diff --git "a/checkpoint-1268/trainer_state.json" "b/checkpoint-1268/trainer_state.json"
new file mode 100644--- /dev/null
+++ "b/checkpoint-1268/trainer_state.json"
@@ -0,0 +1,7629 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9983004507500186,
+  "eval_steps": 500,
+  "global_step": 1268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 3.921568627450981e-07,
+      "loss": 2.8563,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.843137254901962e-07,
+      "loss": 3.0208,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 4.0651,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.5686274509803923e-06,
+      "loss": 3.3154,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 3.9875,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 9.4198,
+      "step": 6
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.7450980392156867e-06,
+      "loss": 3.4956,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.1372549019607846e-06,
+      "loss": 3.646,
+      "step": 8
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 2.9569,
+      "step": 9
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 3.2712,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.313725490196079e-06,
+      "loss": 4.4552,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 3.2141,
+      "step": 12
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.098039215686274e-06,
+      "loss": 2.8645,
+      "step": 13
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.4901960784313735e-06,
+      "loss": 2.9299,
+      "step": 14
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 3.2333,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.274509803921569e-06,
+      "loss": 3.3361,
+      "step": 16
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.8326,
+      "step": 17
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 5.9936,
+      "step": 18
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 7.450980392156863e-06,
+      "loss": 2.7551,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 2.3296,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 2.1901,
+      "step": 21
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 8.627450980392157e-06,
+      "loss": 1.7673,
+      "step": 22
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.019607843137256e-06,
+      "loss": 1.6721,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 1.7151,
+      "step": 24
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 1.7576,
+      "step": 25
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.0196078431372549e-05,
+      "loss": 1.4461,
+      "step": 26
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.0588235294117648e-05,
+      "loss": 3.8357,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.0980392156862747e-05,
+      "loss": 1.5292,
+      "step": 28
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1372549019607844e-05,
+      "loss": 1.484,
+      "step": 29
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 1.2995,
+      "step": 30
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.215686274509804e-05,
+      "loss": 1.1459,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2549019607843138e-05,
+      "loss": 1.1017,
+      "step": 32
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.2941176470588238e-05,
+      "loss": 1.2681,
+      "step": 33
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.7749,
+      "step": 34
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.3725490196078432e-05,
+      "loss": 1.4039,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4117647058823532e-05,
+      "loss": 1.304,
+      "step": 36
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4509803921568629e-05,
+      "loss": 1.1641,
+      "step": 37
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.4901960784313726e-05,
+      "loss": 1.0715,
+      "step": 38
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.5294117647058822e-05,
+      "loss": 1.0567,
+      "step": 39
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.568627450980392e-05,
+      "loss": 1.3111,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.607843137254902e-05,
+      "loss": 1.4909,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.647058823529412e-05,
+      "loss": 0.961,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.686274509803922e-05,
+      "loss": 1.1519,
+      "step": 43
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.7254901960784314e-05,
+      "loss": 0.9403,
+      "step": 44
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 1.1603,
+      "step": 45
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.8039215686274513e-05,
+      "loss": 0.9909,
+      "step": 46
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.843137254901961e-05,
+      "loss": 1.0872,
+      "step": 47
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.8823529411764708e-05,
+      "loss": 1.0935,
+      "step": 48
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9215686274509807e-05,
+      "loss": 1.2776,
+      "step": 49
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9607843137254903e-05,
+      "loss": 1.0812,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 2e-05,
+      "loss": 1.0436,
+      "step": 51
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9987782529016497e-05,
+      "loss": 1.275,
+      "step": 52
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.997556505803299e-05,
+      "loss": 1.1309,
+      "step": 53
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9963347587049484e-05,
+      "loss": 1.0838,
+      "step": 54
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9951130116065975e-05,
+      "loss": 1.0861,
+      "step": 55
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.993891264508247e-05,
+      "loss": 0.9737,
+      "step": 56
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9926695174098962e-05,
+      "loss": 0.9726,
+      "step": 57
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9914477703115457e-05,
+      "loss": 1.1044,
+      "step": 58
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9902260232131952e-05,
+      "loss": 1.2198,
+      "step": 59
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9890042761148444e-05,
+      "loss": 1.2454,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.987782529016494e-05,
+      "loss": 1.0945,
+      "step": 61
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.986560781918143e-05,
+      "loss": 1.2243,
+      "step": 62
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9853390348197926e-05,
+      "loss": 1.0895,
+      "step": 63
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9841172877214418e-05,
+      "loss": 1.3153,
+      "step": 64
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.9828955406230913e-05,
+      "loss": 1.3891,
+      "step": 65
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9816737935247404e-05,
+      "loss": 1.1219,
+      "step": 66
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.98045204642639e-05,
+      "loss": 1.0493,
+      "step": 67
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.979230299328039e-05,
+      "loss": 1.0645,
+      "step": 68
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9780085522296886e-05,
+      "loss": 1.3425,
+      "step": 69
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9767868051313378e-05,
+      "loss": 1.8974,
+      "step": 70
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9755650580329873e-05,
+      "loss": 1.0191,
+      "step": 71
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9743433109346365e-05,
+      "loss": 1.1784,
+      "step": 72
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.973121563836286e-05,
+      "loss": 1.0353,
+      "step": 73
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9718998167379355e-05,
+      "loss": 1.2755,
+      "step": 74
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.970678069639585e-05,
+      "loss": 0.9851,
+      "step": 75
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9694563225412342e-05,
+      "loss": 1.2396,
+      "step": 76
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.9682345754428837e-05,
+      "loss": 1.2519,
+      "step": 77
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.967012828344533e-05,
+      "loss": 0.9313,
+      "step": 78
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9657910812461824e-05,
+      "loss": 1.1745,
+      "step": 79
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9645693341478315e-05,
+      "loss": 1.0521,
+      "step": 80
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.963347587049481e-05,
+      "loss": 0.9781,
+      "step": 81
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.9621258399511302e-05,
+      "loss": 1.0292,
+      "step": 82
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9609040928527797e-05,
+      "loss": 0.851,
+      "step": 83
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.959682345754429e-05,
+      "loss": 1.1486,
+      "step": 84
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9584605986560784e-05,
+      "loss": 1.0732,
+      "step": 85
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.9572388515577276e-05,
+      "loss": 1.0466,
+      "step": 86
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.956017104459377e-05,
+      "loss": 0.9275,
+      "step": 87
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9547953573610263e-05,
+      "loss": 1.7509,
+      "step": 88
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9535736102626758e-05,
+      "loss": 1.3038,
+      "step": 89
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.9523518631643253e-05,
+      "loss": 0.8664,
+      "step": 90
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9511301160659744e-05,
+      "loss": 1.1555,
+      "step": 91
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.949908368967624e-05,
+      "loss": 1.1517,
+      "step": 92
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.948686621869273e-05,
+      "loss": 1.0223,
+      "step": 93
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9474648747709226e-05,
+      "loss": 1.0649,
+      "step": 94
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.9462431276725718e-05,
+      "loss": 1.0147,
+      "step": 95
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9450213805742213e-05,
+      "loss": 1.3624,
+      "step": 96
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.9437996334758705e-05,
+      "loss": 1.1294,
+      "step": 97
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.94257788637752e-05,
+      "loss": 1.1903,
+      "step": 98
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.941356139279169e-05,
+      "loss": 0.8732,
+      "step": 99
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9401343921808187e-05,
+      "loss": 1.1793,
+      "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.938912645082468e-05,
+      "loss": 0.9008,
+      "step": 101
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.9376908979841174e-05,
+      "loss": 1.2374,
+      "step": 102
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.936469150885767e-05,
+      "loss": 0.9163,
+      "step": 103
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9352474037874164e-05,
+      "loss": 0.9702,
+      "step": 104
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9340256566890655e-05,
+      "loss": 1.0813,
+      "step": 105
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.932803909590715e-05,
+      "loss": 1.1164,
+      "step": 106
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.9315821624923642e-05,
+      "loss": 0.9403,
+      "step": 107
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9303604153940137e-05,
+      "loss": 1.074,
+      "step": 108
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.929138668295663e-05,
+      "loss": 1.1077,
+      "step": 109
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9279169211973124e-05,
+      "loss": 1.0153,
+      "step": 110
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.9266951740989616e-05,
+      "loss": 1.0281,
+      "step": 111
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.925473427000611e-05,
+      "loss": 0.9075,
+      "step": 112
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9242516799022603e-05,
+      "loss": 1.2191,
+      "step": 113
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9230299328039098e-05,
+      "loss": 1.0649,
+      "step": 114
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.921808185705559e-05,
+      "loss": 0.9901,
+      "step": 115
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.9205864386072085e-05,
+      "loss": 1.0329,
+      "step": 116
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9193646915088576e-05,
+      "loss": 1.4406,
+      "step": 117
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.918142944410507e-05,
+      "loss": 1.138,
+      "step": 118
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9169211973121567e-05,
+      "loss": 1.1755,
+      "step": 119
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9156994502138058e-05,
+      "loss": 0.9568,
+      "step": 120
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9144777031154553e-05,
+      "loss": 1.0204,
+      "step": 121
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.913255956017105e-05,
+      "loss": 0.9391,
+      "step": 122
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.912034208918754e-05,
+      "loss": 1.109,
+      "step": 123
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.9108124618204035e-05,
+      "loss": 1.2183,
+      "step": 124
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9095907147220527e-05,
+      "loss": 0.9377,
+      "step": 125
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9083689676237022e-05,
+      "loss": 1.0865,
+      "step": 126
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.9071472205253514e-05,
+      "loss": 1.2078,
+      "step": 127
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.905925473427001e-05,
+      "loss": 1.0149,
+      "step": 128
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.90470372632865e-05,
+      "loss": 1.1191,
+      "step": 129
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9034819792302996e-05,
+      "loss": 1.0933,
+      "step": 130
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9022602321319487e-05,
+      "loss": 0.9312,
+      "step": 131
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9010384850335982e-05,
+      "loss": 0.794,
+      "step": 132
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8998167379352474e-05,
+      "loss": 0.8745,
+      "step": 133
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.898594990836897e-05,
+      "loss": 0.9092,
+      "step": 134
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.8973732437385464e-05,
+      "loss": 0.7504,
+      "step": 135
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.8961514966401956e-05,
+      "loss": 1.2165,
+      "step": 136
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.894929749541845e-05,
+      "loss": 0.9727,
+      "step": 137
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8937080024434943e-05,
+      "loss": 1.0236,
+      "step": 138
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8924862553451438e-05,
+      "loss": 0.9628,
+      "step": 139
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.891264508246793e-05,
+      "loss": 0.8762,
+      "step": 140
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8900427611484425e-05,
+      "loss": 1.0712,
+      "step": 141
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8888210140500916e-05,
+      "loss": 0.7999,
+      "step": 142
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.887599266951741e-05,
+      "loss": 0.9812,
+      "step": 143
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.8863775198533903e-05,
+      "loss": 1.8394,
+      "step": 144
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.88515577275504e-05,
+      "loss": 0.9033,
+      "step": 145
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.883934025656689e-05,
+      "loss": 0.9813,
+      "step": 146
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8827122785583385e-05,
+      "loss": 0.7722,
+      "step": 147
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8814905314599877e-05,
+      "loss": 0.9991,
+      "step": 148
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8802687843616375e-05,
+      "loss": 0.9531,
+      "step": 149
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.8790470372632867e-05,
+      "loss": 0.9034,
+      "step": 150
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8778252901649362e-05,
+      "loss": 0.8741,
+      "step": 151
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8766035430665854e-05,
+      "loss": 1.1228,
+      "step": 152
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.875381795968235e-05,
+      "loss": 0.7849,
+      "step": 153
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.874160048869884e-05,
+      "loss": 0.9642,
+      "step": 154
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8729383017715336e-05,
+      "loss": 1.0823,
+      "step": 155
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8717165546731827e-05,
+      "loss": 1.2156,
+      "step": 156
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8704948075748323e-05,
+      "loss": 1.4682,
+      "step": 157
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8692730604764814e-05,
+      "loss": 1.2043,
+      "step": 158
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.868051313378131e-05,
+      "loss": 0.9802,
+      "step": 159
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.86682956627978e-05,
+      "loss": 1.1539,
+      "step": 160
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8656078191814296e-05,
+      "loss": 1.1245,
+      "step": 161
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.8643860720830788e-05,
+      "loss": 1.099,
+      "step": 162
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8631643249847283e-05,
+      "loss": 1.0272,
+      "step": 163
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8619425778863778e-05,
+      "loss": 1.0072,
+      "step": 164
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.860720830788027e-05,
+      "loss": 1.0215,
+      "step": 165
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8594990836896765e-05,
+      "loss": 1.0221,
+      "step": 166
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.8582773365913257e-05,
+      "loss": 1.0754,
+      "step": 167
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.857055589492975e-05,
+      "loss": 0.9724,
+      "step": 168
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.8558338423946243e-05,
+      "loss": 1.031,
+      "step": 169
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.854612095296274e-05,
+      "loss": 1.157,
+      "step": 170
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.853390348197923e-05,
+      "loss": 0.9819,
+      "step": 171
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8521686010995725e-05,
+      "loss": 1.1156,
+      "step": 172
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.850946854001222e-05,
+      "loss": 1.0699,
+      "step": 173
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8497251069028712e-05,
+      "loss": 1.1092,
+      "step": 174
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8485033598045207e-05,
+      "loss": 1.0092,
+      "step": 175
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.84728161270617e-05,
+      "loss": 1.0403,
+      "step": 176
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8460598656078194e-05,
+      "loss": 0.8809,
+      "step": 177
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.8448381185094686e-05,
+      "loss": 1.0139,
+      "step": 178
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.843616371411118e-05,
+      "loss": 1.0701,
+      "step": 179
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8423946243127676e-05,
+      "loss": 0.9199,
+      "step": 180
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8411728772144168e-05,
+      "loss": 0.8542,
+      "step": 181
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8399511301160663e-05,
+      "loss": 1.0369,
+      "step": 182
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8387293830177154e-05,
+      "loss": 0.9847,
+      "step": 183
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.837507635919365e-05,
+      "loss": 0.8046,
+      "step": 184
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.836285888821014e-05,
+      "loss": 1.2821,
+      "step": 185
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8350641417226636e-05,
+      "loss": 1.0127,
+      "step": 186
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8338423946243128e-05,
+      "loss": 0.8535,
+      "step": 187
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.8326206475259623e-05,
+      "loss": 0.984,
+      "step": 188
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8313989004276115e-05,
+      "loss": 0.771,
+      "step": 189
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.830177153329261e-05,
+      "loss": 2.1482,
+      "step": 190
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.82895540623091e-05,
+      "loss": 0.7799,
+      "step": 191
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.8277336591325597e-05,
+      "loss": 1.1474,
+      "step": 192
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.826511912034209e-05,
+      "loss": 1.0967,
+      "step": 193
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8252901649358587e-05,
+      "loss": 0.8824,
+      "step": 194
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.824068417837508e-05,
+      "loss": 0.9202,
+      "step": 195
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.8228466707391574e-05,
+      "loss": 0.8055,
+      "step": 196
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8216249236408065e-05,
+      "loss": 0.7309,
+      "step": 197
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.820403176542456e-05,
+      "loss": 1.1121,
+      "step": 198
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8191814294441052e-05,
+      "loss": 1.5694,
+      "step": 199
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.8179596823457547e-05,
+      "loss": 1.2677,
+      "step": 200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.816737935247404e-05,
+      "loss": 1.1242,
+      "step": 201
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8155161881490534e-05,
+      "loss": 0.8419,
+      "step": 202
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8142944410507026e-05,
+      "loss": 1.1399,
+      "step": 203
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.813072693952352e-05,
+      "loss": 0.7964,
+      "step": 204
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8118509468540013e-05,
+      "loss": 0.9321,
+      "step": 205
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.8106291997556508e-05,
+      "loss": 0.8461,
+      "step": 206
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.8094074526573e-05,
+      "loss": 1.0457,
+      "step": 207
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.8081857055589494e-05,
+      "loss": 1.085,
+      "step": 208
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.806963958460599e-05,
+      "loss": 0.9105,
+      "step": 209
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.805742211362248e-05,
+      "loss": 0.9143,
+      "step": 210
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.8045204642638976e-05,
+      "loss": 1.0978,
+      "step": 211
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.8032987171655468e-05,
+      "loss": 0.9884,
+      "step": 212
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.8020769700671963e-05,
+      "loss": 1.0179,
+      "step": 213
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.8008552229688455e-05,
+      "loss": 1.2135,
+      "step": 214
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.799633475870495e-05,
+      "loss": 0.9051,
+      "step": 215
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7984117287721442e-05,
+      "loss": 0.8954,
+      "step": 216
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.7971899816737937e-05,
+      "loss": 1.1429,
+      "step": 217
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.795968234575443e-05,
+      "loss": 1.0803,
+      "step": 218
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7947464874770924e-05,
+      "loss": 1.0558,
+      "step": 219
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7935247403787415e-05,
+      "loss": 1.0904,
+      "step": 220
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.792302993280391e-05,
+      "loss": 1.0909,
+      "step": 221
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.7910812461820402e-05,
+      "loss": 1.1515,
+      "step": 222
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7898594990836897e-05,
+      "loss": 1.0393,
+      "step": 223
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7886377519853392e-05,
+      "loss": 1.0072,
+      "step": 224
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7874160048869887e-05,
+      "loss": 0.8387,
+      "step": 225
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.786194257788638e-05,
+      "loss": 0.8908,
+      "step": 226
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7849725106902874e-05,
+      "loss": 0.875,
+      "step": 227
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7837507635919366e-05,
+      "loss": 1.0477,
+      "step": 228
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.782529016493586e-05,
+      "loss": 1.0117,
+      "step": 229
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.7813072693952353e-05,
+      "loss": 1.1684,
+      "step": 230
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7800855222968848e-05,
+      "loss": 1.1475,
+      "step": 231
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.778863775198534e-05,
+      "loss": 1.2069,
+      "step": 232
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7776420281001835e-05,
+      "loss": 1.1107,
+      "step": 233
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 1.7764202810018326e-05,
+      "loss": 0.9738,
+      "step": 234
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.775198533903482e-05,
+      "loss": 0.8838,
+      "step": 235
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7739767868051313e-05,
+      "loss": 1.0103,
+      "step": 236
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.7727550397067808e-05,
+      "loss": 0.9279,
+      "step": 237
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.77153329260843e-05,
+      "loss": 0.9682,
+      "step": 238
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7703115455100795e-05,
+      "loss": 1.2049,
+      "step": 239
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.769089798411729e-05,
+      "loss": 1.0387,
+      "step": 240
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7678680513133785e-05,
+      "loss": 0.9754,
+      "step": 241
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7666463042150277e-05,
+      "loss": 1.0202,
+      "step": 242
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.7654245571166772e-05,
+      "loss": 1.0224,
+      "step": 243
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.7642028100183264e-05,
+      "loss": 0.8577,
+      "step": 244
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.762981062919976e-05,
+      "loss": 0.9112,
+      "step": 245
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.761759315821625e-05,
+      "loss": 0.9395,
+      "step": 246
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.7605375687232746e-05,
+      "loss": 1.1198,
+      "step": 247
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7593158216249237e-05,
+      "loss": 1.4934,
+      "step": 248
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7580940745265732e-05,
+      "loss": 1.0408,
+      "step": 249
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7568723274282224e-05,
+      "loss": 0.9475,
+      "step": 250
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.755650580329872e-05,
+      "loss": 1.1368,
+      "step": 251
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.754428833231521e-05,
+      "loss": 0.9984,
+      "step": 252
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7532070861331706e-05,
+      "loss": 1.1552,
+      "step": 253
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.75198533903482e-05,
+      "loss": 1.0785,
+      "step": 254
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7507635919364693e-05,
+      "loss": 0.8089,
+      "step": 255
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7495418448381188e-05,
+      "loss": 1.0439,
+      "step": 256
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.748320097739768e-05,
+      "loss": 0.7603,
+      "step": 257
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7470983506414175e-05,
+      "loss": 0.8235,
+      "step": 258
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.7458766035430666e-05,
+      "loss": 1.7352,
+      "step": 259
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.744654856444716e-05,
+      "loss": 0.9731,
+      "step": 260
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7434331093463653e-05,
+      "loss": 0.8848,
+      "step": 261
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.742211362248015e-05,
+      "loss": 0.8874,
+      "step": 262
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.740989615149664e-05,
+      "loss": 1.0125,
+      "step": 263
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.7397678680513135e-05,
+      "loss": 1.0552,
+      "step": 264
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7385461209529627e-05,
+      "loss": 0.9488,
+      "step": 265
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7373243738546122e-05,
+      "loss": 0.794,
+      "step": 266
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.7361026267562614e-05,
+      "loss": 1.0277,
+      "step": 267
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.734880879657911e-05,
+      "loss": 0.835,
+      "step": 268
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7336591325595604e-05,
+      "loss": 1.2321,
+      "step": 269
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.73243738546121e-05,
+      "loss": 0.9804,
+      "step": 270
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.731215638362859e-05,
+      "loss": 1.1228,
+      "step": 271
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.7299938912645086e-05,
+      "loss": 1.1392,
+      "step": 272
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7287721441661577e-05,
+      "loss": 0.8711,
+      "step": 273
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7275503970678073e-05,
+      "loss": 0.9201,
+      "step": 274
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7263286499694564e-05,
+      "loss": 1.008,
+      "step": 275
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.725106902871106e-05,
+      "loss": 1.0344,
+      "step": 276
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.723885155772755e-05,
+      "loss": 0.9427,
+      "step": 277
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7226634086744046e-05,
+      "loss": 0.8963,
+      "step": 278
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7214416615760538e-05,
+      "loss": 1.3487,
+      "step": 279
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7202199144777033e-05,
+      "loss": 1.0002,
+      "step": 280
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.7189981673793525e-05,
+      "loss": 0.961,
+      "step": 281
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.717776420281002e-05,
+      "loss": 0.9015,
+      "step": 282
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.716554673182651e-05,
+      "loss": 0.9172,
+      "step": 283
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.7153329260843007e-05,
+      "loss": 0.9849,
+      "step": 284
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.71411117898595e-05,
+      "loss": 0.9166,
+      "step": 285
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.7128894318875993e-05,
+      "loss": 1.0685,
+      "step": 286
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.711667684789249e-05,
+      "loss": 1.0196,
+      "step": 287
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.710445937690898e-05,
+      "loss": 0.8409,
+      "step": 288
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.7092241905925475e-05,
+      "loss": 0.9327,
+      "step": 289
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7080024434941967e-05,
+      "loss": 0.8675,
+      "step": 290
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7067806963958462e-05,
+      "loss": 1.1109,
+      "step": 291
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.7055589492974954e-05,
+      "loss": 0.8427,
+      "step": 292
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.704337202199145e-05,
+      "loss": 1.1322,
+      "step": 293
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7031154551007944e-05,
+      "loss": 0.9094,
+      "step": 294
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.7018937080024436e-05,
+      "loss": 1.1168,
+      "step": 295
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.700671960904093e-05,
+      "loss": 0.9982,
+      "step": 296
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.6994502138057422e-05,
+      "loss": 0.7812,
+      "step": 297
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.6982284667073918e-05,
+      "loss": 0.8858,
+      "step": 298
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.6970067196090413e-05,
+      "loss": 0.9693,
+      "step": 299
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.6957849725106904e-05,
+      "loss": 0.9097,
+      "step": 300
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.69456322541234e-05,
+      "loss": 0.9178,
+      "step": 301
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.693341478313989e-05,
+      "loss": 1.0581,
+      "step": 302
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6921197312156386e-05,
+      "loss": 1.1521,
+      "step": 303
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6908979841172878e-05,
+      "loss": 1.065,
+      "step": 304
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6896762370189373e-05,
+      "loss": 0.8954,
+      "step": 305
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.6884544899205865e-05,
+      "loss": 0.7037,
+      "step": 306
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.687232742822236e-05,
+      "loss": 0.9347,
+      "step": 307
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.686010995723885e-05,
+      "loss": 0.9681,
+      "step": 308
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.6847892486255347e-05,
+      "loss": 0.8554,
+      "step": 309
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.683567501527184e-05,
+      "loss": 0.8793,
+      "step": 310
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6823457544288334e-05,
+      "loss": 0.8881,
+      "step": 311
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6811240073304825e-05,
+      "loss": 0.9284,
+      "step": 312
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.679902260232132e-05,
+      "loss": 0.9632,
+      "step": 313
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.6786805131337815e-05,
+      "loss": 1.0815,
+      "step": 314
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.677458766035431e-05,
+      "loss": 0.9314,
+      "step": 315
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.6762370189370802e-05,
+      "loss": 0.7965,
+      "step": 316
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.6750152718387297e-05,
+      "loss": 0.8365,
+      "step": 317
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.673793524740379e-05,
+      "loss": 1.2019,
+      "step": 318
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.6725717776420284e-05,
+      "loss": 0.9525,
+      "step": 319
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6713500305436776e-05,
+      "loss": 0.7911,
+      "step": 320
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.670128283445327e-05,
+      "loss": 0.9614,
+      "step": 321
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6689065363469763e-05,
+      "loss": 1.0212,
+      "step": 322
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.6676847892486258e-05,
+      "loss": 1.128,
+      "step": 323
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.666463042150275e-05,
+      "loss": 0.9668,
+      "step": 324
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.6652412950519245e-05,
+      "loss": 0.9095,
+      "step": 325
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.6640195479535736e-05,
+      "loss": 0.8985,
+      "step": 326
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.662797800855223e-05,
+      "loss": 0.8876,
+      "step": 327
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6615760537568723e-05,
+      "loss": 0.9104,
+      "step": 328
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6603543066585218e-05,
+      "loss": 0.9719,
+      "step": 329
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6591325595601713e-05,
+      "loss": 1.2485,
+      "step": 330
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.6579108124618205e-05,
+      "loss": 0.8247,
+      "step": 331
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.65668906536347e-05,
+      "loss": 1.1209,
+      "step": 332
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.6554673182651192e-05,
+      "loss": 1.0325,
+      "step": 333
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.6542455711667687e-05,
+      "loss": 1.0139,
+      "step": 334
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.653023824068418e-05,
+      "loss": 1.0233,
+      "step": 335
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.6518020769700674e-05,
+      "loss": 0.8545,
+      "step": 336
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6505803298717165e-05,
+      "loss": 1.2186,
+      "step": 337
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.649358582773366e-05,
+      "loss": 0.9952,
+      "step": 338
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6481368356750152e-05,
+      "loss": 1.2843,
+      "step": 339
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.6469150885766647e-05,
+      "loss": 1.2914,
+      "step": 340
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.645693341478314e-05,
+      "loss": 0.7621,
+      "step": 341
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6444715943799634e-05,
+      "loss": 1.0924,
+      "step": 342
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6432498472816126e-05,
+      "loss": 1.1418,
+      "step": 343
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6420281001832624e-05,
+      "loss": 0.9116,
+      "step": 344
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6408063530849116e-05,
+      "loss": 1.7392,
+      "step": 345
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.639584605986561e-05,
+      "loss": 0.7273,
+      "step": 346
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6383628588882103e-05,
+      "loss": 0.9469,
+      "step": 347
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6371411117898598e-05,
+      "loss": 0.7986,
+      "step": 348
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.635919364691509e-05,
+      "loss": 0.8359,
+      "step": 349
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6346976175931585e-05,
+      "loss": 0.7852,
+      "step": 350
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6334758704948076e-05,
+      "loss": 1.1206,
+      "step": 351
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.632254123396457e-05,
+      "loss": 0.9291,
+      "step": 352
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.6310323762981063e-05,
+      "loss": 1.0176,
+      "step": 353
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6298106291997558e-05,
+      "loss": 1.018,
+      "step": 354
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.628588882101405e-05,
+      "loss": 0.7873,
+      "step": 355
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6273671350030545e-05,
+      "loss": 0.9801,
+      "step": 356
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.6261453879047037e-05,
+      "loss": 0.752,
+      "step": 357
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6249236408063532e-05,
+      "loss": 0.8991,
+      "step": 358
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6237018937080027e-05,
+      "loss": 0.8771,
+      "step": 359
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.622480146609652e-05,
+      "loss": 0.8734,
+      "step": 360
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6212583995113014e-05,
+      "loss": 0.9302,
+      "step": 361
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.620036652412951e-05,
+      "loss": 0.9362,
+      "step": 362
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6188149053146e-05,
+      "loss": 0.9994,
+      "step": 363
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6175931582162496e-05,
+      "loss": 0.7499,
+      "step": 364
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.6163714111178987e-05,
+      "loss": 1.7184,
+      "step": 365
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6151496640195482e-05,
+      "loss": 1.0205,
+      "step": 366
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6139279169211974e-05,
+      "loss": 0.8763,
+      "step": 367
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.612706169822847e-05,
+      "loss": 1.0264,
+      "step": 368
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.611484422724496e-05,
+      "loss": 0.9088,
+      "step": 369
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.6102626756261456e-05,
+      "loss": 0.7762,
+      "step": 370
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6090409285277948e-05,
+      "loss": 0.876,
+      "step": 371
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6078191814294443e-05,
+      "loss": 1.0591,
+      "step": 372
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.6065974343310935e-05,
+      "loss": 0.8602,
+      "step": 373
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.605375687232743e-05,
+      "loss": 0.8489,
+      "step": 374
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6041539401343925e-05,
+      "loss": 0.9205,
+      "step": 375
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6029321930360416e-05,
+      "loss": 0.926,
+      "step": 376
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.601710445937691e-05,
+      "loss": 0.8983,
+      "step": 377
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.6004886988393403e-05,
+      "loss": 1.0779,
+      "step": 378
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.59926695174099e-05,
+      "loss": 0.9446,
+      "step": 379
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.598045204642639e-05,
+      "loss": 1.1564,
+      "step": 380
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.5968234575442885e-05,
+      "loss": 1.0101,
+      "step": 381
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.5956017104459377e-05,
+      "loss": 1.0597,
+      "step": 382
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.5943799633475872e-05,
+      "loss": 0.9408,
+      "step": 383
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.5931582162492364e-05,
+      "loss": 1.1833,
+      "step": 384
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.591936469150886e-05,
+      "loss": 1.0106,
+      "step": 385
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.590714722052535e-05,
+      "loss": 1.6698,
+      "step": 386
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5894929749541846e-05,
+      "loss": 1.0123,
+      "step": 387
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5882712278558337e-05,
+      "loss": 0.9237,
+      "step": 388
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5870494807574836e-05,
+      "loss": 0.9182,
+      "step": 389
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5858277336591327e-05,
+      "loss": 0.9832,
+      "step": 390
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.5846059865607823e-05,
+      "loss": 0.7884,
+      "step": 391
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5833842394624314e-05,
+      "loss": 1.0028,
+      "step": 392
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.582162492364081e-05,
+      "loss": 1.0835,
+      "step": 393
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.58094074526573e-05,
+      "loss": 0.9394,
+      "step": 394
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5797189981673796e-05,
+      "loss": 1.25,
+      "step": 395
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5784972510690288e-05,
+      "loss": 1.0046,
+      "step": 396
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5772755039706783e-05,
+      "loss": 0.6862,
+      "step": 397
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.5760537568723275e-05,
+      "loss": 0.9672,
+      "step": 398
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.574832009773977e-05,
+      "loss": 0.847,
+      "step": 399
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.573610262675626e-05,
+      "loss": 1.1316,
+      "step": 400
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5723885155772757e-05,
+      "loss": 1.1577,
+      "step": 401
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5711667684789248e-05,
+      "loss": 0.7909,
+      "step": 402
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.5699450213805743e-05,
+      "loss": 0.9476,
+      "step": 403
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.568723274282224e-05,
+      "loss": 0.8651,
+      "step": 404
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.567501527183873e-05,
+      "loss": 0.8349,
+      "step": 405
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5662797800855225e-05,
+      "loss": 1.0023,
+      "step": 406
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5650580329871717e-05,
+      "loss": 0.9267,
+      "step": 407
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.5638362858888212e-05,
+      "loss": 0.7568,
+      "step": 408
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5626145387904704e-05,
+      "loss": 0.9849,
+      "step": 409
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.56139279169212e-05,
+      "loss": 0.8452,
+      "step": 410
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.560171044593769e-05,
+      "loss": 0.9507,
+      "step": 411
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.5589492974954186e-05,
+      "loss": 0.9459,
+      "step": 412
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.557727550397068e-05,
+      "loss": 0.9053,
+      "step": 413
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5565058032987173e-05,
+      "loss": 1.0029,
+      "step": 414
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5552840562003668e-05,
+      "loss": 0.7987,
+      "step": 415
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.554062309102016e-05,
+      "loss": 0.7423,
+      "step": 416
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5528405620036654e-05,
+      "loss": 1.0905,
+      "step": 417
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5516188149053146e-05,
+      "loss": 0.829,
+      "step": 418
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.550397067806964e-05,
+      "loss": 0.698,
+      "step": 419
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5491753207086136e-05,
+      "loss": 0.8893,
+      "step": 420
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5479535736102628e-05,
+      "loss": 0.992,
+      "step": 421
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5467318265119123e-05,
+      "loss": 1.0658,
+      "step": 422
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.5455100794135615e-05,
+      "loss": 1.2668,
+      "step": 423
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.544288332315211e-05,
+      "loss": 0.8961,
+      "step": 424
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.54306658521686e-05,
+      "loss": 0.8881,
+      "step": 425
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5418448381185097e-05,
+      "loss": 0.8983,
+      "step": 426
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.540623091020159e-05,
+      "loss": 0.7649,
+      "step": 427
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5394013439218084e-05,
+      "loss": 0.7264,
+      "step": 428
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.5381795968234575e-05,
+      "loss": 0.7437,
+      "step": 429
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.536957849725107e-05,
+      "loss": 1.01,
+      "step": 430
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5357361026267562e-05,
+      "loss": 0.9565,
+      "step": 431
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.5345143555284057e-05,
+      "loss": 0.7581,
+      "step": 432
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.533292608430055e-05,
+      "loss": 1.0394,
+      "step": 433
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5320708613317047e-05,
+      "loss": 1.0098,
+      "step": 434
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.530849114233354e-05,
+      "loss": 1.007,
+      "step": 435
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5296273671350034e-05,
+      "loss": 1.0359,
+      "step": 436
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.5284056200366526e-05,
+      "loss": 1.0258,
+      "step": 437
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.527183872938302e-05,
+      "loss": 1.0074,
+      "step": 438
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5259621258399513e-05,
+      "loss": 0.8713,
+      "step": 439
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.5247403787416006e-05,
+      "loss": 0.858,
+      "step": 440
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 1.52351863164325e-05,
+      "loss": 0.9483,
+      "step": 441
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5222968845448993e-05,
+      "loss": 0.8927,
+      "step": 442
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5210751374465486e-05,
+      "loss": 1.05,
+      "step": 443
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.519853390348198e-05,
+      "loss": 0.9705,
+      "step": 444
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5186316432498473e-05,
+      "loss": 0.6877,
+      "step": 445
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 1.5174098961514966e-05,
+      "loss": 1.1924,
+      "step": 446
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.516188149053146e-05,
+      "loss": 1.0023,
+      "step": 447
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5149664019547953e-05,
+      "loss": 0.8875,
+      "step": 448
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.513744654856445e-05,
+      "loss": 0.5401,
+      "step": 449
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.5125229077580943e-05,
+      "loss": 1.6992,
+      "step": 450
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5113011606597437e-05,
+      "loss": 0.9052,
+      "step": 451
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.510079413561393e-05,
+      "loss": 1.1827,
+      "step": 452
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5088576664630424e-05,
+      "loss": 0.9645,
+      "step": 453
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5076359193646917e-05,
+      "loss": 0.8014,
+      "step": 454
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.506414172266341e-05,
+      "loss": 0.9795,
+      "step": 455
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5051924251679904e-05,
+      "loss": 1.0001,
+      "step": 456
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.5039706780696397e-05,
+      "loss": 0.9216,
+      "step": 457
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 1.502748930971289e-05,
+      "loss": 0.7942,
+      "step": 458
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.5015271838729384e-05,
+      "loss": 0.6439,
+      "step": 459
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.5003054367745877e-05,
+      "loss": 0.8977,
+      "step": 460
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4990836896762371e-05,
+      "loss": 0.6901,
+      "step": 461
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4978619425778864e-05,
+      "loss": 1.0185,
+      "step": 462
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 1.4966401954795358e-05,
+      "loss": 0.6792,
+      "step": 463
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4954184483811851e-05,
+      "loss": 0.8694,
+      "step": 464
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4941967012828346e-05,
+      "loss": 0.859,
+      "step": 465
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.492974954184484e-05,
+      "loss": 0.8606,
+      "step": 466
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 1.4917532070861333e-05,
+      "loss": 1.0097,
+      "step": 467
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4905314599877826e-05,
+      "loss": 0.7981,
+      "step": 468
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.489309712889432e-05,
+      "loss": 0.9595,
+      "step": 469
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4880879657910813e-05,
+      "loss": 0.9864,
+      "step": 470
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4868662186927307e-05,
+      "loss": 0.7855,
+      "step": 471
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.48564447159438e-05,
+      "loss": 1.098,
+      "step": 472
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4844227244960293e-05,
+      "loss": 0.9994,
+      "step": 473
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4832009773976788e-05,
+      "loss": 0.6699,
+      "step": 474
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 1.4819792302993282e-05,
+      "loss": 0.7458,
+      "step": 475
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4807574832009775e-05,
+      "loss": 0.6966,
+      "step": 476
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4795357361026269e-05,
+      "loss": 0.7422,
+      "step": 477
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4783139890042762e-05,
+      "loss": 0.8659,
+      "step": 478
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 1.4770922419059255e-05,
+      "loss": 1.1142,
+      "step": 479
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.475870494807575e-05,
+      "loss": 0.9528,
+      "step": 480
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4746487477092244e-05,
+      "loss": 0.9859,
+      "step": 481
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4734270006108737e-05,
+      "loss": 0.8913,
+      "step": 482
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.472205253512523e-05,
+      "loss": 0.7271,
+      "step": 483
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 1.4709835064141724e-05,
+      "loss": 0.883,
+      "step": 484
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4697617593158218e-05,
+      "loss": 0.9758,
+      "step": 485
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4685400122174711e-05,
+      "loss": 0.9754,
+      "step": 486
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4673182651191204e-05,
+      "loss": 0.8249,
+      "step": 487
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.4660965180207698e-05,
+      "loss": 0.665,
+      "step": 488
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4648747709224191e-05,
+      "loss": 0.8274,
+      "step": 489
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4636530238240685e-05,
+      "loss": 0.9918,
+      "step": 490
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4624312767257178e-05,
+      "loss": 0.9642,
+      "step": 491
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.4612095296273671e-05,
+      "loss": 0.9325,
+      "step": 492
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4599877825290165e-05,
+      "loss": 0.9546,
+      "step": 493
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4587660354306658e-05,
+      "loss": 0.7223,
+      "step": 494
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4575442883323155e-05,
+      "loss": 0.7956,
+      "step": 495
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 1.4563225412339648e-05,
+      "loss": 0.8982,
+      "step": 496
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4551007941356142e-05,
+      "loss": 1.0453,
+      "step": 497
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4538790470372635e-05,
+      "loss": 0.7084,
+      "step": 498
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4526572999389129e-05,
+      "loss": 0.7952,
+      "step": 499
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4514355528405622e-05,
+      "loss": 0.7469,
+      "step": 500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.4502138057422115e-05,
+      "loss": 1.045,
+      "step": 501
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.4489920586438609e-05,
+      "loss": 0.9179,
+      "step": 502
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.4477703115455102e-05,
+      "loss": 0.8948,
+      "step": 503
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.4465485644471596e-05,
+      "loss": 0.9697,
+      "step": 504
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.4453268173488089e-05,
+      "loss": 0.8727,
+      "step": 505
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.4441050702504582e-05,
+      "loss": 0.8557,
+      "step": 506
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.4428833231521076e-05,
+      "loss": 0.7547,
+      "step": 507
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.441661576053757e-05,
+      "loss": 0.7066,
+      "step": 508
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.4404398289554063e-05,
+      "loss": 0.8879,
+      "step": 509
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4392180818570558e-05,
+      "loss": 0.9328,
+      "step": 510
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4379963347587051e-05,
+      "loss": 0.697,
+      "step": 511
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4367745876603545e-05,
+      "loss": 1.0393,
+      "step": 512
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4355528405620038e-05,
+      "loss": 0.9015,
+      "step": 513
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.4343310934636531e-05,
+      "loss": 1.9402,
+      "step": 514
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.4331093463653025e-05,
+      "loss": 0.9255,
+      "step": 515
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.4318875992669518e-05,
+      "loss": 0.9368,
+      "step": 516
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.4306658521686012e-05,
+      "loss": 1.0178,
+      "step": 517
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.4294441050702505e-05,
+      "loss": 1.0455,
+      "step": 518
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.4282223579718998e-05,
+      "loss": 0.8832,
+      "step": 519
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.4270006108735492e-05,
+      "loss": 0.9344,
+      "step": 520
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.4257788637751985e-05,
+      "loss": 0.8651,
+      "step": 521
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.4245571166768479e-05,
+      "loss": 0.679,
+      "step": 522
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.4233353695784972e-05,
+      "loss": 1.012,
+      "step": 523
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.4221136224801465e-05,
+      "loss": 0.9372,
+      "step": 524
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.4208918753817962e-05,
+      "loss": 0.8254,
+      "step": 525
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.4196701282834456e-05,
+      "loss": 0.8761,
+      "step": 526
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.4184483811850949e-05,
+      "loss": 1.3707,
+      "step": 527
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.4172266340867442e-05,
+      "loss": 1.0044,
+      "step": 528
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.4160048869883936e-05,
+      "loss": 0.9218,
+      "step": 529
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 1.4147831398900429e-05,
+      "loss": 0.9495,
+      "step": 530
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.4135613927916923e-05,
+      "loss": 0.8675,
+      "step": 531
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.4123396456933416e-05,
+      "loss": 0.9436,
+      "step": 532
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.411117898594991e-05,
+      "loss": 0.8323,
+      "step": 533
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.4098961514966403e-05,
+      "loss": 0.7682,
+      "step": 534
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.4086744043982896e-05,
+      "loss": 0.8088,
+      "step": 535
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.407452657299939e-05,
+      "loss": 0.7954,
+      "step": 536
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.4062309102015883e-05,
+      "loss": 0.8871,
+      "step": 537
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.4050091631032376e-05,
+      "loss": 0.8467,
+      "step": 538
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 1.403787416004887e-05,
+      "loss": 0.9207,
+      "step": 539
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.4025656689065365e-05,
+      "loss": 0.8185,
+      "step": 540
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.4013439218081858e-05,
+      "loss": 0.7643,
+      "step": 541
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.4001221747098352e-05,
+      "loss": 0.9263,
+      "step": 542
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.3989004276114847e-05,
+      "loss": 0.9368,
+      "step": 543
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.397678680513134e-05,
+      "loss": 1.3515,
+      "step": 544
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.3964569334147834e-05,
+      "loss": 0.6968,
+      "step": 545
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.3952351863164327e-05,
+      "loss": 0.8393,
+      "step": 546
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 1.394013439218082e-05,
+      "loss": 0.8813,
+      "step": 547
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.3927916921197314e-05,
+      "loss": 0.9748,
+      "step": 548
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.3915699450213807e-05,
+      "loss": 0.9541,
+      "step": 549
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.39034819792303e-05,
+      "loss": 0.849,
+      "step": 550
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.3891264508246794e-05,
+      "loss": 0.8708,
+      "step": 551
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3879047037263287e-05,
+      "loss": 0.8054,
+      "step": 552
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.386682956627978e-05,
+      "loss": 0.7952,
+      "step": 553
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3854612095296274e-05,
+      "loss": 0.8001,
+      "step": 554
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.384239462431277e-05,
+      "loss": 0.9775,
+      "step": 555
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 1.3830177153329263e-05,
+      "loss": 0.9602,
+      "step": 556
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.3817959682345756e-05,
+      "loss": 0.8274,
+      "step": 557
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.380574221136225e-05,
+      "loss": 0.7411,
+      "step": 558
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.3793524740378743e-05,
+      "loss": 0.9579,
+      "step": 559
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 1.3781307269395236e-05,
+      "loss": 0.9866,
+      "step": 560
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.376908979841173e-05,
+      "loss": 0.8351,
+      "step": 561
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3756872327428223e-05,
+      "loss": 0.8235,
+      "step": 562
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.3744654856444716e-05,
+      "loss": 0.9059,
+      "step": 563
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 1.373243738546121e-05,
+      "loss": 0.7818,
+      "step": 564
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3720219914477703e-05,
+      "loss": 0.9199,
+      "step": 565
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3708002443494197e-05,
+      "loss": 0.9934,
+      "step": 566
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.369578497251069e-05,
+      "loss": 0.7839,
+      "step": 567
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.3683567501527183e-05,
+      "loss": 0.8362,
+      "step": 568
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3671350030543677e-05,
+      "loss": 0.7191,
+      "step": 569
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3659132559560174e-05,
+      "loss": 0.8777,
+      "step": 570
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3646915088576667e-05,
+      "loss": 0.8456,
+      "step": 571
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.363469761759316e-05,
+      "loss": 1.1737,
+      "step": 572
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.3622480146609654e-05,
+      "loss": 0.8631,
+      "step": 573
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.3610262675626147e-05,
+      "loss": 0.7261,
+      "step": 574
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.359804520464264e-05,
+      "loss": 0.8019,
+      "step": 575
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.3585827733659134e-05,
+      "loss": 1.0148,
+      "step": 576
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 1.3573610262675627e-05,
+      "loss": 0.8092,
+      "step": 577
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.3561392791692121e-05,
+      "loss": 0.8525,
+      "step": 578
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.3549175320708614e-05,
+      "loss": 0.9003,
+      "step": 579
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.3536957849725108e-05,
+      "loss": 0.9122,
+      "step": 580
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.3524740378741601e-05,
+      "loss": 0.6651,
+      "step": 581
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.3512522907758094e-05,
+      "loss": 0.9718,
+      "step": 582
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.3500305436774588e-05,
+      "loss": 0.9697,
+      "step": 583
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.3488087965791081e-05,
+      "loss": 0.8414,
+      "step": 584
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.3475870494807576e-05,
+      "loss": 0.9784,
+      "step": 585
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.346365302382407e-05,
+      "loss": 0.8626,
+      "step": 586
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.3451435552840563e-05,
+      "loss": 0.7948,
+      "step": 587
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.3439218081857057e-05,
+      "loss": 0.9505,
+      "step": 588
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 1.342700061087355e-05,
+      "loss": 0.7771,
+      "step": 589
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.3414783139890043e-05,
+      "loss": 1.0326,
+      "step": 590
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.3402565668906537e-05,
+      "loss": 0.7854,
+      "step": 591
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.339034819792303e-05,
+      "loss": 0.8514,
+      "step": 592
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.3378130726939524e-05,
+      "loss": 1.008,
+      "step": 593
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 1.3365913255956019e-05,
+      "loss": 1.05,
+      "step": 594
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.3353695784972512e-05,
+      "loss": 0.8007,
+      "step": 595
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.3341478313989005e-05,
+      "loss": 0.8751,
+      "step": 596
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.3329260843005499e-05,
+      "loss": 0.9423,
+      "step": 597
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 1.3317043372021992e-05,
+      "loss": 0.7228,
+      "step": 598
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.3304825901038486e-05,
+      "loss": 1.3136,
+      "step": 599
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.329260843005498e-05,
+      "loss": 0.7924,
+      "step": 600
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.3280390959071474e-05,
+      "loss": 0.9465,
+      "step": 601
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.3268173488087968e-05,
+      "loss": 1.057,
+      "step": 602
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.3255956017104461e-05,
+      "loss": 1.4896,
+      "step": 603
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.3243738546120954e-05,
+      "loss": 1.4226,
+      "step": 604
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.3231521075137448e-05,
+      "loss": 0.7483,
+      "step": 605
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 1.3219303604153941e-05,
+      "loss": 0.7319,
+      "step": 606
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.3207086133170435e-05,
+      "loss": 0.9093,
+      "step": 607
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.3194868662186928e-05,
+      "loss": 0.6625,
+      "step": 608
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.3182651191203421e-05,
+      "loss": 0.8354,
+      "step": 609
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.3170433720219915e-05,
+      "loss": 0.7068,
+      "step": 610
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.3158216249236408e-05,
+      "loss": 0.9007,
+      "step": 611
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.3145998778252902e-05,
+      "loss": 0.7585,
+      "step": 612
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.3133781307269395e-05,
+      "loss": 0.9246,
+      "step": 613
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.3121563836285888e-05,
+      "loss": 1.0258,
+      "step": 614
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 1.3109346365302385e-05,
+      "loss": 0.8766,
+      "step": 615
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3097128894318879e-05,
+      "loss": 0.7533,
+      "step": 616
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3084911423335372e-05,
+      "loss": 0.9276,
+      "step": 617
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3072693952351865e-05,
+      "loss": 0.8266,
+      "step": 618
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.3060476481368359e-05,
+      "loss": 0.8333,
+      "step": 619
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3048259010384852e-05,
+      "loss": 0.9279,
+      "step": 620
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3036041539401346e-05,
+      "loss": 0.8234,
+      "step": 621
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3023824068417839e-05,
+      "loss": 0.9139,
+      "step": 622
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 1.3011606597434332e-05,
+      "loss": 1.0677,
+      "step": 623
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.2999389126450826e-05,
+      "loss": 0.8633,
+      "step": 624
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.298717165546732e-05,
+      "loss": 0.973,
+      "step": 625
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.2974954184483813e-05,
+      "loss": 0.7714,
+      "step": 626
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.2962736713500306e-05,
+      "loss": 0.8985,
+      "step": 627
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.29505192425168e-05,
+      "loss": 0.7919,
+      "step": 628
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.2938301771533293e-05,
+      "loss": 0.7971,
+      "step": 629
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.2926084300549788e-05,
+      "loss": 0.7678,
+      "step": 630
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.2913866829566281e-05,
+      "loss": 1.0978,
+      "step": 631
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 1.2901649358582775e-05,
+      "loss": 1.046,
+      "step": 632
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.2889431887599268e-05,
+      "loss": 0.7762,
+      "step": 633
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.2877214416615762e-05,
+      "loss": 0.9706,
+      "step": 634
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.2864996945632255e-05,
+      "loss": 0.7892,
+      "step": 635
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.2852779474648748e-05,
+      "loss": 0.8744,
+      "step": 636
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2840562003665242e-05,
+      "loss": 0.8939,
+      "step": 637
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2828344532681735e-05,
+      "loss": 0.9054,
+      "step": 638
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2816127061698229e-05,
+      "loss": 0.8555,
+      "step": 639
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 1.2803909590714722e-05,
+      "loss": 1.0563,
+      "step": 640
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2791692119731215e-05,
+      "loss": 1.0961,
+      "step": 641
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2779474648747709e-05,
+      "loss": 1.0154,
+      "step": 642
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2767257177764202e-05,
+      "loss": 0.8368,
+      "step": 643
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.2755039706780696e-05,
+      "loss": 0.8919,
+      "step": 644
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2742822235797192e-05,
+      "loss": 0.7917,
+      "step": 645
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2730604764813686e-05,
+      "loss": 0.7751,
+      "step": 646
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2718387293830179e-05,
+      "loss": 0.8739,
+      "step": 647
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2706169822846673e-05,
+      "loss": 0.8074,
+      "step": 648
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.2693952351863166e-05,
+      "loss": 0.8114,
+      "step": 649
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.268173488087966e-05,
+      "loss": 0.7754,
+      "step": 650
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.2669517409896153e-05,
+      "loss": 0.9155,
+      "step": 651
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.2657299938912646e-05,
+      "loss": 0.7397,
+      "step": 652
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.264508246792914e-05,
+      "loss": 0.8083,
+      "step": 653
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.2632864996945633e-05,
+      "loss": 0.7667,
+      "step": 654
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.2620647525962126e-05,
+      "loss": 0.7873,
+      "step": 655
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.260843005497862e-05,
+      "loss": 0.7984,
+      "step": 656
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 1.2596212583995113e-05,
+      "loss": 0.9473,
+      "step": 657
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.2583995113011607e-05,
+      "loss": 1.0814,
+      "step": 658
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.25717776420281e-05,
+      "loss": 0.8885,
+      "step": 659
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.2559560171044595e-05,
+      "loss": 0.9122,
+      "step": 660
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.2547342700061088e-05,
+      "loss": 0.908,
+      "step": 661
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.2535125229077582e-05,
+      "loss": 0.8649,
+      "step": 662
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.2522907758094075e-05,
+      "loss": 1.025,
+      "step": 663
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.251069028711057e-05,
+      "loss": 0.861,
+      "step": 664
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.2498472816127064e-05,
+      "loss": 0.9673,
+      "step": 665
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 1.2486255345143557e-05,
+      "loss": 0.8577,
+      "step": 666
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.247403787416005e-05,
+      "loss": 0.861,
+      "step": 667
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.2461820403176544e-05,
+      "loss": 0.928,
+      "step": 668
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.2449602932193037e-05,
+      "loss": 0.6446,
+      "step": 669
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.243738546120953e-05,
+      "loss": 0.7685,
+      "step": 670
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.2425167990226024e-05,
+      "loss": 0.765,
+      "step": 671
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.2412950519242518e-05,
+      "loss": 0.7625,
+      "step": 672
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.2400733048259011e-05,
+      "loss": 1.0833,
+      "step": 673
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 1.2388515577275504e-05,
+      "loss": 0.9833,
+      "step": 674
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.2376298106292e-05,
+      "loss": 0.8189,
+      "step": 675
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.2364080635308493e-05,
+      "loss": 0.8686,
+      "step": 676
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.2351863164324986e-05,
+      "loss": 1.1008,
+      "step": 677
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.233964569334148e-05,
+      "loss": 0.8749,
+      "step": 678
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.2327428222357973e-05,
+      "loss": 0.9367,
+      "step": 679
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.2315210751374466e-05,
+      "loss": 0.8399,
+      "step": 680
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.230299328039096e-05,
+      "loss": 0.8422,
+      "step": 681
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 1.2290775809407453e-05,
+      "loss": 0.9767,
+      "step": 682
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.2278558338423947e-05,
+      "loss": 0.9665,
+      "step": 683
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.226634086744044e-05,
+      "loss": 0.6738,
+      "step": 684
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.2254123396456933e-05,
+      "loss": 0.822,
+      "step": 685
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.2241905925473427e-05,
+      "loss": 0.8574,
+      "step": 686
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.222968845448992e-05,
+      "loss": 0.9515,
+      "step": 687
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.2217470983506414e-05,
+      "loss": 0.7583,
+      "step": 688
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.2205253512522907e-05,
+      "loss": 0.7396,
+      "step": 689
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.2193036041539404e-05,
+      "loss": 1.0343,
+      "step": 690
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.2180818570555897e-05,
+      "loss": 0.8694,
+      "step": 691
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.216860109957239e-05,
+      "loss": 1.0403,
+      "step": 692
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.2156383628588884e-05,
+      "loss": 0.657,
+      "step": 693
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.2144166157605377e-05,
+      "loss": 0.8841,
+      "step": 694
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 1.2131948686621871e-05,
+      "loss": 0.9936,
+      "step": 695
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.2119731215638364e-05,
+      "loss": 0.9932,
+      "step": 696
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.2107513744654858e-05,
+      "loss": 0.7702,
+      "step": 697
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.2095296273671351e-05,
+      "loss": 1.8591,
+      "step": 698
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.2083078802687844e-05,
+      "loss": 1.1554,
+      "step": 699
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.2070861331704338e-05,
+      "loss": 0.7643,
+      "step": 700
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.2058643860720831e-05,
+      "loss": 1.0038,
+      "step": 701
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.2046426389737325e-05,
+      "loss": 0.9304,
+      "step": 702
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.2034208918753818e-05,
+      "loss": 0.9719,
+      "step": 703
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.2021991447770312e-05,
+      "loss": 0.7793,
+      "step": 704
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.2009773976786807e-05,
+      "loss": 1.3826,
+      "step": 705
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.19975565058033e-05,
+      "loss": 0.9339,
+      "step": 706
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.1985339034819793e-05,
+      "loss": 0.7452,
+      "step": 707
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 1.1973121563836287e-05,
+      "loss": 0.9882,
+      "step": 708
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.196090409285278e-05,
+      "loss": 0.9004,
+      "step": 709
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.1948686621869274e-05,
+      "loss": 1.3377,
+      "step": 710
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.1936469150885767e-05,
+      "loss": 0.9779,
+      "step": 711
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.192425167990226e-05,
+      "loss": 0.9391,
+      "step": 712
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1912034208918754e-05,
+      "loss": 1.4261,
+      "step": 713
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1899816737935247e-05,
+      "loss": 0.8363,
+      "step": 714
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1887599266951742e-05,
+      "loss": 0.8793,
+      "step": 715
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.1875381795968236e-05,
+      "loss": 0.8424,
+      "step": 716
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1863164324984729e-05,
+      "loss": 0.7472,
+      "step": 717
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1850946854001223e-05,
+      "loss": 0.9502,
+      "step": 718
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1838729383017716e-05,
+      "loss": 1.3596,
+      "step": 719
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1826511912034211e-05,
+      "loss": 0.7848,
+      "step": 720
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1814294441050704e-05,
+      "loss": 0.8574,
+      "step": 721
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.1802076970067198e-05,
+      "loss": 1.5207,
+      "step": 722
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.1789859499083691e-05,
+      "loss": 0.9117,
+      "step": 723
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.1777642028100185e-05,
+      "loss": 0.8671,
+      "step": 724
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 1.1765424557116678e-05,
+      "loss": 0.8095,
+      "step": 725
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.1753207086133171e-05,
+      "loss": 0.8219,
+      "step": 726
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.1740989615149665e-05,
+      "loss": 1.3958,
+      "step": 727
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.1728772144166158e-05,
+      "loss": 0.7198,
+      "step": 728
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 1.1716554673182652e-05,
+      "loss": 0.8341,
+      "step": 729
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.1704337202199145e-05,
+      "loss": 1.0228,
+      "step": 730
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.1692119731215638e-05,
+      "loss": 0.8357,
+      "step": 731
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.1679902260232132e-05,
+      "loss": 0.9477,
+      "step": 732
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 1.1667684789248625e-05,
+      "loss": 0.6738,
+      "step": 733
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.1655467318265119e-05,
+      "loss": 1.0358,
+      "step": 734
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.1643249847281615e-05,
+      "loss": 1.1283,
+      "step": 735
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.1631032376298109e-05,
+      "loss": 0.9415,
+      "step": 736
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.1618814905314602e-05,
+      "loss": 0.8025,
+      "step": 737
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.1606597434331096e-05,
+      "loss": 0.9122,
+      "step": 738
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.1594379963347589e-05,
+      "loss": 0.8259,
+      "step": 739
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.1582162492364082e-05,
+      "loss": 0.8689,
+      "step": 740
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.1569945021380576e-05,
+      "loss": 0.8513,
+      "step": 741
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 1.155772755039707e-05,
+      "loss": 0.9923,
+      "step": 742
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.1545510079413563e-05,
+      "loss": 0.9475,
+      "step": 743
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.1533292608430056e-05,
+      "loss": 0.8622,
+      "step": 744
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.152107513744655e-05,
+      "loss": 0.8522,
+      "step": 745
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 1.1508857666463043e-05,
+      "loss": 0.9629,
+      "step": 746
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.1496640195479536e-05,
+      "loss": 1.0155,
+      "step": 747
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.148442272449603e-05,
+      "loss": 1.0732,
+      "step": 748
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.1472205253512523e-05,
+      "loss": 0.8798,
+      "step": 749
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 1.1459987782529018e-05,
+      "loss": 0.9328,
+      "step": 750
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.1447770311545512e-05,
+      "loss": 1.0042,
+      "step": 751
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.1435552840562005e-05,
+      "loss": 0.7392,
+      "step": 752
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.1423335369578498e-05,
+      "loss": 0.7546,
+      "step": 753
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.1411117898594992e-05,
+      "loss": 0.8252,
+      "step": 754
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.1398900427611485e-05,
+      "loss": 0.8449,
+      "step": 755
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.1386682956627979e-05,
+      "loss": 0.9371,
+      "step": 756
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.1374465485644472e-05,
+      "loss": 0.8685,
+      "step": 757
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.1362248014660965e-05,
+      "loss": 0.8455,
+      "step": 758
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.1350030543677459e-05,
+      "loss": 0.8107,
+      "step": 759
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.1337813072693952e-05,
+      "loss": 0.7724,
+      "step": 760
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.1325595601710446e-05,
+      "loss": 0.9819,
+      "step": 761
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.1313378130726939e-05,
+      "loss": 0.8345,
+      "step": 762
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.1301160659743432e-05,
+      "loss": 0.7377,
+      "step": 763
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1288943188759926e-05,
+      "loss": 0.8958,
+      "step": 764
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1276725717776423e-05,
+      "loss": 0.7704,
+      "step": 765
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.1264508246792916e-05,
+      "loss": 1.0557,
+      "step": 766
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.125229077580941e-05,
+      "loss": 0.5956,
+      "step": 767
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.1240073304825903e-05,
+      "loss": 0.92,
+      "step": 768
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.1227855833842396e-05,
+      "loss": 1.0114,
+      "step": 769
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.121563836285889e-05,
+      "loss": 0.9246,
+      "step": 770
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.1203420891875383e-05,
+      "loss": 0.8278,
+      "step": 771
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.1191203420891876e-05,
+      "loss": 0.9015,
+      "step": 772
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.117898594990837e-05,
+      "loss": 0.9138,
+      "step": 773
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.1166768478924863e-05,
+      "loss": 0.7906,
+      "step": 774
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.1154551007941357e-05,
+      "loss": 0.8134,
+      "step": 775
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.114233353695785e-05,
+      "loss": 1.4783,
+      "step": 776
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.1130116065974343e-05,
+      "loss": 1.1252,
+      "step": 777
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.1117898594990837e-05,
+      "loss": 0.9041,
+      "step": 778
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.110568112400733e-05,
+      "loss": 0.785,
+      "step": 779
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.1093463653023825e-05,
+      "loss": 0.8366,
+      "step": 780
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.1081246182040319e-05,
+      "loss": 0.9032,
+      "step": 781
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.1069028711056812e-05,
+      "loss": 0.92,
+      "step": 782
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.1056811240073305e-05,
+      "loss": 0.8575,
+      "step": 783
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.10445937690898e-05,
+      "loss": 0.726,
+      "step": 784
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.1032376298106294e-05,
+      "loss": 0.9062,
+      "step": 785
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.1020158827122787e-05,
+      "loss": 0.708,
+      "step": 786
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.100794135613928e-05,
+      "loss": 0.7986,
+      "step": 787
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.0995723885155774e-05,
+      "loss": 1.0306,
+      "step": 788
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0983506414172268e-05,
+      "loss": 0.7421,
+      "step": 789
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0971288943188761e-05,
+      "loss": 0.9103,
+      "step": 790
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0959071472205254e-05,
+      "loss": 1.7107,
+      "step": 791
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0946854001221748e-05,
+      "loss": 0.887,
+      "step": 792
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.0934636530238241e-05,
+      "loss": 0.8573,
+      "step": 793
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.0922419059254735e-05,
+      "loss": 0.7963,
+      "step": 794
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.091020158827123e-05,
+      "loss": 0.9545,
+      "step": 795
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.0897984117287723e-05,
+      "loss": 0.7702,
+      "step": 796
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.0885766646304216e-05,
+      "loss": 1.0585,
+      "step": 797
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.087354917532071e-05,
+      "loss": 0.8233,
+      "step": 798
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.0861331704337203e-05,
+      "loss": 0.7882,
+      "step": 799
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.0849114233353697e-05,
+      "loss": 0.7589,
+      "step": 800
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.083689676237019e-05,
+      "loss": 0.9228,
+      "step": 801
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.0824679291386684e-05,
+      "loss": 0.9933,
+      "step": 802
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.0812461820403177e-05,
+      "loss": 0.8297,
+      "step": 803
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.080024434941967e-05,
+      "loss": 0.7904,
+      "step": 804
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.0788026878436164e-05,
+      "loss": 1.239,
+      "step": 805
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.0775809407452657e-05,
+      "loss": 0.7186,
+      "step": 806
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.076359193646915e-05,
+      "loss": 1.0742,
+      "step": 807
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.0751374465485644e-05,
+      "loss": 0.6076,
+      "step": 808
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.0739156994502137e-05,
+      "loss": 0.7574,
+      "step": 809
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.0726939523518634e-05,
+      "loss": 0.7058,
+      "step": 810
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.0714722052535128e-05,
+      "loss": 0.7694,
+      "step": 811
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.0702504581551621e-05,
+      "loss": 0.6717,
+      "step": 812
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.0690287110568114e-05,
+      "loss": 1.0446,
+      "step": 813
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.0678069639584608e-05,
+      "loss": 0.8143,
+      "step": 814
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.0665852168601101e-05,
+      "loss": 0.8326,
+      "step": 815
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.0653634697617595e-05,
+      "loss": 1.0398,
+      "step": 816
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.0641417226634088e-05,
+      "loss": 0.6769,
+      "step": 817
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.0629199755650581e-05,
+      "loss": 0.8909,
+      "step": 818
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0616982284667075e-05,
+      "loss": 0.7196,
+      "step": 819
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0604764813683568e-05,
+      "loss": 0.6081,
+      "step": 820
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0592547342700062e-05,
+      "loss": 0.8479,
+      "step": 821
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.0580329871716555e-05,
+      "loss": 0.6626,
+      "step": 822
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.0568112400733048e-05,
+      "loss": 0.7727,
+      "step": 823
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.0555894929749542e-05,
+      "loss": 0.835,
+      "step": 824
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.0543677458766037e-05,
+      "loss": 1.5359,
+      "step": 825
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.053145998778253e-05,
+      "loss": 0.8521,
+      "step": 826
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.0519242516799024e-05,
+      "loss": 0.7732,
+      "step": 827
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.0507025045815517e-05,
+      "loss": 0.749,
+      "step": 828
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.049480757483201e-05,
+      "loss": 0.9086,
+      "step": 829
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.0482590103848504e-05,
+      "loss": 0.8064,
+      "step": 830
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.0470372632864997e-05,
+      "loss": 0.8561,
+      "step": 831
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.045815516188149e-05,
+      "loss": 1.0735,
+      "step": 832
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.0445937690897984e-05,
+      "loss": 0.7255,
+      "step": 833
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.0433720219914477e-05,
+      "loss": 1.054,
+      "step": 834
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.0421502748930973e-05,
+      "loss": 0.9361,
+      "step": 835
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.0409285277947466e-05,
+      "loss": 0.8865,
+      "step": 836
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.039706780696396e-05,
+      "loss": 0.916,
+      "step": 837
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.0384850335980453e-05,
+      "loss": 0.8838,
+      "step": 838
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.0372632864996946e-05,
+      "loss": 0.6332,
+      "step": 839
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0360415394013441e-05,
+      "loss": 0.7289,
+      "step": 840
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0348197923029935e-05,
+      "loss": 1.024,
+      "step": 841
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0335980452046428e-05,
+      "loss": 0.8003,
+      "step": 842
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.0323762981062921e-05,
+      "loss": 0.8745,
+      "step": 843
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.0311545510079415e-05,
+      "loss": 0.7543,
+      "step": 844
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.0299328039095908e-05,
+      "loss": 0.9404,
+      "step": 845
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.0287110568112402e-05,
+      "loss": 0.7756,
+      "step": 846
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.0274893097128895e-05,
+      "loss": 0.7677,
+      "step": 847
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.0262675626145388e-05,
+      "loss": 0.8376,
+      "step": 848
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.0250458155161882e-05,
+      "loss": 0.9447,
+      "step": 849
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.0238240684178375e-05,
+      "loss": 0.6205,
+      "step": 850
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.0226023213194869e-05,
+      "loss": 0.8075,
+      "step": 851
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.0213805742211362e-05,
+      "loss": 0.8011,
+      "step": 852
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.0201588271227855e-05,
+      "loss": 0.7242,
+      "step": 853
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.0189370800244349e-05,
+      "loss": 0.7785,
+      "step": 854
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.0177153329260846e-05,
+      "loss": 0.8389,
+      "step": 855
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.0164935858277339e-05,
+      "loss": 0.9529,
+      "step": 856
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.0152718387293832e-05,
+      "loss": 0.7059,
+      "step": 857
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.0140500916310326e-05,
+      "loss": 1.4115,
+      "step": 858
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.012828344532682e-05,
+      "loss": 0.8459,
+      "step": 859
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.0116065974343313e-05,
+      "loss": 1.2616,
+      "step": 860
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.0103848503359806e-05,
+      "loss": 0.8513,
+      "step": 861
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.00916310323763e-05,
+      "loss": 0.7815,
+      "step": 862
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.0079413561392793e-05,
+      "loss": 0.7323,
+      "step": 863
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.0067196090409286e-05,
+      "loss": 0.789,
+      "step": 864
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.005497861942578e-05,
+      "loss": 1.5127,
+      "step": 865
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.0042761148442273e-05,
+      "loss": 1.5117,
+      "step": 866
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.0030543677458766e-05,
+      "loss": 0.6835,
+      "step": 867
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.001832620647526e-05,
+      "loss": 0.7692,
+      "step": 868
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.0006108735491753e-05,
+      "loss": 0.6304,
+      "step": 869
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.993891264508248e-06,
+      "loss": 0.6418,
+      "step": 870
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.981673793524742e-06,
+      "loss": 0.8208,
+      "step": 871
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.969456322541235e-06,
+      "loss": 0.9958,
+      "step": 872
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 9.957238851557729e-06,
+      "loss": 0.9278,
+      "step": 873
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.945021380574222e-06,
+      "loss": 1.0567,
+      "step": 874
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.932803909590715e-06,
+      "loss": 0.8011,
+      "step": 875
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.920586438607209e-06,
+      "loss": 0.8224,
+      "step": 876
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 9.908368967623702e-06,
+      "loss": 0.8474,
+      "step": 877
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.896151496640196e-06,
+      "loss": 0.7681,
+      "step": 878
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.883934025656689e-06,
+      "loss": 0.7248,
+      "step": 879
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.871716554673182e-06,
+      "loss": 0.7187,
+      "step": 880
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.859499083689677e-06,
+      "loss": 0.7447,
+      "step": 881
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.847281612706171e-06,
+      "loss": 1.015,
+      "step": 882
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.835064141722664e-06,
+      "loss": 0.6698,
+      "step": 883
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.822846670739158e-06,
+      "loss": 0.7435,
+      "step": 884
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 9.810629199755651e-06,
+      "loss": 0.7527,
+      "step": 885
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.798411728772144e-06,
+      "loss": 0.5812,
+      "step": 886
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.786194257788638e-06,
+      "loss": 1.1017,
+      "step": 887
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.773976786805131e-06,
+      "loss": 0.8461,
+      "step": 888
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.761759315821626e-06,
+      "loss": 0.6109,
+      "step": 889
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 9.74954184483812e-06,
+      "loss": 0.8444,
+      "step": 890
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.737324373854613e-06,
+      "loss": 0.9308,
+      "step": 891
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.725106902871107e-06,
+      "loss": 0.7788,
+      "step": 892
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.7128894318876e-06,
+      "loss": 0.7444,
+      "step": 893
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 9.700671960904093e-06,
+      "loss": 0.7446,
+      "step": 894
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.688454489920587e-06,
+      "loss": 0.7429,
+      "step": 895
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.676237018937082e-06,
+      "loss": 0.6309,
+      "step": 896
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.664019547953575e-06,
+      "loss": 0.7665,
+      "step": 897
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 9.651802076970069e-06,
+      "loss": 0.6313,
+      "step": 898
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.639584605986562e-06,
+      "loss": 0.8622,
+      "step": 899
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.627367135003055e-06,
+      "loss": 0.6971,
+      "step": 900
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.615149664019549e-06,
+      "loss": 0.8956,
+      "step": 901
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 9.602932193036042e-06,
+      "loss": 0.9075,
+      "step": 902
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.590714722052536e-06,
+      "loss": 0.7028,
+      "step": 903
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.578497251069029e-06,
+      "loss": 0.5738,
+      "step": 904
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.566279780085524e-06,
+      "loss": 0.7779,
+      "step": 905
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.554062309102018e-06,
+      "loss": 0.5873,
+      "step": 906
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 9.541844838118511e-06,
+      "loss": 1.0006,
+      "step": 907
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.529627367135004e-06,
+      "loss": 1.0752,
+      "step": 908
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.517409896151498e-06,
+      "loss": 0.8232,
+      "step": 909
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.505192425167991e-06,
+      "loss": 0.7904,
+      "step": 910
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 9.492974954184485e-06,
+      "loss": 1.0862,
+      "step": 911
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.480757483200978e-06,
+      "loss": 0.7623,
+      "step": 912
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.468540012217471e-06,
+      "loss": 0.6963,
+      "step": 913
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.456322541233965e-06,
+      "loss": 0.96,
+      "step": 914
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 9.444105070250458e-06,
+      "loss": 0.5665,
+      "step": 915
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.431887599266952e-06,
+      "loss": 0.8081,
+      "step": 916
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.419670128283445e-06,
+      "loss": 0.7145,
+      "step": 917
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.407452657299938e-06,
+      "loss": 0.8547,
+      "step": 918
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 9.395235186316434e-06,
+      "loss": 0.9507,
+      "step": 919
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.383017715332927e-06,
+      "loss": 0.9185,
+      "step": 920
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.37080024434942e-06,
+      "loss": 0.6154,
+      "step": 921
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.358582773365914e-06,
+      "loss": 0.5515,
+      "step": 922
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.346365302382407e-06,
+      "loss": 0.6624,
+      "step": 923
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 9.3341478313989e-06,
+      "loss": 0.5877,
+      "step": 924
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.321930360415394e-06,
+      "loss": 0.7074,
+      "step": 925
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.309712889431889e-06,
+      "loss": 0.9121,
+      "step": 926
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.297495418448382e-06,
+      "loss": 0.8488,
+      "step": 927
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 9.285277947464876e-06,
+      "loss": 0.7679,
+      "step": 928
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.27306047648137e-06,
+      "loss": 0.8228,
+      "step": 929
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.260843005497863e-06,
+      "loss": 0.875,
+      "step": 930
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.248625534514356e-06,
+      "loss": 0.6674,
+      "step": 931
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 9.23640806353085e-06,
+      "loss": 0.6769,
+      "step": 932
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 9.224190592547343e-06,
+      "loss": 0.9607,
+      "step": 933
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 9.211973121563838e-06,
+      "loss": 0.8768,
+      "step": 934
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 9.199755650580331e-06,
+      "loss": 1.0233,
+      "step": 935
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 9.187538179596825e-06,
+      "loss": 0.928,
+      "step": 936
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 9.175320708613318e-06,
+      "loss": 0.9588,
+      "step": 937
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 9.163103237629812e-06,
+      "loss": 0.7672,
+      "step": 938
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 9.150885766646305e-06,
+      "loss": 0.6834,
+      "step": 939
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 9.138668295662798e-06,
+      "loss": 0.9839,
+      "step": 940
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 9.126450824679293e-06,
+      "loss": 0.8132,
+      "step": 941
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 9.114233353695787e-06,
+      "loss": 0.6736,
+      "step": 942
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 9.10201588271228e-06,
+      "loss": 0.7579,
+      "step": 943
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 9.089798411728774e-06,
+      "loss": 0.8888,
+      "step": 944
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 9.077580940745267e-06,
+      "loss": 0.6649,
+      "step": 945
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.06536346976176e-06,
+      "loss": 0.6923,
+      "step": 946
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.053145998778254e-06,
+      "loss": 0.787,
+      "step": 947
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.040928527794747e-06,
+      "loss": 1.0507,
+      "step": 948
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.02871105681124e-06,
+      "loss": 0.7555,
+      "step": 949
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 9.016493585827734e-06,
+      "loss": 0.6978,
+      "step": 950
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 9.004276114844227e-06,
+      "loss": 0.9231,
+      "step": 951
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 8.992058643860721e-06,
+      "loss": 0.9051,
+      "step": 952
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 8.979841172877214e-06,
+      "loss": 0.7771,
+      "step": 953
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.967623701893708e-06,
+      "loss": 0.7094,
+      "step": 954
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.955406230910201e-06,
+      "loss": 0.7884,
+      "step": 955
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.943188759926696e-06,
+      "loss": 0.6829,
+      "step": 956
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 8.93097128894319e-06,
+      "loss": 0.8024,
+      "step": 957
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.918753817959683e-06,
+      "loss": 0.6655,
+      "step": 958
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.906536346976176e-06,
+      "loss": 0.9103,
+      "step": 959
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.89431887599267e-06,
+      "loss": 0.7607,
+      "step": 960
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.882101405009163e-06,
+      "loss": 0.6788,
+      "step": 961
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 8.869883934025657e-06,
+      "loss": 0.5413,
+      "step": 962
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.85766646304215e-06,
+      "loss": 0.76,
+      "step": 963
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.845448992058645e-06,
+      "loss": 0.7689,
+      "step": 964
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.833231521075138e-06,
+      "loss": 0.8106,
+      "step": 965
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 8.821014050091632e-06,
+      "loss": 0.8543,
+      "step": 966
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.808796579108125e-06,
+      "loss": 0.7431,
+      "step": 967
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.796579108124619e-06,
+      "loss": 0.812,
+      "step": 968
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.784361637141112e-06,
+      "loss": 0.8223,
+      "step": 969
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 8.772144166157605e-06,
+      "loss": 0.7146,
+      "step": 970
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.7599266951741e-06,
+      "loss": 0.8914,
+      "step": 971
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.747709224190594e-06,
+      "loss": 0.797,
+      "step": 972
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.735491753207087e-06,
+      "loss": 0.6721,
+      "step": 973
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 8.72327428222358e-06,
+      "loss": 0.9,
+      "step": 974
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.711056811240074e-06,
+      "loss": 0.67,
+      "step": 975
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.698839340256568e-06,
+      "loss": 0.7884,
+      "step": 976
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.686621869273061e-06,
+      "loss": 0.7194,
+      "step": 977
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.674404398289554e-06,
+      "loss": 1.1244,
+      "step": 978
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 8.66218692730605e-06,
+      "loss": 0.8656,
+      "step": 979
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.649969456322543e-06,
+      "loss": 0.7089,
+      "step": 980
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.637751985339036e-06,
+      "loss": 0.9729,
+      "step": 981
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.62553451435553e-06,
+      "loss": 0.9135,
+      "step": 982
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 8.613317043372023e-06,
+      "loss": 0.8561,
+      "step": 983
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 8.601099572388516e-06,
+      "loss": 1.6011,
+      "step": 984
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 8.58888210140501e-06,
+      "loss": 0.7282,
+      "step": 985
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 8.576664630421503e-06,
+      "loss": 0.7882,
+      "step": 986
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 8.564447159437997e-06,
+      "loss": 0.8559,
+      "step": 987
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.55222968845449e-06,
+      "loss": 0.62,
+      "step": 988
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.540012217470983e-06,
+      "loss": 0.6588,
+      "step": 989
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.527794746487477e-06,
+      "loss": 0.7994,
+      "step": 990
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 8.515577275503972e-06,
+      "loss": 0.9582,
+      "step": 991
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.503359804520465e-06,
+      "loss": 0.9456,
+      "step": 992
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.491142333536959e-06,
+      "loss": 0.7995,
+      "step": 993
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.478924862553452e-06,
+      "loss": 0.8144,
+      "step": 994
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 8.466707391569946e-06,
+      "loss": 0.851,
+      "step": 995
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.454489920586439e-06,
+      "loss": 1.0865,
+      "step": 996
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.442272449602932e-06,
+      "loss": 0.8716,
+      "step": 997
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.430054978619426e-06,
+      "loss": 1.687,
+      "step": 998
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.41783750763592e-06,
+      "loss": 0.6964,
+      "step": 999
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 8.405620036652413e-06,
+      "loss": 1.0146,
+      "step": 1000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.393402565668908e-06,
+      "loss": 0.6478,
+      "step": 1001
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.381185094685401e-06,
+      "loss": 0.5895,
+      "step": 1002
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.368967623701895e-06,
+      "loss": 0.8438,
+      "step": 1003
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 8.356750152718388e-06,
+      "loss": 0.7302,
+      "step": 1004
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.344532681734881e-06,
+      "loss": 0.9506,
+      "step": 1005
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.332315210751375e-06,
+      "loss": 1.1109,
+      "step": 1006
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.320097739767868e-06,
+      "loss": 0.74,
+      "step": 1007
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 8.307880268784362e-06,
+      "loss": 0.8107,
+      "step": 1008
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.295662797800857e-06,
+      "loss": 0.7339,
+      "step": 1009
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.28344532681735e-06,
+      "loss": 0.6967,
+      "step": 1010
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.271227855833843e-06,
+      "loss": 0.6767,
+      "step": 1011
+    },
+    {
+      "epoch": 2.39,
+      "learning_rate": 8.259010384850337e-06,
+      "loss": 0.7822,
+      "step": 1012
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.24679291386683e-06,
+      "loss": 0.7417,
+      "step": 1013
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.234575442883324e-06,
+      "loss": 0.6725,
+      "step": 1014
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.222357971899817e-06,
+      "loss": 0.7013,
+      "step": 1015
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.210140500916312e-06,
+      "loss": 0.8832,
+      "step": 1016
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 8.197923029932806e-06,
+      "loss": 0.9696,
+      "step": 1017
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 8.185705558949299e-06,
+      "loss": 1.0827,
+      "step": 1018
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 8.173488087965792e-06,
+      "loss": 0.78,
+      "step": 1019
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 8.161270616982286e-06,
+      "loss": 0.9643,
+      "step": 1020
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 8.149053145998779e-06,
+      "loss": 0.7627,
+      "step": 1021
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 8.136835675015273e-06,
+      "loss": 0.6634,
+      "step": 1022
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 8.124618204031766e-06,
+      "loss": 0.8787,
+      "step": 1023
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 8.11240073304826e-06,
+      "loss": 0.9677,
+      "step": 1024
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 8.100183262064754e-06,
+      "loss": 0.8346,
+      "step": 1025
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 8.087965791081248e-06,
+      "loss": 0.824,
+      "step": 1026
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 8.075748320097741e-06,
+      "loss": 0.7037,
+      "step": 1027
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 8.063530849114235e-06,
+      "loss": 0.7988,
+      "step": 1028
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 8.051313378130728e-06,
+      "loss": 0.7762,
+      "step": 1029
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.039095907147221e-06,
+      "loss": 0.9513,
+      "step": 1030
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.026878436163715e-06,
+      "loss": 0.6713,
+      "step": 1031
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.014660965180208e-06,
+      "loss": 0.6979,
+      "step": 1032
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 8.002443494196702e-06,
+      "loss": 1.0106,
+      "step": 1033
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 7.990226023213195e-06,
+      "loss": 0.756,
+      "step": 1034
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.978008552229688e-06,
+      "loss": 0.9929,
+      "step": 1035
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.965791081246182e-06,
+      "loss": 0.8362,
+      "step": 1036
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.953573610262675e-06,
+      "loss": 0.9016,
+      "step": 1037
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 7.941356139279169e-06,
+      "loss": 0.7216,
+      "step": 1038
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.929138668295664e-06,
+      "loss": 0.8508,
+      "step": 1039
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.916921197312157e-06,
+      "loss": 0.5999,
+      "step": 1040
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.90470372632865e-06,
+      "loss": 0.64,
+      "step": 1041
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 7.892486255345144e-06,
+      "loss": 1.0262,
+      "step": 1042
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.880268784361637e-06,
+      "loss": 0.7194,
+      "step": 1043
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.86805131337813e-06,
+      "loss": 0.8673,
+      "step": 1044
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.855833842394624e-06,
+      "loss": 0.9482,
+      "step": 1045
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 7.84361637141112e-06,
+      "loss": 0.9424,
+      "step": 1046
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.831398900427613e-06,
+      "loss": 0.8499,
+      "step": 1047
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.819181429444106e-06,
+      "loss": 0.7288,
+      "step": 1048
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.8069639584606e-06,
+      "loss": 0.6901,
+      "step": 1049
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 7.794746487477093e-06,
+      "loss": 0.6685,
+      "step": 1050
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.782529016493586e-06,
+      "loss": 1.138,
+      "step": 1051
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.77031154551008e-06,
+      "loss": 0.8116,
+      "step": 1052
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.758094074526573e-06,
+      "loss": 0.8918,
+      "step": 1053
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.745876603543068e-06,
+      "loss": 0.8731,
+      "step": 1054
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 7.733659132559562e-06,
+      "loss": 0.7784,
+      "step": 1055
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.721441661576055e-06,
+      "loss": 0.6612,
+      "step": 1056
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.709224190592548e-06,
+      "loss": 0.8031,
+      "step": 1057
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.697006719609042e-06,
+      "loss": 0.6725,
+      "step": 1058
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 7.684789248625535e-06,
+      "loss": 0.8463,
+      "step": 1059
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.672571777642029e-06,
+      "loss": 0.77,
+      "step": 1060
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.660354306658524e-06,
+      "loss": 0.711,
+      "step": 1061
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.648136835675017e-06,
+      "loss": 1.0855,
+      "step": 1062
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 7.63591936469151e-06,
+      "loss": 0.85,
+      "step": 1063
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.623701893708003e-06,
+      "loss": 0.6199,
+      "step": 1064
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.611484422724496e-06,
+      "loss": 0.6982,
+      "step": 1065
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.59926695174099e-06,
+      "loss": 0.9263,
+      "step": 1066
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.587049480757483e-06,
+      "loss": 0.713,
+      "step": 1067
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.574832009773977e-06,
+      "loss": 1.5352,
+      "step": 1068
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.562614538790472e-06,
+      "loss": 0.6505,
+      "step": 1069
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.550397067806965e-06,
+      "loss": 0.9456,
+      "step": 1070
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.5381795968234585e-06,
+      "loss": 0.6478,
+      "step": 1071
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.525962125839952e-06,
+      "loss": 0.5866,
+      "step": 1072
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.513744654856445e-06,
+      "loss": 0.6796,
+      "step": 1073
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.501527183872939e-06,
+      "loss": 0.8093,
+      "step": 1074
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.489309712889432e-06,
+      "loss": 0.8077,
+      "step": 1075
+    },
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.4770922419059255e-06,
+      "loss": 0.7468,
+      "step": 1076
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.46487477092242e-06,
+      "loss": 0.9059,
+      "step": 1077
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.452657299938913e-06,
+      "loss": 1.0124,
+      "step": 1078
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.440439828955407e-06,
+      "loss": 0.8665,
+      "step": 1079
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.4282223579719e-06,
+      "loss": 0.7768,
+      "step": 1080
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.416004886988394e-06,
+      "loss": 0.83,
+      "step": 1081
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.403787416004888e-06,
+      "loss": 0.8671,
+      "step": 1082
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.391569945021381e-06,
+      "loss": 0.9012,
+      "step": 1083
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.379352474037875e-06,
+      "loss": 0.9677,
+      "step": 1084
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.367135003054369e-06,
+      "loss": 0.9414,
+      "step": 1085
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.354917532070862e-06,
+      "loss": 1.2184,
+      "step": 1086
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.3427000610873555e-06,
+      "loss": 0.9328,
+      "step": 1087
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.330482590103849e-06,
+      "loss": 1.4059,
+      "step": 1088
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.318265119120342e-06,
+      "loss": 0.6708,
+      "step": 1089
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.306047648136836e-06,
+      "loss": 0.894,
+      "step": 1090
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.293830177153329e-06,
+      "loss": 0.9659,
+      "step": 1091
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.281612706169824e-06,
+      "loss": 1.1613,
+      "step": 1092
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.269395235186318e-06,
+      "loss": 0.7924,
+      "step": 1093
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.257177764202811e-06,
+      "loss": 0.7787,
+      "step": 1094
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.244960293219304e-06,
+      "loss": 0.7545,
+      "step": 1095
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.232742822235798e-06,
+      "loss": 0.783,
+      "step": 1096
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 7.220525351252291e-06,
+      "loss": 0.7565,
+      "step": 1097
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.208307880268785e-06,
+      "loss": 0.8512,
+      "step": 1098
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.196090409285279e-06,
+      "loss": 0.9638,
+      "step": 1099
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.183872938301772e-06,
+      "loss": 0.8976,
+      "step": 1100
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 7.171655467318266e-06,
+      "loss": 0.9743,
+      "step": 1101
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 7.159437996334759e-06,
+      "loss": 0.8234,
+      "step": 1102
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 7.1472205253512525e-06,
+      "loss": 0.9169,
+      "step": 1103
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 7.135003054367746e-06,
+      "loss": 0.9243,
+      "step": 1104
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 7.122785583384239e-06,
+      "loss": 0.8588,
+      "step": 1105
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.110568112400733e-06,
+      "loss": 1.0318,
+      "step": 1106
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.098350641417228e-06,
+      "loss": 0.7434,
+      "step": 1107
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.086133170433721e-06,
+      "loss": 0.6608,
+      "step": 1108
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.0739156994502146e-06,
+      "loss": 1.1173,
+      "step": 1109
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 7.061698228466708e-06,
+      "loss": 0.7802,
+      "step": 1110
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.049480757483201e-06,
+      "loss": 0.7761,
+      "step": 1111
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.037263286499695e-06,
+      "loss": 0.8065,
+      "step": 1112
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.025045815516188e-06,
+      "loss": 0.631,
+      "step": 1113
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 7.012828344532682e-06,
+      "loss": 0.654,
+      "step": 1114
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.000610873549176e-06,
+      "loss": 0.7289,
+      "step": 1115
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.98839340256567e-06,
+      "loss": 0.7963,
+      "step": 1116
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.9761759315821635e-06,
+      "loss": 0.7764,
+      "step": 1117
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.963958460598657e-06,
+      "loss": 0.7577,
+      "step": 1118
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.95174098961515e-06,
+      "loss": 0.9212,
+      "step": 1119
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.939523518631644e-06,
+      "loss": 0.5796,
+      "step": 1120
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.927306047648137e-06,
+      "loss": 0.7637,
+      "step": 1121
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.915088576664631e-06,
+      "loss": 0.8283,
+      "step": 1122
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.902871105681125e-06,
+      "loss": 0.8477,
+      "step": 1123
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.890653634697618e-06,
+      "loss": 0.7342,
+      "step": 1124
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.8784361637141115e-06,
+      "loss": 0.9373,
+      "step": 1125
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.866218692730605e-06,
+      "loss": 0.7735,
+      "step": 1126
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 6.854001221747098e-06,
+      "loss": 0.691,
+      "step": 1127
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.841783750763592e-06,
+      "loss": 0.6959,
+      "step": 1128
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.829566279780087e-06,
+      "loss": 0.8995,
+      "step": 1129
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.81734880879658e-06,
+      "loss": 0.8236,
+      "step": 1130
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.805131337813074e-06,
+      "loss": 1.0626,
+      "step": 1131
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.792913866829567e-06,
+      "loss": 0.8178,
+      "step": 1132
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.7806963958460604e-06,
+      "loss": 0.6962,
+      "step": 1133
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.768478924862554e-06,
+      "loss": 0.7438,
+      "step": 1134
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 6.756261453879047e-06,
+      "loss": 0.6812,
+      "step": 1135
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.744043982895541e-06,
+      "loss": 0.7409,
+      "step": 1136
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.731826511912035e-06,
+      "loss": 0.7953,
+      "step": 1137
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.719609040928528e-06,
+      "loss": 0.8024,
+      "step": 1138
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 6.707391569945022e-06,
+      "loss": 0.887,
+      "step": 1139
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.695174098961515e-06,
+      "loss": 0.6614,
+      "step": 1140
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.682956627978009e-06,
+      "loss": 0.8199,
+      "step": 1141
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.670739156994503e-06,
+      "loss": 0.6941,
+      "step": 1142
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 6.658521686010996e-06,
+      "loss": 0.7043,
+      "step": 1143
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.64630421502749e-06,
+      "loss": 0.8566,
+      "step": 1144
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.634086744043984e-06,
+      "loss": 0.8391,
+      "step": 1145
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.621869273060477e-06,
+      "loss": 0.8533,
+      "step": 1146
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.609651802076971e-06,
+      "loss": 1.2669,
+      "step": 1147
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 6.597434331093464e-06,
+      "loss": 0.7494,
+      "step": 1148
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.585216860109957e-06,
+      "loss": 0.8497,
+      "step": 1149
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.572999389126451e-06,
+      "loss": 0.8414,
+      "step": 1150
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.560781918142944e-06,
+      "loss": 0.7205,
+      "step": 1151
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 6.548564447159439e-06,
+      "loss": 0.9299,
+      "step": 1152
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.536346976175933e-06,
+      "loss": 0.83,
+      "step": 1153
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.524129505192426e-06,
+      "loss": 0.7246,
+      "step": 1154
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.5119120342089195e-06,
+      "loss": 0.8512,
+      "step": 1155
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 6.499694563225413e-06,
+      "loss": 0.8825,
+      "step": 1156
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.487477092241906e-06,
+      "loss": 0.7143,
+      "step": 1157
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.4752596212584e-06,
+      "loss": 1.5558,
+      "step": 1158
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.463042150274894e-06,
+      "loss": 0.9596,
+      "step": 1159
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 6.450824679291387e-06,
+      "loss": 0.9285,
+      "step": 1160
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.438607208307881e-06,
+      "loss": 0.8805,
+      "step": 1161
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.426389737324374e-06,
+      "loss": 0.9199,
+      "step": 1162
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.4141722663408676e-06,
+      "loss": 0.743,
+      "step": 1163
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.401954795357361e-06,
+      "loss": 0.7258,
+      "step": 1164
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 6.389737324373854e-06,
+      "loss": 0.718,
+      "step": 1165
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 6.377519853390348e-06,
+      "loss": 0.7674,
+      "step": 1166
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 6.365302382406843e-06,
+      "loss": 0.7796,
+      "step": 1167
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 6.353084911423336e-06,
+      "loss": 0.787,
+      "step": 1168
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 6.34086744043983e-06,
+      "loss": 0.9145,
+      "step": 1169
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.328649969456323e-06,
+      "loss": 0.7143,
+      "step": 1170
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.3164324984728165e-06,
+      "loss": 0.657,
+      "step": 1171
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.30421502748931e-06,
+      "loss": 1.8791,
+      "step": 1172
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 6.291997556505803e-06,
+      "loss": 0.8549,
+      "step": 1173
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.2797800855222975e-06,
+      "loss": 0.7444,
+      "step": 1174
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.267562614538791e-06,
+      "loss": 0.6989,
+      "step": 1175
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.255345143555285e-06,
+      "loss": 0.8571,
+      "step": 1176
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 6.243127672571779e-06,
+      "loss": 0.9245,
+      "step": 1177
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.230910201588272e-06,
+      "loss": 0.8139,
+      "step": 1178
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.218692730604765e-06,
+      "loss": 0.956,
+      "step": 1179
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.206475259621259e-06,
+      "loss": 0.9109,
+      "step": 1180
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.194257788637752e-06,
+      "loss": 0.872,
+      "step": 1181
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 6.1820403176542464e-06,
+      "loss": 0.8997,
+      "step": 1182
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 6.16982284667074e-06,
+      "loss": 0.6255,
+      "step": 1183
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 6.157605375687233e-06,
+      "loss": 0.858,
+      "step": 1184
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 6.145387904703727e-06,
+      "loss": 0.5873,
+      "step": 1185
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 6.13317043372022e-06,
+      "loss": 1.1229,
+      "step": 1186
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 6.1209529627367134e-06,
+      "loss": 0.7146,
+      "step": 1187
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 6.108735491753207e-06,
+      "loss": 0.7202,
+      "step": 1188
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 6.096518020769702e-06,
+      "loss": 0.6488,
+      "step": 1189
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 6.084300549786195e-06,
+      "loss": 0.7713,
+      "step": 1190
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 6.072083078802689e-06,
+      "loss": 0.7512,
+      "step": 1191
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 6.059865607819182e-06,
+      "loss": 0.9244,
+      "step": 1192
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 6.0476481368356755e-06,
+      "loss": 0.86,
+      "step": 1193
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 6.035430665852169e-06,
+      "loss": 0.9469,
+      "step": 1194
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 6.023213194868662e-06,
+      "loss": 0.7904,
+      "step": 1195
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 6.010995723885156e-06,
+      "loss": 0.7472,
+      "step": 1196
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 5.99877825290165e-06,
+      "loss": 0.9277,
+      "step": 1197
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 5.986560781918143e-06,
+      "loss": 0.6782,
+      "step": 1198
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.974343310934637e-06,
+      "loss": 0.8162,
+      "step": 1199
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.96212583995113e-06,
+      "loss": 0.7205,
+      "step": 1200
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.949908368967624e-06,
+      "loss": 0.7009,
+      "step": 1201
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.937690897984118e-06,
+      "loss": 0.8698,
+      "step": 1202
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 5.925473427000611e-06,
+      "loss": 0.7732,
+      "step": 1203
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.9132559560171055e-06,
+      "loss": 0.9915,
+      "step": 1204
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.901038485033599e-06,
+      "loss": 0.8665,
+      "step": 1205
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.888821014050092e-06,
+      "loss": 0.8814,
+      "step": 1206
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.876603543066586e-06,
+      "loss": 0.7158,
+      "step": 1207
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.864386072083079e-06,
+      "loss": 0.7831,
+      "step": 1208
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.8521686010995725e-06,
+      "loss": 0.77,
+      "step": 1209
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.839951130116066e-06,
+      "loss": 0.5111,
+      "step": 1210
+    },
+    {
+      "epoch": 2.86,
+      "learning_rate": 5.827733659132559e-06,
+      "loss": 0.7871,
+      "step": 1211
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.815516188149054e-06,
+      "loss": 0.6702,
+      "step": 1212
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.803298717165548e-06,
+      "loss": 1.0326,
+      "step": 1213
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.791081246182041e-06,
+      "loss": 0.7943,
+      "step": 1214
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 5.778863775198535e-06,
+      "loss": 0.8289,
+      "step": 1215
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.766646304215028e-06,
+      "loss": 0.7806,
+      "step": 1216
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.754428833231521e-06,
+      "loss": 0.9023,
+      "step": 1217
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.742211362248015e-06,
+      "loss": 0.8285,
+      "step": 1218
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.729993891264509e-06,
+      "loss": 0.9523,
+      "step": 1219
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 5.7177764202810025e-06,
+      "loss": 0.6429,
+      "step": 1220
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.705558949297496e-06,
+      "loss": 0.9859,
+      "step": 1221
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.693341478313989e-06,
+      "loss": 0.651,
+      "step": 1222
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.681124007330483e-06,
+      "loss": 0.7305,
+      "step": 1223
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 5.668906536346976e-06,
+      "loss": 0.8412,
+      "step": 1224
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.6566890653634695e-06,
+      "loss": 0.6617,
+      "step": 1225
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.644471594379963e-06,
+      "loss": 0.7505,
+      "step": 1226
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.632254123396458e-06,
+      "loss": 0.7157,
+      "step": 1227
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 5.620036652412951e-06,
+      "loss": 0.921,
+      "step": 1228
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.607819181429445e-06,
+      "loss": 0.8239,
+      "step": 1229
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.595601710445938e-06,
+      "loss": 0.8042,
+      "step": 1230
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.583384239462432e-06,
+      "loss": 0.7872,
+      "step": 1231
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 5.571166768478925e-06,
+      "loss": 0.681,
+      "step": 1232
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.558949297495418e-06,
+      "loss": 1.2147,
+      "step": 1233
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.546731826511913e-06,
+      "loss": 0.912,
+      "step": 1234
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.534514355528406e-06,
+      "loss": 0.7043,
+      "step": 1235
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.5222968845449e-06,
+      "loss": 0.7897,
+      "step": 1236
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 5.510079413561394e-06,
+      "loss": 0.8611,
+      "step": 1237
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.497861942577887e-06,
+      "loss": 0.8145,
+      "step": 1238
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.4856444715943805e-06,
+      "loss": 0.8213,
+      "step": 1239
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.473427000610874e-06,
+      "loss": 0.7965,
+      "step": 1240
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 5.461209529627367e-06,
+      "loss": 0.9655,
+      "step": 1241
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.4489920586438615e-06,
+      "loss": 0.9367,
+      "step": 1242
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.436774587660355e-06,
+      "loss": 0.8931,
+      "step": 1243
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.424557116676848e-06,
+      "loss": 0.9453,
+      "step": 1244
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 5.412339645693342e-06,
+      "loss": 1.0025,
+      "step": 1245
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.400122174709835e-06,
+      "loss": 0.8127,
+      "step": 1246
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.3879047037263286e-06,
+      "loss": 1.0161,
+      "step": 1247
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.375687232742822e-06,
+      "loss": 0.8223,
+      "step": 1248
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 5.363469761759317e-06,
+      "loss": 0.6127,
+      "step": 1249
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.3512522907758105e-06,
+      "loss": 0.5526,
+      "step": 1250
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.339034819792304e-06,
+      "loss": 0.7488,
+      "step": 1251
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.326817348808797e-06,
+      "loss": 0.7872,
+      "step": 1252
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 5.314599877825291e-06,
+      "loss": 0.8655,
+      "step": 1253
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.302382406841784e-06,
+      "loss": 0.878,
+      "step": 1254
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.2901649358582775e-06,
+      "loss": 0.9551,
+      "step": 1255
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.277947464874771e-06,
+      "loss": 0.7852,
+      "step": 1256
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.265729993891265e-06,
+      "loss": 0.5514,
+      "step": 1257
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 5.2535125229077585e-06,
+      "loss": 0.8453,
+      "step": 1258
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.241295051924252e-06,
+      "loss": 0.837,
+      "step": 1259
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.229077580940745e-06,
+      "loss": 0.8556,
+      "step": 1260
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.216860109957239e-06,
+      "loss": 0.927,
+      "step": 1261
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 5.204642638973733e-06,
+      "loss": 0.7956,
+      "step": 1262
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.192425167990226e-06,
+      "loss": 0.7326,
+      "step": 1263
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.180207697006721e-06,
+      "loss": 0.7901,
+      "step": 1264
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.167990226023214e-06,
+      "loss": 0.9212,
+      "step": 1265
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.155772755039707e-06,
+      "loss": 1.024,
+      "step": 1266
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.143555284056201e-06,
+      "loss": 0.4996,
+      "step": 1267
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 5.131337813072694e-06,
+      "loss": 0.7015,
+      "step": 1268
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 1688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 6.092207610386186e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}