pmc-internvl-visionzip-523 / trainer_state.json
KerwinFu's picture
Upload folder using huggingface_hub
ef3440f verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9996397261919059,
"eval_steps": 500,
"global_step": 2081,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 6.34920634920635e-07,
"loss": 1.0895,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.26984126984127e-06,
"loss": 1.1735,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.904761904761905e-06,
"loss": 1.1056,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.53968253968254e-06,
"loss": 1.025,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 3.1746031746031746e-06,
"loss": 1.2185,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 3.80952380952381e-06,
"loss": 1.321,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 4.444444444444444e-06,
"loss": 1.0478,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 5.07936507936508e-06,
"loss": 1.058,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.9844,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 6.349206349206349e-06,
"loss": 1.1117,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 6.984126984126984e-06,
"loss": 1.0519,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 7.61904761904762e-06,
"loss": 1.0784,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 8.253968253968254e-06,
"loss": 1.0631,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 8.888888888888888e-06,
"loss": 1.0115,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 9.523809523809525e-06,
"loss": 1.1257,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 1.015873015873016e-05,
"loss": 1.0646,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 1.0793650793650794e-05,
"loss": 0.9735,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 1.1428571428571429e-05,
"loss": 0.8837,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 1.2063492063492064e-05,
"loss": 1.1921,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 1.2698412698412699e-05,
"loss": 0.9976,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.8809,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 1.3968253968253968e-05,
"loss": 0.9342,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 1.4603174603174603e-05,
"loss": 0.9099,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 1.523809523809524e-05,
"loss": 0.8361,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 1.5873015873015872e-05,
"loss": 0.8963,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 1.6507936507936507e-05,
"loss": 1.0563,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 1.7142857142857142e-05,
"loss": 1.0313,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 1.7777777777777777e-05,
"loss": 0.9952,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 1.8412698412698415e-05,
"loss": 0.9503,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 1.904761904761905e-05,
"loss": 1.0316,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 1.9682539682539684e-05,
"loss": 1.0243,
"step": 31
},
{
"epoch": 0.02,
"learning_rate": 2.031746031746032e-05,
"loss": 0.9671,
"step": 32
},
{
"epoch": 0.02,
"learning_rate": 2.0952380952380954e-05,
"loss": 0.8852,
"step": 33
},
{
"epoch": 0.02,
"learning_rate": 2.158730158730159e-05,
"loss": 0.9168,
"step": 34
},
{
"epoch": 0.02,
"learning_rate": 2.2222222222222227e-05,
"loss": 1.0366,
"step": 35
},
{
"epoch": 0.02,
"learning_rate": 2.2857142857142858e-05,
"loss": 0.824,
"step": 36
},
{
"epoch": 0.02,
"learning_rate": 2.3492063492063496e-05,
"loss": 1.0637,
"step": 37
},
{
"epoch": 0.02,
"learning_rate": 2.4126984126984128e-05,
"loss": 0.9852,
"step": 38
},
{
"epoch": 0.02,
"learning_rate": 2.4761904761904766e-05,
"loss": 0.9821,
"step": 39
},
{
"epoch": 0.02,
"learning_rate": 2.5396825396825397e-05,
"loss": 0.8818,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 2.6031746031746035e-05,
"loss": 0.9603,
"step": 41
},
{
"epoch": 0.02,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.8277,
"step": 42
},
{
"epoch": 0.02,
"learning_rate": 2.7301587301587305e-05,
"loss": 1.063,
"step": 43
},
{
"epoch": 0.02,
"learning_rate": 2.7936507936507936e-05,
"loss": 0.9686,
"step": 44
},
{
"epoch": 0.02,
"learning_rate": 2.8571428571428574e-05,
"loss": 0.8671,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 2.9206349206349206e-05,
"loss": 0.709,
"step": 46
},
{
"epoch": 0.02,
"learning_rate": 2.9841269841269844e-05,
"loss": 0.9644,
"step": 47
},
{
"epoch": 0.02,
"learning_rate": 3.047619047619048e-05,
"loss": 0.7724,
"step": 48
},
{
"epoch": 0.02,
"learning_rate": 3.111111111111112e-05,
"loss": 0.9273,
"step": 49
},
{
"epoch": 0.02,
"learning_rate": 3.1746031746031745e-05,
"loss": 0.9536,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 3.2380952380952386e-05,
"loss": 0.8431,
"step": 51
},
{
"epoch": 0.02,
"learning_rate": 3.3015873015873014e-05,
"loss": 0.7777,
"step": 52
},
{
"epoch": 0.03,
"learning_rate": 3.3650793650793656e-05,
"loss": 0.8895,
"step": 53
},
{
"epoch": 0.03,
"learning_rate": 3.4285714285714284e-05,
"loss": 0.9128,
"step": 54
},
{
"epoch": 0.03,
"learning_rate": 3.4920634920634925e-05,
"loss": 0.9728,
"step": 55
},
{
"epoch": 0.03,
"learning_rate": 3.555555555555555e-05,
"loss": 1.0591,
"step": 56
},
{
"epoch": 0.03,
"learning_rate": 3.6190476190476195e-05,
"loss": 0.9821,
"step": 57
},
{
"epoch": 0.03,
"learning_rate": 3.682539682539683e-05,
"loss": 0.7926,
"step": 58
},
{
"epoch": 0.03,
"learning_rate": 3.7460317460317464e-05,
"loss": 0.9065,
"step": 59
},
{
"epoch": 0.03,
"learning_rate": 3.80952380952381e-05,
"loss": 0.9164,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 3.8730158730158734e-05,
"loss": 0.9762,
"step": 61
},
{
"epoch": 0.03,
"learning_rate": 3.936507936507937e-05,
"loss": 0.9714,
"step": 62
},
{
"epoch": 0.03,
"learning_rate": 4e-05,
"loss": 0.8679,
"step": 63
},
{
"epoch": 0.03,
"learning_rate": 3.9999975764201455e-05,
"loss": 1.0564,
"step": 64
},
{
"epoch": 0.03,
"learning_rate": 3.999990305686455e-05,
"loss": 0.7128,
"step": 65
},
{
"epoch": 0.03,
"learning_rate": 3.999978187816552e-05,
"loss": 0.8653,
"step": 66
},
{
"epoch": 0.03,
"learning_rate": 3.999961222839802e-05,
"loss": 0.802,
"step": 67
},
{
"epoch": 0.03,
"learning_rate": 3.999939410797322e-05,
"loss": 0.8232,
"step": 68
},
{
"epoch": 0.03,
"learning_rate": 3.999912751741976e-05,
"loss": 0.9164,
"step": 69
},
{
"epoch": 0.03,
"learning_rate": 3.9998812457383744e-05,
"loss": 0.8491,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 3.999844892862873e-05,
"loss": 0.8464,
"step": 71
},
{
"epoch": 0.03,
"learning_rate": 3.999803693203578e-05,
"loss": 0.9416,
"step": 72
},
{
"epoch": 0.04,
"learning_rate": 3.9997576468603386e-05,
"loss": 0.8149,
"step": 73
},
{
"epoch": 0.04,
"learning_rate": 3.999706753944752e-05,
"loss": 0.9426,
"step": 74
},
{
"epoch": 0.04,
"learning_rate": 3.9996510145801614e-05,
"loss": 0.9123,
"step": 75
},
{
"epoch": 0.04,
"learning_rate": 3.9995904289016565e-05,
"loss": 0.8335,
"step": 76
},
{
"epoch": 0.04,
"learning_rate": 3.9995249970560695e-05,
"loss": 0.8679,
"step": 77
},
{
"epoch": 0.04,
"learning_rate": 3.999454719201982e-05,
"loss": 0.8677,
"step": 78
},
{
"epoch": 0.04,
"learning_rate": 3.9993795955097156e-05,
"loss": 0.8351,
"step": 79
},
{
"epoch": 0.04,
"learning_rate": 3.999299626161341e-05,
"loss": 0.9645,
"step": 80
},
{
"epoch": 0.04,
"learning_rate": 3.999214811350669e-05,
"loss": 1.0644,
"step": 81
},
{
"epoch": 0.04,
"learning_rate": 3.9991251512832544e-05,
"loss": 0.7915,
"step": 82
},
{
"epoch": 0.04,
"learning_rate": 3.999030646176397e-05,
"loss": 0.8231,
"step": 83
},
{
"epoch": 0.04,
"learning_rate": 3.998931296259136e-05,
"loss": 0.8896,
"step": 84
},
{
"epoch": 0.04,
"learning_rate": 3.9988271017722564e-05,
"loss": 0.9326,
"step": 85
},
{
"epoch": 0.04,
"learning_rate": 3.998718062968278e-05,
"loss": 0.8982,
"step": 86
},
{
"epoch": 0.04,
"learning_rate": 3.9986041801114687e-05,
"loss": 0.9352,
"step": 87
},
{
"epoch": 0.04,
"learning_rate": 3.998485453477831e-05,
"loss": 0.8479,
"step": 88
},
{
"epoch": 0.04,
"learning_rate": 3.998361883355108e-05,
"loss": 0.7637,
"step": 89
},
{
"epoch": 0.04,
"learning_rate": 3.9982334700427825e-05,
"loss": 0.8371,
"step": 90
},
{
"epoch": 0.04,
"learning_rate": 3.998100213852075e-05,
"loss": 0.9657,
"step": 91
},
{
"epoch": 0.04,
"learning_rate": 3.9979621151059405e-05,
"loss": 1.0443,
"step": 92
},
{
"epoch": 0.04,
"learning_rate": 3.997819174139074e-05,
"loss": 0.8705,
"step": 93
},
{
"epoch": 0.05,
"learning_rate": 3.9976713912979045e-05,
"loss": 0.7415,
"step": 94
},
{
"epoch": 0.05,
"learning_rate": 3.9975187669405945e-05,
"loss": 1.0969,
"step": 95
},
{
"epoch": 0.05,
"learning_rate": 3.997361301437042e-05,
"loss": 0.9489,
"step": 96
},
{
"epoch": 0.05,
"learning_rate": 3.9971989951688767e-05,
"loss": 0.8558,
"step": 97
},
{
"epoch": 0.05,
"learning_rate": 3.997031848529461e-05,
"loss": 0.8709,
"step": 98
},
{
"epoch": 0.05,
"learning_rate": 3.996859861923888e-05,
"loss": 0.7765,
"step": 99
},
{
"epoch": 0.05,
"learning_rate": 3.996683035768982e-05,
"loss": 0.9204,
"step": 100
},
{
"epoch": 0.05,
"learning_rate": 3.996501370493294e-05,
"loss": 0.8125,
"step": 101
},
{
"epoch": 0.05,
"learning_rate": 3.996314866537105e-05,
"loss": 0.8693,
"step": 102
},
{
"epoch": 0.05,
"learning_rate": 3.9961235243524224e-05,
"loss": 0.7341,
"step": 103
},
{
"epoch": 0.05,
"learning_rate": 3.9959273444029784e-05,
"loss": 0.7737,
"step": 104
},
{
"epoch": 0.05,
"learning_rate": 3.995726327164231e-05,
"loss": 0.9845,
"step": 105
},
{
"epoch": 0.05,
"learning_rate": 3.995520473123362e-05,
"loss": 0.9002,
"step": 106
},
{
"epoch": 0.05,
"learning_rate": 3.995309782779275e-05,
"loss": 0.8678,
"step": 107
},
{
"epoch": 0.05,
"learning_rate": 3.9950942566425954e-05,
"loss": 0.8083,
"step": 108
},
{
"epoch": 0.05,
"learning_rate": 3.9948738952356666e-05,
"loss": 0.7714,
"step": 109
},
{
"epoch": 0.05,
"learning_rate": 3.9946486990925525e-05,
"loss": 0.8358,
"step": 110
},
{
"epoch": 0.05,
"learning_rate": 3.9944186687590357e-05,
"loss": 0.7999,
"step": 111
},
{
"epoch": 0.05,
"learning_rate": 3.994183804792611e-05,
"loss": 1.045,
"step": 112
},
{
"epoch": 0.05,
"learning_rate": 3.9939441077624896e-05,
"loss": 0.905,
"step": 113
},
{
"epoch": 0.05,
"learning_rate": 3.993699578249599e-05,
"loss": 0.8678,
"step": 114
},
{
"epoch": 0.06,
"learning_rate": 3.993450216846573e-05,
"loss": 0.8256,
"step": 115
},
{
"epoch": 0.06,
"learning_rate": 3.993196024157762e-05,
"loss": 0.8424,
"step": 116
},
{
"epoch": 0.06,
"learning_rate": 3.992937000799219e-05,
"loss": 0.8764,
"step": 117
},
{
"epoch": 0.06,
"learning_rate": 3.9926731473987104e-05,
"loss": 0.858,
"step": 118
},
{
"epoch": 0.06,
"learning_rate": 3.992404464595705e-05,
"loss": 0.8272,
"step": 119
},
{
"epoch": 0.06,
"learning_rate": 3.9921309530413764e-05,
"loss": 0.8956,
"step": 120
},
{
"epoch": 0.06,
"learning_rate": 3.991852613398603e-05,
"loss": 0.8312,
"step": 121
},
{
"epoch": 0.06,
"learning_rate": 3.991569446341962e-05,
"loss": 0.8409,
"step": 122
},
{
"epoch": 0.06,
"learning_rate": 3.991281452557732e-05,
"loss": 0.923,
"step": 123
},
{
"epoch": 0.06,
"learning_rate": 3.990988632743888e-05,
"loss": 0.9534,
"step": 124
},
{
"epoch": 0.06,
"learning_rate": 3.990690987610104e-05,
"loss": 0.8584,
"step": 125
},
{
"epoch": 0.06,
"learning_rate": 3.9903885178777445e-05,
"loss": 0.7978,
"step": 126
},
{
"epoch": 0.06,
"learning_rate": 3.990081224279872e-05,
"loss": 0.8837,
"step": 127
},
{
"epoch": 0.06,
"learning_rate": 3.989769107561234e-05,
"loss": 0.9165,
"step": 128
},
{
"epoch": 0.06,
"learning_rate": 3.9894521684782715e-05,
"loss": 0.8943,
"step": 129
},
{
"epoch": 0.06,
"learning_rate": 3.989130407799113e-05,
"loss": 1.0133,
"step": 130
},
{
"epoch": 0.06,
"learning_rate": 3.9888038263035686e-05,
"loss": 1.0161,
"step": 131
},
{
"epoch": 0.06,
"learning_rate": 3.988472424783137e-05,
"loss": 0.8745,
"step": 132
},
{
"epoch": 0.06,
"learning_rate": 3.988136204040995e-05,
"loss": 0.7766,
"step": 133
},
{
"epoch": 0.06,
"learning_rate": 3.987795164892001e-05,
"loss": 0.7795,
"step": 134
},
{
"epoch": 0.06,
"learning_rate": 3.98744930816269e-05,
"loss": 0.8202,
"step": 135
},
{
"epoch": 0.07,
"learning_rate": 3.987098634691274e-05,
"loss": 1.0134,
"step": 136
},
{
"epoch": 0.07,
"learning_rate": 3.986743145327637e-05,
"loss": 0.8346,
"step": 137
},
{
"epoch": 0.07,
"learning_rate": 3.9863828409333374e-05,
"loss": 0.8658,
"step": 138
},
{
"epoch": 0.07,
"learning_rate": 3.986017722381601e-05,
"loss": 0.9497,
"step": 139
},
{
"epoch": 0.07,
"learning_rate": 3.9856477905573214e-05,
"loss": 0.9212,
"step": 140
},
{
"epoch": 0.07,
"learning_rate": 3.985273046357059e-05,
"loss": 0.8871,
"step": 141
},
{
"epoch": 0.07,
"learning_rate": 3.984893490689035e-05,
"loss": 0.8555,
"step": 142
},
{
"epoch": 0.07,
"learning_rate": 3.9845091244731337e-05,
"loss": 0.794,
"step": 143
},
{
"epoch": 0.07,
"learning_rate": 3.984119948640897e-05,
"loss": 0.8643,
"step": 144
},
{
"epoch": 0.07,
"learning_rate": 3.9837259641355235e-05,
"loss": 0.8282,
"step": 145
},
{
"epoch": 0.07,
"learning_rate": 3.9833271719118664e-05,
"loss": 0.696,
"step": 146
},
{
"epoch": 0.07,
"learning_rate": 3.9829235729364306e-05,
"loss": 0.816,
"step": 147
},
{
"epoch": 0.07,
"learning_rate": 3.9825151681873705e-05,
"loss": 0.8172,
"step": 148
},
{
"epoch": 0.07,
"learning_rate": 3.982101958654487e-05,
"loss": 0.9991,
"step": 149
},
{
"epoch": 0.07,
"learning_rate": 3.981683945339226e-05,
"loss": 0.8788,
"step": 150
},
{
"epoch": 0.07,
"learning_rate": 3.981261129254678e-05,
"loss": 0.9226,
"step": 151
},
{
"epoch": 0.07,
"learning_rate": 3.98083351142557e-05,
"loss": 0.8852,
"step": 152
},
{
"epoch": 0.07,
"learning_rate": 3.9804010928882684e-05,
"loss": 0.8589,
"step": 153
},
{
"epoch": 0.07,
"learning_rate": 3.979963874690774e-05,
"loss": 0.8704,
"step": 154
},
{
"epoch": 0.07,
"learning_rate": 3.97952185789272e-05,
"loss": 0.7783,
"step": 155
},
{
"epoch": 0.07,
"learning_rate": 3.9790750435653705e-05,
"loss": 0.8171,
"step": 156
},
{
"epoch": 0.08,
"learning_rate": 3.9786234327916136e-05,
"loss": 0.7907,
"step": 157
},
{
"epoch": 0.08,
"learning_rate": 3.978167026665965e-05,
"loss": 0.7421,
"step": 158
},
{
"epoch": 0.08,
"learning_rate": 3.9777058262945624e-05,
"loss": 0.8666,
"step": 159
},
{
"epoch": 0.08,
"learning_rate": 3.97723983279516e-05,
"loss": 0.8571,
"step": 160
},
{
"epoch": 0.08,
"learning_rate": 3.976769047297132e-05,
"loss": 0.7975,
"step": 161
},
{
"epoch": 0.08,
"learning_rate": 3.976293470941463e-05,
"loss": 1.0014,
"step": 162
},
{
"epoch": 0.08,
"learning_rate": 3.975813104880752e-05,
"loss": 0.8491,
"step": 163
},
{
"epoch": 0.08,
"learning_rate": 3.975327950279203e-05,
"loss": 0.9437,
"step": 164
},
{
"epoch": 0.08,
"learning_rate": 3.9748380083126274e-05,
"loss": 0.7329,
"step": 165
},
{
"epoch": 0.08,
"learning_rate": 3.974343280168439e-05,
"loss": 1.0359,
"step": 166
},
{
"epoch": 0.08,
"learning_rate": 3.97384376704565e-05,
"loss": 0.7802,
"step": 167
},
{
"epoch": 0.08,
"learning_rate": 3.973339470154872e-05,
"loss": 0.9464,
"step": 168
},
{
"epoch": 0.08,
"learning_rate": 3.972830390718308e-05,
"loss": 0.9039,
"step": 169
},
{
"epoch": 0.08,
"learning_rate": 3.972316529969752e-05,
"loss": 0.8495,
"step": 170
},
{
"epoch": 0.08,
"learning_rate": 3.971797889154587e-05,
"loss": 0.8585,
"step": 171
},
{
"epoch": 0.08,
"learning_rate": 3.971274469529781e-05,
"loss": 1.0326,
"step": 172
},
{
"epoch": 0.08,
"learning_rate": 3.970746272363882e-05,
"loss": 0.9453,
"step": 173
},
{
"epoch": 0.08,
"learning_rate": 3.9702132989370195e-05,
"loss": 0.8943,
"step": 174
},
{
"epoch": 0.08,
"learning_rate": 3.969675550540897e-05,
"loss": 0.849,
"step": 175
},
{
"epoch": 0.08,
"learning_rate": 3.9691330284787885e-05,
"loss": 0.9529,
"step": 176
},
{
"epoch": 0.09,
"learning_rate": 3.968585734065542e-05,
"loss": 0.8069,
"step": 177
},
{
"epoch": 0.09,
"learning_rate": 3.968033668627569e-05,
"loss": 0.8602,
"step": 178
},
{
"epoch": 0.09,
"learning_rate": 3.967476833502842e-05,
"loss": 0.9173,
"step": 179
},
{
"epoch": 0.09,
"learning_rate": 3.966915230040898e-05,
"loss": 0.9686,
"step": 180
},
{
"epoch": 0.09,
"learning_rate": 3.966348859602826e-05,
"loss": 1.0021,
"step": 181
},
{
"epoch": 0.09,
"learning_rate": 3.965777723561272e-05,
"loss": 0.8489,
"step": 182
},
{
"epoch": 0.09,
"learning_rate": 3.9652018233004285e-05,
"loss": 0.8457,
"step": 183
},
{
"epoch": 0.09,
"learning_rate": 3.964621160216035e-05,
"loss": 0.9543,
"step": 184
},
{
"epoch": 0.09,
"learning_rate": 3.964035735715376e-05,
"loss": 0.8194,
"step": 185
},
{
"epoch": 0.09,
"learning_rate": 3.963445551217274e-05,
"loss": 0.8343,
"step": 186
},
{
"epoch": 0.09,
"learning_rate": 3.962850608152089e-05,
"loss": 0.8299,
"step": 187
},
{
"epoch": 0.09,
"learning_rate": 3.9622509079617126e-05,
"loss": 1.0046,
"step": 188
},
{
"epoch": 0.09,
"learning_rate": 3.961646452099565e-05,
"loss": 0.9438,
"step": 189
},
{
"epoch": 0.09,
"learning_rate": 3.9610372420305954e-05,
"loss": 0.8098,
"step": 190
},
{
"epoch": 0.09,
"learning_rate": 3.960423279231271e-05,
"loss": 0.8244,
"step": 191
},
{
"epoch": 0.09,
"learning_rate": 3.959804565189581e-05,
"loss": 0.8205,
"step": 192
},
{
"epoch": 0.09,
"learning_rate": 3.959181101405028e-05,
"loss": 0.905,
"step": 193
},
{
"epoch": 0.09,
"learning_rate": 3.958552889388626e-05,
"loss": 0.7775,
"step": 194
},
{
"epoch": 0.09,
"learning_rate": 3.957919930662897e-05,
"loss": 0.8515,
"step": 195
},
{
"epoch": 0.09,
"learning_rate": 3.957282226761867e-05,
"loss": 0.8241,
"step": 196
},
{
"epoch": 0.09,
"learning_rate": 3.9566397792310634e-05,
"loss": 0.8827,
"step": 197
},
{
"epoch": 0.1,
"learning_rate": 3.9559925896275074e-05,
"loss": 0.9258,
"step": 198
},
{
"epoch": 0.1,
"learning_rate": 3.955340659519715e-05,
"loss": 0.8532,
"step": 199
},
{
"epoch": 0.1,
"learning_rate": 3.954683990487692e-05,
"loss": 0.7331,
"step": 200
},
{
"epoch": 0.1,
"learning_rate": 3.9540225841229274e-05,
"loss": 0.8455,
"step": 201
},
{
"epoch": 0.1,
"learning_rate": 3.9533564420283923e-05,
"loss": 0.7878,
"step": 202
},
{
"epoch": 0.1,
"learning_rate": 3.952685565818536e-05,
"loss": 0.8024,
"step": 203
},
{
"epoch": 0.1,
"learning_rate": 3.95200995711928e-05,
"loss": 0.9417,
"step": 204
},
{
"epoch": 0.1,
"learning_rate": 3.951329617568015e-05,
"loss": 0.9053,
"step": 205
},
{
"epoch": 0.1,
"learning_rate": 3.9506445488135995e-05,
"loss": 0.7534,
"step": 206
},
{
"epoch": 0.1,
"learning_rate": 3.949954752516353e-05,
"loss": 0.8626,
"step": 207
},
{
"epoch": 0.1,
"learning_rate": 3.94926023034805e-05,
"loss": 0.9647,
"step": 208
},
{
"epoch": 0.1,
"learning_rate": 3.948560983991922e-05,
"loss": 0.7573,
"step": 209
},
{
"epoch": 0.1,
"learning_rate": 3.9478570151426475e-05,
"loss": 0.7788,
"step": 210
},
{
"epoch": 0.1,
"learning_rate": 3.947148325506351e-05,
"loss": 0.8151,
"step": 211
},
{
"epoch": 0.1,
"learning_rate": 3.946434916800599e-05,
"loss": 0.8526,
"step": 212
},
{
"epoch": 0.1,
"learning_rate": 3.945716790754395e-05,
"loss": 0.9234,
"step": 213
},
{
"epoch": 0.1,
"learning_rate": 3.944993949108174e-05,
"loss": 0.8133,
"step": 214
},
{
"epoch": 0.1,
"learning_rate": 3.9442663936138e-05,
"loss": 0.6915,
"step": 215
},
{
"epoch": 0.1,
"learning_rate": 3.9435341260345636e-05,
"loss": 0.7824,
"step": 216
},
{
"epoch": 0.1,
"learning_rate": 3.9427971481451715e-05,
"loss": 0.7328,
"step": 217
},
{
"epoch": 0.1,
"learning_rate": 3.942055461731751e-05,
"loss": 0.8685,
"step": 218
},
{
"epoch": 0.11,
"learning_rate": 3.941309068591835e-05,
"loss": 0.8444,
"step": 219
},
{
"epoch": 0.11,
"learning_rate": 3.9405579705343705e-05,
"loss": 0.982,
"step": 220
},
{
"epoch": 0.11,
"learning_rate": 3.939802169379701e-05,
"loss": 0.8162,
"step": 221
},
{
"epoch": 0.11,
"learning_rate": 3.9390416669595725e-05,
"loss": 1.0345,
"step": 222
},
{
"epoch": 0.11,
"learning_rate": 3.938276465117122e-05,
"loss": 0.8799,
"step": 223
},
{
"epoch": 0.11,
"learning_rate": 3.9375065657068786e-05,
"loss": 0.8206,
"step": 224
},
{
"epoch": 0.11,
"learning_rate": 3.9367319705947545e-05,
"loss": 0.7084,
"step": 225
},
{
"epoch": 0.11,
"learning_rate": 3.9359526816580425e-05,
"loss": 0.9249,
"step": 226
},
{
"epoch": 0.11,
"learning_rate": 3.935168700785411e-05,
"loss": 0.8001,
"step": 227
},
{
"epoch": 0.11,
"learning_rate": 3.934380029876902e-05,
"loss": 0.7561,
"step": 228
},
{
"epoch": 0.11,
"learning_rate": 3.933586670843922e-05,
"loss": 0.8732,
"step": 229
},
{
"epoch": 0.11,
"learning_rate": 3.9327886256092383e-05,
"loss": 0.9032,
"step": 230
},
{
"epoch": 0.11,
"learning_rate": 3.9319858961069794e-05,
"loss": 0.9088,
"step": 231
},
{
"epoch": 0.11,
"learning_rate": 3.9311784842826224e-05,
"loss": 0.9444,
"step": 232
},
{
"epoch": 0.11,
"learning_rate": 3.930366392092995e-05,
"loss": 0.7806,
"step": 233
},
{
"epoch": 0.11,
"learning_rate": 3.929549621506269e-05,
"loss": 0.8636,
"step": 234
},
{
"epoch": 0.11,
"learning_rate": 3.928728174501951e-05,
"loss": 0.8668,
"step": 235
},
{
"epoch": 0.11,
"learning_rate": 3.927902053070884e-05,
"loss": 0.8495,
"step": 236
},
{
"epoch": 0.11,
"learning_rate": 3.92707125921524e-05,
"loss": 0.8076,
"step": 237
},
{
"epoch": 0.11,
"learning_rate": 3.926235794948515e-05,
"loss": 0.8652,
"step": 238
},
{
"epoch": 0.11,
"learning_rate": 3.9253956622955206e-05,
"loss": 0.6898,
"step": 239
},
{
"epoch": 0.12,
"learning_rate": 3.924550863292387e-05,
"loss": 0.8157,
"step": 240
},
{
"epoch": 0.12,
"learning_rate": 3.923701399986553e-05,
"loss": 0.8027,
"step": 241
},
{
"epoch": 0.12,
"learning_rate": 3.922847274436759e-05,
"loss": 0.8884,
"step": 242
},
{
"epoch": 0.12,
"learning_rate": 3.9219884887130474e-05,
"loss": 0.99,
"step": 243
},
{
"epoch": 0.12,
"learning_rate": 3.9211250448967535e-05,
"loss": 0.9088,
"step": 244
},
{
"epoch": 0.12,
"learning_rate": 3.920256945080502e-05,
"loss": 0.9476,
"step": 245
},
{
"epoch": 0.12,
"learning_rate": 3.919384191368204e-05,
"loss": 0.8133,
"step": 246
},
{
"epoch": 0.12,
"learning_rate": 3.9185067858750464e-05,
"loss": 0.8581,
"step": 247
},
{
"epoch": 0.12,
"learning_rate": 3.917624730727491e-05,
"loss": 0.7402,
"step": 248
},
{
"epoch": 0.12,
"learning_rate": 3.91673802806327e-05,
"loss": 0.7575,
"step": 249
},
{
"epoch": 0.12,
"learning_rate": 3.9158466800313776e-05,
"loss": 0.8305,
"step": 250
},
{
"epoch": 0.12,
"learning_rate": 3.9149506887920676e-05,
"loss": 0.8849,
"step": 251
},
{
"epoch": 0.12,
"learning_rate": 3.914050056516845e-05,
"loss": 0.7999,
"step": 252
},
{
"epoch": 0.12,
"learning_rate": 3.913144785388465e-05,
"loss": 0.7355,
"step": 253
},
{
"epoch": 0.12,
"learning_rate": 3.9122348776009236e-05,
"loss": 0.9156,
"step": 254
},
{
"epoch": 0.12,
"learning_rate": 3.911320335359456e-05,
"loss": 0.8758,
"step": 255
},
{
"epoch": 0.12,
"learning_rate": 3.9104011608805284e-05,
"loss": 0.9079,
"step": 256
},
{
"epoch": 0.12,
"learning_rate": 3.909477356391833e-05,
"loss": 0.6066,
"step": 257
},
{
"epoch": 0.12,
"learning_rate": 3.908548924132283e-05,
"loss": 0.832,
"step": 258
},
{
"epoch": 0.12,
"learning_rate": 3.90761586635201e-05,
"loss": 0.8857,
"step": 259
},
{
"epoch": 0.12,
"learning_rate": 3.9066781853123526e-05,
"loss": 0.9132,
"step": 260
},
{
"epoch": 0.13,
"learning_rate": 3.905735883285856e-05,
"loss": 0.8525,
"step": 261
},
{
"epoch": 0.13,
"learning_rate": 3.9047889625562643e-05,
"loss": 0.7316,
"step": 262
},
{
"epoch": 0.13,
"learning_rate": 3.903837425418516e-05,
"loss": 0.7448,
"step": 263
},
{
"epoch": 0.13,
"learning_rate": 3.902881274178737e-05,
"loss": 0.8542,
"step": 264
},
{
"epoch": 0.13,
"learning_rate": 3.901920511154236e-05,
"loss": 0.7311,
"step": 265
},
{
"epoch": 0.13,
"learning_rate": 3.9009551386734996e-05,
"loss": 0.8629,
"step": 266
},
{
"epoch": 0.13,
"learning_rate": 3.899985159076184e-05,
"loss": 0.8525,
"step": 267
},
{
"epoch": 0.13,
"learning_rate": 3.8990105747131135e-05,
"loss": 0.8914,
"step": 268
},
{
"epoch": 0.13,
"learning_rate": 3.8980313879462694e-05,
"loss": 0.7484,
"step": 269
},
{
"epoch": 0.13,
"learning_rate": 3.897047601148791e-05,
"loss": 0.7643,
"step": 270
},
{
"epoch": 0.13,
"learning_rate": 3.8960592167049635e-05,
"loss": 0.8069,
"step": 271
},
{
"epoch": 0.13,
"learning_rate": 3.8950662370102145e-05,
"loss": 1.0453,
"step": 272
},
{
"epoch": 0.13,
"learning_rate": 3.8940686644711104e-05,
"loss": 0.8446,
"step": 273
},
{
"epoch": 0.13,
"learning_rate": 3.893066501505349e-05,
"loss": 0.8343,
"step": 274
},
{
"epoch": 0.13,
"learning_rate": 3.89205975054175e-05,
"loss": 0.8245,
"step": 275
},
{
"epoch": 0.13,
"learning_rate": 3.891048414020256e-05,
"loss": 0.8813,
"step": 276
},
{
"epoch": 0.13,
"learning_rate": 3.890032494391922e-05,
"loss": 0.7409,
"step": 277
},
{
"epoch": 0.13,
"learning_rate": 3.8890119941189103e-05,
"loss": 0.7772,
"step": 278
},
{
"epoch": 0.13,
"learning_rate": 3.8879869156744845e-05,
"loss": 0.8946,
"step": 279
},
{
"epoch": 0.13,
"learning_rate": 3.886957261543003e-05,
"loss": 0.8574,
"step": 280
},
{
"epoch": 0.13,
"learning_rate": 3.8859230342199174e-05,
"loss": 0.8977,
"step": 281
},
{
"epoch": 0.14,
"learning_rate": 3.8848842362117584e-05,
"loss": 0.9835,
"step": 282
},
{
"epoch": 0.14,
"learning_rate": 3.883840870036136e-05,
"loss": 0.9123,
"step": 283
},
{
"epoch": 0.14,
"learning_rate": 3.882792938221732e-05,
"loss": 0.7726,
"step": 284
},
{
"epoch": 0.14,
"learning_rate": 3.881740443308292e-05,
"loss": 0.8565,
"step": 285
},
{
"epoch": 0.14,
"learning_rate": 3.880683387846623e-05,
"loss": 0.9208,
"step": 286
},
{
"epoch": 0.14,
"learning_rate": 3.879621774398581e-05,
"loss": 0.8102,
"step": 287
},
{
"epoch": 0.14,
"learning_rate": 3.878555605537074e-05,
"loss": 0.8464,
"step": 288
},
{
"epoch": 0.14,
"learning_rate": 3.877484883846044e-05,
"loss": 0.7296,
"step": 289
},
{
"epoch": 0.14,
"learning_rate": 3.8764096119204735e-05,
"loss": 0.8411,
"step": 290
},
{
"epoch": 0.14,
"learning_rate": 3.8753297923663685e-05,
"loss": 0.7941,
"step": 291
},
{
"epoch": 0.14,
"learning_rate": 3.874245427800757e-05,
"loss": 0.8525,
"step": 292
},
{
"epoch": 0.14,
"learning_rate": 3.873156520851684e-05,
"loss": 0.7985,
"step": 293
},
{
"epoch": 0.14,
"learning_rate": 3.872063074158204e-05,
"loss": 0.9064,
"step": 294
},
{
"epoch": 0.14,
"learning_rate": 3.87096509037037e-05,
"loss": 0.8325,
"step": 295
},
{
"epoch": 0.14,
"learning_rate": 3.869862572149234e-05,
"loss": 0.961,
"step": 296
},
{
"epoch": 0.14,
"learning_rate": 3.868755522166838e-05,
"loss": 0.9097,
"step": 297
},
{
"epoch": 0.14,
"learning_rate": 3.8676439431062054e-05,
"loss": 0.8137,
"step": 298
},
{
"epoch": 0.14,
"learning_rate": 3.866527837661337e-05,
"loss": 0.8879,
"step": 299
},
{
"epoch": 0.14,
"learning_rate": 3.865407208537202e-05,
"loss": 0.8256,
"step": 300
},
{
"epoch": 0.14,
"learning_rate": 3.8642820584497366e-05,
"loss": 0.8636,
"step": 301
},
{
"epoch": 0.15,
"learning_rate": 3.863152390125831e-05,
"loss": 0.8038,
"step": 302
},
{
"epoch": 0.15,
"learning_rate": 3.862018206303327e-05,
"loss": 0.8884,
"step": 303
},
{
"epoch": 0.15,
"learning_rate": 3.860879509731009e-05,
"loss": 0.7455,
"step": 304
},
{
"epoch": 0.15,
"learning_rate": 3.859736303168599e-05,
"loss": 0.9096,
"step": 305
},
{
"epoch": 0.15,
"learning_rate": 3.85858858938675e-05,
"loss": 0.8153,
"step": 306
},
{
"epoch": 0.15,
"learning_rate": 3.857436371167038e-05,
"loss": 0.7047,
"step": 307
},
{
"epoch": 0.15,
"learning_rate": 3.856279651301955e-05,
"loss": 0.7015,
"step": 308
},
{
"epoch": 0.15,
"learning_rate": 3.855118432594905e-05,
"loss": 0.8313,
"step": 309
},
{
"epoch": 0.15,
"learning_rate": 3.8539527178601945e-05,
"loss": 0.792,
"step": 310
},
{
"epoch": 0.15,
"learning_rate": 3.8527825099230244e-05,
"loss": 0.8633,
"step": 311
},
{
"epoch": 0.15,
"learning_rate": 3.851607811619489e-05,
"loss": 0.7343,
"step": 312
},
{
"epoch": 0.15,
"learning_rate": 3.850428625796563e-05,
"loss": 0.8593,
"step": 313
},
{
"epoch": 0.15,
"learning_rate": 3.849244955312097e-05,
"loss": 0.8673,
"step": 314
},
{
"epoch": 0.15,
"learning_rate": 3.848056803034811e-05,
"loss": 0.8153,
"step": 315
},
{
"epoch": 0.15,
"learning_rate": 3.8468641718442875e-05,
"loss": 0.8026,
"step": 316
},
{
"epoch": 0.15,
"learning_rate": 3.845667064630962e-05,
"loss": 0.8072,
"step": 317
},
{
"epoch": 0.15,
"learning_rate": 3.844465484296121e-05,
"loss": 0.8605,
"step": 318
},
{
"epoch": 0.15,
"learning_rate": 3.84325943375189e-05,
"loss": 0.7819,
"step": 319
},
{
"epoch": 0.15,
"learning_rate": 3.8420489159212276e-05,
"loss": 0.9863,
"step": 320
},
{
"epoch": 0.15,
"learning_rate": 3.8408339337379216e-05,
"loss": 0.9353,
"step": 321
},
{
"epoch": 0.15,
"learning_rate": 3.839614490146579e-05,
"loss": 0.7617,
"step": 322
},
{
"epoch": 0.16,
"learning_rate": 3.838390588102617e-05,
"loss": 0.9067,
"step": 323
},
{
"epoch": 0.16,
"learning_rate": 3.837162230572262e-05,
"loss": 0.9405,
"step": 324
},
{
"epoch": 0.16,
"learning_rate": 3.835929420532535e-05,
"loss": 0.7311,
"step": 325
},
{
"epoch": 0.16,
"learning_rate": 3.8346921609712484e-05,
"loss": 0.7849,
"step": 326
},
{
"epoch": 0.16,
"learning_rate": 3.8334504548870026e-05,
"loss": 0.8944,
"step": 327
},
{
"epoch": 0.16,
"learning_rate": 3.832204305289169e-05,
"loss": 0.8006,
"step": 328
},
{
"epoch": 0.16,
"learning_rate": 3.830953715197893e-05,
"loss": 0.816,
"step": 329
},
{
"epoch": 0.16,
"learning_rate": 3.829698687644077e-05,
"loss": 0.7985,
"step": 330
},
{
"epoch": 0.16,
"learning_rate": 3.828439225669382e-05,
"loss": 0.81,
"step": 331
},
{
"epoch": 0.16,
"learning_rate": 3.827175332326214e-05,
"loss": 0.8535,
"step": 332
},
{
"epoch": 0.16,
"learning_rate": 3.82590701067772e-05,
"loss": 0.8296,
"step": 333
},
{
"epoch": 0.16,
"learning_rate": 3.824634263797779e-05,
"loss": 0.8121,
"step": 334
},
{
"epoch": 0.16,
"learning_rate": 3.823357094770994e-05,
"loss": 0.8078,
"step": 335
},
{
"epoch": 0.16,
"learning_rate": 3.822075506692686e-05,
"loss": 0.8539,
"step": 336
},
{
"epoch": 0.16,
"learning_rate": 3.8207895026688867e-05,
"loss": 0.8946,
"step": 337
},
{
"epoch": 0.16,
"learning_rate": 3.8194990858163294e-05,
"loss": 0.8443,
"step": 338
},
{
"epoch": 0.16,
"learning_rate": 3.818204259262442e-05,
"loss": 0.8162,
"step": 339
},
{
"epoch": 0.16,
"learning_rate": 3.8169050261453406e-05,
"loss": 0.7585,
"step": 340
},
{
"epoch": 0.16,
"learning_rate": 3.81560138961382e-05,
"loss": 0.8455,
"step": 341
},
{
"epoch": 0.16,
"learning_rate": 3.814293352827347e-05,
"loss": 0.8488,
"step": 342
},
{
"epoch": 0.16,
"learning_rate": 3.812980918956055e-05,
"loss": 0.8369,
"step": 343
},
{
"epoch": 0.17,
"learning_rate": 3.81166409118073e-05,
"loss": 0.7382,
"step": 344
},
{
"epoch": 0.17,
"learning_rate": 3.810342872692811e-05,
"loss": 0.7876,
"step": 345
},
{
"epoch": 0.17,
"learning_rate": 3.8090172666943755e-05,
"loss": 0.8382,
"step": 346
},
{
"epoch": 0.17,
"learning_rate": 3.807687276398136e-05,
"loss": 0.8402,
"step": 347
},
{
"epoch": 0.17,
"learning_rate": 3.80635290502743e-05,
"loss": 0.9505,
"step": 348
},
{
"epoch": 0.17,
"learning_rate": 3.805014155816213e-05,
"loss": 0.9165,
"step": 349
},
{
"epoch": 0.17,
"learning_rate": 3.803671032009051e-05,
"loss": 0.8564,
"step": 350
},
{
"epoch": 0.17,
"learning_rate": 3.80232353686111e-05,
"loss": 0.9599,
"step": 351
},
{
"epoch": 0.17,
"learning_rate": 3.800971673638155e-05,
"loss": 0.8333,
"step": 352
},
{
"epoch": 0.17,
"learning_rate": 3.799615445616533e-05,
"loss": 0.8219,
"step": 353
},
{
"epoch": 0.17,
"learning_rate": 3.798254856083171e-05,
"loss": 0.9042,
"step": 354
},
{
"epoch": 0.17,
"learning_rate": 3.7968899083355664e-05,
"loss": 0.832,
"step": 355
},
{
"epoch": 0.17,
"learning_rate": 3.7955206056817786e-05,
"loss": 0.7922,
"step": 356
},
{
"epoch": 0.17,
"learning_rate": 3.7941469514404225e-05,
"loss": 0.7192,
"step": 357
},
{
"epoch": 0.17,
"learning_rate": 3.792768948940659e-05,
"loss": 0.8974,
"step": 358
},
{
"epoch": 0.17,
"learning_rate": 3.791386601522187e-05,
"loss": 0.8217,
"step": 359
},
{
"epoch": 0.17,
"learning_rate": 3.789999912535235e-05,
"loss": 0.8442,
"step": 360
},
{
"epoch": 0.17,
"learning_rate": 3.788608885340556e-05,
"loss": 0.7616,
"step": 361
},
{
"epoch": 0.17,
"learning_rate": 3.7872135233094145e-05,
"loss": 0.8246,
"step": 362
},
{
"epoch": 0.17,
"learning_rate": 3.7858138298235815e-05,
"loss": 0.848,
"step": 363
},
{
"epoch": 0.17,
"learning_rate": 3.784409808275328e-05,
"loss": 0.8733,
"step": 364
},
{
"epoch": 0.18,
"learning_rate": 3.78300146206741e-05,
"loss": 0.865,
"step": 365
},
{
"epoch": 0.18,
"learning_rate": 3.7815887946130675e-05,
"loss": 0.9627,
"step": 366
},
{
"epoch": 0.18,
"learning_rate": 3.780171809336013e-05,
"loss": 0.8492,
"step": 367
},
{
"epoch": 0.18,
"learning_rate": 3.778750509670424e-05,
"loss": 0.9278,
"step": 368
},
{
"epoch": 0.18,
"learning_rate": 3.777324899060934e-05,
"loss": 0.7373,
"step": 369
},
{
"epoch": 0.18,
"learning_rate": 3.775894980962623e-05,
"loss": 0.8477,
"step": 370
},
{
"epoch": 0.18,
"learning_rate": 3.774460758841012e-05,
"loss": 0.9743,
"step": 371
},
{
"epoch": 0.18,
"learning_rate": 3.773022236172054e-05,
"loss": 0.7991,
"step": 372
},
{
"epoch": 0.18,
"learning_rate": 3.771579416442122e-05,
"loss": 0.7981,
"step": 373
},
{
"epoch": 0.18,
"learning_rate": 3.7701323031480055e-05,
"loss": 0.7349,
"step": 374
},
{
"epoch": 0.18,
"learning_rate": 3.7686808997968996e-05,
"loss": 0.8429,
"step": 375
},
{
"epoch": 0.18,
"learning_rate": 3.767225209906395e-05,
"loss": 0.9152,
"step": 376
},
{
"epoch": 0.18,
"learning_rate": 3.765765237004473e-05,
"loss": 0.8243,
"step": 377
},
{
"epoch": 0.18,
"learning_rate": 3.7643009846294954e-05,
"loss": 0.7706,
"step": 378
},
{
"epoch": 0.18,
"learning_rate": 3.762832456330194e-05,
"loss": 0.8586,
"step": 379
},
{
"epoch": 0.18,
"learning_rate": 3.761359655665664e-05,
"loss": 0.8182,
"step": 380
},
{
"epoch": 0.18,
"learning_rate": 3.7598825862053564e-05,
"loss": 0.8633,
"step": 381
},
{
"epoch": 0.18,
"learning_rate": 3.758401251529066e-05,
"loss": 0.8517,
"step": 382
},
{
"epoch": 0.18,
"learning_rate": 3.756915655226926e-05,
"loss": 0.9424,
"step": 383
},
{
"epoch": 0.18,
"learning_rate": 3.755425800899398e-05,
"loss": 0.8925,
"step": 384
},
{
"epoch": 0.18,
"learning_rate": 3.753931692157263e-05,
"loss": 0.7484,
"step": 385
},
{
"epoch": 0.19,
"learning_rate": 3.7524333326216125e-05,
"loss": 0.7163,
"step": 386
},
{
"epoch": 0.19,
"learning_rate": 3.75093072592384e-05,
"loss": 0.7826,
"step": 387
},
{
"epoch": 0.19,
"learning_rate": 3.749423875705633e-05,
"loss": 0.7602,
"step": 388
},
{
"epoch": 0.19,
"learning_rate": 3.747912785618964e-05,
"loss": 0.9115,
"step": 389
},
{
"epoch": 0.19,
"learning_rate": 3.7463974593260814e-05,
"loss": 0.8326,
"step": 390
},
{
"epoch": 0.19,
"learning_rate": 3.7448779004994976e-05,
"loss": 0.9297,
"step": 391
},
{
"epoch": 0.19,
"learning_rate": 3.743354112821985e-05,
"loss": 0.9103,
"step": 392
},
{
"epoch": 0.19,
"learning_rate": 3.7418260999865654e-05,
"loss": 0.9034,
"step": 393
},
{
"epoch": 0.19,
"learning_rate": 3.740293865696499e-05,
"loss": 0.9349,
"step": 394
},
{
"epoch": 0.19,
"learning_rate": 3.73875741366528e-05,
"loss": 0.7483,
"step": 395
},
{
"epoch": 0.19,
"learning_rate": 3.73721674761662e-05,
"loss": 0.7923,
"step": 396
},
{
"epoch": 0.19,
"learning_rate": 3.7356718712844473e-05,
"loss": 0.6573,
"step": 397
},
{
"epoch": 0.19,
"learning_rate": 3.7341227884128946e-05,
"loss": 0.8281,
"step": 398
},
{
"epoch": 0.19,
"learning_rate": 3.732569502756286e-05,
"loss": 0.828,
"step": 399
},
{
"epoch": 0.19,
"learning_rate": 3.731012018079133e-05,
"loss": 0.8729,
"step": 400
},
{
"epoch": 0.19,
"learning_rate": 3.729450338156125e-05,
"loss": 0.9161,
"step": 401
},
{
"epoch": 0.19,
"learning_rate": 3.727884466772119e-05,
"loss": 0.8946,
"step": 402
},
{
"epoch": 0.19,
"learning_rate": 3.726314407722127e-05,
"loss": 0.7238,
"step": 403
},
{
"epoch": 0.19,
"learning_rate": 3.724740164811315e-05,
"loss": 0.8633,
"step": 404
},
{
"epoch": 0.19,
"learning_rate": 3.723161741854984e-05,
"loss": 0.8415,
"step": 405
},
{
"epoch": 0.2,
"learning_rate": 3.72157914267857e-05,
"loss": 0.7468,
"step": 406
},
{
"epoch": 0.2,
"learning_rate": 3.719992371117627e-05,
"loss": 0.7795,
"step": 407
},
{
"epoch": 0.2,
"learning_rate": 3.718401431017824e-05,
"loss": 0.8727,
"step": 408
},
{
"epoch": 0.2,
"learning_rate": 3.7168063262349305e-05,
"loss": 0.7865,
"step": 409
},
{
"epoch": 0.2,
"learning_rate": 3.7152070606348106e-05,
"loss": 0.7953,
"step": 410
},
{
"epoch": 0.2,
"learning_rate": 3.713603638093412e-05,
"loss": 0.8034,
"step": 411
},
{
"epoch": 0.2,
"learning_rate": 3.7119960624967574e-05,
"loss": 0.7144,
"step": 412
},
{
"epoch": 0.2,
"learning_rate": 3.7103843377409346e-05,
"loss": 0.8954,
"step": 413
},
{
"epoch": 0.2,
"learning_rate": 3.708768467732087e-05,
"loss": 0.8446,
"step": 414
},
{
"epoch": 0.2,
"learning_rate": 3.707148456386405e-05,
"loss": 0.7289,
"step": 415
},
{
"epoch": 0.2,
"learning_rate": 3.705524307630115e-05,
"loss": 0.7269,
"step": 416
},
{
"epoch": 0.2,
"learning_rate": 3.7038960253994714e-05,
"loss": 0.7995,
"step": 417
},
{
"epoch": 0.2,
"learning_rate": 3.7022636136407465e-05,
"loss": 0.7883,
"step": 418
},
{
"epoch": 0.2,
"learning_rate": 3.700627076310222e-05,
"loss": 0.8259,
"step": 419
},
{
"epoch": 0.2,
"learning_rate": 3.698986417374173e-05,
"loss": 0.88,
"step": 420
},
{
"epoch": 0.2,
"learning_rate": 3.69734164080887e-05,
"loss": 0.8297,
"step": 421
},
{
"epoch": 0.2,
"learning_rate": 3.695692750600561e-05,
"loss": 0.818,
"step": 422
},
{
"epoch": 0.2,
"learning_rate": 3.6940397507454614e-05,
"loss": 0.7104,
"step": 423
},
{
"epoch": 0.2,
"learning_rate": 3.692382645249749e-05,
"loss": 0.7665,
"step": 424
},
{
"epoch": 0.2,
"learning_rate": 3.6907214381295516e-05,
"loss": 0.8125,
"step": 425
},
{
"epoch": 0.2,
"learning_rate": 3.689056133410937e-05,
"loss": 0.8496,
"step": 426
},
{
"epoch": 0.21,
"learning_rate": 3.687386735129903e-05,
"loss": 0.6811,
"step": 427
},
{
"epoch": 0.21,
"learning_rate": 3.685713247332372e-05,
"loss": 0.8451,
"step": 428
},
{
"epoch": 0.21,
"learning_rate": 3.6840356740741744e-05,
"loss": 0.7363,
"step": 429
},
{
"epoch": 0.21,
"learning_rate": 3.682354019421042e-05,
"loss": 0.9055,
"step": 430
},
{
"epoch": 0.21,
"learning_rate": 3.6806682874486e-05,
"loss": 0.7397,
"step": 431
},
{
"epoch": 0.21,
"learning_rate": 3.6789784822423544e-05,
"loss": 0.8909,
"step": 432
},
{
"epoch": 0.21,
"learning_rate": 3.677284607897683e-05,
"loss": 0.7827,
"step": 433
},
{
"epoch": 0.21,
"learning_rate": 3.6755866685198255e-05,
"loss": 0.8396,
"step": 434
},
{
"epoch": 0.21,
"learning_rate": 3.673884668223873e-05,
"loss": 0.7953,
"step": 435
},
{
"epoch": 0.21,
"learning_rate": 3.6721786111347603e-05,
"loss": 0.8267,
"step": 436
},
{
"epoch": 0.21,
"learning_rate": 3.670468501387252e-05,
"loss": 0.7708,
"step": 437
},
{
"epoch": 0.21,
"learning_rate": 3.6687543431259366e-05,
"loss": 0.7906,
"step": 438
},
{
"epoch": 0.21,
"learning_rate": 3.6670361405052125e-05,
"loss": 0.7398,
"step": 439
},
{
"epoch": 0.21,
"learning_rate": 3.6653138976892816e-05,
"loss": 0.8282,
"step": 440
},
{
"epoch": 0.21,
"learning_rate": 3.663587618852136e-05,
"loss": 0.8384,
"step": 441
},
{
"epoch": 0.21,
"learning_rate": 3.661857308177552e-05,
"loss": 0.7304,
"step": 442
},
{
"epoch": 0.21,
"learning_rate": 3.660122969859074e-05,
"loss": 0.8538,
"step": 443
},
{
"epoch": 0.21,
"learning_rate": 3.658384608100011e-05,
"loss": 0.7887,
"step": 444
},
{
"epoch": 0.21,
"learning_rate": 3.656642227113419e-05,
"loss": 0.8282,
"step": 445
},
{
"epoch": 0.21,
"learning_rate": 3.6548958311221e-05,
"loss": 0.7296,
"step": 446
},
{
"epoch": 0.21,
"learning_rate": 3.6531454243585834e-05,
"loss": 0.7535,
"step": 447
},
{
"epoch": 0.22,
"learning_rate": 3.65139101106512e-05,
"loss": 0.9152,
"step": 448
},
{
"epoch": 0.22,
"learning_rate": 3.649632595493669e-05,
"loss": 1.0374,
"step": 449
},
{
"epoch": 0.22,
"learning_rate": 3.647870181905893e-05,
"loss": 0.8419,
"step": 450
},
{
"epoch": 0.22,
"learning_rate": 3.646103774573141e-05,
"loss": 0.7652,
"step": 451
},
{
"epoch": 0.22,
"learning_rate": 3.644333377776442e-05,
"loss": 0.7735,
"step": 452
},
{
"epoch": 0.22,
"learning_rate": 3.642558995806495e-05,
"loss": 0.8764,
"step": 453
},
{
"epoch": 0.22,
"learning_rate": 3.6407806329636556e-05,
"loss": 0.7971,
"step": 454
},
{
"epoch": 0.22,
"learning_rate": 3.638998293557928e-05,
"loss": 0.8727,
"step": 455
},
{
"epoch": 0.22,
"learning_rate": 3.637211981908954e-05,
"loss": 0.8415,
"step": 456
},
{
"epoch": 0.22,
"learning_rate": 3.635421702346004e-05,
"loss": 0.8604,
"step": 457
},
{
"epoch": 0.22,
"learning_rate": 3.633627459207962e-05,
"loss": 0.7912,
"step": 458
},
{
"epoch": 0.22,
"learning_rate": 3.63182925684332e-05,
"loss": 0.9299,
"step": 459
},
{
"epoch": 0.22,
"learning_rate": 3.630027099610165e-05,
"loss": 0.9001,
"step": 460
},
{
"epoch": 0.22,
"learning_rate": 3.6282209918761684e-05,
"loss": 0.903,
"step": 461
},
{
"epoch": 0.22,
"learning_rate": 3.626410938018578e-05,
"loss": 0.9535,
"step": 462
},
{
"epoch": 0.22,
"learning_rate": 3.624596942424202e-05,
"loss": 0.9369,
"step": 463
},
{
"epoch": 0.22,
"learning_rate": 3.622779009489405e-05,
"loss": 0.7961,
"step": 464
},
{
"epoch": 0.22,
"learning_rate": 3.620957143620092e-05,
"loss": 0.8618,
"step": 465
},
{
"epoch": 0.22,
"learning_rate": 3.6191313492317005e-05,
"loss": 0.8562,
"step": 466
},
{
"epoch": 0.22,
"learning_rate": 3.61730163074919e-05,
"loss": 0.844,
"step": 467
},
{
"epoch": 0.22,
"learning_rate": 3.6154679926070266e-05,
"loss": 0.9032,
"step": 468
},
{
"epoch": 0.23,
"learning_rate": 3.613630439249182e-05,
"loss": 0.8527,
"step": 469
},
{
"epoch": 0.23,
"learning_rate": 3.611788975129112e-05,
"loss": 0.8766,
"step": 470
},
{
"epoch": 0.23,
"learning_rate": 3.609943604709751e-05,
"loss": 0.7445,
"step": 471
},
{
"epoch": 0.23,
"learning_rate": 3.608094332463503e-05,
"loss": 0.8015,
"step": 472
},
{
"epoch": 0.23,
"learning_rate": 3.606241162872228e-05,
"loss": 0.812,
"step": 473
},
{
"epoch": 0.23,
"learning_rate": 3.604384100427227e-05,
"loss": 0.8537,
"step": 474
},
{
"epoch": 0.23,
"learning_rate": 3.6025231496292426e-05,
"loss": 0.9434,
"step": 475
},
{
"epoch": 0.23,
"learning_rate": 3.600658314988436e-05,
"loss": 0.7642,
"step": 476
},
{
"epoch": 0.23,
"learning_rate": 3.5987896010243824e-05,
"loss": 0.9407,
"step": 477
},
{
"epoch": 0.23,
"learning_rate": 3.59691701226606e-05,
"loss": 0.8671,
"step": 478
},
{
"epoch": 0.23,
"learning_rate": 3.5950405532518387e-05,
"loss": 0.896,
"step": 479
},
{
"epoch": 0.23,
"learning_rate": 3.593160228529464e-05,
"loss": 0.7941,
"step": 480
},
{
"epoch": 0.23,
"learning_rate": 3.5912760426560544e-05,
"loss": 0.8675,
"step": 481
},
{
"epoch": 0.23,
"learning_rate": 3.589388000198085e-05,
"loss": 0.901,
"step": 482
},
{
"epoch": 0.23,
"learning_rate": 3.5874961057313764e-05,
"loss": 0.8555,
"step": 483
},
{
"epoch": 0.23,
"learning_rate": 3.585600363841088e-05,
"loss": 0.7892,
"step": 484
},
{
"epoch": 0.23,
"learning_rate": 3.5837007791216995e-05,
"loss": 0.7373,
"step": 485
},
{
"epoch": 0.23,
"learning_rate": 3.581797356177007e-05,
"loss": 0.7006,
"step": 486
},
{
"epoch": 0.23,
"learning_rate": 3.579890099620109e-05,
"loss": 0.7626,
"step": 487
},
{
"epoch": 0.23,
"learning_rate": 3.577979014073392e-05,
"loss": 0.7997,
"step": 488
},
{
"epoch": 0.23,
"learning_rate": 3.576064104168526e-05,
"loss": 0.8331,
"step": 489
},
{
"epoch": 0.24,
"learning_rate": 3.574145374546447e-05,
"loss": 0.7931,
"step": 490
},
{
"epoch": 0.24,
"learning_rate": 3.57222282985735e-05,
"loss": 0.7866,
"step": 491
},
{
"epoch": 0.24,
"learning_rate": 3.5702964747606765e-05,
"loss": 0.937,
"step": 492
},
{
"epoch": 0.24,
"learning_rate": 3.568366313925101e-05,
"loss": 0.7642,
"step": 493
},
{
"epoch": 0.24,
"learning_rate": 3.566432352028522e-05,
"loss": 0.8629,
"step": 494
},
{
"epoch": 0.24,
"learning_rate": 3.564494593758051e-05,
"loss": 0.7315,
"step": 495
},
{
"epoch": 0.24,
"learning_rate": 3.5625530438100004e-05,
"loss": 1.483,
"step": 496
},
{
"epoch": 0.24,
"learning_rate": 3.5606077068898705e-05,
"loss": 0.766,
"step": 497
},
{
"epoch": 0.24,
"learning_rate": 3.5586585877123415e-05,
"loss": 0.901,
"step": 498
},
{
"epoch": 0.24,
"learning_rate": 3.556705691001259e-05,
"loss": 0.8016,
"step": 499
},
{
"epoch": 0.24,
"learning_rate": 3.554749021489625e-05,
"loss": 0.7369,
"step": 500
},
{
"epoch": 0.24,
"learning_rate": 3.552788583919583e-05,
"loss": 0.7872,
"step": 501
},
{
"epoch": 0.24,
"learning_rate": 3.55082438304241e-05,
"loss": 0.9227,
"step": 502
},
{
"epoch": 0.24,
"learning_rate": 3.5488564236185053e-05,
"loss": 0.7929,
"step": 503
},
{
"epoch": 0.24,
"learning_rate": 3.5468847104173747e-05,
"loss": 0.8551,
"step": 504
},
{
"epoch": 0.24,
"learning_rate": 3.544909248217621e-05,
"loss": 0.7835,
"step": 505
},
{
"epoch": 0.24,
"learning_rate": 3.542930041806938e-05,
"loss": 0.815,
"step": 506
},
{
"epoch": 0.24,
"learning_rate": 3.540947095982088e-05,
"loss": 0.8669,
"step": 507
},
{
"epoch": 0.24,
"learning_rate": 3.5389604155488986e-05,
"loss": 0.7505,
"step": 508
},
{
"epoch": 0.24,
"learning_rate": 3.5369700053222497e-05,
"loss": 0.8883,
"step": 509
},
{
"epoch": 0.24,
"learning_rate": 3.534975870126058e-05,
"loss": 0.7755,
"step": 510
},
{
"epoch": 0.25,
"learning_rate": 3.5329780147932705e-05,
"loss": 0.8622,
"step": 511
},
{
"epoch": 0.25,
"learning_rate": 3.5309764441658496e-05,
"loss": 0.8317,
"step": 512
},
{
"epoch": 0.25,
"learning_rate": 3.5289711630947604e-05,
"loss": 0.6175,
"step": 513
},
{
"epoch": 0.25,
"learning_rate": 3.526962176439962e-05,
"loss": 0.7854,
"step": 514
},
{
"epoch": 0.25,
"learning_rate": 3.524949489070394e-05,
"loss": 0.8157,
"step": 515
},
{
"epoch": 0.25,
"learning_rate": 3.522933105863965e-05,
"loss": 0.9842,
"step": 516
},
{
"epoch": 0.25,
"learning_rate": 3.52091303170754e-05,
"loss": 0.7885,
"step": 517
},
{
"epoch": 0.25,
"learning_rate": 3.518889271496932e-05,
"loss": 0.8805,
"step": 518
},
{
"epoch": 0.25,
"learning_rate": 3.516861830136884e-05,
"loss": 0.765,
"step": 519
},
{
"epoch": 0.25,
"learning_rate": 3.514830712541062e-05,
"loss": 0.8836,
"step": 520
},
{
"epoch": 0.25,
"learning_rate": 3.512795923632041e-05,
"loss": 0.8163,
"step": 521
},
{
"epoch": 0.25,
"learning_rate": 3.5107574683412966e-05,
"loss": 0.8981,
"step": 522
},
{
"epoch": 0.25,
"learning_rate": 3.5087153516091865e-05,
"loss": 0.8185,
"step": 523
},
{
"epoch": 0.25,
"learning_rate": 3.506669578384944e-05,
"loss": 0.7973,
"step": 524
},
{
"epoch": 0.25,
"learning_rate": 3.5046201536266635e-05,
"loss": 0.893,
"step": 525
},
{
"epoch": 0.25,
"learning_rate": 3.50256708230129e-05,
"loss": 0.854,
"step": 526
},
{
"epoch": 0.25,
"learning_rate": 3.500510369384606e-05,
"loss": 0.781,
"step": 527
},
{
"epoch": 0.25,
"learning_rate": 3.498450019861219e-05,
"loss": 0.8094,
"step": 528
},
{
"epoch": 0.25,
"learning_rate": 3.49638603872455e-05,
"loss": 0.7015,
"step": 529
},
{
"epoch": 0.25,
"learning_rate": 3.494318430976824e-05,
"loss": 0.8307,
"step": 530
},
{
"epoch": 0.26,
"learning_rate": 3.492247201629052e-05,
"loss": 0.6934,
"step": 531
},
{
"epoch": 0.26,
"learning_rate": 3.4901723557010236e-05,
"loss": 0.8804,
"step": 532
},
{
"epoch": 0.26,
"learning_rate": 3.4880938982212945e-05,
"loss": 0.8299,
"step": 533
},
{
"epoch": 0.26,
"learning_rate": 3.4860118342271714e-05,
"loss": 0.7884,
"step": 534
},
{
"epoch": 0.26,
"learning_rate": 3.483926168764704e-05,
"loss": 0.8747,
"step": 535
},
{
"epoch": 0.26,
"learning_rate": 3.481836906888667e-05,
"loss": 0.6359,
"step": 536
},
{
"epoch": 0.26,
"learning_rate": 3.4797440536625556e-05,
"loss": 0.8699,
"step": 537
},
{
"epoch": 0.26,
"learning_rate": 3.477647614158566e-05,
"loss": 0.6916,
"step": 538
},
{
"epoch": 0.26,
"learning_rate": 3.4755475934575864e-05,
"loss": 0.8684,
"step": 539
},
{
"epoch": 0.26,
"learning_rate": 3.4734439966491844e-05,
"loss": 0.686,
"step": 540
},
{
"epoch": 0.26,
"learning_rate": 3.471336828831596e-05,
"loss": 0.8439,
"step": 541
},
{
"epoch": 0.26,
"learning_rate": 3.469226095111709e-05,
"loss": 0.7864,
"step": 542
},
{
"epoch": 0.26,
"learning_rate": 3.467111800605056e-05,
"loss": 0.7898,
"step": 543
},
{
"epoch": 0.26,
"learning_rate": 3.4649939504358e-05,
"loss": 0.7938,
"step": 544
},
{
"epoch": 0.26,
"learning_rate": 3.4628725497367167e-05,
"loss": 0.9238,
"step": 545
},
{
"epoch": 0.26,
"learning_rate": 3.460747603649194e-05,
"loss": 0.8985,
"step": 546
},
{
"epoch": 0.26,
"learning_rate": 3.458619117323205e-05,
"loss": 0.7792,
"step": 547
},
{
"epoch": 0.26,
"learning_rate": 3.456487095917308e-05,
"loss": 0.8916,
"step": 548
},
{
"epoch": 0.26,
"learning_rate": 3.4543515445986265e-05,
"loss": 0.8299,
"step": 549
},
{
"epoch": 0.26,
"learning_rate": 3.4522124685428404e-05,
"loss": 0.8005,
"step": 550
},
{
"epoch": 0.26,
"learning_rate": 3.450069872934172e-05,
"loss": 0.7925,
"step": 551
},
{
"epoch": 0.27,
"learning_rate": 3.4479237629653706e-05,
"loss": 0.7626,
"step": 552
},
{
"epoch": 0.27,
"learning_rate": 3.445774143837706e-05,
"loss": 0.8299,
"step": 553
},
{
"epoch": 0.27,
"learning_rate": 3.443621020760953e-05,
"loss": 0.8726,
"step": 554
},
{
"epoch": 0.27,
"learning_rate": 3.4414643989533764e-05,
"loss": 0.7443,
"step": 555
},
{
"epoch": 0.27,
"learning_rate": 3.439304283641721e-05,
"loss": 0.8912,
"step": 556
},
{
"epoch": 0.27,
"learning_rate": 3.4371406800611995e-05,
"loss": 0.7533,
"step": 557
},
{
"epoch": 0.27,
"learning_rate": 3.434973593455477e-05,
"loss": 0.9133,
"step": 558
},
{
"epoch": 0.27,
"learning_rate": 3.432803029076662e-05,
"loss": 0.7537,
"step": 559
},
{
"epoch": 0.27,
"learning_rate": 3.43062899218529e-05,
"loss": 0.7736,
"step": 560
},
{
"epoch": 0.27,
"learning_rate": 3.4284514880503134e-05,
"loss": 0.83,
"step": 561
},
{
"epoch": 0.27,
"learning_rate": 3.426270521949087e-05,
"loss": 0.6362,
"step": 562
},
{
"epoch": 0.27,
"learning_rate": 3.424086099167356e-05,
"loss": 0.8213,
"step": 563
},
{
"epoch": 0.27,
"learning_rate": 3.421898224999244e-05,
"loss": 0.8055,
"step": 564
},
{
"epoch": 0.27,
"learning_rate": 3.419706904747239e-05,
"loss": 0.7437,
"step": 565
},
{
"epoch": 0.27,
"learning_rate": 3.4175121437221794e-05,
"loss": 0.8992,
"step": 566
},
{
"epoch": 0.27,
"learning_rate": 3.4153139472432454e-05,
"loss": 0.8173,
"step": 567
},
{
"epoch": 0.27,
"learning_rate": 3.413112320637941e-05,
"loss": 0.7218,
"step": 568
},
{
"epoch": 0.27,
"learning_rate": 3.410907269242084e-05,
"loss": 0.7529,
"step": 569
},
{
"epoch": 0.27,
"learning_rate": 3.4086987983997916e-05,
"loss": 0.8072,
"step": 570
},
{
"epoch": 0.27,
"learning_rate": 3.406486913463471e-05,
"loss": 0.7501,
"step": 571
},
{
"epoch": 0.27,
"learning_rate": 3.404271619793801e-05,
"loss": 0.91,
"step": 572
},
{
"epoch": 0.28,
"learning_rate": 3.402052922759723e-05,
"loss": 0.8097,
"step": 573
},
{
"epoch": 0.28,
"learning_rate": 3.399830827738426e-05,
"loss": 0.7735,
"step": 574
},
{
"epoch": 0.28,
"learning_rate": 3.397605340115336e-05,
"loss": 0.8764,
"step": 575
},
{
"epoch": 0.28,
"learning_rate": 3.3953764652840976e-05,
"loss": 0.8064,
"step": 576
},
{
"epoch": 0.28,
"learning_rate": 3.393144208646569e-05,
"loss": 0.8023,
"step": 577
},
{
"epoch": 0.28,
"learning_rate": 3.3909085756128026e-05,
"loss": 0.7171,
"step": 578
},
{
"epoch": 0.28,
"learning_rate": 3.388669571601032e-05,
"loss": 0.739,
"step": 579
},
{
"epoch": 0.28,
"learning_rate": 3.3864272020376635e-05,
"loss": 0.7718,
"step": 580
},
{
"epoch": 0.28,
"learning_rate": 3.384181472357257e-05,
"loss": 0.9454,
"step": 581
},
{
"epoch": 0.28,
"learning_rate": 3.38193238800252e-05,
"loss": 0.9419,
"step": 582
},
{
"epoch": 0.28,
"learning_rate": 3.379679954424287e-05,
"loss": 0.8109,
"step": 583
},
{
"epoch": 0.28,
"learning_rate": 3.377424177081511e-05,
"loss": 0.8562,
"step": 584
},
{
"epoch": 0.28,
"learning_rate": 3.375165061441247e-05,
"loss": 0.8789,
"step": 585
},
{
"epoch": 0.28,
"learning_rate": 3.372902612978645e-05,
"loss": 0.8438,
"step": 586
},
{
"epoch": 0.28,
"learning_rate": 3.3706368371769265e-05,
"loss": 0.7863,
"step": 587
},
{
"epoch": 0.28,
"learning_rate": 3.368367739527382e-05,
"loss": 0.8441,
"step": 588
},
{
"epoch": 0.28,
"learning_rate": 3.36609532552935e-05,
"loss": 0.8306,
"step": 589
},
{
"epoch": 0.28,
"learning_rate": 3.363819600690208e-05,
"loss": 0.8554,
"step": 590
},
{
"epoch": 0.28,
"learning_rate": 3.361540570525356e-05,
"loss": 0.9843,
"step": 591
},
{
"epoch": 0.28,
"learning_rate": 3.359258240558207e-05,
"loss": 0.8141,
"step": 592
},
{
"epoch": 0.28,
"learning_rate": 3.3569726163201676e-05,
"loss": 0.7345,
"step": 593
},
{
"epoch": 0.29,
"learning_rate": 3.354683703350633e-05,
"loss": 0.8267,
"step": 594
},
{
"epoch": 0.29,
"learning_rate": 3.352391507196965e-05,
"loss": 0.6914,
"step": 595
},
{
"epoch": 0.29,
"learning_rate": 3.3500960334144856e-05,
"loss": 0.7247,
"step": 596
},
{
"epoch": 0.29,
"learning_rate": 3.347797287566457e-05,
"loss": 0.8007,
"step": 597
},
{
"epoch": 0.29,
"learning_rate": 3.3454952752240744e-05,
"loss": 0.8869,
"step": 598
},
{
"epoch": 0.29,
"learning_rate": 3.343190001966449e-05,
"loss": 0.9197,
"step": 599
},
{
"epoch": 0.29,
"learning_rate": 3.340881473380593e-05,
"loss": 0.7868,
"step": 600
},
{
"epoch": 0.29,
"learning_rate": 3.338569695061411e-05,
"loss": 0.6803,
"step": 601
},
{
"epoch": 0.29,
"learning_rate": 3.336254672611682e-05,
"loss": 0.8608,
"step": 602
},
{
"epoch": 0.29,
"learning_rate": 3.333936411642048e-05,
"loss": 0.767,
"step": 603
},
{
"epoch": 0.29,
"learning_rate": 3.331614917771e-05,
"loss": 0.8731,
"step": 604
},
{
"epoch": 0.29,
"learning_rate": 3.329290196624863e-05,
"loss": 0.8511,
"step": 605
},
{
"epoch": 0.29,
"learning_rate": 3.326962253837783e-05,
"loss": 0.8195,
"step": 606
},
{
"epoch": 0.29,
"learning_rate": 3.3246310950517186e-05,
"loss": 0.7771,
"step": 607
},
{
"epoch": 0.29,
"learning_rate": 3.322296725916417e-05,
"loss": 0.7615,
"step": 608
},
{
"epoch": 0.29,
"learning_rate": 3.319959152089408e-05,
"loss": 0.8213,
"step": 609
},
{
"epoch": 0.29,
"learning_rate": 3.31761837923599e-05,
"loss": 0.7117,
"step": 610
},
{
"epoch": 0.29,
"learning_rate": 3.315274413029212e-05,
"loss": 0.7325,
"step": 611
},
{
"epoch": 0.29,
"learning_rate": 3.312927259149863e-05,
"loss": 0.7084,
"step": 612
},
{
"epoch": 0.29,
"learning_rate": 3.3105769232864576e-05,
"loss": 0.9376,
"step": 613
},
{
"epoch": 0.29,
"learning_rate": 3.308223411135224e-05,
"loss": 0.7905,
"step": 614
},
{
"epoch": 0.3,
"learning_rate": 3.3058667284000856e-05,
"loss": 0.8885,
"step": 615
},
{
"epoch": 0.3,
"learning_rate": 3.303506880792651e-05,
"loss": 0.8944,
"step": 616
},
{
"epoch": 0.3,
"learning_rate": 3.3011438740322006e-05,
"loss": 0.8821,
"step": 617
},
{
"epoch": 0.3,
"learning_rate": 3.298777713845668e-05,
"loss": 0.8499,
"step": 618
},
{
"epoch": 0.3,
"learning_rate": 3.296408405967634e-05,
"loss": 0.8673,
"step": 619
},
{
"epoch": 0.3,
"learning_rate": 3.2940359561403024e-05,
"loss": 0.8858,
"step": 620
},
{
"epoch": 0.3,
"learning_rate": 3.2916603701134975e-05,
"loss": 0.8987,
"step": 621
},
{
"epoch": 0.3,
"learning_rate": 3.2892816536446404e-05,
"loss": 0.9773,
"step": 622
},
{
"epoch": 0.3,
"learning_rate": 3.2868998124987404e-05,
"loss": 0.853,
"step": 623
},
{
"epoch": 0.3,
"learning_rate": 3.2845148524483803e-05,
"loss": 0.7451,
"step": 624
},
{
"epoch": 0.3,
"learning_rate": 3.2821267792737004e-05,
"loss": 0.9901,
"step": 625
},
{
"epoch": 0.3,
"learning_rate": 3.279735598762387e-05,
"loss": 0.8042,
"step": 626
},
{
"epoch": 0.3,
"learning_rate": 3.2773413167096584e-05,
"loss": 0.6899,
"step": 627
},
{
"epoch": 0.3,
"learning_rate": 3.274943938918246e-05,
"loss": 0.7422,
"step": 628
},
{
"epoch": 0.3,
"learning_rate": 3.272543471198388e-05,
"loss": 0.7801,
"step": 629
},
{
"epoch": 0.3,
"learning_rate": 3.270139919367809e-05,
"loss": 0.7765,
"step": 630
},
{
"epoch": 0.3,
"learning_rate": 3.267733289251709e-05,
"loss": 0.732,
"step": 631
},
{
"epoch": 0.3,
"learning_rate": 3.265323586682749e-05,
"loss": 0.8577,
"step": 632
},
{
"epoch": 0.3,
"learning_rate": 3.262910817501033e-05,
"loss": 0.8549,
"step": 633
},
{
"epoch": 0.3,
"learning_rate": 3.260494987554103e-05,
"loss": 0.8105,
"step": 634
},
{
"epoch": 0.31,
"learning_rate": 3.258076102696914e-05,
"loss": 0.8919,
"step": 635
},
{
"epoch": 0.31,
"learning_rate": 3.255654168791827e-05,
"loss": 0.7441,
"step": 636
},
{
"epoch": 0.31,
"learning_rate": 3.2532291917085915e-05,
"loss": 0.8258,
"step": 637
},
{
"epoch": 0.31,
"learning_rate": 3.2508011773243345e-05,
"loss": 0.84,
"step": 638
},
{
"epoch": 0.31,
"learning_rate": 3.248370131523542e-05,
"loss": 0.8119,
"step": 639
},
{
"epoch": 0.31,
"learning_rate": 3.2459360601980475e-05,
"loss": 0.9093,
"step": 640
},
{
"epoch": 0.31,
"learning_rate": 3.243498969247018e-05,
"loss": 0.7744,
"step": 641
},
{
"epoch": 0.31,
"learning_rate": 3.2410588645769365e-05,
"loss": 0.8982,
"step": 642
},
{
"epoch": 0.31,
"learning_rate": 3.238615752101592e-05,
"loss": 0.8141,
"step": 643
},
{
"epoch": 0.31,
"learning_rate": 3.2361696377420644e-05,
"loss": 0.8483,
"step": 644
},
{
"epoch": 0.31,
"learning_rate": 3.233720527426705e-05,
"loss": 0.8516,
"step": 645
},
{
"epoch": 0.31,
"learning_rate": 3.23126842709113e-05,
"loss": 0.8365,
"step": 646
},
{
"epoch": 0.31,
"learning_rate": 3.2288133426781986e-05,
"loss": 0.7851,
"step": 647
},
{
"epoch": 0.31,
"learning_rate": 3.2263552801380056e-05,
"loss": 0.7855,
"step": 648
},
{
"epoch": 0.31,
"learning_rate": 3.223894245427861e-05,
"loss": 0.7006,
"step": 649
},
{
"epoch": 0.31,
"learning_rate": 3.2214302445122786e-05,
"loss": 0.7861,
"step": 650
},
{
"epoch": 0.31,
"learning_rate": 3.2189632833629615e-05,
"loss": 0.7589,
"step": 651
},
{
"epoch": 0.31,
"learning_rate": 3.216493367958788e-05,
"loss": 0.9644,
"step": 652
},
{
"epoch": 0.31,
"learning_rate": 3.2140205042857944e-05,
"loss": 0.8252,
"step": 653
},
{
"epoch": 0.31,
"learning_rate": 3.211544698337164e-05,
"loss": 0.8121,
"step": 654
},
{
"epoch": 0.31,
"learning_rate": 3.209065956113209e-05,
"loss": 0.858,
"step": 655
},
{
"epoch": 0.32,
"learning_rate": 3.206584283621361e-05,
"loss": 0.7403,
"step": 656
},
{
"epoch": 0.32,
"learning_rate": 3.204099686876149e-05,
"loss": 0.9199,
"step": 657
},
{
"epoch": 0.32,
"learning_rate": 3.2016121718991934e-05,
"loss": 0.8291,
"step": 658
},
{
"epoch": 0.32,
"learning_rate": 3.199121744719186e-05,
"loss": 0.8127,
"step": 659
},
{
"epoch": 0.32,
"learning_rate": 3.1966284113718736e-05,
"loss": 0.8221,
"step": 660
},
{
"epoch": 0.32,
"learning_rate": 3.1941321779000504e-05,
"loss": 0.7751,
"step": 661
},
{
"epoch": 0.32,
"learning_rate": 3.191633050353537e-05,
"loss": 0.8099,
"step": 662
},
{
"epoch": 0.32,
"learning_rate": 3.189131034789169e-05,
"loss": 0.7952,
"step": 663
},
{
"epoch": 0.32,
"learning_rate": 3.186626137270781e-05,
"loss": 0.8446,
"step": 664
},
{
"epoch": 0.32,
"learning_rate": 3.184118363869191e-05,
"loss": 0.8809,
"step": 665
},
{
"epoch": 0.32,
"learning_rate": 3.1816077206621896e-05,
"loss": 0.8659,
"step": 666
},
{
"epoch": 0.32,
"learning_rate": 3.1790942137345195e-05,
"loss": 0.705,
"step": 667
},
{
"epoch": 0.32,
"learning_rate": 3.176577849177866e-05,
"loss": 0.8541,
"step": 668
},
{
"epoch": 0.32,
"learning_rate": 3.174058633090841e-05,
"loss": 0.7785,
"step": 669
},
{
"epoch": 0.32,
"learning_rate": 3.1715365715789646e-05,
"loss": 0.7313,
"step": 670
},
{
"epoch": 0.32,
"learning_rate": 3.1690116707546544e-05,
"loss": 0.766,
"step": 671
},
{
"epoch": 0.32,
"learning_rate": 3.166483936737208e-05,
"loss": 0.8271,
"step": 672
},
{
"epoch": 0.32,
"learning_rate": 3.163953375652793e-05,
"loss": 0.7992,
"step": 673
},
{
"epoch": 0.32,
"learning_rate": 3.1614199936344254e-05,
"loss": 0.8336,
"step": 674
},
{
"epoch": 0.32,
"learning_rate": 3.158883796821958e-05,
"loss": 0.78,
"step": 675
},
{
"epoch": 0.32,
"learning_rate": 3.1563447913620666e-05,
"loss": 0.7999,
"step": 676
},
{
"epoch": 0.33,
"learning_rate": 3.1538029834082337e-05,
"loss": 0.8614,
"step": 677
},
{
"epoch": 0.33,
"learning_rate": 3.1512583791207344e-05,
"loss": 0.8046,
"step": 678
},
{
"epoch": 0.33,
"learning_rate": 3.14871098466662e-05,
"loss": 0.714,
"step": 679
},
{
"epoch": 0.33,
"learning_rate": 3.1461608062197046e-05,
"loss": 0.8509,
"step": 680
},
{
"epoch": 0.33,
"learning_rate": 3.1436078499605486e-05,
"loss": 0.8462,
"step": 681
},
{
"epoch": 0.33,
"learning_rate": 3.1410521220764465e-05,
"loss": 0.8384,
"step": 682
},
{
"epoch": 0.33,
"learning_rate": 3.138493628761408e-05,
"loss": 0.8458,
"step": 683
},
{
"epoch": 0.33,
"learning_rate": 3.135932376216146e-05,
"loss": 0.8147,
"step": 684
},
{
"epoch": 0.33,
"learning_rate": 3.133368370648061e-05,
"loss": 0.8713,
"step": 685
},
{
"epoch": 0.33,
"learning_rate": 3.1308016182712253e-05,
"loss": 0.7309,
"step": 686
},
{
"epoch": 0.33,
"learning_rate": 3.128232125306368e-05,
"loss": 0.7653,
"step": 687
},
{
"epoch": 0.33,
"learning_rate": 3.1256598979808604e-05,
"loss": 0.75,
"step": 688
},
{
"epoch": 0.33,
"learning_rate": 3.1230849425287e-05,
"loss": 0.7608,
"step": 689
},
{
"epoch": 0.33,
"learning_rate": 3.120507265190499e-05,
"loss": 0.8003,
"step": 690
},
{
"epoch": 0.33,
"learning_rate": 3.117926872213463e-05,
"loss": 0.7997,
"step": 691
},
{
"epoch": 0.33,
"learning_rate": 3.115343769851381e-05,
"loss": 0.8859,
"step": 692
},
{
"epoch": 0.33,
"learning_rate": 3.112757964364607e-05,
"loss": 0.8336,
"step": 693
},
{
"epoch": 0.33,
"learning_rate": 3.1101694620200476e-05,
"loss": 0.7696,
"step": 694
},
{
"epoch": 0.33,
"learning_rate": 3.107578269091144e-05,
"loss": 0.9193,
"step": 695
},
{
"epoch": 0.33,
"learning_rate": 3.1049843918578615e-05,
"loss": 0.9126,
"step": 696
},
{
"epoch": 0.33,
"learning_rate": 3.102387836606666e-05,
"loss": 0.898,
"step": 697
},
{
"epoch": 0.34,
"learning_rate": 3.099788609630519e-05,
"loss": 0.7109,
"step": 698
},
{
"epoch": 0.34,
"learning_rate": 3.0971867172288525e-05,
"loss": 0.7782,
"step": 699
},
{
"epoch": 0.34,
"learning_rate": 3.094582165707562e-05,
"loss": 0.7975,
"step": 700
},
{
"epoch": 0.34,
"learning_rate": 3.091974961378985e-05,
"loss": 0.8599,
"step": 701
},
{
"epoch": 0.34,
"learning_rate": 3.0893651105618894e-05,
"loss": 0.8781,
"step": 702
},
{
"epoch": 0.34,
"learning_rate": 3.086752619581458e-05,
"loss": 0.8478,
"step": 703
},
{
"epoch": 0.34,
"learning_rate": 3.084137494769271e-05,
"loss": 0.8869,
"step": 704
},
{
"epoch": 0.34,
"learning_rate": 3.081519742463292e-05,
"loss": 0.7297,
"step": 705
},
{
"epoch": 0.34,
"learning_rate": 3.0788993690078535e-05,
"loss": 0.815,
"step": 706
},
{
"epoch": 0.34,
"learning_rate": 3.0762763807536385e-05,
"loss": 0.8696,
"step": 707
},
{
"epoch": 0.34,
"learning_rate": 3.073650784057669e-05,
"loss": 0.8298,
"step": 708
},
{
"epoch": 0.34,
"learning_rate": 3.0710225852832885e-05,
"loss": 0.8462,
"step": 709
},
{
"epoch": 0.34,
"learning_rate": 3.068391790800146e-05,
"loss": 0.8144,
"step": 710
},
{
"epoch": 0.34,
"learning_rate": 3.065758406984183e-05,
"loss": 0.8092,
"step": 711
},
{
"epoch": 0.34,
"learning_rate": 3.0631224402176154e-05,
"loss": 0.7695,
"step": 712
},
{
"epoch": 0.34,
"learning_rate": 3.060483896888919e-05,
"loss": 0.8359,
"step": 713
},
{
"epoch": 0.34,
"learning_rate": 3.057842783392813e-05,
"loss": 0.7896,
"step": 714
},
{
"epoch": 0.34,
"learning_rate": 3.055199106130248e-05,
"loss": 0.7814,
"step": 715
},
{
"epoch": 0.34,
"learning_rate": 3.052552871508386e-05,
"loss": 0.7356,
"step": 716
},
{
"epoch": 0.34,
"learning_rate": 3.0499040859405906e-05,
"loss": 0.9219,
"step": 717
},
{
"epoch": 0.34,
"learning_rate": 3.047252755846402e-05,
"loss": 0.8092,
"step": 718
},
{
"epoch": 0.35,
"learning_rate": 3.044598887651532e-05,
"loss": 1.0218,
"step": 719
},
{
"epoch": 0.35,
"learning_rate": 3.0419424877878422e-05,
"loss": 0.7883,
"step": 720
},
{
"epoch": 0.35,
"learning_rate": 3.0392835626933286e-05,
"loss": 0.8567,
"step": 721
},
{
"epoch": 0.35,
"learning_rate": 3.0366221188121093e-05,
"loss": 0.8846,
"step": 722
},
{
"epoch": 0.35,
"learning_rate": 3.0339581625944068e-05,
"loss": 0.8121,
"step": 723
},
{
"epoch": 0.35,
"learning_rate": 3.0312917004965303e-05,
"loss": 0.745,
"step": 724
},
{
"epoch": 0.35,
"learning_rate": 3.0286227389808644e-05,
"loss": 0.8644,
"step": 725
},
{
"epoch": 0.35,
"learning_rate": 3.0259512845158504e-05,
"loss": 0.6963,
"step": 726
},
{
"epoch": 0.35,
"learning_rate": 3.0232773435759707e-05,
"loss": 0.8206,
"step": 727
},
{
"epoch": 0.35,
"learning_rate": 3.0206009226417365e-05,
"loss": 0.7531,
"step": 728
},
{
"epoch": 0.35,
"learning_rate": 3.0179220281996664e-05,
"loss": 0.7307,
"step": 729
},
{
"epoch": 0.35,
"learning_rate": 3.0152406667422754e-05,
"loss": 0.7837,
"step": 730
},
{
"epoch": 0.35,
"learning_rate": 3.0125568447680563e-05,
"loss": 0.8806,
"step": 731
},
{
"epoch": 0.35,
"learning_rate": 3.0098705687814667e-05,
"loss": 0.7999,
"step": 732
},
{
"epoch": 0.35,
"learning_rate": 3.007181845292911e-05,
"loss": 1.0223,
"step": 733
},
{
"epoch": 0.35,
"learning_rate": 3.0044906808187255e-05,
"loss": 0.7352,
"step": 734
},
{
"epoch": 0.35,
"learning_rate": 3.0017970818811616e-05,
"loss": 0.876,
"step": 735
},
{
"epoch": 0.35,
"learning_rate": 2.999101055008371e-05,
"loss": 0.7495,
"step": 736
},
{
"epoch": 0.35,
"learning_rate": 2.996402606734391e-05,
"loss": 0.8191,
"step": 737
},
{
"epoch": 0.35,
"learning_rate": 2.993701743599127e-05,
"loss": 0.7907,
"step": 738
},
{
"epoch": 0.35,
"learning_rate": 2.990998472148335e-05,
"loss": 0.8066,
"step": 739
},
{
"epoch": 0.36,
"learning_rate": 2.9882927989336107e-05,
"loss": 0.8186,
"step": 740
},
{
"epoch": 0.36,
"learning_rate": 2.9855847305123675e-05,
"loss": 0.7481,
"step": 741
},
{
"epoch": 0.36,
"learning_rate": 2.982874273447827e-05,
"loss": 0.7773,
"step": 742
},
{
"epoch": 0.36,
"learning_rate": 2.9801614343089978e-05,
"loss": 0.8407,
"step": 743
},
{
"epoch": 0.36,
"learning_rate": 2.9774462196706624e-05,
"loss": 0.8318,
"step": 744
},
{
"epoch": 0.36,
"learning_rate": 2.97472863611336e-05,
"loss": 0.7324,
"step": 745
},
{
"epoch": 0.36,
"learning_rate": 2.972008690223371e-05,
"loss": 0.8571,
"step": 746
},
{
"epoch": 0.36,
"learning_rate": 2.9692863885927017e-05,
"loss": 0.7909,
"step": 747
},
{
"epoch": 0.36,
"learning_rate": 2.9665617378190683e-05,
"loss": 0.874,
"step": 748
},
{
"epoch": 0.36,
"learning_rate": 2.9638347445058784e-05,
"loss": 0.7185,
"step": 749
},
{
"epoch": 0.36,
"learning_rate": 2.9611054152622194e-05,
"loss": 0.8008,
"step": 750
},
{
"epoch": 0.36,
"learning_rate": 2.958373756702837e-05,
"loss": 0.7446,
"step": 751
},
{
"epoch": 0.36,
"learning_rate": 2.9556397754481247e-05,
"loss": 0.6969,
"step": 752
},
{
"epoch": 0.36,
"learning_rate": 2.9529034781241046e-05,
"loss": 0.7189,
"step": 753
},
{
"epoch": 0.36,
"learning_rate": 2.9501648713624116e-05,
"loss": 0.8764,
"step": 754
},
{
"epoch": 0.36,
"learning_rate": 2.947423961800278e-05,
"loss": 0.8145,
"step": 755
},
{
"epoch": 0.36,
"learning_rate": 2.9446807560805166e-05,
"loss": 0.8438,
"step": 756
},
{
"epoch": 0.36,
"learning_rate": 2.941935260851506e-05,
"loss": 0.9055,
"step": 757
},
{
"epoch": 0.36,
"learning_rate": 2.9391874827671723e-05,
"loss": 0.8791,
"step": 758
},
{
"epoch": 0.36,
"learning_rate": 2.9364374284869762e-05,
"loss": 0.9194,
"step": 759
},
{
"epoch": 0.37,
"learning_rate": 2.9336851046758932e-05,
"loss": 0.9119,
"step": 760
},
{
"epoch": 0.37,
"learning_rate": 2.9309305180043996e-05,
"loss": 0.8019,
"step": 761
},
{
"epoch": 0.37,
"learning_rate": 2.928173675148457e-05,
"loss": 0.9155,
"step": 762
},
{
"epoch": 0.37,
"learning_rate": 2.9254145827894934e-05,
"loss": 0.793,
"step": 763
},
{
"epoch": 0.37,
"learning_rate": 2.92265324761439e-05,
"loss": 0.8046,
"step": 764
},
{
"epoch": 0.37,
"learning_rate": 2.919889676315463e-05,
"loss": 0.8625,
"step": 765
},
{
"epoch": 0.37,
"learning_rate": 2.9171238755904477e-05,
"loss": 0.8101,
"step": 766
},
{
"epoch": 0.37,
"learning_rate": 2.9143558521424834e-05,
"loss": 0.8133,
"step": 767
},
{
"epoch": 0.37,
"learning_rate": 2.9115856126800964e-05,
"loss": 0.854,
"step": 768
},
{
"epoch": 0.37,
"learning_rate": 2.9088131639171823e-05,
"loss": 0.7527,
"step": 769
},
{
"epoch": 0.37,
"learning_rate": 2.9060385125729928e-05,
"loss": 0.8511,
"step": 770
},
{
"epoch": 0.37,
"learning_rate": 2.9032616653721168e-05,
"loss": 0.8956,
"step": 771
},
{
"epoch": 0.37,
"learning_rate": 2.9004826290444648e-05,
"loss": 0.8175,
"step": 772
},
{
"epoch": 0.37,
"learning_rate": 2.8977014103252543e-05,
"loss": 0.7333,
"step": 773
},
{
"epoch": 0.37,
"learning_rate": 2.8949180159549897e-05,
"loss": 0.7325,
"step": 774
},
{
"epoch": 0.37,
"learning_rate": 2.89213245267945e-05,
"loss": 0.8888,
"step": 775
},
{
"epoch": 0.37,
"learning_rate": 2.889344727249671e-05,
"loss": 0.6153,
"step": 776
},
{
"epoch": 0.37,
"learning_rate": 2.8865548464219268e-05,
"loss": 0.7744,
"step": 777
},
{
"epoch": 0.37,
"learning_rate": 2.8837628169577168e-05,
"loss": 0.8497,
"step": 778
},
{
"epoch": 0.37,
"learning_rate": 2.8809686456237476e-05,
"loss": 0.8876,
"step": 779
},
{
"epoch": 0.37,
"learning_rate": 2.8781723391919162e-05,
"loss": 0.8713,
"step": 780
},
{
"epoch": 0.38,
"learning_rate": 2.8753739044392945e-05,
"loss": 0.6641,
"step": 781
},
{
"epoch": 0.38,
"learning_rate": 2.8725733481481132e-05,
"loss": 0.8615,
"step": 782
},
{
"epoch": 0.38,
"learning_rate": 2.8697706771057437e-05,
"loss": 0.857,
"step": 783
},
{
"epoch": 0.38,
"learning_rate": 2.8669658981046827e-05,
"loss": 0.714,
"step": 784
},
{
"epoch": 0.38,
"learning_rate": 2.8641590179425366e-05,
"loss": 0.9354,
"step": 785
},
{
"epoch": 0.38,
"learning_rate": 2.861350043422003e-05,
"loss": 0.9969,
"step": 786
},
{
"epoch": 0.38,
"learning_rate": 2.8585389813508575e-05,
"loss": 0.8724,
"step": 787
},
{
"epoch": 0.38,
"learning_rate": 2.8557258385419317e-05,
"loss": 0.8891,
"step": 788
},
{
"epoch": 0.38,
"learning_rate": 2.8529106218131022e-05,
"loss": 0.678,
"step": 789
},
{
"epoch": 0.38,
"learning_rate": 2.8500933379872725e-05,
"loss": 0.7923,
"step": 790
},
{
"epoch": 0.38,
"learning_rate": 2.847273993892354e-05,
"loss": 0.7177,
"step": 791
},
{
"epoch": 0.38,
"learning_rate": 2.8444525963612525e-05,
"loss": 0.9207,
"step": 792
},
{
"epoch": 0.38,
"learning_rate": 2.8416291522318506e-05,
"loss": 0.8617,
"step": 793
},
{
"epoch": 0.38,
"learning_rate": 2.83880366834699e-05,
"loss": 0.9428,
"step": 794
},
{
"epoch": 0.38,
"learning_rate": 2.835976151554457e-05,
"loss": 0.8606,
"step": 795
},
{
"epoch": 0.38,
"learning_rate": 2.8331466087069642e-05,
"loss": 0.8234,
"step": 796
},
{
"epoch": 0.38,
"learning_rate": 2.8303150466621344e-05,
"loss": 0.7587,
"step": 797
},
{
"epoch": 0.38,
"learning_rate": 2.827481472282485e-05,
"loss": 0.8345,
"step": 798
},
{
"epoch": 0.38,
"learning_rate": 2.8246458924354092e-05,
"loss": 0.7877,
"step": 799
},
{
"epoch": 0.38,
"learning_rate": 2.8218083139931615e-05,
"loss": 0.8689,
"step": 800
},
{
"epoch": 0.38,
"learning_rate": 2.818968743832839e-05,
"loss": 0.9086,
"step": 801
},
{
"epoch": 0.39,
"learning_rate": 2.816127188836368e-05,
"loss": 0.7266,
"step": 802
},
{
"epoch": 0.39,
"learning_rate": 2.8132836558904832e-05,
"loss": 0.8246,
"step": 803
},
{
"epoch": 0.39,
"learning_rate": 2.8104381518867138e-05,
"loss": 0.7975,
"step": 804
},
{
"epoch": 0.39,
"learning_rate": 2.8075906837213663e-05,
"loss": 0.8531,
"step": 805
},
{
"epoch": 0.39,
"learning_rate": 2.8047412582955066e-05,
"loss": 0.7897,
"step": 806
},
{
"epoch": 0.39,
"learning_rate": 2.801889882514945e-05,
"loss": 0.7114,
"step": 807
},
{
"epoch": 0.39,
"learning_rate": 2.799036563290219e-05,
"loss": 0.6832,
"step": 808
},
{
"epoch": 0.39,
"learning_rate": 2.7961813075365752e-05,
"loss": 0.7334,
"step": 809
},
{
"epoch": 0.39,
"learning_rate": 2.793324122173954e-05,
"loss": 0.9626,
"step": 810
},
{
"epoch": 0.39,
"learning_rate": 2.7904650141269714e-05,
"loss": 0.7868,
"step": 811
},
{
"epoch": 0.39,
"learning_rate": 2.7876039903249052e-05,
"loss": 0.8865,
"step": 812
},
{
"epoch": 0.39,
"learning_rate": 2.7847410577016748e-05,
"loss": 0.8702,
"step": 813
},
{
"epoch": 0.39,
"learning_rate": 2.781876223195826e-05,
"loss": 0.7197,
"step": 814
},
{
"epoch": 0.39,
"learning_rate": 2.779009493750514e-05,
"loss": 0.818,
"step": 815
},
{
"epoch": 0.39,
"learning_rate": 2.776140876313486e-05,
"loss": 0.893,
"step": 816
},
{
"epoch": 0.39,
"learning_rate": 2.7732703778370655e-05,
"loss": 0.7538,
"step": 817
},
{
"epoch": 0.39,
"learning_rate": 2.7703980052781353e-05,
"loss": 0.9259,
"step": 818
},
{
"epoch": 0.39,
"learning_rate": 2.7675237655981197e-05,
"loss": 0.7543,
"step": 819
},
{
"epoch": 0.39,
"learning_rate": 2.7646476657629677e-05,
"loss": 0.9162,
"step": 820
},
{
"epoch": 0.39,
"learning_rate": 2.7617697127431374e-05,
"loss": 0.7199,
"step": 821
},
{
"epoch": 0.39,
"learning_rate": 2.758889913513577e-05,
"loss": 0.7669,
"step": 822
},
{
"epoch": 0.4,
"learning_rate": 2.756008275053711e-05,
"loss": 0.8197,
"step": 823
},
{
"epoch": 0.4,
"learning_rate": 2.7531248043474196e-05,
"loss": 0.7258,
"step": 824
},
{
"epoch": 0.4,
"learning_rate": 2.750239508383024e-05,
"loss": 0.836,
"step": 825
},
{
"epoch": 0.4,
"learning_rate": 2.7473523941532696e-05,
"loss": 0.8518,
"step": 826
},
{
"epoch": 0.4,
"learning_rate": 2.7444634686553087e-05,
"loss": 0.9213,
"step": 827
},
{
"epoch": 0.4,
"learning_rate": 2.741572738890683e-05,
"loss": 0.9349,
"step": 828
},
{
"epoch": 0.4,
"learning_rate": 2.738680211865306e-05,
"loss": 0.8099,
"step": 829
},
{
"epoch": 0.4,
"learning_rate": 2.7357858945894492e-05,
"loss": 0.8306,
"step": 830
},
{
"epoch": 0.4,
"learning_rate": 2.7328897940777208e-05,
"loss": 0.9182,
"step": 831
},
{
"epoch": 0.4,
"learning_rate": 2.7299919173490513e-05,
"loss": 0.8413,
"step": 832
},
{
"epoch": 0.4,
"learning_rate": 2.7270922714266777e-05,
"loss": 0.7613,
"step": 833
},
{
"epoch": 0.4,
"learning_rate": 2.724190863338122e-05,
"loss": 0.9259,
"step": 834
},
{
"epoch": 0.4,
"learning_rate": 2.7212877001151797e-05,
"loss": 0.8356,
"step": 835
},
{
"epoch": 0.4,
"learning_rate": 2.7183827887938973e-05,
"loss": 0.846,
"step": 836
},
{
"epoch": 0.4,
"learning_rate": 2.7154761364145606e-05,
"loss": 0.7379,
"step": 837
},
{
"epoch": 0.4,
"learning_rate": 2.7125677500216724e-05,
"loss": 0.8267,
"step": 838
},
{
"epoch": 0.4,
"learning_rate": 2.7096576366639412e-05,
"loss": 0.7147,
"step": 839
},
{
"epoch": 0.4,
"learning_rate": 2.7067458033942582e-05,
"loss": 0.9711,
"step": 840
},
{
"epoch": 0.4,
"learning_rate": 2.7038322572696833e-05,
"loss": 0.7574,
"step": 841
},
{
"epoch": 0.4,
"learning_rate": 2.7009170053514285e-05,
"loss": 0.7944,
"step": 842
},
{
"epoch": 0.4,
"learning_rate": 2.6980000547048398e-05,
"loss": 0.8095,
"step": 843
},
{
"epoch": 0.41,
"learning_rate": 2.6950814123993803e-05,
"loss": 0.8336,
"step": 844
},
{
"epoch": 0.41,
"learning_rate": 2.6921610855086124e-05,
"loss": 0.7845,
"step": 845
},
{
"epoch": 0.41,
"learning_rate": 2.6892390811101813e-05,
"loss": 0.8121,
"step": 846
},
{
"epoch": 0.41,
"learning_rate": 2.686315406285798e-05,
"loss": 0.827,
"step": 847
},
{
"epoch": 0.41,
"learning_rate": 2.683390068121223e-05,
"loss": 0.9013,
"step": 848
},
{
"epoch": 0.41,
"learning_rate": 2.6804630737062453e-05,
"loss": 0.9542,
"step": 849
},
{
"epoch": 0.41,
"learning_rate": 2.6775344301346704e-05,
"loss": 0.8534,
"step": 850
},
{
"epoch": 0.41,
"learning_rate": 2.6746041445043006e-05,
"loss": 0.8444,
"step": 851
},
{
"epoch": 0.41,
"learning_rate": 2.6716722239169156e-05,
"loss": 0.8776,
"step": 852
},
{
"epoch": 0.41,
"learning_rate": 2.66873867547826e-05,
"loss": 0.7428,
"step": 853
},
{
"epoch": 0.41,
"learning_rate": 2.6658035062980227e-05,
"loss": 0.8084,
"step": 854
},
{
"epoch": 0.41,
"learning_rate": 2.6628667234898206e-05,
"loss": 0.7497,
"step": 855
},
{
"epoch": 0.41,
"learning_rate": 2.6599283341711812e-05,
"loss": 0.9807,
"step": 856
},
{
"epoch": 0.41,
"learning_rate": 2.656988345463525e-05,
"loss": 0.9052,
"step": 857
},
{
"epoch": 0.41,
"learning_rate": 2.65404676449215e-05,
"loss": 0.6598,
"step": 858
},
{
"epoch": 0.41,
"learning_rate": 2.651103598386213e-05,
"loss": 0.7973,
"step": 859
},
{
"epoch": 0.41,
"learning_rate": 2.6481588542787116e-05,
"loss": 0.828,
"step": 860
},
{
"epoch": 0.41,
"learning_rate": 2.6452125393064686e-05,
"loss": 0.7704,
"step": 861
},
{
"epoch": 0.41,
"learning_rate": 2.6422646606101133e-05,
"loss": 0.7976,
"step": 862
},
{
"epoch": 0.41,
"learning_rate": 2.639315225334065e-05,
"loss": 0.8268,
"step": 863
},
{
"epoch": 0.42,
"learning_rate": 2.636364240626516e-05,
"loss": 0.7997,
"step": 864
},
{
"epoch": 0.42,
"learning_rate": 2.6334117136394133e-05,
"loss": 0.82,
"step": 865
},
{
"epoch": 0.42,
"learning_rate": 2.630457651528442e-05,
"loss": 1.0674,
"step": 866
},
{
"epoch": 0.42,
"learning_rate": 2.627502061453007e-05,
"loss": 0.8003,
"step": 867
},
{
"epoch": 0.42,
"learning_rate": 2.6245449505762172e-05,
"loss": 0.8196,
"step": 868
},
{
"epoch": 0.42,
"learning_rate": 2.6215863260648666e-05,
"loss": 0.8604,
"step": 869
},
{
"epoch": 0.42,
"learning_rate": 2.6186261950894186e-05,
"loss": 0.8229,
"step": 870
},
{
"epoch": 0.42,
"learning_rate": 2.6156645648239867e-05,
"loss": 0.8284,
"step": 871
},
{
"epoch": 0.42,
"learning_rate": 2.612701442446318e-05,
"loss": 0.8724,
"step": 872
},
{
"epoch": 0.42,
"learning_rate": 2.609736835137777e-05,
"loss": 0.7375,
"step": 873
},
{
"epoch": 0.42,
"learning_rate": 2.6067707500833252e-05,
"loss": 0.8087,
"step": 874
},
{
"epoch": 0.42,
"learning_rate": 2.6038031944715072e-05,
"loss": 0.8175,
"step": 875
},
{
"epoch": 0.42,
"learning_rate": 2.6008341754944306e-05,
"loss": 0.8015,
"step": 876
},
{
"epoch": 0.42,
"learning_rate": 2.597863700347751e-05,
"loss": 0.8907,
"step": 877
},
{
"epoch": 0.42,
"learning_rate": 2.5948917762306516e-05,
"loss": 0.8232,
"step": 878
},
{
"epoch": 0.42,
"learning_rate": 2.5919184103458275e-05,
"loss": 0.7578,
"step": 879
},
{
"epoch": 0.42,
"learning_rate": 2.5889436098994684e-05,
"loss": 0.7837,
"step": 880
},
{
"epoch": 0.42,
"learning_rate": 2.585967382101241e-05,
"loss": 0.7482,
"step": 881
},
{
"epoch": 0.42,
"learning_rate": 2.5829897341642706e-05,
"loss": 0.9306,
"step": 882
},
{
"epoch": 0.42,
"learning_rate": 2.5800106733051254e-05,
"loss": 0.8276,
"step": 883
},
{
"epoch": 0.42,
"learning_rate": 2.5770302067437963e-05,
"loss": 0.8904,
"step": 884
},
{
"epoch": 0.43,
"learning_rate": 2.5740483417036826e-05,
"loss": 0.795,
"step": 885
},
{
"epoch": 0.43,
"learning_rate": 2.571065085411573e-05,
"loss": 0.7532,
"step": 886
},
{
"epoch": 0.43,
"learning_rate": 2.5680804450976266e-05,
"loss": 0.7793,
"step": 887
},
{
"epoch": 0.43,
"learning_rate": 2.5650944279953577e-05,
"loss": 0.7032,
"step": 888
},
{
"epoch": 0.43,
"learning_rate": 2.5621070413416177e-05,
"loss": 0.7909,
"step": 889
},
{
"epoch": 0.43,
"learning_rate": 2.5591182923765754e-05,
"loss": 0.6184,
"step": 890
},
{
"epoch": 0.43,
"learning_rate": 2.556128188343703e-05,
"loss": 0.6964,
"step": 891
},
{
"epoch": 0.43,
"learning_rate": 2.5531367364897576e-05,
"loss": 0.8541,
"step": 892
},
{
"epoch": 0.43,
"learning_rate": 2.5501439440647603e-05,
"loss": 0.874,
"step": 893
},
{
"epoch": 0.43,
"learning_rate": 2.547149818321984e-05,
"loss": 0.7377,
"step": 894
},
{
"epoch": 0.43,
"learning_rate": 2.5441543665179295e-05,
"loss": 0.6486,
"step": 895
},
{
"epoch": 0.43,
"learning_rate": 2.5411575959123146e-05,
"loss": 0.805,
"step": 896
},
{
"epoch": 0.43,
"learning_rate": 2.5381595137680527e-05,
"loss": 0.6963,
"step": 897
},
{
"epoch": 0.43,
"learning_rate": 2.5351601273512342e-05,
"loss": 0.7427,
"step": 898
},
{
"epoch": 0.43,
"learning_rate": 2.5321594439311116e-05,
"loss": 0.9064,
"step": 899
},
{
"epoch": 0.43,
"learning_rate": 2.5291574707800818e-05,
"loss": 0.7783,
"step": 900
},
{
"epoch": 0.43,
"learning_rate": 2.526154215173666e-05,
"loss": 0.8107,
"step": 901
},
{
"epoch": 0.43,
"learning_rate": 2.523149684390494e-05,
"loss": 0.739,
"step": 902
},
{
"epoch": 0.43,
"learning_rate": 2.5201438857122854e-05,
"loss": 0.7956,
"step": 903
},
{
"epoch": 0.43,
"learning_rate": 2.517136826423835e-05,
"loss": 0.862,
"step": 904
},
{
"epoch": 0.43,
"learning_rate": 2.5141285138129893e-05,
"loss": 0.7451,
"step": 905
},
{
"epoch": 0.44,
"learning_rate": 2.5111189551706346e-05,
"loss": 0.9004,
"step": 906
},
{
"epoch": 0.44,
"learning_rate": 2.508108157790677e-05,
"loss": 0.8009,
"step": 907
},
{
"epoch": 0.44,
"learning_rate": 2.505096128970024e-05,
"loss": 0.767,
"step": 908
},
{
"epoch": 0.44,
"learning_rate": 2.5020828760085685e-05,
"loss": 0.6996,
"step": 909
},
{
"epoch": 0.44,
"learning_rate": 2.49906840620917e-05,
"loss": 0.8032,
"step": 910
},
{
"epoch": 0.44,
"learning_rate": 2.4960527268776354e-05,
"loss": 0.8078,
"step": 911
},
{
"epoch": 0.44,
"learning_rate": 2.493035845322705e-05,
"loss": 0.8546,
"step": 912
},
{
"epoch": 0.44,
"learning_rate": 2.4900177688560326e-05,
"loss": 0.8273,
"step": 913
},
{
"epoch": 0.44,
"learning_rate": 2.486998504792167e-05,
"loss": 0.7545,
"step": 914
},
{
"epoch": 0.44,
"learning_rate": 2.4839780604485365e-05,
"loss": 0.8121,
"step": 915
},
{
"epoch": 0.44,
"learning_rate": 2.4809564431454286e-05,
"loss": 0.8373,
"step": 916
},
{
"epoch": 0.44,
"learning_rate": 2.4779336602059733e-05,
"loss": 0.6404,
"step": 917
},
{
"epoch": 0.44,
"learning_rate": 2.474909718956128e-05,
"loss": 0.9136,
"step": 918
},
{
"epoch": 0.44,
"learning_rate": 2.471884626724655e-05,
"loss": 0.8754,
"step": 919
},
{
"epoch": 0.44,
"learning_rate": 2.468858390843107e-05,
"loss": 0.7354,
"step": 920
},
{
"epoch": 0.44,
"learning_rate": 2.4658310186458082e-05,
"loss": 0.8756,
"step": 921
},
{
"epoch": 0.44,
"learning_rate": 2.462802517469837e-05,
"loss": 0.7962,
"step": 922
},
{
"epoch": 0.44,
"learning_rate": 2.4597728946550076e-05,
"loss": 0.8312,
"step": 923
},
{
"epoch": 0.44,
"learning_rate": 2.456742157543853e-05,
"loss": 0.721,
"step": 924
},
{
"epoch": 0.44,
"learning_rate": 2.453710313481607e-05,
"loss": 0.81,
"step": 925
},
{
"epoch": 0.44,
"learning_rate": 2.450677369816185e-05,
"loss": 0.8507,
"step": 926
},
{
"epoch": 0.45,
"learning_rate": 2.4476433338981686e-05,
"loss": 0.7319,
"step": 927
},
{
"epoch": 0.45,
"learning_rate": 2.444608213080786e-05,
"loss": 0.7374,
"step": 928
},
{
"epoch": 0.45,
"learning_rate": 2.4415720147198956e-05,
"loss": 0.7582,
"step": 929
},
{
"epoch": 0.45,
"learning_rate": 2.4385347461739656e-05,
"loss": 0.8145,
"step": 930
},
{
"epoch": 0.45,
"learning_rate": 2.4354964148040598e-05,
"loss": 0.9313,
"step": 931
},
{
"epoch": 0.45,
"learning_rate": 2.432457027973816e-05,
"loss": 0.8551,
"step": 932
},
{
"epoch": 0.45,
"learning_rate": 2.4294165930494308e-05,
"loss": 0.7733,
"step": 933
},
{
"epoch": 0.45,
"learning_rate": 2.4263751173996416e-05,
"loss": 0.7777,
"step": 934
},
{
"epoch": 0.45,
"learning_rate": 2.4233326083957077e-05,
"loss": 0.7798,
"step": 935
},
{
"epoch": 0.45,
"learning_rate": 2.4202890734113922e-05,
"loss": 0.7916,
"step": 936
},
{
"epoch": 0.45,
"learning_rate": 2.4172445198229456e-05,
"loss": 0.8147,
"step": 937
},
{
"epoch": 0.45,
"learning_rate": 2.4141989550090857e-05,
"loss": 0.76,
"step": 938
},
{
"epoch": 0.45,
"learning_rate": 2.411152386350983e-05,
"loss": 0.7531,
"step": 939
},
{
"epoch": 0.45,
"learning_rate": 2.408104821232239e-05,
"loss": 0.7487,
"step": 940
},
{
"epoch": 0.45,
"learning_rate": 2.405056267038872e-05,
"loss": 0.9016,
"step": 941
},
{
"epoch": 0.45,
"learning_rate": 2.402006731159297e-05,
"loss": 0.8107,
"step": 942
},
{
"epoch": 0.45,
"learning_rate": 2.3989562209843062e-05,
"loss": 0.7306,
"step": 943
},
{
"epoch": 0.45,
"learning_rate": 2.395904743907055e-05,
"loss": 0.7758,
"step": 944
},
{
"epoch": 0.45,
"learning_rate": 2.3928523073230426e-05,
"loss": 0.718,
"step": 945
},
{
"epoch": 0.45,
"learning_rate": 2.3897989186300926e-05,
"loss": 0.825,
"step": 946
},
{
"epoch": 0.45,
"learning_rate": 2.386744585228336e-05,
"loss": 0.6727,
"step": 947
},
{
"epoch": 0.46,
"learning_rate": 2.3836893145201935e-05,
"loss": 0.7723,
"step": 948
},
{
"epoch": 0.46,
"learning_rate": 2.3806331139103583e-05,
"loss": 0.7267,
"step": 949
},
{
"epoch": 0.46,
"learning_rate": 2.3775759908057756e-05,
"loss": 0.8376,
"step": 950
},
{
"epoch": 0.46,
"learning_rate": 2.3745179526156284e-05,
"loss": 0.7806,
"step": 951
},
{
"epoch": 0.46,
"learning_rate": 2.371459006751316e-05,
"loss": 0.6257,
"step": 952
},
{
"epoch": 0.46,
"learning_rate": 2.368399160626438e-05,
"loss": 0.8575,
"step": 953
},
{
"epoch": 0.46,
"learning_rate": 2.3653384216567753e-05,
"loss": 0.9144,
"step": 954
},
{
"epoch": 0.46,
"learning_rate": 2.3622767972602746e-05,
"loss": 0.8163,
"step": 955
},
{
"epoch": 0.46,
"learning_rate": 2.359214294857026e-05,
"loss": 0.7571,
"step": 956
},
{
"epoch": 0.46,
"learning_rate": 2.3561509218692485e-05,
"loss": 0.6864,
"step": 957
},
{
"epoch": 0.46,
"learning_rate": 2.3530866857212727e-05,
"loss": 0.8461,
"step": 958
},
{
"epoch": 0.46,
"learning_rate": 2.3500215938395178e-05,
"loss": 0.9644,
"step": 959
},
{
"epoch": 0.46,
"learning_rate": 2.346955653652479e-05,
"loss": 0.8808,
"step": 960
},
{
"epoch": 0.46,
"learning_rate": 2.343888872590708e-05,
"loss": 0.7557,
"step": 961
},
{
"epoch": 0.46,
"learning_rate": 2.340821258086793e-05,
"loss": 0.8821,
"step": 962
},
{
"epoch": 0.46,
"learning_rate": 2.3377528175753432e-05,
"loss": 0.759,
"step": 963
},
{
"epoch": 0.46,
"learning_rate": 2.3346835584929685e-05,
"loss": 0.7967,
"step": 964
},
{
"epoch": 0.46,
"learning_rate": 2.3316134882782642e-05,
"loss": 0.7461,
"step": 965
},
{
"epoch": 0.46,
"learning_rate": 2.3285426143717896e-05,
"loss": 0.6334,
"step": 966
},
{
"epoch": 0.46,
"learning_rate": 2.3254709442160537e-05,
"loss": 0.8831,
"step": 967
},
{
"epoch": 0.46,
"learning_rate": 2.3223984852554944e-05,
"loss": 0.8804,
"step": 968
},
{
"epoch": 0.47,
"learning_rate": 2.319325244936461e-05,
"loss": 0.7322,
"step": 969
},
{
"epoch": 0.47,
"learning_rate": 2.3162512307071968e-05,
"loss": 0.8192,
"step": 970
},
{
"epoch": 0.47,
"learning_rate": 2.313176450017821e-05,
"loss": 0.8268,
"step": 971
},
{
"epoch": 0.47,
"learning_rate": 2.3101009103203093e-05,
"loss": 0.7348,
"step": 972
},
{
"epoch": 0.47,
"learning_rate": 2.307024619068479e-05,
"loss": 0.7666,
"step": 973
},
{
"epoch": 0.47,
"learning_rate": 2.3039475837179674e-05,
"loss": 0.8881,
"step": 974
},
{
"epoch": 0.47,
"learning_rate": 2.300869811726215e-05,
"loss": 0.7643,
"step": 975
},
{
"epoch": 0.47,
"learning_rate": 2.2977913105524477e-05,
"loss": 0.773,
"step": 976
},
{
"epoch": 0.47,
"learning_rate": 2.2947120876576593e-05,
"loss": 0.8274,
"step": 977
},
{
"epoch": 0.47,
"learning_rate": 2.291632150504592e-05,
"loss": 0.8946,
"step": 978
},
{
"epoch": 0.47,
"learning_rate": 2.2885515065577203e-05,
"loss": 0.8322,
"step": 979
},
{
"epoch": 0.47,
"learning_rate": 2.2854701632832304e-05,
"loss": 0.6587,
"step": 980
},
{
"epoch": 0.47,
"learning_rate": 2.2823881281490033e-05,
"loss": 0.913,
"step": 981
},
{
"epoch": 0.47,
"learning_rate": 2.2793054086245973e-05,
"loss": 0.8071,
"step": 982
},
{
"epoch": 0.47,
"learning_rate": 2.27622201218123e-05,
"loss": 0.7787,
"step": 983
},
{
"epoch": 0.47,
"learning_rate": 2.2731379462917597e-05,
"loss": 0.8597,
"step": 984
},
{
"epoch": 0.47,
"learning_rate": 2.270053218430664e-05,
"loss": 0.7347,
"step": 985
},
{
"epoch": 0.47,
"learning_rate": 2.2669678360740288e-05,
"loss": 0.8899,
"step": 986
},
{
"epoch": 0.47,
"learning_rate": 2.2638818066995238e-05,
"loss": 0.7668,
"step": 987
},
{
"epoch": 0.47,
"learning_rate": 2.2607951377863885e-05,
"loss": 0.7455,
"step": 988
},
{
"epoch": 0.48,
"learning_rate": 2.2577078368154113e-05,
"loss": 0.8746,
"step": 989
},
{
"epoch": 0.48,
"learning_rate": 2.2546199112689126e-05,
"loss": 0.7987,
"step": 990
},
{
"epoch": 0.48,
"learning_rate": 2.251531368630726e-05,
"loss": 0.6962,
"step": 991
},
{
"epoch": 0.48,
"learning_rate": 2.2484422163861815e-05,
"loss": 0.8109,
"step": 992
},
{
"epoch": 0.48,
"learning_rate": 2.245352462022086e-05,
"loss": 0.9317,
"step": 993
},
{
"epoch": 0.48,
"learning_rate": 2.2422621130267066e-05,
"loss": 0.7289,
"step": 994
},
{
"epoch": 0.48,
"learning_rate": 2.2391711768897513e-05,
"loss": 0.796,
"step": 995
},
{
"epoch": 0.48,
"learning_rate": 2.2360796611023493e-05,
"loss": 0.9338,
"step": 996
},
{
"epoch": 0.48,
"learning_rate": 2.2329875731570362e-05,
"loss": 0.8539,
"step": 997
},
{
"epoch": 0.48,
"learning_rate": 2.2298949205477343e-05,
"loss": 0.7855,
"step": 998
},
{
"epoch": 0.48,
"learning_rate": 2.226801710769735e-05,
"loss": 0.8219,
"step": 999
},
{
"epoch": 0.48,
"learning_rate": 2.2237079513196785e-05,
"loss": 0.8549,
"step": 1000
},
{
"epoch": 0.48,
"learning_rate": 2.220613649695537e-05,
"loss": 0.8478,
"step": 1001
},
{
"epoch": 0.48,
"learning_rate": 2.2175188133965994e-05,
"loss": 0.8277,
"step": 1002
},
{
"epoch": 0.48,
"learning_rate": 2.214423449923447e-05,
"loss": 0.8375,
"step": 1003
},
{
"epoch": 0.48,
"learning_rate": 2.2113275667779416e-05,
"loss": 0.9255,
"step": 1004
},
{
"epoch": 0.48,
"learning_rate": 2.208231171463202e-05,
"loss": 0.8158,
"step": 1005
},
{
"epoch": 0.48,
"learning_rate": 2.2051342714835907e-05,
"loss": 0.8648,
"step": 1006
},
{
"epoch": 0.48,
"learning_rate": 2.2020368743446906e-05,
"loss": 0.6254,
"step": 1007
},
{
"epoch": 0.48,
"learning_rate": 2.1989389875532926e-05,
"loss": 0.8529,
"step": 1008
},
{
"epoch": 0.48,
"learning_rate": 2.195840618617372e-05,
"loss": 0.9507,
"step": 1009
},
{
"epoch": 0.49,
"learning_rate": 2.192741775046074e-05,
"loss": 0.8246,
"step": 1010
},
{
"epoch": 0.49,
"learning_rate": 2.189642464349693e-05,
"loss": 0.7709,
"step": 1011
},
{
"epoch": 0.49,
"learning_rate": 2.1865426940396544e-05,
"loss": 0.8873,
"step": 1012
},
{
"epoch": 0.49,
"learning_rate": 2.1834424716285017e-05,
"loss": 0.7875,
"step": 1013
},
{
"epoch": 0.49,
"learning_rate": 2.18034180462987e-05,
"loss": 0.752,
"step": 1014
},
{
"epoch": 0.49,
"learning_rate": 2.177240700558473e-05,
"loss": 0.7541,
"step": 1015
},
{
"epoch": 0.49,
"learning_rate": 2.1741391669300858e-05,
"loss": 0.7826,
"step": 1016
},
{
"epoch": 0.49,
"learning_rate": 2.1710372112615214e-05,
"loss": 0.825,
"step": 1017
},
{
"epoch": 0.49,
"learning_rate": 2.167934841070617e-05,
"loss": 0.6373,
"step": 1018
},
{
"epoch": 0.49,
"learning_rate": 2.1648320638762147e-05,
"loss": 0.9243,
"step": 1019
},
{
"epoch": 0.49,
"learning_rate": 2.1617288871981436e-05,
"loss": 0.6677,
"step": 1020
},
{
"epoch": 0.49,
"learning_rate": 2.158625318557199e-05,
"loss": 0.8723,
"step": 1021
},
{
"epoch": 0.49,
"learning_rate": 2.1555213654751287e-05,
"loss": 0.7718,
"step": 1022
},
{
"epoch": 0.49,
"learning_rate": 2.15241703547461e-05,
"loss": 0.7793,
"step": 1023
},
{
"epoch": 0.49,
"learning_rate": 2.149312336079234e-05,
"loss": 0.7964,
"step": 1024
},
{
"epoch": 0.49,
"learning_rate": 2.1462072748134887e-05,
"loss": 0.8529,
"step": 1025
},
{
"epoch": 0.49,
"learning_rate": 2.1431018592027374e-05,
"loss": 0.8223,
"step": 1026
},
{
"epoch": 0.49,
"learning_rate": 2.1399960967732034e-05,
"loss": 0.7982,
"step": 1027
},
{
"epoch": 0.49,
"learning_rate": 2.136889995051949e-05,
"loss": 0.8623,
"step": 1028
},
{
"epoch": 0.49,
"learning_rate": 2.13378356156686e-05,
"loss": 0.9192,
"step": 1029
},
{
"epoch": 0.49,
"learning_rate": 2.130676803846627e-05,
"loss": 0.7604,
"step": 1030
},
{
"epoch": 0.5,
"learning_rate": 2.1275697294207244e-05,
"loss": 0.8205,
"step": 1031
},
{
"epoch": 0.5,
"learning_rate": 2.1244623458193954e-05,
"loss": 0.6614,
"step": 1032
},
{
"epoch": 0.5,
"learning_rate": 2.1213546605736326e-05,
"loss": 0.8465,
"step": 1033
},
{
"epoch": 0.5,
"learning_rate": 2.118246681215159e-05,
"loss": 0.9324,
"step": 1034
},
{
"epoch": 0.5,
"learning_rate": 2.115138415276411e-05,
"loss": 0.823,
"step": 1035
},
{
"epoch": 0.5,
"learning_rate": 2.1120298702905195e-05,
"loss": 0.7974,
"step": 1036
},
{
"epoch": 0.5,
"learning_rate": 2.1089210537912914e-05,
"loss": 0.7233,
"step": 1037
},
{
"epoch": 0.5,
"learning_rate": 2.105811973313191e-05,
"loss": 0.7986,
"step": 1038
},
{
"epoch": 0.5,
"learning_rate": 2.102702636391324e-05,
"loss": 0.7569,
"step": 1039
},
{
"epoch": 0.5,
"learning_rate": 2.0995930505614165e-05,
"loss": 0.7425,
"step": 1040
},
{
"epoch": 0.5,
"learning_rate": 2.096483223359798e-05,
"loss": 0.8227,
"step": 1041
},
{
"epoch": 0.5,
"learning_rate": 2.093373162323383e-05,
"loss": 0.7444,
"step": 1042
},
{
"epoch": 0.5,
"learning_rate": 2.090262874989653e-05,
"loss": 0.8037,
"step": 1043
},
{
"epoch": 0.5,
"learning_rate": 2.0871523688966375e-05,
"loss": 0.7835,
"step": 1044
},
{
"epoch": 0.5,
"learning_rate": 2.0840416515828962e-05,
"loss": 0.8601,
"step": 1045
},
{
"epoch": 0.5,
"learning_rate": 2.0809307305875012e-05,
"loss": 0.949,
"step": 1046
},
{
"epoch": 0.5,
"learning_rate": 2.0778196134500178e-05,
"loss": 0.8168,
"step": 1047
},
{
"epoch": 0.5,
"learning_rate": 2.0747083077104877e-05,
"loss": 0.8424,
"step": 1048
},
{
"epoch": 0.5,
"learning_rate": 2.0715968209094076e-05,
"loss": 0.8134,
"step": 1049
},
{
"epoch": 0.5,
"learning_rate": 2.0684851605877146e-05,
"loss": 0.9359,
"step": 1050
},
{
"epoch": 0.5,
"learning_rate": 2.065373334286766e-05,
"loss": 0.9298,
"step": 1051
},
{
"epoch": 0.51,
"learning_rate": 2.0622613495483215e-05,
"loss": 0.7277,
"step": 1052
},
{
"epoch": 0.51,
"learning_rate": 2.0591492139145245e-05,
"loss": 0.7517,
"step": 1053
},
{
"epoch": 0.51,
"learning_rate": 2.056036934927885e-05,
"loss": 0.781,
"step": 1054
},
{
"epoch": 0.51,
"learning_rate": 2.052924520131258e-05,
"loss": 0.8335,
"step": 1055
},
{
"epoch": 0.51,
"learning_rate": 2.04981197706783e-05,
"loss": 0.8026,
"step": 1056
},
{
"epoch": 0.51,
"learning_rate": 2.0466993132810985e-05,
"loss": 0.7245,
"step": 1057
},
{
"epoch": 0.51,
"learning_rate": 2.0435865363148516e-05,
"loss": 0.7823,
"step": 1058
},
{
"epoch": 0.51,
"learning_rate": 2.0404736537131537e-05,
"loss": 0.8255,
"step": 1059
},
{
"epoch": 0.51,
"learning_rate": 2.037360673020324e-05,
"loss": 0.7689,
"step": 1060
},
{
"epoch": 0.51,
"learning_rate": 2.034247601780919e-05,
"loss": 0.7764,
"step": 1061
},
{
"epoch": 0.51,
"learning_rate": 2.031134447539717e-05,
"loss": 0.7824,
"step": 1062
},
{
"epoch": 0.51,
"learning_rate": 2.0280212178416952e-05,
"loss": 0.8695,
"step": 1063
},
{
"epoch": 0.51,
"learning_rate": 2.0249079202320147e-05,
"loss": 0.8521,
"step": 1064
},
{
"epoch": 0.51,
"learning_rate": 2.021794562256e-05,
"loss": 0.7708,
"step": 1065
},
{
"epoch": 0.51,
"learning_rate": 2.0186811514591233e-05,
"loss": 0.8275,
"step": 1066
},
{
"epoch": 0.51,
"learning_rate": 2.015567695386984e-05,
"loss": 0.7666,
"step": 1067
},
{
"epoch": 0.51,
"learning_rate": 2.012454201585292e-05,
"loss": 0.7394,
"step": 1068
},
{
"epoch": 0.51,
"learning_rate": 2.0093406775998484e-05,
"loss": 0.7933,
"step": 1069
},
{
"epoch": 0.51,
"learning_rate": 2.0062271309765268e-05,
"loss": 0.7262,
"step": 1070
},
{
"epoch": 0.51,
"learning_rate": 2.003113569261255e-05,
"loss": 0.7958,
"step": 1071
},
{
"epoch": 0.51,
"learning_rate": 2e-05,
"loss": 0.7564,
"step": 1072
},
{
"epoch": 0.52,
"learning_rate": 1.9968864307387456e-05,
"loss": 0.8544,
"step": 1073
},
{
"epoch": 0.52,
"learning_rate": 1.993772869023474e-05,
"loss": 0.7939,
"step": 1074
},
{
"epoch": 0.52,
"learning_rate": 1.9906593224001523e-05,
"loss": 0.7029,
"step": 1075
},
{
"epoch": 0.52,
"learning_rate": 1.987545798414708e-05,
"loss": 0.7907,
"step": 1076
},
{
"epoch": 0.52,
"learning_rate": 1.9844323046130162e-05,
"loss": 0.72,
"step": 1077
},
{
"epoch": 0.52,
"learning_rate": 1.9813188485408777e-05,
"loss": 0.8664,
"step": 1078
},
{
"epoch": 0.52,
"learning_rate": 1.9782054377440005e-05,
"loss": 0.7373,
"step": 1079
},
{
"epoch": 0.52,
"learning_rate": 1.9750920797679863e-05,
"loss": 0.8029,
"step": 1080
},
{
"epoch": 0.52,
"learning_rate": 1.971978782158305e-05,
"loss": 0.978,
"step": 1081
},
{
"epoch": 0.52,
"learning_rate": 1.9688655524602833e-05,
"loss": 0.8832,
"step": 1082
},
{
"epoch": 0.52,
"learning_rate": 1.9657523982190812e-05,
"loss": 0.8462,
"step": 1083
},
{
"epoch": 0.52,
"learning_rate": 1.962639326979677e-05,
"loss": 0.7041,
"step": 1084
},
{
"epoch": 0.52,
"learning_rate": 1.9595263462868473e-05,
"loss": 0.821,
"step": 1085
},
{
"epoch": 0.52,
"learning_rate": 1.956413463685149e-05,
"loss": 0.751,
"step": 1086
},
{
"epoch": 0.52,
"learning_rate": 1.9533006867189025e-05,
"loss": 0.8456,
"step": 1087
},
{
"epoch": 0.52,
"learning_rate": 1.9501880229321705e-05,
"loss": 0.8125,
"step": 1088
},
{
"epoch": 0.52,
"learning_rate": 1.9470754798687428e-05,
"loss": 0.8438,
"step": 1089
},
{
"epoch": 0.52,
"learning_rate": 1.9439630650721164e-05,
"loss": 0.8199,
"step": 1090
},
{
"epoch": 0.52,
"learning_rate": 1.9408507860854754e-05,
"loss": 0.904,
"step": 1091
},
{
"epoch": 0.52,
"learning_rate": 1.937738650451679e-05,
"loss": 0.8243,
"step": 1092
},
{
"epoch": 0.53,
"learning_rate": 1.934626665713234e-05,
"loss": 0.8768,
"step": 1093
},
{
"epoch": 0.53,
"learning_rate": 1.931514839412286e-05,
"loss": 0.7835,
"step": 1094
},
{
"epoch": 0.53,
"learning_rate": 1.9284031790905934e-05,
"loss": 0.6543,
"step": 1095
},
{
"epoch": 0.53,
"learning_rate": 1.9252916922895126e-05,
"loss": 0.8008,
"step": 1096
},
{
"epoch": 0.53,
"learning_rate": 1.9221803865499825e-05,
"loss": 0.8093,
"step": 1097
},
{
"epoch": 0.53,
"learning_rate": 1.9190692694124988e-05,
"loss": 0.7276,
"step": 1098
},
{
"epoch": 0.53,
"learning_rate": 1.915958348417104e-05,
"loss": 0.9386,
"step": 1099
},
{
"epoch": 0.53,
"learning_rate": 1.9128476311033635e-05,
"loss": 0.8194,
"step": 1100
},
{
"epoch": 0.53,
"learning_rate": 1.9097371250103474e-05,
"loss": 0.7818,
"step": 1101
},
{
"epoch": 0.53,
"learning_rate": 1.9066268376766177e-05,
"loss": 0.8598,
"step": 1102
},
{
"epoch": 0.53,
"learning_rate": 1.903516776640202e-05,
"loss": 0.8341,
"step": 1103
},
{
"epoch": 0.53,
"learning_rate": 1.9004069494385838e-05,
"loss": 0.8001,
"step": 1104
},
{
"epoch": 0.53,
"learning_rate": 1.8972973636086767e-05,
"loss": 0.7861,
"step": 1105
},
{
"epoch": 0.53,
"learning_rate": 1.8941880266868092e-05,
"loss": 0.7341,
"step": 1106
},
{
"epoch": 0.53,
"learning_rate": 1.8910789462087097e-05,
"loss": 0.78,
"step": 1107
},
{
"epoch": 0.53,
"learning_rate": 1.8879701297094805e-05,
"loss": 0.7206,
"step": 1108
},
{
"epoch": 0.53,
"learning_rate": 1.8848615847235895e-05,
"loss": 0.6664,
"step": 1109
},
{
"epoch": 0.53,
"learning_rate": 1.8817533187848412e-05,
"loss": 0.77,
"step": 1110
},
{
"epoch": 0.53,
"learning_rate": 1.878645339426368e-05,
"loss": 0.7241,
"step": 1111
},
{
"epoch": 0.53,
"learning_rate": 1.8755376541806052e-05,
"loss": 0.7241,
"step": 1112
},
{
"epoch": 0.53,
"learning_rate": 1.8724302705792763e-05,
"loss": 0.9062,
"step": 1113
},
{
"epoch": 0.54,
"learning_rate": 1.8693231961533737e-05,
"loss": 0.8041,
"step": 1114
},
{
"epoch": 0.54,
"learning_rate": 1.866216438433141e-05,
"loss": 0.796,
"step": 1115
},
{
"epoch": 0.54,
"learning_rate": 1.8631100049480516e-05,
"loss": 0.8259,
"step": 1116
},
{
"epoch": 0.54,
"learning_rate": 1.860003903226798e-05,
"loss": 0.8069,
"step": 1117
},
{
"epoch": 0.54,
"learning_rate": 1.856898140797263e-05,
"loss": 0.7876,
"step": 1118
},
{
"epoch": 0.54,
"learning_rate": 1.853792725186512e-05,
"loss": 0.8336,
"step": 1119
},
{
"epoch": 0.54,
"learning_rate": 1.850687663920766e-05,
"loss": 0.7858,
"step": 1120
},
{
"epoch": 0.54,
"learning_rate": 1.8475829645253907e-05,
"loss": 0.6726,
"step": 1121
},
{
"epoch": 0.54,
"learning_rate": 1.844478634524872e-05,
"loss": 0.7655,
"step": 1122
},
{
"epoch": 0.54,
"learning_rate": 1.841374681442801e-05,
"loss": 0.8449,
"step": 1123
},
{
"epoch": 0.54,
"learning_rate": 1.838271112801857e-05,
"loss": 0.7344,
"step": 1124
},
{
"epoch": 0.54,
"learning_rate": 1.835167936123785e-05,
"loss": 0.9387,
"step": 1125
},
{
"epoch": 0.54,
"learning_rate": 1.8320651589293837e-05,
"loss": 0.7721,
"step": 1126
},
{
"epoch": 0.54,
"learning_rate": 1.8289627887384796e-05,
"loss": 0.9044,
"step": 1127
},
{
"epoch": 0.54,
"learning_rate": 1.825860833069915e-05,
"loss": 0.7439,
"step": 1128
},
{
"epoch": 0.54,
"learning_rate": 1.8227592994415274e-05,
"loss": 0.8186,
"step": 1129
},
{
"epoch": 0.54,
"learning_rate": 1.8196581953701303e-05,
"loss": 0.7851,
"step": 1130
},
{
"epoch": 0.54,
"learning_rate": 1.816557528371499e-05,
"loss": 0.8013,
"step": 1131
},
{
"epoch": 0.54,
"learning_rate": 1.8134573059603462e-05,
"loss": 0.7881,
"step": 1132
},
{
"epoch": 0.54,
"learning_rate": 1.810357535650308e-05,
"loss": 0.8358,
"step": 1133
},
{
"epoch": 0.54,
"learning_rate": 1.807258224953927e-05,
"loss": 0.8308,
"step": 1134
},
{
"epoch": 0.55,
"learning_rate": 1.804159381382628e-05,
"loss": 0.9222,
"step": 1135
},
{
"epoch": 0.55,
"learning_rate": 1.8010610124467078e-05,
"loss": 0.8118,
"step": 1136
},
{
"epoch": 0.55,
"learning_rate": 1.7979631256553098e-05,
"loss": 0.7905,
"step": 1137
},
{
"epoch": 0.55,
"learning_rate": 1.7948657285164103e-05,
"loss": 0.751,
"step": 1138
},
{
"epoch": 0.55,
"learning_rate": 1.7917688285367985e-05,
"loss": 0.7556,
"step": 1139
},
{
"epoch": 0.55,
"learning_rate": 1.7886724332220594e-05,
"loss": 0.8655,
"step": 1140
},
{
"epoch": 0.55,
"learning_rate": 1.7855765500765533e-05,
"loss": 0.6942,
"step": 1141
},
{
"epoch": 0.55,
"learning_rate": 1.7824811866034016e-05,
"loss": 0.7991,
"step": 1142
},
{
"epoch": 0.55,
"learning_rate": 1.7793863503044632e-05,
"loss": 0.8645,
"step": 1143
},
{
"epoch": 0.55,
"learning_rate": 1.7762920486803225e-05,
"loss": 0.7884,
"step": 1144
},
{
"epoch": 0.55,
"learning_rate": 1.7731982892302653e-05,
"loss": 0.831,
"step": 1145
},
{
"epoch": 0.55,
"learning_rate": 1.770105079452266e-05,
"loss": 0.7858,
"step": 1146
},
{
"epoch": 0.55,
"learning_rate": 1.7670124268429648e-05,
"loss": 0.6456,
"step": 1147
},
{
"epoch": 0.55,
"learning_rate": 1.7639203388976517e-05,
"loss": 0.8965,
"step": 1148
},
{
"epoch": 0.55,
"learning_rate": 1.76082882311025e-05,
"loss": 0.7986,
"step": 1149
},
{
"epoch": 0.55,
"learning_rate": 1.7577378869732934e-05,
"loss": 0.8648,
"step": 1150
},
{
"epoch": 0.55,
"learning_rate": 1.7546475379779145e-05,
"loss": 0.7507,
"step": 1151
},
{
"epoch": 0.55,
"learning_rate": 1.751557783613819e-05,
"loss": 0.8244,
"step": 1152
},
{
"epoch": 0.55,
"learning_rate": 1.7484686313692747e-05,
"loss": 0.8803,
"step": 1153
},
{
"epoch": 0.55,
"learning_rate": 1.7453800887310884e-05,
"loss": 0.7573,
"step": 1154
},
{
"epoch": 0.55,
"learning_rate": 1.7422921631845887e-05,
"loss": 0.8168,
"step": 1155
},
{
"epoch": 0.56,
"learning_rate": 1.7392048622136118e-05,
"loss": 0.8174,
"step": 1156
},
{
"epoch": 0.56,
"learning_rate": 1.736118193300476e-05,
"loss": 0.7399,
"step": 1157
},
{
"epoch": 0.56,
"learning_rate": 1.7330321639259716e-05,
"loss": 0.7196,
"step": 1158
},
{
"epoch": 0.56,
"learning_rate": 1.729946781569337e-05,
"loss": 0.7403,
"step": 1159
},
{
"epoch": 0.56,
"learning_rate": 1.726862053708241e-05,
"loss": 0.7497,
"step": 1160
},
{
"epoch": 0.56,
"learning_rate": 1.7237779878187702e-05,
"loss": 0.8645,
"step": 1161
},
{
"epoch": 0.56,
"learning_rate": 1.7206945913754027e-05,
"loss": 0.8736,
"step": 1162
},
{
"epoch": 0.56,
"learning_rate": 1.7176118718509974e-05,
"loss": 0.783,
"step": 1163
},
{
"epoch": 0.56,
"learning_rate": 1.7145298367167703e-05,
"loss": 0.7814,
"step": 1164
},
{
"epoch": 0.56,
"learning_rate": 1.71144849344228e-05,
"loss": 0.6849,
"step": 1165
},
{
"epoch": 0.56,
"learning_rate": 1.7083678494954084e-05,
"loss": 0.7768,
"step": 1166
},
{
"epoch": 0.56,
"learning_rate": 1.7052879123423414e-05,
"loss": 0.7645,
"step": 1167
},
{
"epoch": 0.56,
"learning_rate": 1.702208689447553e-05,
"loss": 0.9248,
"step": 1168
},
{
"epoch": 0.56,
"learning_rate": 1.699130188273786e-05,
"loss": 0.8502,
"step": 1169
},
{
"epoch": 0.56,
"learning_rate": 1.696052416282033e-05,
"loss": 0.7534,
"step": 1170
},
{
"epoch": 0.56,
"learning_rate": 1.6929753809315214e-05,
"loss": 0.7784,
"step": 1171
},
{
"epoch": 0.56,
"learning_rate": 1.6898990896796907e-05,
"loss": 0.8438,
"step": 1172
},
{
"epoch": 0.56,
"learning_rate": 1.68682354998218e-05,
"loss": 0.9313,
"step": 1173
},
{
"epoch": 0.56,
"learning_rate": 1.6837487692928042e-05,
"loss": 0.8504,
"step": 1174
},
{
"epoch": 0.56,
"learning_rate": 1.6806747550635395e-05,
"loss": 0.854,
"step": 1175
},
{
"epoch": 0.56,
"learning_rate": 1.6776015147445062e-05,
"loss": 0.8048,
"step": 1176
},
{
"epoch": 0.57,
"learning_rate": 1.6745290557839463e-05,
"loss": 0.8528,
"step": 1177
},
{
"epoch": 0.57,
"learning_rate": 1.671457385628211e-05,
"loss": 0.8382,
"step": 1178
},
{
"epoch": 0.57,
"learning_rate": 1.668386511721737e-05,
"loss": 0.8847,
"step": 1179
},
{
"epoch": 0.57,
"learning_rate": 1.665316441507032e-05,
"loss": 0.7371,
"step": 1180
},
{
"epoch": 0.57,
"learning_rate": 1.6622471824246578e-05,
"loss": 0.7098,
"step": 1181
},
{
"epoch": 0.57,
"learning_rate": 1.6591787419132072e-05,
"loss": 0.8048,
"step": 1182
},
{
"epoch": 0.57,
"learning_rate": 1.6561111274092926e-05,
"loss": 0.8229,
"step": 1183
},
{
"epoch": 0.57,
"learning_rate": 1.653044346347521e-05,
"loss": 0.7544,
"step": 1184
},
{
"epoch": 0.57,
"learning_rate": 1.6499784061604832e-05,
"loss": 0.8072,
"step": 1185
},
{
"epoch": 0.57,
"learning_rate": 1.6469133142787283e-05,
"loss": 0.8548,
"step": 1186
},
{
"epoch": 0.57,
"learning_rate": 1.6438490781307515e-05,
"loss": 0.7895,
"step": 1187
},
{
"epoch": 0.57,
"learning_rate": 1.640785705142975e-05,
"loss": 0.9934,
"step": 1188
},
{
"epoch": 0.57,
"learning_rate": 1.6377232027397258e-05,
"loss": 0.9273,
"step": 1189
},
{
"epoch": 0.57,
"learning_rate": 1.634661578343225e-05,
"loss": 0.8787,
"step": 1190
},
{
"epoch": 0.57,
"learning_rate": 1.6316008393735628e-05,
"loss": 0.8416,
"step": 1191
},
{
"epoch": 0.57,
"learning_rate": 1.6285409932486848e-05,
"loss": 0.7842,
"step": 1192
},
{
"epoch": 0.57,
"learning_rate": 1.6254820473843723e-05,
"loss": 0.7785,
"step": 1193
},
{
"epoch": 0.57,
"learning_rate": 1.622424009194225e-05,
"loss": 0.7333,
"step": 1194
},
{
"epoch": 0.57,
"learning_rate": 1.6193668860896427e-05,
"loss": 0.8783,
"step": 1195
},
{
"epoch": 0.57,
"learning_rate": 1.6163106854798075e-05,
"loss": 0.7089,
"step": 1196
},
{
"epoch": 0.57,
"learning_rate": 1.6132554147716643e-05,
"loss": 0.83,
"step": 1197
},
{
"epoch": 0.58,
"learning_rate": 1.610201081369908e-05,
"loss": 0.8082,
"step": 1198
},
{
"epoch": 0.58,
"learning_rate": 1.607147692676957e-05,
"loss": 0.85,
"step": 1199
},
{
"epoch": 0.58,
"learning_rate": 1.6040952560929453e-05,
"loss": 0.877,
"step": 1200
},
{
"epoch": 0.58,
"learning_rate": 1.601043779015695e-05,
"loss": 0.6425,
"step": 1201
},
{
"epoch": 0.58,
"learning_rate": 1.5979932688407038e-05,
"loss": 0.744,
"step": 1202
},
{
"epoch": 0.58,
"learning_rate": 1.5949437329611282e-05,
"loss": 0.8513,
"step": 1203
},
{
"epoch": 0.58,
"learning_rate": 1.591895178767761e-05,
"loss": 0.8467,
"step": 1204
},
{
"epoch": 0.58,
"learning_rate": 1.5888476136490177e-05,
"loss": 0.7514,
"step": 1205
},
{
"epoch": 0.58,
"learning_rate": 1.5858010449909153e-05,
"loss": 0.7605,
"step": 1206
},
{
"epoch": 0.58,
"learning_rate": 1.5827554801770554e-05,
"loss": 0.8327,
"step": 1207
},
{
"epoch": 0.58,
"learning_rate": 1.5797109265886085e-05,
"loss": 0.8947,
"step": 1208
},
{
"epoch": 0.58,
"learning_rate": 1.5766673916042926e-05,
"loss": 0.863,
"step": 1209
},
{
"epoch": 0.58,
"learning_rate": 1.5736248826003587e-05,
"loss": 0.7075,
"step": 1210
},
{
"epoch": 0.58,
"learning_rate": 1.5705834069505702e-05,
"loss": 0.6782,
"step": 1211
},
{
"epoch": 0.58,
"learning_rate": 1.5675429720261848e-05,
"loss": 0.7683,
"step": 1212
},
{
"epoch": 0.58,
"learning_rate": 1.5645035851959412e-05,
"loss": 0.7701,
"step": 1213
},
{
"epoch": 0.58,
"learning_rate": 1.5614652538260344e-05,
"loss": 0.7619,
"step": 1214
},
{
"epoch": 0.58,
"learning_rate": 1.558427985280105e-05,
"loss": 0.7127,
"step": 1215
},
{
"epoch": 0.58,
"learning_rate": 1.5553917869192136e-05,
"loss": 0.8634,
"step": 1216
},
{
"epoch": 0.58,
"learning_rate": 1.552356666101832e-05,
"loss": 0.7333,
"step": 1217
},
{
"epoch": 0.59,
"learning_rate": 1.5493226301838155e-05,
"loss": 1.0024,
"step": 1218
},
{
"epoch": 0.59,
"learning_rate": 1.5462896865183938e-05,
"loss": 0.8464,
"step": 1219
},
{
"epoch": 0.59,
"learning_rate": 1.5432578424561474e-05,
"loss": 0.7389,
"step": 1220
},
{
"epoch": 0.59,
"learning_rate": 1.540227105344993e-05,
"loss": 0.7641,
"step": 1221
},
{
"epoch": 0.59,
"learning_rate": 1.5371974825301636e-05,
"loss": 0.7169,
"step": 1222
},
{
"epoch": 0.59,
"learning_rate": 1.5341689813541928e-05,
"loss": 0.8362,
"step": 1223
},
{
"epoch": 0.59,
"learning_rate": 1.5311416091568935e-05,
"loss": 0.7652,
"step": 1224
},
{
"epoch": 0.59,
"learning_rate": 1.5281153732753458e-05,
"loss": 0.756,
"step": 1225
},
{
"epoch": 0.59,
"learning_rate": 1.5250902810438722e-05,
"loss": 0.7723,
"step": 1226
},
{
"epoch": 0.59,
"learning_rate": 1.522066339794027e-05,
"loss": 0.8064,
"step": 1227
},
{
"epoch": 0.59,
"learning_rate": 1.5190435568545728e-05,
"loss": 0.8577,
"step": 1228
},
{
"epoch": 0.59,
"learning_rate": 1.516021939551464e-05,
"loss": 0.8803,
"step": 1229
},
{
"epoch": 0.59,
"learning_rate": 1.5130014952078334e-05,
"loss": 0.8457,
"step": 1230
},
{
"epoch": 0.59,
"learning_rate": 1.5099822311439675e-05,
"loss": 0.8142,
"step": 1231
},
{
"epoch": 0.59,
"learning_rate": 1.5069641546772955e-05,
"loss": 0.8818,
"step": 1232
},
{
"epoch": 0.59,
"learning_rate": 1.5039472731223657e-05,
"loss": 0.7995,
"step": 1233
},
{
"epoch": 0.59,
"learning_rate": 1.5009315937908307e-05,
"loss": 0.8498,
"step": 1234
},
{
"epoch": 0.59,
"learning_rate": 1.4979171239914321e-05,
"loss": 0.7857,
"step": 1235
},
{
"epoch": 0.59,
"learning_rate": 1.4949038710299759e-05,
"loss": 0.8359,
"step": 1236
},
{
"epoch": 0.59,
"learning_rate": 1.4918918422093236e-05,
"loss": 0.8208,
"step": 1237
},
{
"epoch": 0.59,
"learning_rate": 1.4888810448293667e-05,
"loss": 0.6836,
"step": 1238
},
{
"epoch": 0.6,
"learning_rate": 1.4858714861870116e-05,
"loss": 0.7107,
"step": 1239
},
{
"epoch": 0.6,
"learning_rate": 1.4828631735761663e-05,
"loss": 0.7486,
"step": 1240
},
{
"epoch": 0.6,
"learning_rate": 1.4798561142877147e-05,
"loss": 0.7102,
"step": 1241
},
{
"epoch": 0.6,
"learning_rate": 1.476850315609507e-05,
"loss": 0.8465,
"step": 1242
},
{
"epoch": 0.6,
"learning_rate": 1.4738457848263346e-05,
"loss": 0.6829,
"step": 1243
},
{
"epoch": 0.6,
"learning_rate": 1.4708425292199187e-05,
"loss": 0.7466,
"step": 1244
},
{
"epoch": 0.6,
"learning_rate": 1.4678405560688889e-05,
"loss": 0.8856,
"step": 1245
},
{
"epoch": 0.6,
"learning_rate": 1.4648398726487667e-05,
"loss": 0.973,
"step": 1246
},
{
"epoch": 0.6,
"learning_rate": 1.4618404862319481e-05,
"loss": 0.7838,
"step": 1247
},
{
"epoch": 0.6,
"learning_rate": 1.4588424040876858e-05,
"loss": 0.8828,
"step": 1248
},
{
"epoch": 0.6,
"learning_rate": 1.4558456334820712e-05,
"loss": 0.8453,
"step": 1249
},
{
"epoch": 0.6,
"learning_rate": 1.4528501816780174e-05,
"loss": 0.9562,
"step": 1250
},
{
"epoch": 0.6,
"learning_rate": 1.4498560559352397e-05,
"loss": 0.7759,
"step": 1251
},
{
"epoch": 0.6,
"learning_rate": 1.446863263510243e-05,
"loss": 0.8381,
"step": 1252
},
{
"epoch": 0.6,
"learning_rate": 1.4438718116562969e-05,
"loss": 0.708,
"step": 1253
},
{
"epoch": 0.6,
"learning_rate": 1.4408817076234254e-05,
"loss": 0.9052,
"step": 1254
},
{
"epoch": 0.6,
"learning_rate": 1.4378929586583836e-05,
"loss": 0.7446,
"step": 1255
},
{
"epoch": 0.6,
"learning_rate": 1.4349055720046425e-05,
"loss": 0.8115,
"step": 1256
},
{
"epoch": 0.6,
"learning_rate": 1.4319195549023739e-05,
"loss": 0.7377,
"step": 1257
},
{
"epoch": 0.6,
"learning_rate": 1.4289349145884269e-05,
"loss": 0.7954,
"step": 1258
},
{
"epoch": 0.6,
"learning_rate": 1.4259516582963175e-05,
"loss": 0.8223,
"step": 1259
},
{
"epoch": 0.61,
"learning_rate": 1.4229697932562045e-05,
"loss": 0.6936,
"step": 1260
},
{
"epoch": 0.61,
"learning_rate": 1.4199893266948754e-05,
"loss": 0.7449,
"step": 1261
},
{
"epoch": 0.61,
"learning_rate": 1.4170102658357302e-05,
"loss": 0.6564,
"step": 1262
},
{
"epoch": 0.61,
"learning_rate": 1.4140326178987596e-05,
"loss": 0.8523,
"step": 1263
},
{
"epoch": 0.61,
"learning_rate": 1.4110563901005323e-05,
"loss": 0.7964,
"step": 1264
},
{
"epoch": 0.61,
"learning_rate": 1.4080815896541737e-05,
"loss": 0.9001,
"step": 1265
},
{
"epoch": 0.61,
"learning_rate": 1.4051082237693487e-05,
"loss": 0.7916,
"step": 1266
},
{
"epoch": 0.61,
"learning_rate": 1.4021362996522494e-05,
"loss": 0.6969,
"step": 1267
},
{
"epoch": 0.61,
"learning_rate": 1.3991658245055692e-05,
"loss": 0.806,
"step": 1268
},
{
"epoch": 0.61,
"learning_rate": 1.3961968055284936e-05,
"loss": 0.8583,
"step": 1269
},
{
"epoch": 0.61,
"learning_rate": 1.3932292499166757e-05,
"loss": 0.8543,
"step": 1270
},
{
"epoch": 0.61,
"learning_rate": 1.390263164862224e-05,
"loss": 0.7614,
"step": 1271
},
{
"epoch": 0.61,
"learning_rate": 1.3872985575536826e-05,
"loss": 0.7572,
"step": 1272
},
{
"epoch": 0.61,
"learning_rate": 1.3843354351760141e-05,
"loss": 0.6099,
"step": 1273
},
{
"epoch": 0.61,
"learning_rate": 1.3813738049105819e-05,
"loss": 0.7254,
"step": 1274
},
{
"epoch": 0.61,
"learning_rate": 1.3784136739351342e-05,
"loss": 0.7656,
"step": 1275
},
{
"epoch": 0.61,
"learning_rate": 1.3754550494237835e-05,
"loss": 0.7419,
"step": 1276
},
{
"epoch": 0.61,
"learning_rate": 1.3724979385469938e-05,
"loss": 0.8136,
"step": 1277
},
{
"epoch": 0.61,
"learning_rate": 1.3695423484715584e-05,
"loss": 0.8012,
"step": 1278
},
{
"epoch": 0.61,
"learning_rate": 1.366588286360587e-05,
"loss": 0.745,
"step": 1279
},
{
"epoch": 0.61,
"learning_rate": 1.3636357593734839e-05,
"loss": 0.724,
"step": 1280
},
{
"epoch": 0.62,
"learning_rate": 1.3606847746659353e-05,
"loss": 0.7767,
"step": 1281
},
{
"epoch": 0.62,
"learning_rate": 1.3577353393898875e-05,
"loss": 0.8141,
"step": 1282
},
{
"epoch": 0.62,
"learning_rate": 1.3547874606935319e-05,
"loss": 0.8409,
"step": 1283
},
{
"epoch": 0.62,
"learning_rate": 1.3518411457212887e-05,
"loss": 0.8122,
"step": 1284
},
{
"epoch": 0.62,
"learning_rate": 1.348896401613787e-05,
"loss": 0.829,
"step": 1285
},
{
"epoch": 0.62,
"learning_rate": 1.3459532355078503e-05,
"loss": 0.8344,
"step": 1286
},
{
"epoch": 0.62,
"learning_rate": 1.343011654536476e-05,
"loss": 0.6823,
"step": 1287
},
{
"epoch": 0.62,
"learning_rate": 1.3400716658288198e-05,
"loss": 0.7419,
"step": 1288
},
{
"epoch": 0.62,
"learning_rate": 1.3371332765101803e-05,
"loss": 0.8412,
"step": 1289
},
{
"epoch": 0.62,
"learning_rate": 1.3341964937019776e-05,
"loss": 0.7964,
"step": 1290
},
{
"epoch": 0.62,
"learning_rate": 1.3312613245217403e-05,
"loss": 0.7108,
"step": 1291
},
{
"epoch": 0.62,
"learning_rate": 1.3283277760830852e-05,
"loss": 0.6436,
"step": 1292
},
{
"epoch": 0.62,
"learning_rate": 1.3253958554957e-05,
"loss": 0.6815,
"step": 1293
},
{
"epoch": 0.62,
"learning_rate": 1.32246556986533e-05,
"loss": 0.9237,
"step": 1294
},
{
"epoch": 0.62,
"learning_rate": 1.3195369262937549e-05,
"loss": 0.7677,
"step": 1295
},
{
"epoch": 0.62,
"learning_rate": 1.316609931878778e-05,
"loss": 0.8574,
"step": 1296
},
{
"epoch": 0.62,
"learning_rate": 1.3136845937142022e-05,
"loss": 0.6677,
"step": 1297
},
{
"epoch": 0.62,
"learning_rate": 1.310760918889819e-05,
"loss": 0.8527,
"step": 1298
},
{
"epoch": 0.62,
"learning_rate": 1.3078389144913883e-05,
"loss": 0.7441,
"step": 1299
},
{
"epoch": 0.62,
"learning_rate": 1.3049185876006203e-05,
"loss": 0.811,
"step": 1300
},
{
"epoch": 0.62,
"learning_rate": 1.3019999452951607e-05,
"loss": 0.8852,
"step": 1301
},
{
"epoch": 0.63,
"learning_rate": 1.2990829946485724e-05,
"loss": 0.7903,
"step": 1302
},
{
"epoch": 0.63,
"learning_rate": 1.2961677427303174e-05,
"loss": 0.8985,
"step": 1303
},
{
"epoch": 0.63,
"learning_rate": 1.293254196605743e-05,
"loss": 0.7823,
"step": 1304
},
{
"epoch": 0.63,
"learning_rate": 1.290342363336059e-05,
"loss": 0.7545,
"step": 1305
},
{
"epoch": 0.63,
"learning_rate": 1.2874322499783278e-05,
"loss": 0.7774,
"step": 1306
},
{
"epoch": 0.63,
"learning_rate": 1.2845238635854407e-05,
"loss": 0.9081,
"step": 1307
},
{
"epoch": 0.63,
"learning_rate": 1.2816172112061032e-05,
"loss": 0.7896,
"step": 1308
},
{
"epoch": 0.63,
"learning_rate": 1.2787122998848216e-05,
"loss": 0.6985,
"step": 1309
},
{
"epoch": 0.63,
"learning_rate": 1.2758091366618781e-05,
"loss": 0.8357,
"step": 1310
},
{
"epoch": 0.63,
"learning_rate": 1.2729077285733231e-05,
"loss": 0.793,
"step": 1311
},
{
"epoch": 0.63,
"learning_rate": 1.2700080826509487e-05,
"loss": 0.8226,
"step": 1312
},
{
"epoch": 0.63,
"learning_rate": 1.2671102059222799e-05,
"loss": 0.6967,
"step": 1313
},
{
"epoch": 0.63,
"learning_rate": 1.2642141054105516e-05,
"loss": 0.9131,
"step": 1314
},
{
"epoch": 0.63,
"learning_rate": 1.2613197881346941e-05,
"loss": 0.8196,
"step": 1315
},
{
"epoch": 0.63,
"learning_rate": 1.2584272611093178e-05,
"loss": 0.7749,
"step": 1316
},
{
"epoch": 0.63,
"learning_rate": 1.2555365313446911e-05,
"loss": 0.8242,
"step": 1317
},
{
"epoch": 0.63,
"learning_rate": 1.2526476058467307e-05,
"loss": 0.6551,
"step": 1318
},
{
"epoch": 0.63,
"learning_rate": 1.2497604916169772e-05,
"loss": 0.7725,
"step": 1319
},
{
"epoch": 0.63,
"learning_rate": 1.246875195652581e-05,
"loss": 0.8368,
"step": 1320
},
{
"epoch": 0.63,
"learning_rate": 1.2439917249462898e-05,
"loss": 0.7968,
"step": 1321
},
{
"epoch": 0.64,
"learning_rate": 1.241110086486423e-05,
"loss": 0.7811,
"step": 1322
},
{
"epoch": 0.64,
"learning_rate": 1.2382302872568635e-05,
"loss": 0.7749,
"step": 1323
},
{
"epoch": 0.64,
"learning_rate": 1.2353523342370328e-05,
"loss": 0.7459,
"step": 1324
},
{
"epoch": 0.64,
"learning_rate": 1.2324762344018808e-05,
"loss": 0.9459,
"step": 1325
},
{
"epoch": 0.64,
"learning_rate": 1.2296019947218652e-05,
"loss": 0.7449,
"step": 1326
},
{
"epoch": 0.64,
"learning_rate": 1.2267296221629353e-05,
"loss": 0.9733,
"step": 1327
},
{
"epoch": 0.64,
"learning_rate": 1.223859123686515e-05,
"loss": 0.907,
"step": 1328
},
{
"epoch": 0.64,
"learning_rate": 1.2209905062494874e-05,
"loss": 0.6868,
"step": 1329
},
{
"epoch": 0.64,
"learning_rate": 1.2181237768041745e-05,
"loss": 0.6874,
"step": 1330
},
{
"epoch": 0.64,
"learning_rate": 1.2152589422983256e-05,
"loss": 0.8635,
"step": 1331
},
{
"epoch": 0.64,
"learning_rate": 1.2123960096750946e-05,
"loss": 0.8701,
"step": 1332
},
{
"epoch": 0.64,
"learning_rate": 1.209534985873029e-05,
"loss": 0.7662,
"step": 1333
},
{
"epoch": 0.64,
"learning_rate": 1.2066758778260472e-05,
"loss": 0.7988,
"step": 1334
},
{
"epoch": 0.64,
"learning_rate": 1.203818692463425e-05,
"loss": 0.8568,
"step": 1335
},
{
"epoch": 0.64,
"learning_rate": 1.2009634367097815e-05,
"loss": 0.815,
"step": 1336
},
{
"epoch": 0.64,
"learning_rate": 1.1981101174850549e-05,
"loss": 0.5727,
"step": 1337
},
{
"epoch": 0.64,
"learning_rate": 1.1952587417044938e-05,
"loss": 0.709,
"step": 1338
},
{
"epoch": 0.64,
"learning_rate": 1.192409316278635e-05,
"loss": 0.7023,
"step": 1339
},
{
"epoch": 0.64,
"learning_rate": 1.1895618481132867e-05,
"loss": 0.9157,
"step": 1340
},
{
"epoch": 0.64,
"learning_rate": 1.1867163441095178e-05,
"loss": 0.7744,
"step": 1341
},
{
"epoch": 0.64,
"learning_rate": 1.1838728111636324e-05,
"loss": 0.722,
"step": 1342
},
{
"epoch": 0.65,
"learning_rate": 1.1810312561671617e-05,
"loss": 0.7501,
"step": 1343
},
{
"epoch": 0.65,
"learning_rate": 1.178191686006839e-05,
"loss": 0.7627,
"step": 1344
},
{
"epoch": 0.65,
"learning_rate": 1.1753541075645913e-05,
"loss": 0.735,
"step": 1345
},
{
"epoch": 0.65,
"learning_rate": 1.1725185277175157e-05,
"loss": 0.8688,
"step": 1346
},
{
"epoch": 0.65,
"learning_rate": 1.1696849533378658e-05,
"loss": 0.8493,
"step": 1347
},
{
"epoch": 0.65,
"learning_rate": 1.1668533912930364e-05,
"loss": 0.8519,
"step": 1348
},
{
"epoch": 0.65,
"learning_rate": 1.164023848445543e-05,
"loss": 0.9197,
"step": 1349
},
{
"epoch": 0.65,
"learning_rate": 1.1611963316530106e-05,
"loss": 0.8146,
"step": 1350
},
{
"epoch": 0.65,
"learning_rate": 1.1583708477681506e-05,
"loss": 0.7429,
"step": 1351
},
{
"epoch": 0.65,
"learning_rate": 1.1555474036387482e-05,
"loss": 0.7946,
"step": 1352
},
{
"epoch": 0.65,
"learning_rate": 1.152726006107647e-05,
"loss": 0.828,
"step": 1353
},
{
"epoch": 0.65,
"learning_rate": 1.1499066620127283e-05,
"loss": 0.8039,
"step": 1354
},
{
"epoch": 0.65,
"learning_rate": 1.1470893781868986e-05,
"loss": 0.8712,
"step": 1355
},
{
"epoch": 0.65,
"learning_rate": 1.14427416145807e-05,
"loss": 0.7982,
"step": 1356
},
{
"epoch": 0.65,
"learning_rate": 1.1414610186491437e-05,
"loss": 0.7071,
"step": 1357
},
{
"epoch": 0.65,
"learning_rate": 1.1386499565779978e-05,
"loss": 0.7918,
"step": 1358
},
{
"epoch": 0.65,
"learning_rate": 1.135840982057464e-05,
"loss": 0.8611,
"step": 1359
},
{
"epoch": 0.65,
"learning_rate": 1.1330341018953183e-05,
"loss": 0.8295,
"step": 1360
},
{
"epoch": 0.65,
"learning_rate": 1.130229322894257e-05,
"loss": 0.7554,
"step": 1361
},
{
"epoch": 0.65,
"learning_rate": 1.1274266518518874e-05,
"loss": 0.8147,
"step": 1362
},
{
"epoch": 0.65,
"learning_rate": 1.1246260955607053e-05,
"loss": 1.0165,
"step": 1363
},
{
"epoch": 0.66,
"learning_rate": 1.1218276608080845e-05,
"loss": 0.9676,
"step": 1364
},
{
"epoch": 0.66,
"learning_rate": 1.1190313543762525e-05,
"loss": 0.8096,
"step": 1365
},
{
"epoch": 0.66,
"learning_rate": 1.1162371830422835e-05,
"loss": 0.8757,
"step": 1366
},
{
"epoch": 0.66,
"learning_rate": 1.1134451535780732e-05,
"loss": 0.8996,
"step": 1367
},
{
"epoch": 0.66,
"learning_rate": 1.1106552727503295e-05,
"loss": 0.7988,
"step": 1368
},
{
"epoch": 0.66,
"learning_rate": 1.1078675473205496e-05,
"loss": 0.8329,
"step": 1369
},
{
"epoch": 0.66,
"learning_rate": 1.1050819840450107e-05,
"loss": 0.6578,
"step": 1370
},
{
"epoch": 0.66,
"learning_rate": 1.1022985896747464e-05,
"loss": 0.9332,
"step": 1371
},
{
"epoch": 0.66,
"learning_rate": 1.0995173709555352e-05,
"loss": 0.8767,
"step": 1372
},
{
"epoch": 0.66,
"learning_rate": 1.0967383346278837e-05,
"loss": 0.7504,
"step": 1373
},
{
"epoch": 0.66,
"learning_rate": 1.093961487427007e-05,
"loss": 0.7289,
"step": 1374
},
{
"epoch": 0.66,
"learning_rate": 1.0911868360828177e-05,
"loss": 0.7684,
"step": 1375
},
{
"epoch": 0.66,
"learning_rate": 1.0884143873199036e-05,
"loss": 0.8557,
"step": 1376
},
{
"epoch": 0.66,
"learning_rate": 1.0856441478575164e-05,
"loss": 0.7547,
"step": 1377
},
{
"epoch": 0.66,
"learning_rate": 1.0828761244095528e-05,
"loss": 0.7937,
"step": 1378
},
{
"epoch": 0.66,
"learning_rate": 1.0801103236845371e-05,
"loss": 0.7634,
"step": 1379
},
{
"epoch": 0.66,
"learning_rate": 1.0773467523856104e-05,
"loss": 0.7386,
"step": 1380
},
{
"epoch": 0.66,
"learning_rate": 1.0745854172105066e-05,
"loss": 0.8253,
"step": 1381
},
{
"epoch": 0.66,
"learning_rate": 1.0718263248515434e-05,
"loss": 0.7391,
"step": 1382
},
{
"epoch": 0.66,
"learning_rate": 1.069069481995601e-05,
"loss": 0.7483,
"step": 1383
},
{
"epoch": 0.66,
"learning_rate": 1.0663148953241075e-05,
"loss": 0.8856,
"step": 1384
},
{
"epoch": 0.67,
"learning_rate": 1.0635625715130246e-05,
"loss": 0.7958,
"step": 1385
},
{
"epoch": 0.67,
"learning_rate": 1.0608125172328278e-05,
"loss": 0.8836,
"step": 1386
},
{
"epoch": 0.67,
"learning_rate": 1.0580647391484949e-05,
"loss": 0.75,
"step": 1387
},
{
"epoch": 0.67,
"learning_rate": 1.055319243919484e-05,
"loss": 0.778,
"step": 1388
},
{
"epoch": 0.67,
"learning_rate": 1.0525760381997223e-05,
"loss": 0.7749,
"step": 1389
},
{
"epoch": 0.67,
"learning_rate": 1.049835128637589e-05,
"loss": 0.7563,
"step": 1390
},
{
"epoch": 0.67,
"learning_rate": 1.0470965218758953e-05,
"loss": 0.7654,
"step": 1391
},
{
"epoch": 0.67,
"learning_rate": 1.0443602245518756e-05,
"loss": 0.816,
"step": 1392
},
{
"epoch": 0.67,
"learning_rate": 1.0416262432971638e-05,
"loss": 0.7753,
"step": 1393
},
{
"epoch": 0.67,
"learning_rate": 1.0388945847377815e-05,
"loss": 0.8129,
"step": 1394
},
{
"epoch": 0.67,
"learning_rate": 1.036165255494122e-05,
"loss": 0.8415,
"step": 1395
},
{
"epoch": 0.67,
"learning_rate": 1.033438262180932e-05,
"loss": 0.864,
"step": 1396
},
{
"epoch": 0.67,
"learning_rate": 1.0307136114072987e-05,
"loss": 0.7572,
"step": 1397
},
{
"epoch": 0.67,
"learning_rate": 1.0279913097766301e-05,
"loss": 0.9031,
"step": 1398
},
{
"epoch": 0.67,
"learning_rate": 1.025271363886641e-05,
"loss": 0.7405,
"step": 1399
},
{
"epoch": 0.67,
"learning_rate": 1.0225537803293384e-05,
"loss": 0.6923,
"step": 1400
},
{
"epoch": 0.67,
"learning_rate": 1.0198385656910024e-05,
"loss": 0.7479,
"step": 1401
},
{
"epoch": 0.67,
"learning_rate": 1.0171257265521735e-05,
"loss": 0.7799,
"step": 1402
},
{
"epoch": 0.67,
"learning_rate": 1.0144152694876332e-05,
"loss": 0.8073,
"step": 1403
},
{
"epoch": 0.67,
"learning_rate": 1.0117072010663903e-05,
"loss": 0.7006,
"step": 1404
},
{
"epoch": 0.67,
"learning_rate": 1.0090015278516658e-05,
"loss": 0.8247,
"step": 1405
},
{
"epoch": 0.68,
"learning_rate": 1.0062982564008737e-05,
"loss": 0.7815,
"step": 1406
},
{
"epoch": 0.68,
"learning_rate": 1.0035973932656096e-05,
"loss": 0.8321,
"step": 1407
},
{
"epoch": 0.68,
"learning_rate": 1.0008989449916294e-05,
"loss": 0.8156,
"step": 1408
},
{
"epoch": 0.68,
"learning_rate": 9.982029181188397e-06,
"loss": 0.8239,
"step": 1409
},
{
"epoch": 0.68,
"learning_rate": 9.955093191812762e-06,
"loss": 0.7769,
"step": 1410
},
{
"epoch": 0.68,
"learning_rate": 9.928181547070897e-06,
"loss": 0.8023,
"step": 1411
},
{
"epoch": 0.68,
"learning_rate": 9.901294312185343e-06,
"loss": 0.8008,
"step": 1412
},
{
"epoch": 0.68,
"learning_rate": 9.874431552319444e-06,
"loss": 0.7156,
"step": 1413
},
{
"epoch": 0.68,
"learning_rate": 9.84759333257726e-06,
"loss": 0.7347,
"step": 1414
},
{
"epoch": 0.68,
"learning_rate": 9.820779718003341e-06,
"loss": 0.8215,
"step": 1415
},
{
"epoch": 0.68,
"learning_rate": 9.793990773582642e-06,
"loss": 0.6976,
"step": 1416
},
{
"epoch": 0.68,
"learning_rate": 9.767226564240291e-06,
"loss": 0.8492,
"step": 1417
},
{
"epoch": 0.68,
"learning_rate": 9.740487154841504e-06,
"loss": 0.7922,
"step": 1418
},
{
"epoch": 0.68,
"learning_rate": 9.71377261019136e-06,
"loss": 0.7727,
"step": 1419
},
{
"epoch": 0.68,
"learning_rate": 9.687082995034702e-06,
"loss": 0.8026,
"step": 1420
},
{
"epoch": 0.68,
"learning_rate": 9.660418374055935e-06,
"loss": 0.736,
"step": 1421
},
{
"epoch": 0.68,
"learning_rate": 9.633778811878909e-06,
"loss": 0.7331,
"step": 1422
},
{
"epoch": 0.68,
"learning_rate": 9.607164373066714e-06,
"loss": 0.8121,
"step": 1423
},
{
"epoch": 0.68,
"learning_rate": 9.580575122121583e-06,
"loss": 0.7405,
"step": 1424
},
{
"epoch": 0.68,
"learning_rate": 9.554011123484683e-06,
"loss": 0.7511,
"step": 1425
},
{
"epoch": 0.69,
"learning_rate": 9.527472441535978e-06,
"loss": 0.8387,
"step": 1426
},
{
"epoch": 0.69,
"learning_rate": 9.500959140594099e-06,
"loss": 0.8015,
"step": 1427
},
{
"epoch": 0.69,
"learning_rate": 9.474471284916131e-06,
"loss": 0.8523,
"step": 1428
},
{
"epoch": 0.69,
"learning_rate": 9.448008938697527e-06,
"loss": 0.7908,
"step": 1429
},
{
"epoch": 0.69,
"learning_rate": 9.42157216607188e-06,
"loss": 0.9333,
"step": 1430
},
{
"epoch": 0.69,
"learning_rate": 9.395161031110818e-06,
"loss": 0.8327,
"step": 1431
},
{
"epoch": 0.69,
"learning_rate": 9.36877559782385e-06,
"loss": 0.7779,
"step": 1432
},
{
"epoch": 0.69,
"learning_rate": 9.342415930158167e-06,
"loss": 0.7566,
"step": 1433
},
{
"epoch": 0.69,
"learning_rate": 9.31608209199854e-06,
"loss": 0.8775,
"step": 1434
},
{
"epoch": 0.69,
"learning_rate": 9.289774147167117e-06,
"loss": 0.7531,
"step": 1435
},
{
"epoch": 0.69,
"learning_rate": 9.263492159423315e-06,
"loss": 0.7585,
"step": 1436
},
{
"epoch": 0.69,
"learning_rate": 9.237236192463623e-06,
"loss": 0.7515,
"step": 1437
},
{
"epoch": 0.69,
"learning_rate": 9.211006309921471e-06,
"loss": 0.7984,
"step": 1438
},
{
"epoch": 0.69,
"learning_rate": 9.184802575367081e-06,
"loss": 0.7771,
"step": 1439
},
{
"epoch": 0.69,
"learning_rate": 9.158625052307289e-06,
"loss": 0.8067,
"step": 1440
},
{
"epoch": 0.69,
"learning_rate": 9.132473804185422e-06,
"loss": 0.9069,
"step": 1441
},
{
"epoch": 0.69,
"learning_rate": 9.106348894381112e-06,
"loss": 0.7876,
"step": 1442
},
{
"epoch": 0.69,
"learning_rate": 9.080250386210156e-06,
"loss": 0.7432,
"step": 1443
},
{
"epoch": 0.69,
"learning_rate": 9.05417834292439e-06,
"loss": 0.8866,
"step": 1444
},
{
"epoch": 0.69,
"learning_rate": 9.028132827711477e-06,
"loss": 0.8469,
"step": 1445
},
{
"epoch": 0.69,
"learning_rate": 9.002113903694818e-06,
"loss": 0.8669,
"step": 1446
},
{
"epoch": 0.7,
"learning_rate": 8.976121633933345e-06,
"loss": 0.8811,
"step": 1447
},
{
"epoch": 0.7,
"learning_rate": 8.95015608142139e-06,
"loss": 0.8613,
"step": 1448
},
{
"epoch": 0.7,
"learning_rate": 8.924217309088563e-06,
"loss": 0.9477,
"step": 1449
},
{
"epoch": 0.7,
"learning_rate": 8.89830537979953e-06,
"loss": 0.84,
"step": 1450
},
{
"epoch": 0.7,
"learning_rate": 8.872420356353938e-06,
"loss": 0.6912,
"step": 1451
},
{
"epoch": 0.7,
"learning_rate": 8.8465623014862e-06,
"loss": 0.6554,
"step": 1452
},
{
"epoch": 0.7,
"learning_rate": 8.820731277865374e-06,
"loss": 0.8475,
"step": 1453
},
{
"epoch": 0.7,
"learning_rate": 8.794927348095015e-06,
"loss": 0.7827,
"step": 1454
},
{
"epoch": 0.7,
"learning_rate": 8.769150574712999e-06,
"loss": 0.7208,
"step": 1455
},
{
"epoch": 0.7,
"learning_rate": 8.743401020191406e-06,
"loss": 0.9659,
"step": 1456
},
{
"epoch": 0.7,
"learning_rate": 8.717678746936334e-06,
"loss": 0.8438,
"step": 1457
},
{
"epoch": 0.7,
"learning_rate": 8.691983817287755e-06,
"loss": 0.9008,
"step": 1458
},
{
"epoch": 0.7,
"learning_rate": 8.666316293519399e-06,
"loss": 0.8585,
"step": 1459
},
{
"epoch": 0.7,
"learning_rate": 8.640676237838545e-06,
"loss": 0.7097,
"step": 1460
},
{
"epoch": 0.7,
"learning_rate": 8.615063712385932e-06,
"loss": 0.7962,
"step": 1461
},
{
"epoch": 0.7,
"learning_rate": 8.589478779235549e-06,
"loss": 0.7608,
"step": 1462
},
{
"epoch": 0.7,
"learning_rate": 8.56392150039452e-06,
"loss": 0.674,
"step": 1463
},
{
"epoch": 0.7,
"learning_rate": 8.538391937802968e-06,
"loss": 0.6829,
"step": 1464
},
{
"epoch": 0.7,
"learning_rate": 8.512890153333806e-06,
"loss": 0.9768,
"step": 1465
},
{
"epoch": 0.7,
"learning_rate": 8.487416208792664e-06,
"loss": 0.6861,
"step": 1466
},
{
"epoch": 0.7,
"learning_rate": 8.461970165917668e-06,
"loss": 0.8438,
"step": 1467
},
{
"epoch": 0.71,
"learning_rate": 8.436552086379346e-06,
"loss": 0.8243,
"step": 1468
},
{
"epoch": 0.71,
"learning_rate": 8.411162031780428e-06,
"loss": 0.7041,
"step": 1469
},
{
"epoch": 0.71,
"learning_rate": 8.385800063655756e-06,
"loss": 0.7406,
"step": 1470
},
{
"epoch": 0.71,
"learning_rate": 8.36046624347207e-06,
"loss": 0.693,
"step": 1471
},
{
"epoch": 0.71,
"learning_rate": 8.33516063262792e-06,
"loss": 0.6651,
"step": 1472
},
{
"epoch": 0.71,
"learning_rate": 8.309883292453461e-06,
"loss": 0.7385,
"step": 1473
},
{
"epoch": 0.71,
"learning_rate": 8.28463428421036e-06,
"loss": 0.67,
"step": 1474
},
{
"epoch": 0.71,
"learning_rate": 8.25941366909159e-06,
"loss": 0.7692,
"step": 1475
},
{
"epoch": 0.71,
"learning_rate": 8.234221508221338e-06,
"loss": 0.8259,
"step": 1476
},
{
"epoch": 0.71,
"learning_rate": 8.209057862654806e-06,
"loss": 0.7763,
"step": 1477
},
{
"epoch": 0.71,
"learning_rate": 8.183922793378111e-06,
"loss": 0.8802,
"step": 1478
},
{
"epoch": 0.71,
"learning_rate": 8.158816361308096e-06,
"loss": 0.8748,
"step": 1479
},
{
"epoch": 0.71,
"learning_rate": 8.133738627292194e-06,
"loss": 0.7644,
"step": 1480
},
{
"epoch": 0.71,
"learning_rate": 8.108689652108312e-06,
"loss": 0.8871,
"step": 1481
},
{
"epoch": 0.71,
"learning_rate": 8.083669496464629e-06,
"loss": 0.7383,
"step": 1482
},
{
"epoch": 0.71,
"learning_rate": 8.058678220999498e-06,
"loss": 0.7946,
"step": 1483
},
{
"epoch": 0.71,
"learning_rate": 8.033715886281268e-06,
"loss": 0.7911,
"step": 1484
},
{
"epoch": 0.71,
"learning_rate": 8.008782552808145e-06,
"loss": 0.7207,
"step": 1485
},
{
"epoch": 0.71,
"learning_rate": 7.983878281008066e-06,
"loss": 0.7501,
"step": 1486
},
{
"epoch": 0.71,
"learning_rate": 7.95900313123851e-06,
"loss": 0.7201,
"step": 1487
},
{
"epoch": 0.71,
"learning_rate": 7.934157163786397e-06,
"loss": 0.9694,
"step": 1488
},
{
"epoch": 0.72,
"learning_rate": 7.909340438867914e-06,
"loss": 0.7998,
"step": 1489
},
{
"epoch": 0.72,
"learning_rate": 7.884553016628365e-06,
"loss": 0.713,
"step": 1490
},
{
"epoch": 0.72,
"learning_rate": 7.85979495714206e-06,
"loss": 0.8601,
"step": 1491
},
{
"epoch": 0.72,
"learning_rate": 7.835066320412121e-06,
"loss": 0.7852,
"step": 1492
},
{
"epoch": 0.72,
"learning_rate": 7.810367166370387e-06,
"loss": 0.6758,
"step": 1493
},
{
"epoch": 0.72,
"learning_rate": 7.785697554877226e-06,
"loss": 0.8012,
"step": 1494
},
{
"epoch": 0.72,
"learning_rate": 7.761057545721398e-06,
"loss": 0.9093,
"step": 1495
},
{
"epoch": 0.72,
"learning_rate": 7.736447198619952e-06,
"loss": 0.7586,
"step": 1496
},
{
"epoch": 0.72,
"learning_rate": 7.711866573218016e-06,
"loss": 0.7983,
"step": 1497
},
{
"epoch": 0.72,
"learning_rate": 7.68731572908871e-06,
"loss": 0.7787,
"step": 1498
},
{
"epoch": 0.72,
"learning_rate": 7.66279472573295e-06,
"loss": 0.8072,
"step": 1499
},
{
"epoch": 0.72,
"learning_rate": 7.638303622579365e-06,
"loss": 0.6882,
"step": 1500
},
{
"epoch": 0.72,
"learning_rate": 7.613842478984086e-06,
"loss": 0.8786,
"step": 1501
},
{
"epoch": 0.72,
"learning_rate": 7.589411354230643e-06,
"loss": 0.8019,
"step": 1502
},
{
"epoch": 0.72,
"learning_rate": 7.565010307529834e-06,
"loss": 0.9197,
"step": 1503
},
{
"epoch": 0.72,
"learning_rate": 7.5406393980195294e-06,
"loss": 0.748,
"step": 1504
},
{
"epoch": 0.72,
"learning_rate": 7.516298684764587e-06,
"loss": 0.7812,
"step": 1505
},
{
"epoch": 0.72,
"learning_rate": 7.491988226756664e-06,
"loss": 0.8592,
"step": 1506
},
{
"epoch": 0.72,
"learning_rate": 7.467708082914087e-06,
"loss": 0.734,
"step": 1507
},
{
"epoch": 0.72,
"learning_rate": 7.443458312081739e-06,
"loss": 0.8436,
"step": 1508
},
{
"epoch": 0.72,
"learning_rate": 7.419238973030865e-06,
"loss": 0.9025,
"step": 1509
},
{
"epoch": 0.73,
"learning_rate": 7.3950501244589755e-06,
"loss": 0.8887,
"step": 1510
},
{
"epoch": 0.73,
"learning_rate": 7.370891824989674e-06,
"loss": 0.7684,
"step": 1511
},
{
"epoch": 0.73,
"learning_rate": 7.346764133172519e-06,
"loss": 0.7576,
"step": 1512
},
{
"epoch": 0.73,
"learning_rate": 7.322667107482915e-06,
"loss": 0.6784,
"step": 1513
},
{
"epoch": 0.73,
"learning_rate": 7.298600806321912e-06,
"loss": 0.8285,
"step": 1514
},
{
"epoch": 0.73,
"learning_rate": 7.274565288016124e-06,
"loss": 0.7349,
"step": 1515
},
{
"epoch": 0.73,
"learning_rate": 7.2505606108175474e-06,
"loss": 0.8572,
"step": 1516
},
{
"epoch": 0.73,
"learning_rate": 7.226586832903424e-06,
"loss": 0.868,
"step": 1517
},
{
"epoch": 0.73,
"learning_rate": 7.202644012376135e-06,
"loss": 0.8423,
"step": 1518
},
{
"epoch": 0.73,
"learning_rate": 7.178732207263002e-06,
"loss": 0.7127,
"step": 1519
},
{
"epoch": 0.73,
"learning_rate": 7.154851475516209e-06,
"loss": 0.8426,
"step": 1520
},
{
"epoch": 0.73,
"learning_rate": 7.131001875012602e-06,
"loss": 0.8268,
"step": 1521
},
{
"epoch": 0.73,
"learning_rate": 7.107183463553604e-06,
"loss": 0.8871,
"step": 1522
},
{
"epoch": 0.73,
"learning_rate": 7.083396298865029e-06,
"loss": 0.8004,
"step": 1523
},
{
"epoch": 0.73,
"learning_rate": 7.05964043859698e-06,
"loss": 0.7995,
"step": 1524
},
{
"epoch": 0.73,
"learning_rate": 7.035915940323668e-06,
"loss": 0.8283,
"step": 1525
},
{
"epoch": 0.73,
"learning_rate": 7.012222861543323e-06,
"loss": 0.7193,
"step": 1526
},
{
"epoch": 0.73,
"learning_rate": 6.9885612596779995e-06,
"loss": 0.7968,
"step": 1527
},
{
"epoch": 0.73,
"learning_rate": 6.964931192073494e-06,
"loss": 0.7081,
"step": 1528
},
{
"epoch": 0.73,
"learning_rate": 6.9413327159991475e-06,
"loss": 0.9797,
"step": 1529
},
{
"epoch": 0.73,
"learning_rate": 6.917765888647765e-06,
"loss": 0.8899,
"step": 1530
},
{
"epoch": 0.74,
"learning_rate": 6.894230767135421e-06,
"loss": 0.7598,
"step": 1531
},
{
"epoch": 0.74,
"learning_rate": 6.870727408501376e-06,
"loss": 0.8236,
"step": 1532
},
{
"epoch": 0.74,
"learning_rate": 6.8472558697078895e-06,
"loss": 0.8448,
"step": 1533
},
{
"epoch": 0.74,
"learning_rate": 6.823816207640102e-06,
"loss": 0.7203,
"step": 1534
},
{
"epoch": 0.74,
"learning_rate": 6.800408479105922e-06,
"loss": 0.9174,
"step": 1535
},
{
"epoch": 0.74,
"learning_rate": 6.777032740835834e-06,
"loss": 0.7788,
"step": 1536
},
{
"epoch": 0.74,
"learning_rate": 6.753689049482819e-06,
"loss": 0.7869,
"step": 1537
},
{
"epoch": 0.74,
"learning_rate": 6.7303774616221705e-06,
"loss": 0.7362,
"step": 1538
},
{
"epoch": 0.74,
"learning_rate": 6.707098033751378e-06,
"loss": 0.8515,
"step": 1539
},
{
"epoch": 0.74,
"learning_rate": 6.683850822290008e-06,
"loss": 0.946,
"step": 1540
},
{
"epoch": 0.74,
"learning_rate": 6.660635883579518e-06,
"loss": 0.9418,
"step": 1541
},
{
"epoch": 0.74,
"learning_rate": 6.637453273883181e-06,
"loss": 0.6686,
"step": 1542
},
{
"epoch": 0.74,
"learning_rate": 6.614303049385895e-06,
"loss": 0.9048,
"step": 1543
},
{
"epoch": 0.74,
"learning_rate": 6.5911852661940716e-06,
"loss": 0.7182,
"step": 1544
},
{
"epoch": 0.74,
"learning_rate": 6.568099980335518e-06,
"loss": 0.7626,
"step": 1545
},
{
"epoch": 0.74,
"learning_rate": 6.545047247759255e-06,
"loss": 0.748,
"step": 1546
},
{
"epoch": 0.74,
"learning_rate": 6.522027124335433e-06,
"loss": 0.8629,
"step": 1547
},
{
"epoch": 0.74,
"learning_rate": 6.499039665855151e-06,
"loss": 0.7892,
"step": 1548
},
{
"epoch": 0.74,
"learning_rate": 6.4760849280303484e-06,
"loss": 0.959,
"step": 1549
},
{
"epoch": 0.74,
"learning_rate": 6.453162966493675e-06,
"loss": 0.7625,
"step": 1550
},
{
"epoch": 0.75,
"learning_rate": 6.430273836798324e-06,
"loss": 0.816,
"step": 1551
},
{
"epoch": 0.75,
"learning_rate": 6.4074175944179395e-06,
"loss": 0.7587,
"step": 1552
},
{
"epoch": 0.75,
"learning_rate": 6.384594294746447e-06,
"loss": 0.998,
"step": 1553
},
{
"epoch": 0.75,
"learning_rate": 6.361803993097926e-06,
"loss": 0.6944,
"step": 1554
},
{
"epoch": 0.75,
"learning_rate": 6.339046744706505e-06,
"loss": 0.7138,
"step": 1555
},
{
"epoch": 0.75,
"learning_rate": 6.316322604726184e-06,
"loss": 0.6594,
"step": 1556
},
{
"epoch": 0.75,
"learning_rate": 6.29363162823074e-06,
"loss": 0.8516,
"step": 1557
},
{
"epoch": 0.75,
"learning_rate": 6.270973870213563e-06,
"loss": 0.7726,
"step": 1558
},
{
"epoch": 0.75,
"learning_rate": 6.248349385587531e-06,
"loss": 0.8122,
"step": 1559
},
{
"epoch": 0.75,
"learning_rate": 6.225758229184902e-06,
"loss": 0.6941,
"step": 1560
},
{
"epoch": 0.75,
"learning_rate": 6.203200455757132e-06,
"loss": 0.7837,
"step": 1561
},
{
"epoch": 0.75,
"learning_rate": 6.180676119974805e-06,
"loss": 0.7474,
"step": 1562
},
{
"epoch": 0.75,
"learning_rate": 6.158185276427428e-06,
"loss": 0.7785,
"step": 1563
},
{
"epoch": 0.75,
"learning_rate": 6.135727979623376e-06,
"loss": 0.8185,
"step": 1564
},
{
"epoch": 0.75,
"learning_rate": 6.113304283989689e-06,
"loss": 0.8503,
"step": 1565
},
{
"epoch": 0.75,
"learning_rate": 6.0909142438719794e-06,
"loss": 0.9069,
"step": 1566
},
{
"epoch": 0.75,
"learning_rate": 6.068557913534312e-06,
"loss": 0.7969,
"step": 1567
},
{
"epoch": 0.75,
"learning_rate": 6.046235347159024e-06,
"loss": 0.8892,
"step": 1568
},
{
"epoch": 0.75,
"learning_rate": 6.023946598846651e-06,
"loss": 0.7931,
"step": 1569
},
{
"epoch": 0.75,
"learning_rate": 6.001691722615745e-06,
"loss": 0.8272,
"step": 1570
},
{
"epoch": 0.75,
"learning_rate": 5.9794707724027756e-06,
"loss": 0.9673,
"step": 1571
},
{
"epoch": 0.76,
"learning_rate": 5.9572838020619994e-06,
"loss": 0.9058,
"step": 1572
},
{
"epoch": 0.76,
"learning_rate": 5.9351308653652954e-06,
"loss": 0.8536,
"step": 1573
},
{
"epoch": 0.76,
"learning_rate": 5.913012016002091e-06,
"loss": 0.7722,
"step": 1574
},
{
"epoch": 0.76,
"learning_rate": 5.8909273075791705e-06,
"loss": 0.8903,
"step": 1575
},
{
"epoch": 0.76,
"learning_rate": 5.868876793620601e-06,
"loss": 0.6824,
"step": 1576
},
{
"epoch": 0.76,
"learning_rate": 5.8468605275675506e-06,
"loss": 0.8223,
"step": 1577
},
{
"epoch": 0.76,
"learning_rate": 5.824878562778209e-06,
"loss": 0.7742,
"step": 1578
},
{
"epoch": 0.76,
"learning_rate": 5.802930952527616e-06,
"loss": 0.7584,
"step": 1579
},
{
"epoch": 0.76,
"learning_rate": 5.7810177500075644e-06,
"loss": 0.7096,
"step": 1580
},
{
"epoch": 0.76,
"learning_rate": 5.759139008326442e-06,
"loss": 0.7286,
"step": 1581
},
{
"epoch": 0.76,
"learning_rate": 5.737294780509137e-06,
"loss": 0.7718,
"step": 1582
},
{
"epoch": 0.76,
"learning_rate": 5.715485119496868e-06,
"loss": 0.7881,
"step": 1583
},
{
"epoch": 0.76,
"learning_rate": 5.693710078147103e-06,
"loss": 0.8809,
"step": 1584
},
{
"epoch": 0.76,
"learning_rate": 5.671969709233385e-06,
"loss": 0.7704,
"step": 1585
},
{
"epoch": 0.76,
"learning_rate": 5.6502640654452305e-06,
"loss": 0.8623,
"step": 1586
},
{
"epoch": 0.76,
"learning_rate": 5.628593199388011e-06,
"loss": 0.7277,
"step": 1587
},
{
"epoch": 0.76,
"learning_rate": 5.606957163582789e-06,
"loss": 0.9185,
"step": 1588
},
{
"epoch": 0.76,
"learning_rate": 5.5853560104662385e-06,
"loss": 0.7629,
"step": 1589
},
{
"epoch": 0.76,
"learning_rate": 5.563789792390472e-06,
"loss": 0.8838,
"step": 1590
},
{
"epoch": 0.76,
"learning_rate": 5.542258561622937e-06,
"loss": 0.6666,
"step": 1591
},
{
"epoch": 0.76,
"learning_rate": 5.5207623703462995e-06,
"loss": 0.7692,
"step": 1592
},
{
"epoch": 0.77,
"learning_rate": 5.499301270658284e-06,
"loss": 0.9058,
"step": 1593
},
{
"epoch": 0.77,
"learning_rate": 5.4778753145715945e-06,
"loss": 0.7392,
"step": 1594
},
{
"epoch": 0.77,
"learning_rate": 5.456484554013732e-06,
"loss": 0.6149,
"step": 1595
},
{
"epoch": 0.77,
"learning_rate": 5.435129040826925e-06,
"loss": 0.7383,
"step": 1596
},
{
"epoch": 0.77,
"learning_rate": 5.413808826767959e-06,
"loss": 0.8324,
"step": 1597
},
{
"epoch": 0.77,
"learning_rate": 5.392523963508069e-06,
"loss": 0.7086,
"step": 1598
},
{
"epoch": 0.77,
"learning_rate": 5.371274502632835e-06,
"loss": 0.8273,
"step": 1599
},
{
"epoch": 0.77,
"learning_rate": 5.350060495642009e-06,
"loss": 0.8447,
"step": 1600
},
{
"epoch": 0.77,
"learning_rate": 5.328881993949442e-06,
"loss": 0.8047,
"step": 1601
},
{
"epoch": 0.77,
"learning_rate": 5.3077390488829186e-06,
"loss": 0.7535,
"step": 1602
},
{
"epoch": 0.77,
"learning_rate": 5.286631711684049e-06,
"loss": 0.7135,
"step": 1603
},
{
"epoch": 0.77,
"learning_rate": 5.2655600335081615e-06,
"loss": 0.7662,
"step": 1604
},
{
"epoch": 0.77,
"learning_rate": 5.2445240654241415e-06,
"loss": 0.7937,
"step": 1605
},
{
"epoch": 0.77,
"learning_rate": 5.223523858414346e-06,
"loss": 0.8672,
"step": 1606
},
{
"epoch": 0.77,
"learning_rate": 5.202559463374448e-06,
"loss": 0.8392,
"step": 1607
},
{
"epoch": 0.77,
"learning_rate": 5.181630931113331e-06,
"loss": 0.7644,
"step": 1608
},
{
"epoch": 0.77,
"learning_rate": 5.160738312352971e-06,
"loss": 0.7379,
"step": 1609
},
{
"epoch": 0.77,
"learning_rate": 5.139881657728287e-06,
"loss": 0.8887,
"step": 1610
},
{
"epoch": 0.77,
"learning_rate": 5.119061017787064e-06,
"loss": 0.8846,
"step": 1611
},
{
"epoch": 0.77,
"learning_rate": 5.098276442989774e-06,
"loss": 0.6188,
"step": 1612
},
{
"epoch": 0.77,
"learning_rate": 5.07752798370949e-06,
"loss": 0.8652,
"step": 1613
},
{
"epoch": 0.78,
"learning_rate": 5.056815690231769e-06,
"loss": 0.7992,
"step": 1614
},
{
"epoch": 0.78,
"learning_rate": 5.036139612754501e-06,
"loss": 0.7035,
"step": 1615
},
{
"epoch": 0.78,
"learning_rate": 5.01549980138782e-06,
"loss": 0.7311,
"step": 1616
},
{
"epoch": 0.78,
"learning_rate": 4.994896306153949e-06,
"loss": 0.8101,
"step": 1617
},
{
"epoch": 0.78,
"learning_rate": 4.9743291769871025e-06,
"loss": 0.8478,
"step": 1618
},
{
"epoch": 0.78,
"learning_rate": 4.953798463733372e-06,
"loss": 0.7407,
"step": 1619
},
{
"epoch": 0.78,
"learning_rate": 4.933304216150565e-06,
"loss": 0.8636,
"step": 1620
},
{
"epoch": 0.78,
"learning_rate": 4.912846483908142e-06,
"loss": 0.6478,
"step": 1621
},
{
"epoch": 0.78,
"learning_rate": 4.892425316587044e-06,
"loss": 0.8704,
"step": 1622
},
{
"epoch": 0.78,
"learning_rate": 4.872040763679593e-06,
"loss": 0.7613,
"step": 1623
},
{
"epoch": 0.78,
"learning_rate": 4.851692874589395e-06,
"loss": 0.8397,
"step": 1624
},
{
"epoch": 0.78,
"learning_rate": 4.831381698631172e-06,
"loss": 0.8374,
"step": 1625
},
{
"epoch": 0.78,
"learning_rate": 4.811107285030692e-06,
"loss": 0.6728,
"step": 1626
},
{
"epoch": 0.78,
"learning_rate": 4.790869682924602e-06,
"loss": 0.9003,
"step": 1627
},
{
"epoch": 0.78,
"learning_rate": 4.7706689413603615e-06,
"loss": 0.6864,
"step": 1628
},
{
"epoch": 0.78,
"learning_rate": 4.750505109296069e-06,
"loss": 0.8228,
"step": 1629
},
{
"epoch": 0.78,
"learning_rate": 4.73037823560039e-06,
"loss": 0.7335,
"step": 1630
},
{
"epoch": 0.78,
"learning_rate": 4.7102883690524e-06,
"loss": 0.7233,
"step": 1631
},
{
"epoch": 0.78,
"learning_rate": 4.690235558341509e-06,
"loss": 0.7314,
"step": 1632
},
{
"epoch": 0.78,
"learning_rate": 4.670219852067293e-06,
"loss": 0.8123,
"step": 1633
},
{
"epoch": 0.78,
"learning_rate": 4.650241298739422e-06,
"loss": 0.694,
"step": 1634
},
{
"epoch": 0.79,
"learning_rate": 4.630299946777508e-06,
"loss": 0.828,
"step": 1635
},
{
"epoch": 0.79,
"learning_rate": 4.610395844511017e-06,
"loss": 0.7576,
"step": 1636
},
{
"epoch": 0.79,
"learning_rate": 4.590529040179126e-06,
"loss": 0.7949,
"step": 1637
},
{
"epoch": 0.79,
"learning_rate": 4.570699581930627e-06,
"loss": 0.787,
"step": 1638
},
{
"epoch": 0.79,
"learning_rate": 4.55090751782379e-06,
"loss": 0.7649,
"step": 1639
},
{
"epoch": 0.79,
"learning_rate": 4.531152895826261e-06,
"loss": 0.7154,
"step": 1640
},
{
"epoch": 0.79,
"learning_rate": 4.511435763814951e-06,
"loss": 0.6292,
"step": 1641
},
{
"epoch": 0.79,
"learning_rate": 4.491756169575896e-06,
"loss": 0.7495,
"step": 1642
},
{
"epoch": 0.79,
"learning_rate": 4.472114160804175e-06,
"loss": 0.7981,
"step": 1643
},
{
"epoch": 0.79,
"learning_rate": 4.452509785103758e-06,
"loss": 0.8569,
"step": 1644
},
{
"epoch": 0.79,
"learning_rate": 4.4329430899874095e-06,
"loss": 0.6838,
"step": 1645
},
{
"epoch": 0.79,
"learning_rate": 4.413414122876587e-06,
"loss": 0.9124,
"step": 1646
},
{
"epoch": 0.79,
"learning_rate": 4.393922931101296e-06,
"loss": 0.7863,
"step": 1647
},
{
"epoch": 0.79,
"learning_rate": 4.374469561900001e-06,
"loss": 0.7922,
"step": 1648
},
{
"epoch": 0.79,
"learning_rate": 4.355054062419494e-06,
"loss": 0.8025,
"step": 1649
},
{
"epoch": 0.79,
"learning_rate": 4.335676479714783e-06,
"loss": 0.6002,
"step": 1650
},
{
"epoch": 0.79,
"learning_rate": 4.316336860748997e-06,
"loss": 0.8782,
"step": 1651
},
{
"epoch": 0.79,
"learning_rate": 4.297035252393236e-06,
"loss": 0.6764,
"step": 1652
},
{
"epoch": 0.79,
"learning_rate": 4.2777717014264985e-06,
"loss": 0.6844,
"step": 1653
},
{
"epoch": 0.79,
"learning_rate": 4.258546254535536e-06,
"loss": 0.7753,
"step": 1654
},
{
"epoch": 0.8,
"learning_rate": 4.239358958314747e-06,
"loss": 0.8182,
"step": 1655
},
{
"epoch": 0.8,
"learning_rate": 4.220209859266089e-06,
"loss": 0.8466,
"step": 1656
},
{
"epoch": 0.8,
"learning_rate": 4.201099003798918e-06,
"loss": 0.7496,
"step": 1657
},
{
"epoch": 0.8,
"learning_rate": 4.182026438229933e-06,
"loss": 0.8054,
"step": 1658
},
{
"epoch": 0.8,
"learning_rate": 4.162992208783008e-06,
"loss": 0.9287,
"step": 1659
},
{
"epoch": 0.8,
"learning_rate": 4.143996361589129e-06,
"loss": 0.9243,
"step": 1660
},
{
"epoch": 0.8,
"learning_rate": 4.125038942686239e-06,
"loss": 0.8774,
"step": 1661
},
{
"epoch": 0.8,
"learning_rate": 4.106119998019158e-06,
"loss": 0.787,
"step": 1662
},
{
"epoch": 0.8,
"learning_rate": 4.0872395734394635e-06,
"loss": 0.8279,
"step": 1663
},
{
"epoch": 0.8,
"learning_rate": 4.068397714705366e-06,
"loss": 0.7005,
"step": 1664
},
{
"epoch": 0.8,
"learning_rate": 4.0495944674816235e-06,
"loss": 0.6935,
"step": 1665
},
{
"epoch": 0.8,
"learning_rate": 4.030829877339404e-06,
"loss": 0.8361,
"step": 1666
},
{
"epoch": 0.8,
"learning_rate": 4.012103989756179e-06,
"loss": 0.7957,
"step": 1667
},
{
"epoch": 0.8,
"learning_rate": 3.99341685011565e-06,
"loss": 0.8517,
"step": 1668
},
{
"epoch": 0.8,
"learning_rate": 3.974768503707578e-06,
"loss": 0.864,
"step": 1669
},
{
"epoch": 0.8,
"learning_rate": 3.9561589957277325e-06,
"loss": 1.0038,
"step": 1670
},
{
"epoch": 0.8,
"learning_rate": 3.937588371277734e-06,
"loss": 0.7805,
"step": 1671
},
{
"epoch": 0.8,
"learning_rate": 3.9190566753649695e-06,
"loss": 0.8726,
"step": 1672
},
{
"epoch": 0.8,
"learning_rate": 3.900563952902494e-06,
"loss": 0.7562,
"step": 1673
},
{
"epoch": 0.8,
"learning_rate": 3.882110248708888e-06,
"loss": 0.745,
"step": 1674
},
{
"epoch": 0.8,
"learning_rate": 3.8636956075081865e-06,
"loss": 0.7297,
"step": 1675
},
{
"epoch": 0.81,
"learning_rate": 3.8453200739297395e-06,
"loss": 0.8068,
"step": 1676
},
{
"epoch": 0.81,
"learning_rate": 3.826983692508113e-06,
"loss": 0.8313,
"step": 1677
},
{
"epoch": 0.81,
"learning_rate": 3.8086865076830016e-06,
"loss": 0.7962,
"step": 1678
},
{
"epoch": 0.81,
"learning_rate": 3.7904285637990847e-06,
"loss": 0.7614,
"step": 1679
},
{
"epoch": 0.81,
"learning_rate": 3.772209905105959e-06,
"loss": 0.864,
"step": 1680
},
{
"epoch": 0.81,
"learning_rate": 3.7540305757579852e-06,
"loss": 0.7649,
"step": 1681
},
{
"epoch": 0.81,
"learning_rate": 3.735890619814231e-06,
"loss": 0.8309,
"step": 1682
},
{
"epoch": 0.81,
"learning_rate": 3.7177900812383196e-06,
"loss": 0.7396,
"step": 1683
},
{
"epoch": 0.81,
"learning_rate": 3.6997290038983604e-06,
"loss": 0.7018,
"step": 1684
},
{
"epoch": 0.81,
"learning_rate": 3.6817074315668054e-06,
"loss": 0.9805,
"step": 1685
},
{
"epoch": 0.81,
"learning_rate": 3.6637254079203865e-06,
"loss": 0.7778,
"step": 1686
},
{
"epoch": 0.81,
"learning_rate": 3.6457829765399644e-06,
"loss": 0.8163,
"step": 1687
},
{
"epoch": 0.81,
"learning_rate": 3.6278801809104614e-06,
"loss": 0.8582,
"step": 1688
},
{
"epoch": 0.81,
"learning_rate": 3.610017064420723e-06,
"loss": 0.8101,
"step": 1689
},
{
"epoch": 0.81,
"learning_rate": 3.5921936703634506e-06,
"loss": 0.8097,
"step": 1690
},
{
"epoch": 0.81,
"learning_rate": 3.5744100419350523e-06,
"loss": 0.7586,
"step": 1691
},
{
"epoch": 0.81,
"learning_rate": 3.556666222235581e-06,
"loss": 0.7634,
"step": 1692
},
{
"epoch": 0.81,
"learning_rate": 3.5389622542685963e-06,
"loss": 0.7933,
"step": 1693
},
{
"epoch": 0.81,
"learning_rate": 3.5212981809410708e-06,
"loss": 0.8243,
"step": 1694
},
{
"epoch": 0.81,
"learning_rate": 3.50367404506331e-06,
"loss": 0.8139,
"step": 1695
},
{
"epoch": 0.81,
"learning_rate": 3.486089889348805e-06,
"loss": 0.8511,
"step": 1696
},
{
"epoch": 0.82,
"learning_rate": 3.4685457564141676e-06,
"loss": 0.788,
"step": 1697
},
{
"epoch": 0.82,
"learning_rate": 3.4510416887790023e-06,
"loss": 0.8526,
"step": 1698
},
{
"epoch": 0.82,
"learning_rate": 3.4335777288658114e-06,
"loss": 0.8583,
"step": 1699
},
{
"epoch": 0.82,
"learning_rate": 3.416153918999903e-06,
"loss": 0.7428,
"step": 1700
},
{
"epoch": 0.82,
"learning_rate": 3.3987703014092623e-06,
"loss": 0.7699,
"step": 1701
},
{
"epoch": 0.82,
"learning_rate": 3.381426918224486e-06,
"loss": 0.799,
"step": 1702
},
{
"epoch": 0.82,
"learning_rate": 3.3641238114786433e-06,
"loss": 0.7842,
"step": 1703
},
{
"epoch": 0.82,
"learning_rate": 3.3468610231071906e-06,
"loss": 0.7975,
"step": 1704
},
{
"epoch": 0.82,
"learning_rate": 3.3296385949478814e-06,
"loss": 0.8276,
"step": 1705
},
{
"epoch": 0.82,
"learning_rate": 3.3124565687406385e-06,
"loss": 0.7976,
"step": 1706
},
{
"epoch": 0.82,
"learning_rate": 3.2953149861274827e-06,
"loss": 0.6723,
"step": 1707
},
{
"epoch": 0.82,
"learning_rate": 3.278213888652404e-06,
"loss": 0.7095,
"step": 1708
},
{
"epoch": 0.82,
"learning_rate": 3.261153317761272e-06,
"loss": 0.7894,
"step": 1709
},
{
"epoch": 0.82,
"learning_rate": 3.244133314801754e-06,
"loss": 0.796,
"step": 1710
},
{
"epoch": 0.82,
"learning_rate": 3.2271539210231738e-06,
"loss": 0.7484,
"step": 1711
},
{
"epoch": 0.82,
"learning_rate": 3.210215177576461e-06,
"loss": 0.8462,
"step": 1712
},
{
"epoch": 0.82,
"learning_rate": 3.193317125514006e-06,
"loss": 0.7991,
"step": 1713
},
{
"epoch": 0.82,
"learning_rate": 3.1764598057895844e-06,
"loss": 0.8161,
"step": 1714
},
{
"epoch": 0.82,
"learning_rate": 3.1596432592582647e-06,
"loss": 0.7618,
"step": 1715
},
{
"epoch": 0.82,
"learning_rate": 3.142867526676283e-06,
"loss": 0.9829,
"step": 1716
},
{
"epoch": 0.82,
"learning_rate": 3.1261326487009726e-06,
"loss": 0.8478,
"step": 1717
},
{
"epoch": 0.83,
"learning_rate": 3.1094386658906427e-06,
"loss": 0.6584,
"step": 1718
},
{
"epoch": 0.83,
"learning_rate": 3.0927856187044925e-06,
"loss": 0.7591,
"step": 1719
},
{
"epoch": 0.83,
"learning_rate": 3.076173547502519e-06,
"loss": 0.7973,
"step": 1720
},
{
"epoch": 0.83,
"learning_rate": 3.0596024925453927e-06,
"loss": 0.8468,
"step": 1721
},
{
"epoch": 0.83,
"learning_rate": 3.043072493994399e-06,
"loss": 0.7986,
"step": 1722
},
{
"epoch": 0.83,
"learning_rate": 3.0265835919112984e-06,
"loss": 0.7687,
"step": 1723
},
{
"epoch": 0.83,
"learning_rate": 3.010135826258276e-06,
"loss": 0.6432,
"step": 1724
},
{
"epoch": 0.83,
"learning_rate": 2.9937292368977956e-06,
"loss": 0.8014,
"step": 1725
},
{
"epoch": 0.83,
"learning_rate": 2.977363863592533e-06,
"loss": 0.7958,
"step": 1726
},
{
"epoch": 0.83,
"learning_rate": 2.9610397460052877e-06,
"loss": 0.8394,
"step": 1727
},
{
"epoch": 0.83,
"learning_rate": 2.944756923698853e-06,
"loss": 0.8421,
"step": 1728
},
{
"epoch": 0.83,
"learning_rate": 2.928515436135959e-06,
"loss": 0.8952,
"step": 1729
},
{
"epoch": 0.83,
"learning_rate": 2.91231532267914e-06,
"loss": 0.7446,
"step": 1730
},
{
"epoch": 0.83,
"learning_rate": 2.8961566225906622e-06,
"loss": 0.8212,
"step": 1731
},
{
"epoch": 0.83,
"learning_rate": 2.880039375032435e-06,
"loss": 0.7599,
"step": 1732
},
{
"epoch": 0.83,
"learning_rate": 2.863963619065886e-06,
"loss": 0.8142,
"step": 1733
},
{
"epoch": 0.83,
"learning_rate": 2.8479293936519025e-06,
"loss": 0.7751,
"step": 1734
},
{
"epoch": 0.83,
"learning_rate": 2.831936737650698e-06,
"loss": 0.8624,
"step": 1735
},
{
"epoch": 0.83,
"learning_rate": 2.8159856898217654e-06,
"loss": 0.8792,
"step": 1736
},
{
"epoch": 0.83,
"learning_rate": 2.80007628882373e-06,
"loss": 0.7768,
"step": 1737
},
{
"epoch": 0.83,
"learning_rate": 2.7842085732143066e-06,
"loss": 0.7565,
"step": 1738
},
{
"epoch": 0.84,
"learning_rate": 2.768382581450162e-06,
"loss": 0.8546,
"step": 1739
},
{
"epoch": 0.84,
"learning_rate": 2.7525983518868593e-06,
"loss": 0.8207,
"step": 1740
},
{
"epoch": 0.84,
"learning_rate": 2.7368559227787295e-06,
"loss": 0.8777,
"step": 1741
},
{
"epoch": 0.84,
"learning_rate": 2.7211553322788175e-06,
"loss": 0.7463,
"step": 1742
},
{
"epoch": 0.84,
"learning_rate": 2.70549661843875e-06,
"loss": 0.7858,
"step": 1743
},
{
"epoch": 0.84,
"learning_rate": 2.689879819208674e-06,
"loss": 0.9936,
"step": 1744
},
{
"epoch": 0.84,
"learning_rate": 2.674304972437152e-06,
"loss": 0.7667,
"step": 1745
},
{
"epoch": 0.84,
"learning_rate": 2.65877211587106e-06,
"loss": 0.777,
"step": 1746
},
{
"epoch": 0.84,
"learning_rate": 2.643281287155526e-06,
"loss": 0.7273,
"step": 1747
},
{
"epoch": 0.84,
"learning_rate": 2.627832523833802e-06,
"loss": 0.6368,
"step": 1748
},
{
"epoch": 0.84,
"learning_rate": 2.6124258633472078e-06,
"loss": 0.7229,
"step": 1749
},
{
"epoch": 0.84,
"learning_rate": 2.5970613430350076e-06,
"loss": 0.7988,
"step": 1750
},
{
"epoch": 0.84,
"learning_rate": 2.5817390001343536e-06,
"loss": 0.7748,
"step": 1751
},
{
"epoch": 0.84,
"learning_rate": 2.5664588717801575e-06,
"loss": 0.8473,
"step": 1752
},
{
"epoch": 0.84,
"learning_rate": 2.5512209950050304e-06,
"loss": 0.9118,
"step": 1753
},
{
"epoch": 0.84,
"learning_rate": 2.5360254067391934e-06,
"loss": 0.8104,
"step": 1754
},
{
"epoch": 0.84,
"learning_rate": 2.5208721438103557e-06,
"loss": 0.6764,
"step": 1755
},
{
"epoch": 0.84,
"learning_rate": 2.5057612429436697e-06,
"loss": 0.7736,
"step": 1756
},
{
"epoch": 0.84,
"learning_rate": 2.490692740761609e-06,
"loss": 0.8584,
"step": 1757
},
{
"epoch": 0.84,
"learning_rate": 2.4756666737838832e-06,
"loss": 0.7709,
"step": 1758
},
{
"epoch": 0.84,
"learning_rate": 2.460683078427377e-06,
"loss": 0.8495,
"step": 1759
},
{
"epoch": 0.85,
"learning_rate": 2.445741991006021e-06,
"loss": 0.6408,
"step": 1760
},
{
"epoch": 0.85,
"learning_rate": 2.430843447730742e-06,
"loss": 0.7008,
"step": 1761
},
{
"epoch": 0.85,
"learning_rate": 2.4159874847093458e-06,
"loss": 0.7162,
"step": 1762
},
{
"epoch": 0.85,
"learning_rate": 2.4011741379464404e-06,
"loss": 0.7658,
"step": 1763
},
{
"epoch": 0.85,
"learning_rate": 2.3864034433433635e-06,
"loss": 0.9827,
"step": 1764
},
{
"epoch": 0.85,
"learning_rate": 2.3716754366980622e-06,
"loss": 0.7374,
"step": 1765
},
{
"epoch": 0.85,
"learning_rate": 2.3569901537050476e-06,
"loss": 0.7533,
"step": 1766
},
{
"epoch": 0.85,
"learning_rate": 2.3423476299552726e-06,
"loss": 0.8775,
"step": 1767
},
{
"epoch": 0.85,
"learning_rate": 2.3277479009360547e-06,
"loss": 0.7563,
"step": 1768
},
{
"epoch": 0.85,
"learning_rate": 2.3131910020310144e-06,
"loss": 0.6648,
"step": 1769
},
{
"epoch": 0.85,
"learning_rate": 2.2986769685199508e-06,
"loss": 0.719,
"step": 1770
},
{
"epoch": 0.85,
"learning_rate": 2.2842058355787875e-06,
"loss": 0.8639,
"step": 1771
},
{
"epoch": 0.85,
"learning_rate": 2.269777638279471e-06,
"loss": 0.8373,
"step": 1772
},
{
"epoch": 0.85,
"learning_rate": 2.2553924115898828e-06,
"loss": 0.8113,
"step": 1773
},
{
"epoch": 0.85,
"learning_rate": 2.241050190373777e-06,
"loss": 0.7905,
"step": 1774
},
{
"epoch": 0.85,
"learning_rate": 2.2267510093906665e-06,
"loss": 0.8163,
"step": 1775
},
{
"epoch": 0.85,
"learning_rate": 2.2124949032957634e-06,
"loss": 0.8049,
"step": 1776
},
{
"epoch": 0.85,
"learning_rate": 2.198281906639876e-06,
"loss": 0.8953,
"step": 1777
},
{
"epoch": 0.85,
"learning_rate": 2.1841120538693315e-06,
"loss": 0.8397,
"step": 1778
},
{
"epoch": 0.85,
"learning_rate": 2.169985379325912e-06,
"loss": 0.8456,
"step": 1779
},
{
"epoch": 0.86,
"learning_rate": 2.1559019172467276e-06,
"loss": 1.007,
"step": 1780
},
{
"epoch": 0.86,
"learning_rate": 2.141861701764185e-06,
"loss": 0.7179,
"step": 1781
},
{
"epoch": 0.86,
"learning_rate": 2.1278647669058584e-06,
"loss": 0.7166,
"step": 1782
},
{
"epoch": 0.86,
"learning_rate": 2.113911146594445e-06,
"loss": 0.8631,
"step": 1783
},
{
"epoch": 0.86,
"learning_rate": 2.1000008746476543e-06,
"loss": 0.7627,
"step": 1784
},
{
"epoch": 0.86,
"learning_rate": 2.086133984778136e-06,
"loss": 0.7772,
"step": 1785
},
{
"epoch": 0.86,
"learning_rate": 2.072310510593416e-06,
"loss": 0.79,
"step": 1786
},
{
"epoch": 0.86,
"learning_rate": 2.0585304855957778e-06,
"loss": 0.9189,
"step": 1787
},
{
"epoch": 0.86,
"learning_rate": 2.0447939431822193e-06,
"loss": 0.8636,
"step": 1788
},
{
"epoch": 0.86,
"learning_rate": 2.0311009166443416e-06,
"loss": 0.8295,
"step": 1789
},
{
"epoch": 0.86,
"learning_rate": 2.0174514391682964e-06,
"loss": 0.8834,
"step": 1790
},
{
"epoch": 0.86,
"learning_rate": 2.0038455438346725e-06,
"loss": 1.0268,
"step": 1791
},
{
"epoch": 0.86,
"learning_rate": 1.990283263618451e-06,
"loss": 0.9491,
"step": 1792
},
{
"epoch": 0.86,
"learning_rate": 1.9767646313888965e-06,
"loss": 0.8521,
"step": 1793
},
{
"epoch": 0.86,
"learning_rate": 1.9632896799095015e-06,
"loss": 0.8468,
"step": 1794
},
{
"epoch": 0.86,
"learning_rate": 1.9498584418378753e-06,
"loss": 0.769,
"step": 1795
},
{
"epoch": 0.86,
"learning_rate": 1.936470949725706e-06,
"loss": 0.863,
"step": 1796
},
{
"epoch": 0.86,
"learning_rate": 1.9231272360186427e-06,
"loss": 0.8091,
"step": 1797
},
{
"epoch": 0.86,
"learning_rate": 1.9098273330562488e-06,
"loss": 0.8035,
"step": 1798
},
{
"epoch": 0.86,
"learning_rate": 1.8965712730718943e-06,
"loss": 0.6403,
"step": 1799
},
{
"epoch": 0.86,
"learning_rate": 1.8833590881927e-06,
"loss": 0.7157,
"step": 1800
},
{
"epoch": 0.87,
"learning_rate": 1.8701908104394562e-06,
"loss": 0.8206,
"step": 1801
},
{
"epoch": 0.87,
"learning_rate": 1.8570664717265251e-06,
"loss": 0.5984,
"step": 1802
},
{
"epoch": 0.87,
"learning_rate": 1.8439861038618034e-06,
"loss": 0.8247,
"step": 1803
},
{
"epoch": 0.87,
"learning_rate": 1.8309497385465992e-06,
"loss": 0.7316,
"step": 1804
},
{
"epoch": 0.87,
"learning_rate": 1.8179574073755812e-06,
"loss": 0.8623,
"step": 1805
},
{
"epoch": 0.87,
"learning_rate": 1.805009141836711e-06,
"loss": 0.7296,
"step": 1806
},
{
"epoch": 0.87,
"learning_rate": 1.7921049733111329e-06,
"loss": 0.7896,
"step": 1807
},
{
"epoch": 0.87,
"learning_rate": 1.779244933073141e-06,
"loss": 0.8222,
"step": 1808
},
{
"epoch": 0.87,
"learning_rate": 1.7664290522900663e-06,
"loss": 0.8393,
"step": 1809
},
{
"epoch": 0.87,
"learning_rate": 1.753657362022212e-06,
"loss": 0.7363,
"step": 1810
},
{
"epoch": 0.87,
"learning_rate": 1.7409298932228002e-06,
"loss": 0.8046,
"step": 1811
},
{
"epoch": 0.87,
"learning_rate": 1.7282466767378592e-06,
"loss": 0.7361,
"step": 1812
},
{
"epoch": 0.87,
"learning_rate": 1.7156077433061825e-06,
"loss": 0.8613,
"step": 1813
},
{
"epoch": 0.87,
"learning_rate": 1.7030131235592318e-06,
"loss": 0.7886,
"step": 1814
},
{
"epoch": 0.87,
"learning_rate": 1.6904628480210749e-06,
"loss": 0.7348,
"step": 1815
},
{
"epoch": 0.87,
"learning_rate": 1.6779569471083078e-06,
"loss": 0.824,
"step": 1816
},
{
"epoch": 0.87,
"learning_rate": 1.665495451129977e-06,
"loss": 0.7885,
"step": 1817
},
{
"epoch": 0.87,
"learning_rate": 1.653078390287517e-06,
"loss": 0.8066,
"step": 1818
},
{
"epoch": 0.87,
"learning_rate": 1.6407057946746597e-06,
"loss": 0.8185,
"step": 1819
},
{
"epoch": 0.87,
"learning_rate": 1.6283776942773878e-06,
"loss": 0.8738,
"step": 1820
},
{
"epoch": 0.87,
"learning_rate": 1.6160941189738299e-06,
"loss": 0.8296,
"step": 1821
},
{
"epoch": 0.88,
"learning_rate": 1.6038550985342126e-06,
"loss": 0.8503,
"step": 1822
},
{
"epoch": 0.88,
"learning_rate": 1.5916606626207843e-06,
"loss": 0.8268,
"step": 1823
},
{
"epoch": 0.88,
"learning_rate": 1.5795108407877258e-06,
"loss": 0.7455,
"step": 1824
},
{
"epoch": 0.88,
"learning_rate": 1.5674056624811096e-06,
"loss": 0.8188,
"step": 1825
},
{
"epoch": 0.88,
"learning_rate": 1.5553451570387968e-06,
"loss": 0.7861,
"step": 1826
},
{
"epoch": 0.88,
"learning_rate": 1.5433293536903837e-06,
"loss": 0.7601,
"step": 1827
},
{
"epoch": 0.88,
"learning_rate": 1.531358281557136e-06,
"loss": 0.7836,
"step": 1828
},
{
"epoch": 0.88,
"learning_rate": 1.5194319696518944e-06,
"loss": 0.8343,
"step": 1829
},
{
"epoch": 0.88,
"learning_rate": 1.5075504468790358e-06,
"loss": 0.7926,
"step": 1830
},
{
"epoch": 0.88,
"learning_rate": 1.495713742034377e-06,
"loss": 0.7364,
"step": 1831
},
{
"epoch": 0.88,
"learning_rate": 1.4839218838051128e-06,
"loss": 0.7906,
"step": 1832
},
{
"epoch": 0.88,
"learning_rate": 1.4721749007697605e-06,
"loss": 0.8372,
"step": 1833
},
{
"epoch": 0.88,
"learning_rate": 1.4604728213980646e-06,
"loss": 0.8345,
"step": 1834
},
{
"epoch": 0.88,
"learning_rate": 1.448815674050954e-06,
"loss": 0.763,
"step": 1835
},
{
"epoch": 0.88,
"learning_rate": 1.4372034869804562e-06,
"loss": 0.7455,
"step": 1836
},
{
"epoch": 0.88,
"learning_rate": 1.4256362883296304e-06,
"loss": 0.7792,
"step": 1837
},
{
"epoch": 0.88,
"learning_rate": 1.4141141061325093e-06,
"loss": 0.7958,
"step": 1838
},
{
"epoch": 0.88,
"learning_rate": 1.4026369683140194e-06,
"loss": 0.7817,
"step": 1839
},
{
"epoch": 0.88,
"learning_rate": 1.3912049026899222e-06,
"loss": 0.9599,
"step": 1840
},
{
"epoch": 0.88,
"learning_rate": 1.3798179369667386e-06,
"loss": 0.7668,
"step": 1841
},
{
"epoch": 0.88,
"learning_rate": 1.3684760987416955e-06,
"loss": 0.7051,
"step": 1842
},
{
"epoch": 0.89,
"learning_rate": 1.3571794155026385e-06,
"loss": 0.6687,
"step": 1843
},
{
"epoch": 0.89,
"learning_rate": 1.3459279146279825e-06,
"loss": 0.8387,
"step": 1844
},
{
"epoch": 0.89,
"learning_rate": 1.3347216233866389e-06,
"loss": 0.8472,
"step": 1845
},
{
"epoch": 0.89,
"learning_rate": 1.3235605689379495e-06,
"loss": 0.7332,
"step": 1846
},
{
"epoch": 0.89,
"learning_rate": 1.3124447783316186e-06,
"loss": 0.8496,
"step": 1847
},
{
"epoch": 0.89,
"learning_rate": 1.3013742785076588e-06,
"loss": 0.7102,
"step": 1848
},
{
"epoch": 0.89,
"learning_rate": 1.2903490962963016e-06,
"loss": 0.7193,
"step": 1849
},
{
"epoch": 0.89,
"learning_rate": 1.2793692584179661e-06,
"loss": 0.9132,
"step": 1850
},
{
"epoch": 0.89,
"learning_rate": 1.2684347914831551e-06,
"loss": 0.7766,
"step": 1851
},
{
"epoch": 0.89,
"learning_rate": 1.2575457219924348e-06,
"loss": 0.8676,
"step": 1852
},
{
"epoch": 0.89,
"learning_rate": 1.2467020763363258e-06,
"loss": 0.8197,
"step": 1853
},
{
"epoch": 0.89,
"learning_rate": 1.2359038807952705e-06,
"loss": 0.7333,
"step": 1854
},
{
"epoch": 0.89,
"learning_rate": 1.2251511615395618e-06,
"loss": 0.7514,
"step": 1855
},
{
"epoch": 0.89,
"learning_rate": 1.2144439446292666e-06,
"loss": 0.7764,
"step": 1856
},
{
"epoch": 0.89,
"learning_rate": 1.2037822560141876e-06,
"loss": 0.6432,
"step": 1857
},
{
"epoch": 0.89,
"learning_rate": 1.1931661215337776e-06,
"loss": 0.6839,
"step": 1858
},
{
"epoch": 0.89,
"learning_rate": 1.1825955669170797e-06,
"loss": 0.7978,
"step": 1859
},
{
"epoch": 0.89,
"learning_rate": 1.1720706177826858e-06,
"loss": 0.7621,
"step": 1860
},
{
"epoch": 0.89,
"learning_rate": 1.1615912996386424e-06,
"loss": 0.7235,
"step": 1861
},
{
"epoch": 0.89,
"learning_rate": 1.1511576378824208e-06,
"loss": 0.7554,
"step": 1862
},
{
"epoch": 0.89,
"learning_rate": 1.1407696578008287e-06,
"loss": 0.7399,
"step": 1863
},
{
"epoch": 0.9,
"learning_rate": 1.1304273845699677e-06,
"loss": 0.7374,
"step": 1864
},
{
"epoch": 0.9,
"learning_rate": 1.1201308432551628e-06,
"loss": 0.7701,
"step": 1865
},
{
"epoch": 0.9,
"learning_rate": 1.1098800588108994e-06,
"loss": 0.8395,
"step": 1866
},
{
"epoch": 0.9,
"learning_rate": 1.0996750560807823e-06,
"loss": 0.7723,
"step": 1867
},
{
"epoch": 0.9,
"learning_rate": 1.0895158597974431e-06,
"loss": 0.6817,
"step": 1868
},
{
"epoch": 0.9,
"learning_rate": 1.0794024945825043e-06,
"loss": 0.8405,
"step": 1869
},
{
"epoch": 0.9,
"learning_rate": 1.0693349849465173e-06,
"loss": 0.6523,
"step": 1870
},
{
"epoch": 0.9,
"learning_rate": 1.0593133552888935e-06,
"loss": 1.0328,
"step": 1871
},
{
"epoch": 0.9,
"learning_rate": 1.0493376298978575e-06,
"loss": 0.904,
"step": 1872
},
{
"epoch": 0.9,
"learning_rate": 1.039407832950372e-06,
"loss": 0.8709,
"step": 1873
},
{
"epoch": 0.9,
"learning_rate": 1.0295239885120912e-06,
"loss": 0.7673,
"step": 1874
},
{
"epoch": 0.9,
"learning_rate": 1.0196861205373065e-06,
"loss": 0.8498,
"step": 1875
},
{
"epoch": 0.9,
"learning_rate": 1.0098942528688726e-06,
"loss": 0.7199,
"step": 1876
},
{
"epoch": 0.9,
"learning_rate": 1.0001484092381642e-06,
"loss": 0.9574,
"step": 1877
},
{
"epoch": 0.9,
"learning_rate": 9.904486132650092e-07,
"loss": 0.7808,
"step": 1878
},
{
"epoch": 0.9,
"learning_rate": 9.807948884576435e-07,
"loss": 0.8434,
"step": 1879
},
{
"epoch": 0.9,
"learning_rate": 9.71187258212638e-07,
"loss": 0.8126,
"step": 1880
},
{
"epoch": 0.9,
"learning_rate": 9.616257458148448e-07,
"loss": 0.7238,
"step": 1881
},
{
"epoch": 0.9,
"learning_rate": 9.521103744373627e-07,
"loss": 0.6984,
"step": 1882
},
{
"epoch": 0.9,
"learning_rate": 9.42641167141447e-07,
"loss": 0.7997,
"step": 1883
},
{
"epoch": 0.91,
"learning_rate": 9.332181468764823e-07,
"loss": 0.9143,
"step": 1884
},
{
"epoch": 0.91,
"learning_rate": 9.238413364799092e-07,
"loss": 0.8173,
"step": 1885
},
{
"epoch": 0.91,
"learning_rate": 9.145107586771718e-07,
"loss": 0.8494,
"step": 1886
},
{
"epoch": 0.91,
"learning_rate": 9.052264360816788e-07,
"loss": 0.844,
"step": 1887
},
{
"epoch": 0.91,
"learning_rate": 8.959883911947199e-07,
"loss": 0.853,
"step": 1888
},
{
"epoch": 0.91,
"learning_rate": 8.867966464054411e-07,
"loss": 0.8262,
"step": 1889
},
{
"epoch": 0.91,
"learning_rate": 8.776512239907675e-07,
"loss": 0.7729,
"step": 1890
},
{
"epoch": 0.91,
"learning_rate": 8.685521461153579e-07,
"loss": 0.8433,
"step": 1891
},
{
"epoch": 0.91,
"learning_rate": 8.594994348315566e-07,
"loss": 0.8724,
"step": 1892
},
{
"epoch": 0.91,
"learning_rate": 8.504931120793314e-07,
"loss": 0.7585,
"step": 1893
},
{
"epoch": 0.91,
"learning_rate": 8.415331996862263e-07,
"loss": 0.6362,
"step": 1894
},
{
"epoch": 0.91,
"learning_rate": 8.326197193673002e-07,
"loss": 0.8052,
"step": 1895
},
{
"epoch": 0.91,
"learning_rate": 8.237526927250905e-07,
"loss": 0.6686,
"step": 1896
},
{
"epoch": 0.91,
"learning_rate": 8.149321412495403e-07,
"loss": 0.7978,
"step": 1897
},
{
"epoch": 0.91,
"learning_rate": 8.06158086317963e-07,
"loss": 0.6994,
"step": 1898
},
{
"epoch": 0.91,
"learning_rate": 7.974305491949774e-07,
"loss": 0.7491,
"step": 1899
},
{
"epoch": 0.91,
"learning_rate": 7.887495510324727e-07,
"loss": 0.7033,
"step": 1900
},
{
"epoch": 0.91,
"learning_rate": 7.801151128695328e-07,
"loss": 0.6809,
"step": 1901
},
{
"epoch": 0.91,
"learning_rate": 7.715272556324182e-07,
"loss": 0.618,
"step": 1902
},
{
"epoch": 0.91,
"learning_rate": 7.62986000134478e-07,
"loss": 0.8353,
"step": 1903
},
{
"epoch": 0.91,
"learning_rate": 7.544913670761312e-07,
"loss": 0.7895,
"step": 1904
},
{
"epoch": 0.92,
"learning_rate": 7.460433770448006e-07,
"loss": 0.6966,
"step": 1905
},
{
"epoch": 0.92,
"learning_rate": 7.376420505148596e-07,
"loss": 0.7782,
"step": 1906
},
{
"epoch": 0.92,
"learning_rate": 7.292874078475987e-07,
"loss": 0.7009,
"step": 1907
},
{
"epoch": 0.92,
"learning_rate": 7.209794692911587e-07,
"loss": 0.873,
"step": 1908
},
{
"epoch": 0.92,
"learning_rate": 7.127182549804934e-07,
"loss": 0.8967,
"step": 1909
},
{
"epoch": 0.92,
"learning_rate": 7.045037849373138e-07,
"loss": 0.7229,
"step": 1910
},
{
"epoch": 0.92,
"learning_rate": 6.96336079070048e-07,
"loss": 0.7422,
"step": 1911
},
{
"epoch": 0.92,
"learning_rate": 6.882151571737816e-07,
"loss": 0.9238,
"step": 1912
},
{
"epoch": 0.92,
"learning_rate": 6.801410389302132e-07,
"loss": 0.7907,
"step": 1913
},
{
"epoch": 0.92,
"learning_rate": 6.721137439076186e-07,
"loss": 0.8472,
"step": 1914
},
{
"epoch": 0.92,
"learning_rate": 6.641332915607845e-07,
"loss": 0.8317,
"step": 1915
},
{
"epoch": 0.92,
"learning_rate": 6.561997012309796e-07,
"loss": 0.6712,
"step": 1916
},
{
"epoch": 0.92,
"learning_rate": 6.483129921458875e-07,
"loss": 0.7183,
"step": 1917
},
{
"epoch": 0.92,
"learning_rate": 6.404731834195788e-07,
"loss": 0.8612,
"step": 1918
},
{
"epoch": 0.92,
"learning_rate": 6.326802940524591e-07,
"loss": 0.7981,
"step": 1919
},
{
"epoch": 0.92,
"learning_rate": 6.249343429312161e-07,
"loss": 0.7665,
"step": 1920
},
{
"epoch": 0.92,
"learning_rate": 6.172353488287797e-07,
"loss": 0.824,
"step": 1921
},
{
"epoch": 0.92,
"learning_rate": 6.09583330404282e-07,
"loss": 0.6806,
"step": 1922
},
{
"epoch": 0.92,
"learning_rate": 6.019783062029927e-07,
"loss": 0.6911,
"step": 1923
},
{
"epoch": 0.92,
"learning_rate": 5.944202946563016e-07,
"loss": 0.7806,
"step": 1924
},
{
"epoch": 0.92,
"learning_rate": 5.869093140816473e-07,
"loss": 0.9656,
"step": 1925
},
{
"epoch": 0.93,
"learning_rate": 5.794453826824998e-07,
"loss": 0.7291,
"step": 1926
},
{
"epoch": 0.93,
"learning_rate": 5.720285185482865e-07,
"loss": 0.8032,
"step": 1927
},
{
"epoch": 0.93,
"learning_rate": 5.646587396543691e-07,
"loss": 0.7787,
"step": 1928
},
{
"epoch": 0.93,
"learning_rate": 5.573360638619996e-07,
"loss": 0.6745,
"step": 1929
},
{
"epoch": 0.93,
"learning_rate": 5.50060508918262e-07,
"loss": 0.9704,
"step": 1930
},
{
"epoch": 0.93,
"learning_rate": 5.428320924560515e-07,
"loss": 0.8058,
"step": 1931
},
{
"epoch": 0.93,
"learning_rate": 5.356508319940102e-07,
"loss": 0.7408,
"step": 1932
},
{
"epoch": 0.93,
"learning_rate": 5.285167449364915e-07,
"loss": 0.7023,
"step": 1933
},
{
"epoch": 0.93,
"learning_rate": 5.214298485735314e-07,
"loss": 0.7662,
"step": 1934
},
{
"epoch": 0.93,
"learning_rate": 5.143901600807844e-07,
"loss": 0.8133,
"step": 1935
},
{
"epoch": 0.93,
"learning_rate": 5.073976965195027e-07,
"loss": 0.7792,
"step": 1936
},
{
"epoch": 0.93,
"learning_rate": 5.004524748364748e-07,
"loss": 0.763,
"step": 1937
},
{
"epoch": 0.93,
"learning_rate": 4.935545118640028e-07,
"loss": 0.7631,
"step": 1938
},
{
"epoch": 0.93,
"learning_rate": 4.867038243198519e-07,
"loss": 0.8214,
"step": 1939
},
{
"epoch": 0.93,
"learning_rate": 4.799004288072073e-07,
"loss": 0.9035,
"step": 1940
},
{
"epoch": 0.93,
"learning_rate": 4.731443418146464e-07,
"loss": 0.8213,
"step": 1941
},
{
"epoch": 0.93,
"learning_rate": 4.66435579716078e-07,
"loss": 0.7004,
"step": 1942
},
{
"epoch": 0.93,
"learning_rate": 4.597741587707294e-07,
"loss": 0.77,
"step": 1943
},
{
"epoch": 0.93,
"learning_rate": 4.531600951230841e-07,
"loss": 0.8242,
"step": 1944
},
{
"epoch": 0.93,
"learning_rate": 4.4659340480285085e-07,
"loss": 0.7834,
"step": 1945
},
{
"epoch": 0.93,
"learning_rate": 4.4007410372493453e-07,
"loss": 0.6946,
"step": 1946
},
{
"epoch": 0.94,
"learning_rate": 4.336022076893742e-07,
"loss": 0.8164,
"step": 1947
},
{
"epoch": 0.94,
"learning_rate": 4.27177732381332e-07,
"loss": 0.9032,
"step": 1948
},
{
"epoch": 0.94,
"learning_rate": 4.208006933710329e-07,
"loss": 0.956,
"step": 1949
},
{
"epoch": 0.94,
"learning_rate": 4.144711061137452e-07,
"loss": 0.7393,
"step": 1950
},
{
"epoch": 0.94,
"learning_rate": 4.0818898594972455e-07,
"loss": 0.7495,
"step": 1951
},
{
"epoch": 0.94,
"learning_rate": 4.019543481041921e-07,
"loss": 0.8178,
"step": 1952
},
{
"epoch": 0.94,
"learning_rate": 3.9576720768729205e-07,
"loss": 0.7956,
"step": 1953
},
{
"epoch": 0.94,
"learning_rate": 3.8962757969405184e-07,
"loss": 0.7989,
"step": 1954
},
{
"epoch": 0.94,
"learning_rate": 3.8353547900435107e-07,
"loss": 0.8337,
"step": 1955
},
{
"epoch": 0.94,
"learning_rate": 3.7749092038288137e-07,
"loss": 0.8836,
"step": 1956
},
{
"epoch": 0.94,
"learning_rate": 3.714939184791133e-07,
"loss": 0.7453,
"step": 1957
},
{
"epoch": 0.94,
"learning_rate": 3.655444878272607e-07,
"loss": 0.7661,
"step": 1958
},
{
"epoch": 0.94,
"learning_rate": 3.5964264284624294e-07,
"loss": 0.7837,
"step": 1959
},
{
"epoch": 0.94,
"learning_rate": 3.537883978396517e-07,
"loss": 0.7851,
"step": 1960
},
{
"epoch": 0.94,
"learning_rate": 3.4798176699572193e-07,
"loss": 0.6859,
"step": 1961
},
{
"epoch": 0.94,
"learning_rate": 3.4222276438728106e-07,
"loss": 0.7565,
"step": 1962
},
{
"epoch": 0.94,
"learning_rate": 3.365114039717354e-07,
"loss": 0.8842,
"step": 1963
},
{
"epoch": 0.94,
"learning_rate": 3.308476995910237e-07,
"loss": 0.761,
"step": 1964
},
{
"epoch": 0.94,
"learning_rate": 3.252316649715814e-07,
"loss": 0.8768,
"step": 1965
},
{
"epoch": 0.94,
"learning_rate": 3.19663313724321e-07,
"loss": 0.9163,
"step": 1966
},
{
"epoch": 0.94,
"learning_rate": 3.141426593445829e-07,
"loss": 0.7217,
"step": 1967
},
{
"epoch": 0.95,
"learning_rate": 3.0866971521211764e-07,
"loss": 0.7374,
"step": 1968
},
{
"epoch": 0.95,
"learning_rate": 3.0324449459104175e-07,
"loss": 0.6896,
"step": 1969
},
{
"epoch": 0.95,
"learning_rate": 2.978670106298087e-07,
"loss": 0.8954,
"step": 1970
},
{
"epoch": 0.95,
"learning_rate": 2.925372763611822e-07,
"loss": 0.7606,
"step": 1971
},
{
"epoch": 0.95,
"learning_rate": 2.872553047021964e-07,
"loss": 0.7081,
"step": 1972
},
{
"epoch": 0.95,
"learning_rate": 2.8202110845413357e-07,
"loss": 0.78,
"step": 1973
},
{
"epoch": 0.95,
"learning_rate": 2.7683470030248407e-07,
"loss": 0.7278,
"step": 1974
},
{
"epoch": 0.95,
"learning_rate": 2.7169609281692653e-07,
"loss": 0.7887,
"step": 1975
},
{
"epoch": 0.95,
"learning_rate": 2.6660529845128123e-07,
"loss": 0.9141,
"step": 1976
},
{
"epoch": 0.95,
"learning_rate": 2.615623295434988e-07,
"loss": 0.7856,
"step": 1977
},
{
"epoch": 0.95,
"learning_rate": 2.5656719831561594e-07,
"loss": 0.7657,
"step": 1978
},
{
"epoch": 0.95,
"learning_rate": 2.5161991687372876e-07,
"loss": 0.7214,
"step": 1979
},
{
"epoch": 0.95,
"learning_rate": 2.467204972079751e-07,
"loss": 0.8158,
"step": 1980
},
{
"epoch": 0.95,
"learning_rate": 2.418689511924854e-07,
"loss": 0.8239,
"step": 1981
},
{
"epoch": 0.95,
"learning_rate": 2.3706529058536986e-07,
"loss": 0.7365,
"step": 1982
},
{
"epoch": 0.95,
"learning_rate": 2.3230952702868458e-07,
"loss": 0.8375,
"step": 1983
},
{
"epoch": 0.95,
"learning_rate": 2.276016720484009e-07,
"loss": 0.7789,
"step": 1984
},
{
"epoch": 0.95,
"learning_rate": 2.2294173705438072e-07,
"loss": 0.8496,
"step": 1985
},
{
"epoch": 0.95,
"learning_rate": 2.1832973334035225e-07,
"loss": 0.8173,
"step": 1986
},
{
"epoch": 0.95,
"learning_rate": 2.1376567208386988e-07,
"loss": 0.9581,
"step": 1987
},
{
"epoch": 0.95,
"learning_rate": 2.0924956434630328e-07,
"loss": 0.7356,
"step": 1988
},
{
"epoch": 0.96,
"learning_rate": 2.0478142107279942e-07,
"loss": 0.8488,
"step": 1989
},
{
"epoch": 0.96,
"learning_rate": 2.0036125309226274e-07,
"loss": 0.8433,
"step": 1990
},
{
"epoch": 0.96,
"learning_rate": 1.9598907111731958e-07,
"loss": 0.8994,
"step": 1991
},
{
"epoch": 0.96,
"learning_rate": 1.9166488574430487e-07,
"loss": 0.8825,
"step": 1992
},
{
"epoch": 0.96,
"learning_rate": 1.8738870745322656e-07,
"loss": 0.7001,
"step": 1993
},
{
"epoch": 0.96,
"learning_rate": 1.831605466077413e-07,
"loss": 0.8457,
"step": 1994
},
{
"epoch": 0.96,
"learning_rate": 1.7898041345513872e-07,
"loss": 0.7381,
"step": 1995
},
{
"epoch": 0.96,
"learning_rate": 1.7484831812630388e-07,
"loss": 0.8493,
"step": 1996
},
{
"epoch": 0.96,
"learning_rate": 1.7076427063569712e-07,
"loss": 0.771,
"step": 1997
},
{
"epoch": 0.96,
"learning_rate": 1.6672828088133862e-07,
"loss": 0.816,
"step": 1998
},
{
"epoch": 0.96,
"learning_rate": 1.6274035864476846e-07,
"loss": 0.6762,
"step": 1999
},
{
"epoch": 0.96,
"learning_rate": 1.5880051359103532e-07,
"loss": 0.8481,
"step": 2000
},
{
"epoch": 0.96,
"learning_rate": 1.5490875526866788e-07,
"loss": 0.7148,
"step": 2001
},
{
"epoch": 0.96,
"learning_rate": 1.5106509310965466e-07,
"loss": 0.5975,
"step": 2002
},
{
"epoch": 0.96,
"learning_rate": 1.4726953642941522e-07,
"loss": 0.7898,
"step": 2003
},
{
"epoch": 0.96,
"learning_rate": 1.4352209442678677e-07,
"loss": 0.905,
"step": 2004
},
{
"epoch": 0.96,
"learning_rate": 1.398227761839954e-07,
"loss": 0.6776,
"step": 2005
},
{
"epoch": 0.96,
"learning_rate": 1.3617159066662944e-07,
"loss": 0.8488,
"step": 2006
},
{
"epoch": 0.96,
"learning_rate": 1.3256854672363263e-07,
"loss": 0.6709,
"step": 2007
},
{
"epoch": 0.96,
"learning_rate": 1.2901365308726878e-07,
"loss": 0.7547,
"step": 2008
},
{
"epoch": 0.97,
"learning_rate": 1.2550691837310614e-07,
"loss": 0.8751,
"step": 2009
},
{
"epoch": 0.97,
"learning_rate": 1.2204835107999746e-07,
"loss": 0.8257,
"step": 2010
},
{
"epoch": 0.97,
"learning_rate": 1.186379595900533e-07,
"loss": 0.7858,
"step": 2011
},
{
"epoch": 0.97,
"learning_rate": 1.1527575216863318e-07,
"loss": 0.7069,
"step": 2012
},
{
"epoch": 0.97,
"learning_rate": 1.1196173696431445e-07,
"loss": 0.7155,
"step": 2013
},
{
"epoch": 0.97,
"learning_rate": 1.086959220088768e-07,
"loss": 0.8951,
"step": 2014
},
{
"epoch": 0.97,
"learning_rate": 1.0547831521728447e-07,
"loss": 0.8752,
"step": 2015
},
{
"epoch": 0.97,
"learning_rate": 1.0230892438766404e-07,
"loss": 0.7507,
"step": 2016
},
{
"epoch": 0.97,
"learning_rate": 9.918775720128893e-08,
"loss": 0.7597,
"step": 2017
},
{
"epoch": 0.97,
"learning_rate": 9.611482122255489e-08,
"loss": 0.7164,
"step": 2018
},
{
"epoch": 0.97,
"learning_rate": 9.309012389896677e-08,
"loss": 0.7541,
"step": 2019
},
{
"epoch": 0.97,
"learning_rate": 9.011367256112292e-08,
"loss": 0.7041,
"step": 2020
},
{
"epoch": 0.97,
"learning_rate": 8.718547442268855e-08,
"loss": 0.9207,
"step": 2021
},
{
"epoch": 0.97,
"learning_rate": 8.430553658038687e-08,
"loss": 0.7468,
"step": 2022
},
{
"epoch": 0.97,
"learning_rate": 8.147386601397689e-08,
"loss": 0.7138,
"step": 2023
},
{
"epoch": 0.97,
"learning_rate": 7.869046958623782e-08,
"loss": 0.7367,
"step": 2024
},
{
"epoch": 0.97,
"learning_rate": 7.595535404295584e-08,
"loss": 0.6845,
"step": 2025
},
{
"epoch": 0.97,
"learning_rate": 7.326852601289735e-08,
"loss": 0.9195,
"step": 2026
},
{
"epoch": 0.97,
"learning_rate": 7.062999200780906e-08,
"loss": 0.7876,
"step": 2027
},
{
"epoch": 0.97,
"learning_rate": 6.803975842238686e-08,
"loss": 0.7008,
"step": 2028
},
{
"epoch": 0.97,
"learning_rate": 6.549783153426692e-08,
"loss": 0.7194,
"step": 2029
},
{
"epoch": 0.98,
"learning_rate": 6.300421750401464e-08,
"loss": 0.8785,
"step": 2030
},
{
"epoch": 0.98,
"learning_rate": 6.055892237510241e-08,
"loss": 0.9092,
"step": 2031
},
{
"epoch": 0.98,
"learning_rate": 5.81619520738963e-08,
"loss": 0.7507,
"step": 2032
},
{
"epoch": 0.98,
"learning_rate": 5.581331240964938e-08,
"loss": 0.7115,
"step": 2033
},
{
"epoch": 0.98,
"learning_rate": 5.3513009074472874e-08,
"loss": 0.7851,
"step": 2034
},
{
"epoch": 0.98,
"learning_rate": 5.126104764333839e-08,
"loss": 0.9028,
"step": 2035
},
{
"epoch": 0.98,
"learning_rate": 4.905743357405124e-08,
"loss": 0.8539,
"step": 2036
},
{
"epoch": 0.98,
"learning_rate": 4.690217220725046e-08,
"loss": 0.7222,
"step": 2037
},
{
"epoch": 0.98,
"learning_rate": 4.4795268766379963e-08,
"loss": 0.8067,
"step": 2038
},
{
"epoch": 0.98,
"learning_rate": 4.2736728357692935e-08,
"loss": 0.7003,
"step": 2039
},
{
"epoch": 0.98,
"learning_rate": 4.0726555970223015e-08,
"loss": 0.78,
"step": 2040
},
{
"epoch": 0.98,
"learning_rate": 3.876475647578204e-08,
"loss": 0.7718,
"step": 2041
},
{
"epoch": 0.98,
"learning_rate": 3.685133462895341e-08,
"loss": 0.7875,
"step": 2042
},
{
"epoch": 0.98,
"learning_rate": 3.498629506706097e-08,
"loss": 0.7403,
"step": 2043
},
{
"epoch": 0.98,
"learning_rate": 3.3169642310182384e-08,
"loss": 0.8347,
"step": 2044
},
{
"epoch": 0.98,
"learning_rate": 3.14013807611202e-08,
"loss": 0.962,
"step": 2045
},
{
"epoch": 0.98,
"learning_rate": 2.9681514705393045e-08,
"loss": 0.8896,
"step": 2046
},
{
"epoch": 0.98,
"learning_rate": 2.801004831123999e-08,
"loss": 0.8373,
"step": 2047
},
{
"epoch": 0.98,
"learning_rate": 2.6386985629587303e-08,
"loss": 0.702,
"step": 2048
},
{
"epoch": 0.98,
"learning_rate": 2.481233059405952e-08,
"loss": 0.7443,
"step": 2049
},
{
"epoch": 0.98,
"learning_rate": 2.328608702095947e-08,
"loss": 0.7173,
"step": 2050
},
{
"epoch": 0.99,
"learning_rate": 2.1808258609261613e-08,
"loss": 0.7821,
"step": 2051
},
{
"epoch": 0.99,
"learning_rate": 2.0378848940598716e-08,
"loss": 0.7199,
"step": 2052
},
{
"epoch": 0.99,
"learning_rate": 1.8997861479259637e-08,
"loss": 0.7673,
"step": 2053
},
{
"epoch": 0.99,
"learning_rate": 1.7665299572176e-08,
"loss": 0.6804,
"step": 2054
},
{
"epoch": 0.99,
"learning_rate": 1.638116644892218e-08,
"loss": 0.8385,
"step": 2055
},
{
"epoch": 0.99,
"learning_rate": 1.5145465221695353e-08,
"loss": 0.7585,
"step": 2056
},
{
"epoch": 0.99,
"learning_rate": 1.3958198885315467e-08,
"loss": 0.913,
"step": 2057
},
{
"epoch": 0.99,
"learning_rate": 1.2819370317218583e-08,
"loss": 0.8979,
"step": 2058
},
{
"epoch": 0.99,
"learning_rate": 1.1728982277443569e-08,
"loss": 0.7767,
"step": 2059
},
{
"epoch": 0.99,
"learning_rate": 1.0687037408636525e-08,
"loss": 0.8949,
"step": 2060
},
{
"epoch": 0.99,
"learning_rate": 9.693538236033029e-09,
"loss": 0.7811,
"step": 2061
},
{
"epoch": 0.99,
"learning_rate": 8.74848716745813e-09,
"loss": 0.7495,
"step": 2062
},
{
"epoch": 0.99,
"learning_rate": 7.851886493317473e-09,
"loss": 0.6359,
"step": 2063
},
{
"epoch": 0.99,
"learning_rate": 7.003738386595071e-09,
"loss": 0.9381,
"step": 2064
},
{
"epoch": 0.99,
"learning_rate": 6.204044902844431e-09,
"loss": 0.8975,
"step": 2065
},
{
"epoch": 0.99,
"learning_rate": 5.452807980186325e-09,
"loss": 0.8496,
"step": 2066
},
{
"epoch": 0.99,
"learning_rate": 4.75002943930658e-09,
"loss": 0.7888,
"step": 2067
},
{
"epoch": 0.99,
"learning_rate": 4.095710983442746e-09,
"loss": 0.7674,
"step": 2068
},
{
"epoch": 0.99,
"learning_rate": 3.489854198386322e-09,
"loss": 0.847,
"step": 2069
},
{
"epoch": 0.99,
"learning_rate": 2.932460552482752e-09,
"loss": 0.8345,
"step": 2070
},
{
"epoch": 0.99,
"learning_rate": 2.4235313966203268e-09,
"loss": 0.9327,
"step": 2071
},
{
"epoch": 1.0,
"learning_rate": 1.9630679642257398e-09,
"loss": 0.8124,
"step": 2072
},
{
"epoch": 1.0,
"learning_rate": 1.5510713712707515e-09,
"loss": 0.8164,
"step": 2073
},
{
"epoch": 1.0,
"learning_rate": 1.1875426162633041e-09,
"loss": 0.8303,
"step": 2074
},
{
"epoch": 1.0,
"learning_rate": 8.724825802430837e-10,
"loss": 0.7074,
"step": 2075
},
{
"epoch": 1.0,
"learning_rate": 6.058920267837387e-10,
"loss": 0.8208,
"step": 2076
},
{
"epoch": 1.0,
"learning_rate": 3.8777160198844033e-10,
"loss": 0.751,
"step": 2077
},
{
"epoch": 1.0,
"learning_rate": 2.1812183448988167e-10,
"loss": 0.7847,
"step": 2078
},
{
"epoch": 1.0,
"learning_rate": 9.694313544583722e-11,
"loss": 0.7622,
"step": 2079
},
{
"epoch": 1.0,
"learning_rate": 2.423579854582414e-11,
"loss": 0.7019,
"step": 2080
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 0.7925,
"step": 2081
},
{
"epoch": 1.0,
"step": 2081,
"total_flos": 6.1537201706232e+21,
"train_loss": 0.8170489284179923,
"train_runtime": 14766.6549,
"train_samples_per_second": 2.256,
"train_steps_per_second": 0.141
}
],
"logging_steps": 1.0,
"max_steps": 2081,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 200,
"total_flos": 6.1537201706232e+21,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}