instructany2pix / ckpts /llm /trainer_state.json
Shufan Li
commit model
f62f9d0
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 3859,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.7241379310344828e-07,
"loss": 3.6719,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 3.4482758620689656e-07,
"loss": 3.5625,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 5.172413793103449e-07,
"loss": 3.6426,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 6.896551724137931e-07,
"loss": 3.6504,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 8.620689655172415e-07,
"loss": 3.5977,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 1.0344827586206898e-06,
"loss": 3.5508,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 1.2068965517241381e-06,
"loss": 3.5293,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 1.3793103448275862e-06,
"loss": 3.5215,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 1.5517241379310346e-06,
"loss": 3.4219,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 1.724137931034483e-06,
"loss": 3.168,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 1.896551724137931e-06,
"loss": 3.2773,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 2.0689655172413796e-06,
"loss": 2.8066,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 2.241379310344828e-06,
"loss": 2.6738,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 2.4137931034482762e-06,
"loss": 2.5586,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 2.5862068965517246e-06,
"loss": 2.3398,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 2.7586206896551725e-06,
"loss": 1.8877,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 2.931034482758621e-06,
"loss": 1.8281,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 3.103448275862069e-06,
"loss": 1.7666,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 3.2758620689655175e-06,
"loss": 1.6055,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 3.448275862068966e-06,
"loss": 1.5791,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 3.620689655172414e-06,
"loss": 1.2471,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 3.793103448275862e-06,
"loss": 1.2168,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 3.96551724137931e-06,
"loss": 1.1494,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 4.137931034482759e-06,
"loss": 1.0649,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 4.310344827586207e-06,
"loss": 1.0879,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 4.482758620689656e-06,
"loss": 1.0229,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 4.655172413793104e-06,
"loss": 0.9854,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 4.8275862068965525e-06,
"loss": 0.9907,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 5e-06,
"loss": 1.0132,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 5.172413793103449e-06,
"loss": 0.9487,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 5.344827586206896e-06,
"loss": 0.9448,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 5.517241379310345e-06,
"loss": 0.9409,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 5.689655172413794e-06,
"loss": 0.8623,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 5.862068965517242e-06,
"loss": 0.8936,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 6.03448275862069e-06,
"loss": 0.9243,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 6.206896551724138e-06,
"loss": 0.9146,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 6.379310344827587e-06,
"loss": 0.8799,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 6.551724137931035e-06,
"loss": 0.8101,
"step": 38
},
{
"epoch": 0.01,
"learning_rate": 6.724137931034484e-06,
"loss": 0.8496,
"step": 39
},
{
"epoch": 0.01,
"learning_rate": 6.896551724137932e-06,
"loss": 0.8496,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 7.0689655172413796e-06,
"loss": 0.8193,
"step": 41
},
{
"epoch": 0.01,
"learning_rate": 7.241379310344828e-06,
"loss": 0.8018,
"step": 42
},
{
"epoch": 0.01,
"learning_rate": 7.413793103448277e-06,
"loss": 0.8716,
"step": 43
},
{
"epoch": 0.01,
"learning_rate": 7.586206896551724e-06,
"loss": 0.7988,
"step": 44
},
{
"epoch": 0.01,
"learning_rate": 7.758620689655173e-06,
"loss": 0.8701,
"step": 45
},
{
"epoch": 0.01,
"learning_rate": 7.93103448275862e-06,
"loss": 0.8213,
"step": 46
},
{
"epoch": 0.01,
"learning_rate": 8.103448275862069e-06,
"loss": 0.8076,
"step": 47
},
{
"epoch": 0.01,
"learning_rate": 8.275862068965518e-06,
"loss": 0.8062,
"step": 48
},
{
"epoch": 0.01,
"learning_rate": 8.448275862068966e-06,
"loss": 0.8286,
"step": 49
},
{
"epoch": 0.01,
"learning_rate": 8.620689655172414e-06,
"loss": 0.7734,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 8.793103448275862e-06,
"loss": 0.8203,
"step": 51
},
{
"epoch": 0.01,
"learning_rate": 8.965517241379312e-06,
"loss": 0.77,
"step": 52
},
{
"epoch": 0.01,
"learning_rate": 9.13793103448276e-06,
"loss": 0.8145,
"step": 53
},
{
"epoch": 0.01,
"learning_rate": 9.310344827586207e-06,
"loss": 0.7617,
"step": 54
},
{
"epoch": 0.01,
"learning_rate": 9.482758620689655e-06,
"loss": 0.7979,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 9.655172413793105e-06,
"loss": 0.7676,
"step": 56
},
{
"epoch": 0.01,
"learning_rate": 9.827586206896553e-06,
"loss": 0.7837,
"step": 57
},
{
"epoch": 0.02,
"learning_rate": 1e-05,
"loss": 0.8037,
"step": 58
},
{
"epoch": 0.02,
"learning_rate": 1.0172413793103449e-05,
"loss": 0.7817,
"step": 59
},
{
"epoch": 0.02,
"learning_rate": 1.0344827586206898e-05,
"loss": 0.7432,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 1.0517241379310346e-05,
"loss": 0.7686,
"step": 61
},
{
"epoch": 0.02,
"learning_rate": 1.0689655172413792e-05,
"loss": 0.7383,
"step": 62
},
{
"epoch": 0.02,
"learning_rate": 1.0862068965517242e-05,
"loss": 0.7637,
"step": 63
},
{
"epoch": 0.02,
"learning_rate": 1.103448275862069e-05,
"loss": 0.7476,
"step": 64
},
{
"epoch": 0.02,
"learning_rate": 1.1206896551724138e-05,
"loss": 0.7256,
"step": 65
},
{
"epoch": 0.02,
"learning_rate": 1.1379310344827587e-05,
"loss": 0.7495,
"step": 66
},
{
"epoch": 0.02,
"learning_rate": 1.1551724137931035e-05,
"loss": 0.728,
"step": 67
},
{
"epoch": 0.02,
"learning_rate": 1.1724137931034483e-05,
"loss": 0.7515,
"step": 68
},
{
"epoch": 0.02,
"learning_rate": 1.1896551724137933e-05,
"loss": 0.7749,
"step": 69
},
{
"epoch": 0.02,
"learning_rate": 1.206896551724138e-05,
"loss": 0.6997,
"step": 70
},
{
"epoch": 0.02,
"learning_rate": 1.2241379310344827e-05,
"loss": 0.7412,
"step": 71
},
{
"epoch": 0.02,
"learning_rate": 1.2413793103448277e-05,
"loss": 0.7153,
"step": 72
},
{
"epoch": 0.02,
"learning_rate": 1.2586206896551725e-05,
"loss": 0.7549,
"step": 73
},
{
"epoch": 0.02,
"learning_rate": 1.2758620689655174e-05,
"loss": 0.7407,
"step": 74
},
{
"epoch": 0.02,
"learning_rate": 1.2931034482758622e-05,
"loss": 0.751,
"step": 75
},
{
"epoch": 0.02,
"learning_rate": 1.310344827586207e-05,
"loss": 0.7158,
"step": 76
},
{
"epoch": 0.02,
"learning_rate": 1.327586206896552e-05,
"loss": 0.7607,
"step": 77
},
{
"epoch": 0.02,
"learning_rate": 1.3448275862068967e-05,
"loss": 0.6968,
"step": 78
},
{
"epoch": 0.02,
"learning_rate": 1.3620689655172414e-05,
"loss": 0.7114,
"step": 79
},
{
"epoch": 0.02,
"learning_rate": 1.3793103448275863e-05,
"loss": 0.7109,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 1.3965517241379311e-05,
"loss": 0.7368,
"step": 81
},
{
"epoch": 0.02,
"learning_rate": 1.4137931034482759e-05,
"loss": 0.7046,
"step": 82
},
{
"epoch": 0.02,
"learning_rate": 1.4310344827586209e-05,
"loss": 0.7041,
"step": 83
},
{
"epoch": 0.02,
"learning_rate": 1.4482758620689657e-05,
"loss": 0.7212,
"step": 84
},
{
"epoch": 0.02,
"learning_rate": 1.4655172413793105e-05,
"loss": 0.6968,
"step": 85
},
{
"epoch": 0.02,
"learning_rate": 1.4827586206896554e-05,
"loss": 0.707,
"step": 86
},
{
"epoch": 0.02,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.731,
"step": 87
},
{
"epoch": 0.02,
"learning_rate": 1.5172413793103448e-05,
"loss": 0.7056,
"step": 88
},
{
"epoch": 0.02,
"learning_rate": 1.5344827586206898e-05,
"loss": 0.7046,
"step": 89
},
{
"epoch": 0.02,
"learning_rate": 1.5517241379310346e-05,
"loss": 0.7104,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 1.5689655172413794e-05,
"loss": 0.7334,
"step": 91
},
{
"epoch": 0.02,
"learning_rate": 1.586206896551724e-05,
"loss": 0.6533,
"step": 92
},
{
"epoch": 0.02,
"learning_rate": 1.603448275862069e-05,
"loss": 0.7456,
"step": 93
},
{
"epoch": 0.02,
"learning_rate": 1.6206896551724137e-05,
"loss": 0.6899,
"step": 94
},
{
"epoch": 0.02,
"learning_rate": 1.637931034482759e-05,
"loss": 0.7217,
"step": 95
},
{
"epoch": 0.02,
"learning_rate": 1.6551724137931037e-05,
"loss": 0.6895,
"step": 96
},
{
"epoch": 0.03,
"learning_rate": 1.6724137931034485e-05,
"loss": 0.7407,
"step": 97
},
{
"epoch": 0.03,
"learning_rate": 1.6896551724137932e-05,
"loss": 0.6841,
"step": 98
},
{
"epoch": 0.03,
"learning_rate": 1.706896551724138e-05,
"loss": 0.7275,
"step": 99
},
{
"epoch": 0.03,
"learning_rate": 1.7241379310344828e-05,
"loss": 0.7114,
"step": 100
},
{
"epoch": 0.03,
"learning_rate": 1.7413793103448276e-05,
"loss": 0.7065,
"step": 101
},
{
"epoch": 0.03,
"learning_rate": 1.7586206896551724e-05,
"loss": 0.6797,
"step": 102
},
{
"epoch": 0.03,
"learning_rate": 1.7758620689655175e-05,
"loss": 0.7227,
"step": 103
},
{
"epoch": 0.03,
"learning_rate": 1.7931034482758623e-05,
"loss": 0.6948,
"step": 104
},
{
"epoch": 0.03,
"learning_rate": 1.810344827586207e-05,
"loss": 0.6743,
"step": 105
},
{
"epoch": 0.03,
"learning_rate": 1.827586206896552e-05,
"loss": 0.689,
"step": 106
},
{
"epoch": 0.03,
"learning_rate": 1.8448275862068967e-05,
"loss": 0.73,
"step": 107
},
{
"epoch": 0.03,
"learning_rate": 1.8620689655172415e-05,
"loss": 0.73,
"step": 108
},
{
"epoch": 0.03,
"learning_rate": 1.8793103448275863e-05,
"loss": 0.6963,
"step": 109
},
{
"epoch": 0.03,
"learning_rate": 1.896551724137931e-05,
"loss": 0.6807,
"step": 110
},
{
"epoch": 0.03,
"learning_rate": 1.913793103448276e-05,
"loss": 0.7041,
"step": 111
},
{
"epoch": 0.03,
"learning_rate": 1.931034482758621e-05,
"loss": 0.6611,
"step": 112
},
{
"epoch": 0.03,
"learning_rate": 1.9482758620689658e-05,
"loss": 0.6948,
"step": 113
},
{
"epoch": 0.03,
"learning_rate": 1.9655172413793106e-05,
"loss": 0.7085,
"step": 114
},
{
"epoch": 0.03,
"learning_rate": 1.9827586206896554e-05,
"loss": 0.6646,
"step": 115
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 0.6431,
"step": 116
},
{
"epoch": 0.03,
"learning_rate": 1.999999647766977e-05,
"loss": 0.6821,
"step": 117
},
{
"epoch": 0.03,
"learning_rate": 1.9999985910681565e-05,
"loss": 0.6743,
"step": 118
},
{
"epoch": 0.03,
"learning_rate": 1.9999968299042825e-05,
"loss": 0.6772,
"step": 119
},
{
"epoch": 0.03,
"learning_rate": 1.9999943642765957e-05,
"loss": 0.6538,
"step": 120
},
{
"epoch": 0.03,
"learning_rate": 1.9999911941868336e-05,
"loss": 0.6562,
"step": 121
},
{
"epoch": 0.03,
"learning_rate": 1.9999873196372284e-05,
"loss": 0.6528,
"step": 122
},
{
"epoch": 0.03,
"learning_rate": 1.9999827406305105e-05,
"loss": 0.6855,
"step": 123
},
{
"epoch": 0.03,
"learning_rate": 1.9999774571699057e-05,
"loss": 0.6313,
"step": 124
},
{
"epoch": 0.03,
"learning_rate": 1.9999714692591352e-05,
"loss": 0.6582,
"step": 125
},
{
"epoch": 0.03,
"learning_rate": 1.999964776902418e-05,
"loss": 0.6875,
"step": 126
},
{
"epoch": 0.03,
"learning_rate": 1.999957380104468e-05,
"loss": 0.686,
"step": 127
},
{
"epoch": 0.03,
"learning_rate": 1.9999492788704966e-05,
"loss": 0.6851,
"step": 128
},
{
"epoch": 0.03,
"learning_rate": 1.9999404732062107e-05,
"loss": 0.6777,
"step": 129
},
{
"epoch": 0.03,
"learning_rate": 1.9999309631178135e-05,
"loss": 0.6704,
"step": 130
},
{
"epoch": 0.03,
"learning_rate": 1.9999207486120048e-05,
"loss": 0.6816,
"step": 131
},
{
"epoch": 0.03,
"learning_rate": 1.9999098296959798e-05,
"loss": 0.7021,
"step": 132
},
{
"epoch": 0.03,
"learning_rate": 1.9998982063774307e-05,
"loss": 0.7251,
"step": 133
},
{
"epoch": 0.03,
"learning_rate": 1.9998858786645462e-05,
"loss": 0.6465,
"step": 134
},
{
"epoch": 0.03,
"learning_rate": 1.9998728465660105e-05,
"loss": 0.6748,
"step": 135
},
{
"epoch": 0.04,
"learning_rate": 1.9998591100910038e-05,
"loss": 0.6875,
"step": 136
},
{
"epoch": 0.04,
"learning_rate": 1.9998446692492037e-05,
"loss": 0.6904,
"step": 137
},
{
"epoch": 0.04,
"learning_rate": 1.999829524050783e-05,
"loss": 0.6748,
"step": 138
},
{
"epoch": 0.04,
"learning_rate": 1.9998136745064105e-05,
"loss": 0.6689,
"step": 139
},
{
"epoch": 0.04,
"learning_rate": 1.9997971206272524e-05,
"loss": 0.6787,
"step": 140
},
{
"epoch": 0.04,
"learning_rate": 1.99977986242497e-05,
"loss": 0.6797,
"step": 141
},
{
"epoch": 0.04,
"learning_rate": 1.999761899911721e-05,
"loss": 0.7271,
"step": 142
},
{
"epoch": 0.04,
"learning_rate": 1.9997432331001597e-05,
"loss": 0.6802,
"step": 143
},
{
"epoch": 0.04,
"learning_rate": 1.999723862003436e-05,
"loss": 0.6392,
"step": 144
},
{
"epoch": 0.04,
"learning_rate": 1.9997037866351966e-05,
"loss": 0.6616,
"step": 145
},
{
"epoch": 0.04,
"learning_rate": 1.9996830070095836e-05,
"loss": 0.6509,
"step": 146
},
{
"epoch": 0.04,
"learning_rate": 1.999661523141235e-05,
"loss": 0.6812,
"step": 147
},
{
"epoch": 0.04,
"learning_rate": 1.999639335045286e-05,
"loss": 0.686,
"step": 148
},
{
"epoch": 0.04,
"learning_rate": 1.999616442737368e-05,
"loss": 0.6631,
"step": 149
},
{
"epoch": 0.04,
"learning_rate": 1.9995928462336064e-05,
"loss": 0.6807,
"step": 150
},
{
"epoch": 0.04,
"learning_rate": 1.9995685455506253e-05,
"loss": 0.6533,
"step": 151
},
{
"epoch": 0.04,
"learning_rate": 1.9995435407055433e-05,
"loss": 0.6763,
"step": 152
},
{
"epoch": 0.04,
"learning_rate": 1.9995178317159755e-05,
"loss": 0.6787,
"step": 153
},
{
"epoch": 0.04,
"learning_rate": 1.999491418600033e-05,
"loss": 0.6753,
"step": 154
},
{
"epoch": 0.04,
"learning_rate": 1.999464301376323e-05,
"loss": 0.6802,
"step": 155
},
{
"epoch": 0.04,
"learning_rate": 1.999436480063948e-05,
"loss": 0.6548,
"step": 156
},
{
"epoch": 0.04,
"learning_rate": 1.9994079546825085e-05,
"loss": 0.6392,
"step": 157
},
{
"epoch": 0.04,
"learning_rate": 1.9993787252520985e-05,
"loss": 0.6831,
"step": 158
},
{
"epoch": 0.04,
"learning_rate": 1.99934879179331e-05,
"loss": 0.6948,
"step": 159
},
{
"epoch": 0.04,
"learning_rate": 1.9993181543272294e-05,
"loss": 0.6543,
"step": 160
},
{
"epoch": 0.04,
"learning_rate": 1.99928681287544e-05,
"loss": 0.6807,
"step": 161
},
{
"epoch": 0.04,
"learning_rate": 1.999254767460021e-05,
"loss": 0.624,
"step": 162
},
{
"epoch": 0.04,
"learning_rate": 1.999222018103547e-05,
"loss": 0.668,
"step": 163
},
{
"epoch": 0.04,
"learning_rate": 1.9991885648290893e-05,
"loss": 0.6748,
"step": 164
},
{
"epoch": 0.04,
"learning_rate": 1.999154407660214e-05,
"loss": 0.665,
"step": 165
},
{
"epoch": 0.04,
"learning_rate": 1.9991195466209837e-05,
"loss": 0.6489,
"step": 166
},
{
"epoch": 0.04,
"learning_rate": 1.9990839817359572e-05,
"loss": 0.6719,
"step": 167
},
{
"epoch": 0.04,
"learning_rate": 1.9990477130301885e-05,
"loss": 0.6675,
"step": 168
},
{
"epoch": 0.04,
"learning_rate": 1.9990107405292278e-05,
"loss": 0.666,
"step": 169
},
{
"epoch": 0.04,
"learning_rate": 1.998973064259121e-05,
"loss": 0.6421,
"step": 170
},
{
"epoch": 0.04,
"learning_rate": 1.9989346842464097e-05,
"loss": 0.6606,
"step": 171
},
{
"epoch": 0.04,
"learning_rate": 1.998895600518131e-05,
"loss": 0.6509,
"step": 172
},
{
"epoch": 0.04,
"learning_rate": 1.9988558131018188e-05,
"loss": 0.6548,
"step": 173
},
{
"epoch": 0.05,
"learning_rate": 1.998815322025501e-05,
"loss": 0.6504,
"step": 174
},
{
"epoch": 0.05,
"learning_rate": 1.9987741273177033e-05,
"loss": 0.6626,
"step": 175
},
{
"epoch": 0.05,
"learning_rate": 1.998732229007445e-05,
"loss": 0.6421,
"step": 176
},
{
"epoch": 0.05,
"learning_rate": 1.9986896271242426e-05,
"loss": 0.7095,
"step": 177
},
{
"epoch": 0.05,
"learning_rate": 1.9986463216981074e-05,
"loss": 0.6528,
"step": 178
},
{
"epoch": 0.05,
"learning_rate": 1.998602312759547e-05,
"loss": 0.6694,
"step": 179
},
{
"epoch": 0.05,
"learning_rate": 1.9985576003395635e-05,
"loss": 0.6606,
"step": 180
},
{
"epoch": 0.05,
"learning_rate": 1.998512184469656e-05,
"loss": 0.6421,
"step": 181
},
{
"epoch": 0.05,
"learning_rate": 1.998466065181818e-05,
"loss": 0.6694,
"step": 182
},
{
"epoch": 0.05,
"learning_rate": 1.9984192425085388e-05,
"loss": 0.6431,
"step": 183
},
{
"epoch": 0.05,
"learning_rate": 1.9983717164828044e-05,
"loss": 0.6519,
"step": 184
},
{
"epoch": 0.05,
"learning_rate": 1.998323487138094e-05,
"loss": 0.6592,
"step": 185
},
{
"epoch": 0.05,
"learning_rate": 1.9982745545083842e-05,
"loss": 0.6484,
"step": 186
},
{
"epoch": 0.05,
"learning_rate": 1.9982249186281465e-05,
"loss": 0.6729,
"step": 187
},
{
"epoch": 0.05,
"learning_rate": 1.998174579532347e-05,
"loss": 0.665,
"step": 188
},
{
"epoch": 0.05,
"learning_rate": 1.998123537256449e-05,
"loss": 0.647,
"step": 189
},
{
"epoch": 0.05,
"learning_rate": 1.9980717918364092e-05,
"loss": 0.6392,
"step": 190
},
{
"epoch": 0.05,
"learning_rate": 1.9980193433086804e-05,
"loss": 0.6606,
"step": 191
},
{
"epoch": 0.05,
"learning_rate": 1.9979661917102116e-05,
"loss": 0.6665,
"step": 192
},
{
"epoch": 0.05,
"learning_rate": 1.9979123370784454e-05,
"loss": 0.6416,
"step": 193
},
{
"epoch": 0.05,
"learning_rate": 1.997857779451321e-05,
"loss": 0.6655,
"step": 194
},
{
"epoch": 0.05,
"learning_rate": 1.9978025188672726e-05,
"loss": 0.6431,
"step": 195
},
{
"epoch": 0.05,
"learning_rate": 1.997746555365229e-05,
"loss": 0.6567,
"step": 196
},
{
"epoch": 0.05,
"learning_rate": 1.997689888984615e-05,
"loss": 0.6655,
"step": 197
},
{
"epoch": 0.05,
"learning_rate": 1.9976325197653494e-05,
"loss": 0.6499,
"step": 198
},
{
"epoch": 0.05,
"learning_rate": 1.9975744477478472e-05,
"loss": 0.6587,
"step": 199
},
{
"epoch": 0.05,
"learning_rate": 1.9975156729730188e-05,
"loss": 0.646,
"step": 200
},
{
"epoch": 0.05,
"learning_rate": 1.9974561954822684e-05,
"loss": 0.667,
"step": 201
},
{
"epoch": 0.05,
"learning_rate": 1.997396015317496e-05,
"loss": 0.6509,
"step": 202
},
{
"epoch": 0.05,
"learning_rate": 1.997335132521097e-05,
"loss": 0.6274,
"step": 203
},
{
"epoch": 0.05,
"learning_rate": 1.99727354713596e-05,
"loss": 0.6455,
"step": 204
},
{
"epoch": 0.05,
"learning_rate": 1.997211259205471e-05,
"loss": 0.6724,
"step": 205
},
{
"epoch": 0.05,
"learning_rate": 1.9971482687735094e-05,
"loss": 0.6401,
"step": 206
},
{
"epoch": 0.05,
"learning_rate": 1.9970845758844493e-05,
"loss": 0.6592,
"step": 207
},
{
"epoch": 0.05,
"learning_rate": 1.997020180583161e-05,
"loss": 0.6406,
"step": 208
},
{
"epoch": 0.05,
"learning_rate": 1.9969550829150082e-05,
"loss": 0.6396,
"step": 209
},
{
"epoch": 0.05,
"learning_rate": 1.9968892829258502e-05,
"loss": 0.6348,
"step": 210
},
{
"epoch": 0.05,
"learning_rate": 1.9968227806620413e-05,
"loss": 0.6167,
"step": 211
},
{
"epoch": 0.05,
"learning_rate": 1.996755576170429e-05,
"loss": 0.6279,
"step": 212
},
{
"epoch": 0.06,
"learning_rate": 1.996687669498358e-05,
"loss": 0.6396,
"step": 213
},
{
"epoch": 0.06,
"learning_rate": 1.996619060693665e-05,
"loss": 0.6333,
"step": 214
},
{
"epoch": 0.06,
"learning_rate": 1.996549749804683e-05,
"loss": 0.6172,
"step": 215
},
{
"epoch": 0.06,
"learning_rate": 1.9964797368802395e-05,
"loss": 0.6636,
"step": 216
},
{
"epoch": 0.06,
"learning_rate": 1.996409021969656e-05,
"loss": 0.6587,
"step": 217
},
{
"epoch": 0.06,
"learning_rate": 1.9963376051227482e-05,
"loss": 0.6221,
"step": 218
},
{
"epoch": 0.06,
"learning_rate": 1.996265486389828e-05,
"loss": 0.6426,
"step": 219
},
{
"epoch": 0.06,
"learning_rate": 1.9961926658216995e-05,
"loss": 0.6558,
"step": 220
},
{
"epoch": 0.06,
"learning_rate": 1.9961191434696627e-05,
"loss": 0.6377,
"step": 221
},
{
"epoch": 0.06,
"learning_rate": 1.9960449193855118e-05,
"loss": 0.6602,
"step": 222
},
{
"epoch": 0.06,
"learning_rate": 1.995969993621535e-05,
"loss": 0.6123,
"step": 223
},
{
"epoch": 0.06,
"learning_rate": 1.9958943662305152e-05,
"loss": 0.6421,
"step": 224
},
{
"epoch": 0.06,
"learning_rate": 1.995818037265729e-05,
"loss": 0.6445,
"step": 225
},
{
"epoch": 0.06,
"learning_rate": 1.9957410067809477e-05,
"loss": 0.666,
"step": 226
},
{
"epoch": 0.06,
"learning_rate": 1.9956632748304365e-05,
"loss": 0.6567,
"step": 227
},
{
"epoch": 0.06,
"learning_rate": 1.995584841468955e-05,
"loss": 0.6265,
"step": 228
},
{
"epoch": 0.06,
"learning_rate": 1.995505706751757e-05,
"loss": 0.6685,
"step": 229
},
{
"epoch": 0.06,
"learning_rate": 1.9954258707345903e-05,
"loss": 0.6528,
"step": 230
},
{
"epoch": 0.06,
"learning_rate": 1.9953453334736964e-05,
"loss": 0.6147,
"step": 231
},
{
"epoch": 0.06,
"learning_rate": 1.9952640950258107e-05,
"loss": 0.6562,
"step": 232
},
{
"epoch": 0.06,
"learning_rate": 1.9951821554481637e-05,
"loss": 0.623,
"step": 233
},
{
"epoch": 0.06,
"learning_rate": 1.9950995147984786e-05,
"loss": 0.6313,
"step": 234
},
{
"epoch": 0.06,
"learning_rate": 1.995016173134973e-05,
"loss": 0.6318,
"step": 235
},
{
"epoch": 0.06,
"learning_rate": 1.994932130516359e-05,
"loss": 0.6274,
"step": 236
},
{
"epoch": 0.06,
"learning_rate": 1.9948473870018403e-05,
"loss": 0.6177,
"step": 237
},
{
"epoch": 0.06,
"learning_rate": 1.994761942651117e-05,
"loss": 0.6279,
"step": 238
},
{
"epoch": 0.06,
"learning_rate": 1.9946757975243807e-05,
"loss": 0.6318,
"step": 239
},
{
"epoch": 0.06,
"learning_rate": 1.9945889516823192e-05,
"loss": 0.645,
"step": 240
},
{
"epoch": 0.06,
"learning_rate": 1.9945014051861115e-05,
"loss": 0.6172,
"step": 241
},
{
"epoch": 0.06,
"learning_rate": 1.994413158097431e-05,
"loss": 0.6348,
"step": 242
},
{
"epoch": 0.06,
"learning_rate": 1.994324210478445e-05,
"loss": 0.6255,
"step": 243
},
{
"epoch": 0.06,
"learning_rate": 1.9942345623918144e-05,
"loss": 0.5991,
"step": 244
},
{
"epoch": 0.06,
"learning_rate": 1.994144213900693e-05,
"loss": 0.6685,
"step": 245
},
{
"epoch": 0.06,
"learning_rate": 1.994053165068728e-05,
"loss": 0.6333,
"step": 246
},
{
"epoch": 0.06,
"learning_rate": 1.99396141596006e-05,
"loss": 0.6572,
"step": 247
},
{
"epoch": 0.06,
"learning_rate": 1.993868966639324e-05,
"loss": 0.6548,
"step": 248
},
{
"epoch": 0.06,
"learning_rate": 1.9937758171716468e-05,
"loss": 0.6411,
"step": 249
},
{
"epoch": 0.06,
"learning_rate": 1.9936819676226494e-05,
"loss": 0.6143,
"step": 250
},
{
"epoch": 0.07,
"learning_rate": 1.9935874180584452e-05,
"loss": 0.6377,
"step": 251
},
{
"epoch": 0.07,
"learning_rate": 1.9934921685456414e-05,
"loss": 0.6294,
"step": 252
},
{
"epoch": 0.07,
"learning_rate": 1.9933962191513382e-05,
"loss": 0.6494,
"step": 253
},
{
"epoch": 0.07,
"learning_rate": 1.993299569943128e-05,
"loss": 0.6274,
"step": 254
},
{
"epoch": 0.07,
"learning_rate": 1.993202220989098e-05,
"loss": 0.6353,
"step": 255
},
{
"epoch": 0.07,
"learning_rate": 1.9931041723578263e-05,
"loss": 0.6216,
"step": 256
},
{
"epoch": 0.07,
"learning_rate": 1.993005424118385e-05,
"loss": 0.6118,
"step": 257
},
{
"epoch": 0.07,
"learning_rate": 1.9929059763403392e-05,
"loss": 0.6094,
"step": 258
},
{
"epoch": 0.07,
"learning_rate": 1.9928058290937466e-05,
"loss": 0.6118,
"step": 259
},
{
"epoch": 0.07,
"learning_rate": 1.9927049824491566e-05,
"loss": 0.6255,
"step": 260
},
{
"epoch": 0.07,
"learning_rate": 1.9926034364776133e-05,
"loss": 0.6216,
"step": 261
},
{
"epoch": 0.07,
"learning_rate": 1.9925011912506517e-05,
"loss": 0.6187,
"step": 262
},
{
"epoch": 0.07,
"learning_rate": 1.9923982468403008e-05,
"loss": 0.6265,
"step": 263
},
{
"epoch": 0.07,
"learning_rate": 1.9922946033190808e-05,
"loss": 0.6177,
"step": 264
},
{
"epoch": 0.07,
"learning_rate": 1.9921902607600052e-05,
"loss": 0.6216,
"step": 265
},
{
"epoch": 0.07,
"learning_rate": 1.9920852192365797e-05,
"loss": 0.645,
"step": 266
},
{
"epoch": 0.07,
"learning_rate": 1.991979478822803e-05,
"loss": 0.5933,
"step": 267
},
{
"epoch": 0.07,
"learning_rate": 1.9918730395931648e-05,
"loss": 0.6411,
"step": 268
},
{
"epoch": 0.07,
"learning_rate": 1.9917659016226487e-05,
"loss": 0.625,
"step": 269
},
{
"epoch": 0.07,
"learning_rate": 1.9916580649867293e-05,
"loss": 0.666,
"step": 270
},
{
"epoch": 0.07,
"learning_rate": 1.991549529761374e-05,
"loss": 0.6406,
"step": 271
},
{
"epoch": 0.07,
"learning_rate": 1.9914402960230423e-05,
"loss": 0.6445,
"step": 272
},
{
"epoch": 0.07,
"learning_rate": 1.9913303638486855e-05,
"loss": 0.6045,
"step": 273
},
{
"epoch": 0.07,
"learning_rate": 1.991219733315747e-05,
"loss": 0.5938,
"step": 274
},
{
"epoch": 0.07,
"learning_rate": 1.9911084045021623e-05,
"loss": 0.6104,
"step": 275
},
{
"epoch": 0.07,
"learning_rate": 1.990996377486359e-05,
"loss": 0.6206,
"step": 276
},
{
"epoch": 0.07,
"learning_rate": 1.9908836523472562e-05,
"loss": 0.6147,
"step": 277
},
{
"epoch": 0.07,
"learning_rate": 1.990770229164265e-05,
"loss": 0.6167,
"step": 278
},
{
"epoch": 0.07,
"learning_rate": 1.9906561080172878e-05,
"loss": 0.6084,
"step": 279
},
{
"epoch": 0.07,
"learning_rate": 1.9905412889867194e-05,
"loss": 0.6323,
"step": 280
},
{
"epoch": 0.07,
"learning_rate": 1.990425772153446e-05,
"loss": 0.6191,
"step": 281
},
{
"epoch": 0.07,
"learning_rate": 1.990309557598845e-05,
"loss": 0.6133,
"step": 282
},
{
"epoch": 0.07,
"learning_rate": 1.990192645404786e-05,
"loss": 0.6431,
"step": 283
},
{
"epoch": 0.07,
"learning_rate": 1.990075035653629e-05,
"loss": 0.6025,
"step": 284
},
{
"epoch": 0.07,
"learning_rate": 1.989956728428227e-05,
"loss": 0.6147,
"step": 285
},
{
"epoch": 0.07,
"learning_rate": 1.9898377238119226e-05,
"loss": 0.6113,
"step": 286
},
{
"epoch": 0.07,
"learning_rate": 1.989718021888551e-05,
"loss": 0.5996,
"step": 287
},
{
"epoch": 0.07,
"learning_rate": 1.9895976227424377e-05,
"loss": 0.6343,
"step": 288
},
{
"epoch": 0.07,
"learning_rate": 1.9894765264584005e-05,
"loss": 0.6597,
"step": 289
},
{
"epoch": 0.08,
"learning_rate": 1.9893547331217466e-05,
"loss": 0.603,
"step": 290
},
{
"epoch": 0.08,
"learning_rate": 1.9892322428182764e-05,
"loss": 0.6055,
"step": 291
},
{
"epoch": 0.08,
"learning_rate": 1.9891090556342796e-05,
"loss": 0.623,
"step": 292
},
{
"epoch": 0.08,
"learning_rate": 1.9889851716565374e-05,
"loss": 0.627,
"step": 293
},
{
"epoch": 0.08,
"learning_rate": 1.9888605909723216e-05,
"loss": 0.6182,
"step": 294
},
{
"epoch": 0.08,
"learning_rate": 1.9887353136693957e-05,
"loss": 0.6006,
"step": 295
},
{
"epoch": 0.08,
"learning_rate": 1.988609339836013e-05,
"loss": 0.6113,
"step": 296
},
{
"epoch": 0.08,
"learning_rate": 1.9884826695609173e-05,
"loss": 0.5903,
"step": 297
},
{
"epoch": 0.08,
"learning_rate": 1.988355302933344e-05,
"loss": 0.6138,
"step": 298
},
{
"epoch": 0.08,
"learning_rate": 1.9882272400430192e-05,
"loss": 0.6099,
"step": 299
},
{
"epoch": 0.08,
"learning_rate": 1.9880984809801575e-05,
"loss": 0.6011,
"step": 300
},
{
"epoch": 0.08,
"learning_rate": 1.987969025835466e-05,
"loss": 0.6255,
"step": 301
},
{
"epoch": 0.08,
"learning_rate": 1.987838874700142e-05,
"loss": 0.6172,
"step": 302
},
{
"epoch": 0.08,
"learning_rate": 1.9877080276658713e-05,
"loss": 0.6348,
"step": 303
},
{
"epoch": 0.08,
"learning_rate": 1.9875764848248323e-05,
"loss": 0.6299,
"step": 304
},
{
"epoch": 0.08,
"learning_rate": 1.9874442462696913e-05,
"loss": 0.647,
"step": 305
},
{
"epoch": 0.08,
"learning_rate": 1.9873113120936074e-05,
"loss": 0.6362,
"step": 306
},
{
"epoch": 0.08,
"learning_rate": 1.9871776823902273e-05,
"loss": 0.6128,
"step": 307
},
{
"epoch": 0.08,
"learning_rate": 1.9870433572536883e-05,
"loss": 0.5991,
"step": 308
},
{
"epoch": 0.08,
"learning_rate": 1.9869083367786188e-05,
"loss": 0.6201,
"step": 309
},
{
"epoch": 0.08,
"learning_rate": 1.9867726210601353e-05,
"loss": 0.5967,
"step": 310
},
{
"epoch": 0.08,
"learning_rate": 1.9866362101938453e-05,
"loss": 0.5933,
"step": 311
},
{
"epoch": 0.08,
"learning_rate": 1.9864991042758456e-05,
"loss": 0.6074,
"step": 312
},
{
"epoch": 0.08,
"learning_rate": 1.9863613034027224e-05,
"loss": 0.5952,
"step": 313
},
{
"epoch": 0.08,
"learning_rate": 1.9862228076715524e-05,
"loss": 0.5864,
"step": 314
},
{
"epoch": 0.08,
"learning_rate": 1.9860836171799007e-05,
"loss": 0.6128,
"step": 315
},
{
"epoch": 0.08,
"learning_rate": 1.985943732025822e-05,
"loss": 0.6157,
"step": 316
},
{
"epoch": 0.08,
"learning_rate": 1.985803152307861e-05,
"loss": 0.5771,
"step": 317
},
{
"epoch": 0.08,
"learning_rate": 1.9856618781250513e-05,
"loss": 0.6206,
"step": 318
},
{
"epoch": 0.08,
"learning_rate": 1.9855199095769157e-05,
"loss": 0.6313,
"step": 319
},
{
"epoch": 0.08,
"learning_rate": 1.9853772467634665e-05,
"loss": 0.6528,
"step": 320
},
{
"epoch": 0.08,
"learning_rate": 1.9852338897852044e-05,
"loss": 0.6038,
"step": 321
},
{
"epoch": 0.08,
"learning_rate": 1.9850898387431194e-05,
"loss": 0.583,
"step": 322
},
{
"epoch": 0.08,
"learning_rate": 1.9849450937386914e-05,
"loss": 0.6279,
"step": 323
},
{
"epoch": 0.08,
"learning_rate": 1.9847996548738876e-05,
"loss": 0.5903,
"step": 324
},
{
"epoch": 0.08,
"learning_rate": 1.9846535222511648e-05,
"loss": 0.5903,
"step": 325
},
{
"epoch": 0.08,
"learning_rate": 1.9845066959734687e-05,
"loss": 0.6011,
"step": 326
},
{
"epoch": 0.08,
"learning_rate": 1.9843591761442334e-05,
"loss": 0.5981,
"step": 327
},
{
"epoch": 0.08,
"learning_rate": 1.9842109628673815e-05,
"loss": 0.626,
"step": 328
},
{
"epoch": 0.09,
"learning_rate": 1.984062056247324e-05,
"loss": 0.6187,
"step": 329
},
{
"epoch": 0.09,
"learning_rate": 1.9839124563889613e-05,
"loss": 0.623,
"step": 330
},
{
"epoch": 0.09,
"learning_rate": 1.983762163397681e-05,
"loss": 0.6372,
"step": 331
},
{
"epoch": 0.09,
"learning_rate": 1.9836111773793588e-05,
"loss": 0.6079,
"step": 332
},
{
"epoch": 0.09,
"learning_rate": 1.98345949844036e-05,
"loss": 0.624,
"step": 333
},
{
"epoch": 0.09,
"learning_rate": 1.983307126687537e-05,
"loss": 0.6016,
"step": 334
},
{
"epoch": 0.09,
"learning_rate": 1.983154062228231e-05,
"loss": 0.5991,
"step": 335
},
{
"epoch": 0.09,
"learning_rate": 1.98300030517027e-05,
"loss": 0.6445,
"step": 336
},
{
"epoch": 0.09,
"learning_rate": 1.982845855621971e-05,
"loss": 0.6011,
"step": 337
},
{
"epoch": 0.09,
"learning_rate": 1.9826907136921382e-05,
"loss": 0.6401,
"step": 338
},
{
"epoch": 0.09,
"learning_rate": 1.982534879490064e-05,
"loss": 0.6362,
"step": 339
},
{
"epoch": 0.09,
"learning_rate": 1.982378353125528e-05,
"loss": 0.5972,
"step": 340
},
{
"epoch": 0.09,
"learning_rate": 1.982221134708799e-05,
"loss": 0.5752,
"step": 341
},
{
"epoch": 0.09,
"learning_rate": 1.9820632243506304e-05,
"loss": 0.606,
"step": 342
},
{
"epoch": 0.09,
"learning_rate": 1.981904622162265e-05,
"loss": 0.6143,
"step": 343
},
{
"epoch": 0.09,
"learning_rate": 1.9817453282554334e-05,
"loss": 0.5938,
"step": 344
},
{
"epoch": 0.09,
"learning_rate": 1.9815853427423524e-05,
"loss": 0.6074,
"step": 345
},
{
"epoch": 0.09,
"learning_rate": 1.9814246657357263e-05,
"loss": 0.6265,
"step": 346
},
{
"epoch": 0.09,
"learning_rate": 1.9812632973487463e-05,
"loss": 0.5986,
"step": 347
},
{
"epoch": 0.09,
"learning_rate": 1.9811012376950915e-05,
"loss": 0.6089,
"step": 348
},
{
"epoch": 0.09,
"learning_rate": 1.980938486888927e-05,
"loss": 0.6113,
"step": 349
},
{
"epoch": 0.09,
"learning_rate": 1.9807750450449055e-05,
"loss": 0.5923,
"step": 350
},
{
"epoch": 0.09,
"learning_rate": 1.9806109122781662e-05,
"loss": 0.6064,
"step": 351
},
{
"epoch": 0.09,
"learning_rate": 1.980446088704335e-05,
"loss": 0.6182,
"step": 352
},
{
"epoch": 0.09,
"learning_rate": 1.980280574439524e-05,
"loss": 0.5703,
"step": 353
},
{
"epoch": 0.09,
"learning_rate": 1.9801143696003334e-05,
"loss": 0.6211,
"step": 354
},
{
"epoch": 0.09,
"learning_rate": 1.9799474743038482e-05,
"loss": 0.5996,
"step": 355
},
{
"epoch": 0.09,
"learning_rate": 1.9797798886676407e-05,
"loss": 0.627,
"step": 356
},
{
"epoch": 0.09,
"learning_rate": 1.9796116128097693e-05,
"loss": 0.5879,
"step": 357
},
{
"epoch": 0.09,
"learning_rate": 1.979442646848778e-05,
"loss": 0.5962,
"step": 358
},
{
"epoch": 0.09,
"learning_rate": 1.9792729909036983e-05,
"loss": 0.6118,
"step": 359
},
{
"epoch": 0.09,
"learning_rate": 1.9791026450940468e-05,
"loss": 0.603,
"step": 360
},
{
"epoch": 0.09,
"learning_rate": 1.9789316095398266e-05,
"loss": 0.5981,
"step": 361
},
{
"epoch": 0.09,
"learning_rate": 1.9787598843615262e-05,
"loss": 0.6094,
"step": 362
},
{
"epoch": 0.09,
"learning_rate": 1.97858746968012e-05,
"loss": 0.6284,
"step": 363
},
{
"epoch": 0.09,
"learning_rate": 1.9784143656170688e-05,
"loss": 0.5781,
"step": 364
},
{
"epoch": 0.09,
"learning_rate": 1.9782405722943182e-05,
"loss": 0.627,
"step": 365
},
{
"epoch": 0.09,
"learning_rate": 1.9780660898342994e-05,
"loss": 0.5981,
"step": 366
},
{
"epoch": 0.1,
"learning_rate": 1.97789091835993e-05,
"loss": 0.6099,
"step": 367
},
{
"epoch": 0.1,
"learning_rate": 1.977715057994612e-05,
"loss": 0.5864,
"step": 368
},
{
"epoch": 0.1,
"learning_rate": 1.977538508862233e-05,
"loss": 0.6104,
"step": 369
},
{
"epoch": 0.1,
"learning_rate": 1.977361271087166e-05,
"loss": 0.6289,
"step": 370
},
{
"epoch": 0.1,
"learning_rate": 1.9771833447942684e-05,
"loss": 0.5718,
"step": 371
},
{
"epoch": 0.1,
"learning_rate": 1.9770047301088846e-05,
"loss": 0.5796,
"step": 372
},
{
"epoch": 0.1,
"learning_rate": 1.9768254271568415e-05,
"loss": 0.5972,
"step": 373
},
{
"epoch": 0.1,
"learning_rate": 1.9766454360644517e-05,
"loss": 0.5835,
"step": 374
},
{
"epoch": 0.1,
"learning_rate": 1.976464756958514e-05,
"loss": 0.5962,
"step": 375
},
{
"epoch": 0.1,
"learning_rate": 1.97628338996631e-05,
"loss": 0.5767,
"step": 376
},
{
"epoch": 0.1,
"learning_rate": 1.9761013352156064e-05,
"loss": 0.6196,
"step": 377
},
{
"epoch": 0.1,
"learning_rate": 1.9759185928346546e-05,
"loss": 0.5898,
"step": 378
},
{
"epoch": 0.1,
"learning_rate": 1.9757351629521908e-05,
"loss": 0.6064,
"step": 379
},
{
"epoch": 0.1,
"learning_rate": 1.975551045697435e-05,
"loss": 0.6128,
"step": 380
},
{
"epoch": 0.1,
"learning_rate": 1.9753662412000915e-05,
"loss": 0.5918,
"step": 381
},
{
"epoch": 0.1,
"learning_rate": 1.9751807495903484e-05,
"loss": 0.5854,
"step": 382
},
{
"epoch": 0.1,
"learning_rate": 1.974994570998879e-05,
"loss": 0.6006,
"step": 383
},
{
"epoch": 0.1,
"learning_rate": 1.9748077055568392e-05,
"loss": 0.5854,
"step": 384
},
{
"epoch": 0.1,
"learning_rate": 1.9746201533958698e-05,
"loss": 0.5864,
"step": 385
},
{
"epoch": 0.1,
"learning_rate": 1.9744319146480947e-05,
"loss": 0.6021,
"step": 386
},
{
"epoch": 0.1,
"learning_rate": 1.9742429894461214e-05,
"loss": 0.5605,
"step": 387
},
{
"epoch": 0.1,
"learning_rate": 1.974053377923042e-05,
"loss": 0.5762,
"step": 388
},
{
"epoch": 0.1,
"learning_rate": 1.9738630802124307e-05,
"loss": 0.5688,
"step": 389
},
{
"epoch": 0.1,
"learning_rate": 1.973672096448346e-05,
"loss": 0.5942,
"step": 390
},
{
"epoch": 0.1,
"learning_rate": 1.9734804267653294e-05,
"loss": 0.5859,
"step": 391
},
{
"epoch": 0.1,
"learning_rate": 1.973288071298406e-05,
"loss": 0.5977,
"step": 392
},
{
"epoch": 0.1,
"learning_rate": 1.9730950301830837e-05,
"loss": 0.5859,
"step": 393
},
{
"epoch": 0.1,
"learning_rate": 1.972901303555353e-05,
"loss": 0.6147,
"step": 394
},
{
"epoch": 0.1,
"learning_rate": 1.972706891551688e-05,
"loss": 0.6338,
"step": 395
},
{
"epoch": 0.1,
"learning_rate": 1.9725117943090453e-05,
"loss": 0.5996,
"step": 396
},
{
"epoch": 0.1,
"learning_rate": 1.9723160119648644e-05,
"loss": 0.5796,
"step": 397
},
{
"epoch": 0.1,
"learning_rate": 1.972119544657067e-05,
"loss": 0.5811,
"step": 398
},
{
"epoch": 0.1,
"learning_rate": 1.971922392524058e-05,
"loss": 0.5879,
"step": 399
},
{
"epoch": 0.1,
"learning_rate": 1.971724555704724e-05,
"loss": 0.6067,
"step": 400
},
{
"epoch": 0.1,
"learning_rate": 1.971526034338435e-05,
"loss": 0.5825,
"step": 401
},
{
"epoch": 0.1,
"learning_rate": 1.9713268285650415e-05,
"loss": 0.6055,
"step": 402
},
{
"epoch": 0.1,
"learning_rate": 1.9711269385248783e-05,
"loss": 0.5874,
"step": 403
},
{
"epoch": 0.1,
"learning_rate": 1.9709263643587607e-05,
"loss": 0.584,
"step": 404
},
{
"epoch": 0.1,
"learning_rate": 1.970725106207986e-05,
"loss": 0.585,
"step": 405
},
{
"epoch": 0.11,
"learning_rate": 1.9705231642143342e-05,
"loss": 0.5752,
"step": 406
},
{
"epoch": 0.11,
"learning_rate": 1.9703205385200666e-05,
"loss": 0.603,
"step": 407
},
{
"epoch": 0.11,
"learning_rate": 1.970117229267926e-05,
"loss": 0.605,
"step": 408
},
{
"epoch": 0.11,
"learning_rate": 1.9699132366011366e-05,
"loss": 0.6152,
"step": 409
},
{
"epoch": 0.11,
"learning_rate": 1.9697085606634047e-05,
"loss": 0.6099,
"step": 410
},
{
"epoch": 0.11,
"learning_rate": 1.9695032015989174e-05,
"loss": 0.6191,
"step": 411
},
{
"epoch": 0.11,
"learning_rate": 1.969297159552343e-05,
"loss": 0.5879,
"step": 412
},
{
"epoch": 0.11,
"learning_rate": 1.9690904346688318e-05,
"loss": 0.5879,
"step": 413
},
{
"epoch": 0.11,
"learning_rate": 1.9688830270940136e-05,
"loss": 0.5991,
"step": 414
},
{
"epoch": 0.11,
"learning_rate": 1.9686749369740005e-05,
"loss": 0.585,
"step": 415
},
{
"epoch": 0.11,
"learning_rate": 1.968466164455385e-05,
"loss": 0.5781,
"step": 416
},
{
"epoch": 0.11,
"learning_rate": 1.96825670968524e-05,
"loss": 0.5842,
"step": 417
},
{
"epoch": 0.11,
"learning_rate": 1.968046572811119e-05,
"loss": 0.5967,
"step": 418
},
{
"epoch": 0.11,
"learning_rate": 1.9678357539810567e-05,
"loss": 0.606,
"step": 419
},
{
"epoch": 0.11,
"learning_rate": 1.967624253343568e-05,
"loss": 0.5967,
"step": 420
},
{
"epoch": 0.11,
"learning_rate": 1.9674120710476474e-05,
"loss": 0.5962,
"step": 421
},
{
"epoch": 0.11,
"learning_rate": 1.9671992072427702e-05,
"loss": 0.5957,
"step": 422
},
{
"epoch": 0.11,
"learning_rate": 1.966985662078892e-05,
"loss": 0.5728,
"step": 423
},
{
"epoch": 0.11,
"learning_rate": 1.9667714357064486e-05,
"loss": 0.5986,
"step": 424
},
{
"epoch": 0.11,
"learning_rate": 1.9665565282763543e-05,
"loss": 0.5894,
"step": 425
},
{
"epoch": 0.11,
"learning_rate": 1.966340939940004e-05,
"loss": 0.5786,
"step": 426
},
{
"epoch": 0.11,
"learning_rate": 1.966124670849273e-05,
"loss": 0.5957,
"step": 427
},
{
"epoch": 0.11,
"learning_rate": 1.965907721156515e-05,
"loss": 0.6069,
"step": 428
},
{
"epoch": 0.11,
"learning_rate": 1.9656900910145648e-05,
"loss": 0.6006,
"step": 429
},
{
"epoch": 0.11,
"learning_rate": 1.9654717805767342e-05,
"loss": 0.5737,
"step": 430
},
{
"epoch": 0.11,
"learning_rate": 1.9652527899968155e-05,
"loss": 0.563,
"step": 431
},
{
"epoch": 0.11,
"learning_rate": 1.965033119429081e-05,
"loss": 0.5791,
"step": 432
},
{
"epoch": 0.11,
"learning_rate": 1.9648127690282805e-05,
"loss": 0.582,
"step": 433
},
{
"epoch": 0.11,
"learning_rate": 1.964591738949644e-05,
"loss": 0.5786,
"step": 434
},
{
"epoch": 0.11,
"learning_rate": 1.9643700293488788e-05,
"loss": 0.5742,
"step": 435
},
{
"epoch": 0.11,
"learning_rate": 1.9641476403821724e-05,
"loss": 0.5793,
"step": 436
},
{
"epoch": 0.11,
"learning_rate": 1.9639245722061902e-05,
"loss": 0.6035,
"step": 437
},
{
"epoch": 0.11,
"learning_rate": 1.963700824978076e-05,
"loss": 0.5811,
"step": 438
},
{
"epoch": 0.11,
"learning_rate": 1.963476398855452e-05,
"loss": 0.5601,
"step": 439
},
{
"epoch": 0.11,
"learning_rate": 1.9632512939964193e-05,
"loss": 0.5684,
"step": 440
},
{
"epoch": 0.11,
"learning_rate": 1.9630255105595563e-05,
"loss": 0.5835,
"step": 441
},
{
"epoch": 0.11,
"learning_rate": 1.96279904870392e-05,
"loss": 0.5962,
"step": 442
},
{
"epoch": 0.11,
"learning_rate": 1.9625719085890445e-05,
"loss": 0.5791,
"step": 443
},
{
"epoch": 0.12,
"learning_rate": 1.962344090374943e-05,
"loss": 0.5747,
"step": 444
},
{
"epoch": 0.12,
"learning_rate": 1.9621155942221048e-05,
"loss": 0.5664,
"step": 445
},
{
"epoch": 0.12,
"learning_rate": 1.961886420291499e-05,
"loss": 0.5923,
"step": 446
},
{
"epoch": 0.12,
"learning_rate": 1.9616565687445694e-05,
"loss": 0.5635,
"step": 447
},
{
"epoch": 0.12,
"learning_rate": 1.96142603974324e-05,
"loss": 0.5559,
"step": 448
},
{
"epoch": 0.12,
"learning_rate": 1.9611948334499097e-05,
"loss": 0.5972,
"step": 449
},
{
"epoch": 0.12,
"learning_rate": 1.9609629500274554e-05,
"loss": 0.5703,
"step": 450
},
{
"epoch": 0.12,
"learning_rate": 1.9607303896392318e-05,
"loss": 0.5791,
"step": 451
},
{
"epoch": 0.12,
"learning_rate": 1.9604971524490692e-05,
"loss": 0.5854,
"step": 452
},
{
"epoch": 0.12,
"learning_rate": 1.9602632386212758e-05,
"loss": 0.5845,
"step": 453
},
{
"epoch": 0.12,
"learning_rate": 1.9600286483206358e-05,
"loss": 0.5898,
"step": 454
},
{
"epoch": 0.12,
"learning_rate": 1.9597933817124096e-05,
"loss": 0.6123,
"step": 455
},
{
"epoch": 0.12,
"learning_rate": 1.959557438962335e-05,
"loss": 0.5874,
"step": 456
},
{
"epoch": 0.12,
"learning_rate": 1.9593208202366257e-05,
"loss": 0.6094,
"step": 457
},
{
"epoch": 0.12,
"learning_rate": 1.9590835257019715e-05,
"loss": 0.5857,
"step": 458
},
{
"epoch": 0.12,
"learning_rate": 1.958845555525538e-05,
"loss": 0.5884,
"step": 459
},
{
"epoch": 0.12,
"learning_rate": 1.9586069098749677e-05,
"loss": 0.5649,
"step": 460
},
{
"epoch": 0.12,
"learning_rate": 1.958367588918378e-05,
"loss": 0.5669,
"step": 461
},
{
"epoch": 0.12,
"learning_rate": 1.9581275928243624e-05,
"loss": 0.5806,
"step": 462
},
{
"epoch": 0.12,
"learning_rate": 1.95788692176199e-05,
"loss": 0.5811,
"step": 463
},
{
"epoch": 0.12,
"learning_rate": 1.9576455759008052e-05,
"loss": 0.5823,
"step": 464
},
{
"epoch": 0.12,
"learning_rate": 1.9574035554108285e-05,
"loss": 0.5737,
"step": 465
},
{
"epoch": 0.12,
"learning_rate": 1.9571608604625544e-05,
"loss": 0.5801,
"step": 466
},
{
"epoch": 0.12,
"learning_rate": 1.9569174912269542e-05,
"loss": 0.5723,
"step": 467
},
{
"epoch": 0.12,
"learning_rate": 1.9566734478754724e-05,
"loss": 0.5947,
"step": 468
},
{
"epoch": 0.12,
"learning_rate": 1.9564287305800293e-05,
"loss": 0.5718,
"step": 469
},
{
"epoch": 0.12,
"learning_rate": 1.9561833395130207e-05,
"loss": 0.5688,
"step": 470
},
{
"epoch": 0.12,
"learning_rate": 1.9559372748473157e-05,
"loss": 0.5732,
"step": 471
},
{
"epoch": 0.12,
"learning_rate": 1.9556905367562584e-05,
"loss": 0.6011,
"step": 472
},
{
"epoch": 0.12,
"learning_rate": 1.9554431254136676e-05,
"loss": 0.5723,
"step": 473
},
{
"epoch": 0.12,
"learning_rate": 1.9551950409938364e-05,
"loss": 0.5649,
"step": 474
},
{
"epoch": 0.12,
"learning_rate": 1.9549462836715313e-05,
"loss": 0.5874,
"step": 475
},
{
"epoch": 0.12,
"learning_rate": 1.954696853621994e-05,
"loss": 0.5903,
"step": 476
},
{
"epoch": 0.12,
"learning_rate": 1.954446751020939e-05,
"loss": 0.574,
"step": 477
},
{
"epoch": 0.12,
"learning_rate": 1.954195976044555e-05,
"loss": 0.5645,
"step": 478
},
{
"epoch": 0.12,
"learning_rate": 1.953944528869505e-05,
"loss": 0.562,
"step": 479
},
{
"epoch": 0.12,
"learning_rate": 1.9536924096729253e-05,
"loss": 0.562,
"step": 480
},
{
"epoch": 0.12,
"learning_rate": 1.953439618632424e-05,
"loss": 0.5977,
"step": 481
},
{
"epoch": 0.12,
"learning_rate": 1.953186155926085e-05,
"loss": 0.5757,
"step": 482
},
{
"epoch": 0.13,
"learning_rate": 1.9529320217324637e-05,
"loss": 0.5801,
"step": 483
},
{
"epoch": 0.13,
"learning_rate": 1.9526772162305893e-05,
"loss": 0.5659,
"step": 484
},
{
"epoch": 0.13,
"learning_rate": 1.9524217395999627e-05,
"loss": 0.5381,
"step": 485
},
{
"epoch": 0.13,
"learning_rate": 1.9521655920205596e-05,
"loss": 0.5591,
"step": 486
},
{
"epoch": 0.13,
"learning_rate": 1.9519087736728267e-05,
"loss": 0.5903,
"step": 487
},
{
"epoch": 0.13,
"learning_rate": 1.9516512847376844e-05,
"loss": 0.5952,
"step": 488
},
{
"epoch": 0.13,
"learning_rate": 1.951393125396524e-05,
"loss": 0.5806,
"step": 489
},
{
"epoch": 0.13,
"learning_rate": 1.9511342958312106e-05,
"loss": 0.563,
"step": 490
},
{
"epoch": 0.13,
"learning_rate": 1.950874796224081e-05,
"loss": 0.5767,
"step": 491
},
{
"epoch": 0.13,
"learning_rate": 1.950614626757943e-05,
"loss": 0.5806,
"step": 492
},
{
"epoch": 0.13,
"learning_rate": 1.9503537876160782e-05,
"loss": 0.5586,
"step": 493
},
{
"epoch": 0.13,
"learning_rate": 1.9500922789822382e-05,
"loss": 0.5869,
"step": 494
},
{
"epoch": 0.13,
"learning_rate": 1.9498301010406473e-05,
"loss": 0.5742,
"step": 495
},
{
"epoch": 0.13,
"learning_rate": 1.949567253976001e-05,
"loss": 0.5603,
"step": 496
},
{
"epoch": 0.13,
"learning_rate": 1.9493037379734658e-05,
"loss": 0.5527,
"step": 497
},
{
"epoch": 0.13,
"learning_rate": 1.9490395532186798e-05,
"loss": 0.5542,
"step": 498
},
{
"epoch": 0.13,
"learning_rate": 1.9487746998977525e-05,
"loss": 0.561,
"step": 499
},
{
"epoch": 0.13,
"learning_rate": 1.9485091781972644e-05,
"loss": 0.5669,
"step": 500
},
{
"epoch": 0.13,
"learning_rate": 1.9482429883042653e-05,
"loss": 0.5898,
"step": 501
},
{
"epoch": 0.13,
"learning_rate": 1.947976130406278e-05,
"loss": 0.5781,
"step": 502
},
{
"epoch": 0.13,
"learning_rate": 1.9477086046912945e-05,
"loss": 0.5903,
"step": 503
},
{
"epoch": 0.13,
"learning_rate": 1.9474404113477775e-05,
"loss": 0.5698,
"step": 504
},
{
"epoch": 0.13,
"learning_rate": 1.9471715505646607e-05,
"loss": 0.562,
"step": 505
},
{
"epoch": 0.13,
"learning_rate": 1.9469020225313465e-05,
"loss": 0.5603,
"step": 506
},
{
"epoch": 0.13,
"learning_rate": 1.946631827437709e-05,
"loss": 0.585,
"step": 507
},
{
"epoch": 0.13,
"learning_rate": 1.9463609654740906e-05,
"loss": 0.5659,
"step": 508
},
{
"epoch": 0.13,
"learning_rate": 1.9460894368313052e-05,
"loss": 0.563,
"step": 509
},
{
"epoch": 0.13,
"learning_rate": 1.9458172417006347e-05,
"loss": 0.5845,
"step": 510
},
{
"epoch": 0.13,
"learning_rate": 1.9455443802738323e-05,
"loss": 0.5898,
"step": 511
},
{
"epoch": 0.13,
"learning_rate": 1.945270852743119e-05,
"loss": 0.5657,
"step": 512
},
{
"epoch": 0.13,
"learning_rate": 1.9449966593011858e-05,
"loss": 0.562,
"step": 513
},
{
"epoch": 0.13,
"learning_rate": 1.9447218001411924e-05,
"loss": 0.5757,
"step": 514
},
{
"epoch": 0.13,
"learning_rate": 1.9444462754567682e-05,
"loss": 0.5322,
"step": 515
},
{
"epoch": 0.13,
"learning_rate": 1.9441700854420112e-05,
"loss": 0.5747,
"step": 516
},
{
"epoch": 0.13,
"learning_rate": 1.9438932302914868e-05,
"loss": 0.564,
"step": 517
},
{
"epoch": 0.13,
"learning_rate": 1.943615710200231e-05,
"loss": 0.5942,
"step": 518
},
{
"epoch": 0.13,
"learning_rate": 1.943337525363747e-05,
"loss": 0.5591,
"step": 519
},
{
"epoch": 0.13,
"learning_rate": 1.9430586759780065e-05,
"loss": 0.5933,
"step": 520
},
{
"epoch": 0.14,
"learning_rate": 1.9427791622394496e-05,
"loss": 0.5654,
"step": 521
},
{
"epoch": 0.14,
"learning_rate": 1.942498984344984e-05,
"loss": 0.5854,
"step": 522
},
{
"epoch": 0.14,
"learning_rate": 1.9422181424919858e-05,
"loss": 0.5981,
"step": 523
},
{
"epoch": 0.14,
"learning_rate": 1.9419366368782983e-05,
"loss": 0.5566,
"step": 524
},
{
"epoch": 0.14,
"learning_rate": 1.941654467702233e-05,
"loss": 0.5918,
"step": 525
},
{
"epoch": 0.14,
"learning_rate": 1.9413716351625678e-05,
"loss": 0.562,
"step": 526
},
{
"epoch": 0.14,
"learning_rate": 1.9410881394585493e-05,
"loss": 0.5544,
"step": 527
},
{
"epoch": 0.14,
"learning_rate": 1.94080398078989e-05,
"loss": 0.5967,
"step": 528
},
{
"epoch": 0.14,
"learning_rate": 1.940519159356771e-05,
"loss": 0.5479,
"step": 529
},
{
"epoch": 0.14,
"learning_rate": 1.9402336753598387e-05,
"loss": 0.5825,
"step": 530
},
{
"epoch": 0.14,
"learning_rate": 1.9399475290002066e-05,
"loss": 0.5571,
"step": 531
},
{
"epoch": 0.14,
"learning_rate": 1.9396607204794554e-05,
"loss": 0.6006,
"step": 532
},
{
"epoch": 0.14,
"learning_rate": 1.939373249999632e-05,
"loss": 0.5464,
"step": 533
},
{
"epoch": 0.14,
"learning_rate": 1.9390851177632496e-05,
"loss": 0.5989,
"step": 534
},
{
"epoch": 0.14,
"learning_rate": 1.9387963239732876e-05,
"loss": 0.5771,
"step": 535
},
{
"epoch": 0.14,
"learning_rate": 1.9385068688331913e-05,
"loss": 0.5928,
"step": 536
},
{
"epoch": 0.14,
"learning_rate": 1.9382167525468722e-05,
"loss": 0.5825,
"step": 537
},
{
"epoch": 0.14,
"learning_rate": 1.937925975318707e-05,
"loss": 0.5576,
"step": 538
},
{
"epoch": 0.14,
"learning_rate": 1.9376345373535386e-05,
"loss": 0.582,
"step": 539
},
{
"epoch": 0.14,
"learning_rate": 1.9373424388566758e-05,
"loss": 0.5498,
"step": 540
},
{
"epoch": 0.14,
"learning_rate": 1.937049680033891e-05,
"loss": 0.5503,
"step": 541
},
{
"epoch": 0.14,
"learning_rate": 1.9367562610914233e-05,
"loss": 0.5825,
"step": 542
},
{
"epoch": 0.14,
"learning_rate": 1.9364621822359764e-05,
"loss": 0.5732,
"step": 543
},
{
"epoch": 0.14,
"learning_rate": 1.936167443674719e-05,
"loss": 0.5684,
"step": 544
},
{
"epoch": 0.14,
"learning_rate": 1.935872045615284e-05,
"loss": 0.5566,
"step": 545
},
{
"epoch": 0.14,
"learning_rate": 1.93557598826577e-05,
"loss": 0.5386,
"step": 546
},
{
"epoch": 0.14,
"learning_rate": 1.9352792718347386e-05,
"loss": 0.5811,
"step": 547
},
{
"epoch": 0.14,
"learning_rate": 1.9349818965312165e-05,
"loss": 0.5918,
"step": 548
},
{
"epoch": 0.14,
"learning_rate": 1.934683862564695e-05,
"loss": 0.5378,
"step": 549
},
{
"epoch": 0.14,
"learning_rate": 1.934385170145129e-05,
"loss": 0.5713,
"step": 550
},
{
"epoch": 0.14,
"learning_rate": 1.9340858194829367e-05,
"loss": 0.5723,
"step": 551
},
{
"epoch": 0.14,
"learning_rate": 1.9337858107890003e-05,
"loss": 0.5669,
"step": 552
},
{
"epoch": 0.14,
"learning_rate": 1.9334851442746665e-05,
"loss": 0.5684,
"step": 553
},
{
"epoch": 0.14,
"learning_rate": 1.933183820151744e-05,
"loss": 0.5903,
"step": 554
},
{
"epoch": 0.14,
"learning_rate": 1.932881838632506e-05,
"loss": 0.5928,
"step": 555
},
{
"epoch": 0.14,
"learning_rate": 1.9325791999296873e-05,
"loss": 0.5754,
"step": 556
},
{
"epoch": 0.14,
"learning_rate": 1.9322759042564875e-05,
"loss": 0.5518,
"step": 557
},
{
"epoch": 0.14,
"learning_rate": 1.9319719518265677e-05,
"loss": 0.5786,
"step": 558
},
{
"epoch": 0.14,
"learning_rate": 1.931667342854052e-05,
"loss": 0.5991,
"step": 559
},
{
"epoch": 0.15,
"learning_rate": 1.9313620775535275e-05,
"loss": 0.5752,
"step": 560
},
{
"epoch": 0.15,
"learning_rate": 1.931056156140042e-05,
"loss": 0.5811,
"step": 561
},
{
"epoch": 0.15,
"learning_rate": 1.9307495788291088e-05,
"loss": 0.5962,
"step": 562
},
{
"epoch": 0.15,
"learning_rate": 1.9304423458366998e-05,
"loss": 0.5535,
"step": 563
},
{
"epoch": 0.15,
"learning_rate": 1.9301344573792503e-05,
"loss": 0.5337,
"step": 564
},
{
"epoch": 0.15,
"learning_rate": 1.9298259136736575e-05,
"loss": 0.5718,
"step": 565
},
{
"epoch": 0.15,
"learning_rate": 1.92951671493728e-05,
"loss": 0.55,
"step": 566
},
{
"epoch": 0.15,
"learning_rate": 1.9292068613879377e-05,
"loss": 0.5732,
"step": 567
},
{
"epoch": 0.15,
"learning_rate": 1.928896353243912e-05,
"loss": 0.5898,
"step": 568
},
{
"epoch": 0.15,
"learning_rate": 1.9285851907239453e-05,
"loss": 0.5386,
"step": 569
},
{
"epoch": 0.15,
"learning_rate": 1.928273374047241e-05,
"loss": 0.5532,
"step": 570
},
{
"epoch": 0.15,
"learning_rate": 1.9279609034334635e-05,
"loss": 0.5713,
"step": 571
},
{
"epoch": 0.15,
"learning_rate": 1.9276477791027374e-05,
"loss": 0.5693,
"step": 572
},
{
"epoch": 0.15,
"learning_rate": 1.9273340012756486e-05,
"loss": 0.5776,
"step": 573
},
{
"epoch": 0.15,
"learning_rate": 1.9270195701732424e-05,
"loss": 0.5771,
"step": 574
},
{
"epoch": 0.15,
"learning_rate": 1.9267044860170253e-05,
"loss": 0.582,
"step": 575
},
{
"epoch": 0.15,
"learning_rate": 1.9263887490289634e-05,
"loss": 0.5708,
"step": 576
},
{
"epoch": 0.15,
"learning_rate": 1.9260723594314826e-05,
"loss": 0.5481,
"step": 577
},
{
"epoch": 0.15,
"learning_rate": 1.925755317447468e-05,
"loss": 0.6055,
"step": 578
},
{
"epoch": 0.15,
"learning_rate": 1.9254376233002657e-05,
"loss": 0.5713,
"step": 579
},
{
"epoch": 0.15,
"learning_rate": 1.9251192772136808e-05,
"loss": 0.5874,
"step": 580
},
{
"epoch": 0.15,
"learning_rate": 1.924800279411976e-05,
"loss": 0.5967,
"step": 581
},
{
"epoch": 0.15,
"learning_rate": 1.9244806301198752e-05,
"loss": 0.605,
"step": 582
},
{
"epoch": 0.15,
"learning_rate": 1.9241603295625605e-05,
"loss": 0.5767,
"step": 583
},
{
"epoch": 0.15,
"learning_rate": 1.9238393779656727e-05,
"loss": 0.5684,
"step": 584
},
{
"epoch": 0.15,
"learning_rate": 1.9235177755553117e-05,
"loss": 0.5527,
"step": 585
},
{
"epoch": 0.15,
"learning_rate": 1.9231955225580346e-05,
"loss": 0.5701,
"step": 586
},
{
"epoch": 0.15,
"learning_rate": 1.9228726192008578e-05,
"loss": 0.5723,
"step": 587
},
{
"epoch": 0.15,
"learning_rate": 1.9225490657112565e-05,
"loss": 0.5442,
"step": 588
},
{
"epoch": 0.15,
"learning_rate": 1.9222248623171628e-05,
"loss": 0.5601,
"step": 589
},
{
"epoch": 0.15,
"learning_rate": 1.921900009246967e-05,
"loss": 0.5371,
"step": 590
},
{
"epoch": 0.15,
"learning_rate": 1.9215745067295168e-05,
"loss": 0.563,
"step": 591
},
{
"epoch": 0.15,
"learning_rate": 1.9212483549941175e-05,
"loss": 0.5481,
"step": 592
},
{
"epoch": 0.15,
"learning_rate": 1.920921554270533e-05,
"loss": 0.5215,
"step": 593
},
{
"epoch": 0.15,
"learning_rate": 1.9205941047889824e-05,
"loss": 0.5654,
"step": 594
},
{
"epoch": 0.15,
"learning_rate": 1.9202660067801425e-05,
"loss": 0.5605,
"step": 595
},
{
"epoch": 0.15,
"learning_rate": 1.919937260475148e-05,
"loss": 0.543,
"step": 596
},
{
"epoch": 0.15,
"learning_rate": 1.9196078661055893e-05,
"loss": 0.561,
"step": 597
},
{
"epoch": 0.15,
"learning_rate": 1.9192778239035127e-05,
"loss": 0.5464,
"step": 598
},
{
"epoch": 0.16,
"learning_rate": 1.9189471341014232e-05,
"loss": 0.5562,
"step": 599
},
{
"epoch": 0.16,
"learning_rate": 1.9186157969322795e-05,
"loss": 0.5776,
"step": 600
},
{
"epoch": 0.16,
"learning_rate": 1.9182838126294977e-05,
"loss": 0.5583,
"step": 601
},
{
"epoch": 0.16,
"learning_rate": 1.917951181426949e-05,
"loss": 0.541,
"step": 602
},
{
"epoch": 0.16,
"learning_rate": 1.9176179035589618e-05,
"loss": 0.5742,
"step": 603
},
{
"epoch": 0.16,
"learning_rate": 1.9172839792603183e-05,
"loss": 0.5503,
"step": 604
},
{
"epoch": 0.16,
"learning_rate": 1.9169494087662567e-05,
"loss": 0.5664,
"step": 605
},
{
"epoch": 0.16,
"learning_rate": 1.916614192312471e-05,
"loss": 0.5757,
"step": 606
},
{
"epoch": 0.16,
"learning_rate": 1.9162783301351096e-05,
"loss": 0.5471,
"step": 607
},
{
"epoch": 0.16,
"learning_rate": 1.915941822470776e-05,
"loss": 0.5532,
"step": 608
},
{
"epoch": 0.16,
"learning_rate": 1.9156046695565286e-05,
"loss": 0.5444,
"step": 609
},
{
"epoch": 0.16,
"learning_rate": 1.91526687162988e-05,
"loss": 0.5684,
"step": 610
},
{
"epoch": 0.16,
"learning_rate": 1.914928428928797e-05,
"loss": 0.5522,
"step": 611
},
{
"epoch": 0.16,
"learning_rate": 1.914589341691702e-05,
"loss": 0.5405,
"step": 612
},
{
"epoch": 0.16,
"learning_rate": 1.9142496101574698e-05,
"loss": 0.5728,
"step": 613
},
{
"epoch": 0.16,
"learning_rate": 1.9139092345654294e-05,
"loss": 0.5854,
"step": 614
},
{
"epoch": 0.16,
"learning_rate": 1.9135682151553647e-05,
"loss": 0.5669,
"step": 615
},
{
"epoch": 0.16,
"learning_rate": 1.9132265521675114e-05,
"loss": 0.5967,
"step": 616
},
{
"epoch": 0.16,
"learning_rate": 1.9128842458425602e-05,
"loss": 0.5388,
"step": 617
},
{
"epoch": 0.16,
"learning_rate": 1.9125412964216538e-05,
"loss": 0.5364,
"step": 618
},
{
"epoch": 0.16,
"learning_rate": 1.9121977041463884e-05,
"loss": 0.5371,
"step": 619
},
{
"epoch": 0.16,
"learning_rate": 1.9118534692588137e-05,
"loss": 0.5728,
"step": 620
},
{
"epoch": 0.16,
"learning_rate": 1.911508592001431e-05,
"loss": 0.541,
"step": 621
},
{
"epoch": 0.16,
"learning_rate": 1.9111630726171944e-05,
"loss": 0.5413,
"step": 622
},
{
"epoch": 0.16,
"learning_rate": 1.9108169113495113e-05,
"loss": 0.5444,
"step": 623
},
{
"epoch": 0.16,
"learning_rate": 1.9104701084422398e-05,
"loss": 0.5581,
"step": 624
},
{
"epoch": 0.16,
"learning_rate": 1.9101226641396913e-05,
"loss": 0.5547,
"step": 625
},
{
"epoch": 0.16,
"learning_rate": 1.909774578686628e-05,
"loss": 0.5515,
"step": 626
},
{
"epoch": 0.16,
"learning_rate": 1.9094258523282653e-05,
"loss": 0.5435,
"step": 627
},
{
"epoch": 0.16,
"learning_rate": 1.909076485310268e-05,
"loss": 0.542,
"step": 628
},
{
"epoch": 0.16,
"learning_rate": 1.9087264778787534e-05,
"loss": 0.5352,
"step": 629
},
{
"epoch": 0.16,
"learning_rate": 1.9083758302802905e-05,
"loss": 0.5898,
"step": 630
},
{
"epoch": 0.16,
"learning_rate": 1.908024542761898e-05,
"loss": 0.5261,
"step": 631
},
{
"epoch": 0.16,
"learning_rate": 1.9076726155710464e-05,
"loss": 0.5557,
"step": 632
},
{
"epoch": 0.16,
"learning_rate": 1.9073200489556565e-05,
"loss": 0.5806,
"step": 633
},
{
"epoch": 0.16,
"learning_rate": 1.9069668431640994e-05,
"loss": 0.5522,
"step": 634
},
{
"epoch": 0.16,
"learning_rate": 1.9066129984451964e-05,
"loss": 0.5371,
"step": 635
},
{
"epoch": 0.16,
"learning_rate": 1.906258515048219e-05,
"loss": 0.5471,
"step": 636
},
{
"epoch": 0.17,
"learning_rate": 1.9059033932228895e-05,
"loss": 0.5581,
"step": 637
},
{
"epoch": 0.17,
"learning_rate": 1.9055476332193784e-05,
"loss": 0.563,
"step": 638
},
{
"epoch": 0.17,
"learning_rate": 1.9051912352883066e-05,
"loss": 0.5339,
"step": 639
},
{
"epoch": 0.17,
"learning_rate": 1.9048341996807445e-05,
"loss": 0.5415,
"step": 640
},
{
"epoch": 0.17,
"learning_rate": 1.9044765266482117e-05,
"loss": 0.5688,
"step": 641
},
{
"epoch": 0.17,
"learning_rate": 1.9041182164426765e-05,
"loss": 0.582,
"step": 642
},
{
"epoch": 0.17,
"learning_rate": 1.9037592693165564e-05,
"loss": 0.554,
"step": 643
},
{
"epoch": 0.17,
"learning_rate": 1.903399685522717e-05,
"loss": 0.5737,
"step": 644
},
{
"epoch": 0.17,
"learning_rate": 1.9030394653144738e-05,
"loss": 0.543,
"step": 645
},
{
"epoch": 0.17,
"learning_rate": 1.9026786089455892e-05,
"loss": 0.5542,
"step": 646
},
{
"epoch": 0.17,
"learning_rate": 1.902317116670274e-05,
"loss": 0.5264,
"step": 647
},
{
"epoch": 0.17,
"learning_rate": 1.901954988743188e-05,
"loss": 0.5347,
"step": 648
},
{
"epoch": 0.17,
"learning_rate": 1.901592225419437e-05,
"loss": 0.5247,
"step": 649
},
{
"epoch": 0.17,
"learning_rate": 1.901228826954576e-05,
"loss": 0.5229,
"step": 650
},
{
"epoch": 0.17,
"learning_rate": 1.900864793604607e-05,
"loss": 0.5388,
"step": 651
},
{
"epoch": 0.17,
"learning_rate": 1.9005001256259787e-05,
"loss": 0.5757,
"step": 652
},
{
"epoch": 0.17,
"learning_rate": 1.9001348232755877e-05,
"loss": 0.5513,
"step": 653
},
{
"epoch": 0.17,
"learning_rate": 1.8997688868107774e-05,
"loss": 0.5356,
"step": 654
},
{
"epoch": 0.17,
"learning_rate": 1.899402316489337e-05,
"loss": 0.54,
"step": 655
},
{
"epoch": 0.17,
"learning_rate": 1.8990351125695027e-05,
"loss": 0.5571,
"step": 656
},
{
"epoch": 0.17,
"learning_rate": 1.8986672753099574e-05,
"loss": 0.5815,
"step": 657
},
{
"epoch": 0.17,
"learning_rate": 1.8982988049698304e-05,
"loss": 0.5361,
"step": 658
},
{
"epoch": 0.17,
"learning_rate": 1.8979297018086967e-05,
"loss": 0.542,
"step": 659
},
{
"epoch": 0.17,
"learning_rate": 1.8975599660865757e-05,
"loss": 0.5273,
"step": 660
},
{
"epoch": 0.17,
"learning_rate": 1.897189598063935e-05,
"loss": 0.5449,
"step": 661
},
{
"epoch": 0.17,
"learning_rate": 1.8968185980016854e-05,
"loss": 0.5474,
"step": 662
},
{
"epoch": 0.17,
"learning_rate": 1.8964469661611844e-05,
"loss": 0.5459,
"step": 663
},
{
"epoch": 0.17,
"learning_rate": 1.8960747028042335e-05,
"loss": 0.5513,
"step": 664
},
{
"epoch": 0.17,
"learning_rate": 1.8957018081930804e-05,
"loss": 0.5708,
"step": 665
},
{
"epoch": 0.17,
"learning_rate": 1.895328282590416e-05,
"loss": 0.5342,
"step": 666
},
{
"epoch": 0.17,
"learning_rate": 1.8949541262593764e-05,
"loss": 0.5352,
"step": 667
},
{
"epoch": 0.17,
"learning_rate": 1.8945793394635423e-05,
"loss": 0.5422,
"step": 668
},
{
"epoch": 0.17,
"learning_rate": 1.8942039224669383e-05,
"loss": 0.5449,
"step": 669
},
{
"epoch": 0.17,
"learning_rate": 1.8938278755340327e-05,
"loss": 0.5447,
"step": 670
},
{
"epoch": 0.17,
"learning_rate": 1.893451198929738e-05,
"loss": 0.5283,
"step": 671
},
{
"epoch": 0.17,
"learning_rate": 1.89307389291941e-05,
"loss": 0.5659,
"step": 672
},
{
"epoch": 0.17,
"learning_rate": 1.892695957768848e-05,
"loss": 0.5369,
"step": 673
},
{
"epoch": 0.17,
"learning_rate": 1.892317393744294e-05,
"loss": 0.5669,
"step": 674
},
{
"epoch": 0.17,
"learning_rate": 1.8919382011124346e-05,
"loss": 0.563,
"step": 675
},
{
"epoch": 0.18,
"learning_rate": 1.8915583801403973e-05,
"loss": 0.5132,
"step": 676
},
{
"epoch": 0.18,
"learning_rate": 1.891177931095753e-05,
"loss": 0.5444,
"step": 677
},
{
"epoch": 0.18,
"learning_rate": 1.890796854246516e-05,
"loss": 0.5425,
"step": 678
},
{
"epoch": 0.18,
"learning_rate": 1.890415149861141e-05,
"loss": 0.541,
"step": 679
},
{
"epoch": 0.18,
"learning_rate": 1.8900328182085262e-05,
"loss": 0.5183,
"step": 680
},
{
"epoch": 0.18,
"learning_rate": 1.889649859558011e-05,
"loss": 0.5708,
"step": 681
},
{
"epoch": 0.18,
"learning_rate": 1.889266274179377e-05,
"loss": 0.5527,
"step": 682
},
{
"epoch": 0.18,
"learning_rate": 1.8888820623428476e-05,
"loss": 0.5444,
"step": 683
},
{
"epoch": 0.18,
"learning_rate": 1.8884972243190863e-05,
"loss": 0.5491,
"step": 684
},
{
"epoch": 0.18,
"learning_rate": 1.8881117603791984e-05,
"loss": 0.5464,
"step": 685
},
{
"epoch": 0.18,
"learning_rate": 1.8877256707947308e-05,
"loss": 0.5371,
"step": 686
},
{
"epoch": 0.18,
"learning_rate": 1.8873389558376697e-05,
"loss": 0.5356,
"step": 687
},
{
"epoch": 0.18,
"learning_rate": 1.886951615780443e-05,
"loss": 0.5347,
"step": 688
},
{
"epoch": 0.18,
"learning_rate": 1.8865636508959187e-05,
"loss": 0.5635,
"step": 689
},
{
"epoch": 0.18,
"learning_rate": 1.8861750614574048e-05,
"loss": 0.543,
"step": 690
},
{
"epoch": 0.18,
"learning_rate": 1.8857858477386495e-05,
"loss": 0.5479,
"step": 691
},
{
"epoch": 0.18,
"learning_rate": 1.8853960100138403e-05,
"loss": 0.5642,
"step": 692
},
{
"epoch": 0.18,
"learning_rate": 1.8850055485576055e-05,
"loss": 0.5391,
"step": 693
},
{
"epoch": 0.18,
"learning_rate": 1.8846144636450107e-05,
"loss": 0.5486,
"step": 694
},
{
"epoch": 0.18,
"learning_rate": 1.8842227555515626e-05,
"loss": 0.5459,
"step": 695
},
{
"epoch": 0.18,
"learning_rate": 1.8838304245532063e-05,
"loss": 0.543,
"step": 696
},
{
"epoch": 0.18,
"learning_rate": 1.8834374709263258e-05,
"loss": 0.5525,
"step": 697
},
{
"epoch": 0.18,
"learning_rate": 1.883043894947743e-05,
"loss": 0.5132,
"step": 698
},
{
"epoch": 0.18,
"learning_rate": 1.8826496968947198e-05,
"loss": 0.5239,
"step": 699
},
{
"epoch": 0.18,
"learning_rate": 1.8822548770449544e-05,
"loss": 0.5532,
"step": 700
},
{
"epoch": 0.18,
"learning_rate": 1.881859435676584e-05,
"loss": 0.5415,
"step": 701
},
{
"epoch": 0.18,
"learning_rate": 1.8814633730681843e-05,
"loss": 0.5381,
"step": 702
},
{
"epoch": 0.18,
"learning_rate": 1.8810666894987673e-05,
"loss": 0.5378,
"step": 703
},
{
"epoch": 0.18,
"learning_rate": 1.8806693852477832e-05,
"loss": 0.5508,
"step": 704
},
{
"epoch": 0.18,
"learning_rate": 1.88027146059512e-05,
"loss": 0.5454,
"step": 705
},
{
"epoch": 0.18,
"learning_rate": 1.8798729158211016e-05,
"loss": 0.5435,
"step": 706
},
{
"epoch": 0.18,
"learning_rate": 1.879473751206489e-05,
"loss": 0.5405,
"step": 707
},
{
"epoch": 0.18,
"learning_rate": 1.8790739670324808e-05,
"loss": 0.5566,
"step": 708
},
{
"epoch": 0.18,
"learning_rate": 1.8786735635807108e-05,
"loss": 0.5413,
"step": 709
},
{
"epoch": 0.18,
"learning_rate": 1.87827254113325e-05,
"loss": 0.5432,
"step": 710
},
{
"epoch": 0.18,
"learning_rate": 1.8778708999726047e-05,
"loss": 0.5728,
"step": 711
},
{
"epoch": 0.18,
"learning_rate": 1.877468640381718e-05,
"loss": 0.5537,
"step": 712
},
{
"epoch": 0.18,
"learning_rate": 1.8770657626439678e-05,
"loss": 0.5293,
"step": 713
},
{
"epoch": 0.19,
"learning_rate": 1.8766622670431675e-05,
"loss": 0.5234,
"step": 714
},
{
"epoch": 0.19,
"learning_rate": 1.8762581538635665e-05,
"loss": 0.5544,
"step": 715
},
{
"epoch": 0.19,
"learning_rate": 1.875853423389849e-05,
"loss": 0.5615,
"step": 716
},
{
"epoch": 0.19,
"learning_rate": 1.875448075907133e-05,
"loss": 0.5562,
"step": 717
},
{
"epoch": 0.19,
"learning_rate": 1.8750421117009728e-05,
"loss": 0.5757,
"step": 718
},
{
"epoch": 0.19,
"learning_rate": 1.8746355310573562e-05,
"loss": 0.5615,
"step": 719
},
{
"epoch": 0.19,
"learning_rate": 1.8742283342627055e-05,
"loss": 0.521,
"step": 720
},
{
"epoch": 0.19,
"learning_rate": 1.873820521603877e-05,
"loss": 0.5515,
"step": 721
},
{
"epoch": 0.19,
"learning_rate": 1.8734120933681604e-05,
"loss": 0.5615,
"step": 722
},
{
"epoch": 0.19,
"learning_rate": 1.8730030498432805e-05,
"loss": 0.5154,
"step": 723
},
{
"epoch": 0.19,
"learning_rate": 1.872593391317394e-05,
"loss": 0.5405,
"step": 724
},
{
"epoch": 0.19,
"learning_rate": 1.872183118079091e-05,
"loss": 0.5532,
"step": 725
},
{
"epoch": 0.19,
"learning_rate": 1.871772230417396e-05,
"loss": 0.5376,
"step": 726
},
{
"epoch": 0.19,
"learning_rate": 1.8713607286217646e-05,
"loss": 0.5322,
"step": 727
},
{
"epoch": 0.19,
"learning_rate": 1.8709486129820863e-05,
"loss": 0.5063,
"step": 728
},
{
"epoch": 0.19,
"learning_rate": 1.8705358837886825e-05,
"loss": 0.5337,
"step": 729
},
{
"epoch": 0.19,
"learning_rate": 1.870122541332307e-05,
"loss": 0.5461,
"step": 730
},
{
"epoch": 0.19,
"learning_rate": 1.8697085859041452e-05,
"loss": 0.5159,
"step": 731
},
{
"epoch": 0.19,
"learning_rate": 1.8692940177958147e-05,
"loss": 0.5347,
"step": 732
},
{
"epoch": 0.19,
"learning_rate": 1.868878837299365e-05,
"loss": 0.5566,
"step": 733
},
{
"epoch": 0.19,
"learning_rate": 1.868463044707276e-05,
"loss": 0.5435,
"step": 734
},
{
"epoch": 0.19,
"learning_rate": 1.86804664031246e-05,
"loss": 0.5435,
"step": 735
},
{
"epoch": 0.19,
"learning_rate": 1.8676296244082605e-05,
"loss": 0.5361,
"step": 736
},
{
"epoch": 0.19,
"learning_rate": 1.867211997288449e-05,
"loss": 0.5466,
"step": 737
},
{
"epoch": 0.19,
"learning_rate": 1.8667937592472315e-05,
"loss": 0.5312,
"step": 738
},
{
"epoch": 0.19,
"learning_rate": 1.866374910579242e-05,
"loss": 0.5229,
"step": 739
},
{
"epoch": 0.19,
"learning_rate": 1.8659554515795446e-05,
"loss": 0.5293,
"step": 740
},
{
"epoch": 0.19,
"learning_rate": 1.865535382543634e-05,
"loss": 0.5244,
"step": 741
},
{
"epoch": 0.19,
"learning_rate": 1.865114703767436e-05,
"loss": 0.54,
"step": 742
},
{
"epoch": 0.19,
"learning_rate": 1.8646934155473025e-05,
"loss": 0.5352,
"step": 743
},
{
"epoch": 0.19,
"learning_rate": 1.8642715181800177e-05,
"loss": 0.5508,
"step": 744
},
{
"epoch": 0.19,
"learning_rate": 1.863849011962794e-05,
"loss": 0.5435,
"step": 745
},
{
"epoch": 0.19,
"learning_rate": 1.8634258971932726e-05,
"loss": 0.5527,
"step": 746
},
{
"epoch": 0.19,
"learning_rate": 1.8630021741695236e-05,
"loss": 0.5251,
"step": 747
},
{
"epoch": 0.19,
"learning_rate": 1.8625778431900453e-05,
"loss": 0.5662,
"step": 748
},
{
"epoch": 0.19,
"learning_rate": 1.8621529045537644e-05,
"loss": 0.4998,
"step": 749
},
{
"epoch": 0.19,
"learning_rate": 1.8617273585600363e-05,
"loss": 0.5498,
"step": 750
},
{
"epoch": 0.19,
"learning_rate": 1.8613012055086428e-05,
"loss": 0.5469,
"step": 751
},
{
"epoch": 0.19,
"learning_rate": 1.860874445699795e-05,
"loss": 0.5371,
"step": 752
},
{
"epoch": 0.2,
"learning_rate": 1.8604470794341304e-05,
"loss": 0.5923,
"step": 753
},
{
"epoch": 0.2,
"learning_rate": 1.860019107012714e-05,
"loss": 0.5349,
"step": 754
},
{
"epoch": 0.2,
"learning_rate": 1.859590528737038e-05,
"loss": 0.5435,
"step": 755
},
{
"epoch": 0.2,
"learning_rate": 1.859161344909021e-05,
"loss": 0.5198,
"step": 756
},
{
"epoch": 0.2,
"learning_rate": 1.8587315558310087e-05,
"loss": 0.5581,
"step": 757
},
{
"epoch": 0.2,
"learning_rate": 1.858301161805773e-05,
"loss": 0.5415,
"step": 758
},
{
"epoch": 0.2,
"learning_rate": 1.8578701631365113e-05,
"loss": 0.5493,
"step": 759
},
{
"epoch": 0.2,
"learning_rate": 1.8574385601268477e-05,
"loss": 0.5198,
"step": 760
},
{
"epoch": 0.2,
"learning_rate": 1.8570063530808323e-05,
"loss": 0.5317,
"step": 761
},
{
"epoch": 0.2,
"learning_rate": 1.8565735423029406e-05,
"loss": 0.5459,
"step": 762
},
{
"epoch": 0.2,
"learning_rate": 1.8561401280980718e-05,
"loss": 0.5151,
"step": 763
},
{
"epoch": 0.2,
"learning_rate": 1.8557061107715525e-05,
"loss": 0.5181,
"step": 764
},
{
"epoch": 0.2,
"learning_rate": 1.855271490629133e-05,
"loss": 0.5669,
"step": 765
},
{
"epoch": 0.2,
"learning_rate": 1.854836267976988e-05,
"loss": 0.5403,
"step": 766
},
{
"epoch": 0.2,
"learning_rate": 1.8544004431217177e-05,
"loss": 0.5381,
"step": 767
},
{
"epoch": 0.2,
"learning_rate": 1.8539640163703456e-05,
"loss": 0.5347,
"step": 768
},
{
"epoch": 0.2,
"learning_rate": 1.8535269880303196e-05,
"loss": 0.5391,
"step": 769
},
{
"epoch": 0.2,
"learning_rate": 1.8530893584095113e-05,
"loss": 0.5356,
"step": 770
},
{
"epoch": 0.2,
"learning_rate": 1.8526511278162157e-05,
"loss": 0.5354,
"step": 771
},
{
"epoch": 0.2,
"learning_rate": 1.852212296559152e-05,
"loss": 0.5493,
"step": 772
},
{
"epoch": 0.2,
"learning_rate": 1.851772864947461e-05,
"loss": 0.5557,
"step": 773
},
{
"epoch": 0.2,
"learning_rate": 1.851332833290708e-05,
"loss": 0.5298,
"step": 774
},
{
"epoch": 0.2,
"learning_rate": 1.85089220189888e-05,
"loss": 0.5493,
"step": 775
},
{
"epoch": 0.2,
"learning_rate": 1.8504509710823876e-05,
"loss": 0.5181,
"step": 776
},
{
"epoch": 0.2,
"learning_rate": 1.8500091411520618e-05,
"loss": 0.5249,
"step": 777
},
{
"epoch": 0.2,
"learning_rate": 1.8495667124191577e-05,
"loss": 0.5425,
"step": 778
},
{
"epoch": 0.2,
"learning_rate": 1.849123685195351e-05,
"loss": 0.5127,
"step": 779
},
{
"epoch": 0.2,
"learning_rate": 1.848680059792739e-05,
"loss": 0.52,
"step": 780
},
{
"epoch": 0.2,
"learning_rate": 1.8482358365238414e-05,
"loss": 0.543,
"step": 781
},
{
"epoch": 0.2,
"learning_rate": 1.847791015701598e-05,
"loss": 0.5298,
"step": 782
},
{
"epoch": 0.2,
"learning_rate": 1.8473455976393698e-05,
"loss": 0.5715,
"step": 783
},
{
"epoch": 0.2,
"learning_rate": 1.846899582650939e-05,
"loss": 0.5234,
"step": 784
},
{
"epoch": 0.2,
"learning_rate": 1.8464529710505082e-05,
"loss": 0.54,
"step": 785
},
{
"epoch": 0.2,
"learning_rate": 1.8460057631526998e-05,
"loss": 0.5146,
"step": 786
},
{
"epoch": 0.2,
"learning_rate": 1.8455579592725565e-05,
"loss": 0.5427,
"step": 787
},
{
"epoch": 0.2,
"learning_rate": 1.845109559725541e-05,
"loss": 0.541,
"step": 788
},
{
"epoch": 0.2,
"learning_rate": 1.8446605648275356e-05,
"loss": 0.5522,
"step": 789
},
{
"epoch": 0.2,
"learning_rate": 1.844210974894842e-05,
"loss": 0.5552,
"step": 790
},
{
"epoch": 0.2,
"learning_rate": 1.8437607902441814e-05,
"loss": 0.5542,
"step": 791
},
{
"epoch": 0.21,
"learning_rate": 1.843310011192693e-05,
"loss": 0.5354,
"step": 792
},
{
"epoch": 0.21,
"learning_rate": 1.8428586380579357e-05,
"loss": 0.5449,
"step": 793
},
{
"epoch": 0.21,
"learning_rate": 1.842406671157886e-05,
"loss": 0.5605,
"step": 794
},
{
"epoch": 0.21,
"learning_rate": 1.84195411081094e-05,
"loss": 0.5483,
"step": 795
},
{
"epoch": 0.21,
"learning_rate": 1.8415009573359106e-05,
"loss": 0.5249,
"step": 796
},
{
"epoch": 0.21,
"learning_rate": 1.841047211052029e-05,
"loss": 0.541,
"step": 797
},
{
"epoch": 0.21,
"learning_rate": 1.8405928722789446e-05,
"loss": 0.54,
"step": 798
},
{
"epoch": 0.21,
"learning_rate": 1.840137941336723e-05,
"loss": 0.5625,
"step": 799
},
{
"epoch": 0.21,
"learning_rate": 1.839682418545848e-05,
"loss": 0.5396,
"step": 800
},
{
"epoch": 0.21,
"learning_rate": 1.8392263042272195e-05,
"loss": 0.5225,
"step": 801
},
{
"epoch": 0.21,
"learning_rate": 1.8387695987021554e-05,
"loss": 0.5474,
"step": 802
},
{
"epoch": 0.21,
"learning_rate": 1.8383123022923883e-05,
"loss": 0.5349,
"step": 803
},
{
"epoch": 0.21,
"learning_rate": 1.8378544153200685e-05,
"loss": 0.5405,
"step": 804
},
{
"epoch": 0.21,
"learning_rate": 1.8373959381077618e-05,
"loss": 0.5388,
"step": 805
},
{
"epoch": 0.21,
"learning_rate": 1.8369368709784495e-05,
"loss": 0.53,
"step": 806
},
{
"epoch": 0.21,
"learning_rate": 1.8364772142555293e-05,
"loss": 0.5317,
"step": 807
},
{
"epoch": 0.21,
"learning_rate": 1.8360169682628134e-05,
"loss": 0.5469,
"step": 808
},
{
"epoch": 0.21,
"learning_rate": 1.8355561333245297e-05,
"loss": 0.4783,
"step": 809
},
{
"epoch": 0.21,
"learning_rate": 1.83509470976532e-05,
"loss": 0.5491,
"step": 810
},
{
"epoch": 0.21,
"learning_rate": 1.834632697910243e-05,
"loss": 0.5566,
"step": 811
},
{
"epoch": 0.21,
"learning_rate": 1.834170098084769e-05,
"loss": 0.5359,
"step": 812
},
{
"epoch": 0.21,
"learning_rate": 1.8337069106147848e-05,
"loss": 0.5537,
"step": 813
},
{
"epoch": 0.21,
"learning_rate": 1.8332431358265896e-05,
"loss": 0.5261,
"step": 814
},
{
"epoch": 0.21,
"learning_rate": 1.8327787740468974e-05,
"loss": 0.5303,
"step": 815
},
{
"epoch": 0.21,
"learning_rate": 1.832313825602835e-05,
"loss": 0.5435,
"step": 816
},
{
"epoch": 0.21,
"learning_rate": 1.831848290821943e-05,
"loss": 0.5334,
"step": 817
},
{
"epoch": 0.21,
"learning_rate": 1.8313821700321747e-05,
"loss": 0.5312,
"step": 818
},
{
"epoch": 0.21,
"learning_rate": 1.8309154635618967e-05,
"loss": 0.5669,
"step": 819
},
{
"epoch": 0.21,
"learning_rate": 1.8304481717398877e-05,
"loss": 0.5337,
"step": 820
},
{
"epoch": 0.21,
"learning_rate": 1.8299802948953385e-05,
"loss": 0.5298,
"step": 821
},
{
"epoch": 0.21,
"learning_rate": 1.829511833357853e-05,
"loss": 0.5291,
"step": 822
},
{
"epoch": 0.21,
"learning_rate": 1.829042787457446e-05,
"loss": 0.5259,
"step": 823
},
{
"epoch": 0.21,
"learning_rate": 1.8285731575245446e-05,
"loss": 0.5322,
"step": 824
},
{
"epoch": 0.21,
"learning_rate": 1.8281029438899875e-05,
"loss": 0.5161,
"step": 825
},
{
"epoch": 0.21,
"learning_rate": 1.827632146885024e-05,
"loss": 0.5562,
"step": 826
},
{
"epoch": 0.21,
"learning_rate": 1.8271607668413142e-05,
"loss": 0.5352,
"step": 827
},
{
"epoch": 0.21,
"learning_rate": 1.82668880409093e-05,
"loss": 0.5198,
"step": 828
},
{
"epoch": 0.21,
"learning_rate": 1.8262162589663527e-05,
"loss": 0.5298,
"step": 829
},
{
"epoch": 0.22,
"learning_rate": 1.8257431318004744e-05,
"loss": 0.5381,
"step": 830
},
{
"epoch": 0.22,
"learning_rate": 1.825269422926597e-05,
"loss": 0.5249,
"step": 831
},
{
"epoch": 0.22,
"learning_rate": 1.8247951326784323e-05,
"loss": 0.5498,
"step": 832
},
{
"epoch": 0.22,
"learning_rate": 1.824320261390102e-05,
"loss": 0.5327,
"step": 833
},
{
"epoch": 0.22,
"learning_rate": 1.8238448093961368e-05,
"loss": 0.5552,
"step": 834
},
{
"epoch": 0.22,
"learning_rate": 1.823368777031476e-05,
"loss": 0.5305,
"step": 835
},
{
"epoch": 0.22,
"learning_rate": 1.822892164631469e-05,
"loss": 0.4963,
"step": 836
},
{
"epoch": 0.22,
"learning_rate": 1.822414972531872e-05,
"loss": 0.5303,
"step": 837
},
{
"epoch": 0.22,
"learning_rate": 1.8219372010688516e-05,
"loss": 0.5337,
"step": 838
},
{
"epoch": 0.22,
"learning_rate": 1.821458850578981e-05,
"loss": 0.5388,
"step": 839
},
{
"epoch": 0.22,
"learning_rate": 1.8209799213992422e-05,
"loss": 0.5637,
"step": 840
},
{
"epoch": 0.22,
"learning_rate": 1.8205004138670244e-05,
"loss": 0.5349,
"step": 841
},
{
"epoch": 0.22,
"learning_rate": 1.8200203283201245e-05,
"loss": 0.5408,
"step": 842
},
{
"epoch": 0.22,
"learning_rate": 1.819539665096746e-05,
"loss": 0.552,
"step": 843
},
{
"epoch": 0.22,
"learning_rate": 1.8190584245355004e-05,
"loss": 0.5474,
"step": 844
},
{
"epoch": 0.22,
"learning_rate": 1.8185766069754053e-05,
"loss": 0.5247,
"step": 845
},
{
"epoch": 0.22,
"learning_rate": 1.8180942127558844e-05,
"loss": 0.5278,
"step": 846
},
{
"epoch": 0.22,
"learning_rate": 1.8176112422167685e-05,
"loss": 0.5579,
"step": 847
},
{
"epoch": 0.22,
"learning_rate": 1.8171276956982934e-05,
"loss": 0.5195,
"step": 848
},
{
"epoch": 0.22,
"learning_rate": 1.816643573541102e-05,
"loss": 0.519,
"step": 849
},
{
"epoch": 0.22,
"learning_rate": 1.8161588760862408e-05,
"loss": 0.5276,
"step": 850
},
{
"epoch": 0.22,
"learning_rate": 1.8156736036751635e-05,
"loss": 0.542,
"step": 851
},
{
"epoch": 0.22,
"learning_rate": 1.8151877566497284e-05,
"loss": 0.5088,
"step": 852
},
{
"epoch": 0.22,
"learning_rate": 1.8147013353521974e-05,
"loss": 0.5498,
"step": 853
},
{
"epoch": 0.22,
"learning_rate": 1.814214340125238e-05,
"loss": 0.5195,
"step": 854
},
{
"epoch": 0.22,
"learning_rate": 1.813726771311922e-05,
"loss": 0.532,
"step": 855
},
{
"epoch": 0.22,
"learning_rate": 1.8132386292557253e-05,
"loss": 0.5242,
"step": 856
},
{
"epoch": 0.22,
"learning_rate": 1.8127499143005266e-05,
"loss": 0.5188,
"step": 857
},
{
"epoch": 0.22,
"learning_rate": 1.8122606267906097e-05,
"loss": 0.5,
"step": 858
},
{
"epoch": 0.22,
"learning_rate": 1.8117707670706607e-05,
"loss": 0.5159,
"step": 859
},
{
"epoch": 0.22,
"learning_rate": 1.8112803354857696e-05,
"loss": 0.5176,
"step": 860
},
{
"epoch": 0.22,
"learning_rate": 1.810789332381428e-05,
"loss": 0.5396,
"step": 861
},
{
"epoch": 0.22,
"learning_rate": 1.8102977581035315e-05,
"loss": 0.5225,
"step": 862
},
{
"epoch": 0.22,
"learning_rate": 1.8098056129983774e-05,
"loss": 0.5293,
"step": 863
},
{
"epoch": 0.22,
"learning_rate": 1.8093128974126654e-05,
"loss": 0.5193,
"step": 864
},
{
"epoch": 0.22,
"learning_rate": 1.8088196116934965e-05,
"loss": 0.5381,
"step": 865
},
{
"epoch": 0.22,
"learning_rate": 1.8083257561883736e-05,
"loss": 0.5342,
"step": 866
},
{
"epoch": 0.22,
"learning_rate": 1.8078313312452018e-05,
"loss": 0.4941,
"step": 867
},
{
"epoch": 0.22,
"learning_rate": 1.8073363372122866e-05,
"loss": 0.5283,
"step": 868
},
{
"epoch": 0.23,
"learning_rate": 1.806840774438334e-05,
"loss": 0.4858,
"step": 869
},
{
"epoch": 0.23,
"learning_rate": 1.806344643272451e-05,
"loss": 0.4976,
"step": 870
},
{
"epoch": 0.23,
"learning_rate": 1.8058479440641456e-05,
"loss": 0.5347,
"step": 871
},
{
"epoch": 0.23,
"learning_rate": 1.805350677163326e-05,
"loss": 0.5527,
"step": 872
},
{
"epoch": 0.23,
"learning_rate": 1.804852842920299e-05,
"loss": 0.5034,
"step": 873
},
{
"epoch": 0.23,
"learning_rate": 1.8043544416857722e-05,
"loss": 0.509,
"step": 874
},
{
"epoch": 0.23,
"learning_rate": 1.8038554738108523e-05,
"loss": 0.5371,
"step": 875
},
{
"epoch": 0.23,
"learning_rate": 1.8033559396470455e-05,
"loss": 0.5283,
"step": 876
},
{
"epoch": 0.23,
"learning_rate": 1.8028558395462563e-05,
"loss": 0.5508,
"step": 877
},
{
"epoch": 0.23,
"learning_rate": 1.8023551738607886e-05,
"loss": 0.5203,
"step": 878
},
{
"epoch": 0.23,
"learning_rate": 1.801853942943344e-05,
"loss": 0.5271,
"step": 879
},
{
"epoch": 0.23,
"learning_rate": 1.8013521471470228e-05,
"loss": 0.5281,
"step": 880
},
{
"epoch": 0.23,
"learning_rate": 1.800849786825323e-05,
"loss": 0.5132,
"step": 881
},
{
"epoch": 0.23,
"learning_rate": 1.8003468623321406e-05,
"loss": 0.5325,
"step": 882
},
{
"epoch": 0.23,
"learning_rate": 1.799843374021769e-05,
"loss": 0.5229,
"step": 883
},
{
"epoch": 0.23,
"learning_rate": 1.7993393222488983e-05,
"loss": 0.4868,
"step": 884
},
{
"epoch": 0.23,
"learning_rate": 1.7988347073686158e-05,
"loss": 0.5139,
"step": 885
},
{
"epoch": 0.23,
"learning_rate": 1.798329529736406e-05,
"loss": 0.5454,
"step": 886
},
{
"epoch": 0.23,
"learning_rate": 1.7978237897081486e-05,
"loss": 0.5439,
"step": 887
},
{
"epoch": 0.23,
"learning_rate": 1.797317487640121e-05,
"loss": 0.5554,
"step": 888
},
{
"epoch": 0.23,
"learning_rate": 1.7968106238889954e-05,
"loss": 0.53,
"step": 889
},
{
"epoch": 0.23,
"learning_rate": 1.7963031988118406e-05,
"loss": 0.52,
"step": 890
},
{
"epoch": 0.23,
"learning_rate": 1.79579521276612e-05,
"loss": 0.51,
"step": 891
},
{
"epoch": 0.23,
"learning_rate": 1.7952866661096922e-05,
"loss": 0.543,
"step": 892
},
{
"epoch": 0.23,
"learning_rate": 1.7947775592008118e-05,
"loss": 0.5054,
"step": 893
},
{
"epoch": 0.23,
"learning_rate": 1.7942678923981266e-05,
"loss": 0.5154,
"step": 894
},
{
"epoch": 0.23,
"learning_rate": 1.79375766606068e-05,
"loss": 0.5051,
"step": 895
},
{
"epoch": 0.23,
"learning_rate": 1.7932468805479087e-05,
"loss": 0.5264,
"step": 896
},
{
"epoch": 0.23,
"learning_rate": 1.7927355362196442e-05,
"loss": 0.5337,
"step": 897
},
{
"epoch": 0.23,
"learning_rate": 1.792223633436111e-05,
"loss": 0.5322,
"step": 898
},
{
"epoch": 0.23,
"learning_rate": 1.7917111725579277e-05,
"loss": 0.5325,
"step": 899
},
{
"epoch": 0.23,
"learning_rate": 1.791198153946105e-05,
"loss": 0.5005,
"step": 900
},
{
"epoch": 0.23,
"learning_rate": 1.790684577962047e-05,
"loss": 0.4971,
"step": 901
},
{
"epoch": 0.23,
"learning_rate": 1.7901704449675513e-05,
"loss": 0.5042,
"step": 902
},
{
"epoch": 0.23,
"learning_rate": 1.7896557553248063e-05,
"loss": 0.5359,
"step": 903
},
{
"epoch": 0.23,
"learning_rate": 1.789140509396394e-05,
"loss": 0.5752,
"step": 904
},
{
"epoch": 0.23,
"learning_rate": 1.788624707545287e-05,
"loss": 0.5576,
"step": 905
},
{
"epoch": 0.23,
"learning_rate": 1.788108350134851e-05,
"loss": 0.5415,
"step": 906
},
{
"epoch": 0.24,
"learning_rate": 1.7875914375288414e-05,
"loss": 0.5625,
"step": 907
},
{
"epoch": 0.24,
"learning_rate": 1.7870739700914063e-05,
"loss": 0.5295,
"step": 908
},
{
"epoch": 0.24,
"learning_rate": 1.7865559481870835e-05,
"loss": 0.5376,
"step": 909
},
{
"epoch": 0.24,
"learning_rate": 1.7860373721808022e-05,
"loss": 0.5403,
"step": 910
},
{
"epoch": 0.24,
"learning_rate": 1.7855182424378816e-05,
"loss": 0.5339,
"step": 911
},
{
"epoch": 0.24,
"learning_rate": 1.7849985593240303e-05,
"loss": 0.5195,
"step": 912
},
{
"epoch": 0.24,
"learning_rate": 1.7844783232053484e-05,
"loss": 0.521,
"step": 913
},
{
"epoch": 0.24,
"learning_rate": 1.7839575344483237e-05,
"loss": 0.5337,
"step": 914
},
{
"epoch": 0.24,
"learning_rate": 1.7834361934198346e-05,
"loss": 0.4937,
"step": 915
},
{
"epoch": 0.24,
"learning_rate": 1.7829143004871482e-05,
"loss": 0.5254,
"step": 916
},
{
"epoch": 0.24,
"learning_rate": 1.7823918560179202e-05,
"loss": 0.5166,
"step": 917
},
{
"epoch": 0.24,
"learning_rate": 1.781868860380195e-05,
"loss": 0.5234,
"step": 918
},
{
"epoch": 0.24,
"learning_rate": 1.781345313942406e-05,
"loss": 0.5251,
"step": 919
},
{
"epoch": 0.24,
"learning_rate": 1.7808212170733724e-05,
"loss": 0.5312,
"step": 920
},
{
"epoch": 0.24,
"learning_rate": 1.7802965701423037e-05,
"loss": 0.4932,
"step": 921
},
{
"epoch": 0.24,
"learning_rate": 1.7797713735187955e-05,
"loss": 0.5386,
"step": 922
},
{
"epoch": 0.24,
"learning_rate": 1.7792456275728312e-05,
"loss": 0.5476,
"step": 923
},
{
"epoch": 0.24,
"learning_rate": 1.778719332674781e-05,
"loss": 0.5244,
"step": 924
},
{
"epoch": 0.24,
"learning_rate": 1.7781924891954017e-05,
"loss": 0.5215,
"step": 925
},
{
"epoch": 0.24,
"learning_rate": 1.7776650975058364e-05,
"loss": 0.5444,
"step": 926
},
{
"epoch": 0.24,
"learning_rate": 1.7771371579776147e-05,
"loss": 0.531,
"step": 927
},
{
"epoch": 0.24,
"learning_rate": 1.7766086709826526e-05,
"loss": 0.5088,
"step": 928
},
{
"epoch": 0.24,
"learning_rate": 1.7760796368932505e-05,
"loss": 0.5139,
"step": 929
},
{
"epoch": 0.24,
"learning_rate": 1.7755500560820954e-05,
"loss": 0.5315,
"step": 930
},
{
"epoch": 0.24,
"learning_rate": 1.775019928922259e-05,
"loss": 0.5103,
"step": 931
},
{
"epoch": 0.24,
"learning_rate": 1.7744892557871977e-05,
"loss": 0.5063,
"step": 932
},
{
"epoch": 0.24,
"learning_rate": 1.7739580370507533e-05,
"loss": 0.5063,
"step": 933
},
{
"epoch": 0.24,
"learning_rate": 1.77342627308715e-05,
"loss": 0.5349,
"step": 934
},
{
"epoch": 0.24,
"learning_rate": 1.7728939642709992e-05,
"loss": 0.4895,
"step": 935
},
{
"epoch": 0.24,
"learning_rate": 1.772361110977293e-05,
"loss": 0.5479,
"step": 936
},
{
"epoch": 0.24,
"learning_rate": 1.771827713581409e-05,
"loss": 0.5168,
"step": 937
},
{
"epoch": 0.24,
"learning_rate": 1.7712937724591074e-05,
"loss": 0.4824,
"step": 938
},
{
"epoch": 0.24,
"learning_rate": 1.7707592879865318e-05,
"loss": 0.519,
"step": 939
},
{
"epoch": 0.24,
"learning_rate": 1.770224260540208e-05,
"loss": 0.5095,
"step": 940
},
{
"epoch": 0.24,
"learning_rate": 1.7696886904970453e-05,
"loss": 0.5386,
"step": 941
},
{
"epoch": 0.24,
"learning_rate": 1.769152578234334e-05,
"loss": 0.502,
"step": 942
},
{
"epoch": 0.24,
"learning_rate": 1.7686159241297475e-05,
"loss": 0.5461,
"step": 943
},
{
"epoch": 0.24,
"learning_rate": 1.7680787285613397e-05,
"loss": 0.5327,
"step": 944
},
{
"epoch": 0.24,
"learning_rate": 1.7675409919075476e-05,
"loss": 0.5063,
"step": 945
},
{
"epoch": 0.25,
"learning_rate": 1.7670027145471877e-05,
"loss": 0.5188,
"step": 946
},
{
"epoch": 0.25,
"learning_rate": 1.7664638968594583e-05,
"loss": 0.5344,
"step": 947
},
{
"epoch": 0.25,
"learning_rate": 1.765924539223938e-05,
"loss": 0.4885,
"step": 948
},
{
"epoch": 0.25,
"learning_rate": 1.7653846420205862e-05,
"loss": 0.5129,
"step": 949
},
{
"epoch": 0.25,
"learning_rate": 1.7648442056297418e-05,
"loss": 0.5479,
"step": 950
},
{
"epoch": 0.25,
"learning_rate": 1.7643032304321246e-05,
"loss": 0.4727,
"step": 951
},
{
"epoch": 0.25,
"learning_rate": 1.7637617168088327e-05,
"loss": 0.5269,
"step": 952
},
{
"epoch": 0.25,
"learning_rate": 1.763219665141344e-05,
"loss": 0.5088,
"step": 953
},
{
"epoch": 0.25,
"learning_rate": 1.7626770758115155e-05,
"loss": 0.5342,
"step": 954
},
{
"epoch": 0.25,
"learning_rate": 1.7621339492015835e-05,
"loss": 0.4956,
"step": 955
},
{
"epoch": 0.25,
"learning_rate": 1.7615902856941617e-05,
"loss": 0.4988,
"step": 956
},
{
"epoch": 0.25,
"learning_rate": 1.7610460856722426e-05,
"loss": 0.5076,
"step": 957
},
{
"epoch": 0.25,
"learning_rate": 1.7605013495191972e-05,
"loss": 0.5186,
"step": 958
},
{
"epoch": 0.25,
"learning_rate": 1.759956077618773e-05,
"loss": 0.4958,
"step": 959
},
{
"epoch": 0.25,
"learning_rate": 1.7594102703550957e-05,
"loss": 0.5112,
"step": 960
},
{
"epoch": 0.25,
"learning_rate": 1.758863928112668e-05,
"loss": 0.4756,
"step": 961
},
{
"epoch": 0.25,
"learning_rate": 1.7583170512763693e-05,
"loss": 0.5332,
"step": 962
},
{
"epoch": 0.25,
"learning_rate": 1.7577696402314567e-05,
"loss": 0.5256,
"step": 963
},
{
"epoch": 0.25,
"learning_rate": 1.757221695363561e-05,
"loss": 0.4966,
"step": 964
},
{
"epoch": 0.25,
"learning_rate": 1.7566732170586923e-05,
"loss": 0.512,
"step": 965
},
{
"epoch": 0.25,
"learning_rate": 1.7561242057032343e-05,
"loss": 0.5166,
"step": 966
},
{
"epoch": 0.25,
"learning_rate": 1.7555746616839466e-05,
"loss": 0.5171,
"step": 967
},
{
"epoch": 0.25,
"learning_rate": 1.755024585387965e-05,
"loss": 0.5547,
"step": 968
},
{
"epoch": 0.25,
"learning_rate": 1.7544739772027988e-05,
"loss": 0.5103,
"step": 969
},
{
"epoch": 0.25,
"learning_rate": 1.7539228375163337e-05,
"loss": 0.4922,
"step": 970
},
{
"epoch": 0.25,
"learning_rate": 1.753371166716828e-05,
"loss": 0.5217,
"step": 971
},
{
"epoch": 0.25,
"learning_rate": 1.7528189651929156e-05,
"loss": 0.4873,
"step": 972
},
{
"epoch": 0.25,
"learning_rate": 1.752266233333603e-05,
"loss": 0.5088,
"step": 973
},
{
"epoch": 0.25,
"learning_rate": 1.751712971528272e-05,
"loss": 0.5391,
"step": 974
},
{
"epoch": 0.25,
"learning_rate": 1.7511591801666763e-05,
"loss": 0.5288,
"step": 975
},
{
"epoch": 0.25,
"learning_rate": 1.750604859638943e-05,
"loss": 0.5291,
"step": 976
},
{
"epoch": 0.25,
"learning_rate": 1.7500500103355722e-05,
"loss": 0.5293,
"step": 977
},
{
"epoch": 0.25,
"learning_rate": 1.7494946326474365e-05,
"loss": 0.5312,
"step": 978
},
{
"epoch": 0.25,
"learning_rate": 1.7489387269657804e-05,
"loss": 0.5232,
"step": 979
},
{
"epoch": 0.25,
"learning_rate": 1.7483822936822208e-05,
"loss": 0.5032,
"step": 980
},
{
"epoch": 0.25,
"learning_rate": 1.7478253331887458e-05,
"loss": 0.4978,
"step": 981
},
{
"epoch": 0.25,
"learning_rate": 1.7472678458777154e-05,
"loss": 0.53,
"step": 982
},
{
"epoch": 0.25,
"learning_rate": 1.7467098321418604e-05,
"loss": 0.5225,
"step": 983
},
{
"epoch": 0.25,
"learning_rate": 1.7461512923742828e-05,
"loss": 0.5078,
"step": 984
},
{
"epoch": 0.26,
"learning_rate": 1.7455922269684543e-05,
"loss": 0.533,
"step": 985
},
{
"epoch": 0.26,
"learning_rate": 1.745032636318218e-05,
"loss": 0.5156,
"step": 986
},
{
"epoch": 0.26,
"learning_rate": 1.7444725208177863e-05,
"loss": 0.4985,
"step": 987
},
{
"epoch": 0.26,
"learning_rate": 1.7439118808617418e-05,
"loss": 0.5027,
"step": 988
},
{
"epoch": 0.26,
"learning_rate": 1.7433507168450354e-05,
"loss": 0.5078,
"step": 989
},
{
"epoch": 0.26,
"learning_rate": 1.7427890291629895e-05,
"loss": 0.519,
"step": 990
},
{
"epoch": 0.26,
"learning_rate": 1.742226818211293e-05,
"loss": 0.5054,
"step": 991
},
{
"epoch": 0.26,
"learning_rate": 1.7416640843860048e-05,
"loss": 0.5276,
"step": 992
},
{
"epoch": 0.26,
"learning_rate": 1.7411008280835514e-05,
"loss": 0.532,
"step": 993
},
{
"epoch": 0.26,
"learning_rate": 1.7405370497007287e-05,
"loss": 0.5432,
"step": 994
},
{
"epoch": 0.26,
"learning_rate": 1.7399727496346985e-05,
"loss": 0.5183,
"step": 995
},
{
"epoch": 0.26,
"learning_rate": 1.739407928282991e-05,
"loss": 0.5127,
"step": 996
},
{
"epoch": 0.26,
"learning_rate": 1.738842586043504e-05,
"loss": 0.5151,
"step": 997
},
{
"epoch": 0.26,
"learning_rate": 1.738276723314502e-05,
"loss": 0.5254,
"step": 998
},
{
"epoch": 0.26,
"learning_rate": 1.7377103404946162e-05,
"loss": 0.5137,
"step": 999
},
{
"epoch": 0.26,
"learning_rate": 1.7371434379828436e-05,
"loss": 0.4844,
"step": 1000
},
{
"epoch": 0.26,
"learning_rate": 1.7365760161785478e-05,
"loss": 0.4822,
"step": 1001
},
{
"epoch": 0.26,
"learning_rate": 1.7360080754814585e-05,
"loss": 0.5337,
"step": 1002
},
{
"epoch": 0.26,
"learning_rate": 1.7354396162916708e-05,
"loss": 0.5229,
"step": 1003
},
{
"epoch": 0.26,
"learning_rate": 1.7348706390096445e-05,
"loss": 0.5098,
"step": 1004
},
{
"epoch": 0.26,
"learning_rate": 1.7343011440362048e-05,
"loss": 0.5464,
"step": 1005
},
{
"epoch": 0.26,
"learning_rate": 1.7337311317725417e-05,
"loss": 0.5212,
"step": 1006
},
{
"epoch": 0.26,
"learning_rate": 1.7331606026202092e-05,
"loss": 0.5017,
"step": 1007
},
{
"epoch": 0.26,
"learning_rate": 1.7325895569811264e-05,
"loss": 0.5151,
"step": 1008
},
{
"epoch": 0.26,
"learning_rate": 1.732017995257575e-05,
"loss": 0.5117,
"step": 1009
},
{
"epoch": 0.26,
"learning_rate": 1.731445917852201e-05,
"loss": 0.5264,
"step": 1010
},
{
"epoch": 0.26,
"learning_rate": 1.7308733251680136e-05,
"loss": 0.5269,
"step": 1011
},
{
"epoch": 0.26,
"learning_rate": 1.7303002176083844e-05,
"loss": 0.5042,
"step": 1012
},
{
"epoch": 0.26,
"learning_rate": 1.7297265955770486e-05,
"loss": 0.5247,
"step": 1013
},
{
"epoch": 0.26,
"learning_rate": 1.7291524594781038e-05,
"loss": 0.5173,
"step": 1014
},
{
"epoch": 0.26,
"learning_rate": 1.7285778097160086e-05,
"loss": 0.5247,
"step": 1015
},
{
"epoch": 0.26,
"learning_rate": 1.7280026466955852e-05,
"loss": 0.5046,
"step": 1016
},
{
"epoch": 0.26,
"learning_rate": 1.7274269708220155e-05,
"loss": 0.5486,
"step": 1017
},
{
"epoch": 0.26,
"learning_rate": 1.726850782500844e-05,
"loss": 0.5142,
"step": 1018
},
{
"epoch": 0.26,
"learning_rate": 1.7262740821379758e-05,
"loss": 0.5332,
"step": 1019
},
{
"epoch": 0.26,
"learning_rate": 1.725696870139677e-05,
"loss": 0.5317,
"step": 1020
},
{
"epoch": 0.26,
"learning_rate": 1.7251191469125732e-05,
"loss": 0.5125,
"step": 1021
},
{
"epoch": 0.26,
"learning_rate": 1.7245409128636516e-05,
"loss": 0.4993,
"step": 1022
},
{
"epoch": 0.27,
"learning_rate": 1.7239621684002575e-05,
"loss": 0.4834,
"step": 1023
},
{
"epoch": 0.27,
"learning_rate": 1.723382913930098e-05,
"loss": 0.5117,
"step": 1024
},
{
"epoch": 0.27,
"learning_rate": 1.7228031498612368e-05,
"loss": 0.5229,
"step": 1025
},
{
"epoch": 0.27,
"learning_rate": 1.722222876602099e-05,
"loss": 0.5037,
"step": 1026
},
{
"epoch": 0.27,
"learning_rate": 1.7216420945614668e-05,
"loss": 0.498,
"step": 1027
},
{
"epoch": 0.27,
"learning_rate": 1.721060804148482e-05,
"loss": 0.5029,
"step": 1028
},
{
"epoch": 0.27,
"learning_rate": 1.7204790057726435e-05,
"loss": 0.4976,
"step": 1029
},
{
"epoch": 0.27,
"learning_rate": 1.7198966998438087e-05,
"loss": 0.5305,
"step": 1030
},
{
"epoch": 0.27,
"learning_rate": 1.7193138867721924e-05,
"loss": 0.52,
"step": 1031
},
{
"epoch": 0.27,
"learning_rate": 1.7187305669683666e-05,
"loss": 0.5017,
"step": 1032
},
{
"epoch": 0.27,
"learning_rate": 1.7181467408432597e-05,
"loss": 0.5425,
"step": 1033
},
{
"epoch": 0.27,
"learning_rate": 1.717562408808158e-05,
"loss": 0.5452,
"step": 1034
},
{
"epoch": 0.27,
"learning_rate": 1.7169775712747042e-05,
"loss": 0.561,
"step": 1035
},
{
"epoch": 0.27,
"learning_rate": 1.7163922286548953e-05,
"loss": 0.4902,
"step": 1036
},
{
"epoch": 0.27,
"learning_rate": 1.7158063813610856e-05,
"loss": 0.5073,
"step": 1037
},
{
"epoch": 0.27,
"learning_rate": 1.7152200298059854e-05,
"loss": 0.498,
"step": 1038
},
{
"epoch": 0.27,
"learning_rate": 1.7146331744026582e-05,
"loss": 0.564,
"step": 1039
},
{
"epoch": 0.27,
"learning_rate": 1.7140458155645246e-05,
"loss": 0.5151,
"step": 1040
},
{
"epoch": 0.27,
"learning_rate": 1.713457953705359e-05,
"loss": 0.4956,
"step": 1041
},
{
"epoch": 0.27,
"learning_rate": 1.7128695892392894e-05,
"loss": 0.5017,
"step": 1042
},
{
"epoch": 0.27,
"learning_rate": 1.7122807225807997e-05,
"loss": 0.5581,
"step": 1043
},
{
"epoch": 0.27,
"learning_rate": 1.7116913541447252e-05,
"loss": 0.5024,
"step": 1044
},
{
"epoch": 0.27,
"learning_rate": 1.711101484346257e-05,
"loss": 0.5161,
"step": 1045
},
{
"epoch": 0.27,
"learning_rate": 1.7105111136009375e-05,
"loss": 0.5166,
"step": 1046
},
{
"epoch": 0.27,
"learning_rate": 1.7099202423246632e-05,
"loss": 0.5083,
"step": 1047
},
{
"epoch": 0.27,
"learning_rate": 1.709328870933683e-05,
"loss": 0.4929,
"step": 1048
},
{
"epoch": 0.27,
"learning_rate": 1.708736999844598e-05,
"loss": 0.5283,
"step": 1049
},
{
"epoch": 0.27,
"learning_rate": 1.708144629474361e-05,
"loss": 0.4932,
"step": 1050
},
{
"epoch": 0.27,
"learning_rate": 1.707551760240277e-05,
"loss": 0.5002,
"step": 1051
},
{
"epoch": 0.27,
"learning_rate": 1.7069583925600024e-05,
"loss": 0.5227,
"step": 1052
},
{
"epoch": 0.27,
"learning_rate": 1.706364526851544e-05,
"loss": 0.5117,
"step": 1053
},
{
"epoch": 0.27,
"learning_rate": 1.7057701635332607e-05,
"loss": 0.5154,
"step": 1054
},
{
"epoch": 0.27,
"learning_rate": 1.7051753030238612e-05,
"loss": 0.5449,
"step": 1055
},
{
"epoch": 0.27,
"learning_rate": 1.704579945742404e-05,
"loss": 0.4846,
"step": 1056
},
{
"epoch": 0.27,
"learning_rate": 1.7039840921082985e-05,
"loss": 0.5098,
"step": 1057
},
{
"epoch": 0.27,
"learning_rate": 1.703387742541303e-05,
"loss": 0.5044,
"step": 1058
},
{
"epoch": 0.27,
"learning_rate": 1.702790897461526e-05,
"loss": 0.4895,
"step": 1059
},
{
"epoch": 0.27,
"learning_rate": 1.7021935572894247e-05,
"loss": 0.4929,
"step": 1060
},
{
"epoch": 0.27,
"learning_rate": 1.7015957224458042e-05,
"loss": 0.522,
"step": 1061
},
{
"epoch": 0.28,
"learning_rate": 1.7009973933518194e-05,
"loss": 0.4897,
"step": 1062
},
{
"epoch": 0.28,
"learning_rate": 1.700398570428973e-05,
"loss": 0.4773,
"step": 1063
},
{
"epoch": 0.28,
"learning_rate": 1.6997992540991148e-05,
"loss": 0.5125,
"step": 1064
},
{
"epoch": 0.28,
"learning_rate": 1.699199444784443e-05,
"loss": 0.509,
"step": 1065
},
{
"epoch": 0.28,
"learning_rate": 1.6985991429075038e-05,
"loss": 0.5222,
"step": 1066
},
{
"epoch": 0.28,
"learning_rate": 1.6979983488911883e-05,
"loss": 0.4976,
"step": 1067
},
{
"epoch": 0.28,
"learning_rate": 1.6973970631587358e-05,
"loss": 0.5085,
"step": 1068
},
{
"epoch": 0.28,
"learning_rate": 1.6967952861337317e-05,
"loss": 0.5015,
"step": 1069
},
{
"epoch": 0.28,
"learning_rate": 1.6961930182401077e-05,
"loss": 0.5205,
"step": 1070
},
{
"epoch": 0.28,
"learning_rate": 1.6955902599021416e-05,
"loss": 0.5251,
"step": 1071
},
{
"epoch": 0.28,
"learning_rate": 1.6949870115444546e-05,
"loss": 0.4817,
"step": 1072
},
{
"epoch": 0.28,
"learning_rate": 1.694383273592016e-05,
"loss": 0.5225,
"step": 1073
},
{
"epoch": 0.28,
"learning_rate": 1.6937790464701386e-05,
"loss": 0.5254,
"step": 1074
},
{
"epoch": 0.28,
"learning_rate": 1.693174330604479e-05,
"loss": 0.5132,
"step": 1075
},
{
"epoch": 0.28,
"learning_rate": 1.69256912642104e-05,
"loss": 0.5024,
"step": 1076
},
{
"epoch": 0.28,
"learning_rate": 1.691963434346167e-05,
"loss": 0.5137,
"step": 1077
},
{
"epoch": 0.28,
"learning_rate": 1.6913572548065496e-05,
"loss": 0.5203,
"step": 1078
},
{
"epoch": 0.28,
"learning_rate": 1.6907505882292205e-05,
"loss": 0.4844,
"step": 1079
},
{
"epoch": 0.28,
"learning_rate": 1.690143435041556e-05,
"loss": 0.4895,
"step": 1080
},
{
"epoch": 0.28,
"learning_rate": 1.6895357956712746e-05,
"loss": 0.5256,
"step": 1081
},
{
"epoch": 0.28,
"learning_rate": 1.6889276705464376e-05,
"loss": 0.5137,
"step": 1082
},
{
"epoch": 0.28,
"learning_rate": 1.6883190600954488e-05,
"loss": 0.5032,
"step": 1083
},
{
"epoch": 0.28,
"learning_rate": 1.6877099647470533e-05,
"loss": 0.5007,
"step": 1084
},
{
"epoch": 0.28,
"learning_rate": 1.687100384930338e-05,
"loss": 0.4819,
"step": 1085
},
{
"epoch": 0.28,
"learning_rate": 1.686490321074732e-05,
"loss": 0.4998,
"step": 1086
},
{
"epoch": 0.28,
"learning_rate": 1.6858797736100034e-05,
"loss": 0.5093,
"step": 1087
},
{
"epoch": 0.28,
"learning_rate": 1.685268742966263e-05,
"loss": 0.5188,
"step": 1088
},
{
"epoch": 0.28,
"learning_rate": 1.6846572295739608e-05,
"loss": 0.5171,
"step": 1089
},
{
"epoch": 0.28,
"learning_rate": 1.6840452338638874e-05,
"loss": 0.5264,
"step": 1090
},
{
"epoch": 0.28,
"learning_rate": 1.6834327562671728e-05,
"loss": 0.4958,
"step": 1091
},
{
"epoch": 0.28,
"learning_rate": 1.6828197972152867e-05,
"loss": 0.5107,
"step": 1092
},
{
"epoch": 0.28,
"learning_rate": 1.682206357140038e-05,
"loss": 0.5105,
"step": 1093
},
{
"epoch": 0.28,
"learning_rate": 1.681592436473575e-05,
"loss": 0.4871,
"step": 1094
},
{
"epoch": 0.28,
"learning_rate": 1.6809780356483826e-05,
"loss": 0.5144,
"step": 1095
},
{
"epoch": 0.28,
"learning_rate": 1.6803631550972866e-05,
"loss": 0.5159,
"step": 1096
},
{
"epoch": 0.28,
"learning_rate": 1.6797477952534486e-05,
"loss": 0.5347,
"step": 1097
},
{
"epoch": 0.28,
"learning_rate": 1.6791319565503693e-05,
"loss": 0.5078,
"step": 1098
},
{
"epoch": 0.28,
"learning_rate": 1.6785156394218857e-05,
"loss": 0.4905,
"step": 1099
},
{
"epoch": 0.29,
"learning_rate": 1.6778988443021725e-05,
"loss": 0.5037,
"step": 1100
},
{
"epoch": 0.29,
"learning_rate": 1.6772815716257414e-05,
"loss": 0.5117,
"step": 1101
},
{
"epoch": 0.29,
"learning_rate": 1.676663821827439e-05,
"loss": 0.5149,
"step": 1102
},
{
"epoch": 0.29,
"learning_rate": 1.67604559534245e-05,
"loss": 0.5024,
"step": 1103
},
{
"epoch": 0.29,
"learning_rate": 1.6754268926062936e-05,
"loss": 0.5002,
"step": 1104
},
{
"epoch": 0.29,
"learning_rate": 1.6748077140548248e-05,
"loss": 0.5391,
"step": 1105
},
{
"epoch": 0.29,
"learning_rate": 1.674188060124234e-05,
"loss": 0.5354,
"step": 1106
},
{
"epoch": 0.29,
"learning_rate": 1.6735679312510464e-05,
"loss": 0.521,
"step": 1107
},
{
"epoch": 0.29,
"learning_rate": 1.672947327872121e-05,
"loss": 0.5173,
"step": 1108
},
{
"epoch": 0.29,
"learning_rate": 1.6723262504246536e-05,
"loss": 0.5339,
"step": 1109
},
{
"epoch": 0.29,
"learning_rate": 1.67170469934617e-05,
"loss": 0.5142,
"step": 1110
},
{
"epoch": 0.29,
"learning_rate": 1.6710826750745332e-05,
"loss": 0.488,
"step": 1111
},
{
"epoch": 0.29,
"learning_rate": 1.6704601780479382e-05,
"loss": 0.4871,
"step": 1112
},
{
"epoch": 0.29,
"learning_rate": 1.669837208704912e-05,
"loss": 0.4849,
"step": 1113
},
{
"epoch": 0.29,
"learning_rate": 1.6692137674843164e-05,
"loss": 0.5276,
"step": 1114
},
{
"epoch": 0.29,
"learning_rate": 1.6685898548253442e-05,
"loss": 0.5022,
"step": 1115
},
{
"epoch": 0.29,
"learning_rate": 1.6679654711675205e-05,
"loss": 0.5083,
"step": 1116
},
{
"epoch": 0.29,
"learning_rate": 1.6673406169507026e-05,
"loss": 0.4954,
"step": 1117
},
{
"epoch": 0.29,
"learning_rate": 1.666715292615079e-05,
"loss": 0.4897,
"step": 1118
},
{
"epoch": 0.29,
"learning_rate": 1.6660894986011693e-05,
"loss": 0.4946,
"step": 1119
},
{
"epoch": 0.29,
"learning_rate": 1.6654632353498246e-05,
"loss": 0.5137,
"step": 1120
},
{
"epoch": 0.29,
"learning_rate": 1.6648365033022256e-05,
"loss": 0.51,
"step": 1121
},
{
"epoch": 0.29,
"learning_rate": 1.664209302899884e-05,
"loss": 0.5002,
"step": 1122
},
{
"epoch": 0.29,
"learning_rate": 1.6635816345846413e-05,
"loss": 0.5137,
"step": 1123
},
{
"epoch": 0.29,
"learning_rate": 1.662953498798668e-05,
"loss": 0.5266,
"step": 1124
},
{
"epoch": 0.29,
"learning_rate": 1.6623248959844653e-05,
"loss": 0.4937,
"step": 1125
},
{
"epoch": 0.29,
"learning_rate": 1.6616958265848618e-05,
"loss": 0.5037,
"step": 1126
},
{
"epoch": 0.29,
"learning_rate": 1.6610662910430154e-05,
"loss": 0.4961,
"step": 1127
},
{
"epoch": 0.29,
"learning_rate": 1.6604362898024137e-05,
"loss": 0.5078,
"step": 1128
},
{
"epoch": 0.29,
"learning_rate": 1.65980582330687e-05,
"loss": 0.5007,
"step": 1129
},
{
"epoch": 0.29,
"learning_rate": 1.6591748920005266e-05,
"loss": 0.519,
"step": 1130
},
{
"epoch": 0.29,
"learning_rate": 1.6585434963278534e-05,
"loss": 0.521,
"step": 1131
},
{
"epoch": 0.29,
"learning_rate": 1.6579116367336477e-05,
"loss": 0.5007,
"step": 1132
},
{
"epoch": 0.29,
"learning_rate": 1.6572793136630327e-05,
"loss": 0.5186,
"step": 1133
},
{
"epoch": 0.29,
"learning_rate": 1.6566465275614586e-05,
"loss": 0.4951,
"step": 1134
},
{
"epoch": 0.29,
"learning_rate": 1.6560132788747013e-05,
"loss": 0.4954,
"step": 1135
},
{
"epoch": 0.29,
"learning_rate": 1.6553795680488635e-05,
"loss": 0.5073,
"step": 1136
},
{
"epoch": 0.29,
"learning_rate": 1.6547453955303733e-05,
"loss": 0.4766,
"step": 1137
},
{
"epoch": 0.29,
"learning_rate": 1.654110761765983e-05,
"loss": 0.5027,
"step": 1138
},
{
"epoch": 0.3,
"learning_rate": 1.6534756672027703e-05,
"loss": 0.5071,
"step": 1139
},
{
"epoch": 0.3,
"learning_rate": 1.652840112288139e-05,
"loss": 0.5049,
"step": 1140
},
{
"epoch": 0.3,
"learning_rate": 1.6522040974698148e-05,
"loss": 0.4834,
"step": 1141
},
{
"epoch": 0.3,
"learning_rate": 1.6515676231958488e-05,
"loss": 0.5166,
"step": 1142
},
{
"epoch": 0.3,
"learning_rate": 1.650930689914616e-05,
"loss": 0.4939,
"step": 1143
},
{
"epoch": 0.3,
"learning_rate": 1.6502932980748138e-05,
"loss": 0.5068,
"step": 1144
},
{
"epoch": 0.3,
"learning_rate": 1.6496554481254632e-05,
"loss": 0.5044,
"step": 1145
},
{
"epoch": 0.3,
"learning_rate": 1.649017140515908e-05,
"loss": 0.5078,
"step": 1146
},
{
"epoch": 0.3,
"learning_rate": 1.6483783756958142e-05,
"loss": 0.4731,
"step": 1147
},
{
"epoch": 0.3,
"learning_rate": 1.6477391541151696e-05,
"loss": 0.4907,
"step": 1148
},
{
"epoch": 0.3,
"learning_rate": 1.647099476224284e-05,
"loss": 0.51,
"step": 1149
},
{
"epoch": 0.3,
"learning_rate": 1.6464593424737894e-05,
"loss": 0.5022,
"step": 1150
},
{
"epoch": 0.3,
"learning_rate": 1.6458187533146385e-05,
"loss": 0.5039,
"step": 1151
},
{
"epoch": 0.3,
"learning_rate": 1.6451777091981037e-05,
"loss": 0.5005,
"step": 1152
},
{
"epoch": 0.3,
"learning_rate": 1.644536210575779e-05,
"loss": 0.5142,
"step": 1153
},
{
"epoch": 0.3,
"learning_rate": 1.6438942578995786e-05,
"loss": 0.5132,
"step": 1154
},
{
"epoch": 0.3,
"learning_rate": 1.6432518516217367e-05,
"loss": 0.5371,
"step": 1155
},
{
"epoch": 0.3,
"learning_rate": 1.642608992194806e-05,
"loss": 0.5129,
"step": 1156
},
{
"epoch": 0.3,
"learning_rate": 1.64196568007166e-05,
"loss": 0.5,
"step": 1157
},
{
"epoch": 0.3,
"learning_rate": 1.6413219157054893e-05,
"loss": 0.4822,
"step": 1158
},
{
"epoch": 0.3,
"learning_rate": 1.6406776995498048e-05,
"loss": 0.5156,
"step": 1159
},
{
"epoch": 0.3,
"learning_rate": 1.6400330320584347e-05,
"loss": 0.5164,
"step": 1160
},
{
"epoch": 0.3,
"learning_rate": 1.6393879136855247e-05,
"loss": 0.4854,
"step": 1161
},
{
"epoch": 0.3,
"learning_rate": 1.63874234488554e-05,
"loss": 0.5146,
"step": 1162
},
{
"epoch": 0.3,
"learning_rate": 1.638096326113261e-05,
"loss": 0.4905,
"step": 1163
},
{
"epoch": 0.3,
"learning_rate": 1.637449857823786e-05,
"loss": 0.4663,
"step": 1164
},
{
"epoch": 0.3,
"learning_rate": 1.6368029404725308e-05,
"loss": 0.4944,
"step": 1165
},
{
"epoch": 0.3,
"learning_rate": 1.6361555745152258e-05,
"loss": 0.4868,
"step": 1166
},
{
"epoch": 0.3,
"learning_rate": 1.6355077604079187e-05,
"loss": 0.5051,
"step": 1167
},
{
"epoch": 0.3,
"learning_rate": 1.634859498606972e-05,
"loss": 0.4878,
"step": 1168
},
{
"epoch": 0.3,
"learning_rate": 1.6342107895690653e-05,
"loss": 0.5073,
"step": 1169
},
{
"epoch": 0.3,
"learning_rate": 1.633561633751191e-05,
"loss": 0.4839,
"step": 1170
},
{
"epoch": 0.3,
"learning_rate": 1.6329120316106578e-05,
"loss": 0.481,
"step": 1171
},
{
"epoch": 0.3,
"learning_rate": 1.6322619836050884e-05,
"loss": 0.4946,
"step": 1172
},
{
"epoch": 0.3,
"learning_rate": 1.6316114901924195e-05,
"loss": 0.5337,
"step": 1173
},
{
"epoch": 0.3,
"learning_rate": 1.6309605518309016e-05,
"loss": 0.5137,
"step": 1174
},
{
"epoch": 0.3,
"learning_rate": 1.6303091689790986e-05,
"loss": 0.5076,
"step": 1175
},
{
"epoch": 0.3,
"learning_rate": 1.6296573420958877e-05,
"loss": 0.5149,
"step": 1176
},
{
"epoch": 0.31,
"learning_rate": 1.6290050716404588e-05,
"loss": 0.4897,
"step": 1177
},
{
"epoch": 0.31,
"learning_rate": 1.628352358072314e-05,
"loss": 0.4858,
"step": 1178
},
{
"epoch": 0.31,
"learning_rate": 1.627699201851268e-05,
"loss": 0.5317,
"step": 1179
},
{
"epoch": 0.31,
"learning_rate": 1.6270456034374477e-05,
"loss": 0.4941,
"step": 1180
},
{
"epoch": 0.31,
"learning_rate": 1.62639156329129e-05,
"loss": 0.501,
"step": 1181
},
{
"epoch": 0.31,
"learning_rate": 1.625737081873545e-05,
"loss": 0.5068,
"step": 1182
},
{
"epoch": 0.31,
"learning_rate": 1.625082159645272e-05,
"loss": 0.5044,
"step": 1183
},
{
"epoch": 0.31,
"learning_rate": 1.624426797067842e-05,
"loss": 0.512,
"step": 1184
},
{
"epoch": 0.31,
"learning_rate": 1.6237709946029347e-05,
"loss": 0.5161,
"step": 1185
},
{
"epoch": 0.31,
"learning_rate": 1.6231147527125415e-05,
"loss": 0.4817,
"step": 1186
},
{
"epoch": 0.31,
"learning_rate": 1.6224580718589626e-05,
"loss": 0.4966,
"step": 1187
},
{
"epoch": 0.31,
"learning_rate": 1.6218009525048068e-05,
"loss": 0.5088,
"step": 1188
},
{
"epoch": 0.31,
"learning_rate": 1.6211433951129928e-05,
"loss": 0.4841,
"step": 1189
},
{
"epoch": 0.31,
"learning_rate": 1.6204854001467473e-05,
"loss": 0.4827,
"step": 1190
},
{
"epoch": 0.31,
"learning_rate": 1.619826968069605e-05,
"loss": 0.5078,
"step": 1191
},
{
"epoch": 0.31,
"learning_rate": 1.61916809934541e-05,
"loss": 0.5132,
"step": 1192
},
{
"epoch": 0.31,
"learning_rate": 1.618508794438312e-05,
"loss": 0.479,
"step": 1193
},
{
"epoch": 0.31,
"learning_rate": 1.6178490538127696e-05,
"loss": 0.5142,
"step": 1194
},
{
"epoch": 0.31,
"learning_rate": 1.617188877933547e-05,
"loss": 0.4873,
"step": 1195
},
{
"epoch": 0.31,
"learning_rate": 1.6165282672657158e-05,
"loss": 0.4746,
"step": 1196
},
{
"epoch": 0.31,
"learning_rate": 1.615867222274654e-05,
"loss": 0.4988,
"step": 1197
},
{
"epoch": 0.31,
"learning_rate": 1.6152057434260456e-05,
"loss": 0.4832,
"step": 1198
},
{
"epoch": 0.31,
"learning_rate": 1.61454383118588e-05,
"loss": 0.4724,
"step": 1199
},
{
"epoch": 0.31,
"learning_rate": 1.6138814860204513e-05,
"loss": 0.5337,
"step": 1200
},
{
"epoch": 0.31,
"learning_rate": 1.6132187083963593e-05,
"loss": 0.5005,
"step": 1201
},
{
"epoch": 0.31,
"learning_rate": 1.6125554987805084e-05,
"loss": 0.4897,
"step": 1202
},
{
"epoch": 0.31,
"learning_rate": 1.611891857640108e-05,
"loss": 0.4973,
"step": 1203
},
{
"epoch": 0.31,
"learning_rate": 1.6112277854426696e-05,
"loss": 0.5178,
"step": 1204
},
{
"epoch": 0.31,
"learning_rate": 1.6105632826560108e-05,
"loss": 0.5327,
"step": 1205
},
{
"epoch": 0.31,
"learning_rate": 1.6098983497482497e-05,
"loss": 0.519,
"step": 1206
},
{
"epoch": 0.31,
"learning_rate": 1.6092329871878102e-05,
"loss": 0.4863,
"step": 1207
},
{
"epoch": 0.31,
"learning_rate": 1.608567195443417e-05,
"loss": 0.5139,
"step": 1208
},
{
"epoch": 0.31,
"learning_rate": 1.607900974984098e-05,
"loss": 0.4844,
"step": 1209
},
{
"epoch": 0.31,
"learning_rate": 1.607234326279183e-05,
"loss": 0.4922,
"step": 1210
},
{
"epoch": 0.31,
"learning_rate": 1.606567249798303e-05,
"loss": 0.4985,
"step": 1211
},
{
"epoch": 0.31,
"learning_rate": 1.605899746011391e-05,
"loss": 0.5103,
"step": 1212
},
{
"epoch": 0.31,
"learning_rate": 1.605231815388681e-05,
"loss": 0.5046,
"step": 1213
},
{
"epoch": 0.31,
"learning_rate": 1.604563458400707e-05,
"loss": 0.5327,
"step": 1214
},
{
"epoch": 0.31,
"learning_rate": 1.6038946755183038e-05,
"loss": 0.5156,
"step": 1215
},
{
"epoch": 0.32,
"learning_rate": 1.6032254672126068e-05,
"loss": 0.4788,
"step": 1216
},
{
"epoch": 0.32,
"learning_rate": 1.6025558339550497e-05,
"loss": 0.4878,
"step": 1217
},
{
"epoch": 0.32,
"learning_rate": 1.6018857762173672e-05,
"loss": 0.5034,
"step": 1218
},
{
"epoch": 0.32,
"learning_rate": 1.6012152944715915e-05,
"loss": 0.5198,
"step": 1219
},
{
"epoch": 0.32,
"learning_rate": 1.600544389190055e-05,
"loss": 0.4834,
"step": 1220
},
{
"epoch": 0.32,
"learning_rate": 1.5998730608453868e-05,
"loss": 0.5056,
"step": 1221
},
{
"epoch": 0.32,
"learning_rate": 1.5992013099105156e-05,
"loss": 0.5071,
"step": 1222
},
{
"epoch": 0.32,
"learning_rate": 1.598529136858667e-05,
"loss": 0.5068,
"step": 1223
},
{
"epoch": 0.32,
"learning_rate": 1.5978565421633642e-05,
"loss": 0.5024,
"step": 1224
},
{
"epoch": 0.32,
"learning_rate": 1.5971835262984266e-05,
"loss": 0.5212,
"step": 1225
},
{
"epoch": 0.32,
"learning_rate": 1.596510089737972e-05,
"loss": 0.509,
"step": 1226
},
{
"epoch": 0.32,
"learning_rate": 1.5958362329564127e-05,
"loss": 0.4924,
"step": 1227
},
{
"epoch": 0.32,
"learning_rate": 1.5951619564284588e-05,
"loss": 0.5122,
"step": 1228
},
{
"epoch": 0.32,
"learning_rate": 1.5944872606291148e-05,
"loss": 0.5034,
"step": 1229
},
{
"epoch": 0.32,
"learning_rate": 1.593812146033681e-05,
"loss": 0.5022,
"step": 1230
},
{
"epoch": 0.32,
"learning_rate": 1.5931366131177524e-05,
"loss": 0.4836,
"step": 1231
},
{
"epoch": 0.32,
"learning_rate": 1.5924606623572194e-05,
"loss": 0.4597,
"step": 1232
},
{
"epoch": 0.32,
"learning_rate": 1.5917842942282663e-05,
"loss": 0.5127,
"step": 1233
},
{
"epoch": 0.32,
"learning_rate": 1.5911075092073717e-05,
"loss": 0.4995,
"step": 1234
},
{
"epoch": 0.32,
"learning_rate": 1.5904303077713068e-05,
"loss": 0.458,
"step": 1235
},
{
"epoch": 0.32,
"learning_rate": 1.589752690397138e-05,
"loss": 0.4641,
"step": 1236
},
{
"epoch": 0.32,
"learning_rate": 1.589074657562223e-05,
"loss": 0.4927,
"step": 1237
},
{
"epoch": 0.32,
"learning_rate": 1.5883962097442137e-05,
"loss": 0.5132,
"step": 1238
},
{
"epoch": 0.32,
"learning_rate": 1.587717347421053e-05,
"loss": 0.4861,
"step": 1239
},
{
"epoch": 0.32,
"learning_rate": 1.5870380710709762e-05,
"loss": 0.4958,
"step": 1240
},
{
"epoch": 0.32,
"learning_rate": 1.5863583811725106e-05,
"loss": 0.5195,
"step": 1241
},
{
"epoch": 0.32,
"learning_rate": 1.5856782782044752e-05,
"loss": 0.49,
"step": 1242
},
{
"epoch": 0.32,
"learning_rate": 1.584997762645979e-05,
"loss": 0.491,
"step": 1243
},
{
"epoch": 0.32,
"learning_rate": 1.5843168349764217e-05,
"loss": 0.4985,
"step": 1244
},
{
"epoch": 0.32,
"learning_rate": 1.5836354956754946e-05,
"loss": 0.5234,
"step": 1245
},
{
"epoch": 0.32,
"learning_rate": 1.582953745223177e-05,
"loss": 0.4937,
"step": 1246
},
{
"epoch": 0.32,
"learning_rate": 1.58227158409974e-05,
"loss": 0.4893,
"step": 1247
},
{
"epoch": 0.32,
"learning_rate": 1.5815890127857426e-05,
"loss": 0.499,
"step": 1248
},
{
"epoch": 0.32,
"learning_rate": 1.5809060317620328e-05,
"loss": 0.4917,
"step": 1249
},
{
"epoch": 0.32,
"learning_rate": 1.5802226415097478e-05,
"loss": 0.5137,
"step": 1250
},
{
"epoch": 0.32,
"learning_rate": 1.5795388425103127e-05,
"loss": 0.4827,
"step": 1251
},
{
"epoch": 0.32,
"learning_rate": 1.578854635245441e-05,
"loss": 0.491,
"step": 1252
},
{
"epoch": 0.32,
"learning_rate": 1.5781700201971332e-05,
"loss": 0.4739,
"step": 1253
},
{
"epoch": 0.32,
"learning_rate": 1.5774849978476774e-05,
"loss": 0.4783,
"step": 1254
},
{
"epoch": 0.33,
"learning_rate": 1.5767995686796487e-05,
"loss": 0.4963,
"step": 1255
},
{
"epoch": 0.33,
"learning_rate": 1.5761137331759084e-05,
"loss": 0.4851,
"step": 1256
},
{
"epoch": 0.33,
"learning_rate": 1.5754274918196046e-05,
"loss": 0.4919,
"step": 1257
},
{
"epoch": 0.33,
"learning_rate": 1.574740845094171e-05,
"loss": 0.491,
"step": 1258
},
{
"epoch": 0.33,
"learning_rate": 1.574053793483327e-05,
"loss": 0.4846,
"step": 1259
},
{
"epoch": 0.33,
"learning_rate": 1.5733663374710768e-05,
"loss": 0.4961,
"step": 1260
},
{
"epoch": 0.33,
"learning_rate": 1.5726784775417097e-05,
"loss": 0.5352,
"step": 1261
},
{
"epoch": 0.33,
"learning_rate": 1.5719902141798e-05,
"loss": 0.4912,
"step": 1262
},
{
"epoch": 0.33,
"learning_rate": 1.5713015478702064e-05,
"loss": 0.5142,
"step": 1263
},
{
"epoch": 0.33,
"learning_rate": 1.57061247909807e-05,
"loss": 0.5061,
"step": 1264
},
{
"epoch": 0.33,
"learning_rate": 1.5699230083488167e-05,
"loss": 0.5095,
"step": 1265
},
{
"epoch": 0.33,
"learning_rate": 1.5692331361081553e-05,
"loss": 0.4832,
"step": 1266
},
{
"epoch": 0.33,
"learning_rate": 1.5685428628620773e-05,
"loss": 0.5144,
"step": 1267
},
{
"epoch": 0.33,
"learning_rate": 1.5678521890968566e-05,
"loss": 0.5068,
"step": 1268
},
{
"epoch": 0.33,
"learning_rate": 1.56716111529905e-05,
"loss": 0.4773,
"step": 1269
},
{
"epoch": 0.33,
"learning_rate": 1.566469641955495e-05,
"loss": 0.4741,
"step": 1270
},
{
"epoch": 0.33,
"learning_rate": 1.565777769553311e-05,
"loss": 0.4956,
"step": 1271
},
{
"epoch": 0.33,
"learning_rate": 1.565085498579899e-05,
"loss": 0.4922,
"step": 1272
},
{
"epoch": 0.33,
"learning_rate": 1.56439282952294e-05,
"loss": 0.5083,
"step": 1273
},
{
"epoch": 0.33,
"learning_rate": 1.5636997628703966e-05,
"loss": 0.4758,
"step": 1274
},
{
"epoch": 0.33,
"learning_rate": 1.56300629911051e-05,
"loss": 0.5164,
"step": 1275
},
{
"epoch": 0.33,
"learning_rate": 1.5623124387318018e-05,
"loss": 0.5063,
"step": 1276
},
{
"epoch": 0.33,
"learning_rate": 1.5616181822230734e-05,
"loss": 0.4995,
"step": 1277
},
{
"epoch": 0.33,
"learning_rate": 1.560923530073405e-05,
"loss": 0.5024,
"step": 1278
},
{
"epoch": 0.33,
"learning_rate": 1.5602284827721552e-05,
"loss": 0.4954,
"step": 1279
},
{
"epoch": 0.33,
"learning_rate": 1.5595330408089613e-05,
"loss": 0.5144,
"step": 1280
},
{
"epoch": 0.33,
"learning_rate": 1.558837204673739e-05,
"loss": 0.4675,
"step": 1281
},
{
"epoch": 0.33,
"learning_rate": 1.55814097485668e-05,
"loss": 0.5034,
"step": 1282
},
{
"epoch": 0.33,
"learning_rate": 1.5574443518482564e-05,
"loss": 0.5068,
"step": 1283
},
{
"epoch": 0.33,
"learning_rate": 1.5567473361392135e-05,
"loss": 0.5044,
"step": 1284
},
{
"epoch": 0.33,
"learning_rate": 1.556049928220577e-05,
"loss": 0.5027,
"step": 1285
},
{
"epoch": 0.33,
"learning_rate": 1.5553521285836455e-05,
"loss": 0.4758,
"step": 1286
},
{
"epoch": 0.33,
"learning_rate": 1.5546539377199964e-05,
"loss": 0.5046,
"step": 1287
},
{
"epoch": 0.33,
"learning_rate": 1.553955356121481e-05,
"loss": 0.512,
"step": 1288
},
{
"epoch": 0.33,
"learning_rate": 1.553256384280226e-05,
"loss": 0.4902,
"step": 1289
},
{
"epoch": 0.33,
"learning_rate": 1.5525570226886334e-05,
"loss": 0.501,
"step": 1290
},
{
"epoch": 0.33,
"learning_rate": 1.5518572718393804e-05,
"loss": 0.5166,
"step": 1291
},
{
"epoch": 0.33,
"learning_rate": 1.5511571322254172e-05,
"loss": 0.4873,
"step": 1292
},
{
"epoch": 0.34,
"learning_rate": 1.5504566043399682e-05,
"loss": 0.5098,
"step": 1293
},
{
"epoch": 0.34,
"learning_rate": 1.5497556886765316e-05,
"loss": 0.5088,
"step": 1294
},
{
"epoch": 0.34,
"learning_rate": 1.5490543857288793e-05,
"loss": 0.5098,
"step": 1295
},
{
"epoch": 0.34,
"learning_rate": 1.5483526959910543e-05,
"loss": 0.4917,
"step": 1296
},
{
"epoch": 0.34,
"learning_rate": 1.547650619957374e-05,
"loss": 0.4924,
"step": 1297
},
{
"epoch": 0.34,
"learning_rate": 1.5469481581224274e-05,
"loss": 0.5071,
"step": 1298
},
{
"epoch": 0.34,
"learning_rate": 1.5462453109810738e-05,
"loss": 0.4729,
"step": 1299
},
{
"epoch": 0.34,
"learning_rate": 1.5455420790284463e-05,
"loss": 0.5098,
"step": 1300
},
{
"epoch": 0.34,
"learning_rate": 1.5448384627599473e-05,
"loss": 0.459,
"step": 1301
},
{
"epoch": 0.34,
"learning_rate": 1.544134462671251e-05,
"loss": 0.5186,
"step": 1302
},
{
"epoch": 0.34,
"learning_rate": 1.5434300792583012e-05,
"loss": 0.4958,
"step": 1303
},
{
"epoch": 0.34,
"learning_rate": 1.5427253130173126e-05,
"loss": 0.4944,
"step": 1304
},
{
"epoch": 0.34,
"learning_rate": 1.5420201644447682e-05,
"loss": 0.4824,
"step": 1305
},
{
"epoch": 0.34,
"learning_rate": 1.5413146340374222e-05,
"loss": 0.4968,
"step": 1306
},
{
"epoch": 0.34,
"learning_rate": 1.540608722292296e-05,
"loss": 0.5032,
"step": 1307
},
{
"epoch": 0.34,
"learning_rate": 1.5399024297066813e-05,
"loss": 0.5107,
"step": 1308
},
{
"epoch": 0.34,
"learning_rate": 1.5391957567781363e-05,
"loss": 0.4937,
"step": 1309
},
{
"epoch": 0.34,
"learning_rate": 1.5384887040044885e-05,
"loss": 0.4993,
"step": 1310
},
{
"epoch": 0.34,
"learning_rate": 1.5377812718838332e-05,
"loss": 0.5139,
"step": 1311
},
{
"epoch": 0.34,
"learning_rate": 1.5370734609145314e-05,
"loss": 0.5117,
"step": 1312
},
{
"epoch": 0.34,
"learning_rate": 1.536365271595212e-05,
"loss": 0.4902,
"step": 1313
},
{
"epoch": 0.34,
"learning_rate": 1.535656704424771e-05,
"loss": 0.5049,
"step": 1314
},
{
"epoch": 0.34,
"learning_rate": 1.5349477599023696e-05,
"loss": 0.5054,
"step": 1315
},
{
"epoch": 0.34,
"learning_rate": 1.5342384385274346e-05,
"loss": 0.4868,
"step": 1316
},
{
"epoch": 0.34,
"learning_rate": 1.5335287407996597e-05,
"loss": 0.4634,
"step": 1317
},
{
"epoch": 0.34,
"learning_rate": 1.532818667219002e-05,
"loss": 0.4834,
"step": 1318
},
{
"epoch": 0.34,
"learning_rate": 1.5321082182856848e-05,
"loss": 0.4993,
"step": 1319
},
{
"epoch": 0.34,
"learning_rate": 1.531397394500195e-05,
"loss": 0.4656,
"step": 1320
},
{
"epoch": 0.34,
"learning_rate": 1.530686196363284e-05,
"loss": 0.4907,
"step": 1321
},
{
"epoch": 0.34,
"learning_rate": 1.5299746243759668e-05,
"loss": 0.4858,
"step": 1322
},
{
"epoch": 0.34,
"learning_rate": 1.5292626790395213e-05,
"loss": 0.5017,
"step": 1323
},
{
"epoch": 0.34,
"learning_rate": 1.5285503608554893e-05,
"loss": 0.4993,
"step": 1324
},
{
"epoch": 0.34,
"learning_rate": 1.527837670325674e-05,
"loss": 0.5413,
"step": 1325
},
{
"epoch": 0.34,
"learning_rate": 1.5271246079521428e-05,
"loss": 0.49,
"step": 1326
},
{
"epoch": 0.34,
"learning_rate": 1.526411174237223e-05,
"loss": 0.5173,
"step": 1327
},
{
"epoch": 0.34,
"learning_rate": 1.5256973696835048e-05,
"loss": 0.5037,
"step": 1328
},
{
"epoch": 0.34,
"learning_rate": 1.5249831947938394e-05,
"loss": 0.4419,
"step": 1329
},
{
"epoch": 0.34,
"learning_rate": 1.5242686500713383e-05,
"loss": 0.488,
"step": 1330
},
{
"epoch": 0.34,
"learning_rate": 1.5235537360193749e-05,
"loss": 0.5132,
"step": 1331
},
{
"epoch": 0.35,
"learning_rate": 1.5228384531415809e-05,
"loss": 0.4856,
"step": 1332
},
{
"epoch": 0.35,
"learning_rate": 1.522122801941849e-05,
"loss": 0.4763,
"step": 1333
},
{
"epoch": 0.35,
"learning_rate": 1.5214067829243316e-05,
"loss": 0.4951,
"step": 1334
},
{
"epoch": 0.35,
"learning_rate": 1.5206903965934394e-05,
"loss": 0.4922,
"step": 1335
},
{
"epoch": 0.35,
"learning_rate": 1.5199736434538425e-05,
"loss": 0.4937,
"step": 1336
},
{
"epoch": 0.35,
"learning_rate": 1.5192565240104691e-05,
"loss": 0.4751,
"step": 1337
},
{
"epoch": 0.35,
"learning_rate": 1.5185390387685055e-05,
"loss": 0.5027,
"step": 1338
},
{
"epoch": 0.35,
"learning_rate": 1.5178211882333953e-05,
"loss": 0.5093,
"step": 1339
},
{
"epoch": 0.35,
"learning_rate": 1.5171029729108404e-05,
"loss": 0.4846,
"step": 1340
},
{
"epoch": 0.35,
"learning_rate": 1.5163843933067986e-05,
"loss": 0.5002,
"step": 1341
},
{
"epoch": 0.35,
"learning_rate": 1.5156654499274852e-05,
"loss": 0.5115,
"step": 1342
},
{
"epoch": 0.35,
"learning_rate": 1.5149461432793713e-05,
"loss": 0.48,
"step": 1343
},
{
"epoch": 0.35,
"learning_rate": 1.514226473869184e-05,
"loss": 0.4897,
"step": 1344
},
{
"epoch": 0.35,
"learning_rate": 1.513506442203906e-05,
"loss": 0.4968,
"step": 1345
},
{
"epoch": 0.35,
"learning_rate": 1.5127860487907752e-05,
"loss": 0.4773,
"step": 1346
},
{
"epoch": 0.35,
"learning_rate": 1.5120652941372842e-05,
"loss": 0.4854,
"step": 1347
},
{
"epoch": 0.35,
"learning_rate": 1.51134417875118e-05,
"loss": 0.4934,
"step": 1348
},
{
"epoch": 0.35,
"learning_rate": 1.5106227031404643e-05,
"loss": 0.5017,
"step": 1349
},
{
"epoch": 0.35,
"learning_rate": 1.509900867813392e-05,
"loss": 0.4856,
"step": 1350
},
{
"epoch": 0.35,
"learning_rate": 1.5091786732784717e-05,
"loss": 0.5085,
"step": 1351
},
{
"epoch": 0.35,
"learning_rate": 1.5084561200444646e-05,
"loss": 0.4856,
"step": 1352
},
{
"epoch": 0.35,
"learning_rate": 1.5077332086203847e-05,
"loss": 0.4844,
"step": 1353
},
{
"epoch": 0.35,
"learning_rate": 1.5070099395154994e-05,
"loss": 0.4998,
"step": 1354
},
{
"epoch": 0.35,
"learning_rate": 1.5062863132393269e-05,
"loss": 0.4851,
"step": 1355
},
{
"epoch": 0.35,
"learning_rate": 1.505562330301637e-05,
"loss": 0.5056,
"step": 1356
},
{
"epoch": 0.35,
"learning_rate": 1.5048379912124516e-05,
"loss": 0.5166,
"step": 1357
},
{
"epoch": 0.35,
"learning_rate": 1.5041132964820424e-05,
"loss": 0.4822,
"step": 1358
},
{
"epoch": 0.35,
"learning_rate": 1.5033882466209327e-05,
"loss": 0.478,
"step": 1359
},
{
"epoch": 0.35,
"learning_rate": 1.502662842139895e-05,
"loss": 0.4897,
"step": 1360
},
{
"epoch": 0.35,
"learning_rate": 1.5019370835499532e-05,
"loss": 0.5005,
"step": 1361
},
{
"epoch": 0.35,
"learning_rate": 1.5012109713623782e-05,
"loss": 0.4958,
"step": 1362
},
{
"epoch": 0.35,
"learning_rate": 1.5004845060886921e-05,
"loss": 0.491,
"step": 1363
},
{
"epoch": 0.35,
"learning_rate": 1.4997576882406652e-05,
"loss": 0.4976,
"step": 1364
},
{
"epoch": 0.35,
"learning_rate": 1.499030518330316e-05,
"loss": 0.49,
"step": 1365
},
{
"epoch": 0.35,
"learning_rate": 1.4983029968699103e-05,
"loss": 0.4802,
"step": 1366
},
{
"epoch": 0.35,
"learning_rate": 1.4975751243719632e-05,
"loss": 0.4956,
"step": 1367
},
{
"epoch": 0.35,
"learning_rate": 1.4968469013492355e-05,
"loss": 0.5208,
"step": 1368
},
{
"epoch": 0.35,
"learning_rate": 1.4961183283147356e-05,
"loss": 0.4729,
"step": 1369
},
{
"epoch": 0.36,
"learning_rate": 1.495389405781719e-05,
"loss": 0.4888,
"step": 1370
},
{
"epoch": 0.36,
"learning_rate": 1.4946601342636861e-05,
"loss": 0.5139,
"step": 1371
},
{
"epoch": 0.36,
"learning_rate": 1.4939305142743845e-05,
"loss": 0.4832,
"step": 1372
},
{
"epoch": 0.36,
"learning_rate": 1.493200546327807e-05,
"loss": 0.5273,
"step": 1373
},
{
"epoch": 0.36,
"learning_rate": 1.4924702309381905e-05,
"loss": 0.4868,
"step": 1374
},
{
"epoch": 0.36,
"learning_rate": 1.4917395686200173e-05,
"loss": 0.4832,
"step": 1375
},
{
"epoch": 0.36,
"learning_rate": 1.4910085598880151e-05,
"loss": 0.498,
"step": 1376
},
{
"epoch": 0.36,
"learning_rate": 1.4902772052571541e-05,
"loss": 0.4692,
"step": 1377
},
{
"epoch": 0.36,
"learning_rate": 1.4895455052426491e-05,
"loss": 0.4749,
"step": 1378
},
{
"epoch": 0.36,
"learning_rate": 1.4888134603599575e-05,
"loss": 0.4895,
"step": 1379
},
{
"epoch": 0.36,
"learning_rate": 1.4880810711247803e-05,
"loss": 0.4707,
"step": 1380
},
{
"epoch": 0.36,
"learning_rate": 1.487348338053061e-05,
"loss": 0.4844,
"step": 1381
},
{
"epoch": 0.36,
"learning_rate": 1.4866152616609849e-05,
"loss": 0.4922,
"step": 1382
},
{
"epoch": 0.36,
"learning_rate": 1.4858818424649795e-05,
"loss": 0.4744,
"step": 1383
},
{
"epoch": 0.36,
"learning_rate": 1.4851480809817139e-05,
"loss": 0.4729,
"step": 1384
},
{
"epoch": 0.36,
"learning_rate": 1.4844139777280979e-05,
"loss": 0.5061,
"step": 1385
},
{
"epoch": 0.36,
"learning_rate": 1.4836795332212825e-05,
"loss": 0.4841,
"step": 1386
},
{
"epoch": 0.36,
"learning_rate": 1.482944747978659e-05,
"loss": 0.4717,
"step": 1387
},
{
"epoch": 0.36,
"learning_rate": 1.4822096225178582e-05,
"loss": 0.468,
"step": 1388
},
{
"epoch": 0.36,
"learning_rate": 1.4814741573567514e-05,
"loss": 0.5002,
"step": 1389
},
{
"epoch": 0.36,
"learning_rate": 1.4807383530134495e-05,
"loss": 0.5042,
"step": 1390
},
{
"epoch": 0.36,
"learning_rate": 1.4800022100062998e-05,
"loss": 0.4946,
"step": 1391
},
{
"epoch": 0.36,
"learning_rate": 1.4792657288538918e-05,
"loss": 0.4668,
"step": 1392
},
{
"epoch": 0.36,
"learning_rate": 1.4785289100750509e-05,
"loss": 0.4934,
"step": 1393
},
{
"epoch": 0.36,
"learning_rate": 1.4777917541888408e-05,
"loss": 0.4651,
"step": 1394
},
{
"epoch": 0.36,
"learning_rate": 1.4770542617145627e-05,
"loss": 0.4956,
"step": 1395
},
{
"epoch": 0.36,
"learning_rate": 1.4763164331717556e-05,
"loss": 0.5007,
"step": 1396
},
{
"epoch": 0.36,
"learning_rate": 1.475578269080194e-05,
"loss": 0.4956,
"step": 1397
},
{
"epoch": 0.36,
"learning_rate": 1.4748397699598895e-05,
"loss": 0.5327,
"step": 1398
},
{
"epoch": 0.36,
"learning_rate": 1.47410093633109e-05,
"loss": 0.5032,
"step": 1399
},
{
"epoch": 0.36,
"learning_rate": 1.4733617687142782e-05,
"loss": 0.5061,
"step": 1400
},
{
"epoch": 0.36,
"learning_rate": 1.4726222676301734e-05,
"loss": 0.4739,
"step": 1401
},
{
"epoch": 0.36,
"learning_rate": 1.4718824335997283e-05,
"loss": 0.4854,
"step": 1402
},
{
"epoch": 0.36,
"learning_rate": 1.4711422671441311e-05,
"loss": 0.491,
"step": 1403
},
{
"epoch": 0.36,
"learning_rate": 1.470401768784804e-05,
"loss": 0.4714,
"step": 1404
},
{
"epoch": 0.36,
"learning_rate": 1.4696609390434029e-05,
"loss": 0.4807,
"step": 1405
},
{
"epoch": 0.36,
"learning_rate": 1.468919778441817e-05,
"loss": 0.4614,
"step": 1406
},
{
"epoch": 0.36,
"learning_rate": 1.4681782875021689e-05,
"loss": 0.4866,
"step": 1407
},
{
"epoch": 0.36,
"learning_rate": 1.467436466746814e-05,
"loss": 0.4844,
"step": 1408
},
{
"epoch": 0.37,
"learning_rate": 1.4666943166983395e-05,
"loss": 0.5298,
"step": 1409
},
{
"epoch": 0.37,
"learning_rate": 1.4659518378795651e-05,
"loss": 0.4727,
"step": 1410
},
{
"epoch": 0.37,
"learning_rate": 1.4652090308135423e-05,
"loss": 0.5227,
"step": 1411
},
{
"epoch": 0.37,
"learning_rate": 1.4644658960235525e-05,
"loss": 0.4883,
"step": 1412
},
{
"epoch": 0.37,
"learning_rate": 1.4637224340331098e-05,
"loss": 0.489,
"step": 1413
},
{
"epoch": 0.37,
"learning_rate": 1.4629786453659576e-05,
"loss": 0.4856,
"step": 1414
},
{
"epoch": 0.37,
"learning_rate": 1.4622345305460696e-05,
"loss": 0.4861,
"step": 1415
},
{
"epoch": 0.37,
"learning_rate": 1.4614900900976496e-05,
"loss": 0.4888,
"step": 1416
},
{
"epoch": 0.37,
"learning_rate": 1.4607453245451307e-05,
"loss": 0.4758,
"step": 1417
},
{
"epoch": 0.37,
"learning_rate": 1.460000234413175e-05,
"loss": 0.4832,
"step": 1418
},
{
"epoch": 0.37,
"learning_rate": 1.459254820226673e-05,
"loss": 0.478,
"step": 1419
},
{
"epoch": 0.37,
"learning_rate": 1.4585090825107435e-05,
"loss": 0.4856,
"step": 1420
},
{
"epoch": 0.37,
"learning_rate": 1.457763021790734e-05,
"loss": 0.4626,
"step": 1421
},
{
"epoch": 0.37,
"learning_rate": 1.4570166385922182e-05,
"loss": 0.4697,
"step": 1422
},
{
"epoch": 0.37,
"learning_rate": 1.4562699334409982e-05,
"loss": 0.4758,
"step": 1423
},
{
"epoch": 0.37,
"learning_rate": 1.4555229068631024e-05,
"loss": 0.4553,
"step": 1424
},
{
"epoch": 0.37,
"learning_rate": 1.4547755593847859e-05,
"loss": 0.4963,
"step": 1425
},
{
"epoch": 0.37,
"learning_rate": 1.454027891532529e-05,
"loss": 0.4773,
"step": 1426
},
{
"epoch": 0.37,
"learning_rate": 1.4532799038330385e-05,
"loss": 0.5,
"step": 1427
},
{
"epoch": 0.37,
"learning_rate": 1.4525315968132466e-05,
"loss": 0.4778,
"step": 1428
},
{
"epoch": 0.37,
"learning_rate": 1.4517829710003102e-05,
"loss": 0.4675,
"step": 1429
},
{
"epoch": 0.37,
"learning_rate": 1.4510340269216104e-05,
"loss": 0.4678,
"step": 1430
},
{
"epoch": 0.37,
"learning_rate": 1.4502847651047534e-05,
"loss": 0.4756,
"step": 1431
},
{
"epoch": 0.37,
"learning_rate": 1.4495351860775682e-05,
"loss": 0.4634,
"step": 1432
},
{
"epoch": 0.37,
"learning_rate": 1.4487852903681079e-05,
"loss": 0.4597,
"step": 1433
},
{
"epoch": 0.37,
"learning_rate": 1.4480350785046486e-05,
"loss": 0.4636,
"step": 1434
},
{
"epoch": 0.37,
"learning_rate": 1.4472845510156892e-05,
"loss": 0.4907,
"step": 1435
},
{
"epoch": 0.37,
"learning_rate": 1.4465337084299509e-05,
"loss": 0.4919,
"step": 1436
},
{
"epoch": 0.37,
"learning_rate": 1.4457825512763767e-05,
"loss": 0.457,
"step": 1437
},
{
"epoch": 0.37,
"learning_rate": 1.4450310800841312e-05,
"loss": 0.4741,
"step": 1438
},
{
"epoch": 0.37,
"learning_rate": 1.4442792953826002e-05,
"loss": 0.4709,
"step": 1439
},
{
"epoch": 0.37,
"learning_rate": 1.443527197701391e-05,
"loss": 0.5046,
"step": 1440
},
{
"epoch": 0.37,
"learning_rate": 1.4427747875703304e-05,
"loss": 0.5,
"step": 1441
},
{
"epoch": 0.37,
"learning_rate": 1.4420220655194661e-05,
"loss": 0.4658,
"step": 1442
},
{
"epoch": 0.37,
"learning_rate": 1.4412690320790652e-05,
"loss": 0.4854,
"step": 1443
},
{
"epoch": 0.37,
"learning_rate": 1.4405156877796139e-05,
"loss": 0.4978,
"step": 1444
},
{
"epoch": 0.37,
"learning_rate": 1.4397620331518178e-05,
"loss": 0.4932,
"step": 1445
},
{
"epoch": 0.37,
"learning_rate": 1.4390080687266013e-05,
"loss": 0.4727,
"step": 1446
},
{
"epoch": 0.37,
"learning_rate": 1.4382537950351063e-05,
"loss": 0.4783,
"step": 1447
},
{
"epoch": 0.38,
"learning_rate": 1.4374992126086934e-05,
"loss": 0.4993,
"step": 1448
},
{
"epoch": 0.38,
"learning_rate": 1.4367443219789403e-05,
"loss": 0.4824,
"step": 1449
},
{
"epoch": 0.38,
"learning_rate": 1.4359891236776414e-05,
"loss": 0.4719,
"step": 1450
},
{
"epoch": 0.38,
"learning_rate": 1.4352336182368082e-05,
"loss": 0.4729,
"step": 1451
},
{
"epoch": 0.38,
"learning_rate": 1.4344778061886695e-05,
"loss": 0.5247,
"step": 1452
},
{
"epoch": 0.38,
"learning_rate": 1.4337216880656683e-05,
"loss": 0.498,
"step": 1453
},
{
"epoch": 0.38,
"learning_rate": 1.4329652644004645e-05,
"loss": 0.499,
"step": 1454
},
{
"epoch": 0.38,
"learning_rate": 1.4322085357259332e-05,
"loss": 0.4873,
"step": 1455
},
{
"epoch": 0.38,
"learning_rate": 1.4314515025751634e-05,
"loss": 0.4734,
"step": 1456
},
{
"epoch": 0.38,
"learning_rate": 1.4306941654814594e-05,
"loss": 0.4817,
"step": 1457
},
{
"epoch": 0.38,
"learning_rate": 1.42993652497834e-05,
"loss": 0.4944,
"step": 1458
},
{
"epoch": 0.38,
"learning_rate": 1.429178581599537e-05,
"loss": 0.4753,
"step": 1459
},
{
"epoch": 0.38,
"learning_rate": 1.4284203358789954e-05,
"loss": 0.4785,
"step": 1460
},
{
"epoch": 0.38,
"learning_rate": 1.4276617883508739e-05,
"loss": 0.501,
"step": 1461
},
{
"epoch": 0.38,
"learning_rate": 1.4269029395495432e-05,
"loss": 0.4976,
"step": 1462
},
{
"epoch": 0.38,
"learning_rate": 1.426143790009587e-05,
"loss": 0.4661,
"step": 1463
},
{
"epoch": 0.38,
"learning_rate": 1.4253843402658e-05,
"loss": 0.4905,
"step": 1464
},
{
"epoch": 0.38,
"learning_rate": 1.4246245908531883e-05,
"loss": 0.4604,
"step": 1465
},
{
"epoch": 0.38,
"learning_rate": 1.4238645423069709e-05,
"loss": 0.4622,
"step": 1466
},
{
"epoch": 0.38,
"learning_rate": 1.423104195162575e-05,
"loss": 0.4805,
"step": 1467
},
{
"epoch": 0.38,
"learning_rate": 1.4223435499556397e-05,
"loss": 0.4993,
"step": 1468
},
{
"epoch": 0.38,
"learning_rate": 1.4215826072220136e-05,
"loss": 0.4451,
"step": 1469
},
{
"epoch": 0.38,
"learning_rate": 1.4208213674977555e-05,
"loss": 0.5095,
"step": 1470
},
{
"epoch": 0.38,
"learning_rate": 1.4200598313191325e-05,
"loss": 0.4919,
"step": 1471
},
{
"epoch": 0.38,
"learning_rate": 1.4192979992226211e-05,
"loss": 0.4697,
"step": 1472
},
{
"epoch": 0.38,
"learning_rate": 1.4185358717449063e-05,
"loss": 0.4788,
"step": 1473
},
{
"epoch": 0.38,
"learning_rate": 1.4177734494228808e-05,
"loss": 0.4883,
"step": 1474
},
{
"epoch": 0.38,
"learning_rate": 1.4170107327936452e-05,
"loss": 0.4922,
"step": 1475
},
{
"epoch": 0.38,
"learning_rate": 1.4162477223945073e-05,
"loss": 0.4905,
"step": 1476
},
{
"epoch": 0.38,
"learning_rate": 1.4154844187629828e-05,
"loss": 0.4841,
"step": 1477
},
{
"epoch": 0.38,
"learning_rate": 1.4147208224367922e-05,
"loss": 0.4724,
"step": 1478
},
{
"epoch": 0.38,
"learning_rate": 1.4139569339538642e-05,
"loss": 0.4966,
"step": 1479
},
{
"epoch": 0.38,
"learning_rate": 1.4131927538523315e-05,
"loss": 0.51,
"step": 1480
},
{
"epoch": 0.38,
"learning_rate": 1.4124282826705333e-05,
"loss": 0.4717,
"step": 1481
},
{
"epoch": 0.38,
"learning_rate": 1.4116635209470135e-05,
"loss": 0.4727,
"step": 1482
},
{
"epoch": 0.38,
"learning_rate": 1.4108984692205212e-05,
"loss": 0.4854,
"step": 1483
},
{
"epoch": 0.38,
"learning_rate": 1.410133128030009e-05,
"loss": 0.4556,
"step": 1484
},
{
"epoch": 0.38,
"learning_rate": 1.4093674979146335e-05,
"loss": 0.4666,
"step": 1485
},
{
"epoch": 0.39,
"learning_rate": 1.4086015794137555e-05,
"loss": 0.4888,
"step": 1486
},
{
"epoch": 0.39,
"learning_rate": 1.4078353730669386e-05,
"loss": 0.48,
"step": 1487
},
{
"epoch": 0.39,
"learning_rate": 1.4070688794139488e-05,
"loss": 0.4749,
"step": 1488
},
{
"epoch": 0.39,
"learning_rate": 1.4063020989947555e-05,
"loss": 0.4441,
"step": 1489
},
{
"epoch": 0.39,
"learning_rate": 1.4055350323495292e-05,
"loss": 0.4785,
"step": 1490
},
{
"epoch": 0.39,
"learning_rate": 1.4047676800186417e-05,
"loss": 0.4807,
"step": 1491
},
{
"epoch": 0.39,
"learning_rate": 1.4040000425426675e-05,
"loss": 0.46,
"step": 1492
},
{
"epoch": 0.39,
"learning_rate": 1.4032321204623807e-05,
"loss": 0.4563,
"step": 1493
},
{
"epoch": 0.39,
"learning_rate": 1.4024639143187563e-05,
"loss": 0.4858,
"step": 1494
},
{
"epoch": 0.39,
"learning_rate": 1.4016954246529697e-05,
"loss": 0.4866,
"step": 1495
},
{
"epoch": 0.39,
"learning_rate": 1.4009266520063956e-05,
"loss": 0.4685,
"step": 1496
},
{
"epoch": 0.39,
"learning_rate": 1.4001575969206081e-05,
"loss": 0.479,
"step": 1497
},
{
"epoch": 0.39,
"learning_rate": 1.3993882599373808e-05,
"loss": 0.4878,
"step": 1498
},
{
"epoch": 0.39,
"learning_rate": 1.3986186415986854e-05,
"loss": 0.4819,
"step": 1499
},
{
"epoch": 0.39,
"learning_rate": 1.3978487424466914e-05,
"loss": 0.4819,
"step": 1500
},
{
"epoch": 0.39,
"learning_rate": 1.397078563023767e-05,
"loss": 0.4546,
"step": 1501
},
{
"epoch": 0.39,
"learning_rate": 1.3963081038724778e-05,
"loss": 0.5212,
"step": 1502
},
{
"epoch": 0.39,
"learning_rate": 1.3955373655355852e-05,
"loss": 0.4617,
"step": 1503
},
{
"epoch": 0.39,
"learning_rate": 1.3947663485560488e-05,
"loss": 0.4644,
"step": 1504
},
{
"epoch": 0.39,
"learning_rate": 1.3939950534770238e-05,
"loss": 0.4641,
"step": 1505
},
{
"epoch": 0.39,
"learning_rate": 1.3932234808418614e-05,
"loss": 0.4409,
"step": 1506
},
{
"epoch": 0.39,
"learning_rate": 1.3924516311941085e-05,
"loss": 0.4634,
"step": 1507
},
{
"epoch": 0.39,
"learning_rate": 1.3916795050775066e-05,
"loss": 0.4631,
"step": 1508
},
{
"epoch": 0.39,
"learning_rate": 1.3909071030359927e-05,
"loss": 0.4907,
"step": 1509
},
{
"epoch": 0.39,
"learning_rate": 1.3901344256136974e-05,
"loss": 0.4583,
"step": 1510
},
{
"epoch": 0.39,
"learning_rate": 1.3893614733549459e-05,
"loss": 0.4983,
"step": 1511
},
{
"epoch": 0.39,
"learning_rate": 1.3885882468042571e-05,
"loss": 0.4866,
"step": 1512
},
{
"epoch": 0.39,
"learning_rate": 1.3878147465063423e-05,
"loss": 0.5042,
"step": 1513
},
{
"epoch": 0.39,
"learning_rate": 1.3870409730061067e-05,
"loss": 0.4954,
"step": 1514
},
{
"epoch": 0.39,
"learning_rate": 1.386266926848647e-05,
"loss": 0.4521,
"step": 1515
},
{
"epoch": 0.39,
"learning_rate": 1.3854926085792528e-05,
"loss": 0.5115,
"step": 1516
},
{
"epoch": 0.39,
"learning_rate": 1.384718018743405e-05,
"loss": 0.4937,
"step": 1517
},
{
"epoch": 0.39,
"learning_rate": 1.3839431578867759e-05,
"loss": 0.467,
"step": 1518
},
{
"epoch": 0.39,
"learning_rate": 1.3831680265552283e-05,
"loss": 0.4941,
"step": 1519
},
{
"epoch": 0.39,
"learning_rate": 1.3823926252948161e-05,
"loss": 0.4871,
"step": 1520
},
{
"epoch": 0.39,
"learning_rate": 1.3816169546517833e-05,
"loss": 0.4595,
"step": 1521
},
{
"epoch": 0.39,
"learning_rate": 1.3808410151725633e-05,
"loss": 0.4805,
"step": 1522
},
{
"epoch": 0.39,
"learning_rate": 1.3800648074037792e-05,
"loss": 0.4927,
"step": 1523
},
{
"epoch": 0.39,
"learning_rate": 1.3792883318922434e-05,
"loss": 0.4927,
"step": 1524
},
{
"epoch": 0.4,
"learning_rate": 1.3785115891849556e-05,
"loss": 0.4592,
"step": 1525
},
{
"epoch": 0.4,
"learning_rate": 1.3777345798291057e-05,
"loss": 0.4705,
"step": 1526
},
{
"epoch": 0.4,
"learning_rate": 1.3769573043720699e-05,
"loss": 0.4917,
"step": 1527
},
{
"epoch": 0.4,
"learning_rate": 1.3761797633614122e-05,
"loss": 0.4705,
"step": 1528
},
{
"epoch": 0.4,
"learning_rate": 1.375401957344884e-05,
"loss": 0.48,
"step": 1529
},
{
"epoch": 0.4,
"learning_rate": 1.3746238868704237e-05,
"loss": 0.4668,
"step": 1530
},
{
"epoch": 0.4,
"learning_rate": 1.3738455524861551e-05,
"loss": 0.4822,
"step": 1531
},
{
"epoch": 0.4,
"learning_rate": 1.3730669547403879e-05,
"loss": 0.4727,
"step": 1532
},
{
"epoch": 0.4,
"learning_rate": 1.3722880941816185e-05,
"loss": 0.49,
"step": 1533
},
{
"epoch": 0.4,
"learning_rate": 1.3715089713585277e-05,
"loss": 0.4863,
"step": 1534
},
{
"epoch": 0.4,
"learning_rate": 1.3707295868199806e-05,
"loss": 0.4783,
"step": 1535
},
{
"epoch": 0.4,
"learning_rate": 1.3699499411150274e-05,
"loss": 0.5068,
"step": 1536
},
{
"epoch": 0.4,
"learning_rate": 1.369170034792902e-05,
"loss": 0.4722,
"step": 1537
},
{
"epoch": 0.4,
"learning_rate": 1.3683898684030219e-05,
"loss": 0.4812,
"step": 1538
},
{
"epoch": 0.4,
"learning_rate": 1.367609442494988e-05,
"loss": 0.4648,
"step": 1539
},
{
"epoch": 0.4,
"learning_rate": 1.3668287576185835e-05,
"loss": 0.4629,
"step": 1540
},
{
"epoch": 0.4,
"learning_rate": 1.3660478143237748e-05,
"loss": 0.4861,
"step": 1541
},
{
"epoch": 0.4,
"learning_rate": 1.3652666131607098e-05,
"loss": 0.4915,
"step": 1542
},
{
"epoch": 0.4,
"learning_rate": 1.364485154679718e-05,
"loss": 0.488,
"step": 1543
},
{
"epoch": 0.4,
"learning_rate": 1.3637034394313102e-05,
"loss": 0.4717,
"step": 1544
},
{
"epoch": 0.4,
"learning_rate": 1.3629214679661788e-05,
"loss": 0.4734,
"step": 1545
},
{
"epoch": 0.4,
"learning_rate": 1.3621392408351961e-05,
"loss": 0.4575,
"step": 1546
},
{
"epoch": 0.4,
"learning_rate": 1.3613567585894142e-05,
"loss": 0.4709,
"step": 1547
},
{
"epoch": 0.4,
"learning_rate": 1.3605740217800653e-05,
"loss": 0.481,
"step": 1548
},
{
"epoch": 0.4,
"learning_rate": 1.3597910309585614e-05,
"loss": 0.4873,
"step": 1549
},
{
"epoch": 0.4,
"learning_rate": 1.3590077866764921e-05,
"loss": 0.4785,
"step": 1550
},
{
"epoch": 0.4,
"learning_rate": 1.358224289485627e-05,
"loss": 0.4614,
"step": 1551
},
{
"epoch": 0.4,
"learning_rate": 1.3574405399379133e-05,
"loss": 0.4775,
"step": 1552
},
{
"epoch": 0.4,
"learning_rate": 1.356656538585476e-05,
"loss": 0.468,
"step": 1553
},
{
"epoch": 0.4,
"learning_rate": 1.3558722859806168e-05,
"loss": 0.4631,
"step": 1554
},
{
"epoch": 0.4,
"learning_rate": 1.3550877826758155e-05,
"loss": 0.4727,
"step": 1555
},
{
"epoch": 0.4,
"learning_rate": 1.3543030292237283e-05,
"loss": 0.4734,
"step": 1556
},
{
"epoch": 0.4,
"learning_rate": 1.3535180261771865e-05,
"loss": 0.4587,
"step": 1557
},
{
"epoch": 0.4,
"learning_rate": 1.3527327740891991e-05,
"loss": 0.499,
"step": 1558
},
{
"epoch": 0.4,
"learning_rate": 1.3519472735129493e-05,
"loss": 0.499,
"step": 1559
},
{
"epoch": 0.4,
"learning_rate": 1.3511615250017948e-05,
"loss": 0.4697,
"step": 1560
},
{
"epoch": 0.4,
"learning_rate": 1.3503755291092698e-05,
"loss": 0.4656,
"step": 1561
},
{
"epoch": 0.4,
"learning_rate": 1.349589286389081e-05,
"loss": 0.4749,
"step": 1562
},
{
"epoch": 0.41,
"learning_rate": 1.3488027973951096e-05,
"loss": 0.4983,
"step": 1563
},
{
"epoch": 0.41,
"learning_rate": 1.3480160626814114e-05,
"loss": 0.4814,
"step": 1564
},
{
"epoch": 0.41,
"learning_rate": 1.3472290828022132e-05,
"loss": 0.4568,
"step": 1565
},
{
"epoch": 0.41,
"learning_rate": 1.346441858311916e-05,
"loss": 0.4768,
"step": 1566
},
{
"epoch": 0.41,
"learning_rate": 1.3456543897650928e-05,
"loss": 0.5103,
"step": 1567
},
{
"epoch": 0.41,
"learning_rate": 1.3448666777164885e-05,
"loss": 0.5107,
"step": 1568
},
{
"epoch": 0.41,
"learning_rate": 1.3440787227210194e-05,
"loss": 0.4756,
"step": 1569
},
{
"epoch": 0.41,
"learning_rate": 1.343290525333773e-05,
"loss": 0.4666,
"step": 1570
},
{
"epoch": 0.41,
"learning_rate": 1.3425020861100078e-05,
"loss": 0.4971,
"step": 1571
},
{
"epoch": 0.41,
"learning_rate": 1.341713405605152e-05,
"loss": 0.4844,
"step": 1572
},
{
"epoch": 0.41,
"learning_rate": 1.3409244843748046e-05,
"loss": 0.5012,
"step": 1573
},
{
"epoch": 0.41,
"learning_rate": 1.3401353229747338e-05,
"loss": 0.4658,
"step": 1574
},
{
"epoch": 0.41,
"learning_rate": 1.339345921960877e-05,
"loss": 0.4763,
"step": 1575
},
{
"epoch": 0.41,
"learning_rate": 1.33855628188934e-05,
"loss": 0.4763,
"step": 1576
},
{
"epoch": 0.41,
"learning_rate": 1.3377664033163983e-05,
"loss": 0.5083,
"step": 1577
},
{
"epoch": 0.41,
"learning_rate": 1.3369762867984939e-05,
"loss": 0.4744,
"step": 1578
},
{
"epoch": 0.41,
"learning_rate": 1.3361859328922368e-05,
"loss": 0.4626,
"step": 1579
},
{
"epoch": 0.41,
"learning_rate": 1.3353953421544052e-05,
"loss": 0.4619,
"step": 1580
},
{
"epoch": 0.41,
"learning_rate": 1.3346045151419432e-05,
"loss": 0.4763,
"step": 1581
},
{
"epoch": 0.41,
"learning_rate": 1.3338134524119612e-05,
"loss": 0.501,
"step": 1582
},
{
"epoch": 0.41,
"learning_rate": 1.3330221545217365e-05,
"loss": 0.4995,
"step": 1583
},
{
"epoch": 0.41,
"learning_rate": 1.3322306220287116e-05,
"loss": 0.4949,
"step": 1584
},
{
"epoch": 0.41,
"learning_rate": 1.3314388554904936e-05,
"loss": 0.4934,
"step": 1585
},
{
"epoch": 0.41,
"learning_rate": 1.330646855464856e-05,
"loss": 0.4546,
"step": 1586
},
{
"epoch": 0.41,
"learning_rate": 1.3298546225097353e-05,
"loss": 0.4543,
"step": 1587
},
{
"epoch": 0.41,
"learning_rate": 1.3290621571832331e-05,
"loss": 0.4634,
"step": 1588
},
{
"epoch": 0.41,
"learning_rate": 1.3282694600436141e-05,
"loss": 0.4604,
"step": 1589
},
{
"epoch": 0.41,
"learning_rate": 1.3274765316493068e-05,
"loss": 0.4976,
"step": 1590
},
{
"epoch": 0.41,
"learning_rate": 1.326683372558902e-05,
"loss": 0.5044,
"step": 1591
},
{
"epoch": 0.41,
"learning_rate": 1.3258899833311534e-05,
"loss": 0.49,
"step": 1592
},
{
"epoch": 0.41,
"learning_rate": 1.325096364524977e-05,
"loss": 0.4656,
"step": 1593
},
{
"epoch": 0.41,
"learning_rate": 1.3243025166994499e-05,
"loss": 0.4663,
"step": 1594
},
{
"epoch": 0.41,
"learning_rate": 1.3235084404138114e-05,
"loss": 0.4541,
"step": 1595
},
{
"epoch": 0.41,
"learning_rate": 1.3227141362274612e-05,
"loss": 0.4663,
"step": 1596
},
{
"epoch": 0.41,
"learning_rate": 1.3219196046999594e-05,
"loss": 0.4861,
"step": 1597
},
{
"epoch": 0.41,
"learning_rate": 1.3211248463910263e-05,
"loss": 0.4612,
"step": 1598
},
{
"epoch": 0.41,
"learning_rate": 1.3203298618605426e-05,
"loss": 0.4634,
"step": 1599
},
{
"epoch": 0.41,
"learning_rate": 1.3195346516685481e-05,
"loss": 0.4763,
"step": 1600
},
{
"epoch": 0.41,
"learning_rate": 1.3187392163752404e-05,
"loss": 0.5046,
"step": 1601
},
{
"epoch": 0.42,
"learning_rate": 1.3179435565409775e-05,
"loss": 0.4653,
"step": 1602
},
{
"epoch": 0.42,
"learning_rate": 1.3171476727262746e-05,
"loss": 0.4741,
"step": 1603
},
{
"epoch": 0.42,
"learning_rate": 1.3163515654918046e-05,
"loss": 0.4656,
"step": 1604
},
{
"epoch": 0.42,
"learning_rate": 1.3155552353983985e-05,
"loss": 0.4866,
"step": 1605
},
{
"epoch": 0.42,
"learning_rate": 1.3147586830070434e-05,
"loss": 0.4736,
"step": 1606
},
{
"epoch": 0.42,
"learning_rate": 1.3139619088788828e-05,
"loss": 0.4856,
"step": 1607
},
{
"epoch": 0.42,
"learning_rate": 1.3131649135752185e-05,
"loss": 0.479,
"step": 1608
},
{
"epoch": 0.42,
"learning_rate": 1.3123676976575055e-05,
"loss": 0.4932,
"step": 1609
},
{
"epoch": 0.42,
"learning_rate": 1.3115702616873556e-05,
"loss": 0.4744,
"step": 1610
},
{
"epoch": 0.42,
"learning_rate": 1.3107726062265356e-05,
"loss": 0.4895,
"step": 1611
},
{
"epoch": 0.42,
"learning_rate": 1.3099747318369664e-05,
"loss": 0.4822,
"step": 1612
},
{
"epoch": 0.42,
"learning_rate": 1.3091766390807235e-05,
"loss": 0.4819,
"step": 1613
},
{
"epoch": 0.42,
"learning_rate": 1.3083783285200362e-05,
"loss": 0.4604,
"step": 1614
},
{
"epoch": 0.42,
"learning_rate": 1.3075798007172872e-05,
"loss": 0.4771,
"step": 1615
},
{
"epoch": 0.42,
"learning_rate": 1.3067810562350123e-05,
"loss": 0.4658,
"step": 1616
},
{
"epoch": 0.42,
"learning_rate": 1.3059820956358998e-05,
"loss": 0.4917,
"step": 1617
},
{
"epoch": 0.42,
"learning_rate": 1.30518291948279e-05,
"loss": 0.4719,
"step": 1618
},
{
"epoch": 0.42,
"learning_rate": 1.304383528338676e-05,
"loss": 0.4673,
"step": 1619
},
{
"epoch": 0.42,
"learning_rate": 1.303583922766701e-05,
"loss": 0.4478,
"step": 1620
},
{
"epoch": 0.42,
"learning_rate": 1.3027841033301605e-05,
"loss": 0.4534,
"step": 1621
},
{
"epoch": 0.42,
"learning_rate": 1.3019840705925e-05,
"loss": 0.467,
"step": 1622
},
{
"epoch": 0.42,
"learning_rate": 1.3011838251173152e-05,
"loss": 0.4768,
"step": 1623
},
{
"epoch": 0.42,
"learning_rate": 1.3003833674683524e-05,
"loss": 0.4956,
"step": 1624
},
{
"epoch": 0.42,
"learning_rate": 1.299582698209506e-05,
"loss": 0.49,
"step": 1625
},
{
"epoch": 0.42,
"learning_rate": 1.298781817904821e-05,
"loss": 0.4685,
"step": 1626
},
{
"epoch": 0.42,
"learning_rate": 1.2979807271184903e-05,
"loss": 0.501,
"step": 1627
},
{
"epoch": 0.42,
"learning_rate": 1.297179426414855e-05,
"loss": 0.4678,
"step": 1628
},
{
"epoch": 0.42,
"learning_rate": 1.2963779163584041e-05,
"loss": 0.4763,
"step": 1629
},
{
"epoch": 0.42,
"learning_rate": 1.2955761975137743e-05,
"loss": 0.4934,
"step": 1630
},
{
"epoch": 0.42,
"learning_rate": 1.2947742704457495e-05,
"loss": 0.457,
"step": 1631
},
{
"epoch": 0.42,
"learning_rate": 1.2939721357192598e-05,
"loss": 0.4941,
"step": 1632
},
{
"epoch": 0.42,
"learning_rate": 1.2931697938993824e-05,
"loss": 0.4854,
"step": 1633
},
{
"epoch": 0.42,
"learning_rate": 1.2923672455513394e-05,
"loss": 0.4851,
"step": 1634
},
{
"epoch": 0.42,
"learning_rate": 1.2915644912404988e-05,
"loss": 0.4929,
"step": 1635
},
{
"epoch": 0.42,
"learning_rate": 1.290761531532374e-05,
"loss": 0.4875,
"step": 1636
},
{
"epoch": 0.42,
"learning_rate": 1.289958366992623e-05,
"loss": 0.4861,
"step": 1637
},
{
"epoch": 0.42,
"learning_rate": 1.2891549981870475e-05,
"loss": 0.4612,
"step": 1638
},
{
"epoch": 0.42,
"learning_rate": 1.2883514256815937e-05,
"loss": 0.4919,
"step": 1639
},
{
"epoch": 0.42,
"learning_rate": 1.2875476500423516e-05,
"loss": 0.4644,
"step": 1640
},
{
"epoch": 0.43,
"learning_rate": 1.286743671835553e-05,
"loss": 0.4775,
"step": 1641
},
{
"epoch": 0.43,
"learning_rate": 1.285939491627574e-05,
"loss": 0.4954,
"step": 1642
},
{
"epoch": 0.43,
"learning_rate": 1.2851351099849321e-05,
"loss": 0.4587,
"step": 1643
},
{
"epoch": 0.43,
"learning_rate": 1.2843305274742866e-05,
"loss": 0.489,
"step": 1644
},
{
"epoch": 0.43,
"learning_rate": 1.2835257446624386e-05,
"loss": 0.4941,
"step": 1645
},
{
"epoch": 0.43,
"learning_rate": 1.2827207621163305e-05,
"loss": 0.4485,
"step": 1646
},
{
"epoch": 0.43,
"learning_rate": 1.281915580403045e-05,
"loss": 0.4705,
"step": 1647
},
{
"epoch": 0.43,
"learning_rate": 1.2811102000898049e-05,
"loss": 0.4905,
"step": 1648
},
{
"epoch": 0.43,
"learning_rate": 1.2803046217439741e-05,
"loss": 0.4526,
"step": 1649
},
{
"epoch": 0.43,
"learning_rate": 1.2794988459330547e-05,
"loss": 0.4702,
"step": 1650
},
{
"epoch": 0.43,
"learning_rate": 1.2786928732246885e-05,
"loss": 0.4602,
"step": 1651
},
{
"epoch": 0.43,
"learning_rate": 1.2778867041866559e-05,
"loss": 0.4629,
"step": 1652
},
{
"epoch": 0.43,
"learning_rate": 1.2770803393868756e-05,
"loss": 0.4648,
"step": 1653
},
{
"epoch": 0.43,
"learning_rate": 1.276273779393404e-05,
"loss": 0.4758,
"step": 1654
},
{
"epoch": 0.43,
"learning_rate": 1.2754670247744353e-05,
"loss": 0.4504,
"step": 1655
},
{
"epoch": 0.43,
"learning_rate": 1.2746600760983015e-05,
"loss": 0.4924,
"step": 1656
},
{
"epoch": 0.43,
"learning_rate": 1.2738529339334695e-05,
"loss": 0.4529,
"step": 1657
},
{
"epoch": 0.43,
"learning_rate": 1.2730455988485442e-05,
"loss": 0.4841,
"step": 1658
},
{
"epoch": 0.43,
"learning_rate": 1.2722380714122655e-05,
"loss": 0.4563,
"step": 1659
},
{
"epoch": 0.43,
"learning_rate": 1.2714303521935088e-05,
"loss": 0.4812,
"step": 1660
},
{
"epoch": 0.43,
"learning_rate": 1.2706224417612853e-05,
"loss": 0.4756,
"step": 1661
},
{
"epoch": 0.43,
"learning_rate": 1.2698143406847405e-05,
"loss": 0.4888,
"step": 1662
},
{
"epoch": 0.43,
"learning_rate": 1.269006049533154e-05,
"loss": 0.48,
"step": 1663
},
{
"epoch": 0.43,
"learning_rate": 1.2681975688759394e-05,
"loss": 0.4683,
"step": 1664
},
{
"epoch": 0.43,
"learning_rate": 1.267388899282644e-05,
"loss": 0.4763,
"step": 1665
},
{
"epoch": 0.43,
"learning_rate": 1.2665800413229479e-05,
"loss": 0.4636,
"step": 1666
},
{
"epoch": 0.43,
"learning_rate": 1.265770995566664e-05,
"loss": 0.4844,
"step": 1667
},
{
"epoch": 0.43,
"learning_rate": 1.2649617625837381e-05,
"loss": 0.4729,
"step": 1668
},
{
"epoch": 0.43,
"learning_rate": 1.264152342944247e-05,
"loss": 0.4639,
"step": 1669
},
{
"epoch": 0.43,
"learning_rate": 1.263342737218399e-05,
"loss": 0.4829,
"step": 1670
},
{
"epoch": 0.43,
"learning_rate": 1.2625329459765344e-05,
"loss": 0.4656,
"step": 1671
},
{
"epoch": 0.43,
"learning_rate": 1.2617229697891234e-05,
"loss": 0.449,
"step": 1672
},
{
"epoch": 0.43,
"learning_rate": 1.2609128092267666e-05,
"loss": 0.4612,
"step": 1673
},
{
"epoch": 0.43,
"learning_rate": 1.260102464860195e-05,
"loss": 0.4685,
"step": 1674
},
{
"epoch": 0.43,
"learning_rate": 1.2592919372602685e-05,
"loss": 0.4797,
"step": 1675
},
{
"epoch": 0.43,
"learning_rate": 1.2584812269979761e-05,
"loss": 0.4734,
"step": 1676
},
{
"epoch": 0.43,
"learning_rate": 1.2576703346444359e-05,
"loss": 0.4871,
"step": 1677
},
{
"epoch": 0.43,
"learning_rate": 1.2568592607708938e-05,
"loss": 0.458,
"step": 1678
},
{
"epoch": 0.44,
"learning_rate": 1.2560480059487237e-05,
"loss": 0.4824,
"step": 1679
},
{
"epoch": 0.44,
"learning_rate": 1.2552365707494279e-05,
"loss": 0.5063,
"step": 1680
},
{
"epoch": 0.44,
"learning_rate": 1.254424955744634e-05,
"loss": 0.4783,
"step": 1681
},
{
"epoch": 0.44,
"learning_rate": 1.2536131615060972e-05,
"loss": 0.4783,
"step": 1682
},
{
"epoch": 0.44,
"learning_rate": 1.2528011886056996e-05,
"loss": 0.4663,
"step": 1683
},
{
"epoch": 0.44,
"learning_rate": 1.2519890376154484e-05,
"loss": 0.4768,
"step": 1684
},
{
"epoch": 0.44,
"learning_rate": 1.2511767091074762e-05,
"loss": 0.4646,
"step": 1685
},
{
"epoch": 0.44,
"learning_rate": 1.2503642036540408e-05,
"loss": 0.4868,
"step": 1686
},
{
"epoch": 0.44,
"learning_rate": 1.2495515218275251e-05,
"loss": 0.4675,
"step": 1687
},
{
"epoch": 0.44,
"learning_rate": 1.2487386642004353e-05,
"loss": 0.4607,
"step": 1688
},
{
"epoch": 0.44,
"learning_rate": 1.2479256313454023e-05,
"loss": 0.4675,
"step": 1689
},
{
"epoch": 0.44,
"learning_rate": 1.2471124238351802e-05,
"loss": 0.4497,
"step": 1690
},
{
"epoch": 0.44,
"learning_rate": 1.246299042242646e-05,
"loss": 0.4656,
"step": 1691
},
{
"epoch": 0.44,
"learning_rate": 1.2454854871407993e-05,
"loss": 0.5054,
"step": 1692
},
{
"epoch": 0.44,
"learning_rate": 1.2446717591027624e-05,
"loss": 0.4729,
"step": 1693
},
{
"epoch": 0.44,
"learning_rate": 1.2438578587017784e-05,
"loss": 0.4966,
"step": 1694
},
{
"epoch": 0.44,
"learning_rate": 1.2430437865112132e-05,
"loss": 0.4641,
"step": 1695
},
{
"epoch": 0.44,
"learning_rate": 1.2422295431045525e-05,
"loss": 0.4722,
"step": 1696
},
{
"epoch": 0.44,
"learning_rate": 1.2414151290554037e-05,
"loss": 0.4832,
"step": 1697
},
{
"epoch": 0.44,
"learning_rate": 1.2406005449374936e-05,
"loss": 0.4656,
"step": 1698
},
{
"epoch": 0.44,
"learning_rate": 1.2397857913246688e-05,
"loss": 0.4822,
"step": 1699
},
{
"epoch": 0.44,
"learning_rate": 1.2389708687908956e-05,
"loss": 0.4868,
"step": 1700
},
{
"epoch": 0.44,
"learning_rate": 1.2381557779102593e-05,
"loss": 0.4827,
"step": 1701
},
{
"epoch": 0.44,
"learning_rate": 1.237340519256964e-05,
"loss": 0.4412,
"step": 1702
},
{
"epoch": 0.44,
"learning_rate": 1.2365250934053317e-05,
"loss": 0.4397,
"step": 1703
},
{
"epoch": 0.44,
"learning_rate": 1.235709500929802e-05,
"loss": 0.4541,
"step": 1704
},
{
"epoch": 0.44,
"learning_rate": 1.2348937424049321e-05,
"loss": 0.4597,
"step": 1705
},
{
"epoch": 0.44,
"learning_rate": 1.2340778184053965e-05,
"loss": 0.4568,
"step": 1706
},
{
"epoch": 0.44,
"learning_rate": 1.2332617295059857e-05,
"loss": 0.4651,
"step": 1707
},
{
"epoch": 0.44,
"learning_rate": 1.2324454762816062e-05,
"loss": 0.4761,
"step": 1708
},
{
"epoch": 0.44,
"learning_rate": 1.2316290593072817e-05,
"loss": 0.4666,
"step": 1709
},
{
"epoch": 0.44,
"learning_rate": 1.2308124791581496e-05,
"loss": 0.4941,
"step": 1710
},
{
"epoch": 0.44,
"learning_rate": 1.2299957364094625e-05,
"loss": 0.4688,
"step": 1711
},
{
"epoch": 0.44,
"learning_rate": 1.229178831636589e-05,
"loss": 0.4871,
"step": 1712
},
{
"epoch": 0.44,
"learning_rate": 1.22836176541501e-05,
"loss": 0.4568,
"step": 1713
},
{
"epoch": 0.44,
"learning_rate": 1.2275445383203209e-05,
"loss": 0.4846,
"step": 1714
},
{
"epoch": 0.44,
"learning_rate": 1.2267271509282308e-05,
"loss": 0.4863,
"step": 1715
},
{
"epoch": 0.44,
"learning_rate": 1.2259096038145612e-05,
"loss": 0.4788,
"step": 1716
},
{
"epoch": 0.44,
"learning_rate": 1.225091897555246e-05,
"loss": 0.4744,
"step": 1717
},
{
"epoch": 0.45,
"learning_rate": 1.2242740327263319e-05,
"loss": 0.4675,
"step": 1718
},
{
"epoch": 0.45,
"learning_rate": 1.223456009903977e-05,
"loss": 0.4956,
"step": 1719
},
{
"epoch": 0.45,
"learning_rate": 1.22263782966445e-05,
"loss": 0.4705,
"step": 1720
},
{
"epoch": 0.45,
"learning_rate": 1.2218194925841317e-05,
"loss": 0.4766,
"step": 1721
},
{
"epoch": 0.45,
"learning_rate": 1.2210009992395127e-05,
"loss": 0.4749,
"step": 1722
},
{
"epoch": 0.45,
"learning_rate": 1.2201823502071932e-05,
"loss": 0.4524,
"step": 1723
},
{
"epoch": 0.45,
"learning_rate": 1.2193635460638845e-05,
"loss": 0.4636,
"step": 1724
},
{
"epoch": 0.45,
"learning_rate": 1.2185445873864058e-05,
"loss": 0.4431,
"step": 1725
},
{
"epoch": 0.45,
"learning_rate": 1.2177254747516858e-05,
"loss": 0.4792,
"step": 1726
},
{
"epoch": 0.45,
"learning_rate": 1.2169062087367614e-05,
"loss": 0.4641,
"step": 1727
},
{
"epoch": 0.45,
"learning_rate": 1.2160867899187778e-05,
"loss": 0.4656,
"step": 1728
},
{
"epoch": 0.45,
"learning_rate": 1.2152672188749877e-05,
"loss": 0.4255,
"step": 1729
},
{
"epoch": 0.45,
"learning_rate": 1.214447496182751e-05,
"loss": 0.4294,
"step": 1730
},
{
"epoch": 0.45,
"learning_rate": 1.2136276224195349e-05,
"loss": 0.468,
"step": 1731
},
{
"epoch": 0.45,
"learning_rate": 1.2128075981629124e-05,
"loss": 0.4758,
"step": 1732
},
{
"epoch": 0.45,
"learning_rate": 1.2119874239905624e-05,
"loss": 0.4548,
"step": 1733
},
{
"epoch": 0.45,
"learning_rate": 1.2111671004802702e-05,
"loss": 0.438,
"step": 1734
},
{
"epoch": 0.45,
"learning_rate": 1.2103466282099257e-05,
"loss": 0.468,
"step": 1735
},
{
"epoch": 0.45,
"learning_rate": 1.2095260077575234e-05,
"loss": 0.4849,
"step": 1736
},
{
"epoch": 0.45,
"learning_rate": 1.2087052397011634e-05,
"loss": 0.4531,
"step": 1737
},
{
"epoch": 0.45,
"learning_rate": 1.2078843246190483e-05,
"loss": 0.4661,
"step": 1738
},
{
"epoch": 0.45,
"learning_rate": 1.2070632630894849e-05,
"loss": 0.4673,
"step": 1739
},
{
"epoch": 0.45,
"learning_rate": 1.2062420556908836e-05,
"loss": 0.4836,
"step": 1740
},
{
"epoch": 0.45,
"learning_rate": 1.2054207030017567e-05,
"loss": 0.5083,
"step": 1741
},
{
"epoch": 0.45,
"learning_rate": 1.2045992056007192e-05,
"loss": 0.458,
"step": 1742
},
{
"epoch": 0.45,
"learning_rate": 1.2037775640664884e-05,
"loss": 0.489,
"step": 1743
},
{
"epoch": 0.45,
"learning_rate": 1.2029557789778832e-05,
"loss": 0.4802,
"step": 1744
},
{
"epoch": 0.45,
"learning_rate": 1.2021338509138223e-05,
"loss": 0.4629,
"step": 1745
},
{
"epoch": 0.45,
"learning_rate": 1.2013117804533269e-05,
"loss": 0.4971,
"step": 1746
},
{
"epoch": 0.45,
"learning_rate": 1.2004895681755178e-05,
"loss": 0.4688,
"step": 1747
},
{
"epoch": 0.45,
"learning_rate": 1.1996672146596151e-05,
"loss": 0.4814,
"step": 1748
},
{
"epoch": 0.45,
"learning_rate": 1.1988447204849391e-05,
"loss": 0.4912,
"step": 1749
},
{
"epoch": 0.45,
"learning_rate": 1.1980220862309097e-05,
"loss": 0.4834,
"step": 1750
},
{
"epoch": 0.45,
"learning_rate": 1.1971993124770436e-05,
"loss": 0.4729,
"step": 1751
},
{
"epoch": 0.45,
"learning_rate": 1.1963763998029578e-05,
"loss": 0.4749,
"step": 1752
},
{
"epoch": 0.45,
"learning_rate": 1.1955533487883662e-05,
"loss": 0.4661,
"step": 1753
},
{
"epoch": 0.45,
"learning_rate": 1.1947301600130803e-05,
"loss": 0.4827,
"step": 1754
},
{
"epoch": 0.45,
"learning_rate": 1.193906834057008e-05,
"loss": 0.479,
"step": 1755
},
{
"epoch": 0.46,
"learning_rate": 1.1930833715001557e-05,
"loss": 0.5081,
"step": 1756
},
{
"epoch": 0.46,
"learning_rate": 1.1922597729226238e-05,
"loss": 0.4749,
"step": 1757
},
{
"epoch": 0.46,
"learning_rate": 1.19143603890461e-05,
"loss": 0.4812,
"step": 1758
},
{
"epoch": 0.46,
"learning_rate": 1.1906121700264069e-05,
"loss": 0.4788,
"step": 1759
},
{
"epoch": 0.46,
"learning_rate": 1.1897881668684019e-05,
"loss": 0.4597,
"step": 1760
},
{
"epoch": 0.46,
"learning_rate": 1.1889640300110775e-05,
"loss": 0.4509,
"step": 1761
},
{
"epoch": 0.46,
"learning_rate": 1.1881397600350103e-05,
"loss": 0.4517,
"step": 1762
},
{
"epoch": 0.46,
"learning_rate": 1.1873153575208702e-05,
"loss": 0.4783,
"step": 1763
},
{
"epoch": 0.46,
"learning_rate": 1.1864908230494205e-05,
"loss": 0.4695,
"step": 1764
},
{
"epoch": 0.46,
"learning_rate": 1.1856661572015184e-05,
"loss": 0.489,
"step": 1765
},
{
"epoch": 0.46,
"learning_rate": 1.1848413605581126e-05,
"loss": 0.4731,
"step": 1766
},
{
"epoch": 0.46,
"learning_rate": 1.1840164337002445e-05,
"loss": 0.4719,
"step": 1767
},
{
"epoch": 0.46,
"learning_rate": 1.1831913772090469e-05,
"loss": 0.4741,
"step": 1768
},
{
"epoch": 0.46,
"learning_rate": 1.1823661916657441e-05,
"loss": 0.4746,
"step": 1769
},
{
"epoch": 0.46,
"learning_rate": 1.1815408776516513e-05,
"loss": 0.4441,
"step": 1770
},
{
"epoch": 0.46,
"learning_rate": 1.1807154357481743e-05,
"loss": 0.4675,
"step": 1771
},
{
"epoch": 0.46,
"learning_rate": 1.179889866536809e-05,
"loss": 0.4734,
"step": 1772
},
{
"epoch": 0.46,
"learning_rate": 1.1790641705991407e-05,
"loss": 0.4641,
"step": 1773
},
{
"epoch": 0.46,
"learning_rate": 1.178238348516844e-05,
"loss": 0.479,
"step": 1774
},
{
"epoch": 0.46,
"learning_rate": 1.177412400871683e-05,
"loss": 0.4519,
"step": 1775
},
{
"epoch": 0.46,
"learning_rate": 1.176586328245509e-05,
"loss": 0.4795,
"step": 1776
},
{
"epoch": 0.46,
"learning_rate": 1.175760131220263e-05,
"loss": 0.4458,
"step": 1777
},
{
"epoch": 0.46,
"learning_rate": 1.1749338103779722e-05,
"loss": 0.4734,
"step": 1778
},
{
"epoch": 0.46,
"learning_rate": 1.1741073663007516e-05,
"loss": 0.4448,
"step": 1779
},
{
"epoch": 0.46,
"learning_rate": 1.173280799570803e-05,
"loss": 0.4583,
"step": 1780
},
{
"epoch": 0.46,
"learning_rate": 1.1724541107704152e-05,
"loss": 0.4636,
"step": 1781
},
{
"epoch": 0.46,
"learning_rate": 1.1716273004819617e-05,
"loss": 0.4868,
"step": 1782
},
{
"epoch": 0.46,
"learning_rate": 1.170800369287902e-05,
"loss": 0.4563,
"step": 1783
},
{
"epoch": 0.46,
"learning_rate": 1.169973317770782e-05,
"loss": 0.4541,
"step": 1784
},
{
"epoch": 0.46,
"learning_rate": 1.169146146513231e-05,
"loss": 0.4668,
"step": 1785
},
{
"epoch": 0.46,
"learning_rate": 1.1683188560979625e-05,
"loss": 0.4819,
"step": 1786
},
{
"epoch": 0.46,
"learning_rate": 1.1674914471077754e-05,
"loss": 0.4719,
"step": 1787
},
{
"epoch": 0.46,
"learning_rate": 1.1666639201255507e-05,
"loss": 0.4929,
"step": 1788
},
{
"epoch": 0.46,
"learning_rate": 1.165836275734253e-05,
"loss": 0.4521,
"step": 1789
},
{
"epoch": 0.46,
"learning_rate": 1.16500851451693e-05,
"loss": 0.4758,
"step": 1790
},
{
"epoch": 0.46,
"learning_rate": 1.1641806370567117e-05,
"loss": 0.4644,
"step": 1791
},
{
"epoch": 0.46,
"learning_rate": 1.1633526439368086e-05,
"loss": 0.4641,
"step": 1792
},
{
"epoch": 0.46,
"learning_rate": 1.1625245357405145e-05,
"loss": 0.4666,
"step": 1793
},
{
"epoch": 0.46,
"learning_rate": 1.1616963130512035e-05,
"loss": 0.4639,
"step": 1794
},
{
"epoch": 0.47,
"learning_rate": 1.16086797645233e-05,
"loss": 0.4529,
"step": 1795
},
{
"epoch": 0.47,
"learning_rate": 1.1600395265274296e-05,
"loss": 0.4792,
"step": 1796
},
{
"epoch": 0.47,
"learning_rate": 1.1592109638601166e-05,
"loss": 0.4922,
"step": 1797
},
{
"epoch": 0.47,
"learning_rate": 1.158382289034085e-05,
"loss": 0.4861,
"step": 1798
},
{
"epoch": 0.47,
"learning_rate": 1.1575535026331088e-05,
"loss": 0.469,
"step": 1799
},
{
"epoch": 0.47,
"learning_rate": 1.1567246052410397e-05,
"loss": 0.47,
"step": 1800
},
{
"epoch": 0.47,
"learning_rate": 1.1558955974418076e-05,
"loss": 0.4729,
"step": 1801
},
{
"epoch": 0.47,
"learning_rate": 1.1550664798194204e-05,
"loss": 0.4573,
"step": 1802
},
{
"epoch": 0.47,
"learning_rate": 1.1542372529579634e-05,
"loss": 0.4399,
"step": 1803
},
{
"epoch": 0.47,
"learning_rate": 1.1534079174415986e-05,
"loss": 0.4521,
"step": 1804
},
{
"epoch": 0.47,
"learning_rate": 1.1525784738545645e-05,
"loss": 0.4666,
"step": 1805
},
{
"epoch": 0.47,
"learning_rate": 1.1517489227811765e-05,
"loss": 0.428,
"step": 1806
},
{
"epoch": 0.47,
"learning_rate": 1.150919264805825e-05,
"loss": 0.4744,
"step": 1807
},
{
"epoch": 0.47,
"learning_rate": 1.1500895005129757e-05,
"loss": 0.4583,
"step": 1808
},
{
"epoch": 0.47,
"learning_rate": 1.1492596304871694e-05,
"loss": 0.4712,
"step": 1809
},
{
"epoch": 0.47,
"learning_rate": 1.1484296553130214e-05,
"loss": 0.4375,
"step": 1810
},
{
"epoch": 0.47,
"learning_rate": 1.147599575575221e-05,
"loss": 0.4661,
"step": 1811
},
{
"epoch": 0.47,
"learning_rate": 1.1467693918585311e-05,
"loss": 0.449,
"step": 1812
},
{
"epoch": 0.47,
"learning_rate": 1.1459391047477883e-05,
"loss": 0.4722,
"step": 1813
},
{
"epoch": 0.47,
"learning_rate": 1.1451087148279013e-05,
"loss": 0.4514,
"step": 1814
},
{
"epoch": 0.47,
"learning_rate": 1.144278222683852e-05,
"loss": 0.4548,
"step": 1815
},
{
"epoch": 0.47,
"learning_rate": 1.1434476289006935e-05,
"loss": 0.4585,
"step": 1816
},
{
"epoch": 0.47,
"learning_rate": 1.1426169340635509e-05,
"loss": 0.4492,
"step": 1817
},
{
"epoch": 0.47,
"learning_rate": 1.1417861387576208e-05,
"loss": 0.4856,
"step": 1818
},
{
"epoch": 0.47,
"learning_rate": 1.1409552435681702e-05,
"loss": 0.4814,
"step": 1819
},
{
"epoch": 0.47,
"learning_rate": 1.1401242490805364e-05,
"loss": 0.4333,
"step": 1820
},
{
"epoch": 0.47,
"learning_rate": 1.1392931558801273e-05,
"loss": 0.4753,
"step": 1821
},
{
"epoch": 0.47,
"learning_rate": 1.1384619645524192e-05,
"loss": 0.4678,
"step": 1822
},
{
"epoch": 0.47,
"learning_rate": 1.1376306756829583e-05,
"loss": 0.4717,
"step": 1823
},
{
"epoch": 0.47,
"learning_rate": 1.1367992898573594e-05,
"loss": 0.4841,
"step": 1824
},
{
"epoch": 0.47,
"learning_rate": 1.1359678076613058e-05,
"loss": 0.4773,
"step": 1825
},
{
"epoch": 0.47,
"learning_rate": 1.1351362296805487e-05,
"loss": 0.4724,
"step": 1826
},
{
"epoch": 0.47,
"learning_rate": 1.1343045565009061e-05,
"loss": 0.4785,
"step": 1827
},
{
"epoch": 0.47,
"learning_rate": 1.1334727887082634e-05,
"loss": 0.4585,
"step": 1828
},
{
"epoch": 0.47,
"learning_rate": 1.1326409268885732e-05,
"loss": 0.4863,
"step": 1829
},
{
"epoch": 0.47,
"learning_rate": 1.1318089716278535e-05,
"loss": 0.4888,
"step": 1830
},
{
"epoch": 0.47,
"learning_rate": 1.1309769235121892e-05,
"loss": 0.4595,
"step": 1831
},
{
"epoch": 0.47,
"learning_rate": 1.1301447831277293e-05,
"loss": 0.4788,
"step": 1832
},
{
"epoch": 0.47,
"learning_rate": 1.1293125510606882e-05,
"loss": 0.4746,
"step": 1833
},
{
"epoch": 0.48,
"learning_rate": 1.1284802278973458e-05,
"loss": 0.4668,
"step": 1834
},
{
"epoch": 0.48,
"learning_rate": 1.1276478142240457e-05,
"loss": 0.46,
"step": 1835
},
{
"epoch": 0.48,
"learning_rate": 1.126815310627194e-05,
"loss": 0.4661,
"step": 1836
},
{
"epoch": 0.48,
"learning_rate": 1.1259827176932625e-05,
"loss": 0.4688,
"step": 1837
},
{
"epoch": 0.48,
"learning_rate": 1.1251500360087837e-05,
"loss": 0.4468,
"step": 1838
},
{
"epoch": 0.48,
"learning_rate": 1.1243172661603536e-05,
"loss": 0.446,
"step": 1839
},
{
"epoch": 0.48,
"learning_rate": 1.123484408734631e-05,
"loss": 0.4485,
"step": 1840
},
{
"epoch": 0.48,
"learning_rate": 1.1226514643183352e-05,
"loss": 0.4758,
"step": 1841
},
{
"epoch": 0.48,
"learning_rate": 1.121818433498247e-05,
"loss": 0.4521,
"step": 1842
},
{
"epoch": 0.48,
"learning_rate": 1.120985316861209e-05,
"loss": 0.4385,
"step": 1843
},
{
"epoch": 0.48,
"learning_rate": 1.1201521149941232e-05,
"loss": 0.4727,
"step": 1844
},
{
"epoch": 0.48,
"learning_rate": 1.1193188284839518e-05,
"loss": 0.4446,
"step": 1845
},
{
"epoch": 0.48,
"learning_rate": 1.1184854579177173e-05,
"loss": 0.4482,
"step": 1846
},
{
"epoch": 0.48,
"learning_rate": 1.1176520038825007e-05,
"loss": 0.4741,
"step": 1847
},
{
"epoch": 0.48,
"learning_rate": 1.1168184669654423e-05,
"loss": 0.4539,
"step": 1848
},
{
"epoch": 0.48,
"learning_rate": 1.11598484775374e-05,
"loss": 0.4751,
"step": 1849
},
{
"epoch": 0.48,
"learning_rate": 1.115151146834651e-05,
"loss": 0.4636,
"step": 1850
},
{
"epoch": 0.48,
"learning_rate": 1.1143173647954888e-05,
"loss": 0.469,
"step": 1851
},
{
"epoch": 0.48,
"learning_rate": 1.1134835022236244e-05,
"loss": 0.457,
"step": 1852
},
{
"epoch": 0.48,
"learning_rate": 1.1126495597064862e-05,
"loss": 0.4739,
"step": 1853
},
{
"epoch": 0.48,
"learning_rate": 1.111815537831558e-05,
"loss": 0.4731,
"step": 1854
},
{
"epoch": 0.48,
"learning_rate": 1.1109814371863801e-05,
"loss": 0.4268,
"step": 1855
},
{
"epoch": 0.48,
"learning_rate": 1.1101472583585479e-05,
"loss": 0.4644,
"step": 1856
},
{
"epoch": 0.48,
"learning_rate": 1.1093130019357121e-05,
"loss": 0.4524,
"step": 1857
},
{
"epoch": 0.48,
"learning_rate": 1.108478668505578e-05,
"loss": 0.4539,
"step": 1858
},
{
"epoch": 0.48,
"learning_rate": 1.1076442586559053e-05,
"loss": 0.4565,
"step": 1859
},
{
"epoch": 0.48,
"learning_rate": 1.1068097729745076e-05,
"loss": 0.4407,
"step": 1860
},
{
"epoch": 0.48,
"learning_rate": 1.1059752120492511e-05,
"loss": 0.4529,
"step": 1861
},
{
"epoch": 0.48,
"learning_rate": 1.1051405764680561e-05,
"loss": 0.4731,
"step": 1862
},
{
"epoch": 0.48,
"learning_rate": 1.104305866818895e-05,
"loss": 0.4714,
"step": 1863
},
{
"epoch": 0.48,
"learning_rate": 1.1034710836897922e-05,
"loss": 0.4553,
"step": 1864
},
{
"epoch": 0.48,
"learning_rate": 1.1026362276688243e-05,
"loss": 0.449,
"step": 1865
},
{
"epoch": 0.48,
"learning_rate": 1.1018012993441194e-05,
"loss": 0.4602,
"step": 1866
},
{
"epoch": 0.48,
"learning_rate": 1.100966299303855e-05,
"loss": 0.448,
"step": 1867
},
{
"epoch": 0.48,
"learning_rate": 1.1001312281362612e-05,
"loss": 0.4751,
"step": 1868
},
{
"epoch": 0.48,
"learning_rate": 1.0992960864296172e-05,
"loss": 0.4565,
"step": 1869
},
{
"epoch": 0.48,
"learning_rate": 1.0984608747722517e-05,
"loss": 0.4558,
"step": 1870
},
{
"epoch": 0.48,
"learning_rate": 1.0976255937525426e-05,
"loss": 0.4482,
"step": 1871
},
{
"epoch": 0.49,
"learning_rate": 1.0967902439589184e-05,
"loss": 0.4631,
"step": 1872
},
{
"epoch": 0.49,
"learning_rate": 1.0959548259798529e-05,
"loss": 0.4507,
"step": 1873
},
{
"epoch": 0.49,
"learning_rate": 1.095119340403871e-05,
"loss": 0.4426,
"step": 1874
},
{
"epoch": 0.49,
"learning_rate": 1.0942837878195436e-05,
"loss": 0.4607,
"step": 1875
},
{
"epoch": 0.49,
"learning_rate": 1.0934481688154887e-05,
"loss": 0.4612,
"step": 1876
},
{
"epoch": 0.49,
"learning_rate": 1.092612483980372e-05,
"loss": 0.449,
"step": 1877
},
{
"epoch": 0.49,
"learning_rate": 1.091776733902905e-05,
"loss": 0.4805,
"step": 1878
},
{
"epoch": 0.49,
"learning_rate": 1.0909409191718453e-05,
"loss": 0.4456,
"step": 1879
},
{
"epoch": 0.49,
"learning_rate": 1.0901050403759951e-05,
"loss": 0.4548,
"step": 1880
},
{
"epoch": 0.49,
"learning_rate": 1.089269098104204e-05,
"loss": 0.4595,
"step": 1881
},
{
"epoch": 0.49,
"learning_rate": 1.0884330929453643e-05,
"loss": 0.4697,
"step": 1882
},
{
"epoch": 0.49,
"learning_rate": 1.087597025488413e-05,
"loss": 0.4692,
"step": 1883
},
{
"epoch": 0.49,
"learning_rate": 1.0867608963223319e-05,
"loss": 0.4751,
"step": 1884
},
{
"epoch": 0.49,
"learning_rate": 1.0859247060361451e-05,
"loss": 0.4929,
"step": 1885
},
{
"epoch": 0.49,
"learning_rate": 1.0850884552189202e-05,
"loss": 0.4478,
"step": 1886
},
{
"epoch": 0.49,
"learning_rate": 1.084252144459768e-05,
"loss": 0.4568,
"step": 1887
},
{
"epoch": 0.49,
"learning_rate": 1.0834157743478407e-05,
"loss": 0.4626,
"step": 1888
},
{
"epoch": 0.49,
"learning_rate": 1.0825793454723325e-05,
"loss": 0.4727,
"step": 1889
},
{
"epoch": 0.49,
"learning_rate": 1.0817428584224794e-05,
"loss": 0.4546,
"step": 1890
},
{
"epoch": 0.49,
"learning_rate": 1.0809063137875581e-05,
"loss": 0.447,
"step": 1891
},
{
"epoch": 0.49,
"learning_rate": 1.0800697121568855e-05,
"loss": 0.469,
"step": 1892
},
{
"epoch": 0.49,
"learning_rate": 1.0792330541198197e-05,
"loss": 0.4626,
"step": 1893
},
{
"epoch": 0.49,
"learning_rate": 1.0783963402657575e-05,
"loss": 0.4661,
"step": 1894
},
{
"epoch": 0.49,
"learning_rate": 1.0775595711841356e-05,
"loss": 0.4863,
"step": 1895
},
{
"epoch": 0.49,
"learning_rate": 1.0767227474644293e-05,
"loss": 0.4832,
"step": 1896
},
{
"epoch": 0.49,
"learning_rate": 1.0758858696961523e-05,
"loss": 0.4631,
"step": 1897
},
{
"epoch": 0.49,
"learning_rate": 1.0750489384688568e-05,
"loss": 0.4646,
"step": 1898
},
{
"epoch": 0.49,
"learning_rate": 1.0742119543721322e-05,
"loss": 0.4458,
"step": 1899
},
{
"epoch": 0.49,
"learning_rate": 1.0733749179956057e-05,
"loss": 0.4434,
"step": 1900
},
{
"epoch": 0.49,
"learning_rate": 1.072537829928941e-05,
"loss": 0.4727,
"step": 1901
},
{
"epoch": 0.49,
"learning_rate": 1.0717006907618377e-05,
"loss": 0.4714,
"step": 1902
},
{
"epoch": 0.49,
"learning_rate": 1.0708635010840324e-05,
"loss": 0.4719,
"step": 1903
},
{
"epoch": 0.49,
"learning_rate": 1.070026261485297e-05,
"loss": 0.4673,
"step": 1904
},
{
"epoch": 0.49,
"learning_rate": 1.0691889725554377e-05,
"loss": 0.4741,
"step": 1905
},
{
"epoch": 0.49,
"learning_rate": 1.0683516348842966e-05,
"loss": 0.4761,
"step": 1906
},
{
"epoch": 0.49,
"learning_rate": 1.0675142490617499e-05,
"loss": 0.4851,
"step": 1907
},
{
"epoch": 0.49,
"learning_rate": 1.0666768156777066e-05,
"loss": 0.4546,
"step": 1908
},
{
"epoch": 0.49,
"learning_rate": 1.0658393353221108e-05,
"loss": 0.4558,
"step": 1909
},
{
"epoch": 0.49,
"learning_rate": 1.0650018085849387e-05,
"loss": 0.4639,
"step": 1910
},
{
"epoch": 0.5,
"learning_rate": 1.0641642360561995e-05,
"loss": 0.4468,
"step": 1911
},
{
"epoch": 0.5,
"learning_rate": 1.0633266183259348e-05,
"loss": 0.4744,
"step": 1912
},
{
"epoch": 0.5,
"learning_rate": 1.062488955984218e-05,
"loss": 0.4902,
"step": 1913
},
{
"epoch": 0.5,
"learning_rate": 1.0616512496211528e-05,
"loss": 0.4434,
"step": 1914
},
{
"epoch": 0.5,
"learning_rate": 1.060813499826876e-05,
"loss": 0.4434,
"step": 1915
},
{
"epoch": 0.5,
"learning_rate": 1.0599757071915534e-05,
"loss": 0.4453,
"step": 1916
},
{
"epoch": 0.5,
"learning_rate": 1.0591378723053814e-05,
"loss": 0.4705,
"step": 1917
},
{
"epoch": 0.5,
"learning_rate": 1.0582999957585862e-05,
"loss": 0.4504,
"step": 1918
},
{
"epoch": 0.5,
"learning_rate": 1.0574620781414238e-05,
"loss": 0.4456,
"step": 1919
},
{
"epoch": 0.5,
"learning_rate": 1.0566241200441783e-05,
"loss": 0.4575,
"step": 1920
},
{
"epoch": 0.5,
"learning_rate": 1.0557861220571626e-05,
"loss": 0.457,
"step": 1921
},
{
"epoch": 0.5,
"learning_rate": 1.0549480847707184e-05,
"loss": 0.4763,
"step": 1922
},
{
"epoch": 0.5,
"learning_rate": 1.054110008775214e-05,
"loss": 0.4407,
"step": 1923
},
{
"epoch": 0.5,
"learning_rate": 1.053271894661046e-05,
"loss": 0.4294,
"step": 1924
},
{
"epoch": 0.5,
"learning_rate": 1.0524337430186368e-05,
"loss": 0.4351,
"step": 1925
},
{
"epoch": 0.5,
"learning_rate": 1.051595554438436e-05,
"loss": 0.448,
"step": 1926
},
{
"epoch": 0.5,
"learning_rate": 1.0507573295109188e-05,
"loss": 0.4558,
"step": 1927
},
{
"epoch": 0.5,
"learning_rate": 1.0499190688265866e-05,
"loss": 0.479,
"step": 1928
},
{
"epoch": 0.5,
"learning_rate": 1.0490807729759654e-05,
"loss": 0.4473,
"step": 1929
},
{
"epoch": 0.5,
"learning_rate": 1.0482424425496061e-05,
"loss": 0.449,
"step": 1930
},
{
"epoch": 0.5,
"learning_rate": 1.047404078138084e-05,
"loss": 0.467,
"step": 1931
},
{
"epoch": 0.5,
"learning_rate": 1.0465656803319984e-05,
"loss": 0.4624,
"step": 1932
},
{
"epoch": 0.5,
"learning_rate": 1.045727249721972e-05,
"loss": 0.469,
"step": 1933
},
{
"epoch": 0.5,
"learning_rate": 1.0448887868986508e-05,
"loss": 0.4524,
"step": 1934
},
{
"epoch": 0.5,
"learning_rate": 1.0440502924527034e-05,
"loss": 0.4519,
"step": 1935
},
{
"epoch": 0.5,
"learning_rate": 1.0432117669748209e-05,
"loss": 0.4519,
"step": 1936
},
{
"epoch": 0.5,
"learning_rate": 1.0423732110557157e-05,
"loss": 0.4575,
"step": 1937
},
{
"epoch": 0.5,
"learning_rate": 1.041534625286122e-05,
"loss": 0.4478,
"step": 1938
},
{
"epoch": 0.5,
"learning_rate": 1.040696010256795e-05,
"loss": 0.4585,
"step": 1939
},
{
"epoch": 0.5,
"learning_rate": 1.0398573665585105e-05,
"loss": 0.4609,
"step": 1940
},
{
"epoch": 0.5,
"learning_rate": 1.0390186947820648e-05,
"loss": 0.4443,
"step": 1941
},
{
"epoch": 0.5,
"learning_rate": 1.0381799955182734e-05,
"loss": 0.4414,
"step": 1942
},
{
"epoch": 0.5,
"learning_rate": 1.0373412693579714e-05,
"loss": 0.429,
"step": 1943
},
{
"epoch": 0.5,
"learning_rate": 1.0365025168920133e-05,
"loss": 0.4348,
"step": 1944
},
{
"epoch": 0.5,
"learning_rate": 1.0356637387112713e-05,
"loss": 0.4502,
"step": 1945
},
{
"epoch": 0.5,
"learning_rate": 1.034824935406636e-05,
"loss": 0.4861,
"step": 1946
},
{
"epoch": 0.5,
"learning_rate": 1.0339861075690167e-05,
"loss": 0.4524,
"step": 1947
},
{
"epoch": 0.5,
"learning_rate": 1.0331472557893385e-05,
"loss": 0.458,
"step": 1948
},
{
"epoch": 0.51,
"learning_rate": 1.0323083806585436e-05,
"loss": 0.4424,
"step": 1949
},
{
"epoch": 0.51,
"learning_rate": 1.031469482767592e-05,
"loss": 0.4636,
"step": 1950
},
{
"epoch": 0.51,
"learning_rate": 1.0306305627074581e-05,
"loss": 0.4622,
"step": 1951
},
{
"epoch": 0.51,
"learning_rate": 1.0297916210691328e-05,
"loss": 0.447,
"step": 1952
},
{
"epoch": 0.51,
"learning_rate": 1.0289526584436223e-05,
"loss": 0.4546,
"step": 1953
},
{
"epoch": 0.51,
"learning_rate": 1.0281136754219467e-05,
"loss": 0.4448,
"step": 1954
},
{
"epoch": 0.51,
"learning_rate": 1.0272746725951412e-05,
"loss": 0.4373,
"step": 1955
},
{
"epoch": 0.51,
"learning_rate": 1.0264356505542552e-05,
"loss": 0.4731,
"step": 1956
},
{
"epoch": 0.51,
"learning_rate": 1.0255966098903509e-05,
"loss": 0.4421,
"step": 1957
},
{
"epoch": 0.51,
"learning_rate": 1.0247575511945041e-05,
"loss": 0.4685,
"step": 1958
},
{
"epoch": 0.51,
"learning_rate": 1.023918475057803e-05,
"loss": 0.4773,
"step": 1959
},
{
"epoch": 0.51,
"learning_rate": 1.0230793820713487e-05,
"loss": 0.4507,
"step": 1960
},
{
"epoch": 0.51,
"learning_rate": 1.0222402728262529e-05,
"loss": 0.4609,
"step": 1961
},
{
"epoch": 0.51,
"learning_rate": 1.0214011479136402e-05,
"loss": 0.4622,
"step": 1962
},
{
"epoch": 0.51,
"learning_rate": 1.0205620079246455e-05,
"loss": 0.4434,
"step": 1963
},
{
"epoch": 0.51,
"learning_rate": 1.0197228534504144e-05,
"loss": 0.439,
"step": 1964
},
{
"epoch": 0.51,
"learning_rate": 1.0188836850821026e-05,
"loss": 0.4541,
"step": 1965
},
{
"epoch": 0.51,
"learning_rate": 1.0180445034108761e-05,
"loss": 0.4675,
"step": 1966
},
{
"epoch": 0.51,
"learning_rate": 1.0172053090279094e-05,
"loss": 0.4517,
"step": 1967
},
{
"epoch": 0.51,
"learning_rate": 1.0163661025243868e-05,
"loss": 0.4343,
"step": 1968
},
{
"epoch": 0.51,
"learning_rate": 1.0155268844915006e-05,
"loss": 0.4414,
"step": 1969
},
{
"epoch": 0.51,
"learning_rate": 1.0146876555204515e-05,
"loss": 0.4612,
"step": 1970
},
{
"epoch": 0.51,
"learning_rate": 1.0138484162024478e-05,
"loss": 0.4773,
"step": 1971
},
{
"epoch": 0.51,
"learning_rate": 1.013009167128705e-05,
"loss": 0.4753,
"step": 1972
},
{
"epoch": 0.51,
"learning_rate": 1.0121699088904457e-05,
"loss": 0.4561,
"step": 1973
},
{
"epoch": 0.51,
"learning_rate": 1.0113306420788987e-05,
"loss": 0.4534,
"step": 1974
},
{
"epoch": 0.51,
"learning_rate": 1.0104913672852994e-05,
"loss": 0.449,
"step": 1975
},
{
"epoch": 0.51,
"learning_rate": 1.009652085100888e-05,
"loss": 0.4602,
"step": 1976
},
{
"epoch": 0.51,
"learning_rate": 1.00881279611691e-05,
"loss": 0.4573,
"step": 1977
},
{
"epoch": 0.51,
"learning_rate": 1.0079735009246168e-05,
"loss": 0.4563,
"step": 1978
},
{
"epoch": 0.51,
"learning_rate": 1.0071342001152628e-05,
"loss": 0.4529,
"step": 1979
},
{
"epoch": 0.51,
"learning_rate": 1.0062948942801067e-05,
"loss": 0.468,
"step": 1980
},
{
"epoch": 0.51,
"learning_rate": 1.0054555840104118e-05,
"loss": 0.4604,
"step": 1981
},
{
"epoch": 0.51,
"learning_rate": 1.0046162698974434e-05,
"loss": 0.4568,
"step": 1982
},
{
"epoch": 0.51,
"learning_rate": 1.003776952532469e-05,
"loss": 0.459,
"step": 1983
},
{
"epoch": 0.51,
"learning_rate": 1.0029376325067601e-05,
"loss": 0.4517,
"step": 1984
},
{
"epoch": 0.51,
"learning_rate": 1.0020983104115887e-05,
"loss": 0.4734,
"step": 1985
},
{
"epoch": 0.51,
"learning_rate": 1.001258986838229e-05,
"loss": 0.4871,
"step": 1986
},
{
"epoch": 0.51,
"learning_rate": 1.0004196623779556e-05,
"loss": 0.4451,
"step": 1987
},
{
"epoch": 0.52,
"learning_rate": 9.995803376220444e-06,
"loss": 0.4712,
"step": 1988
},
{
"epoch": 0.52,
"learning_rate": 9.987410131617713e-06,
"loss": 0.4546,
"step": 1989
},
{
"epoch": 0.52,
"learning_rate": 9.979016895884113e-06,
"loss": 0.4583,
"step": 1990
},
{
"epoch": 0.52,
"learning_rate": 9.970623674932402e-06,
"loss": 0.4512,
"step": 1991
},
{
"epoch": 0.52,
"learning_rate": 9.962230474675313e-06,
"loss": 0.4666,
"step": 1992
},
{
"epoch": 0.52,
"learning_rate": 9.95383730102557e-06,
"loss": 0.4617,
"step": 1993
},
{
"epoch": 0.52,
"learning_rate": 9.945444159895885e-06,
"loss": 0.4644,
"step": 1994
},
{
"epoch": 0.52,
"learning_rate": 9.937051057198932e-06,
"loss": 0.4399,
"step": 1995
},
{
"epoch": 0.52,
"learning_rate": 9.928657998847375e-06,
"loss": 0.4568,
"step": 1996
},
{
"epoch": 0.52,
"learning_rate": 9.920264990753837e-06,
"loss": 0.4622,
"step": 1997
},
{
"epoch": 0.52,
"learning_rate": 9.911872038830902e-06,
"loss": 0.4521,
"step": 1998
},
{
"epoch": 0.52,
"learning_rate": 9.903479148991124e-06,
"loss": 0.47,
"step": 1999
},
{
"epoch": 0.52,
"learning_rate": 9.895086327147007e-06,
"loss": 0.4692,
"step": 2000
},
{
"epoch": 0.52,
"learning_rate": 9.886693579211015e-06,
"loss": 0.4463,
"step": 2001
},
{
"epoch": 0.52,
"learning_rate": 9.878300911095545e-06,
"loss": 0.4294,
"step": 2002
},
{
"epoch": 0.52,
"learning_rate": 9.869908328712953e-06,
"loss": 0.468,
"step": 2003
},
{
"epoch": 0.52,
"learning_rate": 9.861515837975529e-06,
"loss": 0.4719,
"step": 2004
},
{
"epoch": 0.52,
"learning_rate": 9.85312344479549e-06,
"loss": 0.4512,
"step": 2005
},
{
"epoch": 0.52,
"learning_rate": 9.844731155084998e-06,
"loss": 0.4414,
"step": 2006
},
{
"epoch": 0.52,
"learning_rate": 9.836338974756134e-06,
"loss": 0.4519,
"step": 2007
},
{
"epoch": 0.52,
"learning_rate": 9.827946909720907e-06,
"loss": 0.4619,
"step": 2008
},
{
"epoch": 0.52,
"learning_rate": 9.819554965891244e-06,
"loss": 0.4651,
"step": 2009
},
{
"epoch": 0.52,
"learning_rate": 9.811163149178976e-06,
"loss": 0.4592,
"step": 2010
},
{
"epoch": 0.52,
"learning_rate": 9.802771465495858e-06,
"loss": 0.4819,
"step": 2011
},
{
"epoch": 0.52,
"learning_rate": 9.794379920753545e-06,
"loss": 0.4495,
"step": 2012
},
{
"epoch": 0.52,
"learning_rate": 9.7859885208636e-06,
"loss": 0.4548,
"step": 2013
},
{
"epoch": 0.52,
"learning_rate": 9.777597271737474e-06,
"loss": 0.4839,
"step": 2014
},
{
"epoch": 0.52,
"learning_rate": 9.769206179286517e-06,
"loss": 0.4387,
"step": 2015
},
{
"epoch": 0.52,
"learning_rate": 9.760815249421973e-06,
"loss": 0.4478,
"step": 2016
},
{
"epoch": 0.52,
"learning_rate": 9.75242448805496e-06,
"loss": 0.457,
"step": 2017
},
{
"epoch": 0.52,
"learning_rate": 9.744033901096494e-06,
"loss": 0.4675,
"step": 2018
},
{
"epoch": 0.52,
"learning_rate": 9.735643494457448e-06,
"loss": 0.4512,
"step": 2019
},
{
"epoch": 0.52,
"learning_rate": 9.72725327404859e-06,
"loss": 0.4792,
"step": 2020
},
{
"epoch": 0.52,
"learning_rate": 9.718863245780538e-06,
"loss": 0.4456,
"step": 2021
},
{
"epoch": 0.52,
"learning_rate": 9.71047341556378e-06,
"loss": 0.4326,
"step": 2022
},
{
"epoch": 0.52,
"learning_rate": 9.702083789308677e-06,
"loss": 0.429,
"step": 2023
},
{
"epoch": 0.52,
"learning_rate": 9.693694372925422e-06,
"loss": 0.4629,
"step": 2024
},
{
"epoch": 0.52,
"learning_rate": 9.685305172324083e-06,
"loss": 0.4683,
"step": 2025
},
{
"epoch": 0.53,
"learning_rate": 9.676916193414569e-06,
"loss": 0.4612,
"step": 2026
},
{
"epoch": 0.53,
"learning_rate": 9.668527442106619e-06,
"loss": 0.4502,
"step": 2027
},
{
"epoch": 0.53,
"learning_rate": 9.660138924309838e-06,
"loss": 0.4619,
"step": 2028
},
{
"epoch": 0.53,
"learning_rate": 9.65175064593364e-06,
"loss": 0.4646,
"step": 2029
},
{
"epoch": 0.53,
"learning_rate": 9.64336261288729e-06,
"loss": 0.4734,
"step": 2030
},
{
"epoch": 0.53,
"learning_rate": 9.634974831079868e-06,
"loss": 0.459,
"step": 2031
},
{
"epoch": 0.53,
"learning_rate": 9.626587306420287e-06,
"loss": 0.4727,
"step": 2032
},
{
"epoch": 0.53,
"learning_rate": 9.61820004481727e-06,
"loss": 0.4395,
"step": 2033
},
{
"epoch": 0.53,
"learning_rate": 9.609813052179354e-06,
"loss": 0.4321,
"step": 2034
},
{
"epoch": 0.53,
"learning_rate": 9.601426334414898e-06,
"loss": 0.4697,
"step": 2035
},
{
"epoch": 0.53,
"learning_rate": 9.593039897432053e-06,
"loss": 0.4751,
"step": 2036
},
{
"epoch": 0.53,
"learning_rate": 9.584653747138784e-06,
"loss": 0.4441,
"step": 2037
},
{
"epoch": 0.53,
"learning_rate": 9.576267889442848e-06,
"loss": 0.4409,
"step": 2038
},
{
"epoch": 0.53,
"learning_rate": 9.567882330251794e-06,
"loss": 0.4602,
"step": 2039
},
{
"epoch": 0.53,
"learning_rate": 9.559497075472967e-06,
"loss": 0.4666,
"step": 2040
},
{
"epoch": 0.53,
"learning_rate": 9.551112131013493e-06,
"loss": 0.4717,
"step": 2041
},
{
"epoch": 0.53,
"learning_rate": 9.542727502780285e-06,
"loss": 0.4253,
"step": 2042
},
{
"epoch": 0.53,
"learning_rate": 9.53434319668002e-06,
"loss": 0.4355,
"step": 2043
},
{
"epoch": 0.53,
"learning_rate": 9.525959218619164e-06,
"loss": 0.4751,
"step": 2044
},
{
"epoch": 0.53,
"learning_rate": 9.517575574503945e-06,
"loss": 0.4397,
"step": 2045
},
{
"epoch": 0.53,
"learning_rate": 9.509192270240348e-06,
"loss": 0.4541,
"step": 2046
},
{
"epoch": 0.53,
"learning_rate": 9.500809311734137e-06,
"loss": 0.4399,
"step": 2047
},
{
"epoch": 0.53,
"learning_rate": 9.492426704890812e-06,
"loss": 0.4897,
"step": 2048
},
{
"epoch": 0.53,
"learning_rate": 9.484044455615642e-06,
"loss": 0.4272,
"step": 2049
},
{
"epoch": 0.53,
"learning_rate": 9.475662569813637e-06,
"loss": 0.4365,
"step": 2050
},
{
"epoch": 0.53,
"learning_rate": 9.467281053389543e-06,
"loss": 0.4636,
"step": 2051
},
{
"epoch": 0.53,
"learning_rate": 9.458899912247861e-06,
"loss": 0.4363,
"step": 2052
},
{
"epoch": 0.53,
"learning_rate": 9.450519152292816e-06,
"loss": 0.4553,
"step": 2053
},
{
"epoch": 0.53,
"learning_rate": 9.442138779428376e-06,
"loss": 0.4189,
"step": 2054
},
{
"epoch": 0.53,
"learning_rate": 9.433758799558222e-06,
"loss": 0.4624,
"step": 2055
},
{
"epoch": 0.53,
"learning_rate": 9.425379218585765e-06,
"loss": 0.4561,
"step": 2056
},
{
"epoch": 0.53,
"learning_rate": 9.417000042414141e-06,
"loss": 0.4629,
"step": 2057
},
{
"epoch": 0.53,
"learning_rate": 9.40862127694619e-06,
"loss": 0.4441,
"step": 2058
},
{
"epoch": 0.53,
"learning_rate": 9.40024292808447e-06,
"loss": 0.4648,
"step": 2059
},
{
"epoch": 0.53,
"learning_rate": 9.391865001731242e-06,
"loss": 0.4883,
"step": 2060
},
{
"epoch": 0.53,
"learning_rate": 9.383487503788473e-06,
"loss": 0.4219,
"step": 2061
},
{
"epoch": 0.53,
"learning_rate": 9.375110440157827e-06,
"loss": 0.4805,
"step": 2062
},
{
"epoch": 0.53,
"learning_rate": 9.366733816740652e-06,
"loss": 0.4541,
"step": 2063
},
{
"epoch": 0.53,
"learning_rate": 9.358357639438007e-06,
"loss": 0.4604,
"step": 2064
},
{
"epoch": 0.54,
"learning_rate": 9.349981914150611e-06,
"loss": 0.438,
"step": 2065
},
{
"epoch": 0.54,
"learning_rate": 9.341606646778895e-06,
"loss": 0.4714,
"step": 2066
},
{
"epoch": 0.54,
"learning_rate": 9.333231843222938e-06,
"loss": 0.4736,
"step": 2067
},
{
"epoch": 0.54,
"learning_rate": 9.324857509382504e-06,
"loss": 0.4539,
"step": 2068
},
{
"epoch": 0.54,
"learning_rate": 9.316483651157037e-06,
"loss": 0.4712,
"step": 2069
},
{
"epoch": 0.54,
"learning_rate": 9.308110274445625e-06,
"loss": 0.4524,
"step": 2070
},
{
"epoch": 0.54,
"learning_rate": 9.299737385147033e-06,
"loss": 0.4521,
"step": 2071
},
{
"epoch": 0.54,
"learning_rate": 9.291364989159679e-06,
"loss": 0.4614,
"step": 2072
},
{
"epoch": 0.54,
"learning_rate": 9.282993092381626e-06,
"loss": 0.47,
"step": 2073
},
{
"epoch": 0.54,
"learning_rate": 9.274621700710594e-06,
"loss": 0.4536,
"step": 2074
},
{
"epoch": 0.54,
"learning_rate": 9.266250820043945e-06,
"loss": 0.4451,
"step": 2075
},
{
"epoch": 0.54,
"learning_rate": 9.257880456278682e-06,
"loss": 0.4419,
"step": 2076
},
{
"epoch": 0.54,
"learning_rate": 9.249510615311434e-06,
"loss": 0.4651,
"step": 2077
},
{
"epoch": 0.54,
"learning_rate": 9.24114130303848e-06,
"loss": 0.4519,
"step": 2078
},
{
"epoch": 0.54,
"learning_rate": 9.232772525355712e-06,
"loss": 0.4583,
"step": 2079
},
{
"epoch": 0.54,
"learning_rate": 9.224404288158645e-06,
"loss": 0.4446,
"step": 2080
},
{
"epoch": 0.54,
"learning_rate": 9.216036597342427e-06,
"loss": 0.4404,
"step": 2081
},
{
"epoch": 0.54,
"learning_rate": 9.207669458801803e-06,
"loss": 0.4429,
"step": 2082
},
{
"epoch": 0.54,
"learning_rate": 9.199302878431146e-06,
"loss": 0.4426,
"step": 2083
},
{
"epoch": 0.54,
"learning_rate": 9.190936862124424e-06,
"loss": 0.4409,
"step": 2084
},
{
"epoch": 0.54,
"learning_rate": 9.182571415775209e-06,
"loss": 0.4343,
"step": 2085
},
{
"epoch": 0.54,
"learning_rate": 9.174206545276678e-06,
"loss": 0.4473,
"step": 2086
},
{
"epoch": 0.54,
"learning_rate": 9.165842256521595e-06,
"loss": 0.4722,
"step": 2087
},
{
"epoch": 0.54,
"learning_rate": 9.157478555402324e-06,
"loss": 0.4607,
"step": 2088
},
{
"epoch": 0.54,
"learning_rate": 9.149115447810798e-06,
"loss": 0.4487,
"step": 2089
},
{
"epoch": 0.54,
"learning_rate": 9.14075293963855e-06,
"loss": 0.4561,
"step": 2090
},
{
"epoch": 0.54,
"learning_rate": 9.132391036776686e-06,
"loss": 0.437,
"step": 2091
},
{
"epoch": 0.54,
"learning_rate": 9.124029745115872e-06,
"loss": 0.4624,
"step": 2092
},
{
"epoch": 0.54,
"learning_rate": 9.11566907054636e-06,
"loss": 0.4377,
"step": 2093
},
{
"epoch": 0.54,
"learning_rate": 9.10730901895796e-06,
"loss": 0.4731,
"step": 2094
},
{
"epoch": 0.54,
"learning_rate": 9.09894959624005e-06,
"loss": 0.4397,
"step": 2095
},
{
"epoch": 0.54,
"learning_rate": 9.090590808281554e-06,
"loss": 0.4575,
"step": 2096
},
{
"epoch": 0.54,
"learning_rate": 9.082232660970953e-06,
"loss": 0.4482,
"step": 2097
},
{
"epoch": 0.54,
"learning_rate": 9.073875160196283e-06,
"loss": 0.4553,
"step": 2098
},
{
"epoch": 0.54,
"learning_rate": 9.065518311845114e-06,
"loss": 0.4485,
"step": 2099
},
{
"epoch": 0.54,
"learning_rate": 9.057162121804567e-06,
"loss": 0.4646,
"step": 2100
},
{
"epoch": 0.54,
"learning_rate": 9.048806595961294e-06,
"loss": 0.4639,
"step": 2101
},
{
"epoch": 0.54,
"learning_rate": 9.040451740201473e-06,
"loss": 0.4629,
"step": 2102
},
{
"epoch": 0.54,
"learning_rate": 9.032097560410821e-06,
"loss": 0.4302,
"step": 2103
},
{
"epoch": 0.55,
"learning_rate": 9.023744062474574e-06,
"loss": 0.4443,
"step": 2104
},
{
"epoch": 0.55,
"learning_rate": 9.015391252277488e-06,
"loss": 0.4641,
"step": 2105
},
{
"epoch": 0.55,
"learning_rate": 9.00703913570383e-06,
"loss": 0.46,
"step": 2106
},
{
"epoch": 0.55,
"learning_rate": 8.998687718637391e-06,
"loss": 0.5034,
"step": 2107
},
{
"epoch": 0.55,
"learning_rate": 8.990337006961454e-06,
"loss": 0.4312,
"step": 2108
},
{
"epoch": 0.55,
"learning_rate": 8.98198700655881e-06,
"loss": 0.4624,
"step": 2109
},
{
"epoch": 0.55,
"learning_rate": 8.973637723311759e-06,
"loss": 0.4641,
"step": 2110
},
{
"epoch": 0.55,
"learning_rate": 8.96528916310208e-06,
"loss": 0.4502,
"step": 2111
},
{
"epoch": 0.55,
"learning_rate": 8.956941331811052e-06,
"loss": 0.4595,
"step": 2112
},
{
"epoch": 0.55,
"learning_rate": 8.948594235319444e-06,
"loss": 0.4844,
"step": 2113
},
{
"epoch": 0.55,
"learning_rate": 8.940247879507492e-06,
"loss": 0.4521,
"step": 2114
},
{
"epoch": 0.55,
"learning_rate": 8.931902270254929e-06,
"loss": 0.4404,
"step": 2115
},
{
"epoch": 0.55,
"learning_rate": 8.923557413440947e-06,
"loss": 0.4314,
"step": 2116
},
{
"epoch": 0.55,
"learning_rate": 8.915213314944224e-06,
"loss": 0.4656,
"step": 2117
},
{
"epoch": 0.55,
"learning_rate": 8.906869980642882e-06,
"loss": 0.4504,
"step": 2118
},
{
"epoch": 0.55,
"learning_rate": 8.898527416414524e-06,
"loss": 0.4819,
"step": 2119
},
{
"epoch": 0.55,
"learning_rate": 8.890185628136204e-06,
"loss": 0.4346,
"step": 2120
},
{
"epoch": 0.55,
"learning_rate": 8.881844621684423e-06,
"loss": 0.4397,
"step": 2121
},
{
"epoch": 0.55,
"learning_rate": 8.873504402935142e-06,
"loss": 0.4624,
"step": 2122
},
{
"epoch": 0.55,
"learning_rate": 8.865164977763756e-06,
"loss": 0.468,
"step": 2123
},
{
"epoch": 0.55,
"learning_rate": 8.856826352045115e-06,
"loss": 0.4707,
"step": 2124
},
{
"epoch": 0.55,
"learning_rate": 8.848488531653494e-06,
"loss": 0.4766,
"step": 2125
},
{
"epoch": 0.55,
"learning_rate": 8.840151522462602e-06,
"loss": 0.4578,
"step": 2126
},
{
"epoch": 0.55,
"learning_rate": 8.83181533034558e-06,
"loss": 0.4431,
"step": 2127
},
{
"epoch": 0.55,
"learning_rate": 8.823479961174993e-06,
"loss": 0.4495,
"step": 2128
},
{
"epoch": 0.55,
"learning_rate": 8.81514542082283e-06,
"loss": 0.4463,
"step": 2129
},
{
"epoch": 0.55,
"learning_rate": 8.806811715160485e-06,
"loss": 0.4583,
"step": 2130
},
{
"epoch": 0.55,
"learning_rate": 8.79847885005877e-06,
"loss": 0.4414,
"step": 2131
},
{
"epoch": 0.55,
"learning_rate": 8.790146831387913e-06,
"loss": 0.4573,
"step": 2132
},
{
"epoch": 0.55,
"learning_rate": 8.781815665017531e-06,
"loss": 0.4529,
"step": 2133
},
{
"epoch": 0.55,
"learning_rate": 8.773485356816651e-06,
"loss": 0.4417,
"step": 2134
},
{
"epoch": 0.55,
"learning_rate": 8.76515591265369e-06,
"loss": 0.4392,
"step": 2135
},
{
"epoch": 0.55,
"learning_rate": 8.756827338396465e-06,
"loss": 0.468,
"step": 2136
},
{
"epoch": 0.55,
"learning_rate": 8.748499639912168e-06,
"loss": 0.4587,
"step": 2137
},
{
"epoch": 0.55,
"learning_rate": 8.740172823067378e-06,
"loss": 0.4556,
"step": 2138
},
{
"epoch": 0.55,
"learning_rate": 8.731846893728062e-06,
"loss": 0.4465,
"step": 2139
},
{
"epoch": 0.55,
"learning_rate": 8.723521857759547e-06,
"loss": 0.4514,
"step": 2140
},
{
"epoch": 0.55,
"learning_rate": 8.715197721026543e-06,
"loss": 0.4399,
"step": 2141
},
{
"epoch": 0.56,
"learning_rate": 8.706874489393123e-06,
"loss": 0.4087,
"step": 2142
},
{
"epoch": 0.56,
"learning_rate": 8.69855216872271e-06,
"loss": 0.4756,
"step": 2143
},
{
"epoch": 0.56,
"learning_rate": 8.690230764878114e-06,
"loss": 0.4502,
"step": 2144
},
{
"epoch": 0.56,
"learning_rate": 8.681910283721465e-06,
"loss": 0.4363,
"step": 2145
},
{
"epoch": 0.56,
"learning_rate": 8.67359073111427e-06,
"loss": 0.4521,
"step": 2146
},
{
"epoch": 0.56,
"learning_rate": 8.665272112917366e-06,
"loss": 0.4626,
"step": 2147
},
{
"epoch": 0.56,
"learning_rate": 8.656954434990942e-06,
"loss": 0.4751,
"step": 2148
},
{
"epoch": 0.56,
"learning_rate": 8.648637703194515e-06,
"loss": 0.4707,
"step": 2149
},
{
"epoch": 0.56,
"learning_rate": 8.64032192338694e-06,
"loss": 0.4578,
"step": 2150
},
{
"epoch": 0.56,
"learning_rate": 8.632007101426409e-06,
"loss": 0.4678,
"step": 2151
},
{
"epoch": 0.56,
"learning_rate": 8.62369324317042e-06,
"loss": 0.4653,
"step": 2152
},
{
"epoch": 0.56,
"learning_rate": 8.615380354475812e-06,
"loss": 0.4407,
"step": 2153
},
{
"epoch": 0.56,
"learning_rate": 8.607068441198734e-06,
"loss": 0.4385,
"step": 2154
},
{
"epoch": 0.56,
"learning_rate": 8.598757509194638e-06,
"loss": 0.4343,
"step": 2155
},
{
"epoch": 0.56,
"learning_rate": 8.5904475643183e-06,
"loss": 0.4331,
"step": 2156
},
{
"epoch": 0.56,
"learning_rate": 8.582138612423794e-06,
"loss": 0.437,
"step": 2157
},
{
"epoch": 0.56,
"learning_rate": 8.573830659364495e-06,
"loss": 0.4819,
"step": 2158
},
{
"epoch": 0.56,
"learning_rate": 8.565523710993072e-06,
"loss": 0.4492,
"step": 2159
},
{
"epoch": 0.56,
"learning_rate": 8.557217773161484e-06,
"loss": 0.467,
"step": 2160
},
{
"epoch": 0.56,
"learning_rate": 8.54891285172099e-06,
"loss": 0.4683,
"step": 2161
},
{
"epoch": 0.56,
"learning_rate": 8.540608952522116e-06,
"loss": 0.4465,
"step": 2162
},
{
"epoch": 0.56,
"learning_rate": 8.53230608141469e-06,
"loss": 0.4402,
"step": 2163
},
{
"epoch": 0.56,
"learning_rate": 8.524004244247792e-06,
"loss": 0.4189,
"step": 2164
},
{
"epoch": 0.56,
"learning_rate": 8.515703446869789e-06,
"loss": 0.4521,
"step": 2165
},
{
"epoch": 0.56,
"learning_rate": 8.50740369512831e-06,
"loss": 0.447,
"step": 2166
},
{
"epoch": 0.56,
"learning_rate": 8.499104994870247e-06,
"loss": 0.4502,
"step": 2167
},
{
"epoch": 0.56,
"learning_rate": 8.490807351941753e-06,
"loss": 0.4475,
"step": 2168
},
{
"epoch": 0.56,
"learning_rate": 8.482510772188235e-06,
"loss": 0.4595,
"step": 2169
},
{
"epoch": 0.56,
"learning_rate": 8.474215261454356e-06,
"loss": 0.4507,
"step": 2170
},
{
"epoch": 0.56,
"learning_rate": 8.46592082558402e-06,
"loss": 0.4448,
"step": 2171
},
{
"epoch": 0.56,
"learning_rate": 8.457627470420368e-06,
"loss": 0.4714,
"step": 2172
},
{
"epoch": 0.56,
"learning_rate": 8.449335201805801e-06,
"loss": 0.4531,
"step": 2173
},
{
"epoch": 0.56,
"learning_rate": 8.441044025581926e-06,
"loss": 0.448,
"step": 2174
},
{
"epoch": 0.56,
"learning_rate": 8.432753947589605e-06,
"loss": 0.4324,
"step": 2175
},
{
"epoch": 0.56,
"learning_rate": 8.424464973668912e-06,
"loss": 0.4485,
"step": 2176
},
{
"epoch": 0.56,
"learning_rate": 8.416177109659153e-06,
"loss": 0.4497,
"step": 2177
},
{
"epoch": 0.56,
"learning_rate": 8.40789036139884e-06,
"loss": 0.4263,
"step": 2178
},
{
"epoch": 0.56,
"learning_rate": 8.399604734725707e-06,
"loss": 0.4841,
"step": 2179
},
{
"epoch": 0.56,
"learning_rate": 8.391320235476703e-06,
"loss": 0.4229,
"step": 2180
},
{
"epoch": 0.57,
"learning_rate": 8.383036869487965e-06,
"loss": 0.4497,
"step": 2181
},
{
"epoch": 0.57,
"learning_rate": 8.374754642594856e-06,
"loss": 0.4348,
"step": 2182
},
{
"epoch": 0.57,
"learning_rate": 8.366473560631917e-06,
"loss": 0.4329,
"step": 2183
},
{
"epoch": 0.57,
"learning_rate": 8.358193629432885e-06,
"loss": 0.4199,
"step": 2184
},
{
"epoch": 0.57,
"learning_rate": 8.349914854830701e-06,
"loss": 0.458,
"step": 2185
},
{
"epoch": 0.57,
"learning_rate": 8.34163724265747e-06,
"loss": 0.4399,
"step": 2186
},
{
"epoch": 0.57,
"learning_rate": 8.333360798744496e-06,
"loss": 0.4204,
"step": 2187
},
{
"epoch": 0.57,
"learning_rate": 8.325085528922251e-06,
"loss": 0.436,
"step": 2188
},
{
"epoch": 0.57,
"learning_rate": 8.316811439020378e-06,
"loss": 0.4524,
"step": 2189
},
{
"epoch": 0.57,
"learning_rate": 8.308538534867695e-06,
"loss": 0.4678,
"step": 2190
},
{
"epoch": 0.57,
"learning_rate": 8.300266822292182e-06,
"loss": 0.4553,
"step": 2191
},
{
"epoch": 0.57,
"learning_rate": 8.291996307120982e-06,
"loss": 0.4741,
"step": 2192
},
{
"epoch": 0.57,
"learning_rate": 8.283726995180388e-06,
"loss": 0.4219,
"step": 2193
},
{
"epoch": 0.57,
"learning_rate": 8.275458892295851e-06,
"loss": 0.4575,
"step": 2194
},
{
"epoch": 0.57,
"learning_rate": 8.267192004291973e-06,
"loss": 0.4619,
"step": 2195
},
{
"epoch": 0.57,
"learning_rate": 8.258926336992486e-06,
"loss": 0.4543,
"step": 2196
},
{
"epoch": 0.57,
"learning_rate": 8.250661896220281e-06,
"loss": 0.4346,
"step": 2197
},
{
"epoch": 0.57,
"learning_rate": 8.242398687797372e-06,
"loss": 0.4585,
"step": 2198
},
{
"epoch": 0.57,
"learning_rate": 8.234136717544915e-06,
"loss": 0.4255,
"step": 2199
},
{
"epoch": 0.57,
"learning_rate": 8.225875991283177e-06,
"loss": 0.4641,
"step": 2200
},
{
"epoch": 0.57,
"learning_rate": 8.217616514831563e-06,
"loss": 0.4639,
"step": 2201
},
{
"epoch": 0.57,
"learning_rate": 8.209358294008597e-06,
"loss": 0.458,
"step": 2202
},
{
"epoch": 0.57,
"learning_rate": 8.201101334631912e-06,
"loss": 0.4338,
"step": 2203
},
{
"epoch": 0.57,
"learning_rate": 8.192845642518259e-06,
"loss": 0.4438,
"step": 2204
},
{
"epoch": 0.57,
"learning_rate": 8.184591223483489e-06,
"loss": 0.4153,
"step": 2205
},
{
"epoch": 0.57,
"learning_rate": 8.17633808334256e-06,
"loss": 0.4519,
"step": 2206
},
{
"epoch": 0.57,
"learning_rate": 8.168086227909536e-06,
"loss": 0.4568,
"step": 2207
},
{
"epoch": 0.57,
"learning_rate": 8.159835662997559e-06,
"loss": 0.4531,
"step": 2208
},
{
"epoch": 0.57,
"learning_rate": 8.151586394418876e-06,
"loss": 0.4465,
"step": 2209
},
{
"epoch": 0.57,
"learning_rate": 8.143338427984817e-06,
"loss": 0.4524,
"step": 2210
},
{
"epoch": 0.57,
"learning_rate": 8.135091769505798e-06,
"loss": 0.4453,
"step": 2211
},
{
"epoch": 0.57,
"learning_rate": 8.126846424791303e-06,
"loss": 0.4219,
"step": 2212
},
{
"epoch": 0.57,
"learning_rate": 8.1186023996499e-06,
"loss": 0.4368,
"step": 2213
},
{
"epoch": 0.57,
"learning_rate": 8.110359699889227e-06,
"loss": 0.4668,
"step": 2214
},
{
"epoch": 0.57,
"learning_rate": 8.102118331315983e-06,
"loss": 0.4377,
"step": 2215
},
{
"epoch": 0.57,
"learning_rate": 8.093878299735933e-06,
"loss": 0.4795,
"step": 2216
},
{
"epoch": 0.57,
"learning_rate": 8.085639610953905e-06,
"loss": 0.4358,
"step": 2217
},
{
"epoch": 0.57,
"learning_rate": 8.077402270773764e-06,
"loss": 0.4497,
"step": 2218
},
{
"epoch": 0.58,
"learning_rate": 8.069166284998446e-06,
"loss": 0.4568,
"step": 2219
},
{
"epoch": 0.58,
"learning_rate": 8.060931659429919e-06,
"loss": 0.4402,
"step": 2220
},
{
"epoch": 0.58,
"learning_rate": 8.0526983998692e-06,
"loss": 0.4341,
"step": 2221
},
{
"epoch": 0.58,
"learning_rate": 8.044466512116338e-06,
"loss": 0.4504,
"step": 2222
},
{
"epoch": 0.58,
"learning_rate": 8.036236001970425e-06,
"loss": 0.4568,
"step": 2223
},
{
"epoch": 0.58,
"learning_rate": 8.028006875229566e-06,
"loss": 0.4346,
"step": 2224
},
{
"epoch": 0.58,
"learning_rate": 8.019779137690906e-06,
"loss": 0.4546,
"step": 2225
},
{
"epoch": 0.58,
"learning_rate": 8.01155279515061e-06,
"loss": 0.446,
"step": 2226
},
{
"epoch": 0.58,
"learning_rate": 8.00332785340385e-06,
"loss": 0.478,
"step": 2227
},
{
"epoch": 0.58,
"learning_rate": 7.995104318244824e-06,
"loss": 0.4409,
"step": 2228
},
{
"epoch": 0.58,
"learning_rate": 7.986882195466734e-06,
"loss": 0.4641,
"step": 2229
},
{
"epoch": 0.58,
"learning_rate": 7.978661490861778e-06,
"loss": 0.4478,
"step": 2230
},
{
"epoch": 0.58,
"learning_rate": 7.970442210221173e-06,
"loss": 0.4631,
"step": 2231
},
{
"epoch": 0.58,
"learning_rate": 7.962224359335117e-06,
"loss": 0.4619,
"step": 2232
},
{
"epoch": 0.58,
"learning_rate": 7.954007943992812e-06,
"loss": 0.4446,
"step": 2233
},
{
"epoch": 0.58,
"learning_rate": 7.945792969982437e-06,
"loss": 0.4529,
"step": 2234
},
{
"epoch": 0.58,
"learning_rate": 7.937579443091167e-06,
"loss": 0.4636,
"step": 2235
},
{
"epoch": 0.58,
"learning_rate": 7.929367369105154e-06,
"loss": 0.4424,
"step": 2236
},
{
"epoch": 0.58,
"learning_rate": 7.92115675380952e-06,
"loss": 0.4351,
"step": 2237
},
{
"epoch": 0.58,
"learning_rate": 7.912947602988368e-06,
"loss": 0.438,
"step": 2238
},
{
"epoch": 0.58,
"learning_rate": 7.904739922424764e-06,
"loss": 0.4346,
"step": 2239
},
{
"epoch": 0.58,
"learning_rate": 7.896533717900745e-06,
"loss": 0.4595,
"step": 2240
},
{
"epoch": 0.58,
"learning_rate": 7.888328995197303e-06,
"loss": 0.4517,
"step": 2241
},
{
"epoch": 0.58,
"learning_rate": 7.880125760094378e-06,
"loss": 0.4226,
"step": 2242
},
{
"epoch": 0.58,
"learning_rate": 7.87192401837088e-06,
"loss": 0.4531,
"step": 2243
},
{
"epoch": 0.58,
"learning_rate": 7.863723775804651e-06,
"loss": 0.449,
"step": 2244
},
{
"epoch": 0.58,
"learning_rate": 7.855525038172491e-06,
"loss": 0.4275,
"step": 2245
},
{
"epoch": 0.58,
"learning_rate": 7.847327811250128e-06,
"loss": 0.4409,
"step": 2246
},
{
"epoch": 0.58,
"learning_rate": 7.839132100812225e-06,
"loss": 0.4443,
"step": 2247
},
{
"epoch": 0.58,
"learning_rate": 7.83093791263239e-06,
"loss": 0.4575,
"step": 2248
},
{
"epoch": 0.58,
"learning_rate": 7.822745252483146e-06,
"loss": 0.4565,
"step": 2249
},
{
"epoch": 0.58,
"learning_rate": 7.814554126135944e-06,
"loss": 0.4495,
"step": 2250
},
{
"epoch": 0.58,
"learning_rate": 7.806364539361155e-06,
"loss": 0.4502,
"step": 2251
},
{
"epoch": 0.58,
"learning_rate": 7.79817649792807e-06,
"loss": 0.4482,
"step": 2252
},
{
"epoch": 0.58,
"learning_rate": 7.789990007604878e-06,
"loss": 0.4456,
"step": 2253
},
{
"epoch": 0.58,
"learning_rate": 7.781805074158684e-06,
"loss": 0.4377,
"step": 2254
},
{
"epoch": 0.58,
"learning_rate": 7.773621703355502e-06,
"loss": 0.4612,
"step": 2255
},
{
"epoch": 0.58,
"learning_rate": 7.765439900960234e-06,
"loss": 0.4326,
"step": 2256
},
{
"epoch": 0.58,
"learning_rate": 7.757259672736683e-06,
"loss": 0.4651,
"step": 2257
},
{
"epoch": 0.59,
"learning_rate": 7.749081024447546e-06,
"loss": 0.4324,
"step": 2258
},
{
"epoch": 0.59,
"learning_rate": 7.740903961854391e-06,
"loss": 0.481,
"step": 2259
},
{
"epoch": 0.59,
"learning_rate": 7.732728490717697e-06,
"loss": 0.4668,
"step": 2260
},
{
"epoch": 0.59,
"learning_rate": 7.724554616796793e-06,
"loss": 0.4316,
"step": 2261
},
{
"epoch": 0.59,
"learning_rate": 7.716382345849904e-06,
"loss": 0.4614,
"step": 2262
},
{
"epoch": 0.59,
"learning_rate": 7.708211683634112e-06,
"loss": 0.4595,
"step": 2263
},
{
"epoch": 0.59,
"learning_rate": 7.700042635905376e-06,
"loss": 0.4043,
"step": 2264
},
{
"epoch": 0.59,
"learning_rate": 7.69187520841851e-06,
"loss": 0.448,
"step": 2265
},
{
"epoch": 0.59,
"learning_rate": 7.683709406927185e-06,
"loss": 0.4263,
"step": 2266
},
{
"epoch": 0.59,
"learning_rate": 7.67554523718394e-06,
"loss": 0.4434,
"step": 2267
},
{
"epoch": 0.59,
"learning_rate": 7.667382704940148e-06,
"loss": 0.4377,
"step": 2268
},
{
"epoch": 0.59,
"learning_rate": 7.659221815946039e-06,
"loss": 0.4465,
"step": 2269
},
{
"epoch": 0.59,
"learning_rate": 7.651062575950682e-06,
"loss": 0.4419,
"step": 2270
},
{
"epoch": 0.59,
"learning_rate": 7.642904990701982e-06,
"loss": 0.4458,
"step": 2271
},
{
"epoch": 0.59,
"learning_rate": 7.634749065946686e-06,
"loss": 0.4575,
"step": 2272
},
{
"epoch": 0.59,
"learning_rate": 7.62659480743036e-06,
"loss": 0.4607,
"step": 2273
},
{
"epoch": 0.59,
"learning_rate": 7.618442220897409e-06,
"loss": 0.436,
"step": 2274
},
{
"epoch": 0.59,
"learning_rate": 7.610291312091048e-06,
"loss": 0.4558,
"step": 2275
},
{
"epoch": 0.59,
"learning_rate": 7.6021420867533155e-06,
"loss": 0.4355,
"step": 2276
},
{
"epoch": 0.59,
"learning_rate": 7.59399455062507e-06,
"loss": 0.4539,
"step": 2277
},
{
"epoch": 0.59,
"learning_rate": 7.585848709445962e-06,
"loss": 0.4475,
"step": 2278
},
{
"epoch": 0.59,
"learning_rate": 7.577704568954476e-06,
"loss": 0.4299,
"step": 2279
},
{
"epoch": 0.59,
"learning_rate": 7.569562134887869e-06,
"loss": 0.4531,
"step": 2280
},
{
"epoch": 0.59,
"learning_rate": 7.561421412982217e-06,
"loss": 0.4631,
"step": 2281
},
{
"epoch": 0.59,
"learning_rate": 7.553282408972382e-06,
"loss": 0.4438,
"step": 2282
},
{
"epoch": 0.59,
"learning_rate": 7.545145128592009e-06,
"loss": 0.4263,
"step": 2283
},
{
"epoch": 0.59,
"learning_rate": 7.537009577573544e-06,
"loss": 0.4871,
"step": 2284
},
{
"epoch": 0.59,
"learning_rate": 7.528875761648199e-06,
"loss": 0.429,
"step": 2285
},
{
"epoch": 0.59,
"learning_rate": 7.520743686545981e-06,
"loss": 0.4316,
"step": 2286
},
{
"epoch": 0.59,
"learning_rate": 7.512613357995652e-06,
"loss": 0.4412,
"step": 2287
},
{
"epoch": 0.59,
"learning_rate": 7.504484781724752e-06,
"loss": 0.4319,
"step": 2288
},
{
"epoch": 0.59,
"learning_rate": 7.496357963459595e-06,
"loss": 0.447,
"step": 2289
},
{
"epoch": 0.59,
"learning_rate": 7.488232908925241e-06,
"loss": 0.4519,
"step": 2290
},
{
"epoch": 0.59,
"learning_rate": 7.48010962384552e-06,
"loss": 0.4465,
"step": 2291
},
{
"epoch": 0.59,
"learning_rate": 7.471988113943005e-06,
"loss": 0.4553,
"step": 2292
},
{
"epoch": 0.59,
"learning_rate": 7.463868384939031e-06,
"loss": 0.4312,
"step": 2293
},
{
"epoch": 0.59,
"learning_rate": 7.455750442553667e-06,
"loss": 0.4438,
"step": 2294
},
{
"epoch": 0.59,
"learning_rate": 7.447634292505725e-06,
"loss": 0.4678,
"step": 2295
},
{
"epoch": 0.59,
"learning_rate": 7.439519940512766e-06,
"loss": 0.4517,
"step": 2296
},
{
"epoch": 0.6,
"learning_rate": 7.431407392291064e-06,
"loss": 0.4551,
"step": 2297
},
{
"epoch": 0.6,
"learning_rate": 7.423296653555645e-06,
"loss": 0.438,
"step": 2298
},
{
"epoch": 0.6,
"learning_rate": 7.415187730020242e-06,
"loss": 0.4629,
"step": 2299
},
{
"epoch": 0.6,
"learning_rate": 7.407080627397316e-06,
"loss": 0.4644,
"step": 2300
},
{
"epoch": 0.6,
"learning_rate": 7.398975351398054e-06,
"loss": 0.4185,
"step": 2301
},
{
"epoch": 0.6,
"learning_rate": 7.390871907732335e-06,
"loss": 0.4819,
"step": 2302
},
{
"epoch": 0.6,
"learning_rate": 7.382770302108768e-06,
"loss": 0.4546,
"step": 2303
},
{
"epoch": 0.6,
"learning_rate": 7.3746705402346605e-06,
"loss": 0.4353,
"step": 2304
},
{
"epoch": 0.6,
"learning_rate": 7.3665726278160136e-06,
"loss": 0.4536,
"step": 2305
},
{
"epoch": 0.6,
"learning_rate": 7.358476570557536e-06,
"loss": 0.4426,
"step": 2306
},
{
"epoch": 0.6,
"learning_rate": 7.350382374162622e-06,
"loss": 0.4424,
"step": 2307
},
{
"epoch": 0.6,
"learning_rate": 7.342290044333362e-06,
"loss": 0.4421,
"step": 2308
},
{
"epoch": 0.6,
"learning_rate": 7.334199586770524e-06,
"loss": 0.4436,
"step": 2309
},
{
"epoch": 0.6,
"learning_rate": 7.3261110071735645e-06,
"loss": 0.4363,
"step": 2310
},
{
"epoch": 0.6,
"learning_rate": 7.3180243112406106e-06,
"loss": 0.4495,
"step": 2311
},
{
"epoch": 0.6,
"learning_rate": 7.3099395046684626e-06,
"loss": 0.4353,
"step": 2312
},
{
"epoch": 0.6,
"learning_rate": 7.301856593152596e-06,
"loss": 0.4419,
"step": 2313
},
{
"epoch": 0.6,
"learning_rate": 7.293775582387146e-06,
"loss": 0.4609,
"step": 2314
},
{
"epoch": 0.6,
"learning_rate": 7.285696478064915e-06,
"loss": 0.4592,
"step": 2315
},
{
"epoch": 0.6,
"learning_rate": 7.277619285877351e-06,
"loss": 0.4275,
"step": 2316
},
{
"epoch": 0.6,
"learning_rate": 7.26954401151456e-06,
"loss": 0.4285,
"step": 2317
},
{
"epoch": 0.6,
"learning_rate": 7.261470660665306e-06,
"loss": 0.4414,
"step": 2318
},
{
"epoch": 0.6,
"learning_rate": 7.253399239016986e-06,
"loss": 0.425,
"step": 2319
},
{
"epoch": 0.6,
"learning_rate": 7.2453297522556475e-06,
"loss": 0.4512,
"step": 2320
},
{
"epoch": 0.6,
"learning_rate": 7.237262206065962e-06,
"loss": 0.4531,
"step": 2321
},
{
"epoch": 0.6,
"learning_rate": 7.229196606131248e-06,
"loss": 0.437,
"step": 2322
},
{
"epoch": 0.6,
"learning_rate": 7.221132958133446e-06,
"loss": 0.4148,
"step": 2323
},
{
"epoch": 0.6,
"learning_rate": 7.213071267753118e-06,
"loss": 0.4365,
"step": 2324
},
{
"epoch": 0.6,
"learning_rate": 7.2050115406694554e-06,
"loss": 0.4612,
"step": 2325
},
{
"epoch": 0.6,
"learning_rate": 7.19695378256026e-06,
"loss": 0.4365,
"step": 2326
},
{
"epoch": 0.6,
"learning_rate": 7.188897999101954e-06,
"loss": 0.4417,
"step": 2327
},
{
"epoch": 0.6,
"learning_rate": 7.1808441959695565e-06,
"loss": 0.4441,
"step": 2328
},
{
"epoch": 0.6,
"learning_rate": 7.1727923788366986e-06,
"loss": 0.4485,
"step": 2329
},
{
"epoch": 0.6,
"learning_rate": 7.164742553375618e-06,
"loss": 0.4363,
"step": 2330
},
{
"epoch": 0.6,
"learning_rate": 7.156694725257137e-06,
"loss": 0.4275,
"step": 2331
},
{
"epoch": 0.6,
"learning_rate": 7.148648900150682e-06,
"loss": 0.4358,
"step": 2332
},
{
"epoch": 0.6,
"learning_rate": 7.140605083724264e-06,
"loss": 0.4377,
"step": 2333
},
{
"epoch": 0.6,
"learning_rate": 7.132563281644471e-06,
"loss": 0.4443,
"step": 2334
},
{
"epoch": 0.61,
"learning_rate": 7.124523499576488e-06,
"loss": 0.4348,
"step": 2335
},
{
"epoch": 0.61,
"learning_rate": 7.116485743184063e-06,
"loss": 0.4395,
"step": 2336
},
{
"epoch": 0.61,
"learning_rate": 7.108450018129527e-06,
"loss": 0.4641,
"step": 2337
},
{
"epoch": 0.61,
"learning_rate": 7.100416330073772e-06,
"loss": 0.4543,
"step": 2338
},
{
"epoch": 0.61,
"learning_rate": 7.092384684676263e-06,
"loss": 0.4565,
"step": 2339
},
{
"epoch": 0.61,
"learning_rate": 7.084355087595015e-06,
"loss": 0.4424,
"step": 2340
},
{
"epoch": 0.61,
"learning_rate": 7.076327544486607e-06,
"loss": 0.4539,
"step": 2341
},
{
"epoch": 0.61,
"learning_rate": 7.06830206100618e-06,
"loss": 0.4316,
"step": 2342
},
{
"epoch": 0.61,
"learning_rate": 7.060278642807402e-06,
"loss": 0.4565,
"step": 2343
},
{
"epoch": 0.61,
"learning_rate": 7.052257295542508e-06,
"loss": 0.4302,
"step": 2344
},
{
"epoch": 0.61,
"learning_rate": 7.044238024862262e-06,
"loss": 0.4438,
"step": 2345
},
{
"epoch": 0.61,
"learning_rate": 7.036220836415964e-06,
"loss": 0.437,
"step": 2346
},
{
"epoch": 0.61,
"learning_rate": 7.0282057358514545e-06,
"loss": 0.4458,
"step": 2347
},
{
"epoch": 0.61,
"learning_rate": 7.020192728815098e-06,
"loss": 0.458,
"step": 2348
},
{
"epoch": 0.61,
"learning_rate": 7.012181820951793e-06,
"loss": 0.4458,
"step": 2349
},
{
"epoch": 0.61,
"learning_rate": 7.004173017904941e-06,
"loss": 0.4348,
"step": 2350
},
{
"epoch": 0.61,
"learning_rate": 6.99616632531648e-06,
"loss": 0.4233,
"step": 2351
},
{
"epoch": 0.61,
"learning_rate": 6.9881617488268516e-06,
"loss": 0.4543,
"step": 2352
},
{
"epoch": 0.61,
"learning_rate": 6.980159294075004e-06,
"loss": 0.4402,
"step": 2353
},
{
"epoch": 0.61,
"learning_rate": 6.972158966698399e-06,
"loss": 0.4609,
"step": 2354
},
{
"epoch": 0.61,
"learning_rate": 6.96416077233299e-06,
"loss": 0.4209,
"step": 2355
},
{
"epoch": 0.61,
"learning_rate": 6.956164716613243e-06,
"loss": 0.4375,
"step": 2356
},
{
"epoch": 0.61,
"learning_rate": 6.948170805172103e-06,
"loss": 0.4309,
"step": 2357
},
{
"epoch": 0.61,
"learning_rate": 6.940179043641005e-06,
"loss": 0.4648,
"step": 2358
},
{
"epoch": 0.61,
"learning_rate": 6.932189437649879e-06,
"loss": 0.4326,
"step": 2359
},
{
"epoch": 0.61,
"learning_rate": 6.924201992827129e-06,
"loss": 0.4453,
"step": 2360
},
{
"epoch": 0.61,
"learning_rate": 6.916216714799641e-06,
"loss": 0.4548,
"step": 2361
},
{
"epoch": 0.61,
"learning_rate": 6.908233609192769e-06,
"loss": 0.4246,
"step": 2362
},
{
"epoch": 0.61,
"learning_rate": 6.900252681630339e-06,
"loss": 0.4497,
"step": 2363
},
{
"epoch": 0.61,
"learning_rate": 6.892273937734649e-06,
"loss": 0.4407,
"step": 2364
},
{
"epoch": 0.61,
"learning_rate": 6.884297383126446e-06,
"loss": 0.4385,
"step": 2365
},
{
"epoch": 0.61,
"learning_rate": 6.876323023424949e-06,
"loss": 0.4241,
"step": 2366
},
{
"epoch": 0.61,
"learning_rate": 6.868350864247817e-06,
"loss": 0.4175,
"step": 2367
},
{
"epoch": 0.61,
"learning_rate": 6.860380911211173e-06,
"loss": 0.4478,
"step": 2368
},
{
"epoch": 0.61,
"learning_rate": 6.8524131699295725e-06,
"loss": 0.4377,
"step": 2369
},
{
"epoch": 0.61,
"learning_rate": 6.844447646016017e-06,
"loss": 0.4473,
"step": 2370
},
{
"epoch": 0.61,
"learning_rate": 6.836484345081956e-06,
"loss": 0.4326,
"step": 2371
},
{
"epoch": 0.61,
"learning_rate": 6.8285232727372554e-06,
"loss": 0.4529,
"step": 2372
},
{
"epoch": 0.61,
"learning_rate": 6.820564434590227e-06,
"loss": 0.4224,
"step": 2373
},
{
"epoch": 0.62,
"learning_rate": 6.8126078362476e-06,
"loss": 0.4395,
"step": 2374
},
{
"epoch": 0.62,
"learning_rate": 6.804653483314523e-06,
"loss": 0.4187,
"step": 2375
},
{
"epoch": 0.62,
"learning_rate": 6.796701381394577e-06,
"loss": 0.4338,
"step": 2376
},
{
"epoch": 0.62,
"learning_rate": 6.788751536089739e-06,
"loss": 0.4158,
"step": 2377
},
{
"epoch": 0.62,
"learning_rate": 6.78080395300041e-06,
"loss": 0.4409,
"step": 2378
},
{
"epoch": 0.62,
"learning_rate": 6.77285863772539e-06,
"loss": 0.4348,
"step": 2379
},
{
"epoch": 0.62,
"learning_rate": 6.764915595861888e-06,
"loss": 0.438,
"step": 2380
},
{
"epoch": 0.62,
"learning_rate": 6.756974833005503e-06,
"loss": 0.4519,
"step": 2381
},
{
"epoch": 0.62,
"learning_rate": 6.749036354750231e-06,
"loss": 0.4421,
"step": 2382
},
{
"epoch": 0.62,
"learning_rate": 6.74110016668847e-06,
"loss": 0.408,
"step": 2383
},
{
"epoch": 0.62,
"learning_rate": 6.7331662744109825e-06,
"loss": 0.4434,
"step": 2384
},
{
"epoch": 0.62,
"learning_rate": 6.725234683506934e-06,
"loss": 0.4529,
"step": 2385
},
{
"epoch": 0.62,
"learning_rate": 6.717305399563863e-06,
"loss": 0.4446,
"step": 2386
},
{
"epoch": 0.62,
"learning_rate": 6.7093784281676725e-06,
"loss": 0.4224,
"step": 2387
},
{
"epoch": 0.62,
"learning_rate": 6.7014537749026495e-06,
"loss": 0.4387,
"step": 2388
},
{
"epoch": 0.62,
"learning_rate": 6.6935314453514424e-06,
"loss": 0.4434,
"step": 2389
},
{
"epoch": 0.62,
"learning_rate": 6.6856114450950675e-06,
"loss": 0.4351,
"step": 2390
},
{
"epoch": 0.62,
"learning_rate": 6.67769377971289e-06,
"loss": 0.457,
"step": 2391
},
{
"epoch": 0.62,
"learning_rate": 6.6697784547826365e-06,
"loss": 0.4414,
"step": 2392
},
{
"epoch": 0.62,
"learning_rate": 6.6618654758803916e-06,
"loss": 0.4333,
"step": 2393
},
{
"epoch": 0.62,
"learning_rate": 6.65395484858057e-06,
"loss": 0.4395,
"step": 2394
},
{
"epoch": 0.62,
"learning_rate": 6.646046578455952e-06,
"loss": 0.4595,
"step": 2395
},
{
"epoch": 0.62,
"learning_rate": 6.638140671077633e-06,
"loss": 0.4331,
"step": 2396
},
{
"epoch": 0.62,
"learning_rate": 6.6302371320150646e-06,
"loss": 0.4446,
"step": 2397
},
{
"epoch": 0.62,
"learning_rate": 6.622335966836022e-06,
"loss": 0.4382,
"step": 2398
},
{
"epoch": 0.62,
"learning_rate": 6.6144371811066015e-06,
"loss": 0.4377,
"step": 2399
},
{
"epoch": 0.62,
"learning_rate": 6.6065407803912355e-06,
"loss": 0.4314,
"step": 2400
},
{
"epoch": 0.62,
"learning_rate": 6.598646770252664e-06,
"loss": 0.4373,
"step": 2401
},
{
"epoch": 0.62,
"learning_rate": 6.590755156251958e-06,
"loss": 0.4619,
"step": 2402
},
{
"epoch": 0.62,
"learning_rate": 6.5828659439484845e-06,
"loss": 0.4434,
"step": 2403
},
{
"epoch": 0.62,
"learning_rate": 6.574979138899926e-06,
"loss": 0.4397,
"step": 2404
},
{
"epoch": 0.62,
"learning_rate": 6.567094746662275e-06,
"loss": 0.459,
"step": 2405
},
{
"epoch": 0.62,
"learning_rate": 6.559212772789808e-06,
"loss": 0.4475,
"step": 2406
},
{
"epoch": 0.62,
"learning_rate": 6.551333222835117e-06,
"loss": 0.4609,
"step": 2407
},
{
"epoch": 0.62,
"learning_rate": 6.543456102349072e-06,
"loss": 0.4351,
"step": 2408
},
{
"epoch": 0.62,
"learning_rate": 6.535581416880843e-06,
"loss": 0.4397,
"step": 2409
},
{
"epoch": 0.62,
"learning_rate": 6.527709171977872e-06,
"loss": 0.4507,
"step": 2410
},
{
"epoch": 0.62,
"learning_rate": 6.519839373185889e-06,
"loss": 0.4343,
"step": 2411
},
{
"epoch": 0.63,
"learning_rate": 6.5119720260489064e-06,
"loss": 0.4448,
"step": 2412
},
{
"epoch": 0.63,
"learning_rate": 6.5041071361091925e-06,
"loss": 0.4417,
"step": 2413
},
{
"epoch": 0.63,
"learning_rate": 6.496244708907307e-06,
"loss": 0.4561,
"step": 2414
},
{
"epoch": 0.63,
"learning_rate": 6.488384749982054e-06,
"loss": 0.4373,
"step": 2415
},
{
"epoch": 0.63,
"learning_rate": 6.48052726487051e-06,
"loss": 0.4253,
"step": 2416
},
{
"epoch": 0.63,
"learning_rate": 6.472672259108011e-06,
"loss": 0.4006,
"step": 2417
},
{
"epoch": 0.63,
"learning_rate": 6.4648197382281345e-06,
"loss": 0.4397,
"step": 2418
},
{
"epoch": 0.63,
"learning_rate": 6.456969707762721e-06,
"loss": 0.4456,
"step": 2419
},
{
"epoch": 0.63,
"learning_rate": 6.449122173241849e-06,
"loss": 0.4336,
"step": 2420
},
{
"epoch": 0.63,
"learning_rate": 6.441277140193836e-06,
"loss": 0.4377,
"step": 2421
},
{
"epoch": 0.63,
"learning_rate": 6.433434614145244e-06,
"loss": 0.4329,
"step": 2422
},
{
"epoch": 0.63,
"learning_rate": 6.425594600620868e-06,
"loss": 0.4414,
"step": 2423
},
{
"epoch": 0.63,
"learning_rate": 6.417757105143732e-06,
"loss": 0.4573,
"step": 2424
},
{
"epoch": 0.63,
"learning_rate": 6.40992213323508e-06,
"loss": 0.4697,
"step": 2425
},
{
"epoch": 0.63,
"learning_rate": 6.40208969041439e-06,
"loss": 0.4053,
"step": 2426
},
{
"epoch": 0.63,
"learning_rate": 6.39425978219935e-06,
"loss": 0.4539,
"step": 2427
},
{
"epoch": 0.63,
"learning_rate": 6.386432414105861e-06,
"loss": 0.4421,
"step": 2428
},
{
"epoch": 0.63,
"learning_rate": 6.378607591648042e-06,
"loss": 0.4495,
"step": 2429
},
{
"epoch": 0.63,
"learning_rate": 6.370785320338211e-06,
"loss": 0.4294,
"step": 2430
},
{
"epoch": 0.63,
"learning_rate": 6.3629656056869e-06,
"loss": 0.415,
"step": 2431
},
{
"epoch": 0.63,
"learning_rate": 6.355148453202826e-06,
"loss": 0.4294,
"step": 2432
},
{
"epoch": 0.63,
"learning_rate": 6.347333868392906e-06,
"loss": 0.4644,
"step": 2433
},
{
"epoch": 0.63,
"learning_rate": 6.339521856762254e-06,
"loss": 0.4211,
"step": 2434
},
{
"epoch": 0.63,
"learning_rate": 6.331712423814164e-06,
"loss": 0.4509,
"step": 2435
},
{
"epoch": 0.63,
"learning_rate": 6.323905575050124e-06,
"loss": 0.4482,
"step": 2436
},
{
"epoch": 0.63,
"learning_rate": 6.316101315969783e-06,
"loss": 0.428,
"step": 2437
},
{
"epoch": 0.63,
"learning_rate": 6.308299652070982e-06,
"loss": 0.4446,
"step": 2438
},
{
"epoch": 0.63,
"learning_rate": 6.300500588849729e-06,
"loss": 0.4434,
"step": 2439
},
{
"epoch": 0.63,
"learning_rate": 6.292704131800196e-06,
"loss": 0.4541,
"step": 2440
},
{
"epoch": 0.63,
"learning_rate": 6.284910286414726e-06,
"loss": 0.4121,
"step": 2441
},
{
"epoch": 0.63,
"learning_rate": 6.277119058183814e-06,
"loss": 0.4395,
"step": 2442
},
{
"epoch": 0.63,
"learning_rate": 6.269330452596123e-06,
"loss": 0.4177,
"step": 2443
},
{
"epoch": 0.63,
"learning_rate": 6.261544475138455e-06,
"loss": 0.4285,
"step": 2444
},
{
"epoch": 0.63,
"learning_rate": 6.2537611312957635e-06,
"loss": 0.4475,
"step": 2445
},
{
"epoch": 0.63,
"learning_rate": 6.245980426551162e-06,
"loss": 0.4578,
"step": 2446
},
{
"epoch": 0.63,
"learning_rate": 6.2382023663858796e-06,
"loss": 0.4143,
"step": 2447
},
{
"epoch": 0.63,
"learning_rate": 6.230426956279305e-06,
"loss": 0.428,
"step": 2448
},
{
"epoch": 0.63,
"learning_rate": 6.222654201708949e-06,
"loss": 0.4265,
"step": 2449
},
{
"epoch": 0.63,
"learning_rate": 6.2148841081504465e-06,
"loss": 0.4182,
"step": 2450
},
{
"epoch": 0.64,
"learning_rate": 6.207116681077572e-06,
"loss": 0.4763,
"step": 2451
},
{
"epoch": 0.64,
"learning_rate": 6.199351925962209e-06,
"loss": 0.4441,
"step": 2452
},
{
"epoch": 0.64,
"learning_rate": 6.191589848274369e-06,
"loss": 0.4529,
"step": 2453
},
{
"epoch": 0.64,
"learning_rate": 6.183830453482168e-06,
"loss": 0.4316,
"step": 2454
},
{
"epoch": 0.64,
"learning_rate": 6.176073747051842e-06,
"loss": 0.437,
"step": 2455
},
{
"epoch": 0.64,
"learning_rate": 6.168319734447721e-06,
"loss": 0.448,
"step": 2456
},
{
"epoch": 0.64,
"learning_rate": 6.1605684211322435e-06,
"loss": 0.4541,
"step": 2457
},
{
"epoch": 0.64,
"learning_rate": 6.152819812565954e-06,
"loss": 0.4465,
"step": 2458
},
{
"epoch": 0.64,
"learning_rate": 6.145073914207473e-06,
"loss": 0.4546,
"step": 2459
},
{
"epoch": 0.64,
"learning_rate": 6.137330731513531e-06,
"loss": 0.4358,
"step": 2460
},
{
"epoch": 0.64,
"learning_rate": 6.1295902699389385e-06,
"loss": 0.4316,
"step": 2461
},
{
"epoch": 0.64,
"learning_rate": 6.12185253493658e-06,
"loss": 0.4321,
"step": 2462
},
{
"epoch": 0.64,
"learning_rate": 6.114117531957433e-06,
"loss": 0.4368,
"step": 2463
},
{
"epoch": 0.64,
"learning_rate": 6.106385266450542e-06,
"loss": 0.4531,
"step": 2464
},
{
"epoch": 0.64,
"learning_rate": 6.09865574386303e-06,
"loss": 0.4385,
"step": 2465
},
{
"epoch": 0.64,
"learning_rate": 6.090928969640076e-06,
"loss": 0.4434,
"step": 2466
},
{
"epoch": 0.64,
"learning_rate": 6.083204949224936e-06,
"loss": 0.4468,
"step": 2467
},
{
"epoch": 0.64,
"learning_rate": 6.0754836880589186e-06,
"loss": 0.4399,
"step": 2468
},
{
"epoch": 0.64,
"learning_rate": 6.0677651915813875e-06,
"loss": 0.4397,
"step": 2469
},
{
"epoch": 0.64,
"learning_rate": 6.060049465229765e-06,
"loss": 0.425,
"step": 2470
},
{
"epoch": 0.64,
"learning_rate": 6.052336514439513e-06,
"loss": 0.4231,
"step": 2471
},
{
"epoch": 0.64,
"learning_rate": 6.044626344644151e-06,
"loss": 0.426,
"step": 2472
},
{
"epoch": 0.64,
"learning_rate": 6.036918961275229e-06,
"loss": 0.4382,
"step": 2473
},
{
"epoch": 0.64,
"learning_rate": 6.029214369762332e-06,
"loss": 0.4241,
"step": 2474
},
{
"epoch": 0.64,
"learning_rate": 6.021512575533088e-06,
"loss": 0.4309,
"step": 2475
},
{
"epoch": 0.64,
"learning_rate": 6.0138135840131486e-06,
"loss": 0.4351,
"step": 2476
},
{
"epoch": 0.64,
"learning_rate": 6.006117400626195e-06,
"loss": 0.4248,
"step": 2477
},
{
"epoch": 0.64,
"learning_rate": 5.998424030793922e-06,
"loss": 0.4136,
"step": 2478
},
{
"epoch": 0.64,
"learning_rate": 5.990733479936046e-06,
"loss": 0.438,
"step": 2479
},
{
"epoch": 0.64,
"learning_rate": 5.983045753470308e-06,
"loss": 0.4414,
"step": 2480
},
{
"epoch": 0.64,
"learning_rate": 5.97536085681244e-06,
"loss": 0.4287,
"step": 2481
},
{
"epoch": 0.64,
"learning_rate": 5.967678795376197e-06,
"loss": 0.4395,
"step": 2482
},
{
"epoch": 0.64,
"learning_rate": 5.959999574573328e-06,
"loss": 0.4641,
"step": 2483
},
{
"epoch": 0.64,
"learning_rate": 5.952323199813587e-06,
"loss": 0.459,
"step": 2484
},
{
"epoch": 0.64,
"learning_rate": 5.944649676504715e-06,
"loss": 0.4304,
"step": 2485
},
{
"epoch": 0.64,
"learning_rate": 5.936979010052446e-06,
"loss": 0.4329,
"step": 2486
},
{
"epoch": 0.64,
"learning_rate": 5.929311205860515e-06,
"loss": 0.4397,
"step": 2487
},
{
"epoch": 0.64,
"learning_rate": 5.921646269330617e-06,
"loss": 0.4353,
"step": 2488
},
{
"epoch": 0.64,
"learning_rate": 5.913984205862449e-06,
"loss": 0.4546,
"step": 2489
},
{
"epoch": 0.65,
"learning_rate": 5.906325020853671e-06,
"loss": 0.4414,
"step": 2490
},
{
"epoch": 0.65,
"learning_rate": 5.898668719699914e-06,
"loss": 0.4236,
"step": 2491
},
{
"epoch": 0.65,
"learning_rate": 5.891015307794792e-06,
"loss": 0.4617,
"step": 2492
},
{
"epoch": 0.65,
"learning_rate": 5.8833647905298655e-06,
"loss": 0.4343,
"step": 2493
},
{
"epoch": 0.65,
"learning_rate": 5.875717173294668e-06,
"loss": 0.4546,
"step": 2494
},
{
"epoch": 0.65,
"learning_rate": 5.868072461476686e-06,
"loss": 0.4282,
"step": 2495
},
{
"epoch": 0.65,
"learning_rate": 5.860430660461361e-06,
"loss": 0.4116,
"step": 2496
},
{
"epoch": 0.65,
"learning_rate": 5.8527917756320785e-06,
"loss": 0.4197,
"step": 2497
},
{
"epoch": 0.65,
"learning_rate": 5.8451558123701735e-06,
"loss": 0.438,
"step": 2498
},
{
"epoch": 0.65,
"learning_rate": 5.837522776054929e-06,
"loss": 0.4448,
"step": 2499
},
{
"epoch": 0.65,
"learning_rate": 5.829892672063552e-06,
"loss": 0.4272,
"step": 2500
},
{
"epoch": 0.65,
"learning_rate": 5.822265505771199e-06,
"loss": 0.4451,
"step": 2501
},
{
"epoch": 0.65,
"learning_rate": 5.814641282550941e-06,
"loss": 0.4124,
"step": 2502
},
{
"epoch": 0.65,
"learning_rate": 5.807020007773789e-06,
"loss": 0.415,
"step": 2503
},
{
"epoch": 0.65,
"learning_rate": 5.799401686808678e-06,
"loss": 0.4297,
"step": 2504
},
{
"epoch": 0.65,
"learning_rate": 5.791786325022446e-06,
"loss": 0.4341,
"step": 2505
},
{
"epoch": 0.65,
"learning_rate": 5.784173927779866e-06,
"loss": 0.4348,
"step": 2506
},
{
"epoch": 0.65,
"learning_rate": 5.77656450044361e-06,
"loss": 0.4456,
"step": 2507
},
{
"epoch": 0.65,
"learning_rate": 5.768958048374256e-06,
"loss": 0.4138,
"step": 2508
},
{
"epoch": 0.65,
"learning_rate": 5.761354576930296e-06,
"loss": 0.4297,
"step": 2509
},
{
"epoch": 0.65,
"learning_rate": 5.753754091468116e-06,
"loss": 0.4417,
"step": 2510
},
{
"epoch": 0.65,
"learning_rate": 5.746156597342005e-06,
"loss": 0.4517,
"step": 2511
},
{
"epoch": 0.65,
"learning_rate": 5.7385620999041325e-06,
"loss": 0.4446,
"step": 2512
},
{
"epoch": 0.65,
"learning_rate": 5.730970604504571e-06,
"loss": 0.4253,
"step": 2513
},
{
"epoch": 0.65,
"learning_rate": 5.723382116491264e-06,
"loss": 0.4392,
"step": 2514
},
{
"epoch": 0.65,
"learning_rate": 5.715796641210048e-06,
"loss": 0.4216,
"step": 2515
},
{
"epoch": 0.65,
"learning_rate": 5.708214184004634e-06,
"loss": 0.4316,
"step": 2516
},
{
"epoch": 0.65,
"learning_rate": 5.7006347502166e-06,
"loss": 0.4419,
"step": 2517
},
{
"epoch": 0.65,
"learning_rate": 5.693058345185407e-06,
"loss": 0.4204,
"step": 2518
},
{
"epoch": 0.65,
"learning_rate": 5.685484974248372e-06,
"loss": 0.4341,
"step": 2519
},
{
"epoch": 0.65,
"learning_rate": 5.677914642740674e-06,
"loss": 0.4507,
"step": 2520
},
{
"epoch": 0.65,
"learning_rate": 5.670347355995356e-06,
"loss": 0.4458,
"step": 2521
},
{
"epoch": 0.65,
"learning_rate": 5.662783119343318e-06,
"loss": 0.4421,
"step": 2522
},
{
"epoch": 0.65,
"learning_rate": 5.655221938113309e-06,
"loss": 0.4556,
"step": 2523
},
{
"epoch": 0.65,
"learning_rate": 5.647663817631917e-06,
"loss": 0.4424,
"step": 2524
},
{
"epoch": 0.65,
"learning_rate": 5.6401087632235906e-06,
"loss": 0.4268,
"step": 2525
},
{
"epoch": 0.65,
"learning_rate": 5.632556780210604e-06,
"loss": 0.4417,
"step": 2526
},
{
"epoch": 0.65,
"learning_rate": 5.625007873913069e-06,
"loss": 0.4182,
"step": 2527
},
{
"epoch": 0.66,
"learning_rate": 5.617462049648938e-06,
"loss": 0.4229,
"step": 2528
},
{
"epoch": 0.66,
"learning_rate": 5.609919312733987e-06,
"loss": 0.4236,
"step": 2529
},
{
"epoch": 0.66,
"learning_rate": 5.602379668481823e-06,
"loss": 0.4553,
"step": 2530
},
{
"epoch": 0.66,
"learning_rate": 5.594843122203867e-06,
"loss": 0.446,
"step": 2531
},
{
"epoch": 0.66,
"learning_rate": 5.587309679209353e-06,
"loss": 0.4373,
"step": 2532
},
{
"epoch": 0.66,
"learning_rate": 5.57977934480534e-06,
"loss": 0.4475,
"step": 2533
},
{
"epoch": 0.66,
"learning_rate": 5.572252124296696e-06,
"loss": 0.4458,
"step": 2534
},
{
"epoch": 0.66,
"learning_rate": 5.5647280229860925e-06,
"loss": 0.4434,
"step": 2535
},
{
"epoch": 0.66,
"learning_rate": 5.557207046174002e-06,
"loss": 0.4531,
"step": 2536
},
{
"epoch": 0.66,
"learning_rate": 5.549689199158692e-06,
"loss": 0.4451,
"step": 2537
},
{
"epoch": 0.66,
"learning_rate": 5.542174487236238e-06,
"loss": 0.4604,
"step": 2538
},
{
"epoch": 0.66,
"learning_rate": 5.534662915700494e-06,
"loss": 0.4368,
"step": 2539
},
{
"epoch": 0.66,
"learning_rate": 5.527154489843108e-06,
"loss": 0.4136,
"step": 2540
},
{
"epoch": 0.66,
"learning_rate": 5.519649214953513e-06,
"loss": 0.4446,
"step": 2541
},
{
"epoch": 0.66,
"learning_rate": 5.512147096318924e-06,
"loss": 0.4609,
"step": 2542
},
{
"epoch": 0.66,
"learning_rate": 5.504648139224325e-06,
"loss": 0.4412,
"step": 2543
},
{
"epoch": 0.66,
"learning_rate": 5.49715234895247e-06,
"loss": 0.4441,
"step": 2544
},
{
"epoch": 0.66,
"learning_rate": 5.489659730783901e-06,
"loss": 0.4207,
"step": 2545
},
{
"epoch": 0.66,
"learning_rate": 5.482170289996902e-06,
"loss": 0.4709,
"step": 2546
},
{
"epoch": 0.66,
"learning_rate": 5.474684031867535e-06,
"loss": 0.4663,
"step": 2547
},
{
"epoch": 0.66,
"learning_rate": 5.467200961669619e-06,
"loss": 0.4199,
"step": 2548
},
{
"epoch": 0.66,
"learning_rate": 5.459721084674714e-06,
"loss": 0.4236,
"step": 2549
},
{
"epoch": 0.66,
"learning_rate": 5.452244406152147e-06,
"loss": 0.4253,
"step": 2550
},
{
"epoch": 0.66,
"learning_rate": 5.444770931368978e-06,
"loss": 0.418,
"step": 2551
},
{
"epoch": 0.66,
"learning_rate": 5.437300665590018e-06,
"loss": 0.4272,
"step": 2552
},
{
"epoch": 0.66,
"learning_rate": 5.429833614077817e-06,
"loss": 0.4324,
"step": 2553
},
{
"epoch": 0.66,
"learning_rate": 5.4223697820926635e-06,
"loss": 0.4314,
"step": 2554
},
{
"epoch": 0.66,
"learning_rate": 5.414909174892569e-06,
"loss": 0.4517,
"step": 2555
},
{
"epoch": 0.66,
"learning_rate": 5.407451797733274e-06,
"loss": 0.4675,
"step": 2556
},
{
"epoch": 0.66,
"learning_rate": 5.399997655868256e-06,
"loss": 0.4336,
"step": 2557
},
{
"epoch": 0.66,
"learning_rate": 5.392546754548696e-06,
"loss": 0.4536,
"step": 2558
},
{
"epoch": 0.66,
"learning_rate": 5.385099099023504e-06,
"loss": 0.4424,
"step": 2559
},
{
"epoch": 0.66,
"learning_rate": 5.377654694539307e-06,
"loss": 0.4277,
"step": 2560
},
{
"epoch": 0.66,
"learning_rate": 5.370213546340427e-06,
"loss": 0.4556,
"step": 2561
},
{
"epoch": 0.66,
"learning_rate": 5.362775659668907e-06,
"loss": 0.4363,
"step": 2562
},
{
"epoch": 0.66,
"learning_rate": 5.3553410397644766e-06,
"loss": 0.415,
"step": 2563
},
{
"epoch": 0.66,
"learning_rate": 5.347909691864583e-06,
"loss": 0.4487,
"step": 2564
},
{
"epoch": 0.66,
"learning_rate": 5.34048162120435e-06,
"loss": 0.4487,
"step": 2565
},
{
"epoch": 0.66,
"learning_rate": 5.3330568330166055e-06,
"loss": 0.4131,
"step": 2566
},
{
"epoch": 0.67,
"learning_rate": 5.325635332531864e-06,
"loss": 0.4153,
"step": 2567
},
{
"epoch": 0.67,
"learning_rate": 5.318217124978313e-06,
"loss": 0.4587,
"step": 2568
},
{
"epoch": 0.67,
"learning_rate": 5.310802215581835e-06,
"loss": 0.4336,
"step": 2569
},
{
"epoch": 0.67,
"learning_rate": 5.303390609565975e-06,
"loss": 0.4321,
"step": 2570
},
{
"epoch": 0.67,
"learning_rate": 5.295982312151962e-06,
"loss": 0.4451,
"step": 2571
},
{
"epoch": 0.67,
"learning_rate": 5.2885773285586915e-06,
"loss": 0.4377,
"step": 2572
},
{
"epoch": 0.67,
"learning_rate": 5.2811756640027175e-06,
"loss": 0.4106,
"step": 2573
},
{
"epoch": 0.67,
"learning_rate": 5.2737773236982705e-06,
"loss": 0.4126,
"step": 2574
},
{
"epoch": 0.67,
"learning_rate": 5.266382312857219e-06,
"loss": 0.4519,
"step": 2575
},
{
"epoch": 0.67,
"learning_rate": 5.258990636689106e-06,
"loss": 0.4292,
"step": 2576
},
{
"epoch": 0.67,
"learning_rate": 5.251602300401108e-06,
"loss": 0.4424,
"step": 2577
},
{
"epoch": 0.67,
"learning_rate": 5.244217309198063e-06,
"loss": 0.4353,
"step": 2578
},
{
"epoch": 0.67,
"learning_rate": 5.23683566828245e-06,
"loss": 0.4495,
"step": 2579
},
{
"epoch": 0.67,
"learning_rate": 5.229457382854374e-06,
"loss": 0.426,
"step": 2580
},
{
"epoch": 0.67,
"learning_rate": 5.222082458111597e-06,
"loss": 0.4414,
"step": 2581
},
{
"epoch": 0.67,
"learning_rate": 5.214710899249494e-06,
"loss": 0.426,
"step": 2582
},
{
"epoch": 0.67,
"learning_rate": 5.2073427114610855e-06,
"loss": 0.4082,
"step": 2583
},
{
"epoch": 0.67,
"learning_rate": 5.199977899937003e-06,
"loss": 0.4138,
"step": 2584
},
{
"epoch": 0.67,
"learning_rate": 5.1926164698655105e-06,
"loss": 0.4292,
"step": 2585
},
{
"epoch": 0.67,
"learning_rate": 5.1852584264324864e-06,
"loss": 0.415,
"step": 2586
},
{
"epoch": 0.67,
"learning_rate": 5.177903774821418e-06,
"loss": 0.4197,
"step": 2587
},
{
"epoch": 0.67,
"learning_rate": 5.170552520213414e-06,
"loss": 0.4219,
"step": 2588
},
{
"epoch": 0.67,
"learning_rate": 5.163204667787176e-06,
"loss": 0.4304,
"step": 2589
},
{
"epoch": 0.67,
"learning_rate": 5.155860222719022e-06,
"loss": 0.4231,
"step": 2590
},
{
"epoch": 0.67,
"learning_rate": 5.148519190182864e-06,
"loss": 0.4436,
"step": 2591
},
{
"epoch": 0.67,
"learning_rate": 5.1411815753502055e-06,
"loss": 0.425,
"step": 2592
},
{
"epoch": 0.67,
"learning_rate": 5.133847383390155e-06,
"loss": 0.4338,
"step": 2593
},
{
"epoch": 0.67,
"learning_rate": 5.126516619469397e-06,
"loss": 0.4185,
"step": 2594
},
{
"epoch": 0.67,
"learning_rate": 5.119189288752201e-06,
"loss": 0.4326,
"step": 2595
},
{
"epoch": 0.67,
"learning_rate": 5.1118653964004284e-06,
"loss": 0.426,
"step": 2596
},
{
"epoch": 0.67,
"learning_rate": 5.104544947573511e-06,
"loss": 0.4448,
"step": 2597
},
{
"epoch": 0.67,
"learning_rate": 5.0972279474284605e-06,
"loss": 0.4316,
"step": 2598
},
{
"epoch": 0.67,
"learning_rate": 5.089914401119849e-06,
"loss": 0.4365,
"step": 2599
},
{
"epoch": 0.67,
"learning_rate": 5.082604313799828e-06,
"loss": 0.4172,
"step": 2600
},
{
"epoch": 0.67,
"learning_rate": 5.075297690618101e-06,
"loss": 0.4495,
"step": 2601
},
{
"epoch": 0.67,
"learning_rate": 5.067994536721936e-06,
"loss": 0.4409,
"step": 2602
},
{
"epoch": 0.67,
"learning_rate": 5.0606948572561554e-06,
"loss": 0.4282,
"step": 2603
},
{
"epoch": 0.67,
"learning_rate": 5.0533986573631386e-06,
"loss": 0.4646,
"step": 2604
},
{
"epoch": 0.68,
"learning_rate": 5.046105942182815e-06,
"loss": 0.4348,
"step": 2605
},
{
"epoch": 0.68,
"learning_rate": 5.038816716852648e-06,
"loss": 0.4482,
"step": 2606
},
{
"epoch": 0.68,
"learning_rate": 5.03153098650765e-06,
"loss": 0.4314,
"step": 2607
},
{
"epoch": 0.68,
"learning_rate": 5.024248756280371e-06,
"loss": 0.4202,
"step": 2608
},
{
"epoch": 0.68,
"learning_rate": 5.016970031300896e-06,
"loss": 0.4438,
"step": 2609
},
{
"epoch": 0.68,
"learning_rate": 5.0096948166968425e-06,
"loss": 0.4304,
"step": 2610
},
{
"epoch": 0.68,
"learning_rate": 5.002423117593347e-06,
"loss": 0.4375,
"step": 2611
},
{
"epoch": 0.68,
"learning_rate": 4.995154939113079e-06,
"loss": 0.4421,
"step": 2612
},
{
"epoch": 0.68,
"learning_rate": 4.987890286376224e-06,
"loss": 0.4285,
"step": 2613
},
{
"epoch": 0.68,
"learning_rate": 4.980629164500474e-06,
"loss": 0.4485,
"step": 2614
},
{
"epoch": 0.68,
"learning_rate": 4.973371578601051e-06,
"loss": 0.4187,
"step": 2615
},
{
"epoch": 0.68,
"learning_rate": 4.966117533790675e-06,
"loss": 0.4458,
"step": 2616
},
{
"epoch": 0.68,
"learning_rate": 4.9588670351795795e-06,
"loss": 0.4316,
"step": 2617
},
{
"epoch": 0.68,
"learning_rate": 4.951620087875491e-06,
"loss": 0.4285,
"step": 2618
},
{
"epoch": 0.68,
"learning_rate": 4.944376696983633e-06,
"loss": 0.4299,
"step": 2619
},
{
"epoch": 0.68,
"learning_rate": 4.937136867606736e-06,
"loss": 0.4231,
"step": 2620
},
{
"epoch": 0.68,
"learning_rate": 4.929900604845009e-06,
"loss": 0.4502,
"step": 2621
},
{
"epoch": 0.68,
"learning_rate": 4.922667913796153e-06,
"loss": 0.4197,
"step": 2622
},
{
"epoch": 0.68,
"learning_rate": 4.91543879955536e-06,
"loss": 0.4236,
"step": 2623
},
{
"epoch": 0.68,
"learning_rate": 4.908213267215287e-06,
"loss": 0.4192,
"step": 2624
},
{
"epoch": 0.68,
"learning_rate": 4.900991321866084e-06,
"loss": 0.4448,
"step": 2625
},
{
"epoch": 0.68,
"learning_rate": 4.89377296859536e-06,
"loss": 0.4338,
"step": 2626
},
{
"epoch": 0.68,
"learning_rate": 4.8865582124882005e-06,
"loss": 0.4387,
"step": 2627
},
{
"epoch": 0.68,
"learning_rate": 4.879347058627159e-06,
"loss": 0.4226,
"step": 2628
},
{
"epoch": 0.68,
"learning_rate": 4.87213951209225e-06,
"loss": 0.427,
"step": 2629
},
{
"epoch": 0.68,
"learning_rate": 4.864935577960943e-06,
"loss": 0.4561,
"step": 2630
},
{
"epoch": 0.68,
"learning_rate": 4.857735261308162e-06,
"loss": 0.4468,
"step": 2631
},
{
"epoch": 0.68,
"learning_rate": 4.850538567206291e-06,
"loss": 0.4358,
"step": 2632
},
{
"epoch": 0.68,
"learning_rate": 4.843345500725151e-06,
"loss": 0.4375,
"step": 2633
},
{
"epoch": 0.68,
"learning_rate": 4.836156066932015e-06,
"loss": 0.4143,
"step": 2634
},
{
"epoch": 0.68,
"learning_rate": 4.828970270891601e-06,
"loss": 0.4402,
"step": 2635
},
{
"epoch": 0.68,
"learning_rate": 4.82178811766605e-06,
"loss": 0.4526,
"step": 2636
},
{
"epoch": 0.68,
"learning_rate": 4.814609612314951e-06,
"loss": 0.4399,
"step": 2637
},
{
"epoch": 0.68,
"learning_rate": 4.807434759895312e-06,
"loss": 0.436,
"step": 2638
},
{
"epoch": 0.68,
"learning_rate": 4.800263565461579e-06,
"loss": 0.4246,
"step": 2639
},
{
"epoch": 0.68,
"learning_rate": 4.7930960340656075e-06,
"loss": 0.4282,
"step": 2640
},
{
"epoch": 0.68,
"learning_rate": 4.785932170756686e-06,
"loss": 0.428,
"step": 2641
},
{
"epoch": 0.68,
"learning_rate": 4.778771980581512e-06,
"loss": 0.4199,
"step": 2642
},
{
"epoch": 0.68,
"learning_rate": 4.771615468584194e-06,
"loss": 0.4268,
"step": 2643
},
{
"epoch": 0.69,
"learning_rate": 4.764462639806256e-06,
"loss": 0.4421,
"step": 2644
},
{
"epoch": 0.69,
"learning_rate": 4.7573134992866174e-06,
"loss": 0.4224,
"step": 2645
},
{
"epoch": 0.69,
"learning_rate": 4.750168052061607e-06,
"loss": 0.4319,
"step": 2646
},
{
"epoch": 0.69,
"learning_rate": 4.743026303164955e-06,
"loss": 0.4409,
"step": 2647
},
{
"epoch": 0.69,
"learning_rate": 4.7358882576277724e-06,
"loss": 0.4434,
"step": 2648
},
{
"epoch": 0.69,
"learning_rate": 4.728753920478577e-06,
"loss": 0.446,
"step": 2649
},
{
"epoch": 0.69,
"learning_rate": 4.721623296743261e-06,
"loss": 0.4407,
"step": 2650
},
{
"epoch": 0.69,
"learning_rate": 4.714496391445114e-06,
"loss": 0.4329,
"step": 2651
},
{
"epoch": 0.69,
"learning_rate": 4.70737320960479e-06,
"loss": 0.4197,
"step": 2652
},
{
"epoch": 0.69,
"learning_rate": 4.700253756240334e-06,
"loss": 0.4082,
"step": 2653
},
{
"epoch": 0.69,
"learning_rate": 4.693138036367162e-06,
"loss": 0.447,
"step": 2654
},
{
"epoch": 0.69,
"learning_rate": 4.68602605499805e-06,
"loss": 0.4316,
"step": 2655
},
{
"epoch": 0.69,
"learning_rate": 4.6789178171431544e-06,
"loss": 0.4246,
"step": 2656
},
{
"epoch": 0.69,
"learning_rate": 4.671813327809981e-06,
"loss": 0.4592,
"step": 2657
},
{
"epoch": 0.69,
"learning_rate": 4.664712592003407e-06,
"loss": 0.4282,
"step": 2658
},
{
"epoch": 0.69,
"learning_rate": 4.657615614725655e-06,
"loss": 0.4111,
"step": 2659
},
{
"epoch": 0.69,
"learning_rate": 4.650522400976304e-06,
"loss": 0.4226,
"step": 2660
},
{
"epoch": 0.69,
"learning_rate": 4.64343295575229e-06,
"loss": 0.4255,
"step": 2661
},
{
"epoch": 0.69,
"learning_rate": 4.636347284047878e-06,
"loss": 0.4307,
"step": 2662
},
{
"epoch": 0.69,
"learning_rate": 4.629265390854689e-06,
"loss": 0.4382,
"step": 2663
},
{
"epoch": 0.69,
"learning_rate": 4.622187281161673e-06,
"loss": 0.4324,
"step": 2664
},
{
"epoch": 0.69,
"learning_rate": 4.615112959955113e-06,
"loss": 0.4087,
"step": 2665
},
{
"epoch": 0.69,
"learning_rate": 4.608042432218639e-06,
"loss": 0.4355,
"step": 2666
},
{
"epoch": 0.69,
"learning_rate": 4.60097570293319e-06,
"loss": 0.4531,
"step": 2667
},
{
"epoch": 0.69,
"learning_rate": 4.593912777077043e-06,
"loss": 0.4365,
"step": 2668
},
{
"epoch": 0.69,
"learning_rate": 4.586853659625782e-06,
"loss": 0.4104,
"step": 2669
},
{
"epoch": 0.69,
"learning_rate": 4.579798355552322e-06,
"loss": 0.4292,
"step": 2670
},
{
"epoch": 0.69,
"learning_rate": 4.572746869826879e-06,
"loss": 0.4583,
"step": 2671
},
{
"epoch": 0.69,
"learning_rate": 4.565699207416988e-06,
"loss": 0.4282,
"step": 2672
},
{
"epoch": 0.69,
"learning_rate": 4.558655373287494e-06,
"loss": 0.438,
"step": 2673
},
{
"epoch": 0.69,
"learning_rate": 4.551615372400529e-06,
"loss": 0.425,
"step": 2674
},
{
"epoch": 0.69,
"learning_rate": 4.544579209715542e-06,
"loss": 0.4392,
"step": 2675
},
{
"epoch": 0.69,
"learning_rate": 4.5375468901892685e-06,
"loss": 0.4297,
"step": 2676
},
{
"epoch": 0.69,
"learning_rate": 4.530518418775734e-06,
"loss": 0.4104,
"step": 2677
},
{
"epoch": 0.69,
"learning_rate": 4.523493800426262e-06,
"loss": 0.4373,
"step": 2678
},
{
"epoch": 0.69,
"learning_rate": 4.516473040089457e-06,
"loss": 0.4341,
"step": 2679
},
{
"epoch": 0.69,
"learning_rate": 4.509456142711213e-06,
"loss": 0.4197,
"step": 2680
},
{
"epoch": 0.69,
"learning_rate": 4.502443113234688e-06,
"loss": 0.4197,
"step": 2681
},
{
"epoch": 0.69,
"learning_rate": 4.495433956600321e-06,
"loss": 0.4351,
"step": 2682
},
{
"epoch": 0.7,
"learning_rate": 4.488428677745829e-06,
"loss": 0.4282,
"step": 2683
},
{
"epoch": 0.7,
"learning_rate": 4.4814272816061945e-06,
"loss": 0.4158,
"step": 2684
},
{
"epoch": 0.7,
"learning_rate": 4.474429773113665e-06,
"loss": 0.4331,
"step": 2685
},
{
"epoch": 0.7,
"learning_rate": 4.467436157197741e-06,
"loss": 0.4148,
"step": 2686
},
{
"epoch": 0.7,
"learning_rate": 4.460446438785194e-06,
"loss": 0.4382,
"step": 2687
},
{
"epoch": 0.7,
"learning_rate": 4.45346062280004e-06,
"loss": 0.4651,
"step": 2688
},
{
"epoch": 0.7,
"learning_rate": 4.446478714163547e-06,
"loss": 0.4167,
"step": 2689
},
{
"epoch": 0.7,
"learning_rate": 4.439500717794234e-06,
"loss": 0.4512,
"step": 2690
},
{
"epoch": 0.7,
"learning_rate": 4.432526638607864e-06,
"loss": 0.4692,
"step": 2691
},
{
"epoch": 0.7,
"learning_rate": 4.425556481517441e-06,
"loss": 0.429,
"step": 2692
},
{
"epoch": 0.7,
"learning_rate": 4.418590251433202e-06,
"loss": 0.4343,
"step": 2693
},
{
"epoch": 0.7,
"learning_rate": 4.411627953262616e-06,
"loss": 0.4397,
"step": 2694
},
{
"epoch": 0.7,
"learning_rate": 4.404669591910392e-06,
"loss": 0.4473,
"step": 2695
},
{
"epoch": 0.7,
"learning_rate": 4.397715172278452e-06,
"loss": 0.4329,
"step": 2696
},
{
"epoch": 0.7,
"learning_rate": 4.390764699265953e-06,
"loss": 0.4292,
"step": 2697
},
{
"epoch": 0.7,
"learning_rate": 4.3838181777692665e-06,
"loss": 0.4299,
"step": 2698
},
{
"epoch": 0.7,
"learning_rate": 4.376875612681986e-06,
"loss": 0.4338,
"step": 2699
},
{
"epoch": 0.7,
"learning_rate": 4.369937008894906e-06,
"loss": 0.4419,
"step": 2700
},
{
"epoch": 0.7,
"learning_rate": 4.363002371296037e-06,
"loss": 0.4219,
"step": 2701
},
{
"epoch": 0.7,
"learning_rate": 4.356071704770598e-06,
"loss": 0.4741,
"step": 2702
},
{
"epoch": 0.7,
"learning_rate": 4.349145014201008e-06,
"loss": 0.4348,
"step": 2703
},
{
"epoch": 0.7,
"learning_rate": 4.342222304466891e-06,
"loss": 0.4155,
"step": 2704
},
{
"epoch": 0.7,
"learning_rate": 4.335303580445054e-06,
"loss": 0.4302,
"step": 2705
},
{
"epoch": 0.7,
"learning_rate": 4.328388847009502e-06,
"loss": 0.4507,
"step": 2706
},
{
"epoch": 0.7,
"learning_rate": 4.321478109031436e-06,
"loss": 0.4287,
"step": 2707
},
{
"epoch": 0.7,
"learning_rate": 4.314571371379229e-06,
"loss": 0.4246,
"step": 2708
},
{
"epoch": 0.7,
"learning_rate": 4.307668638918448e-06,
"loss": 0.4387,
"step": 2709
},
{
"epoch": 0.7,
"learning_rate": 4.300769916511837e-06,
"loss": 0.4175,
"step": 2710
},
{
"epoch": 0.7,
"learning_rate": 4.293875209019303e-06,
"loss": 0.4229,
"step": 2711
},
{
"epoch": 0.7,
"learning_rate": 4.286984521297941e-06,
"loss": 0.4094,
"step": 2712
},
{
"epoch": 0.7,
"learning_rate": 4.280097858202e-06,
"loss": 0.4402,
"step": 2713
},
{
"epoch": 0.7,
"learning_rate": 4.273215224582907e-06,
"loss": 0.4153,
"step": 2714
},
{
"epoch": 0.7,
"learning_rate": 4.266336625289238e-06,
"loss": 0.4268,
"step": 2715
},
{
"epoch": 0.7,
"learning_rate": 4.259462065166734e-06,
"loss": 0.4287,
"step": 2716
},
{
"epoch": 0.7,
"learning_rate": 4.252591549058294e-06,
"loss": 0.4272,
"step": 2717
},
{
"epoch": 0.7,
"learning_rate": 4.245725081803955e-06,
"loss": 0.4219,
"step": 2718
},
{
"epoch": 0.7,
"learning_rate": 4.23886266824092e-06,
"loss": 0.4365,
"step": 2719
},
{
"epoch": 0.7,
"learning_rate": 4.232004313203516e-06,
"loss": 0.4331,
"step": 2720
},
{
"epoch": 0.71,
"learning_rate": 4.225150021523226e-06,
"loss": 0.4324,
"step": 2721
},
{
"epoch": 0.71,
"learning_rate": 4.2182997980286715e-06,
"loss": 0.4407,
"step": 2722
},
{
"epoch": 0.71,
"learning_rate": 4.211453647545591e-06,
"loss": 0.4246,
"step": 2723
},
{
"epoch": 0.71,
"learning_rate": 4.204611574896875e-06,
"loss": 0.4094,
"step": 2724
},
{
"epoch": 0.71,
"learning_rate": 4.197773584902524e-06,
"loss": 0.4094,
"step": 2725
},
{
"epoch": 0.71,
"learning_rate": 4.190939682379676e-06,
"loss": 0.4333,
"step": 2726
},
{
"epoch": 0.71,
"learning_rate": 4.184109872142577e-06,
"loss": 0.4199,
"step": 2727
},
{
"epoch": 0.71,
"learning_rate": 4.1772841590026e-06,
"loss": 0.415,
"step": 2728
},
{
"epoch": 0.71,
"learning_rate": 4.170462547768232e-06,
"loss": 0.4272,
"step": 2729
},
{
"epoch": 0.71,
"learning_rate": 4.163645043245058e-06,
"loss": 0.4143,
"step": 2730
},
{
"epoch": 0.71,
"learning_rate": 4.156831650235786e-06,
"loss": 0.4263,
"step": 2731
},
{
"epoch": 0.71,
"learning_rate": 4.150022373540214e-06,
"loss": 0.4219,
"step": 2732
},
{
"epoch": 0.71,
"learning_rate": 4.143217217955251e-06,
"loss": 0.4255,
"step": 2733
},
{
"epoch": 0.71,
"learning_rate": 4.136416188274894e-06,
"loss": 0.4067,
"step": 2734
},
{
"epoch": 0.71,
"learning_rate": 4.129619289290239e-06,
"loss": 0.4238,
"step": 2735
},
{
"epoch": 0.71,
"learning_rate": 4.122826525789475e-06,
"loss": 0.4275,
"step": 2736
},
{
"epoch": 0.71,
"learning_rate": 4.116037902557866e-06,
"loss": 0.4287,
"step": 2737
},
{
"epoch": 0.71,
"learning_rate": 4.109253424377773e-06,
"loss": 0.4216,
"step": 2738
},
{
"epoch": 0.71,
"learning_rate": 4.102473096028624e-06,
"loss": 0.4216,
"step": 2739
},
{
"epoch": 0.71,
"learning_rate": 4.095696922286933e-06,
"loss": 0.4133,
"step": 2740
},
{
"epoch": 0.71,
"learning_rate": 4.08892490792629e-06,
"loss": 0.4226,
"step": 2741
},
{
"epoch": 0.71,
"learning_rate": 4.082157057717339e-06,
"loss": 0.4441,
"step": 2742
},
{
"epoch": 0.71,
"learning_rate": 4.075393376427809e-06,
"loss": 0.4121,
"step": 2743
},
{
"epoch": 0.71,
"learning_rate": 4.068633868822478e-06,
"loss": 0.4189,
"step": 2744
},
{
"epoch": 0.71,
"learning_rate": 4.061878539663196e-06,
"loss": 0.4312,
"step": 2745
},
{
"epoch": 0.71,
"learning_rate": 4.055127393708854e-06,
"loss": 0.4167,
"step": 2746
},
{
"epoch": 0.71,
"learning_rate": 4.048380435715411e-06,
"loss": 0.4211,
"step": 2747
},
{
"epoch": 0.71,
"learning_rate": 4.041637670435873e-06,
"loss": 0.4368,
"step": 2748
},
{
"epoch": 0.71,
"learning_rate": 4.034899102620282e-06,
"loss": 0.4346,
"step": 2749
},
{
"epoch": 0.71,
"learning_rate": 4.028164737015736e-06,
"loss": 0.4043,
"step": 2750
},
{
"epoch": 0.71,
"learning_rate": 4.0214345783663655e-06,
"loss": 0.4294,
"step": 2751
},
{
"epoch": 0.71,
"learning_rate": 4.014708631413333e-06,
"loss": 0.4014,
"step": 2752
},
{
"epoch": 0.71,
"learning_rate": 4.007986900894846e-06,
"loss": 0.4343,
"step": 2753
},
{
"epoch": 0.71,
"learning_rate": 4.001269391546132e-06,
"loss": 0.4243,
"step": 2754
},
{
"epoch": 0.71,
"learning_rate": 3.994556108099455e-06,
"loss": 0.4238,
"step": 2755
},
{
"epoch": 0.71,
"learning_rate": 3.987847055284085e-06,
"loss": 0.4409,
"step": 2756
},
{
"epoch": 0.71,
"learning_rate": 3.981142237826332e-06,
"loss": 0.4199,
"step": 2757
},
{
"epoch": 0.71,
"learning_rate": 3.974441660449508e-06,
"loss": 0.4341,
"step": 2758
},
{
"epoch": 0.71,
"learning_rate": 3.967745327873934e-06,
"loss": 0.4658,
"step": 2759
},
{
"epoch": 0.72,
"learning_rate": 3.9610532448169636e-06,
"loss": 0.415,
"step": 2760
},
{
"epoch": 0.72,
"learning_rate": 3.954365415992932e-06,
"loss": 0.4263,
"step": 2761
},
{
"epoch": 0.72,
"learning_rate": 3.947681846113194e-06,
"loss": 0.4194,
"step": 2762
},
{
"epoch": 0.72,
"learning_rate": 3.941002539886094e-06,
"loss": 0.4336,
"step": 2763
},
{
"epoch": 0.72,
"learning_rate": 3.9343275020169735e-06,
"loss": 0.4207,
"step": 2764
},
{
"epoch": 0.72,
"learning_rate": 3.927656737208173e-06,
"loss": 0.45,
"step": 2765
},
{
"epoch": 0.72,
"learning_rate": 3.9209902501590205e-06,
"loss": 0.4343,
"step": 2766
},
{
"epoch": 0.72,
"learning_rate": 3.914328045565833e-06,
"loss": 0.428,
"step": 2767
},
{
"epoch": 0.72,
"learning_rate": 3.9076701281219e-06,
"loss": 0.4424,
"step": 2768
},
{
"epoch": 0.72,
"learning_rate": 3.901016502517505e-06,
"loss": 0.4094,
"step": 2769
},
{
"epoch": 0.72,
"learning_rate": 3.8943671734398995e-06,
"loss": 0.4529,
"step": 2770
},
{
"epoch": 0.72,
"learning_rate": 3.887722145573305e-06,
"loss": 0.4629,
"step": 2771
},
{
"epoch": 0.72,
"learning_rate": 3.881081423598921e-06,
"loss": 0.4172,
"step": 2772
},
{
"epoch": 0.72,
"learning_rate": 3.874445012194913e-06,
"loss": 0.4304,
"step": 2773
},
{
"epoch": 0.72,
"learning_rate": 3.86781291603641e-06,
"loss": 0.4463,
"step": 2774
},
{
"epoch": 0.72,
"learning_rate": 3.8611851397954935e-06,
"loss": 0.4299,
"step": 2775
},
{
"epoch": 0.72,
"learning_rate": 3.854561688141205e-06,
"loss": 0.429,
"step": 2776
},
{
"epoch": 0.72,
"learning_rate": 3.847942565739547e-06,
"loss": 0.4241,
"step": 2777
},
{
"epoch": 0.72,
"learning_rate": 3.841327777253457e-06,
"loss": 0.429,
"step": 2778
},
{
"epoch": 0.72,
"learning_rate": 3.834717327342844e-06,
"loss": 0.4133,
"step": 2779
},
{
"epoch": 0.72,
"learning_rate": 3.828111220664536e-06,
"loss": 0.4224,
"step": 2780
},
{
"epoch": 0.72,
"learning_rate": 3.8215094618723085e-06,
"loss": 0.4448,
"step": 2781
},
{
"epoch": 0.72,
"learning_rate": 3.814912055616884e-06,
"loss": 0.4341,
"step": 2782
},
{
"epoch": 0.72,
"learning_rate": 3.808319006545903e-06,
"loss": 0.4258,
"step": 2783
},
{
"epoch": 0.72,
"learning_rate": 3.801730319303949e-06,
"loss": 0.4121,
"step": 2784
},
{
"epoch": 0.72,
"learning_rate": 3.795145998532529e-06,
"loss": 0.4194,
"step": 2785
},
{
"epoch": 0.72,
"learning_rate": 3.788566048870075e-06,
"loss": 0.439,
"step": 2786
},
{
"epoch": 0.72,
"learning_rate": 3.7819904749519366e-06,
"loss": 0.3931,
"step": 2787
},
{
"epoch": 0.72,
"learning_rate": 3.7754192814103776e-06,
"loss": 0.4297,
"step": 2788
},
{
"epoch": 0.72,
"learning_rate": 3.768852472874589e-06,
"loss": 0.45,
"step": 2789
},
{
"epoch": 0.72,
"learning_rate": 3.7622900539706563e-06,
"loss": 0.417,
"step": 2790
},
{
"epoch": 0.72,
"learning_rate": 3.7557320293215836e-06,
"loss": 0.427,
"step": 2791
},
{
"epoch": 0.72,
"learning_rate": 3.749178403547282e-06,
"loss": 0.4031,
"step": 2792
},
{
"epoch": 0.72,
"learning_rate": 3.742629181264551e-06,
"loss": 0.4509,
"step": 2793
},
{
"epoch": 0.72,
"learning_rate": 3.7360843670871015e-06,
"loss": 0.4348,
"step": 2794
},
{
"epoch": 0.72,
"learning_rate": 3.729543965625526e-06,
"loss": 0.4319,
"step": 2795
},
{
"epoch": 0.72,
"learning_rate": 3.7230079814873233e-06,
"loss": 0.4146,
"step": 2796
},
{
"epoch": 0.72,
"learning_rate": 3.71647641927686e-06,
"loss": 0.4365,
"step": 2797
},
{
"epoch": 0.73,
"learning_rate": 3.7099492835954154e-06,
"loss": 0.438,
"step": 2798
},
{
"epoch": 0.73,
"learning_rate": 3.703426579041126e-06,
"loss": 0.4441,
"step": 2799
},
{
"epoch": 0.73,
"learning_rate": 3.696908310209015e-06,
"loss": 0.4536,
"step": 2800
},
{
"epoch": 0.73,
"learning_rate": 3.6903944816909867e-06,
"loss": 0.4165,
"step": 2801
},
{
"epoch": 0.73,
"learning_rate": 3.6838850980758056e-06,
"loss": 0.4216,
"step": 2802
},
{
"epoch": 0.73,
"learning_rate": 3.6773801639491147e-06,
"loss": 0.4241,
"step": 2803
},
{
"epoch": 0.73,
"learning_rate": 3.6708796838934224e-06,
"loss": 0.4326,
"step": 2804
},
{
"epoch": 0.73,
"learning_rate": 3.6643836624880903e-06,
"loss": 0.4407,
"step": 2805
},
{
"epoch": 0.73,
"learning_rate": 3.6578921043093507e-06,
"loss": 0.4136,
"step": 2806
},
{
"epoch": 0.73,
"learning_rate": 3.6514050139302804e-06,
"loss": 0.4167,
"step": 2807
},
{
"epoch": 0.73,
"learning_rate": 3.644922395920819e-06,
"loss": 0.4343,
"step": 2808
},
{
"epoch": 0.73,
"learning_rate": 3.638444254847746e-06,
"loss": 0.4424,
"step": 2809
},
{
"epoch": 0.73,
"learning_rate": 3.6319705952746943e-06,
"loss": 0.4395,
"step": 2810
},
{
"epoch": 0.73,
"learning_rate": 3.625501421762141e-06,
"loss": 0.4277,
"step": 2811
},
{
"epoch": 0.73,
"learning_rate": 3.619036738867392e-06,
"loss": 0.437,
"step": 2812
},
{
"epoch": 0.73,
"learning_rate": 3.6125765511446043e-06,
"loss": 0.4294,
"step": 2813
},
{
"epoch": 0.73,
"learning_rate": 3.606120863144753e-06,
"loss": 0.4285,
"step": 2814
},
{
"epoch": 0.73,
"learning_rate": 3.5996696794156584e-06,
"loss": 0.4631,
"step": 2815
},
{
"epoch": 0.73,
"learning_rate": 3.5932230045019545e-06,
"loss": 0.4246,
"step": 2816
},
{
"epoch": 0.73,
"learning_rate": 3.586780842945107e-06,
"loss": 0.4243,
"step": 2817
},
{
"epoch": 0.73,
"learning_rate": 3.5803431992834036e-06,
"loss": 0.4221,
"step": 2818
},
{
"epoch": 0.73,
"learning_rate": 3.5739100780519398e-06,
"loss": 0.4229,
"step": 2819
},
{
"epoch": 0.73,
"learning_rate": 3.5674814837826364e-06,
"loss": 0.4539,
"step": 2820
},
{
"epoch": 0.73,
"learning_rate": 3.561057421004215e-06,
"loss": 0.4243,
"step": 2821
},
{
"epoch": 0.73,
"learning_rate": 3.554637894242211e-06,
"loss": 0.4089,
"step": 2822
},
{
"epoch": 0.73,
"learning_rate": 3.548222908018968e-06,
"loss": 0.4331,
"step": 2823
},
{
"epoch": 0.73,
"learning_rate": 3.541812466853618e-06,
"loss": 0.4099,
"step": 2824
},
{
"epoch": 0.73,
"learning_rate": 3.5354065752621058e-06,
"loss": 0.4199,
"step": 2825
},
{
"epoch": 0.73,
"learning_rate": 3.529005237757159e-06,
"loss": 0.4309,
"step": 2826
},
{
"epoch": 0.73,
"learning_rate": 3.522608458848309e-06,
"loss": 0.4521,
"step": 2827
},
{
"epoch": 0.73,
"learning_rate": 3.516216243041862e-06,
"loss": 0.4089,
"step": 2828
},
{
"epoch": 0.73,
"learning_rate": 3.5098285948409216e-06,
"loss": 0.4316,
"step": 2829
},
{
"epoch": 0.73,
"learning_rate": 3.50344551874537e-06,
"loss": 0.428,
"step": 2830
},
{
"epoch": 0.73,
"learning_rate": 3.497067019251863e-06,
"loss": 0.4307,
"step": 2831
},
{
"epoch": 0.73,
"learning_rate": 3.4906931008538425e-06,
"loss": 0.3801,
"step": 2832
},
{
"epoch": 0.73,
"learning_rate": 3.4843237680415153e-06,
"loss": 0.4255,
"step": 2833
},
{
"epoch": 0.73,
"learning_rate": 3.4779590253018558e-06,
"loss": 0.4321,
"step": 2834
},
{
"epoch": 0.73,
"learning_rate": 3.471598877118614e-06,
"loss": 0.4316,
"step": 2835
},
{
"epoch": 0.73,
"learning_rate": 3.465243327972295e-06,
"loss": 0.4426,
"step": 2836
},
{
"epoch": 0.74,
"learning_rate": 3.4588923823401745e-06,
"loss": 0.4219,
"step": 2837
},
{
"epoch": 0.74,
"learning_rate": 3.4525460446962735e-06,
"loss": 0.3948,
"step": 2838
},
{
"epoch": 0.74,
"learning_rate": 3.446204319511366e-06,
"loss": 0.4248,
"step": 2839
},
{
"epoch": 0.74,
"learning_rate": 3.4398672112529885e-06,
"loss": 0.437,
"step": 2840
},
{
"epoch": 0.74,
"learning_rate": 3.4335347243854165e-06,
"loss": 0.405,
"step": 2841
},
{
"epoch": 0.74,
"learning_rate": 3.4272068633696752e-06,
"loss": 0.4263,
"step": 2842
},
{
"epoch": 0.74,
"learning_rate": 3.420883632663523e-06,
"loss": 0.4309,
"step": 2843
},
{
"epoch": 0.74,
"learning_rate": 3.4145650367214668e-06,
"loss": 0.4199,
"step": 2844
},
{
"epoch": 0.74,
"learning_rate": 3.40825107999474e-06,
"loss": 0.4155,
"step": 2845
},
{
"epoch": 0.74,
"learning_rate": 3.401941766931306e-06,
"loss": 0.4326,
"step": 2846
},
{
"epoch": 0.74,
"learning_rate": 3.395637101975867e-06,
"loss": 0.4136,
"step": 2847
},
{
"epoch": 0.74,
"learning_rate": 3.389337089569844e-06,
"loss": 0.4202,
"step": 2848
},
{
"epoch": 0.74,
"learning_rate": 3.3830417341513856e-06,
"loss": 0.4131,
"step": 2849
},
{
"epoch": 0.74,
"learning_rate": 3.3767510401553516e-06,
"loss": 0.4189,
"step": 2850
},
{
"epoch": 0.74,
"learning_rate": 3.3704650120133207e-06,
"loss": 0.4194,
"step": 2851
},
{
"epoch": 0.74,
"learning_rate": 3.364183654153592e-06,
"loss": 0.45,
"step": 2852
},
{
"epoch": 0.74,
"learning_rate": 3.3579069710011626e-06,
"loss": 0.4131,
"step": 2853
},
{
"epoch": 0.74,
"learning_rate": 3.351634966977746e-06,
"loss": 0.4324,
"step": 2854
},
{
"epoch": 0.74,
"learning_rate": 3.3453676465017547e-06,
"loss": 0.4053,
"step": 2855
},
{
"epoch": 0.74,
"learning_rate": 3.3391050139883085e-06,
"loss": 0.4294,
"step": 2856
},
{
"epoch": 0.74,
"learning_rate": 3.332847073849216e-06,
"loss": 0.4197,
"step": 2857
},
{
"epoch": 0.74,
"learning_rate": 3.3265938304929777e-06,
"loss": 0.4233,
"step": 2858
},
{
"epoch": 0.74,
"learning_rate": 3.3203452883247966e-06,
"loss": 0.438,
"step": 2859
},
{
"epoch": 0.74,
"learning_rate": 3.3141014517465588e-06,
"loss": 0.436,
"step": 2860
},
{
"epoch": 0.74,
"learning_rate": 3.3078623251568376e-06,
"loss": 0.4329,
"step": 2861
},
{
"epoch": 0.74,
"learning_rate": 3.301627912950882e-06,
"loss": 0.4199,
"step": 2862
},
{
"epoch": 0.74,
"learning_rate": 3.2953982195206214e-06,
"loss": 0.4221,
"step": 2863
},
{
"epoch": 0.74,
"learning_rate": 3.2891732492546702e-06,
"loss": 0.4312,
"step": 2864
},
{
"epoch": 0.74,
"learning_rate": 3.282953006538301e-06,
"loss": 0.4316,
"step": 2865
},
{
"epoch": 0.74,
"learning_rate": 3.276737495753467e-06,
"loss": 0.417,
"step": 2866
},
{
"epoch": 0.74,
"learning_rate": 3.2705267212787896e-06,
"loss": 0.4297,
"step": 2867
},
{
"epoch": 0.74,
"learning_rate": 3.2643206874895385e-06,
"loss": 0.406,
"step": 2868
},
{
"epoch": 0.74,
"learning_rate": 3.258119398757663e-06,
"loss": 0.4417,
"step": 2869
},
{
"epoch": 0.74,
"learning_rate": 3.2519228594517538e-06,
"loss": 0.4209,
"step": 2870
},
{
"epoch": 0.74,
"learning_rate": 3.2457310739370684e-06,
"loss": 0.4194,
"step": 2871
},
{
"epoch": 0.74,
"learning_rate": 3.2395440465755025e-06,
"loss": 0.4092,
"step": 2872
},
{
"epoch": 0.74,
"learning_rate": 3.2333617817256103e-06,
"loss": 0.4236,
"step": 2873
},
{
"epoch": 0.74,
"learning_rate": 3.2271842837425917e-06,
"loss": 0.4351,
"step": 2874
},
{
"epoch": 0.75,
"learning_rate": 3.221011556978276e-06,
"loss": 0.4255,
"step": 2875
},
{
"epoch": 0.75,
"learning_rate": 3.214843605781147e-06,
"loss": 0.4109,
"step": 2876
},
{
"epoch": 0.75,
"learning_rate": 3.208680434496312e-06,
"loss": 0.4121,
"step": 2877
},
{
"epoch": 0.75,
"learning_rate": 3.202522047465516e-06,
"loss": 0.4302,
"step": 2878
},
{
"epoch": 0.75,
"learning_rate": 3.1963684490271396e-06,
"loss": 0.4285,
"step": 2879
},
{
"epoch": 0.75,
"learning_rate": 3.1902196435161757e-06,
"loss": 0.45,
"step": 2880
},
{
"epoch": 0.75,
"learning_rate": 3.1840756352642564e-06,
"loss": 0.4214,
"step": 2881
},
{
"epoch": 0.75,
"learning_rate": 3.1779364285996194e-06,
"loss": 0.4409,
"step": 2882
},
{
"epoch": 0.75,
"learning_rate": 3.171802027847135e-06,
"loss": 0.4277,
"step": 2883
},
{
"epoch": 0.75,
"learning_rate": 3.1656724373282743e-06,
"loss": 0.4182,
"step": 2884
},
{
"epoch": 0.75,
"learning_rate": 3.1595476613611265e-06,
"loss": 0.4468,
"step": 2885
},
{
"epoch": 0.75,
"learning_rate": 3.1534277042603943e-06,
"loss": 0.4443,
"step": 2886
},
{
"epoch": 0.75,
"learning_rate": 3.1473125703373707e-06,
"loss": 0.4319,
"step": 2887
},
{
"epoch": 0.75,
"learning_rate": 3.1412022638999682e-06,
"loss": 0.4158,
"step": 2888
},
{
"epoch": 0.75,
"learning_rate": 3.135096789252683e-06,
"loss": 0.4429,
"step": 2889
},
{
"epoch": 0.75,
"learning_rate": 3.1289961506966217e-06,
"loss": 0.428,
"step": 2890
},
{
"epoch": 0.75,
"learning_rate": 3.12290035252947e-06,
"loss": 0.4312,
"step": 2891
},
{
"epoch": 0.75,
"learning_rate": 3.116809399045514e-06,
"loss": 0.4277,
"step": 2892
},
{
"epoch": 0.75,
"learning_rate": 3.110723294535627e-06,
"loss": 0.4275,
"step": 2893
},
{
"epoch": 0.75,
"learning_rate": 3.104642043287256e-06,
"loss": 0.4148,
"step": 2894
},
{
"epoch": 0.75,
"learning_rate": 3.098565649584444e-06,
"loss": 0.4165,
"step": 2895
},
{
"epoch": 0.75,
"learning_rate": 3.092494117707796e-06,
"loss": 0.408,
"step": 2896
},
{
"epoch": 0.75,
"learning_rate": 3.086427451934504e-06,
"loss": 0.417,
"step": 2897
},
{
"epoch": 0.75,
"learning_rate": 3.08036565653833e-06,
"loss": 0.4287,
"step": 2898
},
{
"epoch": 0.75,
"learning_rate": 3.0743087357895986e-06,
"loss": 0.4268,
"step": 2899
},
{
"epoch": 0.75,
"learning_rate": 3.0682566939552103e-06,
"loss": 0.4375,
"step": 2900
},
{
"epoch": 0.75,
"learning_rate": 3.062209535298617e-06,
"loss": 0.4424,
"step": 2901
},
{
"epoch": 0.75,
"learning_rate": 3.0561672640798425e-06,
"loss": 0.4258,
"step": 2902
},
{
"epoch": 0.75,
"learning_rate": 3.050129884555455e-06,
"loss": 0.4448,
"step": 2903
},
{
"epoch": 0.75,
"learning_rate": 3.0440974009785883e-06,
"loss": 0.4141,
"step": 2904
},
{
"epoch": 0.75,
"learning_rate": 3.0380698175989233e-06,
"loss": 0.4214,
"step": 2905
},
{
"epoch": 0.75,
"learning_rate": 3.0320471386626826e-06,
"loss": 0.4097,
"step": 2906
},
{
"epoch": 0.75,
"learning_rate": 3.0260293684126454e-06,
"loss": 0.427,
"step": 2907
},
{
"epoch": 0.75,
"learning_rate": 3.020016511088123e-06,
"loss": 0.407,
"step": 2908
},
{
"epoch": 0.75,
"learning_rate": 3.0140085709249666e-06,
"loss": 0.4253,
"step": 2909
},
{
"epoch": 0.75,
"learning_rate": 3.0080055521555683e-06,
"loss": 0.4358,
"step": 2910
},
{
"epoch": 0.75,
"learning_rate": 3.002007459008852e-06,
"loss": 0.4089,
"step": 2911
},
{
"epoch": 0.75,
"learning_rate": 2.996014295710273e-06,
"loss": 0.4353,
"step": 2912
},
{
"epoch": 0.75,
"learning_rate": 2.990026066481806e-06,
"loss": 0.4553,
"step": 2913
},
{
"epoch": 0.76,
"learning_rate": 2.98404277554196e-06,
"loss": 0.4336,
"step": 2914
},
{
"epoch": 0.76,
"learning_rate": 2.9780644271057556e-06,
"loss": 0.4231,
"step": 2915
},
{
"epoch": 0.76,
"learning_rate": 2.972091025384738e-06,
"loss": 0.4172,
"step": 2916
},
{
"epoch": 0.76,
"learning_rate": 2.9661225745869703e-06,
"loss": 0.4285,
"step": 2917
},
{
"epoch": 0.76,
"learning_rate": 2.9601590789170166e-06,
"loss": 0.4199,
"step": 2918
},
{
"epoch": 0.76,
"learning_rate": 2.9542005425759634e-06,
"loss": 0.4314,
"step": 2919
},
{
"epoch": 0.76,
"learning_rate": 2.9482469697613937e-06,
"loss": 0.4329,
"step": 2920
},
{
"epoch": 0.76,
"learning_rate": 2.942298364667394e-06,
"loss": 0.4346,
"step": 2921
},
{
"epoch": 0.76,
"learning_rate": 2.9363547314845598e-06,
"loss": 0.4304,
"step": 2922
},
{
"epoch": 0.76,
"learning_rate": 2.9304160743999766e-06,
"loss": 0.4297,
"step": 2923
},
{
"epoch": 0.76,
"learning_rate": 2.9244823975972303e-06,
"loss": 0.426,
"step": 2924
},
{
"epoch": 0.76,
"learning_rate": 2.9185537052563926e-06,
"loss": 0.4146,
"step": 2925
},
{
"epoch": 0.76,
"learning_rate": 2.912630001554022e-06,
"loss": 0.4219,
"step": 2926
},
{
"epoch": 0.76,
"learning_rate": 2.9067112906631736e-06,
"loss": 0.4272,
"step": 2927
},
{
"epoch": 0.76,
"learning_rate": 2.9007975767533714e-06,
"loss": 0.4204,
"step": 2928
},
{
"epoch": 0.76,
"learning_rate": 2.8948888639906283e-06,
"loss": 0.4167,
"step": 2929
},
{
"epoch": 0.76,
"learning_rate": 2.8889851565374337e-06,
"loss": 0.4292,
"step": 2930
},
{
"epoch": 0.76,
"learning_rate": 2.8830864585527506e-06,
"loss": 0.4333,
"step": 2931
},
{
"epoch": 0.76,
"learning_rate": 2.8771927741920092e-06,
"loss": 0.4331,
"step": 2932
},
{
"epoch": 0.76,
"learning_rate": 2.8713041076071067e-06,
"loss": 0.4307,
"step": 2933
},
{
"epoch": 0.76,
"learning_rate": 2.865420462946411e-06,
"loss": 0.4319,
"step": 2934
},
{
"epoch": 0.76,
"learning_rate": 2.859541844354752e-06,
"loss": 0.4141,
"step": 2935
},
{
"epoch": 0.76,
"learning_rate": 2.8536682559734188e-06,
"loss": 0.4033,
"step": 2936
},
{
"epoch": 0.76,
"learning_rate": 2.8477997019401517e-06,
"loss": 0.4526,
"step": 2937
},
{
"epoch": 0.76,
"learning_rate": 2.841936186389144e-06,
"loss": 0.4536,
"step": 2938
},
{
"epoch": 0.76,
"learning_rate": 2.8360777134510507e-06,
"loss": 0.4187,
"step": 2939
},
{
"epoch": 0.76,
"learning_rate": 2.830224287252962e-06,
"loss": 0.4575,
"step": 2940
},
{
"epoch": 0.76,
"learning_rate": 2.824375911918418e-06,
"loss": 0.4368,
"step": 2941
},
{
"epoch": 0.76,
"learning_rate": 2.8185325915674023e-06,
"loss": 0.4253,
"step": 2942
},
{
"epoch": 0.76,
"learning_rate": 2.812694330316339e-06,
"loss": 0.4236,
"step": 2943
},
{
"epoch": 0.76,
"learning_rate": 2.8068611322780816e-06,
"loss": 0.4507,
"step": 2944
},
{
"epoch": 0.76,
"learning_rate": 2.801033001561916e-06,
"loss": 0.4395,
"step": 2945
},
{
"epoch": 0.76,
"learning_rate": 2.795209942273569e-06,
"loss": 0.4263,
"step": 2946
},
{
"epoch": 0.76,
"learning_rate": 2.789391958515183e-06,
"loss": 0.4241,
"step": 2947
},
{
"epoch": 0.76,
"learning_rate": 2.7835790543853326e-06,
"loss": 0.4148,
"step": 2948
},
{
"epoch": 0.76,
"learning_rate": 2.7777712339790143e-06,
"loss": 0.4175,
"step": 2949
},
{
"epoch": 0.76,
"learning_rate": 2.771968501387634e-06,
"loss": 0.4365,
"step": 2950
},
{
"epoch": 0.76,
"learning_rate": 2.7661708606990254e-06,
"loss": 0.4485,
"step": 2951
},
{
"epoch": 0.76,
"learning_rate": 2.760378315997425e-06,
"loss": 0.4189,
"step": 2952
},
{
"epoch": 0.77,
"learning_rate": 2.7545908713634863e-06,
"loss": 0.4294,
"step": 2953
},
{
"epoch": 0.77,
"learning_rate": 2.7488085308742694e-06,
"loss": 0.4373,
"step": 2954
},
{
"epoch": 0.77,
"learning_rate": 2.743031298603233e-06,
"loss": 0.4241,
"step": 2955
},
{
"epoch": 0.77,
"learning_rate": 2.737259178620244e-06,
"loss": 0.4097,
"step": 2956
},
{
"epoch": 0.77,
"learning_rate": 2.7314921749915624e-06,
"loss": 0.4463,
"step": 2957
},
{
"epoch": 0.77,
"learning_rate": 2.72573029177985e-06,
"loss": 0.4258,
"step": 2958
},
{
"epoch": 0.77,
"learning_rate": 2.7199735330441523e-06,
"loss": 0.4194,
"step": 2959
},
{
"epoch": 0.77,
"learning_rate": 2.7142219028399143e-06,
"loss": 0.4475,
"step": 2960
},
{
"epoch": 0.77,
"learning_rate": 2.7084754052189665e-06,
"loss": 0.4348,
"step": 2961
},
{
"epoch": 0.77,
"learning_rate": 2.702734044229515e-06,
"loss": 0.4199,
"step": 2962
},
{
"epoch": 0.77,
"learning_rate": 2.696997823916161e-06,
"loss": 0.4187,
"step": 2963
},
{
"epoch": 0.77,
"learning_rate": 2.6912667483198685e-06,
"loss": 0.4438,
"step": 2964
},
{
"epoch": 0.77,
"learning_rate": 2.6855408214779944e-06,
"loss": 0.4194,
"step": 2965
},
{
"epoch": 0.77,
"learning_rate": 2.679820047424253e-06,
"loss": 0.4319,
"step": 2966
},
{
"epoch": 0.77,
"learning_rate": 2.6741044301887377e-06,
"loss": 0.4358,
"step": 2967
},
{
"epoch": 0.77,
"learning_rate": 2.668393973797909e-06,
"loss": 0.4023,
"step": 2968
},
{
"epoch": 0.77,
"learning_rate": 2.662688682274586e-06,
"loss": 0.4143,
"step": 2969
},
{
"epoch": 0.77,
"learning_rate": 2.6569885596379562e-06,
"loss": 0.4402,
"step": 2970
},
{
"epoch": 0.77,
"learning_rate": 2.651293609903559e-06,
"loss": 0.4509,
"step": 2971
},
{
"epoch": 0.77,
"learning_rate": 2.645603837083294e-06,
"loss": 0.4282,
"step": 2972
},
{
"epoch": 0.77,
"learning_rate": 2.639919245185416e-06,
"loss": 0.4265,
"step": 2973
},
{
"epoch": 0.77,
"learning_rate": 2.634239838214523e-06,
"loss": 0.4277,
"step": 2974
},
{
"epoch": 0.77,
"learning_rate": 2.6285656201715694e-06,
"loss": 0.4175,
"step": 2975
},
{
"epoch": 0.77,
"learning_rate": 2.622896595053841e-06,
"loss": 0.4243,
"step": 2976
},
{
"epoch": 0.77,
"learning_rate": 2.6172327668549834e-06,
"loss": 0.4172,
"step": 2977
},
{
"epoch": 0.77,
"learning_rate": 2.6115741395649617e-06,
"loss": 0.4153,
"step": 2978
},
{
"epoch": 0.77,
"learning_rate": 2.605920717170092e-06,
"loss": 0.4338,
"step": 2979
},
{
"epoch": 0.77,
"learning_rate": 2.6002725036530207e-06,
"loss": 0.4395,
"step": 2980
},
{
"epoch": 0.77,
"learning_rate": 2.594629502992716e-06,
"loss": 0.4182,
"step": 2981
},
{
"epoch": 0.77,
"learning_rate": 2.5889917191644864e-06,
"loss": 0.427,
"step": 2982
},
{
"epoch": 0.77,
"learning_rate": 2.5833591561399576e-06,
"loss": 0.4253,
"step": 2983
},
{
"epoch": 0.77,
"learning_rate": 2.5777318178870735e-06,
"loss": 0.4343,
"step": 2984
},
{
"epoch": 0.77,
"learning_rate": 2.5721097083701085e-06,
"loss": 0.4343,
"step": 2985
},
{
"epoch": 0.77,
"learning_rate": 2.566492831549645e-06,
"loss": 0.4221,
"step": 2986
},
{
"epoch": 0.77,
"learning_rate": 2.560881191382587e-06,
"loss": 0.4241,
"step": 2987
},
{
"epoch": 0.77,
"learning_rate": 2.5552747918221387e-06,
"loss": 0.429,
"step": 2988
},
{
"epoch": 0.77,
"learning_rate": 2.549673636817823e-06,
"loss": 0.4026,
"step": 2989
},
{
"epoch": 0.77,
"learning_rate": 2.5440777303154607e-06,
"loss": 0.4253,
"step": 2990
},
{
"epoch": 0.78,
"learning_rate": 2.5384870762571724e-06,
"loss": 0.408,
"step": 2991
},
{
"epoch": 0.78,
"learning_rate": 2.5329016785813965e-06,
"loss": 0.4229,
"step": 2992
},
{
"epoch": 0.78,
"learning_rate": 2.527321541222846e-06,
"loss": 0.4424,
"step": 2993
},
{
"epoch": 0.78,
"learning_rate": 2.5217466681125434e-06,
"loss": 0.4185,
"step": 2994
},
{
"epoch": 0.78,
"learning_rate": 2.516177063177797e-06,
"loss": 0.4329,
"step": 2995
},
{
"epoch": 0.78,
"learning_rate": 2.510612730342199e-06,
"loss": 0.4209,
"step": 2996
},
{
"epoch": 0.78,
"learning_rate": 2.505053673525637e-06,
"loss": 0.4304,
"step": 2997
},
{
"epoch": 0.78,
"learning_rate": 2.4994998966442787e-06,
"loss": 0.4426,
"step": 2998
},
{
"epoch": 0.78,
"learning_rate": 2.493951403610573e-06,
"loss": 0.4131,
"step": 2999
},
{
"epoch": 0.78,
"learning_rate": 2.4884081983332385e-06,
"loss": 0.4297,
"step": 3000
},
{
"epoch": 0.78,
"learning_rate": 2.4828702847172825e-06,
"loss": 0.4255,
"step": 3001
},
{
"epoch": 0.78,
"learning_rate": 2.4773376666639735e-06,
"loss": 0.4377,
"step": 3002
},
{
"epoch": 0.78,
"learning_rate": 2.47181034807085e-06,
"loss": 0.4316,
"step": 3003
},
{
"epoch": 0.78,
"learning_rate": 2.466288332831722e-06,
"loss": 0.4138,
"step": 3004
},
{
"epoch": 0.78,
"learning_rate": 2.460771624836664e-06,
"loss": 0.4248,
"step": 3005
},
{
"epoch": 0.78,
"learning_rate": 2.4552602279720117e-06,
"loss": 0.438,
"step": 3006
},
{
"epoch": 0.78,
"learning_rate": 2.4497541461203546e-06,
"loss": 0.4319,
"step": 3007
},
{
"epoch": 0.78,
"learning_rate": 2.4442533831605352e-06,
"loss": 0.405,
"step": 3008
},
{
"epoch": 0.78,
"learning_rate": 2.4387579429676623e-06,
"loss": 0.4202,
"step": 3009
},
{
"epoch": 0.78,
"learning_rate": 2.4332678294130774e-06,
"loss": 0.4292,
"step": 3010
},
{
"epoch": 0.78,
"learning_rate": 2.42778304636439e-06,
"loss": 0.4189,
"step": 3011
},
{
"epoch": 0.78,
"learning_rate": 2.4223035976854393e-06,
"loss": 0.4126,
"step": 3012
},
{
"epoch": 0.78,
"learning_rate": 2.4168294872363076e-06,
"loss": 0.4438,
"step": 3013
},
{
"epoch": 0.78,
"learning_rate": 2.4113607188733248e-06,
"loss": 0.4167,
"step": 3014
},
{
"epoch": 0.78,
"learning_rate": 2.405897296449047e-06,
"loss": 0.427,
"step": 3015
},
{
"epoch": 0.78,
"learning_rate": 2.4004392238122733e-06,
"loss": 0.4292,
"step": 3016
},
{
"epoch": 0.78,
"learning_rate": 2.394986504808029e-06,
"loss": 0.4316,
"step": 3017
},
{
"epoch": 0.78,
"learning_rate": 2.389539143277574e-06,
"loss": 0.4121,
"step": 3018
},
{
"epoch": 0.78,
"learning_rate": 2.384097143058386e-06,
"loss": 0.4241,
"step": 3019
},
{
"epoch": 0.78,
"learning_rate": 2.3786605079841673e-06,
"loss": 0.4238,
"step": 3020
},
{
"epoch": 0.78,
"learning_rate": 2.3732292418848467e-06,
"loss": 0.4268,
"step": 3021
},
{
"epoch": 0.78,
"learning_rate": 2.3678033485865626e-06,
"loss": 0.4263,
"step": 3022
},
{
"epoch": 0.78,
"learning_rate": 2.362382831911675e-06,
"loss": 0.4326,
"step": 3023
},
{
"epoch": 0.78,
"learning_rate": 2.356967695678757e-06,
"loss": 0.4387,
"step": 3024
},
{
"epoch": 0.78,
"learning_rate": 2.3515579437025813e-06,
"loss": 0.4214,
"step": 3025
},
{
"epoch": 0.78,
"learning_rate": 2.3461535797941416e-06,
"loss": 0.436,
"step": 3026
},
{
"epoch": 0.78,
"learning_rate": 2.3407546077606223e-06,
"loss": 0.4629,
"step": 3027
},
{
"epoch": 0.78,
"learning_rate": 2.335361031405422e-06,
"loss": 0.4006,
"step": 3028
},
{
"epoch": 0.78,
"learning_rate": 2.329972854528123e-06,
"loss": 0.427,
"step": 3029
},
{
"epoch": 0.79,
"learning_rate": 2.3245900809245248e-06,
"loss": 0.427,
"step": 3030
},
{
"epoch": 0.79,
"learning_rate": 2.3192127143866027e-06,
"loss": 0.4268,
"step": 3031
},
{
"epoch": 0.79,
"learning_rate": 2.313840758702527e-06,
"loss": 0.4321,
"step": 3032
},
{
"epoch": 0.79,
"learning_rate": 2.3084742176566623e-06,
"loss": 0.417,
"step": 3033
},
{
"epoch": 0.79,
"learning_rate": 2.303113095029549e-06,
"loss": 0.4177,
"step": 3034
},
{
"epoch": 0.79,
"learning_rate": 2.2977573945979194e-06,
"loss": 0.4058,
"step": 3035
},
{
"epoch": 0.79,
"learning_rate": 2.2924071201346853e-06,
"loss": 0.4329,
"step": 3036
},
{
"epoch": 0.79,
"learning_rate": 2.287062275408929e-06,
"loss": 0.4187,
"step": 3037
},
{
"epoch": 0.79,
"learning_rate": 2.2817228641859157e-06,
"loss": 0.4021,
"step": 3038
},
{
"epoch": 0.79,
"learning_rate": 2.2763888902270735e-06,
"loss": 0.4189,
"step": 3039
},
{
"epoch": 0.79,
"learning_rate": 2.2710603572900137e-06,
"loss": 0.4104,
"step": 3040
},
{
"epoch": 0.79,
"learning_rate": 2.2657372691284997e-06,
"loss": 0.4148,
"step": 3041
},
{
"epoch": 0.79,
"learning_rate": 2.2604196294924696e-06,
"loss": 0.4392,
"step": 3042
},
{
"epoch": 0.79,
"learning_rate": 2.2551074421280226e-06,
"loss": 0.4248,
"step": 3043
},
{
"epoch": 0.79,
"learning_rate": 2.24980071077741e-06,
"loss": 0.4243,
"step": 3044
},
{
"epoch": 0.79,
"learning_rate": 2.2444994391790463e-06,
"loss": 0.4351,
"step": 3045
},
{
"epoch": 0.79,
"learning_rate": 2.2392036310674956e-06,
"loss": 0.4031,
"step": 3046
},
{
"epoch": 0.79,
"learning_rate": 2.233913290173477e-06,
"loss": 0.4573,
"step": 3047
},
{
"epoch": 0.79,
"learning_rate": 2.2286284202238538e-06,
"loss": 0.4258,
"step": 3048
},
{
"epoch": 0.79,
"learning_rate": 2.223349024941638e-06,
"loss": 0.4275,
"step": 3049
},
{
"epoch": 0.79,
"learning_rate": 2.2180751080459874e-06,
"loss": 0.4119,
"step": 3050
},
{
"epoch": 0.79,
"learning_rate": 2.2128066732521915e-06,
"loss": 0.4255,
"step": 3051
},
{
"epoch": 0.79,
"learning_rate": 2.2075437242716903e-06,
"loss": 0.4333,
"step": 3052
},
{
"epoch": 0.79,
"learning_rate": 2.2022862648120456e-06,
"loss": 0.3982,
"step": 3053
},
{
"epoch": 0.79,
"learning_rate": 2.1970342985769645e-06,
"loss": 0.4216,
"step": 3054
},
{
"epoch": 0.79,
"learning_rate": 2.1917878292662785e-06,
"loss": 0.4155,
"step": 3055
},
{
"epoch": 0.79,
"learning_rate": 2.186546860575944e-06,
"loss": 0.4258,
"step": 3056
},
{
"epoch": 0.79,
"learning_rate": 2.1813113961980503e-06,
"loss": 0.429,
"step": 3057
},
{
"epoch": 0.79,
"learning_rate": 2.1760814398207986e-06,
"loss": 0.4109,
"step": 3058
},
{
"epoch": 0.79,
"learning_rate": 2.170856995128521e-06,
"loss": 0.4009,
"step": 3059
},
{
"epoch": 0.79,
"learning_rate": 2.1656380658016553e-06,
"loss": 0.4167,
"step": 3060
},
{
"epoch": 0.79,
"learning_rate": 2.160424655516764e-06,
"loss": 0.4304,
"step": 3061
},
{
"epoch": 0.79,
"learning_rate": 2.1552167679465196e-06,
"loss": 0.4431,
"step": 3062
},
{
"epoch": 0.79,
"learning_rate": 2.150014406759697e-06,
"loss": 0.4312,
"step": 3063
},
{
"epoch": 0.79,
"learning_rate": 2.1448175756211874e-06,
"loss": 0.4104,
"step": 3064
},
{
"epoch": 0.79,
"learning_rate": 2.139626278191981e-06,
"loss": 0.4016,
"step": 3065
},
{
"epoch": 0.79,
"learning_rate": 2.1344405181291662e-06,
"loss": 0.4404,
"step": 3066
},
{
"epoch": 0.79,
"learning_rate": 2.129260299085939e-06,
"loss": 0.4055,
"step": 3067
},
{
"epoch": 0.8,
"learning_rate": 2.124085624711587e-06,
"loss": 0.4236,
"step": 3068
},
{
"epoch": 0.8,
"learning_rate": 2.118916498651494e-06,
"loss": 0.425,
"step": 3069
},
{
"epoch": 0.8,
"learning_rate": 2.1137529245471345e-06,
"loss": 0.4148,
"step": 3070
},
{
"epoch": 0.8,
"learning_rate": 2.1085949060360654e-06,
"loss": 0.4231,
"step": 3071
},
{
"epoch": 0.8,
"learning_rate": 2.10344244675194e-06,
"loss": 0.4294,
"step": 3072
},
{
"epoch": 0.8,
"learning_rate": 2.0982955503244895e-06,
"loss": 0.4219,
"step": 3073
},
{
"epoch": 0.8,
"learning_rate": 2.0931542203795306e-06,
"loss": 0.4036,
"step": 3074
},
{
"epoch": 0.8,
"learning_rate": 2.088018460538952e-06,
"loss": 0.4241,
"step": 3075
},
{
"epoch": 0.8,
"learning_rate": 2.0828882744207255e-06,
"loss": 0.4097,
"step": 3076
},
{
"epoch": 0.8,
"learning_rate": 2.077763665638891e-06,
"loss": 0.4155,
"step": 3077
},
{
"epoch": 0.8,
"learning_rate": 2.0726446378035593e-06,
"loss": 0.4355,
"step": 3078
},
{
"epoch": 0.8,
"learning_rate": 2.0675311945209142e-06,
"loss": 0.4524,
"step": 3079
},
{
"epoch": 0.8,
"learning_rate": 2.0624233393932024e-06,
"loss": 0.4185,
"step": 3080
},
{
"epoch": 0.8,
"learning_rate": 2.0573210760187368e-06,
"loss": 0.4153,
"step": 3081
},
{
"epoch": 0.8,
"learning_rate": 2.0522244079918876e-06,
"loss": 0.4561,
"step": 3082
},
{
"epoch": 0.8,
"learning_rate": 2.04713333890308e-06,
"loss": 0.4465,
"step": 3083
},
{
"epoch": 0.8,
"learning_rate": 2.042047872338805e-06,
"loss": 0.4263,
"step": 3084
},
{
"epoch": 0.8,
"learning_rate": 2.036968011881596e-06,
"loss": 0.4353,
"step": 3085
},
{
"epoch": 0.8,
"learning_rate": 2.0318937611100454e-06,
"loss": 0.4187,
"step": 3086
},
{
"epoch": 0.8,
"learning_rate": 2.02682512359879e-06,
"loss": 0.4204,
"step": 3087
},
{
"epoch": 0.8,
"learning_rate": 2.021762102918515e-06,
"loss": 0.4299,
"step": 3088
},
{
"epoch": 0.8,
"learning_rate": 2.0167047026359456e-06,
"loss": 0.4224,
"step": 3089
},
{
"epoch": 0.8,
"learning_rate": 2.011652926313844e-06,
"loss": 0.4128,
"step": 3090
},
{
"epoch": 0.8,
"learning_rate": 2.0066067775110187e-06,
"loss": 0.4285,
"step": 3091
},
{
"epoch": 0.8,
"learning_rate": 2.0015662597823104e-06,
"loss": 0.4351,
"step": 3092
},
{
"epoch": 0.8,
"learning_rate": 1.9965313766785943e-06,
"loss": 0.4192,
"step": 3093
},
{
"epoch": 0.8,
"learning_rate": 1.991502131746773e-06,
"loss": 0.405,
"step": 3094
},
{
"epoch": 0.8,
"learning_rate": 1.986478528529776e-06,
"loss": 0.3977,
"step": 3095
},
{
"epoch": 0.8,
"learning_rate": 1.981460570566566e-06,
"loss": 0.3933,
"step": 3096
},
{
"epoch": 0.8,
"learning_rate": 1.976448261392119e-06,
"loss": 0.4133,
"step": 3097
},
{
"epoch": 0.8,
"learning_rate": 1.9714416045374395e-06,
"loss": 0.4324,
"step": 3098
},
{
"epoch": 0.8,
"learning_rate": 1.9664406035295493e-06,
"loss": 0.4272,
"step": 3099
},
{
"epoch": 0.8,
"learning_rate": 1.961445261891479e-06,
"loss": 0.4219,
"step": 3100
},
{
"epoch": 0.8,
"learning_rate": 1.9564555831422826e-06,
"loss": 0.4336,
"step": 3101
},
{
"epoch": 0.8,
"learning_rate": 1.9514715707970134e-06,
"loss": 0.4192,
"step": 3102
},
{
"epoch": 0.8,
"learning_rate": 1.946493228366745e-06,
"loss": 0.4377,
"step": 3103
},
{
"epoch": 0.8,
"learning_rate": 1.941520559358544e-06,
"loss": 0.406,
"step": 3104
},
{
"epoch": 0.8,
"learning_rate": 1.9365535672754907e-06,
"loss": 0.4202,
"step": 3105
},
{
"epoch": 0.8,
"learning_rate": 1.9315922556166656e-06,
"loss": 0.4241,
"step": 3106
},
{
"epoch": 0.81,
"learning_rate": 1.9266366278771377e-06,
"loss": 0.4126,
"step": 3107
},
{
"epoch": 0.81,
"learning_rate": 1.9216866875479836e-06,
"loss": 0.4062,
"step": 3108
},
{
"epoch": 0.81,
"learning_rate": 1.916742438116265e-06,
"loss": 0.4128,
"step": 3109
},
{
"epoch": 0.81,
"learning_rate": 1.9118038830650376e-06,
"loss": 0.4204,
"step": 3110
},
{
"epoch": 0.81,
"learning_rate": 1.9068710258733491e-06,
"loss": 0.4072,
"step": 3111
},
{
"epoch": 0.81,
"learning_rate": 1.9019438700162262e-06,
"loss": 0.4443,
"step": 3112
},
{
"epoch": 0.81,
"learning_rate": 1.897022418964687e-06,
"loss": 0.4033,
"step": 3113
},
{
"epoch": 0.81,
"learning_rate": 1.892106676185722e-06,
"loss": 0.4146,
"step": 3114
},
{
"epoch": 0.81,
"learning_rate": 1.8871966451423097e-06,
"loss": 0.4138,
"step": 3115
},
{
"epoch": 0.81,
"learning_rate": 1.8822923292933948e-06,
"loss": 0.408,
"step": 3116
},
{
"epoch": 0.81,
"learning_rate": 1.877393732093904e-06,
"loss": 0.4128,
"step": 3117
},
{
"epoch": 0.81,
"learning_rate": 1.8725008569947366e-06,
"loss": 0.4382,
"step": 3118
},
{
"epoch": 0.81,
"learning_rate": 1.8676137074427502e-06,
"loss": 0.4297,
"step": 3119
},
{
"epoch": 0.81,
"learning_rate": 1.8627322868807817e-06,
"loss": 0.4338,
"step": 3120
},
{
"epoch": 0.81,
"learning_rate": 1.8578565987476215e-06,
"loss": 0.4314,
"step": 3121
},
{
"epoch": 0.81,
"learning_rate": 1.85298664647803e-06,
"loss": 0.4312,
"step": 3122
},
{
"epoch": 0.81,
"learning_rate": 1.8481224335027182e-06,
"loss": 0.4307,
"step": 3123
},
{
"epoch": 0.81,
"learning_rate": 1.843263963248364e-06,
"loss": 0.4302,
"step": 3124
},
{
"epoch": 0.81,
"learning_rate": 1.8384112391375942e-06,
"loss": 0.4126,
"step": 3125
},
{
"epoch": 0.81,
"learning_rate": 1.833564264588984e-06,
"loss": 0.4207,
"step": 3126
},
{
"epoch": 0.81,
"learning_rate": 1.8287230430170688e-06,
"loss": 0.449,
"step": 3127
},
{
"epoch": 0.81,
"learning_rate": 1.8238875778323185e-06,
"loss": 0.4124,
"step": 3128
},
{
"epoch": 0.81,
"learning_rate": 1.8190578724411567e-06,
"loss": 0.4326,
"step": 3129
},
{
"epoch": 0.81,
"learning_rate": 1.81423393024595e-06,
"loss": 0.4163,
"step": 3130
},
{
"epoch": 0.81,
"learning_rate": 1.8094157546449965e-06,
"loss": 0.4285,
"step": 3131
},
{
"epoch": 0.81,
"learning_rate": 1.8046033490325422e-06,
"loss": 0.4055,
"step": 3132
},
{
"epoch": 0.81,
"learning_rate": 1.7997967167987585e-06,
"loss": 0.4233,
"step": 3133
},
{
"epoch": 0.81,
"learning_rate": 1.7949958613297602e-06,
"loss": 0.4375,
"step": 3134
},
{
"epoch": 0.81,
"learning_rate": 1.7902007860075809e-06,
"loss": 0.4077,
"step": 3135
},
{
"epoch": 0.81,
"learning_rate": 1.7854114942101909e-06,
"loss": 0.4448,
"step": 3136
},
{
"epoch": 0.81,
"learning_rate": 1.7806279893114874e-06,
"loss": 0.4446,
"step": 3137
},
{
"epoch": 0.81,
"learning_rate": 1.7758502746812811e-06,
"loss": 0.4041,
"step": 3138
},
{
"epoch": 0.81,
"learning_rate": 1.7710783536853149e-06,
"loss": 0.4272,
"step": 3139
},
{
"epoch": 0.81,
"learning_rate": 1.766312229685243e-06,
"loss": 0.4221,
"step": 3140
},
{
"epoch": 0.81,
"learning_rate": 1.7615519060386355e-06,
"loss": 0.4175,
"step": 3141
},
{
"epoch": 0.81,
"learning_rate": 1.7567973860989806e-06,
"loss": 0.4233,
"step": 3142
},
{
"epoch": 0.81,
"learning_rate": 1.7520486732156772e-06,
"loss": 0.4263,
"step": 3143
},
{
"epoch": 0.81,
"learning_rate": 1.7473057707340334e-06,
"loss": 0.4299,
"step": 3144
},
{
"epoch": 0.81,
"learning_rate": 1.7425686819952591e-06,
"loss": 0.418,
"step": 3145
},
{
"epoch": 0.82,
"learning_rate": 1.737837410336477e-06,
"loss": 0.4302,
"step": 3146
},
{
"epoch": 0.82,
"learning_rate": 1.733111959090702e-06,
"loss": 0.416,
"step": 3147
},
{
"epoch": 0.82,
"learning_rate": 1.7283923315868577e-06,
"loss": 0.4084,
"step": 3148
},
{
"epoch": 0.82,
"learning_rate": 1.723678531149763e-06,
"loss": 0.4141,
"step": 3149
},
{
"epoch": 0.82,
"learning_rate": 1.718970561100125e-06,
"loss": 0.406,
"step": 3150
},
{
"epoch": 0.82,
"learning_rate": 1.7142684247545537e-06,
"loss": 0.4143,
"step": 3151
},
{
"epoch": 0.82,
"learning_rate": 1.7095721254255437e-06,
"loss": 0.4243,
"step": 3152
},
{
"epoch": 0.82,
"learning_rate": 1.704881666421474e-06,
"loss": 0.4114,
"step": 3153
},
{
"epoch": 0.82,
"learning_rate": 1.7001970510466171e-06,
"loss": 0.4099,
"step": 3154
},
{
"epoch": 0.82,
"learning_rate": 1.6955182826011252e-06,
"loss": 0.4236,
"step": 3155
},
{
"epoch": 0.82,
"learning_rate": 1.6908453643810342e-06,
"loss": 0.405,
"step": 3156
},
{
"epoch": 0.82,
"learning_rate": 1.6861782996782538e-06,
"loss": 0.4395,
"step": 3157
},
{
"epoch": 0.82,
"learning_rate": 1.6815170917805711e-06,
"loss": 0.4138,
"step": 3158
},
{
"epoch": 0.82,
"learning_rate": 1.676861743971653e-06,
"loss": 0.4333,
"step": 3159
},
{
"epoch": 0.82,
"learning_rate": 1.6722122595310286e-06,
"loss": 0.4045,
"step": 3160
},
{
"epoch": 0.82,
"learning_rate": 1.6675686417341042e-06,
"loss": 0.4294,
"step": 3161
},
{
"epoch": 0.82,
"learning_rate": 1.6629308938521528e-06,
"loss": 0.437,
"step": 3162
},
{
"epoch": 0.82,
"learning_rate": 1.6582990191523097e-06,
"loss": 0.4014,
"step": 3163
},
{
"epoch": 0.82,
"learning_rate": 1.6536730208975738e-06,
"loss": 0.4463,
"step": 3164
},
{
"epoch": 0.82,
"learning_rate": 1.6490529023467993e-06,
"loss": 0.4216,
"step": 3165
},
{
"epoch": 0.82,
"learning_rate": 1.6444386667547063e-06,
"loss": 0.425,
"step": 3166
},
{
"epoch": 0.82,
"learning_rate": 1.6398303173718667e-06,
"loss": 0.427,
"step": 3167
},
{
"epoch": 0.82,
"learning_rate": 1.635227857444709e-06,
"loss": 0.449,
"step": 3168
},
{
"epoch": 0.82,
"learning_rate": 1.6306312902155075e-06,
"loss": 0.4258,
"step": 3169
},
{
"epoch": 0.82,
"learning_rate": 1.6260406189223854e-06,
"loss": 0.4233,
"step": 3170
},
{
"epoch": 0.82,
"learning_rate": 1.621455846799318e-06,
"loss": 0.4226,
"step": 3171
},
{
"epoch": 0.82,
"learning_rate": 1.6168769770761194e-06,
"loss": 0.4158,
"step": 3172
},
{
"epoch": 0.82,
"learning_rate": 1.6123040129784484e-06,
"loss": 0.4131,
"step": 3173
},
{
"epoch": 0.82,
"learning_rate": 1.6077369577278035e-06,
"loss": 0.4199,
"step": 3174
},
{
"epoch": 0.82,
"learning_rate": 1.6031758145415222e-06,
"loss": 0.415,
"step": 3175
},
{
"epoch": 0.82,
"learning_rate": 1.5986205866327732e-06,
"loss": 0.4065,
"step": 3176
},
{
"epoch": 0.82,
"learning_rate": 1.5940712772105572e-06,
"loss": 0.4097,
"step": 3177
},
{
"epoch": 0.82,
"learning_rate": 1.589527889479713e-06,
"loss": 0.4014,
"step": 3178
},
{
"epoch": 0.82,
"learning_rate": 1.5849904266408978e-06,
"loss": 0.4329,
"step": 3179
},
{
"epoch": 0.82,
"learning_rate": 1.5804588918906028e-06,
"loss": 0.4084,
"step": 3180
},
{
"epoch": 0.82,
"learning_rate": 1.575933288421142e-06,
"loss": 0.3938,
"step": 3181
},
{
"epoch": 0.82,
"learning_rate": 1.5714136194206464e-06,
"loss": 0.4236,
"step": 3182
},
{
"epoch": 0.82,
"learning_rate": 1.5668998880730735e-06,
"loss": 0.4153,
"step": 3183
},
{
"epoch": 0.83,
"learning_rate": 1.5623920975581874e-06,
"loss": 0.4307,
"step": 3184
},
{
"epoch": 0.83,
"learning_rate": 1.557890251051578e-06,
"loss": 0.4146,
"step": 3185
},
{
"epoch": 0.83,
"learning_rate": 1.553394351724644e-06,
"loss": 0.4329,
"step": 3186
},
{
"epoch": 0.83,
"learning_rate": 1.548904402744591e-06,
"loss": 0.4099,
"step": 3187
},
{
"epoch": 0.83,
"learning_rate": 1.5444204072744385e-06,
"loss": 0.4141,
"step": 3188
},
{
"epoch": 0.83,
"learning_rate": 1.5399423684730052e-06,
"loss": 0.418,
"step": 3189
},
{
"epoch": 0.83,
"learning_rate": 1.5354702894949214e-06,
"loss": 0.4473,
"step": 3190
},
{
"epoch": 0.83,
"learning_rate": 1.531004173490611e-06,
"loss": 0.4053,
"step": 3191
},
{
"epoch": 0.83,
"learning_rate": 1.5265440236063035e-06,
"loss": 0.4189,
"step": 3192
},
{
"epoch": 0.83,
"learning_rate": 1.5220898429840236e-06,
"loss": 0.4275,
"step": 3193
},
{
"epoch": 0.83,
"learning_rate": 1.5176416347615886e-06,
"loss": 0.4158,
"step": 3194
},
{
"epoch": 0.83,
"learning_rate": 1.5131994020726127e-06,
"loss": 0.4226,
"step": 3195
},
{
"epoch": 0.83,
"learning_rate": 1.5087631480464936e-06,
"loss": 0.405,
"step": 3196
},
{
"epoch": 0.83,
"learning_rate": 1.5043328758084274e-06,
"loss": 0.4082,
"step": 3197
},
{
"epoch": 0.83,
"learning_rate": 1.499908588479384e-06,
"loss": 0.4365,
"step": 3198
},
{
"epoch": 0.83,
"learning_rate": 1.495490289176128e-06,
"loss": 0.4019,
"step": 3199
},
{
"epoch": 0.83,
"learning_rate": 1.4910779810112019e-06,
"loss": 0.4204,
"step": 3200
},
{
"epoch": 0.83,
"learning_rate": 1.4866716670929226e-06,
"loss": 0.4109,
"step": 3201
},
{
"epoch": 0.83,
"learning_rate": 1.4822713505253938e-06,
"loss": 0.4053,
"step": 3202
},
{
"epoch": 0.83,
"learning_rate": 1.4778770344084848e-06,
"loss": 0.4114,
"step": 3203
},
{
"epoch": 0.83,
"learning_rate": 1.4734887218378435e-06,
"loss": 0.4172,
"step": 3204
},
{
"epoch": 0.83,
"learning_rate": 1.4691064159048907e-06,
"loss": 0.4648,
"step": 3205
},
{
"epoch": 0.83,
"learning_rate": 1.4647301196968055e-06,
"loss": 0.395,
"step": 3206
},
{
"epoch": 0.83,
"learning_rate": 1.4603598362965465e-06,
"loss": 0.4177,
"step": 3207
},
{
"epoch": 0.83,
"learning_rate": 1.4559955687828242e-06,
"loss": 0.4028,
"step": 3208
},
{
"epoch": 0.83,
"learning_rate": 1.4516373202301216e-06,
"loss": 0.4292,
"step": 3209
},
{
"epoch": 0.83,
"learning_rate": 1.4472850937086736e-06,
"loss": 0.4175,
"step": 3210
},
{
"epoch": 0.83,
"learning_rate": 1.4429388922844756e-06,
"loss": 0.4219,
"step": 3211
},
{
"epoch": 0.83,
"learning_rate": 1.438598719019284e-06,
"loss": 0.4294,
"step": 3212
},
{
"epoch": 0.83,
"learning_rate": 1.4342645769705977e-06,
"loss": 0.4382,
"step": 3213
},
{
"epoch": 0.83,
"learning_rate": 1.4299364691916773e-06,
"loss": 0.4209,
"step": 3214
},
{
"epoch": 0.83,
"learning_rate": 1.4256143987315253e-06,
"loss": 0.438,
"step": 3215
},
{
"epoch": 0.83,
"learning_rate": 1.4212983686348913e-06,
"loss": 0.4211,
"step": 3216
},
{
"epoch": 0.83,
"learning_rate": 1.4169883819422736e-06,
"loss": 0.4292,
"step": 3217
},
{
"epoch": 0.83,
"learning_rate": 1.4126844416899132e-06,
"loss": 0.4377,
"step": 3218
},
{
"epoch": 0.83,
"learning_rate": 1.4083865509097916e-06,
"loss": 0.4248,
"step": 3219
},
{
"epoch": 0.83,
"learning_rate": 1.404094712629621e-06,
"loss": 0.4175,
"step": 3220
},
{
"epoch": 0.83,
"learning_rate": 1.3998089298728624e-06,
"loss": 0.4185,
"step": 3221
},
{
"epoch": 0.83,
"learning_rate": 1.3955292056587e-06,
"loss": 0.4141,
"step": 3222
},
{
"epoch": 0.84,
"learning_rate": 1.3912555430020501e-06,
"loss": 0.4226,
"step": 3223
},
{
"epoch": 0.84,
"learning_rate": 1.3869879449135736e-06,
"loss": 0.4348,
"step": 3224
},
{
"epoch": 0.84,
"learning_rate": 1.38272641439964e-06,
"loss": 0.4138,
"step": 3225
},
{
"epoch": 0.84,
"learning_rate": 1.3784709544623575e-06,
"loss": 0.4258,
"step": 3226
},
{
"epoch": 0.84,
"learning_rate": 1.3742215680995507e-06,
"loss": 0.4087,
"step": 3227
},
{
"epoch": 0.84,
"learning_rate": 1.3699782583047672e-06,
"loss": 0.4275,
"step": 3228
},
{
"epoch": 0.84,
"learning_rate": 1.3657410280672757e-06,
"loss": 0.4521,
"step": 3229
},
{
"epoch": 0.84,
"learning_rate": 1.3615098803720606e-06,
"loss": 0.4128,
"step": 3230
},
{
"epoch": 0.84,
"learning_rate": 1.3572848181998255e-06,
"loss": 0.4509,
"step": 3231
},
{
"epoch": 0.84,
"learning_rate": 1.3530658445269784e-06,
"loss": 0.4023,
"step": 3232
},
{
"epoch": 0.84,
"learning_rate": 1.3488529623256464e-06,
"loss": 0.425,
"step": 3233
},
{
"epoch": 0.84,
"learning_rate": 1.3446461745636608e-06,
"loss": 0.4014,
"step": 3234
},
{
"epoch": 0.84,
"learning_rate": 1.3404454842045578e-06,
"loss": 0.4138,
"step": 3235
},
{
"epoch": 0.84,
"learning_rate": 1.3362508942075836e-06,
"loss": 0.4272,
"step": 3236
},
{
"epoch": 0.84,
"learning_rate": 1.3320624075276844e-06,
"loss": 0.4214,
"step": 3237
},
{
"epoch": 0.84,
"learning_rate": 1.327880027115509e-06,
"loss": 0.4304,
"step": 3238
},
{
"epoch": 0.84,
"learning_rate": 1.3237037559174016e-06,
"loss": 0.4187,
"step": 3239
},
{
"epoch": 0.84,
"learning_rate": 1.3195335968753985e-06,
"loss": 0.4114,
"step": 3240
},
{
"epoch": 0.84,
"learning_rate": 1.3153695529272415e-06,
"loss": 0.4236,
"step": 3241
},
{
"epoch": 0.84,
"learning_rate": 1.3112116270063512e-06,
"loss": 0.4014,
"step": 3242
},
{
"epoch": 0.84,
"learning_rate": 1.307059822041854e-06,
"loss": 0.4133,
"step": 3243
},
{
"epoch": 0.84,
"learning_rate": 1.3029141409585521e-06,
"loss": 0.4023,
"step": 3244
},
{
"epoch": 0.84,
"learning_rate": 1.2987745866769319e-06,
"loss": 0.4141,
"step": 3245
},
{
"epoch": 0.84,
"learning_rate": 1.2946411621131772e-06,
"loss": 0.4417,
"step": 3246
},
{
"epoch": 0.84,
"learning_rate": 1.2905138701791376e-06,
"loss": 0.4187,
"step": 3247
},
{
"epoch": 0.84,
"learning_rate": 1.286392713782354e-06,
"loss": 0.3997,
"step": 3248
},
{
"epoch": 0.84,
"learning_rate": 1.2822776958260397e-06,
"loss": 0.4197,
"step": 3249
},
{
"epoch": 0.84,
"learning_rate": 1.278168819209089e-06,
"loss": 0.4031,
"step": 3250
},
{
"epoch": 0.84,
"learning_rate": 1.2740660868260634e-06,
"loss": 0.4429,
"step": 3251
},
{
"epoch": 0.84,
"learning_rate": 1.2699695015671965e-06,
"loss": 0.4111,
"step": 3252
},
{
"epoch": 0.84,
"learning_rate": 1.2658790663183962e-06,
"loss": 0.4053,
"step": 3253
},
{
"epoch": 0.84,
"learning_rate": 1.2617947839612333e-06,
"loss": 0.4248,
"step": 3254
},
{
"epoch": 0.84,
"learning_rate": 1.2577166573729471e-06,
"loss": 0.4121,
"step": 3255
},
{
"epoch": 0.84,
"learning_rate": 1.2536446894264408e-06,
"loss": 0.4275,
"step": 3256
},
{
"epoch": 0.84,
"learning_rate": 1.2495788829902733e-06,
"loss": 0.4121,
"step": 3257
},
{
"epoch": 0.84,
"learning_rate": 1.2455192409286733e-06,
"loss": 0.4163,
"step": 3258
},
{
"epoch": 0.84,
"learning_rate": 1.241465766101515e-06,
"loss": 0.4265,
"step": 3259
},
{
"epoch": 0.84,
"learning_rate": 1.237418461364338e-06,
"loss": 0.4321,
"step": 3260
},
{
"epoch": 0.85,
"learning_rate": 1.233377329568325e-06,
"loss": 0.4363,
"step": 3261
},
{
"epoch": 0.85,
"learning_rate": 1.229342373560325e-06,
"loss": 0.4177,
"step": 3262
},
{
"epoch": 0.85,
"learning_rate": 1.2253135961828233e-06,
"loss": 0.4419,
"step": 3263
},
{
"epoch": 0.85,
"learning_rate": 1.2212910002739531e-06,
"loss": 0.4202,
"step": 3264
},
{
"epoch": 0.85,
"learning_rate": 1.217274588667503e-06,
"loss": 0.439,
"step": 3265
},
{
"epoch": 0.85,
"learning_rate": 1.2132643641928931e-06,
"loss": 0.4065,
"step": 3266
},
{
"epoch": 0.85,
"learning_rate": 1.2092603296751926e-06,
"loss": 0.4216,
"step": 3267
},
{
"epoch": 0.85,
"learning_rate": 1.2052624879351105e-06,
"loss": 0.4141,
"step": 3268
},
{
"epoch": 0.85,
"learning_rate": 1.2012708417889852e-06,
"loss": 0.4185,
"step": 3269
},
{
"epoch": 0.85,
"learning_rate": 1.1972853940488017e-06,
"loss": 0.4097,
"step": 3270
},
{
"epoch": 0.85,
"learning_rate": 1.1933061475221675e-06,
"loss": 0.4248,
"step": 3271
},
{
"epoch": 0.85,
"learning_rate": 1.1893331050123314e-06,
"loss": 0.4099,
"step": 3272
},
{
"epoch": 0.85,
"learning_rate": 1.185366269318161e-06,
"loss": 0.4553,
"step": 3273
},
{
"epoch": 0.85,
"learning_rate": 1.1814056432341625e-06,
"loss": 0.4324,
"step": 3274
},
{
"epoch": 0.85,
"learning_rate": 1.1774512295504615e-06,
"loss": 0.4414,
"step": 3275
},
{
"epoch": 0.85,
"learning_rate": 1.173503031052806e-06,
"loss": 0.4031,
"step": 3276
},
{
"epoch": 0.85,
"learning_rate": 1.1695610505225708e-06,
"loss": 0.425,
"step": 3277
},
{
"epoch": 0.85,
"learning_rate": 1.165625290736745e-06,
"loss": 0.4265,
"step": 3278
},
{
"epoch": 0.85,
"learning_rate": 1.1616957544679396e-06,
"loss": 0.4243,
"step": 3279
},
{
"epoch": 0.85,
"learning_rate": 1.1577724444843764e-06,
"loss": 0.4194,
"step": 3280
},
{
"epoch": 0.85,
"learning_rate": 1.1538553635498951e-06,
"loss": 0.4187,
"step": 3281
},
{
"epoch": 0.85,
"learning_rate": 1.1499445144239507e-06,
"loss": 0.4282,
"step": 3282
},
{
"epoch": 0.85,
"learning_rate": 1.1460398998615974e-06,
"loss": 0.406,
"step": 3283
},
{
"epoch": 0.85,
"learning_rate": 1.142141522613508e-06,
"loss": 0.4307,
"step": 3284
},
{
"epoch": 0.85,
"learning_rate": 1.1382493854259535e-06,
"loss": 0.4087,
"step": 3285
},
{
"epoch": 0.85,
"learning_rate": 1.1343634910408142e-06,
"loss": 0.4167,
"step": 3286
},
{
"epoch": 0.85,
"learning_rate": 1.1304838421955732e-06,
"loss": 0.4067,
"step": 3287
},
{
"epoch": 0.85,
"learning_rate": 1.126610441623306e-06,
"loss": 0.4167,
"step": 3288
},
{
"epoch": 0.85,
"learning_rate": 1.122743292052697e-06,
"loss": 0.4336,
"step": 3289
},
{
"epoch": 0.85,
"learning_rate": 1.1188823962080163e-06,
"loss": 0.418,
"step": 3290
},
{
"epoch": 0.85,
"learning_rate": 1.1150277568091405e-06,
"loss": 0.4124,
"step": 3291
},
{
"epoch": 0.85,
"learning_rate": 1.111179376571525e-06,
"loss": 0.4148,
"step": 3292
},
{
"epoch": 0.85,
"learning_rate": 1.107337258206228e-06,
"loss": 0.4109,
"step": 3293
},
{
"epoch": 0.85,
"learning_rate": 1.1035014044198921e-06,
"loss": 0.4045,
"step": 3294
},
{
"epoch": 0.85,
"learning_rate": 1.0996718179147413e-06,
"loss": 0.4351,
"step": 3295
},
{
"epoch": 0.85,
"learning_rate": 1.0958485013885944e-06,
"loss": 0.4294,
"step": 3296
},
{
"epoch": 0.85,
"learning_rate": 1.0920314575348456e-06,
"loss": 0.3984,
"step": 3297
},
{
"epoch": 0.85,
"learning_rate": 1.0882206890424707e-06,
"loss": 0.4229,
"step": 3298
},
{
"epoch": 0.85,
"learning_rate": 1.084416198596029e-06,
"loss": 0.4185,
"step": 3299
},
{
"epoch": 0.86,
"learning_rate": 1.0806179888756551e-06,
"loss": 0.4597,
"step": 3300
},
{
"epoch": 0.86,
"learning_rate": 1.0768260625570592e-06,
"loss": 0.4312,
"step": 3301
},
{
"epoch": 0.86,
"learning_rate": 1.0730404223115243e-06,
"loss": 0.4045,
"step": 3302
},
{
"epoch": 0.86,
"learning_rate": 1.0692610708059037e-06,
"loss": 0.4153,
"step": 3303
},
{
"epoch": 0.86,
"learning_rate": 1.0654880107026222e-06,
"loss": 0.417,
"step": 3304
},
{
"epoch": 0.86,
"learning_rate": 1.0617212446596736e-06,
"loss": 0.4082,
"step": 3305
},
{
"epoch": 0.86,
"learning_rate": 1.0579607753306198e-06,
"loss": 0.449,
"step": 3306
},
{
"epoch": 0.86,
"learning_rate": 1.0542066053645784e-06,
"loss": 0.4194,
"step": 3307
},
{
"epoch": 0.86,
"learning_rate": 1.0504587374062392e-06,
"loss": 0.4287,
"step": 3308
},
{
"epoch": 0.86,
"learning_rate": 1.0467171740958449e-06,
"loss": 0.3904,
"step": 3309
},
{
"epoch": 0.86,
"learning_rate": 1.042981918069199e-06,
"loss": 0.4158,
"step": 3310
},
{
"epoch": 0.86,
"learning_rate": 1.039252971957665e-06,
"loss": 0.4451,
"step": 3311
},
{
"epoch": 0.86,
"learning_rate": 1.0355303383881577e-06,
"loss": 0.4248,
"step": 3312
},
{
"epoch": 0.86,
"learning_rate": 1.0318140199831473e-06,
"loss": 0.4106,
"step": 3313
},
{
"epoch": 0.86,
"learning_rate": 1.028104019360654e-06,
"loss": 0.4153,
"step": 3314
},
{
"epoch": 0.86,
"learning_rate": 1.0244003391342439e-06,
"loss": 0.4106,
"step": 3315
},
{
"epoch": 0.86,
"learning_rate": 1.0207029819130388e-06,
"loss": 0.4167,
"step": 3316
},
{
"epoch": 0.86,
"learning_rate": 1.017011950301696e-06,
"loss": 0.4277,
"step": 3317
},
{
"epoch": 0.86,
"learning_rate": 1.0133272469004264e-06,
"loss": 0.4255,
"step": 3318
},
{
"epoch": 0.86,
"learning_rate": 1.009648874304976e-06,
"loss": 0.4011,
"step": 3319
},
{
"epoch": 0.86,
"learning_rate": 1.0059768351066356e-06,
"loss": 0.4373,
"step": 3320
},
{
"epoch": 0.86,
"learning_rate": 1.0023111318922308e-06,
"loss": 0.4446,
"step": 3321
},
{
"epoch": 0.86,
"learning_rate": 9.986517672441243e-07,
"loss": 0.4253,
"step": 3322
},
{
"epoch": 0.86,
"learning_rate": 9.949987437402132e-07,
"loss": 0.4087,
"step": 3323
},
{
"epoch": 0.86,
"learning_rate": 9.913520639539321e-07,
"loss": 0.4128,
"step": 3324
},
{
"epoch": 0.86,
"learning_rate": 9.877117304542416e-07,
"loss": 0.4006,
"step": 3325
},
{
"epoch": 0.86,
"learning_rate": 9.840777458056339e-07,
"loss": 0.4348,
"step": 3326
},
{
"epoch": 0.86,
"learning_rate": 9.804501125681243e-07,
"loss": 0.4158,
"step": 3327
},
{
"epoch": 0.86,
"learning_rate": 9.76828833297261e-07,
"loss": 0.4216,
"step": 3328
},
{
"epoch": 0.86,
"learning_rate": 9.732139105441097e-07,
"loss": 0.3823,
"step": 3329
},
{
"epoch": 0.86,
"learning_rate": 9.696053468552614e-07,
"loss": 0.4258,
"step": 3330
},
{
"epoch": 0.86,
"learning_rate": 9.660031447728292e-07,
"loss": 0.4041,
"step": 3331
},
{
"epoch": 0.86,
"learning_rate": 9.624073068344385e-07,
"loss": 0.4285,
"step": 3332
},
{
"epoch": 0.86,
"learning_rate": 9.58817835573238e-07,
"loss": 0.4314,
"step": 3333
},
{
"epoch": 0.86,
"learning_rate": 9.552347335178858e-07,
"loss": 0.4355,
"step": 3334
},
{
"epoch": 0.86,
"learning_rate": 9.516580031925582e-07,
"loss": 0.4424,
"step": 3335
},
{
"epoch": 0.86,
"learning_rate": 9.480876471169376e-07,
"loss": 0.4104,
"step": 3336
},
{
"epoch": 0.86,
"learning_rate": 9.445236678062197e-07,
"loss": 0.4414,
"step": 3337
},
{
"epoch": 0.86,
"learning_rate": 9.409660677711085e-07,
"loss": 0.4128,
"step": 3338
},
{
"epoch": 0.87,
"learning_rate": 9.374148495178104e-07,
"loss": 0.4324,
"step": 3339
},
{
"epoch": 0.87,
"learning_rate": 9.338700155480396e-07,
"loss": 0.4131,
"step": 3340
},
{
"epoch": 0.87,
"learning_rate": 9.303315683590086e-07,
"loss": 0.396,
"step": 3341
},
{
"epoch": 0.87,
"learning_rate": 9.267995104434357e-07,
"loss": 0.4062,
"step": 3342
},
{
"epoch": 0.87,
"learning_rate": 9.232738442895362e-07,
"loss": 0.4275,
"step": 3343
},
{
"epoch": 0.87,
"learning_rate": 9.197545723810197e-07,
"loss": 0.4348,
"step": 3344
},
{
"epoch": 0.87,
"learning_rate": 9.162416971970978e-07,
"loss": 0.436,
"step": 3345
},
{
"epoch": 0.87,
"learning_rate": 9.127352212124663e-07,
"loss": 0.4377,
"step": 3346
},
{
"epoch": 0.87,
"learning_rate": 9.092351468973248e-07,
"loss": 0.4409,
"step": 3347
},
{
"epoch": 0.87,
"learning_rate": 9.0574147671735e-07,
"loss": 0.4133,
"step": 3348
},
{
"epoch": 0.87,
"learning_rate": 9.022542131337186e-07,
"loss": 0.4448,
"step": 3349
},
{
"epoch": 0.87,
"learning_rate": 8.987733586030889e-07,
"loss": 0.428,
"step": 3350
},
{
"epoch": 0.87,
"learning_rate": 8.952989155776026e-07,
"loss": 0.4441,
"step": 3351
},
{
"epoch": 0.87,
"learning_rate": 8.918308865048897e-07,
"loss": 0.4072,
"step": 3352
},
{
"epoch": 0.87,
"learning_rate": 8.883692738280558e-07,
"loss": 0.4116,
"step": 3353
},
{
"epoch": 0.87,
"learning_rate": 8.849140799856936e-07,
"loss": 0.4319,
"step": 3354
},
{
"epoch": 0.87,
"learning_rate": 8.814653074118651e-07,
"loss": 0.4287,
"step": 3355
},
{
"epoch": 0.87,
"learning_rate": 8.780229585361155e-07,
"loss": 0.4082,
"step": 3356
},
{
"epoch": 0.87,
"learning_rate": 8.745870357834652e-07,
"loss": 0.4248,
"step": 3357
},
{
"epoch": 0.87,
"learning_rate": 8.711575415744012e-07,
"loss": 0.4458,
"step": 3358
},
{
"epoch": 0.87,
"learning_rate": 8.677344783248887e-07,
"loss": 0.4058,
"step": 3359
},
{
"epoch": 0.87,
"learning_rate": 8.643178484463566e-07,
"loss": 0.4055,
"step": 3360
},
{
"epoch": 0.87,
"learning_rate": 8.609076543457062e-07,
"loss": 0.3901,
"step": 3361
},
{
"epoch": 0.87,
"learning_rate": 8.575038984253048e-07,
"loss": 0.4236,
"step": 3362
},
{
"epoch": 0.87,
"learning_rate": 8.541065830829809e-07,
"loss": 0.4153,
"step": 3363
},
{
"epoch": 0.87,
"learning_rate": 8.507157107120301e-07,
"loss": 0.4092,
"step": 3364
},
{
"epoch": 0.87,
"learning_rate": 8.473312837012027e-07,
"loss": 0.4045,
"step": 3365
},
{
"epoch": 0.87,
"learning_rate": 8.43953304434717e-07,
"loss": 0.427,
"step": 3366
},
{
"epoch": 0.87,
"learning_rate": 8.405817752922418e-07,
"loss": 0.4148,
"step": 3367
},
{
"epoch": 0.87,
"learning_rate": 8.372166986489061e-07,
"loss": 0.4194,
"step": 3368
},
{
"epoch": 0.87,
"learning_rate": 8.338580768752935e-07,
"loss": 0.4182,
"step": 3369
},
{
"epoch": 0.87,
"learning_rate": 8.305059123374348e-07,
"loss": 0.4163,
"step": 3370
},
{
"epoch": 0.87,
"learning_rate": 8.271602073968221e-07,
"loss": 0.417,
"step": 3371
},
{
"epoch": 0.87,
"learning_rate": 8.238209644103867e-07,
"loss": 0.425,
"step": 3372
},
{
"epoch": 0.87,
"learning_rate": 8.204881857305113e-07,
"loss": 0.4287,
"step": 3373
},
{
"epoch": 0.87,
"learning_rate": 8.171618737050269e-07,
"loss": 0.4204,
"step": 3374
},
{
"epoch": 0.87,
"learning_rate": 8.138420306772066e-07,
"loss": 0.3977,
"step": 3375
},
{
"epoch": 0.87,
"learning_rate": 8.105286589857708e-07,
"loss": 0.4014,
"step": 3376
},
{
"epoch": 0.88,
"learning_rate": 8.072217609648714e-07,
"loss": 0.4341,
"step": 3377
},
{
"epoch": 0.88,
"learning_rate": 8.039213389441114e-07,
"loss": 0.4373,
"step": 3378
},
{
"epoch": 0.88,
"learning_rate": 8.00627395248521e-07,
"loss": 0.4263,
"step": 3379
},
{
"epoch": 0.88,
"learning_rate": 7.973399321985753e-07,
"loss": 0.4133,
"step": 3380
},
{
"epoch": 0.88,
"learning_rate": 7.940589521101805e-07,
"loss": 0.4473,
"step": 3381
},
{
"epoch": 0.88,
"learning_rate": 7.907844572946721e-07,
"loss": 0.4219,
"step": 3382
},
{
"epoch": 0.88,
"learning_rate": 7.875164500588239e-07,
"loss": 0.4116,
"step": 3383
},
{
"epoch": 0.88,
"learning_rate": 7.842549327048366e-07,
"loss": 0.4189,
"step": 3384
},
{
"epoch": 0.88,
"learning_rate": 7.809999075303332e-07,
"loss": 0.4238,
"step": 3385
},
{
"epoch": 0.88,
"learning_rate": 7.777513768283729e-07,
"loss": 0.4192,
"step": 3386
},
{
"epoch": 0.88,
"learning_rate": 7.745093428874351e-07,
"loss": 0.4294,
"step": 3387
},
{
"epoch": 0.88,
"learning_rate": 7.712738079914228e-07,
"loss": 0.4072,
"step": 3388
},
{
"epoch": 0.88,
"learning_rate": 7.680447744196595e-07,
"loss": 0.4321,
"step": 3389
},
{
"epoch": 0.88,
"learning_rate": 7.648222444468878e-07,
"loss": 0.4307,
"step": 3390
},
{
"epoch": 0.88,
"learning_rate": 7.616062203432739e-07,
"loss": 0.4109,
"step": 3391
},
{
"epoch": 0.88,
"learning_rate": 7.583967043743956e-07,
"loss": 0.4141,
"step": 3392
},
{
"epoch": 0.88,
"learning_rate": 7.551936988012487e-07,
"loss": 0.4131,
"step": 3393
},
{
"epoch": 0.88,
"learning_rate": 7.519972058802405e-07,
"loss": 0.3862,
"step": 3394
},
{
"epoch": 0.88,
"learning_rate": 7.488072278631963e-07,
"loss": 0.3999,
"step": 3395
},
{
"epoch": 0.88,
"learning_rate": 7.456237669973432e-07,
"loss": 0.4121,
"step": 3396
},
{
"epoch": 0.88,
"learning_rate": 7.424468255253203e-07,
"loss": 0.3972,
"step": 3397
},
{
"epoch": 0.88,
"learning_rate": 7.392764056851764e-07,
"loss": 0.4177,
"step": 3398
},
{
"epoch": 0.88,
"learning_rate": 7.361125097103661e-07,
"loss": 0.4226,
"step": 3399
},
{
"epoch": 0.88,
"learning_rate": 7.329551398297463e-07,
"loss": 0.4316,
"step": 3400
},
{
"epoch": 0.88,
"learning_rate": 7.298042982675768e-07,
"loss": 0.4255,
"step": 3401
},
{
"epoch": 0.88,
"learning_rate": 7.266599872435165e-07,
"loss": 0.3965,
"step": 3402
},
{
"epoch": 0.88,
"learning_rate": 7.23522208972628e-07,
"loss": 0.4207,
"step": 3403
},
{
"epoch": 0.88,
"learning_rate": 7.203909656653674e-07,
"loss": 0.4189,
"step": 3404
},
{
"epoch": 0.88,
"learning_rate": 7.172662595275914e-07,
"loss": 0.4141,
"step": 3405
},
{
"epoch": 0.88,
"learning_rate": 7.141480927605471e-07,
"loss": 0.4116,
"step": 3406
},
{
"epoch": 0.88,
"learning_rate": 7.110364675608805e-07,
"loss": 0.4353,
"step": 3407
},
{
"epoch": 0.88,
"learning_rate": 7.07931386120625e-07,
"loss": 0.4236,
"step": 3408
},
{
"epoch": 0.88,
"learning_rate": 7.048328506272017e-07,
"loss": 0.4231,
"step": 3409
},
{
"epoch": 0.88,
"learning_rate": 7.01740863263427e-07,
"loss": 0.4094,
"step": 3410
},
{
"epoch": 0.88,
"learning_rate": 6.986554262074996e-07,
"loss": 0.4045,
"step": 3411
},
{
"epoch": 0.88,
"learning_rate": 6.955765416330052e-07,
"loss": 0.4385,
"step": 3412
},
{
"epoch": 0.88,
"learning_rate": 6.925042117089142e-07,
"loss": 0.4004,
"step": 3413
},
{
"epoch": 0.88,
"learning_rate": 6.894384385995778e-07,
"loss": 0.4167,
"step": 3414
},
{
"epoch": 0.88,
"learning_rate": 6.863792244647305e-07,
"loss": 0.427,
"step": 3415
},
{
"epoch": 0.89,
"learning_rate": 6.833265714594828e-07,
"loss": 0.4478,
"step": 3416
},
{
"epoch": 0.89,
"learning_rate": 6.802804817343256e-07,
"loss": 0.4294,
"step": 3417
},
{
"epoch": 0.89,
"learning_rate": 6.77240957435128e-07,
"loss": 0.4421,
"step": 3418
},
{
"epoch": 0.89,
"learning_rate": 6.742080007031282e-07,
"loss": 0.4399,
"step": 3419
},
{
"epoch": 0.89,
"learning_rate": 6.711816136749449e-07,
"loss": 0.4158,
"step": 3420
},
{
"epoch": 0.89,
"learning_rate": 6.681617984825617e-07,
"loss": 0.4128,
"step": 3421
},
{
"epoch": 0.89,
"learning_rate": 6.651485572533379e-07,
"loss": 0.4143,
"step": 3422
},
{
"epoch": 0.89,
"learning_rate": 6.621418921099976e-07,
"loss": 0.4336,
"step": 3423
},
{
"epoch": 0.89,
"learning_rate": 6.591418051706355e-07,
"loss": 0.4258,
"step": 3424
},
{
"epoch": 0.89,
"learning_rate": 6.561482985487122e-07,
"loss": 0.4197,
"step": 3425
},
{
"epoch": 0.89,
"learning_rate": 6.531613743530496e-07,
"loss": 0.417,
"step": 3426
},
{
"epoch": 0.89,
"learning_rate": 6.501810346878368e-07,
"loss": 0.4048,
"step": 3427
},
{
"epoch": 0.89,
"learning_rate": 6.472072816526176e-07,
"loss": 0.4307,
"step": 3428
},
{
"epoch": 0.89,
"learning_rate": 6.442401173423051e-07,
"loss": 0.4231,
"step": 3429
},
{
"epoch": 0.89,
"learning_rate": 6.412795438471619e-07,
"loss": 0.437,
"step": 3430
},
{
"epoch": 0.89,
"learning_rate": 6.383255632528129e-07,
"loss": 0.4365,
"step": 3431
},
{
"epoch": 0.89,
"learning_rate": 6.35378177640239e-07,
"loss": 0.4292,
"step": 3432
},
{
"epoch": 0.89,
"learning_rate": 6.324373890857694e-07,
"loss": 0.4424,
"step": 3433
},
{
"epoch": 0.89,
"learning_rate": 6.295031996610934e-07,
"loss": 0.427,
"step": 3434
},
{
"epoch": 0.89,
"learning_rate": 6.265756114332455e-07,
"loss": 0.4487,
"step": 3435
},
{
"epoch": 0.89,
"learning_rate": 6.236546264646126e-07,
"loss": 0.4114,
"step": 3436
},
{
"epoch": 0.89,
"learning_rate": 6.207402468129309e-07,
"loss": 0.4099,
"step": 3437
},
{
"epoch": 0.89,
"learning_rate": 6.178324745312792e-07,
"loss": 0.4326,
"step": 3438
},
{
"epoch": 0.89,
"learning_rate": 6.149313116680889e-07,
"loss": 0.4216,
"step": 3439
},
{
"epoch": 0.89,
"learning_rate": 6.120367602671251e-07,
"loss": 0.4387,
"step": 3440
},
{
"epoch": 0.89,
"learning_rate": 6.091488223675058e-07,
"loss": 0.4451,
"step": 3441
},
{
"epoch": 0.89,
"learning_rate": 6.062675000036811e-07,
"loss": 0.4368,
"step": 3442
},
{
"epoch": 0.89,
"learning_rate": 6.033927952054475e-07,
"loss": 0.4336,
"step": 3443
},
{
"epoch": 0.89,
"learning_rate": 6.005247099979372e-07,
"loss": 0.446,
"step": 3444
},
{
"epoch": 0.89,
"learning_rate": 5.976632464016163e-07,
"loss": 0.4331,
"step": 3445
},
{
"epoch": 0.89,
"learning_rate": 5.948084064322912e-07,
"loss": 0.4272,
"step": 3446
},
{
"epoch": 0.89,
"learning_rate": 5.919601921010998e-07,
"loss": 0.4551,
"step": 3447
},
{
"epoch": 0.89,
"learning_rate": 5.891186054145103e-07,
"loss": 0.4041,
"step": 3448
},
{
"epoch": 0.89,
"learning_rate": 5.86283648374324e-07,
"loss": 0.4302,
"step": 3449
},
{
"epoch": 0.89,
"learning_rate": 5.83455322977674e-07,
"loss": 0.4104,
"step": 3450
},
{
"epoch": 0.89,
"learning_rate": 5.806336312170191e-07,
"loss": 0.416,
"step": 3451
},
{
"epoch": 0.89,
"learning_rate": 5.778185750801435e-07,
"loss": 0.4297,
"step": 3452
},
{
"epoch": 0.89,
"learning_rate": 5.75010156550162e-07,
"loss": 0.4329,
"step": 3453
},
{
"epoch": 0.9,
"learning_rate": 5.722083776055076e-07,
"loss": 0.4219,
"step": 3454
},
{
"epoch": 0.9,
"learning_rate": 5.69413240219936e-07,
"loss": 0.426,
"step": 3455
},
{
"epoch": 0.9,
"learning_rate": 5.666247463625319e-07,
"loss": 0.4072,
"step": 3456
},
{
"epoch": 0.9,
"learning_rate": 5.638428979976906e-07,
"loss": 0.4146,
"step": 3457
},
{
"epoch": 0.9,
"learning_rate": 5.610676970851336e-07,
"loss": 0.416,
"step": 3458
},
{
"epoch": 0.9,
"learning_rate": 5.582991455798925e-07,
"loss": 0.4216,
"step": 3459
},
{
"epoch": 0.9,
"learning_rate": 5.555372454323182e-07,
"loss": 0.4275,
"step": 3460
},
{
"epoch": 0.9,
"learning_rate": 5.527819985880755e-07,
"loss": 0.3972,
"step": 3461
},
{
"epoch": 0.9,
"learning_rate": 5.50033406988143e-07,
"loss": 0.429,
"step": 3462
},
{
"epoch": 0.9,
"learning_rate": 5.472914725688117e-07,
"loss": 0.3999,
"step": 3463
},
{
"epoch": 0.9,
"learning_rate": 5.445561972616786e-07,
"loss": 0.3997,
"step": 3464
},
{
"epoch": 0.9,
"learning_rate": 5.418275829936537e-07,
"loss": 0.4187,
"step": 3465
},
{
"epoch": 0.9,
"learning_rate": 5.391056316869536e-07,
"loss": 0.4277,
"step": 3466
},
{
"epoch": 0.9,
"learning_rate": 5.363903452590979e-07,
"loss": 0.4302,
"step": 3467
},
{
"epoch": 0.9,
"learning_rate": 5.336817256229154e-07,
"loss": 0.4326,
"step": 3468
},
{
"epoch": 0.9,
"learning_rate": 5.309797746865364e-07,
"loss": 0.3958,
"step": 3469
},
{
"epoch": 0.9,
"learning_rate": 5.28284494353396e-07,
"loss": 0.4167,
"step": 3470
},
{
"epoch": 0.9,
"learning_rate": 5.255958865222255e-07,
"loss": 0.4414,
"step": 3471
},
{
"epoch": 0.9,
"learning_rate": 5.229139530870553e-07,
"loss": 0.405,
"step": 3472
},
{
"epoch": 0.9,
"learning_rate": 5.202386959372218e-07,
"loss": 0.4121,
"step": 3473
},
{
"epoch": 0.9,
"learning_rate": 5.175701169573477e-07,
"loss": 0.4294,
"step": 3474
},
{
"epoch": 0.9,
"learning_rate": 5.149082180273601e-07,
"loss": 0.4204,
"step": 3475
},
{
"epoch": 0.9,
"learning_rate": 5.122530010224757e-07,
"loss": 0.4141,
"step": 3476
},
{
"epoch": 0.9,
"learning_rate": 5.096044678132028e-07,
"loss": 0.4102,
"step": 3477
},
{
"epoch": 0.9,
"learning_rate": 5.069626202653455e-07,
"loss": 0.4121,
"step": 3478
},
{
"epoch": 0.9,
"learning_rate": 5.043274602399939e-07,
"loss": 0.4402,
"step": 3479
},
{
"epoch": 0.9,
"learning_rate": 5.016989895935287e-07,
"loss": 0.396,
"step": 3480
},
{
"epoch": 0.9,
"learning_rate": 4.990772101776187e-07,
"loss": 0.4136,
"step": 3481
},
{
"epoch": 0.9,
"learning_rate": 4.964621238392208e-07,
"loss": 0.4236,
"step": 3482
},
{
"epoch": 0.9,
"learning_rate": 4.938537324205717e-07,
"loss": 0.4019,
"step": 3483
},
{
"epoch": 0.9,
"learning_rate": 4.912520377591945e-07,
"loss": 0.4109,
"step": 3484
},
{
"epoch": 0.9,
"learning_rate": 4.886570416878966e-07,
"loss": 0.4282,
"step": 3485
},
{
"epoch": 0.9,
"learning_rate": 4.860687460347624e-07,
"loss": 0.417,
"step": 3486
},
{
"epoch": 0.9,
"learning_rate": 4.834871526231588e-07,
"loss": 0.4158,
"step": 3487
},
{
"epoch": 0.9,
"learning_rate": 4.809122632717345e-07,
"loss": 0.4158,
"step": 3488
},
{
"epoch": 0.9,
"learning_rate": 4.783440797944061e-07,
"loss": 0.4185,
"step": 3489
},
{
"epoch": 0.9,
"learning_rate": 4.7578260400037546e-07,
"loss": 0.4324,
"step": 3490
},
{
"epoch": 0.9,
"learning_rate": 4.732278376941124e-07,
"loss": 0.426,
"step": 3491
},
{
"epoch": 0.9,
"learning_rate": 4.706797826753662e-07,
"loss": 0.3958,
"step": 3492
},
{
"epoch": 0.91,
"learning_rate": 4.681384407391498e-07,
"loss": 0.3943,
"step": 3493
},
{
"epoch": 0.91,
"learning_rate": 4.6560381367576013e-07,
"loss": 0.4285,
"step": 3494
},
{
"epoch": 0.91,
"learning_rate": 4.63075903270751e-07,
"loss": 0.4114,
"step": 3495
},
{
"epoch": 0.91,
"learning_rate": 4.605547113049491e-07,
"loss": 0.4231,
"step": 3496
},
{
"epoch": 0.91,
"learning_rate": 4.580402395544503e-07,
"loss": 0.4094,
"step": 3497
},
{
"epoch": 0.91,
"learning_rate": 4.555324897906133e-07,
"loss": 0.3994,
"step": 3498
},
{
"epoch": 0.91,
"learning_rate": 4.530314637800637e-07,
"loss": 0.4265,
"step": 3499
},
{
"epoch": 0.91,
"learning_rate": 4.5053716328469e-07,
"loss": 0.3933,
"step": 3500
},
{
"epoch": 0.91,
"learning_rate": 4.4804959006163995e-07,
"loss": 0.4197,
"step": 3501
},
{
"epoch": 0.91,
"learning_rate": 4.455687458633262e-07,
"loss": 0.4185,
"step": 3502
},
{
"epoch": 0.91,
"learning_rate": 4.4309463243741856e-07,
"loss": 0.4153,
"step": 3503
},
{
"epoch": 0.91,
"learning_rate": 4.4062725152684616e-07,
"loss": 0.4231,
"step": 3504
},
{
"epoch": 0.91,
"learning_rate": 4.3816660486979524e-07,
"loss": 0.4163,
"step": 3505
},
{
"epoch": 0.91,
"learning_rate": 4.3571269419970586e-07,
"loss": 0.4238,
"step": 3506
},
{
"epoch": 0.91,
"learning_rate": 4.3326552124527964e-07,
"loss": 0.3901,
"step": 3507
},
{
"epoch": 0.91,
"learning_rate": 4.3082508773046096e-07,
"loss": 0.3889,
"step": 3508
},
{
"epoch": 0.91,
"learning_rate": 4.283913953744567e-07,
"loss": 0.3916,
"step": 3509
},
{
"epoch": 0.91,
"learning_rate": 4.259644458917178e-07,
"loss": 0.3884,
"step": 3510
},
{
"epoch": 0.91,
"learning_rate": 4.2354424099195104e-07,
"loss": 0.4351,
"step": 3511
},
{
"epoch": 0.91,
"learning_rate": 4.2113078238010364e-07,
"loss": 0.429,
"step": 3512
},
{
"epoch": 0.91,
"learning_rate": 4.1872407175637896e-07,
"loss": 0.4285,
"step": 3513
},
{
"epoch": 0.91,
"learning_rate": 4.16324110816223e-07,
"loss": 0.3962,
"step": 3514
},
{
"epoch": 0.91,
"learning_rate": 4.1393090125032453e-07,
"loss": 0.4048,
"step": 3515
},
{
"epoch": 0.91,
"learning_rate": 4.115444447446204e-07,
"loss": 0.3962,
"step": 3516
},
{
"epoch": 0.91,
"learning_rate": 4.0916474298028694e-07,
"loss": 0.4109,
"step": 3517
},
{
"epoch": 0.91,
"learning_rate": 4.0679179763374323e-07,
"loss": 0.3984,
"step": 3518
},
{
"epoch": 0.91,
"learning_rate": 4.0442561037665087e-07,
"loss": 0.396,
"step": 3519
},
{
"epoch": 0.91,
"learning_rate": 4.0206618287590536e-07,
"loss": 0.407,
"step": 3520
},
{
"epoch": 0.91,
"learning_rate": 3.997135167936461e-07,
"loss": 0.4009,
"step": 3521
},
{
"epoch": 0.91,
"learning_rate": 3.973676137872429e-07,
"loss": 0.4026,
"step": 3522
},
{
"epoch": 0.91,
"learning_rate": 3.9502847550930925e-07,
"loss": 0.3984,
"step": 3523
},
{
"epoch": 0.91,
"learning_rate": 3.9269610360768374e-07,
"loss": 0.4246,
"step": 3524
},
{
"epoch": 0.91,
"learning_rate": 3.903704997254465e-07,
"loss": 0.3987,
"step": 3525
},
{
"epoch": 0.91,
"learning_rate": 3.880516655009081e-07,
"loss": 0.4219,
"step": 3526
},
{
"epoch": 0.91,
"learning_rate": 3.85739602567603e-07,
"loss": 0.4082,
"step": 3527
},
{
"epoch": 0.91,
"learning_rate": 3.834343125543061e-07,
"loss": 0.4189,
"step": 3528
},
{
"epoch": 0.91,
"learning_rate": 3.8113579708501493e-07,
"loss": 0.4238,
"step": 3529
},
{
"epoch": 0.91,
"learning_rate": 3.7884405777895206e-07,
"loss": 0.4009,
"step": 3530
},
{
"epoch": 0.92,
"learning_rate": 3.765590962505739e-07,
"loss": 0.4116,
"step": 3531
},
{
"epoch": 0.92,
"learning_rate": 3.74280914109556e-07,
"loss": 0.4355,
"step": 3532
},
{
"epoch": 0.92,
"learning_rate": 3.720095129608037e-07,
"loss": 0.4067,
"step": 3533
},
{
"epoch": 0.92,
"learning_rate": 3.6974489440443795e-07,
"loss": 0.4119,
"step": 3534
},
{
"epoch": 0.92,
"learning_rate": 3.6748706003580826e-07,
"loss": 0.3994,
"step": 3535
},
{
"epoch": 0.92,
"learning_rate": 3.6523601144548003e-07,
"loss": 0.4155,
"step": 3536
},
{
"epoch": 0.92,
"learning_rate": 3.629917502192415e-07,
"loss": 0.4312,
"step": 3537
},
{
"epoch": 0.92,
"learning_rate": 3.6075427793810016e-07,
"loss": 0.4099,
"step": 3538
},
{
"epoch": 0.92,
"learning_rate": 3.585235961782774e-07,
"loss": 0.4214,
"step": 3539
},
{
"epoch": 0.92,
"learning_rate": 3.5629970651121506e-07,
"loss": 0.4253,
"step": 3540
},
{
"epoch": 0.92,
"learning_rate": 3.540826105035644e-07,
"loss": 0.4019,
"step": 3541
},
{
"epoch": 0.92,
"learning_rate": 3.518723097171961e-07,
"loss": 0.4058,
"step": 3542
},
{
"epoch": 0.92,
"learning_rate": 3.4966880570919235e-07,
"loss": 0.3901,
"step": 3543
},
{
"epoch": 0.92,
"learning_rate": 3.4747210003184597e-07,
"loss": 0.4326,
"step": 3544
},
{
"epoch": 0.92,
"learning_rate": 3.452821942326623e-07,
"loss": 0.4224,
"step": 3545
},
{
"epoch": 0.92,
"learning_rate": 3.4309908985435626e-07,
"loss": 0.4224,
"step": 3546
},
{
"epoch": 0.92,
"learning_rate": 3.4092278843484873e-07,
"loss": 0.4216,
"step": 3547
},
{
"epoch": 0.92,
"learning_rate": 3.3875329150727333e-07,
"loss": 0.4148,
"step": 3548
},
{
"epoch": 0.92,
"learning_rate": 3.3659060059996305e-07,
"loss": 0.4253,
"step": 3549
},
{
"epoch": 0.92,
"learning_rate": 3.344347172364615e-07,
"loss": 0.4302,
"step": 3550
},
{
"epoch": 0.92,
"learning_rate": 3.32285642935517e-07,
"loss": 0.4282,
"step": 3551
},
{
"epoch": 0.92,
"learning_rate": 3.3014337921107864e-07,
"loss": 0.4124,
"step": 3552
},
{
"epoch": 0.92,
"learning_rate": 3.2800792757229917e-07,
"loss": 0.4204,
"step": 3553
},
{
"epoch": 0.92,
"learning_rate": 3.2587928952352853e-07,
"loss": 0.4141,
"step": 3554
},
{
"epoch": 0.92,
"learning_rate": 3.2375746656432284e-07,
"loss": 0.4216,
"step": 3555
},
{
"epoch": 0.92,
"learning_rate": 3.2164246018943414e-07,
"loss": 0.3931,
"step": 3556
},
{
"epoch": 0.92,
"learning_rate": 3.1953427188881283e-07,
"loss": 0.425,
"step": 3557
},
{
"epoch": 0.92,
"learning_rate": 3.1743290314760534e-07,
"loss": 0.4224,
"step": 3558
},
{
"epoch": 0.92,
"learning_rate": 3.153383554461531e-07,
"loss": 0.4202,
"step": 3559
},
{
"epoch": 0.92,
"learning_rate": 3.132506302599969e-07,
"loss": 0.4089,
"step": 3560
},
{
"epoch": 0.92,
"learning_rate": 3.111697290598659e-07,
"loss": 0.3982,
"step": 3561
},
{
"epoch": 0.92,
"learning_rate": 3.09095653311684e-07,
"loss": 0.4092,
"step": 3562
},
{
"epoch": 0.92,
"learning_rate": 3.070284044765692e-07,
"loss": 0.4036,
"step": 3563
},
{
"epoch": 0.92,
"learning_rate": 3.0496798401082773e-07,
"loss": 0.4346,
"step": 3564
},
{
"epoch": 0.92,
"learning_rate": 3.029143933659562e-07,
"loss": 0.4089,
"step": 3565
},
{
"epoch": 0.92,
"learning_rate": 3.0086763398863627e-07,
"loss": 0.4136,
"step": 3566
},
{
"epoch": 0.92,
"learning_rate": 2.988277073207446e-07,
"loss": 0.3967,
"step": 3567
},
{
"epoch": 0.92,
"learning_rate": 2.967946147993372e-07,
"loss": 0.4131,
"step": 3568
},
{
"epoch": 0.92,
"learning_rate": 2.947683578566596e-07,
"loss": 0.4058,
"step": 3569
},
{
"epoch": 0.93,
"learning_rate": 2.9274893792014315e-07,
"loss": 0.4082,
"step": 3570
},
{
"epoch": 0.93,
"learning_rate": 2.907363564123977e-07,
"loss": 0.3979,
"step": 3571
},
{
"epoch": 0.93,
"learning_rate": 2.887306147512203e-07,
"loss": 0.4089,
"step": 3572
},
{
"epoch": 0.93,
"learning_rate": 2.867317143495862e-07,
"loss": 0.3872,
"step": 3573
},
{
"epoch": 0.93,
"learning_rate": 2.8473965661565353e-07,
"loss": 0.4153,
"step": 3574
},
{
"epoch": 0.93,
"learning_rate": 2.8275444295276175e-07,
"loss": 0.4192,
"step": 3575
},
{
"epoch": 0.93,
"learning_rate": 2.807760747594224e-07,
"loss": 0.4128,
"step": 3576
},
{
"epoch": 0.93,
"learning_rate": 2.7880455342933266e-07,
"loss": 0.4194,
"step": 3577
},
{
"epoch": 0.93,
"learning_rate": 2.7683988035135834e-07,
"loss": 0.4441,
"step": 3578
},
{
"epoch": 0.93,
"learning_rate": 2.7488205690954893e-07,
"loss": 0.4087,
"step": 3579
},
{
"epoch": 0.93,
"learning_rate": 2.7293108448312124e-07,
"loss": 0.4136,
"step": 3580
},
{
"epoch": 0.93,
"learning_rate": 2.7098696444647135e-07,
"loss": 0.4014,
"step": 3581
},
{
"epoch": 0.93,
"learning_rate": 2.690496981691648e-07,
"loss": 0.4216,
"step": 3582
},
{
"epoch": 0.93,
"learning_rate": 2.6711928701594003e-07,
"loss": 0.4036,
"step": 3583
},
{
"epoch": 0.93,
"learning_rate": 2.6519573234670694e-07,
"loss": 0.4351,
"step": 3584
},
{
"epoch": 0.93,
"learning_rate": 2.6327903551654267e-07,
"loss": 0.4238,
"step": 3585
},
{
"epoch": 0.93,
"learning_rate": 2.6136919787569714e-07,
"loss": 0.4128,
"step": 3586
},
{
"epoch": 0.93,
"learning_rate": 2.5946622076958415e-07,
"loss": 0.418,
"step": 3587
},
{
"epoch": 0.93,
"learning_rate": 2.575701055387869e-07,
"loss": 0.4199,
"step": 3588
},
{
"epoch": 0.93,
"learning_rate": 2.556808535190558e-07,
"loss": 0.4219,
"step": 3589
},
{
"epoch": 0.93,
"learning_rate": 2.5379846604130287e-07,
"loss": 0.4202,
"step": 3590
},
{
"epoch": 0.93,
"learning_rate": 2.519229444316085e-07,
"loss": 0.4192,
"step": 3591
},
{
"epoch": 0.93,
"learning_rate": 2.5005429001121127e-07,
"loss": 0.4255,
"step": 3592
},
{
"epoch": 0.93,
"learning_rate": 2.4819250409651605e-07,
"loss": 0.4194,
"step": 3593
},
{
"epoch": 0.93,
"learning_rate": 2.463375879990881e-07,
"loss": 0.4136,
"step": 3594
},
{
"epoch": 0.93,
"learning_rate": 2.444895430256511e-07,
"loss": 0.4146,
"step": 3595
},
{
"epoch": 0.93,
"learning_rate": 2.4264837047809354e-07,
"loss": 0.4177,
"step": 3596
},
{
"epoch": 0.93,
"learning_rate": 2.408140716534546e-07,
"loss": 0.4248,
"step": 3597
},
{
"epoch": 0.93,
"learning_rate": 2.3898664784393954e-07,
"loss": 0.4043,
"step": 3598
},
{
"epoch": 0.93,
"learning_rate": 2.3716610033690303e-07,
"loss": 0.4377,
"step": 3599
},
{
"epoch": 0.93,
"learning_rate": 2.3535243041486133e-07,
"loss": 0.4316,
"step": 3600
},
{
"epoch": 0.93,
"learning_rate": 2.3354563935548248e-07,
"loss": 0.4189,
"step": 3601
},
{
"epoch": 0.93,
"learning_rate": 2.3174572843158826e-07,
"loss": 0.3955,
"step": 3602
},
{
"epoch": 0.93,
"learning_rate": 2.299526989111578e-07,
"loss": 0.4478,
"step": 3603
},
{
"epoch": 0.93,
"learning_rate": 2.2816655205731731e-07,
"loss": 0.3857,
"step": 3604
},
{
"epoch": 0.93,
"learning_rate": 2.2638728912834584e-07,
"loss": 0.4238,
"step": 3605
},
{
"epoch": 0.93,
"learning_rate": 2.246149113776741e-07,
"loss": 0.4224,
"step": 3606
},
{
"epoch": 0.93,
"learning_rate": 2.2284942005388331e-07,
"loss": 0.4163,
"step": 3607
},
{
"epoch": 0.93,
"learning_rate": 2.2109081640070307e-07,
"loss": 0.4067,
"step": 3608
},
{
"epoch": 0.94,
"learning_rate": 2.1933910165700677e-07,
"loss": 0.408,
"step": 3609
},
{
"epoch": 0.94,
"learning_rate": 2.1759427705682067e-07,
"loss": 0.407,
"step": 3610
},
{
"epoch": 0.94,
"learning_rate": 2.1585634382931376e-07,
"loss": 0.4321,
"step": 3611
},
{
"epoch": 0.94,
"learning_rate": 2.1412530319879888e-07,
"loss": 0.4478,
"step": 3612
},
{
"epoch": 0.94,
"learning_rate": 2.1240115638473947e-07,
"loss": 0.4158,
"step": 3613
},
{
"epoch": 0.94,
"learning_rate": 2.1068390460173504e-07,
"loss": 0.4041,
"step": 3614
},
{
"epoch": 0.94,
"learning_rate": 2.0897354905953237e-07,
"loss": 0.3945,
"step": 3615
},
{
"epoch": 0.94,
"learning_rate": 2.0727009096301877e-07,
"loss": 0.4238,
"step": 3616
},
{
"epoch": 0.94,
"learning_rate": 2.0557353151222314e-07,
"loss": 0.4309,
"step": 3617
},
{
"epoch": 0.94,
"learning_rate": 2.0388387190231173e-07,
"loss": 0.4309,
"step": 3618
},
{
"epoch": 0.94,
"learning_rate": 2.022011133235946e-07,
"loss": 0.4307,
"step": 3619
},
{
"epoch": 0.94,
"learning_rate": 2.0052525696151904e-07,
"loss": 0.425,
"step": 3620
},
{
"epoch": 0.94,
"learning_rate": 1.9885630399666622e-07,
"loss": 0.4194,
"step": 3621
},
{
"epoch": 0.94,
"learning_rate": 1.97194255604759e-07,
"loss": 0.4072,
"step": 3622
},
{
"epoch": 0.94,
"learning_rate": 1.9553911295665306e-07,
"loss": 0.3901,
"step": 3623
},
{
"epoch": 0.94,
"learning_rate": 1.938908772183401e-07,
"loss": 0.4163,
"step": 3624
},
{
"epoch": 0.94,
"learning_rate": 1.9224954955094577e-07,
"loss": 0.4021,
"step": 3625
},
{
"epoch": 0.94,
"learning_rate": 1.906151311107296e-07,
"loss": 0.4314,
"step": 3626
},
{
"epoch": 0.94,
"learning_rate": 1.8898762304908612e-07,
"loss": 0.4165,
"step": 3627
},
{
"epoch": 0.94,
"learning_rate": 1.8736702651253823e-07,
"loss": 0.4111,
"step": 3628
},
{
"epoch": 0.94,
"learning_rate": 1.8575334264273935e-07,
"loss": 0.439,
"step": 3629
},
{
"epoch": 0.94,
"learning_rate": 1.8414657257647683e-07,
"loss": 0.4141,
"step": 3630
},
{
"epoch": 0.94,
"learning_rate": 1.825467174456652e-07,
"loss": 0.4207,
"step": 3631
},
{
"epoch": 0.94,
"learning_rate": 1.8095377837734961e-07,
"loss": 0.405,
"step": 3632
},
{
"epoch": 0.94,
"learning_rate": 1.793677564937002e-07,
"loss": 0.4382,
"step": 3633
},
{
"epoch": 0.94,
"learning_rate": 1.777886529120143e-07,
"loss": 0.3989,
"step": 3634
},
{
"epoch": 0.94,
"learning_rate": 1.7621646874471875e-07,
"loss": 0.4165,
"step": 3635
},
{
"epoch": 0.94,
"learning_rate": 1.7465120509936207e-07,
"loss": 0.4045,
"step": 3636
},
{
"epoch": 0.94,
"learning_rate": 1.7309286307861994e-07,
"loss": 0.3835,
"step": 3637
},
{
"epoch": 0.94,
"learning_rate": 1.7154144378029202e-07,
"loss": 0.4038,
"step": 3638
},
{
"epoch": 0.94,
"learning_rate": 1.6999694829730185e-07,
"loss": 0.4045,
"step": 3639
},
{
"epoch": 0.94,
"learning_rate": 1.684593777176924e-07,
"loss": 0.4121,
"step": 3640
},
{
"epoch": 0.94,
"learning_rate": 1.6692873312462942e-07,
"loss": 0.4048,
"step": 3641
},
{
"epoch": 0.94,
"learning_rate": 1.6540501559640044e-07,
"loss": 0.3838,
"step": 3642
},
{
"epoch": 0.94,
"learning_rate": 1.6388822620641342e-07,
"loss": 0.4287,
"step": 3643
},
{
"epoch": 0.94,
"learning_rate": 1.6237836602319367e-07,
"loss": 0.4302,
"step": 3644
},
{
"epoch": 0.94,
"learning_rate": 1.6087543611038926e-07,
"loss": 0.4294,
"step": 3645
},
{
"epoch": 0.94,
"learning_rate": 1.5937943752675987e-07,
"loss": 0.3899,
"step": 3646
},
{
"epoch": 0.95,
"learning_rate": 1.5789037132618812e-07,
"loss": 0.4333,
"step": 3647
},
{
"epoch": 0.95,
"learning_rate": 1.5640823855766817e-07,
"loss": 0.4207,
"step": 3648
},
{
"epoch": 0.95,
"learning_rate": 1.5493304026531485e-07,
"loss": 0.425,
"step": 3649
},
{
"epoch": 0.95,
"learning_rate": 1.5346477748835353e-07,
"loss": 0.4082,
"step": 3650
},
{
"epoch": 0.95,
"learning_rate": 1.5200345126112682e-07,
"loss": 0.4338,
"step": 3651
},
{
"epoch": 0.95,
"learning_rate": 1.5054906261308898e-07,
"loss": 0.4204,
"step": 3652
},
{
"epoch": 0.95,
"learning_rate": 1.4910161256880605e-07,
"loss": 0.4133,
"step": 3653
},
{
"epoch": 0.95,
"learning_rate": 1.4766110214795904e-07,
"loss": 0.4175,
"step": 3654
},
{
"epoch": 0.95,
"learning_rate": 1.4622753236533728e-07,
"loss": 0.4031,
"step": 3655
},
{
"epoch": 0.95,
"learning_rate": 1.4480090423084403e-07,
"loss": 0.4165,
"step": 3656
},
{
"epoch": 0.95,
"learning_rate": 1.4338121874948874e-07,
"loss": 0.4236,
"step": 3657
},
{
"epoch": 0.95,
"learning_rate": 1.4196847692139137e-07,
"loss": 0.4172,
"step": 3658
},
{
"epoch": 0.95,
"learning_rate": 1.405626797417825e-07,
"loss": 0.4282,
"step": 3659
},
{
"epoch": 0.95,
"learning_rate": 1.391638282009966e-07,
"loss": 0.4207,
"step": 3660
},
{
"epoch": 0.95,
"learning_rate": 1.3777192328447875e-07,
"loss": 0.4001,
"step": 3661
},
{
"epoch": 0.95,
"learning_rate": 1.3638696597277678e-07,
"loss": 0.4065,
"step": 3662
},
{
"epoch": 0.95,
"learning_rate": 1.3500895724154695e-07,
"loss": 0.4282,
"step": 3663
},
{
"epoch": 0.95,
"learning_rate": 1.3363789806155047e-07,
"loss": 0.394,
"step": 3664
},
{
"epoch": 0.95,
"learning_rate": 1.3227378939865033e-07,
"loss": 0.4182,
"step": 3665
},
{
"epoch": 0.95,
"learning_rate": 1.3091663221381557e-07,
"loss": 0.4395,
"step": 3666
},
{
"epoch": 0.95,
"learning_rate": 1.295664274631181e-07,
"loss": 0.4128,
"step": 3667
},
{
"epoch": 0.95,
"learning_rate": 1.282231760977304e-07,
"loss": 0.4131,
"step": 3668
},
{
"epoch": 0.95,
"learning_rate": 1.2688687906392772e-07,
"loss": 0.4241,
"step": 3669
},
{
"epoch": 0.95,
"learning_rate": 1.2555753730308594e-07,
"loss": 0.407,
"step": 3670
},
{
"epoch": 0.95,
"learning_rate": 1.2423515175168154e-07,
"loss": 0.4097,
"step": 3671
},
{
"epoch": 0.95,
"learning_rate": 1.2291972334128931e-07,
"loss": 0.3936,
"step": 3672
},
{
"epoch": 0.95,
"learning_rate": 1.2161125299858467e-07,
"loss": 0.4009,
"step": 3673
},
{
"epoch": 0.95,
"learning_rate": 1.2030974164534025e-07,
"loss": 0.4412,
"step": 3674
},
{
"epoch": 0.95,
"learning_rate": 1.19015190198426e-07,
"loss": 0.4126,
"step": 3675
},
{
"epoch": 0.95,
"learning_rate": 1.1772759956981127e-07,
"loss": 0.4292,
"step": 3676
},
{
"epoch": 0.95,
"learning_rate": 1.164469706665583e-07,
"loss": 0.4121,
"step": 3677
},
{
"epoch": 0.95,
"learning_rate": 1.1517330439082763e-07,
"loss": 0.3982,
"step": 3678
},
{
"epoch": 0.95,
"learning_rate": 1.1390660163987377e-07,
"loss": 0.4114,
"step": 3679
},
{
"epoch": 0.95,
"learning_rate": 1.1264686330604512e-07,
"loss": 0.4211,
"step": 3680
},
{
"epoch": 0.95,
"learning_rate": 1.1139409027678405e-07,
"loss": 0.4331,
"step": 3681
},
{
"epoch": 0.95,
"learning_rate": 1.1014828343462791e-07,
"loss": 0.4111,
"step": 3682
},
{
"epoch": 0.95,
"learning_rate": 1.0890944365720579e-07,
"loss": 0.4226,
"step": 3683
},
{
"epoch": 0.95,
"learning_rate": 1.0767757181723737e-07,
"loss": 0.4189,
"step": 3684
},
{
"epoch": 0.95,
"learning_rate": 1.0645266878253402e-07,
"loss": 0.4238,
"step": 3685
},
{
"epoch": 0.96,
"learning_rate": 1.0523473541599883e-07,
"loss": 0.3914,
"step": 3686
},
{
"epoch": 0.96,
"learning_rate": 1.0402377257562435e-07,
"loss": 0.417,
"step": 3687
},
{
"epoch": 0.96,
"learning_rate": 1.0281978111449375e-07,
"loss": 0.4048,
"step": 3688
},
{
"epoch": 0.96,
"learning_rate": 1.0162276188077636e-07,
"loss": 0.4136,
"step": 3689
},
{
"epoch": 0.96,
"learning_rate": 1.0043271571773316e-07,
"loss": 0.415,
"step": 3690
},
{
"epoch": 0.96,
"learning_rate": 9.924964346371136e-08,
"loss": 0.4285,
"step": 3691
},
{
"epoch": 0.96,
"learning_rate": 9.807354595214313e-08,
"loss": 0.4133,
"step": 3692
},
{
"epoch": 0.96,
"learning_rate": 9.690442401155131e-08,
"loss": 0.4221,
"step": 3693
},
{
"epoch": 0.96,
"learning_rate": 9.574227846554151e-08,
"loss": 0.4121,
"step": 3694
},
{
"epoch": 0.96,
"learning_rate": 9.458711013280775e-08,
"loss": 0.4519,
"step": 3695
},
{
"epoch": 0.96,
"learning_rate": 9.34389198271235e-08,
"loss": 0.4163,
"step": 3696
},
{
"epoch": 0.96,
"learning_rate": 9.229770835735286e-08,
"loss": 0.427,
"step": 3697
},
{
"epoch": 0.96,
"learning_rate": 9.11634765274394e-08,
"loss": 0.4077,
"step": 3698
},
{
"epoch": 0.96,
"learning_rate": 9.003622513641064e-08,
"loss": 0.425,
"step": 3699
},
{
"epoch": 0.96,
"learning_rate": 8.891595497837691e-08,
"loss": 0.3975,
"step": 3700
},
{
"epoch": 0.96,
"learning_rate": 8.780266684253025e-08,
"loss": 0.3921,
"step": 3701
},
{
"epoch": 0.96,
"learning_rate": 8.669636151314664e-08,
"loss": 0.4109,
"step": 3702
},
{
"epoch": 0.96,
"learning_rate": 8.559703976957822e-08,
"loss": 0.4268,
"step": 3703
},
{
"epoch": 0.96,
"learning_rate": 8.450470238625996e-08,
"loss": 0.4111,
"step": 3704
},
{
"epoch": 0.96,
"learning_rate": 8.341935013270852e-08,
"loss": 0.4229,
"step": 3705
},
{
"epoch": 0.96,
"learning_rate": 8.23409837735134e-08,
"loss": 0.4148,
"step": 3706
},
{
"epoch": 0.96,
"learning_rate": 8.12696040683525e-08,
"loss": 0.4214,
"step": 3707
},
{
"epoch": 0.96,
"learning_rate": 8.020521177197204e-08,
"loss": 0.4353,
"step": 3708
},
{
"epoch": 0.96,
"learning_rate": 7.914780763420338e-08,
"loss": 0.4241,
"step": 3709
},
{
"epoch": 0.96,
"learning_rate": 7.809739239995062e-08,
"loss": 0.4067,
"step": 3710
},
{
"epoch": 0.96,
"learning_rate": 7.705396680919409e-08,
"loss": 0.4236,
"step": 3711
},
{
"epoch": 0.96,
"learning_rate": 7.601753159699354e-08,
"loss": 0.4136,
"step": 3712
},
{
"epoch": 0.96,
"learning_rate": 7.498808749348274e-08,
"loss": 0.4353,
"step": 3713
},
{
"epoch": 0.96,
"learning_rate": 7.396563522386824e-08,
"loss": 0.4175,
"step": 3714
},
{
"epoch": 0.96,
"learning_rate": 7.295017550843497e-08,
"loss": 0.4116,
"step": 3715
},
{
"epoch": 0.96,
"learning_rate": 7.194170906253851e-08,
"loss": 0.416,
"step": 3716
},
{
"epoch": 0.96,
"learning_rate": 7.094023659660942e-08,
"loss": 0.4189,
"step": 3717
},
{
"epoch": 0.96,
"learning_rate": 6.994575881615118e-08,
"loss": 0.4087,
"step": 3718
},
{
"epoch": 0.96,
"learning_rate": 6.895827642174002e-08,
"loss": 0.4163,
"step": 3719
},
{
"epoch": 0.96,
"learning_rate": 6.797779010902395e-08,
"loss": 0.4114,
"step": 3720
},
{
"epoch": 0.96,
"learning_rate": 6.700430056872043e-08,
"loss": 0.4358,
"step": 3721
},
{
"epoch": 0.96,
"learning_rate": 6.603780848662201e-08,
"loss": 0.3972,
"step": 3722
},
{
"epoch": 0.96,
"learning_rate": 6.507831454358737e-08,
"loss": 0.4189,
"step": 3723
},
{
"epoch": 0.97,
"learning_rate": 6.41258194155503e-08,
"loss": 0.4075,
"step": 3724
},
{
"epoch": 0.97,
"learning_rate": 6.318032377350847e-08,
"loss": 0.4082,
"step": 3725
},
{
"epoch": 0.97,
"learning_rate": 6.224182828353243e-08,
"loss": 0.4294,
"step": 3726
},
{
"epoch": 0.97,
"learning_rate": 6.131033360676219e-08,
"loss": 0.4004,
"step": 3727
},
{
"epoch": 0.97,
"learning_rate": 6.038584039940065e-08,
"loss": 0.4182,
"step": 3728
},
{
"epoch": 0.97,
"learning_rate": 5.946834931272572e-08,
"loss": 0.4053,
"step": 3729
},
{
"epoch": 0.97,
"learning_rate": 5.855786099307481e-08,
"loss": 0.4209,
"step": 3730
},
{
"epoch": 0.97,
"learning_rate": 5.76543760818582e-08,
"loss": 0.4094,
"step": 3731
},
{
"epoch": 0.97,
"learning_rate": 5.67578952155512e-08,
"loss": 0.4353,
"step": 3732
},
{
"epoch": 0.97,
"learning_rate": 5.586841902569196e-08,
"loss": 0.4246,
"step": 3733
},
{
"epoch": 0.97,
"learning_rate": 5.4985948138888135e-08,
"loss": 0.4133,
"step": 3734
},
{
"epoch": 0.97,
"learning_rate": 5.4110483176810224e-08,
"loss": 0.4373,
"step": 3735
},
{
"epoch": 0.97,
"learning_rate": 5.324202475619156e-08,
"loss": 0.4153,
"step": 3736
},
{
"epoch": 0.97,
"learning_rate": 5.2380573488833855e-08,
"loss": 0.4434,
"step": 3737
},
{
"epoch": 0.97,
"learning_rate": 5.152612998159945e-08,
"loss": 0.4131,
"step": 3738
},
{
"epoch": 0.97,
"learning_rate": 5.067869483641574e-08,
"loss": 0.4011,
"step": 3739
},
{
"epoch": 0.97,
"learning_rate": 4.983826865026964e-08,
"loss": 0.3787,
"step": 3740
},
{
"epoch": 0.97,
"learning_rate": 4.900485201521532e-08,
"loss": 0.4167,
"step": 3741
},
{
"epoch": 0.97,
"learning_rate": 4.817844551836426e-08,
"loss": 0.4133,
"step": 3742
},
{
"epoch": 0.97,
"learning_rate": 4.735904974189409e-08,
"loss": 0.4241,
"step": 3743
},
{
"epoch": 0.97,
"learning_rate": 4.6546665263040856e-08,
"loss": 0.4182,
"step": 3744
},
{
"epoch": 0.97,
"learning_rate": 4.57412926541001e-08,
"loss": 0.4336,
"step": 3745
},
{
"epoch": 0.97,
"learning_rate": 4.494293248243131e-08,
"loss": 0.4277,
"step": 3746
},
{
"epoch": 0.97,
"learning_rate": 4.4151585310451274e-08,
"loss": 0.4182,
"step": 3747
},
{
"epoch": 0.97,
"learning_rate": 4.336725169563738e-08,
"loss": 0.3994,
"step": 3748
},
{
"epoch": 0.97,
"learning_rate": 4.258993219052543e-08,
"loss": 0.4094,
"step": 3749
},
{
"epoch": 0.97,
"learning_rate": 4.181962734271183e-08,
"loss": 0.4192,
"step": 3750
},
{
"epoch": 0.97,
"learning_rate": 4.105633769484918e-08,
"loss": 0.4297,
"step": 3751
},
{
"epoch": 0.97,
"learning_rate": 4.030006378464957e-08,
"loss": 0.4229,
"step": 3752
},
{
"epoch": 0.97,
"learning_rate": 3.9550806144882384e-08,
"loss": 0.4153,
"step": 3753
},
{
"epoch": 0.97,
"learning_rate": 3.880856530337429e-08,
"loss": 0.4092,
"step": 3754
},
{
"epoch": 0.97,
"learning_rate": 3.807334178300814e-08,
"loss": 0.437,
"step": 3755
},
{
"epoch": 0.97,
"learning_rate": 3.7345136101724076e-08,
"loss": 0.4021,
"step": 3756
},
{
"epoch": 0.97,
"learning_rate": 3.66239487725184e-08,
"loss": 0.4114,
"step": 3757
},
{
"epoch": 0.97,
"learning_rate": 3.590978030344472e-08,
"loss": 0.4011,
"step": 3758
},
{
"epoch": 0.97,
"learning_rate": 3.5202631197607254e-08,
"loss": 0.4263,
"step": 3759
},
{
"epoch": 0.97,
"learning_rate": 3.450250195317084e-08,
"loss": 0.4287,
"step": 3760
},
{
"epoch": 0.97,
"learning_rate": 3.380939306335318e-08,
"loss": 0.4126,
"step": 3761
},
{
"epoch": 0.97,
"learning_rate": 3.312330501642369e-08,
"loss": 0.4221,
"step": 3762
},
{
"epoch": 0.98,
"learning_rate": 3.244423829570909e-08,
"loss": 0.4124,
"step": 3763
},
{
"epoch": 0.98,
"learning_rate": 3.177219337958892e-08,
"loss": 0.4106,
"step": 3764
},
{
"epoch": 0.98,
"learning_rate": 3.1107170741497827e-08,
"loss": 0.4124,
"step": 3765
},
{
"epoch": 0.98,
"learning_rate": 3.044917084991883e-08,
"loss": 0.405,
"step": 3766
},
{
"epoch": 0.98,
"learning_rate": 2.9798194168391138e-08,
"loss": 0.4167,
"step": 3767
},
{
"epoch": 0.98,
"learning_rate": 2.91542411555068e-08,
"loss": 0.4216,
"step": 3768
},
{
"epoch": 0.98,
"learning_rate": 2.8517312264908502e-08,
"loss": 0.4277,
"step": 3769
},
{
"epoch": 0.98,
"learning_rate": 2.7887407945291768e-08,
"loss": 0.4202,
"step": 3770
},
{
"epoch": 0.98,
"learning_rate": 2.7264528640400522e-08,
"loss": 0.4167,
"step": 3771
},
{
"epoch": 0.98,
"learning_rate": 2.6648674789033767e-08,
"loss": 0.4207,
"step": 3772
},
{
"epoch": 0.98,
"learning_rate": 2.6039846825040015e-08,
"loss": 0.3889,
"step": 3773
},
{
"epoch": 0.98,
"learning_rate": 2.5438045177316183e-08,
"loss": 0.4119,
"step": 3774
},
{
"epoch": 0.98,
"learning_rate": 2.4843270269813147e-08,
"loss": 0.4346,
"step": 3775
},
{
"epoch": 0.98,
"learning_rate": 2.4255522521526853e-08,
"loss": 0.396,
"step": 3776
},
{
"epoch": 0.98,
"learning_rate": 2.3674802346509428e-08,
"loss": 0.4114,
"step": 3777
},
{
"epoch": 0.98,
"learning_rate": 2.3101110153855854e-08,
"loss": 0.4246,
"step": 3778
},
{
"epoch": 0.98,
"learning_rate": 2.2534446347712847e-08,
"loss": 0.4167,
"step": 3779
},
{
"epoch": 0.98,
"learning_rate": 2.1974811327276636e-08,
"loss": 0.3931,
"step": 3780
},
{
"epoch": 0.98,
"learning_rate": 2.142220548679075e-08,
"loss": 0.384,
"step": 3781
},
{
"epoch": 0.98,
"learning_rate": 2.0876629215547118e-08,
"loss": 0.4192,
"step": 3782
},
{
"epoch": 0.98,
"learning_rate": 2.033808289788608e-08,
"loss": 0.4331,
"step": 3783
},
{
"epoch": 0.98,
"learning_rate": 1.9806566913195267e-08,
"loss": 0.4053,
"step": 3784
},
{
"epoch": 0.98,
"learning_rate": 1.928208163590961e-08,
"loss": 0.4189,
"step": 3785
},
{
"epoch": 0.98,
"learning_rate": 1.876462743551022e-08,
"loss": 0.3984,
"step": 3786
},
{
"epoch": 0.98,
"learning_rate": 1.825420467652772e-08,
"loss": 0.4434,
"step": 3787
},
{
"epoch": 0.98,
"learning_rate": 1.77508137185356e-08,
"loss": 0.4426,
"step": 3788
},
{
"epoch": 0.98,
"learning_rate": 1.725445491615796e-08,
"loss": 0.4148,
"step": 3789
},
{
"epoch": 0.98,
"learning_rate": 1.6765128619060656e-08,
"loss": 0.4214,
"step": 3790
},
{
"epoch": 0.98,
"learning_rate": 1.6282835171959055e-08,
"loss": 0.4226,
"step": 3791
},
{
"epoch": 0.98,
"learning_rate": 1.5807574914611378e-08,
"loss": 0.4192,
"step": 3792
},
{
"epoch": 0.98,
"learning_rate": 1.5339348181823144e-08,
"loss": 0.4424,
"step": 3793
},
{
"epoch": 0.98,
"learning_rate": 1.487815530344272e-08,
"loss": 0.4016,
"step": 3794
},
{
"epoch": 0.98,
"learning_rate": 1.4423996604366886e-08,
"loss": 0.4087,
"step": 3795
},
{
"epoch": 0.98,
"learning_rate": 1.3976872404534158e-08,
"loss": 0.4016,
"step": 3796
},
{
"epoch": 0.98,
"learning_rate": 1.3536783018928135e-08,
"loss": 0.4177,
"step": 3797
},
{
"epoch": 0.98,
"learning_rate": 1.3103728757576372e-08,
"loss": 0.4097,
"step": 3798
},
{
"epoch": 0.98,
"learning_rate": 1.2677709925551506e-08,
"loss": 0.4092,
"step": 3799
},
{
"epoch": 0.98,
"learning_rate": 1.2258726822970135e-08,
"loss": 0.4185,
"step": 3800
},
{
"epoch": 0.98,
"learning_rate": 1.184677974498949e-08,
"loss": 0.429,
"step": 3801
},
{
"epoch": 0.99,
"learning_rate": 1.1441868981815207e-08,
"loss": 0.4153,
"step": 3802
},
{
"epoch": 0.99,
"learning_rate": 1.104399481869023e-08,
"loss": 0.4165,
"step": 3803
},
{
"epoch": 0.99,
"learning_rate": 1.06531575359059e-08,
"loss": 0.4248,
"step": 3804
},
{
"epoch": 0.99,
"learning_rate": 1.026935740879198e-08,
"loss": 0.3997,
"step": 3805
},
{
"epoch": 0.99,
"learning_rate": 9.892594707723302e-09,
"loss": 0.3916,
"step": 3806
},
{
"epoch": 0.99,
"learning_rate": 9.522869698116444e-09,
"loss": 0.406,
"step": 3807
},
{
"epoch": 0.99,
"learning_rate": 9.160182640429727e-09,
"loss": 0.4138,
"step": 3808
},
{
"epoch": 0.99,
"learning_rate": 8.804533790165437e-09,
"loss": 0.4189,
"step": 3809
},
{
"epoch": 0.99,
"learning_rate": 8.455923397863164e-09,
"loss": 0.4441,
"step": 3810
},
{
"epoch": 0.99,
"learning_rate": 8.114351709109792e-09,
"loss": 0.4004,
"step": 3811
},
{
"epoch": 0.99,
"learning_rate": 7.779818964530617e-09,
"loss": 0.4199,
"step": 3812
},
{
"epoch": 0.99,
"learning_rate": 7.452325399791571e-09,
"loss": 0.4104,
"step": 3813
},
{
"epoch": 0.99,
"learning_rate": 7.131871245600331e-09,
"loss": 0.4104,
"step": 3814
},
{
"epoch": 0.99,
"learning_rate": 6.818456727707423e-09,
"loss": 0.4075,
"step": 3815
},
{
"epoch": 0.99,
"learning_rate": 6.5120820669017926e-09,
"loss": 0.3921,
"step": 3816
},
{
"epoch": 0.99,
"learning_rate": 6.212747479015236e-09,
"loss": 0.4133,
"step": 3817
},
{
"epoch": 0.99,
"learning_rate": 5.920453174916851e-09,
"loss": 0.4326,
"step": 3818
},
{
"epoch": 0.99,
"learning_rate": 5.635199360519705e-09,
"loss": 0.4221,
"step": 3819
},
{
"epoch": 0.99,
"learning_rate": 5.356986236774165e-09,
"loss": 0.4197,
"step": 3820
},
{
"epoch": 0.99,
"learning_rate": 5.08581399967345e-09,
"loss": 0.4258,
"step": 3821
},
{
"epoch": 0.99,
"learning_rate": 4.821682840248087e-09,
"loss": 0.3965,
"step": 3822
},
{
"epoch": 0.99,
"learning_rate": 4.564592944569235e-09,
"loss": 0.4194,
"step": 3823
},
{
"epoch": 0.99,
"learning_rate": 4.314544493748685e-09,
"loss": 0.4116,
"step": 3824
},
{
"epoch": 0.99,
"learning_rate": 4.071537663936642e-09,
"loss": 0.3997,
"step": 3825
},
{
"epoch": 0.99,
"learning_rate": 3.835572626323947e-09,
"loss": 0.406,
"step": 3826
},
{
"epoch": 0.99,
"learning_rate": 3.606649547139851e-09,
"loss": 0.417,
"step": 3827
},
{
"epoch": 0.99,
"learning_rate": 3.3847685876520208e-09,
"loss": 0.3848,
"step": 3828
},
{
"epoch": 0.99,
"learning_rate": 3.1699299041676457e-09,
"loss": 0.425,
"step": 3829
},
{
"epoch": 0.99,
"learning_rate": 2.9621336480345485e-09,
"loss": 0.405,
"step": 3830
},
{
"epoch": 0.99,
"learning_rate": 2.761379965637856e-09,
"loss": 0.4202,
"step": 3831
},
{
"epoch": 0.99,
"learning_rate": 2.5676689984022173e-09,
"loss": 0.3979,
"step": 3832
},
{
"epoch": 0.99,
"learning_rate": 2.3810008827895857e-09,
"loss": 0.4207,
"step": 3833
},
{
"epoch": 0.99,
"learning_rate": 2.201375750301438e-09,
"loss": 0.4304,
"step": 3834
},
{
"epoch": 0.99,
"learning_rate": 2.0287937274765522e-09,
"loss": 0.4187,
"step": 3835
},
{
"epoch": 0.99,
"learning_rate": 1.863254935895453e-09,
"loss": 0.436,
"step": 3836
},
{
"epoch": 0.99,
"learning_rate": 1.7047594921737465e-09,
"loss": 0.3892,
"step": 3837
},
{
"epoch": 0.99,
"learning_rate": 1.5533075079643411e-09,
"loss": 0.3723,
"step": 3838
},
{
"epoch": 0.99,
"learning_rate": 1.4088990899618904e-09,
"loss": 0.4175,
"step": 3839
},
{
"epoch": 1.0,
"learning_rate": 1.2715343398972401e-09,
"loss": 0.4141,
"step": 3840
},
{
"epoch": 1.0,
"learning_rate": 1.1412133545385395e-09,
"loss": 0.4268,
"step": 3841
},
{
"epoch": 1.0,
"learning_rate": 1.017936225692351e-09,
"loss": 0.4265,
"step": 3842
},
{
"epoch": 1.0,
"learning_rate": 9.017030402036497e-10,
"loss": 0.397,
"step": 3843
},
{
"epoch": 1.0,
"learning_rate": 7.92513879954715e-10,
"loss": 0.4211,
"step": 3844
},
{
"epoch": 1.0,
"learning_rate": 6.903688218651283e-10,
"loss": 0.4036,
"step": 3845
},
{
"epoch": 1.0,
"learning_rate": 5.95267937892885e-10,
"loss": 0.4087,
"step": 3846
},
{
"epoch": 1.0,
"learning_rate": 5.072112950343933e-10,
"loss": 0.4233,
"step": 3847
},
{
"epoch": 1.0,
"learning_rate": 4.2619895532114433e-10,
"loss": 0.4126,
"step": 3848
},
{
"epoch": 1.0,
"learning_rate": 3.522309758230424e-10,
"loss": 0.4294,
"step": 3849
},
{
"epoch": 1.0,
"learning_rate": 2.8530740865062576e-10,
"loss": 0.406,
"step": 3850
},
{
"epoch": 1.0,
"learning_rate": 2.2542830094729462e-10,
"loss": 0.4314,
"step": 3851
},
{
"epoch": 1.0,
"learning_rate": 1.7259369489597277e-10,
"loss": 0.4229,
"step": 3852
},
{
"epoch": 1.0,
"learning_rate": 1.2680362771688714e-10,
"loss": 0.4136,
"step": 3853
},
{
"epoch": 1.0,
"learning_rate": 8.805813166756772e-11,
"loss": 0.427,
"step": 3854
},
{
"epoch": 1.0,
"learning_rate": 5.6357234043957766e-11,
"loss": 0.4243,
"step": 3855
},
{
"epoch": 1.0,
"learning_rate": 3.1700957177083214e-11,
"loss": 0.4087,
"step": 3856
},
{
"epoch": 1.0,
"learning_rate": 1.4089318436383281e-11,
"loss": 0.4285,
"step": 3857
},
{
"epoch": 1.0,
"learning_rate": 3.522330229710491e-12,
"loss": 0.4219,
"step": 3858
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.4307,
"step": 3859
},
{
"epoch": 1.0,
"step": 3859,
"total_flos": 816438756818944.0,
"train_loss": 0.49826279932058176,
"train_runtime": 64871.1521,
"train_samples_per_second": 15.227,
"train_steps_per_second": 0.059
}
],
"logging_steps": 1.0,
"max_steps": 3859,
"num_train_epochs": 1,
"save_steps": 500,
"total_flos": 816438756818944.0,
"trial_name": null,
"trial_params": null
}