Files
mistral-en-th-translate-v7.…/trainer_state.json
ModelHub XC 6a1496f1f8 初始化项目,由ModelHub XC社区提供模型
Model: scb10x/mistral-en-th-translate-v7.4-ep3
Source: Original Platform
2026-07-03 14:56:12 +08:00

12602 lines
247 KiB
JSON

{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 500,
"global_step": 2097,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 3.0000000000000004e-07,
"loss": 1.3728,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 6.000000000000001e-07,
"loss": 1.3433,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 9e-07,
"loss": 1.2595,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 1.2000000000000002e-06,
"loss": 1.349,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.5e-06,
"loss": 1.1932,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1.8e-06,
"loss": 1.0434,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 2.1e-06,
"loss": 1.0981,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 2.4000000000000003e-06,
"loss": 1.0906,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 2.7e-06,
"loss": 0.9613,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 3e-06,
"loss": 0.9857,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 3.3e-06,
"loss": 0.9342,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 3.6e-06,
"loss": 0.9784,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 3.9e-06,
"loss": 0.8184,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 4.2e-06,
"loss": 0.8974,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 4.5e-06,
"loss": 0.8764,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 4.800000000000001e-06,
"loss": 0.8595,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 5.1e-06,
"loss": 0.81,
"step": 17
},
{
"epoch": 0.03,
"learning_rate": 5.4e-06,
"loss": 0.7368,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 5.7e-06,
"loss": 0.7934,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 6e-06,
"loss": 0.8137,
"step": 20
},
{
"epoch": 0.03,
"learning_rate": 5.999996568231934e-06,
"loss": 0.8093,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 5.99998627293559e-06,
"loss": 0.8365,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 5.999969114134519e-06,
"loss": 0.7956,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 5.999945091867979e-06,
"loss": 0.6646,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 5.999914206190929e-06,
"loss": 0.6623,
"step": 25
},
{
"epoch": 0.04,
"learning_rate": 5.999876457174032e-06,
"loss": 0.597,
"step": 26
},
{
"epoch": 0.04,
"learning_rate": 5.99983184490365e-06,
"loss": 0.698,
"step": 27
},
{
"epoch": 0.04,
"learning_rate": 5.999780369481851e-06,
"loss": 0.7337,
"step": 28
},
{
"epoch": 0.04,
"learning_rate": 5.9997220310264e-06,
"loss": 0.711,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 5.999656829670768e-06,
"loss": 0.6972,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 5.999584765564127e-06,
"loss": 0.7473,
"step": 31
},
{
"epoch": 0.05,
"learning_rate": 5.999505838871346e-06,
"loss": 0.7053,
"step": 32
},
{
"epoch": 0.05,
"learning_rate": 5.999420049772999e-06,
"loss": 0.6369,
"step": 33
},
{
"epoch": 0.05,
"learning_rate": 5.999327398465357e-06,
"loss": 0.6776,
"step": 34
},
{
"epoch": 0.05,
"learning_rate": 5.999227885160392e-06,
"loss": 0.7152,
"step": 35
},
{
"epoch": 0.05,
"learning_rate": 5.999121510085776e-06,
"loss": 0.6827,
"step": 36
},
{
"epoch": 0.05,
"learning_rate": 5.9990082734848776e-06,
"loss": 0.6521,
"step": 37
},
{
"epoch": 0.05,
"learning_rate": 5.998888175616766e-06,
"loss": 0.7099,
"step": 38
},
{
"epoch": 0.06,
"learning_rate": 5.998761216756204e-06,
"loss": 0.651,
"step": 39
},
{
"epoch": 0.06,
"learning_rate": 5.998627397193657e-06,
"loss": 0.5868,
"step": 40
},
{
"epoch": 0.06,
"learning_rate": 5.998486717235281e-06,
"loss": 0.5914,
"step": 41
},
{
"epoch": 0.06,
"learning_rate": 5.99833917720293e-06,
"loss": 0.6515,
"step": 42
},
{
"epoch": 0.06,
"learning_rate": 5.998184777434156e-06,
"loss": 0.644,
"step": 43
},
{
"epoch": 0.06,
"learning_rate": 5.998023518282198e-06,
"loss": 0.6282,
"step": 44
},
{
"epoch": 0.06,
"learning_rate": 5.997855400115994e-06,
"loss": 0.5895,
"step": 45
},
{
"epoch": 0.07,
"learning_rate": 5.997680423320172e-06,
"loss": 0.6466,
"step": 46
},
{
"epoch": 0.07,
"learning_rate": 5.997498588295052e-06,
"loss": 0.6042,
"step": 47
},
{
"epoch": 0.07,
"learning_rate": 5.997309895456643e-06,
"loss": 0.6621,
"step": 48
},
{
"epoch": 0.07,
"learning_rate": 5.997114345236648e-06,
"loss": 0.719,
"step": 49
},
{
"epoch": 0.07,
"learning_rate": 5.996911938082453e-06,
"loss": 0.6207,
"step": 50
},
{
"epoch": 0.07,
"learning_rate": 5.996702674457134e-06,
"loss": 0.7137,
"step": 51
},
{
"epoch": 0.07,
"learning_rate": 5.9964865548394565e-06,
"loss": 0.7262,
"step": 52
},
{
"epoch": 0.08,
"learning_rate": 5.9962635797238665e-06,
"loss": 0.7645,
"step": 53
},
{
"epoch": 0.08,
"learning_rate": 5.9960337496204976e-06,
"loss": 0.5831,
"step": 54
},
{
"epoch": 0.08,
"learning_rate": 5.995797065055166e-06,
"loss": 0.6303,
"step": 55
},
{
"epoch": 0.08,
"learning_rate": 5.995553526569367e-06,
"loss": 0.626,
"step": 56
},
{
"epoch": 0.08,
"learning_rate": 5.995303134720281e-06,
"loss": 0.5947,
"step": 57
},
{
"epoch": 0.08,
"learning_rate": 5.995045890080767e-06,
"loss": 0.687,
"step": 58
},
{
"epoch": 0.08,
"learning_rate": 5.994781793239357e-06,
"loss": 0.5448,
"step": 59
},
{
"epoch": 0.09,
"learning_rate": 5.994510844800268e-06,
"loss": 0.6212,
"step": 60
},
{
"epoch": 0.09,
"learning_rate": 5.994233045383386e-06,
"loss": 0.5216,
"step": 61
},
{
"epoch": 0.09,
"learning_rate": 5.993948395624273e-06,
"loss": 0.6711,
"step": 62
},
{
"epoch": 0.09,
"learning_rate": 5.993656896174165e-06,
"loss": 0.6171,
"step": 63
},
{
"epoch": 0.09,
"learning_rate": 5.993358547699966e-06,
"loss": 0.5687,
"step": 64
},
{
"epoch": 0.09,
"learning_rate": 5.993053350884251e-06,
"loss": 0.6564,
"step": 65
},
{
"epoch": 0.09,
"learning_rate": 5.9927413064252655e-06,
"loss": 0.6048,
"step": 66
},
{
"epoch": 0.1,
"learning_rate": 5.992422415036917e-06,
"loss": 0.6308,
"step": 67
},
{
"epoch": 0.1,
"learning_rate": 5.99209667744878e-06,
"loss": 0.526,
"step": 68
},
{
"epoch": 0.1,
"learning_rate": 5.9917640944060925e-06,
"loss": 0.7224,
"step": 69
},
{
"epoch": 0.1,
"learning_rate": 5.991424666669752e-06,
"loss": 0.6005,
"step": 70
},
{
"epoch": 0.1,
"learning_rate": 5.991078395016317e-06,
"loss": 0.579,
"step": 71
},
{
"epoch": 0.1,
"learning_rate": 5.990725280238004e-06,
"loss": 0.636,
"step": 72
},
{
"epoch": 0.1,
"learning_rate": 5.990365323142685e-06,
"loss": 0.5991,
"step": 73
},
{
"epoch": 0.11,
"learning_rate": 5.989998524553885e-06,
"loss": 0.5697,
"step": 74
},
{
"epoch": 0.11,
"learning_rate": 5.989624885310784e-06,
"loss": 0.6151,
"step": 75
},
{
"epoch": 0.11,
"learning_rate": 5.989244406268211e-06,
"loss": 0.5416,
"step": 76
},
{
"epoch": 0.11,
"learning_rate": 5.988857088296641e-06,
"loss": 0.6208,
"step": 77
},
{
"epoch": 0.11,
"learning_rate": 5.9884629322821985e-06,
"loss": 0.6556,
"step": 78
},
{
"epoch": 0.11,
"learning_rate": 5.988061939126653e-06,
"loss": 0.6059,
"step": 79
},
{
"epoch": 0.11,
"learning_rate": 5.987654109747414e-06,
"loss": 0.5411,
"step": 80
},
{
"epoch": 0.12,
"learning_rate": 5.987239445077531e-06,
"loss": 0.5717,
"step": 81
},
{
"epoch": 0.12,
"learning_rate": 5.986817946065695e-06,
"loss": 0.5762,
"step": 82
},
{
"epoch": 0.12,
"learning_rate": 5.986389613676227e-06,
"loss": 0.6339,
"step": 83
},
{
"epoch": 0.12,
"learning_rate": 5.985954448889089e-06,
"loss": 0.6014,
"step": 84
},
{
"epoch": 0.12,
"learning_rate": 5.985512452699869e-06,
"loss": 0.6185,
"step": 85
},
{
"epoch": 0.12,
"learning_rate": 5.985063626119786e-06,
"loss": 0.5103,
"step": 86
},
{
"epoch": 0.12,
"learning_rate": 5.984607970175685e-06,
"loss": 0.5154,
"step": 87
},
{
"epoch": 0.13,
"learning_rate": 5.984145485910038e-06,
"loss": 0.5931,
"step": 88
},
{
"epoch": 0.13,
"learning_rate": 5.983676174380937e-06,
"loss": 0.5427,
"step": 89
},
{
"epoch": 0.13,
"learning_rate": 5.983200036662094e-06,
"loss": 0.537,
"step": 90
},
{
"epoch": 0.13,
"learning_rate": 5.982717073842838e-06,
"loss": 0.6072,
"step": 91
},
{
"epoch": 0.13,
"learning_rate": 5.9822272870281135e-06,
"loss": 0.5999,
"step": 92
},
{
"epoch": 0.13,
"learning_rate": 5.981730677338478e-06,
"loss": 0.5457,
"step": 93
},
{
"epoch": 0.13,
"learning_rate": 5.9812272459100955e-06,
"loss": 0.6194,
"step": 94
},
{
"epoch": 0.14,
"learning_rate": 5.9807169938947415e-06,
"loss": 0.6601,
"step": 95
},
{
"epoch": 0.14,
"learning_rate": 5.980199922459793e-06,
"loss": 0.5689,
"step": 96
},
{
"epoch": 0.14,
"learning_rate": 5.979676032788229e-06,
"loss": 0.5674,
"step": 97
},
{
"epoch": 0.14,
"learning_rate": 5.979145326078628e-06,
"loss": 0.5382,
"step": 98
},
{
"epoch": 0.14,
"learning_rate": 5.978607803545166e-06,
"loss": 0.5361,
"step": 99
},
{
"epoch": 0.14,
"learning_rate": 5.978063466417611e-06,
"loss": 0.5995,
"step": 100
},
{
"epoch": 0.14,
"learning_rate": 5.977512315941321e-06,
"loss": 0.6182,
"step": 101
},
{
"epoch": 0.15,
"learning_rate": 5.9769543533772435e-06,
"loss": 0.5807,
"step": 102
},
{
"epoch": 0.15,
"learning_rate": 5.9763895800019126e-06,
"loss": 0.5704,
"step": 103
},
{
"epoch": 0.15,
"learning_rate": 5.97581799710744e-06,
"loss": 0.633,
"step": 104
},
{
"epoch": 0.15,
"learning_rate": 5.97523960600152e-06,
"loss": 0.5625,
"step": 105
},
{
"epoch": 0.15,
"learning_rate": 5.974654408007422e-06,
"loss": 0.5691,
"step": 106
},
{
"epoch": 0.15,
"learning_rate": 5.974062404463988e-06,
"loss": 0.5612,
"step": 107
},
{
"epoch": 0.15,
"learning_rate": 5.973463596725631e-06,
"loss": 0.6259,
"step": 108
},
{
"epoch": 0.16,
"learning_rate": 5.972857986162331e-06,
"loss": 0.5406,
"step": 109
},
{
"epoch": 0.16,
"learning_rate": 5.972245574159631e-06,
"loss": 0.5672,
"step": 110
},
{
"epoch": 0.16,
"learning_rate": 5.971626362118635e-06,
"loss": 0.4996,
"step": 111
},
{
"epoch": 0.16,
"learning_rate": 5.971000351456004e-06,
"loss": 0.5107,
"step": 112
},
{
"epoch": 0.16,
"learning_rate": 5.9703675436039524e-06,
"loss": 0.6065,
"step": 113
},
{
"epoch": 0.16,
"learning_rate": 5.96972794001025e-06,
"loss": 0.5807,
"step": 114
},
{
"epoch": 0.16,
"learning_rate": 5.969081542138208e-06,
"loss": 0.4425,
"step": 115
},
{
"epoch": 0.17,
"learning_rate": 5.968428351466687e-06,
"loss": 0.4992,
"step": 116
},
{
"epoch": 0.17,
"learning_rate": 5.967768369490084e-06,
"loss": 0.521,
"step": 117
},
{
"epoch": 0.17,
"learning_rate": 5.967101597718337e-06,
"loss": 0.6316,
"step": 118
},
{
"epoch": 0.17,
"learning_rate": 5.966428037676917e-06,
"loss": 0.5818,
"step": 119
},
{
"epoch": 0.17,
"learning_rate": 5.9657476909068245e-06,
"loss": 0.5236,
"step": 120
},
{
"epoch": 0.17,
"learning_rate": 5.965060558964587e-06,
"loss": 0.4862,
"step": 121
},
{
"epoch": 0.17,
"learning_rate": 5.964366643422259e-06,
"loss": 0.5359,
"step": 122
},
{
"epoch": 0.18,
"learning_rate": 5.963665945867408e-06,
"loss": 0.5774,
"step": 123
},
{
"epoch": 0.18,
"learning_rate": 5.962958467903125e-06,
"loss": 0.543,
"step": 124
},
{
"epoch": 0.18,
"learning_rate": 5.9622442111480095e-06,
"loss": 0.5485,
"step": 125
},
{
"epoch": 0.18,
"learning_rate": 5.961523177236169e-06,
"loss": 0.6129,
"step": 126
},
{
"epoch": 0.18,
"learning_rate": 5.960795367817219e-06,
"loss": 0.6115,
"step": 127
},
{
"epoch": 0.18,
"learning_rate": 5.9600607845562744e-06,
"loss": 0.5865,
"step": 128
},
{
"epoch": 0.18,
"learning_rate": 5.959319429133947e-06,
"loss": 0.5034,
"step": 129
},
{
"epoch": 0.19,
"learning_rate": 5.958571303246346e-06,
"loss": 0.6086,
"step": 130
},
{
"epoch": 0.19,
"learning_rate": 5.957816408605066e-06,
"loss": 0.5931,
"step": 131
},
{
"epoch": 0.19,
"learning_rate": 5.957054746937189e-06,
"loss": 0.5843,
"step": 132
},
{
"epoch": 0.19,
"learning_rate": 5.95628631998528e-06,
"loss": 0.5659,
"step": 133
},
{
"epoch": 0.19,
"learning_rate": 5.95551112950738e-06,
"loss": 0.4721,
"step": 134
},
{
"epoch": 0.19,
"learning_rate": 5.954729177277007e-06,
"loss": 0.4916,
"step": 135
},
{
"epoch": 0.19,
"learning_rate": 5.953940465083145e-06,
"loss": 0.5495,
"step": 136
},
{
"epoch": 0.2,
"learning_rate": 5.953144994730246e-06,
"loss": 0.5408,
"step": 137
},
{
"epoch": 0.2,
"learning_rate": 5.952342768038222e-06,
"loss": 0.6165,
"step": 138
},
{
"epoch": 0.2,
"learning_rate": 5.951533786842446e-06,
"loss": 0.541,
"step": 139
},
{
"epoch": 0.2,
"learning_rate": 5.950718052993741e-06,
"loss": 0.5711,
"step": 140
},
{
"epoch": 0.2,
"learning_rate": 5.949895568358378e-06,
"loss": 0.4726,
"step": 141
},
{
"epoch": 0.2,
"learning_rate": 5.9490663348180775e-06,
"loss": 0.522,
"step": 142
},
{
"epoch": 0.2,
"learning_rate": 5.948230354269997e-06,
"loss": 0.6605,
"step": 143
},
{
"epoch": 0.21,
"learning_rate": 5.947387628626728e-06,
"loss": 0.5183,
"step": 144
},
{
"epoch": 0.21,
"learning_rate": 5.9465381598163e-06,
"loss": 0.6753,
"step": 145
},
{
"epoch": 0.21,
"learning_rate": 5.945681949782165e-06,
"loss": 0.5352,
"step": 146
},
{
"epoch": 0.21,
"learning_rate": 5.944819000483198e-06,
"loss": 0.4159,
"step": 147
},
{
"epoch": 0.21,
"learning_rate": 5.9439493138936964e-06,
"loss": 0.5175,
"step": 148
},
{
"epoch": 0.21,
"learning_rate": 5.9430728920033655e-06,
"loss": 0.4859,
"step": 149
},
{
"epoch": 0.21,
"learning_rate": 5.942189736817325e-06,
"loss": 0.4897,
"step": 150
},
{
"epoch": 0.22,
"learning_rate": 5.941299850356096e-06,
"loss": 0.6346,
"step": 151
},
{
"epoch": 0.22,
"learning_rate": 5.940403234655603e-06,
"loss": 0.6062,
"step": 152
},
{
"epoch": 0.22,
"learning_rate": 5.939499891767162e-06,
"loss": 0.5384,
"step": 153
},
{
"epoch": 0.22,
"learning_rate": 5.938589823757484e-06,
"loss": 0.5179,
"step": 154
},
{
"epoch": 0.22,
"learning_rate": 5.937673032708662e-06,
"loss": 0.5203,
"step": 155
},
{
"epoch": 0.22,
"learning_rate": 5.9367495207181725e-06,
"loss": 0.6493,
"step": 156
},
{
"epoch": 0.22,
"learning_rate": 5.93581928989887e-06,
"loss": 0.5057,
"step": 157
},
{
"epoch": 0.23,
"learning_rate": 5.934882342378976e-06,
"loss": 0.4281,
"step": 158
},
{
"epoch": 0.23,
"learning_rate": 5.933938680302084e-06,
"loss": 0.544,
"step": 159
},
{
"epoch": 0.23,
"learning_rate": 5.9329883058271455e-06,
"loss": 0.5327,
"step": 160
},
{
"epoch": 0.23,
"learning_rate": 5.93203122112847e-06,
"loss": 0.5584,
"step": 161
},
{
"epoch": 0.23,
"learning_rate": 5.93106742839572e-06,
"loss": 0.5904,
"step": 162
},
{
"epoch": 0.23,
"learning_rate": 5.930096929833905e-06,
"loss": 0.5261,
"step": 163
},
{
"epoch": 0.23,
"learning_rate": 5.929119727663375e-06,
"loss": 0.5719,
"step": 164
},
{
"epoch": 0.24,
"learning_rate": 5.928135824119817e-06,
"loss": 0.4904,
"step": 165
},
{
"epoch": 0.24,
"learning_rate": 5.92714522145425e-06,
"loss": 0.5359,
"step": 166
},
{
"epoch": 0.24,
"learning_rate": 5.926147921933021e-06,
"loss": 0.6273,
"step": 167
},
{
"epoch": 0.24,
"learning_rate": 5.925143927837796e-06,
"loss": 0.4773,
"step": 168
},
{
"epoch": 0.24,
"learning_rate": 5.9241332414655585e-06,
"loss": 0.524,
"step": 169
},
{
"epoch": 0.24,
"learning_rate": 5.923115865128603e-06,
"loss": 0.5378,
"step": 170
},
{
"epoch": 0.24,
"learning_rate": 5.922091801154529e-06,
"loss": 0.613,
"step": 171
},
{
"epoch": 0.25,
"learning_rate": 5.921061051886236e-06,
"loss": 0.5478,
"step": 172
},
{
"epoch": 0.25,
"learning_rate": 5.92002361968192e-06,
"loss": 0.4592,
"step": 173
},
{
"epoch": 0.25,
"learning_rate": 5.918979506915065e-06,
"loss": 0.495,
"step": 174
},
{
"epoch": 0.25,
"learning_rate": 5.917928715974439e-06,
"loss": 0.5839,
"step": 175
},
{
"epoch": 0.25,
"learning_rate": 5.91687124926409e-06,
"loss": 0.5062,
"step": 176
},
{
"epoch": 0.25,
"learning_rate": 5.915807109203338e-06,
"loss": 0.5093,
"step": 177
},
{
"epoch": 0.25,
"learning_rate": 5.9147362982267715e-06,
"loss": 0.5157,
"step": 178
},
{
"epoch": 0.26,
"learning_rate": 5.913658818784239e-06,
"loss": 0.5065,
"step": 179
},
{
"epoch": 0.26,
"learning_rate": 5.9125746733408485e-06,
"loss": 0.5495,
"step": 180
},
{
"epoch": 0.26,
"learning_rate": 5.911483864376956e-06,
"loss": 0.7047,
"step": 181
},
{
"epoch": 0.26,
"learning_rate": 5.9103863943881645e-06,
"loss": 0.4837,
"step": 182
},
{
"epoch": 0.26,
"learning_rate": 5.9092822658853144e-06,
"loss": 0.482,
"step": 183
},
{
"epoch": 0.26,
"learning_rate": 5.9081714813944825e-06,
"loss": 0.4884,
"step": 184
},
{
"epoch": 0.26,
"learning_rate": 5.907054043456972e-06,
"loss": 0.5998,
"step": 185
},
{
"epoch": 0.27,
"learning_rate": 5.905929954629306e-06,
"loss": 0.5446,
"step": 186
},
{
"epoch": 0.27,
"learning_rate": 5.904799217483229e-06,
"loss": 0.6245,
"step": 187
},
{
"epoch": 0.27,
"learning_rate": 5.903661834605689e-06,
"loss": 0.6359,
"step": 188
},
{
"epoch": 0.27,
"learning_rate": 5.9025178085988456e-06,
"loss": 0.5743,
"step": 189
},
{
"epoch": 0.27,
"learning_rate": 5.901367142080053e-06,
"loss": 0.5549,
"step": 190
},
{
"epoch": 0.27,
"learning_rate": 5.900209837681856e-06,
"loss": 0.5068,
"step": 191
},
{
"epoch": 0.27,
"learning_rate": 5.89904589805199e-06,
"loss": 0.4905,
"step": 192
},
{
"epoch": 0.28,
"learning_rate": 5.897875325853367e-06,
"loss": 0.5275,
"step": 193
},
{
"epoch": 0.28,
"learning_rate": 5.896698123764079e-06,
"loss": 0.5228,
"step": 194
},
{
"epoch": 0.28,
"learning_rate": 5.8955142944773786e-06,
"loss": 0.5026,
"step": 195
},
{
"epoch": 0.28,
"learning_rate": 5.894323840701686e-06,
"loss": 0.4724,
"step": 196
},
{
"epoch": 0.28,
"learning_rate": 5.8931267651605745e-06,
"loss": 0.4206,
"step": 197
},
{
"epoch": 0.28,
"learning_rate": 5.891923070592768e-06,
"loss": 0.4649,
"step": 198
},
{
"epoch": 0.28,
"learning_rate": 5.890712759752134e-06,
"loss": 0.5731,
"step": 199
},
{
"epoch": 0.29,
"learning_rate": 5.8894958354076765e-06,
"loss": 0.5392,
"step": 200
},
{
"epoch": 0.29,
"learning_rate": 5.88827230034353e-06,
"loss": 0.592,
"step": 201
},
{
"epoch": 0.29,
"learning_rate": 5.887042157358954e-06,
"loss": 0.4699,
"step": 202
},
{
"epoch": 0.29,
"learning_rate": 5.885805409268325e-06,
"loss": 0.4438,
"step": 203
},
{
"epoch": 0.29,
"learning_rate": 5.88456205890113e-06,
"loss": 0.5111,
"step": 204
},
{
"epoch": 0.29,
"learning_rate": 5.883312109101966e-06,
"loss": 0.4526,
"step": 205
},
{
"epoch": 0.29,
"learning_rate": 5.8820555627305205e-06,
"loss": 0.458,
"step": 206
},
{
"epoch": 0.3,
"learning_rate": 5.8807924226615805e-06,
"loss": 0.4888,
"step": 207
},
{
"epoch": 0.3,
"learning_rate": 5.8795226917850145e-06,
"loss": 0.5094,
"step": 208
},
{
"epoch": 0.3,
"learning_rate": 5.87824637300577e-06,
"loss": 0.4927,
"step": 209
},
{
"epoch": 0.3,
"learning_rate": 5.876963469243867e-06,
"loss": 0.5839,
"step": 210
},
{
"epoch": 0.3,
"learning_rate": 5.875673983434391e-06,
"loss": 0.594,
"step": 211
},
{
"epoch": 0.3,
"learning_rate": 5.874377918527486e-06,
"loss": 0.5922,
"step": 212
},
{
"epoch": 0.3,
"learning_rate": 5.873075277488349e-06,
"loss": 0.4832,
"step": 213
},
{
"epoch": 0.31,
"learning_rate": 5.871766063297219e-06,
"loss": 0.4888,
"step": 214
},
{
"epoch": 0.31,
"learning_rate": 5.870450278949379e-06,
"loss": 0.4728,
"step": 215
},
{
"epoch": 0.31,
"learning_rate": 5.869127927455138e-06,
"loss": 0.5382,
"step": 216
},
{
"epoch": 0.31,
"learning_rate": 5.867799011839831e-06,
"loss": 0.4764,
"step": 217
},
{
"epoch": 0.31,
"learning_rate": 5.866463535143814e-06,
"loss": 0.497,
"step": 218
},
{
"epoch": 0.31,
"learning_rate": 5.8651215004224505e-06,
"loss": 0.5501,
"step": 219
},
{
"epoch": 0.31,
"learning_rate": 5.8637729107461054e-06,
"loss": 0.487,
"step": 220
},
{
"epoch": 0.32,
"learning_rate": 5.862417769200147e-06,
"loss": 0.5143,
"step": 221
},
{
"epoch": 0.32,
"learning_rate": 5.861056078884927e-06,
"loss": 0.4817,
"step": 222
},
{
"epoch": 0.32,
"learning_rate": 5.859687842915785e-06,
"loss": 0.5086,
"step": 223
},
{
"epoch": 0.32,
"learning_rate": 5.858313064423031e-06,
"loss": 0.5173,
"step": 224
},
{
"epoch": 0.32,
"learning_rate": 5.8569317465519465e-06,
"loss": 0.4462,
"step": 225
},
{
"epoch": 0.32,
"learning_rate": 5.855543892462774e-06,
"loss": 0.5658,
"step": 226
},
{
"epoch": 0.32,
"learning_rate": 5.854149505330708e-06,
"loss": 0.5682,
"step": 227
},
{
"epoch": 0.33,
"learning_rate": 5.8527485883458905e-06,
"loss": 0.4515,
"step": 228
},
{
"epoch": 0.33,
"learning_rate": 5.851341144713404e-06,
"loss": 0.4577,
"step": 229
},
{
"epoch": 0.33,
"learning_rate": 5.84992717765326e-06,
"loss": 0.4997,
"step": 230
},
{
"epoch": 0.33,
"learning_rate": 5.8485066904004e-06,
"loss": 0.5358,
"step": 231
},
{
"epoch": 0.33,
"learning_rate": 5.847079686204674e-06,
"loss": 0.5506,
"step": 232
},
{
"epoch": 0.33,
"learning_rate": 5.845646168330851e-06,
"loss": 0.557,
"step": 233
},
{
"epoch": 0.33,
"learning_rate": 5.844206140058599e-06,
"loss": 0.4143,
"step": 234
},
{
"epoch": 0.34,
"learning_rate": 5.842759604682476e-06,
"loss": 0.4527,
"step": 235
},
{
"epoch": 0.34,
"learning_rate": 5.841306565511935e-06,
"loss": 0.495,
"step": 236
},
{
"epoch": 0.34,
"learning_rate": 5.839847025871303e-06,
"loss": 0.4606,
"step": 237
},
{
"epoch": 0.34,
"learning_rate": 5.838380989099782e-06,
"loss": 0.4318,
"step": 238
},
{
"epoch": 0.34,
"learning_rate": 5.836908458551435e-06,
"loss": 0.4564,
"step": 239
},
{
"epoch": 0.34,
"learning_rate": 5.835429437595187e-06,
"loss": 0.5563,
"step": 240
},
{
"epoch": 0.34,
"learning_rate": 5.833943929614809e-06,
"loss": 0.5469,
"step": 241
},
{
"epoch": 0.35,
"learning_rate": 5.832451938008912e-06,
"loss": 0.5073,
"step": 242
},
{
"epoch": 0.35,
"learning_rate": 5.830953466190943e-06,
"loss": 0.5266,
"step": 243
},
{
"epoch": 0.35,
"learning_rate": 5.829448517589174e-06,
"loss": 0.4524,
"step": 244
},
{
"epoch": 0.35,
"learning_rate": 5.827937095646695e-06,
"loss": 0.527,
"step": 245
},
{
"epoch": 0.35,
"learning_rate": 5.826419203821406e-06,
"loss": 0.5655,
"step": 246
},
{
"epoch": 0.35,
"learning_rate": 5.824894845586007e-06,
"loss": 0.4384,
"step": 247
},
{
"epoch": 0.35,
"learning_rate": 5.823364024427995e-06,
"loss": 0.4923,
"step": 248
},
{
"epoch": 0.36,
"learning_rate": 5.821826743849652e-06,
"loss": 0.4933,
"step": 249
},
{
"epoch": 0.36,
"learning_rate": 5.820283007368039e-06,
"loss": 0.47,
"step": 250
},
{
"epoch": 0.36,
"learning_rate": 5.818732818514985e-06,
"loss": 0.502,
"step": 251
},
{
"epoch": 0.36,
"learning_rate": 5.817176180837083e-06,
"loss": 0.484,
"step": 252
},
{
"epoch": 0.36,
"learning_rate": 5.815613097895681e-06,
"loss": 0.4331,
"step": 253
},
{
"epoch": 0.36,
"learning_rate": 5.814043573266867e-06,
"loss": 0.4021,
"step": 254
},
{
"epoch": 0.36,
"learning_rate": 5.812467610541476e-06,
"loss": 0.4464,
"step": 255
},
{
"epoch": 0.37,
"learning_rate": 5.810885213325062e-06,
"loss": 0.4667,
"step": 256
},
{
"epoch": 0.37,
"learning_rate": 5.809296385237908e-06,
"loss": 0.487,
"step": 257
},
{
"epoch": 0.37,
"learning_rate": 5.807701129915006e-06,
"loss": 0.5105,
"step": 258
},
{
"epoch": 0.37,
"learning_rate": 5.806099451006055e-06,
"loss": 0.4802,
"step": 259
},
{
"epoch": 0.37,
"learning_rate": 5.804491352175447e-06,
"loss": 0.6026,
"step": 260
},
{
"epoch": 0.37,
"learning_rate": 5.802876837102264e-06,
"loss": 0.5987,
"step": 261
},
{
"epoch": 0.37,
"learning_rate": 5.801255909480267e-06,
"loss": 0.502,
"step": 262
},
{
"epoch": 0.38,
"learning_rate": 5.799628573017887e-06,
"loss": 0.4337,
"step": 263
},
{
"epoch": 0.38,
"learning_rate": 5.79799483143822e-06,
"loss": 0.5235,
"step": 264
},
{
"epoch": 0.38,
"learning_rate": 5.7963546884790124e-06,
"loss": 0.5353,
"step": 265
},
{
"epoch": 0.38,
"learning_rate": 5.794708147892659e-06,
"loss": 0.5195,
"step": 266
},
{
"epoch": 0.38,
"learning_rate": 5.793055213446188e-06,
"loss": 0.5742,
"step": 267
},
{
"epoch": 0.38,
"learning_rate": 5.791395888921261e-06,
"loss": 0.4578,
"step": 268
},
{
"epoch": 0.38,
"learning_rate": 5.789730178114152e-06,
"loss": 0.4479,
"step": 269
},
{
"epoch": 0.39,
"learning_rate": 5.788058084835753e-06,
"loss": 0.4366,
"step": 270
},
{
"epoch": 0.39,
"learning_rate": 5.7863796129115535e-06,
"loss": 0.473,
"step": 271
},
{
"epoch": 0.39,
"learning_rate": 5.7846947661816375e-06,
"loss": 0.4549,
"step": 272
},
{
"epoch": 0.39,
"learning_rate": 5.783003548500676e-06,
"loss": 0.455,
"step": 273
},
{
"epoch": 0.39,
"learning_rate": 5.78130596373791e-06,
"loss": 0.6019,
"step": 274
},
{
"epoch": 0.39,
"learning_rate": 5.7796020157771535e-06,
"loss": 0.5117,
"step": 275
},
{
"epoch": 0.39,
"learning_rate": 5.777891708516776e-06,
"loss": 0.4644,
"step": 276
},
{
"epoch": 0.4,
"learning_rate": 5.776175045869694e-06,
"loss": 0.5412,
"step": 277
},
{
"epoch": 0.4,
"learning_rate": 5.774452031763369e-06,
"loss": 0.4978,
"step": 278
},
{
"epoch": 0.4,
"learning_rate": 5.7727226701397885e-06,
"loss": 0.4694,
"step": 279
},
{
"epoch": 0.4,
"learning_rate": 5.770986964955466e-06,
"loss": 0.4606,
"step": 280
},
{
"epoch": 0.4,
"learning_rate": 5.769244920181424e-06,
"loss": 0.4694,
"step": 281
},
{
"epoch": 0.4,
"learning_rate": 5.767496539803196e-06,
"loss": 0.3937,
"step": 282
},
{
"epoch": 0.4,
"learning_rate": 5.765741827820802e-06,
"loss": 0.547,
"step": 283
},
{
"epoch": 0.41,
"learning_rate": 5.763980788248754e-06,
"loss": 0.6174,
"step": 284
},
{
"epoch": 0.41,
"learning_rate": 5.762213425116037e-06,
"loss": 0.5587,
"step": 285
},
{
"epoch": 0.41,
"learning_rate": 5.760439742466106e-06,
"loss": 0.5126,
"step": 286
},
{
"epoch": 0.41,
"learning_rate": 5.7586597443568695e-06,
"loss": 0.4732,
"step": 287
},
{
"epoch": 0.41,
"learning_rate": 5.756873434860692e-06,
"loss": 0.5621,
"step": 288
},
{
"epoch": 0.41,
"learning_rate": 5.755080818064371e-06,
"loss": 0.4327,
"step": 289
},
{
"epoch": 0.41,
"learning_rate": 5.753281898069138e-06,
"loss": 0.4823,
"step": 290
},
{
"epoch": 0.42,
"learning_rate": 5.751476678990641e-06,
"loss": 0.4961,
"step": 291
},
{
"epoch": 0.42,
"learning_rate": 5.749665164958945e-06,
"loss": 0.44,
"step": 292
},
{
"epoch": 0.42,
"learning_rate": 5.7478473601185136e-06,
"loss": 0.5074,
"step": 293
},
{
"epoch": 0.42,
"learning_rate": 5.746023268628202e-06,
"loss": 0.551,
"step": 294
},
{
"epoch": 0.42,
"learning_rate": 5.74419289466125e-06,
"loss": 0.4976,
"step": 295
},
{
"epoch": 0.42,
"learning_rate": 5.74235624240527e-06,
"loss": 0.5112,
"step": 296
},
{
"epoch": 0.42,
"learning_rate": 5.74051331606224e-06,
"loss": 0.4624,
"step": 297
},
{
"epoch": 0.43,
"learning_rate": 5.738664119848488e-06,
"loss": 0.5235,
"step": 298
},
{
"epoch": 0.43,
"learning_rate": 5.7368086579946905e-06,
"loss": 0.4711,
"step": 299
},
{
"epoch": 0.43,
"learning_rate": 5.7349469347458575e-06,
"loss": 0.5297,
"step": 300
},
{
"epoch": 0.43,
"learning_rate": 5.733078954361322e-06,
"loss": 0.5247,
"step": 301
},
{
"epoch": 0.43,
"learning_rate": 5.731204721114737e-06,
"loss": 0.5439,
"step": 302
},
{
"epoch": 0.43,
"learning_rate": 5.7293242392940575e-06,
"loss": 0.5285,
"step": 303
},
{
"epoch": 0.43,
"learning_rate": 5.727437513201534e-06,
"loss": 0.4981,
"step": 304
},
{
"epoch": 0.44,
"learning_rate": 5.725544547153705e-06,
"loss": 0.4488,
"step": 305
},
{
"epoch": 0.44,
"learning_rate": 5.723645345481384e-06,
"loss": 0.5299,
"step": 306
},
{
"epoch": 0.44,
"learning_rate": 5.721739912529651e-06,
"loss": 0.4434,
"step": 307
},
{
"epoch": 0.44,
"learning_rate": 5.719828252657842e-06,
"loss": 0.4923,
"step": 308
},
{
"epoch": 0.44,
"learning_rate": 5.717910370239538e-06,
"loss": 0.5326,
"step": 309
},
{
"epoch": 0.44,
"learning_rate": 5.7159862696625585e-06,
"loss": 0.4671,
"step": 310
},
{
"epoch": 0.44,
"learning_rate": 5.714055955328947e-06,
"loss": 0.5157,
"step": 311
},
{
"epoch": 0.45,
"learning_rate": 5.712119431654967e-06,
"loss": 0.5061,
"step": 312
},
{
"epoch": 0.45,
"learning_rate": 5.710176703071083e-06,
"loss": 0.4856,
"step": 313
},
{
"epoch": 0.45,
"learning_rate": 5.708227774021958e-06,
"loss": 0.496,
"step": 314
},
{
"epoch": 0.45,
"learning_rate": 5.706272648966439e-06,
"loss": 0.4369,
"step": 315
},
{
"epoch": 0.45,
"learning_rate": 5.704311332377552e-06,
"loss": 0.4283,
"step": 316
},
{
"epoch": 0.45,
"learning_rate": 5.702343828742485e-06,
"loss": 0.5402,
"step": 317
},
{
"epoch": 0.45,
"learning_rate": 5.700370142562582e-06,
"loss": 0.464,
"step": 318
},
{
"epoch": 0.46,
"learning_rate": 5.698390278353334e-06,
"loss": 0.449,
"step": 319
},
{
"epoch": 0.46,
"learning_rate": 5.69640424064436e-06,
"loss": 0.4713,
"step": 320
},
{
"epoch": 0.46,
"learning_rate": 5.694412033979411e-06,
"loss": 0.4858,
"step": 321
},
{
"epoch": 0.46,
"learning_rate": 5.692413662916345e-06,
"loss": 0.4065,
"step": 322
},
{
"epoch": 0.46,
"learning_rate": 5.690409132027129e-06,
"loss": 0.5034,
"step": 323
},
{
"epoch": 0.46,
"learning_rate": 5.688398445897817e-06,
"loss": 0.4979,
"step": 324
},
{
"epoch": 0.46,
"learning_rate": 5.686381609128548e-06,
"loss": 0.5714,
"step": 325
},
{
"epoch": 0.47,
"learning_rate": 5.684358626333535e-06,
"loss": 0.5179,
"step": 326
},
{
"epoch": 0.47,
"learning_rate": 5.682329502141048e-06,
"loss": 0.5197,
"step": 327
},
{
"epoch": 0.47,
"learning_rate": 5.68029424119341e-06,
"loss": 0.4192,
"step": 328
},
{
"epoch": 0.47,
"learning_rate": 5.6782528481469835e-06,
"loss": 0.4912,
"step": 329
},
{
"epoch": 0.47,
"learning_rate": 5.676205327672159e-06,
"loss": 0.4895,
"step": 330
},
{
"epoch": 0.47,
"learning_rate": 5.674151684453349e-06,
"loss": 0.5114,
"step": 331
},
{
"epoch": 0.47,
"learning_rate": 5.6720919231889696e-06,
"loss": 0.4062,
"step": 332
},
{
"epoch": 0.48,
"learning_rate": 5.670026048591437e-06,
"loss": 0.5049,
"step": 333
},
{
"epoch": 0.48,
"learning_rate": 5.667954065387153e-06,
"loss": 0.5127,
"step": 334
},
{
"epoch": 0.48,
"learning_rate": 5.665875978316493e-06,
"loss": 0.4005,
"step": 335
},
{
"epoch": 0.48,
"learning_rate": 5.663791792133801e-06,
"loss": 0.5004,
"step": 336
},
{
"epoch": 0.48,
"learning_rate": 5.661701511607373e-06,
"loss": 0.5025,
"step": 337
},
{
"epoch": 0.48,
"learning_rate": 5.659605141519445e-06,
"loss": 0.3864,
"step": 338
},
{
"epoch": 0.48,
"learning_rate": 5.657502686666191e-06,
"loss": 0.515,
"step": 339
},
{
"epoch": 0.49,
"learning_rate": 5.655394151857699e-06,
"loss": 0.4819,
"step": 340
},
{
"epoch": 0.49,
"learning_rate": 5.6532795419179744e-06,
"loss": 0.4826,
"step": 341
},
{
"epoch": 0.49,
"learning_rate": 5.651158861684915e-06,
"loss": 0.5299,
"step": 342
},
{
"epoch": 0.49,
"learning_rate": 5.649032116010311e-06,
"loss": 0.4516,
"step": 343
},
{
"epoch": 0.49,
"learning_rate": 5.646899309759825e-06,
"loss": 0.4405,
"step": 344
},
{
"epoch": 0.49,
"learning_rate": 5.6447604478129915e-06,
"loss": 0.4961,
"step": 345
},
{
"epoch": 0.49,
"learning_rate": 5.642615535063194e-06,
"loss": 0.5255,
"step": 346
},
{
"epoch": 0.5,
"learning_rate": 5.640464576417661e-06,
"loss": 0.4904,
"step": 347
},
{
"epoch": 0.5,
"learning_rate": 5.638307576797453e-06,
"loss": 0.5038,
"step": 348
},
{
"epoch": 0.5,
"learning_rate": 5.636144541137453e-06,
"loss": 0.5798,
"step": 349
},
{
"epoch": 0.5,
"learning_rate": 5.6339754743863516e-06,
"loss": 0.4814,
"step": 350
},
{
"epoch": 0.5,
"learning_rate": 5.631800381506638e-06,
"loss": 0.4326,
"step": 351
},
{
"epoch": 0.5,
"learning_rate": 5.6296192674745874e-06,
"loss": 0.531,
"step": 352
},
{
"epoch": 0.51,
"learning_rate": 5.627432137280253e-06,
"loss": 0.3814,
"step": 353
},
{
"epoch": 0.51,
"learning_rate": 5.62523899592745e-06,
"loss": 0.5805,
"step": 354
},
{
"epoch": 0.51,
"learning_rate": 5.623039848433746e-06,
"loss": 0.5217,
"step": 355
},
{
"epoch": 0.51,
"learning_rate": 5.6208346998304525e-06,
"loss": 0.5043,
"step": 356
},
{
"epoch": 0.51,
"learning_rate": 5.618623555162606e-06,
"loss": 0.5035,
"step": 357
},
{
"epoch": 0.51,
"learning_rate": 5.616406419488964e-06,
"loss": 0.5084,
"step": 358
},
{
"epoch": 0.51,
"learning_rate": 5.614183297881993e-06,
"loss": 0.3744,
"step": 359
},
{
"epoch": 0.52,
"learning_rate": 5.611954195427847e-06,
"loss": 0.4984,
"step": 360
},
{
"epoch": 0.52,
"learning_rate": 5.609719117226371e-06,
"loss": 0.4334,
"step": 361
},
{
"epoch": 0.52,
"learning_rate": 5.607478068391077e-06,
"loss": 0.527,
"step": 362
},
{
"epoch": 0.52,
"learning_rate": 5.60523105404914e-06,
"loss": 0.4892,
"step": 363
},
{
"epoch": 0.52,
"learning_rate": 5.602978079341378e-06,
"loss": 0.5266,
"step": 364
},
{
"epoch": 0.52,
"learning_rate": 5.600719149422251e-06,
"loss": 0.4671,
"step": 365
},
{
"epoch": 0.52,
"learning_rate": 5.598454269459842e-06,
"loss": 0.4781,
"step": 366
},
{
"epoch": 0.53,
"learning_rate": 5.596183444635845e-06,
"loss": 0.5074,
"step": 367
},
{
"epoch": 0.53,
"learning_rate": 5.5939066801455554e-06,
"loss": 0.3877,
"step": 368
},
{
"epoch": 0.53,
"learning_rate": 5.5916239811978606e-06,
"loss": 0.441,
"step": 369
},
{
"epoch": 0.53,
"learning_rate": 5.589335353015221e-06,
"loss": 0.409,
"step": 370
},
{
"epoch": 0.53,
"learning_rate": 5.587040800833664e-06,
"loss": 0.4811,
"step": 371
},
{
"epoch": 0.53,
"learning_rate": 5.584740329902771e-06,
"loss": 0.4585,
"step": 372
},
{
"epoch": 0.53,
"learning_rate": 5.582433945485663e-06,
"loss": 0.3881,
"step": 373
},
{
"epoch": 0.54,
"learning_rate": 5.5801216528589926e-06,
"loss": 0.4246,
"step": 374
},
{
"epoch": 0.54,
"learning_rate": 5.577803457312926e-06,
"loss": 0.484,
"step": 375
},
{
"epoch": 0.54,
"learning_rate": 5.5754793641511364e-06,
"loss": 0.5489,
"step": 376
},
{
"epoch": 0.54,
"learning_rate": 5.5731493786907895e-06,
"loss": 0.5169,
"step": 377
},
{
"epoch": 0.54,
"learning_rate": 5.570813506262533e-06,
"loss": 0.4702,
"step": 378
},
{
"epoch": 0.54,
"learning_rate": 5.568471752210481e-06,
"loss": 0.5406,
"step": 379
},
{
"epoch": 0.54,
"learning_rate": 5.566124121892204e-06,
"loss": 0.3726,
"step": 380
},
{
"epoch": 0.55,
"learning_rate": 5.563770620678719e-06,
"loss": 0.5249,
"step": 381
},
{
"epoch": 0.55,
"learning_rate": 5.5614112539544705e-06,
"loss": 0.4901,
"step": 382
},
{
"epoch": 0.55,
"learning_rate": 5.559046027117327e-06,
"loss": 0.505,
"step": 383
},
{
"epoch": 0.55,
"learning_rate": 5.5566749455785605e-06,
"loss": 0.4494,
"step": 384
},
{
"epoch": 0.55,
"learning_rate": 5.55429801476284e-06,
"loss": 0.4665,
"step": 385
},
{
"epoch": 0.55,
"learning_rate": 5.551915240108214e-06,
"loss": 0.4716,
"step": 386
},
{
"epoch": 0.55,
"learning_rate": 5.5495266270661026e-06,
"loss": 0.5059,
"step": 387
},
{
"epoch": 0.56,
"learning_rate": 5.547132181101285e-06,
"loss": 0.4208,
"step": 388
},
{
"epoch": 0.56,
"learning_rate": 5.544731907691882e-06,
"loss": 0.4222,
"step": 389
},
{
"epoch": 0.56,
"learning_rate": 5.542325812329348e-06,
"loss": 0.4797,
"step": 390
},
{
"epoch": 0.56,
"learning_rate": 5.539913900518458e-06,
"loss": 0.4928,
"step": 391
},
{
"epoch": 0.56,
"learning_rate": 5.537496177777292e-06,
"loss": 0.4272,
"step": 392
},
{
"epoch": 0.56,
"learning_rate": 5.535072649637227e-06,
"loss": 0.4793,
"step": 393
},
{
"epoch": 0.56,
"learning_rate": 5.53264332164292e-06,
"loss": 0.4004,
"step": 394
},
{
"epoch": 0.57,
"learning_rate": 5.530208199352299e-06,
"loss": 0.4911,
"step": 395
},
{
"epoch": 0.57,
"learning_rate": 5.5277672883365446e-06,
"loss": 0.5294,
"step": 396
},
{
"epoch": 0.57,
"learning_rate": 5.525320594180085e-06,
"loss": 0.5181,
"step": 397
},
{
"epoch": 0.57,
"learning_rate": 5.52286812248058e-06,
"loss": 0.4322,
"step": 398
},
{
"epoch": 0.57,
"learning_rate": 5.520409878848904e-06,
"loss": 0.567,
"step": 399
},
{
"epoch": 0.57,
"learning_rate": 5.517945868909138e-06,
"loss": 0.3809,
"step": 400
},
{
"epoch": 0.57,
"learning_rate": 5.5154760982985565e-06,
"loss": 0.6226,
"step": 401
},
{
"epoch": 0.58,
"learning_rate": 5.513000572667612e-06,
"loss": 0.3994,
"step": 402
},
{
"epoch": 0.58,
"learning_rate": 5.510519297679926e-06,
"loss": 0.4482,
"step": 403
},
{
"epoch": 0.58,
"learning_rate": 5.50803227901227e-06,
"loss": 0.4766,
"step": 404
},
{
"epoch": 0.58,
"learning_rate": 5.505539522354559e-06,
"loss": 0.5381,
"step": 405
},
{
"epoch": 0.58,
"learning_rate": 5.503041033409836e-06,
"loss": 0.5029,
"step": 406
},
{
"epoch": 0.58,
"learning_rate": 5.500536817894254e-06,
"loss": 0.4606,
"step": 407
},
{
"epoch": 0.58,
"learning_rate": 5.498026881537075e-06,
"loss": 0.4889,
"step": 408
},
{
"epoch": 0.59,
"learning_rate": 5.495511230080643e-06,
"loss": 0.4496,
"step": 409
},
{
"epoch": 0.59,
"learning_rate": 5.49298986928038e-06,
"loss": 0.4331,
"step": 410
},
{
"epoch": 0.59,
"learning_rate": 5.49046280490477e-06,
"loss": 0.5755,
"step": 411
},
{
"epoch": 0.59,
"learning_rate": 5.487930042735345e-06,
"loss": 0.5353,
"step": 412
},
{
"epoch": 0.59,
"learning_rate": 5.485391588566672e-06,
"loss": 0.4559,
"step": 413
},
{
"epoch": 0.59,
"learning_rate": 5.482847448206345e-06,
"loss": 0.5054,
"step": 414
},
{
"epoch": 0.59,
"learning_rate": 5.48029762747496e-06,
"loss": 0.4516,
"step": 415
},
{
"epoch": 0.6,
"learning_rate": 5.477742132206115e-06,
"loss": 0.4858,
"step": 416
},
{
"epoch": 0.6,
"learning_rate": 5.475180968246389e-06,
"loss": 0.4238,
"step": 417
},
{
"epoch": 0.6,
"learning_rate": 5.472614141455325e-06,
"loss": 0.5185,
"step": 418
},
{
"epoch": 0.6,
"learning_rate": 5.47004165770543e-06,
"loss": 0.4526,
"step": 419
},
{
"epoch": 0.6,
"learning_rate": 5.467463522882147e-06,
"loss": 0.5379,
"step": 420
},
{
"epoch": 0.6,
"learning_rate": 5.4648797428838505e-06,
"loss": 0.449,
"step": 421
},
{
"epoch": 0.6,
"learning_rate": 5.46229032362183e-06,
"loss": 0.4392,
"step": 422
},
{
"epoch": 0.61,
"learning_rate": 5.459695271020274e-06,
"loss": 0.4898,
"step": 423
},
{
"epoch": 0.61,
"learning_rate": 5.457094591016264e-06,
"loss": 0.5669,
"step": 424
},
{
"epoch": 0.61,
"learning_rate": 5.4544882895597535e-06,
"loss": 0.5021,
"step": 425
},
{
"epoch": 0.61,
"learning_rate": 5.4518763726135565e-06,
"loss": 0.4193,
"step": 426
},
{
"epoch": 0.61,
"learning_rate": 5.449258846153335e-06,
"loss": 0.4732,
"step": 427
},
{
"epoch": 0.61,
"learning_rate": 5.4466357161675855e-06,
"loss": 0.4882,
"step": 428
},
{
"epoch": 0.61,
"learning_rate": 5.444006988657624e-06,
"loss": 0.5325,
"step": 429
},
{
"epoch": 0.62,
"learning_rate": 5.441372669637572e-06,
"loss": 0.4433,
"step": 430
},
{
"epoch": 0.62,
"learning_rate": 5.438732765134344e-06,
"loss": 0.4672,
"step": 431
},
{
"epoch": 0.62,
"learning_rate": 5.436087281187633e-06,
"loss": 0.4323,
"step": 432
},
{
"epoch": 0.62,
"learning_rate": 5.433436223849899e-06,
"loss": 0.4036,
"step": 433
},
{
"epoch": 0.62,
"learning_rate": 5.430779599186349e-06,
"loss": 0.47,
"step": 434
},
{
"epoch": 0.62,
"learning_rate": 5.42811741327493e-06,
"loss": 0.4924,
"step": 435
},
{
"epoch": 0.62,
"learning_rate": 5.425449672206313e-06,
"loss": 0.3927,
"step": 436
},
{
"epoch": 0.63,
"learning_rate": 5.422776382083877e-06,
"loss": 0.4562,
"step": 437
},
{
"epoch": 0.63,
"learning_rate": 5.420097549023694e-06,
"loss": 0.4269,
"step": 438
},
{
"epoch": 0.63,
"learning_rate": 5.417413179154523e-06,
"loss": 0.4991,
"step": 439
},
{
"epoch": 0.63,
"learning_rate": 5.414723278617784e-06,
"loss": 0.4538,
"step": 440
},
{
"epoch": 0.63,
"learning_rate": 5.412027853567557e-06,
"loss": 0.4263,
"step": 441
},
{
"epoch": 0.63,
"learning_rate": 5.409326910170555e-06,
"loss": 0.4087,
"step": 442
},
{
"epoch": 0.63,
"learning_rate": 5.406620454606121e-06,
"loss": 0.4574,
"step": 443
},
{
"epoch": 0.64,
"learning_rate": 5.403908493066205e-06,
"loss": 0.5621,
"step": 444
},
{
"epoch": 0.64,
"learning_rate": 5.401191031755356e-06,
"loss": 0.5007,
"step": 445
},
{
"epoch": 0.64,
"learning_rate": 5.398468076890706e-06,
"loss": 0.3748,
"step": 446
},
{
"epoch": 0.64,
"learning_rate": 5.395739634701954e-06,
"loss": 0.4121,
"step": 447
},
{
"epoch": 0.64,
"learning_rate": 5.393005711431355e-06,
"loss": 0.4371,
"step": 448
},
{
"epoch": 0.64,
"learning_rate": 5.390266313333701e-06,
"loss": 0.542,
"step": 449
},
{
"epoch": 0.64,
"learning_rate": 5.387521446676313e-06,
"loss": 0.4617,
"step": 450
},
{
"epoch": 0.65,
"learning_rate": 5.384771117739021e-06,
"loss": 0.5518,
"step": 451
},
{
"epoch": 0.65,
"learning_rate": 5.382015332814151e-06,
"loss": 0.4069,
"step": 452
},
{
"epoch": 0.65,
"learning_rate": 5.379254098206514e-06,
"loss": 0.4998,
"step": 453
},
{
"epoch": 0.65,
"learning_rate": 5.376487420233388e-06,
"loss": 0.4728,
"step": 454
},
{
"epoch": 0.65,
"learning_rate": 5.373715305224504e-06,
"loss": 0.4597,
"step": 455
},
{
"epoch": 0.65,
"learning_rate": 5.370937759522032e-06,
"loss": 0.3967,
"step": 456
},
{
"epoch": 0.65,
"learning_rate": 5.36815478948057e-06,
"loss": 0.4631,
"step": 457
},
{
"epoch": 0.66,
"learning_rate": 5.365366401467118e-06,
"loss": 0.4023,
"step": 458
},
{
"epoch": 0.66,
"learning_rate": 5.362572601861081e-06,
"loss": 0.4511,
"step": 459
},
{
"epoch": 0.66,
"learning_rate": 5.359773397054239e-06,
"loss": 0.5139,
"step": 460
},
{
"epoch": 0.66,
"learning_rate": 5.35696879345074e-06,
"loss": 0.4738,
"step": 461
},
{
"epoch": 0.66,
"learning_rate": 5.354158797467082e-06,
"loss": 0.5281,
"step": 462
},
{
"epoch": 0.66,
"learning_rate": 5.351343415532103e-06,
"loss": 0.374,
"step": 463
},
{
"epoch": 0.66,
"learning_rate": 5.3485226540869606e-06,
"loss": 0.5568,
"step": 464
},
{
"epoch": 0.67,
"learning_rate": 5.345696519585122e-06,
"loss": 0.4969,
"step": 465
},
{
"epoch": 0.67,
"learning_rate": 5.342865018492345e-06,
"loss": 0.4556,
"step": 466
},
{
"epoch": 0.67,
"learning_rate": 5.340028157286666e-06,
"loss": 0.4517,
"step": 467
},
{
"epoch": 0.67,
"learning_rate": 5.337185942458386e-06,
"loss": 0.5229,
"step": 468
},
{
"epoch": 0.67,
"learning_rate": 5.334338380510052e-06,
"loss": 0.4098,
"step": 469
},
{
"epoch": 0.67,
"learning_rate": 5.331485477956445e-06,
"loss": 0.5186,
"step": 470
},
{
"epoch": 0.67,
"learning_rate": 5.328627241324567e-06,
"loss": 0.4412,
"step": 471
},
{
"epoch": 0.68,
"learning_rate": 5.325763677153619e-06,
"loss": 0.5039,
"step": 472
},
{
"epoch": 0.68,
"learning_rate": 5.322894791994995e-06,
"loss": 0.4975,
"step": 473
},
{
"epoch": 0.68,
"learning_rate": 5.3200205924122595e-06,
"loss": 0.4927,
"step": 474
},
{
"epoch": 0.68,
"learning_rate": 5.317141084981138e-06,
"loss": 0.4043,
"step": 475
},
{
"epoch": 0.68,
"learning_rate": 5.314256276289496e-06,
"loss": 0.4729,
"step": 476
},
{
"epoch": 0.68,
"learning_rate": 5.311366172937331e-06,
"loss": 0.4853,
"step": 477
},
{
"epoch": 0.68,
"learning_rate": 5.308470781536754e-06,
"loss": 0.4108,
"step": 478
},
{
"epoch": 0.69,
"learning_rate": 5.30557010871197e-06,
"loss": 0.4321,
"step": 479
},
{
"epoch": 0.69,
"learning_rate": 5.302664161099272e-06,
"loss": 0.4709,
"step": 480
},
{
"epoch": 0.69,
"learning_rate": 5.299752945347019e-06,
"loss": 0.4881,
"step": 481
},
{
"epoch": 0.69,
"learning_rate": 5.296836468115621e-06,
"loss": 0.4235,
"step": 482
},
{
"epoch": 0.69,
"learning_rate": 5.293914736077528e-06,
"loss": 0.4929,
"step": 483
},
{
"epoch": 0.69,
"learning_rate": 5.29098775591721e-06,
"loss": 0.4245,
"step": 484
},
{
"epoch": 0.69,
"learning_rate": 5.288055534331146e-06,
"loss": 0.509,
"step": 485
},
{
"epoch": 0.7,
"learning_rate": 5.2851180780278066e-06,
"loss": 0.4915,
"step": 486
},
{
"epoch": 0.7,
"learning_rate": 5.282175393727635e-06,
"loss": 0.4655,
"step": 487
},
{
"epoch": 0.7,
"learning_rate": 5.27922748816304e-06,
"loss": 0.4013,
"step": 488
},
{
"epoch": 0.7,
"learning_rate": 5.2762743680783725e-06,
"loss": 0.4388,
"step": 489
},
{
"epoch": 0.7,
"learning_rate": 5.273316040229916e-06,
"loss": 0.446,
"step": 490
},
{
"epoch": 0.7,
"learning_rate": 5.2703525113858665e-06,
"loss": 0.4686,
"step": 491
},
{
"epoch": 0.7,
"learning_rate": 5.267383788326318e-06,
"loss": 0.5223,
"step": 492
},
{
"epoch": 0.71,
"learning_rate": 5.264409877843254e-06,
"loss": 0.4112,
"step": 493
},
{
"epoch": 0.71,
"learning_rate": 5.2614307867405175e-06,
"loss": 0.4223,
"step": 494
},
{
"epoch": 0.71,
"learning_rate": 5.258446521833811e-06,
"loss": 0.4572,
"step": 495
},
{
"epoch": 0.71,
"learning_rate": 5.255457089950669e-06,
"loss": 0.4159,
"step": 496
},
{
"epoch": 0.71,
"learning_rate": 5.252462497930452e-06,
"loss": 0.5226,
"step": 497
},
{
"epoch": 0.71,
"learning_rate": 5.249462752624322e-06,
"loss": 0.4441,
"step": 498
},
{
"epoch": 0.71,
"learning_rate": 5.246457860895232e-06,
"loss": 0.468,
"step": 499
},
{
"epoch": 0.72,
"learning_rate": 5.243447829617911e-06,
"loss": 0.4007,
"step": 500
},
{
"epoch": 0.72,
"learning_rate": 5.2404326656788445e-06,
"loss": 0.4246,
"step": 501
},
{
"epoch": 0.72,
"learning_rate": 5.23741237597626e-06,
"loss": 0.5296,
"step": 502
},
{
"epoch": 0.72,
"learning_rate": 5.234386967420116e-06,
"loss": 0.5331,
"step": 503
},
{
"epoch": 0.72,
"learning_rate": 5.231356446932078e-06,
"loss": 0.4256,
"step": 504
},
{
"epoch": 0.72,
"learning_rate": 5.2283208214455084e-06,
"loss": 0.5028,
"step": 505
},
{
"epoch": 0.72,
"learning_rate": 5.2252800979054485e-06,
"loss": 0.4613,
"step": 506
},
{
"epoch": 0.73,
"learning_rate": 5.222234283268605e-06,
"loss": 0.539,
"step": 507
},
{
"epoch": 0.73,
"learning_rate": 5.219183384503329e-06,
"loss": 0.3855,
"step": 508
},
{
"epoch": 0.73,
"learning_rate": 5.2161274085896055e-06,
"loss": 0.3656,
"step": 509
},
{
"epoch": 0.73,
"learning_rate": 5.213066362519036e-06,
"loss": 0.3799,
"step": 510
},
{
"epoch": 0.73,
"learning_rate": 5.21000025329482e-06,
"loss": 0.4007,
"step": 511
},
{
"epoch": 0.73,
"learning_rate": 5.206929087931742e-06,
"loss": 0.4751,
"step": 512
},
{
"epoch": 0.73,
"learning_rate": 5.203852873456152e-06,
"loss": 0.466,
"step": 513
},
{
"epoch": 0.74,
"learning_rate": 5.200771616905955e-06,
"loss": 0.4813,
"step": 514
},
{
"epoch": 0.74,
"learning_rate": 5.197685325330586e-06,
"loss": 0.4517,
"step": 515
},
{
"epoch": 0.74,
"learning_rate": 5.194594005791007e-06,
"loss": 0.4548,
"step": 516
},
{
"epoch": 0.74,
"learning_rate": 5.191497665359678e-06,
"loss": 0.3559,
"step": 517
},
{
"epoch": 0.74,
"learning_rate": 5.188396311120545e-06,
"loss": 0.396,
"step": 518
},
{
"epoch": 0.74,
"learning_rate": 5.18528995016903e-06,
"loss": 0.4812,
"step": 519
},
{
"epoch": 0.74,
"learning_rate": 5.182178589612004e-06,
"loss": 0.3215,
"step": 520
},
{
"epoch": 0.75,
"learning_rate": 5.17906223656778e-06,
"loss": 0.468,
"step": 521
},
{
"epoch": 0.75,
"learning_rate": 5.175940898166092e-06,
"loss": 0.4694,
"step": 522
},
{
"epoch": 0.75,
"learning_rate": 5.172814581548079e-06,
"loss": 0.5225,
"step": 523
},
{
"epoch": 0.75,
"learning_rate": 5.169683293866272e-06,
"loss": 0.4213,
"step": 524
},
{
"epoch": 0.75,
"learning_rate": 5.166547042284571e-06,
"loss": 0.4493,
"step": 525
},
{
"epoch": 0.75,
"learning_rate": 5.163405833978234e-06,
"loss": 0.4245,
"step": 526
},
{
"epoch": 0.75,
"learning_rate": 5.160259676133862e-06,
"loss": 0.3559,
"step": 527
},
{
"epoch": 0.76,
"learning_rate": 5.157108575949377e-06,
"loss": 0.4904,
"step": 528
},
{
"epoch": 0.76,
"learning_rate": 5.153952540634008e-06,
"loss": 0.5226,
"step": 529
},
{
"epoch": 0.76,
"learning_rate": 5.150791577408278e-06,
"loss": 0.3978,
"step": 530
},
{
"epoch": 0.76,
"learning_rate": 5.14762569350398e-06,
"loss": 0.4997,
"step": 531
},
{
"epoch": 0.76,
"learning_rate": 5.144454896164167e-06,
"loss": 0.4716,
"step": 532
},
{
"epoch": 0.76,
"learning_rate": 5.141279192643134e-06,
"loss": 0.4596,
"step": 533
},
{
"epoch": 0.76,
"learning_rate": 5.138098590206399e-06,
"loss": 0.5511,
"step": 534
},
{
"epoch": 0.77,
"learning_rate": 5.134913096130689e-06,
"loss": 0.4718,
"step": 535
},
{
"epoch": 0.77,
"learning_rate": 5.131722717703922e-06,
"loss": 0.4111,
"step": 536
},
{
"epoch": 0.77,
"learning_rate": 5.1285274622251905e-06,
"loss": 0.4209,
"step": 537
},
{
"epoch": 0.77,
"learning_rate": 5.1253273370047445e-06,
"loss": 0.4668,
"step": 538
},
{
"epoch": 0.77,
"learning_rate": 5.122122349363976e-06,
"loss": 0.522,
"step": 539
},
{
"epoch": 0.77,
"learning_rate": 5.1189125066354e-06,
"loss": 0.4463,
"step": 540
},
{
"epoch": 0.77,
"learning_rate": 5.115697816162642e-06,
"loss": 0.4159,
"step": 541
},
{
"epoch": 0.78,
"learning_rate": 5.112478285300416e-06,
"loss": 0.4044,
"step": 542
},
{
"epoch": 0.78,
"learning_rate": 5.109253921414511e-06,
"loss": 0.4559,
"step": 543
},
{
"epoch": 0.78,
"learning_rate": 5.106024731881773e-06,
"loss": 0.4574,
"step": 544
},
{
"epoch": 0.78,
"learning_rate": 5.10279072409009e-06,
"loss": 0.5361,
"step": 545
},
{
"epoch": 0.78,
"learning_rate": 5.099551905438367e-06,
"loss": 0.4744,
"step": 546
},
{
"epoch": 0.78,
"learning_rate": 5.096308283336525e-06,
"loss": 0.3802,
"step": 547
},
{
"epoch": 0.78,
"learning_rate": 5.093059865205467e-06,
"loss": 0.4328,
"step": 548
},
{
"epoch": 0.79,
"learning_rate": 5.0898066584770745e-06,
"loss": 0.3582,
"step": 549
},
{
"epoch": 0.79,
"learning_rate": 5.086548670594179e-06,
"loss": 0.3987,
"step": 550
},
{
"epoch": 0.79,
"learning_rate": 5.083285909010553e-06,
"loss": 0.3954,
"step": 551
},
{
"epoch": 0.79,
"learning_rate": 5.080018381190891e-06,
"loss": 0.4501,
"step": 552
},
{
"epoch": 0.79,
"learning_rate": 5.076746094610792e-06,
"loss": 0.4543,
"step": 553
},
{
"epoch": 0.79,
"learning_rate": 5.07346905675674e-06,
"loss": 0.4066,
"step": 554
},
{
"epoch": 0.79,
"learning_rate": 5.070187275126094e-06,
"loss": 0.4318,
"step": 555
},
{
"epoch": 0.8,
"learning_rate": 5.06690075722706e-06,
"loss": 0.4984,
"step": 556
},
{
"epoch": 0.8,
"learning_rate": 5.063609510578684e-06,
"loss": 0.4193,
"step": 557
},
{
"epoch": 0.8,
"learning_rate": 5.060313542710829e-06,
"loss": 0.4286,
"step": 558
},
{
"epoch": 0.8,
"learning_rate": 5.05701286116416e-06,
"loss": 0.3812,
"step": 559
},
{
"epoch": 0.8,
"learning_rate": 5.053707473490127e-06,
"loss": 0.4593,
"step": 560
},
{
"epoch": 0.8,
"learning_rate": 5.0503973872509444e-06,
"loss": 0.3736,
"step": 561
},
{
"epoch": 0.8,
"learning_rate": 5.047082610019578e-06,
"loss": 0.3899,
"step": 562
},
{
"epoch": 0.81,
"learning_rate": 5.0437631493797265e-06,
"loss": 0.4312,
"step": 563
},
{
"epoch": 0.81,
"learning_rate": 5.040439012925802e-06,
"loss": 0.4096,
"step": 564
},
{
"epoch": 0.81,
"learning_rate": 5.037110208262915e-06,
"loss": 0.4577,
"step": 565
},
{
"epoch": 0.81,
"learning_rate": 5.033776743006855e-06,
"loss": 0.3611,
"step": 566
},
{
"epoch": 0.81,
"learning_rate": 5.030438624784075e-06,
"loss": 0.5791,
"step": 567
},
{
"epoch": 0.81,
"learning_rate": 5.027095861231674e-06,
"loss": 0.5173,
"step": 568
},
{
"epoch": 0.81,
"learning_rate": 5.023748459997379e-06,
"loss": 0.4107,
"step": 569
},
{
"epoch": 0.82,
"learning_rate": 5.020396428739526e-06,
"loss": 0.4812,
"step": 570
},
{
"epoch": 0.82,
"learning_rate": 5.0170397751270435e-06,
"loss": 0.3816,
"step": 571
},
{
"epoch": 0.82,
"learning_rate": 5.013678506839436e-06,
"loss": 0.4827,
"step": 572
},
{
"epoch": 0.82,
"learning_rate": 5.010312631566765e-06,
"loss": 0.396,
"step": 573
},
{
"epoch": 0.82,
"learning_rate": 5.006942157009635e-06,
"loss": 0.4057,
"step": 574
},
{
"epoch": 0.82,
"learning_rate": 5.003567090879167e-06,
"loss": 0.4667,
"step": 575
},
{
"epoch": 0.82,
"learning_rate": 5.000187440896995e-06,
"loss": 0.4104,
"step": 576
},
{
"epoch": 0.83,
"learning_rate": 4.996803214795232e-06,
"loss": 0.4168,
"step": 577
},
{
"epoch": 0.83,
"learning_rate": 4.993414420316466e-06,
"loss": 0.4152,
"step": 578
},
{
"epoch": 0.83,
"learning_rate": 4.990021065213733e-06,
"loss": 0.5325,
"step": 579
},
{
"epoch": 0.83,
"learning_rate": 4.9866231572505065e-06,
"loss": 0.4709,
"step": 580
},
{
"epoch": 0.83,
"learning_rate": 4.983220704200673e-06,
"loss": 0.4489,
"step": 581
},
{
"epoch": 0.83,
"learning_rate": 4.97981371384852e-06,
"loss": 0.4172,
"step": 582
},
{
"epoch": 0.83,
"learning_rate": 4.976402193988715e-06,
"loss": 0.4164,
"step": 583
},
{
"epoch": 0.84,
"learning_rate": 4.972986152426287e-06,
"loss": 0.3997,
"step": 584
},
{
"epoch": 0.84,
"learning_rate": 4.969565596976612e-06,
"loss": 0.4982,
"step": 585
},
{
"epoch": 0.84,
"learning_rate": 4.9661405354653895e-06,
"loss": 0.3557,
"step": 586
},
{
"epoch": 0.84,
"learning_rate": 4.962710975728634e-06,
"loss": 0.4978,
"step": 587
},
{
"epoch": 0.84,
"learning_rate": 4.9592769256126455e-06,
"loss": 0.4101,
"step": 588
},
{
"epoch": 0.84,
"learning_rate": 4.955838392974e-06,
"loss": 0.4904,
"step": 589
},
{
"epoch": 0.84,
"learning_rate": 4.9523953856795295e-06,
"loss": 0.5603,
"step": 590
},
{
"epoch": 0.85,
"learning_rate": 4.948947911606303e-06,
"loss": 0.4819,
"step": 591
},
{
"epoch": 0.85,
"learning_rate": 4.945495978641605e-06,
"loss": 0.3994,
"step": 592
},
{
"epoch": 0.85,
"learning_rate": 4.942039594682928e-06,
"loss": 0.4293,
"step": 593
},
{
"epoch": 0.85,
"learning_rate": 4.938578767637941e-06,
"loss": 0.4657,
"step": 594
},
{
"epoch": 0.85,
"learning_rate": 4.935113505424483e-06,
"loss": 0.4192,
"step": 595
},
{
"epoch": 0.85,
"learning_rate": 4.931643815970538e-06,
"loss": 0.4095,
"step": 596
},
{
"epoch": 0.85,
"learning_rate": 4.928169707214218e-06,
"loss": 0.4107,
"step": 597
},
{
"epoch": 0.86,
"learning_rate": 4.924691187103746e-06,
"loss": 0.4525,
"step": 598
},
{
"epoch": 0.86,
"learning_rate": 4.9212082635974416e-06,
"loss": 0.4852,
"step": 599
},
{
"epoch": 0.86,
"learning_rate": 4.917720944663692e-06,
"loss": 0.4355,
"step": 600
},
{
"epoch": 0.86,
"learning_rate": 4.9142292382809454e-06,
"loss": 0.615,
"step": 601
},
{
"epoch": 0.86,
"learning_rate": 4.910733152437684e-06,
"loss": 0.4891,
"step": 602
},
{
"epoch": 0.86,
"learning_rate": 4.907232695132416e-06,
"loss": 0.338,
"step": 603
},
{
"epoch": 0.86,
"learning_rate": 4.90372787437364e-06,
"loss": 0.5141,
"step": 604
},
{
"epoch": 0.87,
"learning_rate": 4.90021869817985e-06,
"loss": 0.4873,
"step": 605
},
{
"epoch": 0.87,
"learning_rate": 4.8967051745794955e-06,
"loss": 0.5374,
"step": 606
},
{
"epoch": 0.87,
"learning_rate": 4.8931873116109744e-06,
"loss": 0.4597,
"step": 607
},
{
"epoch": 0.87,
"learning_rate": 4.889665117322617e-06,
"loss": 0.511,
"step": 608
},
{
"epoch": 0.87,
"learning_rate": 4.8861385997726555e-06,
"loss": 0.4522,
"step": 609
},
{
"epoch": 0.87,
"learning_rate": 4.882607767029218e-06,
"loss": 0.5202,
"step": 610
},
{
"epoch": 0.87,
"learning_rate": 4.879072627170303e-06,
"loss": 0.4294,
"step": 611
},
{
"epoch": 0.88,
"learning_rate": 4.875533188283767e-06,
"loss": 0.3775,
"step": 612
},
{
"epoch": 0.88,
"learning_rate": 4.871989458467295e-06,
"loss": 0.4315,
"step": 613
},
{
"epoch": 0.88,
"learning_rate": 4.868441445828396e-06,
"loss": 0.4603,
"step": 614
},
{
"epoch": 0.88,
"learning_rate": 4.864889158484372e-06,
"loss": 0.3861,
"step": 615
},
{
"epoch": 0.88,
"learning_rate": 4.861332604562308e-06,
"loss": 0.438,
"step": 616
},
{
"epoch": 0.88,
"learning_rate": 4.857771792199051e-06,
"loss": 0.5107,
"step": 617
},
{
"epoch": 0.88,
"learning_rate": 4.854206729541186e-06,
"loss": 0.3689,
"step": 618
},
{
"epoch": 0.89,
"learning_rate": 4.850637424745027e-06,
"loss": 0.3583,
"step": 619
},
{
"epoch": 0.89,
"learning_rate": 4.8470638859765925e-06,
"loss": 0.5364,
"step": 620
},
{
"epoch": 0.89,
"learning_rate": 4.8434861214115846e-06,
"loss": 0.5606,
"step": 621
},
{
"epoch": 0.89,
"learning_rate": 4.839904139235377e-06,
"loss": 0.4171,
"step": 622
},
{
"epoch": 0.89,
"learning_rate": 4.836317947642989e-06,
"loss": 0.4187,
"step": 623
},
{
"epoch": 0.89,
"learning_rate": 4.832727554839074e-06,
"loss": 0.4433,
"step": 624
},
{
"epoch": 0.89,
"learning_rate": 4.829132969037896e-06,
"loss": 0.3913,
"step": 625
},
{
"epoch": 0.9,
"learning_rate": 4.8255341984633105e-06,
"loss": 0.5009,
"step": 626
},
{
"epoch": 0.9,
"learning_rate": 4.821931251348749e-06,
"loss": 0.4361,
"step": 627
},
{
"epoch": 0.9,
"learning_rate": 4.818324135937196e-06,
"loss": 0.3899,
"step": 628
},
{
"epoch": 0.9,
"learning_rate": 4.814712860481174e-06,
"loss": 0.4439,
"step": 629
},
{
"epoch": 0.9,
"learning_rate": 4.811097433242725e-06,
"loss": 0.3416,
"step": 630
},
{
"epoch": 0.9,
"learning_rate": 4.807477862493385e-06,
"loss": 0.4541,
"step": 631
},
{
"epoch": 0.9,
"learning_rate": 4.803854156514174e-06,
"loss": 0.488,
"step": 632
},
{
"epoch": 0.91,
"learning_rate": 4.800226323595571e-06,
"loss": 0.4683,
"step": 633
},
{
"epoch": 0.91,
"learning_rate": 4.796594372037495e-06,
"loss": 0.4418,
"step": 634
},
{
"epoch": 0.91,
"learning_rate": 4.792958310149291e-06,
"loss": 0.3661,
"step": 635
},
{
"epoch": 0.91,
"learning_rate": 4.789318146249705e-06,
"loss": 0.4844,
"step": 636
},
{
"epoch": 0.91,
"learning_rate": 4.785673888666871e-06,
"loss": 0.4785,
"step": 637
},
{
"epoch": 0.91,
"learning_rate": 4.782025545738286e-06,
"loss": 0.4481,
"step": 638
},
{
"epoch": 0.91,
"learning_rate": 4.778373125810794e-06,
"loss": 0.4527,
"step": 639
},
{
"epoch": 0.92,
"learning_rate": 4.774716637240568e-06,
"loss": 0.4257,
"step": 640
},
{
"epoch": 0.92,
"learning_rate": 4.771056088393087e-06,
"loss": 0.5438,
"step": 641
},
{
"epoch": 0.92,
"learning_rate": 4.767391487643122e-06,
"loss": 0.4149,
"step": 642
},
{
"epoch": 0.92,
"learning_rate": 4.763722843374713e-06,
"loss": 0.4386,
"step": 643
},
{
"epoch": 0.92,
"learning_rate": 4.7600501639811506e-06,
"loss": 0.4356,
"step": 644
},
{
"epoch": 0.92,
"learning_rate": 4.756373457864957e-06,
"loss": 0.4436,
"step": 645
},
{
"epoch": 0.92,
"learning_rate": 4.752692733437868e-06,
"loss": 0.4531,
"step": 646
},
{
"epoch": 0.93,
"learning_rate": 4.749007999120811e-06,
"loss": 0.5013,
"step": 647
},
{
"epoch": 0.93,
"learning_rate": 4.745319263343889e-06,
"loss": 0.5079,
"step": 648
},
{
"epoch": 0.93,
"learning_rate": 4.741626534546359e-06,
"loss": 0.4039,
"step": 649
},
{
"epoch": 0.93,
"learning_rate": 4.737929821176613e-06,
"loss": 0.3419,
"step": 650
},
{
"epoch": 0.93,
"learning_rate": 4.73422913169216e-06,
"loss": 0.4503,
"step": 651
},
{
"epoch": 0.93,
"learning_rate": 4.730524474559606e-06,
"loss": 0.5075,
"step": 652
},
{
"epoch": 0.93,
"learning_rate": 4.7268158582546324e-06,
"loss": 0.4372,
"step": 653
},
{
"epoch": 0.94,
"learning_rate": 4.723103291261981e-06,
"loss": 0.5,
"step": 654
},
{
"epoch": 0.94,
"learning_rate": 4.719386782075431e-06,
"loss": 0.5095,
"step": 655
},
{
"epoch": 0.94,
"learning_rate": 4.715666339197779e-06,
"loss": 0.3759,
"step": 656
},
{
"epoch": 0.94,
"learning_rate": 4.711941971140826e-06,
"loss": 0.4706,
"step": 657
},
{
"epoch": 0.94,
"learning_rate": 4.708213686425348e-06,
"loss": 0.509,
"step": 658
},
{
"epoch": 0.94,
"learning_rate": 4.704481493581083e-06,
"loss": 0.4566,
"step": 659
},
{
"epoch": 0.94,
"learning_rate": 4.700745401146715e-06,
"loss": 0.3885,
"step": 660
},
{
"epoch": 0.95,
"learning_rate": 4.697005417669843e-06,
"loss": 0.4212,
"step": 661
},
{
"epoch": 0.95,
"learning_rate": 4.6932615517069705e-06,
"loss": 0.4641,
"step": 662
},
{
"epoch": 0.95,
"learning_rate": 4.689513811823485e-06,
"loss": 0.4767,
"step": 663
},
{
"epoch": 0.95,
"learning_rate": 4.685762206593637e-06,
"loss": 0.4208,
"step": 664
},
{
"epoch": 0.95,
"learning_rate": 4.682006744600517e-06,
"loss": 0.4974,
"step": 665
},
{
"epoch": 0.95,
"learning_rate": 4.678247434436042e-06,
"loss": 0.4433,
"step": 666
},
{
"epoch": 0.95,
"learning_rate": 4.6744842847009325e-06,
"loss": 0.3971,
"step": 667
},
{
"epoch": 0.96,
"learning_rate": 4.6707173040046935e-06,
"loss": 0.4154,
"step": 668
},
{
"epoch": 0.96,
"learning_rate": 4.666946500965595e-06,
"loss": 0.3689,
"step": 669
},
{
"epoch": 0.96,
"learning_rate": 4.663171884210649e-06,
"loss": 0.4324,
"step": 670
},
{
"epoch": 0.96,
"learning_rate": 4.659393462375598e-06,
"loss": 0.3767,
"step": 671
},
{
"epoch": 0.96,
"learning_rate": 4.655611244104885e-06,
"loss": 0.5331,
"step": 672
},
{
"epoch": 0.96,
"learning_rate": 4.6518252380516414e-06,
"loss": 0.4413,
"step": 673
},
{
"epoch": 0.96,
"learning_rate": 4.648035452877663e-06,
"loss": 0.4158,
"step": 674
},
{
"epoch": 0.97,
"learning_rate": 4.644241897253393e-06,
"loss": 0.4724,
"step": 675
},
{
"epoch": 0.97,
"learning_rate": 4.640444579857899e-06,
"loss": 0.3756,
"step": 676
},
{
"epoch": 0.97,
"learning_rate": 4.636643509378857e-06,
"loss": 0.5379,
"step": 677
},
{
"epoch": 0.97,
"learning_rate": 4.6328386945125285e-06,
"loss": 0.4473,
"step": 678
},
{
"epoch": 0.97,
"learning_rate": 4.62903014396374e-06,
"loss": 0.4413,
"step": 679
},
{
"epoch": 0.97,
"learning_rate": 4.625217866445869e-06,
"loss": 0.4159,
"step": 680
},
{
"epoch": 0.97,
"learning_rate": 4.621401870680816e-06,
"loss": 0.4367,
"step": 681
},
{
"epoch": 0.98,
"learning_rate": 4.617582165398987e-06,
"loss": 0.3701,
"step": 682
},
{
"epoch": 0.98,
"learning_rate": 4.613758759339281e-06,
"loss": 0.399,
"step": 683
},
{
"epoch": 0.98,
"learning_rate": 4.6099316612490566e-06,
"loss": 0.4108,
"step": 684
},
{
"epoch": 0.98,
"learning_rate": 4.606100879884124e-06,
"loss": 0.4093,
"step": 685
},
{
"epoch": 0.98,
"learning_rate": 4.602266424008718e-06,
"loss": 0.3988,
"step": 686
},
{
"epoch": 0.98,
"learning_rate": 4.598428302395482e-06,
"loss": 0.4873,
"step": 687
},
{
"epoch": 0.98,
"learning_rate": 4.5945865238254424e-06,
"loss": 0.3939,
"step": 688
},
{
"epoch": 0.99,
"learning_rate": 4.5907410970879985e-06,
"loss": 0.4312,
"step": 689
},
{
"epoch": 0.99,
"learning_rate": 4.586892030980887e-06,
"loss": 0.5106,
"step": 690
},
{
"epoch": 0.99,
"learning_rate": 4.58303933431018e-06,
"loss": 0.4364,
"step": 691
},
{
"epoch": 0.99,
"learning_rate": 4.57918301589025e-06,
"loss": 0.4712,
"step": 692
},
{
"epoch": 0.99,
"learning_rate": 4.575323084543757e-06,
"loss": 0.5679,
"step": 693
},
{
"epoch": 0.99,
"learning_rate": 4.57145954910163e-06,
"loss": 0.3622,
"step": 694
},
{
"epoch": 0.99,
"learning_rate": 4.5675924184030356e-06,
"loss": 0.4903,
"step": 695
},
{
"epoch": 1.0,
"learning_rate": 4.5637217012953755e-06,
"loss": 0.471,
"step": 696
},
{
"epoch": 1.0,
"learning_rate": 4.55984740663425e-06,
"loss": 0.4877,
"step": 697
},
{
"epoch": 1.0,
"learning_rate": 4.555969543283445e-06,
"loss": 0.4672,
"step": 698
},
{
"epoch": 1.0,
"learning_rate": 4.552088120114915e-06,
"loss": 0.4331,
"step": 699
},
{
"epoch": 1.0,
"learning_rate": 4.548203146008755e-06,
"loss": 0.2252,
"step": 700
},
{
"epoch": 1.0,
"learning_rate": 4.5443146298531835e-06,
"loss": 0.2158,
"step": 701
},
{
"epoch": 1.0,
"learning_rate": 4.540422580544526e-06,
"loss": 0.2276,
"step": 702
},
{
"epoch": 1.01,
"learning_rate": 4.5365270069871885e-06,
"loss": 0.1966,
"step": 703
},
{
"epoch": 1.01,
"learning_rate": 4.532627918093642e-06,
"loss": 0.2444,
"step": 704
},
{
"epoch": 1.01,
"learning_rate": 4.528725322784399e-06,
"loss": 0.2062,
"step": 705
},
{
"epoch": 1.01,
"learning_rate": 4.524819229987992e-06,
"loss": 0.2316,
"step": 706
},
{
"epoch": 1.01,
"learning_rate": 4.52090964864096e-06,
"loss": 0.2418,
"step": 707
},
{
"epoch": 1.01,
"learning_rate": 4.516996587687818e-06,
"loss": 0.1928,
"step": 708
},
{
"epoch": 1.01,
"learning_rate": 4.513080056081048e-06,
"loss": 0.3668,
"step": 709
},
{
"epoch": 1.02,
"learning_rate": 4.509160062781066e-06,
"loss": 0.2042,
"step": 710
},
{
"epoch": 1.02,
"learning_rate": 4.505236616756211e-06,
"loss": 0.2923,
"step": 711
},
{
"epoch": 1.02,
"learning_rate": 4.501309726982721e-06,
"loss": 0.2577,
"step": 712
},
{
"epoch": 1.02,
"learning_rate": 4.4973794024447126e-06,
"loss": 0.2529,
"step": 713
},
{
"epoch": 1.02,
"learning_rate": 4.493445652134161e-06,
"loss": 0.2727,
"step": 714
},
{
"epoch": 1.02,
"learning_rate": 4.489508485050877e-06,
"loss": 0.2636,
"step": 715
},
{
"epoch": 1.02,
"learning_rate": 4.485567910202493e-06,
"loss": 0.2274,
"step": 716
},
{
"epoch": 1.03,
"learning_rate": 4.481623936604433e-06,
"loss": 0.2702,
"step": 717
},
{
"epoch": 1.03,
"learning_rate": 4.4776765732798995e-06,
"loss": 0.3051,
"step": 718
},
{
"epoch": 1.03,
"learning_rate": 4.473725829259848e-06,
"loss": 0.2659,
"step": 719
},
{
"epoch": 1.03,
"learning_rate": 4.469771713582972e-06,
"loss": 0.2238,
"step": 720
},
{
"epoch": 1.03,
"learning_rate": 4.465814235295675e-06,
"loss": 0.2127,
"step": 721
},
{
"epoch": 1.03,
"learning_rate": 4.461853403452057e-06,
"loss": 0.2404,
"step": 722
},
{
"epoch": 1.03,
"learning_rate": 4.457889227113888e-06,
"loss": 0.2369,
"step": 723
},
{
"epoch": 1.04,
"learning_rate": 4.45392171535059e-06,
"loss": 0.2311,
"step": 724
},
{
"epoch": 1.04,
"learning_rate": 4.4499508772392175e-06,
"loss": 0.2587,
"step": 725
},
{
"epoch": 1.04,
"learning_rate": 4.445976721864434e-06,
"loss": 0.2415,
"step": 726
},
{
"epoch": 1.04,
"learning_rate": 4.441999258318492e-06,
"loss": 0.2308,
"step": 727
},
{
"epoch": 1.04,
"learning_rate": 4.438018495701212e-06,
"loss": 0.2262,
"step": 728
},
{
"epoch": 1.04,
"learning_rate": 4.434034443119965e-06,
"loss": 0.2065,
"step": 729
},
{
"epoch": 1.04,
"learning_rate": 4.430047109689648e-06,
"loss": 0.2042,
"step": 730
},
{
"epoch": 1.05,
"learning_rate": 4.426056504532661e-06,
"loss": 0.2428,
"step": 731
},
{
"epoch": 1.05,
"learning_rate": 4.422062636778893e-06,
"loss": 0.2589,
"step": 732
},
{
"epoch": 1.05,
"learning_rate": 4.418065515565696e-06,
"loss": 0.2355,
"step": 733
},
{
"epoch": 1.05,
"learning_rate": 4.414065150037865e-06,
"loss": 0.2494,
"step": 734
},
{
"epoch": 1.05,
"learning_rate": 4.410061549347617e-06,
"loss": 0.2903,
"step": 735
},
{
"epoch": 1.05,
"learning_rate": 4.4060547226545726e-06,
"loss": 0.2604,
"step": 736
},
{
"epoch": 1.05,
"learning_rate": 4.4020446791257305e-06,
"loss": 0.1822,
"step": 737
},
{
"epoch": 1.06,
"learning_rate": 4.398031427935451e-06,
"loss": 0.2516,
"step": 738
},
{
"epoch": 1.06,
"learning_rate": 4.394014978265433e-06,
"loss": 0.1945,
"step": 739
},
{
"epoch": 1.06,
"learning_rate": 4.389995339304691e-06,
"loss": 0.2492,
"step": 740
},
{
"epoch": 1.06,
"learning_rate": 4.385972520249538e-06,
"loss": 0.1614,
"step": 741
},
{
"epoch": 1.06,
"learning_rate": 4.381946530303561e-06,
"loss": 0.2486,
"step": 742
},
{
"epoch": 1.06,
"learning_rate": 4.3779173786776045e-06,
"loss": 0.2166,
"step": 743
},
{
"epoch": 1.06,
"learning_rate": 4.373885074589743e-06,
"loss": 0.234,
"step": 744
},
{
"epoch": 1.07,
"learning_rate": 4.369849627265265e-06,
"loss": 0.2599,
"step": 745
},
{
"epoch": 1.07,
"learning_rate": 4.36581104593665e-06,
"loss": 0.2358,
"step": 746
},
{
"epoch": 1.07,
"learning_rate": 4.361769339843547e-06,
"loss": 0.2443,
"step": 747
},
{
"epoch": 1.07,
"learning_rate": 4.357724518232756e-06,
"loss": 0.2141,
"step": 748
},
{
"epoch": 1.07,
"learning_rate": 4.353676590358203e-06,
"loss": 0.1821,
"step": 749
},
{
"epoch": 1.07,
"learning_rate": 4.349625565480921e-06,
"loss": 0.2004,
"step": 750
},
{
"epoch": 1.07,
"learning_rate": 4.345571452869028e-06,
"loss": 0.2745,
"step": 751
},
{
"epoch": 1.08,
"learning_rate": 4.341514261797706e-06,
"loss": 0.2188,
"step": 752
},
{
"epoch": 1.08,
"learning_rate": 4.337454001549184e-06,
"loss": 0.2304,
"step": 753
},
{
"epoch": 1.08,
"learning_rate": 4.333390681412705e-06,
"loss": 0.2596,
"step": 754
},
{
"epoch": 1.08,
"learning_rate": 4.329324310684522e-06,
"loss": 0.2431,
"step": 755
},
{
"epoch": 1.08,
"learning_rate": 4.325254898667859e-06,
"loss": 0.2186,
"step": 756
},
{
"epoch": 1.08,
"learning_rate": 4.321182454672904e-06,
"loss": 0.2268,
"step": 757
},
{
"epoch": 1.08,
"learning_rate": 4.317106988016776e-06,
"loss": 0.2316,
"step": 758
},
{
"epoch": 1.09,
"learning_rate": 4.313028508023516e-06,
"loss": 0.2499,
"step": 759
},
{
"epoch": 1.09,
"learning_rate": 4.308947024024054e-06,
"loss": 0.223,
"step": 760
},
{
"epoch": 1.09,
"learning_rate": 4.3048625453561935e-06,
"loss": 0.2058,
"step": 761
},
{
"epoch": 1.09,
"learning_rate": 4.300775081364591e-06,
"loss": 0.2033,
"step": 762
},
{
"epoch": 1.09,
"learning_rate": 4.2966846414007325e-06,
"loss": 0.2104,
"step": 763
},
{
"epoch": 1.09,
"learning_rate": 4.2925912348229115e-06,
"loss": 0.2345,
"step": 764
},
{
"epoch": 1.09,
"learning_rate": 4.28849487099621e-06,
"loss": 0.2488,
"step": 765
},
{
"epoch": 1.1,
"learning_rate": 4.284395559292473e-06,
"loss": 0.2569,
"step": 766
},
{
"epoch": 1.1,
"learning_rate": 4.280293309090295e-06,
"loss": 0.2634,
"step": 767
},
{
"epoch": 1.1,
"learning_rate": 4.276188129774989e-06,
"loss": 0.2349,
"step": 768
},
{
"epoch": 1.1,
"learning_rate": 4.2720800307385694e-06,
"loss": 0.2171,
"step": 769
},
{
"epoch": 1.1,
"learning_rate": 4.2679690213797314e-06,
"loss": 0.219,
"step": 770
},
{
"epoch": 1.1,
"learning_rate": 4.26385511110383e-06,
"loss": 0.2428,
"step": 771
},
{
"epoch": 1.1,
"learning_rate": 4.259738309322858e-06,
"loss": 0.25,
"step": 772
},
{
"epoch": 1.11,
"learning_rate": 4.255618625455415e-06,
"loss": 0.226,
"step": 773
},
{
"epoch": 1.11,
"learning_rate": 4.251496068926707e-06,
"loss": 0.2019,
"step": 774
},
{
"epoch": 1.11,
"learning_rate": 4.247370649168502e-06,
"loss": 0.2221,
"step": 775
},
{
"epoch": 1.11,
"learning_rate": 4.243242375619125e-06,
"loss": 0.2488,
"step": 776
},
{
"epoch": 1.11,
"learning_rate": 4.239111257723425e-06,
"loss": 0.2267,
"step": 777
},
{
"epoch": 1.11,
"learning_rate": 4.234977304932763e-06,
"loss": 0.2512,
"step": 778
},
{
"epoch": 1.11,
"learning_rate": 4.230840526704984e-06,
"loss": 0.221,
"step": 779
},
{
"epoch": 1.12,
"learning_rate": 4.2267009325043955e-06,
"loss": 0.2545,
"step": 780
},
{
"epoch": 1.12,
"learning_rate": 4.222558531801749e-06,
"loss": 0.1911,
"step": 781
},
{
"epoch": 1.12,
"learning_rate": 4.218413334074218e-06,
"loss": 0.2364,
"step": 782
},
{
"epoch": 1.12,
"learning_rate": 4.214265348805374e-06,
"loss": 0.2375,
"step": 783
},
{
"epoch": 1.12,
"learning_rate": 4.210114585485164e-06,
"loss": 0.2262,
"step": 784
},
{
"epoch": 1.12,
"learning_rate": 4.205961053609895e-06,
"loss": 0.2074,
"step": 785
},
{
"epoch": 1.12,
"learning_rate": 4.201804762682204e-06,
"loss": 0.2594,
"step": 786
},
{
"epoch": 1.13,
"learning_rate": 4.197645722211042e-06,
"loss": 0.1488,
"step": 787
},
{
"epoch": 1.13,
"learning_rate": 4.193483941711653e-06,
"loss": 0.2551,
"step": 788
},
{
"epoch": 1.13,
"learning_rate": 4.189319430705544e-06,
"loss": 0.2729,
"step": 789
},
{
"epoch": 1.13,
"learning_rate": 4.185152198720474e-06,
"loss": 0.2254,
"step": 790
},
{
"epoch": 1.13,
"learning_rate": 4.1809822552904256e-06,
"loss": 0.2496,
"step": 791
},
{
"epoch": 1.13,
"learning_rate": 4.176809609955584e-06,
"loss": 0.2343,
"step": 792
},
{
"epoch": 1.13,
"learning_rate": 4.172634272262316e-06,
"loss": 0.2339,
"step": 793
},
{
"epoch": 1.14,
"learning_rate": 4.168456251763149e-06,
"loss": 0.2322,
"step": 794
},
{
"epoch": 1.14,
"learning_rate": 4.164275558016749e-06,
"loss": 0.2316,
"step": 795
},
{
"epoch": 1.14,
"learning_rate": 4.160092200587896e-06,
"loss": 0.1992,
"step": 796
},
{
"epoch": 1.14,
"learning_rate": 4.155906189047465e-06,
"loss": 0.2635,
"step": 797
},
{
"epoch": 1.14,
"learning_rate": 4.151717532972402e-06,
"loss": 0.2004,
"step": 798
},
{
"epoch": 1.14,
"learning_rate": 4.147526241945707e-06,
"loss": 0.1791,
"step": 799
},
{
"epoch": 1.14,
"learning_rate": 4.143332325556404e-06,
"loss": 0.2646,
"step": 800
},
{
"epoch": 1.15,
"learning_rate": 4.1391357933995256e-06,
"loss": 0.2502,
"step": 801
},
{
"epoch": 1.15,
"learning_rate": 4.134936655076089e-06,
"loss": 0.2051,
"step": 802
},
{
"epoch": 1.15,
"learning_rate": 4.1307349201930716e-06,
"loss": 0.248,
"step": 803
},
{
"epoch": 1.15,
"learning_rate": 4.1265305983633945e-06,
"loss": 0.213,
"step": 804
},
{
"epoch": 1.15,
"learning_rate": 4.122323699205897e-06,
"loss": 0.1615,
"step": 805
},
{
"epoch": 1.15,
"learning_rate": 4.118114232345311e-06,
"loss": 0.221,
"step": 806
},
{
"epoch": 1.15,
"learning_rate": 4.11390220741225e-06,
"loss": 0.1979,
"step": 807
},
{
"epoch": 1.16,
"learning_rate": 4.109687634043171e-06,
"loss": 0.2541,
"step": 808
},
{
"epoch": 1.16,
"learning_rate": 4.10547052188037e-06,
"loss": 0.2234,
"step": 809
},
{
"epoch": 1.16,
"learning_rate": 4.101250880571945e-06,
"loss": 0.2459,
"step": 810
},
{
"epoch": 1.16,
"learning_rate": 4.097028719771785e-06,
"loss": 0.1874,
"step": 811
},
{
"epoch": 1.16,
"learning_rate": 4.092804049139539e-06,
"loss": 0.2559,
"step": 812
},
{
"epoch": 1.16,
"learning_rate": 4.0885768783406024e-06,
"loss": 0.2564,
"step": 813
},
{
"epoch": 1.16,
"learning_rate": 4.084347217046086e-06,
"loss": 0.1937,
"step": 814
},
{
"epoch": 1.17,
"learning_rate": 4.080115074932802e-06,
"loss": 0.2427,
"step": 815
},
{
"epoch": 1.17,
"learning_rate": 4.075880461683238e-06,
"loss": 0.2169,
"step": 816
},
{
"epoch": 1.17,
"learning_rate": 4.071643386985534e-06,
"loss": 0.2374,
"step": 817
},
{
"epoch": 1.17,
"learning_rate": 4.067403860533461e-06,
"loss": 0.1836,
"step": 818
},
{
"epoch": 1.17,
"learning_rate": 4.063161892026399e-06,
"loss": 0.2399,
"step": 819
},
{
"epoch": 1.17,
"learning_rate": 4.058917491169318e-06,
"loss": 0.2226,
"step": 820
},
{
"epoch": 1.17,
"learning_rate": 4.054670667672751e-06,
"loss": 0.205,
"step": 821
},
{
"epoch": 1.18,
"learning_rate": 4.0504214312527704e-06,
"loss": 0.2272,
"step": 822
},
{
"epoch": 1.18,
"learning_rate": 4.046169791630977e-06,
"loss": 0.2465,
"step": 823
},
{
"epoch": 1.18,
"learning_rate": 4.041915758534461e-06,
"loss": 0.2318,
"step": 824
},
{
"epoch": 1.18,
"learning_rate": 4.037659341695794e-06,
"loss": 0.2242,
"step": 825
},
{
"epoch": 1.18,
"learning_rate": 4.0334005508529985e-06,
"loss": 0.2294,
"step": 826
},
{
"epoch": 1.18,
"learning_rate": 4.029139395749531e-06,
"loss": 0.2216,
"step": 827
},
{
"epoch": 1.18,
"learning_rate": 4.024875886134255e-06,
"loss": 0.2273,
"step": 828
},
{
"epoch": 1.19,
"learning_rate": 4.02061003176142e-06,
"loss": 0.2968,
"step": 829
},
{
"epoch": 1.19,
"learning_rate": 4.016341842390641e-06,
"loss": 0.2565,
"step": 830
},
{
"epoch": 1.19,
"learning_rate": 4.012071327786878e-06,
"loss": 0.2044,
"step": 831
},
{
"epoch": 1.19,
"learning_rate": 4.0077984977204065e-06,
"loss": 0.2323,
"step": 832
},
{
"epoch": 1.19,
"learning_rate": 4.0035233619668e-06,
"loss": 0.2307,
"step": 833
},
{
"epoch": 1.19,
"learning_rate": 3.999245930306911e-06,
"loss": 0.2872,
"step": 834
},
{
"epoch": 1.19,
"learning_rate": 3.994966212526838e-06,
"loss": 0.2152,
"step": 835
},
{
"epoch": 1.2,
"learning_rate": 3.990684218417916e-06,
"loss": 0.2366,
"step": 836
},
{
"epoch": 1.2,
"learning_rate": 3.986399957776685e-06,
"loss": 0.2502,
"step": 837
},
{
"epoch": 1.2,
"learning_rate": 3.982113440404871e-06,
"loss": 0.2519,
"step": 838
},
{
"epoch": 1.2,
"learning_rate": 3.9778246761093625e-06,
"loss": 0.2304,
"step": 839
},
{
"epoch": 1.2,
"learning_rate": 3.973533674702189e-06,
"loss": 0.2139,
"step": 840
},
{
"epoch": 1.2,
"learning_rate": 3.969240446000498e-06,
"loss": 0.219,
"step": 841
},
{
"epoch": 1.2,
"learning_rate": 3.964944999826534e-06,
"loss": 0.2125,
"step": 842
},
{
"epoch": 1.21,
"learning_rate": 3.9606473460076125e-06,
"loss": 0.2582,
"step": 843
},
{
"epoch": 1.21,
"learning_rate": 3.956347494376102e-06,
"loss": 0.2311,
"step": 844
},
{
"epoch": 1.21,
"learning_rate": 3.952045454769398e-06,
"loss": 0.1914,
"step": 845
},
{
"epoch": 1.21,
"learning_rate": 3.947741237029901e-06,
"loss": 0.1897,
"step": 846
},
{
"epoch": 1.21,
"learning_rate": 3.943434851004996e-06,
"loss": 0.2232,
"step": 847
},
{
"epoch": 1.21,
"learning_rate": 3.93912630654703e-06,
"loss": 0.1956,
"step": 848
},
{
"epoch": 1.21,
"learning_rate": 3.934815613513283e-06,
"loss": 0.2293,
"step": 849
},
{
"epoch": 1.22,
"learning_rate": 3.930502781765958e-06,
"loss": 0.2412,
"step": 850
},
{
"epoch": 1.22,
"learning_rate": 3.9261878211721454e-06,
"loss": 0.2277,
"step": 851
},
{
"epoch": 1.22,
"learning_rate": 3.921870741603807e-06,
"loss": 0.2664,
"step": 852
},
{
"epoch": 1.22,
"learning_rate": 3.917551552937754e-06,
"loss": 0.2212,
"step": 853
},
{
"epoch": 1.22,
"learning_rate": 3.913230265055624e-06,
"loss": 0.2407,
"step": 854
},
{
"epoch": 1.22,
"learning_rate": 3.908906887843853e-06,
"loss": 0.2051,
"step": 855
},
{
"epoch": 1.22,
"learning_rate": 3.9045814311936605e-06,
"loss": 0.2261,
"step": 856
},
{
"epoch": 1.23,
"learning_rate": 3.900253905001022e-06,
"loss": 0.2396,
"step": 857
},
{
"epoch": 1.23,
"learning_rate": 3.8959243191666496e-06,
"loss": 0.2664,
"step": 858
},
{
"epoch": 1.23,
"learning_rate": 3.8915926835959656e-06,
"loss": 0.2494,
"step": 859
},
{
"epoch": 1.23,
"learning_rate": 3.887259008199082e-06,
"loss": 0.2007,
"step": 860
},
{
"epoch": 1.23,
"learning_rate": 3.882923302890778e-06,
"loss": 0.221,
"step": 861
},
{
"epoch": 1.23,
"learning_rate": 3.878585577590477e-06,
"loss": 0.2161,
"step": 862
},
{
"epoch": 1.23,
"learning_rate": 3.874245842222224e-06,
"loss": 0.2429,
"step": 863
},
{
"epoch": 1.24,
"learning_rate": 3.869904106714662e-06,
"loss": 0.1863,
"step": 864
},
{
"epoch": 1.24,
"learning_rate": 3.865560381001012e-06,
"loss": 0.2017,
"step": 865
},
{
"epoch": 1.24,
"learning_rate": 3.861214675019047e-06,
"loss": 0.232,
"step": 866
},
{
"epoch": 1.24,
"learning_rate": 3.8568669987110674e-06,
"loss": 0.2333,
"step": 867
},
{
"epoch": 1.24,
"learning_rate": 3.852517362023886e-06,
"loss": 0.2566,
"step": 868
},
{
"epoch": 1.24,
"learning_rate": 3.8481657749088e-06,
"loss": 0.241,
"step": 869
},
{
"epoch": 1.24,
"learning_rate": 3.843812247321566e-06,
"loss": 0.2219,
"step": 870
},
{
"epoch": 1.25,
"learning_rate": 3.839456789222384e-06,
"loss": 0.251,
"step": 871
},
{
"epoch": 1.25,
"learning_rate": 3.835099410575867e-06,
"loss": 0.2309,
"step": 872
},
{
"epoch": 1.25,
"learning_rate": 3.830740121351024e-06,
"loss": 0.196,
"step": 873
},
{
"epoch": 1.25,
"learning_rate": 3.826378931521235e-06,
"loss": 0.2373,
"step": 874
},
{
"epoch": 1.25,
"learning_rate": 3.822015851064228e-06,
"loss": 0.2169,
"step": 875
},
{
"epoch": 1.25,
"learning_rate": 3.817650889962056e-06,
"loss": 0.2422,
"step": 876
},
{
"epoch": 1.25,
"learning_rate": 3.8132840582010754e-06,
"loss": 0.1846,
"step": 877
},
{
"epoch": 1.26,
"learning_rate": 3.8089153657719217e-06,
"loss": 0.245,
"step": 878
},
{
"epoch": 1.26,
"learning_rate": 3.804544822669489e-06,
"loss": 0.2179,
"step": 879
},
{
"epoch": 1.26,
"learning_rate": 3.8001724388929026e-06,
"loss": 0.2308,
"step": 880
},
{
"epoch": 1.26,
"learning_rate": 3.795798224445501e-06,
"loss": 0.2756,
"step": 881
},
{
"epoch": 1.26,
"learning_rate": 3.791422189334811e-06,
"loss": 0.2137,
"step": 882
},
{
"epoch": 1.26,
"learning_rate": 3.7870443435725235e-06,
"loss": 0.2354,
"step": 883
},
{
"epoch": 1.26,
"learning_rate": 3.782664697174473e-06,
"loss": 0.2577,
"step": 884
},
{
"epoch": 1.27,
"learning_rate": 3.778283260160613e-06,
"loss": 0.2459,
"step": 885
},
{
"epoch": 1.27,
"learning_rate": 3.773900042554995e-06,
"loss": 0.1936,
"step": 886
},
{
"epoch": 1.27,
"learning_rate": 3.769515054385742e-06,
"loss": 0.1819,
"step": 887
},
{
"epoch": 1.27,
"learning_rate": 3.7651283056850297e-06,
"loss": 0.1639,
"step": 888
},
{
"epoch": 1.27,
"learning_rate": 3.76073980648906e-06,
"loss": 0.2414,
"step": 889
},
{
"epoch": 1.27,
"learning_rate": 3.756349566838041e-06,
"loss": 0.2417,
"step": 890
},
{
"epoch": 1.27,
"learning_rate": 3.751957596776162e-06,
"loss": 0.2356,
"step": 891
},
{
"epoch": 1.28,
"learning_rate": 3.7475639063515717e-06,
"loss": 0.2202,
"step": 892
},
{
"epoch": 1.28,
"learning_rate": 3.7431685056163537e-06,
"loss": 0.2419,
"step": 893
},
{
"epoch": 1.28,
"learning_rate": 3.7387714046265068e-06,
"loss": 0.2137,
"step": 894
},
{
"epoch": 1.28,
"learning_rate": 3.734372613441916e-06,
"loss": 0.2891,
"step": 895
},
{
"epoch": 1.28,
"learning_rate": 3.729972142126337e-06,
"loss": 0.2222,
"step": 896
},
{
"epoch": 1.28,
"learning_rate": 3.725570000747367e-06,
"loss": 0.2272,
"step": 897
},
{
"epoch": 1.28,
"learning_rate": 3.721166199376426e-06,
"loss": 0.1705,
"step": 898
},
{
"epoch": 1.29,
"learning_rate": 3.7167607480887293e-06,
"loss": 0.2249,
"step": 899
},
{
"epoch": 1.29,
"learning_rate": 3.712353656963268e-06,
"loss": 0.2462,
"step": 900
},
{
"epoch": 1.29,
"learning_rate": 3.707944936082787e-06,
"loss": 0.212,
"step": 901
},
{
"epoch": 1.29,
"learning_rate": 3.7035345955337557e-06,
"loss": 0.2637,
"step": 902
},
{
"epoch": 1.29,
"learning_rate": 3.6991226454063532e-06,
"loss": 0.2284,
"step": 903
},
{
"epoch": 1.29,
"learning_rate": 3.6947090957944377e-06,
"loss": 0.216,
"step": 904
},
{
"epoch": 1.29,
"learning_rate": 3.6902939567955297e-06,
"loss": 0.2334,
"step": 905
},
{
"epoch": 1.3,
"learning_rate": 3.6858772385107833e-06,
"loss": 0.2554,
"step": 906
},
{
"epoch": 1.3,
"learning_rate": 3.681458951044968e-06,
"loss": 0.2249,
"step": 907
},
{
"epoch": 1.3,
"learning_rate": 3.677039104506442e-06,
"loss": 0.2018,
"step": 908
},
{
"epoch": 1.3,
"learning_rate": 3.6726177090071307e-06,
"loss": 0.2244,
"step": 909
},
{
"epoch": 1.3,
"learning_rate": 3.668194774662503e-06,
"loss": 0.1904,
"step": 910
},
{
"epoch": 1.3,
"learning_rate": 3.6637703115915487e-06,
"loss": 0.2114,
"step": 911
},
{
"epoch": 1.3,
"learning_rate": 3.659344329916756e-06,
"loss": 0.2183,
"step": 912
},
{
"epoch": 1.31,
"learning_rate": 3.654916839764087e-06,
"loss": 0.2317,
"step": 913
},
{
"epoch": 1.31,
"learning_rate": 3.6504878512629534e-06,
"loss": 0.2752,
"step": 914
},
{
"epoch": 1.31,
"learning_rate": 3.6460573745461964e-06,
"loss": 0.2391,
"step": 915
},
{
"epoch": 1.31,
"learning_rate": 3.6416254197500616e-06,
"loss": 0.2483,
"step": 916
},
{
"epoch": 1.31,
"learning_rate": 3.6371919970141765e-06,
"loss": 0.2548,
"step": 917
},
{
"epoch": 1.31,
"learning_rate": 3.632757116481526e-06,
"loss": 0.2573,
"step": 918
},
{
"epoch": 1.31,
"learning_rate": 3.6283207882984344e-06,
"loss": 0.1811,
"step": 919
},
{
"epoch": 1.32,
"learning_rate": 3.6238830226145294e-06,
"loss": 0.2179,
"step": 920
},
{
"epoch": 1.32,
"learning_rate": 3.6194438295827363e-06,
"loss": 0.2537,
"step": 921
},
{
"epoch": 1.32,
"learning_rate": 3.6150032193592407e-06,
"loss": 0.2179,
"step": 922
},
{
"epoch": 1.32,
"learning_rate": 3.6105612021034734e-06,
"loss": 0.252,
"step": 923
},
{
"epoch": 1.32,
"learning_rate": 3.6061177879780824e-06,
"loss": 0.2221,
"step": 924
},
{
"epoch": 1.32,
"learning_rate": 3.6016729871489123e-06,
"loss": 0.1989,
"step": 925
},
{
"epoch": 1.32,
"learning_rate": 3.5972268097849804e-06,
"loss": 0.2574,
"step": 926
},
{
"epoch": 1.33,
"learning_rate": 3.5927792660584526e-06,
"loss": 0.283,
"step": 927
},
{
"epoch": 1.33,
"learning_rate": 3.5883303661446206e-06,
"loss": 0.2599,
"step": 928
},
{
"epoch": 1.33,
"learning_rate": 3.5838801202218807e-06,
"loss": 0.2187,
"step": 929
},
{
"epoch": 1.33,
"learning_rate": 3.5794285384717075e-06,
"loss": 0.1921,
"step": 930
},
{
"epoch": 1.33,
"learning_rate": 3.5749756310786312e-06,
"loss": 0.2569,
"step": 931
},
{
"epoch": 1.33,
"learning_rate": 3.5705214082302143e-06,
"loss": 0.2195,
"step": 932
},
{
"epoch": 1.33,
"learning_rate": 3.566065880117032e-06,
"loss": 0.2248,
"step": 933
},
{
"epoch": 1.34,
"learning_rate": 3.5616090569326427e-06,
"loss": 0.2446,
"step": 934
},
{
"epoch": 1.34,
"learning_rate": 3.5571509488735687e-06,
"loss": 0.2268,
"step": 935
},
{
"epoch": 1.34,
"learning_rate": 3.5526915661392725e-06,
"loss": 0.2877,
"step": 936
},
{
"epoch": 1.34,
"learning_rate": 3.5482309189321317e-06,
"loss": 0.2189,
"step": 937
},
{
"epoch": 1.34,
"learning_rate": 3.543769017457417e-06,
"loss": 0.241,
"step": 938
},
{
"epoch": 1.34,
"learning_rate": 3.539305871923269e-06,
"loss": 0.2441,
"step": 939
},
{
"epoch": 1.34,
"learning_rate": 3.5348414925406766e-06,
"loss": 0.2092,
"step": 940
},
{
"epoch": 1.35,
"learning_rate": 3.530375889523447e-06,
"loss": 0.1927,
"step": 941
},
{
"epoch": 1.35,
"learning_rate": 3.5259090730881907e-06,
"loss": 0.2179,
"step": 942
},
{
"epoch": 1.35,
"learning_rate": 3.5214410534542934e-06,
"loss": 0.2018,
"step": 943
},
{
"epoch": 1.35,
"learning_rate": 3.5169718408438916e-06,
"loss": 0.227,
"step": 944
},
{
"epoch": 1.35,
"learning_rate": 3.5125014454818545e-06,
"loss": 0.2299,
"step": 945
},
{
"epoch": 1.35,
"learning_rate": 3.5080298775957542e-06,
"loss": 0.2183,
"step": 946
},
{
"epoch": 1.35,
"learning_rate": 3.5035571474158473e-06,
"loss": 0.2069,
"step": 947
},
{
"epoch": 1.36,
"learning_rate": 3.4990832651750485e-06,
"loss": 0.2025,
"step": 948
},
{
"epoch": 1.36,
"learning_rate": 3.4946082411089082e-06,
"loss": 0.2453,
"step": 949
},
{
"epoch": 1.36,
"learning_rate": 3.4901320854555903e-06,
"loss": 0.1797,
"step": 950
},
{
"epoch": 1.36,
"learning_rate": 3.485654808455847e-06,
"loss": 0.2219,
"step": 951
},
{
"epoch": 1.36,
"learning_rate": 3.481176420352996e-06,
"loss": 0.2076,
"step": 952
},
{
"epoch": 1.36,
"learning_rate": 3.4766969313928946e-06,
"loss": 0.2665,
"step": 953
},
{
"epoch": 1.36,
"learning_rate": 3.4722163518239235e-06,
"loss": 0.2743,
"step": 954
},
{
"epoch": 1.37,
"learning_rate": 3.4677346918969545e-06,
"loss": 0.2199,
"step": 955
},
{
"epoch": 1.37,
"learning_rate": 3.4632519618653327e-06,
"loss": 0.2081,
"step": 956
},
{
"epoch": 1.37,
"learning_rate": 3.458768171984853e-06,
"loss": 0.2071,
"step": 957
},
{
"epoch": 1.37,
"learning_rate": 3.4542833325137304e-06,
"loss": 0.2156,
"step": 958
},
{
"epoch": 1.37,
"learning_rate": 3.4497974537125863e-06,
"loss": 0.2301,
"step": 959
},
{
"epoch": 1.37,
"learning_rate": 3.4453105458444168e-06,
"loss": 0.2285,
"step": 960
},
{
"epoch": 1.37,
"learning_rate": 3.4408226191745736e-06,
"loss": 0.2158,
"step": 961
},
{
"epoch": 1.38,
"learning_rate": 3.43633368397074e-06,
"loss": 0.2187,
"step": 962
},
{
"epoch": 1.38,
"learning_rate": 3.431843750502903e-06,
"loss": 0.2404,
"step": 963
},
{
"epoch": 1.38,
"learning_rate": 3.4273528290433387e-06,
"loss": 0.2165,
"step": 964
},
{
"epoch": 1.38,
"learning_rate": 3.4228609298665803e-06,
"loss": 0.214,
"step": 965
},
{
"epoch": 1.38,
"learning_rate": 3.4183680632493987e-06,
"loss": 0.192,
"step": 966
},
{
"epoch": 1.38,
"learning_rate": 3.4138742394707774e-06,
"loss": 0.2461,
"step": 967
},
{
"epoch": 1.38,
"learning_rate": 3.409379468811891e-06,
"loss": 0.2496,
"step": 968
},
{
"epoch": 1.39,
"learning_rate": 3.4048837615560785e-06,
"loss": 0.6325,
"step": 969
},
{
"epoch": 1.39,
"learning_rate": 3.400387127988824e-06,
"loss": 0.2153,
"step": 970
},
{
"epoch": 1.39,
"learning_rate": 3.39588957839773e-06,
"loss": 0.238,
"step": 971
},
{
"epoch": 1.39,
"learning_rate": 3.391391123072494e-06,
"loss": 0.2321,
"step": 972
},
{
"epoch": 1.39,
"learning_rate": 3.3868917723048877e-06,
"loss": 0.185,
"step": 973
},
{
"epoch": 1.39,
"learning_rate": 3.3823915363887274e-06,
"loss": 0.2346,
"step": 974
},
{
"epoch": 1.39,
"learning_rate": 3.3778904256198585e-06,
"loss": 0.2314,
"step": 975
},
{
"epoch": 1.4,
"learning_rate": 3.373388450296127e-06,
"loss": 0.1952,
"step": 976
},
{
"epoch": 1.4,
"learning_rate": 3.3688856207173547e-06,
"loss": 0.1985,
"step": 977
},
{
"epoch": 1.4,
"learning_rate": 3.364381947185322e-06,
"loss": 0.2439,
"step": 978
},
{
"epoch": 1.4,
"learning_rate": 3.359877440003734e-06,
"loss": 0.2186,
"step": 979
},
{
"epoch": 1.4,
"learning_rate": 3.3553721094782103e-06,
"loss": 0.2174,
"step": 980
},
{
"epoch": 1.4,
"learning_rate": 3.3508659659162483e-06,
"loss": 0.2146,
"step": 981
},
{
"epoch": 1.4,
"learning_rate": 3.3463590196272075e-06,
"loss": 0.2226,
"step": 982
},
{
"epoch": 1.41,
"learning_rate": 3.341851280922285e-06,
"loss": 0.2485,
"step": 983
},
{
"epoch": 1.41,
"learning_rate": 3.33734276011449e-06,
"loss": 0.2318,
"step": 984
},
{
"epoch": 1.41,
"learning_rate": 3.332833467518621e-06,
"loss": 0.2282,
"step": 985
},
{
"epoch": 1.41,
"learning_rate": 3.3283234134512416e-06,
"loss": 0.1986,
"step": 986
},
{
"epoch": 1.41,
"learning_rate": 3.323812608230659e-06,
"loss": 0.2302,
"step": 987
},
{
"epoch": 1.41,
"learning_rate": 3.319301062176898e-06,
"loss": 0.1959,
"step": 988
},
{
"epoch": 1.41,
"learning_rate": 3.314788785611678e-06,
"loss": 0.2331,
"step": 989
},
{
"epoch": 1.42,
"learning_rate": 3.3102757888583897e-06,
"loss": 0.2268,
"step": 990
},
{
"epoch": 1.42,
"learning_rate": 3.3057620822420723e-06,
"loss": 0.2533,
"step": 991
},
{
"epoch": 1.42,
"learning_rate": 3.3012476760893886e-06,
"loss": 0.2442,
"step": 992
},
{
"epoch": 1.42,
"learning_rate": 3.296732580728601e-06,
"loss": 0.2008,
"step": 993
},
{
"epoch": 1.42,
"learning_rate": 3.2922168064895514e-06,
"loss": 0.2409,
"step": 994
},
{
"epoch": 1.42,
"learning_rate": 3.2877003637036316e-06,
"loss": 0.2161,
"step": 995
},
{
"epoch": 1.42,
"learning_rate": 3.283183262703765e-06,
"loss": 0.2152,
"step": 996
},
{
"epoch": 1.43,
"learning_rate": 3.27866551382438e-06,
"loss": 0.213,
"step": 997
},
{
"epoch": 1.43,
"learning_rate": 3.2741471274013874e-06,
"loss": 0.2242,
"step": 998
},
{
"epoch": 1.43,
"learning_rate": 3.2696281137721567e-06,
"loss": 0.2026,
"step": 999
},
{
"epoch": 1.43,
"learning_rate": 3.2651084832754922e-06,
"loss": 0.2185,
"step": 1000
},
{
"epoch": 1.43,
"learning_rate": 3.26058824625161e-06,
"loss": 0.2347,
"step": 1001
},
{
"epoch": 1.43,
"learning_rate": 3.256067413042114e-06,
"loss": 0.2731,
"step": 1002
},
{
"epoch": 1.43,
"learning_rate": 3.2515459939899697e-06,
"loss": 0.2042,
"step": 1003
},
{
"epoch": 1.44,
"learning_rate": 3.2470239994394868e-06,
"loss": 0.2097,
"step": 1004
},
{
"epoch": 1.44,
"learning_rate": 3.242501439736288e-06,
"loss": 0.2261,
"step": 1005
},
{
"epoch": 1.44,
"learning_rate": 3.2379783252272918e-06,
"loss": 0.1997,
"step": 1006
},
{
"epoch": 1.44,
"learning_rate": 3.233454666260684e-06,
"loss": 0.2017,
"step": 1007
},
{
"epoch": 1.44,
"learning_rate": 3.2289304731858983e-06,
"loss": 0.2377,
"step": 1008
},
{
"epoch": 1.44,
"learning_rate": 3.2244057563535872e-06,
"loss": 0.2043,
"step": 1009
},
{
"epoch": 1.44,
"learning_rate": 3.219880526115603e-06,
"loss": 0.2355,
"step": 1010
},
{
"epoch": 1.45,
"learning_rate": 3.2153547928249754e-06,
"loss": 0.2096,
"step": 1011
},
{
"epoch": 1.45,
"learning_rate": 3.210828566835879e-06,
"loss": 0.2244,
"step": 1012
},
{
"epoch": 1.45,
"learning_rate": 3.2063018585036215e-06,
"loss": 0.2251,
"step": 1013
},
{
"epoch": 1.45,
"learning_rate": 3.2017746781846107e-06,
"loss": 0.216,
"step": 1014
},
{
"epoch": 1.45,
"learning_rate": 3.197247036236335e-06,
"loss": 0.1726,
"step": 1015
},
{
"epoch": 1.45,
"learning_rate": 3.1927189430173398e-06,
"loss": 0.2361,
"step": 1016
},
{
"epoch": 1.45,
"learning_rate": 3.1881904088872007e-06,
"loss": 0.2659,
"step": 1017
},
{
"epoch": 1.46,
"learning_rate": 3.1836614442065054e-06,
"loss": 0.2586,
"step": 1018
},
{
"epoch": 1.46,
"learning_rate": 3.1791320593368236e-06,
"loss": 0.2091,
"step": 1019
},
{
"epoch": 1.46,
"learning_rate": 3.1746022646406883e-06,
"loss": 0.2414,
"step": 1020
},
{
"epoch": 1.46,
"learning_rate": 3.170072070481569e-06,
"loss": 0.2078,
"step": 1021
},
{
"epoch": 1.46,
"learning_rate": 3.1655414872238503e-06,
"loss": 0.2246,
"step": 1022
},
{
"epoch": 1.46,
"learning_rate": 3.1610105252328043e-06,
"loss": 0.23,
"step": 1023
},
{
"epoch": 1.46,
"learning_rate": 3.1564791948745724e-06,
"loss": 0.2001,
"step": 1024
},
{
"epoch": 1.47,
"learning_rate": 3.1519475065161383e-06,
"loss": 0.2226,
"step": 1025
},
{
"epoch": 1.47,
"learning_rate": 3.1474154705253033e-06,
"loss": 0.1864,
"step": 1026
},
{
"epoch": 1.47,
"learning_rate": 3.142883097270667e-06,
"loss": 0.2222,
"step": 1027
},
{
"epoch": 1.47,
"learning_rate": 3.1383503971215952e-06,
"loss": 0.2479,
"step": 1028
},
{
"epoch": 1.47,
"learning_rate": 3.1338173804482087e-06,
"loss": 0.2109,
"step": 1029
},
{
"epoch": 1.47,
"learning_rate": 3.1292840576213464e-06,
"loss": 0.2025,
"step": 1030
},
{
"epoch": 1.47,
"learning_rate": 3.1247504390125497e-06,
"loss": 0.2233,
"step": 1031
},
{
"epoch": 1.48,
"learning_rate": 3.1202165349940396e-06,
"loss": 0.2266,
"step": 1032
},
{
"epoch": 1.48,
"learning_rate": 3.115682355938684e-06,
"loss": 0.227,
"step": 1033
},
{
"epoch": 1.48,
"learning_rate": 3.111147912219986e-06,
"loss": 0.2213,
"step": 1034
},
{
"epoch": 1.48,
"learning_rate": 3.106613214212051e-06,
"loss": 0.1847,
"step": 1035
},
{
"epoch": 1.48,
"learning_rate": 3.1020782722895653e-06,
"loss": 0.1925,
"step": 1036
},
{
"epoch": 1.48,
"learning_rate": 3.097543096827778e-06,
"loss": 0.2045,
"step": 1037
},
{
"epoch": 1.48,
"learning_rate": 3.0930076982024668e-06,
"loss": 0.256,
"step": 1038
},
{
"epoch": 1.49,
"learning_rate": 3.0884720867899238e-06,
"loss": 0.2373,
"step": 1039
},
{
"epoch": 1.49,
"learning_rate": 3.083936272966925e-06,
"loss": 0.2235,
"step": 1040
},
{
"epoch": 1.49,
"learning_rate": 3.079400267110713e-06,
"loss": 0.2036,
"step": 1041
},
{
"epoch": 1.49,
"learning_rate": 3.074864079598966e-06,
"loss": 0.2277,
"step": 1042
},
{
"epoch": 1.49,
"learning_rate": 3.070327720809782e-06,
"loss": 0.2278,
"step": 1043
},
{
"epoch": 1.49,
"learning_rate": 3.0657912011216463e-06,
"loss": 0.2212,
"step": 1044
},
{
"epoch": 1.49,
"learning_rate": 3.0612545309134147e-06,
"loss": 0.1951,
"step": 1045
},
{
"epoch": 1.5,
"learning_rate": 3.0567177205642885e-06,
"loss": 0.1843,
"step": 1046
},
{
"epoch": 1.5,
"learning_rate": 3.0521807804537864e-06,
"loss": 0.176,
"step": 1047
},
{
"epoch": 1.5,
"learning_rate": 3.0476437209617293e-06,
"loss": 0.2035,
"step": 1048
},
{
"epoch": 1.5,
"learning_rate": 3.043106552468203e-06,
"loss": 0.2449,
"step": 1049
},
{
"epoch": 1.5,
"learning_rate": 3.0385692853535514e-06,
"loss": 0.2313,
"step": 1050
},
{
"epoch": 1.5,
"learning_rate": 3.034031929998338e-06,
"loss": 0.3627,
"step": 1051
},
{
"epoch": 1.51,
"learning_rate": 3.0294944967833313e-06,
"loss": 0.2246,
"step": 1052
},
{
"epoch": 1.51,
"learning_rate": 3.024956996089476e-06,
"loss": 0.1681,
"step": 1053
},
{
"epoch": 1.51,
"learning_rate": 3.020419438297873e-06,
"loss": 0.2013,
"step": 1054
},
{
"epoch": 1.51,
"learning_rate": 3.015881833789752e-06,
"loss": 0.2459,
"step": 1055
},
{
"epoch": 1.51,
"learning_rate": 3.011344192946452e-06,
"loss": 0.2272,
"step": 1056
},
{
"epoch": 1.51,
"learning_rate": 3.0068065261493907e-06,
"loss": 0.2728,
"step": 1057
},
{
"epoch": 1.51,
"learning_rate": 3.002268843780052e-06,
"loss": 0.2138,
"step": 1058
},
{
"epoch": 1.52,
"learning_rate": 2.997731156219948e-06,
"loss": 0.234,
"step": 1059
},
{
"epoch": 1.52,
"learning_rate": 2.9931934738506095e-06,
"loss": 0.2318,
"step": 1060
},
{
"epoch": 1.52,
"learning_rate": 2.9886558070535487e-06,
"loss": 0.2369,
"step": 1061
},
{
"epoch": 1.52,
"learning_rate": 2.9841181662102484e-06,
"loss": 0.2356,
"step": 1062
},
{
"epoch": 1.52,
"learning_rate": 2.9795805617021276e-06,
"loss": 0.2287,
"step": 1063
},
{
"epoch": 1.52,
"learning_rate": 2.975043003910524e-06,
"loss": 0.2352,
"step": 1064
},
{
"epoch": 1.52,
"learning_rate": 2.9705055032166697e-06,
"loss": 0.2381,
"step": 1065
},
{
"epoch": 1.53,
"learning_rate": 2.9659680700016615e-06,
"loss": 0.2168,
"step": 1066
},
{
"epoch": 1.53,
"learning_rate": 2.961430714646449e-06,
"loss": 0.2494,
"step": 1067
},
{
"epoch": 1.53,
"learning_rate": 2.956893447531797e-06,
"loss": 0.2445,
"step": 1068
},
{
"epoch": 1.53,
"learning_rate": 2.9523562790382713e-06,
"loss": 0.2397,
"step": 1069
},
{
"epoch": 1.53,
"learning_rate": 2.9478192195462138e-06,
"loss": 0.2239,
"step": 1070
},
{
"epoch": 1.53,
"learning_rate": 2.9432822794357112e-06,
"loss": 0.2007,
"step": 1071
},
{
"epoch": 1.53,
"learning_rate": 2.938745469086586e-06,
"loss": 0.1833,
"step": 1072
},
{
"epoch": 1.54,
"learning_rate": 2.934208798878355e-06,
"loss": 0.1898,
"step": 1073
},
{
"epoch": 1.54,
"learning_rate": 2.929672279190219e-06,
"loss": 0.2262,
"step": 1074
},
{
"epoch": 1.54,
"learning_rate": 2.925135920401034e-06,
"loss": 0.2187,
"step": 1075
},
{
"epoch": 1.54,
"learning_rate": 2.920599732889287e-06,
"loss": 0.2451,
"step": 1076
},
{
"epoch": 1.54,
"learning_rate": 2.916063727033076e-06,
"loss": 0.2173,
"step": 1077
},
{
"epoch": 1.54,
"learning_rate": 2.9115279132100776e-06,
"loss": 0.2003,
"step": 1078
},
{
"epoch": 1.54,
"learning_rate": 2.906992301797534e-06,
"loss": 0.2564,
"step": 1079
},
{
"epoch": 1.55,
"learning_rate": 2.9024569031722228e-06,
"loss": 0.2176,
"step": 1080
},
{
"epoch": 1.55,
"learning_rate": 2.897921727710434e-06,
"loss": 0.2086,
"step": 1081
},
{
"epoch": 1.55,
"learning_rate": 2.8933867857879498e-06,
"loss": 0.2124,
"step": 1082
},
{
"epoch": 1.55,
"learning_rate": 2.888852087780015e-06,
"loss": 0.2045,
"step": 1083
},
{
"epoch": 1.55,
"learning_rate": 2.8843176440613164e-06,
"loss": 0.255,
"step": 1084
},
{
"epoch": 1.55,
"learning_rate": 2.879783465005962e-06,
"loss": 0.2352,
"step": 1085
},
{
"epoch": 1.55,
"learning_rate": 2.8752495609874496e-06,
"loss": 0.1461,
"step": 1086
},
{
"epoch": 1.56,
"learning_rate": 2.870715942378654e-06,
"loss": 0.2197,
"step": 1087
},
{
"epoch": 1.56,
"learning_rate": 2.866182619551791e-06,
"loss": 0.2011,
"step": 1088
},
{
"epoch": 1.56,
"learning_rate": 2.861649602878405e-06,
"loss": 0.2113,
"step": 1089
},
{
"epoch": 1.56,
"learning_rate": 2.857116902729334e-06,
"loss": 0.2453,
"step": 1090
},
{
"epoch": 1.56,
"learning_rate": 2.8525845294746964e-06,
"loss": 0.2127,
"step": 1091
},
{
"epoch": 1.56,
"learning_rate": 2.8480524934838623e-06,
"loss": 0.208,
"step": 1092
},
{
"epoch": 1.56,
"learning_rate": 2.8435208051254273e-06,
"loss": 0.2652,
"step": 1093
},
{
"epoch": 1.57,
"learning_rate": 2.8389894747671963e-06,
"loss": 0.2779,
"step": 1094
},
{
"epoch": 1.57,
"learning_rate": 2.8344585127761515e-06,
"loss": 0.2508,
"step": 1095
},
{
"epoch": 1.57,
"learning_rate": 2.829927929518431e-06,
"loss": 0.2178,
"step": 1096
},
{
"epoch": 1.57,
"learning_rate": 2.825397735359312e-06,
"loss": 0.2497,
"step": 1097
},
{
"epoch": 1.57,
"learning_rate": 2.820867940663176e-06,
"loss": 0.1649,
"step": 1098
},
{
"epoch": 1.57,
"learning_rate": 2.8163385557934948e-06,
"loss": 0.2703,
"step": 1099
},
{
"epoch": 1.57,
"learning_rate": 2.8118095911128003e-06,
"loss": 0.2083,
"step": 1100
},
{
"epoch": 1.58,
"learning_rate": 2.8072810569826604e-06,
"loss": 0.2243,
"step": 1101
},
{
"epoch": 1.58,
"learning_rate": 2.802752963763666e-06,
"loss": 0.2159,
"step": 1102
},
{
"epoch": 1.58,
"learning_rate": 2.79822532181539e-06,
"loss": 0.1964,
"step": 1103
},
{
"epoch": 1.58,
"learning_rate": 2.793698141496379e-06,
"loss": 0.2152,
"step": 1104
},
{
"epoch": 1.58,
"learning_rate": 2.7891714331641223e-06,
"loss": 0.1824,
"step": 1105
},
{
"epoch": 1.58,
"learning_rate": 2.784645207175025e-06,
"loss": 0.2112,
"step": 1106
},
{
"epoch": 1.58,
"learning_rate": 2.7801194738843974e-06,
"loss": 0.2479,
"step": 1107
},
{
"epoch": 1.59,
"learning_rate": 2.7755942436464137e-06,
"loss": 0.151,
"step": 1108
},
{
"epoch": 1.59,
"learning_rate": 2.7710695268141027e-06,
"loss": 0.2345,
"step": 1109
},
{
"epoch": 1.59,
"learning_rate": 2.7665453337393163e-06,
"loss": 0.1929,
"step": 1110
},
{
"epoch": 1.59,
"learning_rate": 2.762021674772709e-06,
"loss": 0.2398,
"step": 1111
},
{
"epoch": 1.59,
"learning_rate": 2.7574985602637133e-06,
"loss": 0.2132,
"step": 1112
},
{
"epoch": 1.59,
"learning_rate": 2.7529760005605134e-06,
"loss": 0.193,
"step": 1113
},
{
"epoch": 1.59,
"learning_rate": 2.7484540060100312e-06,
"loss": 0.196,
"step": 1114
},
{
"epoch": 1.6,
"learning_rate": 2.7439325869578875e-06,
"loss": 0.187,
"step": 1115
},
{
"epoch": 1.6,
"learning_rate": 2.73941175374839e-06,
"loss": 0.2228,
"step": 1116
},
{
"epoch": 1.6,
"learning_rate": 2.7348915167245084e-06,
"loss": 0.2124,
"step": 1117
},
{
"epoch": 1.6,
"learning_rate": 2.730371886227843e-06,
"loss": 0.1919,
"step": 1118
},
{
"epoch": 1.6,
"learning_rate": 2.725852872598613e-06,
"loss": 0.2161,
"step": 1119
},
{
"epoch": 1.6,
"learning_rate": 2.7213344861756205e-06,
"loss": 0.2409,
"step": 1120
},
{
"epoch": 1.6,
"learning_rate": 2.7168167372962354e-06,
"loss": 0.1924,
"step": 1121
},
{
"epoch": 1.61,
"learning_rate": 2.7122996362963686e-06,
"loss": 0.1949,
"step": 1122
},
{
"epoch": 1.61,
"learning_rate": 2.7077831935104484e-06,
"loss": 0.1505,
"step": 1123
},
{
"epoch": 1.61,
"learning_rate": 2.7032674192713996e-06,
"loss": 0.1843,
"step": 1124
},
{
"epoch": 1.61,
"learning_rate": 2.6987523239106115e-06,
"loss": 0.2494,
"step": 1125
},
{
"epoch": 1.61,
"learning_rate": 2.6942379177579287e-06,
"loss": 0.2086,
"step": 1126
},
{
"epoch": 1.61,
"learning_rate": 2.6897242111416113e-06,
"loss": 0.2475,
"step": 1127
},
{
"epoch": 1.61,
"learning_rate": 2.685211214388322e-06,
"loss": 0.1914,
"step": 1128
},
{
"epoch": 1.62,
"learning_rate": 2.680698937823102e-06,
"loss": 0.2481,
"step": 1129
},
{
"epoch": 1.62,
"learning_rate": 2.67618739176934e-06,
"loss": 0.23,
"step": 1130
},
{
"epoch": 1.62,
"learning_rate": 2.6716765865487585e-06,
"loss": 0.205,
"step": 1131
},
{
"epoch": 1.62,
"learning_rate": 2.6671665324813796e-06,
"loss": 0.2068,
"step": 1132
},
{
"epoch": 1.62,
"learning_rate": 2.66265723988551e-06,
"loss": 0.1879,
"step": 1133
},
{
"epoch": 1.62,
"learning_rate": 2.6581487190777155e-06,
"loss": 0.2192,
"step": 1134
},
{
"epoch": 1.62,
"learning_rate": 2.6536409803727926e-06,
"loss": 0.2167,
"step": 1135
},
{
"epoch": 1.63,
"learning_rate": 2.6491340340837527e-06,
"loss": 0.2192,
"step": 1136
},
{
"epoch": 1.63,
"learning_rate": 2.644627890521791e-06,
"loss": 0.2218,
"step": 1137
},
{
"epoch": 1.63,
"learning_rate": 2.6401225599962663e-06,
"loss": 0.1915,
"step": 1138
},
{
"epoch": 1.63,
"learning_rate": 2.6356180528146793e-06,
"loss": 0.2005,
"step": 1139
},
{
"epoch": 1.63,
"learning_rate": 2.6311143792826454e-06,
"loss": 0.2011,
"step": 1140
},
{
"epoch": 1.63,
"learning_rate": 2.6266115497038736e-06,
"loss": 0.2276,
"step": 1141
},
{
"epoch": 1.63,
"learning_rate": 2.6221095743801425e-06,
"loss": 0.2223,
"step": 1142
},
{
"epoch": 1.64,
"learning_rate": 2.6176084636112732e-06,
"loss": 0.2489,
"step": 1143
},
{
"epoch": 1.64,
"learning_rate": 2.6131082276951137e-06,
"loss": 0.2019,
"step": 1144
},
{
"epoch": 1.64,
"learning_rate": 2.608608876927506e-06,
"loss": 0.2386,
"step": 1145
},
{
"epoch": 1.64,
"learning_rate": 2.6041104216022707e-06,
"loss": 0.2077,
"step": 1146
},
{
"epoch": 1.64,
"learning_rate": 2.5996128720111763e-06,
"loss": 0.2446,
"step": 1147
},
{
"epoch": 1.64,
"learning_rate": 2.595116238443922e-06,
"loss": 0.2464,
"step": 1148
},
{
"epoch": 1.64,
"learning_rate": 2.5906205311881106e-06,
"loss": 0.2843,
"step": 1149
},
{
"epoch": 1.65,
"learning_rate": 2.5861257605292236e-06,
"loss": 0.2145,
"step": 1150
},
{
"epoch": 1.65,
"learning_rate": 2.5816319367506023e-06,
"loss": 0.2242,
"step": 1151
},
{
"epoch": 1.65,
"learning_rate": 2.57713907013342e-06,
"loss": 0.1932,
"step": 1152
},
{
"epoch": 1.65,
"learning_rate": 2.5726471709566614e-06,
"loss": 0.2549,
"step": 1153
},
{
"epoch": 1.65,
"learning_rate": 2.5681562494970976e-06,
"loss": 0.1978,
"step": 1154
},
{
"epoch": 1.65,
"learning_rate": 2.5636663160292607e-06,
"loss": 0.1745,
"step": 1155
},
{
"epoch": 1.65,
"learning_rate": 2.5591773808254274e-06,
"loss": 0.2232,
"step": 1156
},
{
"epoch": 1.66,
"learning_rate": 2.554689454155584e-06,
"loss": 0.2172,
"step": 1157
},
{
"epoch": 1.66,
"learning_rate": 2.5502025462874147e-06,
"loss": 0.2147,
"step": 1158
},
{
"epoch": 1.66,
"learning_rate": 2.545716667486271e-06,
"loss": 0.2359,
"step": 1159
},
{
"epoch": 1.66,
"learning_rate": 2.5412318280151477e-06,
"loss": 0.2578,
"step": 1160
},
{
"epoch": 1.66,
"learning_rate": 2.536748038134668e-06,
"loss": 0.1461,
"step": 1161
},
{
"epoch": 1.66,
"learning_rate": 2.5322653081030456e-06,
"loss": 0.2108,
"step": 1162
},
{
"epoch": 1.66,
"learning_rate": 2.527783648176077e-06,
"loss": 0.2124,
"step": 1163
},
{
"epoch": 1.67,
"learning_rate": 2.523303068607106e-06,
"loss": 0.2224,
"step": 1164
},
{
"epoch": 1.67,
"learning_rate": 2.518823579647005e-06,
"loss": 0.2416,
"step": 1165
},
{
"epoch": 1.67,
"learning_rate": 2.514345191544154e-06,
"loss": 0.2352,
"step": 1166
},
{
"epoch": 1.67,
"learning_rate": 2.509867914544409e-06,
"loss": 0.2331,
"step": 1167
},
{
"epoch": 1.67,
"learning_rate": 2.5053917588910924e-06,
"loss": 0.2082,
"step": 1168
},
{
"epoch": 1.67,
"learning_rate": 2.5009167348249525e-06,
"loss": 0.2529,
"step": 1169
},
{
"epoch": 1.67,
"learning_rate": 2.4964428525841533e-06,
"loss": 0.1941,
"step": 1170
},
{
"epoch": 1.68,
"learning_rate": 2.4919701224042463e-06,
"loss": 0.2083,
"step": 1171
},
{
"epoch": 1.68,
"learning_rate": 2.4874985545181457e-06,
"loss": 0.2096,
"step": 1172
},
{
"epoch": 1.68,
"learning_rate": 2.483028159156109e-06,
"loss": 0.2181,
"step": 1173
},
{
"epoch": 1.68,
"learning_rate": 2.478558946545708e-06,
"loss": 0.2218,
"step": 1174
},
{
"epoch": 1.68,
"learning_rate": 2.4740909269118094e-06,
"loss": 0.2033,
"step": 1175
},
{
"epoch": 1.68,
"learning_rate": 2.4696241104765535e-06,
"loss": 0.2414,
"step": 1176
},
{
"epoch": 1.68,
"learning_rate": 2.4651585074593236e-06,
"loss": 0.2313,
"step": 1177
},
{
"epoch": 1.69,
"learning_rate": 2.4606941280767313e-06,
"loss": 0.2438,
"step": 1178
},
{
"epoch": 1.69,
"learning_rate": 2.456230982542583e-06,
"loss": 0.2365,
"step": 1179
},
{
"epoch": 1.69,
"learning_rate": 2.4517690810678693e-06,
"loss": 0.2378,
"step": 1180
},
{
"epoch": 1.69,
"learning_rate": 2.4473084338607285e-06,
"loss": 0.1993,
"step": 1181
},
{
"epoch": 1.69,
"learning_rate": 2.4428490511264314e-06,
"loss": 0.2186,
"step": 1182
},
{
"epoch": 1.69,
"learning_rate": 2.4383909430673574e-06,
"loss": 0.192,
"step": 1183
},
{
"epoch": 1.69,
"learning_rate": 2.4339341198829678e-06,
"loss": 0.2661,
"step": 1184
},
{
"epoch": 1.7,
"learning_rate": 2.4294785917697862e-06,
"loss": 0.1909,
"step": 1185
},
{
"epoch": 1.7,
"learning_rate": 2.42502436892137e-06,
"loss": 0.1855,
"step": 1186
},
{
"epoch": 1.7,
"learning_rate": 2.420571461528293e-06,
"loss": 0.216,
"step": 1187
},
{
"epoch": 1.7,
"learning_rate": 2.4161198797781195e-06,
"loss": 0.1769,
"step": 1188
},
{
"epoch": 1.7,
"learning_rate": 2.4116696338553796e-06,
"loss": 0.1915,
"step": 1189
},
{
"epoch": 1.7,
"learning_rate": 2.407220733941548e-06,
"loss": 0.2411,
"step": 1190
},
{
"epoch": 1.7,
"learning_rate": 2.402773190215021e-06,
"loss": 0.1619,
"step": 1191
},
{
"epoch": 1.71,
"learning_rate": 2.398327012851088e-06,
"loss": 0.2122,
"step": 1192
},
{
"epoch": 1.71,
"learning_rate": 2.393882212021918e-06,
"loss": 0.1699,
"step": 1193
},
{
"epoch": 1.71,
"learning_rate": 2.3894387978965263e-06,
"loss": 0.2099,
"step": 1194
},
{
"epoch": 1.71,
"learning_rate": 2.3849967806407595e-06,
"loss": 0.2592,
"step": 1195
},
{
"epoch": 1.71,
"learning_rate": 2.380556170417265e-06,
"loss": 0.2033,
"step": 1196
},
{
"epoch": 1.71,
"learning_rate": 2.376116977385471e-06,
"loss": 0.2634,
"step": 1197
},
{
"epoch": 1.71,
"learning_rate": 2.3716792117015675e-06,
"loss": 0.2224,
"step": 1198
},
{
"epoch": 1.72,
"learning_rate": 2.3672428835184733e-06,
"loss": 0.257,
"step": 1199
},
{
"epoch": 1.72,
"learning_rate": 2.362808002985824e-06,
"loss": 0.1757,
"step": 1200
},
{
"epoch": 1.72,
"learning_rate": 2.3583745802499398e-06,
"loss": 0.2301,
"step": 1201
},
{
"epoch": 1.72,
"learning_rate": 2.353942625453804e-06,
"loss": 0.2062,
"step": 1202
},
{
"epoch": 1.72,
"learning_rate": 2.349512148737048e-06,
"loss": 0.2263,
"step": 1203
},
{
"epoch": 1.72,
"learning_rate": 2.3450831602359136e-06,
"loss": 0.2333,
"step": 1204
},
{
"epoch": 1.72,
"learning_rate": 2.340655670083244e-06,
"loss": 0.2486,
"step": 1205
},
{
"epoch": 1.73,
"learning_rate": 2.336229688408451e-06,
"loss": 0.2617,
"step": 1206
},
{
"epoch": 1.73,
"learning_rate": 2.331805225337498e-06,
"loss": 0.2364,
"step": 1207
},
{
"epoch": 1.73,
"learning_rate": 2.3273822909928707e-06,
"loss": 0.1855,
"step": 1208
},
{
"epoch": 1.73,
"learning_rate": 2.3229608954935582e-06,
"loss": 0.2531,
"step": 1209
},
{
"epoch": 1.73,
"learning_rate": 2.3185410489550328e-06,
"loss": 0.2065,
"step": 1210
},
{
"epoch": 1.73,
"learning_rate": 2.314122761489217e-06,
"loss": 0.2222,
"step": 1211
},
{
"epoch": 1.73,
"learning_rate": 2.309706043204471e-06,
"loss": 0.2333,
"step": 1212
},
{
"epoch": 1.74,
"learning_rate": 2.3052909042055633e-06,
"loss": 0.2344,
"step": 1213
},
{
"epoch": 1.74,
"learning_rate": 2.300877354593647e-06,
"loss": 0.2684,
"step": 1214
},
{
"epoch": 1.74,
"learning_rate": 2.2964654044662453e-06,
"loss": 0.242,
"step": 1215
},
{
"epoch": 1.74,
"learning_rate": 2.2920550639172136e-06,
"loss": 0.2062,
"step": 1216
},
{
"epoch": 1.74,
"learning_rate": 2.2876463430367324e-06,
"loss": 0.2457,
"step": 1217
},
{
"epoch": 1.74,
"learning_rate": 2.2832392519112717e-06,
"loss": 0.1959,
"step": 1218
},
{
"epoch": 1.74,
"learning_rate": 2.278833800623574e-06,
"loss": 0.2745,
"step": 1219
},
{
"epoch": 1.75,
"learning_rate": 2.2744299992526334e-06,
"loss": 0.2255,
"step": 1220
},
{
"epoch": 1.75,
"learning_rate": 2.270027857873663e-06,
"loss": 0.213,
"step": 1221
},
{
"epoch": 1.75,
"learning_rate": 2.2656273865580846e-06,
"loss": 0.2055,
"step": 1222
},
{
"epoch": 1.75,
"learning_rate": 2.2612285953734946e-06,
"loss": 0.2185,
"step": 1223
},
{
"epoch": 1.75,
"learning_rate": 2.2568314943836465e-06,
"loss": 0.1978,
"step": 1224
},
{
"epoch": 1.75,
"learning_rate": 2.2524360936484293e-06,
"loss": 0.2239,
"step": 1225
},
{
"epoch": 1.75,
"learning_rate": 2.2480424032238383e-06,
"loss": 0.228,
"step": 1226
},
{
"epoch": 1.76,
"learning_rate": 2.24365043316196e-06,
"loss": 0.2249,
"step": 1227
},
{
"epoch": 1.76,
"learning_rate": 2.239260193510941e-06,
"loss": 0.2355,
"step": 1228
},
{
"epoch": 1.76,
"learning_rate": 2.234871694314971e-06,
"loss": 0.232,
"step": 1229
},
{
"epoch": 1.76,
"learning_rate": 2.230484945614258e-06,
"loss": 0.2163,
"step": 1230
},
{
"epoch": 1.76,
"learning_rate": 2.226099957445005e-06,
"loss": 0.2926,
"step": 1231
},
{
"epoch": 1.76,
"learning_rate": 2.2217167398393873e-06,
"loss": 0.2085,
"step": 1232
},
{
"epoch": 1.76,
"learning_rate": 2.217335302825528e-06,
"loss": 0.1876,
"step": 1233
},
{
"epoch": 1.77,
"learning_rate": 2.212955656427477e-06,
"loss": 0.2088,
"step": 1234
},
{
"epoch": 1.77,
"learning_rate": 2.20857781066519e-06,
"loss": 0.153,
"step": 1235
},
{
"epoch": 1.77,
"learning_rate": 2.2042017755544993e-06,
"loss": 0.2002,
"step": 1236
},
{
"epoch": 1.77,
"learning_rate": 2.199827561107098e-06,
"loss": 0.2036,
"step": 1237
},
{
"epoch": 1.77,
"learning_rate": 2.195455177330511e-06,
"loss": 0.225,
"step": 1238
},
{
"epoch": 1.77,
"learning_rate": 2.1910846342280785e-06,
"loss": 0.2183,
"step": 1239
},
{
"epoch": 1.77,
"learning_rate": 2.186715941798925e-06,
"loss": 0.2094,
"step": 1240
},
{
"epoch": 1.78,
"learning_rate": 2.1823491100379444e-06,
"loss": 0.1864,
"step": 1241
},
{
"epoch": 1.78,
"learning_rate": 2.1779841489357726e-06,
"loss": 0.2376,
"step": 1242
},
{
"epoch": 1.78,
"learning_rate": 2.1736210684787655e-06,
"loss": 0.2368,
"step": 1243
},
{
"epoch": 1.78,
"learning_rate": 2.169259878648976e-06,
"loss": 0.2162,
"step": 1244
},
{
"epoch": 1.78,
"learning_rate": 2.164900589424134e-06,
"loss": 0.2169,
"step": 1245
},
{
"epoch": 1.78,
"learning_rate": 2.1605432107776166e-06,
"loss": 0.1917,
"step": 1246
},
{
"epoch": 1.78,
"learning_rate": 2.1561877526784343e-06,
"loss": 0.229,
"step": 1247
},
{
"epoch": 1.79,
"learning_rate": 2.1518342250912e-06,
"loss": 0.2383,
"step": 1248
},
{
"epoch": 1.79,
"learning_rate": 2.147482637976114e-06,
"loss": 0.181,
"step": 1249
},
{
"epoch": 1.79,
"learning_rate": 2.1431330012889336e-06,
"loss": 0.2697,
"step": 1250
},
{
"epoch": 1.79,
"learning_rate": 2.1387853249809542e-06,
"loss": 0.2171,
"step": 1251
},
{
"epoch": 1.79,
"learning_rate": 2.1344396189989875e-06,
"loss": 0.2213,
"step": 1252
},
{
"epoch": 1.79,
"learning_rate": 2.130095893285337e-06,
"loss": 0.1648,
"step": 1253
},
{
"epoch": 1.79,
"learning_rate": 2.1257541577777762e-06,
"loss": 0.2235,
"step": 1254
},
{
"epoch": 1.8,
"learning_rate": 2.121414422409524e-06,
"loss": 0.2105,
"step": 1255
},
{
"epoch": 1.8,
"learning_rate": 2.1170766971092224e-06,
"loss": 0.1627,
"step": 1256
},
{
"epoch": 1.8,
"learning_rate": 2.1127409918009195e-06,
"loss": 0.1856,
"step": 1257
},
{
"epoch": 1.8,
"learning_rate": 2.108407316404035e-06,
"loss": 0.2382,
"step": 1258
},
{
"epoch": 1.8,
"learning_rate": 2.104075680833351e-06,
"loss": 0.1975,
"step": 1259
},
{
"epoch": 1.8,
"learning_rate": 2.0997460949989785e-06,
"loss": 0.2486,
"step": 1260
},
{
"epoch": 1.8,
"learning_rate": 2.0954185688063397e-06,
"loss": 0.1759,
"step": 1261
},
{
"epoch": 1.81,
"learning_rate": 2.091093112156148e-06,
"loss": 0.1917,
"step": 1262
},
{
"epoch": 1.81,
"learning_rate": 2.086769734944376e-06,
"loss": 0.219,
"step": 1263
},
{
"epoch": 1.81,
"learning_rate": 2.0824484470622457e-06,
"loss": 0.2065,
"step": 1264
},
{
"epoch": 1.81,
"learning_rate": 2.078129258396193e-06,
"loss": 0.2099,
"step": 1265
},
{
"epoch": 1.81,
"learning_rate": 2.073812178827855e-06,
"loss": 0.214,
"step": 1266
},
{
"epoch": 1.81,
"learning_rate": 2.069497218234043e-06,
"loss": 0.1798,
"step": 1267
},
{
"epoch": 1.81,
"learning_rate": 2.065184386486716e-06,
"loss": 0.1925,
"step": 1268
},
{
"epoch": 1.82,
"learning_rate": 2.0608736934529714e-06,
"loss": 0.2139,
"step": 1269
},
{
"epoch": 1.82,
"learning_rate": 2.056565148995004e-06,
"loss": 0.2107,
"step": 1270
},
{
"epoch": 1.82,
"learning_rate": 2.0522587629700996e-06,
"loss": 0.1979,
"step": 1271
},
{
"epoch": 1.82,
"learning_rate": 2.047954545230603e-06,
"loss": 0.1473,
"step": 1272
},
{
"epoch": 1.82,
"learning_rate": 2.043652505623898e-06,
"loss": 0.1807,
"step": 1273
},
{
"epoch": 1.82,
"learning_rate": 2.039352653992388e-06,
"loss": 0.1937,
"step": 1274
},
{
"epoch": 1.82,
"learning_rate": 2.035055000173466e-06,
"loss": 0.1908,
"step": 1275
},
{
"epoch": 1.83,
"learning_rate": 2.030759553999503e-06,
"loss": 0.1971,
"step": 1276
},
{
"epoch": 1.83,
"learning_rate": 2.0264663252978123e-06,
"loss": 0.2423,
"step": 1277
},
{
"epoch": 1.83,
"learning_rate": 2.022175323890638e-06,
"loss": 0.1863,
"step": 1278
},
{
"epoch": 1.83,
"learning_rate": 2.0178865595951294e-06,
"loss": 0.2002,
"step": 1279
},
{
"epoch": 1.83,
"learning_rate": 2.0136000422233148e-06,
"loss": 0.1955,
"step": 1280
},
{
"epoch": 1.83,
"learning_rate": 2.0093157815820844e-06,
"loss": 0.1989,
"step": 1281
},
{
"epoch": 1.83,
"learning_rate": 2.0050337874731625e-06,
"loss": 0.2396,
"step": 1282
},
{
"epoch": 1.84,
"learning_rate": 2.00075406969309e-06,
"loss": 0.2078,
"step": 1283
},
{
"epoch": 1.84,
"learning_rate": 1.9964766380331995e-06,
"loss": 0.253,
"step": 1284
},
{
"epoch": 1.84,
"learning_rate": 1.9922015022795936e-06,
"loss": 0.2186,
"step": 1285
},
{
"epoch": 1.84,
"learning_rate": 1.9879286722131227e-06,
"loss": 0.2059,
"step": 1286
},
{
"epoch": 1.84,
"learning_rate": 1.983658157609359e-06,
"loss": 0.2172,
"step": 1287
},
{
"epoch": 1.84,
"learning_rate": 1.979389968238581e-06,
"loss": 0.2398,
"step": 1288
},
{
"epoch": 1.84,
"learning_rate": 1.9751241138657465e-06,
"loss": 0.2406,
"step": 1289
},
{
"epoch": 1.85,
"learning_rate": 1.970860604250469e-06,
"loss": 0.1867,
"step": 1290
},
{
"epoch": 1.85,
"learning_rate": 1.9665994491470013e-06,
"loss": 0.1967,
"step": 1291
},
{
"epoch": 1.85,
"learning_rate": 1.9623406583042074e-06,
"loss": 0.1738,
"step": 1292
},
{
"epoch": 1.85,
"learning_rate": 1.9580842414655397e-06,
"loss": 0.2122,
"step": 1293
},
{
"epoch": 1.85,
"learning_rate": 1.953830208369024e-06,
"loss": 0.2211,
"step": 1294
},
{
"epoch": 1.85,
"learning_rate": 1.949578568747229e-06,
"loss": 0.2056,
"step": 1295
},
{
"epoch": 1.85,
"learning_rate": 1.9453293323272503e-06,
"loss": 0.2276,
"step": 1296
},
{
"epoch": 1.86,
"learning_rate": 1.941082508830682e-06,
"loss": 0.1651,
"step": 1297
},
{
"epoch": 1.86,
"learning_rate": 1.9368381079736014e-06,
"loss": 0.2279,
"step": 1298
},
{
"epoch": 1.86,
"learning_rate": 1.9325961394665407e-06,
"loss": 0.233,
"step": 1299
},
{
"epoch": 1.86,
"learning_rate": 1.9283566130144666e-06,
"loss": 0.1987,
"step": 1300
},
{
"epoch": 1.86,
"learning_rate": 1.9241195383167622e-06,
"loss": 0.179,
"step": 1301
},
{
"epoch": 1.86,
"learning_rate": 1.9198849250671975e-06,
"loss": 0.2066,
"step": 1302
},
{
"epoch": 1.86,
"learning_rate": 1.915652782953914e-06,
"loss": 0.2188,
"step": 1303
},
{
"epoch": 1.87,
"learning_rate": 1.911423121659399e-06,
"loss": 0.1704,
"step": 1304
},
{
"epoch": 1.87,
"learning_rate": 1.9071959508604612e-06,
"loss": 0.223,
"step": 1305
},
{
"epoch": 1.87,
"learning_rate": 1.902971280228216e-06,
"loss": 0.1755,
"step": 1306
},
{
"epoch": 1.87,
"learning_rate": 1.898749119428055e-06,
"loss": 0.2192,
"step": 1307
},
{
"epoch": 1.87,
"learning_rate": 1.8945294781196305e-06,
"loss": 0.1795,
"step": 1308
},
{
"epoch": 1.87,
"learning_rate": 1.8903123659568302e-06,
"loss": 0.1923,
"step": 1309
},
{
"epoch": 1.87,
"learning_rate": 1.886097792587751e-06,
"loss": 0.2242,
"step": 1310
},
{
"epoch": 1.88,
"learning_rate": 1.8818857676546894e-06,
"loss": 0.2341,
"step": 1311
},
{
"epoch": 1.88,
"learning_rate": 1.877676300794104e-06,
"loss": 0.1823,
"step": 1312
},
{
"epoch": 1.88,
"learning_rate": 1.8734694016366058e-06,
"loss": 0.2241,
"step": 1313
},
{
"epoch": 1.88,
"learning_rate": 1.8692650798069294e-06,
"loss": 0.2126,
"step": 1314
},
{
"epoch": 1.88,
"learning_rate": 1.8650633449239122e-06,
"loss": 0.235,
"step": 1315
},
{
"epoch": 1.88,
"learning_rate": 1.8608642066004752e-06,
"loss": 0.1755,
"step": 1316
},
{
"epoch": 1.88,
"learning_rate": 1.8566676744435958e-06,
"loss": 0.1883,
"step": 1317
},
{
"epoch": 1.89,
"learning_rate": 1.8524737580542935e-06,
"loss": 0.1924,
"step": 1318
},
{
"epoch": 1.89,
"learning_rate": 1.848282467027598e-06,
"loss": 0.2212,
"step": 1319
},
{
"epoch": 1.89,
"learning_rate": 1.8440938109525356e-06,
"loss": 0.2141,
"step": 1320
},
{
"epoch": 1.89,
"learning_rate": 1.8399077994121048e-06,
"loss": 0.1613,
"step": 1321
},
{
"epoch": 1.89,
"learning_rate": 1.8357244419832503e-06,
"loss": 0.1509,
"step": 1322
},
{
"epoch": 1.89,
"learning_rate": 1.8315437482368514e-06,
"loss": 0.2452,
"step": 1323
},
{
"epoch": 1.89,
"learning_rate": 1.8273657277376841e-06,
"loss": 0.2176,
"step": 1324
},
{
"epoch": 1.9,
"learning_rate": 1.8231903900444165e-06,
"loss": 0.2547,
"step": 1325
},
{
"epoch": 1.9,
"learning_rate": 1.819017744709575e-06,
"loss": 0.2012,
"step": 1326
},
{
"epoch": 1.9,
"learning_rate": 1.8148478012795256e-06,
"loss": 0.1978,
"step": 1327
},
{
"epoch": 1.9,
"learning_rate": 1.8106805692944566e-06,
"loss": 0.2444,
"step": 1328
},
{
"epoch": 1.9,
"learning_rate": 1.8065160582883467e-06,
"loss": 0.2176,
"step": 1329
},
{
"epoch": 1.9,
"learning_rate": 1.8023542777889576e-06,
"loss": 0.1705,
"step": 1330
},
{
"epoch": 1.9,
"learning_rate": 1.7981952373177966e-06,
"loss": 0.271,
"step": 1331
},
{
"epoch": 1.91,
"learning_rate": 1.7940389463901052e-06,
"loss": 0.2235,
"step": 1332
},
{
"epoch": 1.91,
"learning_rate": 1.7898854145148358e-06,
"loss": 0.2287,
"step": 1333
},
{
"epoch": 1.91,
"learning_rate": 1.7857346511946263e-06,
"loss": 0.1643,
"step": 1334
},
{
"epoch": 1.91,
"learning_rate": 1.7815866659257823e-06,
"loss": 0.2069,
"step": 1335
},
{
"epoch": 1.91,
"learning_rate": 1.7774414681982514e-06,
"loss": 0.1526,
"step": 1336
},
{
"epoch": 1.91,
"learning_rate": 1.7732990674956048e-06,
"loss": 0.2421,
"step": 1337
},
{
"epoch": 1.91,
"learning_rate": 1.769159473295017e-06,
"loss": 0.235,
"step": 1338
},
{
"epoch": 1.92,
"learning_rate": 1.7650226950672367e-06,
"loss": 0.2109,
"step": 1339
},
{
"epoch": 1.92,
"learning_rate": 1.7608887422765757e-06,
"loss": 0.2119,
"step": 1340
},
{
"epoch": 1.92,
"learning_rate": 1.7567576243808767e-06,
"loss": 0.205,
"step": 1341
},
{
"epoch": 1.92,
"learning_rate": 1.7526293508314987e-06,
"loss": 0.2507,
"step": 1342
},
{
"epoch": 1.92,
"learning_rate": 1.7485039310732949e-06,
"loss": 0.2712,
"step": 1343
},
{
"epoch": 1.92,
"learning_rate": 1.7443813745445848e-06,
"loss": 0.225,
"step": 1344
},
{
"epoch": 1.92,
"learning_rate": 1.7402616906771436e-06,
"loss": 0.2198,
"step": 1345
},
{
"epoch": 1.93,
"learning_rate": 1.7361448888961695e-06,
"loss": 0.2155,
"step": 1346
},
{
"epoch": 1.93,
"learning_rate": 1.732030978620269e-06,
"loss": 0.1677,
"step": 1347
},
{
"epoch": 1.93,
"learning_rate": 1.727919969261432e-06,
"loss": 0.1873,
"step": 1348
},
{
"epoch": 1.93,
"learning_rate": 1.723811870225011e-06,
"loss": 0.1741,
"step": 1349
},
{
"epoch": 1.93,
"learning_rate": 1.7197066909097055e-06,
"loss": 0.2545,
"step": 1350
},
{
"epoch": 1.93,
"learning_rate": 1.7156044407075274e-06,
"loss": 0.2057,
"step": 1351
},
{
"epoch": 1.93,
"learning_rate": 1.7115051290037904e-06,
"loss": 0.1932,
"step": 1352
},
{
"epoch": 1.94,
"learning_rate": 1.707408765177089e-06,
"loss": 0.2039,
"step": 1353
},
{
"epoch": 1.94,
"learning_rate": 1.703315358599268e-06,
"loss": 0.1845,
"step": 1354
},
{
"epoch": 1.94,
"learning_rate": 1.6992249186354098e-06,
"loss": 0.2459,
"step": 1355
},
{
"epoch": 1.94,
"learning_rate": 1.6951374546438062e-06,
"loss": 0.1567,
"step": 1356
},
{
"epoch": 1.94,
"learning_rate": 1.6910529759759477e-06,
"loss": 0.2292,
"step": 1357
},
{
"epoch": 1.94,
"learning_rate": 1.6869714919764853e-06,
"loss": 0.2089,
"step": 1358
},
{
"epoch": 1.94,
"learning_rate": 1.6828930119832237e-06,
"loss": 0.1876,
"step": 1359
},
{
"epoch": 1.95,
"learning_rate": 1.678817545327097e-06,
"loss": 0.1968,
"step": 1360
},
{
"epoch": 1.95,
"learning_rate": 1.6747451013321412e-06,
"loss": 0.1775,
"step": 1361
},
{
"epoch": 1.95,
"learning_rate": 1.6706756893154789e-06,
"loss": 0.2113,
"step": 1362
},
{
"epoch": 1.95,
"learning_rate": 1.6666093185872951e-06,
"loss": 0.2223,
"step": 1363
},
{
"epoch": 1.95,
"learning_rate": 1.6625459984508178e-06,
"loss": 0.2556,
"step": 1364
},
{
"epoch": 1.95,
"learning_rate": 1.6584857382022944e-06,
"loss": 0.2091,
"step": 1365
},
{
"epoch": 1.95,
"learning_rate": 1.6544285471309726e-06,
"loss": 0.2327,
"step": 1366
},
{
"epoch": 1.96,
"learning_rate": 1.6503744345190805e-06,
"loss": 0.1828,
"step": 1367
},
{
"epoch": 1.96,
"learning_rate": 1.6463234096417983e-06,
"loss": 0.2479,
"step": 1368
},
{
"epoch": 1.96,
"learning_rate": 1.6422754817672435e-06,
"loss": 0.2256,
"step": 1369
},
{
"epoch": 1.96,
"learning_rate": 1.6382306601564528e-06,
"loss": 0.203,
"step": 1370
},
{
"epoch": 1.96,
"learning_rate": 1.6341889540633506e-06,
"loss": 0.1699,
"step": 1371
},
{
"epoch": 1.96,
"learning_rate": 1.6301503727347357e-06,
"loss": 0.2016,
"step": 1372
},
{
"epoch": 1.96,
"learning_rate": 1.6261149254102579e-06,
"loss": 0.1784,
"step": 1373
},
{
"epoch": 1.97,
"learning_rate": 1.6220826213223963e-06,
"loss": 0.2398,
"step": 1374
},
{
"epoch": 1.97,
"learning_rate": 1.6180534696964395e-06,
"loss": 0.1764,
"step": 1375
},
{
"epoch": 1.97,
"learning_rate": 1.6140274797504623e-06,
"loss": 0.1843,
"step": 1376
},
{
"epoch": 1.97,
"learning_rate": 1.6100046606953092e-06,
"loss": 0.2311,
"step": 1377
},
{
"epoch": 1.97,
"learning_rate": 1.6059850217345685e-06,
"loss": 0.2122,
"step": 1378
},
{
"epoch": 1.97,
"learning_rate": 1.601968572064549e-06,
"loss": 0.2097,
"step": 1379
},
{
"epoch": 1.97,
"learning_rate": 1.59795532087427e-06,
"loss": 0.2095,
"step": 1380
},
{
"epoch": 1.98,
"learning_rate": 1.5939452773454286e-06,
"loss": 0.1631,
"step": 1381
},
{
"epoch": 1.98,
"learning_rate": 1.5899384506523839e-06,
"loss": 0.2513,
"step": 1382
},
{
"epoch": 1.98,
"learning_rate": 1.5859348499621354e-06,
"loss": 0.2051,
"step": 1383
},
{
"epoch": 1.98,
"learning_rate": 1.5819344844343039e-06,
"loss": 0.1437,
"step": 1384
},
{
"epoch": 1.98,
"learning_rate": 1.5779373632211079e-06,
"loss": 0.2136,
"step": 1385
},
{
"epoch": 1.98,
"learning_rate": 1.573943495467339e-06,
"loss": 0.2064,
"step": 1386
},
{
"epoch": 1.98,
"learning_rate": 1.5699528903103524e-06,
"loss": 0.2377,
"step": 1387
},
{
"epoch": 1.99,
"learning_rate": 1.5659655568800345e-06,
"loss": 0.2522,
"step": 1388
},
{
"epoch": 1.99,
"learning_rate": 1.5619815042987882e-06,
"loss": 0.164,
"step": 1389
},
{
"epoch": 1.99,
"learning_rate": 1.5580007416815091e-06,
"loss": 0.178,
"step": 1390
},
{
"epoch": 1.99,
"learning_rate": 1.554023278135566e-06,
"loss": 0.2116,
"step": 1391
},
{
"epoch": 1.99,
"learning_rate": 1.5500491227607828e-06,
"loss": 0.1915,
"step": 1392
},
{
"epoch": 1.99,
"learning_rate": 1.5460782846494093e-06,
"loss": 0.1657,
"step": 1393
},
{
"epoch": 1.99,
"learning_rate": 1.542110772886112e-06,
"loss": 0.1981,
"step": 1394
},
{
"epoch": 2.0,
"learning_rate": 1.5381465965479426e-06,
"loss": 0.2054,
"step": 1395
},
{
"epoch": 2.0,
"learning_rate": 1.5341857647043247e-06,
"loss": 0.2093,
"step": 1396
},
{
"epoch": 2.0,
"learning_rate": 1.5302282864170283e-06,
"loss": 0.1952,
"step": 1397
},
{
"epoch": 2.0,
"learning_rate": 1.5262741707401522e-06,
"loss": 0.1666,
"step": 1398
},
{
"epoch": 2.0,
"learning_rate": 1.5223234267201013e-06,
"loss": 0.0884,
"step": 1399
},
{
"epoch": 2.0,
"learning_rate": 1.5183760633955678e-06,
"loss": 0.0863,
"step": 1400
},
{
"epoch": 2.0,
"learning_rate": 1.5144320897975066e-06,
"loss": 0.0763,
"step": 1401
},
{
"epoch": 2.01,
"learning_rate": 1.5104915149491236e-06,
"loss": 0.0916,
"step": 1402
},
{
"epoch": 2.01,
"learning_rate": 1.5065543478658396e-06,
"loss": 0.0788,
"step": 1403
},
{
"epoch": 2.01,
"learning_rate": 1.5026205975552878e-06,
"loss": 0.1275,
"step": 1404
},
{
"epoch": 2.01,
"learning_rate": 1.4986902730172796e-06,
"loss": 0.0988,
"step": 1405
},
{
"epoch": 2.01,
"learning_rate": 1.4947633832437898e-06,
"loss": 0.0741,
"step": 1406
},
{
"epoch": 2.01,
"learning_rate": 1.4908399372189346e-06,
"loss": 0.0722,
"step": 1407
},
{
"epoch": 2.01,
"learning_rate": 1.4869199439189515e-06,
"loss": 0.0665,
"step": 1408
},
{
"epoch": 2.02,
"learning_rate": 1.4830034123121817e-06,
"loss": 0.0846,
"step": 1409
},
{
"epoch": 2.02,
"learning_rate": 1.4790903513590401e-06,
"loss": 0.0731,
"step": 1410
},
{
"epoch": 2.02,
"learning_rate": 1.4751807700120077e-06,
"loss": 0.0819,
"step": 1411
},
{
"epoch": 2.02,
"learning_rate": 1.4712746772156018e-06,
"loss": 0.0766,
"step": 1412
},
{
"epoch": 2.02,
"learning_rate": 1.467372081906358e-06,
"loss": 0.0879,
"step": 1413
},
{
"epoch": 2.02,
"learning_rate": 1.4634729930128114e-06,
"loss": 0.066,
"step": 1414
},
{
"epoch": 2.02,
"learning_rate": 1.4595774194554737e-06,
"loss": 0.0754,
"step": 1415
},
{
"epoch": 2.03,
"learning_rate": 1.4556853701468172e-06,
"loss": 0.0742,
"step": 1416
},
{
"epoch": 2.03,
"learning_rate": 1.4517968539912466e-06,
"loss": 0.0671,
"step": 1417
},
{
"epoch": 2.03,
"learning_rate": 1.4479118798850848e-06,
"loss": 0.0937,
"step": 1418
},
{
"epoch": 2.03,
"learning_rate": 1.4440304567165543e-06,
"loss": 0.074,
"step": 1419
},
{
"epoch": 2.03,
"learning_rate": 1.4401525933657504e-06,
"loss": 0.0727,
"step": 1420
},
{
"epoch": 2.03,
"learning_rate": 1.4362782987046246e-06,
"loss": 0.0913,
"step": 1421
},
{
"epoch": 2.03,
"learning_rate": 1.4324075815969644e-06,
"loss": 0.088,
"step": 1422
},
{
"epoch": 2.04,
"learning_rate": 1.4285404508983711e-06,
"loss": 0.0625,
"step": 1423
},
{
"epoch": 2.04,
"learning_rate": 1.4246769154562428e-06,
"loss": 0.0625,
"step": 1424
},
{
"epoch": 2.04,
"learning_rate": 1.4208169841097494e-06,
"loss": 0.0832,
"step": 1425
},
{
"epoch": 2.04,
"learning_rate": 1.41696066568982e-06,
"loss": 0.0725,
"step": 1426
},
{
"epoch": 2.04,
"learning_rate": 1.4131079690191136e-06,
"loss": 0.0902,
"step": 1427
},
{
"epoch": 2.04,
"learning_rate": 1.4092589029120023e-06,
"loss": 0.0738,
"step": 1428
},
{
"epoch": 2.04,
"learning_rate": 1.405413476174557e-06,
"loss": 0.0752,
"step": 1429
},
{
"epoch": 2.05,
"learning_rate": 1.4015716976045183e-06,
"loss": 0.0886,
"step": 1430
},
{
"epoch": 2.05,
"learning_rate": 1.397733575991282e-06,
"loss": 0.0737,
"step": 1431
},
{
"epoch": 2.05,
"learning_rate": 1.3938991201158765e-06,
"loss": 0.0777,
"step": 1432
},
{
"epoch": 2.05,
"learning_rate": 1.390068338750943e-06,
"loss": 0.0602,
"step": 1433
},
{
"epoch": 2.05,
"learning_rate": 1.3862412406607203e-06,
"loss": 0.0875,
"step": 1434
},
{
"epoch": 2.05,
"learning_rate": 1.3824178346010124e-06,
"loss": 0.0612,
"step": 1435
},
{
"epoch": 2.05,
"learning_rate": 1.3785981293191846e-06,
"loss": 0.0691,
"step": 1436
},
{
"epoch": 2.06,
"learning_rate": 1.3747821335541322e-06,
"loss": 0.0705,
"step": 1437
},
{
"epoch": 2.06,
"learning_rate": 1.3709698560362598e-06,
"loss": 0.0632,
"step": 1438
},
{
"epoch": 2.06,
"learning_rate": 1.3671613054874725e-06,
"loss": 0.091,
"step": 1439
},
{
"epoch": 2.06,
"learning_rate": 1.363356490621144e-06,
"loss": 0.0928,
"step": 1440
},
{
"epoch": 2.06,
"learning_rate": 1.359555420142102e-06,
"loss": 0.0763,
"step": 1441
},
{
"epoch": 2.06,
"learning_rate": 1.3557581027466073e-06,
"loss": 0.0692,
"step": 1442
},
{
"epoch": 2.06,
"learning_rate": 1.3519645471223367e-06,
"loss": 0.0764,
"step": 1443
},
{
"epoch": 2.07,
"learning_rate": 1.3481747619483596e-06,
"loss": 0.0887,
"step": 1444
},
{
"epoch": 2.07,
"learning_rate": 1.3443887558951147e-06,
"loss": 0.0697,
"step": 1445
},
{
"epoch": 2.07,
"learning_rate": 1.3406065376244018e-06,
"loss": 0.0692,
"step": 1446
},
{
"epoch": 2.07,
"learning_rate": 1.3368281157893507e-06,
"loss": 0.0662,
"step": 1447
},
{
"epoch": 2.07,
"learning_rate": 1.3330534990344056e-06,
"loss": 0.0769,
"step": 1448
},
{
"epoch": 2.07,
"learning_rate": 1.3292826959953066e-06,
"loss": 0.0958,
"step": 1449
},
{
"epoch": 2.07,
"learning_rate": 1.325515715299067e-06,
"loss": 0.0623,
"step": 1450
},
{
"epoch": 2.08,
"learning_rate": 1.3217525655639594e-06,
"loss": 0.0981,
"step": 1451
},
{
"epoch": 2.08,
"learning_rate": 1.3179932553994837e-06,
"loss": 0.0757,
"step": 1452
},
{
"epoch": 2.08,
"learning_rate": 1.3142377934063637e-06,
"loss": 0.0836,
"step": 1453
},
{
"epoch": 2.08,
"learning_rate": 1.310486188176515e-06,
"loss": 0.0947,
"step": 1454
},
{
"epoch": 2.08,
"learning_rate": 1.30673844829303e-06,
"loss": 0.0624,
"step": 1455
},
{
"epoch": 2.08,
"learning_rate": 1.302994582330158e-06,
"loss": 0.0585,
"step": 1456
},
{
"epoch": 2.08,
"learning_rate": 1.2992545988532847e-06,
"loss": 0.0734,
"step": 1457
},
{
"epoch": 2.09,
"learning_rate": 1.2955185064189168e-06,
"loss": 0.0604,
"step": 1458
},
{
"epoch": 2.09,
"learning_rate": 1.2917863135746537e-06,
"loss": 0.0772,
"step": 1459
},
{
"epoch": 2.09,
"learning_rate": 1.2880580288591743e-06,
"loss": 0.0848,
"step": 1460
},
{
"epoch": 2.09,
"learning_rate": 1.2843336608022207e-06,
"loss": 0.0577,
"step": 1461
},
{
"epoch": 2.09,
"learning_rate": 1.2806132179245698e-06,
"loss": 0.0846,
"step": 1462
},
{
"epoch": 2.09,
"learning_rate": 1.2768967087380193e-06,
"loss": 0.0913,
"step": 1463
},
{
"epoch": 2.09,
"learning_rate": 1.273184141745368e-06,
"loss": 0.0636,
"step": 1464
},
{
"epoch": 2.1,
"learning_rate": 1.2694755254403948e-06,
"loss": 0.0718,
"step": 1465
},
{
"epoch": 2.1,
"learning_rate": 1.2657708683078406e-06,
"loss": 0.0564,
"step": 1466
},
{
"epoch": 2.1,
"learning_rate": 1.2620701788233872e-06,
"loss": 0.067,
"step": 1467
},
{
"epoch": 2.1,
"learning_rate": 1.2583734654536415e-06,
"loss": 0.0639,
"step": 1468
},
{
"epoch": 2.1,
"learning_rate": 1.2546807366561113e-06,
"loss": 0.0929,
"step": 1469
},
{
"epoch": 2.1,
"learning_rate": 1.2509920008791895e-06,
"loss": 0.0783,
"step": 1470
},
{
"epoch": 2.1,
"learning_rate": 1.2473072665621326e-06,
"loss": 0.0796,
"step": 1471
},
{
"epoch": 2.11,
"learning_rate": 1.2436265421350435e-06,
"loss": 0.0828,
"step": 1472
},
{
"epoch": 2.11,
"learning_rate": 1.23994983601885e-06,
"loss": 0.0808,
"step": 1473
},
{
"epoch": 2.11,
"learning_rate": 1.2362771566252863e-06,
"loss": 0.0847,
"step": 1474
},
{
"epoch": 2.11,
"learning_rate": 1.2326085123568785e-06,
"loss": 0.073,
"step": 1475
},
{
"epoch": 2.11,
"learning_rate": 1.2289439116069143e-06,
"loss": 0.0642,
"step": 1476
},
{
"epoch": 2.11,
"learning_rate": 1.2252833627594327e-06,
"loss": 0.0941,
"step": 1477
},
{
"epoch": 2.11,
"learning_rate": 1.2216268741892064e-06,
"loss": 0.0675,
"step": 1478
},
{
"epoch": 2.12,
"learning_rate": 1.2179744542617147e-06,
"loss": 0.0773,
"step": 1479
},
{
"epoch": 2.12,
"learning_rate": 1.2143261113331295e-06,
"loss": 0.0906,
"step": 1480
},
{
"epoch": 2.12,
"learning_rate": 1.2106818537502955e-06,
"loss": 0.0722,
"step": 1481
},
{
"epoch": 2.12,
"learning_rate": 1.2070416898507099e-06,
"loss": 0.0676,
"step": 1482
},
{
"epoch": 2.12,
"learning_rate": 1.2034056279625057e-06,
"loss": 0.07,
"step": 1483
},
{
"epoch": 2.12,
"learning_rate": 1.1997736764044287e-06,
"loss": 0.0929,
"step": 1484
},
{
"epoch": 2.12,
"learning_rate": 1.196145843485825e-06,
"loss": 0.0575,
"step": 1485
},
{
"epoch": 2.13,
"learning_rate": 1.192522137506615e-06,
"loss": 0.0682,
"step": 1486
},
{
"epoch": 2.13,
"learning_rate": 1.1889025667572751e-06,
"loss": 0.0668,
"step": 1487
},
{
"epoch": 2.13,
"learning_rate": 1.1852871395188256e-06,
"loss": 0.0784,
"step": 1488
},
{
"epoch": 2.13,
"learning_rate": 1.181675864062805e-06,
"loss": 0.1147,
"step": 1489
},
{
"epoch": 2.13,
"learning_rate": 1.1780687486512524e-06,
"loss": 0.0708,
"step": 1490
},
{
"epoch": 2.13,
"learning_rate": 1.1744658015366903e-06,
"loss": 0.061,
"step": 1491
},
{
"epoch": 2.13,
"learning_rate": 1.1708670309621042e-06,
"loss": 0.0737,
"step": 1492
},
{
"epoch": 2.14,
"learning_rate": 1.1672724451609269e-06,
"loss": 0.0755,
"step": 1493
},
{
"epoch": 2.14,
"learning_rate": 1.1636820523570113e-06,
"loss": 0.0667,
"step": 1494
},
{
"epoch": 2.14,
"learning_rate": 1.160095860764624e-06,
"loss": 0.0694,
"step": 1495
},
{
"epoch": 2.14,
"learning_rate": 1.156513878588416e-06,
"loss": 0.0629,
"step": 1496
},
{
"epoch": 2.14,
"learning_rate": 1.1529361140234083e-06,
"loss": 0.0807,
"step": 1497
},
{
"epoch": 2.14,
"learning_rate": 1.149362575254973e-06,
"loss": 0.0634,
"step": 1498
},
{
"epoch": 2.14,
"learning_rate": 1.1457932704588139e-06,
"loss": 0.0618,
"step": 1499
},
{
"epoch": 2.15,
"learning_rate": 1.1422282078009505e-06,
"loss": 0.0604,
"step": 1500
},
{
"epoch": 2.15,
"learning_rate": 1.1386673954376916e-06,
"loss": 0.0574,
"step": 1501
},
{
"epoch": 2.15,
"learning_rate": 1.1351108415156281e-06,
"loss": 0.0862,
"step": 1502
},
{
"epoch": 2.15,
"learning_rate": 1.1315585541716043e-06,
"loss": 0.0688,
"step": 1503
},
{
"epoch": 2.15,
"learning_rate": 1.128010541532705e-06,
"loss": 0.0661,
"step": 1504
},
{
"epoch": 2.15,
"learning_rate": 1.1244668117162339e-06,
"loss": 0.0773,
"step": 1505
},
{
"epoch": 2.15,
"learning_rate": 1.120927372829697e-06,
"loss": 0.0715,
"step": 1506
},
{
"epoch": 2.16,
"learning_rate": 1.117392232970783e-06,
"loss": 0.0642,
"step": 1507
},
{
"epoch": 2.16,
"learning_rate": 1.113861400227346e-06,
"loss": 0.072,
"step": 1508
},
{
"epoch": 2.16,
"learning_rate": 1.1103348826773836e-06,
"loss": 0.0488,
"step": 1509
},
{
"epoch": 2.16,
"learning_rate": 1.1068126883890261e-06,
"loss": 0.0612,
"step": 1510
},
{
"epoch": 2.16,
"learning_rate": 1.1032948254205051e-06,
"loss": 0.0785,
"step": 1511
},
{
"epoch": 2.16,
"learning_rate": 1.0997813018201507e-06,
"loss": 0.0758,
"step": 1512
},
{
"epoch": 2.16,
"learning_rate": 1.0962721256263599e-06,
"loss": 0.0755,
"step": 1513
},
{
"epoch": 2.17,
"learning_rate": 1.092767304867586e-06,
"loss": 0.0655,
"step": 1514
},
{
"epoch": 2.17,
"learning_rate": 1.089266847562316e-06,
"loss": 0.0773,
"step": 1515
},
{
"epoch": 2.17,
"learning_rate": 1.0857707617190547e-06,
"loss": 0.0719,
"step": 1516
},
{
"epoch": 2.17,
"learning_rate": 1.0822790553363086e-06,
"loss": 0.0805,
"step": 1517
},
{
"epoch": 2.17,
"learning_rate": 1.0787917364025594e-06,
"loss": 0.0733,
"step": 1518
},
{
"epoch": 2.17,
"learning_rate": 1.0753088128962533e-06,
"loss": 0.0569,
"step": 1519
},
{
"epoch": 2.17,
"learning_rate": 1.0718302927857828e-06,
"loss": 0.0754,
"step": 1520
},
{
"epoch": 2.18,
"learning_rate": 1.0683561840294629e-06,
"loss": 0.0634,
"step": 1521
},
{
"epoch": 2.18,
"learning_rate": 1.0648864945755175e-06,
"loss": 0.0634,
"step": 1522
},
{
"epoch": 2.18,
"learning_rate": 1.0614212323620596e-06,
"loss": 0.0566,
"step": 1523
},
{
"epoch": 2.18,
"learning_rate": 1.0579604053170731e-06,
"loss": 0.0909,
"step": 1524
},
{
"epoch": 2.18,
"learning_rate": 1.054504021358395e-06,
"loss": 0.0693,
"step": 1525
},
{
"epoch": 2.18,
"learning_rate": 1.0510520883936971e-06,
"loss": 0.0582,
"step": 1526
},
{
"epoch": 2.18,
"learning_rate": 1.0476046143204696e-06,
"loss": 0.0933,
"step": 1527
},
{
"epoch": 2.19,
"learning_rate": 1.0441616070259993e-06,
"loss": 0.0684,
"step": 1528
},
{
"epoch": 2.19,
"learning_rate": 1.0407230743873548e-06,
"loss": 0.0726,
"step": 1529
},
{
"epoch": 2.19,
"learning_rate": 1.0372890242713665e-06,
"loss": 0.0611,
"step": 1530
},
{
"epoch": 2.19,
"learning_rate": 1.0338594645346104e-06,
"loss": 0.0945,
"step": 1531
},
{
"epoch": 2.19,
"learning_rate": 1.0304344030233892e-06,
"loss": 0.095,
"step": 1532
},
{
"epoch": 2.19,
"learning_rate": 1.0270138475737128e-06,
"loss": 0.0474,
"step": 1533
},
{
"epoch": 2.19,
"learning_rate": 1.023597806011285e-06,
"loss": 0.0562,
"step": 1534
},
{
"epoch": 2.2,
"learning_rate": 1.0201862861514808e-06,
"loss": 0.0644,
"step": 1535
},
{
"epoch": 2.2,
"learning_rate": 1.0167792957993271e-06,
"loss": 0.0575,
"step": 1536
},
{
"epoch": 2.2,
"learning_rate": 1.0133768427494945e-06,
"loss": 0.0776,
"step": 1537
},
{
"epoch": 2.2,
"learning_rate": 1.0099789347862677e-06,
"loss": 0.0565,
"step": 1538
},
{
"epoch": 2.2,
"learning_rate": 1.0065855796835352e-06,
"loss": 0.0603,
"step": 1539
},
{
"epoch": 2.2,
"learning_rate": 1.0031967852047688e-06,
"loss": 0.0768,
"step": 1540
},
{
"epoch": 2.2,
"learning_rate": 9.99812559103005e-07,
"loss": 0.0693,
"step": 1541
},
{
"epoch": 2.21,
"learning_rate": 9.96432909120833e-07,
"loss": 0.0843,
"step": 1542
},
{
"epoch": 2.21,
"learning_rate": 9.930578429903654e-07,
"loss": 0.0966,
"step": 1543
},
{
"epoch": 2.21,
"learning_rate": 9.896873684332346e-07,
"loss": 0.1121,
"step": 1544
},
{
"epoch": 2.21,
"learning_rate": 9.863214931605656e-07,
"loss": 0.0918,
"step": 1545
},
{
"epoch": 2.21,
"learning_rate": 9.829602248729571e-07,
"loss": 0.0493,
"step": 1546
},
{
"epoch": 2.21,
"learning_rate": 9.796035712604743e-07,
"loss": 0.0871,
"step": 1547
},
{
"epoch": 2.21,
"learning_rate": 9.762515400026208e-07,
"loss": 0.068,
"step": 1548
},
{
"epoch": 2.22,
"learning_rate": 9.729041387683258e-07,
"loss": 0.0627,
"step": 1549
},
{
"epoch": 2.22,
"learning_rate": 9.695613752159256e-07,
"loss": 0.0672,
"step": 1550
},
{
"epoch": 2.22,
"learning_rate": 9.662232569931455e-07,
"loss": 0.0668,
"step": 1551
},
{
"epoch": 2.22,
"learning_rate": 9.628897917370866e-07,
"loss": 0.0543,
"step": 1552
},
{
"epoch": 2.22,
"learning_rate": 9.595609870741983e-07,
"loss": 0.0655,
"step": 1553
},
{
"epoch": 2.22,
"learning_rate": 9.562368506202737e-07,
"loss": 0.0684,
"step": 1554
},
{
"epoch": 2.22,
"learning_rate": 9.52917389980422e-07,
"loss": 0.0838,
"step": 1555
},
{
"epoch": 2.23,
"learning_rate": 9.496026127490561e-07,
"loss": 0.061,
"step": 1556
},
{
"epoch": 2.23,
"learning_rate": 9.46292526509874e-07,
"loss": 0.0841,
"step": 1557
},
{
"epoch": 2.23,
"learning_rate": 9.429871388358395e-07,
"loss": 0.0694,
"step": 1558
},
{
"epoch": 2.23,
"learning_rate": 9.39686457289172e-07,
"loss": 0.059,
"step": 1559
},
{
"epoch": 2.23,
"learning_rate": 9.363904894213163e-07,
"loss": 0.0834,
"step": 1560
},
{
"epoch": 2.23,
"learning_rate": 9.330992427729401e-07,
"loss": 0.0777,
"step": 1561
},
{
"epoch": 2.23,
"learning_rate": 9.298127248739064e-07,
"loss": 0.0846,
"step": 1562
},
{
"epoch": 2.24,
"learning_rate": 9.265309432432596e-07,
"loss": 0.0686,
"step": 1563
},
{
"epoch": 2.24,
"learning_rate": 9.232539053892087e-07,
"loss": 0.0716,
"step": 1564
},
{
"epoch": 2.24,
"learning_rate": 9.199816188091085e-07,
"loss": 0.0662,
"step": 1565
},
{
"epoch": 2.24,
"learning_rate": 9.167140909894479e-07,
"loss": 0.0749,
"step": 1566
},
{
"epoch": 2.24,
"learning_rate": 9.134513294058221e-07,
"loss": 0.0722,
"step": 1567
},
{
"epoch": 2.24,
"learning_rate": 9.101933415229253e-07,
"loss": 0.0619,
"step": 1568
},
{
"epoch": 2.24,
"learning_rate": 9.069401347945322e-07,
"loss": 0.079,
"step": 1569
},
{
"epoch": 2.25,
"learning_rate": 9.03691716663475e-07,
"loss": 0.0786,
"step": 1570
},
{
"epoch": 2.25,
"learning_rate": 9.00448094561633e-07,
"loss": 0.0776,
"step": 1571
},
{
"epoch": 2.25,
"learning_rate": 8.972092759099116e-07,
"loss": 0.075,
"step": 1572
},
{
"epoch": 2.25,
"learning_rate": 8.93975268118227e-07,
"loss": 0.0728,
"step": 1573
},
{
"epoch": 2.25,
"learning_rate": 8.907460785854894e-07,
"loss": 0.0662,
"step": 1574
},
{
"epoch": 2.25,
"learning_rate": 8.875217146995836e-07,
"loss": 0.0927,
"step": 1575
},
{
"epoch": 2.25,
"learning_rate": 8.843021838373578e-07,
"loss": 0.0692,
"step": 1576
},
{
"epoch": 2.26,
"learning_rate": 8.81087493364601e-07,
"loss": 0.0454,
"step": 1577
},
{
"epoch": 2.26,
"learning_rate": 8.778776506360248e-07,
"loss": 0.0736,
"step": 1578
},
{
"epoch": 2.26,
"learning_rate": 8.746726629952561e-07,
"loss": 0.0649,
"step": 1579
},
{
"epoch": 2.26,
"learning_rate": 8.714725377748101e-07,
"loss": 0.0891,
"step": 1580
},
{
"epoch": 2.26,
"learning_rate": 8.682772822960779e-07,
"loss": 0.0814,
"step": 1581
},
{
"epoch": 2.26,
"learning_rate": 8.650869038693111e-07,
"loss": 0.0708,
"step": 1582
},
{
"epoch": 2.26,
"learning_rate": 8.619014097936012e-07,
"loss": 0.0798,
"step": 1583
},
{
"epoch": 2.27,
"learning_rate": 8.587208073568665e-07,
"loss": 0.0646,
"step": 1584
},
{
"epoch": 2.27,
"learning_rate": 8.55545103835833e-07,
"loss": 0.0729,
"step": 1585
},
{
"epoch": 2.27,
"learning_rate": 8.523743064960203e-07,
"loss": 0.0634,
"step": 1586
},
{
"epoch": 2.27,
"learning_rate": 8.492084225917225e-07,
"loss": 0.0704,
"step": 1587
},
{
"epoch": 2.27,
"learning_rate": 8.46047459365992e-07,
"loss": 0.0788,
"step": 1588
},
{
"epoch": 2.27,
"learning_rate": 8.428914240506235e-07,
"loss": 0.0874,
"step": 1589
},
{
"epoch": 2.27,
"learning_rate": 8.397403238661383e-07,
"loss": 0.06,
"step": 1590
},
{
"epoch": 2.28,
"learning_rate": 8.365941660217666e-07,
"loss": 0.0718,
"step": 1591
},
{
"epoch": 2.28,
"learning_rate": 8.334529577154294e-07,
"loss": 0.0834,
"step": 1592
},
{
"epoch": 2.28,
"learning_rate": 8.303167061337282e-07,
"loss": 0.0574,
"step": 1593
},
{
"epoch": 2.28,
"learning_rate": 8.271854184519216e-07,
"loss": 0.0586,
"step": 1594
},
{
"epoch": 2.28,
"learning_rate": 8.240591018339081e-07,
"loss": 0.066,
"step": 1595
},
{
"epoch": 2.28,
"learning_rate": 8.209377634322205e-07,
"loss": 0.0862,
"step": 1596
},
{
"epoch": 2.28,
"learning_rate": 8.178214103879968e-07,
"loss": 0.0759,
"step": 1597
},
{
"epoch": 2.29,
"learning_rate": 8.147100498309713e-07,
"loss": 0.1007,
"step": 1598
},
{
"epoch": 2.29,
"learning_rate": 8.116036888794555e-07,
"loss": 0.0869,
"step": 1599
},
{
"epoch": 2.29,
"learning_rate": 8.085023346403227e-07,
"loss": 0.0956,
"step": 1600
},
{
"epoch": 2.29,
"learning_rate": 8.054059942089937e-07,
"loss": 0.0564,
"step": 1601
},
{
"epoch": 2.29,
"learning_rate": 8.023146746694135e-07,
"loss": 0.0639,
"step": 1602
},
{
"epoch": 2.29,
"learning_rate": 7.99228383094046e-07,
"loss": 0.0734,
"step": 1603
},
{
"epoch": 2.29,
"learning_rate": 7.961471265438482e-07,
"loss": 0.0886,
"step": 1604
},
{
"epoch": 2.3,
"learning_rate": 7.930709120682587e-07,
"loss": 0.0611,
"step": 1605
},
{
"epoch": 2.3,
"learning_rate": 7.899997467051801e-07,
"loss": 0.063,
"step": 1606
},
{
"epoch": 2.3,
"learning_rate": 7.869336374809633e-07,
"loss": 0.0776,
"step": 1607
},
{
"epoch": 2.3,
"learning_rate": 7.83872591410395e-07,
"loss": 0.0619,
"step": 1608
},
{
"epoch": 2.3,
"learning_rate": 7.808166154966722e-07,
"loss": 0.0814,
"step": 1609
},
{
"epoch": 2.3,
"learning_rate": 7.777657167313956e-07,
"loss": 0.0641,
"step": 1610
},
{
"epoch": 2.3,
"learning_rate": 7.747199020945517e-07,
"loss": 0.0631,
"step": 1611
},
{
"epoch": 2.31,
"learning_rate": 7.716791785544919e-07,
"loss": 0.0775,
"step": 1612
},
{
"epoch": 2.31,
"learning_rate": 7.686435530679225e-07,
"loss": 0.0657,
"step": 1613
},
{
"epoch": 2.31,
"learning_rate": 7.656130325798842e-07,
"loss": 0.0747,
"step": 1614
},
{
"epoch": 2.31,
"learning_rate": 7.625876240237398e-07,
"loss": 0.0626,
"step": 1615
},
{
"epoch": 2.31,
"learning_rate": 7.595673343211564e-07,
"loss": 0.0746,
"step": 1616
},
{
"epoch": 2.31,
"learning_rate": 7.565521703820891e-07,
"loss": 0.062,
"step": 1617
},
{
"epoch": 2.31,
"learning_rate": 7.535421391047686e-07,
"loss": 0.1843,
"step": 1618
},
{
"epoch": 2.32,
"learning_rate": 7.505372473756785e-07,
"loss": 0.0697,
"step": 1619
},
{
"epoch": 2.32,
"learning_rate": 7.475375020695484e-07,
"loss": 0.0776,
"step": 1620
},
{
"epoch": 2.32,
"learning_rate": 7.44542910049331e-07,
"loss": 0.0989,
"step": 1621
},
{
"epoch": 2.32,
"learning_rate": 7.4155347816619e-07,
"loss": 0.0748,
"step": 1622
},
{
"epoch": 2.32,
"learning_rate": 7.38569213259483e-07,
"loss": 0.0795,
"step": 1623
},
{
"epoch": 2.32,
"learning_rate": 7.355901221567463e-07,
"loss": 0.0872,
"step": 1624
},
{
"epoch": 2.32,
"learning_rate": 7.326162116736821e-07,
"loss": 0.0762,
"step": 1625
},
{
"epoch": 2.33,
"learning_rate": 7.296474886141346e-07,
"loss": 0.0952,
"step": 1626
},
{
"epoch": 2.33,
"learning_rate": 7.266839597700839e-07,
"loss": 0.0838,
"step": 1627
},
{
"epoch": 2.33,
"learning_rate": 7.237256319216274e-07,
"loss": 0.0614,
"step": 1628
},
{
"epoch": 2.33,
"learning_rate": 7.207725118369604e-07,
"loss": 0.0753,
"step": 1629
},
{
"epoch": 2.33,
"learning_rate": 7.178246062723656e-07,
"loss": 0.0638,
"step": 1630
},
{
"epoch": 2.33,
"learning_rate": 7.148819219721944e-07,
"loss": 0.0722,
"step": 1631
},
{
"epoch": 2.33,
"learning_rate": 7.119444656688545e-07,
"loss": 0.0676,
"step": 1632
},
{
"epoch": 2.34,
"learning_rate": 7.090122440827909e-07,
"loss": 0.0732,
"step": 1633
},
{
"epoch": 2.34,
"learning_rate": 7.060852639224727e-07,
"loss": 0.0658,
"step": 1634
},
{
"epoch": 2.34,
"learning_rate": 7.031635318843795e-07,
"loss": 0.0669,
"step": 1635
},
{
"epoch": 2.34,
"learning_rate": 7.002470546529826e-07,
"loss": 0.0709,
"step": 1636
},
{
"epoch": 2.34,
"learning_rate": 6.973358389007279e-07,
"loss": 0.0781,
"step": 1637
},
{
"epoch": 2.34,
"learning_rate": 6.944298912880303e-07,
"loss": 0.0702,
"step": 1638
},
{
"epoch": 2.34,
"learning_rate": 6.91529218463247e-07,
"loss": 0.0874,
"step": 1639
},
{
"epoch": 2.35,
"learning_rate": 6.886338270626694e-07,
"loss": 0.0718,
"step": 1640
},
{
"epoch": 2.35,
"learning_rate": 6.85743723710505e-07,
"loss": 0.0683,
"step": 1641
},
{
"epoch": 2.35,
"learning_rate": 6.828589150188629e-07,
"loss": 0.0806,
"step": 1642
},
{
"epoch": 2.35,
"learning_rate": 6.799794075877413e-07,
"loss": 0.0683,
"step": 1643
},
{
"epoch": 2.35,
"learning_rate": 6.771052080050053e-07,
"loss": 0.0664,
"step": 1644
},
{
"epoch": 2.35,
"learning_rate": 6.74236322846381e-07,
"loss": 0.0679,
"step": 1645
},
{
"epoch": 2.35,
"learning_rate": 6.713727586754336e-07,
"loss": 0.0668,
"step": 1646
},
{
"epoch": 2.36,
"learning_rate": 6.685145220435551e-07,
"loss": 0.0635,
"step": 1647
},
{
"epoch": 2.36,
"learning_rate": 6.656616194899489e-07,
"loss": 0.0652,
"step": 1648
},
{
"epoch": 2.36,
"learning_rate": 6.628140575416148e-07,
"loss": 0.0585,
"step": 1649
},
{
"epoch": 2.36,
"learning_rate": 6.599718427133347e-07,
"loss": 0.0668,
"step": 1650
},
{
"epoch": 2.36,
"learning_rate": 6.571349815076552e-07,
"loss": 0.0649,
"step": 1651
},
{
"epoch": 2.36,
"learning_rate": 6.543034804148782e-07,
"loss": 0.0521,
"step": 1652
},
{
"epoch": 2.36,
"learning_rate": 6.514773459130402e-07,
"loss": 0.089,
"step": 1653
},
{
"epoch": 2.37,
"learning_rate": 6.486565844678975e-07,
"loss": 0.0572,
"step": 1654
},
{
"epoch": 2.37,
"learning_rate": 6.458412025329184e-07,
"loss": 0.0908,
"step": 1655
},
{
"epoch": 2.37,
"learning_rate": 6.430312065492612e-07,
"loss": 0.0818,
"step": 1656
},
{
"epoch": 2.37,
"learning_rate": 6.402266029457617e-07,
"loss": 0.1053,
"step": 1657
},
{
"epoch": 2.37,
"learning_rate": 6.374273981389193e-07,
"loss": 0.0609,
"step": 1658
},
{
"epoch": 2.37,
"learning_rate": 6.346335985328813e-07,
"loss": 0.0643,
"step": 1659
},
{
"epoch": 2.37,
"learning_rate": 6.318452105194315e-07,
"loss": 0.0768,
"step": 1660
},
{
"epoch": 2.38,
"learning_rate": 6.290622404779672e-07,
"loss": 0.0543,
"step": 1661
},
{
"epoch": 2.38,
"learning_rate": 6.262846947754958e-07,
"loss": 0.0709,
"step": 1662
},
{
"epoch": 2.38,
"learning_rate": 6.23512579766612e-07,
"loss": 0.0775,
"step": 1663
},
{
"epoch": 2.38,
"learning_rate": 6.207459017934861e-07,
"loss": 0.0771,
"step": 1664
},
{
"epoch": 2.38,
"learning_rate": 6.179846671858495e-07,
"loss": 0.0816,
"step": 1665
},
{
"epoch": 2.38,
"learning_rate": 6.152288822609794e-07,
"loss": 0.0851,
"step": 1666
},
{
"epoch": 2.38,
"learning_rate": 6.124785533236876e-07,
"loss": 0.086,
"step": 1667
},
{
"epoch": 2.39,
"learning_rate": 6.097336866662996e-07,
"loss": 0.0788,
"step": 1668
},
{
"epoch": 2.39,
"learning_rate": 6.069942885686453e-07,
"loss": 0.0863,
"step": 1669
},
{
"epoch": 2.39,
"learning_rate": 6.04260365298046e-07,
"loss": 0.0735,
"step": 1670
},
{
"epoch": 2.39,
"learning_rate": 6.015319231092944e-07,
"loss": 0.0693,
"step": 1671
},
{
"epoch": 2.39,
"learning_rate": 5.988089682446446e-07,
"loss": 0.0759,
"step": 1672
},
{
"epoch": 2.39,
"learning_rate": 5.960915069337954e-07,
"loss": 0.0776,
"step": 1673
},
{
"epoch": 2.39,
"learning_rate": 5.933795453938801e-07,
"loss": 0.0824,
"step": 1674
},
{
"epoch": 2.4,
"learning_rate": 5.906730898294454e-07,
"loss": 0.0733,
"step": 1675
},
{
"epoch": 2.4,
"learning_rate": 5.879721464324431e-07,
"loss": 0.0808,
"step": 1676
},
{
"epoch": 2.4,
"learning_rate": 5.852767213822154e-07,
"loss": 0.0708,
"step": 1677
},
{
"epoch": 2.4,
"learning_rate": 5.825868208454778e-07,
"loss": 0.0947,
"step": 1678
},
{
"epoch": 2.4,
"learning_rate": 5.799024509763063e-07,
"loss": 0.0748,
"step": 1679
},
{
"epoch": 2.4,
"learning_rate": 5.772236179161242e-07,
"loss": 0.0717,
"step": 1680
},
{
"epoch": 2.4,
"learning_rate": 5.745503277936875e-07,
"loss": 0.0476,
"step": 1681
},
{
"epoch": 2.41,
"learning_rate": 5.718825867250703e-07,
"loss": 0.0664,
"step": 1682
},
{
"epoch": 2.41,
"learning_rate": 5.692204008136514e-07,
"loss": 0.0552,
"step": 1683
},
{
"epoch": 2.41,
"learning_rate": 5.665637761501015e-07,
"loss": 0.08,
"step": 1684
},
{
"epoch": 2.41,
"learning_rate": 5.639127188123678e-07,
"loss": 0.0547,
"step": 1685
},
{
"epoch": 2.41,
"learning_rate": 5.612672348656564e-07,
"loss": 0.0615,
"step": 1686
},
{
"epoch": 2.41,
"learning_rate": 5.586273303624286e-07,
"loss": 0.0714,
"step": 1687
},
{
"epoch": 2.41,
"learning_rate": 5.559930113423764e-07,
"loss": 0.0796,
"step": 1688
},
{
"epoch": 2.42,
"learning_rate": 5.533642838324149e-07,
"loss": 0.0724,
"step": 1689
},
{
"epoch": 2.42,
"learning_rate": 5.507411538466654e-07,
"loss": 0.102,
"step": 1690
},
{
"epoch": 2.42,
"learning_rate": 5.481236273864443e-07,
"loss": 0.0639,
"step": 1691
},
{
"epoch": 2.42,
"learning_rate": 5.455117104402474e-07,
"loss": 0.0699,
"step": 1692
},
{
"epoch": 2.42,
"learning_rate": 5.429054089837361e-07,
"loss": 0.0557,
"step": 1693
},
{
"epoch": 2.42,
"learning_rate": 5.403047289797263e-07,
"loss": 0.0859,
"step": 1694
},
{
"epoch": 2.42,
"learning_rate": 5.377096763781718e-07,
"loss": 0.0523,
"step": 1695
},
{
"epoch": 2.43,
"learning_rate": 5.351202571161496e-07,
"loss": 0.0931,
"step": 1696
},
{
"epoch": 2.43,
"learning_rate": 5.325364771178529e-07,
"loss": 0.0872,
"step": 1697
},
{
"epoch": 2.43,
"learning_rate": 5.299583422945701e-07,
"loss": 0.087,
"step": 1698
},
{
"epoch": 2.43,
"learning_rate": 5.273858585446748e-07,
"loss": 0.0734,
"step": 1699
},
{
"epoch": 2.43,
"learning_rate": 5.248190317536119e-07,
"loss": 0.0919,
"step": 1700
},
{
"epoch": 2.43,
"learning_rate": 5.222578677938842e-07,
"loss": 0.061,
"step": 1701
},
{
"epoch": 2.43,
"learning_rate": 5.197023725250402e-07,
"loss": 0.0923,
"step": 1702
},
{
"epoch": 2.44,
"learning_rate": 5.171525517936554e-07,
"loss": 0.069,
"step": 1703
},
{
"epoch": 2.44,
"learning_rate": 5.146084114333278e-07,
"loss": 0.0693,
"step": 1704
},
{
"epoch": 2.44,
"learning_rate": 5.120699572646561e-07,
"loss": 0.0704,
"step": 1705
},
{
"epoch": 2.44,
"learning_rate": 5.095371950952306e-07,
"loss": 0.0782,
"step": 1706
},
{
"epoch": 2.44,
"learning_rate": 5.070101307196203e-07,
"loss": 0.0846,
"step": 1707
},
{
"epoch": 2.44,
"learning_rate": 5.044887699193567e-07,
"loss": 0.0843,
"step": 1708
},
{
"epoch": 2.44,
"learning_rate": 5.019731184629253e-07,
"loss": 0.092,
"step": 1709
},
{
"epoch": 2.45,
"learning_rate": 4.994631821057453e-07,
"loss": 0.0604,
"step": 1710
},
{
"epoch": 2.45,
"learning_rate": 4.969589665901649e-07,
"loss": 0.0677,
"step": 1711
},
{
"epoch": 2.45,
"learning_rate": 4.944604776454411e-07,
"loss": 0.0631,
"step": 1712
},
{
"epoch": 2.45,
"learning_rate": 4.919677209877303e-07,
"loss": 0.0756,
"step": 1713
},
{
"epoch": 2.45,
"learning_rate": 4.894807023200747e-07,
"loss": 0.1164,
"step": 1714
},
{
"epoch": 2.45,
"learning_rate": 4.869994273323877e-07,
"loss": 0.074,
"step": 1715
},
{
"epoch": 2.45,
"learning_rate": 4.845239017014444e-07,
"loss": 0.0857,
"step": 1716
},
{
"epoch": 2.46,
"learning_rate": 4.82054131090863e-07,
"loss": 0.0723,
"step": 1717
},
{
"epoch": 2.46,
"learning_rate": 4.795901211510963e-07,
"loss": 0.0638,
"step": 1718
},
{
"epoch": 2.46,
"learning_rate": 4.771318775194203e-07,
"loss": 0.0749,
"step": 1719
},
{
"epoch": 2.46,
"learning_rate": 4.7467940581991474e-07,
"loss": 0.0826,
"step": 1720
},
{
"epoch": 2.46,
"learning_rate": 4.7223271166345627e-07,
"loss": 0.0566,
"step": 1721
},
{
"epoch": 2.46,
"learning_rate": 4.697918006477024e-07,
"loss": 0.0958,
"step": 1722
},
{
"epoch": 2.46,
"learning_rate": 4.673566783570805e-07,
"loss": 0.0525,
"step": 1723
},
{
"epoch": 2.47,
"learning_rate": 4.6492735036277335e-07,
"loss": 0.0539,
"step": 1724
},
{
"epoch": 2.47,
"learning_rate": 4.625038222227077e-07,
"loss": 0.0552,
"step": 1725
},
{
"epoch": 2.47,
"learning_rate": 4.600860994815427e-07,
"loss": 0.0589,
"step": 1726
},
{
"epoch": 2.47,
"learning_rate": 4.576741876706526e-07,
"loss": 0.0548,
"step": 1727
},
{
"epoch": 2.47,
"learning_rate": 4.552680923081182e-07,
"loss": 0.0541,
"step": 1728
},
{
"epoch": 2.47,
"learning_rate": 4.5286781889871533e-07,
"loss": 0.0788,
"step": 1729
},
{
"epoch": 2.47,
"learning_rate": 4.504733729338977e-07,
"loss": 0.0629,
"step": 1730
},
{
"epoch": 2.48,
"learning_rate": 4.4808475989178723e-07,
"loss": 0.1056,
"step": 1731
},
{
"epoch": 2.48,
"learning_rate": 4.4570198523716057e-07,
"loss": 0.0546,
"step": 1732
},
{
"epoch": 2.48,
"learning_rate": 4.4332505442144e-07,
"loss": 0.0594,
"step": 1733
},
{
"epoch": 2.48,
"learning_rate": 4.409539728826736e-07,
"loss": 0.0748,
"step": 1734
},
{
"epoch": 2.48,
"learning_rate": 4.3858874604552936e-07,
"loss": 0.0675,
"step": 1735
},
{
"epoch": 2.48,
"learning_rate": 4.3622937932128135e-07,
"loss": 0.0869,
"step": 1736
},
{
"epoch": 2.48,
"learning_rate": 4.3387587810779584e-07,
"loss": 0.0755,
"step": 1737
},
{
"epoch": 2.49,
"learning_rate": 4.315282477895196e-07,
"loss": 0.0803,
"step": 1738
},
{
"epoch": 2.49,
"learning_rate": 4.291864937374673e-07,
"loss": 0.0607,
"step": 1739
},
{
"epoch": 2.49,
"learning_rate": 4.268506213092107e-07,
"loss": 0.0703,
"step": 1740
},
{
"epoch": 2.49,
"learning_rate": 4.2452063584886457e-07,
"loss": 0.077,
"step": 1741
},
{
"epoch": 2.49,
"learning_rate": 4.221965426870742e-07,
"loss": 0.0839,
"step": 1742
},
{
"epoch": 2.49,
"learning_rate": 4.198783471410076e-07,
"loss": 0.0803,
"step": 1743
},
{
"epoch": 2.49,
"learning_rate": 4.175660545143373e-07,
"loss": 0.0607,
"step": 1744
},
{
"epoch": 2.5,
"learning_rate": 4.152596700972289e-07,
"loss": 0.0689,
"step": 1745
},
{
"epoch": 2.5,
"learning_rate": 4.1295919916633617e-07,
"loss": 0.0645,
"step": 1746
},
{
"epoch": 2.5,
"learning_rate": 4.106646469847795e-07,
"loss": 0.068,
"step": 1747
},
{
"epoch": 2.5,
"learning_rate": 4.083760188021398e-07,
"loss": 0.0713,
"step": 1748
},
{
"epoch": 2.5,
"learning_rate": 4.060933198544445e-07,
"loss": 0.0679,
"step": 1749
},
{
"epoch": 2.5,
"learning_rate": 4.0381655536415505e-07,
"loss": 0.0717,
"step": 1750
},
{
"epoch": 2.51,
"learning_rate": 4.0154573054015843e-07,
"loss": 0.0793,
"step": 1751
},
{
"epoch": 2.51,
"learning_rate": 3.9928085057774844e-07,
"loss": 0.0553,
"step": 1752
},
{
"epoch": 2.51,
"learning_rate": 3.970219206586222e-07,
"loss": 0.074,
"step": 1753
},
{
"epoch": 2.51,
"learning_rate": 3.94768945950861e-07,
"loss": 0.0957,
"step": 1754
},
{
"epoch": 2.51,
"learning_rate": 3.92521931608923e-07,
"loss": 0.0748,
"step": 1755
},
{
"epoch": 2.51,
"learning_rate": 3.902808827736294e-07,
"loss": 0.3802,
"step": 1756
},
{
"epoch": 2.51,
"learning_rate": 3.8804580457215345e-07,
"loss": 0.0847,
"step": 1757
},
{
"epoch": 2.52,
"learning_rate": 3.8581670211800847e-07,
"loss": 0.0585,
"step": 1758
},
{
"epoch": 2.52,
"learning_rate": 3.8359358051103597e-07,
"loss": 0.0614,
"step": 1759
},
{
"epoch": 2.52,
"learning_rate": 3.813764448373942e-07,
"loss": 0.0687,
"step": 1760
},
{
"epoch": 2.52,
"learning_rate": 3.7916530016954854e-07,
"loss": 0.0898,
"step": 1761
},
{
"epoch": 2.52,
"learning_rate": 3.7696015156625373e-07,
"loss": 0.0672,
"step": 1762
},
{
"epoch": 2.52,
"learning_rate": 3.747610040725502e-07,
"loss": 0.0718,
"step": 1763
},
{
"epoch": 2.52,
"learning_rate": 3.725678627197473e-07,
"loss": 0.0607,
"step": 1764
},
{
"epoch": 2.53,
"learning_rate": 3.70380732525413e-07,
"loss": 0.0783,
"step": 1765
},
{
"epoch": 2.53,
"learning_rate": 3.6819961849336315e-07,
"loss": 0.0873,
"step": 1766
},
{
"epoch": 2.53,
"learning_rate": 3.6602452561364863e-07,
"loss": 0.0655,
"step": 1767
},
{
"epoch": 2.53,
"learning_rate": 3.6385545886254754e-07,
"loss": 0.0852,
"step": 1768
},
{
"epoch": 2.53,
"learning_rate": 3.61692423202547e-07,
"loss": 0.0621,
"step": 1769
},
{
"epoch": 2.53,
"learning_rate": 3.5953542358233983e-07,
"loss": 0.0607,
"step": 1770
},
{
"epoch": 2.53,
"learning_rate": 3.573844649368068e-07,
"loss": 0.0759,
"step": 1771
},
{
"epoch": 2.54,
"learning_rate": 3.5523955218700874e-07,
"loss": 0.0658,
"step": 1772
},
{
"epoch": 2.54,
"learning_rate": 3.531006902401748e-07,
"loss": 0.0535,
"step": 1773
},
{
"epoch": 2.54,
"learning_rate": 3.5096788398968946e-07,
"loss": 0.0619,
"step": 1774
},
{
"epoch": 2.54,
"learning_rate": 3.4884113831508534e-07,
"loss": 0.0848,
"step": 1775
},
{
"epoch": 2.54,
"learning_rate": 3.4672045808202624e-07,
"loss": 0.0686,
"step": 1776
},
{
"epoch": 2.54,
"learning_rate": 3.446058481423001e-07,
"loss": 0.063,
"step": 1777
},
{
"epoch": 2.54,
"learning_rate": 3.424973133338094e-07,
"loss": 0.0684,
"step": 1778
},
{
"epoch": 2.55,
"learning_rate": 3.4039485848055465e-07,
"loss": 0.0538,
"step": 1779
},
{
"epoch": 2.55,
"learning_rate": 3.382984883926278e-07,
"loss": 0.0575,
"step": 1780
},
{
"epoch": 2.55,
"learning_rate": 3.36208207866199e-07,
"loss": 0.0787,
"step": 1781
},
{
"epoch": 2.55,
"learning_rate": 3.341240216835072e-07,
"loss": 0.0669,
"step": 1782
},
{
"epoch": 2.55,
"learning_rate": 3.3204593461284817e-07,
"loss": 0.0859,
"step": 1783
},
{
"epoch": 2.55,
"learning_rate": 3.2997395140856313e-07,
"loss": 0.0669,
"step": 1784
},
{
"epoch": 2.55,
"learning_rate": 3.2790807681103054e-07,
"loss": 0.0561,
"step": 1785
},
{
"epoch": 2.56,
"learning_rate": 3.258483155466516e-07,
"loss": 0.0581,
"step": 1786
},
{
"epoch": 2.56,
"learning_rate": 3.237946723278405e-07,
"loss": 0.0585,
"step": 1787
},
{
"epoch": 2.56,
"learning_rate": 3.2174715185301694e-07,
"loss": 0.0691,
"step": 1788
},
{
"epoch": 2.56,
"learning_rate": 3.1970575880659005e-07,
"loss": 0.074,
"step": 1789
},
{
"epoch": 2.56,
"learning_rate": 3.176704978589522e-07,
"loss": 0.0643,
"step": 1790
},
{
"epoch": 2.56,
"learning_rate": 3.1564137366646505e-07,
"loss": 0.067,
"step": 1791
},
{
"epoch": 2.56,
"learning_rate": 3.136183908714515e-07,
"loss": 0.0741,
"step": 1792
},
{
"epoch": 2.57,
"learning_rate": 3.116015541021843e-07,
"loss": 0.0895,
"step": 1793
},
{
"epoch": 2.57,
"learning_rate": 3.0959086797287174e-07,
"loss": 0.0821,
"step": 1794
},
{
"epoch": 2.57,
"learning_rate": 3.075863370836548e-07,
"loss": 0.0825,
"step": 1795
},
{
"epoch": 2.57,
"learning_rate": 3.055879660205897e-07,
"loss": 0.0689,
"step": 1796
},
{
"epoch": 2.57,
"learning_rate": 3.035957593556402e-07,
"loss": 0.0648,
"step": 1797
},
{
"epoch": 2.57,
"learning_rate": 3.016097216466671e-07,
"loss": 0.0678,
"step": 1798
},
{
"epoch": 2.57,
"learning_rate": 2.9962985743741777e-07,
"loss": 0.0613,
"step": 1799
},
{
"epoch": 2.58,
"learning_rate": 2.9765617125751523e-07,
"loss": 0.0727,
"step": 1800
},
{
"epoch": 2.58,
"learning_rate": 2.9568866762244804e-07,
"loss": 0.0796,
"step": 1801
},
{
"epoch": 2.58,
"learning_rate": 2.93727351033561e-07,
"loss": 0.0622,
"step": 1802
},
{
"epoch": 2.58,
"learning_rate": 2.9177222597804353e-07,
"loss": 0.0748,
"step": 1803
},
{
"epoch": 2.58,
"learning_rate": 2.898232969289177e-07,
"loss": 0.1164,
"step": 1804
},
{
"epoch": 2.58,
"learning_rate": 2.8788056834503316e-07,
"loss": 0.0645,
"step": 1805
},
{
"epoch": 2.58,
"learning_rate": 2.859440446710525e-07,
"loss": 0.055,
"step": 1806
},
{
"epoch": 2.59,
"learning_rate": 2.8401373033744204e-07,
"loss": 0.056,
"step": 1807
},
{
"epoch": 2.59,
"learning_rate": 2.8208962976046283e-07,
"loss": 0.0694,
"step": 1808
},
{
"epoch": 2.59,
"learning_rate": 2.8017174734215857e-07,
"loss": 0.0841,
"step": 1809
},
{
"epoch": 2.59,
"learning_rate": 2.782600874703497e-07,
"loss": 0.0719,
"step": 1810
},
{
"epoch": 2.59,
"learning_rate": 2.763546545186157e-07,
"loss": 0.0786,
"step": 1811
},
{
"epoch": 2.59,
"learning_rate": 2.744554528462949e-07,
"loss": 0.0716,
"step": 1812
},
{
"epoch": 2.59,
"learning_rate": 2.7256248679846616e-07,
"loss": 0.0714,
"step": 1813
},
{
"epoch": 2.6,
"learning_rate": 2.706757607059429e-07,
"loss": 0.065,
"step": 1814
},
{
"epoch": 2.6,
"learning_rate": 2.687952788852629e-07,
"loss": 0.0708,
"step": 1815
},
{
"epoch": 2.6,
"learning_rate": 2.6692104563867734e-07,
"loss": 0.0734,
"step": 1816
},
{
"epoch": 2.6,
"learning_rate": 2.650530652541433e-07,
"loss": 0.0584,
"step": 1817
},
{
"epoch": 2.6,
"learning_rate": 2.631913420053101e-07,
"loss": 0.0638,
"step": 1818
},
{
"epoch": 2.6,
"learning_rate": 2.613358801515121e-07,
"loss": 0.0576,
"step": 1819
},
{
"epoch": 2.6,
"learning_rate": 2.5948668393776054e-07,
"loss": 0.0707,
"step": 1820
},
{
"epoch": 2.61,
"learning_rate": 2.5764375759472994e-07,
"loss": 0.0734,
"step": 1821
},
{
"epoch": 2.61,
"learning_rate": 2.558071053387505e-07,
"loss": 0.0532,
"step": 1822
},
{
"epoch": 2.61,
"learning_rate": 2.539767313717981e-07,
"loss": 0.0576,
"step": 1823
},
{
"epoch": 2.61,
"learning_rate": 2.5215263988148727e-07,
"loss": 0.0741,
"step": 1824
},
{
"epoch": 2.61,
"learning_rate": 2.5033483504105517e-07,
"loss": 0.0586,
"step": 1825
},
{
"epoch": 2.61,
"learning_rate": 2.4852332100935895e-07,
"loss": 0.0744,
"step": 1826
},
{
"epoch": 2.61,
"learning_rate": 2.4671810193086276e-07,
"loss": 0.062,
"step": 1827
},
{
"epoch": 2.62,
"learning_rate": 2.4491918193562925e-07,
"loss": 0.0775,
"step": 1828
},
{
"epoch": 2.62,
"learning_rate": 2.431265651393082e-07,
"loss": 0.0671,
"step": 1829
},
{
"epoch": 2.62,
"learning_rate": 2.4134025564313035e-07,
"loss": 0.0668,
"step": 1830
},
{
"epoch": 2.62,
"learning_rate": 2.3956025753389523e-07,
"loss": 0.0758,
"step": 1831
},
{
"epoch": 2.62,
"learning_rate": 2.3778657488396327e-07,
"loss": 0.0611,
"step": 1832
},
{
"epoch": 2.62,
"learning_rate": 2.360192117512462e-07,
"loss": 0.0876,
"step": 1833
},
{
"epoch": 2.62,
"learning_rate": 2.3425817217919855e-07,
"loss": 0.0774,
"step": 1834
},
{
"epoch": 2.63,
"learning_rate": 2.325034601968048e-07,
"loss": 0.0726,
"step": 1835
},
{
"epoch": 2.63,
"learning_rate": 2.3075507981857537e-07,
"loss": 0.0744,
"step": 1836
},
{
"epoch": 2.63,
"learning_rate": 2.2901303504453486e-07,
"loss": 0.0728,
"step": 1837
},
{
"epoch": 2.63,
"learning_rate": 2.2727732986021189e-07,
"loss": 0.0789,
"step": 1838
},
{
"epoch": 2.63,
"learning_rate": 2.255479682366316e-07,
"loss": 0.055,
"step": 1839
},
{
"epoch": 2.63,
"learning_rate": 2.238249541303058e-07,
"loss": 0.0825,
"step": 1840
},
{
"epoch": 2.63,
"learning_rate": 2.2210829148322453e-07,
"loss": 0.0747,
"step": 1841
},
{
"epoch": 2.64,
"learning_rate": 2.2039798422284651e-07,
"loss": 0.07,
"step": 1842
},
{
"epoch": 2.64,
"learning_rate": 2.186940362620897e-07,
"loss": 0.0577,
"step": 1843
},
{
"epoch": 2.64,
"learning_rate": 2.1699645149932445e-07,
"loss": 0.0784,
"step": 1844
},
{
"epoch": 2.64,
"learning_rate": 2.1530523381836264e-07,
"loss": 0.0742,
"step": 1845
},
{
"epoch": 2.64,
"learning_rate": 2.136203870884469e-07,
"loss": 0.0817,
"step": 1846
},
{
"epoch": 2.64,
"learning_rate": 2.1194191516424743e-07,
"loss": 0.0855,
"step": 1847
},
{
"epoch": 2.64,
"learning_rate": 2.1026982188584853e-07,
"loss": 0.0796,
"step": 1848
},
{
"epoch": 2.65,
"learning_rate": 2.0860411107874043e-07,
"loss": 0.076,
"step": 1849
},
{
"epoch": 2.65,
"learning_rate": 2.0694478655381176e-07,
"loss": 0.0835,
"step": 1850
},
{
"epoch": 2.65,
"learning_rate": 2.0529185210734147e-07,
"loss": 0.0841,
"step": 1851
},
{
"epoch": 2.65,
"learning_rate": 2.036453115209882e-07,
"loss": 0.0747,
"step": 1852
},
{
"epoch": 2.65,
"learning_rate": 2.0200516856177998e-07,
"loss": 0.0686,
"step": 1853
},
{
"epoch": 2.65,
"learning_rate": 2.0037142698211252e-07,
"loss": 0.0548,
"step": 1854
},
{
"epoch": 2.65,
"learning_rate": 1.987440905197333e-07,
"loss": 0.0727,
"step": 1855
},
{
"epoch": 2.66,
"learning_rate": 1.9712316289773614e-07,
"loss": 0.0783,
"step": 1856
},
{
"epoch": 2.66,
"learning_rate": 1.9550864782455325e-07,
"loss": 0.0652,
"step": 1857
},
{
"epoch": 2.66,
"learning_rate": 1.9390054899394495e-07,
"loss": 0.0601,
"step": 1858
},
{
"epoch": 2.66,
"learning_rate": 1.922988700849939e-07,
"loss": 0.0679,
"step": 1859
},
{
"epoch": 2.66,
"learning_rate": 1.9070361476209197e-07,
"loss": 0.0921,
"step": 1860
},
{
"epoch": 2.66,
"learning_rate": 1.891147866749383e-07,
"loss": 0.077,
"step": 1861
},
{
"epoch": 2.66,
"learning_rate": 1.8753238945852492e-07,
"loss": 0.0735,
"step": 1862
},
{
"epoch": 2.67,
"learning_rate": 1.8595642673313252e-07,
"loss": 0.0861,
"step": 1863
},
{
"epoch": 2.67,
"learning_rate": 1.8438690210431995e-07,
"loss": 0.0503,
"step": 1864
},
{
"epoch": 2.67,
"learning_rate": 1.8282381916291692e-07,
"loss": 0.0649,
"step": 1865
},
{
"epoch": 2.67,
"learning_rate": 1.8126718148501543e-07,
"loss": 0.0748,
"step": 1866
},
{
"epoch": 2.67,
"learning_rate": 1.7971699263196172e-07,
"loss": 0.0621,
"step": 1867
},
{
"epoch": 2.67,
"learning_rate": 1.7817325615034786e-07,
"loss": 0.0658,
"step": 1868
},
{
"epoch": 2.67,
"learning_rate": 1.7663597557200562e-07,
"loss": 0.0623,
"step": 1869
},
{
"epoch": 2.68,
"learning_rate": 1.7510515441399332e-07,
"loss": 0.0742,
"step": 1870
},
{
"epoch": 2.68,
"learning_rate": 1.7358079617859446e-07,
"loss": 0.0841,
"step": 1871
},
{
"epoch": 2.68,
"learning_rate": 1.7206290435330463e-07,
"loss": 0.0564,
"step": 1872
},
{
"epoch": 2.68,
"learning_rate": 1.705514824108253e-07,
"loss": 0.0627,
"step": 1873
},
{
"epoch": 2.68,
"learning_rate": 1.6904653380905677e-07,
"loss": 0.0631,
"step": 1874
},
{
"epoch": 2.68,
"learning_rate": 1.6754806199108786e-07,
"loss": 0.0692,
"step": 1875
},
{
"epoch": 2.68,
"learning_rate": 1.660560703851919e-07,
"loss": 0.0681,
"step": 1876
},
{
"epoch": 2.69,
"learning_rate": 1.6457056240481338e-07,
"loss": 0.0667,
"step": 1877
},
{
"epoch": 2.69,
"learning_rate": 1.6309154144856508e-07,
"loss": 0.1009,
"step": 1878
},
{
"epoch": 2.69,
"learning_rate": 1.6161901090021925e-07,
"loss": 0.0893,
"step": 1879
},
{
"epoch": 2.69,
"learning_rate": 1.6015297412869766e-07,
"loss": 0.0542,
"step": 1880
},
{
"epoch": 2.69,
"learning_rate": 1.586934344880654e-07,
"loss": 0.0496,
"step": 1881
},
{
"epoch": 2.69,
"learning_rate": 1.5724039531752332e-07,
"loss": 0.0704,
"step": 1882
},
{
"epoch": 2.69,
"learning_rate": 1.5579385994140194e-07,
"loss": 0.0579,
"step": 1883
},
{
"epoch": 2.7,
"learning_rate": 1.5435383166914862e-07,
"loss": 0.0695,
"step": 1884
},
{
"epoch": 2.7,
"learning_rate": 1.5292031379532568e-07,
"loss": 0.079,
"step": 1885
},
{
"epoch": 2.7,
"learning_rate": 1.5149330959960128e-07,
"loss": 0.1079,
"step": 1886
},
{
"epoch": 2.7,
"learning_rate": 1.500728223467399e-07,
"loss": 0.07,
"step": 1887
},
{
"epoch": 2.7,
"learning_rate": 1.4865885528659694e-07,
"loss": 0.0717,
"step": 1888
},
{
"epoch": 2.7,
"learning_rate": 1.4725141165411006e-07,
"loss": 0.0552,
"step": 1889
},
{
"epoch": 2.7,
"learning_rate": 1.458504946692928e-07,
"loss": 0.0486,
"step": 1890
},
{
"epoch": 2.71,
"learning_rate": 1.4445610753722638e-07,
"loss": 0.0651,
"step": 1891
},
{
"epoch": 2.71,
"learning_rate": 1.4306825344805297e-07,
"loss": 0.0655,
"step": 1892
},
{
"epoch": 2.71,
"learning_rate": 1.4168693557696898e-07,
"loss": 0.0653,
"step": 1893
},
{
"epoch": 2.71,
"learning_rate": 1.4031215708421552e-07,
"loss": 0.0907,
"step": 1894
},
{
"epoch": 2.71,
"learning_rate": 1.3894392111507258e-07,
"loss": 0.0822,
"step": 1895
},
{
"epoch": 2.71,
"learning_rate": 1.3758223079985354e-07,
"loss": 0.068,
"step": 1896
},
{
"epoch": 2.71,
"learning_rate": 1.362270892538947e-07,
"loss": 0.0651,
"step": 1897
},
{
"epoch": 2.72,
"learning_rate": 1.3487849957755072e-07,
"loss": 0.0555,
"step": 1898
},
{
"epoch": 2.72,
"learning_rate": 1.3353646485618588e-07,
"loss": 0.0544,
"step": 1899
},
{
"epoch": 2.72,
"learning_rate": 1.3220098816016812e-07,
"loss": 0.0628,
"step": 1900
},
{
"epoch": 2.72,
"learning_rate": 1.308720725448621e-07,
"loss": 0.0768,
"step": 1901
},
{
"epoch": 2.72,
"learning_rate": 1.2954972105062047e-07,
"loss": 0.0678,
"step": 1902
},
{
"epoch": 2.72,
"learning_rate": 1.2823393670278015e-07,
"loss": 0.0677,
"step": 1903
},
{
"epoch": 2.72,
"learning_rate": 1.2692472251165155e-07,
"loss": 0.0665,
"step": 1904
},
{
"epoch": 2.73,
"learning_rate": 1.2562208147251398e-07,
"loss": 0.0546,
"step": 1905
},
{
"epoch": 2.73,
"learning_rate": 1.2432601656560917e-07,
"loss": 0.0795,
"step": 1906
},
{
"epoch": 2.73,
"learning_rate": 1.230365307561332e-07,
"loss": 0.0826,
"step": 1907
},
{
"epoch": 2.73,
"learning_rate": 1.217536269942302e-07,
"loss": 0.0847,
"step": 1908
},
{
"epoch": 2.73,
"learning_rate": 1.2047730821498536e-07,
"loss": 0.0589,
"step": 1909
},
{
"epoch": 2.73,
"learning_rate": 1.1920757733841925e-07,
"loss": 0.0529,
"step": 1910
},
{
"epoch": 2.73,
"learning_rate": 1.1794443726947978e-07,
"loss": 0.0631,
"step": 1911
},
{
"epoch": 2.74,
"learning_rate": 1.16687890898035e-07,
"loss": 0.0956,
"step": 1912
},
{
"epoch": 2.74,
"learning_rate": 1.1543794109886996e-07,
"loss": 0.065,
"step": 1913
},
{
"epoch": 2.74,
"learning_rate": 1.1419459073167616e-07,
"loss": 0.0678,
"step": 1914
},
{
"epoch": 2.74,
"learning_rate": 1.1295784264104681e-07,
"loss": 0.0785,
"step": 1915
},
{
"epoch": 2.74,
"learning_rate": 1.1172769965647023e-07,
"loss": 0.0941,
"step": 1916
},
{
"epoch": 2.74,
"learning_rate": 1.1050416459232349e-07,
"loss": 0.0766,
"step": 1917
},
{
"epoch": 2.74,
"learning_rate": 1.0928724024786607e-07,
"loss": 0.0695,
"step": 1918
},
{
"epoch": 2.75,
"learning_rate": 1.0807692940723191e-07,
"loss": 0.0728,
"step": 1919
},
{
"epoch": 2.75,
"learning_rate": 1.0687323483942569e-07,
"loss": 0.0541,
"step": 1920
},
{
"epoch": 2.75,
"learning_rate": 1.0567615929831453e-07,
"loss": 0.0754,
"step": 1921
},
{
"epoch": 2.75,
"learning_rate": 1.0448570552262171e-07,
"loss": 0.0726,
"step": 1922
},
{
"epoch": 2.75,
"learning_rate": 1.0330187623592158e-07,
"loss": 0.0579,
"step": 1923
},
{
"epoch": 2.75,
"learning_rate": 1.0212467414663196e-07,
"loss": 0.0785,
"step": 1924
},
{
"epoch": 2.75,
"learning_rate": 1.0095410194801047e-07,
"loss": 0.0683,
"step": 1925
},
{
"epoch": 2.76,
"learning_rate": 9.979016231814453e-08,
"loss": 0.0505,
"step": 1926
},
{
"epoch": 2.76,
"learning_rate": 9.863285791994769e-08,
"loss": 0.0551,
"step": 1927
},
{
"epoch": 2.76,
"learning_rate": 9.7482191401154e-08,
"loss": 0.0505,
"step": 1928
},
{
"epoch": 2.76,
"learning_rate": 9.633816539431062e-08,
"loss": 0.0528,
"step": 1929
},
{
"epoch": 2.76,
"learning_rate": 9.520078251677189e-08,
"loss": 0.0939,
"step": 1930
},
{
"epoch": 2.76,
"learning_rate": 9.407004537069396e-08,
"loss": 0.0563,
"step": 1931
},
{
"epoch": 2.76,
"learning_rate": 9.294595654302884e-08,
"loss": 0.0975,
"step": 1932
},
{
"epoch": 2.77,
"learning_rate": 9.182851860551767e-08,
"loss": 0.0617,
"step": 1933
},
{
"epoch": 2.77,
"learning_rate": 9.071773411468542e-08,
"loss": 0.0698,
"step": 1934
},
{
"epoch": 2.77,
"learning_rate": 8.961360561183595e-08,
"loss": 0.0647,
"step": 1935
},
{
"epoch": 2.77,
"learning_rate": 8.851613562304428e-08,
"loss": 0.066,
"step": 1936
},
{
"epoch": 2.77,
"learning_rate": 8.74253266591516e-08,
"loss": 0.0697,
"step": 1937
},
{
"epoch": 2.77,
"learning_rate": 8.634118121576096e-08,
"loss": 0.0528,
"step": 1938
},
{
"epoch": 2.77,
"learning_rate": 8.526370177322896e-08,
"loss": 0.0671,
"step": 1939
},
{
"epoch": 2.78,
"learning_rate": 8.41928907966617e-08,
"loss": 0.077,
"step": 1940
},
{
"epoch": 2.78,
"learning_rate": 8.312875073590953e-08,
"loss": 0.0561,
"step": 1941
},
{
"epoch": 2.78,
"learning_rate": 8.207128402556097e-08,
"loss": 0.0979,
"step": 1942
},
{
"epoch": 2.78,
"learning_rate": 8.102049308493542e-08,
"loss": 0.0818,
"step": 1943
},
{
"epoch": 2.78,
"learning_rate": 7.997638031807985e-08,
"loss": 0.0614,
"step": 1944
},
{
"epoch": 2.78,
"learning_rate": 7.893894811376379e-08,
"loss": 0.0535,
"step": 1945
},
{
"epoch": 2.78,
"learning_rate": 7.790819884547129e-08,
"loss": 0.058,
"step": 1946
},
{
"epoch": 2.79,
"learning_rate": 7.688413487139733e-08,
"loss": 0.068,
"step": 1947
},
{
"epoch": 2.79,
"learning_rate": 7.58667585344418e-08,
"loss": 0.0624,
"step": 1948
},
{
"epoch": 2.79,
"learning_rate": 7.485607216220447e-08,
"loss": 0.0858,
"step": 1949
},
{
"epoch": 2.79,
"learning_rate": 7.385207806697935e-08,
"loss": 0.0892,
"step": 1950
},
{
"epoch": 2.79,
"learning_rate": 7.285477854575007e-08,
"loss": 0.0529,
"step": 1951
},
{
"epoch": 2.79,
"learning_rate": 7.186417588018346e-08,
"loss": 0.0759,
"step": 1952
},
{
"epoch": 2.79,
"learning_rate": 7.088027233662564e-08,
"loss": 0.0788,
"step": 1953
},
{
"epoch": 2.8,
"learning_rate": 6.990307016609498e-08,
"loss": 0.0669,
"step": 1954
},
{
"epoch": 2.8,
"learning_rate": 6.89325716042798e-08,
"loss": 0.0755,
"step": 1955
},
{
"epoch": 2.8,
"learning_rate": 6.79687788715303e-08,
"loss": 0.0734,
"step": 1956
},
{
"epoch": 2.8,
"learning_rate": 6.701169417285536e-08,
"loss": 0.0418,
"step": 1957
},
{
"epoch": 2.8,
"learning_rate": 6.606131969791673e-08,
"loss": 0.0533,
"step": 1958
},
{
"epoch": 2.8,
"learning_rate": 6.511765762102385e-08,
"loss": 0.0537,
"step": 1959
},
{
"epoch": 2.8,
"learning_rate": 6.41807101011307e-08,
"loss": 0.0809,
"step": 1960
},
{
"epoch": 2.81,
"learning_rate": 6.325047928182726e-08,
"loss": 0.0653,
"step": 1961
},
{
"epoch": 2.81,
"learning_rate": 6.232696729133846e-08,
"loss": 0.0679,
"step": 1962
},
{
"epoch": 2.81,
"learning_rate": 6.141017624251655e-08,
"loss": 0.0638,
"step": 1963
},
{
"epoch": 2.81,
"learning_rate": 6.050010823283803e-08,
"loss": 0.074,
"step": 1964
},
{
"epoch": 2.81,
"learning_rate": 5.95967653443974e-08,
"loss": 0.0692,
"step": 1965
},
{
"epoch": 2.81,
"learning_rate": 5.87001496439038e-08,
"loss": 0.0791,
"step": 1966
},
{
"epoch": 2.81,
"learning_rate": 5.7810263182675685e-08,
"loss": 0.0633,
"step": 1967
},
{
"epoch": 2.82,
"learning_rate": 5.692710799663447e-08,
"loss": 0.0871,
"step": 1968
},
{
"epoch": 2.82,
"learning_rate": 5.605068610630393e-08,
"loss": 0.0528,
"step": 1969
},
{
"epoch": 2.82,
"learning_rate": 5.518099951680144e-08,
"loss": 0.0701,
"step": 1970
},
{
"epoch": 2.82,
"learning_rate": 5.431805021783509e-08,
"loss": 0.0701,
"step": 1971
},
{
"epoch": 2.82,
"learning_rate": 5.346184018369993e-08,
"loss": 0.0658,
"step": 1972
},
{
"epoch": 2.82,
"learning_rate": 5.261237137327168e-08,
"loss": 0.0783,
"step": 1973
},
{
"epoch": 2.82,
"learning_rate": 5.1769645730003754e-08,
"loss": 0.0735,
"step": 1974
},
{
"epoch": 2.83,
"learning_rate": 5.0933665181922554e-08,
"loss": 0.0435,
"step": 1975
},
{
"epoch": 2.83,
"learning_rate": 5.010443164162149e-08,
"loss": 0.0885,
"step": 1976
},
{
"epoch": 2.83,
"learning_rate": 4.928194700625965e-08,
"loss": 0.0722,
"step": 1977
},
{
"epoch": 2.83,
"learning_rate": 4.846621315755384e-08,
"loss": 0.0673,
"step": 1978
},
{
"epoch": 2.83,
"learning_rate": 4.7657231961777846e-08,
"loss": 0.0913,
"step": 1979
},
{
"epoch": 2.83,
"learning_rate": 4.68550052697545e-08,
"loss": 0.0543,
"step": 1980
},
{
"epoch": 2.83,
"learning_rate": 4.605953491685533e-08,
"loss": 0.0767,
"step": 1981
},
{
"epoch": 2.84,
"learning_rate": 4.527082272299321e-08,
"loss": 0.0836,
"step": 1982
},
{
"epoch": 2.84,
"learning_rate": 4.448887049261941e-08,
"loss": 0.0481,
"step": 1983
},
{
"epoch": 2.84,
"learning_rate": 4.37136800147202e-08,
"loss": 0.0768,
"step": 1984
},
{
"epoch": 2.84,
"learning_rate": 4.2945253062811275e-08,
"loss": 0.0836,
"step": 1985
},
{
"epoch": 2.84,
"learning_rate": 4.218359139493433e-08,
"loss": 0.0716,
"step": 1986
},
{
"epoch": 2.84,
"learning_rate": 4.142869675365446e-08,
"loss": 0.0503,
"step": 1987
},
{
"epoch": 2.84,
"learning_rate": 4.0680570866052815e-08,
"loss": 0.0448,
"step": 1988
},
{
"epoch": 2.85,
"learning_rate": 3.9939215443726584e-08,
"loss": 0.0853,
"step": 1989
},
{
"epoch": 2.85,
"learning_rate": 3.92046321827817e-08,
"loss": 0.0931,
"step": 1990
},
{
"epoch": 2.85,
"learning_rate": 3.8476822763831466e-08,
"loss": 0.0666,
"step": 1991
},
{
"epoch": 2.85,
"learning_rate": 3.775578885199127e-08,
"loss": 0.0673,
"step": 1992
},
{
"epoch": 2.85,
"learning_rate": 3.7041532096874554e-08,
"loss": 0.0663,
"step": 1993
},
{
"epoch": 2.85,
"learning_rate": 3.63340541325915e-08,
"loss": 0.0743,
"step": 1994
},
{
"epoch": 2.85,
"learning_rate": 3.563335657774169e-08,
"loss": 0.0755,
"step": 1995
},
{
"epoch": 2.86,
"learning_rate": 3.49394410354128e-08,
"loss": 0.0588,
"step": 1996
},
{
"epoch": 2.86,
"learning_rate": 3.425230909317623e-08,
"loss": 0.0735,
"step": 1997
},
{
"epoch": 2.86,
"learning_rate": 3.357196232308346e-08,
"loss": 0.0727,
"step": 1998
},
{
"epoch": 2.86,
"learning_rate": 3.2898402281663406e-08,
"loss": 0.0634,
"step": 1999
},
{
"epoch": 2.86,
"learning_rate": 3.2231630509916066e-08,
"loss": 0.0613,
"step": 2000
},
{
"epoch": 2.86,
"learning_rate": 3.157164853331351e-08,
"loss": 0.0852,
"step": 2001
},
{
"epoch": 2.86,
"learning_rate": 3.091845786179193e-08,
"loss": 0.0546,
"step": 2002
},
{
"epoch": 2.87,
"learning_rate": 3.027205998975025e-08,
"loss": 0.0691,
"step": 2003
},
{
"epoch": 2.87,
"learning_rate": 2.963245639604717e-08,
"loss": 0.0736,
"step": 2004
},
{
"epoch": 2.87,
"learning_rate": 2.8999648543996837e-08,
"loss": 0.0673,
"step": 2005
},
{
"epoch": 2.87,
"learning_rate": 2.837363788136549e-08,
"loss": 0.0532,
"step": 2006
},
{
"epoch": 2.87,
"learning_rate": 2.7754425840369135e-08,
"loss": 0.0722,
"step": 2007
},
{
"epoch": 2.87,
"learning_rate": 2.71420138376689e-08,
"loss": 0.0706,
"step": 2008
},
{
"epoch": 2.87,
"learning_rate": 2.6536403274368682e-08,
"loss": 0.0634,
"step": 2009
},
{
"epoch": 2.88,
"learning_rate": 2.5937595536011826e-08,
"loss": 0.0539,
"step": 2010
},
{
"epoch": 2.88,
"learning_rate": 2.5345591992578466e-08,
"loss": 0.0801,
"step": 2011
},
{
"epoch": 2.88,
"learning_rate": 2.4760393998480513e-08,
"loss": 0.0705,
"step": 2012
},
{
"epoch": 2.88,
"learning_rate": 2.418200289256034e-08,
"loss": 0.0689,
"step": 2013
},
{
"epoch": 2.88,
"learning_rate": 2.3610419998087773e-08,
"loss": 0.0735,
"step": 2014
},
{
"epoch": 2.88,
"learning_rate": 2.30456466227561e-08,
"loss": 0.0808,
"step": 2015
},
{
"epoch": 2.88,
"learning_rate": 2.2487684058679403e-08,
"loss": 0.0628,
"step": 2016
},
{
"epoch": 2.89,
"learning_rate": 2.1936533582389894e-08,
"loss": 0.0714,
"step": 2017
},
{
"epoch": 2.89,
"learning_rate": 2.1392196454834256e-08,
"loss": 0.0782,
"step": 2018
},
{
"epoch": 2.89,
"learning_rate": 2.085467392137197e-08,
"loss": 0.0766,
"step": 2019
},
{
"epoch": 2.89,
"learning_rate": 2.0323967211771323e-08,
"loss": 0.0507,
"step": 2020
},
{
"epoch": 2.89,
"learning_rate": 1.9800077540207405e-08,
"loss": 0.07,
"step": 2021
},
{
"epoch": 2.89,
"learning_rate": 1.928300610525846e-08,
"loss": 0.0641,
"step": 2022
},
{
"epoch": 2.89,
"learning_rate": 1.877275408990453e-08,
"loss": 0.0628,
"step": 2023
},
{
"epoch": 2.9,
"learning_rate": 1.8269322661522815e-08,
"loss": 0.0734,
"step": 2024
},
{
"epoch": 2.9,
"learning_rate": 1.777271297188632e-08,
"loss": 0.0667,
"step": 2025
},
{
"epoch": 2.9,
"learning_rate": 1.7282926157162205e-08,
"loss": 0.0704,
"step": 2026
},
{
"epoch": 2.9,
"learning_rate": 1.6799963337906122e-08,
"loss": 0.061,
"step": 2027
},
{
"epoch": 2.9,
"learning_rate": 1.6323825619062872e-08,
"loss": 0.0596,
"step": 2028
},
{
"epoch": 2.9,
"learning_rate": 1.5854514089961747e-08,
"loss": 0.0711,
"step": 2029
},
{
"epoch": 2.9,
"learning_rate": 1.5392029824314537e-08,
"loss": 0.079,
"step": 2030
},
{
"epoch": 2.91,
"learning_rate": 1.493637388021418e-08,
"loss": 0.0674,
"step": 2031
},
{
"epoch": 2.91,
"learning_rate": 1.4487547300131131e-08,
"loss": 0.0453,
"step": 2032
},
{
"epoch": 2.91,
"learning_rate": 1.4045551110910992e-08,
"loss": 0.08,
"step": 2033
},
{
"epoch": 2.91,
"learning_rate": 1.3610386323772539e-08,
"loss": 0.068,
"step": 2034
},
{
"epoch": 2.91,
"learning_rate": 1.3182053934305715e-08,
"loss": 0.0695,
"step": 2035
},
{
"epoch": 2.91,
"learning_rate": 1.276055492246897e-08,
"loss": 0.0892,
"step": 2036
},
{
"epoch": 2.91,
"learning_rate": 1.2345890252586255e-08,
"loss": 0.062,
"step": 2037
},
{
"epoch": 2.92,
"learning_rate": 1.1938060873347035e-08,
"loss": 0.0911,
"step": 2038
},
{
"epoch": 2.92,
"learning_rate": 1.1537067717801275e-08,
"loss": 0.0818,
"step": 2039
},
{
"epoch": 2.92,
"learning_rate": 1.1142911703359793e-08,
"loss": 0.0537,
"step": 2040
},
{
"epoch": 2.92,
"learning_rate": 1.0755593731789914e-08,
"loss": 0.0755,
"step": 2041
},
{
"epoch": 2.92,
"learning_rate": 1.0375114689215815e-08,
"loss": 0.0696,
"step": 2042
},
{
"epoch": 2.92,
"learning_rate": 1.000147544611485e-08,
"loss": 0.0783,
"step": 2043
},
{
"epoch": 2.92,
"learning_rate": 9.634676857315561e-09,
"loss": 0.0628,
"step": 2044
},
{
"epoch": 2.93,
"learning_rate": 9.27471976199601e-09,
"loss": 0.0777,
"step": 2045
},
{
"epoch": 2.93,
"learning_rate": 8.921604983682774e-09,
"loss": 0.0629,
"step": 2046
},
{
"epoch": 2.93,
"learning_rate": 8.575333330248292e-09,
"loss": 0.0712,
"step": 2047
},
{
"epoch": 2.93,
"learning_rate": 8.235905593907856e-09,
"loss": 0.0818,
"step": 2048
},
{
"epoch": 2.93,
"learning_rate": 7.90332255121995e-09,
"loss": 0.0816,
"step": 2049
},
{
"epoch": 2.93,
"learning_rate": 7.577584963082918e-09,
"loss": 0.0683,
"step": 2050
},
{
"epoch": 2.93,
"learning_rate": 7.2586935747346316e-09,
"loss": 0.0864,
"step": 2051
},
{
"epoch": 2.94,
"learning_rate": 6.946649115748493e-09,
"loss": 0.0609,
"step": 2052
},
{
"epoch": 2.94,
"learning_rate": 6.641452300034434e-09,
"loss": 0.0661,
"step": 2053
},
{
"epoch": 2.94,
"learning_rate": 6.343103825835584e-09,
"loss": 0.0715,
"step": 2054
},
{
"epoch": 2.94,
"learning_rate": 6.051604375726938e-09,
"loss": 0.0625,
"step": 2055
},
{
"epoch": 2.94,
"learning_rate": 5.7669546166140285e-09,
"loss": 0.0671,
"step": 2056
},
{
"epoch": 2.94,
"learning_rate": 5.489155199731921e-09,
"loss": 0.0644,
"step": 2057
},
{
"epoch": 2.94,
"learning_rate": 5.218206760642552e-09,
"loss": 0.0628,
"step": 2058
},
{
"epoch": 2.95,
"learning_rate": 4.954109919233729e-09,
"loss": 0.0744,
"step": 2059
},
{
"epoch": 2.95,
"learning_rate": 4.6968652797187985e-09,
"loss": 0.0701,
"step": 2060
},
{
"epoch": 2.95,
"learning_rate": 4.446473430633313e-09,
"loss": 0.0612,
"step": 2061
},
{
"epoch": 2.95,
"learning_rate": 4.202934944835035e-09,
"loss": 0.0708,
"step": 2062
},
{
"epoch": 2.95,
"learning_rate": 3.9662503795026e-09,
"loss": 0.0871,
"step": 2063
},
{
"epoch": 2.95,
"learning_rate": 3.736420276133523e-09,
"loss": 0.0664,
"step": 2064
},
{
"epoch": 2.95,
"learning_rate": 3.51344516054386e-09,
"loss": 0.0612,
"step": 2065
},
{
"epoch": 2.96,
"learning_rate": 3.297325542865881e-09,
"loss": 0.06,
"step": 2066
},
{
"epoch": 2.96,
"learning_rate": 3.0880619175477355e-09,
"loss": 0.065,
"step": 2067
},
{
"epoch": 2.96,
"learning_rate": 2.885654763352452e-09,
"loss": 0.0719,
"step": 2068
},
{
"epoch": 2.96,
"learning_rate": 2.6901045433566084e-09,
"loss": 0.0885,
"step": 2069
},
{
"epoch": 2.96,
"learning_rate": 2.501411704948331e-09,
"loss": 0.0731,
"step": 2070
},
{
"epoch": 2.96,
"learning_rate": 2.319576679827962e-09,
"loss": 0.0576,
"step": 2071
},
{
"epoch": 2.96,
"learning_rate": 2.144599884005727e-09,
"loss": 0.0689,
"step": 2072
},
{
"epoch": 2.97,
"learning_rate": 1.976481717801737e-09,
"loss": 0.0687,
"step": 2073
},
{
"epoch": 2.97,
"learning_rate": 1.815222565844321e-09,
"loss": 0.0654,
"step": 2074
},
{
"epoch": 2.97,
"learning_rate": 1.6608227970690281e-09,
"loss": 0.0865,
"step": 2075
},
{
"epoch": 2.97,
"learning_rate": 1.5132827647192925e-09,
"loss": 0.0795,
"step": 2076
},
{
"epoch": 2.97,
"learning_rate": 1.3726028063437702e-09,
"loss": 0.0838,
"step": 2077
},
{
"epoch": 2.97,
"learning_rate": 1.2387832437960045e-09,
"loss": 0.0583,
"step": 2078
},
{
"epoch": 2.97,
"learning_rate": 1.1118243832347608e-09,
"loss": 0.0471,
"step": 2079
},
{
"epoch": 2.98,
"learning_rate": 9.917265151223598e-10,
"loss": 0.0689,
"step": 2080
},
{
"epoch": 2.98,
"learning_rate": 8.784899142243453e-10,
"loss": 0.0611,
"step": 2081
},
{
"epoch": 2.98,
"learning_rate": 7.721148396078181e-10,
"loss": 0.0563,
"step": 2082
},
{
"epoch": 2.98,
"learning_rate": 6.726015346431024e-10,
"loss": 0.0671,
"step": 2083
},
{
"epoch": 2.98,
"learning_rate": 5.799502270014135e-10,
"loss": 0.0687,
"step": 2084
},
{
"epoch": 2.98,
"learning_rate": 4.941611286538583e-10,
"loss": 0.0647,
"step": 2085
},
{
"epoch": 2.98,
"learning_rate": 4.1523443587343503e-10,
"loss": 0.0841,
"step": 2086
},
{
"epoch": 2.99,
"learning_rate": 3.4317032923170124e-10,
"loss": 0.0625,
"step": 2087
},
{
"epoch": 2.99,
"learning_rate": 2.7796897360043983e-10,
"loss": 0.0589,
"step": 2088
},
{
"epoch": 2.99,
"learning_rate": 2.196305181499936e-10,
"loss": 0.0764,
"step": 2089
},
{
"epoch": 2.99,
"learning_rate": 1.6815509635026426e-10,
"loss": 0.0734,
"step": 2090
},
{
"epoch": 2.99,
"learning_rate": 1.235428259683813e-10,
"loss": 0.0683,
"step": 2091
},
{
"epoch": 2.99,
"learning_rate": 8.579380907103307e-11,
"loss": 0.0752,
"step": 2092
},
{
"epoch": 2.99,
"learning_rate": 5.4908132021469494e-11,
"loss": 0.0711,
"step": 2093
},
{
"epoch": 3.0,
"learning_rate": 3.08858654815003e-11,
"loss": 0.0804,
"step": 2094
},
{
"epoch": 3.0,
"learning_rate": 1.3727064410828937e-11,
"loss": 0.0573,
"step": 2095
},
{
"epoch": 3.0,
"learning_rate": 3.431768065387253e-12,
"loss": 0.0624,
"step": 2096
},
{
"epoch": 3.0,
"learning_rate": 0.0,
"loss": 0.0818,
"step": 2097
}
],
"logging_steps": 1,
"max_steps": 2097,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 4.405607909208097e+18,
"trial_name": null,
"trial_params": null
}