": 1.338,
"step": 945
},
{
"epoch": 1.21,
"learning_rate": 1.3531126431992906e-05,
"loss": 1.2717,
"step": 946
},
{
"epoch": 1.21,
"learning_rate": 1.3518186379872815e-05,
"loss": 1.2307,
"step": 947
},
{
"epoch": 1.21,
"learning_rate": 1.3505239601055734e-05,
"loss": 1.296,
"step": 948
},
{
"epoch": 1.21,
"learning_rate": 1.3492286120295624e-05,
"loss": 1.3322,
"step": 949
},
{
"epoch": 1.22,
"learning_rate": 1.3479325962359263e-05,
"loss": 1.1685,
"step": 950
},
{
"epoch": 1.22,
"learning_rate": 1.3466359152026197e-05,
"loss": 1.0792,
"step": 951
},
{
"epoch": 1.22,
"learning_rate": 1.3453385714088686e-05,
"loss": 1.3691,
"step": 952
},
{
"epoch": 1.22,
"learning_rate": 1.3440405673351668e-05,
"loss": 1.2432,
"step": 953
},
{
"epoch": 1.22,
"learning_rate": 1.3427419054632705e-05,
"loss": 1.2322,
"step": 954
},
{
"epoch": 1.22,
"learning_rate": 1.341442588276193e-05,
"loss": 1.2585,
"step": 955
},
{
"epoch": 1.22,
"learning_rate": 1.3401426182582009e-05,
"loss": 1.2795,
"step": 956
},
{
"epoch": 1.22,
"learning_rate": 1.3388419978948092e-05,
"loss": 1.222,
"step": 957
},
{
"epoch": 1.23,
"learning_rate": 1.3375407296727762e-05,
"loss": 1.0831,
"step": 958
},
{
"epoch": 1.23,
"learning_rate": 1.3362388160800992e-05,
"loss": 1.1849,
"step": 959
},
{
"epoch": 1.23,
"learning_rate": 1.3349362596060084e-05,
"loss": 1.2971,
"step": 960
},
{
"epoch": 1.23,
"learning_rate": 1.3336330627409642e-05,
"loss": 1.1618,
"step": 961
},
{
"epoch": 1.23,
"learning_rate": 1.332329227976651e-05,
"loss": 1.205,
"step": 962
},
{
"epoch": 1.23,
"learning_rate": 1.3310247578059734e-05,
"loss": 1.2194,
"step": 963
},
{
"epoch": 1.23,
"learning_rate": 1.3297196547230497e-05,
"loss": 1.223,
"step": 964
},
{
"epoch": 1.24,
"learning_rate": 1.3284139212232095e-05,
"loss": 1.3378,
"step": 965
},
{
"epoch": 1.24,
"learning_rate": 1.327107559802987e-05,
"loss": 1.2353,
"step": 966
},
{
"epoch": 1.24,
"learning_rate": 1.3258005729601178e-05,
"loss": 1.1581,
"step": 967
},
{
"epoch": 1.24,
"learning_rate": 1.3244929631935322e-05,
"loss": 1.2425,
"step": 968
},
{
"epoch": 1.24,
"learning_rate": 1.3231847330033521e-05,
"loss": 1.1883,
"step": 969
},
{
"epoch": 1.24,
"learning_rate": 1.3218758848908857e-05,
"loss": 1.1119,
"step": 970
},
{
"epoch": 1.24,
"learning_rate": 1.3205664213586227e-05,
"loss": 1.2546,
"step": 971
},
{
"epoch": 1.24,
"learning_rate": 1.3192563449102291e-05,
"loss": 1.0959,
"step": 972
},
{
"epoch": 1.25,
"learning_rate": 1.3179456580505432e-05,
"loss": 1.2063,
"step": 973
},
{
"epoch": 1.25,
"learning_rate": 1.31663436328557e-05,
"loss": 1.1055,
"step": 974
},
{
"epoch": 1.25,
"learning_rate": 1.3153224631224772e-05,
"loss": 1.2694,
"step": 975
},
{
"epoch": 1.25,
"learning_rate": 1.3140099600695899e-05,
"loss": 1.0975,
"step": 976
},
{
"epoch": 1.25,
"learning_rate": 1.3126968566363853e-05,
"loss": 1.2222,
"step": 977
},
{
"epoch": 1.25,
"learning_rate": 1.3113831553334894e-05,
"loss": 1.286,
"step": 978
},
{
"epoch": 1.25,
"learning_rate": 1.310068858672671e-05,
"loss": 1.2431,
"step": 979
},
{
"epoch": 1.25,
"learning_rate": 1.3087539691668373e-05,
"loss": 1.2218,
"step": 980
},
{
"epoch": 1.26,
"learning_rate": 1.3074384893300285e-05,
"loss": 1.1672,
"step": 981
},
{
"epoch": 1.26,
"learning_rate": 1.3061224216774137e-05,
"loss": 1.252,
"step": 982
},
{
"epoch": 1.26,
"learning_rate": 1.3048057687252866e-05,
"loss": 1.0989,
"step": 983
},
{
"epoch": 1.26,
"learning_rate": 1.3034885329910593e-05,
"loss": 1.3368,
"step": 984
},
{
"epoch": 1.26,
"learning_rate": 1.3021707169932585e-05,
"loss": 1.2396,
"step": 985
},
{
"epoch": 1.26,
"learning_rate": 1.3008523232515193e-05,
"loss": 1.1901,
"step": 986
},
{
"epoch": 1.26,
"learning_rate": 1.2995333542865831e-05,
"loss": 1.1528,
"step": 987
},
{
"epoch": 1.26,
"learning_rate": 1.2982138126202901e-05,
"loss": 1.2131,
"step": 988
},
{
"epoch": 1.27,
"learning_rate": 1.2968937007755756e-05,
"loss": 1.1468,
"step": 989
},
{
"epoch": 1.27,
"learning_rate": 1.2955730212764655e-05,
"loss": 1.2623,
"step": 990
},
{
"epoch": 1.27,
"learning_rate": 1.2942517766480702e-05,
"loss": 1.2391,
"step": 991
},
{
"epoch": 1.27,
"learning_rate": 1.2929299694165813e-05,
"loss": 1.2141,
"step": 992
},
{
"epoch": 1.27,
"learning_rate": 1.2916076021092661e-05,
"loss": 1.1282,
"step": 993
},
{
"epoch": 1.27,
"learning_rate": 1.2902846772544625e-05,
"loss": 1.2265,
"step": 994
},
{
"epoch": 1.27,
"learning_rate": 1.2889611973815746e-05,
"loss": 1.2512,
"step": 995
},
{
"epoch": 1.27,
"learning_rate": 1.2876371650210671e-05,
"loss": 1.3452,
"step": 996
},
{
"epoch": 1.28,
"learning_rate": 1.2863125827044619e-05,
"loss": 1.2332,
"step": 997
},
{
"epoch": 1.28,
"learning_rate": 1.2849874529643318e-05,
"loss": 1.3424,
"step": 998
},
{
"epoch": 1.28,
"learning_rate": 1.2836617783342968e-05,
"loss": 1.1914,
"step": 999
},
{
"epoch": 1.28,
"learning_rate": 1.2823355613490182e-05,
"loss": 1.2177,
"step": 1000
},
{
"epoch": 1.28,
"learning_rate": 1.2810088045441944e-05,
"loss": 1.1754,
"step": 1001
},
{
"epoch": 1.28,
"learning_rate": 1.2796815104565559e-05,
"loss": 1.1826,
"step": 1002
},
{
"epoch": 1.28,
"learning_rate": 1.278353681623861e-05,
"loss": 1.2538,
"step": 1003
},
{
"epoch": 1.29,
"learning_rate": 1.2770253205848895e-05,
"loss": 1.1912,
"step": 1004
},
{
"epoch": 1.29,
"learning_rate": 1.2756964298794396e-05,
"loss": 1.0092,
"step": 1005
},
{
"epoch": 1.29,
"learning_rate": 1.2743670120483216e-05,
"loss": 1.1961,
"step": 1006
},
{
"epoch": 1.29,
"learning_rate": 1.2730370696333538e-05,
"loss": 1.204,
"step": 1007
},
{
"epoch": 1.29,
"learning_rate": 1.271706605177358e-05,
"loss": 1.3658,
"step": 1008
},
{
"epoch": 1.29,
"learning_rate": 1.270375621224154e-05,
"loss": 1.2451,
"step": 1009
},
{
"epoch": 1.29,
"learning_rate": 1.2690441203185537e-05,
"loss": 1.2666,
"step": 1010
},
{
"epoch": 1.29,
"learning_rate": 1.2677121050063588e-05,
"loss": 1.0864,
"step": 1011
},
{
"epoch": 1.3,
"learning_rate": 1.2663795778343543e-05,
"loss": 1.1692,
"step": 1012
},
{
"epoch": 1.3,
"learning_rate": 1.2650465413503033e-05,
"loss": 1.3123,
"step": 1013
},
{
"epoch": 1.3,
"learning_rate": 1.2637129981029428e-05,
"loss": 1.2077,
"step": 1014
},
{
"epoch": 1.3,
"learning_rate": 1.2623789506419792e-05,
"loss": 1.1327,
"step": 1015
},
{
"epoch": 1.3,
"learning_rate": 1.2610444015180825e-05,
"loss": 1.2426,
"step": 1016
},
{
"epoch": 1.3,
"learning_rate": 1.2597093532828826e-05,
"loss": 1.285,
"step": 1017
},
{
"epoch": 1.3,
"learning_rate": 1.2583738084889623e-05,
"loss": 1.2837,
"step": 1018
},
{
"epoch": 1.3,
"learning_rate": 1.2570377696898552e-05,
"loss": 1.1604,
"step": 1019
},
{
"epoch": 1.31,
"learning_rate": 1.2557012394400387e-05,
"loss": 1.1691,
"step": 1020
},
{
"epoch": 1.31,
"learning_rate": 1.2543642202949297e-05,
"loss": 1.246,
"step": 1021
},
{
"epoch": 1.31,
"learning_rate": 1.253026714810881e-05,
"loss": 1.1309,
"step": 1022
},
{
"epoch": 1.31,
"learning_rate": 1.2516887255451735e-05,
"loss": 1.2366,
"step": 1023
},
{
"epoch": 1.31,
"learning_rate": 1.2503502550560145e-05,
"loss": 1.3223,
"step": 1024
},
{
"epoch": 1.31,
"learning_rate": 1.2490113059025308e-05,
"loss": 1.2855,
"step": 1025
},
{
"epoch": 1.31,
"learning_rate": 1.2476718806447646e-05,
"loss": 1.2117,
"step": 1026
},
{
"epoch": 1.31,
"learning_rate": 1.2463319818436681e-05,
"loss": 1.2173,
"step": 1027
},
{
"epoch": 1.32,
"learning_rate": 1.2449916120610991e-05,
"loss": 1.2821,
"step": 1028
},
{
"epoch": 1.32,
"learning_rate": 1.2436507738598162e-05,
"loss": 1.178,
"step": 1029
},
{
"epoch": 1.32,
"learning_rate": 1.2423094698034732e-05,
"loss": 1.2223,
"step": 1030
},
{
"epoch": 1.32,
"learning_rate": 1.2409677024566145e-05,
"loss": 1.2041,
"step": 1031
},
{
"epoch": 1.32,
"learning_rate": 1.2396254743846707e-05,
"loss": 1.2204,
"step": 1032
},
{
"epoch": 1.32,
"learning_rate": 1.2382827881539531e-05,
"loss": 1.2247,
"step": 1033
},
{
"epoch": 1.32,
"learning_rate": 1.2369396463316491e-05,
"loss": 1.2221,
"step": 1034
},
{
"epoch": 1.32,
"learning_rate": 1.2355960514858171e-05,
"loss": 1.1776,
"step": 1035
},
{
"epoch": 1.33,
"learning_rate": 1.2342520061853812e-05,
"loss": 1.2304,
"step": 1036
},
{
"epoch": 1.33,
"learning_rate": 1.232907513000128e-05,
"loss": 1.1772,
"step": 1037
},
{
"epoch": 1.33,
"learning_rate": 1.2315625745006991e-05,
"loss": 1.1897,
"step": 1038
},
{
"epoch": 1.33,
"learning_rate": 1.2302171932585885e-05,
"loss": 1.226,
"step": 1039
},
{
"epoch": 1.33,
"learning_rate": 1.2288713718461356e-05,
"loss": 1.1921,
"step": 1040
},
{
"epoch": 1.33,
"learning_rate": 1.227525112836523e-05,
"loss": 1.2414,
"step": 1041
},
{
"epoch": 1.33,
"learning_rate": 1.2261784188037682e-05,
"loss": 1.2773,
"step": 1042
},
{
"epoch": 1.34,
"learning_rate": 1.2248312923227224e-05,
"loss": 1.3523,
"step": 1043
},
{
"epoch": 1.34,
"learning_rate": 1.2234837359690616e-05,
"loss": 1.1346,
"step": 1044
},
{
"epoch": 1.34,
"learning_rate": 1.2221357523192851e-05,
"loss": 1.2644,
"step": 1045
},
{
"epoch": 1.34,
"learning_rate": 1.2207873439507087e-05,
"loss": 1.209,
"step": 1046
},
{
"epoch": 1.34,
"learning_rate": 1.2194385134414608e-05,
"loss": 1.2497,
"step": 1047
},
{
"epoch": 1.34,
"learning_rate": 1.2180892633704756e-05,
"loss": 1.2583,
"step": 1048
},
{
"epoch": 1.34,
"learning_rate": 1.2167395963174906e-05,
"loss": 1.2783,
"step": 1049
},
{
"epoch": 1.34,
"learning_rate": 1.2153895148630406e-05,
"loss": 1.1737,
"step": 1050
},
{
"epoch": 1.35,
"learning_rate": 1.2140390215884523e-05,
"loss": 1.2858,
"step": 1051
},
{
"epoch": 1.35,
"learning_rate": 1.2126881190758397e-05,
"loss": 1.2904,
"step": 1052
},
{
"epoch": 1.35,
"learning_rate": 1.2113368099080997e-05,
"loss": 1.1233,
"step": 1053
},
{
"epoch": 1.35,
"learning_rate": 1.2099850966689064e-05,
"loss": 1.2289,
"step": 1054
},
{
"epoch": 1.35,
"learning_rate": 1.2086329819427065e-05,
"loss": 1.1652,
"step": 1055
},
{
"epoch": 1.35,
"learning_rate": 1.2072804683147146e-05,
"loss": 1.288,
"step": 1056
},
{
"epoch": 1.35,
"learning_rate": 1.2059275583709074e-05,
"loss": 1.2332,
"step": 1057
},
{
"epoch": 1.35,
"learning_rate": 1.20457425469802e-05,
"loss": 1.2306,
"step": 1058
},
{
"epoch": 1.36,
"learning_rate": 1.20322055988354e-05,
"loss": 1.2533,
"step": 1059
},
{
"epoch": 1.36,
"learning_rate": 1.2018664765157029e-05,
"loss": 1.1684,
"step": 1060
},
{
"epoch": 1.36,
"learning_rate": 1.200512007183487e-05,
"loss": 1.1907,
"step": 1061
},
{
"epoch": 1.36,
"learning_rate": 1.1991571544766085e-05,
"loss": 1.2096,
"step": 1062
},
{
"epoch": 1.36,
"learning_rate": 1.1978019209855174e-05,
"loss": 1.1476,
"step": 1063
},
{
"epoch": 1.36,
"learning_rate": 1.1964463093013905e-05,
"loss": 1.2318,
"step": 1064
},
{
"epoch": 1.36,
"learning_rate": 1.1950903220161286e-05,
"loss": 1.1828,
"step": 1065
},
{
"epoch": 1.36,
"learning_rate": 1.1937339617223498e-05,
"loss": 1.1491,
"step": 1066
},
{
"epoch": 1.37,
"learning_rate": 1.1923772310133866e-05,
"loss": 1.2285,
"step": 1067
},
{
"epoch": 1.37,
"learning_rate": 1.191020132483279e-05,
"loss": 1.2351,
"step": 1068
},
{
"epoch": 1.37,
"learning_rate": 1.1896626687267698e-05,
"loss": 1.1737,
"step": 1069
},
{
"epoch": 1.37,
"learning_rate": 1.188304842339301e-05,
"loss": 1.2429,
"step": 1070
},
{
"epoch": 1.37,
"learning_rate": 1.1869466559170073e-05,
"loss": 1.1993,
"step": 1071
},
{
"epoch": 1.37,
"learning_rate": 1.1855881120567125e-05,
"loss": 1.2313,
"step": 1072
},
{
"epoch": 1.37,
"learning_rate": 1.184229213355923e-05,
"loss": 1.1466,
"step": 1073
},
{
"epoch": 1.37,
"learning_rate": 1.1828699624128241e-05,
"loss": 1.1341,
"step": 1074
},
{
"epoch": 1.38,
"learning_rate": 1.1815103618262746e-05,
"loss": 1.1827,
"step": 1075
},
{
"epoch": 1.38,
"learning_rate": 1.1801504141958016e-05,
"loss": 1.3454,
"step": 1076
},
{
"epoch": 1.38,
"learning_rate": 1.1787901221215956e-05,
"loss": 1.1905,
"step": 1077
},
{
"epoch": 1.38,
"learning_rate": 1.1774294882045063e-05,
"loss": 1.2414,
"step": 1078
},
{
"epoch": 1.38,
"learning_rate": 1.1760685150460363e-05,
"loss": 1.1697,
"step": 1079
},
{
"epoch": 1.38,
"learning_rate": 1.1747072052483374e-05,
"loss": 1.2075,
"step": 1080
},
{
"epoch": 1.38,
"learning_rate": 1.1733455614142047e-05,
"loss": 1.2436,
"step": 1081
},
{
"epoch": 1.38,
"learning_rate": 1.1719835861470717e-05,
"loss": 1.1449,
"step": 1082
},
{
"epoch": 1.39,
"learning_rate": 1.1706212820510061e-05,
"loss": 1.1728,
"step": 1083
},
{
"epoch": 1.39,
"learning_rate": 1.1692586517307047e-05,
"loss": 1.2989,
"step": 1084
},
{
"epoch": 1.39,
"learning_rate": 1.1678956977914868e-05,
"loss": 1.194,
"step": 1085
},
{
"epoch": 1.39,
"learning_rate": 1.1665324228392914e-05,
"loss": 1.1926,
"step": 1086
},
{
"epoch": 1.39,
"learning_rate": 1.1651688294806706e-05,
"loss": 1.2826,
"step": 1087
},
{
"epoch": 1.39,
"learning_rate": 1.1638049203227868e-05,
"loss": 1.2815,
"step": 1088
},
{
"epoch": 1.39,
"learning_rate": 1.1624406979734038e-05,
"loss": 1.4368,
"step": 1089
},
{
"epoch": 1.4,
"learning_rate": 1.1610761650408862e-05,
"loss": 1.292,
"step": 1090
},
{
"epoch": 1.4,
"learning_rate": 1.1597113241341915e-05,
"loss": 1.2566,
"step": 1091
},
{
"epoch": 1.4,
"learning_rate": 1.1583461778628664e-05,
"loss": 1.2278,
"step": 1092
},
{
"epoch": 1.4,
"learning_rate": 1.1569807288370417e-05,
"loss": 1.1719,
"step": 1093
},
{
"epoch": 1.4,
"learning_rate": 1.1556149796674259e-05,
"loss": 1.2424,
"step": 1094
},
{
"epoch": 1.4,
"learning_rate": 1.1542489329653024e-05,
"loss": 1.2071,
"step": 1095
},
{
"epoch": 1.4,
"learning_rate": 1.1528825913425237e-05,
"loss": 1.2317,
"step": 1096
},
{
"epoch": 1.4,
"learning_rate": 1.1515159574115053e-05,
"loss": 1.1678,
"step": 1097
},
{
"epoch": 1.41,
"learning_rate": 1.1501490337852221e-05,
"loss": 1.1983,
"step": 1098
},
{
"epoch": 1.41,
"learning_rate": 1.1487818230772025e-05,
"loss": 1.2461,
"step": 1099
},
{
"epoch": 1.41,
"learning_rate": 1.1474143279015247e-05,
"loss": 1.2219,
"step": 1100
},
{
"epoch": 1.41,
"learning_rate": 1.1460465508728097e-05,
"loss": 1.2425,
"step": 1101
},
{
"epoch": 1.41,
"learning_rate": 1.1446784946062181e-05,
"loss": 1.165,
"step": 1102
},
{
"epoch": 1.41,
"learning_rate": 1.143310161717444e-05,
"loss": 1.1056,
"step": 1103
},
{
"epoch": 1.41,
"learning_rate": 1.1419415548227109e-05,
"loss": 1.2139,
"step": 1104
},
{
"epoch": 1.41,
"learning_rate": 1.1405726765387654e-05,
"loss": 1.2269,
"step": 1105
},
{
"epoch": 1.42,
"learning_rate": 1.1392035294828738e-05,
"loss": 1.1764,
"step": 1106
},
{
"epoch": 1.42,
"learning_rate": 1.1378341162728158e-05,
"loss": 1.1935,
"step": 1107
},
{
"epoch": 1.42,
"learning_rate": 1.13646443952688e-05,
"loss": 1.2995,
"step": 1108
},
{
"epoch": 1.42,
"learning_rate": 1.1350945018638596e-05,
"loss": 1.2678,
"step": 1109
},
{
"epoch": 1.42,
"learning_rate": 1.1337243059030451e-05,
"loss": 1.259,
"step": 1110
},
{
"epoch": 1.42,
"learning_rate": 1.1323538542642227e-05,
"loss": 1.2291,
"step": 1111
},
{
"epoch": 1.42,
"learning_rate": 1.130983149567666e-05,
"loss": 1.2805,
"step": 1112
},
{
"epoch": 1.42,
"learning_rate": 1.1296121944341332e-05,
"loss": 1.2107,
"step": 1113
},
{
"epoch": 1.43,
"learning_rate": 1.1282409914848616e-05,
"loss": 1.1662,
"step": 1114
},
{
"epoch": 1.43,
"learning_rate": 1.1268695433415608e-05,
"loss": 1.2584,
"step": 1115
},
{
"epoch": 1.43,
"learning_rate": 1.1254978526264113e-05,
"loss": 1.2842,
"step": 1116
},
{
"epoch": 1.43,
"learning_rate": 1.1241259219620559e-05,
"loss": 1.2067,
"step": 1117
},
{
"epoch": 1.43,
"learning_rate": 1.1227537539715969e-05,
"loss": 1.2046,
"step": 1118
},
{
"epoch": 1.43,
"learning_rate": 1.1213813512785897e-05,
"loss": 1.2397,
"step": 1119
},
{
"epoch": 1.43,
"learning_rate": 1.1200087165070393e-05,
"loss": 1.2248,
"step": 1120
},
{
"epoch": 1.43,
"learning_rate": 1.1186358522813935e-05,
"loss": 1.1961,
"step": 1121
},
{
"epoch": 1.44,
"learning_rate": 1.1172627612265397e-05,
"loss": 1.2,
"step": 1122
},
{
"epoch": 1.44,
"learning_rate": 1.1158894459677983e-05,
"loss": 1.2396,
"step": 1123
},
{
"epoch": 1.44,
"learning_rate": 1.1145159091309189e-05,
"loss": 1.1822,
"step": 1124
},
{
"epoch": 1.44,
"learning_rate": 1.113142153342074e-05,
"loss": 1.2142,
"step": 1125
},
{
"epoch": 1.44,
"learning_rate": 1.111768181227856e-05,
"loss": 1.1318,
"step": 1126
},
{
"epoch": 1.44,
"learning_rate": 1.11039399541527e-05,
"loss": 1.2041,
"step": 1127
},
{
"epoch": 1.44,
"learning_rate": 1.1090195985317294e-05,
"loss": 1.2663,
"step": 1128
},
{
"epoch": 1.45,
"learning_rate": 1.1076449932050517e-05,
"loss": 1.266,
"step": 1129
},
{
"epoch": 1.45,
"learning_rate": 1.106270182063453e-05,
"loss": 1.1773,
"step": 1130
},
{
"epoch": 1.45,
"learning_rate": 1.1048951677355426e-05,
"loss": 1.1955,
"step": 1131
},
{
"epoch": 1.45,
"learning_rate": 1.1035199528503188e-05,
"loss": 1.0673,
"step": 1132
},
{
"epoch": 1.45,
"learning_rate": 1.1021445400371626e-05,
"loss": 1.2931,
"step": 1133
},
{
"epoch": 1.45,
"learning_rate": 1.1007689319258339e-05,
"loss": 1.1637,
"step": 1134
},
{
"epoch": 1.45,
"learning_rate": 1.099393131146466e-05,
"loss": 1.2179,
"step": 1135
},
{
"epoch": 1.45,
"learning_rate": 1.098017140329561e-05,
"loss": 1.2468,
"step": 1136
},
{
"epoch": 1.46,
"learning_rate": 1.0966409621059827e-05,
"loss": 1.1762,
"step": 1137
},
{
"epoch": 1.46,
"learning_rate": 1.0952645991069555e-05,
"loss": 1.2549,
"step": 1138
},
{
"epoch": 1.46,
"learning_rate": 1.0938880539640555e-05,
"loss": 1.2583,
"step": 1139
},
{
"epoch": 1.46,
"learning_rate": 1.0925113293092076e-05,
"loss": 1.1927,
"step": 1140
},
{
"epoch": 1.46,
"learning_rate": 1.0911344277746798e-05,
"loss": 1.101,
"step": 1141
},
{
"epoch": 1.46,
"learning_rate": 1.0897573519930785e-05,
"loss": 1.2897,
"step": 1142
},
{
"epoch": 1.46,
"learning_rate": 1.0883801045973425e-05,
"loss": 1.2225,
"step": 1143
},
{
"epoch": 1.46,
"learning_rate": 1.08700268822074e-05,
"loss": 1.2594,
"step": 1144
},
{
"epoch": 1.47,
"learning_rate": 1.0856251054968615e-05,
"loss": 1.1848,
"step": 1145
},
{
"epoch": 1.47,
"learning_rate": 1.0842473590596158e-05,
"loss": 1.2013,
"step": 1146
},
{
"epoch": 1.47,
"learning_rate": 1.0828694515432239e-05,
"loss": 1.2891,
"step": 1147
},
{
"epoch": 1.47,
"learning_rate": 1.081491385582216e-05,
"loss": 1.3359,
"step": 1148
},
{
"epoch": 1.47,
"learning_rate": 1.0801131638114247e-05,
"loss": 1.1543,
"step": 1149
},
{
"epoch": 1.47,
"learning_rate": 1.07873478886598e-05,
"loss": 1.2348,
"step": 1150
},
{
"epoch": 1.47,
"learning_rate": 1.0773562633813061e-05,
"loss": 1.2465,
"step": 1151
},
{
"epoch": 1.47,
"learning_rate": 1.0759775899931135e-05,
"loss": 1.128,
"step": 1152
},
{
"epoch": 1.48,
"learning_rate": 1.0745987713373962e-05,
"loss": 1.2658,
"step": 1153
},
{
"epoch": 1.48,
"learning_rate": 1.0732198100504266e-05,
"loss": 1.0994,
"step": 1154
},
{
"epoch": 1.48,
"learning_rate": 1.0718407087687486e-05,
"loss": 1.1552,
"step": 1155
},
{
"epoch": 1.48,
"learning_rate": 1.070461470129174e-05,
"loss": 1.2499,
"step": 1156
},
{
"epoch": 1.48,
"learning_rate": 1.0690820967687782e-05,
"loss": 1.1218,
"step": 1157
},
{
"epoch": 1.48,
"learning_rate": 1.0677025913248933e-05,
"loss": 1.1318,
"step": 1158
},
{
"epoch": 1.48,
"learning_rate": 1.066322956435104e-05,
"loss": 1.145,
"step": 1159
},
{
"epoch": 1.48,
"learning_rate": 1.0649431947372428e-05,
"loss": 1.2118,
"step": 1160
},
{
"epoch": 1.49,
"learning_rate": 1.0635633088693844e-05,
"loss": 1.1378,
"step": 1161
},
{
"epoch": 1.49,
"learning_rate": 1.0621833014698413e-05,
"loss": 1.1867,
"step": 1162
},
{
"epoch": 1.49,
"learning_rate": 1.0608031751771577e-05,
"loss": 1.2299,
"step": 1163
},
{
"epoch": 1.49,
"learning_rate": 1.0594229326301058e-05,
"loss": 1.3025,
"step": 1164
},
{
"epoch": 1.49,
"learning_rate": 1.0580425764676796e-05,
"loss": 1.1908,
"step": 1165
},
{
"epoch": 1.49,
"learning_rate": 1.0566621093290905e-05,
"loss": 1.2278,
"step": 1166
},
{
"epoch": 1.49,
"learning_rate": 1.0552815338537621e-05,
"loss": 1.1709,
"step": 1167
},
{
"epoch": 1.5,
"learning_rate": 1.0539008526813255e-05,
"loss": 1.1814,
"step": 1168
},
{
"epoch": 1.5,
"learning_rate": 1.0525200684516131e-05,
"loss": 1.1933,
"step": 1169
},
{
"epoch": 1.5,
"learning_rate": 1.0511391838046547e-05,
"loss": 1.2449,
"step": 1170
},
{
"epoch": 1.5,
"learning_rate": 1.0497582013806723e-05,
"loss": 1.1893,
"step": 1171
},
{
"epoch": 1.5,
"learning_rate": 1.0483771238200752e-05,
"loss": 1.1745,
"step": 1172
},
{
"epoch": 1.5,
"learning_rate": 1.0469959537634535e-05,
"loss": 1.1528,
"step": 1173
},
{
"epoch": 1.5,
"learning_rate": 1.045614693851575e-05,
"loss": 1.1539,
"step": 1174
},
{
"epoch": 1.5,
"learning_rate": 1.044233346725379e-05,
"loss": 1.1539,
"step": 1175
},
{
"epoch": 1.51,
"learning_rate": 1.0428519150259717e-05,
"loss": 1.2377,
"step": 1176
},
{
"epoch": 1.51,
"learning_rate": 1.0414704013946206e-05,
"loss": 1.2317,
"step": 1177
},
{
"epoch": 1.51,
"learning_rate": 1.0400888084727506e-05,
"loss": 1.217,
"step": 1178
},
{
"epoch": 1.51,
"learning_rate": 1.0387071389019371e-05,
"loss": 1.177,
"step": 1179
},
{
"epoch": 1.51,
"learning_rate": 1.037325395323904e-05,
"loss": 1.3033,
"step": 1180
},
{
"epoch": 1.51,
"learning_rate": 1.035943580380514e-05,
"loss": 1.2733,
"step": 1181
},
{
"epoch": 1.51,
"learning_rate": 1.0345616967137686e-05,
"loss": 1.2211,
"step": 1182
},
{
"epoch": 1.51,
"learning_rate": 1.0331797469657992e-05,
"loss": 1.3157,
"step": 1183
},
{
"epoch": 1.52,
"learning_rate": 1.0317977337788646e-05,
"loss": 1.1992,
"step": 1184
},
{
"epoch": 1.52,
"learning_rate": 1.0304156597953443e-05,
"loss": 1.1105,
"step": 1185
},
{
"epoch": 1.52,
"learning_rate": 1.0290335276577336e-05,
"loss": 1.2747,
"step": 1186
},
{
"epoch": 1.52,
"learning_rate": 1.0276513400086403e-05,
"loss": 1.3201,
"step": 1187
},
{
"epoch": 1.52,
"learning_rate": 1.0262690994907771e-05,
"loss": 1.2312,
"step": 1188
},
{
"epoch": 1.52,
"learning_rate": 1.0248868087469586e-05,
"loss": 1.2129,
"step": 1189
},
{
"epoch": 1.52,
"learning_rate": 1.0235044704200947e-05,
"loss": 1.1454,
"step": 1190
},
{
"epoch": 1.52,
"learning_rate": 1.022122087153187e-05,
"loss": 1.3206,
"step": 1191
},
{
"epoch": 1.53,
"learning_rate": 1.0207396615893223e-05,
"loss": 1.3062,
"step": 1192
},
{
"epoch": 1.53,
"learning_rate": 1.0193571963716695e-05,
"loss": 1.2413,
"step": 1193
},
{
"epoch": 1.53,
"learning_rate": 1.0179746941434714e-05,
"loss": 1.2914,
"step": 1194
},
{
"epoch": 1.53,
"learning_rate": 1.0165921575480433e-05,
"loss": 1.1856,
"step": 1195
},
{
"epoch": 1.53,
"learning_rate": 1.0152095892287653e-05,
"loss": 1.2448,
"step": 1196
},
{
"epoch": 1.53,
"learning_rate": 1.0138269918290788e-05,
"loss": 1.2546,
"step": 1197
},
{
"epoch": 1.53,
"learning_rate": 1.0124443679924799e-05,
"loss": 1.2695,
"step": 1198
},
{
"epoch": 1.53,
"learning_rate": 1.011061720362516e-05,
"loss": 1.2566,
"step": 1199
},
{
"epoch": 1.54,
"learning_rate": 1.0096790515827795e-05,
"loss": 1.2004,
"step": 1200
},
{
"epoch": 1.54,
"learning_rate": 1.0082963642969041e-05,
"loss": 1.2348,
"step": 1201
},
{
"epoch": 1.54,
"learning_rate": 1.0069136611485577e-05,
"loss": 1.2215,
"step": 1202
},
{
"epoch": 1.54,
"learning_rate": 1.0055309447814394e-05,
"loss": 1.1867,
"step": 1203
},
{
"epoch": 1.54,
"learning_rate": 1.004148217839273e-05,
"loss": 1.0689,
"step": 1204
},
{
"epoch": 1.54,
"learning_rate": 1.0027654829658031e-05,
"loss": 1.1713,
"step": 1205
},
{
"epoch": 1.54,
"learning_rate": 1.001382742804789e-05,
"loss": 1.1697,
"step": 1206
},
{
"epoch": 1.54,
"learning_rate": 1e-05,
"loss": 1.2225,
"step": 1207
},
{
"epoch": 1.55,
"learning_rate": 9.986172571952116e-06,
"loss": 1.2603,
"step": 1208
},
{
"epoch": 1.55,
"learning_rate": 9.972345170341972e-06,
"loss": 1.3214,
"step": 1209
},
{
"epoch": 1.55,
"learning_rate": 9.958517821607272e-06,
"loss": 1.1838,
"step": 1210
},
{
"epoch": 1.55,
"learning_rate": 9.944690552185607e-06,
"loss": 1.2249,
"step": 1211
},
{
"epoch": 1.55,
"learning_rate": 9.930863388514425e-06,
"loss": 1.2893,
"step": 1212
},
{
"epoch": 1.55,
"learning_rate": 9.917036357030964e-06,
"loss": 1.3325,
"step": 1213
},
{
"epoch": 1.55,
"learning_rate": 9.903209484172205e-06,
"loss": 1.21,
"step": 1214
},
{
"epoch": 1.56,
"learning_rate": 9.889382796374844e-06,
"loss": 1.2518,
"step": 1215
},
{
"epoch": 1.56,
"learning_rate": 9.875556320075206e-06,
"loss": 1.2567,
"step": 1216
},
{
"epoch": 1.56,
"learning_rate": 9.861730081709216e-06,
"loss": 1.1867,
"step": 1217
},
{
"epoch": 1.56,
"learning_rate": 9.84790410771235e-06,
"loss": 1.2231,
"step": 1218
},
{
"epoch": 1.56,
"learning_rate": 9.834078424519568e-06,
"loss": 1.1213,
"step": 1219
},
{
"epoch": 1.56,
"learning_rate": 9.820253058565289e-06,
"loss": 1.2608,
"step": 1220
},
{
"epoch": 1.56,
"learning_rate": 9.806428036283312e-06,
"loss": 1.1948,
"step": 1221
},
{
"epoch": 1.56,
"learning_rate": 9.792603384106777e-06,
"loss": 1.2356,
"step": 1222
},
{
"epoch": 1.57,
"learning_rate": 9.778779128468133e-06,
"loss": 1.2408,
"step": 1223
},
{
"epoch": 1.57,
"learning_rate": 9.764955295799056e-06,
"loss": 1.1777,
"step": 1224
},
{
"epoch": 1.57,
"learning_rate": 9.751131912530416e-06,
"loss": 1.3538,
"step": 1225
},
{
"epoch": 1.57,
"learning_rate": 9.737309005092232e-06,
"loss": 1.1906,
"step": 1226
},
{
"epoch": 1.57,
"learning_rate": 9.723486599913598e-06,
"loss": 1.2888,
"step": 1227
},
{
"epoch": 1.57,
"learning_rate": 9.709664723422666e-06,
"loss": 1.2535,
"step": 1228
},
{
"epoch": 1.57,
"learning_rate": 9.695843402046562e-06,
"loss": 1.2193,
"step": 1229
},
{
"epoch": 1.57,
"learning_rate": 9.682022662211356e-06,
"loss": 1.3029,
"step": 1230
},
{
"epoch": 1.58,
"learning_rate": 9.66820253034201e-06,
"loss": 1.3119,
"step": 1231
},
{
"epoch": 1.58,
"learning_rate": 9.654383032862316e-06,
"loss": 1.177,
"step": 1232
},
{
"epoch": 1.58,
"learning_rate": 9.640564196194862e-06,
"loss": 1.2104,
"step": 1233
},
{
"epoch": 1.58,
"learning_rate": 9.626746046760967e-06,
"loss": 1.2007,
"step": 1234
},
{
"epoch": 1.58,
"learning_rate": 9.612928610980627e-06,
"loss": 1.1755,
"step": 1235
},
{
"epoch": 1.58,
"learning_rate": 9.5991119152725e-06,
"loss": 1.1419,
"step": 1236
},
{
"epoch": 1.58,
"learning_rate": 9.5852959860538e-06,
"loss": 1.2028,
"step": 1237
},
{
"epoch": 1.58,
"learning_rate": 9.571480849740287e-06,
"loss": 1.2802,
"step": 1238
},
{
"epoch": 1.59,
"learning_rate": 9.557666532746214e-06,
"loss": 1.3392,
"step": 1239
},
{
"epoch": 1.59,
"learning_rate": 9.543853061484251e-06,
"loss": 1.2309,
"step": 1240
},
{
"epoch": 1.59,
"learning_rate": 9.530040462365467e-06,
"loss": 1.1705,
"step": 1241
},
{
"epoch": 1.59,
"learning_rate": 9.516228761799251e-06,
"loss": 1.2026,
"step": 1242
},
{
"epoch": 1.59,
"learning_rate": 9.502417986193275e-06,
"loss": 1.2524,
"step": 1243
},
{
"epoch": 1.59,
"learning_rate": 9.488608161953455e-06,
"loss": 1.1734,
"step": 1244
},
{
"epoch": 1.59,
"learning_rate": 9.474799315483874e-06,
"loss": 1.159,
"step": 1245
},
{
"epoch": 1.59,
"learning_rate": 9.460991473186748e-06,
"loss": 1.2606,
"step": 1246
},
{
"epoch": 1.6,
"learning_rate": 9.447184661462382e-06,
"loss": 1.2185,
"step": 1247
},
{
"epoch": 1.6,
"learning_rate": 9.433378906709097e-06,
"loss": 1.1551,
"step": 1248
},
{
"epoch": 1.6,
"learning_rate": 9.419574235323208e-06,
"loss": 1.1854,
"step": 1249
},
{
"epoch": 1.6,
"learning_rate": 9.405770673698947e-06,
"loss": 1.2538,
"step": 1250
},
{
"epoch": 1.6,
"learning_rate": 9.391968248228425e-06,
"loss": 1.1945,
"step": 1251
},
{
"epoch": 1.6,
"learning_rate": 9.37816698530159e-06,
"loss": 1.227,
"step": 1252
},
{
"epoch": 1.6,
"learning_rate": 9.364366911306158e-06,
"loss": 1.2195,
"step": 1253
},
{
"epoch": 1.61,
"learning_rate": 9.350568052627574e-06,
"loss": 1.1223,
"step": 1254
},
{
"epoch": 1.61,
"learning_rate": 9.336770435648963e-06,
"loss": 1.1254,
"step": 1255
},
{
"epoch": 1.61,
"learning_rate": 9.322974086751069e-06,
"loss": 1.2231,
"step": 1256
},
{
"epoch": 1.61,
"learning_rate": 9.309179032312221e-06,
"loss": 1.1632,
"step": 1257
},
{
"epoch": 1.61,
"learning_rate": 9.29538529870826e-06,
"loss": 1.2553,
"step": 1258
},
{
"epoch": 1.61,
"learning_rate": 9.281592912312519e-06,
"loss": 1.1913,
"step": 1259
},
{
"epoch": 1.61,
"learning_rate": 9.26780189949574e-06,
"loss": 1.2201,
"step": 1260
},
{
"epoch": 1.61,
"learning_rate": 9.254012286626037e-06,
"loss": 1.2545,
"step": 1261
},
{
"epoch": 1.62,
"learning_rate": 9.240224100068868e-06,
"loss": 1.1376,
"step": 1262
},
{
"epoch": 1.62,
"learning_rate": 9.226437366186942e-06,
"loss": 1.2654,
"step": 1263
},
{
"epoch": 1.62,
"learning_rate": 9.2126521113402e-06,
"loss": 1.2355,
"step": 1264
},
{
"epoch": 1.62,
"learning_rate": 9.198868361885758e-06,
"loss": 1.2238,
"step": 1265
},
{
"epoch": 1.62,
"learning_rate": 9.185086144177843e-06,
"loss": 1.3105,
"step": 1266
},
{
"epoch": 1.62,
"learning_rate": 9.171305484567763e-06,
"loss": 1.2534,
"step": 1267
},
{
"epoch": 1.62,
"learning_rate": 9.157526409403845e-06,
"loss": 1.2002,
"step": 1268
},
{
"epoch": 1.62,
"learning_rate": 9.143748945031386e-06,
"loss": 1.1885,
"step": 1269
},
{
"epoch": 1.63,
"learning_rate": 9.129973117792601e-06,
"loss": 1.1954,
"step": 1270
},
{
"epoch": 1.63,
"learning_rate": 9.116198954026577e-06,
"loss": 1.1995,
"step": 1271
},
{
"epoch": 1.63,
"learning_rate": 9.10242648006922e-06,
"loss": 1.103,
"step": 1272
},
{
"epoch": 1.63,
"learning_rate": 9.088655722253205e-06,
"loss": 1.3276,
"step": 1273
},
{
"epoch": 1.63,
"learning_rate": 9.074886706907928e-06,
"loss": 1.1884,
"step": 1274
},
{
"epoch": 1.63,
"learning_rate": 9.061119460359448e-06,
"loss": 1.1646,
"step": 1275
},
{
"epoch": 1.63,
"learning_rate": 9.047354008930448e-06,
"loss": 1.2076,
"step": 1276
},
{
"epoch": 1.63,
"learning_rate": 9.033590378940174e-06,
"loss": 1.3016,
"step": 1277
},
{
"epoch": 1.64,
"learning_rate": 9.019828596704394e-06,
"loss": 1.2364,
"step": 1278
},
{
"epoch": 1.64,
"learning_rate": 9.006068688535342e-06,
"loss": 1.1564,
"step": 1279
},
{
"epoch": 1.64,
"learning_rate": 8.992310680741663e-06,
"loss": 1.2053,
"step": 1280
},
{
"epoch": 1.64,
"learning_rate": 8.978554599628377e-06,
"loss": 1.2804,
"step": 1281
},
{
"epoch": 1.64,
"learning_rate": 8.964800471496815e-06,
"loss": 1.1789,
"step": 1282
},
{
"epoch": 1.64,
"learning_rate": 8.951048322644576e-06,
"loss": 1.2137,
"step": 1283
},
{
"epoch": 1.64,
"learning_rate": 8.937298179365474e-06,
"loss": 1.2667,
"step": 1284
},
{
"epoch": 1.64,
"learning_rate": 8.923550067949486e-06,
"loss": 1.2012,
"step": 1285
},
{
"epoch": 1.65,
"learning_rate": 8.90980401468271e-06,
"loss": 1.1657,
"step": 1286
},
{
"epoch": 1.65,
"learning_rate": 8.896060045847305e-06,
"loss": 1.2268,
"step": 1287
},
{
"epoch": 1.65,
"learning_rate": 8.882318187721441e-06,
"loss": 1.1706,
"step": 1288
},
{
"epoch": 1.65,
"learning_rate": 8.868578466579261e-06,
"loss": 1.286,
"step": 1289
},
{
"epoch": 1.65,
"learning_rate": 8.854840908690815e-06,
"loss": 1.1666,
"step": 1290
},
{
"epoch": 1.65,
"learning_rate": 8.841105540322018e-06,
"loss": 1.1818,
"step": 1291
},
{
"epoch": 1.65,
"learning_rate": 8.827372387734607e-06,
"loss": 1.1979,
"step": 1292
},
{
"epoch": 1.66,
"learning_rate": 8.813641477186069e-06,
"loss": 1.3155,
"step": 1293
},
{
"epoch": 1.66,
"learning_rate": 8.799912834929612e-06,
"loss": 1.2488,
"step": 1294
},
{
"epoch": 1.66,
"learning_rate": 8.786186487214108e-06,
"loss": 1.2747,
"step": 1295
},
{
"epoch": 1.66,
"learning_rate": 8.772462460284033e-06,
"loss": 1.1985,
"step": 1296
},
{
"epoch": 1.66,
"learning_rate": 8.758740780379443e-06,
"loss": 1.1771,
"step": 1297
},
{
"epoch": 1.66,
"learning_rate": 8.745021473735889e-06,
"loss": 1.254,
"step": 1298
},
{
"epoch": 1.66,
"learning_rate": 8.731304566584394e-06,
"loss": 1.2877,
"step": 1299
},
{
"epoch": 1.66,
"learning_rate": 8.71759008515139e-06,
"loss": 1.2556,
"step": 1300
},
{
"epoch": 1.67,
"learning_rate": 8.703878055658668e-06,
"loss": 1.2291,
"step": 1301
},
{
"epoch": 1.67,
"learning_rate": 8.690168504323343e-06,
"loss": 1.2848,
"step": 1302
},
{
"epoch": 1.67,
"learning_rate": 8.676461457357777e-06,
"loss": 1.2288,
"step": 1303
},
{
"epoch": 1.67,
"learning_rate": 8.66275694096955e-06,
"loss": 1.2396,
"step": 1304
},
{
"epoch": 1.67,
"learning_rate": 8.64905498136141e-06,
"loss": 1.2925,
"step": 1305
},
{
"epoch": 1.67,
"learning_rate": 8.6353556047312e-06,
"loss": 1.137,
"step": 1306
},
{
"epoch": 1.67,
"learning_rate": 8.621658837271844e-06,
"loss": 1.1228,
"step": 1307
},
{
"epoch": 1.67,
"learning_rate": 8.607964705171267e-06,
"loss": 1.2767,
"step": 1308
},
{
"epoch": 1.68,
"learning_rate": 8.594273234612347e-06,
"loss": 1.089,
"step": 1309
},
{
"epoch": 1.68,
"learning_rate": 8.580584451772895e-06,
"loss": 1.2522,
"step": 1310
},
{
"epoch": 1.68,
"learning_rate": 8.566898382825558e-06,
"loss": 1.2113,
"step": 1311
},
{
"epoch": 1.68,
"learning_rate": 8.55321505393782e-06,
"loss": 1.1131,
"step": 1312
},
{
"epoch": 1.68,
"learning_rate": 8.539534491271906e-06,
"loss": 1.2038,
"step": 1313
},
{
"epoch": 1.68,
"learning_rate": 8.525856720984755e-06,
"loss": 1.151,
"step": 1314
},
{
"epoch": 1.68,
"learning_rate": 8.512181769227976e-06,
"loss": 1.1602,
"step": 1315
},
{
"epoch": 1.68,
"learning_rate": 8.498509662147784e-06,
"loss": 1.1346,
"step": 1316
},
{
"epoch": 1.69,
"learning_rate": 8.484840425884949e-06,
"loss": 1.3731,
"step": 1317
},
{
"epoch": 1.69,
"learning_rate": 8.471174086574767e-06,
"loss": 1.2035,
"step": 1318
},
{
"epoch": 1.69,
"learning_rate": 8.457510670346976e-06,
"loss": 1.2039,
"step": 1319
},
{
"epoch": 1.69,
"learning_rate": 8.443850203325745e-06,
"loss": 1.0988,
"step": 1320
},
{
"epoch": 1.69,
"learning_rate": 8.430192711629588e-06,
"loss": 1.3004,
"step": 1321
},
{
"epoch": 1.69,
"learning_rate": 8.416538221371336e-06,
"loss": 1.2406,
"step": 1322
},
{
"epoch": 1.69,
"learning_rate": 8.402886758658087e-06,
"loss": 1.1473,
"step": 1323
},
{
"epoch": 1.69,
"learning_rate": 8.389238349591143e-06,
"loss": 1.2939,
"step": 1324
},
{
"epoch": 1.7,
"learning_rate": 8.375593020265964e-06,
"loss": 1.1418,
"step": 1325
},
{
"epoch": 1.7,
"learning_rate": 8.361950796772139e-06,
"loss": 1.1144,
"step": 1326
},
{
"epoch": 1.7,
"learning_rate": 8.348311705193294e-06,
"loss": 1.2204,
"step": 1327
},
{
"epoch": 1.7,
"learning_rate": 8.334675771607091e-06,
"loss": 1.2422,
"step": 1328
},
{
"epoch": 1.7,
"learning_rate": 8.321043022085139e-06,
"loss": 1.2705,
"step": 1329
},
{
"epoch": 1.7,
"learning_rate": 8.307413482692955e-06,
"loss": 1.2326,
"step": 1330
},
{
"epoch": 1.7,
"learning_rate": 8.29378717948994e-06,
"loss": 1.1773,
"step": 1331
},
{
"epoch": 1.7,
"learning_rate": 8.280164138529285e-06,
"loss": 1.201,
"step": 1332
},
{
"epoch": 1.71,
"learning_rate": 8.266544385857958e-06,
"loss": 1.1861,
"step": 1333
},
{
"epoch": 1.71,
"learning_rate": 8.252927947516631e-06,
"loss": 1.0718,
"step": 1334
},
{
"epoch": 1.71,
"learning_rate": 8.239314849539639e-06,
"loss": 1.3154,
"step": 1335
},
{
"epoch": 1.71,
"learning_rate": 8.22570511795494e-06,
"loss": 1.2147,
"step": 1336
},
{
"epoch": 1.71,
"learning_rate": 8.212098778784049e-06,
"loss": 1.2228,
"step": 1337
},
{
"epoch": 1.71,
"learning_rate": 8.198495858041988e-06,
"loss": 1.2397,
"step": 1338
},
{
"epoch": 1.71,
"learning_rate": 8.184896381737257e-06,
"loss": 1.1285,
"step": 1339
},
{
"epoch": 1.72,
"learning_rate": 8.171300375871759e-06,
"loss": 1.0844,
"step": 1340
},
{
"epoch": 1.72,
"learning_rate": 8.157707866440772e-06,
"loss": 1.169,
"step": 1341
},
{
"epoch": 1.72,
"learning_rate": 8.144118879432879e-06,
"loss": 1.1869,
"step": 1342
},
{
"epoch": 1.72,
"learning_rate": 8.130533440829927e-06,
"loss": 1.3084,
"step": 1343
},
{
"epoch": 1.72,
"learning_rate": 8.116951576606994e-06,
"loss": 1.2427,
"step": 1344
},
{
"epoch": 1.72,
"learning_rate": 8.103373312732308e-06,
"loss": 1.2171,
"step": 1345
},
{
"epoch": 1.72,
"learning_rate": 8.089798675167214e-06,
"loss": 1.2308,
"step": 1346
},
{
"epoch": 1.72,
"learning_rate": 8.076227689866138e-06,
"loss": 1.3029,
"step": 1347
},
{
"epoch": 1.73,
"learning_rate": 8.062660382776503e-06,
"loss": 1.1341,
"step": 1348
},
{
"epoch": 1.73,
"learning_rate": 8.04909677983872e-06,
"loss": 1.1793,
"step": 1349
},
{
"epoch": 1.73,
"learning_rate": 8.0355369069861e-06,
"loss": 1.2853,
"step": 1350
},
{
"epoch": 1.73,
"learning_rate": 8.021980790144828e-06,
"loss": 1.2242,
"step": 1351
},
{
"epoch": 1.73,
"learning_rate": 8.008428455233916e-06,
"loss": 1.2111,
"step": 1352
},
{
"epoch": 1.73,
"learning_rate": 7.994879928165132e-06,
"loss": 1.2698,
"step": 1353
},
{
"epoch": 1.73,
"learning_rate": 7.981335234842975e-06,
"loss": 1.2268,
"step": 1354
},
{
"epoch": 1.73,
"learning_rate": 7.967794401164604e-06,
"loss": 1.2708,
"step": 1355
},
{
"epoch": 1.74,
"learning_rate": 7.954257453019802e-06,
"loss": 1.2289,
"step": 1356
},
{
"epoch": 1.74,
"learning_rate": 7.940724416290931e-06,
"loss": 1.2533,
"step": 1357
},
{
"epoch": 1.74,
"learning_rate": 7.927195316852861e-06,
"loss": 1.184,
"step": 1358
},
{
"epoch": 1.74,
"learning_rate": 7.913670180572936e-06,
"loss": 1.2034,
"step": 1359
},
{
"epoch": 1.74,
"learning_rate": 7.90014903331094e-06,
"loss": 1.1699,
"step": 1360
},
{
"epoch": 1.74,
"learning_rate": 7.886631900919005e-06,
"loss": 1.1744,
"step": 1361
},
{
"epoch": 1.74,
"learning_rate": 7.873118809241605e-06,
"loss": 1.2295,
"step": 1362
},
{
"epoch": 1.74,
"learning_rate": 7.85960978411548e-06,
"loss": 1.1816,
"step": 1363
},
{
"epoch": 1.75,
"learning_rate": 7.846104851369595e-06,
"loss": 1.196,
"step": 1364
},
{
"epoch": 1.75,
"learning_rate": 7.832604036825096e-06,
"loss": 1.2683,
"step": 1365
},
{
"epoch": 1.75,
"learning_rate": 7.81910736629525e-06,
"loss": 1.2391,
"step": 1366
},
{
"epoch": 1.75,
"learning_rate": 7.805614865585397e-06,
"loss": 1.2124,
"step": 1367
},
{
"epoch": 1.75,
"learning_rate": 7.792126560492915e-06,
"loss": 1.2382,
"step": 1368
},
{
"epoch": 1.75,
"learning_rate": 7.778642476807149e-06,
"loss": 1.1709,
"step": 1369
},
{
"epoch": 1.75,
"learning_rate": 7.765162640309387e-06,
"loss": 1.3215,
"step": 1370
},
{
"epoch": 1.75,
"learning_rate": 7.751687076772781e-06,
"loss": 1.1953,
"step": 1371
},
{
"epoch": 1.76,
"learning_rate": 7.738215811962318e-06,
"loss": 1.1826,
"step": 1372
},
{
"epoch": 1.76,
"learning_rate": 7.724748871634776e-06,
"loss": 1.1949,
"step": 1373
},
{
"epoch": 1.76,
"learning_rate": 7.711286281538644e-06,
"loss": 1.2285,
"step": 1374
},
{
"epoch": 1.76,
"learning_rate": 7.69782806741412e-06,
"loss": 1.1769,
"step": 1375
},
{
"epoch": 1.76,
"learning_rate": 7.684374254993012e-06,
"loss": 1.171,
"step": 1376
},
{
"epoch": 1.76,
"learning_rate": 7.670924869998721e-06,
"loss": 1.298,
"step": 1377
},
{
"epoch": 1.76,
"learning_rate": 7.65747993814619e-06,
"loss": 1.1573,
"step": 1378
},
{
"epoch": 1.77,
"learning_rate": 7.644039485141834e-06,
"loss": 1.203,
"step": 1379
},
{
"epoch": 1.77,
"learning_rate": 7.63060353668351e-06,
"loss": 1.2373,
"step": 1380
},
{
"epoch": 1.77,
"learning_rate": 7.617172118460472e-06,
"loss": 1.1766,
"step": 1381
},
{
"epoch": 1.77,
"learning_rate": 7.603745256153293e-06,
"loss": 1.1084,
"step": 1382
},
{
"epoch": 1.77,
"learning_rate": 7.590322975433857e-06,
"loss": 1.1462,
"step": 1383
},
{
"epoch": 1.77,
"learning_rate": 7.576905301965273e-06,
"loss": 1.1686,
"step": 1384
},
{
"epoch": 1.77,
"learning_rate": 7.5634922614018395e-06,
"loss": 1.2987,
"step": 1385
},
{
"epoch": 1.77,
"learning_rate": 7.550083879389012e-06,
"loss": 1.1828,
"step": 1386
},
{
"epoch": 1.78,
"learning_rate": 7.536680181563324e-06,
"loss": 1.2234,
"step": 1387
},
{
"epoch": 1.78,
"learning_rate": 7.5232811935523564e-06,
"loss": 1.2498,
"step": 1388
},
{
"epoch": 1.78,
"learning_rate": 7.5098869409746956e-06,
"loss": 1.1995,
"step": 1389
},
{
"epoch": 1.78,
"learning_rate": 7.496497449439857e-06,
"loss": 1.2482,
"step": 1390
},
{
"epoch": 1.78,
"learning_rate": 7.4831127445482675e-06,
"loss": 1.1674,
"step": 1391
},
{
"epoch": 1.78,
"learning_rate": 7.469732851891196e-06,
"loss": 1.3185,
"step": 1392
},
{
"epoch": 1.78,
"learning_rate": 7.456357797050702e-06,
"loss": 1.2152,
"step": 1393
},
{
"epoch": 1.78,
"learning_rate": 7.442987605599617e-06,
"loss": 1.2486,
"step": 1394
},
{
"epoch": 1.79,
"learning_rate": 7.429622303101452e-06,
"loss": 1.1224,
"step": 1395
},
{
"epoch": 1.79,
"learning_rate": 7.416261915110379e-06,
"loss": 1.1414,
"step": 1396
},
{
"epoch": 1.79,
"learning_rate": 7.402906467171178e-06,
"loss": 1.2516,
"step": 1397
},
{
"epoch": 1.79,
"learning_rate": 7.389555984819175e-06,
"loss": 1.2951,
"step": 1398
},
{
"epoch": 1.79,
"learning_rate": 7.376210493580211e-06,
"loss": 1.1454,
"step": 1399
},
{
"epoch": 1.79,
"learning_rate": 7.362870018970576e-06,
"loss": 1.2325,
"step": 1400
},
{
"epoch": 1.79,
"learning_rate": 7.349534586496972e-06,
"loss": 1.1991,
"step": 1401
},
{
"epoch": 1.79,
"learning_rate": 7.336204221656461e-06,
"loss": 1.2179,
"step": 1402
},
{
"epoch": 1.8,
"learning_rate": 7.3228789499364114e-06,
"loss": 1.3545,
"step": 1403
},
{
"epoch": 1.8,
"learning_rate": 7.309558796814466e-06,
"loss": 1.1229,
"step": 1404
},
{
"epoch": 1.8,
"learning_rate": 7.296243787758463e-06,
"loss": 1.1341,
"step": 1405
},
{
"epoch": 1.8,
"learning_rate": 7.282933948226418e-06,
"loss": 1.2491,
"step": 1406
},
{
"epoch": 1.8,
"learning_rate": 7.269629303666463e-06,
"loss": 1.2477,
"step": 1407
},
{
"epoch": 1.8,
"learning_rate": 7.256329879516788e-06,
"loss": 1.2735,
"step": 1408
},
{
"epoch": 1.8,
"learning_rate": 7.243035701205608e-06,
"loss": 1.1586,
"step": 1409
},
{
"epoch": 1.8,
"learning_rate": 7.229746794151107e-06,
"loss": 1.2793,
"step": 1410
},
{
"epoch": 1.81,
"learning_rate": 7.216463183761392e-06,
"loss": 1.1497,
"step": 1411
},
{
"epoch": 1.81,
"learning_rate": 7.203184895434443e-06,
"loss": 1.1339,
"step": 1412
},
{
"epoch": 1.81,
"learning_rate": 7.1899119545580595e-06,
"loss": 1.17,
"step": 1413
},
{
"epoch": 1.81,
"learning_rate": 7.176644386509821e-06,
"loss": 1.2709,
"step": 1414
},
{
"epoch": 1.81,
"learning_rate": 7.163382216657033e-06,
"loss": 1.1636,
"step": 1415
},
{
"epoch": 1.81,
"learning_rate": 7.1501254703566845e-06,
"loss": 1.2577,
"step": 1416
},
{
"epoch": 1.81,
"learning_rate": 7.136874172955385e-06,
"loss": 1.008,
"step": 1417
},
{
"epoch": 1.82,
"learning_rate": 7.123628349789332e-06,
"loss": 1.2189,
"step": 1418
},
{
"epoch": 1.82,
"learning_rate": 7.110388026184259e-06,
"loss": 1.1411,
"step": 1419
},
{
"epoch": 1.82,
"learning_rate": 7.097153227455379e-06,
"loss": 1.1516,
"step": 1420
},
{
"epoch": 1.82,
"learning_rate": 7.083923978907341e-06,
"loss": 1.2314,
"step": 1421
},
{
"epoch": 1.82,
"learning_rate": 7.070700305834189e-06,
"loss": 1.204,
"step": 1422
},
{
"epoch": 1.82,
"learning_rate": 7.0574822335193015e-06,
"loss": 1.2731,
"step": 1423
},
{
"epoch": 1.82,
"learning_rate": 7.044269787235348e-06,
"loss": 1.3234,
"step": 1424
},
{
"epoch": 1.82,
"learning_rate": 7.031062992244246e-06,
"loss": 1.1738,
"step": 1425
},
{
"epoch": 1.83,
"learning_rate": 7.017861873797102e-06,
"loss": 1.1253,
"step": 1426
},
{
"epoch": 1.83,
"learning_rate": 7.0046664571341715e-06,
"loss": 1.1937,
"step": 1427
},
{
"epoch": 1.83,
"learning_rate": 6.991476767484809e-06,
"loss": 1.1622,
"step": 1428
},
{
"epoch": 1.83,
"learning_rate": 6.9782928300674215e-06,
"loss": 1.1891,
"step": 1429
},
{
"epoch": 1.83,
"learning_rate": 6.965114670089409e-06,
"loss": 1.0855,
"step": 1430
},
{
"epoch": 1.83,
"learning_rate": 6.951942312747135e-06,
"loss": 1.0969,
"step": 1431
},
{
"epoch": 1.83,
"learning_rate": 6.938775783225864e-06,
"loss": 1.2792,
"step": 1432
},
{
"epoch": 1.83,
"learning_rate": 6.925615106699718e-06,
"loss": 1.1715,
"step": 1433
},
{
"epoch": 1.84,
"learning_rate": 6.912460308331631e-06,
"loss": 1.2868,
"step": 1434
},
{
"epoch": 1.84,
"learning_rate": 6.899311413273292e-06,
"loss": 1.2059,
"step": 1435
},
{
"epoch": 1.84,
"learning_rate": 6.886168446665107e-06,
"loss": 1.1905,
"step": 1436
},
{
"epoch": 1.84,
"learning_rate": 6.873031433636151e-06,
"loss": 1.2055,
"step": 1437
},
{
"epoch": 1.84,
"learning_rate": 6.859900399304104e-06,
"loss": 1.2846,
"step": 1438
},
{
"epoch": 1.84,
"learning_rate": 6.846775368775231e-06,
"loss": 1.159,
"step": 1439
},
{
"epoch": 1.84,
"learning_rate": 6.8336563671443015e-06,
"loss": 1.2263,
"step": 1440
},
{
"epoch": 1.84,
"learning_rate": 6.82054341949457e-06,
"loss": 1.2224,
"step": 1441
},
{
"epoch": 1.85,
"learning_rate": 6.807436550897713e-06,
"loss": 1.2751,
"step": 1442
},
{
"epoch": 1.85,
"learning_rate": 6.794335786413775e-06,
"loss": 1.2331,
"step": 1443
},
{
"epoch": 1.85,
"learning_rate": 6.781241151091146e-06,
"loss": 1.2263,
"step": 1444
},
{
"epoch": 1.85,
"learning_rate": 6.768152669966482e-06,
"loss": 1.1878,
"step": 1445
},
{
"epoch": 1.85,
"learning_rate": 6.755070368064682e-06,
"loss": 1.2407,
"step": 1446
},
{
"epoch": 1.85,
"learning_rate": 6.741994270398826e-06,
"loss": 1.2185,
"step": 1447
},
{
"epoch": 1.85,
"learning_rate": 6.72892440197013e-06,
"loss": 1.2299,
"step": 1448
},
{
"epoch": 1.85,
"learning_rate": 6.715860787767908e-06,
"loss": 1.2441,
"step": 1449
},
{
"epoch": 1.86,
"learning_rate": 6.702803452769507e-06,
"loss": 1.167,
"step": 1450
},
{
"epoch": 1.86,
"learning_rate": 6.68975242194027e-06,
"loss": 1.2689,
"step": 1451
},
{
"epoch": 1.86,
"learning_rate": 6.676707720233493e-06,
"loss": 1.2297,
"step": 1452
},
{
"epoch": 1.86,
"learning_rate": 6.663669372590359e-06,
"loss": 1.2276,
"step": 1453
},
{
"epoch": 1.86,
"learning_rate": 6.650637403939919e-06,
"loss": 1.0347,
"step": 1454
},
{
"epoch": 1.86,
"learning_rate": 6.637611839199013e-06,
"loss": 1.245,
"step": 1455
},
{
"epoch": 1.86,
"learning_rate": 6.624592703272237e-06,
"loss": 1.1784,
"step": 1456
},
{
"epoch": 1.86,
"learning_rate": 6.61158002105191e-06,
"loss": 1.2064,
"step": 1457
},
{
"epoch": 1.87,
"learning_rate": 6.598573817417995e-06,
"loss": 1.2198,
"step": 1458
},
{
"epoch": 1.87,
"learning_rate": 6.585574117238074e-06,
"loss": 1.1274,
"step": 1459
},
{
"epoch": 1.87,
"learning_rate": 6.572580945367299e-06,
"loss": 1.2477,
"step": 1460
},
{
"epoch": 1.87,
"learning_rate": 6.559594326648333e-06,
"loss": 1.2273,
"step": 1461
},
{
"epoch": 1.87,
"learning_rate": 6.546614285911317e-06,
"loss": 1.2612,
"step": 1462
},
{
"epoch": 1.87,
"learning_rate": 6.533640847973809e-06,
"loss": 1.2091,
"step": 1463
},
{
"epoch": 1.87,
"learning_rate": 6.52067403764074e-06,
"loss": 1.2417,
"step": 1464
},
{
"epoch": 1.88,
"learning_rate": 6.50771387970438e-06,
"loss": 1.2327,
"step": 1465
},
{
"epoch": 1.88,
"learning_rate": 6.494760398944271e-06,
"loss": 1.2424,
"step": 1466
},
{
"epoch": 1.88,
"learning_rate": 6.4818136201271864e-06,
"loss": 1.2398,
"step": 1467
},
{
"epoch": 1.88,
"learning_rate": 6.468873568007099e-06,
"loss": 1.2524,
"step": 1468
},
{
"epoch": 1.88,
"learning_rate": 6.4559402673251005e-06,
"loss": 1.132,
"step": 1469
},
{
"epoch": 1.88,
"learning_rate": 6.443013742809397e-06,
"loss": 1.1357,
"step": 1470
},
{
"epoch": 1.88,
"learning_rate": 6.430094019175217e-06,
"loss": 1.1602,
"step": 1471
},
{
"epoch": 1.88,
"learning_rate": 6.417181121124796e-06,
"loss": 1.248,
"step": 1472
},
{
"epoch": 1.89,
"learning_rate": 6.404275073347324e-06,
"loss": 1.1438,
"step": 1473
},
{
"epoch": 1.89,
"learning_rate": 6.391375900518879e-06,
"loss": 1.1996,
"step": 1474
},
{
"epoch": 1.89,
"learning_rate": 6.378483627302415e-06,
"loss": 1.1685,
"step": 1475
},
{
"epoch": 1.89,
"learning_rate": 6.365598278347675e-06,
"loss": 1.274,
"step": 1476
},
{
"epoch": 1.89,
"learning_rate": 6.352719878291167e-06,
"loss": 1.3252,
"step": 1477
},
{
"epoch": 1.89,
"learning_rate": 6.3398484517561255e-06,
"loss": 1.1939,
"step": 1478
},
{
"epoch": 1.89,
"learning_rate": 6.326984023352435e-06,
"loss": 1.2356,
"step": 1479
},
{
"epoch": 1.89,
"learning_rate": 6.314126617676606e-06,
"loss": 1.1645,
"step": 1480
},
{
"epoch": 1.9,
"learning_rate": 6.301276259311728e-06,
"loss": 1.2177,
"step": 1481
},
{
"epoch": 1.9,
"learning_rate": 6.288432972827406e-06,
"loss": 1.1975,
"step": 1482
},
{
"epoch": 1.9,
"learning_rate": 6.2755967827797346e-06,
"loss": 1.2273,
"step": 1483
},
{
"epoch": 1.9,
"learning_rate": 6.262767713711231e-06,
"loss": 1.1871,
"step": 1484
},
{
"epoch": 1.9,
"learning_rate": 6.249945790150798e-06,
"loss": 1.2117,
"step": 1485
},
{
"epoch": 1.9,
"learning_rate": 6.237131036613682e-06,
"loss": 1.1942,
"step": 1486
},
{
"epoch": 1.9,
"learning_rate": 6.224323477601417e-06,
"loss": 1.1107,
"step": 1487
},
{
"epoch": 1.9,
"learning_rate": 6.211523137601778e-06,
"loss": 1.1699,
"step": 1488
},
{
"epoch": 1.91,
"learning_rate": 6.198730041088747e-06,
"loss": 1.1788,
"step": 1489
},
{
"epoch": 1.91,
"learning_rate": 6.1859442125224425e-06,
"loss": 1.1894,
"step": 1490
},
{
"epoch": 1.91,
"learning_rate": 6.173165676349103e-06,
"loss": 1.188,
"step": 1491
},
{
"epoch": 1.91,
"learning_rate": 6.160394457001013e-06,
"loss": 1.1823,
"step": 1492
},
{
"epoch": 1.91,
"learning_rate": 6.147630578896467e-06,
"loss": 1.1767,
"step": 1493
},
{
"epoch": 1.91,
"learning_rate": 6.134874066439731e-06,
"loss": 1.151,
"step": 1494
},
{
"epoch": 1.91,
"learning_rate": 6.122124944020978e-06,
"loss": 1.1289,
"step": 1495
},
{
"epoch": 1.91,
"learning_rate": 6.109383236016266e-06,
"loss": 1.2195,
"step": 1496
},
{
"epoch": 1.92,
"learning_rate": 6.0966489667874604e-06,
"loss": 1.2644,
"step": 1497
},
{
"epoch": 1.92,
"learning_rate": 6.08392216068221e-06,
"loss": 1.1951,
"step": 1498
},
{
"epoch": 1.92,
"learning_rate": 6.071202842033903e-06,
"loss": 1.1681,
"step": 1499
},
{
"epoch": 1.92,
"learning_rate": 6.0584910351616e-06,
"loss": 1.0822,
"step": 1500
},
{
"epoch": 1.92,
"learning_rate": 6.045786764369999e-06,
"loss": 1.205,
"step": 1501
},
{
"epoch": 1.92,
"learning_rate": 6.033090053949401e-06,
"loss": 1.1279,
"step": 1502
},
{
"epoch": 1.92,
"learning_rate": 6.020400928175637e-06,
"loss": 1.2276,
"step": 1503
},
{
"epoch": 1.93,
"learning_rate": 6.007719411310053e-06,
"loss": 1.2384,
"step": 1504
},
{
"epoch": 1.93,
"learning_rate": 5.995045527599432e-06,
"loss": 1.1605,
"step": 1505
},
{
"epoch": 1.93,
"learning_rate": 5.982379301275965e-06,
"loss": 1.1511,
"step": 1506
},
{
"epoch": 1.93,
"learning_rate": 5.969720756557211e-06,
"loss": 1.1394,
"step": 1507
},
{
"epoch": 1.93,
"learning_rate": 5.9570699176460356e-06,
"loss": 1.2302,
"step": 1508
},
{
"epoch": 1.93,
"learning_rate": 5.944426808730567e-06,
"loss": 1.2512,
"step": 1509
},
{
"epoch": 1.93,
"learning_rate": 5.931791453984165e-06,
"loss": 1.309,
"step": 1510
},
{
"epoch": 1.93,
"learning_rate": 5.919163877565351e-06,
"loss": 1.1683,
"step": 1511
},
{
"epoch": 1.94,
"learning_rate": 5.906544103617787e-06,
"loss": 1.1527,
"step": 1512
},
{
"epoch": 1.94,
"learning_rate": 5.8939321562702075e-06,
"loss": 1.1849,
"step": 1513
},
{
"epoch": 1.94,
"learning_rate": 5.881328059636382e-06,
"loss": 1.261,
"step": 1514
},
{
"epoch": 1.94,
"learning_rate": 5.868731837815082e-06,
"loss": 1.1192,
"step": 1515
},
{
"epoch": 1.94,
"learning_rate": 5.856143514890003e-06,
"loss": 1.2567,
"step": 1516
},
{
"epoch": 1.94,
"learning_rate": 5.843563114929758e-06,
"loss": 1.1921,
"step": 1517
},
{
"epoch": 1.94,
"learning_rate": 5.830990661987797e-06,
"loss": 1.3111,
"step": 1518
},
{
"epoch": 1.94,
"learning_rate": 5.818426180102382e-06,
"loss": 1.2476,
"step": 1519
},
{
"epoch": 1.95,
"learning_rate": 5.805869693296534e-06,
"loss": 1.2868,
"step": 1520
},
{
"epoch": 1.95,
"learning_rate": 5.79332122557799e-06,
"loss": 1.2284,
"step": 1521
},
{
"epoch": 1.95,
"learning_rate": 5.78078080093914e-06,
"loss": 1.2468,
"step": 1522
},
{
"epoch": 1.95,
"learning_rate": 5.768248443357023e-06,
"loss": 1.2817,
"step": 1523
},
{
"epoch": 1.95,
"learning_rate": 5.75572417679322e-06,
"loss": 1.2287,
"step": 1524
},
{
"epoch": 1.95,
"learning_rate": 5.74320802519388e-06,
"loss": 1.2079,
"step": 1525
},
{
"epoch": 1.95,
"learning_rate": 5.730700012489605e-06,
"loss": 1.1556,
"step": 1526
},
{
"epoch": 1.95,
"learning_rate": 5.718200162595449e-06,
"loss": 1.1299,
"step": 1527
},
{
"epoch": 1.96,
"learning_rate": 5.705708499410856e-06,
"loss": 1.1807,
"step": 1528
},
{
"epoch": 1.96,
"learning_rate": 5.693225046819626e-06,
"loss": 1.2614,
"step": 1529
},
{
"epoch": 1.96,
"learning_rate": 5.680749828689838e-06,
"loss": 1.212,
"step": 1530
},
{
"epoch": 1.96,
"learning_rate": 5.66828286887386e-06,
"loss": 1.1789,
"step": 1531
},
{
"epoch": 1.96,
"learning_rate": 5.655824191208235e-06,
"loss": 1.2098,
"step": 1532
},
{
"epoch": 1.96,
"learning_rate": 5.6433738195137035e-06,
"loss": 1.1266,
"step": 1533
},
{
"epoch": 1.96,
"learning_rate": 5.630931777595099e-06,
"loss": 1.2683,
"step": 1534
},
{
"epoch": 1.96,
"learning_rate": 5.61849808924134e-06,
"loss": 1.1881,
"step": 1535
},
{
"epoch": 1.97,
"learning_rate": 5.606072778225376e-06,
"loss": 1.2769,
"step": 1536
},
{
"epoch": 1.97,
"learning_rate": 5.593655868304137e-06,
"loss": 1.1944,
"step": 1537
},
{
"epoch": 1.97,
"learning_rate": 5.581247383218477e-06,
"loss": 1.1937,
"step": 1538
},
{
"epoch": 1.97,
"learning_rate": 5.568847346693172e-06,
"loss": 1.2951,
"step": 1539
},
{
"epoch": 1.97,
"learning_rate": 5.556455782436808e-06,
"loss": 1.1568,
"step": 1540
},
{
"epoch": 1.97,
"learning_rate": 5.544072714141806e-06,
"loss": 1.1523,
"step": 1541
},
{
"epoch": 1.97,
"learning_rate": 5.531698165484318e-06,
"loss": 1.1155,
"step": 1542
},
{
"epoch": 1.98,
"learning_rate": 5.519332160124215e-06,
"loss": 1.2658,
"step": 1543
},
{
"epoch": 1.98,
"learning_rate": 5.506974721705041e-06,
"loss": 1.1159,
"step": 1544
},
{
"epoch": 1.98,
"learning_rate": 5.494625873853948e-06,
"loss": 1.1216,
"step": 1545
},
{
"epoch": 1.98,
"learning_rate": 5.48228564018167e-06,
"loss": 1.2539,
"step": 1546
},
{
"epoch": 1.98,
"learning_rate": 5.469954044282475e-06,
"loss": 1.1125,
"step": 1547
},
{
"epoch": 1.98,
"learning_rate": 5.457631109734098e-06,
"loss": 1.2033,
"step": 1548
},
{
"epoch": 1.98,
"learning_rate": 5.44531686009774e-06,
"loss": 1.1368,
"step": 1549
},
{
"epoch": 1.98,
"learning_rate": 5.433011318917971e-06,
"loss": 1.1438,
"step": 1550
},
{
"epoch": 1.99,
"learning_rate": 5.420714509722729e-06,
"loss": 1.1716,
"step": 1551
},
{
"epoch": 1.99,
"learning_rate": 5.408426456023246e-06,
"loss": 1.1518,
"step": 1552
},
{
"epoch": 1.99,
"learning_rate": 5.396147181314018e-06,
"loss": 1.1704,
"step": 1553
},
{
"epoch": 1.99,
"learning_rate": 5.383876709072757e-06,
"loss": 1.2655,
"step": 1554
},
{
"epoch": 1.99,
"learning_rate": 5.371615062760346e-06,
"loss": 1.1582,
"step": 1555
},
{
"epoch": 1.99,
"learning_rate": 5.359362265820778e-06,
"loss": 1.1072,
"step": 1556
},
{
"epoch": 1.99,
"learning_rate": 5.347118341681155e-06,
"loss": 1.2682,
"step": 1557
},
{
"epoch": 1.99,
"learning_rate": 5.3348833137515845e-06,
"loss": 1.2154,
"step": 1558
},
{
"epoch": 2.0,
"learning_rate": 5.322657205425184e-06,
"loss": 1.17,
"step": 1559
},
{
"epoch": 2.0,
"learning_rate": 5.310440040078008e-06,
"loss": 1.1694,
"step": 1560
},
{
"epoch": 2.0,
"learning_rate": 5.298231841069017e-06,
"loss": 1.2991,
"step": 1561
},
{
"epoch": 2.0,
"learning_rate": 5.286032631740023e-06,
"loss": 1.2575,
"step": 1562
},
{
"epoch": 2.0,
"learning_rate": 5.273842435415661e-06,
"loss": 1.0553,
"step": 1563
},
{
"epoch": 2.0,
"learning_rate": 5.2616612754033115e-06,
"loss": 0.9876,
"step": 1564
},
{
"epoch": 2.0,
"learning_rate": 5.249489174993106e-06,
"loss": 1.0595,
"step": 1565
},
{
"epoch": 2.0,
"learning_rate": 5.237326157457825e-06,
"loss": 0.8973,
"step": 1566
},
{
"epoch": 2.01,
"learning_rate": 5.225172246052914e-06,
"loss": 0.9984,
"step": 1567
},
{
"epoch": 2.01,
"learning_rate": 5.2130274640163795e-06,
"loss": 0.9015,
"step": 1568
},
{
"epoch": 2.01,
"learning_rate": 5.200891834568786e-06,
"loss": 0.9749,
"step": 1569
},
{
"epoch": 2.01,
"learning_rate": 5.188765380913201e-06,
"loss": 1.0185,
"step": 1570
},
{
"epoch": 2.01,
"learning_rate": 5.176648126235144e-06,
"loss": 0.8835,
"step": 1571
},
{
"epoch": 2.01,
"learning_rate": 5.164540093702537e-06,
"loss": 1.0687,
"step": 1572
},
{
"epoch": 2.01,
"learning_rate": 5.152441306465694e-06,
"loss": 0.9187,
"step": 1573
},
{
"epoch": 2.01,
"learning_rate": 5.140351787657223e-06,
"loss": 1.0196,
"step": 1574
},
{
"epoch": 2.02,
"learning_rate": 5.128271560392037e-06,
"loss": 0.867,
"step": 1575
},
{
"epoch": 2.02,
"learning_rate": 5.1162006477672625e-06,
"loss": 1.0205,
"step": 1576
},
{
"epoch": 2.02,
"learning_rate": 5.104139072862229e-06,
"loss": 0.9017,
"step": 1577
},
{
"epoch": 2.02,
"learning_rate": 5.09208685873841e-06,
"loss": 0.9108,
"step": 1578
},
{
"epoch": 2.02,
"learning_rate": 5.080044028439384e-06,
"loss": 0.9202,
"step": 1579
},
{
"epoch": 2.02,
"learning_rate": 5.068010604990774e-06,
"loss": 1.0001,
"step": 1580
},
{
"epoch": 2.02,
"learning_rate": 5.055986611400241e-06,
"loss": 1.0204,
"step": 1581
},
{
"epoch": 2.02,
"learning_rate": 5.04397207065739e-06,
"loss": 0.9883,
"step": 1582
},
{
"epoch": 2.03,
"learning_rate": 5.03196700573378e-06,
"loss": 0.9101,
"step": 1583
},
{
"epoch": 2.03,
"learning_rate": 5.019971439582827e-06,
"loss": 0.9032,
"step": 1584
},
{
"epoch": 2.03,
"learning_rate": 5.007985395139798e-06,
"loss": 0.9103,
"step": 1585
},
{
"epoch": 2.03,
"learning_rate": 4.996008895321758e-06,
"loss": 0.9687,
"step": 1586
},
{
"epoch": 2.03,
"learning_rate": 4.984041963027512e-06,
"loss": 0.8934,
"step": 1587
},
{
"epoch": 2.03,
"learning_rate": 4.972084621137584e-06,
"loss": 1.0048,
"step": 1588
},
{
"epoch": 2.03,
"learning_rate": 4.9601368925141555e-06,
"loss": 0.9536,
"step": 1589
},
{
"epoch": 2.04,
"learning_rate": 4.948198800001018e-06,
"loss": 0.9386,
"step": 1590
},
{
"epoch": 2.04,
"learning_rate": 4.936270366423563e-06,
"loss": 0.9867,
"step": 1591
},
{
"epoch": 2.04,
"learning_rate": 4.92435161458869e-06,
"loss": 1.0543,
"step": 1592
},
{
"epoch": 2.04,
"learning_rate": 4.9124425672847984e-06,
"loss": 0.8894,
"step": 1593
},
{
"epoch": 2.04,
"learning_rate": 4.900543247281735e-06,
"loss": 0.9253,
"step": 1594
},
{
"epoch": 2.04,
"learning_rate": 4.888653677330742e-06,
"loss": 0.9791,
"step": 1595
},
{
"epoch": 2.04,
"learning_rate": 4.8767738801644215e-06,
"loss": 0.9468,
"step": 1596
},
{
"epoch": 2.04,
"learning_rate": 4.864903878496698e-06,
"loss": 0.9756,
"step": 1597
},
{
"epoch": 2.05,
"learning_rate": 4.8530436950227485e-06,
"loss": 0.9662,
"step": 1598
},
{
"epoch": 2.05,
"learning_rate": 4.841193352419003e-06,
"loss": 0.8578,
"step": 1599
},
{
"epoch": 2.05,
"learning_rate": 4.829352873343054e-06,
"loss": 0.9664,
"step": 1600
},
{
"epoch": 2.05,
"learning_rate": 4.817522280433644e-06,
"loss": 0.8967,
"step": 1601
},
{
"epoch": 2.05,
"learning_rate": 4.805701596310617e-06,
"loss": 0.8151,
"step": 1602
},
{
"epoch": 2.05,
"learning_rate": 4.793890843574865e-06,
"loss": 0.9862,
"step": 1603
},
{
"epoch": 2.05,
"learning_rate": 4.782090044808297e-06,
"loss": 0.8758,
"step": 1604
},
{
"epoch": 2.05,
"learning_rate": 4.770299222573788e-06,
"loss": 0.9145,
"step": 1605
},
{
"epoch": 2.06,
"learning_rate": 4.758518399415128e-06,
"loss": 0.9274,
"step": 1606
},
{
"epoch": 2.06,
"learning_rate": 4.746747597857014e-06,
"loss": 0.9774,
"step": 1607
},
{
"epoch": 2.06,
"learning_rate": 4.734986840404955e-06,
"loss": 0.8476,
"step": 1608
},
{
"epoch": 2.06,
"learning_rate": 4.72323614954527e-06,
"loss": 0.8496,
"step": 1609
},
{
"epoch": 2.06,
"learning_rate": 4.71149554774503e-06,
"loss": 1.0089,
"step": 1610
},
{
"epoch": 2.06,
"learning_rate": 4.699765057452012e-06,
"loss": 0.945,
"step": 1611
},
{
"epoch": 2.06,
"learning_rate": 4.688044701094662e-06,
"loss": 0.9744,
"step": 1612
},
{
"epoch": 2.06,
"learning_rate": 4.676334501082053e-06,
"loss": 0.9844,
"step": 1613
},
{
"epoch": 2.07,
"learning_rate": 4.664634479803834e-06,
"loss": 0.9222,
"step": 1614
},
{
"epoch": 2.07,
"learning_rate": 4.6529446596301996e-06,
"loss": 0.9032,
"step": 1615
},
{
"epoch": 2.07,
"learning_rate": 4.641265062911825e-06,
"loss": 0.8921,
"step": 1616
},
{
"epoch": 2.07,
"learning_rate": 4.629595711979863e-06,
"loss": 0.9486,
"step": 1617
},
{
"epoch": 2.07,
"learning_rate": 4.617936629145852e-06,
"loss": 0.9193,
"step": 1618
},
{
"epoch": 2.07,
"learning_rate": 4.606287836701712e-06,
"loss": 0.8869,
"step": 1619
},
{
"epoch": 2.07,
"learning_rate": 4.5946493569196846e-06,
"loss": 0.8432,
"step": 1620
},
{
"epoch": 2.07,
"learning_rate": 4.583021212052294e-06,
"loss": 1.0055,
"step": 1621
},
{
"epoch": 2.08,
"learning_rate": 4.571403424332304e-06,
"loss": 0.8568,
"step": 1622
},
{
"epoch": 2.08,
"learning_rate": 4.559796015972677e-06,
"loss": 0.9654,
"step": 1623
},
{
"epoch": 2.08,
"learning_rate": 4.5481990091665276e-06,
"loss": 0.9807,
"step": 1624
},
{
"epoch": 2.08,
"learning_rate": 4.536612426087088e-06,
"loss": 0.7968,
"step": 1625
},
{
"epoch": 2.08,
"learning_rate": 4.52503628888765e-06,
"loss": 0.9867,
"step": 1626
},
{
"epoch": 2.08,
"learning_rate": 4.5134706197015435e-06,
"loss": 0.8893,
"step": 1627
},
{
"epoch": 2.08,
"learning_rate": 4.50191544064208e-06,
"loss": 0.9086,
"step": 1628
},
{
"epoch": 2.09,
"learning_rate": 4.490370773802515e-06,
"loss": 1.0271,
"step": 1629
},
{
"epoch": 2.09,
"learning_rate": 4.4788366412560035e-06,
"loss": 0.8963,
"step": 1630
},
{
"epoch": 2.09,
"learning_rate": 4.467313065055561e-06,
"loss": 0.8981,
"step": 1631
},
{
"epoch": 2.09,
"learning_rate": 4.455800067234017e-06,
"loss": 0.9212,
"step": 1632
},
{
"epoch": 2.09,
"learning_rate": 4.444297669803981e-06,
"loss": 1.0019,
"step": 1633
},
{
"epoch": 2.09,
"learning_rate": 4.4328058947577825e-06,
"loss": 0.9532,
"step": 1634
},
{
"epoch": 2.09,
"learning_rate": 4.421324764067454e-06,
"loss": 0.8828,
"step": 1635
},
{
"epoch": 2.09,
"learning_rate": 4.4098542996846705e-06,
"loss": 0.8679,
"step": 1636
},
{
"epoch": 2.1,
"learning_rate": 4.398394523540714e-06,
"loss": 0.8877,
"step": 1637
},
{
"epoch": 2.1,
"learning_rate": 4.386945457546433e-06,
"loss": 0.998,
"step": 1638
},
{
"epoch": 2.1,
"learning_rate": 4.375507123592194e-06,
"loss": 0.9224,
"step": 1639
},
{
"epoch": 2.1,
"learning_rate": 4.364079543547848e-06,
"loss": 0.9539,
"step": 1640
},
{
"epoch": 2.1,
"learning_rate": 4.352662739262682e-06,
"loss": 0.9783,
"step": 1641
},
{
"epoch": 2.1,
"learning_rate": 4.341256732565386e-06,
"loss": 0.9187,
"step": 1642
},
{
"epoch": 2.1,
"learning_rate": 4.329861545263992e-06,
"loss": 0.9102,
"step": 1643
},
{
"epoch": 2.1,
"learning_rate": 4.3184771991458584e-06,
"loss": 0.9146,
"step": 1644
},
{
"epoch": 2.11,
"learning_rate": 4.307103715977612e-06,
"loss": 0.8811,
"step": 1645
},
{
"epoch": 2.11,
"learning_rate": 4.295741117505108e-06,
"loss": 1.0502,
"step": 1646
},
{
"epoch": 2.11,
"learning_rate": 4.2843894254533906e-06,
"loss": 0.9476,
"step": 1647
},
{
"epoch": 2.11,
"learning_rate": 4.273048661526653e-06,
"loss": 0.8427,
"step": 1648
},
{
"epoch": 2.11,
"learning_rate": 4.261718847408192e-06,
"loss": 0.8971,
"step": 1649
},
{
"epoch": 2.11,
"learning_rate": 4.2504000047603734e-06,
"loss": 0.9371,
"step": 1650
},
{
"epoch": 2.11,
"learning_rate": 4.239092155224572e-06,
"loss": 0.8408,
"step": 1651
},
{
"epoch": 2.11,
"learning_rate": 4.227795320421167e-06,
"loss": 0.9018,
"step": 1652
},
{
"epoch": 2.12,
"learning_rate": 4.216509521949455e-06,
"loss": 0.8654,
"step": 1653
},
{
"epoch": 2.12,
"learning_rate": 4.205234781387643e-06,
"loss": 0.8716,
"step": 1654
},
{
"epoch": 2.12,
"learning_rate": 4.193971120292793e-06,
"loss": 0.8943,
"step": 1655
},
{
"epoch": 2.12,
"learning_rate": 4.182718560200787e-06,
"loss": 0.9488,
"step": 1656
},
{
"epoch": 2.12,
"learning_rate": 4.171477122626276e-06,
"loss": 0.8276,
"step": 1657
},
{
"epoch": 2.12,
"learning_rate": 4.160246829062648e-06,
"loss": 0.957,
"step": 1658
},
{
"epoch": 2.12,
"learning_rate": 4.1490277009819845e-06,
"loss": 0.8498,
"step": 1659
},
{
"epoch": 2.12,
"learning_rate": 4.137819759835023e-06,
"loss": 0.9623,
"step": 1660
},
{
"epoch": 2.13,
"learning_rate": 4.126623027051092e-06,
"loss": 0.8857,
"step": 1661
},
{
"epoch": 2.13,
"learning_rate": 4.115437524038124e-06,
"loss": 0.9144,
"step": 1662
},
{
"epoch": 2.13,
"learning_rate": 4.104263272182546e-06,
"loss": 0.9597,
"step": 1663
},
{
"epoch": 2.13,
"learning_rate": 4.093100292849295e-06,
"loss": 0.9234,
"step": 1664
},
{
"epoch": 2.13,
"learning_rate": 4.081948607381746e-06,
"loss": 0.9882,
"step": 1665
},
{
"epoch": 2.13,
"learning_rate": 4.070808237101686e-06,
"loss": 0.8833,
"step": 1666
},
{
"epoch": 2.13,
"learning_rate": 4.0596792033092605e-06,
"loss": 0.8744,
"step": 1667
},
{
"epoch": 2.14,
"learning_rate": 4.048561527282948e-06,
"loss": 0.9768,
"step": 1668
},
{
"epoch": 2.14,
"learning_rate": 4.037455230279499e-06,
"loss": 0.9219,
"step": 1669
},
{
"epoch": 2.14,
"learning_rate": 4.026360333533927e-06,
"loss": 1.0341,
"step": 1670
},
{
"epoch": 2.14,
"learning_rate": 4.015276858259427e-06,
"loss": 0.9072,
"step": 1671
},
{
"epoch": 2.14,
"learning_rate": 4.004204825647371e-06,
"loss": 0.9757,
"step": 1672
},
{
"epoch": 2.14,
"learning_rate": 3.993144256867246e-06,
"loss": 0.8854,
"step": 1673
},
{
"epoch": 2.14,
"learning_rate": 3.982095173066624e-06,
"loss": 0.7917,
"step": 1674
},
{
"epoch": 2.14,
"learning_rate": 3.971057595371116e-06,
"loss": 0.8593,
"step": 1675
},
{
"epoch": 2.15,
"learning_rate": 3.960031544884338e-06,
"loss": 0.9831,
"step": 1676
},
{
"epoch": 2.15,
"learning_rate": 3.949017042687851e-06,
"loss": 0.7972,
"step": 1677
},
{
"epoch": 2.15,
"learning_rate": 3.938014109841163e-06,
"loss": 0.9441,
"step": 1678
},
{
"epoch": 2.15,
"learning_rate": 3.927022767381634e-06,
"loss": 0.8867,
"step": 1679
},
{
"epoch": 2.15,
"learning_rate": 3.91604303632448e-06,
"loss": 0.9397,
"step": 1680
},
{
"epoch": 2.15,
"learning_rate": 3.9050749376627085e-06,
"loss": 0.9325,
"step": 1681
},
{
"epoch": 2.15,
"learning_rate": 3.8941184923670925e-06,
"loss": 1.0011,
"step": 1682
},
{
"epoch": 2.15,
"learning_rate": 3.88317372138612e-06,
"loss": 0.938,
"step": 1683
},
{
"epoch": 2.16,
"learning_rate": 3.872240645645962e-06,
"loss": 0.9411,
"step": 1684
},
{
"epoch": 2.16,
"learning_rate": 3.861319286050413e-06,
"loss": 1.0486,
"step": 1685
},
{
"epoch": 2.16,
"learning_rate": 3.850409663480894e-06,
"loss": 0.9033,
"step": 1686
},
{
"epoch": 2.16,
"learning_rate": 3.839511798796357e-06,
"loss": 1.0295,
"step": 1687
},
{
"epoch": 2.16,
"learning_rate": 3.828625712833297e-06,
"loss": 0.9372,
"step": 1688
},
{
"epoch": 2.16,
"learning_rate": 3.817751426405669e-06,
"loss": 0.819,
"step": 1689
},
{
"epoch": 2.16,
"learning_rate": 3.8068889603048773e-06,
"loss": 0.939,
"step": 1690
},
{
"epoch": 2.16,
"learning_rate": 3.7960383352997264e-06,
"loss": 0.9189,
"step": 1691
},
{
"epoch": 2.17,
"learning_rate": 3.785199572136381e-06,
"loss": 0.9362,
"step": 1692
},
{
"epoch": 2.17,
"learning_rate": 3.774372691538314e-06,
"loss": 1.021,
"step": 1693
},
{
"epoch": 2.17,
"learning_rate": 3.763557714206303e-06,
"loss": 0.963,
"step": 1694
},
{
"epoch": 2.17,
"learning_rate": 3.7527546608183386e-06,
"loss": 0.9682,
"step": 1695
},
{
"epoch": 2.17,
"learning_rate": 3.7419635520296426e-06,
"loss": 0.8836,
"step": 1696
},
{
"epoch": 2.17,
"learning_rate": 3.7311844084725725e-06,
"loss": 0.9708,
"step": 1697
},
{
"epoch": 2.17,
"learning_rate": 3.720417250756623e-06,
"loss": 0.9227,
"step": 1698
},
{
"epoch": 2.17,
"learning_rate": 3.7096620994683695e-06,
"loss": 0.8323,
"step": 1699
},
{
"epoch": 2.18,
"learning_rate": 3.698918975171435e-06,
"loss": 0.96,
"step": 1700
},
{
"epoch": 2.18,
"learning_rate": 3.6881878984064323e-06,
"loss": 0.9208,
"step": 1701
},
{
"epoch": 2.18,
"learning_rate": 3.6774688896909625e-06,
"loss": 0.9071,
"step": 1702
},
{
"epoch": 2.18,
"learning_rate": 3.6667619695195287e-06,
"loss": 1.03,
"step": 1703
},
{
"epoch": 2.18,
"learning_rate": 3.6560671583635467e-06,
"loss": 0.9356,
"step": 1704
},
{
"epoch": 2.18,
"learning_rate": 3.6453844766712553e-06,
"loss": 1.012,
"step": 1705
},
{
"epoch": 2.18,
"learning_rate": 3.634713944867716e-06,
"loss": 0.8723,
"step": 1706
},
{
"epoch": 2.18,
"learning_rate": 3.6240555833547587e-06,
"loss": 0.9082,
"step": 1707
},
{
"epoch": 2.19,
"learning_rate": 3.6134094125109407e-06,
"loss": 0.9916,
"step": 1708
},
{
"epoch": 2.19,
"learning_rate": 3.6027754526915126e-06,
"loss": 0.9049,
"step": 1709
},
{
"epoch": 2.19,
"learning_rate": 3.592153724228382e-06,
"loss": 1.0006,
"step": 1710
},
{
"epoch": 2.19,
"learning_rate": 3.5815442474300564e-06,
"loss": 0.9074,
"step": 1711
},
{
"epoch": 2.19,
"learning_rate": 3.5709470425816407e-06,
"loss": 0.9461,
"step": 1712
},
{
"epoch": 2.19,
"learning_rate": 3.5603621299447534e-06,
"loss": 0.8634,
"step": 1713
},
{
"epoch": 2.19,
"learning_rate": 3.5497895297575248e-06,
"loss": 0.8921,
"step": 1714
},
{
"epoch": 2.2,
"learning_rate": 3.539229262234539e-06,
"loss": 0.9433,
"step": 1715
},
{
"epoch": 2.2,
"learning_rate": 3.5286813475668027e-06,
"loss": 0.8936,
"step": 1716
},
{
"epoch": 2.2,
"learning_rate": 3.518145805921701e-06,
"loss": 0.7956,
"step": 1717
},
{
"epoch": 2.2,
"learning_rate": 3.5076226574429694e-06,
"loss": 0.9654,
"step": 1718
},
{
"epoch": 2.2,
"learning_rate": 3.49711192225063e-06,
"loss": 0.7656,
"step": 1719
},
{
"epoch": 2.2,
"learning_rate": 3.4866136204409985e-06,
"loss": 0.7926,
"step": 1720
},
{
"epoch": 2.2,
"learning_rate": 3.4761277720865918e-06,
"loss": 0.9608,
"step": 1721
},
{
"epoch": 2.2,
"learning_rate": 3.4656543972361322e-06,
"loss": 0.9616,
"step": 1722
},
{
"epoch": 2.21,
"learning_rate": 3.4551935159144854e-06,
"loss": 0.9001,
"step": 1723
},
{
"epoch": 2.21,
"learning_rate": 3.4447451481226357e-06,
"loss": 0.9394,
"step": 1724
},
{
"epoch": 2.21,
"learning_rate": 3.434309313837636e-06,
"loss": 0.812,
"step": 1725
},
{
"epoch": 2.21,
"learning_rate": 3.4238860330125822e-06,
"loss": 0.9025,
"step": 1726
},
{
"epoch": 2.21,
"learning_rate": 3.413475325576554e-06,
"loss": 0.9188,
"step": 1727
},
{
"epoch": 2.21,
"learning_rate": 3.403077211434613e-06,
"loss": 0.8714,
"step": 1728
},
{
"epoch": 2.21,
"learning_rate": 3.3926917104677205e-06,
"loss": 0.9143,
"step": 1729
},
{
"epoch": 2.21,
"learning_rate": 3.3823188425327424e-06,
"loss": 0.7811,
"step": 1730
},
{
"epoch": 2.22,
"learning_rate": 3.3719586274623707e-06,
"loss": 0.9018,
"step": 1731
},
{
"epoch": 2.22,
"learning_rate": 3.3616110850651174e-06,
"loss": 0.8254,
"step": 1732
},
{
"epoch": 2.22,
"learning_rate": 3.3512762351252638e-06,
"loss": 0.9799,
"step": 1733
},
{
"epoch": 2.22,
"learning_rate": 3.340954097402823e-06,
"loss": 0.8388,
"step": 1734
},
{
"epoch": 2.22,
"learning_rate": 3.330644691633492e-06,
"loss": 0.9305,
"step": 1735
},
{
"epoch": 2.22,
"learning_rate": 3.320348037528648e-06,
"loss": 0.9721,
"step": 1736
},
{
"epoch": 2.22,
"learning_rate": 3.3100641547752576e-06,
"loss": 0.9311,
"step": 1737
},
{
"epoch": 2.22,
"learning_rate": 3.2997930630359e-06,
"loss": 0.9306,
"step": 1738
},
{
"epoch": 2.23,
"learning_rate": 3.28953478194867e-06,
"loss": 0.959,
"step": 1739
},
{
"epoch": 2.23,
"learning_rate": 3.2792893311271867e-06,
"loss": 0.8128,
"step": 1740
},
{
"epoch": 2.23,
"learning_rate": 3.2690567301605324e-06,
"loss": 0.8764,
"step": 1741
},
{
"epoch": 2.23,
"learning_rate": 3.258836998613224e-06,
"loss": 0.9671,
"step": 1742
},
{
"epoch": 2.23,
"learning_rate": 3.248630156025159e-06,
"loss": 0.9977,
"step": 1743
},
{
"epoch": 2.23,
"learning_rate": 3.238436221911614e-06,
"loss": 0.8843,
"step": 1744
},
{
"epoch": 2.23,
"learning_rate": 3.228255215763162e-06,
"loss": 0.9281,
"step": 1745
},
{
"epoch": 2.23,
"learning_rate": 3.2180871570456797e-06,
"loss": 0.925,
"step": 1746
},
{
"epoch": 2.24,
"learning_rate": 3.2079320652002686e-06,
"loss": 1.0351,
"step": 1747
},
{
"epoch": 2.24,
"learning_rate": 3.1977899596432506e-06,
"loss": 0.9145,
"step": 1748
},
{
"epoch": 2.24,
"learning_rate": 3.187660859766113e-06,
"loss": 0.9336,
"step": 1749
},
{
"epoch": 2.24,
"learning_rate": 3.177544784935479e-06,
"loss": 0.9329,
"step": 1750
},
{
"epoch": 2.24,
"learning_rate": 3.167441754493066e-06,
"loss": 0.9723,
"step": 1751
},
{
"epoch": 2.24,
"learning_rate": 3.1573517877556548e-06,
"loss": 0.8157,
"step": 1752
},
{
"epoch": 2.24,
"learning_rate": 3.1472749040150365e-06,
"loss": 0.9577,
"step": 1753
},
{
"epoch": 2.25,
"learning_rate": 3.1372111225380096e-06,
"loss": 0.9359,
"step": 1754
},
{
"epoch": 2.25,
"learning_rate": 3.127160462566301e-06,
"loss": 1.0164,
"step": 1755
},
{
"epoch": 2.25,
"learning_rate": 3.1171229433165575e-06,
"loss": 0.937,
"step": 1756
},
{
"epoch": 2.25,
"learning_rate": 3.107098583980301e-06,
"loss": 0.9567,
"step": 1757
},
{
"epoch": 2.25,
"learning_rate": 3.0970874037238952e-06,
"loss": 0.9211,
"step": 1758
},
{
"epoch": 2.25,
"learning_rate": 3.0870894216884994e-06,
"loss": 0.9142,
"step": 1759
},
{
"epoch": 2.25,
"learning_rate": 3.077104656990041e-06,
"loss": 0.9803,
"step": 1760
},
{
"epoch": 2.25,
"learning_rate": 3.0671331287191773e-06,
"loss": 0.9646,
"step": 1761
},
{
"epoch": 2.26,
"learning_rate": 3.0571748559412595e-06,
"loss": 0.9349,
"step": 1762
},
{
"epoch": 2.26,
"learning_rate": 3.0472298576962857e-06,
"loss": 0.9774,
"step": 1763
},
{
"epoch": 2.26,
"learning_rate": 3.037298152998882e-06,
"loss": 0.9041,
"step": 1764
},
{
"epoch": 2.26,
"learning_rate": 3.027379760838256e-06,
"loss": 0.8421,
"step": 1765
},
{
"epoch": 2.26,
"learning_rate": 3.017474700178161e-06,
"loss": 0.8946,
"step": 1766
},
{
"epoch": 2.26,
"learning_rate": 3.00758298995686e-06,
"loss": 0.8961,
"step": 1767
},
{
"epoch": 2.26,
"learning_rate": 2.997704649087091e-06,
"loss": 0.7834,
"step": 1768
},
{
"epoch": 2.26,
"learning_rate": 2.9878396964560307e-06,
"loss": 0.8679,
"step": 1769
},
{
"epoch": 2.27,
"learning_rate": 2.9779881509252574e-06,
"loss": 0.9619,
"step": 1770
},
{
"epoch": 2.27,
"learning_rate": 2.9681500313307176e-06,
"loss": 0.9902,
"step": 1771
},
{
"epoch": 2.27,
"learning_rate": 2.95832535648268e-06,
"loss": 0.9478,
"step": 1772
},
{
"epoch": 2.27,
"learning_rate": 2.948514145165714e-06,
"loss": 0.9337,
"step": 1773
},
{
"epoch": 2.27,
"learning_rate": 2.938716416138647e-06,
"loss": 0.9225,
"step": 1774
},
{
"epoch": 2.27,
"learning_rate": 2.9289321881345257e-06,
"loss": 1.0805,
"step": 1775
},
{
"epoch": 2.27,
"learning_rate": 2.919161479860585e-06,
"loss": 0.8907,
"step": 1776
},
{
"epoch": 2.27,
"learning_rate": 2.9094043099982104e-06,
"loss": 0.9301,
"step": 1777
},
{
"epoch": 2.28,
"learning_rate": 2.899660697202901e-06,
"loss": 0.9534,
"step": 1778
},
{
"epoch": 2.28,
"learning_rate": 2.8899306601042353e-06,
"loss": 0.9699,
"step": 1779
},
{
"epoch": 2.28,
"learning_rate": 2.88021421730584e-06,
"loss": 0.9823,
"step": 1780
},
{
"epoch": 2.28,
"learning_rate": 2.8705113873853384e-06,
"loss": 0.863,
"step": 1781
},
{
"epoch": 2.28,
"learning_rate": 2.860822188894338e-06,
"loss": 0.9131,
"step": 1782
},
{
"epoch": 2.28,
"learning_rate": 2.8511466403583766e-06,
"loss": 0.8497,
"step": 1783
},
{
"epoch": 2.28,
"learning_rate": 2.8414847602768968e-06,
"loss": 0.9432,
"step": 1784
},
{
"epoch": 2.28,
"learning_rate": 2.831836567123207e-06,
"loss": 0.8666,
"step": 1785
},
{
"epoch": 2.29,
"learning_rate": 2.822202079344446e-06,
"loss": 0.9243,
"step": 1786
},
{
"epoch": 2.29,
"learning_rate": 2.8125813153615455e-06,
"loss": 0.9677,
"step": 1787
},
{
"epoch": 2.29,
"learning_rate": 2.802974293569204e-06,
"loss": 0.8537,
"step": 1788
},
{
"epoch": 2.29,
"learning_rate": 2.7933810323358414e-06,
"loss": 0.9206,
"step": 1789
},
{
"epoch": 2.29,
"learning_rate": 2.783801550003562e-06,
"loss": 0.9126,
"step": 1790
},
{
"epoch": 2.29,
"learning_rate": 2.774235864888135e-06,
"loss": 0.9411,
"step": 1791
},
{
"epoch": 2.29,
"learning_rate": 2.764683995278944e-06,
"loss": 0.9471,
"step": 1792
},
{
"epoch": 2.3,
"learning_rate": 2.7551459594389605e-06,
"loss": 1.0012,
"step": 1793
},
{
"epoch": 2.3,
"learning_rate": 2.7456217756047044e-06,
"loss": 0.9193,
"step": 1794
},
{
"epoch": 2.3,
"learning_rate": 2.7361114619862105e-06,
"loss": 1.0385,
"step": 1795
},
{
"epoch": 2.3,
"learning_rate": 2.7266150367669953e-06,
"loss": 0.9454,
"step": 1796
},
{
"epoch": 2.3,
"learning_rate": 2.717132518104023e-06,
"loss": 0.9185,
"step": 1797
},
{
"epoch": 2.3,
"learning_rate": 2.707663924127657e-06,
"loss": 0.8957,
"step": 1798
},
{
"epoch": 2.3,
"learning_rate": 2.698209272941659e-06,
"loss": 1.0563,
"step": 1799
},
{
"epoch": 2.3,
"learning_rate": 2.68876858262311e-06,
"loss": 0.9441,
"step": 1800
},
{
"epoch": 2.31,
"learning_rate": 2.679341871222411e-06,
"loss": 0.8075,
"step": 1801
},
{
"epoch": 2.31,
"learning_rate": 2.66992915676323e-06,
"loss": 0.9214,
"step": 1802
},
{
"epoch": 2.31,
"learning_rate": 2.6605304572424793e-06,
"loss": 0.9836,
"step": 1803
},
{
"epoch": 2.31,
"learning_rate": 2.6511457906302685e-06,
"loss": 0.9149,
"step": 1804
},
{
"epoch": 2.31,
"learning_rate": 2.641775174869882e-06,
"loss": 0.9025,
"step": 1805
},
{
"epoch": 2.31,
"learning_rate": 2.6324186278777285e-06,
"loss": 0.866,
"step": 1806
},
{
"epoch": 2.31,
"learning_rate": 2.623076167543337e-06,
"loss": 0.9417,
"step": 1807
},
{
"epoch": 2.31,
"learning_rate": 2.6137478117292792e-06,
"loss": 1.0292,
"step": 1808
},
{
"epoch": 2.32,
"learning_rate": 2.604433578271185e-06,
"loss": 0.9518,
"step": 1809
},
{
"epoch": 2.32,
"learning_rate": 2.5951334849776576e-06,
"loss": 0.8617,
"step": 1810
},
{
"epoch": 2.32,
"learning_rate": 2.5858475496302813e-06,
"loss": 0.893,
"step": 1811
},
{
"epoch": 2.32,
"learning_rate": 2.5765757899835664e-06,
"loss": 0.9568,
"step": 1812
},
{
"epoch": 2.32,
"learning_rate": 2.5673182237649187e-06,
"loss": 0.9372,
"step": 1813
},
{
"epoch": 2.32,
"learning_rate": 2.5580748686745995e-06,
"loss": 0.9749,
"step": 1814
},
{
"epoch": 2.32,
"learning_rate": 2.548845742385717e-06,
"loss": 1.076,
"step": 1815
},
{
"epoch": 2.32,
"learning_rate": 2.539630862544151e-06,
"loss": 0.9242,
"step": 1816
},
{
"epoch": 2.33,
"learning_rate": 2.530430246768567e-06,
"loss": 0.9107,
"step": 1817
},
{
"epoch": 2.33,
"learning_rate": 2.5212439126503364e-06,
"loss": 0.9187,
"step": 1818
},
{
"epoch": 2.33,
"learning_rate": 2.5120718777535345e-06,
"loss": 0.8949,
"step": 1819
},
{
"epoch": 2.33,
"learning_rate": 2.5029141596148985e-06,
"loss": 1.0752,
"step": 1820
},
{
"epoch": 2.33,
"learning_rate": 2.493770775743789e-06,
"loss": 0.9732,
"step": 1821
},
{
"epoch": 2.33,
"learning_rate": 2.4846417436221536e-06,
"loss": 0.9328,
"step": 1822
},
{
"epoch": 2.33,
"learning_rate": 2.4755270807045174e-06,
"loss": 0.9301,
"step": 1823
},
{
"epoch": 2.33,
"learning_rate": 2.4664268044179075e-06,
"loss": 0.9307,
"step": 1824
},
{
"epoch": 2.34,
"learning_rate": 2.45734093216187e-06,
"loss": 0.9487,
"step": 1825
},
{
"epoch": 2.34,
"learning_rate": 2.4482694813083908e-06,
"loss": 0.9483,
"step": 1826
},
{
"epoch": 2.34,
"learning_rate": 2.439212469201889e-06,
"loss": 0.8474,
"step": 1827
},
{
"epoch": 2.34,
"learning_rate": 2.4301699131591817e-06,
"loss": 0.8025,
"step": 1828
},
{
"epoch": 2.34,
"learning_rate": 2.421141830469439e-06,
"loss": 0.9041,
"step": 1829
},
{
"epoch": 2.34,
"learning_rate": 2.4121282383941637e-06,
"loss": 0.9092,
"step": 1830
},
{
"epoch": 2.34,
"learning_rate": 2.403129154167153e-06,
"loss": 1.012,
"step": 1831
},
{
"epoch": 2.34,
"learning_rate": 2.3941445949944542e-06,
"loss": 0.9348,
"step": 1832
},
{
"epoch": 2.35,
"learning_rate": 2.3851745780543634e-06,
"loss": 0.9443,
"step": 1833
},
{
"epoch": 2.35,
"learning_rate": 2.376219120497353e-06,
"loss": 0.9222,
"step": 1834
},
{
"epoch": 2.35,
"learning_rate": 2.367278239446068e-06,
"loss": 0.9394,
"step": 1835
},
{
"epoch": 2.35,
"learning_rate": 2.3583519519952815e-06,
"loss": 0.8816,
"step": 1836
},
{
"epoch": 2.35,
"learning_rate": 2.349440275211865e-06,
"loss": 0.9472,
"step": 1837
},
{
"epoch": 2.35,
"learning_rate": 2.3405432261347525e-06,
"loss": 0.9385,
"step": 1838
},
{
"epoch": 2.35,
"learning_rate": 2.331660821774915e-06,
"loss": 1.0436,
"step": 1839
},
{
"epoch": 2.36,
"learning_rate": 2.3227930791153096e-06,
"loss": 0.8765,
"step": 1840
},
{
"epoch": 2.36,
"learning_rate": 2.3139400151108825e-06,
"loss": 0.9332,
"step": 1841
},
{
"epoch": 2.36,
"learning_rate": 2.3051016466884946e-06,
"loss": 0.8792,
"step": 1842
},
{
"epoch": 2.36,
"learning_rate": 2.296277990746918e-06,
"loss": 0.869,
"step": 1843
},
{
"epoch": 2.36,
"learning_rate": 2.2874690641567952e-06,
"loss": 0.9428,
"step": 1844
},
{
"epoch": 2.36,
"learning_rate": 2.278674883760604e-06,
"loss": 0.9838,
"step": 1845
},
{
"epoch": 2.36,
"learning_rate": 2.26989546637263e-06,
"loss": 0.8958,
"step": 1846
},
{
"epoch": 2.36,
"learning_rate": 2.2611308287789347e-06,
"loss": 0.9466,
"step": 1847
},
{
"epoch": 2.37,
"learning_rate": 2.252380987737307e-06,
"loss": 0.9677,
"step": 1848
},
{
"epoch": 2.37,
"learning_rate": 2.2436459599772676e-06,
"loss": 0.9,
"step": 1849
},
{
"epoch": 2.37,
"learning_rate": 2.234925762199992e-06,
"loss": 0.8713,
"step": 1850
},
{
"epoch": 2.37,
"learning_rate": 2.2262204110783213e-06,
"loss": 1.0113,
"step": 1851
},
{
"epoch": 2.37,
"learning_rate": 2.217529923256694e-06,
"loss": 0.9633,
"step": 1852
},
{
"epoch": 2.37,
"learning_rate": 2.2088543153511368e-06,
"loss": 0.9615,
"step": 1853
},
{
"epoch": 2.37,
"learning_rate": 2.200193603949229e-06,
"loss": 0.8904,
"step": 1854
},
{
"epoch": 2.37,
"learning_rate": 2.191547805610066e-06,
"loss": 0.9729,
"step": 1855
},
{
"epoch": 2.38,
"learning_rate": 2.1829169368642213e-06,
"loss": 0.9741,
"step": 1856
},
{
"epoch": 2.38,
"learning_rate": 2.174301014213741e-06,
"loss": 0.9176,
"step": 1857
},
{
"epoch": 2.38,
"learning_rate": 2.165700054132076e-06,
"loss": 0.9284,
"step": 1858
},
{
"epoch": 2.38,
"learning_rate": 2.157114073064087e-06,
"loss": 0.9563,
"step": 1859
},
{
"epoch": 2.38,
"learning_rate": 2.148543087425979e-06,
"loss": 1.036,
"step": 1860
},
{
"epoch": 2.38,
"learning_rate": 2.139987113605294e-06,
"loss": 0.9852,
"step": 1861
},
{
"epoch": 2.38,
"learning_rate": 2.1314461679608724e-06,
"loss": 0.935,
"step": 1862
},
{
"epoch": 2.38,
"learning_rate": 2.1229202668228197e-06,
"loss": 0.9547,
"step": 1863
},
{
"epoch": 2.39,
"learning_rate": 2.114409426492471e-06,
"loss": 0.9068,
"step": 1864
},
{
"epoch": 2.39,
"learning_rate": 2.105913663242378e-06,
"loss": 0.9174,
"step": 1865
},
{
"epoch": 2.39,
"learning_rate": 2.0974329933162505e-06,
"loss": 1.0306,
"step": 1866
},
{
"epoch": 2.39,
"learning_rate": 2.088967432928958e-06,
"loss": 0.8501,
"step": 1867
},
{
"epoch": 2.39,
"learning_rate": 2.0805169982664607e-06,
"loss": 0.7826,
"step": 1868
},
{
"epoch": 2.39,
"learning_rate": 2.0720817054858124e-06,
"loss": 0.9202,
"step": 1869
},
{
"epoch": 2.39,
"learning_rate": 2.063661570715113e-06,
"loss": 0.9672,
"step": 1870
},
{
"epoch": 2.39,
"learning_rate": 2.0552566100534787e-06,
"loss": 1.0096,
"step": 1871
},
{
"epoch": 2.4,
"learning_rate": 2.0468668395710145e-06,
"loss": 0.9538,
"step": 1872
},
{
"epoch": 2.4,
"learning_rate": 2.0384922753087843e-06,
"loss": 0.9075,
"step": 1873
},
{
"epoch": 2.4,
"learning_rate": 2.0301329332787676e-06,
"loss": 0.8199,
"step": 1874
},
{
"epoch": 2.4,
"learning_rate": 2.021788829463859e-06,
"loss": 0.9543,
"step": 1875
},
{
"epoch": 2.4,
"learning_rate": 2.013459979817797e-06,
"loss": 0.93,
"step": 1876
},
{
"epoch": 2.4,
"learning_rate": 2.0051464002651665e-06,
"loss": 0.8649,
"step": 1877
},
{
"epoch": 2.4,
"learning_rate": 1.9968481067013546e-06,
"loss": 0.9399,
"step": 1878
},
{
"epoch": 2.41,
"learning_rate": 1.988565114992519e-06,
"loss": 0.9868,
"step": 1879
},
{
"epoch": 2.41,
"learning_rate": 1.980297440975565e-06,
"loss": 0.8749,
"step": 1880
},
{
"epoch": 2.41,
"learning_rate": 1.9720451004581077e-06,
"loss": 0.8347,
"step": 1881
},
{
"epoch": 2.41,
"learning_rate": 1.9638081092184403e-06,
"loss": 0.8397,
"step": 1882
},
{
"epoch": 2.41,
"learning_rate": 1.9555864830055215e-06,
"loss": 1.0395,
"step": 1883
},
{
"epoch": 2.41,
"learning_rate": 1.9473802375389196e-06,
"loss": 0.883,
"step": 1884
},
{
"epoch": 2.41,
"learning_rate": 1.939189388508801e-06,
"loss": 0.9367,
"step": 1885
},
{
"epoch": 2.41,
"learning_rate": 1.931013951575893e-06,
"loss": 0.9554,
"step": 1886
},
{
"epoch": 2.42,
"learning_rate": 1.9228539423714564e-06,
"loss": 0.8722,
"step": 1887
},
{
"epoch": 2.42,
"learning_rate": 1.9147093764972547e-06,
"loss": 0.8608,
"step": 1888
},
{
"epoch": 2.42,
"learning_rate": 1.9065802695255265e-06,
"loss": 0.9613,
"step": 1889
},
{
"epoch": 2.42,
"learning_rate": 1.8984666369989403e-06,
"loss": 0.9606,
"step": 1890
},
{
"epoch": 2.42,
"learning_rate": 1.8903684944306e-06,
"loss": 0.8746,
"step": 1891
},
{
"epoch": 2.42,
"learning_rate": 1.8822858573039715e-06,
"loss": 0.8865,
"step": 1892
},
{
"epoch": 2.42,
"learning_rate": 1.8742187410728862e-06,
"loss": 0.9769,
"step": 1893
},
{
"epoch": 2.42,
"learning_rate": 1.8661671611614995e-06,
"loss": 0.9306,
"step": 1894
},
{
"epoch": 2.43,
"learning_rate": 1.8581311329642592e-06,
"loss": 0.9716,
"step": 1895
},
{
"epoch": 2.43,
"learning_rate": 1.8501106718458773e-06,
"loss": 0.9364,
"step": 1896
},
{
"epoch": 2.43,
"learning_rate": 1.8421057931413055e-06,
"loss": 0.9583,
"step": 1897
},
{
"epoch": 2.43,
"learning_rate": 1.8341165121556992e-06,
"loss": 0.8756,
"step": 1898
},
{
"epoch": 2.43,
"learning_rate": 1.8261428441643957e-06,
"loss": 0.9299,
"step": 1899
},
{
"epoch": 2.43,
"learning_rate": 1.8181848044128703e-06,
"loss": 1.0125,
"step": 1900
},
{
"epoch": 2.43,
"learning_rate": 1.8102424081167336e-06,
"loss": 0.9913,
"step": 1901
},
{
"epoch": 2.43,
"learning_rate": 1.8023156704616696e-06,
"loss": 0.9831,
"step": 1902
},
{
"epoch": 2.44,
"learning_rate": 1.7944046066034338e-06,
"loss": 0.788,
"step": 1903
},
{
"epoch": 2.44,
"learning_rate": 1.7865092316678112e-06,
"loss": 0.8973,
"step": 1904
},
{
"epoch": 2.44,
"learning_rate": 1.7786295607505888e-06,
"loss": 0.9919,
"step": 1905
},
{
"epoch": 2.44,
"learning_rate": 1.7707656089175286e-06,
"loss": 0.9962,
"step": 1906
},
{
"epoch": 2.44,
"learning_rate": 1.7629173912043397e-06,
"loss": 0.8648,
"step": 1907
},
{
"epoch": 2.44,
"learning_rate": 1.7550849226166432e-06,
"loss": 1.0581,
"step": 1908
},
{
"epoch": 2.44,
"learning_rate": 1.7472682181299572e-06,
"loss": 0.8977,
"step": 1909
},
{
"epoch": 2.44,
"learning_rate": 1.7394672926896449e-06,
"loss": 0.8958,
"step": 1910
},
{
"epoch": 2.45,
"learning_rate": 1.7316821612109136e-06,
"loss": 0.865,
"step": 1911
},
{
"epoch": 2.45,
"learning_rate": 1.7239128385787674e-06,
"loss": 0.9205,
"step": 1912
},
{
"epoch": 2.45,
"learning_rate": 1.7161593396479848e-06,
"loss": 0.9056,
"step": 1913
},
{
"epoch": 2.45,
"learning_rate": 1.7084216792430885e-06,
"loss": 0.9238,
"step": 1914
},
{
"epoch": 2.45,
"learning_rate": 1.70069987215832e-06,
"loss": 0.9981,
"step": 1915
},
{
"epoch": 2.45,
"learning_rate": 1.6929939331576096e-06,
"loss": 0.8721,
"step": 1916
},
{
"epoch": 2.45,
"learning_rate": 1.6853038769745466e-06,
"loss": 0.8501,
"step": 1917
},
{
"epoch": 2.46,
"learning_rate": 1.677629718312358e-06,
"loss": 0.8986,
"step": 1918
},
{
"epoch": 2.46,
"learning_rate": 1.6699714718438643e-06,
"loss": 0.7869,
"step": 1919
},
{
"epoch": 2.46,
"learning_rate": 1.6623291522114705e-06,
"loss": 0.9695,
"step": 1920
},
{
"epoch": 2.46,
"learning_rate": 1.6547027740271304e-06,
"loss": 0.9308,
"step": 1921
},
{
"epoch": 2.46,
"learning_rate": 1.6470923518723137e-06,
"loss": 0.9173,
"step": 1922
},
{
"epoch": 2.46,
"learning_rate": 1.6394979002979849e-06,
"loss": 0.929,
"step": 1923
},
{
"epoch": 2.46,
"learning_rate": 1.6319194338245725e-06,
"loss": 0.9998,
"step": 1924
},
{
"epoch": 2.46,
"learning_rate": 1.6243569669419434e-06,
"loss": 0.9173,
"step": 1925
},
{
"epoch": 2.47,
"learning_rate": 1.6168105141093737e-06,
"loss": 0.9882,
"step": 1926
},
{
"epoch": 2.47,
"learning_rate": 1.609280089755515e-06,
"loss": 0.9423,
"step": 1927
},
{
"epoch": 2.47,
"learning_rate": 1.6017657082783788e-06,
"loss": 0.8875,
"step": 1928
},
{
"epoch": 2.47,
"learning_rate": 1.5942673840453038e-06,
"loss": 1.0213,
"step": 1929
},
{
"epoch": 2.47,
"learning_rate": 1.5867851313929229e-06,
"loss": 0.9758,
"step": 1930
},
{
"epoch": 2.47,
"learning_rate": 1.5793189646271434e-06,
"loss": 0.9056,
"step": 1931
},
{
"epoch": 2.47,
"learning_rate": 1.5718688980231168e-06,
"loss": 0.8455,
"step": 1932
},
{
"epoch": 2.47,
"learning_rate": 1.5644349458252117e-06,
"loss": 0.9708,
"step": 1933
},
{
"epoch": 2.48,
"learning_rate": 1.5570171222469854e-06,
"loss": 0.9892,
"step": 1934
},
{
"epoch": 2.48,
"learning_rate": 1.549615441471153e-06,
"loss": 0.9308,
"step": 1935
},
{
"epoch": 2.48,
"learning_rate": 1.5422299176495782e-06,
"loss": 0.9043,
"step": 1936
},
{
"epoch": 2.48,
"learning_rate": 1.5348605649032166e-06,
"loss": 0.9824,
"step": 1937
},
{
"epoch": 2.48,
"learning_rate": 1.5275073973221154e-06,
"loss": 0.9638,
"step": 1938
},
{
"epoch": 2.48,
"learning_rate": 1.520170428965374e-06,
"loss": 0.9408,
"step": 1939
},
{
"epoch": 2.48,
"learning_rate": 1.5128496738611187e-06,
"loss": 0.9569,
"step": 1940
},
{
"epoch": 2.48,
"learning_rate": 1.5055451460064752e-06,
"loss": 1.0012,
"step": 1941
},
{
"epoch": 2.49,
"learning_rate": 1.4982568593675462e-06,
"loss": 0.979,
"step": 1942
},
{
"epoch": 2.49,
"learning_rate": 1.490984827879378e-06,
"loss": 0.9667,
"step": 1943
},
{
"epoch": 2.49,
"learning_rate": 1.4837290654459425e-06,
"loss": 0.9506,
"step": 1944
},
{
"epoch": 2.49,
"learning_rate": 1.4764895859400952e-06,
"loss": 0.879,
"step": 1945
},
{
"epoch": 2.49,
"learning_rate": 1.469266403203573e-06,
"loss": 0.8935,
"step": 1946
},
{
"epoch": 2.49,
"learning_rate": 1.4620595310469421e-06,
"loss": 0.8769,
"step": 1947
},
{
"epoch": 2.49,
"learning_rate": 1.45486898324959e-06,
"loss": 0.8919,
"step": 1948
},
{
"epoch": 2.49,
"learning_rate": 1.447694773559688e-06,
"loss": 0.9093,
"step": 1949
},
{
"epoch": 2.5,
"learning_rate": 1.4405369156941717e-06,
"loss": 0.9248,
"step": 1950
},
{
"epoch": 2.5,
"learning_rate": 1.4333954233387138e-06,
"loss": 0.8488,
"step": 1951
},
{
"epoch": 2.5,
"learning_rate": 1.426270310147695e-06,
"loss": 0.9435,
"step": 1952
},
{
"epoch": 2.5,
"learning_rate": 1.4191615897441746e-06,
"loss": 0.8837,
"step": 1953
},
{
"epoch": 2.5,
"learning_rate": 1.4120692757198806e-06,
"loss": 1.0227,
"step": 1954
},
{
"epoch": 2.5,
"learning_rate": 1.404993381635159e-06,
"loss": 0.8377,
"step": 1955
},
{
"epoch": 2.5,
"learning_rate": 1.3979339210189703e-06,
"loss": 0.9342,
"step": 1956
},
{
"epoch": 2.5,
"learning_rate": 1.3908909073688526e-06,
"loss": 1.0163,
"step": 1957
},
{
"epoch": 2.51,
"learning_rate": 1.3838643541508967e-06,
"loss": 0.897,
"step": 1958
},
{
"epoch": 2.51,
"learning_rate": 1.3768542747997215e-06,
"loss": 0.9731,
"step": 1959
},
{
"epoch": 2.51,
"learning_rate": 1.3698606827184513e-06,
"loss": 0.931,
"step": 1960
},
{
"epoch": 2.51,
"learning_rate": 1.3628835912786774e-06,
"loss": 0.9389,
"step": 1961
},
{
"epoch": 2.51,
"learning_rate": 1.3559230138204583e-06,
"loss": 0.9478,
"step": 1962
},
{
"epoch": 2.51,
"learning_rate": 1.3489789636522621e-06,
"loss": 0.8997,
"step": 1963
},
{
"epoch": 2.51,
"learning_rate": 1.3420514540509655e-06,
"loss": 0.933,
"step": 1964
},
{
"epoch": 2.52,
"learning_rate": 1.3351404982618199e-06,
"loss": 0.9028,
"step": 1965
},
{
"epoch": 2.52,
"learning_rate": 1.3282461094984233e-06,
"loss": 0.9937,
"step": 1966
},
{
"epoch": 2.52,
"learning_rate": 1.3213683009427004e-06,
"loss": 0.9106,
"step": 1967
},
{
"epoch": 2.52,
"learning_rate": 1.314507085744875e-06,
"loss": 0.892,
"step": 1968
},
{
"epoch": 2.52,
"learning_rate": 1.307662477023438e-06,
"loss": 0.8452,
"step": 1969
},
{
"epoch": 2.52,
"learning_rate": 1.3008344878651435e-06,
"loss": 0.8714,
"step": 1970
},
{
"epoch": 2.52,
"learning_rate": 1.2940231313249508e-06,
"loss": 0.9794,
"step": 1971
},
{
"epoch": 2.52,
"learning_rate": 1.2872284204260365e-06,
"loss": 0.8886,
"step": 1972
},
{
"epoch": 2.53,
"learning_rate": 1.2804503681597369e-06,
"loss": 0.9441,
"step": 1973
},
{
"epoch": 2.53,
"learning_rate": 1.273688987485544e-06,
"loss": 0.9442,
"step": 1974
},
{
"epoch": 2.53,
"learning_rate": 1.2669442913310725e-06,
"loss": 0.8971,
"step": 1975
},
{
"epoch": 2.53,
"learning_rate": 1.2602162925920403e-06,
"loss": 0.9381,
"step": 1976
},
{
"epoch": 2.53,
"learning_rate": 1.2535050041322293e-06,
"loss": 0.8865,
"step": 1977
},
{
"epoch": 2.53,
"learning_rate": 1.246810438783488e-06,
"loss": 0.9203,
"step": 1978
},
{
"epoch": 2.53,
"learning_rate": 1.2401326093456733e-06,
"loss": 0.9632,
"step": 1979
},
{
"epoch": 2.53,
"learning_rate": 1.2334715285866616e-06,
"loss": 1.0848,
"step": 1980
},
{
"epoch": 2.54,
"learning_rate": 1.2268272092422895e-06,
"loss": 0.9116,
"step": 1981
},
{
"epoch": 2.54,
"learning_rate": 1.220199664016355e-06,
"loss": 0.9392,
"step": 1982
},
{
"epoch": 2.54,
"learning_rate": 1.213588905580584e-06,
"loss": 0.9275,
"step": 1983
},
{
"epoch": 2.54,
"learning_rate": 1.2069949465746044e-06,
"loss": 0.8655,
"step": 1984
},
{
"epoch": 2.54,
"learning_rate": 1.2004177996059208e-06,
"loss": 0.8951,
"step": 1985
},
{
"epoch": 2.54,
"learning_rate": 1.1938574772499056e-06,
"loss": 0.9523,
"step": 1986
},
{
"epoch": 2.54,
"learning_rate": 1.1873139920497445e-06,
"loss": 0.9707,
"step": 1987
},
{
"epoch": 2.54,
"learning_rate": 1.1807873565164507e-06,
"loss": 0.9084,
"step": 1988
},
{
"epoch": 2.55,
"learning_rate": 1.1742775831288056e-06,
"loss": 0.8355,
"step": 1989
},
{
"epoch": 2.55,
"learning_rate": 1.1677846843333574e-06,
"loss": 1.0318,
"step": 1990
},
{
"epoch": 2.55,
"learning_rate": 1.161308672544389e-06,
"loss": 0.9273,
"step": 1991
},
{
"epoch": 2.55,
"learning_rate": 1.1548495601438981e-06,
"loss": 0.9532,
"step": 1992
},
{
"epoch": 2.55,
"learning_rate": 1.1484073594815691e-06,
"loss": 0.8998,
"step": 1993
},
{
"epoch": 2.55,
"learning_rate": 1.141982082874752e-06,
"loss": 0.8319,
"step": 1994
},
{
"epoch": 2.55,
"learning_rate": 1.1355737426084335e-06,
"loss": 0.911,
"step": 1995
},
{
"epoch": 2.55,
"learning_rate": 1.1291823509352295e-06,
"loss": 0.9495,
"step": 1996
},
{
"epoch": 2.56,
"learning_rate": 1.1228079200753394e-06,
"loss": 0.9539,
"step": 1997
},
{
"epoch": 2.56,
"learning_rate": 1.1164504622165407e-06,
"loss": 0.9018,
"step": 1998
},
{
"epoch": 2.56,
"learning_rate": 1.1101099895141542e-06,
"loss": 0.877,
"step": 1999
},
{
"epoch": 2.56,
"learning_rate": 1.103786514091031e-06,
"loss": 0.9637,
"step": 2000
},
{
"epoch": 2.56,
"learning_rate": 1.097480048037518e-06,
"loss": 0.9737,
"step": 2001
},
{
"epoch": 2.56,
"learning_rate": 1.0911906034114472e-06,
"loss": 0.9838,
"step": 2002
},
{
"epoch": 2.56,
"learning_rate": 1.0849181922380947e-06,
"loss": 0.8776,
"step": 2003
},
{
"epoch": 2.57,
"learning_rate": 1.078662826510185e-06,
"loss": 0.9595,
"step": 2004
},
{
"epoch": 2.57,
"learning_rate": 1.0724245181878369e-06,
"loss": 0.907,
"step": 2005
},
{
"epoch": 2.57,
"learning_rate": 1.0662032791985644e-06,
"loss": 0.825,
"step": 2006
},
{
"epoch": 2.57,
"learning_rate": 1.059999121437244e-06,
"loss": 0.9094,
"step": 2007
},
{
"epoch": 2.57,
"learning_rate": 1.0538120567660904e-06,
"loss": 0.976,
"step": 2008
},
{
"epoch": 2.57,
"learning_rate": 1.0476420970146406e-06,
"loss": 0.8653,
"step": 2009
},
{
"epoch": 2.57,
"learning_rate": 1.0414892539797272e-06,
"loss": 0.9359,
"step": 2010
},
{
"epoch": 2.57,
"learning_rate": 1.0353535394254477e-06,
"loss": 0.9514,
"step": 2011
},
{
"epoch": 2.58,
"learning_rate": 1.0292349650831656e-06,
"loss": 0.9776,
"step": 2012
},
{
"epoch": 2.58,
"learning_rate": 1.0231335426514555e-06,
"loss": 0.8467,
"step": 2013
},
{
"epoch": 2.58,
"learning_rate": 1.0170492837961133e-06,
"loss": 0.9453,
"step": 2014
},
{
"epoch": 2.58,
"learning_rate": 1.010982200150108e-06,
"loss": 0.935,
"step": 2015
},
{
"epoch": 2.58,
"learning_rate": 1.0049323033135738e-06,
"loss": 0.9227,
"step": 2016
},
{
"epoch": 2.58,
"learning_rate": 9.988996048537848e-07,
"loss": 0.8756,
"step": 2017
},
{
"epoch": 2.58,
"learning_rate": 9.928841163051318e-07,
"loss": 0.9422,
"step": 2018
},
{
"epoch": 2.58,
"learning_rate": 9.868858491690947e-07,
"loss": 0.9629,
"step": 2019
},
{
"epoch": 2.59,
"learning_rate": 9.809048149142409e-07,
"loss": 0.9206,
"step": 2020
},
{
"epoch": 2.59,
"learning_rate": 9.749410249761715e-07,
"loss": 0.9085,
"step": 2021
},
{
"epoch": 2.59,
"learning_rate": 9.68994490757531e-07,
"loss": 0.9067,
"step": 2022
},
{
"epoch": 2.59,
"learning_rate": 9.630652236279626e-07,
"loss": 0.9401,
"step": 2023
},
{
"epoch": 2.59,
"learning_rate": 9.571532349240976e-07,
"loss": 0.9138,
"step": 2024
},
{
"epoch": 2.59,
"learning_rate": 9.512585359495319e-07,
"loss": 1.0039,
"step": 2025
},
{
"epoch": 2.59,
"learning_rate": 9.453811379748068e-07,
"loss": 0.9856,
"step": 2026
},
{
"epoch": 2.59,
"learning_rate": 9.395210522373755e-07,
"loss": 1.0115,
"step": 2027
},
{
"epoch": 2.6,
"learning_rate": 9.336782899416031e-07,
"loss": 1.0045,
"step": 2028
},
{
"epoch": 2.6,
"learning_rate": 9.278528622587191e-07,
"loss": 0.9497,
"step": 2029
},
{
"epoch": 2.6,
"learning_rate": 9.220447803268228e-07,
"loss": 0.867,
"step": 2030
},
{
"epoch": 2.6,
"learning_rate": 9.162540552508392e-07,
"loss": 0.9456,
"step": 2031
},
{
"epoch": 2.6,
"learning_rate": 9.104806981025094e-07,
"loss": 0.96,
"step": 2032
},
{
"epoch": 2.6,
"learning_rate": 9.047247199203713e-07,
"loss": 0.8925,
"step": 2033
},
{
"epoch": 2.6,
"learning_rate": 8.989861317097304e-07,
"loss": 0.8728,
"step": 2034
},
{
"epoch": 2.6,
"learning_rate": 8.932649444426445e-07,
"loss": 0.9253,
"step": 2035
},
{
"epoch": 2.61,
"learning_rate": 8.875611690579033e-07,
"loss": 0.8838,
"step": 2036
},
{
"epoch": 2.61,
"learning_rate": 8.81874816460998e-07,
"loss": 0.9694,
"step": 2037
},
{
"epoch": 2.61,
"learning_rate": 8.762058975241194e-07,
"loss": 0.9279,
"step": 2038
},
{
"epoch": 2.61,
"learning_rate": 8.705544230861141e-07,
"loss": 1.0201,
"step": 2039
},
{
"epoch": 2.61,
"learning_rate": 8.649204039524816e-07,
"loss": 0.7873,
"step": 2040
},
{
"epoch": 2.61,
"learning_rate": 8.593038508953466e-07,
"loss": 0.9852,
"step": 2041
},
{
"epoch": 2.61,
"learning_rate": 8.537047746534377e-07,
"loss": 0.9373,
"step": 2042
},
{
"epoch": 2.62,
"learning_rate": 8.481231859320682e-07,
"loss": 0.9618,
"step": 2043
},
{
"epoch": 2.62,
"learning_rate": 8.425590954031171e-07,
"loss": 1.0313,
"step": 2044
},
{
"epoch": 2.62,
"learning_rate": 8.370125137050056e-07,
"loss": 0.9545,
"step": 2045
},
{
"epoch": 2.62,
"learning_rate": 8.314834514426806e-07,
"loss": 0.9007,
"step": 2046
},
{
"epoch": 2.62,
"learning_rate": 8.259719191875892e-07,
"loss": 0.9018,
"step": 2047
},
{
"epoch": 2.62,
"learning_rate": 8.20477927477662e-07,
"loss": 1.0339,
"step": 2048
},
{
"epoch": 2.62,
"learning_rate": 8.150014868172951e-07,
"loss": 1.0561,
"step": 2049
},
{
"epoch": 2.62,
"learning_rate": 8.095426076773261e-07,
"loss": 0.9442,
"step": 2050
},
{
"epoch": 2.63,
"learning_rate": 8.041013004950138e-07,
"loss": 0.9251,
"step": 2051
},
{
"epoch": 2.63,
"learning_rate": 7.986775756740206e-07,
"loss": 0.918,
"step": 2052
},
{
"epoch": 2.63,
"learning_rate": 7.932714435843947e-07,
"loss": 0.8165,
"step": 2053
},
{
"epoch": 2.63,
"learning_rate": 7.878829145625422e-07,
"loss": 0.8565,
"step": 2054
},
{
"epoch": 2.63,
"learning_rate": 7.825119989112173e-07,
"loss": 0.925,
"step": 2055
},
{
"epoch": 2.63,
"learning_rate": 7.771587068994935e-07,
"loss": 1.0064,
"step": 2056
},
{
"epoch": 2.63,
"learning_rate": 7.71823048762751e-07,
"loss": 0.947,
"step": 2057
},
{
"epoch": 2.63,
"learning_rate": 7.665050347026548e-07,
"loss": 1.0526,
"step": 2058
},
{
"epoch": 2.64,
"learning_rate": 7.612046748871327e-07,
"loss": 0.9703,
"step": 2059
},
{
"epoch": 2.64,
"learning_rate": 7.559219794503603e-07,
"loss": 0.9854,
"step": 2060
},
{
"epoch": 2.64,
"learning_rate": 7.50656958492737e-07,
"loss": 0.9629,
"step": 2061
},
{
"epoch": 2.64,
"learning_rate": 7.454096220808715e-07,
"loss": 0.9814,
"step": 2062
},
{
"epoch": 2.64,
"learning_rate": 7.401799802475574e-07,
"loss": 0.982,
"step": 2063
},
{
"epoch": 2.64,
"learning_rate": 7.349680429917594e-07,
"loss": 0.8733,
"step": 2064
},
{
"epoch": 2.64,
"learning_rate": 7.297738202785875e-07,
"loss": 0.86,
"step": 2065
},
{
"epoch": 2.64,
"learning_rate": 7.245973220392854e-07,
"loss": 0.8781,
"step": 2066
},
{
"epoch": 2.65,
"learning_rate": 7.194385581712071e-07,
"loss": 0.9554,
"step": 2067
},
{
"epoch": 2.65,
"learning_rate": 7.142975385377981e-07,
"loss": 0.9102,
"step": 2068
},
{
"epoch": 2.65,
"learning_rate": 7.09174272968578e-07,
"loss": 0.9443,
"step": 2069
},
{
"epoch": 2.65,
"learning_rate": 7.040687712591221e-07,
"loss": 0.975,
"step": 2070
},
{
"epoch": 2.65,
"learning_rate": 6.989810431710375e-07,
"loss": 1.0177,
"step": 2071
},
{
"epoch": 2.65,
"learning_rate": 6.939110984319541e-07,
"loss": 0.9926,
"step": 2072
},
{
"epoch": 2.65,
"learning_rate": 6.888589467354978e-07,
"loss": 0.9268,
"step": 2073
},
{
"epoch": 2.65,
"learning_rate": 6.838245977412717e-07,
"loss": 0.9057,
"step": 2074
},
{
"epoch": 2.66,
"learning_rate": 6.788080610748437e-07,
"loss": 0.9604,
"step": 2075
},
{
"epoch": 2.66,
"learning_rate": 6.738093463277262e-07,
"loss": 0.954,
"step": 2076
},
{
"epoch": 2.66,
"learning_rate": 6.688284630573538e-07,
"loss": 0.9154,
"step": 2077
},
{
"epoch": 2.66,
"learning_rate": 6.638654207870688e-07,
"loss": 0.894,
"step": 2078
},
{
"epoch": 2.66,
"learning_rate": 6.589202290061015e-07,
"loss": 0.9209,
"step": 2079
},
{
"epoch": 2.66,
"learning_rate": 6.539928971695531e-07,
"loss": 0.9184,
"step": 2080
},
{
"epoch": 2.66,
"learning_rate": 6.490834346983765e-07,
"loss": 0.8968,
"step": 2081
},
{
"epoch": 2.66,
"learning_rate": 6.441918509793565e-07,
"loss": 0.9123,
"step": 2082
},
{
"epoch": 2.67,
"learning_rate": 6.393181553651007e-07,
"loss": 0.9991,
"step": 2083
},
{
"epoch": 2.67,
"learning_rate": 6.344623571740083e-07,
"loss": 0.8547,
"step": 2084
},
{
"epoch": 2.67,
"learning_rate": 6.296244656902595e-07,
"loss": 0.8819,
"step": 2085
},
{
"epoch": 2.67,
"learning_rate": 6.248044901638028e-07,
"loss": 0.8958,
"step": 2086
},
{
"epoch": 2.67,
"learning_rate": 6.200024398103255e-07,
"loss": 0.9298,
"step": 2087
},
{
"epoch": 2.67,
"learning_rate": 6.152183238112464e-07,
"loss": 0.91,
"step": 2088
},
{
"epoch": 2.67,
"learning_rate": 6.104521513136941e-07,
"loss": 0.964,
"step": 2089
},
{
"epoch": 2.68,
"learning_rate": 6.057039314304824e-07,
"loss": 0.9043,
"step": 2090
},
{
"epoch": 2.68,
"learning_rate": 6.00973673240115e-07,
"loss": 0.89,
"step": 2091
},
{
"epoch": 2.68,
"learning_rate": 5.96261385786735e-07,
"loss": 0.892,
"step": 2092
},
{
"epoch": 2.68,
"learning_rate": 5.915670780801441e-07,
"loss": 0.8748,
"step": 2093
},
{
"epoch": 2.68,
"learning_rate": 5.868907590957507e-07,
"loss": 0.8928,
"step": 2094
},
{
"epoch": 2.68,
"learning_rate": 5.822324377745792e-07,
"loss": 0.9251,
"step": 2095
},
{
"epoch": 2.68,
"learning_rate": 5.775921230232407e-07,
"loss": 0.8978,
"step": 2096
},
{
"epoch": 2.68,
"learning_rate": 5.729698237139191e-07,
"loss": 0.8754,
"step": 2097
},
{
"epoch": 2.69,
"learning_rate": 5.683655486843465e-07,
"loss": 1.0626,
"step": 2098
},
{
"epoch": 2.69,
"learning_rate": 5.63779306737805e-07,
"loss": 1.0134,
"step": 2099
},
{
"epoch": 2.69,
"learning_rate": 5.592111066430828e-07,
"loss": 0.9338,
"step": 2100
},
{
"epoch": 2.69,
"learning_rate": 5.546609571344897e-07,
"loss": 0.8544,
"step": 2101
},
{
"epoch": 2.69,
"learning_rate": 5.501288669118077e-07,
"loss": 1.0095,
"step": 2102
},
{
"epoch": 2.69,
"learning_rate": 5.456148446402976e-07,
"loss": 0.9461,
"step": 2103
},
{
"epoch": 2.69,
"learning_rate": 5.411188989506733e-07,
"loss": 0.906,
"step": 2104
},
{
"epoch": 2.69,
"learning_rate": 5.366410384390897e-07,
"loss": 0.8949,
"step": 2105
},
{
"epoch": 2.7,
"learning_rate": 5.321812716671137e-07,
"loss": 0.8961,
"step": 2106
},
{
"epoch": 2.7,
"learning_rate": 5.277396071617313e-07,
"loss": 0.9842,
"step": 2107
},
{
"epoch": 2.7,
"learning_rate": 5.233160534153037e-07,
"loss": 0.8478,
"step": 2108
},
{
"epoch": 2.7,
"learning_rate": 5.189106188855753e-07,
"loss": 0.9286,
"step": 2109
},
{
"epoch": 2.7,
"learning_rate": 5.145233119956394e-07,
"loss": 0.9315,
"step": 2110
},
{
"epoch": 2.7,
"learning_rate": 5.101541411339351e-07,
"loss": 0.9396,
"step": 2111
},
{
"epoch": 2.7,
"learning_rate": 5.058031146542219e-07,
"loss": 0.9953,
"step": 2112
},
{
"epoch": 2.7,
"learning_rate": 5.0147024087557e-07,
"loss": 1.0198,
"step": 2113
},
{
"epoch": 2.71,
"learning_rate": 4.971555280823415e-07,
"loss": 1.0282,
"step": 2114
},
{
"epoch": 2.71,
"learning_rate": 4.92858984524175e-07,
"loss": 0.9356,
"step": 2115
},
{
"epoch": 2.71,
"learning_rate": 4.885806184159669e-07,
"loss": 0.8674,
"step": 2116
},
{
"epoch": 2.71,
"learning_rate": 4.843204379378663e-07,
"loss": 0.9352,
"step": 2117
},
{
"epoch": 2.71,
"learning_rate": 4.80078451235243e-07,
"loss": 0.9148,
"step": 2118
},
{
"epoch": 2.71,
"learning_rate": 4.7585466641868696e-07,
"loss": 0.9017,
"step": 2119
},
{
"epoch": 2.71,
"learning_rate": 4.7164909156398265e-07,
"loss": 0.9265,
"step": 2120
},
{
"epoch": 2.71,
"learning_rate": 4.674617347121013e-07,
"loss": 0.9299,
"step": 2121
},
{
"epoch": 2.72,
"learning_rate": 4.6329260386917654e-07,
"loss": 0.9358,
"step": 2122
},
{
"epoch": 2.72,
"learning_rate": 4.5914170700650184e-07,
"loss": 0.9032,
"step": 2123
},
{
"epoch": 2.72,
"learning_rate": 4.5500905206049663e-07,
"loss": 0.9696,
"step": 2124
},
{
"epoch": 2.72,
"learning_rate": 4.5089464693271467e-07,
"loss": 0.9912,
"step": 2125
},
{
"epoch": 2.72,
"learning_rate": 4.467984994898067e-07,
"loss": 0.8969,
"step": 2126
},
{
"epoch": 2.72,
"learning_rate": 4.427206175635201e-07,
"loss": 0.9538,
"step": 2127
},
{
"epoch": 2.72,
"learning_rate": 4.386610089506771e-07,
"loss": 0.9487,
"step": 2128
},
{
"epoch": 2.73,
"learning_rate": 4.3461968141316427e-07,
"loss": 0.9271,
"step": 2129
},
{
"epoch": 2.73,
"learning_rate": 4.305966426779118e-07,
"loss": 0.9953,
"step": 2130
},
{
"epoch": 2.73,
"learning_rate": 4.265919004368846e-07,
"loss": 0.962,
"step": 2131
},
{
"epoch": 2.73,
"learning_rate": 4.22605462347061e-07,
"loss": 0.932,
"step": 2132
},
{
"epoch": 2.73,
"learning_rate": 4.186373360304297e-07,
"loss": 1.0048,
"step": 2133
},
{
"epoch": 2.73,
"learning_rate": 4.1468752907395826e-07,
"loss": 0.7749,
"step": 2134
},
{
"epoch": 2.73,
"learning_rate": 4.107560490295992e-07,
"loss": 0.9691,
"step": 2135
},
{
"epoch": 2.73,
"learning_rate": 4.068429034142529e-07,
"loss": 0.8954,
"step": 2136
},
{
"epoch": 2.74,
"learning_rate": 4.0294809970977235e-07,
"loss": 0.8931,
"step": 2137
},
{
"epoch": 2.74,
"learning_rate": 3.990716453629373e-07,
"loss": 0.8449,
"step": 2138
},
{
"epoch": 2.74,
"learning_rate": 3.9521354778544794e-07,
"loss": 0.9297,
"step": 2139
},
{
"epoch": 2.74,
"learning_rate": 3.913738143538992e-07,
"loss": 0.9894,
"step": 2140
},
{
"epoch": 2.74,
"learning_rate": 3.8755245240978623e-07,
"loss": 0.8579,
"step": 2141
},
{
"epoch": 2.74,
"learning_rate": 3.8374946925946457e-07,
"loss": 0.8972,
"step": 2142
},
{
"epoch": 2.74,
"learning_rate": 3.799648721741622e-07,
"loss": 0.9176,
"step": 2143
},
{
"epoch": 2.74,
"learning_rate": 3.7619866838994324e-07,
"loss": 0.8867,
"step": 2144
},
{
"epoch": 2.75,
"learning_rate": 3.7245086510770965e-07,
"loss": 0.9033,
"step": 2145
},
{
"epoch": 2.75,
"learning_rate": 3.687214694931829e-07,
"loss": 1.0276,
"step": 2146
},
{
"epoch": 2.75,
"learning_rate": 3.650104886768868e-07,
"loss": 0.8234,
"step": 2147
},
{
"epoch": 2.75,
"learning_rate": 3.6131792975413473e-07,
"loss": 0.914,
"step": 2148
},
{
"epoch": 2.75,
"learning_rate": 3.576437997850235e-07,
"loss": 0.9492,
"step": 2149
},
{
"epoch": 2.75,
"learning_rate": 3.5398810579440834e-07,
"loss": 0.9243,
"step": 2150
},
{
"epoch": 2.75,
"learning_rate": 3.5035085477190143e-07,
"loss": 0.963,
"step": 2151
},
{
"epoch": 2.75,
"learning_rate": 3.4673205367184437e-07,
"loss": 0.8881,
"step": 2152
},
{
"epoch": 2.76,
"learning_rate": 3.431317094133102e-07,
"loss": 0.9065,
"step": 2153
},
{
"epoch": 2.76,
"learning_rate": 3.3954982888007915e-07,
"loss": 0.9524,
"step": 2154
},
{
"epoch": 2.76,
"learning_rate": 3.3598641892063075e-07,
"loss": 1.0529,
"step": 2155
},
{
"epoch": 2.76,
"learning_rate": 3.3244148634812733e-07,
"loss": 1.0048,
"step": 2156
},
{
"epoch": 2.76,
"learning_rate": 3.28915037940406e-07,
"loss": 1.022,
"step": 2157
},
{
"epoch": 2.76,
"learning_rate": 3.2540708043995674e-07,
"loss": 0.9923,
"step": 2158
},
{
"epoch": 2.76,
"learning_rate": 3.219176205539243e-07,
"loss": 0.939,
"step": 2159
},
{
"epoch": 2.76,
"learning_rate": 3.184466649540763e-07,
"loss": 0.8588,
"step": 2160
},
{
"epoch": 2.77,
"learning_rate": 3.149942202768086e-07,
"loss": 0.9248,
"step": 2161
},
{
"epoch": 2.77,
"learning_rate": 3.1156029312312097e-07,
"loss": 0.8605,
"step": 2162
},
{
"epoch": 2.77,
"learning_rate": 3.08144890058607e-07,
"loss": 0.82,
"step": 2163
},
{
"epoch": 2.77,
"learning_rate": 3.0474801761344654e-07,
"loss": 1.0657,
"step": 2164
},
{
"epoch": 2.77,
"learning_rate": 3.013696822823864e-07,
"loss": 0.9589,
"step": 2165
},
{
"epoch": 2.77,
"learning_rate": 2.9800989052472863e-07,
"loss": 0.8637,
"step": 2166
},
{
"epoch": 2.77,
"learning_rate": 2.94668648764328e-07,
"loss": 0.8438,
"step": 2167
},
{
"epoch": 2.78,
"learning_rate": 2.913459633895621e-07,
"loss": 0.899,
"step": 2168
},
{
"epoch": 2.78,
"learning_rate": 2.8804184075333695e-07,
"loss": 0.8585,
"step": 2169
},
{
"epoch": 2.78,
"learning_rate": 2.847562871730647e-07,
"loss": 1.0156,
"step": 2170
},
{
"epoch": 2.78,
"learning_rate": 2.814893089306514e-07,
"loss": 0.868,
"step": 2171
},
{
"epoch": 2.78,
"learning_rate": 2.782409122724916e-07,
"loss": 0.9976,
"step": 2172
},
{
"epoch": 2.78,
"learning_rate": 2.750111034094494e-07,
"loss": 0.9533,
"step": 2173
},
{
"epoch": 2.78,
"learning_rate": 2.717998885168471e-07,
"loss": 0.9652,
"step": 2174
},
{
"epoch": 2.78,
"learning_rate": 2.6860727373446473e-07,
"loss": 1.0484,
"step": 2175
},
{
"epoch": 2.79,
"learning_rate": 2.6543326516650815e-07,
"loss": 0.9585,
"step": 2176
},
{
"epoch": 2.79,
"learning_rate": 2.6227786888161634e-07,
"loss": 0.9765,
"step": 2177
},
{
"epoch": 2.79,
"learning_rate": 2.591410909128389e-07,
"loss": 0.9476,
"step": 2178
},
{
"epoch": 2.79,
"learning_rate": 2.560229372576284e-07,
"loss": 0.8876,
"step": 2179
},
{
"epoch": 2.79,
"learning_rate": 2.5292341387782695e-07,
"loss": 0.9232,
"step": 2180
},
{
"epoch": 2.79,
"learning_rate": 2.4984252669965734e-07,
"loss": 0.8714,
"step": 2181
},
{
"epoch": 2.79,
"learning_rate": 2.4678028161370994e-07,
"loss": 0.9322,
"step": 2182
},
{
"epoch": 2.79,
"learning_rate": 2.4373668447493225e-07,
"loss": 0.9322,
"step": 2183
},
{
"epoch": 2.8,
"learning_rate": 2.40711741102615e-07,
"loss": 1.0387,
"step": 2184
},
{
"epoch": 2.8,
"learning_rate": 2.377054572803883e-07,
"loss": 1.0648,
"step": 2185
},
{
"epoch": 2.8,
"learning_rate": 2.347178387561999e-07,
"loss": 0.9778,
"step": 2186
},
{
"epoch": 2.8,
"learning_rate": 2.3174889124231158e-07,
"loss": 1.0032,
"step": 2187
},
{
"epoch": 2.8,
"learning_rate": 2.2879862041529034e-07,
"loss": 0.9426,
"step": 2188
},
{
"epoch": 2.8,
"learning_rate": 2.2586703191598836e-07,
"loss": 0.8759,
"step": 2189
},
{
"epoch": 2.8,
"learning_rate": 2.229541313495409e-07,
"loss": 0.8073,
"step": 2190
},
{
"epoch": 2.8,
"learning_rate": 2.2005992428535184e-07,
"loss": 0.9205,
"step": 2191
},
{
"epoch": 2.81,
"learning_rate": 2.171844162570824e-07,
"loss": 0.9681,
"step": 2192
},
{
"epoch": 2.81,
"learning_rate": 2.143276127626437e-07,
"loss": 0.8642,
"step": 2193
},
{
"epoch": 2.81,
"learning_rate": 2.1148951926418193e-07,
"loss": 1.0066,
"step": 2194
},
{
"epoch": 2.81,
"learning_rate": 2.0867014118806983e-07,
"loss": 0.9553,
"step": 2195
},
{
"epoch": 2.81,
"learning_rate": 2.0586948392489868e-07,
"loss": 0.8729,
"step": 2196
},
{
"epoch": 2.81,
"learning_rate": 2.0308755282946624e-07,
"loss": 1.0024,
"step": 2197
},
{
"epoch": 2.81,
"learning_rate": 2.0032435322076437e-07,
"loss": 0.879,
"step": 2198
},
{
"epoch": 2.81,
"learning_rate": 1.9757989038197146e-07,
"loss": 0.9339,
"step": 2199
},
{
"epoch": 2.82,
"learning_rate": 1.9485416956044222e-07,
"loss": 0.9289,
"step": 2200
},
{
"epoch": 2.82,
"learning_rate": 1.921471959676957e-07,
"loss": 0.921,
"step": 2201
},
{
"epoch": 2.82,
"learning_rate": 1.8945897477940844e-07,
"loss": 0.9297,
"step": 2202
},
{
"epoch": 2.82,
"learning_rate": 1.8678951113540012e-07,
"loss": 0.9944,
"step": 2203
},
{
"epoch": 2.82,
"learning_rate": 1.841388101396291e-07,
"loss": 1.0247,
"step": 2204
},
{
"epoch": 2.82,
"learning_rate": 1.815068768601791e-07,
"loss": 0.7998,
"step": 2205
},
{
"epoch": 2.82,
"learning_rate": 1.7889371632924924e-07,
"loss": 0.9197,
"step": 2206
},
{
"epoch": 2.82,
"learning_rate": 1.7629933354314733e-07,
"loss": 0.9439,
"step": 2207
},
{
"epoch": 2.83,
"learning_rate": 1.7372373346227767e-07,
"loss": 0.9658,
"step": 2208
},
{
"epoch": 2.83,
"learning_rate": 1.711669210111322e-07,
"loss": 0.8774,
"step": 2209
},
{
"epoch": 2.83,
"learning_rate": 1.6862890107828266e-07,
"loss": 0.891,
"step": 2210
},
{
"epoch": 2.83,
"learning_rate": 1.6610967851636629e-07,
"loss": 0.8791,
"step": 2211
},
{
"epoch": 2.83,
"learning_rate": 1.636092581420845e-07,
"loss": 0.977,
"step": 2212
},
{
"epoch": 2.83,
"learning_rate": 1.6112764473618647e-07,
"loss": 0.9197,
"step": 2213
},
{
"epoch": 2.83,
"learning_rate": 1.5866484304346564e-07,
"loss": 0.8602,
"step": 2214
},
{
"epoch": 2.84,
"learning_rate": 1.562208577727442e-07,
"loss": 0.8004,
"step": 2215
},
{
"epoch": 2.84,
"learning_rate": 1.5379569359686985e-07,
"loss": 0.9049,
"step": 2216
},
{
"epoch": 2.84,
"learning_rate": 1.513893551527057e-07,
"loss": 0.9723,
"step": 2217
},
{
"epoch": 2.84,
"learning_rate": 1.490018470411192e-07,
"loss": 0.8713,
"step": 2218
},
{
"epoch": 2.84,
"learning_rate": 1.4663317382697328e-07,
"loss": 0.804,
"step": 2219
},
{
"epoch": 2.84,
"learning_rate": 1.4428334003912192e-07,
"loss": 0.9583,
"step": 2220
},
{
"epoch": 2.84,
"learning_rate": 1.4195235017039566e-07,
"loss": 0.8844,
"step": 2221
},
{
"epoch": 2.84,
"learning_rate": 1.396402086775983e-07,
"loss": 0.9986,
"step": 2222
},
{
"epoch": 2.85,
"learning_rate": 1.3734691998149473e-07,
"loss": 0.8811,
"step": 2223
},
{
"epoch": 2.85,
"learning_rate": 1.350724884668031e-07,
"loss": 0.9256,
"step": 2224
},
{
"epoch": 2.85,
"learning_rate": 1.3281691848218813e-07,
"loss": 0.8379,
"step": 2225
},
{
"epoch": 2.85,
"learning_rate": 1.3058021434025126e-07,
"loss": 0.9923,
"step": 2226
},
{
"epoch": 2.85,
"learning_rate": 1.2836238031752269e-07,
"loss": 0.8646,
"step": 2227
},
{
"epoch": 2.85,
"learning_rate": 1.2616342065445485e-07,
"loss": 0.8732,
"step": 2228
},
{
"epoch": 2.85,
"learning_rate": 1.2398333955540908e-07,
"loss": 1.0197,
"step": 2229
},
{
"epoch": 2.85,
"learning_rate": 1.2182214118865666e-07,
"loss": 0.9308,
"step": 2230
},
{
"epoch": 2.86,
"learning_rate": 1.1967982968635994e-07,
"loss": 0.9724,
"step": 2231
},
{
"epoch": 2.86,
"learning_rate": 1.1755640914457355e-07,
"loss": 0.8944,
"step": 2232
},
{
"epoch": 2.86,
"learning_rate": 1.1545188362323323e-07,
"loss": 1.0192,
"step": 2233
},
{
"epoch": 2.86,
"learning_rate": 1.1336625714614469e-07,
"loss": 0.9587,
"step": 2234
},
{
"epoch": 2.86,
"learning_rate": 1.1129953370098256e-07,
"loss": 0.8751,
"step": 2235
},
{
"epoch": 2.86,
"learning_rate": 1.0925171723927819e-07,
"loss": 0.9521,
"step": 2236
},
{
"epoch": 2.86,
"learning_rate": 1.0722281167641069e-07,
"loss": 0.9035,
"step": 2237
},
{
"epoch": 2.86,
"learning_rate": 1.052128208916059e-07,
"loss": 0.867,
"step": 2238
},
{
"epoch": 2.87,
"learning_rate": 1.032217487279219e-07,
"loss": 0.8952,
"step": 2239
},
{
"epoch": 2.87,
"learning_rate": 1.0124959899224795e-07,
"loss": 0.9427,
"step": 2240
},
{
"epoch": 2.87,
"learning_rate": 9.929637545529003e-08,
"loss": 0.9899,
"step": 2241
},
{
"epoch": 2.87,
"learning_rate": 9.73620818515697e-08,
"loss": 0.8969,
"step": 2242
},
{
"epoch": 2.87,
"learning_rate": 9.54467218794164e-08,
"loss": 0.8914,
"step": 2243
},
{
"epoch": 2.87,
"learning_rate": 9.355029920095738e-08,
"loss": 0.9875,
"step": 2244
},
{
"epoch": 2.87,
"learning_rate": 9.167281744210999e-08,
"loss": 0.8659,
"step": 2245
},
{
"epoch": 2.87,
"learning_rate": 8.981428019258165e-08,
"loss": 0.913,
"step": 2246
},
{
"epoch": 2.88,
"learning_rate": 8.797469100585432e-08,
"loss": 1.0101,
"step": 2247
},
{
"epoch": 2.88,
"learning_rate": 8.615405339918337e-08,
"loss": 1.0033,
"step": 2248
},
{
"epoch": 2.88,
"learning_rate": 8.435237085358872e-08,
"loss": 0.8884,
"step": 2249
},
{
"epoch": 2.88,
"learning_rate": 8.256964681384927e-08,
"loss": 0.9305,
"step": 2250
},
{
"epoch": 2.88,
"learning_rate": 8.080588468849515e-08,
"loss": 0.8898,
"step": 2251
},
{
"epoch": 2.88,
"learning_rate": 7.906108784980216e-08,
"loss": 0.9422,
"step": 2252
},
{
"epoch": 2.88,
"learning_rate": 7.733525963378286e-08,
"loss": 0.7957,
"step": 2253
},
{
"epoch": 2.89,
"learning_rate": 7.56284033401855e-08,
"loss": 0.9738,
"step": 2254
},
{
"epoch": 2.89,
"learning_rate": 7.394052223248182e-08,
"loss": 0.8419,
"step": 2255
},
{
"epoch": 2.89,
"learning_rate": 7.227161953786588e-08,
"loss": 0.9483,
"step": 2256
},
{
"epoch": 2.89,
"learning_rate": 7.062169844724186e-08,
"loss": 0.889,
"step": 2257
},
{
"epoch": 2.89,
"learning_rate": 6.899076211522415e-08,
"loss": 0.9358,
"step": 2258
},
{
"epoch": 2.89,
"learning_rate": 6.737881366012833e-08,
"loss": 0.9565,
"step": 2259
},
{
"epoch": 2.89,
"learning_rate": 6.578585616396571e-08,
"loss": 0.9177,
"step": 2260
},
{
"epoch": 2.89,
"learning_rate": 6.421189267243555e-08,
"loss": 0.8695,
"step": 2261
},
{
"epoch": 2.9,
"learning_rate": 6.265692619492503e-08,
"loss": 0.8254,
"step": 2262
},
{
"epoch": 2.9,
"learning_rate": 6.112095970449261e-08,
"loss": 0.8282,
"step": 2263
},
{
"epoch": 2.9,
"learning_rate": 5.960399613787693e-08,
"loss": 0.8546,
"step": 2264
},
{
"epoch": 2.9,
"learning_rate": 5.810603839547901e-08,
"loss": 0.9774,
"step": 2265
},
{
"epoch": 2.9,
"learning_rate": 5.6627089341361186e-08,
"loss": 0.9648,
"step": 2266
},
{
"epoch": 2.9,
"learning_rate": 5.516715180324261e-08,
"loss": 0.934,
"step": 2267
},
{
"epoch": 2.9,
"learning_rate": 5.3726228572492656e-08,
"loss": 0.9614,
"step": 2268
},
{
"epoch": 2.9,
"learning_rate": 5.230432240412531e-08,
"loss": 0.9708,
"step": 2269
},
{
"epoch": 2.91,
"learning_rate": 5.090143601679587e-08,
"loss": 0.9307,
"step": 2270
},
{
"epoch": 2.91,
"learning_rate": 4.9517572092790954e-08,
"loss": 0.9711,
"step": 2271
},
{
"epoch": 2.91,
"learning_rate": 4.815273327803183e-08,
"loss": 0.9268,
"step": 2272
},
{
"epoch": 2.91,
"learning_rate": 4.680692218205773e-08,
"loss": 0.9245,
"step": 2273
},
{
"epoch": 2.91,
"learning_rate": 4.548014137803258e-08,
"loss": 0.9894,
"step": 2274
},
{
"epoch": 2.91,
"learning_rate": 4.4172393402732717e-08,
"loss": 0.9744,
"step": 2275
},
{
"epoch": 2.91,
"learning_rate": 4.28836807565447e-08,
"loss": 0.9679,
"step": 2276
},
{
"epoch": 2.91,
"learning_rate": 4.161400590345755e-08,
"loss": 0.9537,
"step": 2277
},
{
"epoch": 2.92,
"learning_rate": 4.0363371271064934e-08,
"loss": 0.9047,
"step": 2278
},
{
"epoch": 2.92,
"learning_rate": 3.913177925055189e-08,
"loss": 0.9199,
"step": 2279
},
{
"epoch": 2.92,
"learning_rate": 3.791923219669591e-08,
"loss": 0.8895,
"step": 2280
},
{
"epoch": 2.92,
"learning_rate": 3.672573242786137e-08,
"loss": 0.9589,
"step": 2281
},
{
"epoch": 2.92,
"learning_rate": 3.555128222599513e-08,
"loss": 0.8466,
"step": 2282
},
{
"epoch": 2.92,
"learning_rate": 3.4395883836618735e-08,
"loss": 1.0267,
"step": 2283
},
{
"epoch": 2.92,
"learning_rate": 3.325953946883065e-08,
"loss": 0.8811,
"step": 2284
},
{
"epoch": 2.92,
"learning_rate": 3.214225129529735e-08,
"loss": 0.9944,
"step": 2285
},
{
"epoch": 2.93,
"learning_rate": 3.104402145224894e-08,
"loss": 1.0145,
"step": 2286
},
{
"epoch": 2.93,
"learning_rate": 2.9964852039476854e-08,
"loss": 0.9561,
"step": 2287
},
{
"epoch": 2.93,
"learning_rate": 2.8904745120331702e-08,
"loss": 0.8804,
"step": 2288
},
{
"epoch": 2.93,
"learning_rate": 2.7863702721714348e-08,
"loss": 0.9863,
"step": 2289
},
{
"epoch": 2.93,
"learning_rate": 2.684172683407482e-08,
"loss": 0.9417,
"step": 2290
},
{
"epoch": 2.93,
"learning_rate": 2.5838819411408977e-08,
"loss": 0.9043,
"step": 2291
},
{
"epoch": 2.93,
"learning_rate": 2.4854982371256275e-08,
"loss": 0.8557,
"step": 2292
},
{
"epoch": 2.94,
"learning_rate": 2.3890217594689792e-08,
"loss": 0.8708,
"step": 2293
},
{
"epoch": 2.94,
"learning_rate": 2.2944526926321765e-08,
"loss": 0.8445,
"step": 2294
},
{
"epoch": 2.94,
"learning_rate": 2.201791217428917e-08,
"loss": 0.8733,
"step": 2295
},
{
"epoch": 2.94,
"learning_rate": 2.1110375110262592e-08,
"loss": 0.903,
"step": 2296
},
{
"epoch": 2.94,
"learning_rate": 2.0221917469430696e-08,
"loss": 0.881,
"step": 2297
},
{
"epoch": 2.94,
"learning_rate": 1.935254095050798e-08,
"loss": 1.0253,
"step": 2298
},
{
"epoch": 2.94,
"learning_rate": 1.850224721572258e-08,
"loss": 0.9571,
"step": 2299
},
{
"epoch": 2.94,
"learning_rate": 1.7671037890817366e-08,
"loss": 0.9932,
"step": 2300
},
{
"epoch": 2.95,
"learning_rate": 1.6858914565047736e-08,
"loss": 0.9456,
"step": 2301
},
{
"epoch": 2.95,
"learning_rate": 1.6065878791176048e-08,
"loss": 0.9261,
"step": 2302
},
{
"epoch": 2.95,
"learning_rate": 1.5291932085468308e-08,
"loss": 0.9156,
"step": 2303
},
{
"epoch": 2.95,
"learning_rate": 1.4537075927696375e-08,
"loss": 0.9729,
"step": 2304
},
{
"epoch": 2.95,
"learning_rate": 1.3801311761126868e-08,
"loss": 0.9212,
"step": 2305
},
{
"epoch": 2.95,
"learning_rate": 1.3084640992526708e-08,
"loss": 0.962,
"step": 2306
},
{
"epoch": 2.95,
"learning_rate": 1.2387064992154253e-08,
"loss": 1.0292,
"step": 2307
},
{
"epoch": 2.95,
"learning_rate": 1.1708585093759272e-08,
"loss": 0.9347,
"step": 2308
},
{
"epoch": 2.96,
"learning_rate": 1.1049202594581865e-08,
"loss": 0.919,
"step": 2309
},
{
"epoch": 2.96,
"learning_rate": 1.0408918755347996e-08,
"loss": 0.93,
"step": 2310
},
{
"epoch": 2.96,
"learning_rate": 9.78773480026396e-09,
"loss": 1.0261,
"step": 2311
},
{
"epoch": 2.96,
"learning_rate": 9.185651917023031e-09,
"loss": 0.9381,
"step": 2312
},
{
"epoch": 2.96,
"learning_rate": 8.60267125679215e-09,
"loss": 0.9209,
"step": 2313
},
{
"epoch": 2.96,
"learning_rate": 8.038793934220802e-09,
"loss": 0.9639,
"step": 2314
},
{
"epoch": 2.96,
"learning_rate": 7.494021027427689e-09,
"loss": 0.9684,
"step": 2315
},
{
"epoch": 2.96,
"learning_rate": 6.968353578007403e-09,
"loss": 0.955,
"step": 2316
},
{
"epoch": 2.97,
"learning_rate": 6.4617925910270825e-09,
"loss": 0.8382,
"step": 2317
},
{
"epoch": 2.97,
"learning_rate": 5.97433903501754e-09,
"loss": 0.9086,
"step": 2318
},
{
"epoch": 2.97,
"learning_rate": 5.505993841982138e-09,
"loss": 0.9283,
"step": 2319
},
{
"epoch": 2.97,
"learning_rate": 5.05675790738458e-09,
"loss": 0.9291,
"step": 2320
},
{
"epoch": 2.97,
"learning_rate": 4.62663209015557e-09,
"loss": 0.9277,
"step": 2321
},
{
"epoch": 2.97,
"learning_rate": 4.215617212686151e-09,
"loss": 0.8915,
"step": 2322
},
{
"epoch": 2.97,
"learning_rate": 3.8237140608277105e-09,
"loss": 0.965,
"step": 2323
},
{
"epoch": 2.97,
"learning_rate": 3.450923383891969e-09,
"loss": 0.9895,
"step": 2324
},
{
"epoch": 2.98,
"learning_rate": 3.0972458946454396e-09,
"loss": 0.8938,
"step": 2325
},
{
"epoch": 2.98,
"learning_rate": 2.762682269311645e-09,
"loss": 0.8063,
"step": 2326
},
{
"epoch": 2.98,
"learning_rate": 2.447233147570005e-09,
"loss": 0.9711,
"step": 2327
},
{
"epoch": 2.98,
"learning_rate": 2.1508991325525087e-09,
"loss": 1.048,
"step": 2328
},
{
"epoch": 2.98,
"learning_rate": 1.8736807908426027e-09,
"loss": 0.9388,
"step": 2329
},
{
"epoch": 2.98,
"learning_rate": 1.6155786524763018e-09,
"loss": 0.983,
"step": 2330
},
{
"epoch": 2.98,
"learning_rate": 1.376593210938859e-09,
"loss": 0.9322,
"step": 2331
},
{
"epoch": 2.98,
"learning_rate": 1.156724923165875e-09,
"loss": 0.972,
"step": 2332
},
{
"epoch": 2.99,
"learning_rate": 9.559742095410774e-10,
"loss": 0.9069,
"step": 2333
},
{
"epoch": 2.99,
"learning_rate": 7.74341453895211e-10,
"loss": 1.0329,
"step": 2334
},
{
"epoch": 2.99,
"learning_rate": 6.118270035071483e-10,
"loss": 1.0599,
"step": 2335
},
{
"epoch": 2.99,
"learning_rate": 4.684311690983378e-10,
"loss": 0.9053,
"step": 2336
},
{
"epoch": 2.99,
"learning_rate": 3.4415422484168626e-10,
"loss": 0.9449,
"step": 2337
},
{
"epoch": 2.99,
"learning_rate": 2.3899640834934567e-10,
"loss": 0.8478,
"step": 2338
},
{
"epoch": 2.99,
"learning_rate": 1.5295792068270586e-10,
"loss": 0.8927,
"step": 2339
},
{
"epoch": 3.0,
"learning_rate": 8.603892634462263e-11,
"loss": 0.9631,
"step": 2340
},
{
"epoch": 3.0,
"learning_rate": 3.823955328385864e-11,
"loss": 0.9813,
"step": 2341
},
{
"epoch": 3.0,
"learning_rate": 9.559892890642631e-12,
"loss": 0.8734,
"step": 2342
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 1.0041,
"step": 2343
},
{
"epoch": 3.0,
"step": 2343,
"total_flos": 1.4406392337976525e+18,
"train_loss": 1.2288865842882304,
"train_runtime": 12734.9896,
"train_samples_per_second": 47.114,
"train_steps_per_second": 0.184
}
],
"max_steps": 2343,
"num_train_epochs": 3,
"total_flos": 1.4406392337976525e+18,
"trial_name": null,
"trial_params": null
}