Merlin-chat / trainer_state.json
KaneLin
first commit
2aba0a4
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 2899,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.5977011494252875e-07,
"loss": 0.9402,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 9.195402298850575e-07,
"loss": 1.5057,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.3793103448275862e-06,
"loss": 1.0876,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 1.839080459770115e-06,
"loss": 1.0012,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 2.2988505747126437e-06,
"loss": 1.022,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 2.7586206896551725e-06,
"loss": 1.0081,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 3.2183908045977012e-06,
"loss": 0.9498,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 3.67816091954023e-06,
"loss": 0.8775,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 4.137931034482759e-06,
"loss": 0.9501,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 4.5977011494252875e-06,
"loss": 0.9846,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 5.057471264367817e-06,
"loss": 0.9396,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 5.517241379310345e-06,
"loss": 0.9214,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 5.977011494252874e-06,
"loss": 1.0231,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 6.4367816091954025e-06,
"loss": 0.9333,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 6.896551724137932e-06,
"loss": 0.8895,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 7.35632183908046e-06,
"loss": 0.926,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 7.81609195402299e-06,
"loss": 0.9232,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 8.275862068965518e-06,
"loss": 0.921,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 8.735632183908047e-06,
"loss": 0.9394,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 9.195402298850575e-06,
"loss": 0.8285,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 9.655172413793105e-06,
"loss": 0.9212,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 1.0114942528735633e-05,
"loss": 0.896,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 1.0574712643678162e-05,
"loss": 0.9455,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 1.103448275862069e-05,
"loss": 0.8889,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 1.1494252873563218e-05,
"loss": 0.8246,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 1.1954022988505748e-05,
"loss": 0.856,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 1.2413793103448277e-05,
"loss": 0.9138,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 1.2873563218390805e-05,
"loss": 0.9036,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.9516,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 1.3793103448275863e-05,
"loss": 0.8998,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 1.4252873563218392e-05,
"loss": 0.8715,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 1.471264367816092e-05,
"loss": 0.5937,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 1.5172413793103448e-05,
"loss": 0.8893,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 1.563218390804598e-05,
"loss": 0.8512,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 1.6091954022988507e-05,
"loss": 0.8879,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 1.6551724137931037e-05,
"loss": 0.5239,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 1.7011494252873563e-05,
"loss": 0.8775,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 1.7471264367816093e-05,
"loss": 0.8806,
"step": 38
},
{
"epoch": 0.01,
"learning_rate": 1.7931034482758623e-05,
"loss": 0.9332,
"step": 39
},
{
"epoch": 0.01,
"learning_rate": 1.839080459770115e-05,
"loss": 0.8894,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 1.885057471264368e-05,
"loss": 0.9093,
"step": 41
},
{
"epoch": 0.01,
"learning_rate": 1.931034482758621e-05,
"loss": 0.8819,
"step": 42
},
{
"epoch": 0.01,
"learning_rate": 1.9770114942528737e-05,
"loss": 0.901,
"step": 43
},
{
"epoch": 0.02,
"learning_rate": 2.0229885057471267e-05,
"loss": 0.8763,
"step": 44
},
{
"epoch": 0.02,
"learning_rate": 2.0689655172413797e-05,
"loss": 0.8631,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 2.1149425287356323e-05,
"loss": 0.8829,
"step": 46
},
{
"epoch": 0.02,
"learning_rate": 2.1609195402298853e-05,
"loss": 0.8025,
"step": 47
},
{
"epoch": 0.02,
"learning_rate": 2.206896551724138e-05,
"loss": 0.8385,
"step": 48
},
{
"epoch": 0.02,
"learning_rate": 2.252873563218391e-05,
"loss": 0.8741,
"step": 49
},
{
"epoch": 0.02,
"learning_rate": 2.2988505747126437e-05,
"loss": 0.8777,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 2.3448275862068967e-05,
"loss": 0.882,
"step": 51
},
{
"epoch": 0.02,
"learning_rate": 2.3908045977011497e-05,
"loss": 0.4812,
"step": 52
},
{
"epoch": 0.02,
"learning_rate": 2.4367816091954027e-05,
"loss": 0.4782,
"step": 53
},
{
"epoch": 0.02,
"learning_rate": 2.4827586206896553e-05,
"loss": 0.8622,
"step": 54
},
{
"epoch": 0.02,
"learning_rate": 2.5287356321839083e-05,
"loss": 0.8823,
"step": 55
},
{
"epoch": 0.02,
"learning_rate": 2.574712643678161e-05,
"loss": 0.8563,
"step": 56
},
{
"epoch": 0.02,
"learning_rate": 2.620689655172414e-05,
"loss": 0.8575,
"step": 57
},
{
"epoch": 0.02,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.8838,
"step": 58
},
{
"epoch": 0.02,
"learning_rate": 2.7126436781609197e-05,
"loss": 0.8725,
"step": 59
},
{
"epoch": 0.02,
"learning_rate": 2.7586206896551727e-05,
"loss": 0.8174,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 2.8045977011494257e-05,
"loss": 0.849,
"step": 61
},
{
"epoch": 0.02,
"learning_rate": 2.8505747126436783e-05,
"loss": 0.8715,
"step": 62
},
{
"epoch": 0.02,
"learning_rate": 2.8965517241379313e-05,
"loss": 0.8626,
"step": 63
},
{
"epoch": 0.02,
"learning_rate": 2.942528735632184e-05,
"loss": 0.8661,
"step": 64
},
{
"epoch": 0.02,
"learning_rate": 2.988505747126437e-05,
"loss": 0.9179,
"step": 65
},
{
"epoch": 0.02,
"learning_rate": 3.0344827586206897e-05,
"loss": 0.4568,
"step": 66
},
{
"epoch": 0.02,
"learning_rate": 3.080459770114942e-05,
"loss": 0.8262,
"step": 67
},
{
"epoch": 0.02,
"learning_rate": 3.126436781609196e-05,
"loss": 0.7933,
"step": 68
},
{
"epoch": 0.02,
"learning_rate": 3.172413793103448e-05,
"loss": 0.8421,
"step": 69
},
{
"epoch": 0.02,
"learning_rate": 3.218390804597701e-05,
"loss": 0.871,
"step": 70
},
{
"epoch": 0.02,
"learning_rate": 3.264367816091954e-05,
"loss": 0.877,
"step": 71
},
{
"epoch": 0.02,
"learning_rate": 3.310344827586207e-05,
"loss": 0.8557,
"step": 72
},
{
"epoch": 0.03,
"learning_rate": 3.3563218390804597e-05,
"loss": 0.8597,
"step": 73
},
{
"epoch": 0.03,
"learning_rate": 3.4022988505747127e-05,
"loss": 0.4287,
"step": 74
},
{
"epoch": 0.03,
"learning_rate": 3.4482758620689657e-05,
"loss": 0.8207,
"step": 75
},
{
"epoch": 0.03,
"learning_rate": 3.4942528735632187e-05,
"loss": 0.8642,
"step": 76
},
{
"epoch": 0.03,
"learning_rate": 3.540229885057472e-05,
"loss": 0.8433,
"step": 77
},
{
"epoch": 0.03,
"learning_rate": 3.586206896551725e-05,
"loss": 0.8605,
"step": 78
},
{
"epoch": 0.03,
"learning_rate": 3.632183908045977e-05,
"loss": 0.8293,
"step": 79
},
{
"epoch": 0.03,
"learning_rate": 3.67816091954023e-05,
"loss": 0.8528,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 3.724137931034483e-05,
"loss": 0.8781,
"step": 81
},
{
"epoch": 0.03,
"learning_rate": 3.770114942528736e-05,
"loss": 0.934,
"step": 82
},
{
"epoch": 0.03,
"learning_rate": 3.816091954022988e-05,
"loss": 0.8369,
"step": 83
},
{
"epoch": 0.03,
"learning_rate": 3.862068965517242e-05,
"loss": 0.8653,
"step": 84
},
{
"epoch": 0.03,
"learning_rate": 3.908045977011495e-05,
"loss": 0.8614,
"step": 85
},
{
"epoch": 0.03,
"learning_rate": 3.954022988505747e-05,
"loss": 0.8422,
"step": 86
},
{
"epoch": 0.03,
"learning_rate": 4e-05,
"loss": 0.8306,
"step": 87
},
{
"epoch": 0.03,
"learning_rate": 3.9999987518434296e-05,
"loss": 0.8832,
"step": 88
},
{
"epoch": 0.03,
"learning_rate": 3.999995007375273e-05,
"loss": 0.8645,
"step": 89
},
{
"epoch": 0.03,
"learning_rate": 3.999988766600207e-05,
"loss": 0.8229,
"step": 90
},
{
"epoch": 0.03,
"learning_rate": 3.9999800295260184e-05,
"loss": 0.4377,
"step": 91
},
{
"epoch": 0.03,
"learning_rate": 3.9999687961636146e-05,
"loss": 0.8927,
"step": 92
},
{
"epoch": 0.03,
"learning_rate": 3.999955066527015e-05,
"loss": 0.4511,
"step": 93
},
{
"epoch": 0.03,
"learning_rate": 3.999938840633357e-05,
"loss": 0.8767,
"step": 94
},
{
"epoch": 0.03,
"learning_rate": 3.999920118502894e-05,
"loss": 0.8491,
"step": 95
},
{
"epoch": 0.03,
"learning_rate": 3.999898900158992e-05,
"loss": 0.8732,
"step": 96
},
{
"epoch": 0.03,
"learning_rate": 3.999875185628136e-05,
"loss": 0.884,
"step": 97
},
{
"epoch": 0.03,
"learning_rate": 3.999848974939926e-05,
"loss": 0.8785,
"step": 98
},
{
"epoch": 0.03,
"learning_rate": 3.999820268127076e-05,
"loss": 0.8476,
"step": 99
},
{
"epoch": 0.03,
"learning_rate": 3.9997890652254175e-05,
"loss": 0.7797,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 3.999755366273896e-05,
"loss": 0.8611,
"step": 101
},
{
"epoch": 0.04,
"learning_rate": 3.9997191713145735e-05,
"loss": 0.8813,
"step": 102
},
{
"epoch": 0.04,
"learning_rate": 3.999680480392626e-05,
"loss": 0.8417,
"step": 103
},
{
"epoch": 0.04,
"learning_rate": 3.9996392935563476e-05,
"loss": 0.8261,
"step": 104
},
{
"epoch": 0.04,
"learning_rate": 3.9995956108571444e-05,
"loss": 0.8526,
"step": 105
},
{
"epoch": 0.04,
"learning_rate": 3.999549432349539e-05,
"loss": 0.8462,
"step": 106
},
{
"epoch": 0.04,
"learning_rate": 3.999500758091171e-05,
"loss": 0.8528,
"step": 107
},
{
"epoch": 0.04,
"learning_rate": 3.999449588142792e-05,
"loss": 0.8737,
"step": 108
},
{
"epoch": 0.04,
"learning_rate": 3.999395922568272e-05,
"loss": 0.8245,
"step": 109
},
{
"epoch": 0.04,
"learning_rate": 3.999339761434591e-05,
"loss": 0.8444,
"step": 110
},
{
"epoch": 0.04,
"learning_rate": 3.99928110481185e-05,
"loss": 0.8162,
"step": 111
},
{
"epoch": 0.04,
"learning_rate": 3.99921995277326e-05,
"loss": 0.8911,
"step": 112
},
{
"epoch": 0.04,
"learning_rate": 3.9991563053951476e-05,
"loss": 0.8987,
"step": 113
},
{
"epoch": 0.04,
"learning_rate": 3.999090162756957e-05,
"loss": 0.8302,
"step": 114
},
{
"epoch": 0.04,
"learning_rate": 3.9990215249412426e-05,
"loss": 0.8726,
"step": 115
},
{
"epoch": 0.04,
"learning_rate": 3.9989503920336766e-05,
"loss": 0.8308,
"step": 116
},
{
"epoch": 0.04,
"learning_rate": 3.9988767641230425e-05,
"loss": 0.8732,
"step": 117
},
{
"epoch": 0.04,
"learning_rate": 3.99880064130124e-05,
"loss": 0.8499,
"step": 118
},
{
"epoch": 0.04,
"learning_rate": 3.9987220236632833e-05,
"loss": 0.7688,
"step": 119
},
{
"epoch": 0.04,
"learning_rate": 3.998640911307298e-05,
"loss": 0.8761,
"step": 120
},
{
"epoch": 0.04,
"learning_rate": 3.998557304334527e-05,
"loss": 0.8794,
"step": 121
},
{
"epoch": 0.04,
"learning_rate": 3.998471202849322e-05,
"loss": 0.871,
"step": 122
},
{
"epoch": 0.04,
"learning_rate": 3.9983826069591535e-05,
"loss": 0.8104,
"step": 123
},
{
"epoch": 0.04,
"learning_rate": 3.998291516774602e-05,
"loss": 0.8368,
"step": 124
},
{
"epoch": 0.04,
"learning_rate": 3.998197932409364e-05,
"loss": 0.8718,
"step": 125
},
{
"epoch": 0.04,
"learning_rate": 3.998101853980244e-05,
"loss": 0.8078,
"step": 126
},
{
"epoch": 0.04,
"learning_rate": 3.998003281607166e-05,
"loss": 0.7789,
"step": 127
},
{
"epoch": 0.04,
"learning_rate": 3.997902215413163e-05,
"loss": 0.8346,
"step": 128
},
{
"epoch": 0.04,
"learning_rate": 3.99779865552438e-05,
"loss": 0.8151,
"step": 129
},
{
"epoch": 0.04,
"learning_rate": 3.9976926020700785e-05,
"loss": 0.8229,
"step": 130
},
{
"epoch": 0.05,
"learning_rate": 3.997584055182628e-05,
"loss": 0.8665,
"step": 131
},
{
"epoch": 0.05,
"learning_rate": 3.997473014997512e-05,
"loss": 0.7767,
"step": 132
},
{
"epoch": 0.05,
"learning_rate": 3.997359481653327e-05,
"loss": 0.8302,
"step": 133
},
{
"epoch": 0.05,
"learning_rate": 3.9972434552917795e-05,
"loss": 0.4425,
"step": 134
},
{
"epoch": 0.05,
"learning_rate": 3.99712493605769e-05,
"loss": 0.8477,
"step": 135
},
{
"epoch": 0.05,
"learning_rate": 3.997003924098987e-05,
"loss": 0.8333,
"step": 136
},
{
"epoch": 0.05,
"learning_rate": 3.996880419566713e-05,
"loss": 0.8127,
"step": 137
},
{
"epoch": 0.05,
"learning_rate": 3.996754422615023e-05,
"loss": 0.8304,
"step": 138
},
{
"epoch": 0.05,
"learning_rate": 3.9966259334011774e-05,
"loss": 0.7907,
"step": 139
},
{
"epoch": 0.05,
"learning_rate": 3.9964949520855536e-05,
"loss": 0.7977,
"step": 140
},
{
"epoch": 0.05,
"learning_rate": 3.996361478831636e-05,
"loss": 0.8588,
"step": 141
},
{
"epoch": 0.05,
"learning_rate": 3.99622551380602e-05,
"loss": 0.8554,
"step": 142
},
{
"epoch": 0.05,
"learning_rate": 3.996087057178411e-05,
"loss": 0.8187,
"step": 143
},
{
"epoch": 0.05,
"learning_rate": 3.9959461091216256e-05,
"loss": 0.8389,
"step": 144
},
{
"epoch": 0.05,
"learning_rate": 3.995802669811587e-05,
"loss": 0.8397,
"step": 145
},
{
"epoch": 0.05,
"learning_rate": 3.9956567394273325e-05,
"loss": 0.8386,
"step": 146
},
{
"epoch": 0.05,
"learning_rate": 3.9955083181510046e-05,
"loss": 0.805,
"step": 147
},
{
"epoch": 0.05,
"learning_rate": 3.995357406167856e-05,
"loss": 0.4265,
"step": 148
},
{
"epoch": 0.05,
"learning_rate": 3.995204003666249e-05,
"loss": 0.8252,
"step": 149
},
{
"epoch": 0.05,
"learning_rate": 3.9950481108376535e-05,
"loss": 0.8774,
"step": 150
},
{
"epoch": 0.05,
"learning_rate": 3.9948897278766496e-05,
"loss": 0.8479,
"step": 151
},
{
"epoch": 0.05,
"learning_rate": 3.9947288549809225e-05,
"loss": 0.8036,
"step": 152
},
{
"epoch": 0.05,
"learning_rate": 3.994565492351267e-05,
"loss": 0.8482,
"step": 153
},
{
"epoch": 0.05,
"learning_rate": 3.994399640191586e-05,
"loss": 0.79,
"step": 154
},
{
"epoch": 0.05,
"learning_rate": 3.994231298708888e-05,
"loss": 0.8301,
"step": 155
},
{
"epoch": 0.05,
"learning_rate": 3.99406046811329e-05,
"loss": 0.8434,
"step": 156
},
{
"epoch": 0.05,
"learning_rate": 3.993887148618015e-05,
"loss": 0.7691,
"step": 157
},
{
"epoch": 0.05,
"learning_rate": 3.993711340439394e-05,
"loss": 0.4511,
"step": 158
},
{
"epoch": 0.05,
"learning_rate": 3.9935330437968617e-05,
"loss": 0.8437,
"step": 159
},
{
"epoch": 0.06,
"learning_rate": 3.9933522589129616e-05,
"loss": 0.8111,
"step": 160
},
{
"epoch": 0.06,
"learning_rate": 3.99316898601334e-05,
"loss": 0.8408,
"step": 161
},
{
"epoch": 0.06,
"learning_rate": 3.992983225326751e-05,
"loss": 0.7988,
"step": 162
},
{
"epoch": 0.06,
"learning_rate": 3.9927949770850535e-05,
"loss": 0.438,
"step": 163
},
{
"epoch": 0.06,
"learning_rate": 3.99260424152321e-05,
"loss": 0.8711,
"step": 164
},
{
"epoch": 0.06,
"learning_rate": 3.9924110188792883e-05,
"loss": 0.8113,
"step": 165
},
{
"epoch": 0.06,
"learning_rate": 3.992215309394461e-05,
"loss": 0.8481,
"step": 166
},
{
"epoch": 0.06,
"learning_rate": 3.992017113313004e-05,
"loss": 0.837,
"step": 167
},
{
"epoch": 0.06,
"learning_rate": 3.991816430882297e-05,
"loss": 0.8492,
"step": 168
},
{
"epoch": 0.06,
"learning_rate": 3.991613262352823e-05,
"loss": 0.8579,
"step": 169
},
{
"epoch": 0.06,
"learning_rate": 3.991407607978168e-05,
"loss": 0.7891,
"step": 170
},
{
"epoch": 0.06,
"learning_rate": 3.9911994680150215e-05,
"loss": 0.8407,
"step": 171
},
{
"epoch": 0.06,
"learning_rate": 3.9909888427231746e-05,
"loss": 0.8416,
"step": 172
},
{
"epoch": 0.06,
"learning_rate": 3.9907757323655206e-05,
"loss": 0.8071,
"step": 173
},
{
"epoch": 0.06,
"learning_rate": 3.9905601372080536e-05,
"loss": 0.8515,
"step": 174
},
{
"epoch": 0.06,
"learning_rate": 3.990342057519872e-05,
"loss": 0.8387,
"step": 175
},
{
"epoch": 0.06,
"learning_rate": 3.990121493573171e-05,
"loss": 0.8086,
"step": 176
},
{
"epoch": 0.06,
"learning_rate": 3.9898984456432514e-05,
"loss": 0.8721,
"step": 177
},
{
"epoch": 0.06,
"learning_rate": 3.98967291400851e-05,
"loss": 0.8225,
"step": 178
},
{
"epoch": 0.06,
"learning_rate": 3.989444898950447e-05,
"loss": 0.4115,
"step": 179
},
{
"epoch": 0.06,
"learning_rate": 3.98921440075366e-05,
"loss": 0.8133,
"step": 180
},
{
"epoch": 0.06,
"learning_rate": 3.988981419705847e-05,
"loss": 0.83,
"step": 181
},
{
"epoch": 0.06,
"learning_rate": 3.988745956097806e-05,
"loss": 0.852,
"step": 182
},
{
"epoch": 0.06,
"learning_rate": 3.98850801022343e-05,
"loss": 0.8621,
"step": 183
},
{
"epoch": 0.06,
"learning_rate": 3.988267582379714e-05,
"loss": 0.8137,
"step": 184
},
{
"epoch": 0.06,
"learning_rate": 3.988024672866751e-05,
"loss": 0.8576,
"step": 185
},
{
"epoch": 0.06,
"learning_rate": 3.987779281987728e-05,
"loss": 0.8412,
"step": 186
},
{
"epoch": 0.06,
"learning_rate": 3.9875314100489325e-05,
"loss": 0.8765,
"step": 187
},
{
"epoch": 0.06,
"learning_rate": 3.987281057359746e-05,
"loss": 0.8193,
"step": 188
},
{
"epoch": 0.07,
"learning_rate": 3.98702822423265e-05,
"loss": 0.7915,
"step": 189
},
{
"epoch": 0.07,
"learning_rate": 3.9867729109832184e-05,
"loss": 0.8287,
"step": 190
},
{
"epoch": 0.07,
"learning_rate": 3.986515117930122e-05,
"loss": 0.8164,
"step": 191
},
{
"epoch": 0.07,
"learning_rate": 3.986254845395128e-05,
"loss": 0.7971,
"step": 192
},
{
"epoch": 0.07,
"learning_rate": 3.985992093703096e-05,
"loss": 0.8431,
"step": 193
},
{
"epoch": 0.07,
"learning_rate": 3.985726863181982e-05,
"loss": 0.8562,
"step": 194
},
{
"epoch": 0.07,
"learning_rate": 3.985459154162835e-05,
"loss": 0.8313,
"step": 195
},
{
"epoch": 0.07,
"learning_rate": 3.9851889669797985e-05,
"loss": 0.8296,
"step": 196
},
{
"epoch": 0.07,
"learning_rate": 3.984916301970107e-05,
"loss": 0.8037,
"step": 197
},
{
"epoch": 0.07,
"learning_rate": 3.98464115947409e-05,
"loss": 0.8417,
"step": 198
},
{
"epoch": 0.07,
"learning_rate": 3.984363539835169e-05,
"loss": 0.405,
"step": 199
},
{
"epoch": 0.07,
"learning_rate": 3.984083443399855e-05,
"loss": 0.8516,
"step": 200
},
{
"epoch": 0.07,
"learning_rate": 3.9838008705177537e-05,
"loss": 0.8885,
"step": 201
},
{
"epoch": 0.07,
"learning_rate": 3.98351582154156e-05,
"loss": 0.8318,
"step": 202
},
{
"epoch": 0.07,
"learning_rate": 3.9832282968270595e-05,
"loss": 0.8369,
"step": 203
},
{
"epoch": 0.07,
"learning_rate": 3.982938296733128e-05,
"loss": 0.8768,
"step": 204
},
{
"epoch": 0.07,
"learning_rate": 3.982645821621732e-05,
"loss": 0.8748,
"step": 205
},
{
"epoch": 0.07,
"learning_rate": 3.982350871857924e-05,
"loss": 0.7885,
"step": 206
},
{
"epoch": 0.07,
"learning_rate": 3.982053447809849e-05,
"loss": 0.8228,
"step": 207
},
{
"epoch": 0.07,
"learning_rate": 3.9817535498487385e-05,
"loss": 0.7955,
"step": 208
},
{
"epoch": 0.07,
"learning_rate": 3.9814511783489125e-05,
"loss": 0.7952,
"step": 209
},
{
"epoch": 0.07,
"learning_rate": 3.981146333687778e-05,
"loss": 0.8165,
"step": 210
},
{
"epoch": 0.07,
"learning_rate": 3.9808390162458286e-05,
"loss": 0.8335,
"step": 211
},
{
"epoch": 0.07,
"learning_rate": 3.980529226406644e-05,
"loss": 0.8411,
"step": 212
},
{
"epoch": 0.07,
"learning_rate": 3.980216964556892e-05,
"loss": 0.8428,
"step": 213
},
{
"epoch": 0.07,
"learning_rate": 3.979902231086322e-05,
"loss": 0.8512,
"step": 214
},
{
"epoch": 0.07,
"learning_rate": 3.9795850263877725e-05,
"loss": 0.8327,
"step": 215
},
{
"epoch": 0.07,
"learning_rate": 3.979265350857164e-05,
"loss": 0.796,
"step": 216
},
{
"epoch": 0.07,
"learning_rate": 3.978943204893501e-05,
"loss": 0.8228,
"step": 217
},
{
"epoch": 0.08,
"learning_rate": 3.978618588898873e-05,
"loss": 0.8282,
"step": 218
},
{
"epoch": 0.08,
"learning_rate": 3.9782915032784514e-05,
"loss": 0.8115,
"step": 219
},
{
"epoch": 0.08,
"learning_rate": 3.977961948440491e-05,
"loss": 0.7817,
"step": 220
},
{
"epoch": 0.08,
"learning_rate": 3.977629924796326e-05,
"loss": 0.8583,
"step": 221
},
{
"epoch": 0.08,
"learning_rate": 3.9772954327603756e-05,
"loss": 0.8653,
"step": 222
},
{
"epoch": 0.08,
"learning_rate": 3.976958472750137e-05,
"loss": 0.7902,
"step": 223
},
{
"epoch": 0.08,
"learning_rate": 3.97661904518619e-05,
"loss": 0.8298,
"step": 224
},
{
"epoch": 0.08,
"learning_rate": 3.976277150492193e-05,
"loss": 0.802,
"step": 225
},
{
"epoch": 0.08,
"learning_rate": 3.975932789094883e-05,
"loss": 0.8319,
"step": 226
},
{
"epoch": 0.08,
"learning_rate": 3.975585961424079e-05,
"loss": 0.8505,
"step": 227
},
{
"epoch": 0.08,
"learning_rate": 3.9752366679126754e-05,
"loss": 0.8574,
"step": 228
},
{
"epoch": 0.08,
"learning_rate": 3.974884908996645e-05,
"loss": 0.804,
"step": 229
},
{
"epoch": 0.08,
"learning_rate": 3.974530685115038e-05,
"loss": 0.849,
"step": 230
},
{
"epoch": 0.08,
"learning_rate": 3.9741739967099806e-05,
"loss": 0.7818,
"step": 231
},
{
"epoch": 0.08,
"learning_rate": 3.973814844226677e-05,
"loss": 0.8232,
"step": 232
},
{
"epoch": 0.08,
"learning_rate": 3.973453228113405e-05,
"loss": 0.8285,
"step": 233
},
{
"epoch": 0.08,
"learning_rate": 3.9730891488215186e-05,
"loss": 0.7865,
"step": 234
},
{
"epoch": 0.08,
"learning_rate": 3.972722606805445e-05,
"loss": 0.8463,
"step": 235
},
{
"epoch": 0.08,
"learning_rate": 3.972353602522687e-05,
"loss": 0.833,
"step": 236
},
{
"epoch": 0.08,
"learning_rate": 3.971982136433819e-05,
"loss": 0.8491,
"step": 237
},
{
"epoch": 0.08,
"learning_rate": 3.971608209002489e-05,
"loss": 0.8078,
"step": 238
},
{
"epoch": 0.08,
"learning_rate": 3.971231820695417e-05,
"loss": 0.8273,
"step": 239
},
{
"epoch": 0.08,
"learning_rate": 3.9708529719823954e-05,
"loss": 0.8243,
"step": 240
},
{
"epoch": 0.08,
"learning_rate": 3.9704716633362845e-05,
"loss": 0.4161,
"step": 241
},
{
"epoch": 0.08,
"learning_rate": 3.97008789523302e-05,
"loss": 0.8315,
"step": 242
},
{
"epoch": 0.08,
"learning_rate": 3.969701668151603e-05,
"loss": 0.8276,
"step": 243
},
{
"epoch": 0.08,
"learning_rate": 3.969312982574105e-05,
"loss": 0.7834,
"step": 244
},
{
"epoch": 0.08,
"learning_rate": 3.968921838985667e-05,
"loss": 0.8149,
"step": 245
},
{
"epoch": 0.08,
"learning_rate": 3.968528237874498e-05,
"loss": 0.8653,
"step": 246
},
{
"epoch": 0.09,
"learning_rate": 3.968132179731872e-05,
"loss": 0.8682,
"step": 247
},
{
"epoch": 0.09,
"learning_rate": 3.9677336650521336e-05,
"loss": 0.8556,
"step": 248
},
{
"epoch": 0.09,
"learning_rate": 3.967332694332691e-05,
"loss": 0.8563,
"step": 249
},
{
"epoch": 0.09,
"learning_rate": 3.966929268074018e-05,
"loss": 0.8751,
"step": 250
},
{
"epoch": 0.09,
"learning_rate": 3.9665233867796535e-05,
"loss": 0.8267,
"step": 251
},
{
"epoch": 0.09,
"learning_rate": 3.966115050956202e-05,
"loss": 0.8196,
"step": 252
},
{
"epoch": 0.09,
"learning_rate": 3.9657042611133294e-05,
"loss": 0.853,
"step": 253
},
{
"epoch": 0.09,
"learning_rate": 3.9652910177637664e-05,
"loss": 0.7999,
"step": 254
},
{
"epoch": 0.09,
"learning_rate": 3.9648753214233054e-05,
"loss": 0.8164,
"step": 255
},
{
"epoch": 0.09,
"learning_rate": 3.9644571726108e-05,
"loss": 0.7948,
"step": 256
},
{
"epoch": 0.09,
"learning_rate": 3.9640365718481655e-05,
"loss": 0.8147,
"step": 257
},
{
"epoch": 0.09,
"learning_rate": 3.963613519660379e-05,
"loss": 0.8845,
"step": 258
},
{
"epoch": 0.09,
"learning_rate": 3.963188016575473e-05,
"loss": 0.7914,
"step": 259
},
{
"epoch": 0.09,
"learning_rate": 3.962760063124544e-05,
"loss": 0.8592,
"step": 260
},
{
"epoch": 0.09,
"learning_rate": 3.9623296598417454e-05,
"loss": 0.7995,
"step": 261
},
{
"epoch": 0.09,
"learning_rate": 3.961896807264286e-05,
"loss": 0.7763,
"step": 262
},
{
"epoch": 0.09,
"learning_rate": 3.961461505932435e-05,
"loss": 0.7937,
"step": 263
},
{
"epoch": 0.09,
"learning_rate": 3.961023756389516e-05,
"loss": 0.7908,
"step": 264
},
{
"epoch": 0.09,
"learning_rate": 3.960583559181909e-05,
"loss": 0.8745,
"step": 265
},
{
"epoch": 0.09,
"learning_rate": 3.960140914859049e-05,
"loss": 0.8177,
"step": 266
},
{
"epoch": 0.09,
"learning_rate": 3.9596958239734264e-05,
"loss": 0.8565,
"step": 267
},
{
"epoch": 0.09,
"learning_rate": 3.959248287080583e-05,
"loss": 0.8399,
"step": 268
},
{
"epoch": 0.09,
"learning_rate": 3.9587983047391156e-05,
"loss": 0.83,
"step": 269
},
{
"epoch": 0.09,
"learning_rate": 3.958345877510672e-05,
"loss": 0.8269,
"step": 270
},
{
"epoch": 0.09,
"learning_rate": 3.957891005959953e-05,
"loss": 0.7862,
"step": 271
},
{
"epoch": 0.09,
"learning_rate": 3.957433690654709e-05,
"loss": 0.7951,
"step": 272
},
{
"epoch": 0.09,
"learning_rate": 3.9569739321657416e-05,
"loss": 0.7215,
"step": 273
},
{
"epoch": 0.09,
"learning_rate": 3.956511731066901e-05,
"loss": 0.8236,
"step": 274
},
{
"epoch": 0.09,
"learning_rate": 3.9560470879350866e-05,
"loss": 0.8032,
"step": 275
},
{
"epoch": 0.1,
"learning_rate": 3.955580003350245e-05,
"loss": 0.8098,
"step": 276
},
{
"epoch": 0.1,
"learning_rate": 3.955110477895373e-05,
"loss": 0.7955,
"step": 277
},
{
"epoch": 0.1,
"learning_rate": 3.9546385121565095e-05,
"loss": 0.7326,
"step": 278
},
{
"epoch": 0.1,
"learning_rate": 3.954164106722743e-05,
"loss": 0.8042,
"step": 279
},
{
"epoch": 0.1,
"learning_rate": 3.953687262186205e-05,
"loss": 0.8167,
"step": 280
},
{
"epoch": 0.1,
"learning_rate": 3.953207979142073e-05,
"loss": 0.7923,
"step": 281
},
{
"epoch": 0.1,
"learning_rate": 3.9527262581885674e-05,
"loss": 0.7835,
"step": 282
},
{
"epoch": 0.1,
"learning_rate": 3.952242099926951e-05,
"loss": 0.8413,
"step": 283
},
{
"epoch": 0.1,
"learning_rate": 3.951755504961527e-05,
"loss": 0.4165,
"step": 284
},
{
"epoch": 0.1,
"learning_rate": 3.951266473899646e-05,
"loss": 0.8339,
"step": 285
},
{
"epoch": 0.1,
"learning_rate": 3.950775007351693e-05,
"loss": 0.7708,
"step": 286
},
{
"epoch": 0.1,
"learning_rate": 3.9502811059310955e-05,
"loss": 0.8626,
"step": 287
},
{
"epoch": 0.1,
"learning_rate": 3.9497847702543196e-05,
"loss": 0.8071,
"step": 288
},
{
"epoch": 0.1,
"learning_rate": 3.9492860009408706e-05,
"loss": 0.8627,
"step": 289
},
{
"epoch": 0.1,
"learning_rate": 3.94878479861329e-05,
"loss": 0.8046,
"step": 290
},
{
"epoch": 0.1,
"learning_rate": 3.948281163897157e-05,
"loss": 0.7891,
"step": 291
},
{
"epoch": 0.1,
"learning_rate": 3.947775097421087e-05,
"loss": 0.7641,
"step": 292
},
{
"epoch": 0.1,
"learning_rate": 3.94726659981673e-05,
"loss": 0.7698,
"step": 293
},
{
"epoch": 0.1,
"learning_rate": 3.9467556717187703e-05,
"loss": 0.8076,
"step": 294
},
{
"epoch": 0.1,
"learning_rate": 3.9462423137649264e-05,
"loss": 0.8313,
"step": 295
},
{
"epoch": 0.1,
"learning_rate": 3.945726526595949e-05,
"loss": 0.8058,
"step": 296
},
{
"epoch": 0.1,
"learning_rate": 3.9452083108556225e-05,
"loss": 0.7852,
"step": 297
},
{
"epoch": 0.1,
"learning_rate": 3.94468766719076e-05,
"loss": 0.8346,
"step": 298
},
{
"epoch": 0.1,
"learning_rate": 3.944164596251207e-05,
"loss": 0.7754,
"step": 299
},
{
"epoch": 0.1,
"learning_rate": 3.9436390986898375e-05,
"loss": 0.7864,
"step": 300
},
{
"epoch": 0.1,
"learning_rate": 3.943111175162554e-05,
"loss": 0.8179,
"step": 301
},
{
"epoch": 0.1,
"learning_rate": 3.942580826328289e-05,
"loss": 0.7893,
"step": 302
},
{
"epoch": 0.1,
"learning_rate": 3.942048052849001e-05,
"loss": 0.8504,
"step": 303
},
{
"epoch": 0.1,
"learning_rate": 3.941512855389674e-05,
"loss": 0.8526,
"step": 304
},
{
"epoch": 0.11,
"learning_rate": 3.940975234618319e-05,
"loss": 0.7969,
"step": 305
},
{
"epoch": 0.11,
"learning_rate": 3.94043519120597e-05,
"loss": 0.8272,
"step": 306
},
{
"epoch": 0.11,
"learning_rate": 3.939892725826685e-05,
"loss": 0.8065,
"step": 307
},
{
"epoch": 0.11,
"learning_rate": 3.939347839157548e-05,
"loss": 0.8129,
"step": 308
},
{
"epoch": 0.11,
"learning_rate": 3.938800531878661e-05,
"loss": 0.8042,
"step": 309
},
{
"epoch": 0.11,
"learning_rate": 3.9382508046731505e-05,
"loss": 0.7911,
"step": 310
},
{
"epoch": 0.11,
"learning_rate": 3.937698658227161e-05,
"loss": 0.8448,
"step": 311
},
{
"epoch": 0.11,
"learning_rate": 3.937144093229858e-05,
"loss": 0.4081,
"step": 312
},
{
"epoch": 0.11,
"learning_rate": 3.9365871103734264e-05,
"loss": 0.8087,
"step": 313
},
{
"epoch": 0.11,
"learning_rate": 3.936027710353067e-05,
"loss": 0.8025,
"step": 314
},
{
"epoch": 0.11,
"learning_rate": 3.935465893866998e-05,
"loss": 0.8866,
"step": 315
},
{
"epoch": 0.11,
"learning_rate": 3.934901661616456e-05,
"loss": 0.8298,
"step": 316
},
{
"epoch": 0.11,
"learning_rate": 3.93433501430569e-05,
"loss": 0.8121,
"step": 317
},
{
"epoch": 0.11,
"learning_rate": 3.933765952641965e-05,
"loss": 0.8111,
"step": 318
},
{
"epoch": 0.11,
"learning_rate": 3.933194477335559e-05,
"loss": 0.7749,
"step": 319
},
{
"epoch": 0.11,
"learning_rate": 3.932620589099763e-05,
"loss": 0.8032,
"step": 320
},
{
"epoch": 0.11,
"learning_rate": 3.932044288650879e-05,
"loss": 0.8226,
"step": 321
},
{
"epoch": 0.11,
"learning_rate": 3.93146557670822e-05,
"loss": 0.7978,
"step": 322
},
{
"epoch": 0.11,
"learning_rate": 3.930884453994109e-05,
"loss": 0.8079,
"step": 323
},
{
"epoch": 0.11,
"learning_rate": 3.930300921233879e-05,
"loss": 0.4156,
"step": 324
},
{
"epoch": 0.11,
"learning_rate": 3.92971497915587e-05,
"loss": 0.854,
"step": 325
},
{
"epoch": 0.11,
"learning_rate": 3.9291266284914285e-05,
"loss": 0.8472,
"step": 326
},
{
"epoch": 0.11,
"learning_rate": 3.92853586997491e-05,
"loss": 0.7834,
"step": 327
},
{
"epoch": 0.11,
"learning_rate": 3.9279427043436706e-05,
"loss": 0.8295,
"step": 328
},
{
"epoch": 0.11,
"learning_rate": 3.927347132338077e-05,
"loss": 0.8295,
"step": 329
},
{
"epoch": 0.11,
"learning_rate": 3.926749154701495e-05,
"loss": 0.8108,
"step": 330
},
{
"epoch": 0.11,
"learning_rate": 3.926148772180295e-05,
"loss": 0.8701,
"step": 331
},
{
"epoch": 0.11,
"learning_rate": 3.925545985523847e-05,
"loss": 0.4196,
"step": 332
},
{
"epoch": 0.11,
"learning_rate": 3.924940795484525e-05,
"loss": 0.8015,
"step": 333
},
{
"epoch": 0.12,
"learning_rate": 3.924333202817699e-05,
"loss": 0.8148,
"step": 334
},
{
"epoch": 0.12,
"learning_rate": 3.923723208281741e-05,
"loss": 0.7559,
"step": 335
},
{
"epoch": 0.12,
"learning_rate": 3.9231108126380195e-05,
"loss": 0.7787,
"step": 336
},
{
"epoch": 0.12,
"learning_rate": 3.9224960166509e-05,
"loss": 0.4241,
"step": 337
},
{
"epoch": 0.12,
"learning_rate": 3.9218788210877436e-05,
"loss": 0.8204,
"step": 338
},
{
"epoch": 0.12,
"learning_rate": 3.921259226718908e-05,
"loss": 0.7681,
"step": 339
},
{
"epoch": 0.12,
"learning_rate": 3.920637234317744e-05,
"loss": 0.8204,
"step": 340
},
{
"epoch": 0.12,
"learning_rate": 3.920012844660594e-05,
"loss": 0.8221,
"step": 341
},
{
"epoch": 0.12,
"learning_rate": 3.919386058526796e-05,
"loss": 0.8141,
"step": 342
},
{
"epoch": 0.12,
"learning_rate": 3.918756876698676e-05,
"loss": 0.784,
"step": 343
},
{
"epoch": 0.12,
"learning_rate": 3.918125299961552e-05,
"loss": 0.4079,
"step": 344
},
{
"epoch": 0.12,
"learning_rate": 3.917491329103731e-05,
"loss": 0.8401,
"step": 345
},
{
"epoch": 0.12,
"learning_rate": 3.916854964916506e-05,
"loss": 0.7943,
"step": 346
},
{
"epoch": 0.12,
"learning_rate": 3.916216208194161e-05,
"loss": 0.7433,
"step": 347
},
{
"epoch": 0.12,
"learning_rate": 3.9155750597339634e-05,
"loss": 0.8194,
"step": 348
},
{
"epoch": 0.12,
"learning_rate": 3.914931520336168e-05,
"loss": 0.8369,
"step": 349
},
{
"epoch": 0.12,
"learning_rate": 3.914285590804012e-05,
"loss": 0.791,
"step": 350
},
{
"epoch": 0.12,
"learning_rate": 3.913637271943716e-05,
"loss": 0.8244,
"step": 351
},
{
"epoch": 0.12,
"learning_rate": 3.912986564564485e-05,
"loss": 0.767,
"step": 352
},
{
"epoch": 0.12,
"learning_rate": 3.912333469478502e-05,
"loss": 0.8399,
"step": 353
},
{
"epoch": 0.12,
"learning_rate": 3.911677987500933e-05,
"loss": 0.8349,
"step": 354
},
{
"epoch": 0.12,
"learning_rate": 3.911020119449922e-05,
"loss": 0.776,
"step": 355
},
{
"epoch": 0.12,
"learning_rate": 3.910359866146591e-05,
"loss": 0.8198,
"step": 356
},
{
"epoch": 0.12,
"learning_rate": 3.9096972284150394e-05,
"loss": 0.8084,
"step": 357
},
{
"epoch": 0.12,
"learning_rate": 3.909032207082344e-05,
"loss": 0.7981,
"step": 358
},
{
"epoch": 0.12,
"learning_rate": 3.908364802978554e-05,
"loss": 0.7958,
"step": 359
},
{
"epoch": 0.12,
"learning_rate": 3.907695016936695e-05,
"loss": 0.8499,
"step": 360
},
{
"epoch": 0.12,
"learning_rate": 3.907022849792765e-05,
"loss": 0.7909,
"step": 361
},
{
"epoch": 0.12,
"learning_rate": 3.906348302385733e-05,
"loss": 0.8207,
"step": 362
},
{
"epoch": 0.13,
"learning_rate": 3.90567137555754e-05,
"loss": 0.7949,
"step": 363
},
{
"epoch": 0.13,
"learning_rate": 3.904992070153098e-05,
"loss": 0.7879,
"step": 364
},
{
"epoch": 0.13,
"learning_rate": 3.904310387020285e-05,
"loss": 0.8097,
"step": 365
},
{
"epoch": 0.13,
"learning_rate": 3.903626327009949e-05,
"loss": 0.7733,
"step": 366
},
{
"epoch": 0.13,
"learning_rate": 3.9029398909759034e-05,
"loss": 0.764,
"step": 367
},
{
"epoch": 0.13,
"learning_rate": 3.9022510797749286e-05,
"loss": 0.8315,
"step": 368
},
{
"epoch": 0.13,
"learning_rate": 3.9015598942667684e-05,
"loss": 0.4171,
"step": 369
},
{
"epoch": 0.13,
"learning_rate": 3.90086633531413e-05,
"loss": 0.812,
"step": 370
},
{
"epoch": 0.13,
"learning_rate": 3.900170403782685e-05,
"loss": 0.83,
"step": 371
},
{
"epoch": 0.13,
"learning_rate": 3.899472100541064e-05,
"loss": 0.3824,
"step": 372
},
{
"epoch": 0.13,
"learning_rate": 3.898771426460859e-05,
"loss": 0.857,
"step": 373
},
{
"epoch": 0.13,
"learning_rate": 3.8980683824166206e-05,
"loss": 0.7712,
"step": 374
},
{
"epoch": 0.13,
"learning_rate": 3.897362969285857e-05,
"loss": 0.8184,
"step": 375
},
{
"epoch": 0.13,
"learning_rate": 3.896655187949037e-05,
"loss": 0.7676,
"step": 376
},
{
"epoch": 0.13,
"learning_rate": 3.8959450392895794e-05,
"loss": 0.8361,
"step": 377
},
{
"epoch": 0.13,
"learning_rate": 3.8952325241938635e-05,
"loss": 0.8477,
"step": 378
},
{
"epoch": 0.13,
"learning_rate": 3.894517643551218e-05,
"loss": 0.8239,
"step": 379
},
{
"epoch": 0.13,
"learning_rate": 3.893800398253926e-05,
"loss": 0.7891,
"step": 380
},
{
"epoch": 0.13,
"learning_rate": 3.893080789197223e-05,
"loss": 0.847,
"step": 381
},
{
"epoch": 0.13,
"learning_rate": 3.892358817279293e-05,
"loss": 0.8123,
"step": 382
},
{
"epoch": 0.13,
"learning_rate": 3.8916344834012695e-05,
"loss": 0.858,
"step": 383
},
{
"epoch": 0.13,
"learning_rate": 3.890907788467236e-05,
"loss": 0.7825,
"step": 384
},
{
"epoch": 0.13,
"learning_rate": 3.89017873338422e-05,
"loss": 0.792,
"step": 385
},
{
"epoch": 0.13,
"learning_rate": 3.889447319062198e-05,
"loss": 0.8063,
"step": 386
},
{
"epoch": 0.13,
"learning_rate": 3.888713546414088e-05,
"loss": 0.7702,
"step": 387
},
{
"epoch": 0.13,
"learning_rate": 3.887977416355754e-05,
"loss": 0.7753,
"step": 388
},
{
"epoch": 0.13,
"learning_rate": 3.887238929806001e-05,
"loss": 0.7893,
"step": 389
},
{
"epoch": 0.13,
"learning_rate": 3.886498087686577e-05,
"loss": 0.8034,
"step": 390
},
{
"epoch": 0.13,
"learning_rate": 3.885754890922169e-05,
"loss": 0.7871,
"step": 391
},
{
"epoch": 0.14,
"learning_rate": 3.8850093404404005e-05,
"loss": 0.8417,
"step": 392
},
{
"epoch": 0.14,
"learning_rate": 3.884261437171838e-05,
"loss": 0.8514,
"step": 393
},
{
"epoch": 0.14,
"learning_rate": 3.883511182049981e-05,
"loss": 0.7803,
"step": 394
},
{
"epoch": 0.14,
"learning_rate": 3.882758576011264e-05,
"loss": 0.8034,
"step": 395
},
{
"epoch": 0.14,
"learning_rate": 3.8820036199950594e-05,
"loss": 0.402,
"step": 396
},
{
"epoch": 0.14,
"learning_rate": 3.881246314943669e-05,
"loss": 0.7807,
"step": 397
},
{
"epoch": 0.14,
"learning_rate": 3.8804866618023284e-05,
"loss": 0.8522,
"step": 398
},
{
"epoch": 0.14,
"learning_rate": 3.879724661519204e-05,
"loss": 0.8236,
"step": 399
},
{
"epoch": 0.14,
"learning_rate": 3.878960315045391e-05,
"loss": 0.8122,
"step": 400
},
{
"epoch": 0.14,
"learning_rate": 3.878193623334914e-05,
"loss": 0.8011,
"step": 401
},
{
"epoch": 0.14,
"learning_rate": 3.877424587344724e-05,
"loss": 0.7763,
"step": 402
},
{
"epoch": 0.14,
"learning_rate": 3.876653208034698e-05,
"loss": 0.8636,
"step": 403
},
{
"epoch": 0.14,
"learning_rate": 3.875879486367639e-05,
"loss": 0.4228,
"step": 404
},
{
"epoch": 0.14,
"learning_rate": 3.8751034233092715e-05,
"loss": 0.3859,
"step": 405
},
{
"epoch": 0.14,
"learning_rate": 3.8743250198282446e-05,
"loss": 0.7803,
"step": 406
},
{
"epoch": 0.14,
"learning_rate": 3.873544276896129e-05,
"loss": 0.8324,
"step": 407
},
{
"epoch": 0.14,
"learning_rate": 3.8727611954874114e-05,
"loss": 0.8461,
"step": 408
},
{
"epoch": 0.14,
"learning_rate": 3.871975776579502e-05,
"loss": 0.8309,
"step": 409
},
{
"epoch": 0.14,
"learning_rate": 3.8711880211527244e-05,
"loss": 0.8143,
"step": 410
},
{
"epoch": 0.14,
"learning_rate": 3.870397930190324e-05,
"loss": 0.788,
"step": 411
},
{
"epoch": 0.14,
"learning_rate": 3.869605504678455e-05,
"loss": 0.8087,
"step": 412
},
{
"epoch": 0.14,
"learning_rate": 3.8688107456061904e-05,
"loss": 0.8139,
"step": 413
},
{
"epoch": 0.14,
"learning_rate": 3.8680136539655134e-05,
"loss": 0.8355,
"step": 414
},
{
"epoch": 0.14,
"learning_rate": 3.8672142307513184e-05,
"loss": 0.7906,
"step": 415
},
{
"epoch": 0.14,
"learning_rate": 3.8664124769614116e-05,
"loss": 0.7793,
"step": 416
},
{
"epoch": 0.14,
"learning_rate": 3.8656083935965075e-05,
"loss": 0.8609,
"step": 417
},
{
"epoch": 0.14,
"learning_rate": 3.864801981660227e-05,
"loss": 0.8076,
"step": 418
},
{
"epoch": 0.14,
"learning_rate": 3.8639932421591e-05,
"loss": 0.8265,
"step": 419
},
{
"epoch": 0.14,
"learning_rate": 3.8631821761025583e-05,
"loss": 0.7843,
"step": 420
},
{
"epoch": 0.15,
"learning_rate": 3.86236878450294e-05,
"loss": 0.8508,
"step": 421
},
{
"epoch": 0.15,
"learning_rate": 3.8615530683754857e-05,
"loss": 0.8475,
"step": 422
},
{
"epoch": 0.15,
"learning_rate": 3.860735028738337e-05,
"loss": 0.8076,
"step": 423
},
{
"epoch": 0.15,
"learning_rate": 3.859914666612534e-05,
"loss": 0.7891,
"step": 424
},
{
"epoch": 0.15,
"learning_rate": 3.859091983022018e-05,
"loss": 0.7552,
"step": 425
},
{
"epoch": 0.15,
"learning_rate": 3.8582669789936267e-05,
"loss": 0.8325,
"step": 426
},
{
"epoch": 0.15,
"learning_rate": 3.857439655557095e-05,
"loss": 0.7821,
"step": 427
},
{
"epoch": 0.15,
"learning_rate": 3.856610013745051e-05,
"loss": 0.8116,
"step": 428
},
{
"epoch": 0.15,
"learning_rate": 3.8557780545930194e-05,
"loss": 0.7736,
"step": 429
},
{
"epoch": 0.15,
"learning_rate": 3.8549437791394126e-05,
"loss": 0.8211,
"step": 430
},
{
"epoch": 0.15,
"learning_rate": 3.8541071884255393e-05,
"loss": 0.7896,
"step": 431
},
{
"epoch": 0.15,
"learning_rate": 3.8532682834955954e-05,
"loss": 0.8202,
"step": 432
},
{
"epoch": 0.15,
"learning_rate": 3.852427065396665e-05,
"loss": 0.7768,
"step": 433
},
{
"epoch": 0.15,
"learning_rate": 3.85158353517872e-05,
"loss": 0.8046,
"step": 434
},
{
"epoch": 0.15,
"learning_rate": 3.8507376938946184e-05,
"loss": 0.8202,
"step": 435
},
{
"epoch": 0.15,
"learning_rate": 3.849889542600103e-05,
"loss": 0.7725,
"step": 436
},
{
"epoch": 0.15,
"learning_rate": 3.849039082353799e-05,
"loss": 0.8497,
"step": 437
},
{
"epoch": 0.15,
"learning_rate": 3.848186314217213e-05,
"loss": 0.7992,
"step": 438
},
{
"epoch": 0.15,
"learning_rate": 3.847331239254735e-05,
"loss": 0.7924,
"step": 439
},
{
"epoch": 0.15,
"learning_rate": 3.8464738585336306e-05,
"loss": 0.4306,
"step": 440
},
{
"epoch": 0.15,
"learning_rate": 3.8456141731240465e-05,
"loss": 0.723,
"step": 441
},
{
"epoch": 0.15,
"learning_rate": 3.844752184099004e-05,
"loss": 0.8231,
"step": 442
},
{
"epoch": 0.15,
"learning_rate": 3.843887892534402e-05,
"loss": 0.807,
"step": 443
},
{
"epoch": 0.15,
"learning_rate": 3.8430212995090095e-05,
"loss": 0.7831,
"step": 444
},
{
"epoch": 0.15,
"learning_rate": 3.8421524061044706e-05,
"loss": 0.7691,
"step": 445
},
{
"epoch": 0.15,
"learning_rate": 3.841281213405301e-05,
"loss": 0.7765,
"step": 446
},
{
"epoch": 0.15,
"learning_rate": 3.8404077224988855e-05,
"loss": 0.8366,
"step": 447
},
{
"epoch": 0.15,
"learning_rate": 3.8395319344754776e-05,
"loss": 0.7925,
"step": 448
},
{
"epoch": 0.15,
"learning_rate": 3.838653850428198e-05,
"loss": 0.82,
"step": 449
},
{
"epoch": 0.16,
"learning_rate": 3.8377734714530326e-05,
"loss": 0.7762,
"step": 450
},
{
"epoch": 0.16,
"learning_rate": 3.836890798648832e-05,
"loss": 0.7638,
"step": 451
},
{
"epoch": 0.16,
"learning_rate": 3.836005833117311e-05,
"loss": 0.8011,
"step": 452
},
{
"epoch": 0.16,
"learning_rate": 3.8351185759630435e-05,
"loss": 0.8046,
"step": 453
},
{
"epoch": 0.16,
"learning_rate": 3.834229028293467e-05,
"loss": 0.8109,
"step": 454
},
{
"epoch": 0.16,
"learning_rate": 3.833337191218876e-05,
"loss": 0.7957,
"step": 455
},
{
"epoch": 0.16,
"learning_rate": 3.832443065852423e-05,
"loss": 0.7919,
"step": 456
},
{
"epoch": 0.16,
"learning_rate": 3.8315466533101154e-05,
"loss": 0.8043,
"step": 457
},
{
"epoch": 0.16,
"learning_rate": 3.830647954710816e-05,
"loss": 0.8204,
"step": 458
},
{
"epoch": 0.16,
"learning_rate": 3.8297469711762435e-05,
"loss": 0.7694,
"step": 459
},
{
"epoch": 0.16,
"learning_rate": 3.828843703830965e-05,
"loss": 0.7442,
"step": 460
},
{
"epoch": 0.16,
"learning_rate": 3.8279381538024004e-05,
"loss": 0.8317,
"step": 461
},
{
"epoch": 0.16,
"learning_rate": 3.827030322220817e-05,
"loss": 0.7681,
"step": 462
},
{
"epoch": 0.16,
"learning_rate": 3.826120210219331e-05,
"loss": 0.823,
"step": 463
},
{
"epoch": 0.16,
"learning_rate": 3.825207818933904e-05,
"loss": 0.8378,
"step": 464
},
{
"epoch": 0.16,
"learning_rate": 3.824293149503345e-05,
"loss": 0.8174,
"step": 465
},
{
"epoch": 0.16,
"learning_rate": 3.8233762030693034e-05,
"loss": 0.8109,
"step": 466
},
{
"epoch": 0.16,
"learning_rate": 3.822456980776272e-05,
"loss": 0.7571,
"step": 467
},
{
"epoch": 0.16,
"learning_rate": 3.8215354837715836e-05,
"loss": 0.7923,
"step": 468
},
{
"epoch": 0.16,
"learning_rate": 3.8206117132054124e-05,
"loss": 0.8006,
"step": 469
},
{
"epoch": 0.16,
"learning_rate": 3.819685670230767e-05,
"loss": 0.8278,
"step": 470
},
{
"epoch": 0.16,
"learning_rate": 3.818757356003495e-05,
"loss": 0.816,
"step": 471
},
{
"epoch": 0.16,
"learning_rate": 3.8178267716822783e-05,
"loss": 0.7714,
"step": 472
},
{
"epoch": 0.16,
"learning_rate": 3.816893918428631e-05,
"loss": 0.8113,
"step": 473
},
{
"epoch": 0.16,
"learning_rate": 3.8159587974068995e-05,
"loss": 0.4283,
"step": 474
},
{
"epoch": 0.16,
"learning_rate": 3.815021409784262e-05,
"loss": 0.7759,
"step": 475
},
{
"epoch": 0.16,
"learning_rate": 3.8140817567307254e-05,
"loss": 0.8284,
"step": 476
},
{
"epoch": 0.16,
"learning_rate": 3.813139839419124e-05,
"loss": 0.798,
"step": 477
},
{
"epoch": 0.16,
"learning_rate": 3.8121956590251153e-05,
"loss": 0.7972,
"step": 478
},
{
"epoch": 0.17,
"learning_rate": 3.8112492167271886e-05,
"loss": 0.8449,
"step": 479
},
{
"epoch": 0.17,
"learning_rate": 3.810300513706649e-05,
"loss": 0.8099,
"step": 480
},
{
"epoch": 0.17,
"learning_rate": 3.8093495511476275e-05,
"loss": 0.7779,
"step": 481
},
{
"epoch": 0.17,
"learning_rate": 3.808396330237074e-05,
"loss": 0.8269,
"step": 482
},
{
"epoch": 0.17,
"learning_rate": 3.8074408521647576e-05,
"loss": 0.7421,
"step": 483
},
{
"epoch": 0.17,
"learning_rate": 3.8064831181232647e-05,
"loss": 0.7764,
"step": 484
},
{
"epoch": 0.17,
"learning_rate": 3.8055231293079965e-05,
"loss": 0.7988,
"step": 485
},
{
"epoch": 0.17,
"learning_rate": 3.804560886917171e-05,
"loss": 0.7654,
"step": 486
},
{
"epoch": 0.17,
"learning_rate": 3.803596392151815e-05,
"loss": 0.818,
"step": 487
},
{
"epoch": 0.17,
"learning_rate": 3.802629646215771e-05,
"loss": 0.3948,
"step": 488
},
{
"epoch": 0.17,
"learning_rate": 3.801660650315689e-05,
"loss": 0.7699,
"step": 489
},
{
"epoch": 0.17,
"learning_rate": 3.800689405661027e-05,
"loss": 0.8374,
"step": 490
},
{
"epoch": 0.17,
"learning_rate": 3.7997159134640506e-05,
"loss": 0.7782,
"step": 491
},
{
"epoch": 0.17,
"learning_rate": 3.7987401749398296e-05,
"loss": 0.827,
"step": 492
},
{
"epoch": 0.17,
"learning_rate": 3.79776219130624e-05,
"loss": 0.7285,
"step": 493
},
{
"epoch": 0.17,
"learning_rate": 3.796781963783958e-05,
"loss": 0.775,
"step": 494
},
{
"epoch": 0.17,
"learning_rate": 3.7957994935964605e-05,
"loss": 0.8588,
"step": 495
},
{
"epoch": 0.17,
"learning_rate": 3.794814781970025e-05,
"loss": 0.7997,
"step": 496
},
{
"epoch": 0.17,
"learning_rate": 3.793827830133725e-05,
"loss": 0.8068,
"step": 497
},
{
"epoch": 0.17,
"learning_rate": 3.792838639319431e-05,
"loss": 0.4077,
"step": 498
},
{
"epoch": 0.17,
"learning_rate": 3.791847210761808e-05,
"loss": 0.8552,
"step": 499
},
{
"epoch": 0.17,
"learning_rate": 3.7908535456983146e-05,
"loss": 0.8735,
"step": 500
},
{
"epoch": 0.17,
"learning_rate": 3.7898576453692e-05,
"loss": 0.8313,
"step": 501
},
{
"epoch": 0.17,
"learning_rate": 3.7888595110175034e-05,
"loss": 0.8627,
"step": 502
},
{
"epoch": 0.17,
"learning_rate": 3.787859143889054e-05,
"loss": 0.7675,
"step": 503
},
{
"epoch": 0.17,
"learning_rate": 3.786856545232465e-05,
"loss": 0.7675,
"step": 504
},
{
"epoch": 0.17,
"learning_rate": 3.7858517162991375e-05,
"loss": 0.8188,
"step": 505
},
{
"epoch": 0.17,
"learning_rate": 3.784844658343255e-05,
"loss": 0.8064,
"step": 506
},
{
"epoch": 0.17,
"learning_rate": 3.783835372621783e-05,
"loss": 0.7875,
"step": 507
},
{
"epoch": 0.18,
"learning_rate": 3.782823860394469e-05,
"loss": 0.8009,
"step": 508
},
{
"epoch": 0.18,
"learning_rate": 3.7818101229238394e-05,
"loss": 0.7815,
"step": 509
},
{
"epoch": 0.18,
"learning_rate": 3.780794161475195e-05,
"loss": 0.7589,
"step": 510
},
{
"epoch": 0.18,
"learning_rate": 3.7797759773166166e-05,
"loss": 0.7722,
"step": 511
},
{
"epoch": 0.18,
"learning_rate": 3.778755571718957e-05,
"loss": 0.8003,
"step": 512
},
{
"epoch": 0.18,
"learning_rate": 3.777732945955841e-05,
"loss": 0.7806,
"step": 513
},
{
"epoch": 0.18,
"learning_rate": 3.776708101303667e-05,
"loss": 0.7881,
"step": 514
},
{
"epoch": 0.18,
"learning_rate": 3.7756810390416017e-05,
"loss": 0.7883,
"step": 515
},
{
"epoch": 0.18,
"learning_rate": 3.774651760451578e-05,
"loss": 0.7858,
"step": 516
},
{
"epoch": 0.18,
"learning_rate": 3.773620266818299e-05,
"loss": 0.7766,
"step": 517
},
{
"epoch": 0.18,
"learning_rate": 3.772586559429229e-05,
"loss": 0.8352,
"step": 518
},
{
"epoch": 0.18,
"learning_rate": 3.771550639574596e-05,
"loss": 0.7803,
"step": 519
},
{
"epoch": 0.18,
"learning_rate": 3.770512508547392e-05,
"loss": 0.8241,
"step": 520
},
{
"epoch": 0.18,
"learning_rate": 3.7694721676433655e-05,
"loss": 0.8075,
"step": 521
},
{
"epoch": 0.18,
"learning_rate": 3.768429618161025e-05,
"loss": 0.7607,
"step": 522
},
{
"epoch": 0.18,
"learning_rate": 3.767384861401636e-05,
"loss": 0.8386,
"step": 523
},
{
"epoch": 0.18,
"learning_rate": 3.766337898669219e-05,
"loss": 0.8471,
"step": 524
},
{
"epoch": 0.18,
"learning_rate": 3.765288731270546e-05,
"loss": 0.4467,
"step": 525
},
{
"epoch": 0.18,
"learning_rate": 3.764237360515144e-05,
"loss": 0.7927,
"step": 526
},
{
"epoch": 0.18,
"learning_rate": 3.763183787715286e-05,
"loss": 0.7855,
"step": 527
},
{
"epoch": 0.18,
"learning_rate": 3.762128014185998e-05,
"loss": 0.744,
"step": 528
},
{
"epoch": 0.18,
"learning_rate": 3.76107004124505e-05,
"loss": 0.8291,
"step": 529
},
{
"epoch": 0.18,
"learning_rate": 3.7600098702129565e-05,
"loss": 0.7873,
"step": 530
},
{
"epoch": 0.18,
"learning_rate": 3.758947502412978e-05,
"loss": 0.7909,
"step": 531
},
{
"epoch": 0.18,
"learning_rate": 3.757882939171117e-05,
"loss": 0.7769,
"step": 532
},
{
"epoch": 0.18,
"learning_rate": 3.7568161818161135e-05,
"loss": 0.8047,
"step": 533
},
{
"epoch": 0.18,
"learning_rate": 3.755747231679449e-05,
"loss": 0.7889,
"step": 534
},
{
"epoch": 0.18,
"learning_rate": 3.7546760900953386e-05,
"loss": 0.7676,
"step": 535
},
{
"epoch": 0.18,
"learning_rate": 3.7536027584007365e-05,
"loss": 0.7891,
"step": 536
},
{
"epoch": 0.19,
"learning_rate": 3.752527237935328e-05,
"loss": 0.8062,
"step": 537
},
{
"epoch": 0.19,
"learning_rate": 3.751449530041532e-05,
"loss": 0.811,
"step": 538
},
{
"epoch": 0.19,
"learning_rate": 3.750369636064495e-05,
"loss": 0.8319,
"step": 539
},
{
"epoch": 0.19,
"learning_rate": 3.749287557352095e-05,
"loss": 0.7596,
"step": 540
},
{
"epoch": 0.19,
"learning_rate": 3.748203295254936e-05,
"loss": 0.7928,
"step": 541
},
{
"epoch": 0.19,
"learning_rate": 3.7471168511263456e-05,
"loss": 0.7608,
"step": 542
},
{
"epoch": 0.19,
"learning_rate": 3.7460282263223764e-05,
"loss": 0.8235,
"step": 543
},
{
"epoch": 0.19,
"learning_rate": 3.744937422201804e-05,
"loss": 0.7955,
"step": 544
},
{
"epoch": 0.19,
"learning_rate": 3.743844440126121e-05,
"loss": 0.8087,
"step": 545
},
{
"epoch": 0.19,
"learning_rate": 3.7427492814595406e-05,
"loss": 0.7325,
"step": 546
},
{
"epoch": 0.19,
"learning_rate": 3.741651947568993e-05,
"loss": 0.8413,
"step": 547
},
{
"epoch": 0.19,
"learning_rate": 3.740552439824122e-05,
"loss": 0.396,
"step": 548
},
{
"epoch": 0.19,
"learning_rate": 3.739450759597286e-05,
"loss": 0.7726,
"step": 549
},
{
"epoch": 0.19,
"learning_rate": 3.738346908263553e-05,
"loss": 0.765,
"step": 550
},
{
"epoch": 0.19,
"learning_rate": 3.737240887200705e-05,
"loss": 0.8243,
"step": 551
},
{
"epoch": 0.19,
"learning_rate": 3.736132697789227e-05,
"loss": 0.8037,
"step": 552
},
{
"epoch": 0.19,
"learning_rate": 3.735022341412314e-05,
"loss": 0.8181,
"step": 553
},
{
"epoch": 0.19,
"learning_rate": 3.733909819455864e-05,
"loss": 0.8413,
"step": 554
},
{
"epoch": 0.19,
"learning_rate": 3.7327951333084795e-05,
"loss": 0.7147,
"step": 555
},
{
"epoch": 0.19,
"learning_rate": 3.7316782843614626e-05,
"loss": 0.7989,
"step": 556
},
{
"epoch": 0.19,
"learning_rate": 3.7305592740088155e-05,
"loss": 0.7602,
"step": 557
},
{
"epoch": 0.19,
"learning_rate": 3.7294381036472386e-05,
"loss": 0.4062,
"step": 558
},
{
"epoch": 0.19,
"learning_rate": 3.728314774676128e-05,
"loss": 0.8353,
"step": 559
},
{
"epoch": 0.19,
"learning_rate": 3.727189288497575e-05,
"loss": 0.8143,
"step": 560
},
{
"epoch": 0.19,
"learning_rate": 3.726061646516361e-05,
"loss": 0.7948,
"step": 561
},
{
"epoch": 0.19,
"learning_rate": 3.7249318501399613e-05,
"loss": 0.7747,
"step": 562
},
{
"epoch": 0.19,
"learning_rate": 3.723799900778538e-05,
"loss": 0.7883,
"step": 563
},
{
"epoch": 0.19,
"learning_rate": 3.72266579984494e-05,
"loss": 0.8336,
"step": 564
},
{
"epoch": 0.19,
"learning_rate": 3.721529548754705e-05,
"loss": 0.8293,
"step": 565
},
{
"epoch": 0.2,
"learning_rate": 3.720391148926051e-05,
"loss": 0.7762,
"step": 566
},
{
"epoch": 0.2,
"learning_rate": 3.719250601779879e-05,
"loss": 0.8124,
"step": 567
},
{
"epoch": 0.2,
"learning_rate": 3.7181079087397705e-05,
"loss": 0.8069,
"step": 568
},
{
"epoch": 0.2,
"learning_rate": 3.7169630712319864e-05,
"loss": 0.7949,
"step": 569
},
{
"epoch": 0.2,
"learning_rate": 3.715816090685462e-05,
"loss": 0.7853,
"step": 570
},
{
"epoch": 0.2,
"learning_rate": 3.714666968531809e-05,
"loss": 0.7678,
"step": 571
},
{
"epoch": 0.2,
"learning_rate": 3.713515706205312e-05,
"loss": 0.7765,
"step": 572
},
{
"epoch": 0.2,
"learning_rate": 3.712362305142926e-05,
"loss": 0.7887,
"step": 573
},
{
"epoch": 0.2,
"learning_rate": 3.711206766784277e-05,
"loss": 0.7935,
"step": 574
},
{
"epoch": 0.2,
"learning_rate": 3.710049092571657e-05,
"loss": 0.4203,
"step": 575
},
{
"epoch": 0.2,
"learning_rate": 3.708889283950025e-05,
"loss": 0.7924,
"step": 576
},
{
"epoch": 0.2,
"learning_rate": 3.7077273423670035e-05,
"loss": 0.7781,
"step": 577
},
{
"epoch": 0.2,
"learning_rate": 3.706563269272878e-05,
"loss": 0.8201,
"step": 578
},
{
"epoch": 0.2,
"learning_rate": 3.7053970661205946e-05,
"loss": 0.8483,
"step": 579
},
{
"epoch": 0.2,
"learning_rate": 3.704228734365756e-05,
"loss": 0.7897,
"step": 580
},
{
"epoch": 0.2,
"learning_rate": 3.703058275466623e-05,
"loss": 0.8106,
"step": 581
},
{
"epoch": 0.2,
"learning_rate": 3.701885690884113e-05,
"loss": 0.7546,
"step": 582
},
{
"epoch": 0.2,
"learning_rate": 3.700710982081794e-05,
"loss": 0.7485,
"step": 583
},
{
"epoch": 0.2,
"learning_rate": 3.699534150525887e-05,
"loss": 0.7706,
"step": 584
},
{
"epoch": 0.2,
"learning_rate": 3.698355197685263e-05,
"loss": 0.4109,
"step": 585
},
{
"epoch": 0.2,
"learning_rate": 3.697174125031437e-05,
"loss": 0.3839,
"step": 586
},
{
"epoch": 0.2,
"learning_rate": 3.6959909340385756e-05,
"loss": 0.794,
"step": 587
},
{
"epoch": 0.2,
"learning_rate": 3.694805626183486e-05,
"loss": 0.8587,
"step": 588
},
{
"epoch": 0.2,
"learning_rate": 3.693618202945615e-05,
"loss": 0.4395,
"step": 589
},
{
"epoch": 0.2,
"learning_rate": 3.692428665807056e-05,
"loss": 0.8358,
"step": 590
},
{
"epoch": 0.2,
"learning_rate": 3.691237016252537e-05,
"loss": 0.8271,
"step": 591
},
{
"epoch": 0.2,
"learning_rate": 3.6900432557694215e-05,
"loss": 0.7857,
"step": 592
},
{
"epoch": 0.2,
"learning_rate": 3.688847385847711e-05,
"loss": 0.8228,
"step": 593
},
{
"epoch": 0.2,
"learning_rate": 3.687649407980038e-05,
"loss": 0.8432,
"step": 594
},
{
"epoch": 0.21,
"learning_rate": 3.6864493236616675e-05,
"loss": 0.8062,
"step": 595
},
{
"epoch": 0.21,
"learning_rate": 3.6852471343904905e-05,
"loss": 0.8429,
"step": 596
},
{
"epoch": 0.21,
"learning_rate": 3.684042841667029e-05,
"loss": 0.7961,
"step": 597
},
{
"epoch": 0.21,
"learning_rate": 3.682836446994428e-05,
"loss": 0.8257,
"step": 598
},
{
"epoch": 0.21,
"learning_rate": 3.681627951878458e-05,
"loss": 0.7713,
"step": 599
},
{
"epoch": 0.21,
"learning_rate": 3.6804173578275094e-05,
"loss": 0.8013,
"step": 600
},
{
"epoch": 0.21,
"learning_rate": 3.6792046663525924e-05,
"loss": 0.3927,
"step": 601
},
{
"epoch": 0.21,
"learning_rate": 3.677989878967338e-05,
"loss": 0.7758,
"step": 602
},
{
"epoch": 0.21,
"learning_rate": 3.676772997187989e-05,
"loss": 0.7807,
"step": 603
},
{
"epoch": 0.21,
"learning_rate": 3.675554022533405e-05,
"loss": 0.8249,
"step": 604
},
{
"epoch": 0.21,
"learning_rate": 3.6743329565250575e-05,
"loss": 0.8537,
"step": 605
},
{
"epoch": 0.21,
"learning_rate": 3.673109800687028e-05,
"loss": 0.7876,
"step": 606
},
{
"epoch": 0.21,
"learning_rate": 3.671884556546006e-05,
"loss": 0.3725,
"step": 607
},
{
"epoch": 0.21,
"learning_rate": 3.670657225631289e-05,
"loss": 0.7748,
"step": 608
},
{
"epoch": 0.21,
"learning_rate": 3.669427809474777e-05,
"loss": 0.8083,
"step": 609
},
{
"epoch": 0.21,
"learning_rate": 3.668196309610975e-05,
"loss": 0.7669,
"step": 610
},
{
"epoch": 0.21,
"learning_rate": 3.666962727576987e-05,
"loss": 0.7759,
"step": 611
},
{
"epoch": 0.21,
"learning_rate": 3.665727064912516e-05,
"loss": 0.7934,
"step": 612
},
{
"epoch": 0.21,
"learning_rate": 3.6644893231598635e-05,
"loss": 0.7791,
"step": 613
},
{
"epoch": 0.21,
"learning_rate": 3.663249503863925e-05,
"loss": 0.7802,
"step": 614
},
{
"epoch": 0.21,
"learning_rate": 3.6620076085721875e-05,
"loss": 0.8042,
"step": 615
},
{
"epoch": 0.21,
"learning_rate": 3.660763638834733e-05,
"loss": 0.8253,
"step": 616
},
{
"epoch": 0.21,
"learning_rate": 3.659517596204229e-05,
"loss": 0.7666,
"step": 617
},
{
"epoch": 0.21,
"learning_rate": 3.658269482235932e-05,
"loss": 0.7713,
"step": 618
},
{
"epoch": 0.21,
"learning_rate": 3.657019298487685e-05,
"loss": 0.8036,
"step": 619
},
{
"epoch": 0.21,
"learning_rate": 3.655767046519911e-05,
"loss": 0.7635,
"step": 620
},
{
"epoch": 0.21,
"learning_rate": 3.654512727895618e-05,
"loss": 0.7963,
"step": 621
},
{
"epoch": 0.21,
"learning_rate": 3.6532563441803903e-05,
"loss": 0.8117,
"step": 622
},
{
"epoch": 0.21,
"learning_rate": 3.651997896942394e-05,
"loss": 0.806,
"step": 623
},
{
"epoch": 0.22,
"learning_rate": 3.650737387752366e-05,
"loss": 0.8233,
"step": 624
},
{
"epoch": 0.22,
"learning_rate": 3.649474818183621e-05,
"loss": 0.3948,
"step": 625
},
{
"epoch": 0.22,
"learning_rate": 3.648210189812042e-05,
"loss": 0.803,
"step": 626
},
{
"epoch": 0.22,
"learning_rate": 3.6469435042160844e-05,
"loss": 0.4046,
"step": 627
},
{
"epoch": 0.22,
"learning_rate": 3.645674762976769e-05,
"loss": 0.8122,
"step": 628
},
{
"epoch": 0.22,
"learning_rate": 3.6444039676776843e-05,
"loss": 0.83,
"step": 629
},
{
"epoch": 0.22,
"learning_rate": 3.643131119904982e-05,
"loss": 0.8144,
"step": 630
},
{
"epoch": 0.22,
"learning_rate": 3.641856221247374e-05,
"loss": 0.788,
"step": 631
},
{
"epoch": 0.22,
"learning_rate": 3.6405792732961354e-05,
"loss": 0.7832,
"step": 632
},
{
"epoch": 0.22,
"learning_rate": 3.639300277645096e-05,
"loss": 0.7484,
"step": 633
},
{
"epoch": 0.22,
"learning_rate": 3.6380192358906426e-05,
"loss": 0.7579,
"step": 634
},
{
"epoch": 0.22,
"learning_rate": 3.636736149631716e-05,
"loss": 0.8329,
"step": 635
},
{
"epoch": 0.22,
"learning_rate": 3.6354510204698095e-05,
"loss": 0.7578,
"step": 636
},
{
"epoch": 0.22,
"learning_rate": 3.634163850008964e-05,
"loss": 0.7669,
"step": 637
},
{
"epoch": 0.22,
"learning_rate": 3.6328746398557715e-05,
"loss": 0.795,
"step": 638
},
{
"epoch": 0.22,
"learning_rate": 3.6315833916193674e-05,
"loss": 0.7874,
"step": 639
},
{
"epoch": 0.22,
"learning_rate": 3.630290106911431e-05,
"loss": 0.7908,
"step": 640
},
{
"epoch": 0.22,
"learning_rate": 3.628994787346185e-05,
"loss": 0.806,
"step": 641
},
{
"epoch": 0.22,
"learning_rate": 3.62769743454039e-05,
"loss": 0.812,
"step": 642
},
{
"epoch": 0.22,
"learning_rate": 3.6263980501133466e-05,
"loss": 0.7965,
"step": 643
},
{
"epoch": 0.22,
"learning_rate": 3.6250966356868895e-05,
"loss": 0.7871,
"step": 644
},
{
"epoch": 0.22,
"learning_rate": 3.623793192885388e-05,
"loss": 0.7721,
"step": 645
},
{
"epoch": 0.22,
"learning_rate": 3.6224877233357424e-05,
"loss": 0.4008,
"step": 646
},
{
"epoch": 0.22,
"learning_rate": 3.621180228667383e-05,
"loss": 0.8045,
"step": 647
},
{
"epoch": 0.22,
"learning_rate": 3.619870710512268e-05,
"loss": 0.7596,
"step": 648
},
{
"epoch": 0.22,
"learning_rate": 3.618559170504881e-05,
"loss": 0.7919,
"step": 649
},
{
"epoch": 0.22,
"learning_rate": 3.61724561028223e-05,
"loss": 0.7376,
"step": 650
},
{
"epoch": 0.22,
"learning_rate": 3.6159300314838424e-05,
"loss": 0.7971,
"step": 651
},
{
"epoch": 0.22,
"learning_rate": 3.614612435751768e-05,
"loss": 0.7737,
"step": 652
},
{
"epoch": 0.23,
"learning_rate": 3.6132928247305713e-05,
"loss": 0.7868,
"step": 653
},
{
"epoch": 0.23,
"learning_rate": 3.611971200067335e-05,
"loss": 0.8362,
"step": 654
},
{
"epoch": 0.23,
"learning_rate": 3.610647563411653e-05,
"loss": 0.7672,
"step": 655
},
{
"epoch": 0.23,
"learning_rate": 3.6093219164156294e-05,
"loss": 0.8056,
"step": 656
},
{
"epoch": 0.23,
"learning_rate": 3.607994260733881e-05,
"loss": 0.7869,
"step": 657
},
{
"epoch": 0.23,
"learning_rate": 3.60666459802353e-05,
"loss": 0.7956,
"step": 658
},
{
"epoch": 0.23,
"learning_rate": 3.605332929944203e-05,
"loss": 0.7814,
"step": 659
},
{
"epoch": 0.23,
"learning_rate": 3.6039992581580315e-05,
"loss": 0.7775,
"step": 660
},
{
"epoch": 0.23,
"learning_rate": 3.602663584329644e-05,
"loss": 0.773,
"step": 661
},
{
"epoch": 0.23,
"learning_rate": 3.601325910126173e-05,
"loss": 0.8172,
"step": 662
},
{
"epoch": 0.23,
"learning_rate": 3.599986237217245e-05,
"loss": 0.8065,
"step": 663
},
{
"epoch": 0.23,
"learning_rate": 3.598644567274981e-05,
"loss": 0.7502,
"step": 664
},
{
"epoch": 0.23,
"learning_rate": 3.597300901973995e-05,
"loss": 0.7932,
"step": 665
},
{
"epoch": 0.23,
"learning_rate": 3.595955242991392e-05,
"loss": 0.7708,
"step": 666
},
{
"epoch": 0.23,
"learning_rate": 3.5946075920067655e-05,
"loss": 0.7778,
"step": 667
},
{
"epoch": 0.23,
"learning_rate": 3.593257950702194e-05,
"loss": 0.7997,
"step": 668
},
{
"epoch": 0.23,
"learning_rate": 3.591906320762242e-05,
"loss": 0.797,
"step": 669
},
{
"epoch": 0.23,
"learning_rate": 3.5905527038739544e-05,
"loss": 0.7959,
"step": 670
},
{
"epoch": 0.23,
"learning_rate": 3.589197101726858e-05,
"loss": 0.8005,
"step": 671
},
{
"epoch": 0.23,
"learning_rate": 3.5878395160129564e-05,
"loss": 0.7955,
"step": 672
},
{
"epoch": 0.23,
"learning_rate": 3.586479948426728e-05,
"loss": 0.797,
"step": 673
},
{
"epoch": 0.23,
"learning_rate": 3.585118400665128e-05,
"loss": 0.8178,
"step": 674
},
{
"epoch": 0.23,
"learning_rate": 3.58375487442758e-05,
"loss": 0.7818,
"step": 675
},
{
"epoch": 0.23,
"learning_rate": 3.582389371415977e-05,
"loss": 0.8018,
"step": 676
},
{
"epoch": 0.23,
"learning_rate": 3.5810218933346825e-05,
"loss": 0.7961,
"step": 677
},
{
"epoch": 0.23,
"learning_rate": 3.579652441890523e-05,
"loss": 0.8109,
"step": 678
},
{
"epoch": 0.23,
"learning_rate": 3.578281018792788e-05,
"loss": 0.7279,
"step": 679
},
{
"epoch": 0.23,
"learning_rate": 3.5769076257532274e-05,
"loss": 0.7736,
"step": 680
},
{
"epoch": 0.23,
"learning_rate": 3.575532264486052e-05,
"loss": 0.736,
"step": 681
},
{
"epoch": 0.24,
"learning_rate": 3.574154936707927e-05,
"loss": 0.7862,
"step": 682
},
{
"epoch": 0.24,
"learning_rate": 3.572775644137974e-05,
"loss": 0.7961,
"step": 683
},
{
"epoch": 0.24,
"learning_rate": 3.571394388497765e-05,
"loss": 0.7922,
"step": 684
},
{
"epoch": 0.24,
"learning_rate": 3.5700111715113255e-05,
"loss": 0.7931,
"step": 685
},
{
"epoch": 0.24,
"learning_rate": 3.568625994905124e-05,
"loss": 0.7601,
"step": 686
},
{
"epoch": 0.24,
"learning_rate": 3.56723886040808e-05,
"loss": 0.8055,
"step": 687
},
{
"epoch": 0.24,
"learning_rate": 3.5658497697515534e-05,
"loss": 0.7994,
"step": 688
},
{
"epoch": 0.24,
"learning_rate": 3.564458724669347e-05,
"loss": 0.7764,
"step": 689
},
{
"epoch": 0.24,
"learning_rate": 3.5630657268977034e-05,
"loss": 0.8593,
"step": 690
},
{
"epoch": 0.24,
"learning_rate": 3.561670778175302e-05,
"loss": 0.7673,
"step": 691
},
{
"epoch": 0.24,
"learning_rate": 3.560273880243256e-05,
"loss": 0.7944,
"step": 692
},
{
"epoch": 0.24,
"learning_rate": 3.558875034845113e-05,
"loss": 0.8061,
"step": 693
},
{
"epoch": 0.24,
"learning_rate": 3.5574742437268526e-05,
"loss": 0.8313,
"step": 694
},
{
"epoch": 0.24,
"learning_rate": 3.556071508636879e-05,
"loss": 0.7944,
"step": 695
},
{
"epoch": 0.24,
"learning_rate": 3.554666831326028e-05,
"loss": 0.7885,
"step": 696
},
{
"epoch": 0.24,
"learning_rate": 3.553260213547555e-05,
"loss": 0.8102,
"step": 697
},
{
"epoch": 0.24,
"learning_rate": 3.551851657057139e-05,
"loss": 0.7026,
"step": 698
},
{
"epoch": 0.24,
"learning_rate": 3.55044116361288e-05,
"loss": 0.7344,
"step": 699
},
{
"epoch": 0.24,
"learning_rate": 3.549028734975295e-05,
"loss": 0.7495,
"step": 700
},
{
"epoch": 0.24,
"learning_rate": 3.547614372907314e-05,
"loss": 0.7742,
"step": 701
},
{
"epoch": 0.24,
"learning_rate": 3.546198079174286e-05,
"loss": 0.7569,
"step": 702
},
{
"epoch": 0.24,
"learning_rate": 3.544779855543963e-05,
"loss": 0.8276,
"step": 703
},
{
"epoch": 0.24,
"learning_rate": 3.543359703786513e-05,
"loss": 0.7787,
"step": 704
},
{
"epoch": 0.24,
"learning_rate": 3.541937625674507e-05,
"loss": 0.8398,
"step": 705
},
{
"epoch": 0.24,
"learning_rate": 3.540513622982921e-05,
"loss": 0.7531,
"step": 706
},
{
"epoch": 0.24,
"learning_rate": 3.539087697489134e-05,
"loss": 0.8108,
"step": 707
},
{
"epoch": 0.24,
"learning_rate": 3.5376598509729226e-05,
"loss": 0.8219,
"step": 708
},
{
"epoch": 0.24,
"learning_rate": 3.5362300852164644e-05,
"loss": 0.7708,
"step": 709
},
{
"epoch": 0.24,
"learning_rate": 3.5347984020043304e-05,
"loss": 0.7672,
"step": 710
},
{
"epoch": 0.25,
"learning_rate": 3.5333648031234856e-05,
"loss": 0.8239,
"step": 711
},
{
"epoch": 0.25,
"learning_rate": 3.531929290363286e-05,
"loss": 0.7644,
"step": 712
},
{
"epoch": 0.25,
"learning_rate": 3.5304918655154754e-05,
"loss": 0.7764,
"step": 713
},
{
"epoch": 0.25,
"learning_rate": 3.529052530374185e-05,
"loss": 0.7775,
"step": 714
},
{
"epoch": 0.25,
"learning_rate": 3.5276112867359324e-05,
"loss": 0.7379,
"step": 715
},
{
"epoch": 0.25,
"learning_rate": 3.5261681363996135e-05,
"loss": 0.7972,
"step": 716
},
{
"epoch": 0.25,
"learning_rate": 3.5247230811665065e-05,
"loss": 0.7526,
"step": 717
},
{
"epoch": 0.25,
"learning_rate": 3.523276122840266e-05,
"loss": 0.8293,
"step": 718
},
{
"epoch": 0.25,
"learning_rate": 3.521827263226923e-05,
"loss": 0.8071,
"step": 719
},
{
"epoch": 0.25,
"learning_rate": 3.5203765041348815e-05,
"loss": 0.7957,
"step": 720
},
{
"epoch": 0.25,
"learning_rate": 3.5189238473749155e-05,
"loss": 0.789,
"step": 721
},
{
"epoch": 0.25,
"learning_rate": 3.517469294760168e-05,
"loss": 0.7336,
"step": 722
},
{
"epoch": 0.25,
"learning_rate": 3.516012848106149e-05,
"loss": 0.8464,
"step": 723
},
{
"epoch": 0.25,
"learning_rate": 3.5145545092307313e-05,
"loss": 0.7363,
"step": 724
},
{
"epoch": 0.25,
"learning_rate": 3.513094279954151e-05,
"loss": 0.7999,
"step": 725
},
{
"epoch": 0.25,
"learning_rate": 3.511632162099002e-05,
"loss": 0.3902,
"step": 726
},
{
"epoch": 0.25,
"learning_rate": 3.510168157490237e-05,
"loss": 0.8197,
"step": 727
},
{
"epoch": 0.25,
"learning_rate": 3.5087022679551614e-05,
"loss": 0.7976,
"step": 728
},
{
"epoch": 0.25,
"learning_rate": 3.5072344953234365e-05,
"loss": 0.8064,
"step": 729
},
{
"epoch": 0.25,
"learning_rate": 3.505764841427072e-05,
"loss": 0.7696,
"step": 730
},
{
"epoch": 0.25,
"learning_rate": 3.504293308100426e-05,
"loss": 0.795,
"step": 731
},
{
"epoch": 0.25,
"learning_rate": 3.5028198971802024e-05,
"loss": 0.8118,
"step": 732
},
{
"epoch": 0.25,
"learning_rate": 3.5013446105054486e-05,
"loss": 0.7591,
"step": 733
},
{
"epoch": 0.25,
"learning_rate": 3.499867449917554e-05,
"loss": 0.8378,
"step": 734
},
{
"epoch": 0.25,
"learning_rate": 3.498388417260246e-05,
"loss": 0.737,
"step": 735
},
{
"epoch": 0.25,
"learning_rate": 3.4969075143795886e-05,
"loss": 0.8152,
"step": 736
},
{
"epoch": 0.25,
"learning_rate": 3.49542474312398e-05,
"loss": 0.7615,
"step": 737
},
{
"epoch": 0.25,
"learning_rate": 3.493940105344152e-05,
"loss": 0.397,
"step": 738
},
{
"epoch": 0.25,
"learning_rate": 3.492453602893164e-05,
"loss": 0.7864,
"step": 739
},
{
"epoch": 0.26,
"learning_rate": 3.490965237626405e-05,
"loss": 0.7898,
"step": 740
},
{
"epoch": 0.26,
"learning_rate": 3.4894750114015866e-05,
"loss": 0.7874,
"step": 741
},
{
"epoch": 0.26,
"learning_rate": 3.4879829260787455e-05,
"loss": 0.8461,
"step": 742
},
{
"epoch": 0.26,
"learning_rate": 3.4864889835202366e-05,
"loss": 0.8006,
"step": 743
},
{
"epoch": 0.26,
"learning_rate": 3.484993185590736e-05,
"loss": 0.779,
"step": 744
},
{
"epoch": 0.26,
"learning_rate": 3.4834955341572315e-05,
"loss": 0.8434,
"step": 745
},
{
"epoch": 0.26,
"learning_rate": 3.481996031089028e-05,
"loss": 0.7992,
"step": 746
},
{
"epoch": 0.26,
"learning_rate": 3.48049467825774e-05,
"loss": 0.7987,
"step": 747
},
{
"epoch": 0.26,
"learning_rate": 3.4789914775372905e-05,
"loss": 0.783,
"step": 748
},
{
"epoch": 0.26,
"learning_rate": 3.47748643080391e-05,
"loss": 0.7815,
"step": 749
},
{
"epoch": 0.26,
"learning_rate": 3.4759795399361315e-05,
"loss": 0.818,
"step": 750
},
{
"epoch": 0.26,
"learning_rate": 3.4744708068147915e-05,
"loss": 0.765,
"step": 751
},
{
"epoch": 0.26,
"learning_rate": 3.472960233323025e-05,
"loss": 0.8406,
"step": 752
},
{
"epoch": 0.26,
"learning_rate": 3.471447821346264e-05,
"loss": 0.713,
"step": 753
},
{
"epoch": 0.26,
"learning_rate": 3.469933572772235e-05,
"loss": 0.7894,
"step": 754
},
{
"epoch": 0.26,
"learning_rate": 3.4684174894909585e-05,
"loss": 0.7178,
"step": 755
},
{
"epoch": 0.26,
"learning_rate": 3.466899573394743e-05,
"loss": 0.7682,
"step": 756
},
{
"epoch": 0.26,
"learning_rate": 3.465379826378185e-05,
"loss": 0.7891,
"step": 757
},
{
"epoch": 0.26,
"learning_rate": 3.463858250338168e-05,
"loss": 0.7836,
"step": 758
},
{
"epoch": 0.26,
"learning_rate": 3.462334847173857e-05,
"loss": 0.7702,
"step": 759
},
{
"epoch": 0.26,
"learning_rate": 3.460809618786697e-05,
"loss": 0.7951,
"step": 760
},
{
"epoch": 0.26,
"learning_rate": 3.459282567080411e-05,
"loss": 0.7819,
"step": 761
},
{
"epoch": 0.26,
"learning_rate": 3.4577536939610014e-05,
"loss": 0.7421,
"step": 762
},
{
"epoch": 0.26,
"learning_rate": 3.4562230013367374e-05,
"loss": 0.8453,
"step": 763
},
{
"epoch": 0.26,
"learning_rate": 3.454690491118167e-05,
"loss": 0.8275,
"step": 764
},
{
"epoch": 0.26,
"learning_rate": 3.4531561652181e-05,
"loss": 0.7974,
"step": 765
},
{
"epoch": 0.26,
"learning_rate": 3.451620025551616e-05,
"loss": 0.8143,
"step": 766
},
{
"epoch": 0.26,
"learning_rate": 3.450082074036059e-05,
"loss": 0.8182,
"step": 767
},
{
"epoch": 0.26,
"learning_rate": 3.448542312591032e-05,
"loss": 0.7485,
"step": 768
},
{
"epoch": 0.27,
"learning_rate": 3.447000743138399e-05,
"loss": 0.7587,
"step": 769
},
{
"epoch": 0.27,
"learning_rate": 3.44545736760228e-05,
"loss": 0.7927,
"step": 770
},
{
"epoch": 0.27,
"learning_rate": 3.443912187909049e-05,
"loss": 0.7913,
"step": 771
},
{
"epoch": 0.27,
"learning_rate": 3.4423652059873326e-05,
"loss": 0.7404,
"step": 772
},
{
"epoch": 0.27,
"learning_rate": 3.440816423768007e-05,
"loss": 0.7902,
"step": 773
},
{
"epoch": 0.27,
"learning_rate": 3.4392658431841925e-05,
"loss": 0.7797,
"step": 774
},
{
"epoch": 0.27,
"learning_rate": 3.437713466171259e-05,
"loss": 0.7933,
"step": 775
},
{
"epoch": 0.27,
"learning_rate": 3.436159294666815e-05,
"loss": 0.7509,
"step": 776
},
{
"epoch": 0.27,
"learning_rate": 3.4346033306107105e-05,
"loss": 0.7936,
"step": 777
},
{
"epoch": 0.27,
"learning_rate": 3.433045575945031e-05,
"loss": 0.811,
"step": 778
},
{
"epoch": 0.27,
"learning_rate": 3.4314860326141e-05,
"loss": 0.7774,
"step": 779
},
{
"epoch": 0.27,
"learning_rate": 3.4299247025644695e-05,
"loss": 0.8008,
"step": 780
},
{
"epoch": 0.27,
"learning_rate": 3.4283615877449256e-05,
"loss": 0.7898,
"step": 781
},
{
"epoch": 0.27,
"learning_rate": 3.4267966901064804e-05,
"loss": 0.744,
"step": 782
},
{
"epoch": 0.27,
"learning_rate": 3.42523001160237e-05,
"loss": 0.7327,
"step": 783
},
{
"epoch": 0.27,
"learning_rate": 3.423661554188056e-05,
"loss": 0.7399,
"step": 784
},
{
"epoch": 0.27,
"learning_rate": 3.422091319821217e-05,
"loss": 0.386,
"step": 785
},
{
"epoch": 0.27,
"learning_rate": 3.420519310461753e-05,
"loss": 0.7799,
"step": 786
},
{
"epoch": 0.27,
"learning_rate": 3.418945528071777e-05,
"loss": 0.7703,
"step": 787
},
{
"epoch": 0.27,
"learning_rate": 3.417369974615615e-05,
"loss": 0.7832,
"step": 788
},
{
"epoch": 0.27,
"learning_rate": 3.415792652059806e-05,
"loss": 0.7919,
"step": 789
},
{
"epoch": 0.27,
"learning_rate": 3.4142135623730954e-05,
"loss": 0.7642,
"step": 790
},
{
"epoch": 0.27,
"learning_rate": 3.412632707526434e-05,
"loss": 0.8186,
"step": 791
},
{
"epoch": 0.27,
"learning_rate": 3.4110500894929745e-05,
"loss": 0.7593,
"step": 792
},
{
"epoch": 0.27,
"learning_rate": 3.409465710248074e-05,
"loss": 0.7693,
"step": 793
},
{
"epoch": 0.27,
"learning_rate": 3.4078795717692855e-05,
"loss": 0.8471,
"step": 794
},
{
"epoch": 0.27,
"learning_rate": 3.406291676036358e-05,
"loss": 0.7835,
"step": 795
},
{
"epoch": 0.27,
"learning_rate": 3.404702025031235e-05,
"loss": 0.7592,
"step": 796
},
{
"epoch": 0.27,
"learning_rate": 3.4031106207380476e-05,
"loss": 0.7785,
"step": 797
},
{
"epoch": 0.28,
"learning_rate": 3.401517465143119e-05,
"loss": 0.8249,
"step": 798
},
{
"epoch": 0.28,
"learning_rate": 3.3999225602349564e-05,
"loss": 0.7734,
"step": 799
},
{
"epoch": 0.28,
"learning_rate": 3.398325908004251e-05,
"loss": 0.799,
"step": 800
},
{
"epoch": 0.28,
"learning_rate": 3.3967275104438763e-05,
"loss": 0.8288,
"step": 801
},
{
"epoch": 0.28,
"learning_rate": 3.395127369548879e-05,
"loss": 0.7764,
"step": 802
},
{
"epoch": 0.28,
"learning_rate": 3.393525487316489e-05,
"loss": 0.7606,
"step": 803
},
{
"epoch": 0.28,
"learning_rate": 3.391921865746105e-05,
"loss": 0.7917,
"step": 804
},
{
"epoch": 0.28,
"learning_rate": 3.390316506839297e-05,
"loss": 0.7812,
"step": 805
},
{
"epoch": 0.28,
"learning_rate": 3.3887094125998055e-05,
"loss": 0.757,
"step": 806
},
{
"epoch": 0.28,
"learning_rate": 3.387100585033535e-05,
"loss": 0.7802,
"step": 807
},
{
"epoch": 0.28,
"learning_rate": 3.385490026148554e-05,
"loss": 0.804,
"step": 808
},
{
"epoch": 0.28,
"learning_rate": 3.3838777379550926e-05,
"loss": 0.7561,
"step": 809
},
{
"epoch": 0.28,
"learning_rate": 3.382263722465539e-05,
"loss": 0.818,
"step": 810
},
{
"epoch": 0.28,
"learning_rate": 3.380647981694437e-05,
"loss": 0.7929,
"step": 811
},
{
"epoch": 0.28,
"learning_rate": 3.3790305176584836e-05,
"loss": 0.8004,
"step": 812
},
{
"epoch": 0.28,
"learning_rate": 3.377411332376529e-05,
"loss": 0.7974,
"step": 813
},
{
"epoch": 0.28,
"learning_rate": 3.375790427869567e-05,
"loss": 0.773,
"step": 814
},
{
"epoch": 0.28,
"learning_rate": 3.3741678061607426e-05,
"loss": 0.7498,
"step": 815
},
{
"epoch": 0.28,
"learning_rate": 3.372543469275341e-05,
"loss": 0.79,
"step": 816
},
{
"epoch": 0.28,
"learning_rate": 3.3709174192407886e-05,
"loss": 0.7894,
"step": 817
},
{
"epoch": 0.28,
"learning_rate": 3.369289658086651e-05,
"loss": 0.8071,
"step": 818
},
{
"epoch": 0.28,
"learning_rate": 3.367660187844629e-05,
"loss": 0.7671,
"step": 819
},
{
"epoch": 0.28,
"learning_rate": 3.366029010548556e-05,
"loss": 0.8203,
"step": 820
},
{
"epoch": 0.28,
"learning_rate": 3.364396128234397e-05,
"loss": 0.8102,
"step": 821
},
{
"epoch": 0.28,
"learning_rate": 3.362761542940245e-05,
"loss": 0.7394,
"step": 822
},
{
"epoch": 0.28,
"learning_rate": 3.3611252567063184e-05,
"loss": 0.405,
"step": 823
},
{
"epoch": 0.28,
"learning_rate": 3.359487271574958e-05,
"loss": 0.8108,
"step": 824
},
{
"epoch": 0.28,
"learning_rate": 3.357847589590626e-05,
"loss": 0.7687,
"step": 825
},
{
"epoch": 0.28,
"learning_rate": 3.356206212799903e-05,
"loss": 0.8302,
"step": 826
},
{
"epoch": 0.29,
"learning_rate": 3.354563143251483e-05,
"loss": 0.798,
"step": 827
},
{
"epoch": 0.29,
"learning_rate": 3.352918382996174e-05,
"loss": 0.8221,
"step": 828
},
{
"epoch": 0.29,
"learning_rate": 3.3512719340868955e-05,
"loss": 0.7476,
"step": 829
},
{
"epoch": 0.29,
"learning_rate": 3.349623798578673e-05,
"loss": 0.7808,
"step": 830
},
{
"epoch": 0.29,
"learning_rate": 3.347973978528638e-05,
"loss": 0.7986,
"step": 831
},
{
"epoch": 0.29,
"learning_rate": 3.346322475996024e-05,
"loss": 0.8123,
"step": 832
},
{
"epoch": 0.29,
"learning_rate": 3.344669293042163e-05,
"loss": 0.8156,
"step": 833
},
{
"epoch": 0.29,
"learning_rate": 3.343014431730489e-05,
"loss": 0.8146,
"step": 834
},
{
"epoch": 0.29,
"learning_rate": 3.341357894126527e-05,
"loss": 0.8253,
"step": 835
},
{
"epoch": 0.29,
"learning_rate": 3.3396996822978954e-05,
"loss": 0.7962,
"step": 836
},
{
"epoch": 0.29,
"learning_rate": 3.338039798314301e-05,
"loss": 0.8057,
"step": 837
},
{
"epoch": 0.29,
"learning_rate": 3.336378244247539e-05,
"loss": 0.7765,
"step": 838
},
{
"epoch": 0.29,
"learning_rate": 3.3347150221714914e-05,
"loss": 0.3924,
"step": 839
},
{
"epoch": 0.29,
"learning_rate": 3.333050134162118e-05,
"loss": 0.7812,
"step": 840
},
{
"epoch": 0.29,
"learning_rate": 3.331383582297459e-05,
"loss": 0.7584,
"step": 841
},
{
"epoch": 0.29,
"learning_rate": 3.329715368657634e-05,
"loss": 0.7708,
"step": 842
},
{
"epoch": 0.29,
"learning_rate": 3.3280454953248326e-05,
"loss": 0.7335,
"step": 843
},
{
"epoch": 0.29,
"learning_rate": 3.3263739643833204e-05,
"loss": 0.7852,
"step": 844
},
{
"epoch": 0.29,
"learning_rate": 3.3247007779194276e-05,
"loss": 0.7797,
"step": 845
},
{
"epoch": 0.29,
"learning_rate": 3.323025938021555e-05,
"loss": 0.7962,
"step": 846
},
{
"epoch": 0.29,
"learning_rate": 3.321349446780163e-05,
"loss": 0.7648,
"step": 847
},
{
"epoch": 0.29,
"learning_rate": 3.3196713062877765e-05,
"loss": 0.7585,
"step": 848
},
{
"epoch": 0.29,
"learning_rate": 3.3179915186389774e-05,
"loss": 0.8147,
"step": 849
},
{
"epoch": 0.29,
"learning_rate": 3.3163100859304037e-05,
"loss": 0.7381,
"step": 850
},
{
"epoch": 0.29,
"learning_rate": 3.314627010260746e-05,
"loss": 0.7687,
"step": 851
},
{
"epoch": 0.29,
"learning_rate": 3.3129422937307464e-05,
"loss": 0.8133,
"step": 852
},
{
"epoch": 0.29,
"learning_rate": 3.311255938443196e-05,
"loss": 0.815,
"step": 853
},
{
"epoch": 0.29,
"learning_rate": 3.309567946502929e-05,
"loss": 0.8617,
"step": 854
},
{
"epoch": 0.29,
"learning_rate": 3.3078783200168244e-05,
"loss": 0.7599,
"step": 855
},
{
"epoch": 0.3,
"learning_rate": 3.3061870610938e-05,
"loss": 0.7821,
"step": 856
},
{
"epoch": 0.3,
"learning_rate": 3.3044941718448126e-05,
"loss": 0.7678,
"step": 857
},
{
"epoch": 0.3,
"learning_rate": 3.3027996543828524e-05,
"loss": 0.7746,
"step": 858
},
{
"epoch": 0.3,
"learning_rate": 3.301103510822942e-05,
"loss": 0.7792,
"step": 859
},
{
"epoch": 0.3,
"learning_rate": 3.2994057432821346e-05,
"loss": 0.8134,
"step": 860
},
{
"epoch": 0.3,
"learning_rate": 3.297706353879511e-05,
"loss": 0.8241,
"step": 861
},
{
"epoch": 0.3,
"learning_rate": 3.296005344736174e-05,
"loss": 0.748,
"step": 862
},
{
"epoch": 0.3,
"learning_rate": 3.2943027179752494e-05,
"loss": 0.7816,
"step": 863
},
{
"epoch": 0.3,
"learning_rate": 3.292598475721882e-05,
"loss": 0.7732,
"step": 864
},
{
"epoch": 0.3,
"learning_rate": 3.290892620103234e-05,
"loss": 0.8412,
"step": 865
},
{
"epoch": 0.3,
"learning_rate": 3.2891851532484784e-05,
"loss": 0.8522,
"step": 866
},
{
"epoch": 0.3,
"learning_rate": 3.287476077288803e-05,
"loss": 0.8265,
"step": 867
},
{
"epoch": 0.3,
"learning_rate": 3.285765394357401e-05,
"loss": 0.741,
"step": 868
},
{
"epoch": 0.3,
"learning_rate": 3.284053106589473e-05,
"loss": 0.7306,
"step": 869
},
{
"epoch": 0.3,
"learning_rate": 3.282339216122222e-05,
"loss": 0.7996,
"step": 870
},
{
"epoch": 0.3,
"learning_rate": 3.2806237250948526e-05,
"loss": 0.7559,
"step": 871
},
{
"epoch": 0.3,
"learning_rate": 3.2789066356485655e-05,
"loss": 0.7837,
"step": 872
},
{
"epoch": 0.3,
"learning_rate": 3.277187949926556e-05,
"loss": 0.8174,
"step": 873
},
{
"epoch": 0.3,
"learning_rate": 3.275467670074015e-05,
"loss": 0.8142,
"step": 874
},
{
"epoch": 0.3,
"learning_rate": 3.27374579823812e-05,
"loss": 0.796,
"step": 875
},
{
"epoch": 0.3,
"learning_rate": 3.272022336568037e-05,
"loss": 0.804,
"step": 876
},
{
"epoch": 0.3,
"learning_rate": 3.270297287214916e-05,
"loss": 0.7573,
"step": 877
},
{
"epoch": 0.3,
"learning_rate": 3.268570652331888e-05,
"loss": 0.7714,
"step": 878
},
{
"epoch": 0.3,
"learning_rate": 3.2668424340740646e-05,
"loss": 0.7608,
"step": 879
},
{
"epoch": 0.3,
"learning_rate": 3.2651126345985326e-05,
"loss": 0.8201,
"step": 880
},
{
"epoch": 0.3,
"learning_rate": 3.2633812560643524e-05,
"loss": 0.7903,
"step": 881
},
{
"epoch": 0.3,
"learning_rate": 3.261648300632555e-05,
"loss": 0.8017,
"step": 882
},
{
"epoch": 0.3,
"learning_rate": 3.2599137704661405e-05,
"loss": 0.7903,
"step": 883
},
{
"epoch": 0.3,
"learning_rate": 3.2581776677300746e-05,
"loss": 0.7626,
"step": 884
},
{
"epoch": 0.31,
"learning_rate": 3.256439994591285e-05,
"loss": 0.8078,
"step": 885
},
{
"epoch": 0.31,
"learning_rate": 3.25470075321866e-05,
"loss": 0.8268,
"step": 886
},
{
"epoch": 0.31,
"learning_rate": 3.252959945783044e-05,
"loss": 0.7338,
"step": 887
},
{
"epoch": 0.31,
"learning_rate": 3.251217574457239e-05,
"loss": 0.7885,
"step": 888
},
{
"epoch": 0.31,
"learning_rate": 3.249473641415996e-05,
"loss": 0.7702,
"step": 889
},
{
"epoch": 0.31,
"learning_rate": 3.247728148836018e-05,
"loss": 0.8016,
"step": 890
},
{
"epoch": 0.31,
"learning_rate": 3.24598109889595e-05,
"loss": 0.7602,
"step": 891
},
{
"epoch": 0.31,
"learning_rate": 3.2442324937763876e-05,
"loss": 0.7506,
"step": 892
},
{
"epoch": 0.31,
"learning_rate": 3.242482335659861e-05,
"loss": 0.8302,
"step": 893
},
{
"epoch": 0.31,
"learning_rate": 3.2407306267308426e-05,
"loss": 0.7952,
"step": 894
},
{
"epoch": 0.31,
"learning_rate": 3.23897736917574e-05,
"loss": 0.7942,
"step": 895
},
{
"epoch": 0.31,
"learning_rate": 3.237222565182892e-05,
"loss": 0.7405,
"step": 896
},
{
"epoch": 0.31,
"learning_rate": 3.2354662169425685e-05,
"loss": 0.7333,
"step": 897
},
{
"epoch": 0.31,
"learning_rate": 3.2337083266469687e-05,
"loss": 0.797,
"step": 898
},
{
"epoch": 0.31,
"learning_rate": 3.231948896490214e-05,
"loss": 0.7977,
"step": 899
},
{
"epoch": 0.31,
"learning_rate": 3.2301879286683484e-05,
"loss": 0.7909,
"step": 900
},
{
"epoch": 0.31,
"learning_rate": 3.2284254253793364e-05,
"loss": 0.8233,
"step": 901
},
{
"epoch": 0.31,
"learning_rate": 3.2266613888230566e-05,
"loss": 0.7773,
"step": 902
},
{
"epoch": 0.31,
"learning_rate": 3.224895821201304e-05,
"loss": 0.7881,
"step": 903
},
{
"epoch": 0.31,
"learning_rate": 3.223128724717783e-05,
"loss": 0.759,
"step": 904
},
{
"epoch": 0.31,
"learning_rate": 3.2213601015781066e-05,
"loss": 0.8091,
"step": 905
},
{
"epoch": 0.31,
"learning_rate": 3.219589953989794e-05,
"loss": 0.7975,
"step": 906
},
{
"epoch": 0.31,
"learning_rate": 3.2178182841622664e-05,
"loss": 0.4119,
"step": 907
},
{
"epoch": 0.31,
"learning_rate": 3.2160450943068446e-05,
"loss": 0.8084,
"step": 908
},
{
"epoch": 0.31,
"learning_rate": 3.214270386636747e-05,
"loss": 0.7807,
"step": 909
},
{
"epoch": 0.31,
"learning_rate": 3.212494163367088e-05,
"loss": 0.8346,
"step": 910
},
{
"epoch": 0.31,
"learning_rate": 3.210716426714871e-05,
"loss": 0.7691,
"step": 911
},
{
"epoch": 0.31,
"learning_rate": 3.208937178898989e-05,
"loss": 0.7978,
"step": 912
},
{
"epoch": 0.31,
"learning_rate": 3.207156422140225e-05,
"loss": 0.7992,
"step": 913
},
{
"epoch": 0.32,
"learning_rate": 3.205374158661238e-05,
"loss": 0.7531,
"step": 914
},
{
"epoch": 0.32,
"learning_rate": 3.203590390686576e-05,
"loss": 0.4035,
"step": 915
},
{
"epoch": 0.32,
"learning_rate": 3.201805120442658e-05,
"loss": 0.8252,
"step": 916
},
{
"epoch": 0.32,
"learning_rate": 3.200018350157781e-05,
"loss": 0.8209,
"step": 917
},
{
"epoch": 0.32,
"learning_rate": 3.198230082062115e-05,
"loss": 0.7693,
"step": 918
},
{
"epoch": 0.32,
"learning_rate": 3.196440318387699e-05,
"loss": 0.8083,
"step": 919
},
{
"epoch": 0.32,
"learning_rate": 3.194649061368437e-05,
"loss": 0.7949,
"step": 920
},
{
"epoch": 0.32,
"learning_rate": 3.192856313240099e-05,
"loss": 0.7929,
"step": 921
},
{
"epoch": 0.32,
"learning_rate": 3.1910620762403155e-05,
"loss": 0.4131,
"step": 922
},
{
"epoch": 0.32,
"learning_rate": 3.189266352608574e-05,
"loss": 0.7104,
"step": 923
},
{
"epoch": 0.32,
"learning_rate": 3.1874691445862196e-05,
"loss": 0.4028,
"step": 924
},
{
"epoch": 0.32,
"learning_rate": 3.185670454416449e-05,
"loss": 0.8058,
"step": 925
},
{
"epoch": 0.32,
"learning_rate": 3.1838702843443096e-05,
"loss": 0.7501,
"step": 926
},
{
"epoch": 0.32,
"learning_rate": 3.1820686366166956e-05,
"loss": 0.8155,
"step": 927
},
{
"epoch": 0.32,
"learning_rate": 3.180265513482345e-05,
"loss": 0.4146,
"step": 928
},
{
"epoch": 0.32,
"learning_rate": 3.1784609171918386e-05,
"loss": 0.7795,
"step": 929
},
{
"epoch": 0.32,
"learning_rate": 3.176654849997594e-05,
"loss": 0.8046,
"step": 930
},
{
"epoch": 0.32,
"learning_rate": 3.1748473141538666e-05,
"loss": 0.7586,
"step": 931
},
{
"epoch": 0.32,
"learning_rate": 3.173038311916743e-05,
"loss": 0.734,
"step": 932
},
{
"epoch": 0.32,
"learning_rate": 3.171227845544143e-05,
"loss": 0.7522,
"step": 933
},
{
"epoch": 0.32,
"learning_rate": 3.1694159172958104e-05,
"loss": 0.7384,
"step": 934
},
{
"epoch": 0.32,
"learning_rate": 3.167602529433316e-05,
"loss": 0.7724,
"step": 935
},
{
"epoch": 0.32,
"learning_rate": 3.165787684220053e-05,
"loss": 0.8096,
"step": 936
},
{
"epoch": 0.32,
"learning_rate": 3.163971383921231e-05,
"loss": 0.788,
"step": 937
},
{
"epoch": 0.32,
"learning_rate": 3.162153630803877e-05,
"loss": 0.7509,
"step": 938
},
{
"epoch": 0.32,
"learning_rate": 3.160334427136832e-05,
"loss": 0.8185,
"step": 939
},
{
"epoch": 0.32,
"learning_rate": 3.158513775190747e-05,
"loss": 0.7868,
"step": 940
},
{
"epoch": 0.32,
"learning_rate": 3.1566916772380804e-05,
"loss": 0.8034,
"step": 941
},
{
"epoch": 0.32,
"learning_rate": 3.1548681355530966e-05,
"loss": 0.7952,
"step": 942
},
{
"epoch": 0.33,
"learning_rate": 3.153043152411861e-05,
"loss": 0.8313,
"step": 943
},
{
"epoch": 0.33,
"learning_rate": 3.151216730092236e-05,
"loss": 0.7526,
"step": 944
},
{
"epoch": 0.33,
"learning_rate": 3.1493888708738854e-05,
"loss": 0.8384,
"step": 945
},
{
"epoch": 0.33,
"learning_rate": 3.147559577038263e-05,
"loss": 0.7487,
"step": 946
},
{
"epoch": 0.33,
"learning_rate": 3.145728850868614e-05,
"loss": 0.7493,
"step": 947
},
{
"epoch": 0.33,
"learning_rate": 3.14389669464997e-05,
"loss": 0.7929,
"step": 948
},
{
"epoch": 0.33,
"learning_rate": 3.14206311066915e-05,
"loss": 0.8428,
"step": 949
},
{
"epoch": 0.33,
"learning_rate": 3.140228101214754e-05,
"loss": 0.7788,
"step": 950
},
{
"epoch": 0.33,
"learning_rate": 3.13839166857716e-05,
"loss": 0.7879,
"step": 951
},
{
"epoch": 0.33,
"learning_rate": 3.136553815048525e-05,
"loss": 0.7653,
"step": 952
},
{
"epoch": 0.33,
"learning_rate": 3.134714542922777e-05,
"loss": 0.7877,
"step": 953
},
{
"epoch": 0.33,
"learning_rate": 3.132873854495616e-05,
"loss": 0.7544,
"step": 954
},
{
"epoch": 0.33,
"learning_rate": 3.131031752064509e-05,
"loss": 0.7232,
"step": 955
},
{
"epoch": 0.33,
"learning_rate": 3.129188237928689e-05,
"loss": 0.7897,
"step": 956
},
{
"epoch": 0.33,
"learning_rate": 3.1273433143891485e-05,
"loss": 0.7583,
"step": 957
},
{
"epoch": 0.33,
"learning_rate": 3.1254969837486425e-05,
"loss": 0.7778,
"step": 958
},
{
"epoch": 0.33,
"learning_rate": 3.1236492483116805e-05,
"loss": 0.7493,
"step": 959
},
{
"epoch": 0.33,
"learning_rate": 3.121800110384525e-05,
"loss": 0.7694,
"step": 960
},
{
"epoch": 0.33,
"learning_rate": 3.1199495722751914e-05,
"loss": 0.7809,
"step": 961
},
{
"epoch": 0.33,
"learning_rate": 3.1180976362934386e-05,
"loss": 0.7014,
"step": 962
},
{
"epoch": 0.33,
"learning_rate": 3.116244304750774e-05,
"loss": 0.7887,
"step": 963
},
{
"epoch": 0.33,
"learning_rate": 3.1143895799604454e-05,
"loss": 0.7485,
"step": 964
},
{
"epoch": 0.33,
"learning_rate": 3.1125334642374396e-05,
"loss": 0.7879,
"step": 965
},
{
"epoch": 0.33,
"learning_rate": 3.11067595989848e-05,
"loss": 0.3975,
"step": 966
},
{
"epoch": 0.33,
"learning_rate": 3.1088170692620226e-05,
"loss": 0.8082,
"step": 967
},
{
"epoch": 0.33,
"learning_rate": 3.106956794648254e-05,
"loss": 0.7603,
"step": 968
},
{
"epoch": 0.33,
"learning_rate": 3.1050951383790876e-05,
"loss": 0.7698,
"step": 969
},
{
"epoch": 0.33,
"learning_rate": 3.1032321027781625e-05,
"loss": 0.733,
"step": 970
},
{
"epoch": 0.33,
"learning_rate": 3.101367690170839e-05,
"loss": 0.8208,
"step": 971
},
{
"epoch": 0.34,
"learning_rate": 3.0995019028841956e-05,
"loss": 0.8021,
"step": 972
},
{
"epoch": 0.34,
"learning_rate": 3.097634743247026e-05,
"loss": 0.8142,
"step": 973
},
{
"epoch": 0.34,
"learning_rate": 3.0957662135898406e-05,
"loss": 0.7767,
"step": 974
},
{
"epoch": 0.34,
"learning_rate": 3.093896316244855e-05,
"loss": 0.7776,
"step": 975
},
{
"epoch": 0.34,
"learning_rate": 3.092025053545992e-05,
"loss": 0.7911,
"step": 976
},
{
"epoch": 0.34,
"learning_rate": 3.090152427828884e-05,
"loss": 0.791,
"step": 977
},
{
"epoch": 0.34,
"learning_rate": 3.08827844143086e-05,
"loss": 0.8135,
"step": 978
},
{
"epoch": 0.34,
"learning_rate": 3.086403096690947e-05,
"loss": 0.4192,
"step": 979
},
{
"epoch": 0.34,
"learning_rate": 3.084526395949871e-05,
"loss": 0.7672,
"step": 980
},
{
"epoch": 0.34,
"learning_rate": 3.082648341550046e-05,
"loss": 0.7937,
"step": 981
},
{
"epoch": 0.34,
"learning_rate": 3.08076893583558e-05,
"loss": 0.8341,
"step": 982
},
{
"epoch": 0.34,
"learning_rate": 3.078888181152264e-05,
"loss": 0.7725,
"step": 983
},
{
"epoch": 0.34,
"learning_rate": 3.0770060798475756e-05,
"loss": 0.788,
"step": 984
},
{
"epoch": 0.34,
"learning_rate": 3.0751226342706714e-05,
"loss": 0.7564,
"step": 985
},
{
"epoch": 0.34,
"learning_rate": 3.0732378467723866e-05,
"loss": 0.4002,
"step": 986
},
{
"epoch": 0.34,
"learning_rate": 3.0713517197052305e-05,
"loss": 0.8263,
"step": 987
},
{
"epoch": 0.34,
"learning_rate": 3.0694642554233855e-05,
"loss": 0.7808,
"step": 988
},
{
"epoch": 0.34,
"learning_rate": 3.067575456282702e-05,
"loss": 0.7997,
"step": 989
},
{
"epoch": 0.34,
"learning_rate": 3.065685324640698e-05,
"loss": 0.7895,
"step": 990
},
{
"epoch": 0.34,
"learning_rate": 3.063793862856553e-05,
"loss": 0.7984,
"step": 991
},
{
"epoch": 0.34,
"learning_rate": 3.0619010732911074e-05,
"loss": 0.7919,
"step": 992
},
{
"epoch": 0.34,
"learning_rate": 3.0600069583068594e-05,
"loss": 0.7973,
"step": 993
},
{
"epoch": 0.34,
"learning_rate": 3.0581115202679614e-05,
"loss": 0.8669,
"step": 994
},
{
"epoch": 0.34,
"learning_rate": 3.056214761540216e-05,
"loss": 0.786,
"step": 995
},
{
"epoch": 0.34,
"learning_rate": 3.0543166844910746e-05,
"loss": 0.7671,
"step": 996
},
{
"epoch": 0.34,
"learning_rate": 3.0524172914896365e-05,
"loss": 0.7689,
"step": 997
},
{
"epoch": 0.34,
"learning_rate": 3.0505165849066394e-05,
"loss": 0.7848,
"step": 998
},
{
"epoch": 0.34,
"learning_rate": 3.0486145671144637e-05,
"loss": 0.7813,
"step": 999
},
{
"epoch": 0.34,
"learning_rate": 3.0467112404871257e-05,
"loss": 0.7761,
"step": 1000
},
{
"epoch": 0.35,
"learning_rate": 3.0448066074002746e-05,
"loss": 0.7661,
"step": 1001
},
{
"epoch": 0.35,
"learning_rate": 3.0429006702311906e-05,
"loss": 0.7892,
"step": 1002
},
{
"epoch": 0.35,
"learning_rate": 3.040993431358782e-05,
"loss": 0.7365,
"step": 1003
},
{
"epoch": 0.35,
"learning_rate": 3.0390848931635823e-05,
"loss": 0.7895,
"step": 1004
},
{
"epoch": 0.35,
"learning_rate": 3.037175058027744e-05,
"loss": 0.7838,
"step": 1005
},
{
"epoch": 0.35,
"learning_rate": 3.0352639283350425e-05,
"loss": 0.7371,
"step": 1006
},
{
"epoch": 0.35,
"learning_rate": 3.0333515064708653e-05,
"loss": 0.7801,
"step": 1007
},
{
"epoch": 0.35,
"learning_rate": 3.031437794822215e-05,
"loss": 0.7706,
"step": 1008
},
{
"epoch": 0.35,
"learning_rate": 3.0295227957777028e-05,
"loss": 0.7829,
"step": 1009
},
{
"epoch": 0.35,
"learning_rate": 3.0276065117275483e-05,
"loss": 0.7443,
"step": 1010
},
{
"epoch": 0.35,
"learning_rate": 3.025688945063574e-05,
"loss": 0.7323,
"step": 1011
},
{
"epoch": 0.35,
"learning_rate": 3.0237700981792023e-05,
"loss": 0.816,
"step": 1012
},
{
"epoch": 0.35,
"learning_rate": 3.021849973469455e-05,
"loss": 0.8194,
"step": 1013
},
{
"epoch": 0.35,
"learning_rate": 3.0199285733309494e-05,
"loss": 0.7765,
"step": 1014
},
{
"epoch": 0.35,
"learning_rate": 3.018005900161892e-05,
"loss": 0.7493,
"step": 1015
},
{
"epoch": 0.35,
"learning_rate": 3.016081956362081e-05,
"loss": 0.7798,
"step": 1016
},
{
"epoch": 0.35,
"learning_rate": 3.014156744332899e-05,
"loss": 0.7756,
"step": 1017
},
{
"epoch": 0.35,
"learning_rate": 3.012230266477313e-05,
"loss": 0.7947,
"step": 1018
},
{
"epoch": 0.35,
"learning_rate": 3.010302525199868e-05,
"loss": 0.8219,
"step": 1019
},
{
"epoch": 0.35,
"learning_rate": 3.0083735229066868e-05,
"loss": 0.8383,
"step": 1020
},
{
"epoch": 0.35,
"learning_rate": 3.0064432620054667e-05,
"loss": 0.7983,
"step": 1021
},
{
"epoch": 0.35,
"learning_rate": 3.0045117449054762e-05,
"loss": 0.7851,
"step": 1022
},
{
"epoch": 0.35,
"learning_rate": 3.0025789740175502e-05,
"loss": 0.7822,
"step": 1023
},
{
"epoch": 0.35,
"learning_rate": 3.0006449517540894e-05,
"loss": 0.7863,
"step": 1024
},
{
"epoch": 0.35,
"learning_rate": 2.9987096805290566e-05,
"loss": 0.7936,
"step": 1025
},
{
"epoch": 0.35,
"learning_rate": 2.9967731627579737e-05,
"loss": 0.7801,
"step": 1026
},
{
"epoch": 0.35,
"learning_rate": 2.9948354008579173e-05,
"loss": 0.8427,
"step": 1027
},
{
"epoch": 0.35,
"learning_rate": 2.9928963972475186e-05,
"loss": 0.7931,
"step": 1028
},
{
"epoch": 0.35,
"learning_rate": 2.9909561543469565e-05,
"loss": 0.7673,
"step": 1029
},
{
"epoch": 0.36,
"learning_rate": 2.9890146745779587e-05,
"loss": 0.7857,
"step": 1030
},
{
"epoch": 0.36,
"learning_rate": 2.9870719603637956e-05,
"loss": 0.8027,
"step": 1031
},
{
"epoch": 0.36,
"learning_rate": 2.9851280141292792e-05,
"loss": 0.7689,
"step": 1032
},
{
"epoch": 0.36,
"learning_rate": 2.9831828383007585e-05,
"loss": 0.7826,
"step": 1033
},
{
"epoch": 0.36,
"learning_rate": 2.9812364353061175e-05,
"loss": 0.7925,
"step": 1034
},
{
"epoch": 0.36,
"learning_rate": 2.9792888075747718e-05,
"loss": 0.782,
"step": 1035
},
{
"epoch": 0.36,
"learning_rate": 2.977339957537666e-05,
"loss": 0.7516,
"step": 1036
},
{
"epoch": 0.36,
"learning_rate": 2.9753898876272695e-05,
"loss": 0.7351,
"step": 1037
},
{
"epoch": 0.36,
"learning_rate": 2.9734386002775754e-05,
"loss": 0.758,
"step": 1038
},
{
"epoch": 0.36,
"learning_rate": 2.9714860979240953e-05,
"loss": 0.8041,
"step": 1039
},
{
"epoch": 0.36,
"learning_rate": 2.9695323830038586e-05,
"loss": 0.7643,
"step": 1040
},
{
"epoch": 0.36,
"learning_rate": 2.967577457955407e-05,
"loss": 0.8046,
"step": 1041
},
{
"epoch": 0.36,
"learning_rate": 2.9656213252187934e-05,
"loss": 0.7469,
"step": 1042
},
{
"epoch": 0.36,
"learning_rate": 2.963663987235577e-05,
"loss": 0.7683,
"step": 1043
},
{
"epoch": 0.36,
"learning_rate": 2.9617054464488225e-05,
"loss": 0.7801,
"step": 1044
},
{
"epoch": 0.36,
"learning_rate": 2.9597457053030956e-05,
"loss": 0.7998,
"step": 1045
},
{
"epoch": 0.36,
"learning_rate": 2.95778476624446e-05,
"loss": 0.7255,
"step": 1046
},
{
"epoch": 0.36,
"learning_rate": 2.9558226317204744e-05,
"loss": 0.7898,
"step": 1047
},
{
"epoch": 0.36,
"learning_rate": 2.95385930418019e-05,
"loss": 0.7873,
"step": 1048
},
{
"epoch": 0.36,
"learning_rate": 2.9518947860741476e-05,
"loss": 0.7671,
"step": 1049
},
{
"epoch": 0.36,
"learning_rate": 2.9499290798543723e-05,
"loss": 0.7479,
"step": 1050
},
{
"epoch": 0.36,
"learning_rate": 2.947962187974374e-05,
"loss": 0.7782,
"step": 1051
},
{
"epoch": 0.36,
"learning_rate": 2.9459941128891412e-05,
"loss": 0.8216,
"step": 1052
},
{
"epoch": 0.36,
"learning_rate": 2.9440248570551406e-05,
"loss": 0.3917,
"step": 1053
},
{
"epoch": 0.36,
"learning_rate": 2.942054422930311e-05,
"loss": 0.7534,
"step": 1054
},
{
"epoch": 0.36,
"learning_rate": 2.9400828129740627e-05,
"loss": 0.7906,
"step": 1055
},
{
"epoch": 0.36,
"learning_rate": 2.9381100296472742e-05,
"loss": 0.7688,
"step": 1056
},
{
"epoch": 0.36,
"learning_rate": 2.9361360754122876e-05,
"loss": 0.7967,
"step": 1057
},
{
"epoch": 0.36,
"learning_rate": 2.934160952732907e-05,
"loss": 0.769,
"step": 1058
},
{
"epoch": 0.37,
"learning_rate": 2.9321846640743948e-05,
"loss": 0.7857,
"step": 1059
},
{
"epoch": 0.37,
"learning_rate": 2.930207211903468e-05,
"loss": 0.3988,
"step": 1060
},
{
"epoch": 0.37,
"learning_rate": 2.928228598688297e-05,
"loss": 0.7585,
"step": 1061
},
{
"epoch": 0.37,
"learning_rate": 2.9262488268985016e-05,
"loss": 0.78,
"step": 1062
},
{
"epoch": 0.37,
"learning_rate": 2.9242678990051462e-05,
"loss": 0.7777,
"step": 1063
},
{
"epoch": 0.37,
"learning_rate": 2.922285817480739e-05,
"loss": 0.7726,
"step": 1064
},
{
"epoch": 0.37,
"learning_rate": 2.9203025847992283e-05,
"loss": 0.3931,
"step": 1065
},
{
"epoch": 0.37,
"learning_rate": 2.9183182034359986e-05,
"loss": 0.7994,
"step": 1066
},
{
"epoch": 0.37,
"learning_rate": 2.916332675867869e-05,
"loss": 0.8001,
"step": 1067
},
{
"epoch": 0.37,
"learning_rate": 2.9143460045730886e-05,
"loss": 0.7611,
"step": 1068
},
{
"epoch": 0.37,
"learning_rate": 2.912358192031334e-05,
"loss": 0.768,
"step": 1069
},
{
"epoch": 0.37,
"learning_rate": 2.910369240723706e-05,
"loss": 0.7016,
"step": 1070
},
{
"epoch": 0.37,
"learning_rate": 2.908379153132729e-05,
"loss": 0.7768,
"step": 1071
},
{
"epoch": 0.37,
"learning_rate": 2.9063879317423433e-05,
"loss": 0.8137,
"step": 1072
},
{
"epoch": 0.37,
"learning_rate": 2.9043955790379035e-05,
"loss": 0.8189,
"step": 1073
},
{
"epoch": 0.37,
"learning_rate": 2.9024020975061798e-05,
"loss": 0.7597,
"step": 1074
},
{
"epoch": 0.37,
"learning_rate": 2.9004074896353468e-05,
"loss": 0.7559,
"step": 1075
},
{
"epoch": 0.37,
"learning_rate": 2.8984117579149896e-05,
"loss": 0.7517,
"step": 1076
},
{
"epoch": 0.37,
"learning_rate": 2.896414904836093e-05,
"loss": 0.8296,
"step": 1077
},
{
"epoch": 0.37,
"learning_rate": 2.8944169328910427e-05,
"loss": 0.7499,
"step": 1078
},
{
"epoch": 0.37,
"learning_rate": 2.8924178445736197e-05,
"loss": 0.811,
"step": 1079
},
{
"epoch": 0.37,
"learning_rate": 2.890417642379e-05,
"loss": 0.3864,
"step": 1080
},
{
"epoch": 0.37,
"learning_rate": 2.8884163288037486e-05,
"loss": 0.7926,
"step": 1081
},
{
"epoch": 0.37,
"learning_rate": 2.8864139063458187e-05,
"loss": 0.8107,
"step": 1082
},
{
"epoch": 0.37,
"learning_rate": 2.884410377504547e-05,
"loss": 0.7786,
"step": 1083
},
{
"epoch": 0.37,
"learning_rate": 2.8824057447806502e-05,
"loss": 0.8012,
"step": 1084
},
{
"epoch": 0.37,
"learning_rate": 2.880400010676225e-05,
"loss": 0.7543,
"step": 1085
},
{
"epoch": 0.37,
"learning_rate": 2.878393177694741e-05,
"loss": 0.7623,
"step": 1086
},
{
"epoch": 0.37,
"learning_rate": 2.8763852483410403e-05,
"loss": 0.7124,
"step": 1087
},
{
"epoch": 0.38,
"learning_rate": 2.8743762251213333e-05,
"loss": 0.7707,
"step": 1088
},
{
"epoch": 0.38,
"learning_rate": 2.8723661105431947e-05,
"loss": 0.8044,
"step": 1089
},
{
"epoch": 0.38,
"learning_rate": 2.8703549071155627e-05,
"loss": 0.7128,
"step": 1090
},
{
"epoch": 0.38,
"learning_rate": 2.8683426173487342e-05,
"loss": 0.7922,
"step": 1091
},
{
"epoch": 0.38,
"learning_rate": 2.8663292437543622e-05,
"loss": 0.7874,
"step": 1092
},
{
"epoch": 0.38,
"learning_rate": 2.8643147888454507e-05,
"loss": 0.7562,
"step": 1093
},
{
"epoch": 0.38,
"learning_rate": 2.862299255136357e-05,
"loss": 0.7194,
"step": 1094
},
{
"epoch": 0.38,
"learning_rate": 2.860282645142781e-05,
"loss": 0.7723,
"step": 1095
},
{
"epoch": 0.38,
"learning_rate": 2.8582649613817693e-05,
"loss": 0.7591,
"step": 1096
},
{
"epoch": 0.38,
"learning_rate": 2.856246206371705e-05,
"loss": 0.7719,
"step": 1097
},
{
"epoch": 0.38,
"learning_rate": 2.854226382632312e-05,
"loss": 0.7956,
"step": 1098
},
{
"epoch": 0.38,
"learning_rate": 2.8522054926846463e-05,
"loss": 0.7905,
"step": 1099
},
{
"epoch": 0.38,
"learning_rate": 2.8501835390510952e-05,
"loss": 0.778,
"step": 1100
},
{
"epoch": 0.38,
"learning_rate": 2.8481605242553728e-05,
"loss": 0.7179,
"step": 1101
},
{
"epoch": 0.38,
"learning_rate": 2.846136450822518e-05,
"loss": 0.8199,
"step": 1102
},
{
"epoch": 0.38,
"learning_rate": 2.844111321278893e-05,
"loss": 0.8244,
"step": 1103
},
{
"epoch": 0.38,
"learning_rate": 2.8420851381521753e-05,
"loss": 0.7942,
"step": 1104
},
{
"epoch": 0.38,
"learning_rate": 2.8400579039713583e-05,
"loss": 0.7463,
"step": 1105
},
{
"epoch": 0.38,
"learning_rate": 2.838029621266748e-05,
"loss": 0.7347,
"step": 1106
},
{
"epoch": 0.38,
"learning_rate": 2.83600029256996e-05,
"loss": 0.7902,
"step": 1107
},
{
"epoch": 0.38,
"learning_rate": 2.833969920413913e-05,
"loss": 0.7839,
"step": 1108
},
{
"epoch": 0.38,
"learning_rate": 2.8319385073328294e-05,
"loss": 0.8208,
"step": 1109
},
{
"epoch": 0.38,
"learning_rate": 2.8299060558622314e-05,
"loss": 0.7861,
"step": 1110
},
{
"epoch": 0.38,
"learning_rate": 2.827872568538936e-05,
"loss": 0.3811,
"step": 1111
},
{
"epoch": 0.38,
"learning_rate": 2.825838047901054e-05,
"loss": 0.8025,
"step": 1112
},
{
"epoch": 0.38,
"learning_rate": 2.8238024964879857e-05,
"loss": 0.8055,
"step": 1113
},
{
"epoch": 0.38,
"learning_rate": 2.821765916840418e-05,
"loss": 0.7934,
"step": 1114
},
{
"epoch": 0.38,
"learning_rate": 2.8197283115003214e-05,
"loss": 0.811,
"step": 1115
},
{
"epoch": 0.38,
"learning_rate": 2.817689683010946e-05,
"loss": 0.8192,
"step": 1116
},
{
"epoch": 0.39,
"learning_rate": 2.8156500339168195e-05,
"loss": 0.7707,
"step": 1117
},
{
"epoch": 0.39,
"learning_rate": 2.8136093667637438e-05,
"loss": 0.7929,
"step": 1118
},
{
"epoch": 0.39,
"learning_rate": 2.81156768409879e-05,
"loss": 0.7565,
"step": 1119
},
{
"epoch": 0.39,
"learning_rate": 2.8095249884702985e-05,
"loss": 0.8005,
"step": 1120
},
{
"epoch": 0.39,
"learning_rate": 2.8074812824278736e-05,
"loss": 0.8027,
"step": 1121
},
{
"epoch": 0.39,
"learning_rate": 2.805436568522379e-05,
"loss": 0.751,
"step": 1122
},
{
"epoch": 0.39,
"learning_rate": 2.8033908493059394e-05,
"loss": 0.7262,
"step": 1123
},
{
"epoch": 0.39,
"learning_rate": 2.801344127331931e-05,
"loss": 0.7479,
"step": 1124
},
{
"epoch": 0.39,
"learning_rate": 2.7992964051549852e-05,
"loss": 0.7721,
"step": 1125
},
{
"epoch": 0.39,
"learning_rate": 2.7972476853309788e-05,
"loss": 0.7797,
"step": 1126
},
{
"epoch": 0.39,
"learning_rate": 2.7951979704170353e-05,
"loss": 0.7762,
"step": 1127
},
{
"epoch": 0.39,
"learning_rate": 2.793147262971519e-05,
"loss": 0.8444,
"step": 1128
},
{
"epoch": 0.39,
"learning_rate": 2.7910955655540348e-05,
"loss": 0.8247,
"step": 1129
},
{
"epoch": 0.39,
"learning_rate": 2.789042880725422e-05,
"loss": 0.8047,
"step": 1130
},
{
"epoch": 0.39,
"learning_rate": 2.7869892110477525e-05,
"loss": 0.8178,
"step": 1131
},
{
"epoch": 0.39,
"learning_rate": 2.7849345590843276e-05,
"loss": 0.782,
"step": 1132
},
{
"epoch": 0.39,
"learning_rate": 2.7828789273996748e-05,
"loss": 0.3834,
"step": 1133
},
{
"epoch": 0.39,
"learning_rate": 2.7808223185595448e-05,
"loss": 0.7481,
"step": 1134
},
{
"epoch": 0.39,
"learning_rate": 2.778764735130907e-05,
"loss": 0.8047,
"step": 1135
},
{
"epoch": 0.39,
"learning_rate": 2.7767061796819473e-05,
"loss": 0.7142,
"step": 1136
},
{
"epoch": 0.39,
"learning_rate": 2.7746466547820656e-05,
"loss": 0.7871,
"step": 1137
},
{
"epoch": 0.39,
"learning_rate": 2.7725861630018703e-05,
"loss": 0.7628,
"step": 1138
},
{
"epoch": 0.39,
"learning_rate": 2.7705247069131802e-05,
"loss": 0.7836,
"step": 1139
},
{
"epoch": 0.39,
"learning_rate": 2.7684622890890134e-05,
"loss": 0.384,
"step": 1140
},
{
"epoch": 0.39,
"learning_rate": 2.7663989121035907e-05,
"loss": 0.7377,
"step": 1141
},
{
"epoch": 0.39,
"learning_rate": 2.7643345785323297e-05,
"loss": 0.7791,
"step": 1142
},
{
"epoch": 0.39,
"learning_rate": 2.7622692909518423e-05,
"loss": 0.7917,
"step": 1143
},
{
"epoch": 0.39,
"learning_rate": 2.7602030519399295e-05,
"loss": 0.7991,
"step": 1144
},
{
"epoch": 0.39,
"learning_rate": 2.7581358640755832e-05,
"loss": 0.8096,
"step": 1145
},
{
"epoch": 0.4,
"learning_rate": 2.7560677299389747e-05,
"loss": 0.8009,
"step": 1146
},
{
"epoch": 0.4,
"learning_rate": 2.7539986521114617e-05,
"loss": 0.7569,
"step": 1147
},
{
"epoch": 0.4,
"learning_rate": 2.7519286331755766e-05,
"loss": 0.8107,
"step": 1148
},
{
"epoch": 0.4,
"learning_rate": 2.7498576757150265e-05,
"loss": 0.7465,
"step": 1149
},
{
"epoch": 0.4,
"learning_rate": 2.7477857823146915e-05,
"loss": 0.7552,
"step": 1150
},
{
"epoch": 0.4,
"learning_rate": 2.7457129555606177e-05,
"loss": 0.7871,
"step": 1151
},
{
"epoch": 0.4,
"learning_rate": 2.7436391980400185e-05,
"loss": 0.7602,
"step": 1152
},
{
"epoch": 0.4,
"learning_rate": 2.7415645123412672e-05,
"loss": 0.7127,
"step": 1153
},
{
"epoch": 0.4,
"learning_rate": 2.7394889010538978e-05,
"loss": 0.7924,
"step": 1154
},
{
"epoch": 0.4,
"learning_rate": 2.737412366768596e-05,
"loss": 0.7989,
"step": 1155
},
{
"epoch": 0.4,
"learning_rate": 2.7353349120772036e-05,
"loss": 0.8262,
"step": 1156
},
{
"epoch": 0.4,
"learning_rate": 2.7332565395727092e-05,
"loss": 0.8071,
"step": 1157
},
{
"epoch": 0.4,
"learning_rate": 2.731177251849246e-05,
"loss": 0.7752,
"step": 1158
},
{
"epoch": 0.4,
"learning_rate": 2.7290970515020912e-05,
"loss": 0.7872,
"step": 1159
},
{
"epoch": 0.4,
"learning_rate": 2.7270159411276597e-05,
"loss": 0.7962,
"step": 1160
},
{
"epoch": 0.4,
"learning_rate": 2.724933923323505e-05,
"loss": 0.8113,
"step": 1161
},
{
"epoch": 0.4,
"learning_rate": 2.7228510006883094e-05,
"loss": 0.7509,
"step": 1162
},
{
"epoch": 0.4,
"learning_rate": 2.7207671758218884e-05,
"loss": 0.7793,
"step": 1163
},
{
"epoch": 0.4,
"learning_rate": 2.7186824513251796e-05,
"loss": 0.7886,
"step": 1164
},
{
"epoch": 0.4,
"learning_rate": 2.716596829800247e-05,
"loss": 0.7497,
"step": 1165
},
{
"epoch": 0.4,
"learning_rate": 2.714510313850272e-05,
"loss": 0.7828,
"step": 1166
},
{
"epoch": 0.4,
"learning_rate": 2.712422906079554e-05,
"loss": 0.7493,
"step": 1167
},
{
"epoch": 0.4,
"learning_rate": 2.710334609093504e-05,
"loss": 0.808,
"step": 1168
},
{
"epoch": 0.4,
"learning_rate": 2.7082454254986436e-05,
"loss": 0.7756,
"step": 1169
},
{
"epoch": 0.4,
"learning_rate": 2.7061553579026017e-05,
"loss": 0.8343,
"step": 1170
},
{
"epoch": 0.4,
"learning_rate": 2.7040644089141097e-05,
"loss": 0.734,
"step": 1171
},
{
"epoch": 0.4,
"learning_rate": 2.7019725811429987e-05,
"loss": 0.8193,
"step": 1172
},
{
"epoch": 0.4,
"learning_rate": 2.699879877200198e-05,
"loss": 0.7592,
"step": 1173
},
{
"epoch": 0.4,
"learning_rate": 2.69778629969773e-05,
"loss": 0.7339,
"step": 1174
},
{
"epoch": 0.41,
"learning_rate": 2.695691851248706e-05,
"loss": 0.791,
"step": 1175
},
{
"epoch": 0.41,
"learning_rate": 2.6935965344673266e-05,
"loss": 0.7483,
"step": 1176
},
{
"epoch": 0.41,
"learning_rate": 2.6915003519688747e-05,
"loss": 0.7732,
"step": 1177
},
{
"epoch": 0.41,
"learning_rate": 2.6894033063697143e-05,
"loss": 0.41,
"step": 1178
},
{
"epoch": 0.41,
"learning_rate": 2.6873054002872874e-05,
"loss": 0.3798,
"step": 1179
},
{
"epoch": 0.41,
"learning_rate": 2.6852066363401082e-05,
"loss": 0.7809,
"step": 1180
},
{
"epoch": 0.41,
"learning_rate": 2.683107017147764e-05,
"loss": 0.7847,
"step": 1181
},
{
"epoch": 0.41,
"learning_rate": 2.681006545330907e-05,
"loss": 0.8115,
"step": 1182
},
{
"epoch": 0.41,
"learning_rate": 2.6789052235112554e-05,
"loss": 0.7162,
"step": 1183
},
{
"epoch": 0.41,
"learning_rate": 2.6768030543115876e-05,
"loss": 0.7891,
"step": 1184
},
{
"epoch": 0.41,
"learning_rate": 2.6747000403557402e-05,
"loss": 0.7727,
"step": 1185
},
{
"epoch": 0.41,
"learning_rate": 2.672596184268604e-05,
"loss": 0.8112,
"step": 1186
},
{
"epoch": 0.41,
"learning_rate": 2.6704914886761206e-05,
"loss": 0.7784,
"step": 1187
},
{
"epoch": 0.41,
"learning_rate": 2.66838595620528e-05,
"loss": 0.7294,
"step": 1188
},
{
"epoch": 0.41,
"learning_rate": 2.6662795894841155e-05,
"loss": 0.7651,
"step": 1189
},
{
"epoch": 0.41,
"learning_rate": 2.6641723911417035e-05,
"loss": 0.8164,
"step": 1190
},
{
"epoch": 0.41,
"learning_rate": 2.6620643638081562e-05,
"loss": 0.79,
"step": 1191
},
{
"epoch": 0.41,
"learning_rate": 2.6599555101146236e-05,
"loss": 0.7787,
"step": 1192
},
{
"epoch": 0.41,
"learning_rate": 2.6578458326932842e-05,
"loss": 0.7965,
"step": 1193
},
{
"epoch": 0.41,
"learning_rate": 2.6557353341773456e-05,
"loss": 0.807,
"step": 1194
},
{
"epoch": 0.41,
"learning_rate": 2.653624017201041e-05,
"loss": 0.7746,
"step": 1195
},
{
"epoch": 0.41,
"learning_rate": 2.651511884399624e-05,
"loss": 0.7724,
"step": 1196
},
{
"epoch": 0.41,
"learning_rate": 2.6493989384093674e-05,
"loss": 0.8038,
"step": 1197
},
{
"epoch": 0.41,
"learning_rate": 2.6472851818675583e-05,
"loss": 0.734,
"step": 1198
},
{
"epoch": 0.41,
"learning_rate": 2.6451706174124962e-05,
"loss": 0.802,
"step": 1199
},
{
"epoch": 0.41,
"learning_rate": 2.6430552476834876e-05,
"loss": 0.7854,
"step": 1200
},
{
"epoch": 0.41,
"learning_rate": 2.640939075320847e-05,
"loss": 0.7156,
"step": 1201
},
{
"epoch": 0.41,
"learning_rate": 2.6388221029658872e-05,
"loss": 0.7596,
"step": 1202
},
{
"epoch": 0.41,
"learning_rate": 2.6367043332609223e-05,
"loss": 0.7801,
"step": 1203
},
{
"epoch": 0.42,
"learning_rate": 2.6345857688492595e-05,
"loss": 0.7703,
"step": 1204
},
{
"epoch": 0.42,
"learning_rate": 2.6324664123751992e-05,
"loss": 0.7848,
"step": 1205
},
{
"epoch": 0.42,
"learning_rate": 2.6303462664840303e-05,
"loss": 0.7632,
"step": 1206
},
{
"epoch": 0.42,
"learning_rate": 2.628225333822027e-05,
"loss": 0.759,
"step": 1207
},
{
"epoch": 0.42,
"learning_rate": 2.6261036170364448e-05,
"loss": 0.7875,
"step": 1208
},
{
"epoch": 0.42,
"learning_rate": 2.6239811187755186e-05,
"loss": 0.8171,
"step": 1209
},
{
"epoch": 0.42,
"learning_rate": 2.6218578416884592e-05,
"loss": 0.7735,
"step": 1210
},
{
"epoch": 0.42,
"learning_rate": 2.619733788425448e-05,
"loss": 0.7739,
"step": 1211
},
{
"epoch": 0.42,
"learning_rate": 2.617608961637637e-05,
"loss": 0.8239,
"step": 1212
},
{
"epoch": 0.42,
"learning_rate": 2.6154833639771415e-05,
"loss": 0.824,
"step": 1213
},
{
"epoch": 0.42,
"learning_rate": 2.6133569980970403e-05,
"loss": 0.7586,
"step": 1214
},
{
"epoch": 0.42,
"learning_rate": 2.611229866651372e-05,
"loss": 0.7145,
"step": 1215
},
{
"epoch": 0.42,
"learning_rate": 2.609101972295129e-05,
"loss": 0.8081,
"step": 1216
},
{
"epoch": 0.42,
"learning_rate": 2.606973317684257e-05,
"loss": 0.393,
"step": 1217
},
{
"epoch": 0.42,
"learning_rate": 2.6048439054756492e-05,
"loss": 0.7935,
"step": 1218
},
{
"epoch": 0.42,
"learning_rate": 2.6027137383271466e-05,
"loss": 0.7659,
"step": 1219
},
{
"epoch": 0.42,
"learning_rate": 2.6005828188975315e-05,
"loss": 0.758,
"step": 1220
},
{
"epoch": 0.42,
"learning_rate": 2.598451149846524e-05,
"loss": 0.7534,
"step": 1221
},
{
"epoch": 0.42,
"learning_rate": 2.5963187338347812e-05,
"loss": 0.7855,
"step": 1222
},
{
"epoch": 0.42,
"learning_rate": 2.594185573523892e-05,
"loss": 0.8158,
"step": 1223
},
{
"epoch": 0.42,
"learning_rate": 2.592051671576375e-05,
"loss": 0.7861,
"step": 1224
},
{
"epoch": 0.42,
"learning_rate": 2.5899170306556737e-05,
"loss": 0.8282,
"step": 1225
},
{
"epoch": 0.42,
"learning_rate": 2.587781653426154e-05,
"loss": 0.8062,
"step": 1226
},
{
"epoch": 0.42,
"learning_rate": 2.585645542553101e-05,
"loss": 0.7536,
"step": 1227
},
{
"epoch": 0.42,
"learning_rate": 2.583508700702716e-05,
"loss": 0.776,
"step": 1228
},
{
"epoch": 0.42,
"learning_rate": 2.5813711305421114e-05,
"loss": 0.796,
"step": 1229
},
{
"epoch": 0.42,
"learning_rate": 2.57923283473931e-05,
"loss": 0.7778,
"step": 1230
},
{
"epoch": 0.42,
"learning_rate": 2.57709381596324e-05,
"loss": 0.8134,
"step": 1231
},
{
"epoch": 0.42,
"learning_rate": 2.5749540768837306e-05,
"loss": 0.7726,
"step": 1232
},
{
"epoch": 0.43,
"learning_rate": 2.572813620171513e-05,
"loss": 0.7581,
"step": 1233
},
{
"epoch": 0.43,
"learning_rate": 2.570672448498211e-05,
"loss": 0.7848,
"step": 1234
},
{
"epoch": 0.43,
"learning_rate": 2.568530564536342e-05,
"loss": 0.7735,
"step": 1235
},
{
"epoch": 0.43,
"learning_rate": 2.5663879709593133e-05,
"loss": 0.4407,
"step": 1236
},
{
"epoch": 0.43,
"learning_rate": 2.5642446704414167e-05,
"loss": 0.8055,
"step": 1237
},
{
"epoch": 0.43,
"learning_rate": 2.5621006656578267e-05,
"loss": 0.78,
"step": 1238
},
{
"epoch": 0.43,
"learning_rate": 2.559955959284598e-05,
"loss": 0.78,
"step": 1239
},
{
"epoch": 0.43,
"learning_rate": 2.5578105539986582e-05,
"loss": 0.7926,
"step": 1240
},
{
"epoch": 0.43,
"learning_rate": 2.55566445247781e-05,
"loss": 0.7531,
"step": 1241
},
{
"epoch": 0.43,
"learning_rate": 2.5535176574007245e-05,
"loss": 0.7975,
"step": 1242
},
{
"epoch": 0.43,
"learning_rate": 2.5513701714469373e-05,
"loss": 0.8024,
"step": 1243
},
{
"epoch": 0.43,
"learning_rate": 2.5492219972968473e-05,
"loss": 0.791,
"step": 1244
},
{
"epoch": 0.43,
"learning_rate": 2.5470731376317126e-05,
"loss": 0.7916,
"step": 1245
},
{
"epoch": 0.43,
"learning_rate": 2.5449235951336458e-05,
"loss": 0.7442,
"step": 1246
},
{
"epoch": 0.43,
"learning_rate": 2.5427733724856136e-05,
"loss": 0.7904,
"step": 1247
},
{
"epoch": 0.43,
"learning_rate": 2.540622472371429e-05,
"loss": 0.784,
"step": 1248
},
{
"epoch": 0.43,
"learning_rate": 2.5384708974757536e-05,
"loss": 0.7626,
"step": 1249
},
{
"epoch": 0.43,
"learning_rate": 2.536318650484089e-05,
"loss": 0.7508,
"step": 1250
},
{
"epoch": 0.43,
"learning_rate": 2.5341657340827766e-05,
"loss": 0.7706,
"step": 1251
},
{
"epoch": 0.43,
"learning_rate": 2.532012150958993e-05,
"loss": 0.7862,
"step": 1252
},
{
"epoch": 0.43,
"learning_rate": 2.5298579038007478e-05,
"loss": 0.7646,
"step": 1253
},
{
"epoch": 0.43,
"learning_rate": 2.5277029952968767e-05,
"loss": 0.8164,
"step": 1254
},
{
"epoch": 0.43,
"learning_rate": 2.5255474281370455e-05,
"loss": 0.7794,
"step": 1255
},
{
"epoch": 0.43,
"learning_rate": 2.5233912050117376e-05,
"loss": 0.77,
"step": 1256
},
{
"epoch": 0.43,
"learning_rate": 2.5212343286122587e-05,
"loss": 0.76,
"step": 1257
},
{
"epoch": 0.43,
"learning_rate": 2.519076801630727e-05,
"loss": 0.7427,
"step": 1258
},
{
"epoch": 0.43,
"learning_rate": 2.516918626760075e-05,
"loss": 0.7718,
"step": 1259
},
{
"epoch": 0.43,
"learning_rate": 2.514759806694041e-05,
"loss": 0.748,
"step": 1260
},
{
"epoch": 0.43,
"learning_rate": 2.5126003441271725e-05,
"loss": 0.7985,
"step": 1261
},
{
"epoch": 0.44,
"learning_rate": 2.510440241754816e-05,
"loss": 0.8077,
"step": 1262
},
{
"epoch": 0.44,
"learning_rate": 2.508279502273117e-05,
"loss": 0.7365,
"step": 1263
},
{
"epoch": 0.44,
"learning_rate": 2.5061181283790177e-05,
"loss": 0.8507,
"step": 1264
},
{
"epoch": 0.44,
"learning_rate": 2.5039561227702507e-05,
"loss": 0.7978,
"step": 1265
},
{
"epoch": 0.44,
"learning_rate": 2.5017934881453377e-05,
"loss": 0.8281,
"step": 1266
},
{
"epoch": 0.44,
"learning_rate": 2.4996302272035844e-05,
"loss": 0.7578,
"step": 1267
},
{
"epoch": 0.44,
"learning_rate": 2.4974663426450798e-05,
"loss": 0.7809,
"step": 1268
},
{
"epoch": 0.44,
"learning_rate": 2.4953018371706913e-05,
"loss": 0.7612,
"step": 1269
},
{
"epoch": 0.44,
"learning_rate": 2.4931367134820597e-05,
"loss": 0.7353,
"step": 1270
},
{
"epoch": 0.44,
"learning_rate": 2.4909709742815986e-05,
"loss": 0.7928,
"step": 1271
},
{
"epoch": 0.44,
"learning_rate": 2.4888046222724893e-05,
"loss": 0.3971,
"step": 1272
},
{
"epoch": 0.44,
"learning_rate": 2.4866376601586798e-05,
"loss": 0.8059,
"step": 1273
},
{
"epoch": 0.44,
"learning_rate": 2.484470090644876e-05,
"loss": 0.7367,
"step": 1274
},
{
"epoch": 0.44,
"learning_rate": 2.4823019164365457e-05,
"loss": 0.7647,
"step": 1275
},
{
"epoch": 0.44,
"learning_rate": 2.4801331402399082e-05,
"loss": 0.7905,
"step": 1276
},
{
"epoch": 0.44,
"learning_rate": 2.477963764761937e-05,
"loss": 0.3578,
"step": 1277
},
{
"epoch": 0.44,
"learning_rate": 2.475793792710352e-05,
"loss": 0.7474,
"step": 1278
},
{
"epoch": 0.44,
"learning_rate": 2.4736232267936182e-05,
"loss": 0.7548,
"step": 1279
},
{
"epoch": 0.44,
"learning_rate": 2.4714520697209417e-05,
"loss": 0.7961,
"step": 1280
},
{
"epoch": 0.44,
"learning_rate": 2.4692803242022666e-05,
"loss": 0.3947,
"step": 1281
},
{
"epoch": 0.44,
"learning_rate": 2.4671079929482705e-05,
"loss": 0.7234,
"step": 1282
},
{
"epoch": 0.44,
"learning_rate": 2.4649350786703637e-05,
"loss": 0.8058,
"step": 1283
},
{
"epoch": 0.44,
"learning_rate": 2.4627615840806837e-05,
"loss": 0.7827,
"step": 1284
},
{
"epoch": 0.44,
"learning_rate": 2.4605875118920904e-05,
"loss": 0.742,
"step": 1285
},
{
"epoch": 0.44,
"learning_rate": 2.4584128648181684e-05,
"loss": 0.8109,
"step": 1286
},
{
"epoch": 0.44,
"learning_rate": 2.456237645573217e-05,
"loss": 0.7993,
"step": 1287
},
{
"epoch": 0.44,
"learning_rate": 2.45406185687225e-05,
"loss": 0.8162,
"step": 1288
},
{
"epoch": 0.44,
"learning_rate": 2.4518855014309927e-05,
"loss": 0.7271,
"step": 1289
},
{
"epoch": 0.44,
"learning_rate": 2.4497085819658776e-05,
"loss": 0.7547,
"step": 1290
},
{
"epoch": 0.45,
"learning_rate": 2.4475311011940406e-05,
"loss": 0.7732,
"step": 1291
},
{
"epoch": 0.45,
"learning_rate": 2.4453530618333185e-05,
"loss": 0.7649,
"step": 1292
},
{
"epoch": 0.45,
"learning_rate": 2.443174466602246e-05,
"loss": 0.774,
"step": 1293
},
{
"epoch": 0.45,
"learning_rate": 2.4409953182200507e-05,
"loss": 0.7693,
"step": 1294
},
{
"epoch": 0.45,
"learning_rate": 2.438815619406651e-05,
"loss": 0.7885,
"step": 1295
},
{
"epoch": 0.45,
"learning_rate": 2.4366353728826524e-05,
"loss": 0.7516,
"step": 1296
},
{
"epoch": 0.45,
"learning_rate": 2.4344545813693446e-05,
"loss": 0.8287,
"step": 1297
},
{
"epoch": 0.45,
"learning_rate": 2.4322732475886953e-05,
"loss": 0.7298,
"step": 1298
},
{
"epoch": 0.45,
"learning_rate": 2.4300913742633516e-05,
"loss": 0.8309,
"step": 1299
},
{
"epoch": 0.45,
"learning_rate": 2.4279089641166332e-05,
"loss": 0.3933,
"step": 1300
},
{
"epoch": 0.45,
"learning_rate": 2.4257260198725293e-05,
"loss": 0.8164,
"step": 1301
},
{
"epoch": 0.45,
"learning_rate": 2.423542544255696e-05,
"loss": 0.8056,
"step": 1302
},
{
"epoch": 0.45,
"learning_rate": 2.4213585399914528e-05,
"loss": 0.7978,
"step": 1303
},
{
"epoch": 0.45,
"learning_rate": 2.4191740098057796e-05,
"loss": 0.8111,
"step": 1304
},
{
"epoch": 0.45,
"learning_rate": 2.416988956425311e-05,
"loss": 0.7986,
"step": 1305
},
{
"epoch": 0.45,
"learning_rate": 2.4148033825773366e-05,
"loss": 0.7078,
"step": 1306
},
{
"epoch": 0.45,
"learning_rate": 2.4126172909897943e-05,
"loss": 0.7759,
"step": 1307
},
{
"epoch": 0.45,
"learning_rate": 2.4104306843912687e-05,
"loss": 0.7996,
"step": 1308
},
{
"epoch": 0.45,
"learning_rate": 2.4082435655109878e-05,
"loss": 0.783,
"step": 1309
},
{
"epoch": 0.45,
"learning_rate": 2.4060559370788177e-05,
"loss": 0.7674,
"step": 1310
},
{
"epoch": 0.45,
"learning_rate": 2.4038678018252615e-05,
"loss": 0.8171,
"step": 1311
},
{
"epoch": 0.45,
"learning_rate": 2.4016791624814544e-05,
"loss": 0.7897,
"step": 1312
},
{
"epoch": 0.45,
"learning_rate": 2.3994900217791615e-05,
"loss": 0.8037,
"step": 1313
},
{
"epoch": 0.45,
"learning_rate": 2.3973003824507726e-05,
"loss": 0.4115,
"step": 1314
},
{
"epoch": 0.45,
"learning_rate": 2.3951102472293002e-05,
"loss": 0.7868,
"step": 1315
},
{
"epoch": 0.45,
"learning_rate": 2.3929196188483767e-05,
"loss": 0.7842,
"step": 1316
},
{
"epoch": 0.45,
"learning_rate": 2.390728500042249e-05,
"loss": 0.7688,
"step": 1317
},
{
"epoch": 0.45,
"learning_rate": 2.3885368935457762e-05,
"loss": 0.7959,
"step": 1318
},
{
"epoch": 0.45,
"learning_rate": 2.386344802094427e-05,
"loss": 0.814,
"step": 1319
},
{
"epoch": 0.46,
"learning_rate": 2.384152228424274e-05,
"loss": 0.7858,
"step": 1320
},
{
"epoch": 0.46,
"learning_rate": 2.381959175271993e-05,
"loss": 0.7634,
"step": 1321
},
{
"epoch": 0.46,
"learning_rate": 2.3797656453748567e-05,
"loss": 0.7699,
"step": 1322
},
{
"epoch": 0.46,
"learning_rate": 2.3775716414707355e-05,
"loss": 0.7847,
"step": 1323
},
{
"epoch": 0.46,
"learning_rate": 2.3753771662980884e-05,
"loss": 0.7583,
"step": 1324
},
{
"epoch": 0.46,
"learning_rate": 2.3731822225959648e-05,
"loss": 0.8187,
"step": 1325
},
{
"epoch": 0.46,
"learning_rate": 2.3709868131039972e-05,
"loss": 0.7863,
"step": 1326
},
{
"epoch": 0.46,
"learning_rate": 2.3687909405624016e-05,
"loss": 0.7082,
"step": 1327
},
{
"epoch": 0.46,
"learning_rate": 2.36659460771197e-05,
"loss": 0.729,
"step": 1328
},
{
"epoch": 0.46,
"learning_rate": 2.3643978172940698e-05,
"loss": 0.7865,
"step": 1329
},
{
"epoch": 0.46,
"learning_rate": 2.362200572050639e-05,
"loss": 0.7691,
"step": 1330
},
{
"epoch": 0.46,
"learning_rate": 2.3600028747241845e-05,
"loss": 0.7898,
"step": 1331
},
{
"epoch": 0.46,
"learning_rate": 2.3578047280577762e-05,
"loss": 0.7563,
"step": 1332
},
{
"epoch": 0.46,
"learning_rate": 2.3556061347950455e-05,
"loss": 0.7741,
"step": 1333
},
{
"epoch": 0.46,
"learning_rate": 2.3534070976801807e-05,
"loss": 0.7984,
"step": 1334
},
{
"epoch": 0.46,
"learning_rate": 2.351207619457925e-05,
"loss": 0.7892,
"step": 1335
},
{
"epoch": 0.46,
"learning_rate": 2.3490077028735706e-05,
"loss": 0.7522,
"step": 1336
},
{
"epoch": 0.46,
"learning_rate": 2.3468073506729586e-05,
"loss": 0.758,
"step": 1337
},
{
"epoch": 0.46,
"learning_rate": 2.3446065656024734e-05,
"loss": 0.8235,
"step": 1338
},
{
"epoch": 0.46,
"learning_rate": 2.3424053504090377e-05,
"loss": 0.7932,
"step": 1339
},
{
"epoch": 0.46,
"learning_rate": 2.340203707840115e-05,
"loss": 0.7575,
"step": 1340
},
{
"epoch": 0.46,
"learning_rate": 2.3380016406436986e-05,
"loss": 0.7343,
"step": 1341
},
{
"epoch": 0.46,
"learning_rate": 2.335799151568313e-05,
"loss": 0.7807,
"step": 1342
},
{
"epoch": 0.46,
"learning_rate": 2.33359624336301e-05,
"loss": 0.8151,
"step": 1343
},
{
"epoch": 0.46,
"learning_rate": 2.3313929187773638e-05,
"loss": 0.7785,
"step": 1344
},
{
"epoch": 0.46,
"learning_rate": 2.329189180561468e-05,
"loss": 0.744,
"step": 1345
},
{
"epoch": 0.46,
"learning_rate": 2.3269850314659335e-05,
"loss": 0.7572,
"step": 1346
},
{
"epoch": 0.46,
"learning_rate": 2.3247804742418838e-05,
"loss": 0.7039,
"step": 1347
},
{
"epoch": 0.46,
"learning_rate": 2.3225755116409497e-05,
"loss": 0.7565,
"step": 1348
},
{
"epoch": 0.47,
"learning_rate": 2.3203701464152722e-05,
"loss": 0.7376,
"step": 1349
},
{
"epoch": 0.47,
"learning_rate": 2.3181643813174905e-05,
"loss": 0.7701,
"step": 1350
},
{
"epoch": 0.47,
"learning_rate": 2.315958219100747e-05,
"loss": 0.7588,
"step": 1351
},
{
"epoch": 0.47,
"learning_rate": 2.313751662518674e-05,
"loss": 0.7813,
"step": 1352
},
{
"epoch": 0.47,
"learning_rate": 2.311544714325403e-05,
"loss": 0.743,
"step": 1353
},
{
"epoch": 0.47,
"learning_rate": 2.309337377275549e-05,
"loss": 0.7896,
"step": 1354
},
{
"epoch": 0.47,
"learning_rate": 2.307129654124215e-05,
"loss": 0.8162,
"step": 1355
},
{
"epoch": 0.47,
"learning_rate": 2.3049215476269856e-05,
"loss": 0.7593,
"step": 1356
},
{
"epoch": 0.47,
"learning_rate": 2.3027130605399215e-05,
"loss": 0.7405,
"step": 1357
},
{
"epoch": 0.47,
"learning_rate": 2.300504195619563e-05,
"loss": 0.388,
"step": 1358
},
{
"epoch": 0.47,
"learning_rate": 2.2982949556229176e-05,
"loss": 0.8009,
"step": 1359
},
{
"epoch": 0.47,
"learning_rate": 2.296085343307463e-05,
"loss": 0.7879,
"step": 1360
},
{
"epoch": 0.47,
"learning_rate": 2.2938753614311417e-05,
"loss": 0.8023,
"step": 1361
},
{
"epoch": 0.47,
"learning_rate": 2.291665012752357e-05,
"loss": 0.4003,
"step": 1362
},
{
"epoch": 0.47,
"learning_rate": 2.2894543000299697e-05,
"loss": 0.3954,
"step": 1363
},
{
"epoch": 0.47,
"learning_rate": 2.287243226023296e-05,
"loss": 0.8161,
"step": 1364
},
{
"epoch": 0.47,
"learning_rate": 2.2850317934921022e-05,
"loss": 0.7214,
"step": 1365
},
{
"epoch": 0.47,
"learning_rate": 2.282820005196602e-05,
"loss": 0.7882,
"step": 1366
},
{
"epoch": 0.47,
"learning_rate": 2.2806078638974545e-05,
"loss": 0.8197,
"step": 1367
},
{
"epoch": 0.47,
"learning_rate": 2.2783953723557572e-05,
"loss": 0.7889,
"step": 1368
},
{
"epoch": 0.47,
"learning_rate": 2.2761825333330468e-05,
"loss": 0.7358,
"step": 1369
},
{
"epoch": 0.47,
"learning_rate": 2.273969349591292e-05,
"loss": 0.7458,
"step": 1370
},
{
"epoch": 0.47,
"learning_rate": 2.2717558238928935e-05,
"loss": 0.7239,
"step": 1371
},
{
"epoch": 0.47,
"learning_rate": 2.269541959000678e-05,
"loss": 0.7211,
"step": 1372
},
{
"epoch": 0.47,
"learning_rate": 2.2673277576778946e-05,
"loss": 0.7825,
"step": 1373
},
{
"epoch": 0.47,
"learning_rate": 2.2651132226882147e-05,
"loss": 0.7886,
"step": 1374
},
{
"epoch": 0.47,
"learning_rate": 2.2628983567957228e-05,
"loss": 0.7401,
"step": 1375
},
{
"epoch": 0.47,
"learning_rate": 2.2606831627649198e-05,
"loss": 0.7353,
"step": 1376
},
{
"epoch": 0.47,
"learning_rate": 2.258467643360714e-05,
"loss": 0.7718,
"step": 1377
},
{
"epoch": 0.48,
"learning_rate": 2.2562518013484208e-05,
"loss": 0.753,
"step": 1378
},
{
"epoch": 0.48,
"learning_rate": 2.2540356394937577e-05,
"loss": 0.7529,
"step": 1379
},
{
"epoch": 0.48,
"learning_rate": 2.2518191605628418e-05,
"loss": 0.7818,
"step": 1380
},
{
"epoch": 0.48,
"learning_rate": 2.2496023673221863e-05,
"loss": 0.7747,
"step": 1381
},
{
"epoch": 0.48,
"learning_rate": 2.247385262538696e-05,
"loss": 0.785,
"step": 1382
},
{
"epoch": 0.48,
"learning_rate": 2.245167848979664e-05,
"loss": 0.7515,
"step": 1383
},
{
"epoch": 0.48,
"learning_rate": 2.24295012941277e-05,
"loss": 0.7977,
"step": 1384
},
{
"epoch": 0.48,
"learning_rate": 2.2407321066060762e-05,
"loss": 0.8009,
"step": 1385
},
{
"epoch": 0.48,
"learning_rate": 2.2385137833280213e-05,
"loss": 0.7594,
"step": 1386
},
{
"epoch": 0.48,
"learning_rate": 2.23629516234742e-05,
"loss": 0.7678,
"step": 1387
},
{
"epoch": 0.48,
"learning_rate": 2.23407624643346e-05,
"loss": 0.7974,
"step": 1388
},
{
"epoch": 0.48,
"learning_rate": 2.2318570383556947e-05,
"loss": 0.7654,
"step": 1389
},
{
"epoch": 0.48,
"learning_rate": 2.229637540884043e-05,
"loss": 0.7846,
"step": 1390
},
{
"epoch": 0.48,
"learning_rate": 2.2274177567887857e-05,
"loss": 0.8042,
"step": 1391
},
{
"epoch": 0.48,
"learning_rate": 2.2251976888405608e-05,
"loss": 0.7985,
"step": 1392
},
{
"epoch": 0.48,
"learning_rate": 2.2229773398103606e-05,
"loss": 0.7756,
"step": 1393
},
{
"epoch": 0.48,
"learning_rate": 2.2207567124695285e-05,
"loss": 0.4231,
"step": 1394
},
{
"epoch": 0.48,
"learning_rate": 2.2185358095897555e-05,
"loss": 0.4037,
"step": 1395
},
{
"epoch": 0.48,
"learning_rate": 2.2163146339430758e-05,
"loss": 0.8145,
"step": 1396
},
{
"epoch": 0.48,
"learning_rate": 2.2140931883018642e-05,
"loss": 0.7397,
"step": 1397
},
{
"epoch": 0.48,
"learning_rate": 2.2118714754388323e-05,
"loss": 0.7602,
"step": 1398
},
{
"epoch": 0.48,
"learning_rate": 2.2096494981270266e-05,
"loss": 0.7938,
"step": 1399
},
{
"epoch": 0.48,
"learning_rate": 2.2074272591398217e-05,
"loss": 0.767,
"step": 1400
},
{
"epoch": 0.48,
"learning_rate": 2.2052047612509203e-05,
"loss": 0.8203,
"step": 1401
},
{
"epoch": 0.48,
"learning_rate": 2.202982007234348e-05,
"loss": 0.7644,
"step": 1402
},
{
"epoch": 0.48,
"learning_rate": 2.200758999864449e-05,
"loss": 0.4121,
"step": 1403
},
{
"epoch": 0.48,
"learning_rate": 2.198535741915886e-05,
"loss": 0.7698,
"step": 1404
},
{
"epoch": 0.48,
"learning_rate": 2.196312236163632e-05,
"loss": 0.7809,
"step": 1405
},
{
"epoch": 0.48,
"learning_rate": 2.1940884853829694e-05,
"loss": 0.8099,
"step": 1406
},
{
"epoch": 0.49,
"learning_rate": 2.191864492349489e-05,
"loss": 0.7998,
"step": 1407
},
{
"epoch": 0.49,
"learning_rate": 2.1896402598390818e-05,
"loss": 0.7288,
"step": 1408
},
{
"epoch": 0.49,
"learning_rate": 2.1874157906279382e-05,
"loss": 0.8064,
"step": 1409
},
{
"epoch": 0.49,
"learning_rate": 2.1851910874925438e-05,
"loss": 0.7122,
"step": 1410
},
{
"epoch": 0.49,
"learning_rate": 2.1829661532096762e-05,
"loss": 0.7234,
"step": 1411
},
{
"epoch": 0.49,
"learning_rate": 2.180740990556403e-05,
"loss": 0.7603,
"step": 1412
},
{
"epoch": 0.49,
"learning_rate": 2.178515602310074e-05,
"loss": 0.7332,
"step": 1413
},
{
"epoch": 0.49,
"learning_rate": 2.1762899912483232e-05,
"loss": 0.7858,
"step": 1414
},
{
"epoch": 0.49,
"learning_rate": 2.1740641601490614e-05,
"loss": 0.8044,
"step": 1415
},
{
"epoch": 0.49,
"learning_rate": 2.171838111790474e-05,
"loss": 0.7842,
"step": 1416
},
{
"epoch": 0.49,
"learning_rate": 2.1696118489510186e-05,
"loss": 0.7744,
"step": 1417
},
{
"epoch": 0.49,
"learning_rate": 2.1673853744094193e-05,
"loss": 0.7618,
"step": 1418
},
{
"epoch": 0.49,
"learning_rate": 2.165158690944665e-05,
"loss": 0.7322,
"step": 1419
},
{
"epoch": 0.49,
"learning_rate": 2.1629318013360053e-05,
"loss": 0.7711,
"step": 1420
},
{
"epoch": 0.49,
"learning_rate": 2.160704708362947e-05,
"loss": 0.7869,
"step": 1421
},
{
"epoch": 0.49,
"learning_rate": 2.1584774148052512e-05,
"loss": 0.7347,
"step": 1422
},
{
"epoch": 0.49,
"learning_rate": 2.1562499234429283e-05,
"loss": 0.7809,
"step": 1423
},
{
"epoch": 0.49,
"learning_rate": 2.1540222370562363e-05,
"loss": 0.8056,
"step": 1424
},
{
"epoch": 0.49,
"learning_rate": 2.1517943584256778e-05,
"loss": 0.7431,
"step": 1425
},
{
"epoch": 0.49,
"learning_rate": 2.1495662903319934e-05,
"loss": 0.7642,
"step": 1426
},
{
"epoch": 0.49,
"learning_rate": 2.1473380355561604e-05,
"loss": 0.7881,
"step": 1427
},
{
"epoch": 0.49,
"learning_rate": 2.1451095968793908e-05,
"loss": 0.7737,
"step": 1428
},
{
"epoch": 0.49,
"learning_rate": 2.142880977083124e-05,
"loss": 0.8009,
"step": 1429
},
{
"epoch": 0.49,
"learning_rate": 2.1406521789490262e-05,
"loss": 0.7424,
"step": 1430
},
{
"epoch": 0.49,
"learning_rate": 2.138423205258988e-05,
"loss": 0.8139,
"step": 1431
},
{
"epoch": 0.49,
"learning_rate": 2.1361940587951158e-05,
"loss": 0.7587,
"step": 1432
},
{
"epoch": 0.49,
"learning_rate": 2.1339647423397337e-05,
"loss": 0.7714,
"step": 1433
},
{
"epoch": 0.49,
"learning_rate": 2.131735258675379e-05,
"loss": 0.7838,
"step": 1434
},
{
"epoch": 0.49,
"learning_rate": 2.1295056105847953e-05,
"loss": 0.3843,
"step": 1435
},
{
"epoch": 0.5,
"learning_rate": 2.127275800850933e-05,
"loss": 0.7499,
"step": 1436
},
{
"epoch": 0.5,
"learning_rate": 2.1250458322569433e-05,
"loss": 0.7127,
"step": 1437
},
{
"epoch": 0.5,
"learning_rate": 2.122815707586176e-05,
"loss": 0.8086,
"step": 1438
},
{
"epoch": 0.5,
"learning_rate": 2.1205854296221764e-05,
"loss": 0.7317,
"step": 1439
},
{
"epoch": 0.5,
"learning_rate": 2.1183550011486805e-05,
"loss": 0.7534,
"step": 1440
},
{
"epoch": 0.5,
"learning_rate": 2.1161244249496123e-05,
"loss": 0.7704,
"step": 1441
},
{
"epoch": 0.5,
"learning_rate": 2.1138937038090797e-05,
"loss": 0.7669,
"step": 1442
},
{
"epoch": 0.5,
"learning_rate": 2.111662840511373e-05,
"loss": 0.7093,
"step": 1443
},
{
"epoch": 0.5,
"learning_rate": 2.1094318378409575e-05,
"loss": 0.8038,
"step": 1444
},
{
"epoch": 0.5,
"learning_rate": 2.1072006985824748e-05,
"loss": 0.8182,
"step": 1445
},
{
"epoch": 0.5,
"learning_rate": 2.1049694255207354e-05,
"loss": 0.815,
"step": 1446
},
{
"epoch": 0.5,
"learning_rate": 2.102738021440718e-05,
"loss": 0.7968,
"step": 1447
},
{
"epoch": 0.5,
"learning_rate": 2.1005064891275638e-05,
"loss": 0.7626,
"step": 1448
},
{
"epoch": 0.5,
"learning_rate": 2.098274831366575e-05,
"loss": 0.7522,
"step": 1449
},
{
"epoch": 0.5,
"learning_rate": 2.09604305094321e-05,
"loss": 0.7677,
"step": 1450
},
{
"epoch": 0.5,
"learning_rate": 2.0938111506430793e-05,
"loss": 0.8023,
"step": 1451
},
{
"epoch": 0.5,
"learning_rate": 2.0915791332519442e-05,
"loss": 0.804,
"step": 1452
},
{
"epoch": 0.5,
"learning_rate": 2.0893470015557126e-05,
"loss": 0.7459,
"step": 1453
},
{
"epoch": 0.5,
"learning_rate": 2.087114758340434e-05,
"loss": 0.7244,
"step": 1454
},
{
"epoch": 0.5,
"learning_rate": 2.084882406392297e-05,
"loss": 0.6915,
"step": 1455
},
{
"epoch": 0.5,
"learning_rate": 2.0826499484976265e-05,
"loss": 0.761,
"step": 1456
},
{
"epoch": 0.5,
"learning_rate": 2.0804173874428797e-05,
"loss": 0.4066,
"step": 1457
},
{
"epoch": 0.5,
"learning_rate": 2.078184726014643e-05,
"loss": 0.8044,
"step": 1458
},
{
"epoch": 0.5,
"learning_rate": 2.0759519669996267e-05,
"loss": 0.7745,
"step": 1459
},
{
"epoch": 0.5,
"learning_rate": 2.0737191131846632e-05,
"loss": 0.8149,
"step": 1460
},
{
"epoch": 0.5,
"learning_rate": 2.0714861673567044e-05,
"loss": 0.7627,
"step": 1461
},
{
"epoch": 0.5,
"learning_rate": 2.0692531323028158e-05,
"loss": 0.817,
"step": 1462
},
{
"epoch": 0.5,
"learning_rate": 2.0670200108101754e-05,
"loss": 0.7533,
"step": 1463
},
{
"epoch": 0.51,
"learning_rate": 2.0647868056660675e-05,
"loss": 0.7883,
"step": 1464
},
{
"epoch": 0.51,
"learning_rate": 2.0625535196578824e-05,
"loss": 0.7576,
"step": 1465
},
{
"epoch": 0.51,
"learning_rate": 2.060320155573112e-05,
"loss": 0.7524,
"step": 1466
},
{
"epoch": 0.51,
"learning_rate": 2.058086716199342e-05,
"loss": 0.8252,
"step": 1467
},
{
"epoch": 0.51,
"learning_rate": 2.0558532043242557e-05,
"loss": 0.7867,
"step": 1468
},
{
"epoch": 0.51,
"learning_rate": 2.0536196227356248e-05,
"loss": 0.7351,
"step": 1469
},
{
"epoch": 0.51,
"learning_rate": 2.0513859742213103e-05,
"loss": 0.7765,
"step": 1470
},
{
"epoch": 0.51,
"learning_rate": 2.0491522615692537e-05,
"loss": 0.7933,
"step": 1471
},
{
"epoch": 0.51,
"learning_rate": 2.0469184875674794e-05,
"loss": 0.7822,
"step": 1472
},
{
"epoch": 0.51,
"learning_rate": 2.0446846550040863e-05,
"loss": 0.8229,
"step": 1473
},
{
"epoch": 0.51,
"learning_rate": 2.0424507666672473e-05,
"loss": 0.7835,
"step": 1474
},
{
"epoch": 0.51,
"learning_rate": 2.0402168253452053e-05,
"loss": 0.7334,
"step": 1475
},
{
"epoch": 0.51,
"learning_rate": 2.0379828338262683e-05,
"loss": 0.7586,
"step": 1476
},
{
"epoch": 0.51,
"learning_rate": 2.0357487948988078e-05,
"loss": 0.7696,
"step": 1477
},
{
"epoch": 0.51,
"learning_rate": 2.033514711351253e-05,
"loss": 0.7079,
"step": 1478
},
{
"epoch": 0.51,
"learning_rate": 2.031280585972092e-05,
"loss": 0.8129,
"step": 1479
},
{
"epoch": 0.51,
"learning_rate": 2.029046421549862e-05,
"loss": 0.7249,
"step": 1480
},
{
"epoch": 0.51,
"learning_rate": 2.0268122208731497e-05,
"loss": 0.7333,
"step": 1481
},
{
"epoch": 0.51,
"learning_rate": 2.0245779867305882e-05,
"loss": 0.3766,
"step": 1482
},
{
"epoch": 0.51,
"learning_rate": 2.022343721910851e-05,
"loss": 0.3816,
"step": 1483
},
{
"epoch": 0.51,
"learning_rate": 2.0201094292026503e-05,
"loss": 0.7694,
"step": 1484
},
{
"epoch": 0.51,
"learning_rate": 2.0178751113947338e-05,
"loss": 0.7362,
"step": 1485
},
{
"epoch": 0.51,
"learning_rate": 2.015640771275879e-05,
"loss": 0.7936,
"step": 1486
},
{
"epoch": 0.51,
"learning_rate": 2.0134064116348922e-05,
"loss": 0.7877,
"step": 1487
},
{
"epoch": 0.51,
"learning_rate": 2.0111720352606054e-05,
"loss": 0.7742,
"step": 1488
},
{
"epoch": 0.51,
"learning_rate": 2.0089376449418693e-05,
"loss": 0.7957,
"step": 1489
},
{
"epoch": 0.51,
"learning_rate": 2.0067032434675537e-05,
"loss": 0.7248,
"step": 1490
},
{
"epoch": 0.51,
"learning_rate": 2.0044688336265397e-05,
"loss": 0.843,
"step": 1491
},
{
"epoch": 0.51,
"learning_rate": 2.002234418207722e-05,
"loss": 0.7667,
"step": 1492
},
{
"epoch": 0.52,
"learning_rate": 2e-05,
"loss": 0.6976,
"step": 1493
},
{
"epoch": 0.52,
"learning_rate": 1.9977655817922783e-05,
"loss": 0.7375,
"step": 1494
},
{
"epoch": 0.52,
"learning_rate": 1.995531166373461e-05,
"loss": 0.7993,
"step": 1495
},
{
"epoch": 0.52,
"learning_rate": 1.9932967565324467e-05,
"loss": 0.7501,
"step": 1496
},
{
"epoch": 0.52,
"learning_rate": 1.991062355058131e-05,
"loss": 0.7565,
"step": 1497
},
{
"epoch": 0.52,
"learning_rate": 1.988827964739395e-05,
"loss": 0.7354,
"step": 1498
},
{
"epoch": 0.52,
"learning_rate": 1.9865935883651077e-05,
"loss": 0.7697,
"step": 1499
},
{
"epoch": 0.52,
"learning_rate": 1.984359228724122e-05,
"loss": 0.7789,
"step": 1500
},
{
"epoch": 0.52,
"learning_rate": 1.9821248886052672e-05,
"loss": 0.7608,
"step": 1501
},
{
"epoch": 0.52,
"learning_rate": 1.9798905707973497e-05,
"loss": 0.7922,
"step": 1502
},
{
"epoch": 0.52,
"learning_rate": 1.9776562780891494e-05,
"loss": 0.3972,
"step": 1503
},
{
"epoch": 0.52,
"learning_rate": 1.975422013269412e-05,
"loss": 0.7399,
"step": 1504
},
{
"epoch": 0.52,
"learning_rate": 1.9731877791268506e-05,
"loss": 0.8207,
"step": 1505
},
{
"epoch": 0.52,
"learning_rate": 1.9709535784501384e-05,
"loss": 0.7526,
"step": 1506
},
{
"epoch": 0.52,
"learning_rate": 1.968719414027908e-05,
"loss": 0.7684,
"step": 1507
},
{
"epoch": 0.52,
"learning_rate": 1.966485288648747e-05,
"loss": 0.8367,
"step": 1508
},
{
"epoch": 0.52,
"learning_rate": 1.964251205101193e-05,
"loss": 0.7195,
"step": 1509
},
{
"epoch": 0.52,
"learning_rate": 1.9620171661737327e-05,
"loss": 0.7743,
"step": 1510
},
{
"epoch": 0.52,
"learning_rate": 1.9597831746547954e-05,
"loss": 0.4005,
"step": 1511
},
{
"epoch": 0.52,
"learning_rate": 1.957549233332753e-05,
"loss": 0.8011,
"step": 1512
},
{
"epoch": 0.52,
"learning_rate": 1.9553153449959144e-05,
"loss": 0.7422,
"step": 1513
},
{
"epoch": 0.52,
"learning_rate": 1.9530815124325213e-05,
"loss": 0.7702,
"step": 1514
},
{
"epoch": 0.52,
"learning_rate": 1.9508477384307473e-05,
"loss": 0.7496,
"step": 1515
},
{
"epoch": 0.52,
"learning_rate": 1.9486140257786904e-05,
"loss": 0.7713,
"step": 1516
},
{
"epoch": 0.52,
"learning_rate": 1.9463803772643752e-05,
"loss": 0.7893,
"step": 1517
},
{
"epoch": 0.52,
"learning_rate": 1.9441467956757453e-05,
"loss": 0.7647,
"step": 1518
},
{
"epoch": 0.52,
"learning_rate": 1.9419132838006584e-05,
"loss": 0.7791,
"step": 1519
},
{
"epoch": 0.52,
"learning_rate": 1.9396798444268887e-05,
"loss": 0.7661,
"step": 1520
},
{
"epoch": 0.52,
"learning_rate": 1.937446480342118e-05,
"loss": 0.7593,
"step": 1521
},
{
"epoch": 0.53,
"learning_rate": 1.9352131943339328e-05,
"loss": 0.7627,
"step": 1522
},
{
"epoch": 0.53,
"learning_rate": 1.9329799891898256e-05,
"loss": 0.7983,
"step": 1523
},
{
"epoch": 0.53,
"learning_rate": 1.930746867697185e-05,
"loss": 0.7778,
"step": 1524
},
{
"epoch": 0.53,
"learning_rate": 1.928513832643296e-05,
"loss": 0.7495,
"step": 1525
},
{
"epoch": 0.53,
"learning_rate": 1.9262808868153375e-05,
"loss": 0.7368,
"step": 1526
},
{
"epoch": 0.53,
"learning_rate": 1.9240480330003737e-05,
"loss": 0.7604,
"step": 1527
},
{
"epoch": 0.53,
"learning_rate": 1.9218152739853576e-05,
"loss": 0.7686,
"step": 1528
},
{
"epoch": 0.53,
"learning_rate": 1.9195826125571206e-05,
"loss": 0.7977,
"step": 1529
},
{
"epoch": 0.53,
"learning_rate": 1.9173500515023735e-05,
"loss": 0.7743,
"step": 1530
},
{
"epoch": 0.53,
"learning_rate": 1.915117593607704e-05,
"loss": 0.7557,
"step": 1531
},
{
"epoch": 0.53,
"learning_rate": 1.9128852416595667e-05,
"loss": 0.7507,
"step": 1532
},
{
"epoch": 0.53,
"learning_rate": 1.9106529984442884e-05,
"loss": 0.7173,
"step": 1533
},
{
"epoch": 0.53,
"learning_rate": 1.908420866748056e-05,
"loss": 0.7839,
"step": 1534
},
{
"epoch": 0.53,
"learning_rate": 1.9061888493569217e-05,
"loss": 0.7666,
"step": 1535
},
{
"epoch": 0.53,
"learning_rate": 1.9039569490567912e-05,
"loss": 0.7906,
"step": 1536
},
{
"epoch": 0.53,
"learning_rate": 1.9017251686334257e-05,
"loss": 0.742,
"step": 1537
},
{
"epoch": 0.53,
"learning_rate": 1.8994935108724366e-05,
"loss": 0.4049,
"step": 1538
},
{
"epoch": 0.53,
"learning_rate": 1.8972619785592827e-05,
"loss": 0.7519,
"step": 1539
},
{
"epoch": 0.53,
"learning_rate": 1.895030574479265e-05,
"loss": 0.7801,
"step": 1540
},
{
"epoch": 0.53,
"learning_rate": 1.8927993014175262e-05,
"loss": 0.8017,
"step": 1541
},
{
"epoch": 0.53,
"learning_rate": 1.8905681621590428e-05,
"loss": 0.7523,
"step": 1542
},
{
"epoch": 0.53,
"learning_rate": 1.8883371594886276e-05,
"loss": 0.775,
"step": 1543
},
{
"epoch": 0.53,
"learning_rate": 1.886106296190921e-05,
"loss": 0.7369,
"step": 1544
},
{
"epoch": 0.53,
"learning_rate": 1.883875575050388e-05,
"loss": 0.7336,
"step": 1545
},
{
"epoch": 0.53,
"learning_rate": 1.8816449988513205e-05,
"loss": 0.7653,
"step": 1546
},
{
"epoch": 0.53,
"learning_rate": 1.8794145703778243e-05,
"loss": 0.7772,
"step": 1547
},
{
"epoch": 0.53,
"learning_rate": 1.877184292413824e-05,
"loss": 0.7616,
"step": 1548
},
{
"epoch": 0.53,
"learning_rate": 1.8749541677430577e-05,
"loss": 0.7488,
"step": 1549
},
{
"epoch": 0.53,
"learning_rate": 1.8727241991490674e-05,
"loss": 0.7605,
"step": 1550
},
{
"epoch": 0.54,
"learning_rate": 1.8704943894152054e-05,
"loss": 0.7359,
"step": 1551
},
{
"epoch": 0.54,
"learning_rate": 1.8682647413246218e-05,
"loss": 0.7986,
"step": 1552
},
{
"epoch": 0.54,
"learning_rate": 1.8660352576602663e-05,
"loss": 0.7802,
"step": 1553
},
{
"epoch": 0.54,
"learning_rate": 1.8638059412048855e-05,
"loss": 0.7354,
"step": 1554
},
{
"epoch": 0.54,
"learning_rate": 1.861576794741013e-05,
"loss": 0.3821,
"step": 1555
},
{
"epoch": 0.54,
"learning_rate": 1.8593478210509738e-05,
"loss": 0.7823,
"step": 1556
},
{
"epoch": 0.54,
"learning_rate": 1.857119022916877e-05,
"loss": 0.7861,
"step": 1557
},
{
"epoch": 0.54,
"learning_rate": 1.8548904031206102e-05,
"loss": 0.7419,
"step": 1558
},
{
"epoch": 0.54,
"learning_rate": 1.85266196444384e-05,
"loss": 0.8139,
"step": 1559
},
{
"epoch": 0.54,
"learning_rate": 1.8504337096680072e-05,
"loss": 0.8033,
"step": 1560
},
{
"epoch": 0.54,
"learning_rate": 1.8482056415743222e-05,
"loss": 0.8068,
"step": 1561
},
{
"epoch": 0.54,
"learning_rate": 1.845977762943764e-05,
"loss": 0.7732,
"step": 1562
},
{
"epoch": 0.54,
"learning_rate": 1.843750076557072e-05,
"loss": 0.7895,
"step": 1563
},
{
"epoch": 0.54,
"learning_rate": 1.84152258519475e-05,
"loss": 0.7827,
"step": 1564
},
{
"epoch": 0.54,
"learning_rate": 1.8392952916370536e-05,
"loss": 0.7596,
"step": 1565
},
{
"epoch": 0.54,
"learning_rate": 1.8370681986639954e-05,
"loss": 0.7101,
"step": 1566
},
{
"epoch": 0.54,
"learning_rate": 1.8348413090553356e-05,
"loss": 0.7691,
"step": 1567
},
{
"epoch": 0.54,
"learning_rate": 1.832614625590581e-05,
"loss": 0.7977,
"step": 1568
},
{
"epoch": 0.54,
"learning_rate": 1.8303881510489824e-05,
"loss": 0.404,
"step": 1569
},
{
"epoch": 0.54,
"learning_rate": 1.8281618882095263e-05,
"loss": 0.7951,
"step": 1570
},
{
"epoch": 0.54,
"learning_rate": 1.825935839850939e-05,
"loss": 0.79,
"step": 1571
},
{
"epoch": 0.54,
"learning_rate": 1.8237100087516774e-05,
"loss": 0.3754,
"step": 1572
},
{
"epoch": 0.54,
"learning_rate": 1.8214843976899264e-05,
"loss": 0.7716,
"step": 1573
},
{
"epoch": 0.54,
"learning_rate": 1.8192590094435976e-05,
"loss": 0.7749,
"step": 1574
},
{
"epoch": 0.54,
"learning_rate": 1.8170338467903245e-05,
"loss": 0.7546,
"step": 1575
},
{
"epoch": 0.54,
"learning_rate": 1.814808912507457e-05,
"loss": 0.7815,
"step": 1576
},
{
"epoch": 0.54,
"learning_rate": 1.8125842093720628e-05,
"loss": 0.819,
"step": 1577
},
{
"epoch": 0.54,
"learning_rate": 1.810359740160919e-05,
"loss": 0.7224,
"step": 1578
},
{
"epoch": 0.54,
"learning_rate": 1.808135507650511e-05,
"loss": 0.7294,
"step": 1579
},
{
"epoch": 0.55,
"learning_rate": 1.8059115146170313e-05,
"loss": 0.7542,
"step": 1580
},
{
"epoch": 0.55,
"learning_rate": 1.8036877638363688e-05,
"loss": 0.7648,
"step": 1581
},
{
"epoch": 0.55,
"learning_rate": 1.8014642580841148e-05,
"loss": 0.7641,
"step": 1582
},
{
"epoch": 0.55,
"learning_rate": 1.7992410001355515e-05,
"loss": 0.7641,
"step": 1583
},
{
"epoch": 0.55,
"learning_rate": 1.7970179927656523e-05,
"loss": 0.7619,
"step": 1584
},
{
"epoch": 0.55,
"learning_rate": 1.7947952387490804e-05,
"loss": 0.7915,
"step": 1585
},
{
"epoch": 0.55,
"learning_rate": 1.7925727408601786e-05,
"loss": 0.7604,
"step": 1586
},
{
"epoch": 0.55,
"learning_rate": 1.7903505018729744e-05,
"loss": 0.385,
"step": 1587
},
{
"epoch": 0.55,
"learning_rate": 1.788128524561168e-05,
"loss": 0.7977,
"step": 1588
},
{
"epoch": 0.55,
"learning_rate": 1.7859068116981365e-05,
"loss": 0.8064,
"step": 1589
},
{
"epoch": 0.55,
"learning_rate": 1.783685366056925e-05,
"loss": 0.8158,
"step": 1590
},
{
"epoch": 0.55,
"learning_rate": 1.781464190410245e-05,
"loss": 0.7507,
"step": 1591
},
{
"epoch": 0.55,
"learning_rate": 1.779243287530471e-05,
"loss": 0.7026,
"step": 1592
},
{
"epoch": 0.55,
"learning_rate": 1.7770226601896397e-05,
"loss": 0.7784,
"step": 1593
},
{
"epoch": 0.55,
"learning_rate": 1.77480231115944e-05,
"loss": 0.7513,
"step": 1594
},
{
"epoch": 0.55,
"learning_rate": 1.7725822432112153e-05,
"loss": 0.7479,
"step": 1595
},
{
"epoch": 0.55,
"learning_rate": 1.7703624591159578e-05,
"loss": 0.7961,
"step": 1596
},
{
"epoch": 0.55,
"learning_rate": 1.768142961644306e-05,
"loss": 0.7654,
"step": 1597
},
{
"epoch": 0.55,
"learning_rate": 1.7659237535665404e-05,
"loss": 0.7721,
"step": 1598
},
{
"epoch": 0.55,
"learning_rate": 1.76370483765258e-05,
"loss": 0.3842,
"step": 1599
},
{
"epoch": 0.55,
"learning_rate": 1.7614862166719797e-05,
"loss": 0.7567,
"step": 1600
},
{
"epoch": 0.55,
"learning_rate": 1.7592678933939244e-05,
"loss": 0.3581,
"step": 1601
},
{
"epoch": 0.55,
"learning_rate": 1.75704987058723e-05,
"loss": 0.7777,
"step": 1602
},
{
"epoch": 0.55,
"learning_rate": 1.754832151020337e-05,
"loss": 0.7539,
"step": 1603
},
{
"epoch": 0.55,
"learning_rate": 1.7526147374613047e-05,
"loss": 0.755,
"step": 1604
},
{
"epoch": 0.55,
"learning_rate": 1.750397632677814e-05,
"loss": 0.8078,
"step": 1605
},
{
"epoch": 0.55,
"learning_rate": 1.748180839437159e-05,
"loss": 0.805,
"step": 1606
},
{
"epoch": 0.55,
"learning_rate": 1.7459643605062427e-05,
"loss": 0.7205,
"step": 1607
},
{
"epoch": 0.55,
"learning_rate": 1.74374819865158e-05,
"loss": 0.7746,
"step": 1608
},
{
"epoch": 0.56,
"learning_rate": 1.7415323566392865e-05,
"loss": 0.7714,
"step": 1609
},
{
"epoch": 0.56,
"learning_rate": 1.7393168372350805e-05,
"loss": 0.7159,
"step": 1610
},
{
"epoch": 0.56,
"learning_rate": 1.737101643204278e-05,
"loss": 0.7475,
"step": 1611
},
{
"epoch": 0.56,
"learning_rate": 1.7348867773117856e-05,
"loss": 0.7554,
"step": 1612
},
{
"epoch": 0.56,
"learning_rate": 1.7326722423221057e-05,
"loss": 0.7708,
"step": 1613
},
{
"epoch": 0.56,
"learning_rate": 1.7304580409993226e-05,
"loss": 0.8044,
"step": 1614
},
{
"epoch": 0.56,
"learning_rate": 1.7282441761071064e-05,
"loss": 0.7853,
"step": 1615
},
{
"epoch": 0.56,
"learning_rate": 1.7260306504087086e-05,
"loss": 0.7827,
"step": 1616
},
{
"epoch": 0.56,
"learning_rate": 1.723817466666954e-05,
"loss": 0.7604,
"step": 1617
},
{
"epoch": 0.56,
"learning_rate": 1.7216046276442438e-05,
"loss": 0.7796,
"step": 1618
},
{
"epoch": 0.56,
"learning_rate": 1.719392136102546e-05,
"loss": 0.7552,
"step": 1619
},
{
"epoch": 0.56,
"learning_rate": 1.7171799948033984e-05,
"loss": 0.4173,
"step": 1620
},
{
"epoch": 0.56,
"learning_rate": 1.714968206507898e-05,
"loss": 0.754,
"step": 1621
},
{
"epoch": 0.56,
"learning_rate": 1.7127567739767044e-05,
"loss": 0.7794,
"step": 1622
},
{
"epoch": 0.56,
"learning_rate": 1.7105456999700306e-05,
"loss": 0.7759,
"step": 1623
},
{
"epoch": 0.56,
"learning_rate": 1.7083349872476438e-05,
"loss": 0.7814,
"step": 1624
},
{
"epoch": 0.56,
"learning_rate": 1.7061246385688586e-05,
"loss": 0.7586,
"step": 1625
},
{
"epoch": 0.56,
"learning_rate": 1.7039146566925376e-05,
"loss": 0.7794,
"step": 1626
},
{
"epoch": 0.56,
"learning_rate": 1.7017050443770827e-05,
"loss": 0.7295,
"step": 1627
},
{
"epoch": 0.56,
"learning_rate": 1.6994958043804374e-05,
"loss": 0.7539,
"step": 1628
},
{
"epoch": 0.56,
"learning_rate": 1.6972869394600788e-05,
"loss": 0.7623,
"step": 1629
},
{
"epoch": 0.56,
"learning_rate": 1.695078452373015e-05,
"loss": 0.7769,
"step": 1630
},
{
"epoch": 0.56,
"learning_rate": 1.6928703458757856e-05,
"loss": 0.776,
"step": 1631
},
{
"epoch": 0.56,
"learning_rate": 1.6906626227244513e-05,
"loss": 0.7398,
"step": 1632
},
{
"epoch": 0.56,
"learning_rate": 1.6884552856745972e-05,
"loss": 0.7916,
"step": 1633
},
{
"epoch": 0.56,
"learning_rate": 1.6862483374813262e-05,
"loss": 0.7742,
"step": 1634
},
{
"epoch": 0.56,
"learning_rate": 1.684041780899254e-05,
"loss": 0.7542,
"step": 1635
},
{
"epoch": 0.56,
"learning_rate": 1.6818356186825098e-05,
"loss": 0.7633,
"step": 1636
},
{
"epoch": 0.56,
"learning_rate": 1.6796298535847288e-05,
"loss": 0.8286,
"step": 1637
},
{
"epoch": 0.57,
"learning_rate": 1.6774244883590503e-05,
"loss": 0.7659,
"step": 1638
},
{
"epoch": 0.57,
"learning_rate": 1.6752195257581173e-05,
"loss": 0.7676,
"step": 1639
},
{
"epoch": 0.57,
"learning_rate": 1.6730149685340668e-05,
"loss": 0.7482,
"step": 1640
},
{
"epoch": 0.57,
"learning_rate": 1.670810819438532e-05,
"loss": 0.7739,
"step": 1641
},
{
"epoch": 0.57,
"learning_rate": 1.668607081222637e-05,
"loss": 0.7666,
"step": 1642
},
{
"epoch": 0.57,
"learning_rate": 1.6664037566369905e-05,
"loss": 0.7412,
"step": 1643
},
{
"epoch": 0.57,
"learning_rate": 1.6642008484316878e-05,
"loss": 0.7721,
"step": 1644
},
{
"epoch": 0.57,
"learning_rate": 1.6619983593563024e-05,
"loss": 0.8289,
"step": 1645
},
{
"epoch": 0.57,
"learning_rate": 1.6597962921598852e-05,
"loss": 0.7698,
"step": 1646
},
{
"epoch": 0.57,
"learning_rate": 1.6575946495909626e-05,
"loss": 0.7649,
"step": 1647
},
{
"epoch": 0.57,
"learning_rate": 1.6553934343975273e-05,
"loss": 0.3907,
"step": 1648
},
{
"epoch": 0.57,
"learning_rate": 1.6531926493270424e-05,
"loss": 0.753,
"step": 1649
},
{
"epoch": 0.57,
"learning_rate": 1.65099229712643e-05,
"loss": 0.7658,
"step": 1650
},
{
"epoch": 0.57,
"learning_rate": 1.648792380542076e-05,
"loss": 0.3832,
"step": 1651
},
{
"epoch": 0.57,
"learning_rate": 1.64659290231982e-05,
"loss": 0.7505,
"step": 1652
},
{
"epoch": 0.57,
"learning_rate": 1.644393865204955e-05,
"loss": 0.7319,
"step": 1653
},
{
"epoch": 0.57,
"learning_rate": 1.6421952719422248e-05,
"loss": 0.3867,
"step": 1654
},
{
"epoch": 0.57,
"learning_rate": 1.639997125275816e-05,
"loss": 0.7725,
"step": 1655
},
{
"epoch": 0.57,
"learning_rate": 1.6377994279493613e-05,
"loss": 0.7757,
"step": 1656
},
{
"epoch": 0.57,
"learning_rate": 1.6356021827059312e-05,
"loss": 0.772,
"step": 1657
},
{
"epoch": 0.57,
"learning_rate": 1.6334053922880304e-05,
"loss": 0.7589,
"step": 1658
},
{
"epoch": 0.57,
"learning_rate": 1.6312090594375987e-05,
"loss": 0.8055,
"step": 1659
},
{
"epoch": 0.57,
"learning_rate": 1.6290131868960035e-05,
"loss": 0.7842,
"step": 1660
},
{
"epoch": 0.57,
"learning_rate": 1.626817777404036e-05,
"loss": 0.7412,
"step": 1661
},
{
"epoch": 0.57,
"learning_rate": 1.6246228337019126e-05,
"loss": 0.7641,
"step": 1662
},
{
"epoch": 0.57,
"learning_rate": 1.622428358529265e-05,
"loss": 0.7936,
"step": 1663
},
{
"epoch": 0.57,
"learning_rate": 1.6202343546251432e-05,
"loss": 0.7483,
"step": 1664
},
{
"epoch": 0.57,
"learning_rate": 1.6180408247280078e-05,
"loss": 0.7905,
"step": 1665
},
{
"epoch": 0.57,
"learning_rate": 1.6158477715757262e-05,
"loss": 0.7832,
"step": 1666
},
{
"epoch": 0.58,
"learning_rate": 1.6136551979055738e-05,
"loss": 0.7519,
"step": 1667
},
{
"epoch": 0.58,
"learning_rate": 1.611463106454224e-05,
"loss": 0.7411,
"step": 1668
},
{
"epoch": 0.58,
"learning_rate": 1.6092714999577514e-05,
"loss": 0.7488,
"step": 1669
},
{
"epoch": 0.58,
"learning_rate": 1.607080381151624e-05,
"loss": 0.7985,
"step": 1670
},
{
"epoch": 0.58,
"learning_rate": 1.6048897527707e-05,
"loss": 0.7715,
"step": 1671
},
{
"epoch": 0.58,
"learning_rate": 1.6026996175492287e-05,
"loss": 0.7496,
"step": 1672
},
{
"epoch": 0.58,
"learning_rate": 1.6005099782208392e-05,
"loss": 0.3814,
"step": 1673
},
{
"epoch": 0.58,
"learning_rate": 1.5983208375185463e-05,
"loss": 0.7459,
"step": 1674
},
{
"epoch": 0.58,
"learning_rate": 1.596132198174739e-05,
"loss": 0.7387,
"step": 1675
},
{
"epoch": 0.58,
"learning_rate": 1.593944062921183e-05,
"loss": 0.7427,
"step": 1676
},
{
"epoch": 0.58,
"learning_rate": 1.5917564344890125e-05,
"loss": 0.772,
"step": 1677
},
{
"epoch": 0.58,
"learning_rate": 1.5895693156087317e-05,
"loss": 0.7591,
"step": 1678
},
{
"epoch": 0.58,
"learning_rate": 1.587382709010206e-05,
"loss": 0.7269,
"step": 1679
},
{
"epoch": 0.58,
"learning_rate": 1.5851966174226644e-05,
"loss": 0.741,
"step": 1680
},
{
"epoch": 0.58,
"learning_rate": 1.5830110435746894e-05,
"loss": 0.7452,
"step": 1681
},
{
"epoch": 0.58,
"learning_rate": 1.580825990194221e-05,
"loss": 0.7696,
"step": 1682
},
{
"epoch": 0.58,
"learning_rate": 1.578641460008548e-05,
"loss": 0.7833,
"step": 1683
},
{
"epoch": 0.58,
"learning_rate": 1.5764574557443045e-05,
"loss": 0.7656,
"step": 1684
},
{
"epoch": 0.58,
"learning_rate": 1.5742739801274717e-05,
"loss": 0.3586,
"step": 1685
},
{
"epoch": 0.58,
"learning_rate": 1.5720910358833675e-05,
"loss": 0.746,
"step": 1686
},
{
"epoch": 0.58,
"learning_rate": 1.5699086257366484e-05,
"loss": 0.7814,
"step": 1687
},
{
"epoch": 0.58,
"learning_rate": 1.5677267524113054e-05,
"loss": 0.7372,
"step": 1688
},
{
"epoch": 0.58,
"learning_rate": 1.565545418630656e-05,
"loss": 0.7599,
"step": 1689
},
{
"epoch": 0.58,
"learning_rate": 1.5633646271173483e-05,
"loss": 0.7683,
"step": 1690
},
{
"epoch": 0.58,
"learning_rate": 1.56118438059335e-05,
"loss": 0.7673,
"step": 1691
},
{
"epoch": 0.58,
"learning_rate": 1.5590046817799496e-05,
"loss": 0.798,
"step": 1692
},
{
"epoch": 0.58,
"learning_rate": 1.5568255333977547e-05,
"loss": 0.7166,
"step": 1693
},
{
"epoch": 0.58,
"learning_rate": 1.554646938166682e-05,
"loss": 0.787,
"step": 1694
},
{
"epoch": 0.58,
"learning_rate": 1.5524688988059597e-05,
"loss": 0.7867,
"step": 1695
},
{
"epoch": 0.59,
"learning_rate": 1.550291418034123e-05,
"loss": 0.7909,
"step": 1696
},
{
"epoch": 0.59,
"learning_rate": 1.5481144985690076e-05,
"loss": 0.7788,
"step": 1697
},
{
"epoch": 0.59,
"learning_rate": 1.5459381431277506e-05,
"loss": 0.76,
"step": 1698
},
{
"epoch": 0.59,
"learning_rate": 1.5437623544267836e-05,
"loss": 0.7078,
"step": 1699
},
{
"epoch": 0.59,
"learning_rate": 1.5415871351818316e-05,
"loss": 0.7534,
"step": 1700
},
{
"epoch": 0.59,
"learning_rate": 1.53941248810791e-05,
"loss": 0.6838,
"step": 1701
},
{
"epoch": 0.59,
"learning_rate": 1.5372384159193173e-05,
"loss": 0.816,
"step": 1702
},
{
"epoch": 0.59,
"learning_rate": 1.5350649213296373e-05,
"loss": 0.7713,
"step": 1703
},
{
"epoch": 0.59,
"learning_rate": 1.5328920070517302e-05,
"loss": 0.7813,
"step": 1704
},
{
"epoch": 0.59,
"learning_rate": 1.5307196757977344e-05,
"loss": 0.7564,
"step": 1705
},
{
"epoch": 0.59,
"learning_rate": 1.528547930279059e-05,
"loss": 0.7807,
"step": 1706
},
{
"epoch": 0.59,
"learning_rate": 1.5263767732063824e-05,
"loss": 0.3891,
"step": 1707
},
{
"epoch": 0.59,
"learning_rate": 1.5242062072896483e-05,
"loss": 0.7718,
"step": 1708
},
{
"epoch": 0.59,
"learning_rate": 1.5220362352380636e-05,
"loss": 0.7386,
"step": 1709
},
{
"epoch": 0.59,
"learning_rate": 1.5198668597600921e-05,
"loss": 0.8069,
"step": 1710
},
{
"epoch": 0.59,
"learning_rate": 1.5176980835634556e-05,
"loss": 0.7911,
"step": 1711
},
{
"epoch": 0.59,
"learning_rate": 1.5155299093551243e-05,
"loss": 0.7525,
"step": 1712
},
{
"epoch": 0.59,
"learning_rate": 1.5133623398413209e-05,
"loss": 0.7666,
"step": 1713
},
{
"epoch": 0.59,
"learning_rate": 1.5111953777275112e-05,
"loss": 0.7741,
"step": 1714
},
{
"epoch": 0.59,
"learning_rate": 1.5090290257184019e-05,
"loss": 0.787,
"step": 1715
},
{
"epoch": 0.59,
"learning_rate": 1.5068632865179413e-05,
"loss": 0.7402,
"step": 1716
},
{
"epoch": 0.59,
"learning_rate": 1.5046981628293094e-05,
"loss": 0.7148,
"step": 1717
},
{
"epoch": 0.59,
"learning_rate": 1.50253365735492e-05,
"loss": 0.7867,
"step": 1718
},
{
"epoch": 0.59,
"learning_rate": 1.5003697727964164e-05,
"loss": 0.8271,
"step": 1719
},
{
"epoch": 0.59,
"learning_rate": 1.498206511854663e-05,
"loss": 0.7765,
"step": 1720
},
{
"epoch": 0.59,
"learning_rate": 1.4960438772297501e-05,
"loss": 0.788,
"step": 1721
},
{
"epoch": 0.59,
"learning_rate": 1.4938818716209831e-05,
"loss": 0.7664,
"step": 1722
},
{
"epoch": 0.59,
"learning_rate": 1.4917204977268833e-05,
"loss": 0.8001,
"step": 1723
},
{
"epoch": 0.59,
"learning_rate": 1.489559758245185e-05,
"loss": 0.8093,
"step": 1724
},
{
"epoch": 0.6,
"learning_rate": 1.4873996558728281e-05,
"loss": 0.8142,
"step": 1725
},
{
"epoch": 0.6,
"learning_rate": 1.485240193305959e-05,
"loss": 0.7785,
"step": 1726
},
{
"epoch": 0.6,
"learning_rate": 1.4830813732399261e-05,
"loss": 0.7633,
"step": 1727
},
{
"epoch": 0.6,
"learning_rate": 1.4809231983692733e-05,
"loss": 0.8068,
"step": 1728
},
{
"epoch": 0.6,
"learning_rate": 1.4787656713877418e-05,
"loss": 0.7296,
"step": 1729
},
{
"epoch": 0.6,
"learning_rate": 1.4766087949882625e-05,
"loss": 0.7412,
"step": 1730
},
{
"epoch": 0.6,
"learning_rate": 1.4744525718629548e-05,
"loss": 0.7567,
"step": 1731
},
{
"epoch": 0.6,
"learning_rate": 1.4722970047031237e-05,
"loss": 0.7389,
"step": 1732
},
{
"epoch": 0.6,
"learning_rate": 1.4701420961992533e-05,
"loss": 0.7414,
"step": 1733
},
{
"epoch": 0.6,
"learning_rate": 1.4679878490410077e-05,
"loss": 0.7857,
"step": 1734
},
{
"epoch": 0.6,
"learning_rate": 1.4658342659172237e-05,
"loss": 0.7391,
"step": 1735
},
{
"epoch": 0.6,
"learning_rate": 1.4636813495159112e-05,
"loss": 0.7541,
"step": 1736
},
{
"epoch": 0.6,
"learning_rate": 1.4615291025242467e-05,
"loss": 0.7858,
"step": 1737
},
{
"epoch": 0.6,
"learning_rate": 1.459377527628571e-05,
"loss": 0.7578,
"step": 1738
},
{
"epoch": 0.6,
"learning_rate": 1.4572266275143875e-05,
"loss": 0.7852,
"step": 1739
},
{
"epoch": 0.6,
"learning_rate": 1.4550764048663547e-05,
"loss": 0.8016,
"step": 1740
},
{
"epoch": 0.6,
"learning_rate": 1.4529268623682877e-05,
"loss": 0.7937,
"step": 1741
},
{
"epoch": 0.6,
"learning_rate": 1.4507780027031536e-05,
"loss": 0.7953,
"step": 1742
},
{
"epoch": 0.6,
"learning_rate": 1.4486298285530634e-05,
"loss": 0.7238,
"step": 1743
},
{
"epoch": 0.6,
"learning_rate": 1.4464823425992763e-05,
"loss": 0.7121,
"step": 1744
},
{
"epoch": 0.6,
"learning_rate": 1.4443355475221909e-05,
"loss": 0.7413,
"step": 1745
},
{
"epoch": 0.6,
"learning_rate": 1.4421894460013426e-05,
"loss": 0.7302,
"step": 1746
},
{
"epoch": 0.6,
"learning_rate": 1.4400440407154035e-05,
"loss": 0.7896,
"step": 1747
},
{
"epoch": 0.6,
"learning_rate": 1.4378993343421736e-05,
"loss": 0.8099,
"step": 1748
},
{
"epoch": 0.6,
"learning_rate": 1.4357553295585836e-05,
"loss": 0.7819,
"step": 1749
},
{
"epoch": 0.6,
"learning_rate": 1.4336120290406874e-05,
"loss": 0.7686,
"step": 1750
},
{
"epoch": 0.6,
"learning_rate": 1.431469435463658e-05,
"loss": 0.8099,
"step": 1751
},
{
"epoch": 0.6,
"learning_rate": 1.42932755150179e-05,
"loss": 0.7864,
"step": 1752
},
{
"epoch": 0.6,
"learning_rate": 1.4271863798284877e-05,
"loss": 0.7486,
"step": 1753
},
{
"epoch": 0.61,
"learning_rate": 1.4250459231162692e-05,
"loss": 0.7618,
"step": 1754
},
{
"epoch": 0.61,
"learning_rate": 1.4229061840367608e-05,
"loss": 0.7797,
"step": 1755
},
{
"epoch": 0.61,
"learning_rate": 1.4207671652606902e-05,
"loss": 0.7568,
"step": 1756
},
{
"epoch": 0.61,
"learning_rate": 1.4186288694578894e-05,
"loss": 0.7341,
"step": 1757
},
{
"epoch": 0.61,
"learning_rate": 1.4164912992972846e-05,
"loss": 0.7706,
"step": 1758
},
{
"epoch": 0.61,
"learning_rate": 1.4143544574468995e-05,
"loss": 0.7677,
"step": 1759
},
{
"epoch": 0.61,
"learning_rate": 1.4122183465738466e-05,
"loss": 0.8076,
"step": 1760
},
{
"epoch": 0.61,
"learning_rate": 1.410082969344327e-05,
"loss": 0.3872,
"step": 1761
},
{
"epoch": 0.61,
"learning_rate": 1.407948328423625e-05,
"loss": 0.8052,
"step": 1762
},
{
"epoch": 0.61,
"learning_rate": 1.4058144264761087e-05,
"loss": 0.7215,
"step": 1763
},
{
"epoch": 0.61,
"learning_rate": 1.4036812661652193e-05,
"loss": 0.7244,
"step": 1764
},
{
"epoch": 0.61,
"learning_rate": 1.4015488501534771e-05,
"loss": 0.7972,
"step": 1765
},
{
"epoch": 0.61,
"learning_rate": 1.3994171811024692e-05,
"loss": 0.7397,
"step": 1766
},
{
"epoch": 0.61,
"learning_rate": 1.3972862616728535e-05,
"loss": 0.7475,
"step": 1767
},
{
"epoch": 0.61,
"learning_rate": 1.3951560945243517e-05,
"loss": 0.7742,
"step": 1768
},
{
"epoch": 0.61,
"learning_rate": 1.393026682315744e-05,
"loss": 0.4024,
"step": 1769
},
{
"epoch": 0.61,
"learning_rate": 1.3908980277048723e-05,
"loss": 0.3834,
"step": 1770
},
{
"epoch": 0.61,
"learning_rate": 1.3887701333486287e-05,
"loss": 0.774,
"step": 1771
},
{
"epoch": 0.61,
"learning_rate": 1.38664300190296e-05,
"loss": 0.7828,
"step": 1772
},
{
"epoch": 0.61,
"learning_rate": 1.3845166360228597e-05,
"loss": 0.7635,
"step": 1773
},
{
"epoch": 0.61,
"learning_rate": 1.3823910383623638e-05,
"loss": 0.7753,
"step": 1774
},
{
"epoch": 0.61,
"learning_rate": 1.3802662115745526e-05,
"loss": 0.7523,
"step": 1775
},
{
"epoch": 0.61,
"learning_rate": 1.3781421583115415e-05,
"loss": 0.7998,
"step": 1776
},
{
"epoch": 0.61,
"learning_rate": 1.3760188812244814e-05,
"loss": 0.753,
"step": 1777
},
{
"epoch": 0.61,
"learning_rate": 1.3738963829635559e-05,
"loss": 0.7869,
"step": 1778
},
{
"epoch": 0.61,
"learning_rate": 1.3717746661779737e-05,
"loss": 0.7441,
"step": 1779
},
{
"epoch": 0.61,
"learning_rate": 1.3696537335159697e-05,
"loss": 0.7946,
"step": 1780
},
{
"epoch": 0.61,
"learning_rate": 1.3675335876248013e-05,
"loss": 0.733,
"step": 1781
},
{
"epoch": 0.61,
"learning_rate": 1.3654142311507412e-05,
"loss": 0.7746,
"step": 1782
},
{
"epoch": 0.62,
"learning_rate": 1.3632956667390784e-05,
"loss": 0.3834,
"step": 1783
},
{
"epoch": 0.62,
"learning_rate": 1.3611778970341131e-05,
"loss": 0.8197,
"step": 1784
},
{
"epoch": 0.62,
"learning_rate": 1.3590609246791533e-05,
"loss": 0.7837,
"step": 1785
},
{
"epoch": 0.62,
"learning_rate": 1.3569447523165127e-05,
"loss": 0.7774,
"step": 1786
},
{
"epoch": 0.62,
"learning_rate": 1.3548293825875045e-05,
"loss": 0.7656,
"step": 1787
},
{
"epoch": 0.62,
"learning_rate": 1.3527148181324425e-05,
"loss": 0.7647,
"step": 1788
},
{
"epoch": 0.62,
"learning_rate": 1.3506010615906333e-05,
"loss": 0.7698,
"step": 1789
},
{
"epoch": 0.62,
"learning_rate": 1.3484881156003767e-05,
"loss": 0.7487,
"step": 1790
},
{
"epoch": 0.62,
"learning_rate": 1.3463759827989596e-05,
"loss": 0.3914,
"step": 1791
},
{
"epoch": 0.62,
"learning_rate": 1.3442646658226549e-05,
"loss": 0.8332,
"step": 1792
},
{
"epoch": 0.62,
"learning_rate": 1.3421541673067168e-05,
"loss": 0.7427,
"step": 1793
},
{
"epoch": 0.62,
"learning_rate": 1.340044489885377e-05,
"loss": 0.8091,
"step": 1794
},
{
"epoch": 0.62,
"learning_rate": 1.3379356361918436e-05,
"loss": 0.7757,
"step": 1795
},
{
"epoch": 0.62,
"learning_rate": 1.3358276088582973e-05,
"loss": 0.7536,
"step": 1796
},
{
"epoch": 0.62,
"learning_rate": 1.333720410515885e-05,
"loss": 0.7524,
"step": 1797
},
{
"epoch": 0.62,
"learning_rate": 1.3316140437947207e-05,
"loss": 0.7394,
"step": 1798
},
{
"epoch": 0.62,
"learning_rate": 1.3295085113238801e-05,
"loss": 0.7345,
"step": 1799
},
{
"epoch": 0.62,
"learning_rate": 1.3274038157313963e-05,
"loss": 0.7904,
"step": 1800
},
{
"epoch": 0.62,
"learning_rate": 1.3252999596442606e-05,
"loss": 0.7719,
"step": 1801
},
{
"epoch": 0.62,
"learning_rate": 1.3231969456884129e-05,
"loss": 0.7985,
"step": 1802
},
{
"epoch": 0.62,
"learning_rate": 1.321094776488745e-05,
"loss": 0.7467,
"step": 1803
},
{
"epoch": 0.62,
"learning_rate": 1.318993454669094e-05,
"loss": 0.7238,
"step": 1804
},
{
"epoch": 0.62,
"learning_rate": 1.3168929828522363e-05,
"loss": 0.7605,
"step": 1805
},
{
"epoch": 0.62,
"learning_rate": 1.3147933636598921e-05,
"loss": 0.7722,
"step": 1806
},
{
"epoch": 0.62,
"learning_rate": 1.3126945997127134e-05,
"loss": 0.7671,
"step": 1807
},
{
"epoch": 0.62,
"learning_rate": 1.3105966936302856e-05,
"loss": 0.7607,
"step": 1808
},
{
"epoch": 0.62,
"learning_rate": 1.3084996480311261e-05,
"loss": 0.7282,
"step": 1809
},
{
"epoch": 0.62,
"learning_rate": 1.306403465532674e-05,
"loss": 0.7539,
"step": 1810
},
{
"epoch": 0.62,
"learning_rate": 1.3043081487512944e-05,
"loss": 0.7785,
"step": 1811
},
{
"epoch": 0.63,
"learning_rate": 1.302213700302271e-05,
"loss": 0.3824,
"step": 1812
},
{
"epoch": 0.63,
"learning_rate": 1.3001201227998023e-05,
"loss": 0.6918,
"step": 1813
},
{
"epoch": 0.63,
"learning_rate": 1.2980274188570016e-05,
"loss": 0.7984,
"step": 1814
},
{
"epoch": 0.63,
"learning_rate": 1.2959355910858911e-05,
"loss": 0.7861,
"step": 1815
},
{
"epoch": 0.63,
"learning_rate": 1.2938446420973984e-05,
"loss": 0.7925,
"step": 1816
},
{
"epoch": 0.63,
"learning_rate": 1.291754574501357e-05,
"loss": 0.7772,
"step": 1817
},
{
"epoch": 0.63,
"learning_rate": 1.2896653909064964e-05,
"loss": 0.7496,
"step": 1818
},
{
"epoch": 0.63,
"learning_rate": 1.287577093920447e-05,
"loss": 0.7445,
"step": 1819
},
{
"epoch": 0.63,
"learning_rate": 1.2854896861497284e-05,
"loss": 0.7733,
"step": 1820
},
{
"epoch": 0.63,
"learning_rate": 1.2834031701997538e-05,
"loss": 0.3833,
"step": 1821
},
{
"epoch": 0.63,
"learning_rate": 1.2813175486748208e-05,
"loss": 0.3991,
"step": 1822
},
{
"epoch": 0.63,
"learning_rate": 1.2792328241781124e-05,
"loss": 0.7708,
"step": 1823
},
{
"epoch": 0.63,
"learning_rate": 1.2771489993116913e-05,
"loss": 0.76,
"step": 1824
},
{
"epoch": 0.63,
"learning_rate": 1.2750660766764958e-05,
"loss": 0.7326,
"step": 1825
},
{
"epoch": 0.63,
"learning_rate": 1.2729840588723402e-05,
"loss": 0.7783,
"step": 1826
},
{
"epoch": 0.63,
"learning_rate": 1.2709029484979101e-05,
"loss": 0.7416,
"step": 1827
},
{
"epoch": 0.63,
"learning_rate": 1.2688227481507546e-05,
"loss": 0.7444,
"step": 1828
},
{
"epoch": 0.63,
"learning_rate": 1.2667434604272915e-05,
"loss": 0.7861,
"step": 1829
},
{
"epoch": 0.63,
"learning_rate": 1.264665087922797e-05,
"loss": 0.7848,
"step": 1830
},
{
"epoch": 0.63,
"learning_rate": 1.2625876332314042e-05,
"loss": 0.7687,
"step": 1831
},
{
"epoch": 0.63,
"learning_rate": 1.2605110989461036e-05,
"loss": 0.8066,
"step": 1832
},
{
"epoch": 0.63,
"learning_rate": 1.258435487658733e-05,
"loss": 0.7407,
"step": 1833
},
{
"epoch": 0.63,
"learning_rate": 1.256360801959982e-05,
"loss": 0.7238,
"step": 1834
},
{
"epoch": 0.63,
"learning_rate": 1.2542870444393831e-05,
"loss": 0.7068,
"step": 1835
},
{
"epoch": 0.63,
"learning_rate": 1.2522142176853091e-05,
"loss": 0.748,
"step": 1836
},
{
"epoch": 0.63,
"learning_rate": 1.2501423242849741e-05,
"loss": 0.7695,
"step": 1837
},
{
"epoch": 0.63,
"learning_rate": 1.2480713668244243e-05,
"loss": 0.7094,
"step": 1838
},
{
"epoch": 0.63,
"learning_rate": 1.2460013478885384e-05,
"loss": 0.7527,
"step": 1839
},
{
"epoch": 0.63,
"learning_rate": 1.2439322700610256e-05,
"loss": 0.7681,
"step": 1840
},
{
"epoch": 0.64,
"learning_rate": 1.2418641359244177e-05,
"loss": 0.7687,
"step": 1841
},
{
"epoch": 0.64,
"learning_rate": 1.2397969480600711e-05,
"loss": 0.758,
"step": 1842
},
{
"epoch": 0.64,
"learning_rate": 1.2377307090481586e-05,
"loss": 0.7549,
"step": 1843
},
{
"epoch": 0.64,
"learning_rate": 1.2356654214676706e-05,
"loss": 0.7239,
"step": 1844
},
{
"epoch": 0.64,
"learning_rate": 1.2336010878964098e-05,
"loss": 0.8141,
"step": 1845
},
{
"epoch": 0.64,
"learning_rate": 1.2315377109109871e-05,
"loss": 0.7614,
"step": 1846
},
{
"epoch": 0.64,
"learning_rate": 1.2294752930868201e-05,
"loss": 0.7445,
"step": 1847
},
{
"epoch": 0.64,
"learning_rate": 1.2274138369981298e-05,
"loss": 0.7457,
"step": 1848
},
{
"epoch": 0.64,
"learning_rate": 1.2253533452179351e-05,
"loss": 0.8081,
"step": 1849
},
{
"epoch": 0.64,
"learning_rate": 1.2232938203180537e-05,
"loss": 0.7376,
"step": 1850
},
{
"epoch": 0.64,
"learning_rate": 1.2212352648690935e-05,
"loss": 0.7328,
"step": 1851
},
{
"epoch": 0.64,
"learning_rate": 1.2191776814404554e-05,
"loss": 0.7736,
"step": 1852
},
{
"epoch": 0.64,
"learning_rate": 1.2171210726003256e-05,
"loss": 0.7472,
"step": 1853
},
{
"epoch": 0.64,
"learning_rate": 1.2150654409156725e-05,
"loss": 0.7692,
"step": 1854
},
{
"epoch": 0.64,
"learning_rate": 1.2130107889522485e-05,
"loss": 0.7744,
"step": 1855
},
{
"epoch": 0.64,
"learning_rate": 1.2109571192745789e-05,
"loss": 0.7624,
"step": 1856
},
{
"epoch": 0.64,
"learning_rate": 1.2089044344459656e-05,
"loss": 0.735,
"step": 1857
},
{
"epoch": 0.64,
"learning_rate": 1.2068527370284815e-05,
"loss": 0.7878,
"step": 1858
},
{
"epoch": 0.64,
"learning_rate": 1.2048020295829652e-05,
"loss": 0.7704,
"step": 1859
},
{
"epoch": 0.64,
"learning_rate": 1.2027523146690219e-05,
"loss": 0.7537,
"step": 1860
},
{
"epoch": 0.64,
"learning_rate": 1.2007035948450155e-05,
"loss": 0.7661,
"step": 1861
},
{
"epoch": 0.64,
"learning_rate": 1.198655872668069e-05,
"loss": 0.7656,
"step": 1862
},
{
"epoch": 0.64,
"learning_rate": 1.1966091506940616e-05,
"loss": 0.7322,
"step": 1863
},
{
"epoch": 0.64,
"learning_rate": 1.1945634314776213e-05,
"loss": 0.7638,
"step": 1864
},
{
"epoch": 0.64,
"learning_rate": 1.192518717572127e-05,
"loss": 0.7688,
"step": 1865
},
{
"epoch": 0.64,
"learning_rate": 1.1904750115297018e-05,
"loss": 0.7444,
"step": 1866
},
{
"epoch": 0.64,
"learning_rate": 1.1884323159012103e-05,
"loss": 0.7956,
"step": 1867
},
{
"epoch": 0.64,
"learning_rate": 1.1863906332362569e-05,
"loss": 0.7305,
"step": 1868
},
{
"epoch": 0.64,
"learning_rate": 1.184349966083181e-05,
"loss": 0.7719,
"step": 1869
},
{
"epoch": 0.65,
"learning_rate": 1.1823103169890542e-05,
"loss": 0.7572,
"step": 1870
},
{
"epoch": 0.65,
"learning_rate": 1.1802716884996795e-05,
"loss": 0.7906,
"step": 1871
},
{
"epoch": 0.65,
"learning_rate": 1.1782340831595823e-05,
"loss": 0.7393,
"step": 1872
},
{
"epoch": 0.65,
"learning_rate": 1.176197503512015e-05,
"loss": 0.7988,
"step": 1873
},
{
"epoch": 0.65,
"learning_rate": 1.1741619520989467e-05,
"loss": 0.7977,
"step": 1874
},
{
"epoch": 0.65,
"learning_rate": 1.1721274314610647e-05,
"loss": 0.7745,
"step": 1875
},
{
"epoch": 0.65,
"learning_rate": 1.1700939441377695e-05,
"loss": 0.4158,
"step": 1876
},
{
"epoch": 0.65,
"learning_rate": 1.1680614926671711e-05,
"loss": 0.7491,
"step": 1877
},
{
"epoch": 0.65,
"learning_rate": 1.1660300795860877e-05,
"loss": 0.789,
"step": 1878
},
{
"epoch": 0.65,
"learning_rate": 1.1639997074300406e-05,
"loss": 0.7512,
"step": 1879
},
{
"epoch": 0.65,
"learning_rate": 1.1619703787332522e-05,
"loss": 0.7234,
"step": 1880
},
{
"epoch": 0.65,
"learning_rate": 1.1599420960286425e-05,
"loss": 0.7479,
"step": 1881
},
{
"epoch": 0.65,
"learning_rate": 1.1579148618478259e-05,
"loss": 0.7676,
"step": 1882
},
{
"epoch": 0.65,
"learning_rate": 1.1558886787211071e-05,
"loss": 0.7693,
"step": 1883
},
{
"epoch": 0.65,
"learning_rate": 1.1538635491774826e-05,
"loss": 0.7367,
"step": 1884
},
{
"epoch": 0.65,
"learning_rate": 1.1518394757446275e-05,
"loss": 0.8126,
"step": 1885
},
{
"epoch": 0.65,
"learning_rate": 1.149816460948906e-05,
"loss": 0.3969,
"step": 1886
},
{
"epoch": 0.65,
"learning_rate": 1.1477945073153547e-05,
"loss": 0.6929,
"step": 1887
},
{
"epoch": 0.65,
"learning_rate": 1.1457736173676883e-05,
"loss": 0.7571,
"step": 1888
},
{
"epoch": 0.65,
"learning_rate": 1.1437537936282964e-05,
"loss": 0.7978,
"step": 1889
},
{
"epoch": 0.65,
"learning_rate": 1.1417350386182316e-05,
"loss": 0.7864,
"step": 1890
},
{
"epoch": 0.65,
"learning_rate": 1.13971735485722e-05,
"loss": 0.7944,
"step": 1891
},
{
"epoch": 0.65,
"learning_rate": 1.1377007448636434e-05,
"loss": 0.3928,
"step": 1892
},
{
"epoch": 0.65,
"learning_rate": 1.1356852111545493e-05,
"loss": 0.7846,
"step": 1893
},
{
"epoch": 0.65,
"learning_rate": 1.1336707562456386e-05,
"loss": 0.7672,
"step": 1894
},
{
"epoch": 0.65,
"learning_rate": 1.1316573826512662e-05,
"loss": 0.7921,
"step": 1895
},
{
"epoch": 0.65,
"learning_rate": 1.1296450928844378e-05,
"loss": 0.7339,
"step": 1896
},
{
"epoch": 0.65,
"learning_rate": 1.127633889456806e-05,
"loss": 0.7621,
"step": 1897
},
{
"epoch": 0.65,
"learning_rate": 1.1256237748786675e-05,
"loss": 0.7614,
"step": 1898
},
{
"epoch": 0.66,
"learning_rate": 1.1236147516589603e-05,
"loss": 0.7226,
"step": 1899
},
{
"epoch": 0.66,
"learning_rate": 1.1216068223052596e-05,
"loss": 0.3668,
"step": 1900
},
{
"epoch": 0.66,
"learning_rate": 1.1195999893237759e-05,
"loss": 0.7733,
"step": 1901
},
{
"epoch": 0.66,
"learning_rate": 1.1175942552193507e-05,
"loss": 0.7742,
"step": 1902
},
{
"epoch": 0.66,
"learning_rate": 1.1155896224954543e-05,
"loss": 0.7288,
"step": 1903
},
{
"epoch": 0.66,
"learning_rate": 1.1135860936541823e-05,
"loss": 0.7335,
"step": 1904
},
{
"epoch": 0.66,
"learning_rate": 1.1115836711962522e-05,
"loss": 0.3823,
"step": 1905
},
{
"epoch": 0.66,
"learning_rate": 1.1095823576210001e-05,
"loss": 0.7174,
"step": 1906
},
{
"epoch": 0.66,
"learning_rate": 1.1075821554263813e-05,
"loss": 0.7917,
"step": 1907
},
{
"epoch": 0.66,
"learning_rate": 1.1055830671089578e-05,
"loss": 0.6868,
"step": 1908
},
{
"epoch": 0.66,
"learning_rate": 1.1035850951639077e-05,
"loss": 0.7582,
"step": 1909
},
{
"epoch": 0.66,
"learning_rate": 1.1015882420850105e-05,
"loss": 0.7853,
"step": 1910
},
{
"epoch": 0.66,
"learning_rate": 1.0995925103646532e-05,
"loss": 0.7342,
"step": 1911
},
{
"epoch": 0.66,
"learning_rate": 1.097597902493822e-05,
"loss": 0.7548,
"step": 1912
},
{
"epoch": 0.66,
"learning_rate": 1.0956044209620966e-05,
"loss": 0.4052,
"step": 1913
},
{
"epoch": 0.66,
"learning_rate": 1.0936120682576572e-05,
"loss": 0.7569,
"step": 1914
},
{
"epoch": 0.66,
"learning_rate": 1.0916208468672709e-05,
"loss": 0.713,
"step": 1915
},
{
"epoch": 0.66,
"learning_rate": 1.0896307592762935e-05,
"loss": 0.7576,
"step": 1916
},
{
"epoch": 0.66,
"learning_rate": 1.0876418079686667e-05,
"loss": 0.7753,
"step": 1917
},
{
"epoch": 0.66,
"learning_rate": 1.0856539954269121e-05,
"loss": 0.7849,
"step": 1918
},
{
"epoch": 0.66,
"learning_rate": 1.0836673241321317e-05,
"loss": 0.7365,
"step": 1919
},
{
"epoch": 0.66,
"learning_rate": 1.081681796564002e-05,
"loss": 0.7873,
"step": 1920
},
{
"epoch": 0.66,
"learning_rate": 1.0796974152007724e-05,
"loss": 0.8149,
"step": 1921
},
{
"epoch": 0.66,
"learning_rate": 1.0777141825192614e-05,
"loss": 0.7918,
"step": 1922
},
{
"epoch": 0.66,
"learning_rate": 1.0757321009948543e-05,
"loss": 0.7941,
"step": 1923
},
{
"epoch": 0.66,
"learning_rate": 1.073751173101498e-05,
"loss": 0.7311,
"step": 1924
},
{
"epoch": 0.66,
"learning_rate": 1.0717714013117031e-05,
"loss": 0.7901,
"step": 1925
},
{
"epoch": 0.66,
"learning_rate": 1.0697927880965326e-05,
"loss": 0.385,
"step": 1926
},
{
"epoch": 0.66,
"learning_rate": 1.0678153359256062e-05,
"loss": 0.7498,
"step": 1927
},
{
"epoch": 0.67,
"learning_rate": 1.0658390472670938e-05,
"loss": 0.7405,
"step": 1928
},
{
"epoch": 0.67,
"learning_rate": 1.0638639245877126e-05,
"loss": 0.7473,
"step": 1929
},
{
"epoch": 0.67,
"learning_rate": 1.0618899703527265e-05,
"loss": 0.7469,
"step": 1930
},
{
"epoch": 0.67,
"learning_rate": 1.0599171870259374e-05,
"loss": 0.8201,
"step": 1931
},
{
"epoch": 0.67,
"learning_rate": 1.0579455770696894e-05,
"loss": 0.7529,
"step": 1932
},
{
"epoch": 0.67,
"learning_rate": 1.0559751429448597e-05,
"loss": 0.8203,
"step": 1933
},
{
"epoch": 0.67,
"learning_rate": 1.054005887110859e-05,
"loss": 0.7806,
"step": 1934
},
{
"epoch": 0.67,
"learning_rate": 1.0520378120256271e-05,
"loss": 0.7681,
"step": 1935
},
{
"epoch": 0.67,
"learning_rate": 1.050070920145628e-05,
"loss": 0.7544,
"step": 1936
},
{
"epoch": 0.67,
"learning_rate": 1.048105213925853e-05,
"loss": 0.747,
"step": 1937
},
{
"epoch": 0.67,
"learning_rate": 1.0461406958198101e-05,
"loss": 0.7664,
"step": 1938
},
{
"epoch": 0.67,
"learning_rate": 1.044177368279526e-05,
"loss": 0.7601,
"step": 1939
},
{
"epoch": 0.67,
"learning_rate": 1.0422152337555405e-05,
"loss": 0.7498,
"step": 1940
},
{
"epoch": 0.67,
"learning_rate": 1.0402542946969048e-05,
"loss": 0.7935,
"step": 1941
},
{
"epoch": 0.67,
"learning_rate": 1.038294553551178e-05,
"loss": 0.7626,
"step": 1942
},
{
"epoch": 0.67,
"learning_rate": 1.0363360127644235e-05,
"loss": 0.7945,
"step": 1943
},
{
"epoch": 0.67,
"learning_rate": 1.0343786747812073e-05,
"loss": 0.7952,
"step": 1944
},
{
"epoch": 0.67,
"learning_rate": 1.0324225420445935e-05,
"loss": 0.7468,
"step": 1945
},
{
"epoch": 0.67,
"learning_rate": 1.030467616996142e-05,
"loss": 0.7587,
"step": 1946
},
{
"epoch": 0.67,
"learning_rate": 1.0285139020759045e-05,
"loss": 0.757,
"step": 1947
},
{
"epoch": 0.67,
"learning_rate": 1.0265613997224255e-05,
"loss": 0.7631,
"step": 1948
},
{
"epoch": 0.67,
"learning_rate": 1.0246101123727315e-05,
"loss": 0.728,
"step": 1949
},
{
"epoch": 0.67,
"learning_rate": 1.0226600424623344e-05,
"loss": 0.7619,
"step": 1950
},
{
"epoch": 0.67,
"learning_rate": 1.020711192425229e-05,
"loss": 0.736,
"step": 1951
},
{
"epoch": 0.67,
"learning_rate": 1.0187635646938826e-05,
"loss": 0.7544,
"step": 1952
},
{
"epoch": 0.67,
"learning_rate": 1.0168171616992422e-05,
"loss": 0.749,
"step": 1953
},
{
"epoch": 0.67,
"learning_rate": 1.0148719858707208e-05,
"loss": 0.7619,
"step": 1954
},
{
"epoch": 0.67,
"learning_rate": 1.0129280396362042e-05,
"loss": 0.7505,
"step": 1955
},
{
"epoch": 0.67,
"learning_rate": 1.0109853254220416e-05,
"loss": 0.7708,
"step": 1956
},
{
"epoch": 0.68,
"learning_rate": 1.0090438456530438e-05,
"loss": 0.7786,
"step": 1957
},
{
"epoch": 0.68,
"learning_rate": 1.007103602752483e-05,
"loss": 0.7943,
"step": 1958
},
{
"epoch": 0.68,
"learning_rate": 1.0051645991420828e-05,
"loss": 0.7547,
"step": 1959
},
{
"epoch": 0.68,
"learning_rate": 1.0032268372420266e-05,
"loss": 0.7475,
"step": 1960
},
{
"epoch": 0.68,
"learning_rate": 1.0012903194709436e-05,
"loss": 0.7023,
"step": 1961
},
{
"epoch": 0.68,
"learning_rate": 9.993550482459111e-06,
"loss": 0.7323,
"step": 1962
},
{
"epoch": 0.68,
"learning_rate": 9.974210259824505e-06,
"loss": 0.7596,
"step": 1963
},
{
"epoch": 0.68,
"learning_rate": 9.954882550945244e-06,
"loss": 0.7804,
"step": 1964
},
{
"epoch": 0.68,
"learning_rate": 9.935567379945336e-06,
"loss": 0.7846,
"step": 1965
},
{
"epoch": 0.68,
"learning_rate": 9.916264770933139e-06,
"loss": 0.727,
"step": 1966
},
{
"epoch": 0.68,
"learning_rate": 9.89697474800133e-06,
"loss": 0.368,
"step": 1967
},
{
"epoch": 0.68,
"learning_rate": 9.877697335226872e-06,
"loss": 0.7358,
"step": 1968
},
{
"epoch": 0.68,
"learning_rate": 9.858432556671016e-06,
"loss": 0.7684,
"step": 1969
},
{
"epoch": 0.68,
"learning_rate": 9.839180436379192e-06,
"loss": 0.7467,
"step": 1970
},
{
"epoch": 0.68,
"learning_rate": 9.81994099838109e-06,
"loss": 0.7724,
"step": 1971
},
{
"epoch": 0.68,
"learning_rate": 9.800714266690518e-06,
"loss": 0.7369,
"step": 1972
},
{
"epoch": 0.68,
"learning_rate": 9.781500265305448e-06,
"loss": 0.7735,
"step": 1973
},
{
"epoch": 0.68,
"learning_rate": 9.762299018207987e-06,
"loss": 0.7002,
"step": 1974
},
{
"epoch": 0.68,
"learning_rate": 9.743110549364262e-06,
"loss": 0.7374,
"step": 1975
},
{
"epoch": 0.68,
"learning_rate": 9.723934882724523e-06,
"loss": 0.7419,
"step": 1976
},
{
"epoch": 0.68,
"learning_rate": 9.704772042222972e-06,
"loss": 0.7564,
"step": 1977
},
{
"epoch": 0.68,
"learning_rate": 9.685622051777856e-06,
"loss": 0.7557,
"step": 1978
},
{
"epoch": 0.68,
"learning_rate": 9.666484935291354e-06,
"loss": 0.7739,
"step": 1979
},
{
"epoch": 0.68,
"learning_rate": 9.647360716649583e-06,
"loss": 0.7918,
"step": 1980
},
{
"epoch": 0.68,
"learning_rate": 9.628249419722562e-06,
"loss": 0.7856,
"step": 1981
},
{
"epoch": 0.68,
"learning_rate": 9.609151068364184e-06,
"loss": 0.7682,
"step": 1982
},
{
"epoch": 0.68,
"learning_rate": 9.590065686412182e-06,
"loss": 0.7358,
"step": 1983
},
{
"epoch": 0.68,
"learning_rate": 9.570993297688097e-06,
"loss": 0.7384,
"step": 1984
},
{
"epoch": 0.68,
"learning_rate": 9.551933925997261e-06,
"loss": 0.7068,
"step": 1985
},
{
"epoch": 0.69,
"learning_rate": 9.53288759512875e-06,
"loss": 0.7432,
"step": 1986
},
{
"epoch": 0.69,
"learning_rate": 9.51385432885537e-06,
"loss": 0.7469,
"step": 1987
},
{
"epoch": 0.69,
"learning_rate": 9.494834150933616e-06,
"loss": 0.7515,
"step": 1988
},
{
"epoch": 0.69,
"learning_rate": 9.475827085103649e-06,
"loss": 0.7707,
"step": 1989
},
{
"epoch": 0.69,
"learning_rate": 9.45683315508926e-06,
"loss": 0.8041,
"step": 1990
},
{
"epoch": 0.69,
"learning_rate": 9.437852384597846e-06,
"loss": 0.7732,
"step": 1991
},
{
"epoch": 0.69,
"learning_rate": 9.418884797320396e-06,
"loss": 0.7645,
"step": 1992
},
{
"epoch": 0.69,
"learning_rate": 9.399930416931404e-06,
"loss": 0.7935,
"step": 1993
},
{
"epoch": 0.69,
"learning_rate": 9.380989267088931e-06,
"loss": 0.4,
"step": 1994
},
{
"epoch": 0.69,
"learning_rate": 9.362061371434472e-06,
"loss": 0.7164,
"step": 1995
},
{
"epoch": 0.69,
"learning_rate": 9.343146753593022e-06,
"loss": 0.7966,
"step": 1996
},
{
"epoch": 0.69,
"learning_rate": 9.324245437172987e-06,
"loss": 0.779,
"step": 1997
},
{
"epoch": 0.69,
"learning_rate": 9.30535744576615e-06,
"loss": 0.7661,
"step": 1998
},
{
"epoch": 0.69,
"learning_rate": 9.286482802947699e-06,
"loss": 0.7763,
"step": 1999
},
{
"epoch": 0.69,
"learning_rate": 9.26762153227614e-06,
"loss": 0.7132,
"step": 2000
},
{
"epoch": 0.69,
"learning_rate": 9.24877365729329e-06,
"loss": 0.7268,
"step": 2001
},
{
"epoch": 0.69,
"learning_rate": 9.229939201524247e-06,
"loss": 0.7263,
"step": 2002
},
{
"epoch": 0.69,
"learning_rate": 9.211118188477362e-06,
"loss": 0.733,
"step": 2003
},
{
"epoch": 0.69,
"learning_rate": 9.192310641644206e-06,
"loss": 0.7197,
"step": 2004
},
{
"epoch": 0.69,
"learning_rate": 9.173516584499544e-06,
"loss": 0.7399,
"step": 2005
},
{
"epoch": 0.69,
"learning_rate": 9.1547360405013e-06,
"loss": 0.7857,
"step": 2006
},
{
"epoch": 0.69,
"learning_rate": 9.135969033090535e-06,
"loss": 0.7479,
"step": 2007
},
{
"epoch": 0.69,
"learning_rate": 9.117215585691408e-06,
"loss": 0.7382,
"step": 2008
},
{
"epoch": 0.69,
"learning_rate": 9.098475721711156e-06,
"loss": 0.7354,
"step": 2009
},
{
"epoch": 0.69,
"learning_rate": 9.079749464540081e-06,
"loss": 0.7267,
"step": 2010
},
{
"epoch": 0.69,
"learning_rate": 9.061036837551467e-06,
"loss": 0.7867,
"step": 2011
},
{
"epoch": 0.69,
"learning_rate": 9.042337864101604e-06,
"loss": 0.7555,
"step": 2012
},
{
"epoch": 0.69,
"learning_rate": 9.023652567529744e-06,
"loss": 0.7833,
"step": 2013
},
{
"epoch": 0.69,
"learning_rate": 9.004980971158048e-06,
"loss": 0.7568,
"step": 2014
},
{
"epoch": 0.7,
"learning_rate": 8.986323098291623e-06,
"loss": 0.7822,
"step": 2015
},
{
"epoch": 0.7,
"learning_rate": 8.96767897221838e-06,
"loss": 0.7968,
"step": 2016
},
{
"epoch": 0.7,
"learning_rate": 8.949048616209129e-06,
"loss": 0.7802,
"step": 2017
},
{
"epoch": 0.7,
"learning_rate": 8.930432053517465e-06,
"loss": 0.402,
"step": 2018
},
{
"epoch": 0.7,
"learning_rate": 8.911829307379779e-06,
"loss": 0.7285,
"step": 2019
},
{
"epoch": 0.7,
"learning_rate": 8.89324040101521e-06,
"loss": 0.7656,
"step": 2020
},
{
"epoch": 0.7,
"learning_rate": 8.874665357625605e-06,
"loss": 0.7501,
"step": 2021
},
{
"epoch": 0.7,
"learning_rate": 8.856104200395548e-06,
"loss": 0.7436,
"step": 2022
},
{
"epoch": 0.7,
"learning_rate": 8.837556952492264e-06,
"loss": 0.7365,
"step": 2023
},
{
"epoch": 0.7,
"learning_rate": 8.819023637065619e-06,
"loss": 0.7982,
"step": 2024
},
{
"epoch": 0.7,
"learning_rate": 8.800504277248094e-06,
"loss": 0.806,
"step": 2025
},
{
"epoch": 0.7,
"learning_rate": 8.78199889615475e-06,
"loss": 0.7397,
"step": 2026
},
{
"epoch": 0.7,
"learning_rate": 8.7635075168832e-06,
"loss": 0.7533,
"step": 2027
},
{
"epoch": 0.7,
"learning_rate": 8.745030162513582e-06,
"loss": 0.7699,
"step": 2028
},
{
"epoch": 0.7,
"learning_rate": 8.726566856108523e-06,
"loss": 0.7705,
"step": 2029
},
{
"epoch": 0.7,
"learning_rate": 8.708117620713123e-06,
"loss": 0.7258,
"step": 2030
},
{
"epoch": 0.7,
"learning_rate": 8.689682479354917e-06,
"loss": 0.7246,
"step": 2031
},
{
"epoch": 0.7,
"learning_rate": 8.67126145504384e-06,
"loss": 0.3889,
"step": 2032
},
{
"epoch": 0.7,
"learning_rate": 8.652854570772236e-06,
"loss": 0.7867,
"step": 2033
},
{
"epoch": 0.7,
"learning_rate": 8.634461849514757e-06,
"loss": 0.7497,
"step": 2034
},
{
"epoch": 0.7,
"learning_rate": 8.616083314228399e-06,
"loss": 0.7875,
"step": 2035
},
{
"epoch": 0.7,
"learning_rate": 8.59771898785247e-06,
"loss": 0.7387,
"step": 2036
},
{
"epoch": 0.7,
"learning_rate": 8.579368893308502e-06,
"loss": 0.7665,
"step": 2037
},
{
"epoch": 0.7,
"learning_rate": 8.561033053500312e-06,
"loss": 0.7912,
"step": 2038
},
{
"epoch": 0.7,
"learning_rate": 8.542711491313869e-06,
"loss": 0.7582,
"step": 2039
},
{
"epoch": 0.7,
"learning_rate": 8.524404229617371e-06,
"loss": 0.7605,
"step": 2040
},
{
"epoch": 0.7,
"learning_rate": 8.506111291261146e-06,
"loss": 0.7805,
"step": 2041
},
{
"epoch": 0.7,
"learning_rate": 8.487832699077641e-06,
"loss": 0.7624,
"step": 2042
},
{
"epoch": 0.7,
"learning_rate": 8.46956847588141e-06,
"loss": 0.799,
"step": 2043
},
{
"epoch": 0.71,
"learning_rate": 8.451318644469037e-06,
"loss": 0.7862,
"step": 2044
},
{
"epoch": 0.71,
"learning_rate": 8.433083227619197e-06,
"loss": 0.8034,
"step": 2045
},
{
"epoch": 0.71,
"learning_rate": 8.414862248092534e-06,
"loss": 0.3997,
"step": 2046
},
{
"epoch": 0.71,
"learning_rate": 8.396655728631686e-06,
"loss": 0.7142,
"step": 2047
},
{
"epoch": 0.71,
"learning_rate": 8.378463691961237e-06,
"loss": 0.7485,
"step": 2048
},
{
"epoch": 0.71,
"learning_rate": 8.360286160787699e-06,
"loss": 0.7594,
"step": 2049
},
{
"epoch": 0.71,
"learning_rate": 8.342123157799476e-06,
"loss": 0.7856,
"step": 2050
},
{
"epoch": 0.71,
"learning_rate": 8.323974705666842e-06,
"loss": 0.7644,
"step": 2051
},
{
"epoch": 0.71,
"learning_rate": 8.305840827041903e-06,
"loss": 0.7601,
"step": 2052
},
{
"epoch": 0.71,
"learning_rate": 8.287721544558574e-06,
"loss": 0.7365,
"step": 2053
},
{
"epoch": 0.71,
"learning_rate": 8.269616880832579e-06,
"loss": 0.7593,
"step": 2054
},
{
"epoch": 0.71,
"learning_rate": 8.251526858461341e-06,
"loss": 0.7879,
"step": 2055
},
{
"epoch": 0.71,
"learning_rate": 8.23345150002407e-06,
"loss": 0.7537,
"step": 2056
},
{
"epoch": 0.71,
"learning_rate": 8.215390828081624e-06,
"loss": 0.8026,
"step": 2057
},
{
"epoch": 0.71,
"learning_rate": 8.197344865176548e-06,
"loss": 0.7711,
"step": 2058
},
{
"epoch": 0.71,
"learning_rate": 8.17931363383305e-06,
"loss": 0.7542,
"step": 2059
},
{
"epoch": 0.71,
"learning_rate": 8.161297156556903e-06,
"loss": 0.7866,
"step": 2060
},
{
"epoch": 0.71,
"learning_rate": 8.143295455835519e-06,
"loss": 0.7674,
"step": 2061
},
{
"epoch": 0.71,
"learning_rate": 8.125308554137809e-06,
"loss": 0.6823,
"step": 2062
},
{
"epoch": 0.71,
"learning_rate": 8.10733647391427e-06,
"loss": 0.7711,
"step": 2063
},
{
"epoch": 0.71,
"learning_rate": 8.089379237596855e-06,
"loss": 0.7757,
"step": 2064
},
{
"epoch": 0.71,
"learning_rate": 8.071436867599014e-06,
"loss": 0.755,
"step": 2065
},
{
"epoch": 0.71,
"learning_rate": 8.053509386315632e-06,
"loss": 0.799,
"step": 2066
},
{
"epoch": 0.71,
"learning_rate": 8.035596816123013e-06,
"loss": 0.7311,
"step": 2067
},
{
"epoch": 0.71,
"learning_rate": 8.017699179378849e-06,
"loss": 0.7313,
"step": 2068
},
{
"epoch": 0.71,
"learning_rate": 7.999816498422192e-06,
"loss": 0.7811,
"step": 2069
},
{
"epoch": 0.71,
"learning_rate": 7.98194879557343e-06,
"loss": 0.777,
"step": 2070
},
{
"epoch": 0.71,
"learning_rate": 7.964096093134249e-06,
"loss": 0.6927,
"step": 2071
},
{
"epoch": 0.71,
"learning_rate": 7.946258413387622e-06,
"loss": 0.7672,
"step": 2072
},
{
"epoch": 0.72,
"learning_rate": 7.928435778597763e-06,
"loss": 0.731,
"step": 2073
},
{
"epoch": 0.72,
"learning_rate": 7.910628211010112e-06,
"loss": 0.7544,
"step": 2074
},
{
"epoch": 0.72,
"learning_rate": 7.892835732851302e-06,
"loss": 0.7315,
"step": 2075
},
{
"epoch": 0.72,
"learning_rate": 7.875058366329124e-06,
"loss": 0.7439,
"step": 2076
},
{
"epoch": 0.72,
"learning_rate": 7.857296133632535e-06,
"loss": 0.7376,
"step": 2077
},
{
"epoch": 0.72,
"learning_rate": 7.839549056931557e-06,
"loss": 0.7466,
"step": 2078
},
{
"epoch": 0.72,
"learning_rate": 7.821817158377345e-06,
"loss": 0.7682,
"step": 2079
},
{
"epoch": 0.72,
"learning_rate": 7.80410046010206e-06,
"loss": 0.7682,
"step": 2080
},
{
"epoch": 0.72,
"learning_rate": 7.786398984218932e-06,
"loss": 0.7761,
"step": 2081
},
{
"epoch": 0.72,
"learning_rate": 7.768712752822179e-06,
"loss": 0.7494,
"step": 2082
},
{
"epoch": 0.72,
"learning_rate": 7.751041787986965e-06,
"loss": 0.7743,
"step": 2083
},
{
"epoch": 0.72,
"learning_rate": 7.733386111769446e-06,
"loss": 0.7639,
"step": 2084
},
{
"epoch": 0.72,
"learning_rate": 7.715745746206644e-06,
"loss": 0.7603,
"step": 2085
},
{
"epoch": 0.72,
"learning_rate": 7.69812071331652e-06,
"loss": 0.7851,
"step": 2086
},
{
"epoch": 0.72,
"learning_rate": 7.680511035097864e-06,
"loss": 0.7802,
"step": 2087
},
{
"epoch": 0.72,
"learning_rate": 7.662916733530317e-06,
"loss": 0.733,
"step": 2088
},
{
"epoch": 0.72,
"learning_rate": 7.645337830574315e-06,
"loss": 0.7485,
"step": 2089
},
{
"epoch": 0.72,
"learning_rate": 7.6277743481710885e-06,
"loss": 0.7312,
"step": 2090
},
{
"epoch": 0.72,
"learning_rate": 7.610226308242608e-06,
"loss": 0.7597,
"step": 2091
},
{
"epoch": 0.72,
"learning_rate": 7.592693732691576e-06,
"loss": 0.792,
"step": 2092
},
{
"epoch": 0.72,
"learning_rate": 7.575176643401394e-06,
"loss": 0.7782,
"step": 2093
},
{
"epoch": 0.72,
"learning_rate": 7.557675062236125e-06,
"loss": 0.7699,
"step": 2094
},
{
"epoch": 0.72,
"learning_rate": 7.5401890110404995e-06,
"loss": 0.7651,
"step": 2095
},
{
"epoch": 0.72,
"learning_rate": 7.5227185116398325e-06,
"loss": 0.7978,
"step": 2096
},
{
"epoch": 0.72,
"learning_rate": 7.5052635858400435e-06,
"loss": 0.8127,
"step": 2097
},
{
"epoch": 0.72,
"learning_rate": 7.487824255427616e-06,
"loss": 0.7788,
"step": 2098
},
{
"epoch": 0.72,
"learning_rate": 7.470400542169558e-06,
"loss": 0.3992,
"step": 2099
},
{
"epoch": 0.72,
"learning_rate": 7.452992467813411e-06,
"loss": 0.735,
"step": 2100
},
{
"epoch": 0.72,
"learning_rate": 7.435600054087153e-06,
"loss": 0.7621,
"step": 2101
},
{
"epoch": 0.73,
"learning_rate": 7.418223322699256e-06,
"loss": 0.7609,
"step": 2102
},
{
"epoch": 0.73,
"learning_rate": 7.400862295338595e-06,
"loss": 0.7516,
"step": 2103
},
{
"epoch": 0.73,
"learning_rate": 7.383516993674456e-06,
"loss": 0.8183,
"step": 2104
},
{
"epoch": 0.73,
"learning_rate": 7.366187439356491e-06,
"loss": 0.7358,
"step": 2105
},
{
"epoch": 0.73,
"learning_rate": 7.348873654014679e-06,
"loss": 0.7238,
"step": 2106
},
{
"epoch": 0.73,
"learning_rate": 7.331575659259358e-06,
"loss": 0.7756,
"step": 2107
},
{
"epoch": 0.73,
"learning_rate": 7.314293476681122e-06,
"loss": 0.7882,
"step": 2108
},
{
"epoch": 0.73,
"learning_rate": 7.297027127850847e-06,
"loss": 0.7441,
"step": 2109
},
{
"epoch": 0.73,
"learning_rate": 7.279776634319635e-06,
"loss": 0.7384,
"step": 2110
},
{
"epoch": 0.73,
"learning_rate": 7.262542017618803e-06,
"loss": 0.7482,
"step": 2111
},
{
"epoch": 0.73,
"learning_rate": 7.245323299259854e-06,
"loss": 0.7491,
"step": 2112
},
{
"epoch": 0.73,
"learning_rate": 7.228120500734443e-06,
"loss": 0.7268,
"step": 2113
},
{
"epoch": 0.73,
"learning_rate": 7.210933643514355e-06,
"loss": 0.7848,
"step": 2114
},
{
"epoch": 0.73,
"learning_rate": 7.193762749051481e-06,
"loss": 0.7433,
"step": 2115
},
{
"epoch": 0.73,
"learning_rate": 7.176607838777783e-06,
"loss": 0.7456,
"step": 2116
},
{
"epoch": 0.73,
"learning_rate": 7.159468934105269e-06,
"loss": 0.3911,
"step": 2117
},
{
"epoch": 0.73,
"learning_rate": 7.1423460564259995e-06,
"loss": 0.7584,
"step": 2118
},
{
"epoch": 0.73,
"learning_rate": 7.1252392271119795e-06,
"loss": 0.7887,
"step": 2119
},
{
"epoch": 0.73,
"learning_rate": 7.108148467515217e-06,
"loss": 0.761,
"step": 2120
},
{
"epoch": 0.73,
"learning_rate": 7.091073798967674e-06,
"loss": 0.7422,
"step": 2121
},
{
"epoch": 0.73,
"learning_rate": 7.074015242781181e-06,
"loss": 0.7677,
"step": 2122
},
{
"epoch": 0.73,
"learning_rate": 7.056972820247516e-06,
"loss": 0.8101,
"step": 2123
},
{
"epoch": 0.73,
"learning_rate": 7.0399465526382635e-06,
"loss": 0.7327,
"step": 2124
},
{
"epoch": 0.73,
"learning_rate": 7.022936461204892e-06,
"loss": 0.852,
"step": 2125
},
{
"epoch": 0.73,
"learning_rate": 7.005942567178652e-06,
"loss": 0.7865,
"step": 2126
},
{
"epoch": 0.73,
"learning_rate": 6.9889648917705824e-06,
"loss": 0.7617,
"step": 2127
},
{
"epoch": 0.73,
"learning_rate": 6.97200345617149e-06,
"loss": 0.752,
"step": 2128
},
{
"epoch": 0.73,
"learning_rate": 6.955058281551879e-06,
"loss": 0.7891,
"step": 2129
},
{
"epoch": 0.73,
"learning_rate": 6.938129389062001e-06,
"loss": 0.7538,
"step": 2130
},
{
"epoch": 0.74,
"learning_rate": 6.921216799831758e-06,
"loss": 0.7351,
"step": 2131
},
{
"epoch": 0.74,
"learning_rate": 6.904320534970712e-06,
"loss": 0.7585,
"step": 2132
},
{
"epoch": 0.74,
"learning_rate": 6.887440615568044e-06,
"loss": 0.7644,
"step": 2133
},
{
"epoch": 0.74,
"learning_rate": 6.870577062692538e-06,
"loss": 0.6955,
"step": 2134
},
{
"epoch": 0.74,
"learning_rate": 6.853729897392547e-06,
"loss": 0.7162,
"step": 2135
},
{
"epoch": 0.74,
"learning_rate": 6.836899140695972e-06,
"loss": 0.7731,
"step": 2136
},
{
"epoch": 0.74,
"learning_rate": 6.8200848136102305e-06,
"loss": 0.8259,
"step": 2137
},
{
"epoch": 0.74,
"learning_rate": 6.803286937122233e-06,
"loss": 0.7465,
"step": 2138
},
{
"epoch": 0.74,
"learning_rate": 6.7865055321983754e-06,
"loss": 0.7983,
"step": 2139
},
{
"epoch": 0.74,
"learning_rate": 6.769740619784453e-06,
"loss": 0.7612,
"step": 2140
},
{
"epoch": 0.74,
"learning_rate": 6.75299222080573e-06,
"loss": 0.8038,
"step": 2141
},
{
"epoch": 0.74,
"learning_rate": 6.736260356166806e-06,
"loss": 0.8132,
"step": 2142
},
{
"epoch": 0.74,
"learning_rate": 6.719545046751674e-06,
"loss": 0.6902,
"step": 2143
},
{
"epoch": 0.74,
"learning_rate": 6.702846313423672e-06,
"loss": 0.7842,
"step": 2144
},
{
"epoch": 0.74,
"learning_rate": 6.68616417702541e-06,
"loss": 0.7621,
"step": 2145
},
{
"epoch": 0.74,
"learning_rate": 6.66949865837883e-06,
"loss": 0.7629,
"step": 2146
},
{
"epoch": 0.74,
"learning_rate": 6.652849778285087e-06,
"loss": 0.794,
"step": 2147
},
{
"epoch": 0.74,
"learning_rate": 6.636217557524605e-06,
"loss": 0.7717,
"step": 2148
},
{
"epoch": 0.74,
"learning_rate": 6.619602016856996e-06,
"loss": 0.4093,
"step": 2149
},
{
"epoch": 0.74,
"learning_rate": 6.603003177021055e-06,
"loss": 0.7855,
"step": 2150
},
{
"epoch": 0.74,
"learning_rate": 6.5864210587347334e-06,
"loss": 0.6771,
"step": 2151
},
{
"epoch": 0.74,
"learning_rate": 6.5698556826951095e-06,
"loss": 0.7906,
"step": 2152
},
{
"epoch": 0.74,
"learning_rate": 6.55330706957837e-06,
"loss": 0.7806,
"step": 2153
},
{
"epoch": 0.74,
"learning_rate": 6.53677524003977e-06,
"loss": 0.736,
"step": 2154
},
{
"epoch": 0.74,
"learning_rate": 6.520260214713628e-06,
"loss": 0.7775,
"step": 2155
},
{
"epoch": 0.74,
"learning_rate": 6.503762014213273e-06,
"loss": 0.7786,
"step": 2156
},
{
"epoch": 0.74,
"learning_rate": 6.48728065913105e-06,
"loss": 0.746,
"step": 2157
},
{
"epoch": 0.74,
"learning_rate": 6.4708161700382655e-06,
"loss": 0.7693,
"step": 2158
},
{
"epoch": 0.74,
"learning_rate": 6.4543685674851834e-06,
"loss": 0.7684,
"step": 2159
},
{
"epoch": 0.75,
"learning_rate": 6.437937872000983e-06,
"loss": 0.7342,
"step": 2160
},
{
"epoch": 0.75,
"learning_rate": 6.421524104093742e-06,
"loss": 0.7659,
"step": 2161
},
{
"epoch": 0.75,
"learning_rate": 6.40512728425043e-06,
"loss": 0.7864,
"step": 2162
},
{
"epoch": 0.75,
"learning_rate": 6.388747432936819e-06,
"loss": 0.7657,
"step": 2163
},
{
"epoch": 0.75,
"learning_rate": 6.372384570597559e-06,
"loss": 0.7815,
"step": 2164
},
{
"epoch": 0.75,
"learning_rate": 6.35603871765603e-06,
"loss": 0.7206,
"step": 2165
},
{
"epoch": 0.75,
"learning_rate": 6.3397098945144405e-06,
"loss": 0.7161,
"step": 2166
},
{
"epoch": 0.75,
"learning_rate": 6.323398121553719e-06,
"loss": 0.7706,
"step": 2167
},
{
"epoch": 0.75,
"learning_rate": 6.3071034191334915e-06,
"loss": 0.7317,
"step": 2168
},
{
"epoch": 0.75,
"learning_rate": 6.290825807592123e-06,
"loss": 0.7386,
"step": 2169
},
{
"epoch": 0.75,
"learning_rate": 6.274565307246594e-06,
"loss": 0.7582,
"step": 2170
},
{
"epoch": 0.75,
"learning_rate": 6.258321938392577e-06,
"loss": 0.8039,
"step": 2171
},
{
"epoch": 0.75,
"learning_rate": 6.242095721304333e-06,
"loss": 0.7841,
"step": 2172
},
{
"epoch": 0.75,
"learning_rate": 6.22588667623472e-06,
"loss": 0.4008,
"step": 2173
},
{
"epoch": 0.75,
"learning_rate": 6.209694823415167e-06,
"loss": 0.7627,
"step": 2174
},
{
"epoch": 0.75,
"learning_rate": 6.193520183055637e-06,
"loss": 0.7186,
"step": 2175
},
{
"epoch": 0.75,
"learning_rate": 6.177362775344615e-06,
"loss": 0.7706,
"step": 2176
},
{
"epoch": 0.75,
"learning_rate": 6.161222620449079e-06,
"loss": 0.7634,
"step": 2177
},
{
"epoch": 0.75,
"learning_rate": 6.145099738514466e-06,
"loss": 0.7693,
"step": 2178
},
{
"epoch": 0.75,
"learning_rate": 6.128994149664651e-06,
"loss": 0.7591,
"step": 2179
},
{
"epoch": 0.75,
"learning_rate": 6.112905874001951e-06,
"loss": 0.7724,
"step": 2180
},
{
"epoch": 0.75,
"learning_rate": 6.096834931607034e-06,
"loss": 0.3915,
"step": 2181
},
{
"epoch": 0.75,
"learning_rate": 6.0807813425389575e-06,
"loss": 0.7384,
"step": 2182
},
{
"epoch": 0.75,
"learning_rate": 6.064745126835112e-06,
"loss": 0.6934,
"step": 2183
},
{
"epoch": 0.75,
"learning_rate": 6.0487263045112055e-06,
"loss": 0.3797,
"step": 2184
},
{
"epoch": 0.75,
"learning_rate": 6.032724895561251e-06,
"loss": 0.775,
"step": 2185
},
{
"epoch": 0.75,
"learning_rate": 6.016740919957485e-06,
"loss": 0.7665,
"step": 2186
},
{
"epoch": 0.75,
"learning_rate": 6.000774397650442e-06,
"loss": 0.7552,
"step": 2187
},
{
"epoch": 0.75,
"learning_rate": 5.984825348568812e-06,
"loss": 0.7497,
"step": 2188
},
{
"epoch": 0.76,
"learning_rate": 5.968893792619528e-06,
"loss": 0.7057,
"step": 2189
},
{
"epoch": 0.76,
"learning_rate": 5.952979749687664e-06,
"loss": 0.721,
"step": 2190
},
{
"epoch": 0.76,
"learning_rate": 5.937083239636418e-06,
"loss": 0.7866,
"step": 2191
},
{
"epoch": 0.76,
"learning_rate": 5.9212042823071445e-06,
"loss": 0.7727,
"step": 2192
},
{
"epoch": 0.76,
"learning_rate": 5.905342897519262e-06,
"loss": 0.7829,
"step": 2193
},
{
"epoch": 0.76,
"learning_rate": 5.88949910507026e-06,
"loss": 0.7291,
"step": 2194
},
{
"epoch": 0.76,
"learning_rate": 5.873672924735672e-06,
"loss": 0.8274,
"step": 2195
},
{
"epoch": 0.76,
"learning_rate": 5.857864376269051e-06,
"loss": 0.7494,
"step": 2196
},
{
"epoch": 0.76,
"learning_rate": 5.8420734794019396e-06,
"loss": 0.7269,
"step": 2197
},
{
"epoch": 0.76,
"learning_rate": 5.826300253843851e-06,
"loss": 0.7598,
"step": 2198
},
{
"epoch": 0.76,
"learning_rate": 5.810544719282239e-06,
"loss": 0.7585,
"step": 2199
},
{
"epoch": 0.76,
"learning_rate": 5.794806895382476e-06,
"loss": 0.7757,
"step": 2200
},
{
"epoch": 0.76,
"learning_rate": 5.779086801787834e-06,
"loss": 0.7395,
"step": 2201
},
{
"epoch": 0.76,
"learning_rate": 5.763384458119443e-06,
"loss": 0.7627,
"step": 2202
},
{
"epoch": 0.76,
"learning_rate": 5.7476998839763035e-06,
"loss": 0.7506,
"step": 2203
},
{
"epoch": 0.76,
"learning_rate": 5.732033098935204e-06,
"loss": 0.757,
"step": 2204
},
{
"epoch": 0.76,
"learning_rate": 5.716384122550742e-06,
"loss": 0.7439,
"step": 2205
},
{
"epoch": 0.76,
"learning_rate": 5.700752974355312e-06,
"loss": 0.7592,
"step": 2206
},
{
"epoch": 0.76,
"learning_rate": 5.6851396738590085e-06,
"loss": 0.7606,
"step": 2207
},
{
"epoch": 0.76,
"learning_rate": 5.669544240549698e-06,
"loss": 0.7463,
"step": 2208
},
{
"epoch": 0.76,
"learning_rate": 5.6539666938929e-06,
"loss": 0.3955,
"step": 2209
},
{
"epoch": 0.76,
"learning_rate": 5.638407053331853e-06,
"loss": 0.7542,
"step": 2210
},
{
"epoch": 0.76,
"learning_rate": 5.622865338287413e-06,
"loss": 0.7114,
"step": 2211
},
{
"epoch": 0.76,
"learning_rate": 5.607341568158078e-06,
"loss": 0.7597,
"step": 2212
},
{
"epoch": 0.76,
"learning_rate": 5.591835762319946e-06,
"loss": 0.6961,
"step": 2213
},
{
"epoch": 0.76,
"learning_rate": 5.5763479401266765e-06,
"loss": 0.7868,
"step": 2214
},
{
"epoch": 0.76,
"learning_rate": 5.560878120909512e-06,
"loss": 0.753,
"step": 2215
},
{
"epoch": 0.76,
"learning_rate": 5.5454263239772035e-06,
"loss": 0.7684,
"step": 2216
},
{
"epoch": 0.76,
"learning_rate": 5.529992568616012e-06,
"loss": 0.7692,
"step": 2217
},
{
"epoch": 0.77,
"learning_rate": 5.514576874089683e-06,
"loss": 0.7661,
"step": 2218
},
{
"epoch": 0.77,
"learning_rate": 5.499179259639416e-06,
"loss": 0.7781,
"step": 2219
},
{
"epoch": 0.77,
"learning_rate": 5.483799744483842e-06,
"loss": 0.7644,
"step": 2220
},
{
"epoch": 0.77,
"learning_rate": 5.4684383478190075e-06,
"loss": 0.7399,
"step": 2221
},
{
"epoch": 0.77,
"learning_rate": 5.453095088818338e-06,
"loss": 0.7489,
"step": 2222
},
{
"epoch": 0.77,
"learning_rate": 5.437769986632622e-06,
"loss": 0.7629,
"step": 2223
},
{
"epoch": 0.77,
"learning_rate": 5.422463060389997e-06,
"loss": 0.7415,
"step": 2224
},
{
"epoch": 0.77,
"learning_rate": 5.407174329195886e-06,
"loss": 0.8038,
"step": 2225
},
{
"epoch": 0.77,
"learning_rate": 5.391903812133039e-06,
"loss": 0.772,
"step": 2226
},
{
"epoch": 0.77,
"learning_rate": 5.376651528261436e-06,
"loss": 0.7599,
"step": 2227
},
{
"epoch": 0.77,
"learning_rate": 5.361417496618315e-06,
"loss": 0.7497,
"step": 2228
},
{
"epoch": 0.77,
"learning_rate": 5.346201736218153e-06,
"loss": 0.7751,
"step": 2229
},
{
"epoch": 0.77,
"learning_rate": 5.331004266052573e-06,
"loss": 0.7869,
"step": 2230
},
{
"epoch": 0.77,
"learning_rate": 5.315825105090424e-06,
"loss": 0.7363,
"step": 2231
},
{
"epoch": 0.77,
"learning_rate": 5.300664272277654e-06,
"loss": 0.8242,
"step": 2232
},
{
"epoch": 0.77,
"learning_rate": 5.285521786537368e-06,
"loss": 0.7351,
"step": 2233
},
{
"epoch": 0.77,
"learning_rate": 5.2703976667697575e-06,
"loss": 0.7639,
"step": 2234
},
{
"epoch": 0.77,
"learning_rate": 5.255291931852089e-06,
"loss": 0.7879,
"step": 2235
},
{
"epoch": 0.77,
"learning_rate": 5.240204600638687e-06,
"loss": 0.7437,
"step": 2236
},
{
"epoch": 0.77,
"learning_rate": 5.225135691960906e-06,
"loss": 0.4028,
"step": 2237
},
{
"epoch": 0.77,
"learning_rate": 5.2100852246270975e-06,
"loss": 0.7559,
"step": 2238
},
{
"epoch": 0.77,
"learning_rate": 5.195053217422603e-06,
"loss": 0.7778,
"step": 2239
},
{
"epoch": 0.77,
"learning_rate": 5.180039689109722e-06,
"loss": 0.7614,
"step": 2240
},
{
"epoch": 0.77,
"learning_rate": 5.1650446584276895e-06,
"loss": 0.7164,
"step": 2241
},
{
"epoch": 0.77,
"learning_rate": 5.150068144092648e-06,
"loss": 0.7773,
"step": 2242
},
{
"epoch": 0.77,
"learning_rate": 5.135110164797637e-06,
"loss": 0.7211,
"step": 2243
},
{
"epoch": 0.77,
"learning_rate": 5.120170739212553e-06,
"loss": 0.7827,
"step": 2244
},
{
"epoch": 0.77,
"learning_rate": 5.105249885984141e-06,
"loss": 0.754,
"step": 2245
},
{
"epoch": 0.77,
"learning_rate": 5.090347623735954e-06,
"loss": 0.8102,
"step": 2246
},
{
"epoch": 0.78,
"learning_rate": 5.075463971068366e-06,
"loss": 0.734,
"step": 2247
},
{
"epoch": 0.78,
"learning_rate": 5.060598946558484e-06,
"loss": 0.7665,
"step": 2248
},
{
"epoch": 0.78,
"learning_rate": 5.0457525687602095e-06,
"loss": 0.8034,
"step": 2249
},
{
"epoch": 0.78,
"learning_rate": 5.0309248562041205e-06,
"loss": 0.8154,
"step": 2250
},
{
"epoch": 0.78,
"learning_rate": 5.016115827397545e-06,
"loss": 0.7914,
"step": 2251
},
{
"epoch": 0.78,
"learning_rate": 5.001325500824468e-06,
"loss": 0.8005,
"step": 2252
},
{
"epoch": 0.78,
"learning_rate": 4.986553894945512e-06,
"loss": 0.7549,
"step": 2253
},
{
"epoch": 0.78,
"learning_rate": 4.971801028197982e-06,
"loss": 0.7759,
"step": 2254
},
{
"epoch": 0.78,
"learning_rate": 4.957066918995743e-06,
"loss": 0.7658,
"step": 2255
},
{
"epoch": 0.78,
"learning_rate": 4.942351585729284e-06,
"loss": 0.7704,
"step": 2256
},
{
"epoch": 0.78,
"learning_rate": 4.927655046765638e-06,
"loss": 0.7659,
"step": 2257
},
{
"epoch": 0.78,
"learning_rate": 4.912977320448391e-06,
"loss": 0.7996,
"step": 2258
},
{
"epoch": 0.78,
"learning_rate": 4.898318425097641e-06,
"loss": 0.7986,
"step": 2259
},
{
"epoch": 0.78,
"learning_rate": 4.8836783790099865e-06,
"loss": 0.7495,
"step": 2260
},
{
"epoch": 0.78,
"learning_rate": 4.869057200458496e-06,
"loss": 0.7509,
"step": 2261
},
{
"epoch": 0.78,
"learning_rate": 4.85445490769269e-06,
"loss": 0.7497,
"step": 2262
},
{
"epoch": 0.78,
"learning_rate": 4.839871518938513e-06,
"loss": 0.7924,
"step": 2263
},
{
"epoch": 0.78,
"learning_rate": 4.8253070523983155e-06,
"loss": 0.7643,
"step": 2264
},
{
"epoch": 0.78,
"learning_rate": 4.810761526250849e-06,
"loss": 0.712,
"step": 2265
},
{
"epoch": 0.78,
"learning_rate": 4.796234958651191e-06,
"loss": 0.746,
"step": 2266
},
{
"epoch": 0.78,
"learning_rate": 4.781727367730775e-06,
"loss": 0.7977,
"step": 2267
},
{
"epoch": 0.78,
"learning_rate": 4.767238771597347e-06,
"loss": 0.7748,
"step": 2268
},
{
"epoch": 0.78,
"learning_rate": 4.752769188334941e-06,
"loss": 0.7783,
"step": 2269
},
{
"epoch": 0.78,
"learning_rate": 4.738318636003874e-06,
"loss": 0.7277,
"step": 2270
},
{
"epoch": 0.78,
"learning_rate": 4.723887132640679e-06,
"loss": 0.7461,
"step": 2271
},
{
"epoch": 0.78,
"learning_rate": 4.709474696258154e-06,
"loss": 0.7017,
"step": 2272
},
{
"epoch": 0.78,
"learning_rate": 4.695081344845254e-06,
"loss": 0.7231,
"step": 2273
},
{
"epoch": 0.78,
"learning_rate": 4.68070709636715e-06,
"loss": 0.7736,
"step": 2274
},
{
"epoch": 0.78,
"learning_rate": 4.666351968765155e-06,
"loss": 0.7414,
"step": 2275
},
{
"epoch": 0.79,
"learning_rate": 4.6520159799566984e-06,
"loss": 0.7567,
"step": 2276
},
{
"epoch": 0.79,
"learning_rate": 4.637699147835359e-06,
"loss": 0.8163,
"step": 2277
},
{
"epoch": 0.79,
"learning_rate": 4.623401490270778e-06,
"loss": 0.737,
"step": 2278
},
{
"epoch": 0.79,
"learning_rate": 4.6091230251086706e-06,
"loss": 0.7145,
"step": 2279
},
{
"epoch": 0.79,
"learning_rate": 4.594863770170794e-06,
"loss": 0.7341,
"step": 2280
},
{
"epoch": 0.79,
"learning_rate": 4.580623743254935e-06,
"loss": 0.6692,
"step": 2281
},
{
"epoch": 0.79,
"learning_rate": 4.566402962134875e-06,
"loss": 0.7374,
"step": 2282
},
{
"epoch": 0.79,
"learning_rate": 4.552201444560373e-06,
"loss": 0.8096,
"step": 2283
},
{
"epoch": 0.79,
"learning_rate": 4.538019208257151e-06,
"loss": 0.7346,
"step": 2284
},
{
"epoch": 0.79,
"learning_rate": 4.523856270926858e-06,
"loss": 0.7327,
"step": 2285
},
{
"epoch": 0.79,
"learning_rate": 4.509712650247058e-06,
"loss": 0.4198,
"step": 2286
},
{
"epoch": 0.79,
"learning_rate": 4.495588363871197e-06,
"loss": 0.7177,
"step": 2287
},
{
"epoch": 0.79,
"learning_rate": 4.481483429428615e-06,
"loss": 0.7669,
"step": 2288
},
{
"epoch": 0.79,
"learning_rate": 4.467397864524461e-06,
"loss": 0.7684,
"step": 2289
},
{
"epoch": 0.79,
"learning_rate": 4.45333168673973e-06,
"loss": 0.7389,
"step": 2290
},
{
"epoch": 0.79,
"learning_rate": 4.439284913631215e-06,
"loss": 0.7474,
"step": 2291
},
{
"epoch": 0.79,
"learning_rate": 4.425257562731482e-06,
"loss": 0.7018,
"step": 2292
},
{
"epoch": 0.79,
"learning_rate": 4.4112496515488765e-06,
"loss": 0.7392,
"step": 2293
},
{
"epoch": 0.79,
"learning_rate": 4.397261197567446e-06,
"loss": 0.7487,
"step": 2294
},
{
"epoch": 0.79,
"learning_rate": 4.383292218246988e-06,
"loss": 0.7562,
"step": 2295
},
{
"epoch": 0.79,
"learning_rate": 4.369342731022967e-06,
"loss": 0.8109,
"step": 2296
},
{
"epoch": 0.79,
"learning_rate": 4.355412753306529e-06,
"loss": 0.7711,
"step": 2297
},
{
"epoch": 0.79,
"learning_rate": 4.341502302484472e-06,
"loss": 0.7314,
"step": 2298
},
{
"epoch": 0.79,
"learning_rate": 4.3276113959192025e-06,
"loss": 0.7357,
"step": 2299
},
{
"epoch": 0.79,
"learning_rate": 4.31374005094876e-06,
"loss": 0.7612,
"step": 2300
},
{
"epoch": 0.79,
"learning_rate": 4.299888284886751e-06,
"loss": 0.7581,
"step": 2301
},
{
"epoch": 0.79,
"learning_rate": 4.286056115022348e-06,
"loss": 0.7873,
"step": 2302
},
{
"epoch": 0.79,
"learning_rate": 4.272243558620264e-06,
"loss": 0.7329,
"step": 2303
},
{
"epoch": 0.79,
"learning_rate": 4.258450632920735e-06,
"loss": 0.3897,
"step": 2304
},
{
"epoch": 0.8,
"learning_rate": 4.244677355139488e-06,
"loss": 0.7618,
"step": 2305
},
{
"epoch": 0.8,
"learning_rate": 4.230923742467734e-06,
"loss": 0.7763,
"step": 2306
},
{
"epoch": 0.8,
"learning_rate": 4.217189812072131e-06,
"loss": 0.7735,
"step": 2307
},
{
"epoch": 0.8,
"learning_rate": 4.203475581094771e-06,
"loss": 0.7604,
"step": 2308
},
{
"epoch": 0.8,
"learning_rate": 4.189781066653178e-06,
"loss": 0.3789,
"step": 2309
},
{
"epoch": 0.8,
"learning_rate": 4.176106285840229e-06,
"loss": 0.8037,
"step": 2310
},
{
"epoch": 0.8,
"learning_rate": 4.1624512557242134e-06,
"loss": 0.7438,
"step": 2311
},
{
"epoch": 0.8,
"learning_rate": 4.148815993348727e-06,
"loss": 0.7669,
"step": 2312
},
{
"epoch": 0.8,
"learning_rate": 4.135200515732716e-06,
"loss": 0.7339,
"step": 2313
},
{
"epoch": 0.8,
"learning_rate": 4.121604839870443e-06,
"loss": 0.7549,
"step": 2314
},
{
"epoch": 0.8,
"learning_rate": 4.10802898273142e-06,
"loss": 0.7887,
"step": 2315
},
{
"epoch": 0.8,
"learning_rate": 4.094472961260463e-06,
"loss": 0.818,
"step": 2316
},
{
"epoch": 0.8,
"learning_rate": 4.080936792377586e-06,
"loss": 0.3734,
"step": 2317
},
{
"epoch": 0.8,
"learning_rate": 4.067420492978065e-06,
"loss": 0.7211,
"step": 2318
},
{
"epoch": 0.8,
"learning_rate": 4.053924079932352e-06,
"loss": 0.7757,
"step": 2319
},
{
"epoch": 0.8,
"learning_rate": 4.040447570086084e-06,
"loss": 0.7554,
"step": 2320
},
{
"epoch": 0.8,
"learning_rate": 4.026990980260055e-06,
"loss": 0.7879,
"step": 2321
},
{
"epoch": 0.8,
"learning_rate": 4.013554327250195e-06,
"loss": 0.75,
"step": 2322
},
{
"epoch": 0.8,
"learning_rate": 4.000137627827554e-06,
"loss": 0.7848,
"step": 2323
},
{
"epoch": 0.8,
"learning_rate": 3.986740898738271e-06,
"loss": 0.7975,
"step": 2324
},
{
"epoch": 0.8,
"learning_rate": 3.973364156703563e-06,
"loss": 0.754,
"step": 2325
},
{
"epoch": 0.8,
"learning_rate": 3.960007418419695e-06,
"loss": 0.7513,
"step": 2326
},
{
"epoch": 0.8,
"learning_rate": 3.946670700557971e-06,
"loss": 0.7675,
"step": 2327
},
{
"epoch": 0.8,
"learning_rate": 3.9333540197647035e-06,
"loss": 0.753,
"step": 2328
},
{
"epoch": 0.8,
"learning_rate": 3.920057392661192e-06,
"loss": 0.7495,
"step": 2329
},
{
"epoch": 0.8,
"learning_rate": 3.9067808358437105e-06,
"loss": 0.7198,
"step": 2330
},
{
"epoch": 0.8,
"learning_rate": 3.893524365883477e-06,
"loss": 0.7508,
"step": 2331
},
{
"epoch": 0.8,
"learning_rate": 3.880287999326655e-06,
"loss": 0.7626,
"step": 2332
},
{
"epoch": 0.8,
"learning_rate": 3.867071752694282e-06,
"loss": 0.7446,
"step": 2333
},
{
"epoch": 0.81,
"learning_rate": 3.853875642482328e-06,
"loss": 0.7193,
"step": 2334
},
{
"epoch": 0.81,
"learning_rate": 3.840699685161575e-06,
"loss": 0.7424,
"step": 2335
},
{
"epoch": 0.81,
"learning_rate": 3.8275438971777055e-06,
"loss": 0.7739,
"step": 2336
},
{
"epoch": 0.81,
"learning_rate": 3.8144082949511973e-06,
"loss": 0.7524,
"step": 2337
},
{
"epoch": 0.81,
"learning_rate": 3.8012928948773243e-06,
"loss": 0.7575,
"step": 2338
},
{
"epoch": 0.81,
"learning_rate": 3.7881977133261806e-06,
"loss": 0.7286,
"step": 2339
},
{
"epoch": 0.81,
"learning_rate": 3.7751227666425807e-06,
"loss": 0.7242,
"step": 2340
},
{
"epoch": 0.81,
"learning_rate": 3.762068071146123e-06,
"loss": 0.7843,
"step": 2341
},
{
"epoch": 0.81,
"learning_rate": 3.7490336431311056e-06,
"loss": 0.7635,
"step": 2342
},
{
"epoch": 0.81,
"learning_rate": 3.7360194988665364e-06,
"loss": 0.7206,
"step": 2343
},
{
"epoch": 0.81,
"learning_rate": 3.723025654596102e-06,
"loss": 0.7413,
"step": 2344
},
{
"epoch": 0.81,
"learning_rate": 3.7100521265381573e-06,
"loss": 0.7486,
"step": 2345
},
{
"epoch": 0.81,
"learning_rate": 3.6970989308856965e-06,
"loss": 0.7722,
"step": 2346
},
{
"epoch": 0.81,
"learning_rate": 3.684166083806333e-06,
"loss": 0.8035,
"step": 2347
},
{
"epoch": 0.81,
"learning_rate": 3.6712536014422885e-06,
"loss": 0.7271,
"step": 2348
},
{
"epoch": 0.81,
"learning_rate": 3.6583614999103544e-06,
"loss": 0.7771,
"step": 2349
},
{
"epoch": 0.81,
"learning_rate": 3.645489795301911e-06,
"loss": 0.3837,
"step": 2350
},
{
"epoch": 0.81,
"learning_rate": 3.632638503682844e-06,
"loss": 0.7687,
"step": 2351
},
{
"epoch": 0.81,
"learning_rate": 3.61980764109358e-06,
"loss": 0.7436,
"step": 2352
},
{
"epoch": 0.81,
"learning_rate": 3.606997223549049e-06,
"loss": 0.7885,
"step": 2353
},
{
"epoch": 0.81,
"learning_rate": 3.5942072670386497e-06,
"loss": 0.781,
"step": 2354
},
{
"epoch": 0.81,
"learning_rate": 3.581437787526265e-06,
"loss": 0.8199,
"step": 2355
},
{
"epoch": 0.81,
"learning_rate": 3.568688800950186e-06,
"loss": 0.766,
"step": 2356
},
{
"epoch": 0.81,
"learning_rate": 3.5559603232231645e-06,
"loss": 0.7615,
"step": 2357
},
{
"epoch": 0.81,
"learning_rate": 3.543252370232313e-06,
"loss": 0.816,
"step": 2358
},
{
"epoch": 0.81,
"learning_rate": 3.5305649578391623e-06,
"loss": 0.7539,
"step": 2359
},
{
"epoch": 0.81,
"learning_rate": 3.5178981018795887e-06,
"loss": 0.7509,
"step": 2360
},
{
"epoch": 0.81,
"learning_rate": 3.505251818163795e-06,
"loss": 0.7506,
"step": 2361
},
{
"epoch": 0.81,
"learning_rate": 3.492626122476341e-06,
"loss": 0.721,
"step": 2362
},
{
"epoch": 0.82,
"learning_rate": 3.4800210305760662e-06,
"loss": 0.7549,
"step": 2363
},
{
"epoch": 0.82,
"learning_rate": 3.4674365581961e-06,
"loss": 0.7299,
"step": 2364
},
{
"epoch": 0.82,
"learning_rate": 3.4548727210438316e-06,
"loss": 0.7729,
"step": 2365
},
{
"epoch": 0.82,
"learning_rate": 3.4423295348008966e-06,
"loss": 0.7867,
"step": 2366
},
{
"epoch": 0.82,
"learning_rate": 3.429807015123159e-06,
"loss": 0.7689,
"step": 2367
},
{
"epoch": 0.82,
"learning_rate": 3.4173051776406817e-06,
"loss": 0.7293,
"step": 2368
},
{
"epoch": 0.82,
"learning_rate": 3.4048240379577146e-06,
"loss": 0.7457,
"step": 2369
},
{
"epoch": 0.82,
"learning_rate": 3.392363611652676e-06,
"loss": 0.7328,
"step": 2370
},
{
"epoch": 0.82,
"learning_rate": 3.3799239142781272e-06,
"loss": 0.8162,
"step": 2371
},
{
"epoch": 0.82,
"learning_rate": 3.3675049613607548e-06,
"loss": 0.7418,
"step": 2372
},
{
"epoch": 0.82,
"learning_rate": 3.3551067684013706e-06,
"loss": 0.8268,
"step": 2373
},
{
"epoch": 0.82,
"learning_rate": 3.342729350874845e-06,
"loss": 0.7245,
"step": 2374
},
{
"epoch": 0.82,
"learning_rate": 3.3303727242301377e-06,
"loss": 0.7899,
"step": 2375
},
{
"epoch": 0.82,
"learning_rate": 3.318036903890256e-06,
"loss": 0.7455,
"step": 2376
},
{
"epoch": 0.82,
"learning_rate": 3.3057219052522304e-06,
"loss": 0.7062,
"step": 2377
},
{
"epoch": 0.82,
"learning_rate": 3.2934277436871187e-06,
"loss": 0.7234,
"step": 2378
},
{
"epoch": 0.82,
"learning_rate": 3.281154434539939e-06,
"loss": 0.81,
"step": 2379
},
{
"epoch": 0.82,
"learning_rate": 3.2689019931297228e-06,
"loss": 0.7622,
"step": 2380
},
{
"epoch": 0.82,
"learning_rate": 3.2566704347494295e-06,
"loss": 0.7986,
"step": 2381
},
{
"epoch": 0.82,
"learning_rate": 3.2444597746659534e-06,
"loss": 0.7341,
"step": 2382
},
{
"epoch": 0.82,
"learning_rate": 3.232270028120121e-06,
"loss": 0.8244,
"step": 2383
},
{
"epoch": 0.82,
"learning_rate": 3.220101210326627e-06,
"loss": 0.7241,
"step": 2384
},
{
"epoch": 0.82,
"learning_rate": 3.207953336474077e-06,
"loss": 0.3982,
"step": 2385
},
{
"epoch": 0.82,
"learning_rate": 3.1958264217249145e-06,
"loss": 0.7312,
"step": 2386
},
{
"epoch": 0.82,
"learning_rate": 3.1837204812154265e-06,
"loss": 0.7439,
"step": 2387
},
{
"epoch": 0.82,
"learning_rate": 3.1716355300557256e-06,
"loss": 0.7646,
"step": 2388
},
{
"epoch": 0.82,
"learning_rate": 3.159571583329719e-06,
"loss": 0.7799,
"step": 2389
},
{
"epoch": 0.82,
"learning_rate": 3.1475286560951024e-06,
"loss": 0.7645,
"step": 2390
},
{
"epoch": 0.82,
"learning_rate": 3.1355067633833357e-06,
"loss": 0.7473,
"step": 2391
},
{
"epoch": 0.83,
"learning_rate": 3.1235059201996233e-06,
"loss": 0.7688,
"step": 2392
},
{
"epoch": 0.83,
"learning_rate": 3.111526141522896e-06,
"loss": 0.7518,
"step": 2393
},
{
"epoch": 0.83,
"learning_rate": 3.099567442305793e-06,
"loss": 0.7724,
"step": 2394
},
{
"epoch": 0.83,
"learning_rate": 3.087629837474637e-06,
"loss": 0.7811,
"step": 2395
},
{
"epoch": 0.83,
"learning_rate": 3.075713341929445e-06,
"loss": 0.784,
"step": 2396
},
{
"epoch": 0.83,
"learning_rate": 3.0638179705438544e-06,
"loss": 0.7534,
"step": 2397
},
{
"epoch": 0.83,
"learning_rate": 3.0519437381651507e-06,
"loss": 0.8137,
"step": 2398
},
{
"epoch": 0.83,
"learning_rate": 3.0400906596142476e-06,
"loss": 0.7674,
"step": 2399
},
{
"epoch": 0.83,
"learning_rate": 3.0282587496856262e-06,
"loss": 0.7603,
"step": 2400
},
{
"epoch": 0.83,
"learning_rate": 3.0164480231473823e-06,
"loss": 0.7374,
"step": 2401
},
{
"epoch": 0.83,
"learning_rate": 3.0046584947411308e-06,
"loss": 0.7414,
"step": 2402
},
{
"epoch": 0.83,
"learning_rate": 2.992890179182062e-06,
"loss": 0.7624,
"step": 2403
},
{
"epoch": 0.83,
"learning_rate": 2.9811430911588757e-06,
"loss": 0.7464,
"step": 2404
},
{
"epoch": 0.83,
"learning_rate": 2.9694172453337743e-06,
"loss": 0.3932,
"step": 2405
},
{
"epoch": 0.83,
"learning_rate": 2.9577126563424506e-06,
"loss": 0.7455,
"step": 2406
},
{
"epoch": 0.83,
"learning_rate": 2.946029338794063e-06,
"loss": 0.7769,
"step": 2407
},
{
"epoch": 0.83,
"learning_rate": 2.93436730727122e-06,
"loss": 0.7518,
"step": 2408
},
{
"epoch": 0.83,
"learning_rate": 2.922726576329966e-06,
"loss": 0.7469,
"step": 2409
},
{
"epoch": 0.83,
"learning_rate": 2.9111071604997555e-06,
"loss": 0.7494,
"step": 2410
},
{
"epoch": 0.83,
"learning_rate": 2.8995090742834355e-06,
"loss": 0.7217,
"step": 2411
},
{
"epoch": 0.83,
"learning_rate": 2.887932332157237e-06,
"loss": 0.7625,
"step": 2412
},
{
"epoch": 0.83,
"learning_rate": 2.8763769485707447e-06,
"loss": 0.75,
"step": 2413
},
{
"epoch": 0.83,
"learning_rate": 2.864842937946888e-06,
"loss": 0.7725,
"step": 2414
},
{
"epoch": 0.83,
"learning_rate": 2.853330314681917e-06,
"loss": 0.7401,
"step": 2415
},
{
"epoch": 0.83,
"learning_rate": 2.841839093145382e-06,
"loss": 0.7787,
"step": 2416
},
{
"epoch": 0.83,
"learning_rate": 2.8303692876801434e-06,
"loss": 0.8015,
"step": 2417
},
{
"epoch": 0.83,
"learning_rate": 2.818920912602294e-06,
"loss": 0.7012,
"step": 2418
},
{
"epoch": 0.83,
"learning_rate": 2.8074939822012192e-06,
"loss": 0.7212,
"step": 2419
},
{
"epoch": 0.83,
"learning_rate": 2.7960885107394964e-06,
"loss": 0.7539,
"step": 2420
},
{
"epoch": 0.84,
"learning_rate": 2.784704512452954e-06,
"loss": 0.7739,
"step": 2421
},
{
"epoch": 0.84,
"learning_rate": 2.773342001550603e-06,
"loss": 0.7779,
"step": 2422
},
{
"epoch": 0.84,
"learning_rate": 2.762000992214626e-06,
"loss": 0.7375,
"step": 2423
},
{
"epoch": 0.84,
"learning_rate": 2.7506814986003937e-06,
"loss": 0.7582,
"step": 2424
},
{
"epoch": 0.84,
"learning_rate": 2.7393835348363885e-06,
"loss": 0.3892,
"step": 2425
},
{
"epoch": 0.84,
"learning_rate": 2.728107115024252e-06,
"loss": 0.7472,
"step": 2426
},
{
"epoch": 0.84,
"learning_rate": 2.71685225323872e-06,
"loss": 0.7832,
"step": 2427
},
{
"epoch": 0.84,
"learning_rate": 2.7056189635276162e-06,
"loss": 0.7695,
"step": 2428
},
{
"epoch": 0.84,
"learning_rate": 2.694407259911851e-06,
"loss": 0.7765,
"step": 2429
},
{
"epoch": 0.84,
"learning_rate": 2.6832171563853805e-06,
"loss": 0.7398,
"step": 2430
},
{
"epoch": 0.84,
"learning_rate": 2.6720486669152103e-06,
"loss": 0.715,
"step": 2431
},
{
"epoch": 0.84,
"learning_rate": 2.6609018054413625e-06,
"loss": 0.7717,
"step": 2432
},
{
"epoch": 0.84,
"learning_rate": 2.6497765858768643e-06,
"loss": 0.7545,
"step": 2433
},
{
"epoch": 0.84,
"learning_rate": 2.6386730221077295e-06,
"loss": 0.7706,
"step": 2434
},
{
"epoch": 0.84,
"learning_rate": 2.6275911279929544e-06,
"loss": 0.7629,
"step": 2435
},
{
"epoch": 0.84,
"learning_rate": 2.616530917364468e-06,
"loss": 0.7369,
"step": 2436
},
{
"epoch": 0.84,
"learning_rate": 2.6054924040271477e-06,
"loss": 0.7205,
"step": 2437
},
{
"epoch": 0.84,
"learning_rate": 2.594475601758786e-06,
"loss": 0.8138,
"step": 2438
},
{
"epoch": 0.84,
"learning_rate": 2.5834805243100738e-06,
"loss": 0.8128,
"step": 2439
},
{
"epoch": 0.84,
"learning_rate": 2.5725071854046e-06,
"loss": 0.7462,
"step": 2440
},
{
"epoch": 0.84,
"learning_rate": 2.5615555987387964e-06,
"loss": 0.7279,
"step": 2441
},
{
"epoch": 0.84,
"learning_rate": 2.55062577798197e-06,
"loss": 0.7511,
"step": 2442
},
{
"epoch": 0.84,
"learning_rate": 2.539717736776237e-06,
"loss": 0.7472,
"step": 2443
},
{
"epoch": 0.84,
"learning_rate": 2.5288314887365474e-06,
"loss": 0.7861,
"step": 2444
},
{
"epoch": 0.84,
"learning_rate": 2.517967047450649e-06,
"loss": 0.7547,
"step": 2445
},
{
"epoch": 0.84,
"learning_rate": 2.5071244264790484e-06,
"loss": 0.7679,
"step": 2446
},
{
"epoch": 0.84,
"learning_rate": 2.496303639355051e-06,
"loss": 0.7534,
"step": 2447
},
{
"epoch": 0.84,
"learning_rate": 2.4855046995846844e-06,
"loss": 0.7056,
"step": 2448
},
{
"epoch": 0.84,
"learning_rate": 2.47472762064672e-06,
"loss": 0.7363,
"step": 2449
},
{
"epoch": 0.85,
"learning_rate": 2.463972415992637e-06,
"loss": 0.7478,
"step": 2450
},
{
"epoch": 0.85,
"learning_rate": 2.4532390990466183e-06,
"loss": 0.3797,
"step": 2451
},
{
"epoch": 0.85,
"learning_rate": 2.44252768320552e-06,
"loss": 0.7417,
"step": 2452
},
{
"epoch": 0.85,
"learning_rate": 2.431838181838868e-06,
"loss": 0.7561,
"step": 2453
},
{
"epoch": 0.85,
"learning_rate": 2.4211706082888343e-06,
"loss": 0.7565,
"step": 2454
},
{
"epoch": 0.85,
"learning_rate": 2.410524975870221e-06,
"loss": 0.7561,
"step": 2455
},
{
"epoch": 0.85,
"learning_rate": 2.3999012978704416e-06,
"loss": 0.777,
"step": 2456
},
{
"epoch": 0.85,
"learning_rate": 2.3892995875495097e-06,
"loss": 0.3859,
"step": 2457
},
{
"epoch": 0.85,
"learning_rate": 2.3787198581400285e-06,
"loss": 0.7609,
"step": 2458
},
{
"epoch": 0.85,
"learning_rate": 2.368162122847144e-06,
"loss": 0.6973,
"step": 2459
},
{
"epoch": 0.85,
"learning_rate": 2.357626394848571e-06,
"loss": 0.8278,
"step": 2460
},
{
"epoch": 0.85,
"learning_rate": 2.3471126872945438e-06,
"loss": 0.3946,
"step": 2461
},
{
"epoch": 0.85,
"learning_rate": 2.3366210133078136e-06,
"loss": 0.7484,
"step": 2462
},
{
"epoch": 0.85,
"learning_rate": 2.3261513859836437e-06,
"loss": 0.7146,
"step": 2463
},
{
"epoch": 0.85,
"learning_rate": 2.315703818389752e-06,
"loss": 0.7605,
"step": 2464
},
{
"epoch": 0.85,
"learning_rate": 2.305278323566349e-06,
"loss": 0.7466,
"step": 2465
},
{
"epoch": 0.85,
"learning_rate": 2.2948749145260863e-06,
"loss": 0.7805,
"step": 2466
},
{
"epoch": 0.85,
"learning_rate": 2.2844936042540413e-06,
"loss": 0.7468,
"step": 2467
},
{
"epoch": 0.85,
"learning_rate": 2.27413440570772e-06,
"loss": 0.7864,
"step": 2468
},
{
"epoch": 0.85,
"learning_rate": 2.2637973318170124e-06,
"loss": 0.7407,
"step": 2469
},
{
"epoch": 0.85,
"learning_rate": 2.253482395484219e-06,
"loss": 0.7576,
"step": 2470
},
{
"epoch": 0.85,
"learning_rate": 2.243189609583991e-06,
"loss": 0.788,
"step": 2471
},
{
"epoch": 0.85,
"learning_rate": 2.2329189869633326e-06,
"loss": 0.7099,
"step": 2472
},
{
"epoch": 0.85,
"learning_rate": 2.222670540441596e-06,
"loss": 0.7328,
"step": 2473
},
{
"epoch": 0.85,
"learning_rate": 2.21244428281044e-06,
"loss": 0.4043,
"step": 2474
},
{
"epoch": 0.85,
"learning_rate": 2.2022402268338407e-06,
"loss": 0.8196,
"step": 2475
},
{
"epoch": 0.85,
"learning_rate": 2.1920583852480526e-06,
"loss": 0.7346,
"step": 2476
},
{
"epoch": 0.85,
"learning_rate": 2.1818987707616124e-06,
"loss": 0.7347,
"step": 2477
},
{
"epoch": 0.85,
"learning_rate": 2.17176139605531e-06,
"loss": 0.7338,
"step": 2478
},
{
"epoch": 0.86,
"learning_rate": 2.161646273782172e-06,
"loss": 0.7863,
"step": 2479
},
{
"epoch": 0.86,
"learning_rate": 2.1515534165674535e-06,
"loss": 0.7309,
"step": 2480
},
{
"epoch": 0.86,
"learning_rate": 2.1414828370086326e-06,
"loss": 0.7559,
"step": 2481
},
{
"epoch": 0.86,
"learning_rate": 2.1314345476753573e-06,
"loss": 0.7556,
"step": 2482
},
{
"epoch": 0.86,
"learning_rate": 2.121408561109466e-06,
"loss": 0.7237,
"step": 2483
},
{
"epoch": 0.86,
"learning_rate": 2.1114048898249708e-06,
"loss": 0.8124,
"step": 2484
},
{
"epoch": 0.86,
"learning_rate": 2.1014235463080036e-06,
"loss": 0.77,
"step": 2485
},
{
"epoch": 0.86,
"learning_rate": 2.091464543016861e-06,
"loss": 0.7508,
"step": 2486
},
{
"epoch": 0.86,
"learning_rate": 2.0815278923819228e-06,
"loss": 0.7502,
"step": 2487
},
{
"epoch": 0.86,
"learning_rate": 2.071613606805696e-06,
"loss": 0.7299,
"step": 2488
},
{
"epoch": 0.86,
"learning_rate": 2.0617216986627552e-06,
"loss": 0.7977,
"step": 2489
},
{
"epoch": 0.86,
"learning_rate": 2.051852180299756e-06,
"loss": 0.7678,
"step": 2490
},
{
"epoch": 0.86,
"learning_rate": 2.0420050640353973e-06,
"loss": 0.7541,
"step": 2491
},
{
"epoch": 0.86,
"learning_rate": 2.032180362160423e-06,
"loss": 0.7654,
"step": 2492
},
{
"epoch": 0.86,
"learning_rate": 2.0223780869376018e-06,
"loss": 0.7929,
"step": 2493
},
{
"epoch": 0.86,
"learning_rate": 2.012598250601705e-06,
"loss": 0.7943,
"step": 2494
},
{
"epoch": 0.86,
"learning_rate": 2.0028408653595032e-06,
"loss": 0.7753,
"step": 2495
},
{
"epoch": 0.86,
"learning_rate": 1.993105943389737e-06,
"loss": 0.7614,
"step": 2496
},
{
"epoch": 0.86,
"learning_rate": 1.9833934968431134e-06,
"loss": 0.7847,
"step": 2497
},
{
"epoch": 0.86,
"learning_rate": 1.9737035378422907e-06,
"loss": 0.7321,
"step": 2498
},
{
"epoch": 0.86,
"learning_rate": 1.9640360784818503e-06,
"loss": 0.7496,
"step": 2499
},
{
"epoch": 0.86,
"learning_rate": 1.9543911308282992e-06,
"loss": 0.7751,
"step": 2500
},
{
"epoch": 0.86,
"learning_rate": 1.9447687069200326e-06,
"loss": 0.7691,
"step": 2501
},
{
"epoch": 0.86,
"learning_rate": 1.935168818767359e-06,
"loss": 0.7634,
"step": 2502
},
{
"epoch": 0.86,
"learning_rate": 1.925591478352424e-06,
"loss": 0.7688,
"step": 2503
},
{
"epoch": 0.86,
"learning_rate": 1.9160366976292646e-06,
"loss": 0.7606,
"step": 2504
},
{
"epoch": 0.86,
"learning_rate": 1.9065044885237284e-06,
"loss": 0.6974,
"step": 2505
},
{
"epoch": 0.86,
"learning_rate": 1.8969948629335123e-06,
"loss": 0.7152,
"step": 2506
},
{
"epoch": 0.86,
"learning_rate": 1.8875078327281237e-06,
"loss": 0.7719,
"step": 2507
},
{
"epoch": 0.87,
"learning_rate": 1.8780434097488443e-06,
"loss": 0.7976,
"step": 2508
},
{
"epoch": 0.87,
"learning_rate": 1.8686016058087752e-06,
"loss": 0.7901,
"step": 2509
},
{
"epoch": 0.87,
"learning_rate": 1.8591824326927498e-06,
"loss": 0.7553,
"step": 2510
},
{
"epoch": 0.87,
"learning_rate": 1.8497859021573838e-06,
"loss": 0.759,
"step": 2511
},
{
"epoch": 0.87,
"learning_rate": 1.840412025931011e-06,
"loss": 0.7511,
"step": 2512
},
{
"epoch": 0.87,
"learning_rate": 1.831060815713699e-06,
"loss": 0.7919,
"step": 2513
},
{
"epoch": 0.87,
"learning_rate": 1.8217322831772221e-06,
"loss": 0.7529,
"step": 2514
},
{
"epoch": 0.87,
"learning_rate": 1.8124264399650493e-06,
"loss": 0.729,
"step": 2515
},
{
"epoch": 0.87,
"learning_rate": 1.8031432976923313e-06,
"loss": 0.7533,
"step": 2516
},
{
"epoch": 0.87,
"learning_rate": 1.7938828679458797e-06,
"loss": 0.7771,
"step": 2517
},
{
"epoch": 0.87,
"learning_rate": 1.7846451622841643e-06,
"loss": 0.7487,
"step": 2518
},
{
"epoch": 0.87,
"learning_rate": 1.775430192237284e-06,
"loss": 0.7061,
"step": 2519
},
{
"epoch": 0.87,
"learning_rate": 1.7662379693069742e-06,
"loss": 0.7296,
"step": 2520
},
{
"epoch": 0.87,
"learning_rate": 1.7570685049665548e-06,
"loss": 0.756,
"step": 2521
},
{
"epoch": 0.87,
"learning_rate": 1.747921810660962e-06,
"loss": 0.7659,
"step": 2522
},
{
"epoch": 0.87,
"learning_rate": 1.7387978978066988e-06,
"loss": 0.7178,
"step": 2523
},
{
"epoch": 0.87,
"learning_rate": 1.729696777791834e-06,
"loss": 0.7854,
"step": 2524
},
{
"epoch": 0.87,
"learning_rate": 1.7206184619760024e-06,
"loss": 0.785,
"step": 2525
},
{
"epoch": 0.87,
"learning_rate": 1.7115629616903474e-06,
"loss": 0.7439,
"step": 2526
},
{
"epoch": 0.87,
"learning_rate": 1.702530288237565e-06,
"loss": 0.7764,
"step": 2527
},
{
"epoch": 0.87,
"learning_rate": 1.6935204528918347e-06,
"loss": 0.7458,
"step": 2528
},
{
"epoch": 0.87,
"learning_rate": 1.68453346689885e-06,
"loss": 0.7899,
"step": 2529
},
{
"epoch": 0.87,
"learning_rate": 1.675569341475778e-06,
"loss": 0.7514,
"step": 2530
},
{
"epoch": 0.87,
"learning_rate": 1.6666280878112394e-06,
"loss": 0.6997,
"step": 2531
},
{
"epoch": 0.87,
"learning_rate": 1.6577097170653279e-06,
"loss": 0.7538,
"step": 2532
},
{
"epoch": 0.87,
"learning_rate": 1.6488142403695651e-06,
"loss": 0.7649,
"step": 2533
},
{
"epoch": 0.87,
"learning_rate": 1.6399416688268987e-06,
"loss": 0.7572,
"step": 2534
},
{
"epoch": 0.87,
"learning_rate": 1.631092013511686e-06,
"loss": 0.7062,
"step": 2535
},
{
"epoch": 0.87,
"learning_rate": 1.622265285469682e-06,
"loss": 0.7458,
"step": 2536
},
{
"epoch": 0.88,
"learning_rate": 1.613461495718025e-06,
"loss": 0.7861,
"step": 2537
},
{
"epoch": 0.88,
"learning_rate": 1.6046806552452254e-06,
"loss": 0.7592,
"step": 2538
},
{
"epoch": 0.88,
"learning_rate": 1.5959227750111471e-06,
"loss": 0.7509,
"step": 2539
},
{
"epoch": 0.88,
"learning_rate": 1.587187865946993e-06,
"loss": 0.77,
"step": 2540
},
{
"epoch": 0.88,
"learning_rate": 1.5784759389552994e-06,
"loss": 0.7284,
"step": 2541
},
{
"epoch": 0.88,
"learning_rate": 1.5697870049099106e-06,
"loss": 0.7362,
"step": 2542
},
{
"epoch": 0.88,
"learning_rate": 1.5611210746559868e-06,
"loss": 0.8011,
"step": 2543
},
{
"epoch": 0.88,
"learning_rate": 1.552478159009958e-06,
"loss": 0.7854,
"step": 2544
},
{
"epoch": 0.88,
"learning_rate": 1.5438582687595372e-06,
"loss": 0.7234,
"step": 2545
},
{
"epoch": 0.88,
"learning_rate": 1.5352614146636958e-06,
"loss": 0.3844,
"step": 2546
},
{
"epoch": 0.88,
"learning_rate": 1.5266876074526548e-06,
"loss": 0.7816,
"step": 2547
},
{
"epoch": 0.88,
"learning_rate": 1.5181368578278744e-06,
"loss": 0.748,
"step": 2548
},
{
"epoch": 0.88,
"learning_rate": 1.5096091764620168e-06,
"loss": 0.775,
"step": 2549
},
{
"epoch": 0.88,
"learning_rate": 1.5011045739989727e-06,
"loss": 0.7548,
"step": 2550
},
{
"epoch": 0.88,
"learning_rate": 1.4926230610538173e-06,
"loss": 0.7753,
"step": 2551
},
{
"epoch": 0.88,
"learning_rate": 1.4841646482128024e-06,
"loss": 0.771,
"step": 2552
},
{
"epoch": 0.88,
"learning_rate": 1.4757293460333566e-06,
"loss": 0.7732,
"step": 2553
},
{
"epoch": 0.88,
"learning_rate": 1.4673171650440487e-06,
"loss": 0.7669,
"step": 2554
},
{
"epoch": 0.88,
"learning_rate": 1.4589281157446067e-06,
"loss": 0.7247,
"step": 2555
},
{
"epoch": 0.88,
"learning_rate": 1.4505622086058747e-06,
"loss": 0.7637,
"step": 2556
},
{
"epoch": 0.88,
"learning_rate": 1.442219454069813e-06,
"loss": 0.7306,
"step": 2557
},
{
"epoch": 0.88,
"learning_rate": 1.4338998625494905e-06,
"loss": 0.778,
"step": 2558
},
{
"epoch": 0.88,
"learning_rate": 1.4256034444290535e-06,
"loss": 0.7203,
"step": 2559
},
{
"epoch": 0.88,
"learning_rate": 1.4173302100637342e-06,
"loss": 0.7931,
"step": 2560
},
{
"epoch": 0.88,
"learning_rate": 1.4090801697798261e-06,
"loss": 0.7479,
"step": 2561
},
{
"epoch": 0.88,
"learning_rate": 1.4008533338746676e-06,
"loss": 0.7353,
"step": 2562
},
{
"epoch": 0.88,
"learning_rate": 1.3926497126166405e-06,
"loss": 0.3623,
"step": 2563
},
{
"epoch": 0.88,
"learning_rate": 1.384469316245145e-06,
"loss": 0.7491,
"step": 2564
},
{
"epoch": 0.88,
"learning_rate": 1.3763121549705982e-06,
"loss": 0.7937,
"step": 2565
},
{
"epoch": 0.89,
"learning_rate": 1.3681782389744224e-06,
"loss": 0.7598,
"step": 2566
},
{
"epoch": 0.89,
"learning_rate": 1.3600675784090079e-06,
"loss": 0.7963,
"step": 2567
},
{
"epoch": 0.89,
"learning_rate": 1.3519801833977298e-06,
"loss": 0.7602,
"step": 2568
},
{
"epoch": 0.89,
"learning_rate": 1.3439160640349314e-06,
"loss": 0.7632,
"step": 2569
},
{
"epoch": 0.89,
"learning_rate": 1.3358752303858857e-06,
"loss": 0.7323,
"step": 2570
},
{
"epoch": 0.89,
"learning_rate": 1.3278576924868225e-06,
"loss": 0.803,
"step": 2571
},
{
"epoch": 0.89,
"learning_rate": 1.3198634603448723e-06,
"loss": 0.7635,
"step": 2572
},
{
"epoch": 0.89,
"learning_rate": 1.3118925439381003e-06,
"loss": 0.7236,
"step": 2573
},
{
"epoch": 0.89,
"learning_rate": 1.3039449532154524e-06,
"loss": 0.7415,
"step": 2574
},
{
"epoch": 0.89,
"learning_rate": 1.296020698096767e-06,
"loss": 0.8176,
"step": 2575
},
{
"epoch": 0.89,
"learning_rate": 1.2881197884727592e-06,
"loss": 0.7093,
"step": 2576
},
{
"epoch": 0.89,
"learning_rate": 1.2802422342049914e-06,
"loss": 0.7804,
"step": 2577
},
{
"epoch": 0.89,
"learning_rate": 1.2723880451258918e-06,
"loss": 0.7862,
"step": 2578
},
{
"epoch": 0.89,
"learning_rate": 1.2645572310387188e-06,
"loss": 0.7601,
"step": 2579
},
{
"epoch": 0.89,
"learning_rate": 1.2567498017175518e-06,
"loss": 0.736,
"step": 2580
},
{
"epoch": 0.89,
"learning_rate": 1.2489657669072864e-06,
"loss": 0.7624,
"step": 2581
},
{
"epoch": 0.89,
"learning_rate": 1.2412051363236156e-06,
"loss": 0.7803,
"step": 2582
},
{
"epoch": 0.89,
"learning_rate": 1.2334679196530219e-06,
"loss": 0.7551,
"step": 2583
},
{
"epoch": 0.89,
"learning_rate": 1.225754126552765e-06,
"loss": 0.7567,
"step": 2584
},
{
"epoch": 0.89,
"learning_rate": 1.2180637666508632e-06,
"loss": 0.7456,
"step": 2585
},
{
"epoch": 0.89,
"learning_rate": 1.2103968495460893e-06,
"loss": 0.7389,
"step": 2586
},
{
"epoch": 0.89,
"learning_rate": 1.2027533848079642e-06,
"loss": 0.7844,
"step": 2587
},
{
"epoch": 0.89,
"learning_rate": 1.1951333819767163e-06,
"loss": 0.7432,
"step": 2588
},
{
"epoch": 0.89,
"learning_rate": 1.1875368505633156e-06,
"loss": 0.7354,
"step": 2589
},
{
"epoch": 0.89,
"learning_rate": 1.1799638000494107e-06,
"loss": 0.7345,
"step": 2590
},
{
"epoch": 0.89,
"learning_rate": 1.1724142398873584e-06,
"loss": 0.7225,
"step": 2591
},
{
"epoch": 0.89,
"learning_rate": 1.1648881795001986e-06,
"loss": 0.3726,
"step": 2592
},
{
"epoch": 0.89,
"learning_rate": 1.157385628281622e-06,
"loss": 0.7432,
"step": 2593
},
{
"epoch": 0.89,
"learning_rate": 1.1499065955959953e-06,
"loss": 0.78,
"step": 2594
},
{
"epoch": 0.9,
"learning_rate": 1.142451090778316e-06,
"loss": 0.7257,
"step": 2595
},
{
"epoch": 0.9,
"learning_rate": 1.1350191231342288e-06,
"loss": 0.7866,
"step": 2596
},
{
"epoch": 0.9,
"learning_rate": 1.1276107019399874e-06,
"loss": 0.7543,
"step": 2597
},
{
"epoch": 0.9,
"learning_rate": 1.1202258364424633e-06,
"loss": 0.7739,
"step": 2598
},
{
"epoch": 0.9,
"learning_rate": 1.1128645358591239e-06,
"loss": 0.7541,
"step": 2599
},
{
"epoch": 0.9,
"learning_rate": 1.105526809378028e-06,
"loss": 0.7772,
"step": 2600
},
{
"epoch": 0.9,
"learning_rate": 1.098212666157803e-06,
"loss": 0.7467,
"step": 2601
},
{
"epoch": 0.9,
"learning_rate": 1.0909221153276462e-06,
"loss": 0.7547,
"step": 2602
},
{
"epoch": 0.9,
"learning_rate": 1.0836551659873073e-06,
"loss": 0.7644,
"step": 2603
},
{
"epoch": 0.9,
"learning_rate": 1.0764118272070777e-06,
"loss": 0.3995,
"step": 2604
},
{
"epoch": 0.9,
"learning_rate": 1.0691921080277745e-06,
"loss": 0.7405,
"step": 2605
},
{
"epoch": 0.9,
"learning_rate": 1.0619960174607425e-06,
"loss": 0.7181,
"step": 2606
},
{
"epoch": 0.9,
"learning_rate": 1.054823564487828e-06,
"loss": 0.75,
"step": 2607
},
{
"epoch": 0.9,
"learning_rate": 1.0476747580613723e-06,
"loss": 0.7987,
"step": 2608
},
{
"epoch": 0.9,
"learning_rate": 1.0405496071042042e-06,
"loss": 0.7801,
"step": 2609
},
{
"epoch": 0.9,
"learning_rate": 1.0334481205096368e-06,
"loss": 0.785,
"step": 2610
},
{
"epoch": 0.9,
"learning_rate": 1.0263703071414266e-06,
"loss": 0.7437,
"step": 2611
},
{
"epoch": 0.9,
"learning_rate": 1.0193161758338045e-06,
"loss": 0.7698,
"step": 2612
},
{
"epoch": 0.9,
"learning_rate": 1.012285735391416e-06,
"loss": 0.8318,
"step": 2613
},
{
"epoch": 0.9,
"learning_rate": 1.0052789945893625e-06,
"loss": 0.7666,
"step": 2614
},
{
"epoch": 0.9,
"learning_rate": 9.982959621731526e-07,
"loss": 0.7584,
"step": 2615
},
{
"epoch": 0.9,
"learning_rate": 9.913366468586982e-07,
"loss": 0.7211,
"step": 2616
},
{
"epoch": 0.9,
"learning_rate": 9.84401057332318e-07,
"loss": 0.7306,
"step": 2617
},
{
"epoch": 0.9,
"learning_rate": 9.774892022507166e-07,
"loss": 0.7662,
"step": 2618
},
{
"epoch": 0.9,
"learning_rate": 9.70601090240968e-07,
"loss": 0.7581,
"step": 2619
},
{
"epoch": 0.9,
"learning_rate": 9.637367299005152e-07,
"loss": 0.7797,
"step": 2620
},
{
"epoch": 0.9,
"learning_rate": 9.568961297971534e-07,
"loss": 0.7083,
"step": 2621
},
{
"epoch": 0.9,
"learning_rate": 9.500792984690244e-07,
"loss": 0.7344,
"step": 2622
},
{
"epoch": 0.9,
"learning_rate": 9.432862444245994e-07,
"loss": 0.7214,
"step": 2623
},
{
"epoch": 0.91,
"learning_rate": 9.365169761426763e-07,
"loss": 0.7454,
"step": 2624
},
{
"epoch": 0.91,
"learning_rate": 9.297715020723586e-07,
"loss": 0.7247,
"step": 2625
},
{
"epoch": 0.91,
"learning_rate": 9.23049830633056e-07,
"loss": 0.3765,
"step": 2626
},
{
"epoch": 0.91,
"learning_rate": 9.163519702144618e-07,
"loss": 0.4058,
"step": 2627
},
{
"epoch": 0.91,
"learning_rate": 9.096779291765667e-07,
"loss": 0.7545,
"step": 2628
},
{
"epoch": 0.91,
"learning_rate": 9.03027715849607e-07,
"loss": 0.4003,
"step": 2629
},
{
"epoch": 0.91,
"learning_rate": 8.964013385340942e-07,
"loss": 0.8329,
"step": 2630
},
{
"epoch": 0.91,
"learning_rate": 8.897988055007834e-07,
"loss": 0.7734,
"step": 2631
},
{
"epoch": 0.91,
"learning_rate": 8.832201249906691e-07,
"loss": 0.6995,
"step": 2632
},
{
"epoch": 0.91,
"learning_rate": 8.766653052149831e-07,
"loss": 0.7445,
"step": 2633
},
{
"epoch": 0.91,
"learning_rate": 8.701343543551544e-07,
"loss": 0.7294,
"step": 2634
},
{
"epoch": 0.91,
"learning_rate": 8.636272805628399e-07,
"loss": 0.7219,
"step": 2635
},
{
"epoch": 0.91,
"learning_rate": 8.57144091959885e-07,
"loss": 0.7418,
"step": 2636
},
{
"epoch": 0.91,
"learning_rate": 8.506847966383236e-07,
"loss": 0.7208,
"step": 2637
},
{
"epoch": 0.91,
"learning_rate": 8.442494026603709e-07,
"loss": 0.7829,
"step": 2638
},
{
"epoch": 0.91,
"learning_rate": 8.37837918058395e-07,
"loss": 0.7697,
"step": 2639
},
{
"epoch": 0.91,
"learning_rate": 8.314503508349459e-07,
"loss": 0.7924,
"step": 2640
},
{
"epoch": 0.91,
"learning_rate": 8.250867089627012e-07,
"loss": 0.7478,
"step": 2641
},
{
"epoch": 0.91,
"learning_rate": 8.187470003844833e-07,
"loss": 0.7312,
"step": 2642
},
{
"epoch": 0.91,
"learning_rate": 8.124312330132423e-07,
"loss": 0.7601,
"step": 2643
},
{
"epoch": 0.91,
"learning_rate": 8.061394147320434e-07,
"loss": 0.8095,
"step": 2644
},
{
"epoch": 0.91,
"learning_rate": 7.998715533940604e-07,
"loss": 0.759,
"step": 2645
},
{
"epoch": 0.91,
"learning_rate": 7.936276568225665e-07,
"loss": 0.7442,
"step": 2646
},
{
"epoch": 0.91,
"learning_rate": 7.874077328109208e-07,
"loss": 0.7393,
"step": 2647
},
{
"epoch": 0.91,
"learning_rate": 7.812117891225667e-07,
"loss": 0.7138,
"step": 2648
},
{
"epoch": 0.91,
"learning_rate": 7.75039833491007e-07,
"loss": 0.7239,
"step": 2649
},
{
"epoch": 0.91,
"learning_rate": 7.688918736198081e-07,
"loss": 0.7445,
"step": 2650
},
{
"epoch": 0.91,
"learning_rate": 7.627679171825942e-07,
"loss": 0.7918,
"step": 2651
},
{
"epoch": 0.91,
"learning_rate": 7.56667971823013e-07,
"loss": 0.7529,
"step": 2652
},
{
"epoch": 0.92,
"learning_rate": 7.505920451547544e-07,
"loss": 0.7922,
"step": 2653
},
{
"epoch": 0.92,
"learning_rate": 7.445401447615319e-07,
"loss": 0.7782,
"step": 2654
},
{
"epoch": 0.92,
"learning_rate": 7.385122781970522e-07,
"loss": 0.7678,
"step": 2655
},
{
"epoch": 0.92,
"learning_rate": 7.325084529850523e-07,
"loss": 0.7887,
"step": 2656
},
{
"epoch": 0.92,
"learning_rate": 7.265286766192315e-07,
"loss": 0.7788,
"step": 2657
},
{
"epoch": 0.92,
"learning_rate": 7.205729565632947e-07,
"loss": 0.7363,
"step": 2658
},
{
"epoch": 0.92,
"learning_rate": 7.146413002509112e-07,
"loss": 0.3938,
"step": 2659
},
{
"epoch": 0.92,
"learning_rate": 7.087337150857188e-07,
"loss": 0.7338,
"step": 2660
},
{
"epoch": 0.92,
"learning_rate": 7.028502084413081e-07,
"loss": 0.7594,
"step": 2661
},
{
"epoch": 0.92,
"learning_rate": 6.969907876612114e-07,
"loss": 0.8056,
"step": 2662
},
{
"epoch": 0.92,
"learning_rate": 6.911554600589121e-07,
"loss": 0.7413,
"step": 2663
},
{
"epoch": 0.92,
"learning_rate": 6.853442329178061e-07,
"loss": 0.7956,
"step": 2664
},
{
"epoch": 0.92,
"learning_rate": 6.79557113491216e-07,
"loss": 0.7598,
"step": 2665
},
{
"epoch": 0.92,
"learning_rate": 6.737941090023748e-07,
"loss": 0.7785,
"step": 2666
},
{
"epoch": 0.92,
"learning_rate": 6.680552266444129e-07,
"loss": 0.7465,
"step": 2667
},
{
"epoch": 0.92,
"learning_rate": 6.62340473580354e-07,
"loss": 0.7681,
"step": 2668
},
{
"epoch": 0.92,
"learning_rate": 6.566498569431056e-07,
"loss": 0.3984,
"step": 2669
},
{
"epoch": 0.92,
"learning_rate": 6.509833838354462e-07,
"loss": 0.7365,
"step": 2670
},
{
"epoch": 0.92,
"learning_rate": 6.453410613300226e-07,
"loss": 0.7646,
"step": 2671
},
{
"epoch": 0.92,
"learning_rate": 6.397228964693414e-07,
"loss": 0.7594,
"step": 2672
},
{
"epoch": 0.92,
"learning_rate": 6.341288962657422e-07,
"loss": 0.7647,
"step": 2673
},
{
"epoch": 0.92,
"learning_rate": 6.285590677014241e-07,
"loss": 0.3752,
"step": 2674
},
{
"epoch": 0.92,
"learning_rate": 6.230134177283953e-07,
"loss": 0.7561,
"step": 2675
},
{
"epoch": 0.92,
"learning_rate": 6.174919532685009e-07,
"loss": 0.7362,
"step": 2676
},
{
"epoch": 0.92,
"learning_rate": 6.119946812133926e-07,
"loss": 0.7626,
"step": 2677
},
{
"epoch": 0.92,
"learning_rate": 6.06521608424524e-07,
"loss": 0.7389,
"step": 2678
},
{
"epoch": 0.92,
"learning_rate": 6.01072741733153e-07,
"loss": 0.3725,
"step": 2679
},
{
"epoch": 0.92,
"learning_rate": 5.956480879403081e-07,
"loss": 0.7841,
"step": 2680
},
{
"epoch": 0.92,
"learning_rate": 5.902476538168156e-07,
"loss": 0.732,
"step": 2681
},
{
"epoch": 0.93,
"learning_rate": 5.848714461032612e-07,
"loss": 0.7698,
"step": 2682
},
{
"epoch": 0.93,
"learning_rate": 5.795194715099905e-07,
"loss": 0.7661,
"step": 2683
},
{
"epoch": 0.93,
"learning_rate": 5.74191736717109e-07,
"loss": 0.7772,
"step": 2684
},
{
"epoch": 0.93,
"learning_rate": 5.688882483744617e-07,
"loss": 0.753,
"step": 2685
},
{
"epoch": 0.93,
"learning_rate": 5.636090131016337e-07,
"loss": 0.7503,
"step": 2686
},
{
"epoch": 0.93,
"learning_rate": 5.583540374879381e-07,
"loss": 0.71,
"step": 2687
},
{
"epoch": 0.93,
"learning_rate": 5.531233280924042e-07,
"loss": 0.7968,
"step": 2688
},
{
"epoch": 0.93,
"learning_rate": 5.479168914437783e-07,
"loss": 0.8009,
"step": 2689
},
{
"epoch": 0.93,
"learning_rate": 5.427347340405087e-07,
"loss": 0.7984,
"step": 2690
},
{
"epoch": 0.93,
"learning_rate": 5.375768623507394e-07,
"loss": 0.7264,
"step": 2691
},
{
"epoch": 0.93,
"learning_rate": 5.324432828123005e-07,
"loss": 0.6989,
"step": 2692
},
{
"epoch": 0.93,
"learning_rate": 5.273340018327044e-07,
"loss": 0.7741,
"step": 2693
},
{
"epoch": 0.93,
"learning_rate": 5.222490257891299e-07,
"loss": 0.7948,
"step": 2694
},
{
"epoch": 0.93,
"learning_rate": 5.171883610284312e-07,
"loss": 0.7242,
"step": 2695
},
{
"epoch": 0.93,
"learning_rate": 5.121520138671022e-07,
"loss": 0.7526,
"step": 2696
},
{
"epoch": 0.93,
"learning_rate": 5.07139990591301e-07,
"loss": 0.8003,
"step": 2697
},
{
"epoch": 0.93,
"learning_rate": 5.02152297456806e-07,
"loss": 0.3788,
"step": 2698
},
{
"epoch": 0.93,
"learning_rate": 4.971889406890485e-07,
"loss": 0.7431,
"step": 2699
},
{
"epoch": 0.93,
"learning_rate": 4.922499264830749e-07,
"loss": 0.7312,
"step": 2700
},
{
"epoch": 0.93,
"learning_rate": 4.873352610035409e-07,
"loss": 0.7609,
"step": 2701
},
{
"epoch": 0.93,
"learning_rate": 4.824449503847262e-07,
"loss": 0.708,
"step": 2702
},
{
"epoch": 0.93,
"learning_rate": 4.775790007304993e-07,
"loss": 0.7488,
"step": 2703
},
{
"epoch": 0.93,
"learning_rate": 4.7273741811432847e-07,
"loss": 0.7543,
"step": 2704
},
{
"epoch": 0.93,
"learning_rate": 4.6792020857926665e-07,
"loss": 0.7697,
"step": 2705
},
{
"epoch": 0.93,
"learning_rate": 4.631273781379486e-07,
"loss": 0.759,
"step": 2706
},
{
"epoch": 0.93,
"learning_rate": 4.583589327725735e-07,
"loss": 0.7505,
"step": 2707
},
{
"epoch": 0.93,
"learning_rate": 4.5361487843490924e-07,
"loss": 0.7321,
"step": 2708
},
{
"epoch": 0.93,
"learning_rate": 4.4889522104627715e-07,
"loss": 0.7411,
"step": 2709
},
{
"epoch": 0.93,
"learning_rate": 4.441999664975494e-07,
"loss": 0.7825,
"step": 2710
},
{
"epoch": 0.94,
"learning_rate": 4.395291206491403e-07,
"loss": 0.718,
"step": 2711
},
{
"epoch": 0.94,
"learning_rate": 4.348826893309932e-07,
"loss": 0.7638,
"step": 2712
},
{
"epoch": 0.94,
"learning_rate": 4.3026067834258667e-07,
"loss": 0.7664,
"step": 2713
},
{
"epoch": 0.94,
"learning_rate": 4.2566309345291043e-07,
"loss": 0.8027,
"step": 2714
},
{
"epoch": 0.94,
"learning_rate": 4.21089940400472e-07,
"loss": 0.7827,
"step": 2715
},
{
"epoch": 0.94,
"learning_rate": 4.165412248932832e-07,
"loss": 0.7519,
"step": 2716
},
{
"epoch": 0.94,
"learning_rate": 4.1201695260884687e-07,
"loss": 0.7454,
"step": 2717
},
{
"epoch": 0.94,
"learning_rate": 4.0751712919417484e-07,
"loss": 0.7284,
"step": 2718
},
{
"epoch": 0.94,
"learning_rate": 4.030417602657388e-07,
"loss": 0.757,
"step": 2719
},
{
"epoch": 0.94,
"learning_rate": 3.985908514095083e-07,
"loss": 0.7279,
"step": 2720
},
{
"epoch": 0.94,
"learning_rate": 3.941644081809104e-07,
"loss": 0.7676,
"step": 2721
},
{
"epoch": 0.94,
"learning_rate": 3.8976243610484353e-07,
"loss": 0.7898,
"step": 2722
},
{
"epoch": 0.94,
"learning_rate": 3.853849406756549e-07,
"loss": 0.7889,
"step": 2723
},
{
"epoch": 0.94,
"learning_rate": 3.810319273571428e-07,
"loss": 0.7339,
"step": 2724
},
{
"epoch": 0.94,
"learning_rate": 3.767034015825499e-07,
"loss": 0.7499,
"step": 2725
},
{
"epoch": 0.94,
"learning_rate": 3.723993687545591e-07,
"loss": 0.7842,
"step": 2726
},
{
"epoch": 0.94,
"learning_rate": 3.6811983424527075e-07,
"loss": 0.7624,
"step": 2727
},
{
"epoch": 0.94,
"learning_rate": 3.6386480339621886e-07,
"loss": 0.7941,
"step": 2728
},
{
"epoch": 0.94,
"learning_rate": 3.59634281518344e-07,
"loss": 0.7495,
"step": 2729
},
{
"epoch": 0.94,
"learning_rate": 3.554282738920023e-07,
"loss": 0.7108,
"step": 2730
},
{
"epoch": 0.94,
"learning_rate": 3.512467857669499e-07,
"loss": 0.3815,
"step": 2731
},
{
"epoch": 0.94,
"learning_rate": 3.470898223623387e-07,
"loss": 0.7341,
"step": 2732
},
{
"epoch": 0.94,
"learning_rate": 3.4295738886670925e-07,
"loss": 0.7766,
"step": 2733
},
{
"epoch": 0.94,
"learning_rate": 3.3884949043798464e-07,
"loss": 0.7441,
"step": 2734
},
{
"epoch": 0.94,
"learning_rate": 3.3476613220346565e-07,
"loss": 0.7258,
"step": 2735
},
{
"epoch": 0.94,
"learning_rate": 3.3070731925982645e-07,
"loss": 0.6993,
"step": 2736
},
{
"epoch": 0.94,
"learning_rate": 3.266730566730969e-07,
"loss": 0.7284,
"step": 2737
},
{
"epoch": 0.94,
"learning_rate": 3.226633494786668e-07,
"loss": 0.7905,
"step": 2738
},
{
"epoch": 0.94,
"learning_rate": 3.1867820268128404e-07,
"loss": 0.7734,
"step": 2739
},
{
"epoch": 0.95,
"learning_rate": 3.1471762125503183e-07,
"loss": 0.7215,
"step": 2740
},
{
"epoch": 0.95,
"learning_rate": 3.107816101433381e-07,
"loss": 0.7743,
"step": 2741
},
{
"epoch": 0.95,
"learning_rate": 3.068701742589575e-07,
"loss": 0.7563,
"step": 2742
},
{
"epoch": 0.95,
"learning_rate": 3.0298331848398033e-07,
"loss": 0.7822,
"step": 2743
},
{
"epoch": 0.95,
"learning_rate": 2.991210476698059e-07,
"loss": 0.7277,
"step": 2744
},
{
"epoch": 0.95,
"learning_rate": 2.952833666371535e-07,
"loss": 0.7428,
"step": 2745
},
{
"epoch": 0.95,
"learning_rate": 2.9147028017605385e-07,
"loss": 0.7358,
"step": 2746
},
{
"epoch": 0.95,
"learning_rate": 2.8768179304583087e-07,
"loss": 0.7351,
"step": 2747
},
{
"epoch": 0.95,
"learning_rate": 2.839179099751133e-07,
"loss": 0.7631,
"step": 2748
},
{
"epoch": 0.95,
"learning_rate": 2.8017863566181414e-07,
"loss": 0.7669,
"step": 2749
},
{
"epoch": 0.95,
"learning_rate": 2.7646397477313567e-07,
"loss": 0.7412,
"step": 2750
},
{
"epoch": 0.95,
"learning_rate": 2.7277393194555357e-07,
"loss": 0.7906,
"step": 2751
},
{
"epoch": 0.95,
"learning_rate": 2.691085117848191e-07,
"loss": 0.767,
"step": 2752
},
{
"epoch": 0.95,
"learning_rate": 2.654677188659549e-07,
"loss": 0.7913,
"step": 2753
},
{
"epoch": 0.95,
"learning_rate": 2.618515577332348e-07,
"loss": 0.7351,
"step": 2754
},
{
"epoch": 0.95,
"learning_rate": 2.582600329001972e-07,
"loss": 0.7283,
"step": 2755
},
{
"epoch": 0.95,
"learning_rate": 2.5469314884962735e-07,
"loss": 0.7796,
"step": 2756
},
{
"epoch": 0.95,
"learning_rate": 2.511509100335552e-07,
"loss": 0.7686,
"step": 2757
},
{
"epoch": 0.95,
"learning_rate": 2.476333208732462e-07,
"loss": 0.7591,
"step": 2758
},
{
"epoch": 0.95,
"learning_rate": 2.441403857592084e-07,
"loss": 0.7349,
"step": 2759
},
{
"epoch": 0.95,
"learning_rate": 2.4067210905116764e-07,
"loss": 0.727,
"step": 2760
},
{
"epoch": 0.95,
"learning_rate": 2.3722849507807455e-07,
"loss": 0.732,
"step": 2761
},
{
"epoch": 0.95,
"learning_rate": 2.338095481381042e-07,
"loss": 0.7564,
"step": 2762
},
{
"epoch": 0.95,
"learning_rate": 2.3041527249863193e-07,
"loss": 0.7291,
"step": 2763
},
{
"epoch": 0.95,
"learning_rate": 2.2704567239624885e-07,
"loss": 0.75,
"step": 2764
},
{
"epoch": 0.95,
"learning_rate": 2.2370075203673958e-07,
"loss": 0.7513,
"step": 2765
},
{
"epoch": 0.95,
"learning_rate": 2.2038051559509333e-07,
"loss": 0.7532,
"step": 2766
},
{
"epoch": 0.95,
"learning_rate": 2.17084967215484e-07,
"loss": 0.8148,
"step": 2767
},
{
"epoch": 0.95,
"learning_rate": 2.1381411101127013e-07,
"loss": 0.7663,
"step": 2768
},
{
"epoch": 0.96,
"learning_rate": 2.1056795106499272e-07,
"loss": 0.716,
"step": 2769
},
{
"epoch": 0.96,
"learning_rate": 2.0734649142836626e-07,
"loss": 0.7423,
"step": 2770
},
{
"epoch": 0.96,
"learning_rate": 2.0414973612228107e-07,
"loss": 0.6877,
"step": 2771
},
{
"epoch": 0.96,
"learning_rate": 2.0097768913678317e-07,
"loss": 0.7491,
"step": 2772
},
{
"epoch": 0.96,
"learning_rate": 1.9783035443108999e-07,
"loss": 0.7302,
"step": 2773
},
{
"epoch": 0.96,
"learning_rate": 1.947077359335614e-07,
"loss": 0.7236,
"step": 2774
},
{
"epoch": 0.96,
"learning_rate": 1.9160983754171746e-07,
"loss": 0.7827,
"step": 2775
},
{
"epoch": 0.96,
"learning_rate": 1.8853666312222075e-07,
"loss": 0.7625,
"step": 2776
},
{
"epoch": 0.96,
"learning_rate": 1.8548821651087401e-07,
"loss": 0.7949,
"step": 2777
},
{
"epoch": 0.96,
"learning_rate": 1.8246450151261362e-07,
"loss": 0.3895,
"step": 2778
},
{
"epoch": 0.96,
"learning_rate": 1.794655219015118e-07,
"loss": 0.7634,
"step": 2779
},
{
"epoch": 0.96,
"learning_rate": 1.764912814207653e-07,
"loss": 0.7242,
"step": 2780
},
{
"epoch": 0.96,
"learning_rate": 1.7354178378268916e-07,
"loss": 0.719,
"step": 2781
},
{
"epoch": 0.96,
"learning_rate": 1.7061703266872066e-07,
"loss": 0.7023,
"step": 2782
},
{
"epoch": 0.96,
"learning_rate": 1.6771703172940635e-07,
"loss": 0.769,
"step": 2783
},
{
"epoch": 0.96,
"learning_rate": 1.648417845843997e-07,
"loss": 0.7446,
"step": 2784
},
{
"epoch": 0.96,
"learning_rate": 1.6199129482246335e-07,
"loss": 0.7592,
"step": 2785
},
{
"epoch": 0.96,
"learning_rate": 1.5916556600144906e-07,
"loss": 0.7749,
"step": 2786
},
{
"epoch": 0.96,
"learning_rate": 1.5636460164831557e-07,
"loss": 0.7709,
"step": 2787
},
{
"epoch": 0.96,
"learning_rate": 1.5358840525909967e-07,
"loss": 0.7343,
"step": 2788
},
{
"epoch": 0.96,
"learning_rate": 1.5083698029892957e-07,
"loss": 0.7564,
"step": 2789
},
{
"epoch": 0.96,
"learning_rate": 1.4811033020201815e-07,
"loss": 0.8011,
"step": 2790
},
{
"epoch": 0.96,
"learning_rate": 1.4540845837164753e-07,
"loss": 0.7645,
"step": 2791
},
{
"epoch": 0.96,
"learning_rate": 1.4273136818018008e-07,
"loss": 0.7597,
"step": 2792
},
{
"epoch": 0.96,
"learning_rate": 1.4007906296904072e-07,
"loss": 0.3873,
"step": 2793
},
{
"epoch": 0.96,
"learning_rate": 1.3745154604872358e-07,
"loss": 0.7633,
"step": 2794
},
{
"epoch": 0.96,
"learning_rate": 1.348488206987808e-07,
"loss": 0.7528,
"step": 2795
},
{
"epoch": 0.96,
"learning_rate": 1.3227089016782047e-07,
"loss": 0.7459,
"step": 2796
},
{
"epoch": 0.96,
"learning_rate": 1.2971775767350426e-07,
"loss": 0.7453,
"step": 2797
},
{
"epoch": 0.97,
"learning_rate": 1.2718942640254084e-07,
"loss": 0.757,
"step": 2798
},
{
"epoch": 0.97,
"learning_rate": 1.2468589951068367e-07,
"loss": 0.3897,
"step": 2799
},
{
"epoch": 0.97,
"learning_rate": 1.2220718012272424e-07,
"loss": 0.7136,
"step": 2800
},
{
"epoch": 0.97,
"learning_rate": 1.197532713324967e-07,
"loss": 0.7814,
"step": 2801
},
{
"epoch": 0.97,
"learning_rate": 1.1732417620285763e-07,
"loss": 0.7333,
"step": 2802
},
{
"epoch": 0.97,
"learning_rate": 1.1491989776570623e-07,
"loss": 0.7386,
"step": 2803
},
{
"epoch": 0.97,
"learning_rate": 1.1254043902195089e-07,
"loss": 0.705,
"step": 2804
},
{
"epoch": 0.97,
"learning_rate": 1.1018580294153148e-07,
"loss": 0.7637,
"step": 2805
},
{
"epoch": 0.97,
"learning_rate": 1.0785599246340373e-07,
"loss": 0.7436,
"step": 2806
},
{
"epoch": 0.97,
"learning_rate": 1.0555101049553263e-07,
"loss": 0.387,
"step": 2807
},
{
"epoch": 0.97,
"learning_rate": 1.0327085991490127e-07,
"loss": 0.7327,
"step": 2808
},
{
"epoch": 0.97,
"learning_rate": 1.0101554356749088e-07,
"loss": 0.6968,
"step": 2809
},
{
"epoch": 0.97,
"learning_rate": 9.878506426828971e-08,
"loss": 0.776,
"step": 2810
},
{
"epoch": 0.97,
"learning_rate": 9.657942480128635e-08,
"loss": 0.7945,
"step": 2811
},
{
"epoch": 0.97,
"learning_rate": 9.43986279194653e-08,
"loss": 0.7838,
"step": 2812
},
{
"epoch": 0.97,
"learning_rate": 9.22426763447981e-08,
"loss": 0.7664,
"step": 2813
},
{
"epoch": 0.97,
"learning_rate": 9.011157276825444e-08,
"loss": 0.7568,
"step": 2814
},
{
"epoch": 0.97,
"learning_rate": 8.800531984978433e-08,
"loss": 0.7486,
"step": 2815
},
{
"epoch": 0.97,
"learning_rate": 8.592392021832041e-08,
"loss": 0.7545,
"step": 2816
},
{
"epoch": 0.97,
"learning_rate": 8.386737647177346e-08,
"loss": 0.7175,
"step": 2817
},
{
"epoch": 0.97,
"learning_rate": 8.183569117703461e-08,
"loss": 0.7384,
"step": 2818
},
{
"epoch": 0.97,
"learning_rate": 7.982886686996427e-08,
"loss": 0.757,
"step": 2819
},
{
"epoch": 0.97,
"learning_rate": 7.784690605539435e-08,
"loss": 0.3975,
"step": 2820
},
{
"epoch": 0.97,
"learning_rate": 7.588981120712158e-08,
"loss": 0.7186,
"step": 2821
},
{
"epoch": 0.97,
"learning_rate": 7.395758476790749e-08,
"loss": 0.6721,
"step": 2822
},
{
"epoch": 0.97,
"learning_rate": 7.205022914946957e-08,
"loss": 0.7483,
"step": 2823
},
{
"epoch": 0.97,
"learning_rate": 7.016774673249238e-08,
"loss": 0.7105,
"step": 2824
},
{
"epoch": 0.97,
"learning_rate": 6.831013986660307e-08,
"loss": 0.7304,
"step": 2825
},
{
"epoch": 0.97,
"learning_rate": 6.647741087038916e-08,
"loss": 0.8013,
"step": 2826
},
{
"epoch": 0.98,
"learning_rate": 6.466956203138308e-08,
"loss": 0.7742,
"step": 2827
},
{
"epoch": 0.98,
"learning_rate": 6.288659560606203e-08,
"loss": 0.7423,
"step": 2828
},
{
"epoch": 0.98,
"learning_rate": 6.112851381984808e-08,
"loss": 0.7531,
"step": 2829
},
{
"epoch": 0.98,
"learning_rate": 5.939531886710148e-08,
"loss": 0.7456,
"step": 2830
},
{
"epoch": 0.98,
"learning_rate": 5.7687012911122884e-08,
"loss": 0.7583,
"step": 2831
},
{
"epoch": 0.98,
"learning_rate": 5.600359808414446e-08,
"loss": 0.7131,
"step": 2832
},
{
"epoch": 0.98,
"learning_rate": 5.4345076487332114e-08,
"loss": 0.7868,
"step": 2833
},
{
"epoch": 0.98,
"learning_rate": 5.271145019077883e-08,
"loss": 0.8049,
"step": 2834
},
{
"epoch": 0.98,
"learning_rate": 5.1102721233506904e-08,
"loss": 0.787,
"step": 2835
},
{
"epoch": 0.98,
"learning_rate": 4.951889162346346e-08,
"loss": 0.7548,
"step": 2836
},
{
"epoch": 0.98,
"learning_rate": 4.795996333751385e-08,
"loss": 0.7388,
"step": 2837
},
{
"epoch": 0.98,
"learning_rate": 4.642593832144382e-08,
"loss": 0.7838,
"step": 2838
},
{
"epoch": 0.98,
"learning_rate": 4.4916818489959544e-08,
"loss": 0.7697,
"step": 2839
},
{
"epoch": 0.98,
"learning_rate": 4.3432605726678736e-08,
"loss": 0.7826,
"step": 2840
},
{
"epoch": 0.98,
"learning_rate": 4.1973301884128406e-08,
"loss": 0.7519,
"step": 2841
},
{
"epoch": 0.98,
"learning_rate": 4.053890878374933e-08,
"loss": 0.7611,
"step": 2842
},
{
"epoch": 0.98,
"learning_rate": 3.912942821589161e-08,
"loss": 0.7738,
"step": 2843
},
{
"epoch": 0.98,
"learning_rate": 3.774486193980353e-08,
"loss": 0.7242,
"step": 2844
},
{
"epoch": 0.98,
"learning_rate": 3.638521168364495e-08,
"loss": 0.7155,
"step": 2845
},
{
"epoch": 0.98,
"learning_rate": 3.505047914446724e-08,
"loss": 0.7623,
"step": 2846
},
{
"epoch": 0.98,
"learning_rate": 3.374066598822889e-08,
"loss": 0.8137,
"step": 2847
},
{
"epoch": 0.98,
"learning_rate": 3.2455773849779935e-08,
"loss": 0.7412,
"step": 2848
},
{
"epoch": 0.98,
"learning_rate": 3.119580433287084e-08,
"loss": 0.7624,
"step": 2849
},
{
"epoch": 0.98,
"learning_rate": 2.9960759010134735e-08,
"loss": 0.776,
"step": 2850
},
{
"epoch": 0.98,
"learning_rate": 2.8750639423107408e-08,
"loss": 0.7005,
"step": 2851
},
{
"epoch": 0.98,
"learning_rate": 2.756544708220288e-08,
"loss": 0.7745,
"step": 2852
},
{
"epoch": 0.98,
"learning_rate": 2.6405183466731154e-08,
"loss": 0.772,
"step": 2853
},
{
"epoch": 0.98,
"learning_rate": 2.526985002488047e-08,
"loss": 0.6955,
"step": 2854
},
{
"epoch": 0.98,
"learning_rate": 2.4159448173723955e-08,
"loss": 0.7646,
"step": 2855
},
{
"epoch": 0.99,
"learning_rate": 2.3073979299217398e-08,
"loss": 0.7551,
"step": 2856
},
{
"epoch": 0.99,
"learning_rate": 2.2013444756197044e-08,
"loss": 0.8013,
"step": 2857
},
{
"epoch": 0.99,
"learning_rate": 2.0977845868375145e-08,
"loss": 0.7751,
"step": 2858
},
{
"epoch": 0.99,
"learning_rate": 1.9967183928342182e-08,
"loss": 0.7287,
"step": 2859
},
{
"epoch": 0.99,
"learning_rate": 1.89814601975602e-08,
"loss": 0.7328,
"step": 2860
},
{
"epoch": 0.99,
"learning_rate": 1.8020675906371687e-08,
"loss": 0.7513,
"step": 2861
},
{
"epoch": 0.99,
"learning_rate": 1.708483225397961e-08,
"loss": 0.7526,
"step": 2862
},
{
"epoch": 0.99,
"learning_rate": 1.6173930408467376e-08,
"loss": 0.7336,
"step": 2863
},
{
"epoch": 0.99,
"learning_rate": 1.5287971506781075e-08,
"loss": 0.7878,
"step": 2864
},
{
"epoch": 0.99,
"learning_rate": 1.4426956654738366e-08,
"loss": 0.7138,
"step": 2865
},
{
"epoch": 0.99,
"learning_rate": 1.3590886927019598e-08,
"loss": 0.7623,
"step": 2866
},
{
"epoch": 0.99,
"learning_rate": 1.2779763367170017e-08,
"loss": 0.7639,
"step": 2867
},
{
"epoch": 0.99,
"learning_rate": 1.199358698759978e-08,
"loss": 0.7276,
"step": 2868
},
{
"epoch": 0.99,
"learning_rate": 1.123235876957729e-08,
"loss": 0.7051,
"step": 2869
},
{
"epoch": 0.99,
"learning_rate": 1.0496079663240288e-08,
"loss": 0.7524,
"step": 2870
},
{
"epoch": 0.99,
"learning_rate": 9.784750587573666e-09,
"loss": 0.7351,
"step": 2871
},
{
"epoch": 0.99,
"learning_rate": 9.098372430433877e-09,
"loss": 0.7771,
"step": 2872
},
{
"epoch": 0.99,
"learning_rate": 8.436946048522298e-09,
"loss": 0.7677,
"step": 2873
},
{
"epoch": 0.99,
"learning_rate": 7.800472267407433e-09,
"loss": 0.3823,
"step": 2874
},
{
"epoch": 0.99,
"learning_rate": 7.188951881504924e-09,
"loss": 0.7817,
"step": 2875
},
{
"epoch": 0.99,
"learning_rate": 6.602385654090881e-09,
"loss": 0.7618,
"step": 2876
},
{
"epoch": 0.99,
"learning_rate": 6.0407743172907765e-09,
"loss": 0.7182,
"step": 2877
},
{
"epoch": 0.99,
"learning_rate": 5.504118572081662e-09,
"loss": 0.7576,
"step": 2878
},
{
"epoch": 0.99,
"learning_rate": 4.992419088294398e-09,
"loss": 0.7623,
"step": 2879
},
{
"epoch": 0.99,
"learning_rate": 4.505676504611423e-09,
"loss": 0.3975,
"step": 2880
},
{
"epoch": 0.99,
"learning_rate": 4.043891428564539e-09,
"loss": 0.7523,
"step": 2881
},
{
"epoch": 0.99,
"learning_rate": 3.607064436530472e-09,
"loss": 0.7539,
"step": 2882
},
{
"epoch": 0.99,
"learning_rate": 3.1951960737419686e-09,
"loss": 0.7209,
"step": 2883
},
{
"epoch": 0.99,
"learning_rate": 2.808286854270037e-09,
"loss": 0.7777,
"step": 2884
},
{
"epoch": 1.0,
"learning_rate": 2.4463372610439295e-09,
"loss": 0.7432,
"step": 2885
},
{
"epoch": 1.0,
"learning_rate": 2.109347745828938e-09,
"loss": 0.7754,
"step": 2886
},
{
"epoch": 1.0,
"learning_rate": 1.797318729241937e-09,
"loss": 0.7745,
"step": 2887
},
{
"epoch": 1.0,
"learning_rate": 1.5102506007447227e-09,
"loss": 0.7558,
"step": 2888
},
{
"epoch": 1.0,
"learning_rate": 1.2481437186417922e-09,
"loss": 0.7318,
"step": 2889
},
{
"epoch": 1.0,
"learning_rate": 1.0109984100847846e-09,
"loss": 0.6981,
"step": 2890
},
{
"epoch": 1.0,
"learning_rate": 7.988149710702608e-10,
"loss": 0.789,
"step": 2891
},
{
"epoch": 1.0,
"learning_rate": 6.115936664308209e-10,
"loss": 0.792,
"step": 2892
},
{
"epoch": 1.0,
"learning_rate": 4.493347298528683e-10,
"loss": 0.7555,
"step": 2893
},
{
"epoch": 1.0,
"learning_rate": 3.1203836385884644e-10,
"loss": 0.7727,
"step": 2894
},
{
"epoch": 1.0,
"learning_rate": 1.9970473981612004e-10,
"loss": 0.7274,
"step": 2895
},
{
"epoch": 1.0,
"learning_rate": 1.1233399793697531e-10,
"loss": 0.7164,
"step": 2896
},
{
"epoch": 1.0,
"learning_rate": 4.992624726973816e-11,
"loss": 0.7972,
"step": 2897
},
{
"epoch": 1.0,
"learning_rate": 1.248156571209691e-11,
"loss": 0.6984,
"step": 2898
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.3803,
"step": 2899
},
{
"epoch": 1.0,
"step": 2899,
"total_flos": 1.0321312470165094e+18,
"train_loss": 0.7595680371240403,
"train_runtime": 12032.4402,
"train_samples_per_second": 61.66,
"train_steps_per_second": 0.241
}
],
"max_steps": 2899,
"num_train_epochs": 1,
"total_flos": 1.0321312470165094e+18,
"trial_name": null,
"trial_params": null
}