7B-XXL / checkpoint-1058 /trainer_state.json
Chat-Error's picture
Upload folder using huggingface_hub
a7e026c verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.2503401360544218,
"eval_steps": 500,
"global_step": 1058,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5e-06,
"loss": 2.2147,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 2.4802,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.5e-05,
"loss": 2.0475,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2e-05,
"loss": 1.6983,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 2.5e-05,
"loss": 1.6212,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 3e-05,
"loss": 2.0843,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 3.5e-05,
"loss": 1.8442,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 4e-05,
"loss": 1.3359,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 4.5e-05,
"loss": 2.3761,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 5e-05,
"loss": 1.6338,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 4.999999826891235e-05,
"loss": 1.7487,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 4.999999307564964e-05,
"loss": 2.0834,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 4.9999984420212596e-05,
"loss": 1.5794,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 4.999997230260242e-05,
"loss": 1.7222,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 4.9999956722820765e-05,
"loss": 1.4002,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 4.999993768086981e-05,
"loss": 1.7314,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 4.999991517675219e-05,
"loss": 1.7053,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 4.999988921047102e-05,
"loss": 1.9546,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 4.99998597820299e-05,
"loss": 1.6122,
"step": 19
},
{
"epoch": 0.0,
"learning_rate": 4.9999826891432896e-05,
"loss": 1.7275,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 4.999979053868456e-05,
"loss": 1.8279,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 4.9999750723789936e-05,
"loss": 1.6764,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 4.9999707446754546e-05,
"loss": 1.7501,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 4.999966070758437e-05,
"loss": 1.6349,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 4.999961050628588e-05,
"loss": 1.6796,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 4.9999556842866034e-05,
"loss": 1.6249,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 4.999949971733225e-05,
"loss": 2.0866,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 4.999943912969247e-05,
"loss": 1.6658,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 4.999937507995506e-05,
"loss": 1.7794,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 4.999930756812889e-05,
"loss": 1.743,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 4.999923659422332e-05,
"loss": 2.1359,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 4.999916215824817e-05,
"loss": 1.7393,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 4.999908426021375e-05,
"loss": 1.6387,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 4.999900290013085e-05,
"loss": 1.974,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 4.999891807801075e-05,
"loss": 1.7787,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 4.9998829793865176e-05,
"loss": 2.1738,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 4.999873804770636e-05,
"loss": 1.73,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 4.999864283954701e-05,
"loss": 1.9363,
"step": 38
},
{
"epoch": 0.01,
"learning_rate": 4.999854416940032e-05,
"loss": 1.248,
"step": 39
},
{
"epoch": 0.01,
"learning_rate": 4.999844203727993e-05,
"loss": 2.0461,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 4.999833644320002e-05,
"loss": 2.1294,
"step": 41
},
{
"epoch": 0.01,
"learning_rate": 4.999822738717518e-05,
"loss": 1.3963,
"step": 42
},
{
"epoch": 0.01,
"learning_rate": 4.9998114869220525e-05,
"loss": 1.7942,
"step": 43
},
{
"epoch": 0.01,
"learning_rate": 4.999799888935164e-05,
"loss": 1.4804,
"step": 44
},
{
"epoch": 0.01,
"learning_rate": 4.99978794475846e-05,
"loss": 1.4482,
"step": 45
},
{
"epoch": 0.01,
"learning_rate": 4.999775654393591e-05,
"loss": 1.0604,
"step": 46
},
{
"epoch": 0.01,
"learning_rate": 4.9997630178422624e-05,
"loss": 1.6902,
"step": 47
},
{
"epoch": 0.01,
"learning_rate": 4.999750035106222e-05,
"loss": 1.4982,
"step": 48
},
{
"epoch": 0.01,
"learning_rate": 4.9997367061872694e-05,
"loss": 2.0546,
"step": 49
},
{
"epoch": 0.01,
"learning_rate": 4.99972303108725e-05,
"loss": 1.581,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 4.999709009808057e-05,
"loss": 1.4683,
"step": 51
},
{
"epoch": 0.01,
"learning_rate": 4.9996946423516326e-05,
"loss": 1.9496,
"step": 52
},
{
"epoch": 0.01,
"learning_rate": 4.9996799287199666e-05,
"loss": 1.3316,
"step": 53
},
{
"epoch": 0.01,
"learning_rate": 4.9996648689150966e-05,
"loss": 2.0274,
"step": 54
},
{
"epoch": 0.01,
"learning_rate": 4.9996494629391076e-05,
"loss": 2.1621,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 4.999633710794135e-05,
"loss": 1.6314,
"step": 56
},
{
"epoch": 0.01,
"learning_rate": 4.999617612482358e-05,
"loss": 1.8074,
"step": 57
},
{
"epoch": 0.01,
"learning_rate": 4.9996011680060064e-05,
"loss": 1.8467,
"step": 58
},
{
"epoch": 0.01,
"learning_rate": 4.999584377367359e-05,
"loss": 1.2585,
"step": 59
},
{
"epoch": 0.01,
"learning_rate": 4.99956724056874e-05,
"loss": 1.8106,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 4.9995497576125225e-05,
"loss": 1.7955,
"step": 61
},
{
"epoch": 0.01,
"learning_rate": 4.999531928501128e-05,
"loss": 1.9608,
"step": 62
},
{
"epoch": 0.01,
"learning_rate": 4.999513753237025e-05,
"loss": 2.1124,
"step": 63
},
{
"epoch": 0.02,
"learning_rate": 4.999495231822732e-05,
"loss": 1.8793,
"step": 64
},
{
"epoch": 0.02,
"learning_rate": 4.999476364260812e-05,
"loss": 1.6794,
"step": 65
},
{
"epoch": 0.02,
"learning_rate": 4.99945715055388e-05,
"loss": 1.7991,
"step": 66
},
{
"epoch": 0.02,
"learning_rate": 4.999437590704595e-05,
"loss": 2.0194,
"step": 67
},
{
"epoch": 0.02,
"learning_rate": 4.999417684715668e-05,
"loss": 1.4938,
"step": 68
},
{
"epoch": 0.02,
"learning_rate": 4.999397432589853e-05,
"loss": 1.9159,
"step": 69
},
{
"epoch": 0.02,
"learning_rate": 4.999376834329956e-05,
"loss": 1.3969,
"step": 70
},
{
"epoch": 0.02,
"learning_rate": 4.9993558899388305e-05,
"loss": 1.727,
"step": 71
},
{
"epoch": 0.02,
"learning_rate": 4.999334599419375e-05,
"loss": 1.8063,
"step": 72
},
{
"epoch": 0.02,
"learning_rate": 4.99931296277454e-05,
"loss": 1.9437,
"step": 73
},
{
"epoch": 0.02,
"learning_rate": 4.999290980007321e-05,
"loss": 1.5978,
"step": 74
},
{
"epoch": 0.02,
"learning_rate": 4.9992686511207614e-05,
"loss": 1.9653,
"step": 75
},
{
"epoch": 0.02,
"learning_rate": 4.9992459761179545e-05,
"loss": 2.2229,
"step": 76
},
{
"epoch": 0.02,
"learning_rate": 4.999222955002041e-05,
"loss": 1.7991,
"step": 77
},
{
"epoch": 0.02,
"learning_rate": 4.9991995877762074e-05,
"loss": 2.0293,
"step": 78
},
{
"epoch": 0.02,
"learning_rate": 4.999175874443692e-05,
"loss": 1.5131,
"step": 79
},
{
"epoch": 0.02,
"learning_rate": 4.9991518150077765e-05,
"loss": 1.41,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 4.999127409471794e-05,
"loss": 2.0329,
"step": 81
},
{
"epoch": 0.02,
"learning_rate": 4.9991026578391245e-05,
"loss": 1.7566,
"step": 82
},
{
"epoch": 0.02,
"learning_rate": 4.999077560113196e-05,
"loss": 2.1238,
"step": 83
},
{
"epoch": 0.02,
"learning_rate": 4.9990521162974824e-05,
"loss": 1.4365,
"step": 84
},
{
"epoch": 0.02,
"learning_rate": 4.999026326395509e-05,
"loss": 1.7559,
"step": 85
},
{
"epoch": 0.02,
"learning_rate": 4.999000190410848e-05,
"loss": 2.3886,
"step": 86
},
{
"epoch": 0.02,
"learning_rate": 4.998973708347116e-05,
"loss": 1.5783,
"step": 87
},
{
"epoch": 0.02,
"learning_rate": 4.998946880207983e-05,
"loss": 2.0597,
"step": 88
},
{
"epoch": 0.02,
"learning_rate": 4.998919705997164e-05,
"loss": 1.684,
"step": 89
},
{
"epoch": 0.02,
"learning_rate": 4.998892185718422e-05,
"loss": 1.5005,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 4.998864319375568e-05,
"loss": 1.8982,
"step": 91
},
{
"epoch": 0.02,
"learning_rate": 4.998836106972461e-05,
"loss": 2.4997,
"step": 92
},
{
"epoch": 0.02,
"learning_rate": 4.998807548513008e-05,
"loss": 1.9038,
"step": 93
},
{
"epoch": 0.02,
"learning_rate": 4.998778644001165e-05,
"loss": 1.4326,
"step": 94
},
{
"epoch": 0.02,
"learning_rate": 4.998749393440933e-05,
"loss": 1.9809,
"step": 95
},
{
"epoch": 0.02,
"learning_rate": 4.998719796836366e-05,
"loss": 1.727,
"step": 96
},
{
"epoch": 0.02,
"learning_rate": 4.9986898541915595e-05,
"loss": 1.5198,
"step": 97
},
{
"epoch": 0.02,
"learning_rate": 4.998659565510662e-05,
"loss": 1.7004,
"step": 98
},
{
"epoch": 0.02,
"learning_rate": 4.998628930797866e-05,
"loss": 1.7584,
"step": 99
},
{
"epoch": 0.02,
"learning_rate": 4.9985979500574166e-05,
"loss": 1.7247,
"step": 100
},
{
"epoch": 0.02,
"learning_rate": 4.998566623293603e-05,
"loss": 1.7967,
"step": 101
},
{
"epoch": 0.02,
"learning_rate": 4.998534950510764e-05,
"loss": 1.282,
"step": 102
},
{
"epoch": 0.02,
"learning_rate": 4.9985029317132845e-05,
"loss": 1.7519,
"step": 103
},
{
"epoch": 0.02,
"learning_rate": 4.998470566905601e-05,
"loss": 1.8924,
"step": 104
},
{
"epoch": 0.02,
"learning_rate": 4.9984378560921937e-05,
"loss": 1.411,
"step": 105
},
{
"epoch": 0.03,
"learning_rate": 4.9984047992775926e-05,
"loss": 1.7251,
"step": 106
},
{
"epoch": 0.03,
"learning_rate": 4.9983713964663776e-05,
"loss": 1.6784,
"step": 107
},
{
"epoch": 0.03,
"learning_rate": 4.998337647663173e-05,
"loss": 1.9045,
"step": 108
},
{
"epoch": 0.03,
"learning_rate": 4.998303552872652e-05,
"loss": 1.1327,
"step": 109
},
{
"epoch": 0.03,
"learning_rate": 4.998269112099538e-05,
"loss": 1.6382,
"step": 110
},
{
"epoch": 0.03,
"learning_rate": 4.998234325348599e-05,
"loss": 1.8228,
"step": 111
},
{
"epoch": 0.03,
"learning_rate": 4.998199192624654e-05,
"loss": 1.9773,
"step": 112
},
{
"epoch": 0.03,
"learning_rate": 4.998163713932567e-05,
"loss": 1.6035,
"step": 113
},
{
"epoch": 0.03,
"learning_rate": 4.998127889277252e-05,
"loss": 2.3095,
"step": 114
},
{
"epoch": 0.03,
"learning_rate": 4.998091718663671e-05,
"loss": 1.4727,
"step": 115
},
{
"epoch": 0.03,
"learning_rate": 4.998055202096832e-05,
"loss": 1.8166,
"step": 116
},
{
"epoch": 0.03,
"learning_rate": 4.998018339581792e-05,
"loss": 1.2842,
"step": 117
},
{
"epoch": 0.03,
"learning_rate": 4.997981131123657e-05,
"loss": 1.8485,
"step": 118
},
{
"epoch": 0.03,
"learning_rate": 4.997943576727579e-05,
"loss": 1.1914,
"step": 119
},
{
"epoch": 0.03,
"learning_rate": 4.997905676398759e-05,
"loss": 1.9409,
"step": 120
},
{
"epoch": 0.03,
"learning_rate": 4.997867430142446e-05,
"loss": 2.3757,
"step": 121
},
{
"epoch": 0.03,
"learning_rate": 4.997828837963937e-05,
"loss": 1.6337,
"step": 122
},
{
"epoch": 0.03,
"learning_rate": 4.997789899868575e-05,
"loss": 1.5789,
"step": 123
},
{
"epoch": 0.03,
"learning_rate": 4.9977506158617535e-05,
"loss": 1.61,
"step": 124
},
{
"epoch": 0.03,
"learning_rate": 4.9977109859489133e-05,
"loss": 1.3976,
"step": 125
},
{
"epoch": 0.03,
"learning_rate": 4.997671010135542e-05,
"loss": 1.3944,
"step": 126
},
{
"epoch": 0.03,
"learning_rate": 4.997630688427176e-05,
"loss": 1.5922,
"step": 127
},
{
"epoch": 0.03,
"learning_rate": 4.9975900208293984e-05,
"loss": 2.0075,
"step": 128
},
{
"epoch": 0.03,
"learning_rate": 4.997549007347842e-05,
"loss": 1.4363,
"step": 129
},
{
"epoch": 0.03,
"learning_rate": 4.9975076479881864e-05,
"loss": 1.9972,
"step": 130
},
{
"epoch": 0.03,
"learning_rate": 4.99746594275616e-05,
"loss": 1.8052,
"step": 131
},
{
"epoch": 0.03,
"learning_rate": 4.997423891657538e-05,
"loss": 1.9088,
"step": 132
},
{
"epoch": 0.03,
"learning_rate": 4.997381494698143e-05,
"loss": 1.7322,
"step": 133
},
{
"epoch": 0.03,
"learning_rate": 4.9973387518838474e-05,
"loss": 1.6391,
"step": 134
},
{
"epoch": 0.03,
"learning_rate": 4.9972956632205704e-05,
"loss": 1.8346,
"step": 135
},
{
"epoch": 0.03,
"learning_rate": 4.997252228714279e-05,
"loss": 1.9651,
"step": 136
},
{
"epoch": 0.03,
"learning_rate": 4.997208448370988e-05,
"loss": 1.5544,
"step": 137
},
{
"epoch": 0.03,
"learning_rate": 4.997164322196762e-05,
"loss": 1.4443,
"step": 138
},
{
"epoch": 0.03,
"learning_rate": 4.99711985019771e-05,
"loss": 2.1679,
"step": 139
},
{
"epoch": 0.03,
"learning_rate": 4.997075032379992e-05,
"loss": 1.6557,
"step": 140
},
{
"epoch": 0.03,
"learning_rate": 4.997029868749813e-05,
"loss": 1.5759,
"step": 141
},
{
"epoch": 0.03,
"learning_rate": 4.99698435931343e-05,
"loss": 1.8057,
"step": 142
},
{
"epoch": 0.03,
"learning_rate": 4.9969385040771445e-05,
"loss": 1.1004,
"step": 143
},
{
"epoch": 0.03,
"learning_rate": 4.996892303047306e-05,
"loss": 1.6915,
"step": 144
},
{
"epoch": 0.03,
"learning_rate": 4.996845756230314e-05,
"loss": 1.7905,
"step": 145
},
{
"epoch": 0.03,
"learning_rate": 4.9967988636326136e-05,
"loss": 2.0294,
"step": 146
},
{
"epoch": 0.03,
"learning_rate": 4.996751625260699e-05,
"loss": 1.9933,
"step": 147
},
{
"epoch": 0.04,
"learning_rate": 4.996704041121113e-05,
"loss": 1.5048,
"step": 148
},
{
"epoch": 0.04,
"learning_rate": 4.996656111220443e-05,
"loss": 2.0881,
"step": 149
},
{
"epoch": 0.04,
"learning_rate": 4.996607835565331e-05,
"loss": 1.3425,
"step": 150
},
{
"epoch": 0.04,
"learning_rate": 4.9965592141624586e-05,
"loss": 1.3072,
"step": 151
},
{
"epoch": 0.04,
"learning_rate": 4.9965102470185596e-05,
"loss": 2.5566,
"step": 152
},
{
"epoch": 0.04,
"learning_rate": 4.9964609341404175e-05,
"loss": 1.3695,
"step": 153
},
{
"epoch": 0.04,
"learning_rate": 4.99641127553486e-05,
"loss": 2.0205,
"step": 154
},
{
"epoch": 0.04,
"learning_rate": 4.9963612712087646e-05,
"loss": 2.1791,
"step": 155
},
{
"epoch": 0.04,
"learning_rate": 4.996310921169056e-05,
"loss": 1.6322,
"step": 156
},
{
"epoch": 0.04,
"learning_rate": 4.996260225422707e-05,
"loss": 1.8695,
"step": 157
},
{
"epoch": 0.04,
"learning_rate": 4.9962091839767386e-05,
"loss": 2.1406,
"step": 158
},
{
"epoch": 0.04,
"learning_rate": 4.99615779683822e-05,
"loss": 1.7668,
"step": 159
},
{
"epoch": 0.04,
"learning_rate": 4.996106064014265e-05,
"loss": 1.6439,
"step": 160
},
{
"epoch": 0.04,
"learning_rate": 4.9960539855120415e-05,
"loss": 1.5069,
"step": 161
},
{
"epoch": 0.04,
"learning_rate": 4.996001561338759e-05,
"loss": 1.9099,
"step": 162
},
{
"epoch": 0.04,
"learning_rate": 4.995948791501679e-05,
"loss": 1.5446,
"step": 163
},
{
"epoch": 0.04,
"learning_rate": 4.9958956760081085e-05,
"loss": 1.8427,
"step": 164
},
{
"epoch": 0.04,
"learning_rate": 4.9958422148654045e-05,
"loss": 1.4109,
"step": 165
},
{
"epoch": 0.04,
"learning_rate": 4.995788408080969e-05,
"loss": 1.7544,
"step": 166
},
{
"epoch": 0.04,
"learning_rate": 4.9957342556622557e-05,
"loss": 1.2727,
"step": 167
},
{
"epoch": 0.04,
"learning_rate": 4.995679757616762e-05,
"loss": 1.4266,
"step": 168
},
{
"epoch": 0.04,
"learning_rate": 4.995624913952036e-05,
"loss": 1.3209,
"step": 169
},
{
"epoch": 0.04,
"learning_rate": 4.995569724675673e-05,
"loss": 1.5993,
"step": 170
},
{
"epoch": 0.04,
"learning_rate": 4.995514189795316e-05,
"loss": 1.8296,
"step": 171
},
{
"epoch": 0.04,
"learning_rate": 4.9954583093186544e-05,
"loss": 1.5827,
"step": 172
},
{
"epoch": 0.04,
"learning_rate": 4.9954020832534296e-05,
"loss": 1.6316,
"step": 173
},
{
"epoch": 0.04,
"learning_rate": 4.9953455116074263e-05,
"loss": 1.7216,
"step": 174
},
{
"epoch": 0.04,
"learning_rate": 4.9952885943884795e-05,
"loss": 1.7878,
"step": 175
},
{
"epoch": 0.04,
"learning_rate": 4.995231331604472e-05,
"loss": 1.7959,
"step": 176
},
{
"epoch": 0.04,
"learning_rate": 4.995173723263332e-05,
"loss": 1.4636,
"step": 177
},
{
"epoch": 0.04,
"learning_rate": 4.99511576937304e-05,
"loss": 1.365,
"step": 178
},
{
"epoch": 0.04,
"learning_rate": 4.995057469941621e-05,
"loss": 1.9666,
"step": 179
},
{
"epoch": 0.04,
"learning_rate": 4.994998824977147e-05,
"loss": 1.4686,
"step": 180
},
{
"epoch": 0.04,
"learning_rate": 4.994939834487742e-05,
"loss": 1.4651,
"step": 181
},
{
"epoch": 0.04,
"learning_rate": 4.994880498481575e-05,
"loss": 1.8047,
"step": 182
},
{
"epoch": 0.04,
"learning_rate": 4.9948208169668606e-05,
"loss": 1.779,
"step": 183
},
{
"epoch": 0.04,
"learning_rate": 4.9947607899518675e-05,
"loss": 1.172,
"step": 184
},
{
"epoch": 0.04,
"learning_rate": 4.994700417444908e-05,
"loss": 1.6413,
"step": 185
},
{
"epoch": 0.04,
"learning_rate": 4.9946396994543405e-05,
"loss": 2.0329,
"step": 186
},
{
"epoch": 0.04,
"learning_rate": 4.994578635988576e-05,
"loss": 1.8365,
"step": 187
},
{
"epoch": 0.04,
"learning_rate": 4.9945172270560695e-05,
"loss": 1.8724,
"step": 188
},
{
"epoch": 0.04,
"learning_rate": 4.994455472665327e-05,
"loss": 1.7607,
"step": 189
},
{
"epoch": 0.04,
"learning_rate": 4.9943933728248996e-05,
"loss": 1.6619,
"step": 190
},
{
"epoch": 0.05,
"learning_rate": 4.994330927543387e-05,
"loss": 1.9951,
"step": 191
},
{
"epoch": 0.05,
"learning_rate": 4.994268136829438e-05,
"loss": 1.5133,
"step": 192
},
{
"epoch": 0.05,
"learning_rate": 4.994205000691747e-05,
"loss": 2.238,
"step": 193
},
{
"epoch": 0.05,
"learning_rate": 4.994141519139058e-05,
"loss": 1.6153,
"step": 194
},
{
"epoch": 0.05,
"learning_rate": 4.994077692180164e-05,
"loss": 1.2494,
"step": 195
},
{
"epoch": 0.05,
"learning_rate": 4.9940135198239024e-05,
"loss": 1.7389,
"step": 196
},
{
"epoch": 0.05,
"learning_rate": 4.9939490020791614e-05,
"loss": 1.2335,
"step": 197
},
{
"epoch": 0.05,
"learning_rate": 4.993884138954875e-05,
"loss": 1.4512,
"step": 198
},
{
"epoch": 0.05,
"learning_rate": 4.993818930460026e-05,
"loss": 1.8298,
"step": 199
},
{
"epoch": 0.05,
"learning_rate": 4.993753376603645e-05,
"loss": 1.333,
"step": 200
},
{
"epoch": 0.05,
"learning_rate": 4.9936874773948094e-05,
"loss": 1.8395,
"step": 201
},
{
"epoch": 0.05,
"learning_rate": 4.993621232842648e-05,
"loss": 1.7438,
"step": 202
},
{
"epoch": 0.05,
"learning_rate": 4.993554642956332e-05,
"loss": 1.2777,
"step": 203
},
{
"epoch": 0.05,
"learning_rate": 4.993487707745086e-05,
"loss": 1.5628,
"step": 204
},
{
"epoch": 0.05,
"learning_rate": 4.9934204272181764e-05,
"loss": 1.6458,
"step": 205
},
{
"epoch": 0.05,
"learning_rate": 4.9933528013849235e-05,
"loss": 1.3878,
"step": 206
},
{
"epoch": 0.05,
"learning_rate": 4.993284830254691e-05,
"loss": 1.6489,
"step": 207
},
{
"epoch": 0.05,
"learning_rate": 4.993216513836893e-05,
"loss": 1.4492,
"step": 208
},
{
"epoch": 0.05,
"learning_rate": 4.9931478521409895e-05,
"loss": 1.598,
"step": 209
},
{
"epoch": 0.05,
"learning_rate": 4.99307884517649e-05,
"loss": 1.9357,
"step": 210
},
{
"epoch": 0.05,
"learning_rate": 4.9930094929529506e-05,
"loss": 1.4987,
"step": 211
},
{
"epoch": 0.05,
"learning_rate": 4.992939795479976e-05,
"loss": 1.6394,
"step": 212
},
{
"epoch": 0.05,
"learning_rate": 4.992869752767218e-05,
"loss": 2.1398,
"step": 213
},
{
"epoch": 0.05,
"learning_rate": 4.992799364824377e-05,
"loss": 1.4962,
"step": 214
},
{
"epoch": 0.05,
"learning_rate": 4.992728631661201e-05,
"loss": 1.1668,
"step": 215
},
{
"epoch": 0.05,
"learning_rate": 4.9926575532874847e-05,
"loss": 1.3898,
"step": 216
},
{
"epoch": 0.05,
"learning_rate": 4.9925861297130724e-05,
"loss": 1.828,
"step": 217
},
{
"epoch": 0.05,
"learning_rate": 4.992514360947855e-05,
"loss": 1.4453,
"step": 218
},
{
"epoch": 0.05,
"learning_rate": 4.9924422470017715e-05,
"loss": 1.774,
"step": 219
},
{
"epoch": 0.05,
"learning_rate": 4.992369787884809e-05,
"loss": 2.0532,
"step": 220
},
{
"epoch": 0.05,
"learning_rate": 4.992296983607002e-05,
"loss": 1.881,
"step": 221
},
{
"epoch": 0.05,
"learning_rate": 4.992223834178433e-05,
"loss": 1.7959,
"step": 222
},
{
"epoch": 0.05,
"learning_rate": 4.992150339609232e-05,
"loss": 2.1218,
"step": 223
},
{
"epoch": 0.05,
"learning_rate": 4.992076499909578e-05,
"loss": 1.9065,
"step": 224
},
{
"epoch": 0.05,
"learning_rate": 4.992002315089695e-05,
"loss": 1.783,
"step": 225
},
{
"epoch": 0.05,
"learning_rate": 4.9919277851598575e-05,
"loss": 1.5766,
"step": 226
},
{
"epoch": 0.05,
"learning_rate": 4.991852910130388e-05,
"loss": 1.2045,
"step": 227
},
{
"epoch": 0.05,
"learning_rate": 4.9917776900116556e-05,
"loss": 1.7663,
"step": 228
},
{
"epoch": 0.05,
"learning_rate": 4.991702124814075e-05,
"loss": 1.6417,
"step": 229
},
{
"epoch": 0.05,
"learning_rate": 4.991626214548113e-05,
"loss": 1.6406,
"step": 230
},
{
"epoch": 0.05,
"learning_rate": 4.991549959224282e-05,
"loss": 1.9329,
"step": 231
},
{
"epoch": 0.05,
"learning_rate": 4.991473358853142e-05,
"loss": 2.0136,
"step": 232
},
{
"epoch": 0.06,
"learning_rate": 4.9913964134453014e-05,
"loss": 1.4504,
"step": 233
},
{
"epoch": 0.06,
"learning_rate": 4.9913191230114156e-05,
"loss": 1.9222,
"step": 234
},
{
"epoch": 0.06,
"learning_rate": 4.991241487562189e-05,
"loss": 1.9192,
"step": 235
},
{
"epoch": 0.06,
"learning_rate": 4.991163507108373e-05,
"loss": 1.5397,
"step": 236
},
{
"epoch": 0.06,
"learning_rate": 4.991085181660766e-05,
"loss": 2.1056,
"step": 237
},
{
"epoch": 0.06,
"learning_rate": 4.9910065112302175e-05,
"loss": 1.8552,
"step": 238
},
{
"epoch": 0.06,
"learning_rate": 4.9909274958276185e-05,
"loss": 1.5675,
"step": 239
},
{
"epoch": 0.06,
"learning_rate": 4.990848135463915e-05,
"loss": 1.7246,
"step": 240
},
{
"epoch": 0.06,
"learning_rate": 4.990768430150096e-05,
"loss": 1.6873,
"step": 241
},
{
"epoch": 0.06,
"learning_rate": 4.9906883798971995e-05,
"loss": 2.0968,
"step": 242
},
{
"epoch": 0.06,
"learning_rate": 4.9906079847163115e-05,
"loss": 1.662,
"step": 243
},
{
"epoch": 0.06,
"learning_rate": 4.990527244618566e-05,
"loss": 2.1308,
"step": 244
},
{
"epoch": 0.06,
"learning_rate": 4.990446159615144e-05,
"loss": 1.6716,
"step": 245
},
{
"epoch": 0.06,
"learning_rate": 4.9903647297172764e-05,
"loss": 1.833,
"step": 246
},
{
"epoch": 0.06,
"learning_rate": 4.990282954936237e-05,
"loss": 2.0275,
"step": 247
},
{
"epoch": 0.06,
"learning_rate": 4.990200835283353e-05,
"loss": 1.7828,
"step": 248
},
{
"epoch": 0.06,
"learning_rate": 4.990118370769997e-05,
"loss": 1.8333,
"step": 249
},
{
"epoch": 0.06,
"learning_rate": 4.990035561407588e-05,
"loss": 1.5876,
"step": 250
},
{
"epoch": 0.06,
"learning_rate": 4.989952407207594e-05,
"loss": 1.6541,
"step": 251
},
{
"epoch": 0.06,
"learning_rate": 4.989868908181532e-05,
"loss": 1.9533,
"step": 252
},
{
"epoch": 0.06,
"learning_rate": 4.989785064340965e-05,
"loss": 2.1998,
"step": 253
},
{
"epoch": 0.06,
"learning_rate": 4.989700875697503e-05,
"loss": 1.2615,
"step": 254
},
{
"epoch": 0.06,
"learning_rate": 4.9896163422628076e-05,
"loss": 2.2554,
"step": 255
},
{
"epoch": 0.06,
"learning_rate": 4.9895314640485835e-05,
"loss": 1.6735,
"step": 256
},
{
"epoch": 0.06,
"learning_rate": 4.9894462410665856e-05,
"loss": 1.6169,
"step": 257
},
{
"epoch": 0.06,
"learning_rate": 4.989360673328617e-05,
"loss": 0.9541,
"step": 258
},
{
"epoch": 0.06,
"learning_rate": 4.989274760846527e-05,
"loss": 1.4256,
"step": 259
},
{
"epoch": 0.06,
"learning_rate": 4.989188503632213e-05,
"loss": 1.576,
"step": 260
},
{
"epoch": 0.06,
"learning_rate": 4.989101901697621e-05,
"loss": 1.315,
"step": 261
},
{
"epoch": 0.06,
"learning_rate": 4.9890149550547454e-05,
"loss": 1.6165,
"step": 262
},
{
"epoch": 0.06,
"learning_rate": 4.988927663715626e-05,
"loss": 1.7303,
"step": 263
},
{
"epoch": 0.06,
"learning_rate": 4.9888400276923505e-05,
"loss": 1.389,
"step": 264
},
{
"epoch": 0.06,
"learning_rate": 4.9887520469970574e-05,
"loss": 1.6816,
"step": 265
},
{
"epoch": 0.06,
"learning_rate": 4.9886637216419295e-05,
"loss": 1.7488,
"step": 266
},
{
"epoch": 0.06,
"learning_rate": 4.988575051639199e-05,
"loss": 1.3843,
"step": 267
},
{
"epoch": 0.06,
"learning_rate": 4.9884860370011453e-05,
"loss": 2.1209,
"step": 268
},
{
"epoch": 0.06,
"learning_rate": 4.988396677740097e-05,
"loss": 1.7382,
"step": 269
},
{
"epoch": 0.06,
"learning_rate": 4.9883069738684286e-05,
"loss": 1.3885,
"step": 270
},
{
"epoch": 0.06,
"learning_rate": 4.988216925398562e-05,
"loss": 1.8881,
"step": 271
},
{
"epoch": 0.06,
"learning_rate": 4.988126532342968e-05,
"loss": 2.1026,
"step": 272
},
{
"epoch": 0.06,
"learning_rate": 4.9880357947141664e-05,
"loss": 1.7111,
"step": 273
},
{
"epoch": 0.06,
"learning_rate": 4.9879447125247215e-05,
"loss": 1.3994,
"step": 274
},
{
"epoch": 0.07,
"learning_rate": 4.9878532857872476e-05,
"loss": 1.9436,
"step": 275
},
{
"epoch": 0.07,
"learning_rate": 4.9877615145144055e-05,
"loss": 1.2814,
"step": 276
},
{
"epoch": 0.07,
"learning_rate": 4.9876693987189054e-05,
"loss": 1.5255,
"step": 277
},
{
"epoch": 0.07,
"learning_rate": 4.987576938413504e-05,
"loss": 1.7781,
"step": 278
},
{
"epoch": 0.07,
"learning_rate": 4.9874841336110044e-05,
"loss": 1.834,
"step": 279
},
{
"epoch": 0.07,
"learning_rate": 4.987390984324261e-05,
"loss": 1.0663,
"step": 280
},
{
"epoch": 0.07,
"learning_rate": 4.9872974905661726e-05,
"loss": 1.8486,
"step": 281
},
{
"epoch": 0.07,
"learning_rate": 4.9872036523496866e-05,
"loss": 1.4602,
"step": 282
},
{
"epoch": 0.07,
"learning_rate": 4.9871094696877995e-05,
"loss": 2.1106,
"step": 283
},
{
"epoch": 0.07,
"learning_rate": 4.987014942593553e-05,
"loss": 1.1824,
"step": 284
},
{
"epoch": 0.07,
"learning_rate": 4.986920071080039e-05,
"loss": 1.5234,
"step": 285
},
{
"epoch": 0.07,
"learning_rate": 4.9868248551603945e-05,
"loss": 1.2072,
"step": 286
},
{
"epoch": 0.07,
"learning_rate": 4.986729294847807e-05,
"loss": 1.961,
"step": 287
},
{
"epoch": 0.07,
"learning_rate": 4.986633390155511e-05,
"loss": 0.9717,
"step": 288
},
{
"epoch": 0.07,
"learning_rate": 4.986537141096786e-05,
"loss": 1.7839,
"step": 289
},
{
"epoch": 0.07,
"learning_rate": 4.986440547684963e-05,
"loss": 2.0075,
"step": 290
},
{
"epoch": 0.07,
"learning_rate": 4.986343609933418e-05,
"loss": 1.4374,
"step": 291
},
{
"epoch": 0.07,
"learning_rate": 4.986246327855576e-05,
"loss": 1.3924,
"step": 292
},
{
"epoch": 0.07,
"learning_rate": 4.986148701464909e-05,
"loss": 1.5884,
"step": 293
},
{
"epoch": 0.07,
"learning_rate": 4.986050730774937e-05,
"loss": 1.6415,
"step": 294
},
{
"epoch": 0.07,
"learning_rate": 4.985952415799228e-05,
"loss": 1.8095,
"step": 295
},
{
"epoch": 0.07,
"learning_rate": 4.9858537565513976e-05,
"loss": 1.9536,
"step": 296
},
{
"epoch": 0.07,
"learning_rate": 4.985754753045107e-05,
"loss": 1.1484,
"step": 297
},
{
"epoch": 0.07,
"learning_rate": 4.9856554052940705e-05,
"loss": 1.6013,
"step": 298
},
{
"epoch": 0.07,
"learning_rate": 4.9855557133120436e-05,
"loss": 1.5254,
"step": 299
},
{
"epoch": 0.07,
"learning_rate": 4.985455677112832e-05,
"loss": 1.9474,
"step": 300
},
{
"epoch": 0.07,
"learning_rate": 4.985355296710291e-05,
"loss": 1.816,
"step": 301
},
{
"epoch": 0.07,
"learning_rate": 4.985254572118321e-05,
"loss": 1.451,
"step": 302
},
{
"epoch": 0.07,
"learning_rate": 4.985153503350872e-05,
"loss": 1.353,
"step": 303
},
{
"epoch": 0.07,
"learning_rate": 4.98505209042194e-05,
"loss": 1.6463,
"step": 304
},
{
"epoch": 0.07,
"learning_rate": 4.98495033334557e-05,
"loss": 1.8436,
"step": 305
},
{
"epoch": 0.07,
"learning_rate": 4.984848232135853e-05,
"loss": 1.5973,
"step": 306
},
{
"epoch": 0.07,
"learning_rate": 4.984745786806929e-05,
"loss": 1.6524,
"step": 307
},
{
"epoch": 0.07,
"learning_rate": 4.984642997372987e-05,
"loss": 1.499,
"step": 308
},
{
"epoch": 0.07,
"learning_rate": 4.984539863848259e-05,
"loss": 1.8387,
"step": 309
},
{
"epoch": 0.07,
"learning_rate": 4.98443638624703e-05,
"loss": 2.1306,
"step": 310
},
{
"epoch": 0.07,
"learning_rate": 4.98433256458363e-05,
"loss": 1.9113,
"step": 311
},
{
"epoch": 0.07,
"learning_rate": 4.984228398872436e-05,
"loss": 1.7941,
"step": 312
},
{
"epoch": 0.07,
"learning_rate": 4.984123889127874e-05,
"loss": 1.957,
"step": 313
},
{
"epoch": 0.07,
"learning_rate": 4.984019035364418e-05,
"loss": 1.5927,
"step": 314
},
{
"epoch": 0.07,
"learning_rate": 4.983913837596588e-05,
"loss": 1.6275,
"step": 315
},
{
"epoch": 0.07,
"learning_rate": 4.983808295838953e-05,
"loss": 1.5985,
"step": 316
},
{
"epoch": 0.08,
"learning_rate": 4.983702410106128e-05,
"loss": 1.5638,
"step": 317
},
{
"epoch": 0.08,
"learning_rate": 4.983596180412778e-05,
"loss": 1.431,
"step": 318
},
{
"epoch": 0.08,
"learning_rate": 4.983489606773615e-05,
"loss": 1.6035,
"step": 319
},
{
"epoch": 0.08,
"learning_rate": 4.9833826892033966e-05,
"loss": 2.0482,
"step": 320
},
{
"epoch": 0.08,
"learning_rate": 4.98327542771693e-05,
"loss": 1.7167,
"step": 321
},
{
"epoch": 0.08,
"learning_rate": 4.9831678223290705e-05,
"loss": 1.2944,
"step": 322
},
{
"epoch": 0.08,
"learning_rate": 4.9830598730547185e-05,
"loss": 1.6265,
"step": 323
},
{
"epoch": 0.08,
"learning_rate": 4.982951579908824e-05,
"loss": 1.6205,
"step": 324
},
{
"epoch": 0.08,
"learning_rate": 4.982842942906386e-05,
"loss": 2.1644,
"step": 325
},
{
"epoch": 0.08,
"learning_rate": 4.9827339620624466e-05,
"loss": 1.4672,
"step": 326
},
{
"epoch": 0.08,
"learning_rate": 4.9826246373920994e-05,
"loss": 1.6029,
"step": 327
},
{
"epoch": 0.08,
"learning_rate": 4.9825149689104846e-05,
"loss": 1.5438,
"step": 328
},
{
"epoch": 0.08,
"learning_rate": 4.98240495663279e-05,
"loss": 1.9061,
"step": 329
},
{
"epoch": 0.08,
"learning_rate": 4.9822946005742497e-05,
"loss": 1.8342,
"step": 330
},
{
"epoch": 0.08,
"learning_rate": 4.9821839007501484e-05,
"loss": 1.8016,
"step": 331
},
{
"epoch": 0.08,
"learning_rate": 4.9820728571758155e-05,
"loss": 1.6384,
"step": 332
},
{
"epoch": 0.08,
"learning_rate": 4.9819614698666295e-05,
"loss": 1.4692,
"step": 333
},
{
"epoch": 0.08,
"learning_rate": 4.9818497388380154e-05,
"loss": 1.4886,
"step": 334
},
{
"epoch": 0.08,
"learning_rate": 4.9817376641054466e-05,
"loss": 1.4903,
"step": 335
},
{
"epoch": 0.08,
"learning_rate": 4.981625245684445e-05,
"loss": 2.093,
"step": 336
},
{
"epoch": 0.08,
"learning_rate": 4.981512483590578e-05,
"loss": 1.9255,
"step": 337
},
{
"epoch": 0.08,
"learning_rate": 4.981399377839463e-05,
"loss": 1.6346,
"step": 338
},
{
"epoch": 0.08,
"learning_rate": 4.981285928446762e-05,
"loss": 1.6704,
"step": 339
},
{
"epoch": 0.08,
"learning_rate": 4.981172135428188e-05,
"loss": 0.981,
"step": 340
},
{
"epoch": 0.08,
"learning_rate": 4.9810579987994974e-05,
"loss": 1.7046,
"step": 341
},
{
"epoch": 0.08,
"learning_rate": 4.9809435185765e-05,
"loss": 1.6879,
"step": 342
},
{
"epoch": 0.08,
"learning_rate": 4.980828694775046e-05,
"loss": 2.1196,
"step": 343
},
{
"epoch": 0.08,
"learning_rate": 4.980713527411041e-05,
"loss": 1.6099,
"step": 344
},
{
"epoch": 0.08,
"learning_rate": 4.9805980165004304e-05,
"loss": 1.6977,
"step": 345
},
{
"epoch": 0.08,
"learning_rate": 4.980482162059213e-05,
"loss": 1.8916,
"step": 346
},
{
"epoch": 0.08,
"learning_rate": 4.980365964103434e-05,
"loss": 2.0914,
"step": 347
},
{
"epoch": 0.08,
"learning_rate": 4.980249422649183e-05,
"loss": 1.268,
"step": 348
},
{
"epoch": 0.08,
"learning_rate": 4.980132537712602e-05,
"loss": 1.7568,
"step": 349
},
{
"epoch": 0.08,
"learning_rate": 4.9800153093098756e-05,
"loss": 1.3604,
"step": 350
},
{
"epoch": 0.08,
"learning_rate": 4.9798977374572395e-05,
"loss": 1.5185,
"step": 351
},
{
"epoch": 0.08,
"learning_rate": 4.979779822170977e-05,
"loss": 1.8898,
"step": 352
},
{
"epoch": 0.08,
"learning_rate": 4.9796615634674155e-05,
"loss": 2.0664,
"step": 353
},
{
"epoch": 0.08,
"learning_rate": 4.979542961362934e-05,
"loss": 1.4639,
"step": 354
},
{
"epoch": 0.08,
"learning_rate": 4.9794240158739566e-05,
"loss": 1.2679,
"step": 355
},
{
"epoch": 0.08,
"learning_rate": 4.9793047270169566e-05,
"loss": 1.6697,
"step": 356
},
{
"epoch": 0.08,
"learning_rate": 4.979185094808453e-05,
"loss": 1.3827,
"step": 357
},
{
"epoch": 0.08,
"learning_rate": 4.979065119265013e-05,
"loss": 1.471,
"step": 358
},
{
"epoch": 0.08,
"learning_rate": 4.9789448004032533e-05,
"loss": 2.0245,
"step": 359
},
{
"epoch": 0.09,
"learning_rate": 4.978824138239835e-05,
"loss": 1.6898,
"step": 360
},
{
"epoch": 0.09,
"learning_rate": 4.978703132791469e-05,
"loss": 1.8281,
"step": 361
},
{
"epoch": 0.09,
"learning_rate": 4.978581784074913e-05,
"loss": 1.8089,
"step": 362
},
{
"epoch": 0.09,
"learning_rate": 4.978460092106971e-05,
"loss": 1.6343,
"step": 363
},
{
"epoch": 0.09,
"learning_rate": 4.9783380569044974e-05,
"loss": 2.2785,
"step": 364
},
{
"epoch": 0.09,
"learning_rate": 4.9782156784843916e-05,
"loss": 1.9567,
"step": 365
},
{
"epoch": 0.09,
"learning_rate": 4.9780929568636015e-05,
"loss": 1.3461,
"step": 366
},
{
"epoch": 0.09,
"learning_rate": 4.977969892059123e-05,
"loss": 1.4954,
"step": 367
},
{
"epoch": 0.09,
"learning_rate": 4.977846484087998e-05,
"loss": 1.305,
"step": 368
},
{
"epoch": 0.09,
"learning_rate": 4.9777227329673174e-05,
"loss": 1.8285,
"step": 369
},
{
"epoch": 0.09,
"learning_rate": 4.977598638714219e-05,
"loss": 1.4243,
"step": 370
},
{
"epoch": 0.09,
"learning_rate": 4.97747420134589e-05,
"loss": 1.7667,
"step": 371
},
{
"epoch": 0.09,
"learning_rate": 4.9773494208795604e-05,
"loss": 1.9451,
"step": 372
},
{
"epoch": 0.09,
"learning_rate": 4.9772242973325125e-05,
"loss": 1.5445,
"step": 373
},
{
"epoch": 0.09,
"learning_rate": 4.9770988307220736e-05,
"loss": 1.6328,
"step": 374
},
{
"epoch": 0.09,
"learning_rate": 4.976973021065619e-05,
"loss": 1.6148,
"step": 375
},
{
"epoch": 0.09,
"learning_rate": 4.976846868380572e-05,
"loss": 1.3625,
"step": 376
},
{
"epoch": 0.09,
"learning_rate": 4.976720372684404e-05,
"loss": 1.4694,
"step": 377
},
{
"epoch": 0.09,
"learning_rate": 4.9765935339946326e-05,
"loss": 1.5375,
"step": 378
},
{
"epoch": 0.09,
"learning_rate": 4.976466352328822e-05,
"loss": 1.805,
"step": 379
},
{
"epoch": 0.09,
"learning_rate": 4.976338827704586e-05,
"loss": 1.8427,
"step": 380
},
{
"epoch": 0.09,
"learning_rate": 4.976210960139586e-05,
"loss": 1.9649,
"step": 381
},
{
"epoch": 0.09,
"learning_rate": 4.976082749651529e-05,
"loss": 1.4552,
"step": 382
},
{
"epoch": 0.09,
"learning_rate": 4.9759541962581715e-05,
"loss": 1.7111,
"step": 383
},
{
"epoch": 0.09,
"learning_rate": 4.975825299977315e-05,
"loss": 2.0492,
"step": 384
},
{
"epoch": 0.09,
"learning_rate": 4.9756960608268104e-05,
"loss": 2.4812,
"step": 385
},
{
"epoch": 0.09,
"learning_rate": 4.975566478824556e-05,
"loss": 1.3533,
"step": 386
},
{
"epoch": 0.09,
"learning_rate": 4.975436553988498e-05,
"loss": 1.7609,
"step": 387
},
{
"epoch": 0.09,
"learning_rate": 4.9753062863366276e-05,
"loss": 1.3683,
"step": 388
},
{
"epoch": 0.09,
"learning_rate": 4.975175675886986e-05,
"loss": 1.5215,
"step": 389
},
{
"epoch": 0.09,
"learning_rate": 4.9750447226576617e-05,
"loss": 1.2101,
"step": 390
},
{
"epoch": 0.09,
"learning_rate": 4.9749134266667894e-05,
"loss": 1.5135,
"step": 391
},
{
"epoch": 0.09,
"learning_rate": 4.9747817879325514e-05,
"loss": 1.9498,
"step": 392
},
{
"epoch": 0.09,
"learning_rate": 4.9746498064731786e-05,
"loss": 1.9672,
"step": 393
},
{
"epoch": 0.09,
"learning_rate": 4.9745174823069486e-05,
"loss": 2.1517,
"step": 394
},
{
"epoch": 0.09,
"learning_rate": 4.9743848154521863e-05,
"loss": 1.411,
"step": 395
},
{
"epoch": 0.09,
"learning_rate": 4.974251805927266e-05,
"loss": 1.3972,
"step": 396
},
{
"epoch": 0.09,
"learning_rate": 4.974118453750605e-05,
"loss": 1.6883,
"step": 397
},
{
"epoch": 0.09,
"learning_rate": 4.973984758940672e-05,
"loss": 1.4422,
"step": 398
},
{
"epoch": 0.09,
"learning_rate": 4.973850721515983e-05,
"loss": 1.5046,
"step": 399
},
{
"epoch": 0.09,
"learning_rate": 4.973716341495099e-05,
"loss": 1.9012,
"step": 400
},
{
"epoch": 0.09,
"learning_rate": 4.973581618896631e-05,
"loss": 1.6414,
"step": 401
},
{
"epoch": 0.1,
"learning_rate": 4.973446553739236e-05,
"loss": 1.4029,
"step": 402
},
{
"epoch": 0.1,
"learning_rate": 4.973311146041619e-05,
"loss": 1.3923,
"step": 403
},
{
"epoch": 0.1,
"learning_rate": 4.9731753958225316e-05,
"loss": 0.9104,
"step": 404
},
{
"epoch": 0.1,
"learning_rate": 4.973039303100773e-05,
"loss": 1.4314,
"step": 405
},
{
"epoch": 0.1,
"learning_rate": 4.972902867895191e-05,
"loss": 1.5725,
"step": 406
},
{
"epoch": 0.1,
"learning_rate": 4.972766090224681e-05,
"loss": 1.8915,
"step": 407
},
{
"epoch": 0.1,
"learning_rate": 4.972628970108183e-05,
"loss": 2.0525,
"step": 408
},
{
"epoch": 0.1,
"learning_rate": 4.972491507564688e-05,
"loss": 1.4409,
"step": 409
},
{
"epoch": 0.1,
"learning_rate": 4.9723537026132315e-05,
"loss": 1.4878,
"step": 410
},
{
"epoch": 0.1,
"learning_rate": 4.972215555272899e-05,
"loss": 1.6305,
"step": 411
},
{
"epoch": 0.1,
"learning_rate": 4.972077065562821e-05,
"loss": 1.6004,
"step": 412
},
{
"epoch": 0.1,
"learning_rate": 4.971938233502178e-05,
"loss": 1.6837,
"step": 413
},
{
"epoch": 0.1,
"learning_rate": 4.971799059110195e-05,
"loss": 1.6939,
"step": 414
},
{
"epoch": 0.1,
"learning_rate": 4.971659542406145e-05,
"loss": 1.6326,
"step": 415
},
{
"epoch": 0.1,
"learning_rate": 4.971519683409352e-05,
"loss": 2.0437,
"step": 416
},
{
"epoch": 0.1,
"learning_rate": 4.9713794821391825e-05,
"loss": 1.8919,
"step": 417
},
{
"epoch": 0.1,
"learning_rate": 4.9712389386150535e-05,
"loss": 1.4444,
"step": 418
},
{
"epoch": 0.1,
"learning_rate": 4.971098052856428e-05,
"loss": 1.7376,
"step": 419
},
{
"epoch": 0.1,
"learning_rate": 4.970956824882816e-05,
"loss": 1.2145,
"step": 420
},
{
"epoch": 0.1,
"learning_rate": 4.970815254713779e-05,
"loss": 1.7657,
"step": 421
},
{
"epoch": 0.1,
"learning_rate": 4.970673342368919e-05,
"loss": 1.4632,
"step": 422
},
{
"epoch": 0.1,
"learning_rate": 4.97053108786789e-05,
"loss": 2.0926,
"step": 423
},
{
"epoch": 0.1,
"learning_rate": 4.970388491230393e-05,
"loss": 1.6105,
"step": 424
},
{
"epoch": 0.1,
"learning_rate": 4.9702455524761764e-05,
"loss": 0.8295,
"step": 425
},
{
"epoch": 0.1,
"learning_rate": 4.9701022716250346e-05,
"loss": 1.5312,
"step": 426
},
{
"epoch": 0.1,
"learning_rate": 4.9699586486968094e-05,
"loss": 1.2171,
"step": 427
},
{
"epoch": 0.1,
"learning_rate": 4.969814683711391e-05,
"loss": 1.6475,
"step": 428
},
{
"epoch": 0.1,
"learning_rate": 4.9696703766887174e-05,
"loss": 1.3856,
"step": 429
},
{
"epoch": 0.1,
"learning_rate": 4.9695257276487736e-05,
"loss": 1.413,
"step": 430
},
{
"epoch": 0.1,
"learning_rate": 4.9693807366115905e-05,
"loss": 1.2724,
"step": 431
},
{
"epoch": 0.1,
"learning_rate": 4.969235403597248e-05,
"loss": 2.0263,
"step": 432
},
{
"epoch": 0.1,
"learning_rate": 4.969089728625873e-05,
"loss": 1.6963,
"step": 433
},
{
"epoch": 0.1,
"learning_rate": 4.968943711717638e-05,
"loss": 1.6354,
"step": 434
},
{
"epoch": 0.1,
"learning_rate": 4.968797352892768e-05,
"loss": 1.7197,
"step": 435
},
{
"epoch": 0.1,
"learning_rate": 4.968650652171528e-05,
"loss": 1.7091,
"step": 436
},
{
"epoch": 0.1,
"learning_rate": 4.9685036095742365e-05,
"loss": 2.0653,
"step": 437
},
{
"epoch": 0.1,
"learning_rate": 4.968356225121256e-05,
"loss": 1.8299,
"step": 438
},
{
"epoch": 0.1,
"learning_rate": 4.968208498832997e-05,
"loss": 2.0181,
"step": 439
},
{
"epoch": 0.1,
"learning_rate": 4.968060430729918e-05,
"loss": 1.7343,
"step": 440
},
{
"epoch": 0.1,
"learning_rate": 4.967912020832526e-05,
"loss": 1.9446,
"step": 441
},
{
"epoch": 0.1,
"learning_rate": 4.967763269161372e-05,
"loss": 1.4359,
"step": 442
},
{
"epoch": 0.1,
"learning_rate": 4.967614175737056e-05,
"loss": 2.211,
"step": 443
},
{
"epoch": 0.11,
"learning_rate": 4.967464740580227e-05,
"loss": 1.5243,
"step": 444
},
{
"epoch": 0.11,
"learning_rate": 4.967314963711579e-05,
"loss": 1.0646,
"step": 445
},
{
"epoch": 0.11,
"learning_rate": 4.967164845151855e-05,
"loss": 1.9905,
"step": 446
},
{
"epoch": 0.11,
"learning_rate": 4.967014384921842e-05,
"loss": 1.9194,
"step": 447
},
{
"epoch": 0.11,
"learning_rate": 4.96686358304238e-05,
"loss": 1.5094,
"step": 448
},
{
"epoch": 0.11,
"learning_rate": 4.966712439534351e-05,
"loss": 1.8683,
"step": 449
},
{
"epoch": 0.11,
"learning_rate": 4.9665609544186867e-05,
"loss": 1.422,
"step": 450
},
{
"epoch": 0.11,
"learning_rate": 4.966409127716367e-05,
"loss": 1.8794,
"step": 451
},
{
"epoch": 0.11,
"learning_rate": 4.966256959448416e-05,
"loss": 1.8767,
"step": 452
},
{
"epoch": 0.11,
"learning_rate": 4.966104449635909e-05,
"loss": 1.4035,
"step": 453
},
{
"epoch": 0.11,
"learning_rate": 4.965951598299965e-05,
"loss": 1.9975,
"step": 454
},
{
"epoch": 0.11,
"learning_rate": 4.9657984054617526e-05,
"loss": 2.1903,
"step": 455
},
{
"epoch": 0.11,
"learning_rate": 4.9656448711424876e-05,
"loss": 1.2803,
"step": 456
},
{
"epoch": 0.11,
"learning_rate": 4.9654909953634316e-05,
"loss": 1.4093,
"step": 457
},
{
"epoch": 0.11,
"learning_rate": 4.965336778145895e-05,
"loss": 1.5228,
"step": 458
},
{
"epoch": 0.11,
"learning_rate": 4.965182219511234e-05,
"loss": 1.8209,
"step": 459
},
{
"epoch": 0.11,
"learning_rate": 4.9650273194808546e-05,
"loss": 1.7129,
"step": 460
},
{
"epoch": 0.11,
"learning_rate": 4.964872078076207e-05,
"loss": 1.9,
"step": 461
},
{
"epoch": 0.11,
"learning_rate": 4.96471649531879e-05,
"loss": 1.5979,
"step": 462
},
{
"epoch": 0.11,
"learning_rate": 4.964560571230151e-05,
"loss": 1.6498,
"step": 463
},
{
"epoch": 0.11,
"learning_rate": 4.964404305831883e-05,
"loss": 2.0043,
"step": 464
},
{
"epoch": 0.11,
"learning_rate": 4.964247699145626e-05,
"loss": 1.7263,
"step": 465
},
{
"epoch": 0.11,
"learning_rate": 4.964090751193069e-05,
"loss": 2.1116,
"step": 466
},
{
"epoch": 0.11,
"learning_rate": 4.9639334619959464e-05,
"loss": 2.2474,
"step": 467
},
{
"epoch": 0.11,
"learning_rate": 4.963775831576041e-05,
"loss": 1.6965,
"step": 468
},
{
"epoch": 0.11,
"learning_rate": 4.963617859955183e-05,
"loss": 1.7008,
"step": 469
},
{
"epoch": 0.11,
"learning_rate": 4.963459547155249e-05,
"loss": 1.7393,
"step": 470
},
{
"epoch": 0.11,
"learning_rate": 4.963300893198164e-05,
"loss": 1.9297,
"step": 471
},
{
"epoch": 0.11,
"learning_rate": 4.9631418981058974e-05,
"loss": 1.6991,
"step": 472
},
{
"epoch": 0.11,
"learning_rate": 4.9629825619004704e-05,
"loss": 1.2928,
"step": 473
},
{
"epoch": 0.11,
"learning_rate": 4.962822884603948e-05,
"loss": 1.7254,
"step": 474
},
{
"epoch": 0.11,
"learning_rate": 4.9626628662384434e-05,
"loss": 1.9312,
"step": 475
},
{
"epoch": 0.11,
"learning_rate": 4.962502506826117e-05,
"loss": 1.5214,
"step": 476
},
{
"epoch": 0.11,
"learning_rate": 4.962341806389176e-05,
"loss": 1.3667,
"step": 477
},
{
"epoch": 0.11,
"learning_rate": 4.9621807649498764e-05,
"loss": 1.7049,
"step": 478
},
{
"epoch": 0.11,
"learning_rate": 4.962019382530521e-05,
"loss": 1.7479,
"step": 479
},
{
"epoch": 0.11,
"learning_rate": 4.961857659153456e-05,
"loss": 1.5101,
"step": 480
},
{
"epoch": 0.11,
"learning_rate": 4.961695594841082e-05,
"loss": 1.3799,
"step": 481
},
{
"epoch": 0.11,
"learning_rate": 4.961533189615839e-05,
"loss": 2.4575,
"step": 482
},
{
"epoch": 0.11,
"learning_rate": 4.961370443500221e-05,
"loss": 1.5559,
"step": 483
},
{
"epoch": 0.11,
"learning_rate": 4.961207356516765e-05,
"loss": 1.5502,
"step": 484
},
{
"epoch": 0.11,
"learning_rate": 4.961043928688056e-05,
"loss": 1.3477,
"step": 485
},
{
"epoch": 0.11,
"learning_rate": 4.960880160036728e-05,
"loss": 1.7157,
"step": 486
},
{
"epoch": 0.12,
"learning_rate": 4.960716050585459e-05,
"loss": 1.4801,
"step": 487
},
{
"epoch": 0.12,
"learning_rate": 4.960551600356977e-05,
"loss": 1.3484,
"step": 488
},
{
"epoch": 0.12,
"learning_rate": 4.960386809374057e-05,
"loss": 1.8751,
"step": 489
},
{
"epoch": 0.12,
"learning_rate": 4.960221677659519e-05,
"loss": 1.6072,
"step": 490
},
{
"epoch": 0.12,
"learning_rate": 4.9600562052362333e-05,
"loss": 2.4259,
"step": 491
},
{
"epoch": 0.12,
"learning_rate": 4.9598903921271135e-05,
"loss": 1.9676,
"step": 492
},
{
"epoch": 0.12,
"learning_rate": 4.959724238355123e-05,
"loss": 2.193,
"step": 493
},
{
"epoch": 0.12,
"learning_rate": 4.959557743943274e-05,
"loss": 1.8709,
"step": 494
},
{
"epoch": 0.12,
"learning_rate": 4.9593909089146224e-05,
"loss": 1.5639,
"step": 495
},
{
"epoch": 0.12,
"learning_rate": 4.959223733292272e-05,
"loss": 1.5942,
"step": 496
},
{
"epoch": 0.12,
"learning_rate": 4.9590562170993755e-05,
"loss": 2.474,
"step": 497
},
{
"epoch": 0.12,
"learning_rate": 4.958888360359131e-05,
"loss": 1.8667,
"step": 498
},
{
"epoch": 0.12,
"learning_rate": 4.958720163094786e-05,
"loss": 1.9014,
"step": 499
},
{
"epoch": 0.12,
"learning_rate": 4.958551625329631e-05,
"loss": 1.3199,
"step": 500
},
{
"epoch": 0.12,
"learning_rate": 4.958382747087008e-05,
"loss": 1.4193,
"step": 501
},
{
"epoch": 0.12,
"learning_rate": 4.958213528390305e-05,
"loss": 1.6693,
"step": 502
},
{
"epoch": 0.12,
"learning_rate": 4.958043969262955e-05,
"loss": 1.3332,
"step": 503
},
{
"epoch": 0.12,
"learning_rate": 4.957874069728441e-05,
"loss": 1.3463,
"step": 504
},
{
"epoch": 0.12,
"learning_rate": 4.957703829810292e-05,
"loss": 1.3705,
"step": 505
},
{
"epoch": 0.12,
"learning_rate": 4.9575332495320826e-05,
"loss": 2.1182,
"step": 506
},
{
"epoch": 0.12,
"learning_rate": 4.957362328917437e-05,
"loss": 1.7346,
"step": 507
},
{
"epoch": 0.12,
"learning_rate": 4.9571910679900255e-05,
"loss": 1.3646,
"step": 508
},
{
"epoch": 0.12,
"learning_rate": 4.957019466773565e-05,
"loss": 1.9329,
"step": 509
},
{
"epoch": 0.12,
"learning_rate": 4.95684752529182e-05,
"loss": 1.8554,
"step": 510
},
{
"epoch": 0.12,
"learning_rate": 4.9566752435686036e-05,
"loss": 1.9678,
"step": 511
},
{
"epoch": 0.12,
"learning_rate": 4.956502621627773e-05,
"loss": 1.9655,
"step": 512
},
{
"epoch": 0.12,
"learning_rate": 4.956329659493234e-05,
"loss": 1.5136,
"step": 513
},
{
"epoch": 0.12,
"learning_rate": 4.95615635718894e-05,
"loss": 1.5812,
"step": 514
},
{
"epoch": 0.12,
"learning_rate": 4.955982714738892e-05,
"loss": 2.4143,
"step": 515
},
{
"epoch": 0.12,
"learning_rate": 4.9558087321671374e-05,
"loss": 2.0219,
"step": 516
},
{
"epoch": 0.12,
"learning_rate": 4.955634409497768e-05,
"loss": 1.3464,
"step": 517
},
{
"epoch": 0.12,
"learning_rate": 4.955459746754928e-05,
"loss": 2.011,
"step": 518
},
{
"epoch": 0.12,
"learning_rate": 4.955284743962804e-05,
"loss": 1.1818,
"step": 519
},
{
"epoch": 0.12,
"learning_rate": 4.9551094011456335e-05,
"loss": 1.9715,
"step": 520
},
{
"epoch": 0.12,
"learning_rate": 4.954933718327697e-05,
"loss": 2.2617,
"step": 521
},
{
"epoch": 0.12,
"learning_rate": 4.954757695533326e-05,
"loss": 2.0038,
"step": 522
},
{
"epoch": 0.12,
"learning_rate": 4.954581332786896e-05,
"loss": 1.2001,
"step": 523
},
{
"epoch": 0.12,
"learning_rate": 4.954404630112833e-05,
"loss": 1.1356,
"step": 524
},
{
"epoch": 0.12,
"learning_rate": 4.954227587535606e-05,
"loss": 1.6941,
"step": 525
},
{
"epoch": 0.12,
"learning_rate": 4.9540502050797335e-05,
"loss": 1.3234,
"step": 526
},
{
"epoch": 0.12,
"learning_rate": 4.9538724827697814e-05,
"loss": 2.1369,
"step": 527
},
{
"epoch": 0.12,
"learning_rate": 4.953694420630361e-05,
"loss": 2.0145,
"step": 528
},
{
"epoch": 0.13,
"learning_rate": 4.953516018686133e-05,
"loss": 1.5505,
"step": 529
},
{
"epoch": 0.13,
"learning_rate": 4.953337276961803e-05,
"loss": 1.5479,
"step": 530
},
{
"epoch": 0.13,
"learning_rate": 4.953158195482124e-05,
"loss": 2.4011,
"step": 531
},
{
"epoch": 0.13,
"learning_rate": 4.952978774271897e-05,
"loss": 1.5701,
"step": 532
},
{
"epoch": 0.13,
"learning_rate": 4.9527990133559684e-05,
"loss": 1.576,
"step": 533
},
{
"epoch": 0.13,
"learning_rate": 4.952618912759235e-05,
"loss": 1.7477,
"step": 534
},
{
"epoch": 0.13,
"learning_rate": 4.9524384725066355e-05,
"loss": 1.9253,
"step": 535
},
{
"epoch": 0.13,
"learning_rate": 4.952257692623161e-05,
"loss": 1.5152,
"step": 536
},
{
"epoch": 0.13,
"learning_rate": 4.952076573133846e-05,
"loss": 1.5489,
"step": 537
},
{
"epoch": 0.13,
"learning_rate": 4.951895114063773e-05,
"loss": 1.792,
"step": 538
},
{
"epoch": 0.13,
"learning_rate": 4.9517133154380724e-05,
"loss": 1.4957,
"step": 539
},
{
"epoch": 0.13,
"learning_rate": 4.9515311772819214e-05,
"loss": 1.9255,
"step": 540
},
{
"epoch": 0.13,
"learning_rate": 4.951348699620542e-05,
"loss": 1.5982,
"step": 541
},
{
"epoch": 0.13,
"learning_rate": 4.9511658824792065e-05,
"loss": 1.4355,
"step": 542
},
{
"epoch": 0.13,
"learning_rate": 4.950982725883232e-05,
"loss": 1.4889,
"step": 543
},
{
"epoch": 0.13,
"learning_rate": 4.9507992298579845e-05,
"loss": 1.4814,
"step": 544
},
{
"epoch": 0.13,
"learning_rate": 4.950615394428874e-05,
"loss": 1.7735,
"step": 545
},
{
"epoch": 0.13,
"learning_rate": 4.9504312196213596e-05,
"loss": 1.5049,
"step": 546
},
{
"epoch": 0.13,
"learning_rate": 4.950246705460949e-05,
"loss": 1.516,
"step": 547
},
{
"epoch": 0.13,
"learning_rate": 4.950061851973193e-05,
"loss": 1.805,
"step": 548
},
{
"epoch": 0.13,
"learning_rate": 4.949876659183692e-05,
"loss": 1.3621,
"step": 549
},
{
"epoch": 0.13,
"learning_rate": 4.949691127118093e-05,
"loss": 1.8475,
"step": 550
},
{
"epoch": 0.13,
"learning_rate": 4.9495052558020896e-05,
"loss": 2.3199,
"step": 551
},
{
"epoch": 0.13,
"learning_rate": 4.949319045261423e-05,
"loss": 1.3384,
"step": 552
},
{
"epoch": 0.13,
"learning_rate": 4.949132495521881e-05,
"loss": 1.4563,
"step": 553
},
{
"epoch": 0.13,
"learning_rate": 4.948945606609297e-05,
"loss": 1.6799,
"step": 554
},
{
"epoch": 0.13,
"learning_rate": 4.948758378549554e-05,
"loss": 1.7253,
"step": 555
},
{
"epoch": 0.13,
"learning_rate": 4.94857081136858e-05,
"loss": 1.0717,
"step": 556
},
{
"epoch": 0.13,
"learning_rate": 4.9483829050923514e-05,
"loss": 1.8967,
"step": 557
},
{
"epoch": 0.13,
"learning_rate": 4.9481946597468896e-05,
"loss": 1.4919,
"step": 558
},
{
"epoch": 0.13,
"learning_rate": 4.948006075358266e-05,
"loss": 1.4128,
"step": 559
},
{
"epoch": 0.13,
"learning_rate": 4.947817151952595e-05,
"loss": 0.9676,
"step": 560
},
{
"epoch": 0.13,
"learning_rate": 4.9476278895560406e-05,
"loss": 2.0732,
"step": 561
},
{
"epoch": 0.13,
"learning_rate": 4.9474382881948146e-05,
"loss": 1.3808,
"step": 562
},
{
"epoch": 0.13,
"learning_rate": 4.947248347895172e-05,
"loss": 1.4687,
"step": 563
},
{
"epoch": 0.13,
"learning_rate": 4.947058068683419e-05,
"loss": 1.4168,
"step": 564
},
{
"epoch": 0.13,
"learning_rate": 4.946867450585906e-05,
"loss": 1.352,
"step": 565
},
{
"epoch": 0.13,
"learning_rate": 4.946676493629031e-05,
"loss": 1.8284,
"step": 566
},
{
"epoch": 0.13,
"learning_rate": 4.9464851978392396e-05,
"loss": 1.2706,
"step": 567
},
{
"epoch": 0.13,
"learning_rate": 4.946293563243023e-05,
"loss": 1.4926,
"step": 568
},
{
"epoch": 0.13,
"learning_rate": 4.946101589866921e-05,
"loss": 1.3684,
"step": 569
},
{
"epoch": 0.13,
"learning_rate": 4.945909277737519e-05,
"loss": 1.4088,
"step": 570
},
{
"epoch": 0.14,
"learning_rate": 4.945716626881449e-05,
"loss": 1.5532,
"step": 571
},
{
"epoch": 0.14,
"learning_rate": 4.9455236373253924e-05,
"loss": 1.7944,
"step": 572
},
{
"epoch": 0.14,
"learning_rate": 4.9453303090960745e-05,
"loss": 1.4292,
"step": 573
},
{
"epoch": 0.14,
"learning_rate": 4.9451366422202684e-05,
"loss": 2.0021,
"step": 574
},
{
"epoch": 0.14,
"learning_rate": 4.944942636724795e-05,
"loss": 1.7356,
"step": 575
},
{
"epoch": 0.14,
"learning_rate": 4.944748292636522e-05,
"loss": 1.6986,
"step": 576
},
{
"epoch": 0.14,
"learning_rate": 4.944553609982363e-05,
"loss": 2.0781,
"step": 577
},
{
"epoch": 0.14,
"learning_rate": 4.944358588789279e-05,
"loss": 2.2571,
"step": 578
},
{
"epoch": 0.14,
"learning_rate": 4.944163229084278e-05,
"loss": 1.5924,
"step": 579
},
{
"epoch": 0.14,
"learning_rate": 4.943967530894415e-05,
"loss": 2.0977,
"step": 580
},
{
"epoch": 0.14,
"learning_rate": 4.943771494246791e-05,
"loss": 1.8041,
"step": 581
},
{
"epoch": 0.14,
"learning_rate": 4.943575119168555e-05,
"loss": 1.6522,
"step": 582
},
{
"epoch": 0.14,
"learning_rate": 4.9433784056869023e-05,
"loss": 1.4012,
"step": 583
},
{
"epoch": 0.14,
"learning_rate": 4.943181353829076e-05,
"loss": 1.3196,
"step": 584
},
{
"epoch": 0.14,
"learning_rate": 4.9429839636223644e-05,
"loss": 1.7751,
"step": 585
},
{
"epoch": 0.14,
"learning_rate": 4.942786235094103e-05,
"loss": 1.3212,
"step": 586
},
{
"epoch": 0.14,
"learning_rate": 4.9425881682716747e-05,
"loss": 1.7491,
"step": 587
},
{
"epoch": 0.14,
"learning_rate": 4.94238976318251e-05,
"loss": 1.7227,
"step": 588
},
{
"epoch": 0.14,
"learning_rate": 4.942191019854085e-05,
"loss": 1.4114,
"step": 589
},
{
"epoch": 0.14,
"learning_rate": 4.941991938313924e-05,
"loss": 2.0666,
"step": 590
},
{
"epoch": 0.14,
"learning_rate": 4.941792518589596e-05,
"loss": 1.7138,
"step": 591
},
{
"epoch": 0.14,
"learning_rate": 4.941592760708718e-05,
"loss": 1.7506,
"step": 592
},
{
"epoch": 0.14,
"learning_rate": 4.9413926646989545e-05,
"loss": 1.8036,
"step": 593
},
{
"epoch": 0.14,
"learning_rate": 4.941192230588015e-05,
"loss": 1.357,
"step": 594
},
{
"epoch": 0.14,
"learning_rate": 4.94099145840366e-05,
"loss": 1.5612,
"step": 595
},
{
"epoch": 0.14,
"learning_rate": 4.9407903481736904e-05,
"loss": 1.1086,
"step": 596
},
{
"epoch": 0.14,
"learning_rate": 4.940588899925959e-05,
"loss": 1.217,
"step": 597
},
{
"epoch": 0.14,
"learning_rate": 4.940387113688363e-05,
"loss": 1.6993,
"step": 598
},
{
"epoch": 0.14,
"learning_rate": 4.9401849894888485e-05,
"loss": 1.684,
"step": 599
},
{
"epoch": 0.14,
"learning_rate": 4.939982527355407e-05,
"loss": 1.8285,
"step": 600
},
{
"epoch": 0.14,
"learning_rate": 4.939779727316075e-05,
"loss": 1.28,
"step": 601
},
{
"epoch": 0.14,
"learning_rate": 4.939576589398939e-05,
"loss": 1.6247,
"step": 602
},
{
"epoch": 0.14,
"learning_rate": 4.9393731136321306e-05,
"loss": 1.7047,
"step": 603
},
{
"epoch": 0.14,
"learning_rate": 4.9391693000438286e-05,
"loss": 1.67,
"step": 604
},
{
"epoch": 0.14,
"learning_rate": 4.93896514866226e-05,
"loss": 2.0157,
"step": 605
},
{
"epoch": 0.14,
"learning_rate": 4.9387606595156944e-05,
"loss": 1.5195,
"step": 606
},
{
"epoch": 0.14,
"learning_rate": 4.9385558326324534e-05,
"loss": 1.9139,
"step": 607
},
{
"epoch": 0.14,
"learning_rate": 4.9383506680409006e-05,
"loss": 1.5393,
"step": 608
},
{
"epoch": 0.14,
"learning_rate": 4.938145165769451e-05,
"loss": 2.1366,
"step": 609
},
{
"epoch": 0.14,
"learning_rate": 4.9379393258465623e-05,
"loss": 1.835,
"step": 610
},
{
"epoch": 0.14,
"learning_rate": 4.93773314830074e-05,
"loss": 1.4716,
"step": 611
},
{
"epoch": 0.14,
"learning_rate": 4.93752663316054e-05,
"loss": 1.8467,
"step": 612
},
{
"epoch": 0.15,
"learning_rate": 4.937319780454559e-05,
"loss": 1.5434,
"step": 613
},
{
"epoch": 0.15,
"learning_rate": 4.937112590211445e-05,
"loss": 1.5179,
"step": 614
},
{
"epoch": 0.15,
"learning_rate": 4.936905062459891e-05,
"loss": 1.5824,
"step": 615
},
{
"epoch": 0.15,
"learning_rate": 4.9366971972286356e-05,
"loss": 1.8289,
"step": 616
},
{
"epoch": 0.15,
"learning_rate": 4.936488994546467e-05,
"loss": 1.7236,
"step": 617
},
{
"epoch": 0.15,
"learning_rate": 4.936280454442218e-05,
"loss": 2.3392,
"step": 618
},
{
"epoch": 0.15,
"learning_rate": 4.936071576944769e-05,
"loss": 1.6376,
"step": 619
},
{
"epoch": 0.15,
"learning_rate": 4.9358623620830456e-05,
"loss": 1.7252,
"step": 620
},
{
"epoch": 0.15,
"learning_rate": 4.9356528098860235e-05,
"loss": 1.4184,
"step": 621
},
{
"epoch": 0.15,
"learning_rate": 4.93544292038272e-05,
"loss": 1.4501,
"step": 622
},
{
"epoch": 0.15,
"learning_rate": 4.9352326936022055e-05,
"loss": 1.4233,
"step": 623
},
{
"epoch": 0.15,
"learning_rate": 4.935022129573591e-05,
"loss": 1.6631,
"step": 624
},
{
"epoch": 0.15,
"learning_rate": 4.9348112283260376e-05,
"loss": 1.155,
"step": 625
},
{
"epoch": 0.15,
"learning_rate": 4.934599989888753e-05,
"loss": 1.2512,
"step": 626
},
{
"epoch": 0.15,
"learning_rate": 4.934388414290991e-05,
"loss": 1.3304,
"step": 627
},
{
"epoch": 0.15,
"learning_rate": 4.9341765015620514e-05,
"loss": 1.5858,
"step": 628
},
{
"epoch": 0.15,
"learning_rate": 4.933964251731281e-05,
"loss": 1.3061,
"step": 629
},
{
"epoch": 0.15,
"learning_rate": 4.9337516648280756e-05,
"loss": 1.782,
"step": 630
},
{
"epoch": 0.15,
"learning_rate": 4.933538740881874e-05,
"loss": 1.8033,
"step": 631
},
{
"epoch": 0.15,
"learning_rate": 4.933325479922163e-05,
"loss": 1.8176,
"step": 632
},
{
"epoch": 0.15,
"learning_rate": 4.9331118819784773e-05,
"loss": 1.8735,
"step": 633
},
{
"epoch": 0.15,
"learning_rate": 4.932897947080398e-05,
"loss": 1.59,
"step": 634
},
{
"epoch": 0.15,
"learning_rate": 4.9326836752575514e-05,
"loss": 2.2281,
"step": 635
},
{
"epoch": 0.15,
"learning_rate": 4.932469066539612e-05,
"loss": 2.0652,
"step": 636
},
{
"epoch": 0.15,
"learning_rate": 4.9322541209563e-05,
"loss": 1.9974,
"step": 637
},
{
"epoch": 0.15,
"learning_rate": 4.9320388385373825e-05,
"loss": 1.5013,
"step": 638
},
{
"epoch": 0.15,
"learning_rate": 4.9318232193126737e-05,
"loss": 1.5165,
"step": 639
},
{
"epoch": 0.15,
"learning_rate": 4.931607263312032e-05,
"loss": 1.4775,
"step": 640
},
{
"epoch": 0.15,
"learning_rate": 4.931390970565368e-05,
"loss": 1.8116,
"step": 641
},
{
"epoch": 0.15,
"learning_rate": 4.931174341102634e-05,
"loss": 1.731,
"step": 642
},
{
"epoch": 0.15,
"learning_rate": 4.9309573749538295e-05,
"loss": 1.5851,
"step": 643
},
{
"epoch": 0.15,
"learning_rate": 4.9307400721490015e-05,
"loss": 1.6169,
"step": 644
},
{
"epoch": 0.15,
"learning_rate": 4.930522432718245e-05,
"loss": 1.6315,
"step": 645
},
{
"epoch": 0.15,
"learning_rate": 4.930304456691699e-05,
"loss": 1.6771,
"step": 646
},
{
"epoch": 0.15,
"learning_rate": 4.930086144099551e-05,
"loss": 1.083,
"step": 647
},
{
"epoch": 0.15,
"learning_rate": 4.9298674949720335e-05,
"loss": 1.9102,
"step": 648
},
{
"epoch": 0.15,
"learning_rate": 4.9296485093394283e-05,
"loss": 1.7891,
"step": 649
},
{
"epoch": 0.15,
"learning_rate": 4.92942918723206e-05,
"loss": 1.2337,
"step": 650
},
{
"epoch": 0.15,
"learning_rate": 4.929209528680304e-05,
"loss": 1.8288,
"step": 651
},
{
"epoch": 0.15,
"learning_rate": 4.928989533714579e-05,
"loss": 1.8799,
"step": 652
},
{
"epoch": 0.15,
"learning_rate": 4.92876920236535e-05,
"loss": 2.0931,
"step": 653
},
{
"epoch": 0.15,
"learning_rate": 4.9285485346631334e-05,
"loss": 1.0637,
"step": 654
},
{
"epoch": 0.15,
"learning_rate": 4.9283275306384856e-05,
"loss": 2.1745,
"step": 655
},
{
"epoch": 0.16,
"learning_rate": 4.928106190322015e-05,
"loss": 2.3641,
"step": 656
},
{
"epoch": 0.16,
"learning_rate": 4.927884513744373e-05,
"loss": 1.5699,
"step": 657
},
{
"epoch": 0.16,
"learning_rate": 4.92766250093626e-05,
"loss": 0.9195,
"step": 658
},
{
"epoch": 0.16,
"learning_rate": 4.927440151928421e-05,
"loss": 1.6488,
"step": 659
},
{
"epoch": 0.16,
"learning_rate": 4.927217466751648e-05,
"loss": 1.3872,
"step": 660
},
{
"epoch": 0.16,
"learning_rate": 4.9269944454367813e-05,
"loss": 2.0154,
"step": 661
},
{
"epoch": 0.16,
"learning_rate": 4.926771088014707e-05,
"loss": 1.8308,
"step": 662
},
{
"epoch": 0.16,
"learning_rate": 4.926547394516354e-05,
"loss": 1.6353,
"step": 663
},
{
"epoch": 0.16,
"learning_rate": 4.926323364972705e-05,
"loss": 1.57,
"step": 664
},
{
"epoch": 0.16,
"learning_rate": 4.926098999414782e-05,
"loss": 1.9442,
"step": 665
},
{
"epoch": 0.16,
"learning_rate": 4.925874297873659e-05,
"loss": 1.8304,
"step": 666
},
{
"epoch": 0.16,
"learning_rate": 4.9256492603804526e-05,
"loss": 1.399,
"step": 667
},
{
"epoch": 0.16,
"learning_rate": 4.925423886966328e-05,
"loss": 1.5874,
"step": 668
},
{
"epoch": 0.16,
"learning_rate": 4.925198177662497e-05,
"loss": 1.8739,
"step": 669
},
{
"epoch": 0.16,
"learning_rate": 4.924972132500217e-05,
"loss": 1.6697,
"step": 670
},
{
"epoch": 0.16,
"learning_rate": 4.924745751510792e-05,
"loss": 1.3031,
"step": 671
},
{
"epoch": 0.16,
"learning_rate": 4.9245190347255746e-05,
"loss": 1.5218,
"step": 672
},
{
"epoch": 0.16,
"learning_rate": 4.924291982175959e-05,
"loss": 2.1374,
"step": 673
},
{
"epoch": 0.16,
"learning_rate": 4.924064593893392e-05,
"loss": 1.1152,
"step": 674
},
{
"epoch": 0.16,
"learning_rate": 4.923836869909362e-05,
"loss": 1.8031,
"step": 675
},
{
"epoch": 0.16,
"learning_rate": 4.9236088102554075e-05,
"loss": 2.0702,
"step": 676
},
{
"epoch": 0.16,
"learning_rate": 4.92338041496311e-05,
"loss": 1.6122,
"step": 677
},
{
"epoch": 0.16,
"learning_rate": 4.9231516840641e-05,
"loss": 1.8458,
"step": 678
},
{
"epoch": 0.16,
"learning_rate": 4.9229226175900544e-05,
"loss": 1.5888,
"step": 679
},
{
"epoch": 0.16,
"learning_rate": 4.922693215572695e-05,
"loss": 1.5632,
"step": 680
},
{
"epoch": 0.16,
"learning_rate": 4.922463478043792e-05,
"loss": 1.7268,
"step": 681
},
{
"epoch": 0.16,
"learning_rate": 4.922233405035159e-05,
"loss": 1.6798,
"step": 682
},
{
"epoch": 0.16,
"learning_rate": 4.922002996578661e-05,
"loss": 1.2235,
"step": 683
},
{
"epoch": 0.16,
"learning_rate": 4.921772252706205e-05,
"loss": 1.5721,
"step": 684
},
{
"epoch": 0.16,
"learning_rate": 4.9215411734497464e-05,
"loss": 1.8032,
"step": 685
},
{
"epoch": 0.16,
"learning_rate": 4.921309758841285e-05,
"loss": 1.4632,
"step": 686
},
{
"epoch": 0.16,
"learning_rate": 4.9210780089128715e-05,
"loss": 1.6855,
"step": 687
},
{
"epoch": 0.16,
"learning_rate": 4.920845923696599e-05,
"loss": 1.6799,
"step": 688
},
{
"epoch": 0.16,
"learning_rate": 4.920613503224608e-05,
"loss": 2.0956,
"step": 689
},
{
"epoch": 0.16,
"learning_rate": 4.920380747529085e-05,
"loss": 1.4309,
"step": 690
},
{
"epoch": 0.16,
"learning_rate": 4.9201476566422656e-05,
"loss": 1.1498,
"step": 691
},
{
"epoch": 0.16,
"learning_rate": 4.919914230596429e-05,
"loss": 1.988,
"step": 692
},
{
"epoch": 0.16,
"learning_rate": 4.9196804694239006e-05,
"loss": 1.8407,
"step": 693
},
{
"epoch": 0.16,
"learning_rate": 4.919446373157055e-05,
"loss": 1.7266,
"step": 694
},
{
"epoch": 0.16,
"learning_rate": 4.91921194182831e-05,
"loss": 1.7592,
"step": 695
},
{
"epoch": 0.16,
"learning_rate": 4.918977175470133e-05,
"loss": 1.1552,
"step": 696
},
{
"epoch": 0.16,
"learning_rate": 4.918742074115035e-05,
"loss": 1.5499,
"step": 697
},
{
"epoch": 0.17,
"learning_rate": 4.9185066377955735e-05,
"loss": 1.2127,
"step": 698
},
{
"epoch": 0.17,
"learning_rate": 4.918270866544356e-05,
"loss": 1.4216,
"step": 699
},
{
"epoch": 0.17,
"learning_rate": 4.918034760394031e-05,
"loss": 1.2214,
"step": 700
},
{
"epoch": 0.17,
"learning_rate": 4.917798319377297e-05,
"loss": 1.1203,
"step": 701
},
{
"epoch": 0.17,
"learning_rate": 4.917561543526899e-05,
"loss": 1.6326,
"step": 702
},
{
"epoch": 0.17,
"learning_rate": 4.917324432875627e-05,
"loss": 1.8997,
"step": 703
},
{
"epoch": 0.17,
"learning_rate": 4.917086987456317e-05,
"loss": 2.0038,
"step": 704
},
{
"epoch": 0.17,
"learning_rate": 4.916849207301852e-05,
"loss": 1.6171,
"step": 705
},
{
"epoch": 0.17,
"learning_rate": 4.9166110924451634e-05,
"loss": 1.6013,
"step": 706
},
{
"epoch": 0.17,
"learning_rate": 4.916372642919225e-05,
"loss": 2.0288,
"step": 707
},
{
"epoch": 0.17,
"learning_rate": 4.916133858757059e-05,
"loss": 1.8568,
"step": 708
},
{
"epoch": 0.17,
"learning_rate": 4.915894739991735e-05,
"loss": 2.1949,
"step": 709
},
{
"epoch": 0.17,
"learning_rate": 4.915655286656368e-05,
"loss": 1.4406,
"step": 710
},
{
"epoch": 0.17,
"learning_rate": 4.915415498784118e-05,
"loss": 1.338,
"step": 711
},
{
"epoch": 0.17,
"learning_rate": 4.915175376408193e-05,
"loss": 1.5971,
"step": 712
},
{
"epoch": 0.17,
"learning_rate": 4.914934919561848e-05,
"loss": 1.8418,
"step": 713
},
{
"epoch": 0.17,
"learning_rate": 4.914694128278381e-05,
"loss": 1.2456,
"step": 714
},
{
"epoch": 0.17,
"learning_rate": 4.914453002591139e-05,
"loss": 1.3663,
"step": 715
},
{
"epoch": 0.17,
"learning_rate": 4.9142115425335154e-05,
"loss": 1.226,
"step": 716
},
{
"epoch": 0.17,
"learning_rate": 4.91396974813895e-05,
"loss": 1.6677,
"step": 717
},
{
"epoch": 0.17,
"learning_rate": 4.913727619440926e-05,
"loss": 2.4861,
"step": 718
},
{
"epoch": 0.17,
"learning_rate": 4.913485156472978e-05,
"loss": 1.4411,
"step": 719
},
{
"epoch": 0.17,
"learning_rate": 4.9132423592686816e-05,
"loss": 1.5114,
"step": 720
},
{
"epoch": 0.17,
"learning_rate": 4.912999227861662e-05,
"loss": 1.9969,
"step": 721
},
{
"epoch": 0.17,
"learning_rate": 4.912755762285589e-05,
"loss": 1.7201,
"step": 722
},
{
"epoch": 0.17,
"learning_rate": 4.912511962574181e-05,
"loss": 1.9378,
"step": 723
},
{
"epoch": 0.17,
"learning_rate": 4.912267828761199e-05,
"loss": 1.5512,
"step": 724
},
{
"epoch": 0.17,
"learning_rate": 4.9120233608804546e-05,
"loss": 1.6215,
"step": 725
},
{
"epoch": 0.17,
"learning_rate": 4.9117785589658014e-05,
"loss": 1.6503,
"step": 726
},
{
"epoch": 0.17,
"learning_rate": 4.911533423051143e-05,
"loss": 1.5132,
"step": 727
},
{
"epoch": 0.17,
"learning_rate": 4.9112879531704256e-05,
"loss": 2.3205,
"step": 728
},
{
"epoch": 0.17,
"learning_rate": 4.911042149357646e-05,
"loss": 1.644,
"step": 729
},
{
"epoch": 0.17,
"learning_rate": 4.910796011646843e-05,
"loss": 1.7747,
"step": 730
},
{
"epoch": 0.17,
"learning_rate": 4.9105495400721034e-05,
"loss": 1.9071,
"step": 731
},
{
"epoch": 0.17,
"learning_rate": 4.910302734667562e-05,
"loss": 1.2772,
"step": 732
},
{
"epoch": 0.17,
"learning_rate": 4.910055595467396e-05,
"loss": 1.2807,
"step": 733
},
{
"epoch": 0.17,
"learning_rate": 4.9098081225058326e-05,
"loss": 1.6285,
"step": 734
},
{
"epoch": 0.17,
"learning_rate": 4.9095603158171436e-05,
"loss": 1.7838,
"step": 735
},
{
"epoch": 0.17,
"learning_rate": 4.9093121754356454e-05,
"loss": 1.7611,
"step": 736
},
{
"epoch": 0.17,
"learning_rate": 4.909063701395704e-05,
"loss": 1.8441,
"step": 737
},
{
"epoch": 0.17,
"learning_rate": 4.908814893731728e-05,
"loss": 1.4508,
"step": 738
},
{
"epoch": 0.17,
"learning_rate": 4.908565752478176e-05,
"loss": 1.8418,
"step": 739
},
{
"epoch": 0.18,
"learning_rate": 4.90831627766955e-05,
"loss": 1.1092,
"step": 740
},
{
"epoch": 0.18,
"learning_rate": 4.908066469340399e-05,
"loss": 2.0333,
"step": 741
},
{
"epoch": 0.18,
"learning_rate": 4.907816327525318e-05,
"loss": 1.6242,
"step": 742
},
{
"epoch": 0.18,
"learning_rate": 4.9075658522589486e-05,
"loss": 1.5041,
"step": 743
},
{
"epoch": 0.18,
"learning_rate": 4.9073150435759786e-05,
"loss": 1.5954,
"step": 744
},
{
"epoch": 0.18,
"learning_rate": 4.907063901511141e-05,
"loss": 1.4664,
"step": 745
},
{
"epoch": 0.18,
"learning_rate": 4.906812426099217e-05,
"loss": 1.4326,
"step": 746
},
{
"epoch": 0.18,
"learning_rate": 4.90656061737503e-05,
"loss": 1.6302,
"step": 747
},
{
"epoch": 0.18,
"learning_rate": 4.9063084753734556e-05,
"loss": 2.325,
"step": 748
},
{
"epoch": 0.18,
"learning_rate": 4.906056000129411e-05,
"loss": 1.2344,
"step": 749
},
{
"epoch": 0.18,
"learning_rate": 4.90580319167786e-05,
"loss": 1.5865,
"step": 750
},
{
"epoch": 0.18,
"learning_rate": 4.905550050053813e-05,
"loss": 1.4518,
"step": 751
},
{
"epoch": 0.18,
"learning_rate": 4.905296575292329e-05,
"loss": 1.8988,
"step": 752
},
{
"epoch": 0.18,
"learning_rate": 4.9050427674285085e-05,
"loss": 1.625,
"step": 753
},
{
"epoch": 0.18,
"learning_rate": 4.9047886264975016e-05,
"loss": 1.6413,
"step": 754
},
{
"epoch": 0.18,
"learning_rate": 4.9045341525345035e-05,
"loss": 1.9323,
"step": 755
},
{
"epoch": 0.18,
"learning_rate": 4.904279345574756e-05,
"loss": 1.6475,
"step": 756
},
{
"epoch": 0.18,
"learning_rate": 4.9040242056535465e-05,
"loss": 1.6182,
"step": 757
},
{
"epoch": 0.18,
"learning_rate": 4.903768732806208e-05,
"loss": 1.8794,
"step": 758
},
{
"epoch": 0.18,
"learning_rate": 4.9035129270681196e-05,
"loss": 2.3609,
"step": 759
},
{
"epoch": 0.18,
"learning_rate": 4.903256788474708e-05,
"loss": 1.6079,
"step": 760
},
{
"epoch": 0.18,
"learning_rate": 4.9030003170614456e-05,
"loss": 1.6279,
"step": 761
},
{
"epoch": 0.18,
"learning_rate": 4.9027435128638494e-05,
"loss": 1.4993,
"step": 762
},
{
"epoch": 0.18,
"learning_rate": 4.902486375917483e-05,
"loss": 1.8698,
"step": 763
},
{
"epoch": 0.18,
"learning_rate": 4.902228906257958e-05,
"loss": 1.6502,
"step": 764
},
{
"epoch": 0.18,
"learning_rate": 4.90197110392093e-05,
"loss": 1.2136,
"step": 765
},
{
"epoch": 0.18,
"learning_rate": 4.9017129689421e-05,
"loss": 1.8118,
"step": 766
},
{
"epoch": 0.18,
"learning_rate": 4.901454501357219e-05,
"loss": 1.9347,
"step": 767
},
{
"epoch": 0.18,
"learning_rate": 4.9011957012020793e-05,
"loss": 1.9713,
"step": 768
},
{
"epoch": 0.18,
"learning_rate": 4.900936568512522e-05,
"loss": 2.036,
"step": 769
},
{
"epoch": 0.18,
"learning_rate": 4.900677103324433e-05,
"loss": 1.5848,
"step": 770
},
{
"epoch": 0.18,
"learning_rate": 4.900417305673746e-05,
"loss": 1.1603,
"step": 771
},
{
"epoch": 0.18,
"learning_rate": 4.900157175596438e-05,
"loss": 0.9986,
"step": 772
},
{
"epoch": 0.18,
"learning_rate": 4.8998967131285356e-05,
"loss": 1.431,
"step": 773
},
{
"epoch": 0.18,
"learning_rate": 4.899635918306108e-05,
"loss": 1.6065,
"step": 774
},
{
"epoch": 0.18,
"learning_rate": 4.899374791165273e-05,
"loss": 1.7656,
"step": 775
},
{
"epoch": 0.18,
"learning_rate": 4.899113331742192e-05,
"loss": 1.4621,
"step": 776
},
{
"epoch": 0.18,
"learning_rate": 4.898851540073075e-05,
"loss": 2.0439,
"step": 777
},
{
"epoch": 0.18,
"learning_rate": 4.898589416194176e-05,
"loss": 1.8089,
"step": 778
},
{
"epoch": 0.18,
"learning_rate": 4.898326960141796e-05,
"loss": 1.5008,
"step": 779
},
{
"epoch": 0.18,
"learning_rate": 4.898064171952281e-05,
"loss": 1.4781,
"step": 780
},
{
"epoch": 0.18,
"learning_rate": 4.897801051662025e-05,
"loss": 1.5729,
"step": 781
},
{
"epoch": 0.19,
"learning_rate": 4.8975375993074665e-05,
"loss": 2.0593,
"step": 782
},
{
"epoch": 0.19,
"learning_rate": 4.89727381492509e-05,
"loss": 1.5069,
"step": 783
},
{
"epoch": 0.19,
"learning_rate": 4.897009698551426e-05,
"loss": 1.4593,
"step": 784
},
{
"epoch": 0.19,
"learning_rate": 4.896745250223052e-05,
"loss": 1.535,
"step": 785
},
{
"epoch": 0.19,
"learning_rate": 4.896480469976589e-05,
"loss": 1.4929,
"step": 786
},
{
"epoch": 0.19,
"learning_rate": 4.8962153578487055e-05,
"loss": 1.2304,
"step": 787
},
{
"epoch": 0.19,
"learning_rate": 4.895949913876119e-05,
"loss": 1.9493,
"step": 788
},
{
"epoch": 0.19,
"learning_rate": 4.895684138095588e-05,
"loss": 1.4758,
"step": 789
},
{
"epoch": 0.19,
"learning_rate": 4.895418030543919e-05,
"loss": 1.8714,
"step": 790
},
{
"epoch": 0.19,
"learning_rate": 4.8951515912579645e-05,
"loss": 1.3302,
"step": 791
},
{
"epoch": 0.19,
"learning_rate": 4.894884820274623e-05,
"loss": 2.0195,
"step": 792
},
{
"epoch": 0.19,
"learning_rate": 4.8946177176308396e-05,
"loss": 1.5886,
"step": 793
},
{
"epoch": 0.19,
"learning_rate": 4.8943502833636026e-05,
"loss": 1.7283,
"step": 794
},
{
"epoch": 0.19,
"learning_rate": 4.8940825175099504e-05,
"loss": 1.3368,
"step": 795
},
{
"epoch": 0.19,
"learning_rate": 4.8938144201069635e-05,
"loss": 1.2978,
"step": 796
},
{
"epoch": 0.19,
"learning_rate": 4.8935459911917704e-05,
"loss": 1.4301,
"step": 797
},
{
"epoch": 0.19,
"learning_rate": 4.893277230801546e-05,
"loss": 1.726,
"step": 798
},
{
"epoch": 0.19,
"learning_rate": 4.893008138973508e-05,
"loss": 1.7124,
"step": 799
},
{
"epoch": 0.19,
"learning_rate": 4.892738715744924e-05,
"loss": 1.1582,
"step": 800
},
{
"epoch": 0.19,
"learning_rate": 4.892468961153105e-05,
"loss": 1.6847,
"step": 801
},
{
"epoch": 0.19,
"learning_rate": 4.892198875235409e-05,
"loss": 1.9052,
"step": 802
},
{
"epoch": 0.19,
"learning_rate": 4.891928458029238e-05,
"loss": 1.7829,
"step": 803
},
{
"epoch": 0.19,
"learning_rate": 4.8916577095720424e-05,
"loss": 1.5794,
"step": 804
},
{
"epoch": 0.19,
"learning_rate": 4.891386629901317e-05,
"loss": 2.0447,
"step": 805
},
{
"epoch": 0.19,
"learning_rate": 4.891115219054603e-05,
"loss": 2.0359,
"step": 806
},
{
"epoch": 0.19,
"learning_rate": 4.890843477069487e-05,
"loss": 2.1139,
"step": 807
},
{
"epoch": 0.19,
"learning_rate": 4.890571403983603e-05,
"loss": 1.3969,
"step": 808
},
{
"epoch": 0.19,
"learning_rate": 4.890298999834627e-05,
"loss": 1.7877,
"step": 809
},
{
"epoch": 0.19,
"learning_rate": 4.8900262646602854e-05,
"loss": 1.5858,
"step": 810
},
{
"epoch": 0.19,
"learning_rate": 4.889753198498348e-05,
"loss": 1.6977,
"step": 811
},
{
"epoch": 0.19,
"learning_rate": 4.8894798013866315e-05,
"loss": 1.1872,
"step": 812
},
{
"epoch": 0.19,
"learning_rate": 4.8892060733629963e-05,
"loss": 2.2305,
"step": 813
},
{
"epoch": 0.19,
"learning_rate": 4.888932014465352e-05,
"loss": 1.778,
"step": 814
},
{
"epoch": 0.19,
"learning_rate": 4.888657624731651e-05,
"loss": 1.5463,
"step": 815
},
{
"epoch": 0.19,
"learning_rate": 4.888382904199893e-05,
"loss": 1.4502,
"step": 816
},
{
"epoch": 0.19,
"learning_rate": 4.8881078529081236e-05,
"loss": 1.4547,
"step": 817
},
{
"epoch": 0.19,
"learning_rate": 4.887832470894433e-05,
"loss": 1.4357,
"step": 818
},
{
"epoch": 0.19,
"learning_rate": 4.887556758196959e-05,
"loss": 1.8349,
"step": 819
},
{
"epoch": 0.19,
"learning_rate": 4.8872807148538845e-05,
"loss": 1.543,
"step": 820
},
{
"epoch": 0.19,
"learning_rate": 4.887004340903436e-05,
"loss": 2.1176,
"step": 821
},
{
"epoch": 0.19,
"learning_rate": 4.8867276363838896e-05,
"loss": 1.6262,
"step": 822
},
{
"epoch": 0.19,
"learning_rate": 4.886450601333564e-05,
"loss": 1.5648,
"step": 823
},
{
"epoch": 0.19,
"learning_rate": 4.8861732357908264e-05,
"loss": 1.3948,
"step": 824
},
{
"epoch": 0.2,
"learning_rate": 4.885895539794087e-05,
"loss": 1.3463,
"step": 825
},
{
"epoch": 0.2,
"learning_rate": 4.885617513381803e-05,
"loss": 1.8717,
"step": 826
},
{
"epoch": 0.2,
"learning_rate": 4.885339156592479e-05,
"loss": 1.6983,
"step": 827
},
{
"epoch": 0.2,
"learning_rate": 4.885060469464662e-05,
"loss": 1.734,
"step": 828
},
{
"epoch": 0.2,
"learning_rate": 4.8847814520369475e-05,
"loss": 1.7681,
"step": 829
},
{
"epoch": 0.2,
"learning_rate": 4.884502104347976e-05,
"loss": 1.2692,
"step": 830
},
{
"epoch": 0.2,
"learning_rate": 4.884222426436433e-05,
"loss": 1.4418,
"step": 831
},
{
"epoch": 0.2,
"learning_rate": 4.883942418341051e-05,
"loss": 1.1686,
"step": 832
},
{
"epoch": 0.2,
"learning_rate": 4.883662080100606e-05,
"loss": 1.7017,
"step": 833
},
{
"epoch": 0.2,
"learning_rate": 4.883381411753922e-05,
"loss": 1.4877,
"step": 834
},
{
"epoch": 0.2,
"learning_rate": 4.883100413339869e-05,
"loss": 1.5458,
"step": 835
},
{
"epoch": 0.2,
"learning_rate": 4.8828190848973595e-05,
"loss": 1.5484,
"step": 836
},
{
"epoch": 0.2,
"learning_rate": 4.8825374264653565e-05,
"loss": 1.834,
"step": 837
},
{
"epoch": 0.2,
"learning_rate": 4.882255438082863e-05,
"loss": 2.2466,
"step": 838
},
{
"epoch": 0.2,
"learning_rate": 4.8819731197889334e-05,
"loss": 1.459,
"step": 839
},
{
"epoch": 0.2,
"learning_rate": 4.881690471622663e-05,
"loss": 1.9088,
"step": 840
},
{
"epoch": 0.2,
"learning_rate": 4.881407493623197e-05,
"loss": 1.6538,
"step": 841
},
{
"epoch": 0.2,
"learning_rate": 4.881124185829723e-05,
"loss": 2.1155,
"step": 842
},
{
"epoch": 0.2,
"learning_rate": 4.880840548281475e-05,
"loss": 2.1894,
"step": 843
},
{
"epoch": 0.2,
"learning_rate": 4.8805565810177334e-05,
"loss": 2.033,
"step": 844
},
{
"epoch": 0.2,
"learning_rate": 4.8802722840778246e-05,
"loss": 1.9662,
"step": 845
},
{
"epoch": 0.2,
"learning_rate": 4.87998765750112e-05,
"loss": 1.6538,
"step": 846
},
{
"epoch": 0.2,
"learning_rate": 4.879702701327035e-05,
"loss": 1.259,
"step": 847
},
{
"epoch": 0.2,
"learning_rate": 4.879417415595034e-05,
"loss": 1.6262,
"step": 848
},
{
"epoch": 0.2,
"learning_rate": 4.879131800344626e-05,
"loss": 1.6802,
"step": 849
},
{
"epoch": 0.2,
"learning_rate": 4.8788458556153635e-05,
"loss": 1.336,
"step": 850
},
{
"epoch": 0.2,
"learning_rate": 4.878559581446846e-05,
"loss": 1.8981,
"step": 851
},
{
"epoch": 0.2,
"learning_rate": 4.8782729778787214e-05,
"loss": 1.6329,
"step": 852
},
{
"epoch": 0.2,
"learning_rate": 4.877986044950677e-05,
"loss": 1.1941,
"step": 853
},
{
"epoch": 0.2,
"learning_rate": 4.877698782702451e-05,
"loss": 1.3871,
"step": 854
},
{
"epoch": 0.2,
"learning_rate": 4.8774111911738256e-05,
"loss": 1.829,
"step": 855
},
{
"epoch": 0.2,
"learning_rate": 4.8771232704046283e-05,
"loss": 1.4151,
"step": 856
},
{
"epoch": 0.2,
"learning_rate": 4.8768350204347324e-05,
"loss": 1.7855,
"step": 857
},
{
"epoch": 0.2,
"learning_rate": 4.876546441304056e-05,
"loss": 1.3968,
"step": 858
},
{
"epoch": 0.2,
"learning_rate": 4.876257533052565e-05,
"loss": 1.8227,
"step": 859
},
{
"epoch": 0.2,
"learning_rate": 4.8759682957202685e-05,
"loss": 1.4529,
"step": 860
},
{
"epoch": 0.2,
"learning_rate": 4.875678729347223e-05,
"loss": 1.1851,
"step": 861
},
{
"epoch": 0.2,
"learning_rate": 4.8753888339735274e-05,
"loss": 1.2907,
"step": 862
},
{
"epoch": 0.2,
"learning_rate": 4.8750986096393315e-05,
"loss": 1.7967,
"step": 863
},
{
"epoch": 0.2,
"learning_rate": 4.874808056384825e-05,
"loss": 1.4848,
"step": 864
},
{
"epoch": 0.2,
"learning_rate": 4.8745171742502484e-05,
"loss": 1.6839,
"step": 865
},
{
"epoch": 0.2,
"learning_rate": 4.874225963275882e-05,
"loss": 1.8314,
"step": 866
},
{
"epoch": 0.21,
"learning_rate": 4.873934423502058e-05,
"loss": 2.0282,
"step": 867
},
{
"epoch": 0.21,
"learning_rate": 4.8736425549691475e-05,
"loss": 1.341,
"step": 868
},
{
"epoch": 0.21,
"learning_rate": 4.873350357717573e-05,
"loss": 1.4107,
"step": 869
},
{
"epoch": 0.21,
"learning_rate": 4.8730578317878e-05,
"loss": 1.4731,
"step": 870
},
{
"epoch": 0.21,
"learning_rate": 4.872764977220338e-05,
"loss": 1.9332,
"step": 871
},
{
"epoch": 0.21,
"learning_rate": 4.872471794055744e-05,
"loss": 1.8369,
"step": 872
},
{
"epoch": 0.21,
"learning_rate": 4.872178282334621e-05,
"loss": 1.3453,
"step": 873
},
{
"epoch": 0.21,
"learning_rate": 4.871884442097616e-05,
"loss": 1.7878,
"step": 874
},
{
"epoch": 0.21,
"learning_rate": 4.871590273385421e-05,
"loss": 1.9997,
"step": 875
},
{
"epoch": 0.21,
"learning_rate": 4.871295776238777e-05,
"loss": 1.9064,
"step": 876
},
{
"epoch": 0.21,
"learning_rate": 4.8710009506984656e-05,
"loss": 1.8554,
"step": 877
},
{
"epoch": 0.21,
"learning_rate": 4.8707057968053175e-05,
"loss": 2.1312,
"step": 878
},
{
"epoch": 0.21,
"learning_rate": 4.8704103146002075e-05,
"loss": 1.972,
"step": 879
},
{
"epoch": 0.21,
"learning_rate": 4.870114504124057e-05,
"loss": 2.2831,
"step": 880
},
{
"epoch": 0.21,
"learning_rate": 4.86981836541783e-05,
"loss": 1.4848,
"step": 881
},
{
"epoch": 0.21,
"learning_rate": 4.869521898522539e-05,
"loss": 1.9652,
"step": 882
},
{
"epoch": 0.21,
"learning_rate": 4.86922510347924e-05,
"loss": 1.4183,
"step": 883
},
{
"epoch": 0.21,
"learning_rate": 4.868927980329037e-05,
"loss": 2.0386,
"step": 884
},
{
"epoch": 0.21,
"learning_rate": 4.868630529113075e-05,
"loss": 1.7273,
"step": 885
},
{
"epoch": 0.21,
"learning_rate": 4.8683327498725494e-05,
"loss": 1.3664,
"step": 886
},
{
"epoch": 0.21,
"learning_rate": 4.868034642648699e-05,
"loss": 1.2684,
"step": 887
},
{
"epoch": 0.21,
"learning_rate": 4.867736207482806e-05,
"loss": 1.5481,
"step": 888
},
{
"epoch": 0.21,
"learning_rate": 4.8674374444162005e-05,
"loss": 1.2832,
"step": 889
},
{
"epoch": 0.21,
"learning_rate": 4.867138353490258e-05,
"loss": 2.0168,
"step": 890
},
{
"epoch": 0.21,
"learning_rate": 4.8668389347463973e-05,
"loss": 1.2822,
"step": 891
},
{
"epoch": 0.21,
"learning_rate": 4.8665391882260856e-05,
"loss": 1.6619,
"step": 892
},
{
"epoch": 0.21,
"learning_rate": 4.866239113970833e-05,
"loss": 2.1701,
"step": 893
},
{
"epoch": 0.21,
"learning_rate": 4.8659387120221956e-05,
"loss": 2.0322,
"step": 894
},
{
"epoch": 0.21,
"learning_rate": 4.865637982421776e-05,
"loss": 1.8849,
"step": 895
},
{
"epoch": 0.21,
"learning_rate": 4.8653369252112214e-05,
"loss": 1.4536,
"step": 896
},
{
"epoch": 0.21,
"learning_rate": 4.8650355404322234e-05,
"loss": 1.791,
"step": 897
},
{
"epoch": 0.21,
"learning_rate": 4.86473382812652e-05,
"loss": 1.9112,
"step": 898
},
{
"epoch": 0.21,
"learning_rate": 4.8644317883358956e-05,
"loss": 1.5631,
"step": 899
},
{
"epoch": 0.21,
"learning_rate": 4.8641294211021774e-05,
"loss": 1.4402,
"step": 900
},
{
"epoch": 0.21,
"learning_rate": 4.86382672646724e-05,
"loss": 1.6691,
"step": 901
},
{
"epoch": 0.21,
"learning_rate": 4.863523704473002e-05,
"loss": 1.4176,
"step": 902
},
{
"epoch": 0.21,
"learning_rate": 4.863220355161429e-05,
"loss": 1.6321,
"step": 903
},
{
"epoch": 0.21,
"learning_rate": 4.862916678574531e-05,
"loss": 1.6517,
"step": 904
},
{
"epoch": 0.21,
"learning_rate": 4.862612674754362e-05,
"loss": 1.6625,
"step": 905
},
{
"epoch": 0.21,
"learning_rate": 4.862308343743024e-05,
"loss": 1.2245,
"step": 906
},
{
"epoch": 0.21,
"learning_rate": 4.8620036855826624e-05,
"loss": 1.1567,
"step": 907
},
{
"epoch": 0.21,
"learning_rate": 4.861698700315468e-05,
"loss": 1.4538,
"step": 908
},
{
"epoch": 0.22,
"learning_rate": 4.861393387983677e-05,
"loss": 1.5213,
"step": 909
},
{
"epoch": 0.22,
"learning_rate": 4.8610877486295726e-05,
"loss": 1.8746,
"step": 910
},
{
"epoch": 0.22,
"learning_rate": 4.86078178229548e-05,
"loss": 1.8911,
"step": 911
},
{
"epoch": 0.22,
"learning_rate": 4.860475489023773e-05,
"loss": 1.3414,
"step": 912
},
{
"epoch": 0.22,
"learning_rate": 4.8601688688568695e-05,
"loss": 1.3054,
"step": 913
},
{
"epoch": 0.22,
"learning_rate": 4.8598619218372315e-05,
"loss": 1.9671,
"step": 914
},
{
"epoch": 0.22,
"learning_rate": 4.8595546480073675e-05,
"loss": 1.9155,
"step": 915
},
{
"epoch": 0.22,
"learning_rate": 4.8592470474098304e-05,
"loss": 1.7364,
"step": 916
},
{
"epoch": 0.22,
"learning_rate": 4.858939120087219e-05,
"loss": 1.8287,
"step": 917
},
{
"epoch": 0.22,
"learning_rate": 4.858630866082179e-05,
"loss": 1.2718,
"step": 918
},
{
"epoch": 0.22,
"learning_rate": 4.8583222854373964e-05,
"loss": 1.9186,
"step": 919
},
{
"epoch": 0.22,
"learning_rate": 4.8580133781956086e-05,
"loss": 1.441,
"step": 920
},
{
"epoch": 0.22,
"learning_rate": 4.857704144399594e-05,
"loss": 1.5738,
"step": 921
},
{
"epoch": 0.22,
"learning_rate": 4.857394584092177e-05,
"loss": 1.4612,
"step": 922
},
{
"epoch": 0.22,
"learning_rate": 4.8570846973162284e-05,
"loss": 1.5269,
"step": 923
},
{
"epoch": 0.22,
"learning_rate": 4.856774484114663e-05,
"loss": 1.5464,
"step": 924
},
{
"epoch": 0.22,
"learning_rate": 4.856463944530442e-05,
"loss": 1.8616,
"step": 925
},
{
"epoch": 0.22,
"learning_rate": 4.85615307860657e-05,
"loss": 1.652,
"step": 926
},
{
"epoch": 0.22,
"learning_rate": 4.8558418863860986e-05,
"loss": 1.8906,
"step": 927
},
{
"epoch": 0.22,
"learning_rate": 4.855530367912124e-05,
"loss": 1.7692,
"step": 928
},
{
"epoch": 0.22,
"learning_rate": 4.855218523227787e-05,
"loss": 1.5755,
"step": 929
},
{
"epoch": 0.22,
"learning_rate": 4.854906352376275e-05,
"loss": 1.8406,
"step": 930
},
{
"epoch": 0.22,
"learning_rate": 4.8545938554008184e-05,
"loss": 1.4997,
"step": 931
},
{
"epoch": 0.22,
"learning_rate": 4.854281032344695e-05,
"loss": 1.7373,
"step": 932
},
{
"epoch": 0.22,
"learning_rate": 4.853967883251226e-05,
"loss": 1.8977,
"step": 933
},
{
"epoch": 0.22,
"learning_rate": 4.8536544081637787e-05,
"loss": 1.7549,
"step": 934
},
{
"epoch": 0.22,
"learning_rate": 4.8533406071257644e-05,
"loss": 1.2084,
"step": 935
},
{
"epoch": 0.22,
"learning_rate": 4.853026480180643e-05,
"loss": 1.6226,
"step": 936
},
{
"epoch": 0.22,
"learning_rate": 4.8527120273719144e-05,
"loss": 1.7877,
"step": 937
},
{
"epoch": 0.22,
"learning_rate": 4.852397248743128e-05,
"loss": 1.3214,
"step": 938
},
{
"epoch": 0.22,
"learning_rate": 4.852082144337875e-05,
"loss": 1.4208,
"step": 939
},
{
"epoch": 0.22,
"learning_rate": 4.8517667141997946e-05,
"loss": 1.0795,
"step": 940
},
{
"epoch": 0.22,
"learning_rate": 4.8514509583725684e-05,
"loss": 1.7681,
"step": 941
},
{
"epoch": 0.22,
"learning_rate": 4.851134876899927e-05,
"loss": 1.5075,
"step": 942
},
{
"epoch": 0.22,
"learning_rate": 4.85081846982564e-05,
"loss": 1.4082,
"step": 943
},
{
"epoch": 0.22,
"learning_rate": 4.850501737193529e-05,
"loss": 1.6105,
"step": 944
},
{
"epoch": 0.22,
"learning_rate": 4.850184679047455e-05,
"loss": 1.1266,
"step": 945
},
{
"epoch": 0.22,
"learning_rate": 4.8498672954313275e-05,
"loss": 1.4528,
"step": 946
},
{
"epoch": 0.22,
"learning_rate": 4.849549586389101e-05,
"loss": 1.7253,
"step": 947
},
{
"epoch": 0.22,
"learning_rate": 4.849231551964771e-05,
"loss": 1.5444,
"step": 948
},
{
"epoch": 0.22,
"learning_rate": 4.8489131922023845e-05,
"loss": 2.2302,
"step": 949
},
{
"epoch": 0.22,
"learning_rate": 4.848594507146028e-05,
"loss": 1.4719,
"step": 950
},
{
"epoch": 0.23,
"learning_rate": 4.8482754968398366e-05,
"loss": 1.6143,
"step": 951
},
{
"epoch": 0.23,
"learning_rate": 4.8479561613279876e-05,
"loss": 2.1498,
"step": 952
},
{
"epoch": 0.23,
"learning_rate": 4.847636500654707e-05,
"loss": 1.9538,
"step": 953
},
{
"epoch": 0.23,
"learning_rate": 4.847316514864262e-05,
"loss": 2.097,
"step": 954
},
{
"epoch": 0.23,
"learning_rate": 4.846996204000967e-05,
"loss": 1.7786,
"step": 955
},
{
"epoch": 0.23,
"learning_rate": 4.846675568109179e-05,
"loss": 1.7149,
"step": 956
},
{
"epoch": 0.23,
"learning_rate": 4.8463546072333056e-05,
"loss": 1.6515,
"step": 957
},
{
"epoch": 0.23,
"learning_rate": 4.846033321417793e-05,
"loss": 1.1366,
"step": 958
},
{
"epoch": 0.23,
"learning_rate": 4.845711710707136e-05,
"loss": 1.5233,
"step": 959
},
{
"epoch": 0.23,
"learning_rate": 4.845389775145873e-05,
"loss": 1.7639,
"step": 960
},
{
"epoch": 0.23,
"learning_rate": 4.845067514778589e-05,
"loss": 1.4838,
"step": 961
},
{
"epoch": 0.23,
"learning_rate": 4.844744929649911e-05,
"loss": 1.806,
"step": 962
},
{
"epoch": 0.23,
"learning_rate": 4.8444220198045154e-05,
"loss": 2.4917,
"step": 963
},
{
"epoch": 0.23,
"learning_rate": 4.844098785287119e-05,
"loss": 1.6103,
"step": 964
},
{
"epoch": 0.23,
"learning_rate": 4.843775226142486e-05,
"loss": 0.8902,
"step": 965
},
{
"epoch": 0.23,
"learning_rate": 4.843451342415426e-05,
"loss": 1.7303,
"step": 966
},
{
"epoch": 0.23,
"learning_rate": 4.843127134150791e-05,
"loss": 1.5742,
"step": 967
},
{
"epoch": 0.23,
"learning_rate": 4.842802601393482e-05,
"loss": 2.2771,
"step": 968
},
{
"epoch": 0.23,
"learning_rate": 4.8424777441884405e-05,
"loss": 2.0366,
"step": 969
},
{
"epoch": 0.23,
"learning_rate": 4.8421525625806555e-05,
"loss": 1.2802,
"step": 970
},
{
"epoch": 0.23,
"learning_rate": 4.8418270566151606e-05,
"loss": 1.2683,
"step": 971
},
{
"epoch": 0.23,
"learning_rate": 4.841501226337035e-05,
"loss": 1.4906,
"step": 972
},
{
"epoch": 0.23,
"learning_rate": 4.841175071791401e-05,
"loss": 1.508,
"step": 973
},
{
"epoch": 0.23,
"learning_rate": 4.840848593023426e-05,
"loss": 1.7541,
"step": 974
},
{
"epoch": 0.23,
"learning_rate": 4.840521790078325e-05,
"loss": 1.6975,
"step": 975
},
{
"epoch": 0.23,
"learning_rate": 4.840194663001354e-05,
"loss": 1.7784,
"step": 976
},
{
"epoch": 0.23,
"learning_rate": 4.839867211837817e-05,
"loss": 1.4971,
"step": 977
},
{
"epoch": 0.23,
"learning_rate": 4.839539436633063e-05,
"loss": 2.3331,
"step": 978
},
{
"epoch": 0.23,
"learning_rate": 4.839211337432482e-05,
"loss": 2.0467,
"step": 979
},
{
"epoch": 0.23,
"learning_rate": 4.838882914281513e-05,
"loss": 1.4363,
"step": 980
},
{
"epoch": 0.23,
"learning_rate": 4.838554167225637e-05,
"loss": 1.3551,
"step": 981
},
{
"epoch": 0.23,
"learning_rate": 4.838225096310384e-05,
"loss": 1.8533,
"step": 982
},
{
"epoch": 0.23,
"learning_rate": 4.8378957015813225e-05,
"loss": 1.4613,
"step": 983
},
{
"epoch": 0.23,
"learning_rate": 4.837565983084072e-05,
"loss": 1.5865,
"step": 984
},
{
"epoch": 0.23,
"learning_rate": 4.837235940864293e-05,
"loss": 1.4011,
"step": 985
},
{
"epoch": 0.23,
"learning_rate": 4.8369055749676926e-05,
"loss": 1.3844,
"step": 986
},
{
"epoch": 0.23,
"learning_rate": 4.8365748854400224e-05,
"loss": 1.8292,
"step": 987
},
{
"epoch": 0.23,
"learning_rate": 4.8362438723270775e-05,
"loss": 1.777,
"step": 988
},
{
"epoch": 0.23,
"learning_rate": 4.8359125356747005e-05,
"loss": 1.8838,
"step": 989
},
{
"epoch": 0.23,
"learning_rate": 4.835580875528776e-05,
"loss": 1.2637,
"step": 990
},
{
"epoch": 0.23,
"learning_rate": 4.8352488919352345e-05,
"loss": 1.7713,
"step": 991
},
{
"epoch": 0.23,
"learning_rate": 4.834916584940052e-05,
"loss": 1.477,
"step": 992
},
{
"epoch": 0.23,
"learning_rate": 4.834583954589249e-05,
"loss": 2.2866,
"step": 993
},
{
"epoch": 0.24,
"learning_rate": 4.8342510009288896e-05,
"loss": 1.8303,
"step": 994
},
{
"epoch": 0.24,
"learning_rate": 4.8339177240050835e-05,
"loss": 1.6103,
"step": 995
},
{
"epoch": 0.24,
"learning_rate": 4.833584123863987e-05,
"loss": 1.3783,
"step": 996
},
{
"epoch": 0.24,
"learning_rate": 4.8332502005517976e-05,
"loss": 1.7061,
"step": 997
},
{
"epoch": 0.24,
"learning_rate": 4.83291595411476e-05,
"loss": 1.7425,
"step": 998
},
{
"epoch": 0.24,
"learning_rate": 4.832581384599163e-05,
"loss": 1.4885,
"step": 999
},
{
"epoch": 0.24,
"learning_rate": 4.83224649205134e-05,
"loss": 1.697,
"step": 1000
},
{
"epoch": 0.24,
"learning_rate": 4.831911276517669e-05,
"loss": 2.0936,
"step": 1001
},
{
"epoch": 0.24,
"learning_rate": 4.8315757380445734e-05,
"loss": 1.7644,
"step": 1002
},
{
"epoch": 0.24,
"learning_rate": 4.8312398766785205e-05,
"loss": 1.2963,
"step": 1003
},
{
"epoch": 0.24,
"learning_rate": 4.830903692466024e-05,
"loss": 1.9974,
"step": 1004
},
{
"epoch": 0.24,
"learning_rate": 4.830567185453638e-05,
"loss": 2.0313,
"step": 1005
},
{
"epoch": 0.24,
"learning_rate": 4.830230355687968e-05,
"loss": 1.603,
"step": 1006
},
{
"epoch": 0.24,
"learning_rate": 4.829893203215659e-05,
"loss": 1.5684,
"step": 1007
},
{
"epoch": 0.24,
"learning_rate": 4.829555728083402e-05,
"loss": 1.6818,
"step": 1008
},
{
"epoch": 0.24,
"learning_rate": 4.829217930337933e-05,
"loss": 1.8331,
"step": 1009
},
{
"epoch": 0.24,
"learning_rate": 4.828879810026033e-05,
"loss": 1.4052,
"step": 1010
},
{
"epoch": 0.24,
"learning_rate": 4.8285413671945266e-05,
"loss": 2.1854,
"step": 1011
},
{
"epoch": 0.24,
"learning_rate": 4.828202601890285e-05,
"loss": 1.8066,
"step": 1012
},
{
"epoch": 0.24,
"learning_rate": 4.8278635141602216e-05,
"loss": 1.9945,
"step": 1013
},
{
"epoch": 0.24,
"learning_rate": 4.8275241040512956e-05,
"loss": 1.8455,
"step": 1014
},
{
"epoch": 0.24,
"learning_rate": 4.827184371610511e-05,
"loss": 1.7102,
"step": 1015
},
{
"epoch": 0.24,
"learning_rate": 4.826844316884917e-05,
"loss": 1.2846,
"step": 1016
},
{
"epoch": 0.24,
"learning_rate": 4.826503939921606e-05,
"loss": 0.9758,
"step": 1017
},
{
"epoch": 0.24,
"learning_rate": 4.8261632407677174e-05,
"loss": 1.5587,
"step": 1018
},
{
"epoch": 0.24,
"learning_rate": 4.8258222194704304e-05,
"loss": 1.1849,
"step": 1019
},
{
"epoch": 0.24,
"learning_rate": 4.8254808760769756e-05,
"loss": 1.6938,
"step": 1020
},
{
"epoch": 0.24,
"learning_rate": 4.825139210634623e-05,
"loss": 1.2542,
"step": 1021
},
{
"epoch": 0.24,
"learning_rate": 4.824797223190688e-05,
"loss": 0.9688,
"step": 1022
},
{
"epoch": 0.24,
"learning_rate": 4.824454913792532e-05,
"loss": 1.7337,
"step": 1023
},
{
"epoch": 0.24,
"learning_rate": 4.824112282487562e-05,
"loss": 2.0502,
"step": 1024
},
{
"epoch": 0.24,
"learning_rate": 4.823769329323226e-05,
"loss": 1.8759,
"step": 1025
},
{
"epoch": 0.24,
"learning_rate": 4.823426054347019e-05,
"loss": 1.444,
"step": 1026
},
{
"epoch": 0.24,
"learning_rate": 4.82308245760648e-05,
"loss": 1.5999,
"step": 1027
},
{
"epoch": 0.24,
"learning_rate": 4.822738539149194e-05,
"loss": 1.3271,
"step": 1028
},
{
"epoch": 0.24,
"learning_rate": 4.822394299022788e-05,
"loss": 1.4029,
"step": 1029
},
{
"epoch": 0.24,
"learning_rate": 4.822049737274934e-05,
"loss": 1.7134,
"step": 1030
},
{
"epoch": 0.24,
"learning_rate": 4.821704853953351e-05,
"loss": 1.9922,
"step": 1031
},
{
"epoch": 0.24,
"learning_rate": 4.821359649105801e-05,
"loss": 1.5071,
"step": 1032
},
{
"epoch": 0.24,
"learning_rate": 4.8210141227800885e-05,
"loss": 1.8292,
"step": 1033
},
{
"epoch": 0.24,
"learning_rate": 4.820668275024066e-05,
"loss": 1.3623,
"step": 1034
},
{
"epoch": 0.24,
"learning_rate": 4.8203221058856285e-05,
"loss": 1.5124,
"step": 1035
},
{
"epoch": 0.25,
"learning_rate": 4.8199756154127164e-05,
"loss": 1.8369,
"step": 1036
},
{
"epoch": 0.25,
"learning_rate": 4.819628803653313e-05,
"loss": 1.8629,
"step": 1037
},
{
"epoch": 0.25,
"learning_rate": 4.819281670655448e-05,
"loss": 1.5195,
"step": 1038
},
{
"epoch": 0.25,
"learning_rate": 4.8189342164671944e-05,
"loss": 2.5293,
"step": 1039
},
{
"epoch": 0.25,
"learning_rate": 4.818586441136671e-05,
"loss": 1.8663,
"step": 1040
},
{
"epoch": 0.25,
"learning_rate": 4.818238344712038e-05,
"loss": 1.9068,
"step": 1041
},
{
"epoch": 0.25,
"learning_rate": 4.817889927241506e-05,
"loss": 2.135,
"step": 1042
},
{
"epoch": 0.25,
"learning_rate": 4.817541188773322e-05,
"loss": 1.6423,
"step": 1043
},
{
"epoch": 0.25,
"learning_rate": 4.817192129355785e-05,
"loss": 1.3553,
"step": 1044
},
{
"epoch": 0.25,
"learning_rate": 4.8168427490372335e-05,
"loss": 1.2737,
"step": 1045
},
{
"epoch": 0.25,
"learning_rate": 4.816493047866053e-05,
"loss": 2.1974,
"step": 1046
},
{
"epoch": 0.25,
"learning_rate": 4.816143025890672e-05,
"loss": 1.5832,
"step": 1047
},
{
"epoch": 0.25,
"learning_rate": 4.8157926831595636e-05,
"loss": 2.2052,
"step": 1048
},
{
"epoch": 0.25,
"learning_rate": 4.815442019721247e-05,
"loss": 1.6406,
"step": 1049
},
{
"epoch": 0.25,
"learning_rate": 4.8150910356242834e-05,
"loss": 1.8293,
"step": 1050
},
{
"epoch": 0.25,
"learning_rate": 4.8147397309172803e-05,
"loss": 1.3065,
"step": 1051
},
{
"epoch": 0.25,
"learning_rate": 4.8143881056488884e-05,
"loss": 1.7817,
"step": 1052
},
{
"epoch": 0.25,
"learning_rate": 4.814036159867803e-05,
"loss": 1.3977,
"step": 1053
},
{
"epoch": 0.25,
"learning_rate": 4.8136838936227645e-05,
"loss": 1.4343,
"step": 1054
},
{
"epoch": 0.25,
"learning_rate": 4.813331306962558e-05,
"loss": 1.4871,
"step": 1055
},
{
"epoch": 0.25,
"learning_rate": 4.81297839993601e-05,
"loss": 1.6122,
"step": 1056
},
{
"epoch": 0.25,
"learning_rate": 4.8126251725919954e-05,
"loss": 1.2465,
"step": 1057
},
{
"epoch": 0.25,
"learning_rate": 4.812271624979431e-05,
"loss": 1.4962,
"step": 1058
}
],
"logging_steps": 1,
"max_steps": 8452,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 529,
"total_flos": 6.01330610601984e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}