Wanfq's picture
Upload folder using huggingface_hub
872551c verified
raw
history blame
No virus
88.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9993238674780257,
"eval_steps": 500,
"global_step": 739,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 7.462686567164179e-08,
"loss": 0.5723,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.4925373134328358e-07,
"loss": 0.5898,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 2.2388059701492537e-07,
"loss": 0.5941,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 2.9850746268656716e-07,
"loss": 0.5597,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 3.7313432835820895e-07,
"loss": 0.6111,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 4.4776119402985074e-07,
"loss": 0.6161,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 5.223880597014925e-07,
"loss": 0.7085,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 5.970149253731343e-07,
"loss": 0.5875,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 6.716417910447762e-07,
"loss": 0.6192,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 7.462686567164179e-07,
"loss": 0.5381,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 8.208955223880598e-07,
"loss": 0.6413,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 8.955223880597015e-07,
"loss": 0.5766,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 9.701492537313434e-07,
"loss": 0.6559,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 1.044776119402985e-06,
"loss": 0.491,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 1.119402985074627e-06,
"loss": 0.6057,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1.1940298507462686e-06,
"loss": 0.5614,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 1.2686567164179105e-06,
"loss": 0.5187,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 1.3432835820895524e-06,
"loss": 0.5996,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 1.417910447761194e-06,
"loss": 0.6014,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 1.4925373134328358e-06,
"loss": 0.6026,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 1.5671641791044779e-06,
"loss": 0.5059,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 1.6417910447761196e-06,
"loss": 0.6132,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 1.7164179104477613e-06,
"loss": 0.5594,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 1.791044776119403e-06,
"loss": 0.5835,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 1.865671641791045e-06,
"loss": 0.5352,
"step": 25
},
{
"epoch": 0.04,
"learning_rate": 1.9402985074626867e-06,
"loss": 0.5394,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 2.0149253731343284e-06,
"loss": 0.5654,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 2.08955223880597e-06,
"loss": 0.5662,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 2.1641791044776118e-06,
"loss": 0.5692,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 2.238805970149254e-06,
"loss": 0.5674,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 2.3134328358208956e-06,
"loss": 0.5437,
"step": 31
},
{
"epoch": 0.04,
"learning_rate": 2.3880597014925373e-06,
"loss": 0.5255,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 2.4626865671641794e-06,
"loss": 0.6014,
"step": 33
},
{
"epoch": 0.05,
"learning_rate": 2.537313432835821e-06,
"loss": 0.5777,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 2.6119402985074627e-06,
"loss": 0.6171,
"step": 35
},
{
"epoch": 0.05,
"learning_rate": 2.686567164179105e-06,
"loss": 0.5708,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 2.7611940298507465e-06,
"loss": 0.5315,
"step": 37
},
{
"epoch": 0.05,
"learning_rate": 2.835820895522388e-06,
"loss": 0.542,
"step": 38
},
{
"epoch": 0.05,
"learning_rate": 2.9104477611940303e-06,
"loss": 0.5312,
"step": 39
},
{
"epoch": 0.05,
"learning_rate": 2.9850746268656716e-06,
"loss": 0.557,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 3.0597014925373137e-06,
"loss": 0.5327,
"step": 41
},
{
"epoch": 0.06,
"learning_rate": 3.1343283582089558e-06,
"loss": 0.4807,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 3.208955223880597e-06,
"loss": 0.5238,
"step": 43
},
{
"epoch": 0.06,
"learning_rate": 3.283582089552239e-06,
"loss": 0.567,
"step": 44
},
{
"epoch": 0.06,
"learning_rate": 3.3582089552238813e-06,
"loss": 0.5313,
"step": 45
},
{
"epoch": 0.06,
"learning_rate": 3.4328358208955225e-06,
"loss": 0.574,
"step": 46
},
{
"epoch": 0.06,
"learning_rate": 3.5074626865671646e-06,
"loss": 0.6066,
"step": 47
},
{
"epoch": 0.06,
"learning_rate": 3.582089552238806e-06,
"loss": 0.5488,
"step": 48
},
{
"epoch": 0.07,
"learning_rate": 3.656716417910448e-06,
"loss": 0.6535,
"step": 49
},
{
"epoch": 0.07,
"learning_rate": 3.73134328358209e-06,
"loss": 0.4827,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 3.8059701492537314e-06,
"loss": 0.5727,
"step": 51
},
{
"epoch": 0.07,
"learning_rate": 3.8805970149253735e-06,
"loss": 0.5488,
"step": 52
},
{
"epoch": 0.07,
"learning_rate": 3.955223880597015e-06,
"loss": 0.5498,
"step": 53
},
{
"epoch": 0.07,
"learning_rate": 4.029850746268657e-06,
"loss": 0.5451,
"step": 54
},
{
"epoch": 0.07,
"learning_rate": 4.104477611940299e-06,
"loss": 0.6094,
"step": 55
},
{
"epoch": 0.08,
"learning_rate": 4.17910447761194e-06,
"loss": 0.5319,
"step": 56
},
{
"epoch": 0.08,
"learning_rate": 4.253731343283583e-06,
"loss": 0.5696,
"step": 57
},
{
"epoch": 0.08,
"learning_rate": 4.3283582089552236e-06,
"loss": 0.5584,
"step": 58
},
{
"epoch": 0.08,
"learning_rate": 4.402985074626866e-06,
"loss": 0.5377,
"step": 59
},
{
"epoch": 0.08,
"learning_rate": 4.477611940298508e-06,
"loss": 0.5801,
"step": 60
},
{
"epoch": 0.08,
"learning_rate": 4.5522388059701495e-06,
"loss": 0.4883,
"step": 61
},
{
"epoch": 0.08,
"learning_rate": 4.626865671641791e-06,
"loss": 0.5792,
"step": 62
},
{
"epoch": 0.09,
"learning_rate": 4.701492537313434e-06,
"loss": 0.5722,
"step": 63
},
{
"epoch": 0.09,
"learning_rate": 4.7761194029850745e-06,
"loss": 0.5002,
"step": 64
},
{
"epoch": 0.09,
"learning_rate": 4.850746268656717e-06,
"loss": 0.5625,
"step": 65
},
{
"epoch": 0.09,
"learning_rate": 4.925373134328359e-06,
"loss": 0.5912,
"step": 66
},
{
"epoch": 0.09,
"learning_rate": 5e-06,
"loss": 0.4893,
"step": 67
},
{
"epoch": 0.09,
"learning_rate": 4.999997331097176e-06,
"loss": 0.4961,
"step": 68
},
{
"epoch": 0.09,
"learning_rate": 4.999989324394401e-06,
"loss": 0.5578,
"step": 69
},
{
"epoch": 0.09,
"learning_rate": 4.99997597990877e-06,
"loss": 0.5136,
"step": 70
},
{
"epoch": 0.1,
"learning_rate": 4.999957297668777e-06,
"loss": 0.54,
"step": 71
},
{
"epoch": 0.1,
"learning_rate": 4.999933277714309e-06,
"loss": 0.5485,
"step": 72
},
{
"epoch": 0.1,
"learning_rate": 4.999903920096652e-06,
"loss": 0.5497,
"step": 73
},
{
"epoch": 0.1,
"learning_rate": 4.999869224878489e-06,
"loss": 0.5892,
"step": 74
},
{
"epoch": 0.1,
"learning_rate": 4.999829192133897e-06,
"loss": 0.4547,
"step": 75
},
{
"epoch": 0.1,
"learning_rate": 4.999783821948353e-06,
"loss": 0.5276,
"step": 76
},
{
"epoch": 0.1,
"learning_rate": 4.999733114418726e-06,
"loss": 0.581,
"step": 77
},
{
"epoch": 0.11,
"learning_rate": 4.999677069653283e-06,
"loss": 0.5578,
"step": 78
},
{
"epoch": 0.11,
"learning_rate": 4.999615687771687e-06,
"loss": 0.5679,
"step": 79
},
{
"epoch": 0.11,
"learning_rate": 4.9995489689049945e-06,
"loss": 0.5326,
"step": 80
},
{
"epoch": 0.11,
"learning_rate": 4.999476913195661e-06,
"loss": 0.5328,
"step": 81
},
{
"epoch": 0.11,
"learning_rate": 4.999399520797532e-06,
"loss": 0.5417,
"step": 82
},
{
"epoch": 0.11,
"learning_rate": 4.999316791875851e-06,
"loss": 0.5452,
"step": 83
},
{
"epoch": 0.11,
"learning_rate": 4.999228726607254e-06,
"loss": 0.5813,
"step": 84
},
{
"epoch": 0.11,
"learning_rate": 4.99913532517977e-06,
"loss": 0.5286,
"step": 85
},
{
"epoch": 0.12,
"learning_rate": 4.999036587792824e-06,
"loss": 0.6073,
"step": 86
},
{
"epoch": 0.12,
"learning_rate": 4.998932514657232e-06,
"loss": 0.5865,
"step": 87
},
{
"epoch": 0.12,
"learning_rate": 4.998823105995203e-06,
"loss": 0.4725,
"step": 88
},
{
"epoch": 0.12,
"learning_rate": 4.998708362040336e-06,
"loss": 0.5317,
"step": 89
},
{
"epoch": 0.12,
"learning_rate": 4.998588283037627e-06,
"loss": 0.6672,
"step": 90
},
{
"epoch": 0.12,
"learning_rate": 4.998462869243456e-06,
"loss": 0.6114,
"step": 91
},
{
"epoch": 0.12,
"learning_rate": 4.998332120925598e-06,
"loss": 0.5919,
"step": 92
},
{
"epoch": 0.13,
"learning_rate": 4.998196038363218e-06,
"loss": 0.6296,
"step": 93
},
{
"epoch": 0.13,
"learning_rate": 4.998054621846867e-06,
"loss": 0.4895,
"step": 94
},
{
"epoch": 0.13,
"learning_rate": 4.997907871678486e-06,
"loss": 0.5374,
"step": 95
},
{
"epoch": 0.13,
"learning_rate": 4.997755788171408e-06,
"loss": 0.519,
"step": 96
},
{
"epoch": 0.13,
"learning_rate": 4.997598371650346e-06,
"loss": 0.5333,
"step": 97
},
{
"epoch": 0.13,
"learning_rate": 4.9974356224514055e-06,
"loss": 0.568,
"step": 98
},
{
"epoch": 0.13,
"learning_rate": 4.997267540922076e-06,
"loss": 0.5145,
"step": 99
},
{
"epoch": 0.14,
"learning_rate": 4.997094127421231e-06,
"loss": 0.5509,
"step": 100
},
{
"epoch": 0.14,
"learning_rate": 4.996915382319131e-06,
"loss": 0.5459,
"step": 101
},
{
"epoch": 0.14,
"learning_rate": 4.996731305997416e-06,
"loss": 0.5415,
"step": 102
},
{
"epoch": 0.14,
"learning_rate": 4.9965418988491155e-06,
"loss": 0.4955,
"step": 103
},
{
"epoch": 0.14,
"learning_rate": 4.996347161278634e-06,
"loss": 0.5714,
"step": 104
},
{
"epoch": 0.14,
"learning_rate": 4.996147093701761e-06,
"loss": 0.522,
"step": 105
},
{
"epoch": 0.14,
"learning_rate": 4.995941696545664e-06,
"loss": 0.5644,
"step": 106
},
{
"epoch": 0.14,
"learning_rate": 4.995730970248893e-06,
"loss": 0.5042,
"step": 107
},
{
"epoch": 0.15,
"learning_rate": 4.995514915261373e-06,
"loss": 0.5308,
"step": 108
},
{
"epoch": 0.15,
"learning_rate": 4.995293532044408e-06,
"loss": 0.5566,
"step": 109
},
{
"epoch": 0.15,
"learning_rate": 4.9950668210706795e-06,
"loss": 0.5809,
"step": 110
},
{
"epoch": 0.15,
"learning_rate": 4.994834782824242e-06,
"loss": 0.5435,
"step": 111
},
{
"epoch": 0.15,
"learning_rate": 4.994597417800524e-06,
"loss": 0.5939,
"step": 112
},
{
"epoch": 0.15,
"learning_rate": 4.994354726506332e-06,
"loss": 0.6213,
"step": 113
},
{
"epoch": 0.15,
"learning_rate": 4.99410670945984e-06,
"loss": 0.5454,
"step": 114
},
{
"epoch": 0.16,
"learning_rate": 4.993853367190594e-06,
"loss": 0.6089,
"step": 115
},
{
"epoch": 0.16,
"learning_rate": 4.993594700239513e-06,
"loss": 0.5731,
"step": 116
},
{
"epoch": 0.16,
"learning_rate": 4.993330709158879e-06,
"loss": 0.5587,
"step": 117
},
{
"epoch": 0.16,
"learning_rate": 4.993061394512349e-06,
"loss": 0.4962,
"step": 118
},
{
"epoch": 0.16,
"learning_rate": 4.992786756874941e-06,
"loss": 0.579,
"step": 119
},
{
"epoch": 0.16,
"learning_rate": 4.992506796833039e-06,
"loss": 0.522,
"step": 120
},
{
"epoch": 0.16,
"learning_rate": 4.992221514984393e-06,
"loss": 0.573,
"step": 121
},
{
"epoch": 0.16,
"learning_rate": 4.991930911938116e-06,
"loss": 0.5549,
"step": 122
},
{
"epoch": 0.17,
"learning_rate": 4.991634988314678e-06,
"loss": 0.5559,
"step": 123
},
{
"epoch": 0.17,
"learning_rate": 4.991333744745913e-06,
"loss": 0.5089,
"step": 124
},
{
"epoch": 0.17,
"learning_rate": 4.991027181875014e-06,
"loss": 0.5516,
"step": 125
},
{
"epoch": 0.17,
"learning_rate": 4.990715300356531e-06,
"loss": 0.5755,
"step": 126
},
{
"epoch": 0.17,
"learning_rate": 4.990398100856367e-06,
"loss": 0.5802,
"step": 127
},
{
"epoch": 0.17,
"learning_rate": 4.990075584051782e-06,
"loss": 0.5094,
"step": 128
},
{
"epoch": 0.17,
"learning_rate": 4.989747750631391e-06,
"loss": 0.5289,
"step": 129
},
{
"epoch": 0.18,
"learning_rate": 4.989414601295155e-06,
"loss": 0.575,
"step": 130
},
{
"epoch": 0.18,
"learning_rate": 4.989076136754391e-06,
"loss": 0.5425,
"step": 131
},
{
"epoch": 0.18,
"learning_rate": 4.9887323577317625e-06,
"loss": 0.5186,
"step": 132
},
{
"epoch": 0.18,
"learning_rate": 4.988383264961278e-06,
"loss": 0.4857,
"step": 133
},
{
"epoch": 0.18,
"learning_rate": 4.988028859188294e-06,
"loss": 0.5197,
"step": 134
},
{
"epoch": 0.18,
"learning_rate": 4.98766914116951e-06,
"loss": 0.5208,
"step": 135
},
{
"epoch": 0.18,
"learning_rate": 4.987304111672969e-06,
"loss": 0.584,
"step": 136
},
{
"epoch": 0.19,
"learning_rate": 4.986933771478052e-06,
"loss": 0.5564,
"step": 137
},
{
"epoch": 0.19,
"learning_rate": 4.986558121375482e-06,
"loss": 0.601,
"step": 138
},
{
"epoch": 0.19,
"learning_rate": 4.986177162167317e-06,
"loss": 0.5413,
"step": 139
},
{
"epoch": 0.19,
"learning_rate": 4.985790894666951e-06,
"loss": 0.5669,
"step": 140
},
{
"epoch": 0.19,
"learning_rate": 4.985399319699114e-06,
"loss": 0.5588,
"step": 141
},
{
"epoch": 0.19,
"learning_rate": 4.9850024380998655e-06,
"loss": 0.5499,
"step": 142
},
{
"epoch": 0.19,
"learning_rate": 4.984600250716596e-06,
"loss": 0.51,
"step": 143
},
{
"epoch": 0.19,
"learning_rate": 4.984192758408025e-06,
"loss": 0.5417,
"step": 144
},
{
"epoch": 0.2,
"learning_rate": 4.983779962044198e-06,
"loss": 0.5051,
"step": 145
},
{
"epoch": 0.2,
"learning_rate": 4.983361862506486e-06,
"loss": 0.5727,
"step": 146
},
{
"epoch": 0.2,
"learning_rate": 4.982938460687583e-06,
"loss": 0.5471,
"step": 147
},
{
"epoch": 0.2,
"learning_rate": 4.9825097574915034e-06,
"loss": 0.5174,
"step": 148
},
{
"epoch": 0.2,
"learning_rate": 4.982075753833581e-06,
"loss": 0.5103,
"step": 149
},
{
"epoch": 0.2,
"learning_rate": 4.981636450640467e-06,
"loss": 0.5282,
"step": 150
},
{
"epoch": 0.2,
"learning_rate": 4.981191848850126e-06,
"loss": 0.528,
"step": 151
},
{
"epoch": 0.21,
"learning_rate": 4.980741949411839e-06,
"loss": 0.5371,
"step": 152
},
{
"epoch": 0.21,
"learning_rate": 4.980286753286196e-06,
"loss": 0.5602,
"step": 153
},
{
"epoch": 0.21,
"learning_rate": 4.979826261445094e-06,
"loss": 0.5387,
"step": 154
},
{
"epoch": 0.21,
"learning_rate": 4.979360474871742e-06,
"loss": 0.5186,
"step": 155
},
{
"epoch": 0.21,
"learning_rate": 4.978889394560651e-06,
"loss": 0.5147,
"step": 156
},
{
"epoch": 0.21,
"learning_rate": 4.978413021517634e-06,
"loss": 0.5739,
"step": 157
},
{
"epoch": 0.21,
"learning_rate": 4.977931356759806e-06,
"loss": 0.5979,
"step": 158
},
{
"epoch": 0.22,
"learning_rate": 4.977444401315582e-06,
"loss": 0.5119,
"step": 159
},
{
"epoch": 0.22,
"learning_rate": 4.976952156224668e-06,
"loss": 0.5448,
"step": 160
},
{
"epoch": 0.22,
"learning_rate": 4.9764546225380705e-06,
"loss": 0.5357,
"step": 161
},
{
"epoch": 0.22,
"learning_rate": 4.975951801318083e-06,
"loss": 0.5807,
"step": 162
},
{
"epoch": 0.22,
"learning_rate": 4.975443693638291e-06,
"loss": 0.506,
"step": 163
},
{
"epoch": 0.22,
"learning_rate": 4.9749303005835665e-06,
"loss": 0.6144,
"step": 164
},
{
"epoch": 0.22,
"learning_rate": 4.974411623250066e-06,
"loss": 0.5998,
"step": 165
},
{
"epoch": 0.22,
"learning_rate": 4.973887662745229e-06,
"loss": 0.5098,
"step": 166
},
{
"epoch": 0.23,
"learning_rate": 4.973358420187776e-06,
"loss": 0.4893,
"step": 167
},
{
"epoch": 0.23,
"learning_rate": 4.972823896707704e-06,
"loss": 0.536,
"step": 168
},
{
"epoch": 0.23,
"learning_rate": 4.972284093446286e-06,
"loss": 0.5678,
"step": 169
},
{
"epoch": 0.23,
"learning_rate": 4.971739011556067e-06,
"loss": 0.5409,
"step": 170
},
{
"epoch": 0.23,
"learning_rate": 4.971188652200865e-06,
"loss": 0.545,
"step": 171
},
{
"epoch": 0.23,
"learning_rate": 4.970633016555765e-06,
"loss": 0.4984,
"step": 172
},
{
"epoch": 0.23,
"learning_rate": 4.970072105807116e-06,
"loss": 0.5222,
"step": 173
},
{
"epoch": 0.24,
"learning_rate": 4.9695059211525305e-06,
"loss": 0.5707,
"step": 174
},
{
"epoch": 0.24,
"learning_rate": 4.9689344638008825e-06,
"loss": 0.4643,
"step": 175
},
{
"epoch": 0.24,
"learning_rate": 4.968357734972303e-06,
"loss": 0.5295,
"step": 176
},
{
"epoch": 0.24,
"learning_rate": 4.967775735898179e-06,
"loss": 0.5632,
"step": 177
},
{
"epoch": 0.24,
"learning_rate": 4.96718846782115e-06,
"loss": 0.4858,
"step": 178
},
{
"epoch": 0.24,
"learning_rate": 4.966595931995105e-06,
"loss": 0.4931,
"step": 179
},
{
"epoch": 0.24,
"learning_rate": 4.965998129685179e-06,
"loss": 0.6,
"step": 180
},
{
"epoch": 0.24,
"learning_rate": 4.965395062167756e-06,
"loss": 0.5547,
"step": 181
},
{
"epoch": 0.25,
"learning_rate": 4.964786730730455e-06,
"loss": 0.6046,
"step": 182
},
{
"epoch": 0.25,
"learning_rate": 4.964173136672142e-06,
"loss": 0.5429,
"step": 183
},
{
"epoch": 0.25,
"learning_rate": 4.9635542813029115e-06,
"loss": 0.5641,
"step": 184
},
{
"epoch": 0.25,
"learning_rate": 4.962930165944098e-06,
"loss": 0.5257,
"step": 185
},
{
"epoch": 0.25,
"learning_rate": 4.962300791928263e-06,
"loss": 0.5445,
"step": 186
},
{
"epoch": 0.25,
"learning_rate": 4.961666160599198e-06,
"loss": 0.5309,
"step": 187
},
{
"epoch": 0.25,
"learning_rate": 4.961026273311918e-06,
"loss": 0.5063,
"step": 188
},
{
"epoch": 0.26,
"learning_rate": 4.96038113143266e-06,
"loss": 0.5993,
"step": 189
},
{
"epoch": 0.26,
"learning_rate": 4.95973073633888e-06,
"loss": 0.6167,
"step": 190
},
{
"epoch": 0.26,
"learning_rate": 4.9590750894192545e-06,
"loss": 0.5163,
"step": 191
},
{
"epoch": 0.26,
"learning_rate": 4.958414192073665e-06,
"loss": 0.5246,
"step": 192
},
{
"epoch": 0.26,
"learning_rate": 4.9577480457132124e-06,
"loss": 0.5354,
"step": 193
},
{
"epoch": 0.26,
"learning_rate": 4.957076651760199e-06,
"loss": 0.5212,
"step": 194
},
{
"epoch": 0.26,
"learning_rate": 4.956400011648132e-06,
"loss": 0.5623,
"step": 195
},
{
"epoch": 0.27,
"learning_rate": 4.9557181268217225e-06,
"loss": 0.5248,
"step": 196
},
{
"epoch": 0.27,
"learning_rate": 4.955030998736876e-06,
"loss": 0.5417,
"step": 197
},
{
"epoch": 0.27,
"learning_rate": 4.9543386288606965e-06,
"loss": 0.4593,
"step": 198
},
{
"epoch": 0.27,
"learning_rate": 4.953641018671478e-06,
"loss": 0.58,
"step": 199
},
{
"epoch": 0.27,
"learning_rate": 4.952938169658704e-06,
"loss": 0.5473,
"step": 200
},
{
"epoch": 0.27,
"learning_rate": 4.952230083323042e-06,
"loss": 0.4963,
"step": 201
},
{
"epoch": 0.27,
"learning_rate": 4.951516761176344e-06,
"loss": 0.5247,
"step": 202
},
{
"epoch": 0.27,
"learning_rate": 4.950798204741638e-06,
"loss": 0.4554,
"step": 203
},
{
"epoch": 0.28,
"learning_rate": 4.950074415553133e-06,
"loss": 0.6034,
"step": 204
},
{
"epoch": 0.28,
"learning_rate": 4.9493453951562045e-06,
"loss": 0.5263,
"step": 205
},
{
"epoch": 0.28,
"learning_rate": 4.948611145107402e-06,
"loss": 0.4951,
"step": 206
},
{
"epoch": 0.28,
"learning_rate": 4.947871666974438e-06,
"loss": 0.5475,
"step": 207
},
{
"epoch": 0.28,
"learning_rate": 4.94712696233619e-06,
"loss": 0.5289,
"step": 208
},
{
"epoch": 0.28,
"learning_rate": 4.946377032782691e-06,
"loss": 0.4872,
"step": 209
},
{
"epoch": 0.28,
"learning_rate": 4.945621879915135e-06,
"loss": 0.5051,
"step": 210
},
{
"epoch": 0.29,
"learning_rate": 4.944861505345865e-06,
"loss": 0.5666,
"step": 211
},
{
"epoch": 0.29,
"learning_rate": 4.944095910698372e-06,
"loss": 0.4618,
"step": 212
},
{
"epoch": 0.29,
"learning_rate": 4.943325097607297e-06,
"loss": 0.4812,
"step": 213
},
{
"epoch": 0.29,
"learning_rate": 4.942549067718418e-06,
"loss": 0.5014,
"step": 214
},
{
"epoch": 0.29,
"learning_rate": 4.941767822688653e-06,
"loss": 0.6175,
"step": 215
},
{
"epoch": 0.29,
"learning_rate": 4.94098136418606e-06,
"loss": 0.5236,
"step": 216
},
{
"epoch": 0.29,
"learning_rate": 4.940189693889819e-06,
"loss": 0.569,
"step": 217
},
{
"epoch": 0.29,
"learning_rate": 4.939392813490245e-06,
"loss": 0.5225,
"step": 218
},
{
"epoch": 0.3,
"learning_rate": 4.938590724688774e-06,
"loss": 0.5039,
"step": 219
},
{
"epoch": 0.3,
"learning_rate": 4.937783429197966e-06,
"loss": 0.4852,
"step": 220
},
{
"epoch": 0.3,
"learning_rate": 4.936970928741494e-06,
"loss": 0.526,
"step": 221
},
{
"epoch": 0.3,
"learning_rate": 4.936153225054147e-06,
"loss": 0.5719,
"step": 222
},
{
"epoch": 0.3,
"learning_rate": 4.93533031988182e-06,
"loss": 0.4858,
"step": 223
},
{
"epoch": 0.3,
"learning_rate": 4.934502214981518e-06,
"loss": 0.5288,
"step": 224
},
{
"epoch": 0.3,
"learning_rate": 4.933668912121346e-06,
"loss": 0.4955,
"step": 225
},
{
"epoch": 0.31,
"learning_rate": 4.932830413080507e-06,
"loss": 0.561,
"step": 226
},
{
"epoch": 0.31,
"learning_rate": 4.931986719649298e-06,
"loss": 0.4796,
"step": 227
},
{
"epoch": 0.31,
"learning_rate": 4.931137833629111e-06,
"loss": 0.6016,
"step": 228
},
{
"epoch": 0.31,
"learning_rate": 4.930283756832418e-06,
"loss": 0.576,
"step": 229
},
{
"epoch": 0.31,
"learning_rate": 4.9294244910827795e-06,
"loss": 0.5279,
"step": 230
},
{
"epoch": 0.31,
"learning_rate": 4.928560038214831e-06,
"loss": 0.4913,
"step": 231
},
{
"epoch": 0.31,
"learning_rate": 4.927690400074287e-06,
"loss": 0.5777,
"step": 232
},
{
"epoch": 0.32,
"learning_rate": 4.92681557851793e-06,
"loss": 0.5346,
"step": 233
},
{
"epoch": 0.32,
"learning_rate": 4.925935575413611e-06,
"loss": 0.5679,
"step": 234
},
{
"epoch": 0.32,
"learning_rate": 4.925050392640245e-06,
"loss": 0.5291,
"step": 235
},
{
"epoch": 0.32,
"learning_rate": 4.924160032087804e-06,
"loss": 0.5569,
"step": 236
},
{
"epoch": 0.32,
"learning_rate": 4.923264495657319e-06,
"loss": 0.5389,
"step": 237
},
{
"epoch": 0.32,
"learning_rate": 4.922363785260868e-06,
"loss": 0.5375,
"step": 238
},
{
"epoch": 0.32,
"learning_rate": 4.921457902821578e-06,
"loss": 0.5515,
"step": 239
},
{
"epoch": 0.32,
"learning_rate": 4.920546850273619e-06,
"loss": 0.5702,
"step": 240
},
{
"epoch": 0.33,
"learning_rate": 4.9196306295622e-06,
"loss": 0.5032,
"step": 241
},
{
"epoch": 0.33,
"learning_rate": 4.918709242643563e-06,
"loss": 0.4834,
"step": 242
},
{
"epoch": 0.33,
"learning_rate": 4.917782691484984e-06,
"loss": 0.5656,
"step": 243
},
{
"epoch": 0.33,
"learning_rate": 4.91685097806476e-06,
"loss": 0.541,
"step": 244
},
{
"epoch": 0.33,
"learning_rate": 4.915914104372215e-06,
"loss": 0.5613,
"step": 245
},
{
"epoch": 0.33,
"learning_rate": 4.914972072407689e-06,
"loss": 0.5118,
"step": 246
},
{
"epoch": 0.33,
"learning_rate": 4.914024884182535e-06,
"loss": 0.5014,
"step": 247
},
{
"epoch": 0.34,
"learning_rate": 4.913072541719115e-06,
"loss": 0.5695,
"step": 248
},
{
"epoch": 0.34,
"learning_rate": 4.912115047050796e-06,
"loss": 0.453,
"step": 249
},
{
"epoch": 0.34,
"learning_rate": 4.911152402221949e-06,
"loss": 0.5311,
"step": 250
},
{
"epoch": 0.34,
"learning_rate": 4.910184609287936e-06,
"loss": 0.523,
"step": 251
},
{
"epoch": 0.34,
"learning_rate": 4.909211670315115e-06,
"loss": 0.4906,
"step": 252
},
{
"epoch": 0.34,
"learning_rate": 4.9082335873808275e-06,
"loss": 0.5043,
"step": 253
},
{
"epoch": 0.34,
"learning_rate": 4.907250362573401e-06,
"loss": 0.4983,
"step": 254
},
{
"epoch": 0.34,
"learning_rate": 4.906261997992141e-06,
"loss": 0.4582,
"step": 255
},
{
"epoch": 0.35,
"learning_rate": 4.905268495747327e-06,
"loss": 0.5149,
"step": 256
},
{
"epoch": 0.35,
"learning_rate": 4.904269857960208e-06,
"loss": 0.6121,
"step": 257
},
{
"epoch": 0.35,
"learning_rate": 4.903266086762996e-06,
"loss": 0.6032,
"step": 258
},
{
"epoch": 0.35,
"learning_rate": 4.902257184298867e-06,
"loss": 0.5694,
"step": 259
},
{
"epoch": 0.35,
"learning_rate": 4.901243152721952e-06,
"loss": 0.4777,
"step": 260
},
{
"epoch": 0.35,
"learning_rate": 4.900223994197329e-06,
"loss": 0.5508,
"step": 261
},
{
"epoch": 0.35,
"learning_rate": 4.899199710901028e-06,
"loss": 0.4939,
"step": 262
},
{
"epoch": 0.36,
"learning_rate": 4.89817030502002e-06,
"loss": 0.5684,
"step": 263
},
{
"epoch": 0.36,
"learning_rate": 4.89713577875221e-06,
"loss": 0.532,
"step": 264
},
{
"epoch": 0.36,
"learning_rate": 4.896096134306441e-06,
"loss": 0.4807,
"step": 265
},
{
"epoch": 0.36,
"learning_rate": 4.8950513739024785e-06,
"loss": 0.5145,
"step": 266
},
{
"epoch": 0.36,
"learning_rate": 4.894001499771015e-06,
"loss": 0.5344,
"step": 267
},
{
"epoch": 0.36,
"learning_rate": 4.89294651415366e-06,
"loss": 0.5211,
"step": 268
},
{
"epoch": 0.36,
"learning_rate": 4.891886419302937e-06,
"loss": 0.6224,
"step": 269
},
{
"epoch": 0.37,
"learning_rate": 4.890821217482277e-06,
"loss": 0.5013,
"step": 270
},
{
"epoch": 0.37,
"learning_rate": 4.889750910966017e-06,
"loss": 0.4878,
"step": 271
},
{
"epoch": 0.37,
"learning_rate": 4.888675502039392e-06,
"loss": 0.5432,
"step": 272
},
{
"epoch": 0.37,
"learning_rate": 4.887594992998531e-06,
"loss": 0.5336,
"step": 273
},
{
"epoch": 0.37,
"learning_rate": 4.886509386150454e-06,
"loss": 0.52,
"step": 274
},
{
"epoch": 0.37,
"learning_rate": 4.885418683813064e-06,
"loss": 0.4961,
"step": 275
},
{
"epoch": 0.37,
"learning_rate": 4.8843228883151445e-06,
"loss": 0.5404,
"step": 276
},
{
"epoch": 0.37,
"learning_rate": 4.883222001996352e-06,
"loss": 0.6198,
"step": 277
},
{
"epoch": 0.38,
"learning_rate": 4.882116027207212e-06,
"loss": 0.6363,
"step": 278
},
{
"epoch": 0.38,
"learning_rate": 4.881004966309119e-06,
"loss": 0.5244,
"step": 279
},
{
"epoch": 0.38,
"learning_rate": 4.879888821674321e-06,
"loss": 0.5074,
"step": 280
},
{
"epoch": 0.38,
"learning_rate": 4.878767595685925e-06,
"loss": 0.5203,
"step": 281
},
{
"epoch": 0.38,
"learning_rate": 4.8776412907378845e-06,
"loss": 0.5313,
"step": 282
},
{
"epoch": 0.38,
"learning_rate": 4.876509909234999e-06,
"loss": 0.487,
"step": 283
},
{
"epoch": 0.38,
"learning_rate": 4.875373453592906e-06,
"loss": 0.6121,
"step": 284
},
{
"epoch": 0.39,
"learning_rate": 4.874231926238078e-06,
"loss": 0.5268,
"step": 285
},
{
"epoch": 0.39,
"learning_rate": 4.873085329607814e-06,
"loss": 0.5913,
"step": 286
},
{
"epoch": 0.39,
"learning_rate": 4.871933666150239e-06,
"loss": 0.5683,
"step": 287
},
{
"epoch": 0.39,
"learning_rate": 4.870776938324296e-06,
"loss": 0.5411,
"step": 288
},
{
"epoch": 0.39,
"learning_rate": 4.8696151485997385e-06,
"loss": 0.5568,
"step": 289
},
{
"epoch": 0.39,
"learning_rate": 4.868448299457132e-06,
"loss": 0.4782,
"step": 290
},
{
"epoch": 0.39,
"learning_rate": 4.867276393387839e-06,
"loss": 0.5365,
"step": 291
},
{
"epoch": 0.39,
"learning_rate": 4.866099432894023e-06,
"loss": 0.5094,
"step": 292
},
{
"epoch": 0.4,
"learning_rate": 4.864917420488642e-06,
"loss": 0.5062,
"step": 293
},
{
"epoch": 0.4,
"learning_rate": 4.863730358695433e-06,
"loss": 0.5477,
"step": 294
},
{
"epoch": 0.4,
"learning_rate": 4.86253825004892e-06,
"loss": 0.5736,
"step": 295
},
{
"epoch": 0.4,
"learning_rate": 4.861341097094398e-06,
"loss": 0.5324,
"step": 296
},
{
"epoch": 0.4,
"learning_rate": 4.8601389023879395e-06,
"loss": 0.5694,
"step": 297
},
{
"epoch": 0.4,
"learning_rate": 4.858931668496374e-06,
"loss": 0.5597,
"step": 298
},
{
"epoch": 0.4,
"learning_rate": 4.857719397997293e-06,
"loss": 0.5408,
"step": 299
},
{
"epoch": 0.41,
"learning_rate": 4.856502093479046e-06,
"loss": 0.5923,
"step": 300
},
{
"epoch": 0.41,
"learning_rate": 4.855279757540723e-06,
"loss": 0.5477,
"step": 301
},
{
"epoch": 0.41,
"learning_rate": 4.854052392792162e-06,
"loss": 0.6408,
"step": 302
},
{
"epoch": 0.41,
"learning_rate": 4.852820001853937e-06,
"loss": 0.4951,
"step": 303
},
{
"epoch": 0.41,
"learning_rate": 4.851582587357353e-06,
"loss": 0.4661,
"step": 304
},
{
"epoch": 0.41,
"learning_rate": 4.850340151944441e-06,
"loss": 0.5234,
"step": 305
},
{
"epoch": 0.41,
"learning_rate": 4.849092698267954e-06,
"loss": 0.548,
"step": 306
},
{
"epoch": 0.42,
"learning_rate": 4.8478402289913566e-06,
"loss": 0.5597,
"step": 307
},
{
"epoch": 0.42,
"learning_rate": 4.846582746788824e-06,
"loss": 0.5372,
"step": 308
},
{
"epoch": 0.42,
"learning_rate": 4.845320254345235e-06,
"loss": 0.5385,
"step": 309
},
{
"epoch": 0.42,
"learning_rate": 4.844052754356166e-06,
"loss": 0.5439,
"step": 310
},
{
"epoch": 0.42,
"learning_rate": 4.842780249527882e-06,
"loss": 0.448,
"step": 311
},
{
"epoch": 0.42,
"learning_rate": 4.841502742577339e-06,
"loss": 0.5164,
"step": 312
},
{
"epoch": 0.42,
"learning_rate": 4.840220236232168e-06,
"loss": 0.5716,
"step": 313
},
{
"epoch": 0.42,
"learning_rate": 4.838932733230679e-06,
"loss": 0.4874,
"step": 314
},
{
"epoch": 0.43,
"learning_rate": 4.837640236321848e-06,
"loss": 0.4955,
"step": 315
},
{
"epoch": 0.43,
"learning_rate": 4.836342748265314e-06,
"loss": 0.5933,
"step": 316
},
{
"epoch": 0.43,
"learning_rate": 4.835040271831371e-06,
"loss": 0.5033,
"step": 317
},
{
"epoch": 0.43,
"learning_rate": 4.833732809800966e-06,
"loss": 0.5334,
"step": 318
},
{
"epoch": 0.43,
"learning_rate": 4.832420364965692e-06,
"loss": 0.5586,
"step": 319
},
{
"epoch": 0.43,
"learning_rate": 4.831102940127778e-06,
"loss": 0.6021,
"step": 320
},
{
"epoch": 0.43,
"learning_rate": 4.8297805381000865e-06,
"loss": 0.5998,
"step": 321
},
{
"epoch": 0.44,
"learning_rate": 4.828453161706108e-06,
"loss": 0.5672,
"step": 322
},
{
"epoch": 0.44,
"learning_rate": 4.827120813779954e-06,
"loss": 0.5091,
"step": 323
},
{
"epoch": 0.44,
"learning_rate": 4.825783497166349e-06,
"loss": 0.5702,
"step": 324
},
{
"epoch": 0.44,
"learning_rate": 4.824441214720629e-06,
"loss": 0.4892,
"step": 325
},
{
"epoch": 0.44,
"learning_rate": 4.82309396930873e-06,
"loss": 0.5417,
"step": 326
},
{
"epoch": 0.44,
"learning_rate": 4.821741763807186e-06,
"loss": 0.5725,
"step": 327
},
{
"epoch": 0.44,
"learning_rate": 4.820384601103121e-06,
"loss": 0.5298,
"step": 328
},
{
"epoch": 0.44,
"learning_rate": 4.819022484094243e-06,
"loss": 0.5167,
"step": 329
},
{
"epoch": 0.45,
"learning_rate": 4.81765541568884e-06,
"loss": 0.4795,
"step": 330
},
{
"epoch": 0.45,
"learning_rate": 4.816283398805767e-06,
"loss": 0.5603,
"step": 331
},
{
"epoch": 0.45,
"learning_rate": 4.814906436374451e-06,
"loss": 0.6219,
"step": 332
},
{
"epoch": 0.45,
"learning_rate": 4.8135245313348735e-06,
"loss": 0.5091,
"step": 333
},
{
"epoch": 0.45,
"learning_rate": 4.812137686637571e-06,
"loss": 0.549,
"step": 334
},
{
"epoch": 0.45,
"learning_rate": 4.810745905243626e-06,
"loss": 0.5191,
"step": 335
},
{
"epoch": 0.45,
"learning_rate": 4.809349190124663e-06,
"loss": 0.5041,
"step": 336
},
{
"epoch": 0.46,
"learning_rate": 4.807947544262838e-06,
"loss": 0.5359,
"step": 337
},
{
"epoch": 0.46,
"learning_rate": 4.806540970650839e-06,
"loss": 0.5328,
"step": 338
},
{
"epoch": 0.46,
"learning_rate": 4.80512947229187e-06,
"loss": 0.6413,
"step": 339
},
{
"epoch": 0.46,
"learning_rate": 4.803713052199653e-06,
"loss": 0.491,
"step": 340
},
{
"epoch": 0.46,
"learning_rate": 4.8022917133984185e-06,
"loss": 0.5081,
"step": 341
},
{
"epoch": 0.46,
"learning_rate": 4.800865458922899e-06,
"loss": 0.6018,
"step": 342
},
{
"epoch": 0.46,
"learning_rate": 4.799434291818322e-06,
"loss": 0.5482,
"step": 343
},
{
"epoch": 0.47,
"learning_rate": 4.797998215140404e-06,
"loss": 0.5723,
"step": 344
},
{
"epoch": 0.47,
"learning_rate": 4.796557231955343e-06,
"loss": 0.5536,
"step": 345
},
{
"epoch": 0.47,
"learning_rate": 4.795111345339818e-06,
"loss": 0.5838,
"step": 346
},
{
"epoch": 0.47,
"learning_rate": 4.793660558380969e-06,
"loss": 0.5828,
"step": 347
},
{
"epoch": 0.47,
"learning_rate": 4.7922048741764075e-06,
"loss": 0.5941,
"step": 348
},
{
"epoch": 0.47,
"learning_rate": 4.7907442958341945e-06,
"loss": 0.4413,
"step": 349
},
{
"epoch": 0.47,
"learning_rate": 4.789278826472845e-06,
"loss": 0.5669,
"step": 350
},
{
"epoch": 0.47,
"learning_rate": 4.787808469221315e-06,
"loss": 0.5246,
"step": 351
},
{
"epoch": 0.48,
"learning_rate": 4.786333227218996e-06,
"loss": 0.5913,
"step": 352
},
{
"epoch": 0.48,
"learning_rate": 4.78485310361571e-06,
"loss": 0.5543,
"step": 353
},
{
"epoch": 0.48,
"learning_rate": 4.783368101571704e-06,
"loss": 0.5459,
"step": 354
},
{
"epoch": 0.48,
"learning_rate": 4.781878224257637e-06,
"loss": 0.5769,
"step": 355
},
{
"epoch": 0.48,
"learning_rate": 4.780383474854578e-06,
"loss": 0.4905,
"step": 356
},
{
"epoch": 0.48,
"learning_rate": 4.7788838565540044e-06,
"loss": 0.5934,
"step": 357
},
{
"epoch": 0.48,
"learning_rate": 4.777379372557779e-06,
"loss": 0.5326,
"step": 358
},
{
"epoch": 0.49,
"learning_rate": 4.775870026078163e-06,
"loss": 0.548,
"step": 359
},
{
"epoch": 0.49,
"learning_rate": 4.774355820337794e-06,
"loss": 0.5206,
"step": 360
},
{
"epoch": 0.49,
"learning_rate": 4.772836758569688e-06,
"loss": 0.5485,
"step": 361
},
{
"epoch": 0.49,
"learning_rate": 4.771312844017224e-06,
"loss": 0.5299,
"step": 362
},
{
"epoch": 0.49,
"learning_rate": 4.76978407993415e-06,
"loss": 0.5335,
"step": 363
},
{
"epoch": 0.49,
"learning_rate": 4.768250469584562e-06,
"loss": 0.5285,
"step": 364
},
{
"epoch": 0.49,
"learning_rate": 4.766712016242906e-06,
"loss": 0.5171,
"step": 365
},
{
"epoch": 0.49,
"learning_rate": 4.765168723193968e-06,
"loss": 0.5867,
"step": 366
},
{
"epoch": 0.5,
"learning_rate": 4.763620593732867e-06,
"loss": 0.5783,
"step": 367
},
{
"epoch": 0.5,
"learning_rate": 4.762067631165049e-06,
"loss": 0.522,
"step": 368
},
{
"epoch": 0.5,
"learning_rate": 4.7605098388062795e-06,
"loss": 0.5253,
"step": 369
},
{
"epoch": 0.5,
"learning_rate": 4.758947219982635e-06,
"loss": 0.5085,
"step": 370
},
{
"epoch": 0.5,
"learning_rate": 4.757379778030498e-06,
"loss": 0.5826,
"step": 371
},
{
"epoch": 0.5,
"learning_rate": 4.755807516296548e-06,
"loss": 0.4795,
"step": 372
},
{
"epoch": 0.5,
"learning_rate": 4.754230438137757e-06,
"loss": 0.5658,
"step": 373
},
{
"epoch": 0.51,
"learning_rate": 4.752648546921379e-06,
"loss": 0.5008,
"step": 374
},
{
"epoch": 0.51,
"learning_rate": 4.751061846024944e-06,
"loss": 0.5224,
"step": 375
},
{
"epoch": 0.51,
"learning_rate": 4.749470338836256e-06,
"loss": 0.4875,
"step": 376
},
{
"epoch": 0.51,
"learning_rate": 4.747874028753375e-06,
"loss": 0.5606,
"step": 377
},
{
"epoch": 0.51,
"learning_rate": 4.746272919184618e-06,
"loss": 0.4685,
"step": 378
},
{
"epoch": 0.51,
"learning_rate": 4.74466701354855e-06,
"loss": 0.5589,
"step": 379
},
{
"epoch": 0.51,
"learning_rate": 4.743056315273976e-06,
"loss": 0.5068,
"step": 380
},
{
"epoch": 0.52,
"learning_rate": 4.741440827799934e-06,
"loss": 0.5252,
"step": 381
},
{
"epoch": 0.52,
"learning_rate": 4.7398205545756865e-06,
"loss": 0.491,
"step": 382
},
{
"epoch": 0.52,
"learning_rate": 4.738195499060715e-06,
"loss": 0.5392,
"step": 383
},
{
"epoch": 0.52,
"learning_rate": 4.736565664724713e-06,
"loss": 0.4989,
"step": 384
},
{
"epoch": 0.52,
"learning_rate": 4.734931055047575e-06,
"loss": 0.5889,
"step": 385
},
{
"epoch": 0.52,
"learning_rate": 4.733291673519392e-06,
"loss": 0.529,
"step": 386
},
{
"epoch": 0.52,
"learning_rate": 4.731647523640446e-06,
"loss": 0.5317,
"step": 387
},
{
"epoch": 0.52,
"learning_rate": 4.729998608921195e-06,
"loss": 0.5987,
"step": 388
},
{
"epoch": 0.53,
"learning_rate": 4.728344932882277e-06,
"loss": 0.5334,
"step": 389
},
{
"epoch": 0.53,
"learning_rate": 4.72668649905449e-06,
"loss": 0.522,
"step": 390
},
{
"epoch": 0.53,
"learning_rate": 4.725023310978794e-06,
"loss": 0.5939,
"step": 391
},
{
"epoch": 0.53,
"learning_rate": 4.723355372206297e-06,
"loss": 0.4746,
"step": 392
},
{
"epoch": 0.53,
"learning_rate": 4.721682686298256e-06,
"loss": 0.5866,
"step": 393
},
{
"epoch": 0.53,
"learning_rate": 4.720005256826056e-06,
"loss": 0.506,
"step": 394
},
{
"epoch": 0.53,
"learning_rate": 4.718323087371216e-06,
"loss": 0.6236,
"step": 395
},
{
"epoch": 0.54,
"learning_rate": 4.7166361815253744e-06,
"loss": 0.54,
"step": 396
},
{
"epoch": 0.54,
"learning_rate": 4.7149445428902794e-06,
"loss": 0.6284,
"step": 397
},
{
"epoch": 0.54,
"learning_rate": 4.713248175077787e-06,
"loss": 0.609,
"step": 398
},
{
"epoch": 0.54,
"learning_rate": 4.71154708170985e-06,
"loss": 0.5136,
"step": 399
},
{
"epoch": 0.54,
"learning_rate": 4.70984126641851e-06,
"loss": 0.5115,
"step": 400
},
{
"epoch": 0.54,
"learning_rate": 4.708130732845893e-06,
"loss": 0.5355,
"step": 401
},
{
"epoch": 0.54,
"learning_rate": 4.706415484644196e-06,
"loss": 0.5696,
"step": 402
},
{
"epoch": 0.54,
"learning_rate": 4.704695525475683e-06,
"loss": 0.5373,
"step": 403
},
{
"epoch": 0.55,
"learning_rate": 4.702970859012679e-06,
"loss": 0.5585,
"step": 404
},
{
"epoch": 0.55,
"learning_rate": 4.701241488937556e-06,
"loss": 0.5293,
"step": 405
},
{
"epoch": 0.55,
"learning_rate": 4.699507418942731e-06,
"loss": 0.5066,
"step": 406
},
{
"epoch": 0.55,
"learning_rate": 4.697768652730656e-06,
"loss": 0.4876,
"step": 407
},
{
"epoch": 0.55,
"learning_rate": 4.696025194013809e-06,
"loss": 0.4621,
"step": 408
},
{
"epoch": 0.55,
"learning_rate": 4.694277046514688e-06,
"loss": 0.4735,
"step": 409
},
{
"epoch": 0.55,
"learning_rate": 4.6925242139658005e-06,
"loss": 0.4853,
"step": 410
},
{
"epoch": 0.56,
"learning_rate": 4.690766700109659e-06,
"loss": 0.5791,
"step": 411
},
{
"epoch": 0.56,
"learning_rate": 4.689004508698771e-06,
"loss": 0.5573,
"step": 412
},
{
"epoch": 0.56,
"learning_rate": 4.68723764349563e-06,
"loss": 0.5184,
"step": 413
},
{
"epoch": 0.56,
"learning_rate": 4.68546610827271e-06,
"loss": 0.519,
"step": 414
},
{
"epoch": 0.56,
"learning_rate": 4.683689906812454e-06,
"loss": 0.5616,
"step": 415
},
{
"epoch": 0.56,
"learning_rate": 4.681909042907269e-06,
"loss": 0.5523,
"step": 416
},
{
"epoch": 0.56,
"learning_rate": 4.68012352035952e-06,
"loss": 0.5624,
"step": 417
},
{
"epoch": 0.57,
"learning_rate": 4.678333342981513e-06,
"loss": 0.5253,
"step": 418
},
{
"epoch": 0.57,
"learning_rate": 4.676538514595495e-06,
"loss": 0.5485,
"step": 419
},
{
"epoch": 0.57,
"learning_rate": 4.674739039033648e-06,
"loss": 0.4866,
"step": 420
},
{
"epoch": 0.57,
"learning_rate": 4.672934920138069e-06,
"loss": 0.6174,
"step": 421
},
{
"epoch": 0.57,
"learning_rate": 4.671126161760773e-06,
"loss": 0.5685,
"step": 422
},
{
"epoch": 0.57,
"learning_rate": 4.669312767763681e-06,
"loss": 0.5053,
"step": 423
},
{
"epoch": 0.57,
"learning_rate": 4.6674947420186106e-06,
"loss": 0.5451,
"step": 424
},
{
"epoch": 0.57,
"learning_rate": 4.665672088407268e-06,
"loss": 0.5395,
"step": 425
},
{
"epoch": 0.58,
"learning_rate": 4.663844810821244e-06,
"loss": 0.5706,
"step": 426
},
{
"epoch": 0.58,
"learning_rate": 4.662012913161998e-06,
"loss": 0.5725,
"step": 427
},
{
"epoch": 0.58,
"learning_rate": 4.660176399340854e-06,
"loss": 0.4917,
"step": 428
},
{
"epoch": 0.58,
"learning_rate": 4.658335273278997e-06,
"loss": 0.4931,
"step": 429
},
{
"epoch": 0.58,
"learning_rate": 4.656489538907453e-06,
"loss": 0.468,
"step": 430
},
{
"epoch": 0.58,
"learning_rate": 4.654639200167092e-06,
"loss": 0.599,
"step": 431
},
{
"epoch": 0.58,
"learning_rate": 4.652784261008614e-06,
"loss": 0.5346,
"step": 432
},
{
"epoch": 0.59,
"learning_rate": 4.650924725392538e-06,
"loss": 0.4996,
"step": 433
},
{
"epoch": 0.59,
"learning_rate": 4.649060597289204e-06,
"loss": 0.5708,
"step": 434
},
{
"epoch": 0.59,
"learning_rate": 4.6471918806787516e-06,
"loss": 0.573,
"step": 435
},
{
"epoch": 0.59,
"learning_rate": 4.645318579551119e-06,
"loss": 0.599,
"step": 436
},
{
"epoch": 0.59,
"learning_rate": 4.643440697906033e-06,
"loss": 0.5272,
"step": 437
},
{
"epoch": 0.59,
"learning_rate": 4.641558239753001e-06,
"loss": 0.5311,
"step": 438
},
{
"epoch": 0.59,
"learning_rate": 4.639671209111301e-06,
"loss": 0.546,
"step": 439
},
{
"epoch": 0.59,
"learning_rate": 4.637779610009974e-06,
"loss": 0.5037,
"step": 440
},
{
"epoch": 0.6,
"learning_rate": 4.635883446487816e-06,
"loss": 0.5385,
"step": 441
},
{
"epoch": 0.6,
"learning_rate": 4.633982722593367e-06,
"loss": 0.5402,
"step": 442
},
{
"epoch": 0.6,
"learning_rate": 4.6320774423849055e-06,
"loss": 0.494,
"step": 443
},
{
"epoch": 0.6,
"learning_rate": 4.630167609930437e-06,
"loss": 0.5145,
"step": 444
},
{
"epoch": 0.6,
"learning_rate": 4.628253229307689e-06,
"loss": 0.5929,
"step": 445
},
{
"epoch": 0.6,
"learning_rate": 4.6263343046040954e-06,
"loss": 0.5451,
"step": 446
},
{
"epoch": 0.6,
"learning_rate": 4.624410839916798e-06,
"loss": 0.4753,
"step": 447
},
{
"epoch": 0.61,
"learning_rate": 4.622482839352628e-06,
"loss": 0.5799,
"step": 448
},
{
"epoch": 0.61,
"learning_rate": 4.620550307028101e-06,
"loss": 0.6083,
"step": 449
},
{
"epoch": 0.61,
"learning_rate": 4.618613247069411e-06,
"loss": 0.5589,
"step": 450
},
{
"epoch": 0.61,
"learning_rate": 4.616671663612418e-06,
"loss": 0.4814,
"step": 451
},
{
"epoch": 0.61,
"learning_rate": 4.6147255608026395e-06,
"loss": 0.5771,
"step": 452
},
{
"epoch": 0.61,
"learning_rate": 4.612774942795244e-06,
"loss": 0.6139,
"step": 453
},
{
"epoch": 0.61,
"learning_rate": 4.610819813755038e-06,
"loss": 0.5837,
"step": 454
},
{
"epoch": 0.62,
"learning_rate": 4.608860177856462e-06,
"loss": 0.4636,
"step": 455
},
{
"epoch": 0.62,
"learning_rate": 4.606896039283577e-06,
"loss": 0.5445,
"step": 456
},
{
"epoch": 0.62,
"learning_rate": 4.604927402230061e-06,
"loss": 0.4836,
"step": 457
},
{
"epoch": 0.62,
"learning_rate": 4.6029542708991925e-06,
"loss": 0.486,
"step": 458
},
{
"epoch": 0.62,
"learning_rate": 4.60097664950385e-06,
"loss": 0.5601,
"step": 459
},
{
"epoch": 0.62,
"learning_rate": 4.598994542266496e-06,
"loss": 0.4998,
"step": 460
},
{
"epoch": 0.62,
"learning_rate": 4.597007953419173e-06,
"loss": 0.501,
"step": 461
},
{
"epoch": 0.62,
"learning_rate": 4.595016887203489e-06,
"loss": 0.479,
"step": 462
},
{
"epoch": 0.63,
"learning_rate": 4.593021347870614e-06,
"loss": 0.54,
"step": 463
},
{
"epoch": 0.63,
"learning_rate": 4.5910213396812705e-06,
"loss": 0.5352,
"step": 464
},
{
"epoch": 0.63,
"learning_rate": 4.58901686690572e-06,
"loss": 0.5832,
"step": 465
},
{
"epoch": 0.63,
"learning_rate": 4.587007933823755e-06,
"loss": 0.556,
"step": 466
},
{
"epoch": 0.63,
"learning_rate": 4.584994544724695e-06,
"loss": 0.505,
"step": 467
},
{
"epoch": 0.63,
"learning_rate": 4.582976703907371e-06,
"loss": 0.5025,
"step": 468
},
{
"epoch": 0.63,
"learning_rate": 4.580954415680121e-06,
"loss": 0.5327,
"step": 469
},
{
"epoch": 0.64,
"learning_rate": 4.578927684360777e-06,
"loss": 0.5625,
"step": 470
},
{
"epoch": 0.64,
"learning_rate": 4.576896514276657e-06,
"loss": 0.5102,
"step": 471
},
{
"epoch": 0.64,
"learning_rate": 4.5748609097645595e-06,
"loss": 0.4809,
"step": 472
},
{
"epoch": 0.64,
"learning_rate": 4.5728208751707475e-06,
"loss": 0.535,
"step": 473
},
{
"epoch": 0.64,
"learning_rate": 4.570776414850945e-06,
"loss": 0.5192,
"step": 474
},
{
"epoch": 0.64,
"learning_rate": 4.568727533170324e-06,
"loss": 0.5899,
"step": 475
},
{
"epoch": 0.64,
"learning_rate": 4.566674234503498e-06,
"loss": 0.5526,
"step": 476
},
{
"epoch": 0.65,
"learning_rate": 4.564616523234511e-06,
"loss": 0.5197,
"step": 477
},
{
"epoch": 0.65,
"learning_rate": 4.562554403756827e-06,
"loss": 0.4869,
"step": 478
},
{
"epoch": 0.65,
"learning_rate": 4.560487880473324e-06,
"loss": 0.4464,
"step": 479
},
{
"epoch": 0.65,
"learning_rate": 4.558416957796282e-06,
"loss": 0.4811,
"step": 480
},
{
"epoch": 0.65,
"learning_rate": 4.556341640147375e-06,
"loss": 0.6039,
"step": 481
},
{
"epoch": 0.65,
"learning_rate": 4.554261931957658e-06,
"loss": 0.5388,
"step": 482
},
{
"epoch": 0.65,
"learning_rate": 4.552177837667562e-06,
"loss": 0.5176,
"step": 483
},
{
"epoch": 0.65,
"learning_rate": 4.550089361726885e-06,
"loss": 0.4872,
"step": 484
},
{
"epoch": 0.66,
"learning_rate": 4.547996508594777e-06,
"loss": 0.6086,
"step": 485
},
{
"epoch": 0.66,
"learning_rate": 4.5458992827397364e-06,
"loss": 0.5811,
"step": 486
},
{
"epoch": 0.66,
"learning_rate": 4.543797688639596e-06,
"loss": 0.5198,
"step": 487
},
{
"epoch": 0.66,
"learning_rate": 4.541691730781517e-06,
"loss": 0.5231,
"step": 488
},
{
"epoch": 0.66,
"learning_rate": 4.539581413661976e-06,
"loss": 0.4944,
"step": 489
},
{
"epoch": 0.66,
"learning_rate": 4.537466741786759e-06,
"loss": 0.4775,
"step": 490
},
{
"epoch": 0.66,
"learning_rate": 4.535347719670947e-06,
"loss": 0.5519,
"step": 491
},
{
"epoch": 0.67,
"learning_rate": 4.533224351838914e-06,
"loss": 0.57,
"step": 492
},
{
"epoch": 0.67,
"learning_rate": 4.531096642824308e-06,
"loss": 0.5689,
"step": 493
},
{
"epoch": 0.67,
"learning_rate": 4.528964597170048e-06,
"loss": 0.5704,
"step": 494
},
{
"epoch": 0.67,
"learning_rate": 4.5268282194283145e-06,
"loss": 0.4992,
"step": 495
},
{
"epoch": 0.67,
"learning_rate": 4.524687514160532e-06,
"loss": 0.5058,
"step": 496
},
{
"epoch": 0.67,
"learning_rate": 4.522542485937369e-06,
"loss": 0.5584,
"step": 497
},
{
"epoch": 0.67,
"learning_rate": 4.520393139338723e-06,
"loss": 0.6039,
"step": 498
},
{
"epoch": 0.67,
"learning_rate": 4.518239478953713e-06,
"loss": 0.5135,
"step": 499
},
{
"epoch": 0.68,
"learning_rate": 4.516081509380666e-06,
"loss": 0.5292,
"step": 500
},
{
"epoch": 0.68,
"learning_rate": 4.513919235227111e-06,
"loss": 0.5089,
"step": 501
},
{
"epoch": 0.68,
"learning_rate": 4.5117526611097685e-06,
"loss": 0.551,
"step": 502
},
{
"epoch": 0.68,
"learning_rate": 4.5095817916545385e-06,
"loss": 0.5313,
"step": 503
},
{
"epoch": 0.68,
"learning_rate": 4.507406631496491e-06,
"loss": 0.587,
"step": 504
},
{
"epoch": 0.68,
"learning_rate": 4.505227185279862e-06,
"loss": 0.5078,
"step": 505
},
{
"epoch": 0.68,
"learning_rate": 4.503043457658033e-06,
"loss": 0.5488,
"step": 506
},
{
"epoch": 0.69,
"learning_rate": 4.500855453293532e-06,
"loss": 0.5418,
"step": 507
},
{
"epoch": 0.69,
"learning_rate": 4.498663176858014e-06,
"loss": 0.5425,
"step": 508
},
{
"epoch": 0.69,
"learning_rate": 4.496466633032257e-06,
"loss": 0.484,
"step": 509
},
{
"epoch": 0.69,
"learning_rate": 4.494265826506152e-06,
"loss": 0.543,
"step": 510
},
{
"epoch": 0.69,
"learning_rate": 4.492060761978688e-06,
"loss": 0.4938,
"step": 511
},
{
"epoch": 0.69,
"learning_rate": 4.48985144415795e-06,
"loss": 0.5127,
"step": 512
},
{
"epoch": 0.69,
"learning_rate": 4.4876378777611e-06,
"loss": 0.4654,
"step": 513
},
{
"epoch": 0.7,
"learning_rate": 4.485420067514373e-06,
"loss": 0.5978,
"step": 514
},
{
"epoch": 0.7,
"learning_rate": 4.483198018153065e-06,
"loss": 0.5466,
"step": 515
},
{
"epoch": 0.7,
"learning_rate": 4.4809717344215235e-06,
"loss": 0.5426,
"step": 516
},
{
"epoch": 0.7,
"learning_rate": 4.478741221073136e-06,
"loss": 0.6048,
"step": 517
},
{
"epoch": 0.7,
"learning_rate": 4.476506482870321e-06,
"loss": 0.5122,
"step": 518
},
{
"epoch": 0.7,
"learning_rate": 4.474267524584519e-06,
"loss": 0.5238,
"step": 519
},
{
"epoch": 0.7,
"learning_rate": 4.472024350996178e-06,
"loss": 0.4966,
"step": 520
},
{
"epoch": 0.7,
"learning_rate": 4.469776966894749e-06,
"loss": 0.5739,
"step": 521
},
{
"epoch": 0.71,
"learning_rate": 4.467525377078672e-06,
"loss": 0.5512,
"step": 522
},
{
"epoch": 0.71,
"learning_rate": 4.465269586355365e-06,
"loss": 0.4941,
"step": 523
},
{
"epoch": 0.71,
"learning_rate": 4.463009599541219e-06,
"loss": 0.5012,
"step": 524
},
{
"epoch": 0.71,
"learning_rate": 4.460745421461582e-06,
"loss": 0.6123,
"step": 525
},
{
"epoch": 0.71,
"learning_rate": 4.458477056950748e-06,
"loss": 0.5541,
"step": 526
},
{
"epoch": 0.71,
"learning_rate": 4.456204510851957e-06,
"loss": 0.4851,
"step": 527
},
{
"epoch": 0.71,
"learning_rate": 4.4539277880173695e-06,
"loss": 0.569,
"step": 528
},
{
"epoch": 0.72,
"learning_rate": 4.451646893308068e-06,
"loss": 0.4893,
"step": 529
},
{
"epoch": 0.72,
"learning_rate": 4.449361831594041e-06,
"loss": 0.4968,
"step": 530
},
{
"epoch": 0.72,
"learning_rate": 4.447072607754177e-06,
"loss": 0.5594,
"step": 531
},
{
"epoch": 0.72,
"learning_rate": 4.4447792266762466e-06,
"loss": 0.5468,
"step": 532
},
{
"epoch": 0.72,
"learning_rate": 4.442481693256899e-06,
"loss": 0.5256,
"step": 533
},
{
"epoch": 0.72,
"learning_rate": 4.440180012401649e-06,
"loss": 0.4594,
"step": 534
},
{
"epoch": 0.72,
"learning_rate": 4.437874189024867e-06,
"loss": 0.6129,
"step": 535
},
{
"epoch": 0.72,
"learning_rate": 4.435564228049768e-06,
"loss": 0.6154,
"step": 536
},
{
"epoch": 0.73,
"learning_rate": 4.433250134408401e-06,
"loss": 0.5309,
"step": 537
},
{
"epoch": 0.73,
"learning_rate": 4.430931913041639e-06,
"loss": 0.5416,
"step": 538
},
{
"epoch": 0.73,
"learning_rate": 4.4286095688991655e-06,
"loss": 0.5147,
"step": 539
},
{
"epoch": 0.73,
"learning_rate": 4.426283106939474e-06,
"loss": 0.5433,
"step": 540
},
{
"epoch": 0.73,
"learning_rate": 4.423952532129841e-06,
"loss": 0.5397,
"step": 541
},
{
"epoch": 0.73,
"learning_rate": 4.4216178494463305e-06,
"loss": 0.5013,
"step": 542
},
{
"epoch": 0.73,
"learning_rate": 4.419279063873776e-06,
"loss": 0.5893,
"step": 543
},
{
"epoch": 0.74,
"learning_rate": 4.416936180405769e-06,
"loss": 0.5445,
"step": 544
},
{
"epoch": 0.74,
"learning_rate": 4.4145892040446525e-06,
"loss": 0.5362,
"step": 545
},
{
"epoch": 0.74,
"learning_rate": 4.412238139801509e-06,
"loss": 0.504,
"step": 546
},
{
"epoch": 0.74,
"learning_rate": 4.4098829926961485e-06,
"loss": 0.5849,
"step": 547
},
{
"epoch": 0.74,
"learning_rate": 4.407523767757096e-06,
"loss": 0.588,
"step": 548
},
{
"epoch": 0.74,
"learning_rate": 4.405160470021586e-06,
"loss": 0.5304,
"step": 549
},
{
"epoch": 0.74,
"learning_rate": 4.402793104535548e-06,
"loss": 0.5665,
"step": 550
},
{
"epoch": 0.75,
"learning_rate": 4.400421676353599e-06,
"loss": 0.4967,
"step": 551
},
{
"epoch": 0.75,
"learning_rate": 4.398046190539025e-06,
"loss": 0.546,
"step": 552
},
{
"epoch": 0.75,
"learning_rate": 4.39566665216378e-06,
"loss": 0.5632,
"step": 553
},
{
"epoch": 0.75,
"learning_rate": 4.393283066308469e-06,
"loss": 0.435,
"step": 554
},
{
"epoch": 0.75,
"learning_rate": 4.3908954380623394e-06,
"loss": 0.555,
"step": 555
},
{
"epoch": 0.75,
"learning_rate": 4.388503772523269e-06,
"loss": 0.483,
"step": 556
},
{
"epoch": 0.75,
"learning_rate": 4.386108074797757e-06,
"loss": 0.4855,
"step": 557
},
{
"epoch": 0.75,
"learning_rate": 4.383708350000911e-06,
"loss": 0.5974,
"step": 558
},
{
"epoch": 0.76,
"learning_rate": 4.381304603256436e-06,
"loss": 0.4995,
"step": 559
},
{
"epoch": 0.76,
"learning_rate": 4.378896839696625e-06,
"loss": 0.5939,
"step": 560
},
{
"epoch": 0.76,
"learning_rate": 4.376485064462348e-06,
"loss": 0.5133,
"step": 561
},
{
"epoch": 0.76,
"learning_rate": 4.37406928270304e-06,
"loss": 0.5116,
"step": 562
},
{
"epoch": 0.76,
"learning_rate": 4.371649499576691e-06,
"loss": 0.6338,
"step": 563
},
{
"epoch": 0.76,
"learning_rate": 4.369225720249834e-06,
"loss": 0.4857,
"step": 564
},
{
"epoch": 0.76,
"learning_rate": 4.3667979498975326e-06,
"loss": 0.4963,
"step": 565
},
{
"epoch": 0.77,
"learning_rate": 4.364366193703373e-06,
"loss": 0.4865,
"step": 566
},
{
"epoch": 0.77,
"learning_rate": 4.361930456859455e-06,
"loss": 0.5602,
"step": 567
},
{
"epoch": 0.77,
"learning_rate": 4.359490744566372e-06,
"loss": 0.4783,
"step": 568
},
{
"epoch": 0.77,
"learning_rate": 4.3570470620332086e-06,
"loss": 0.4225,
"step": 569
},
{
"epoch": 0.77,
"learning_rate": 4.354599414477526e-06,
"loss": 0.5636,
"step": 570
},
{
"epoch": 0.77,
"learning_rate": 4.352147807125351e-06,
"loss": 0.4748,
"step": 571
},
{
"epoch": 0.77,
"learning_rate": 4.349692245211166e-06,
"loss": 0.5348,
"step": 572
},
{
"epoch": 0.77,
"learning_rate": 4.347232733977893e-06,
"loss": 0.5288,
"step": 573
},
{
"epoch": 0.78,
"learning_rate": 4.344769278676893e-06,
"loss": 0.4652,
"step": 574
},
{
"epoch": 0.78,
"learning_rate": 4.34230188456794e-06,
"loss": 0.5587,
"step": 575
},
{
"epoch": 0.78,
"learning_rate": 4.339830556919225e-06,
"loss": 0.5586,
"step": 576
},
{
"epoch": 0.78,
"learning_rate": 4.337355301007336e-06,
"loss": 0.5039,
"step": 577
},
{
"epoch": 0.78,
"learning_rate": 4.334876122117242e-06,
"loss": 0.4663,
"step": 578
},
{
"epoch": 0.78,
"learning_rate": 4.332393025542298e-06,
"loss": 0.5201,
"step": 579
},
{
"epoch": 0.78,
"learning_rate": 4.329906016584217e-06,
"loss": 0.594,
"step": 580
},
{
"epoch": 0.79,
"learning_rate": 4.327415100553066e-06,
"loss": 0.5539,
"step": 581
},
{
"epoch": 0.79,
"learning_rate": 4.324920282767256e-06,
"loss": 0.5099,
"step": 582
},
{
"epoch": 0.79,
"learning_rate": 4.322421568553529e-06,
"loss": 0.4996,
"step": 583
},
{
"epoch": 0.79,
"learning_rate": 4.319918963246944e-06,
"loss": 0.4729,
"step": 584
},
{
"epoch": 0.79,
"learning_rate": 4.317412472190871e-06,
"loss": 0.5248,
"step": 585
},
{
"epoch": 0.79,
"learning_rate": 4.314902100736973e-06,
"loss": 0.5159,
"step": 586
},
{
"epoch": 0.79,
"learning_rate": 4.312387854245201e-06,
"loss": 0.4673,
"step": 587
},
{
"epoch": 0.8,
"learning_rate": 4.3098697380837785e-06,
"loss": 0.494,
"step": 588
},
{
"epoch": 0.8,
"learning_rate": 4.30734775762919e-06,
"loss": 0.4555,
"step": 589
},
{
"epoch": 0.8,
"learning_rate": 4.304821918266175e-06,
"loss": 0.5326,
"step": 590
},
{
"epoch": 0.8,
"learning_rate": 4.302292225387707e-06,
"loss": 0.5421,
"step": 591
},
{
"epoch": 0.8,
"learning_rate": 4.2997586843949905e-06,
"loss": 0.5044,
"step": 592
},
{
"epoch": 0.8,
"learning_rate": 4.297221300697444e-06,
"loss": 0.5498,
"step": 593
},
{
"epoch": 0.8,
"learning_rate": 4.294680079712694e-06,
"loss": 0.508,
"step": 594
},
{
"epoch": 0.8,
"learning_rate": 4.292135026866556e-06,
"loss": 0.447,
"step": 595
},
{
"epoch": 0.81,
"learning_rate": 4.289586147593031e-06,
"loss": 0.5108,
"step": 596
},
{
"epoch": 0.81,
"learning_rate": 4.287033447334286e-06,
"loss": 0.4881,
"step": 597
},
{
"epoch": 0.81,
"learning_rate": 4.28447693154065e-06,
"loss": 0.5642,
"step": 598
},
{
"epoch": 0.81,
"learning_rate": 4.281916605670595e-06,
"loss": 0.4873,
"step": 599
},
{
"epoch": 0.81,
"learning_rate": 4.27935247519073e-06,
"loss": 0.5171,
"step": 600
},
{
"epoch": 0.81,
"learning_rate": 4.276784545575788e-06,
"loss": 0.5,
"step": 601
},
{
"epoch": 0.81,
"learning_rate": 4.274212822308612e-06,
"loss": 0.5982,
"step": 602
},
{
"epoch": 0.82,
"learning_rate": 4.271637310880147e-06,
"loss": 0.518,
"step": 603
},
{
"epoch": 0.82,
"learning_rate": 4.2690580167894225e-06,
"loss": 0.4779,
"step": 604
},
{
"epoch": 0.82,
"learning_rate": 4.266474945543548e-06,
"loss": 0.5016,
"step": 605
},
{
"epoch": 0.82,
"learning_rate": 4.263888102657696e-06,
"loss": 0.5129,
"step": 606
},
{
"epoch": 0.82,
"learning_rate": 4.261297493655092e-06,
"loss": 0.5158,
"step": 607
},
{
"epoch": 0.82,
"learning_rate": 4.258703124067005e-06,
"loss": 0.5363,
"step": 608
},
{
"epoch": 0.82,
"learning_rate": 4.256104999432729e-06,
"loss": 0.6077,
"step": 609
},
{
"epoch": 0.82,
"learning_rate": 4.253503125299579e-06,
"loss": 0.5285,
"step": 610
},
{
"epoch": 0.83,
"learning_rate": 4.250897507222873e-06,
"loss": 0.5597,
"step": 611
},
{
"epoch": 0.83,
"learning_rate": 4.248288150765925e-06,
"loss": 0.5324,
"step": 612
},
{
"epoch": 0.83,
"learning_rate": 4.2456750615000306e-06,
"loss": 0.5241,
"step": 613
},
{
"epoch": 0.83,
"learning_rate": 4.243058245004455e-06,
"loss": 0.4829,
"step": 614
},
{
"epoch": 0.83,
"learning_rate": 4.24043770686642e-06,
"loss": 0.5389,
"step": 615
},
{
"epoch": 0.83,
"learning_rate": 4.237813452681095e-06,
"loss": 0.537,
"step": 616
},
{
"epoch": 0.83,
"learning_rate": 4.2351854880515856e-06,
"loss": 0.5469,
"step": 617
},
{
"epoch": 0.84,
"learning_rate": 4.232553818588915e-06,
"loss": 0.5359,
"step": 618
},
{
"epoch": 0.84,
"learning_rate": 4.22991844991202e-06,
"loss": 0.5331,
"step": 619
},
{
"epoch": 0.84,
"learning_rate": 4.227279387647736e-06,
"loss": 0.554,
"step": 620
},
{
"epoch": 0.84,
"learning_rate": 4.224636637430783e-06,
"loss": 0.5213,
"step": 621
},
{
"epoch": 0.84,
"learning_rate": 4.221990204903756e-06,
"loss": 0.4849,
"step": 622
},
{
"epoch": 0.84,
"learning_rate": 4.219340095717111e-06,
"loss": 0.5424,
"step": 623
},
{
"epoch": 0.84,
"learning_rate": 4.216686315529156e-06,
"loss": 0.5197,
"step": 624
},
{
"epoch": 0.85,
"learning_rate": 4.2140288700060365e-06,
"loss": 0.4132,
"step": 625
},
{
"epoch": 0.85,
"learning_rate": 4.211367764821722e-06,
"loss": 0.4495,
"step": 626
},
{
"epoch": 0.85,
"learning_rate": 4.208703005658e-06,
"loss": 0.5514,
"step": 627
},
{
"epoch": 0.85,
"learning_rate": 4.206034598204454e-06,
"loss": 0.4809,
"step": 628
},
{
"epoch": 0.85,
"learning_rate": 4.203362548158462e-06,
"loss": 0.5589,
"step": 629
},
{
"epoch": 0.85,
"learning_rate": 4.200686861225177e-06,
"loss": 0.3918,
"step": 630
},
{
"epoch": 0.85,
"learning_rate": 4.1980075431175184e-06,
"loss": 0.4778,
"step": 631
},
{
"epoch": 0.85,
"learning_rate": 4.195324599556158e-06,
"loss": 0.4515,
"step": 632
},
{
"epoch": 0.86,
"learning_rate": 4.192638036269507e-06,
"loss": 0.5454,
"step": 633
},
{
"epoch": 0.86,
"learning_rate": 4.189947858993708e-06,
"loss": 0.5131,
"step": 634
},
{
"epoch": 0.86,
"learning_rate": 4.1872540734726176e-06,
"loss": 0.6223,
"step": 635
},
{
"epoch": 0.86,
"learning_rate": 4.184556685457798e-06,
"loss": 0.5363,
"step": 636
},
{
"epoch": 0.86,
"learning_rate": 4.1818557007085e-06,
"loss": 0.5458,
"step": 637
},
{
"epoch": 0.86,
"learning_rate": 4.179151124991659e-06,
"loss": 0.5085,
"step": 638
},
{
"epoch": 0.86,
"learning_rate": 4.176442964081874e-06,
"loss": 0.546,
"step": 639
},
{
"epoch": 0.87,
"learning_rate": 4.1737312237613994e-06,
"loss": 0.6053,
"step": 640
},
{
"epoch": 0.87,
"learning_rate": 4.1710159098201316e-06,
"loss": 0.5406,
"step": 641
},
{
"epoch": 0.87,
"learning_rate": 4.168297028055599e-06,
"loss": 0.5697,
"step": 642
},
{
"epoch": 0.87,
"learning_rate": 4.165574584272946e-06,
"loss": 0.5107,
"step": 643
},
{
"epoch": 0.87,
"learning_rate": 4.1628485842849235e-06,
"loss": 0.5479,
"step": 644
},
{
"epoch": 0.87,
"learning_rate": 4.160119033911874e-06,
"loss": 0.5494,
"step": 645
},
{
"epoch": 0.87,
"learning_rate": 4.157385938981722e-06,
"loss": 0.5488,
"step": 646
},
{
"epoch": 0.87,
"learning_rate": 4.154649305329959e-06,
"loss": 0.5697,
"step": 647
},
{
"epoch": 0.88,
"learning_rate": 4.151909138799631e-06,
"loss": 0.587,
"step": 648
},
{
"epoch": 0.88,
"learning_rate": 4.149165445241331e-06,
"loss": 0.4789,
"step": 649
},
{
"epoch": 0.88,
"learning_rate": 4.146418230513179e-06,
"loss": 0.5168,
"step": 650
},
{
"epoch": 0.88,
"learning_rate": 4.143667500480815e-06,
"loss": 0.6004,
"step": 651
},
{
"epoch": 0.88,
"learning_rate": 4.140913261017382e-06,
"loss": 0.5032,
"step": 652
},
{
"epoch": 0.88,
"learning_rate": 4.1381555180035205e-06,
"loss": 0.5335,
"step": 653
},
{
"epoch": 0.88,
"learning_rate": 4.1353942773273475e-06,
"loss": 0.5299,
"step": 654
},
{
"epoch": 0.89,
"learning_rate": 4.13262954488445e-06,
"loss": 0.5509,
"step": 655
},
{
"epoch": 0.89,
"learning_rate": 4.1298613265778685e-06,
"loss": 0.559,
"step": 656
},
{
"epoch": 0.89,
"learning_rate": 4.12708962831809e-06,
"loss": 0.5068,
"step": 657
},
{
"epoch": 0.89,
"learning_rate": 4.124314456023026e-06,
"loss": 0.4923,
"step": 658
},
{
"epoch": 0.89,
"learning_rate": 4.121535815618012e-06,
"loss": 0.5057,
"step": 659
},
{
"epoch": 0.89,
"learning_rate": 4.1187537130357825e-06,
"loss": 0.4899,
"step": 660
},
{
"epoch": 0.89,
"learning_rate": 4.115968154216467e-06,
"loss": 0.5618,
"step": 661
},
{
"epoch": 0.9,
"learning_rate": 4.113179145107576e-06,
"loss": 0.5543,
"step": 662
},
{
"epoch": 0.9,
"learning_rate": 4.110386691663982e-06,
"loss": 0.4595,
"step": 663
},
{
"epoch": 0.9,
"learning_rate": 4.107590799847917e-06,
"loss": 0.5186,
"step": 664
},
{
"epoch": 0.9,
"learning_rate": 4.1047914756289505e-06,
"loss": 0.5161,
"step": 665
},
{
"epoch": 0.9,
"learning_rate": 4.101988724983983e-06,
"loss": 0.5648,
"step": 666
},
{
"epoch": 0.9,
"learning_rate": 4.099182553897228e-06,
"loss": 0.5066,
"step": 667
},
{
"epoch": 0.9,
"learning_rate": 4.096372968360206e-06,
"loss": 0.5123,
"step": 668
},
{
"epoch": 0.9,
"learning_rate": 4.093559974371725e-06,
"loss": 0.5573,
"step": 669
},
{
"epoch": 0.91,
"learning_rate": 4.090743577937869e-06,
"loss": 0.5084,
"step": 670
},
{
"epoch": 0.91,
"learning_rate": 4.087923785071992e-06,
"loss": 0.485,
"step": 671
},
{
"epoch": 0.91,
"learning_rate": 4.085100601794695e-06,
"loss": 0.5345,
"step": 672
},
{
"epoch": 0.91,
"learning_rate": 4.082274034133819e-06,
"loss": 0.484,
"step": 673
},
{
"epoch": 0.91,
"learning_rate": 4.079444088124431e-06,
"loss": 0.4871,
"step": 674
},
{
"epoch": 0.91,
"learning_rate": 4.076610769808814e-06,
"loss": 0.4892,
"step": 675
},
{
"epoch": 0.91,
"learning_rate": 4.073774085236447e-06,
"loss": 0.5771,
"step": 676
},
{
"epoch": 0.92,
"learning_rate": 4.070934040463999e-06,
"loss": 0.5421,
"step": 677
},
{
"epoch": 0.92,
"learning_rate": 4.0680906415553126e-06,
"loss": 0.6013,
"step": 678
},
{
"epoch": 0.92,
"learning_rate": 4.065243894581392e-06,
"loss": 0.5152,
"step": 679
},
{
"epoch": 0.92,
"learning_rate": 4.062393805620391e-06,
"loss": 0.5005,
"step": 680
},
{
"epoch": 0.92,
"learning_rate": 4.059540380757598e-06,
"loss": 0.471,
"step": 681
},
{
"epoch": 0.92,
"learning_rate": 4.056683626085423e-06,
"loss": 0.5494,
"step": 682
},
{
"epoch": 0.92,
"learning_rate": 4.053823547703386e-06,
"loss": 0.5041,
"step": 683
},
{
"epoch": 0.92,
"learning_rate": 4.050960151718105e-06,
"loss": 0.5638,
"step": 684
},
{
"epoch": 0.93,
"learning_rate": 4.04809344424328e-06,
"loss": 0.5051,
"step": 685
},
{
"epoch": 0.93,
"learning_rate": 4.045223431399683e-06,
"loss": 0.5438,
"step": 686
},
{
"epoch": 0.93,
"learning_rate": 4.042350119315142e-06,
"loss": 0.5876,
"step": 687
},
{
"epoch": 0.93,
"learning_rate": 4.0394735141245285e-06,
"loss": 0.5219,
"step": 688
},
{
"epoch": 0.93,
"learning_rate": 4.036593621969747e-06,
"loss": 0.4789,
"step": 689
},
{
"epoch": 0.93,
"learning_rate": 4.033710448999719e-06,
"loss": 0.5924,
"step": 690
},
{
"epoch": 0.93,
"learning_rate": 4.030824001370372e-06,
"loss": 0.5211,
"step": 691
},
{
"epoch": 0.94,
"learning_rate": 4.027934285244624e-06,
"loss": 0.5102,
"step": 692
},
{
"epoch": 0.94,
"learning_rate": 4.025041306792372e-06,
"loss": 0.5255,
"step": 693
},
{
"epoch": 0.94,
"learning_rate": 4.022145072190479e-06,
"loss": 0.5034,
"step": 694
},
{
"epoch": 0.94,
"learning_rate": 4.019245587622761e-06,
"loss": 0.4768,
"step": 695
},
{
"epoch": 0.94,
"learning_rate": 4.0163428592799695e-06,
"loss": 0.5275,
"step": 696
},
{
"epoch": 0.94,
"learning_rate": 4.013436893359787e-06,
"loss": 0.5083,
"step": 697
},
{
"epoch": 0.94,
"learning_rate": 4.010527696066805e-06,
"loss": 0.546,
"step": 698
},
{
"epoch": 0.95,
"learning_rate": 4.007615273612515e-06,
"loss": 0.524,
"step": 699
},
{
"epoch": 0.95,
"learning_rate": 4.004699632215296e-06,
"loss": 0.5306,
"step": 700
},
{
"epoch": 0.95,
"learning_rate": 4.001780778100398e-06,
"loss": 0.5609,
"step": 701
},
{
"epoch": 0.95,
"learning_rate": 3.998858717499931e-06,
"loss": 0.5239,
"step": 702
},
{
"epoch": 0.95,
"learning_rate": 3.995933456652853e-06,
"loss": 0.5428,
"step": 703
},
{
"epoch": 0.95,
"learning_rate": 3.993005001804953e-06,
"loss": 0.585,
"step": 704
},
{
"epoch": 0.95,
"learning_rate": 3.990073359208838e-06,
"loss": 0.5439,
"step": 705
},
{
"epoch": 0.95,
"learning_rate": 3.987138535123927e-06,
"loss": 0.5509,
"step": 706
},
{
"epoch": 0.96,
"learning_rate": 3.984200535816427e-06,
"loss": 0.5269,
"step": 707
},
{
"epoch": 0.96,
"learning_rate": 3.981259367559325e-06,
"loss": 0.5241,
"step": 708
},
{
"epoch": 0.96,
"learning_rate": 3.978315036632373e-06,
"loss": 0.5288,
"step": 709
},
{
"epoch": 0.96,
"learning_rate": 3.975367549322083e-06,
"loss": 0.5768,
"step": 710
},
{
"epoch": 0.96,
"learning_rate": 3.972416911921695e-06,
"loss": 0.4967,
"step": 711
},
{
"epoch": 0.96,
"learning_rate": 3.969463130731183e-06,
"loss": 0.5144,
"step": 712
},
{
"epoch": 0.96,
"learning_rate": 3.966506212057232e-06,
"loss": 0.5018,
"step": 713
},
{
"epoch": 0.97,
"learning_rate": 3.963546162213223e-06,
"loss": 0.5384,
"step": 714
},
{
"epoch": 0.97,
"learning_rate": 3.960582987519225e-06,
"loss": 0.4936,
"step": 715
},
{
"epoch": 0.97,
"learning_rate": 3.957616694301979e-06,
"loss": 0.4893,
"step": 716
},
{
"epoch": 0.97,
"learning_rate": 3.9546472888948825e-06,
"loss": 0.53,
"step": 717
},
{
"epoch": 0.97,
"learning_rate": 3.951674777637979e-06,
"loss": 0.594,
"step": 718
},
{
"epoch": 0.97,
"learning_rate": 3.948699166877946e-06,
"loss": 0.5221,
"step": 719
},
{
"epoch": 0.97,
"learning_rate": 3.945720462968073e-06,
"loss": 0.574,
"step": 720
},
{
"epoch": 0.97,
"learning_rate": 3.942738672268258e-06,
"loss": 0.4762,
"step": 721
},
{
"epoch": 0.98,
"learning_rate": 3.9397538011449896e-06,
"loss": 0.518,
"step": 722
},
{
"epoch": 0.98,
"learning_rate": 3.936765855971332e-06,
"loss": 0.5585,
"step": 723
},
{
"epoch": 0.98,
"learning_rate": 3.933774843126914e-06,
"loss": 0.5688,
"step": 724
},
{
"epoch": 0.98,
"learning_rate": 3.930780768997913e-06,
"loss": 0.4944,
"step": 725
},
{
"epoch": 0.98,
"learning_rate": 3.927783639977043e-06,
"loss": 0.5093,
"step": 726
},
{
"epoch": 0.98,
"learning_rate": 3.924783462463541e-06,
"loss": 0.5191,
"step": 727
},
{
"epoch": 0.98,
"learning_rate": 3.921780242863153e-06,
"loss": 0.5111,
"step": 728
},
{
"epoch": 0.99,
"learning_rate": 3.9187739875881215e-06,
"loss": 0.5262,
"step": 729
},
{
"epoch": 0.99,
"learning_rate": 3.915764703057167e-06,
"loss": 0.5341,
"step": 730
},
{
"epoch": 0.99,
"learning_rate": 3.912752395695481e-06,
"loss": 0.5715,
"step": 731
},
{
"epoch": 0.99,
"learning_rate": 3.909737071934707e-06,
"loss": 0.4842,
"step": 732
},
{
"epoch": 0.99,
"learning_rate": 3.906718738212932e-06,
"loss": 0.5524,
"step": 733
},
{
"epoch": 0.99,
"learning_rate": 3.903697400974665e-06,
"loss": 0.6665,
"step": 734
},
{
"epoch": 0.99,
"learning_rate": 3.9006730666708316e-06,
"loss": 0.4543,
"step": 735
},
{
"epoch": 1.0,
"learning_rate": 3.897645741758755e-06,
"loss": 0.5059,
"step": 736
},
{
"epoch": 1.0,
"learning_rate": 3.894615432702144e-06,
"loss": 0.4965,
"step": 737
},
{
"epoch": 1.0,
"learning_rate": 3.891582145971079e-06,
"loss": 0.452,
"step": 738
},
{
"epoch": 1.0,
"learning_rate": 3.888545888041998e-06,
"loss": 0.4986,
"step": 739
}
],
"logging_steps": 1.0,
"max_steps": 2217,
"num_train_epochs": 3,
"save_steps": 10000.0,
"total_flos": 1.0528895141727437e+18,
"trial_name": null,
"trial_params": null
}