首页 - 技术栈

呼伦贝尔网站设计百度中搜到网站名字

作者: 五速梦信息网
时间: 2026年03月21日 10:53

当前位置：首页 > news >正文

呼伦贝尔网站设计,百度中搜到网站名字,深圳网站建设猴王网络,周大福网站建设主要工作模型微调#xff08;fine-tune)-迁移学习 torchvision微调timm微调半精度训练起源#xff1a; 1、随着深度学习的发展#xff0c;模型的参数越来越大#xff0c;许多开源模型都是在较大数据集上进行训练的#xff0c;比如Imagenet-1k#xff0c;Imagenet-11k等2、如果…模型微调fine-tune)-迁移学习 torchvision微调timm微调半精度训练起源 1、随着深度学习的发展模型的参数越来越大许多开源模型都是在较大数据集上进行训练的比如Imagenet-1kImagenet-11k等2、如果数据集可能只有几千张训练几千万参数的大模型过拟合无法避免3、如果我们想从零开始训练一个大模型那么我们的解决办法是收集更多的数据。然而收集和标注数据会花费大量的时间和资⾦成本无法承受解决方案应用迁移学习(transfer learning)将从源数据集学到的知识迁移到目标数据集上比如ImageNet数据集的图像大多跟椅子无关但在该数据集上训练的模型可以抽取较通用的图像特征从而能够帮助识别边缘、纹理、形状和物体组成模型微调finetune:就是先找到一个同类的别人训练好的模型基于已经训练好的模型换成自己的数据通过训练调整一下参数不同数据集下使用微调数据集1 - 数据量少但数据相似度非常高 - 在这种情况下我们所做的只是修改最后几层或最终的softmax图层的输出类别。数据集2 - 数据量少数据相似度低 - 在这种情况下我们可以冻结预训练模型的初始层比如k层并再次训练剩余的n-k层。由于新数据集的相似度较低因此根据新数据集对较高层进行重新训练具有重要意义。数据集3 - 数据量大数据相似度低 - 在这种情况下由于我们有一个大的数据集我们的神经网络训练将会很有效。但是由于我们的数据与用于训练我们的预训练模型的数据相比有很大不同。使用预训练模型进行的预测不会有效。因此最好根据你的数据从头开始训练神经网络Training from scatch 数据集4 - 数据量大数据相似度高 - 这是理想情况。在这种情况下预训练模型应该是最有效的。使用模型的最好方法是保留模型的体系结构和模型的初始权重。然后我们可以使用在预先训练的模型中的权重来重新训练该模型。
微调的是什么换数据源针对K层进行重新训练K层的权重shape调整 1、模型微调(fine-tune)一般流程 1、在源数据集(如ImageNet数据集)上预训练一个神经网络模型即源模型2、创建一个新的神经网络模型即目标模型它复制了源模型上除了输出层外的所有模型设计及其参数3、为目标模型添加一个输出⼤小为⽬标数据集类别个数的输出层并随机初始化该层的模型参数4、在目标数据集上训练目标模型。我们将从头训练输出层而其余层的参数都是基于源模型的参数微调得到的 [外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-xfegFfaM-1692613842808)(attachment:image.png)] 2、torchvision微调 2.1 实例化Model import torchvision.models as models resnet34 models.resnet34(pretrainedTrue)pretrained参数说明 1、通过True或者False来决定是否使用预训练好的权重在默认状态下pretrained False意味着我们不使用预训练得到的权重2、当pretrained True意味着我们将使用在一些数据集上预训练得到的权重注意如果中途强行停止下载的话一定要去对应路径下将权重文件删除干净否则会报错。 2.2 训练特定层如果我们正在提取特征并且只想为新初始化的层计算梯度其他参数不进行改变。那我们就需要通过设置requires_grad False来冻结部分层 def set_parameter_requires_grad(model, feature_extracting):if feature_extracting:for param in model.parameters():param.requires_grad False2.3 实例使用resnet34为例的将1000类改为10类但是仅改变最后一层的模型参数我们先冻结模型参数的梯度再对模型输出部分的全连接层进行修改 import torch import torch.nn.functional as F import torch.nn as nn from torch.optim.lr_scheduler import LambdaLR from torch.optim.lr_scheduler import StepLR import torchvision from torch.utils.data import Dataset, DataLoader from torchvision.transforms import transforms from torch.utils.tensorboard import SummaryWriter import numpy as np import torchvision.models as models from torchinfo import summary#超参数定义

批次的大小

batch_size 16 #可选32、64、128

优化器的学习率

lr 1e-4 #运行epoch max_epochs 2

方案二使用“device”后续对要使用GPU的变量用.to(device)即可

device torch.device(cuda:1 if torch.cuda.is_available() else cpu) # 数据读取 #cifar10数据集为例给出构建Dataset类的方式 from torchvision import datasets#“data_transform”可以对图像进行一定的变换如翻转、裁剪、归一化等操作可自己定义 data_transformtransforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))])train_cifar_dataset datasets.CIFAR10(cifar10,trainTrue, downloadFalse,transformdata_transform) test_cifar_dataset datasets.CIFAR10(cifar10,trainFalse, downloadFalse,transformdata_transform)#构建好Dataset后就可以使用DataLoader来按批次读入数据了 train_loader torch.utils.data.DataLoader(train_cifar_dataset, batch_sizebatch_size, num_workers4, shuffleTrue, drop_lastTrue)test_loader torch.utils.data.DataLoader(test_cifar_dataset, batch_sizebatch_size, num_workers4, shuffleFalse)

下载预训练模型 restnet50

resnet34 models.resnet34(pretrainedTrue) print(resnet34)D:\Users\xulele\Anaconda3\lib\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter pretrained is deprecated since 0.13 and may be removed in the future, please use weights instead.warnings.warn( D:\Users\xulele\Anaconda3\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for weights are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weightsResNet34_Weights.IMAGENET1K_V1. You can also use weightsResNet34_Weights.DEFAULT to get the most up-to-date weights.warnings.warn(msg) Downloading: https://download.pytorch.org/models/resnet34-b627a593.pth to C:\Users\xulele/.cache\torch\hub\checkpoints\resnet34-b627a593.pth 100%|██████████| 83.3M/83.3M [00:1000:00, 8.57MB/s]ResNet((conv1): Conv2d(3, 64, kernel_size(7, 7), stride(2, 2), padding(3, 3), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(maxpool): MaxPool2d(kernel_size3, stride2, padding1, dilation1, ceil_modeFalse)(layer1): Sequential((0): BasicBlock((conv1): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(1): BasicBlock((conv1): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(2): BasicBlock((conv1): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(64, 64, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(64, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(layer2): Sequential((0): BasicBlock((conv1): Conv2d(64, 128, kernel_size(3, 3), stride(2, 2), padding(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(downsample): Sequential((0): Conv2d(64, 128, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): BasicBlock((conv1): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(2): BasicBlock((conv1): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(3): BasicBlock((conv1): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(128, 128, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(128, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(layer3): Sequential((0): BasicBlock((conv1): Conv2d(128, 256, kernel_size(3, 3), stride(2, 2), padding(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(downsample): Sequential((0): Conv2d(128, 256, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): BasicBlock((conv1): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(2): BasicBlock((conv1): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(3): BasicBlock((conv1): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(4): BasicBlock((conv1): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(5): BasicBlock((conv1): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(256, 256, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(256, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(layer4): Sequential((0): BasicBlock((conv1): Conv2d(256, 512, kernel_size(3, 3), stride(2, 2), padding(1, 1), biasFalse)(bn1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(downsample): Sequential((0): Conv2d(256, 512, kernel_size(1, 1), stride(2, 2), biasFalse)(1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(1): BasicBlock((conv1): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue))(2): BasicBlock((conv1): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn1): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)(relu): ReLU(inplaceTrue)(conv2): Conv2d(512, 512, kernel_size(3, 3), stride(1, 1), padding(1, 1), biasFalse)(bn2): BatchNorm2d(512, eps1e-05, momentum0.1, affineTrue, track_running_statsTrue)))(avgpool): AdaptiveAvgPool2d(output_size(1, 1))(fc): Linear(in_features512, out_features1000, biasTrue) )#查看模型结构 summary(resnet34, (1, 3, 224, 224)) Layer (type:depth-idx) Output Shape Param #ResNet [1, 1000] – ├─Conv2d: 1-1 [1, 64, 112, 112] 9,408 ├─BatchNorm2d: 1-2 [1, 64, 112, 112] 128 ├─ReLU: 1-3 [1, 64, 112, 112] – ├─MaxPool2d: 1-4 [1, 64, 56, 56] – ├─Sequential: 1-5 [1, 64, 56, 56] – │ └─BasicBlock: 2-1 [1, 64, 56, 56] – │ │ └─Conv2d: 3-1 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-2 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-3 [1, 64, 56, 56] – │ │ └─Conv2d: 3-4 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-5 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-6 [1, 64, 56, 56] – │ └─BasicBlock: 2-2 [1, 64, 56, 56] – │ │ └─Conv2d: 3-7 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-8 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-9 [1, 64, 56, 56] – │ │ └─Conv2d: 3-10 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-11 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-12 [1, 64, 56, 56] – │ └─BasicBlock: 2-3 [1, 64, 56, 56] – │ │ └─Conv2d: 3-13 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-14 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-15 [1, 64, 56, 56] – │ │ └─Conv2d: 3-16 [1, 64, 56, 56] 36,864 │ │ └─BatchNorm2d: 3-17 [1, 64, 56, 56] 128 │ │ └─ReLU: 3-18 [1, 64, 56, 56] – ├─Sequential: 1-6 [1, 128, 28, 28] – │ └─BasicBlock: 2-4 [1, 128, 28, 28] – │ │ └─Conv2d: 3-19 [1, 128, 28, 28] 73,728 │ │ └─BatchNorm2d: 3-20 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-21 [1, 128, 28, 28] – │ │ └─Conv2d: 3-22 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-23 [1, 128, 28, 28] 256 │ │ └─Sequential: 3-24 [1, 128, 28, 28] 8,448 │ │ └─ReLU: 3-25 [1, 128, 28, 28] – │ └─BasicBlock: 2-5 [1, 128, 28, 28] – │ │ └─Conv2d: 3-26 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-27 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-28 [1, 128, 28, 28] – │ │ └─Conv2d: 3-29 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-30 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-31 [1, 128, 28, 28] – │ └─BasicBlock: 2-6 [1, 128, 28, 28] – │ │ └─Conv2d: 3-32 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-33 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-34 [1, 128, 28, 28] – │ │ └─Conv2d: 3-35 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-36 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-37 [1, 128, 28, 28] – │ └─BasicBlock: 2-7 [1, 128, 28, 28] – │ │ └─Conv2d: 3-38 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-39 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-40 [1, 128, 28, 28] – │ │ └─Conv2d: 3-41 [1, 128, 28, 28] 147,456 │ │ └─BatchNorm2d: 3-42 [1, 128, 28, 28] 256 │ │ └─ReLU: 3-43 [1, 128, 28, 28] – ├─Sequential: 1-7 [1, 256, 14, 14] – │ └─BasicBlock: 2-8 [1, 256, 14, 14] – │ │ └─Conv2d: 3-44 [1, 256, 14, 14] 294,912 │ │ └─BatchNorm2d: 3-45 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-46 [1, 256, 14, 14] – │ │ └─Conv2d: 3-47 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-48 [1, 256, 14, 14] 512 │ │ └─Sequential: 3-49 [1, 256, 14, 14] 33,280 │ │ └─ReLU: 3-50 [1, 256, 14, 14] – │ └─BasicBlock: 2-9 [1, 256, 14, 14] – │ │ └─Conv2d: 3-51 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-52 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-53 [1, 256, 14, 14] – │ │ └─Conv2d: 3-54 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-55 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-56 [1, 256, 14, 14] – │ └─BasicBlock: 2-10 [1, 256, 14, 14] – │ │ └─Conv2d: 3-57 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-58 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-59 [1, 256, 14, 14] – │ │ └─Conv2d: 3-60 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-61 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-62 [1, 256, 14, 14] – │ └─BasicBlock: 2-11 [1, 256, 14, 14] – │ │ └─Conv2d: 3-63 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-64 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-65 [1, 256, 14, 14] – │ │ └─Conv2d: 3-66 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-67 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-68 [1, 256, 14, 14] – │ └─BasicBlock: 2-12 [1, 256, 14, 14] – │ │ └─Conv2d: 3-69 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-70 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-71 [1, 256, 14, 14] – │ │ └─Conv2d: 3-72 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-73 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-74 [1, 256, 14, 14] – │ └─BasicBlock: 2-13 [1, 256, 14, 14] – │ │ └─Conv2d: 3-75 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-76 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-77 [1, 256, 14, 14] – │ │ └─Conv2d: 3-78 [1, 256, 14, 14] 589,824 │ │ └─BatchNorm2d: 3-79 [1, 256, 14, 14] 512 │ │ └─ReLU: 3-80 [1, 256, 14, 14] – ├─Sequential: 1-8 [1, 512, 7, 7] – │ └─BasicBlock: 2-14 [1, 512, 7, 7] – │ │ └─Conv2d: 3-81 [1, 512, 7, 7] 1,179,648 │ │ └─BatchNorm2d: 3-82 [1, 512, 7, 7] 1,024 │ │ └─ReLU: 3-83 [1, 512, 7, 7] – │ │ └─Conv2d: 3-84 [1, 512, 7, 7] 2,359,296 │ │ └─BatchNorm2d: 3-85 [1, 512, 7, 7] 1,024 │ │ └─Sequential: 3-86 [1, 512, 7, 7] 132,096 │ │ └─ReLU: 3-87 [1, 512, 7, 7] – │ └─BasicBlock: 2-15 [1, 512, 7, 7] – │ │ └─Conv2d: 3-88 [1, 512, 7, 7] 2,359,296 │ │ └─BatchNorm2d: 3-89 [1, 512, 7, 7] 1,024 │ │ └─ReLU: 3-90 [1, 512, 7, 7] – │ │ └─Conv2d: 3-91 [1, 512, 7, 7] 2,359,296 │ │ └─BatchNorm2d: 3-92 [1, 512, 7, 7] 1,024 │ │ └─ReLU: 3-93 [1, 512, 7, 7] – │ └─BasicBlock: 2-16 [1, 512, 7, 7] – │ │ └─Conv2d: 3-94 [1, 512, 7, 7] 2,359,296 │ │ └─BatchNorm2d: 3-95 [1, 512, 7, 7] 1,024 │ │ └─ReLU: 3-96 [1, 512, 7, 7] – │ │ └─Conv2d: 3-97 [1, 512, 7, 7] 2,359,296 │ │ └─BatchNorm2d: 3-98 [1, 512, 7, 7] 1,024 │ │ └─ReLU: 3-99 [1, 512, 7, 7] – ├─AdaptiveAvgPool2d: 1-9 [1, 512, 1, 1] – ├─Linear: 1-10 [1, 1000] 513,000Total params: 21,797,672 Trainable params: 21,797,672 Non-trainable params: 0 Total mult-adds (G): 3.66Input size (MB): 0.60 Forward/backward pass size (MB): 59.82 Params size (MB): 87.19 Estimated Total Size (MB): 147.61#检测模型准确率 def cal_predict_correct(model):test_total_correct 0for iter,(images,labels) in enumerate(test_loader):images images.to(device)labels labels.to(device)outputs model(images)test_total_correct (outputs.argmax(1) labels).sum().item()

print(test_total_correct: str(test_total_correct))return test_total_correcttotal_correct cal_predict_correct(resnet34)

print(test_total_correct: feature_extract True new_model resnet34 set_parameter_requires_grad(new_model, #训练过程中model仍会进行梯度回传但是参数更新则只会发生在fc层 num_ftrs new_model.fc.in_features new_model.fc nn.Linear(in_featuresnum_ftrs, summary(new_model, (1, ├─Conv2d: 1-1 ├─BatchNorm2d: 1-2 ├─ReLU: 1-3 ├─MaxPool2d: 1-4 ├─Sequential: 1-5 │ └─BasicBlock: 2-1 │ │ └─Conv2d: 3-1 │ │ └─BatchNorm2d: 3-2 │ │ └─ReLU: 3-3 │ │ └─Conv2d: 3-4 │ │ └─BatchNorm2d: 3-5 │ │ └─ReLU: 3-6 │ └─BasicBlock: 2-2 │ │ └─Conv2d: 3-7 │ │ └─BatchNorm2d: 3-8 │ │ └─ReLU: 3-9 │ │ └─Conv2d: 3-10 │ │ └─BatchNorm2d: 3-11 │ │ └─ReLU: 3-12 │ └─BasicBlock: 2-3 │ │ └─Conv2d: 3-13 │ │ └─BatchNorm2d: 3-14 │ │ └─ReLU: 3-15 │ │ └─Conv2d: 3-16 │ │ └─BatchNorm2d: 3-17 │ │ └─ReLU: 3-18 ├─Sequential: 1-6 │ └─BasicBlock: 2-4 │ │ └─Conv2d: 3-19 │ │ └─BatchNorm2d: 3-20 │ │ └─ReLU: 3-21 │ │ └─Conv2d: 3-22 │ │ └─BatchNorm2d: 3-23 │ │ └─Sequential: 3-24 │ │ └─ReLU: 3-25 │ └─BasicBlock: 2-5 │ │ └─Conv2d: 3-26 │ │ └─BatchNorm2d: 3-27 │ │ └─ReLU: 3-28 │ │ └─Conv2d: 3-29 │ │ └─BatchNorm2d: 3-30 │ │ └─ReLU: 3-31 │ └─BasicBlock: 2-6 │ │ └─Conv2d: 3-32 │ │ └─BatchNorm2d: 3-33 │ │ └─ReLU: 3-34 │ │ └─Conv2d: 3-35 │ │ └─BatchNorm2d: 3-36 │ │ └─ReLU: 3-37 │ └─BasicBlock: 2-7 │ │ └─Conv2d: 3-38 │ │ └─BatchNorm2d: 3-39 │ │ └─ReLU: 3-40 │ │ └─Conv2d: 3-41 │ │ └─BatchNorm2d: 3-42 │ │ └─ReLU: 3-43 ├─Sequential: 1-7 │ └─BasicBlock: 2-8 │ │ └─Conv2d: 3-44 │ │ └─BatchNorm2d: 3-45 │ │ └─ReLU: 3-46 │ │ └─Conv2d: 3-47 │ │ └─BatchNorm2d: 3-48 │ │ └─Sequential: 3-49 │ │ └─ReLU: 3-50 │ └─BasicBlock: 2-9 │ │ └─Conv2d: 3-51 │ │ └─BatchNorm2d: 3-52 │ │ └─ReLU: 3-53 │ │ └─Conv2d: 3-54 │ │ └─BatchNorm2d: 3-55 │ │ └─ReLU: 3-56 │ └─BasicBlock: 2-10 │ │ └─Conv2d: 3-57 │ │ └─BatchNorm2d: 3-58 │ │ └─ReLU: 3-59 │ │ └─Conv2d: 3-60 │ │ └─BatchNorm2d: 3-61 │ │ └─ReLU: 3-62 │ └─BasicBlock: 2-11 │ │ └─Conv2d: 3-63 │ │ └─BatchNorm2d: 3-64 │ │ └─ReLU: 3-65 │ │ └─Conv2d: 3-66 │ │ └─BatchNorm2d: 3-67 │ │ └─ReLU: 3-68 │ └─BasicBlock: 2-12 │ │ └─Conv2d: 3-69 │ │ └─BatchNorm2d: 3-70 │ │ └─ReLU: 3-71 │ │ └─Conv2d: 3-72 │ │ └─BatchNorm2d: 3-73 │ │ └─ReLU: 3-74 │ └─BasicBlock: 2-13 │ │ └─Conv2d: 3-75 │ │ └─BatchNorm2d: 3-76 │ │ └─ReLU: 3-77 │ │ └─Conv2d: 3-78 │ │ └─BatchNorm2d: 3-79 │ │ └─ReLU: 3-80 ├─Sequential: 1-8 │ └─BasicBlock: 2-14 │ │ └─Conv2d: 3-81 │ │ └─BatchNorm2d: 3-82 │ │ └─ReLU: 3-83 │ │ └─Conv2d: 3-84 │ │ └─BatchNorm2d: 3-85 │ │ └─Sequential: 3-86 │ │ └─ReLU: 3-87 │ └─BasicBlock: 2-15 │ │ └─Conv2d: 3-88 │ │ └─BatchNorm2d: 3-89 │ │ └─ReLU: 3-90 │ │ └─Conv2d: 3-91 │ │ └─BatchNorm2d: 3-92 │ │ └─ReLU: 3-93 │ └─BasicBlock: 2-16 │ │ └─Conv2d: 3-94 │ │ └─BatchNorm2d: 3-95 │ │ └─ReLU: 3-96 │ │ └─Conv2d: 3-97 │ │ └─BatchNorm2d: 3-98 │ │ └─ReLU: 3-99 ├─AdaptiveAvgPool2d: 1-9 ├─Linear: 1-10 Trainable params: 5,130 Non-trainable params: 21,284,672 Total mult-adds (G): 3.66Input Forward/backward pass size (MB): 59.81 Params size (MB): 85.16 Estimated Total Size (MB): 145.57#训练验证 Resnet34_new new_model.to(device) str(test_total_correct / 10000))test_total_correct: 0.1def set_parameter_requires_grad(model, feature_extracting):if feature_extracting:for param in model.parameters():param.requires_grad False# 冻结参数的梯度 feature_extract)# 修改模型 out_features10, biasTrue) 3, 224, 224)) Layer (type:depth-idx) Output Shape Param #ResNet [1, 10] – 1, 64, 112, 112 1, 64, 112, 112 [1, 64, 112, 112] – [1, 64, 56, 56] – [1, 64, 56, 56] – [1, 64, 56, 56] – 1, 64, 56, 56 1, 64, 56, 56 [1, 64, 56, 56] – 1, 64, 56, 56 1, 64, 56, 56 [1, 64, 56, 56] – [1, 64, 56, 56] – 1, 64, 56, 56 1, 64, 56, 56 [1, 64, 56, 56] – 1, 64, 56, 56 1, 64, 56, 56 [1, 64, 56, 56] – [1, 64, 56, 56] – 1, 64, 56, 56 1, 64, 56, 56 [1, 64, 56, 56] – 1, 64, 56, 56 1, 64, 56, 56 [1, 64, 56, 56] – [1, 128, 28, 28] – [1, 128, 28, 28] – 1, 128, 28, 28 1, 128, 28, 28 [1, 128, 28, 28] – 1, 128, 28, 28 1, 128, 28, 28 1, 128, 28, 28 [1, 128, 28, 28] – [1, 128, 28, 28] – 1, 128, 28, 28 1, 128, 28, 28 [1, 128, 28, 28] – 1, 128, 28, 28 1, 128, 28, 28 [1, 128, 28, 28] – [1, 128, 28, 28] – 1, 128, 28, 28 1, 128, 28, 28 [1, 128, 28, 28] – 1, 128, 28, 28 1, 128, 28, 28 [1, 128, 28, 28] – [1, 128, 28, 28] – 1, 128, 28, 28 1, 128, 28, 28 [1, 128, 28, 28] – 1, 128, 28, 28 1, 128, 28, 28 [1, 128, 28, 28] – [1, 256, 14, 14] – [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – 1, 256, 14, 14 1, 256, 14, 14 [1, 256, 14, 14] – [1, 512, 7, 7] – [1, 512, 7, 7] – 1, 512, 7, 7 1, 512, 7, 7 [1, 512, 7, 7] – 1, 512, 7, 7 1, 512, 7, 7 1, 512, 7, 7 [1, 512, 7, 7] – [1, 512, 7, 7] – 1, 512, 7, 7 1, 512, 7, 7 [1, 512, 7, 7] – 1, 512, 7, 7 1, 512, 7, 7 [1, 512, 7, 7] – [1, 512, 7, 7] – 1, 512, 7, 7 1, 512, 7, 7 [1, 512, 7, 7] – 1, 512, 7, 7 1, 512, 7, 7 [1, 512, 7, 7] – [1, 512, 1, 1] – [1, 10] 5,130Total params: 21,289,802 size (MB): 0.60

定义损失函数和优化器

device torch.device(cuda:0 if torch.cuda.is_available() else cpu)

损失函数自定义损失函数

criterion nn.CrossEntropyLoss()

优化器

optimizer torch.optim.Adam(Resnet50_new.parameters(), lrlr) epoch max_epochstotal_step len(train_loader) train_all_loss [] test_all_loss []for i in range(epoch):Resnet34_new.train()train_total_loss 0train_total_num 0train_total_correct 0for iter, (images,labels) in enumerate(train_loader):images images.to(device)labels labels.to(device)outputs Resnet34_new(images)loss criterion(outputs,labels)train_total_correct (outputs.argmax(1) labels).sum().item()#backwordoptimizer.zero_grad()loss.backward()optimizer.step()train_total_num labels.shape[0]train_total_loss loss.item()print(Epoch [{}/{}], Iter [{}/{}], train_loss:{:4f}.format(i1,epoch,iter1,total_step,loss.item()/labels.shape[0]))Resnet34_new.eval()test_total_loss 0test_total_correct 0test_total_num 0for iter,(images,labels) in enumerate(test_loader):images images.to(device)labels labels.to(device)outputs Resnet34_new(images)loss criterion(outputs,labels)test_total_correct (outputs.argmax(1) labels).sum().item()test_total_loss loss.item()test_total_num labels.shape[0]print(Epoch [{}/{}], train_loss:{:.4f}, train_acc:{:.4f}%, test_loss:{:.4f}, test_acc:{:.4f}%.format(i1, epoch, train_total_loss / train_total_num, train_total_correct / train_total_num * 100, test_total_loss / test_total_num, test_total_correct / test_total_num * 100))train_all_loss.append(np.round(train_total_loss / train_total_num,4))test_all_loss.append(np.round(test_total_loss / test_total_num,4)) Epoch [¹⁄₂], Iter [¹⁄₃₁₂₅], train_loss:0.150127 Epoch [¹⁄₂], Iter [²⁄₃₁₂₅], train_loss:0.174470 Epoch [¹⁄₂], Iter [³⁄₃₁₂₅], train_loss:0.165727 Epoch [¹⁄₂], Iter [⁴⁄₃₁₂₅], train_loss:0.174811 Epoch [¹⁄₂], Iter [⁵⁄₃₁₂₅], train_loss:0.158658 Epoch [¹⁄₂], Iter [⁶⁄₃₁₂₅], train_loss:0.153260 Epoch [¹⁄₂], Iter [⁷⁄₃₁₂₅], train_loss:0.164495 Epoch [¹⁄₂], Iter [⁸⁄₃₁₂₅], train_loss:0.164485 Epoch [¹⁄₂], Iter [⁹⁄₃₁₂₅], train_loss:0.157202 Epoch [¹⁄₂], Iter [¹⁰⁄₃₁₂₅], train_loss:0.149555 Epoch [¹⁄₂], Iter [¹¹⁄₃₁₂₅], train_loss:0.172609 Epoch [¹⁄₂], Iter [¹²⁄₃₁₂₅], train_loss:0.180861 Epoch [¹⁄₂], Iter [¹³⁄₃₁₂₅], train_loss:0.156719 Epoch [¹⁄₂], Iter [¹⁴⁄₃₁₂₅], train_loss:0.172375 Epoch [¹⁄₂], Iter [¹⁵⁄₃₁₂₅], train_loss:0.169886 Epoch [¹⁄₂], Iter [¹⁶⁄₃₁₂₅], train_loss:0.148726 Epoch [¹⁄₂], Iter [¹⁷⁄₃₁₂₅], train_loss:0.160391 Epoch [¹⁄₂], Iter [¹⁸⁄₃₁₂₅], train_loss:0.160285 Epoch [¹⁄₂], Iter [¹⁹⁄₃₁₂₅], train_loss:0.167672 Epoch [¹⁄₂], Iter [²⁰⁄₃₁₂₅], train_loss:0.151213 Epoch [¹⁄₂], Iter [²¹⁄₃₁₂₅], train_loss:0.154690 Epoch [¹⁄₂], Iter [²²⁄₃₁₂₅], train_loss:0.155165 Epoch [¹⁄₂], Iter [²³⁄₃₁₂₅], train_loss:0.162777 Epoch [¹⁄₂], Iter [²⁴⁄₃₁₂₅], train_loss:0.169136 Epoch [¹⁄₂], Iter [²⁵⁄₃₁₂₅], train_loss:0.151533 Epoch [¹⁄₂], Iter [²⁶⁄₃₁₂₅], train_loss:0.168992 Epoch [¹⁄₂], Iter [²⁷⁄₃₁₂₅], train_loss:0.176258 Epoch [¹⁄₂], Iter [²⁸⁄₃₁₂₅], train_loss:0.162240 Epoch [¹⁄₂], Iter [²⁹⁄₃₁₂₅], train_loss:0.161768 Epoch [¹⁄₂], Iter [³⁰⁄₃₁₂₅], train_loss:0.165359 Epoch [¹⁄₂], Iter [³¹⁄₃₁₂₅], train_loss:0.166174 Epoch [¹⁄₂], Iter [³²⁄₃₁₂₅], train_loss:0.173654 Epoch [¹⁄₂], Iter [³³⁄₃₁₂₅], train_loss:0.162488 Epoch [¹⁄₂], Iter [³⁴⁄₃₁₂₅], train_loss:0.164815 Epoch [¹⁄₂], Iter [³⁵⁄₃₁₂₅], train_loss:0.154411 Epoch [¹⁄₂], Iter [³⁶⁄₃₁₂₅], train_loss:0.159386 Epoch [¹⁄₂], Iter [³⁷⁄₃₁₂₅], train_loss:0.176261 Epoch [¹⁄₂], Iter [³⁸⁄₃₁₂₅], train_loss:0.163848 Epoch [¹⁄₂], Iter [³⁹⁄₃₁₂₅], train_loss:0.174402 Epoch [¹⁄₂], Iter [⁴⁰⁄₃₁₂₅], train_loss:0.178917 Epoch [¹⁄₂], Iter [⁴¹⁄₃₁₂₅], train_loss:0.149938 Epoch [¹⁄₂], Iter [⁴²⁄₃₁₂₅], train_loss:0.156186 Epoch [¹⁄₂], Iter [⁴³⁄₃₁₂₅], train_loss:0.162950 Epoch [¹⁄₂], Iter [⁴⁴⁄₃₁₂₅], train_loss:0.169058 Epoch [¹⁄₂], Iter [⁴⁵⁄₃₁₂₅], train_loss:0.168587 Epoch [¹⁄₂], Iter [⁴⁶⁄₃₁₂₅], train_loss:0.173754 Epoch [¹⁄₂], Iter [⁴⁷⁄₃₁₂₅], train_loss:0.158612 Epoch [¹⁄₂], Iter [⁴⁸⁄₃₁₂₅], train_loss:0.163891 Epoch [¹⁄₂], Iter [⁴⁹⁄₃₁₂₅], train_loss:0.149220 Epoch [¹⁄₂], Iter [⁵⁰⁄₃₁₂₅], train_loss:0.175387 Epoch [¹⁄₂], Iter [⁵¹⁄₃₁₂₅], train_loss:0.163082 Epoch [¹⁄₂], Iter [⁵²⁄₃₁₂₅], train_loss:0.156597 Epoch [¹⁄₂], Iter [⁵³⁄₃₁₂₅], train_loss:0.179248 Epoch [¹⁄₂], Iter [⁵⁴⁄₃₁₂₅], train_loss:0.170053 Epoch [¹⁄₂], Iter [⁵⁵⁄₃₁₂₅], train_loss:0.140899 Epoch [¹⁄₂], Iter [⁵⁶⁄₃₁₂₅], train_loss:0.168686 Epoch [¹⁄₂], Iter [⁵⁷⁄₃₁₂₅], train_loss:0.189548 Epoch [¹⁄₂], Iter [⁵⁸⁄₃₁₂₅], train_loss:0.169847 Epoch [¹⁄₂], Iter [⁵⁹⁄₃₁₂₅], train_loss:0.171854 Epoch [¹⁄₂], Iter [⁶⁰⁄₃₁₂₅], train_loss:0.175660 Epoch [¹⁄₂], Iter [⁶¹⁄₃₁₂₅], train_loss:0.163686 Epoch [¹⁄₂], Iter [⁶²⁄₃₁₂₅], train_loss:0.174950 Epoch [¹⁄₂], Iter [⁶³⁄₃₁₂₅], train_loss:0.173237 Epoch [¹⁄₂], Iter [⁶⁴⁄₃₁₂₅], train_loss:0.146743 Epoch [¹⁄₂], Iter [⁶⁵⁄₃₁₂₅], train_loss:0.159798 Epoch [¹⁄₂], Iter [⁶⁶⁄₃₁₂₅], train_loss:0.169616 Epoch [¹⁄₂], Iter [⁶⁷⁄₃₁₂₅], train_loss:0.167541 Epoch [¹⁄₂], Iter [⁶⁸⁄₃₁₂₅], train_loss:0.136470 Epoch [¹⁄₂], Iter [⁶⁹⁄₃₁₂₅], train_loss:0.185080 Epoch [¹⁄₂], Iter [⁷⁰⁄₃₁₂₅], train_loss:0.166373 Epoch [¹⁄₂], Iter [⁷¹⁄₃₁₂₅], train_loss:0.160634 Epoch [¹⁄₂], Iter [⁷²⁄₃₁₂₅], train_loss:0.163522 Epoch [¹⁄₂], Iter [⁷³⁄₃₁₂₅], train_loss:0.157858 Epoch [¹⁄₂], Iter [⁷⁴⁄₃₁₂₅], train_loss:0.157069 Epoch [¹⁄₂], Iter [⁷⁵⁄₃₁₂₅], train_loss:0.183969 Epoch [¹⁄₂], Iter [⁷⁶⁄₃₁₂₅], train_loss:0.166041 Epoch [¹⁄₂], Iter [⁷⁷⁄₃₁₂₅], train_loss:0.151215 Epoch [¹⁄₂], Iter [⁷⁸⁄₃₁₂₅], train_loss:0.164155 Epoch [¹⁄₂], Iter [⁷⁹⁄₃₁₂₅], train_loss:0.158990 Epoch [¹⁄₂], Iter [⁸⁰⁄₃₁₂₅], train_loss:0.178859 Epoch [¹⁄₂], Iter [⁸¹⁄₃₁₂₅], train_loss:0.139378 Epoch [¹⁄₂], Iter [⁸²⁄₃₁₂₅], train_loss:0.150422 Epoch [¹⁄₂], Iter [⁸³⁄₃₁₂₅], train_loss:0.155447 Epoch [¹⁄₂], Iter [⁸⁴⁄₃₁₂₅], train_loss:0.146703 Epoch [¹⁄₂], Iter [⁸⁵⁄₃₁₂₅], train_loss:0.165099 Epoch [¹⁄₂], Iter [⁸⁶⁄₃₁₂₅], train_loss:0.175539 Epoch [¹⁄₂], Iter [⁸⁷⁄₃₁₂₅], train_loss:0.178613 Epoch [¹⁄₂], Iter [⁸⁸⁄₃₁₂₅], train_loss:0.169430 Epoch [¹⁄₂], Iter [⁸⁹⁄₃₁₂₅], train_loss:0.160620 Epoch [¹⁄₂], Iter [⁹⁰⁄₃₁₂₅], train_loss:0.172726 Epoch [¹⁄₂], Iter [⁹¹⁄₃₁₂₅], train_loss:0.139834 Epoch [¹⁄₂], Iter [⁹²⁄₃₁₂₅], train_loss:0.162758 Epoch [¹⁄₂], Iter [⁹³⁄₃₁₂₅], train_loss:0.160110 Epoch [¹⁄₂], Iter [⁹⁴⁄₃₁₂₅], train_loss:0.176203 Epoch [¹⁄₂], Iter [⁹⁵⁄₃₁₂₅], train_loss:0.170835 Epoch [¹⁄₂], Iter [⁹⁶⁄₃₁₂₅], train_loss:0.166727 Epoch [¹⁄₂], Iter [⁹⁷⁄₃₁₂₅], train_loss:0.175421 Epoch [¹⁄₂], Iter [⁹⁸⁄₃₁₂₅], train_loss:0.173413 Epoch [¹⁄₂], Iter [⁹⁹⁄₃₁₂₅], train_loss:0.154259 Epoch [¹⁄₂], Iter [¹⁰⁰⁄₃₁₂₅], train_loss:0.146670 Epoch [¹⁄₂], Iter [¹⁰¹⁄₃₁₂₅], train_loss:0.161012 Epoch [¹⁄₂], Iter [¹⁰²⁄₃₁₂₅], train_loss:0.151979 Epoch [¹⁄₂], Iter [¹⁰³⁄₃₁₂₅], train_loss:0.163212 Epoch [¹⁄₂], Iter [¹⁰⁴⁄₃₁₂₅], train_loss:0.174235 Epoch [¹⁄₂], Iter [¹⁰⁵⁄₃₁₂₅], train_loss:0.152968 Epoch [¹⁄₂], Iter [¹⁰⁶⁄₃₁₂₅], train_loss:0.156215 Epoch [¹⁄₂], Iter [¹⁰⁷⁄₃₁₂₅], train_loss:0.164557 Epoch [¹⁄₂], Iter [¹⁰⁸⁄₃₁₂₅], train_loss:0.144438 Epoch [¹⁄₂], Iter [¹⁰⁹⁄₃₁₂₅], train_loss:0.168143 Epoch [¹⁄₂], Iter [¹¹⁰⁄₃₁₂₅], train_loss:0.144444 Epoch [¹⁄₂], Iter [¹¹¹⁄₃₁₂₅], train_loss:0.153808 Epoch [¹⁄₂], Iter [¹¹²⁄₃₁₂₅], train_loss:0.172484 Epoch [¹⁄₂], Iter [¹¹³⁄₃₁₂₅], train_loss:0.168573 Epoch [¹⁄₂], Iter [¹¹⁴⁄₃₁₂₅], train_loss:0.157955 Epoch [¹⁄₂], Iter [¹¹⁵⁄₃₁₂₅], train_loss:0.170679 Epoch [¹⁄₂], Iter [¹¹⁶⁄₃₁₂₅], train_loss:0.150308 Epoch [¹⁄₂], Iter [¹¹⁷⁄₃₁₂₅], train_loss:0.152166 Epoch [¹⁄₂], Iter [¹¹⁸⁄₃₁₂₅], train_loss:0.175642 Epoch [¹⁄₂], Iter [¹¹⁹⁄₃₁₂₅], train_loss:0.167162 Epoch [¹⁄₂], Iter [¹²⁰⁄₃₁₂₅], train_loss:0.159675 Epoch [¹⁄₂], Iter [¹²¹⁄₃₁₂₅], train_loss:0.176089 Epoch [¹⁄₂], Iter [¹²²⁄₃₁₂₅], train_loss:0.154275 Epoch [¹⁄₂], Iter [¹²³⁄₃₁₂₅], train_loss:0.139308 Epoch [¹⁄₂], Iter [¹²⁴⁄₃₁₂₅], train_loss:0.156106 Epoch [¹⁄₂], Iter [¹²⁵⁄₃₁₂₅], train_loss:0.140437 Epoch [¹⁄₂], Iter [¹²⁶⁄₃₁₂₅], train_loss:0.154971 Epoch [¹⁄₂], Iter [¹²⁷⁄₃₁₂₅], train_loss:0.148948 Epoch [¹⁄₂], Iter [¹²⁸⁄₃₁₂₅], train_loss:0.173654 Epoch [¹⁄₂], Iter [¹²⁹⁄₃₁₂₅], train_loss:0.175725 Epoch [¹⁄₂], Iter [¹³⁰⁄₃₁₂₅], train_loss:0.160516 Epoch [¹⁄₂], Iter [¹³¹⁄₃₁₂₅], train_loss:0.170737 Epoch [¹⁄₂], Iter [¹³²⁄₃₁₂₅], train_loss:0.161662 Epoch [¹⁄₂], Iter [¹³³⁄₃₁₂₅], train_loss:0.179921 Epoch [¹⁄₂], Iter [¹³⁴⁄₃₁₂₅], train_loss:0.160738 Epoch [¹⁄₂], Iter [¹³⁵⁄₃₁₂₅], train_loss:0.134471 Epoch [¹⁄₂], Iter [¹³⁶⁄₃₁₂₅], train_loss:0.170317 Epoch [¹⁄₂], Iter [¹³⁷⁄₃₁₂₅], train_loss:0.153042 Epoch [¹⁄₂], Iter [¹³⁸⁄₃₁₂₅], train_loss:0.163370 Epoch [¹⁄₂], Iter [¹³⁹⁄₃₁₂₅], train_loss:0.169346 Epoch [¹⁄₂], Iter [¹⁴⁰⁄₃₁₂₅], train_loss:0.156637 Epoch [¹⁄₂], Iter [¹⁴¹⁄₃₁₂₅], train_loss:0.164446 Epoch [¹⁄₂], Iter [¹⁴²⁄₃₁₂₅], train_loss:0.166337 Epoch [¹⁄₂], Iter [¹⁴³⁄₃₁₂₅], train_loss:0.150206 Epoch [¹⁄₂], Iter [¹⁴⁴⁄₃₁₂₅], train_loss:0.156191 Epoch [¹⁄₂], Iter [¹⁴⁵⁄₃₁₂₅], train_loss:0.169191 Epoch [¹⁄₂], Iter [¹⁴⁶⁄₃₁₂₅], train_loss:0.165300 Epoch [¹⁄₂], Iter [¹⁴⁷⁄₃₁₂₅], train_loss:0.177487 Epoch [¹⁄₂], Iter [¹⁴⁸⁄₃₁₂₅], train_loss:0.179514 Epoch [¹⁄₂], Iter [¹⁴⁹⁄₃₁₂₅], train_loss:0.153518 Epoch [¹⁄₂], Iter [¹⁵⁰⁄₃₁₂₅], train_loss:0.155025 Epoch [¹⁄₂], Iter [¹⁵¹⁄₃₁₂₅], train_loss:0.169826 Epoch [¹⁄₂], Iter [¹⁵²⁄₃₁₂₅], train_loss:0.150576 Epoch [¹⁄₂], Iter [¹⁵³⁄₃₁₂₅], train_loss:0.149755 Epoch [¹⁄₂], Iter [¹⁵⁴⁄₃₁₂₅], train_loss:0.156437 Epoch [¹⁄₂], Iter [¹⁵⁵⁄₃₁₂₅], train_loss:0.163630 Epoch [¹⁄₂], Iter [¹⁵⁶⁄₃₁₂₅], train_loss:0.163358 Epoch [¹⁄₂], Iter [¹⁵⁷⁄₃₁₂₅], train_loss:0.168501 Epoch [¹⁄₂], Iter [¹⁵⁸⁄₃₁₂₅], train_loss:0.152938 Epoch [¹⁄₂], Iter [¹⁵⁹⁄₃₁₂₅], train_loss:0.162743 Epoch [¹⁄₂], Iter [¹⁶⁰⁄₃₁₂₅], train_loss:0.164684 Epoch [¹⁄₂], Iter [¹⁶¹⁄₃₁₂₅], train_loss:0.134906 Epoch [¹⁄₂], Iter [¹⁶²⁄₃₁₂₅], train_loss:0.171217 Epoch [¹⁄₂], Iter [¹⁶³⁄₃₁₂₅], train_loss:0.166338 Epoch [¹⁄₂], Iter [¹⁶⁴⁄₃₁₂₅], train_loss:0.173403 Epoch [¹⁄₂], Iter [¹⁶⁵⁄₃₁₂₅], train_loss:0.166951 Epoch [¹⁄₂], Iter [¹⁶⁶⁄₃₁₂₅], train_loss:0.161986 Epoch [¹⁄₂], Iter [¹⁶⁷⁄₃₁₂₅], train_loss:0.167642 Epoch [¹⁄₂], Iter [¹⁶⁸⁄₃₁₂₅], train_loss:0.163133 Epoch [¹⁄₂], Iter [¹⁶⁹⁄₃₁₂₅], train_loss:0.176087 Epoch [¹⁄₂], Iter [¹⁷⁰⁄₃₁₂₅], train_loss:0.181500 Epoch [¹⁄₂], Iter [¹⁷¹⁄₃₁₂₅], train_loss:0.182332 Epoch [¹⁄₂], Iter [¹⁷²⁄₃₁₂₅], train_loss:0.159162 Epoch [¹⁄₂], Iter [¹⁷³⁄₃₁₂₅], train_loss:0.173818 Epoch [¹⁄₂], Iter [¹⁷⁴⁄₃₁₂₅], train_loss:0.151095 Epoch [¹⁄₂], Iter [¹⁷⁵⁄₃₁₂₅], train_loss:0.169016 Epoch [¹⁄₂], Iter [¹⁷⁶⁄₃₁₂₅], train_loss:0.168345 Epoch [¹⁄₂], Iter [¹⁷⁷⁄₃₁₂₅], train_loss:0.171198 Epoch [¹⁄₂], Iter [¹⁷⁸⁄₃₁₂₅], train_loss:0.158377 Epoch [¹⁄₂], Iter [¹⁷⁹⁄₃₁₂₅], train_loss:0.150349 Epoch [¹⁄₂], Iter [¹⁸⁰⁄₃₁₂₅], train_loss:0.154732 Epoch [¹⁄₂], Iter [¹⁸¹⁄₃₁₂₅], train_loss:0.159255 Epoch [¹⁄₂], Iter [¹⁸²⁄₃₁₂₅], train_loss:0.180752 Epoch [¹⁄₂], Iter [¹⁸³⁄₃₁₂₅], train_loss:0.130398 Epoch [¹⁄₂], Iter [¹⁸⁴⁄₃₁₂₅], train_loss:0.149835 Epoch [¹⁄₂], Iter [¹⁸⁵⁄₃₁₂₅], train_loss:0.163545 Epoch [¹⁄₂], Iter [¹⁸⁶⁄₃₁₂₅], train_loss:0.165769 Epoch [¹⁄₂], Iter [¹⁸⁷⁄₃₁₂₅], train_loss:0.165499 Epoch [¹⁄₂], Iter [¹⁸⁸⁄₃₁₂₅], train_loss:0.191183 Epoch [¹⁄₂], Iter [¹⁸⁹⁄₃₁₂₅], train_loss:0.165406 Epoch [¹⁄₂], Iter [¹⁹⁰⁄₃₁₂₅], train_loss:0.158130 Epoch [¹⁄₂], Iter [¹⁹¹⁄₃₁₂₅], train_loss:0.167049 Epoch [¹⁄₂], Iter [¹⁹²⁄₃₁₂₅], train_loss:0.158406 Epoch [¹⁄₂], Iter [¹⁹³⁄₃₁₂₅], train_loss:0.155791 Epoch [¹⁄₂], Iter [¹⁹⁴⁄₃₁₂₅], train_loss:0.154068 Epoch [¹⁄₂], Iter [¹⁹⁵⁄₃₁₂₅], train_loss:0.173929 Epoch [¹⁄₂], Iter [¹⁹⁶⁄₃₁₂₅], train_loss:0.166356 Epoch [¹⁄₂], Iter [¹⁹⁷⁄₃₁₂₅], train_loss:0.153073 Epoch [¹⁄₂], Iter [¹⁹⁸⁄₃₁₂₅], train_loss:0.159932 Epoch [¹⁄₂], Iter [¹⁹⁹⁄₃₁₂₅], train_loss:0.158823 Epoch [¹⁄₂], Iter [²⁰⁰⁄₃₁₂₅], train_loss:0.187810 Epoch [¹⁄₂], Iter [²⁰¹⁄₃₁₂₅], train_loss:0.178415 Epoch [¹⁄₂], Iter [²⁰²⁄₃₁₂₅], train_loss:0.156469 Epoch [¹⁄₂], Iter [²⁰³⁄₃₁₂₅], train_loss:0.160102 Epoch [¹⁄₂], Iter [²⁰⁴⁄₃₁₂₅], train_loss:0.147824 Epoch [¹⁄₂], Iter [²⁰⁵⁄₃₁₂₅], train_loss:0.159959 Epoch [¹⁄₂], Iter [²⁰⁶⁄₃₁₂₅], train_loss:0.168457 Epoch [¹⁄₂], Iter [²⁰⁷⁄₃₁₂₅], train_loss:0.152751 Epoch [¹⁄₂], Iter [²⁰⁸⁄₃₁₂₅], train_loss:0.153071 Epoch [¹⁄₂], Iter [²⁰⁹⁄₃₁₂₅], train_loss:0.162002 Epoch [¹⁄₂], Iter [²¹⁰⁄₃₁₂₅], train_loss:0.177490 Epoch [¹⁄₂], Iter [²¹¹⁄₃₁₂₅], train_loss:0.153973 Epoch [¹⁄₂], Iter [²¹²⁄₃₁₂₅], train_loss:0.178655 Epoch [¹⁄₂], Iter [²¹³⁄₃₁₂₅], train_loss:0.172759 Epoch [¹⁄₂], Iter [²¹⁴⁄₃₁₂₅], train_loss:0.161288 Epoch [¹⁄₂], Iter [²¹⁵⁄₃₁₂₅], train_loss:0.145693 Epoch [¹⁄₂], Iter [²¹⁶⁄₃₁₂₅], train_loss:0.149355 Epoch [¹⁄₂], Iter [²¹⁷⁄₃₁₂₅], train_loss:0.177612 Epoch [¹⁄₂], Iter [²¹⁸⁄₃₁₂₅], train_loss:0.156104 Epoch [¹⁄₂], Iter [²¹⁹⁄₃₁₂₅], train_loss:0.146696 Epoch [¹⁄₂], Iter [²²⁰⁄₃₁₂₅], train_loss:0.168620 Epoch [¹⁄₂], Iter [²²¹⁄₃₁₂₅], train_loss:0.134316 Epoch [¹⁄₂], Iter [²²²⁄₃₁₂₅], train_loss:0.164465 Epoch [¹⁄₂], Iter [²²³⁄₃₁₂₅], train_loss:0.161020 Epoch [¹⁄₂], Iter [²²⁴⁄₃₁₂₅], train_loss:0.144464 Epoch [¹⁄₂], Iter [²²⁵⁄₃₁₂₅], train_loss:0.145501 Epoch [¹⁄₂], Iter [²²⁶⁄₃₁₂₅], train_loss:0.156721 Epoch [¹⁄₂], Iter [²²⁷⁄₃₁₂₅], train_loss:0.160348 Epoch [¹⁄₂], Iter [²²⁸⁄₃₁₂₅], train_loss:0.157792 Epoch [¹⁄₂], Iter [²²⁹⁄₃₁₂₅], train_loss:0.143886 Epoch [¹⁄₂], Iter [²³⁰⁄₃₁₂₅], train_loss:0.146231 Epoch [¹⁄₂], Iter [²³¹⁄₃₁₂₅], train_loss:0.161353 Epoch [¹⁄₂], Iter [²³²⁄₃₁₂₅], train_loss:0.172967 Epoch [¹⁄₂], Iter [²³³⁄₃₁₂₅], train_loss:0.173051 Epoch [¹⁄₂], Iter [²³⁴⁄₃₁₂₅], train_loss:0.173887 Epoch [¹⁄₂], Iter [²³⁵⁄₃₁₂₅], train_loss:0.155447 Epoch [¹⁄₂], Iter [²³⁶⁄₃₁₂₅], train_loss:0.162683 Epoch [¹⁄₂], Iter [²³⁷⁄₃₁₂₅], train_loss:0.147682 Epoch [¹⁄₂], Iter [²³⁸⁄₃₁₂₅], train_loss:0.170582 Epoch [¹⁄₂], Iter [²³⁹⁄₃₁₂₅], train_loss:0.159764 Epoch [¹⁄₂], Iter [²⁴⁰⁄₃₁₂₅], train_loss:0.157225 Epoch [¹⁄₂], Iter [²⁴¹⁄₃₁₂₅], train_loss:0.153664 Epoch [¹⁄₂], Iter [²⁴²⁄₃₁₂₅], train_loss:0.166018 Epoch [¹⁄₂], Iter [²⁴³⁄₃₁₂₅], train_loss:0.175373 Epoch [¹⁄₂], Iter [²⁴⁴⁄₃₁₂₅], train_loss:0.146529 Epoch [¹⁄₂], Iter [²⁴⁵⁄₃₁₂₅], train_loss:0.166091 Epoch [¹⁄₂], Iter [²⁴⁶⁄₃₁₂₅], train_loss:0.161189 Epoch [¹⁄₂], Iter [²⁴⁷⁄₃₁₂₅], train_loss:0.144563 Epoch [¹⁄₂], Iter [²⁴⁸⁄₃₁₂₅], train_loss:0.150318 Epoch [¹⁄₂], Iter [²⁴⁹⁄₃₁₂₅], train_loss:0.140906 Epoch [¹⁄₂], Iter [²⁵⁰⁄₃₁₂₅], train_loss:0.169033 Epoch [¹⁄₂], Iter [²⁵¹⁄₃₁₂₅], train_loss:0.155781 Epoch [¹⁄₂], Iter [²⁵²⁄₃₁₂₅], train_loss:0.163493 Epoch [¹⁄₂], Iter [²⁵³⁄₃₁₂₅], train_loss:0.153378 Epoch [¹⁄₂], Iter [²⁵⁴⁄₃₁₂₅], train_loss:0.183447 Epoch [¹⁄₂], Iter [²⁵⁵⁄₃₁₂₅], train_loss:0.178129 Epoch [¹⁄₂], Iter [²⁵⁶⁄₃₁₂₅], train_loss:0.177007 Epoch [¹⁄₂], Iter [²⁵⁷⁄₃₁₂₅], train_loss:0.179591 Epoch [¹⁄₂], Iter [²⁵⁸⁄₃₁₂₅], train_loss:0.169509 Epoch [¹⁄₂], Iter [²⁵⁹⁄₃₁₂₅], train_loss:0.146213 Epoch [¹⁄₂], Iter [²⁶⁰⁄₃₁₂₅], train_loss:0.171849 Epoch [¹⁄₂], Iter [²⁶¹⁄₃₁₂₅], train_loss:0.163851 Epoch [¹⁄₂], Iter [²⁶²⁄₃₁₂₅], train_loss:0.178366 Epoch [¹⁄₂], Iter [²⁶³⁄₃₁₂₅], train_loss:0.194072 Epoch [¹⁄₂], Iter [²⁶⁴⁄₃₁₂₅], train_loss:0.172418 Epoch [¹⁄₂], Iter [²⁶⁵⁄₃₁₂₅], train_loss:0.143541 Epoch [¹⁄₂], Iter [²⁶⁶⁄₃₁₂₅], train_loss:0.158418 Epoch [¹⁄₂], Iter [²⁶⁷⁄₃₁₂₅], train_loss:0.163535 Epoch [¹⁄₂], Iter [²⁶⁸⁄₃₁₂₅], train_loss:0.171397 Epoch [¹⁄₂], Iter [²⁶⁹⁄₃₁₂₅], train_loss:0.183410 Epoch [¹⁄₂], Iter [²⁷⁰⁄₃₁₂₅], train_loss:0.191745 Epoch [¹⁄₂], Iter [²⁷¹⁄₃₁₂₅], train_loss:0.195354 Epoch [¹⁄₂], Iter [²⁷²⁄₃₁₂₅], train_loss:0.166208 Epoch [¹⁄₂], Iter [²⁷³⁄₃₁₂₅], train_loss:0.148297 Epoch [¹⁄₂], Iter [²⁷⁴⁄₃₁₂₅], train_loss:0.164007 Epoch [¹⁄₂], Iter [²⁷⁵⁄₃₁₂₅], train_loss:0.168109 Epoch [¹⁄₂], Iter [²⁷⁶⁄₃₁₂₅], train_loss:0.187189 Epoch [¹⁄₂], Iter [²⁷⁷⁄₃₁₂₅], train_loss:0.171387 Epoch [¹⁄₂], Iter [²⁷⁸⁄₃₁₂₅], train_loss:0.143764 Epoch [¹⁄₂], Iter [²⁷⁹⁄₃₁₂₅], train_loss:0.175919 Epoch [¹⁄₂], Iter [²⁸⁰⁄₃₁₂₅], train_loss:0.172834 Epoch [¹⁄₂], Iter [²⁸¹⁄₃₁₂₅], train_loss:0.173480 Epoch [¹⁄₂], Iter [²⁸²⁄₃₁₂₅], train_loss:0.141544 Epoch [¹⁄₂], Iter [²⁸³⁄₃₁₂₅], train_loss:0.187073 Epoch [¹⁄₂], Iter [²⁸⁴⁄₃₁₂₅], train_loss:0.147416 Epoch [¹⁄₂], Iter [²⁸⁵⁄₃₁₂₅], train_loss:0.163346 Epoch [¹⁄₂], Iter [²⁸⁶⁄₃₁₂₅], train_loss:0.155601 Epoch [¹⁄₂], Iter [²⁸⁷⁄₃₁₂₅], train_loss:0.160135 Epoch [¹⁄₂], Iter [²⁸⁸⁄₃₁₂₅], train_loss:0.153201 Epoch [¹⁄₂], Iter [²⁸⁹⁄₃₁₂₅], train_loss:0.157078 Epoch [¹⁄₂], Iter [²⁹⁰⁄₃₁₂₅], train_loss:0.143863 Epoch [¹⁄₂], Iter [²⁹¹⁄₃₁₂₅], train_loss:0.170847 Epoch [¹⁄₂], Iter [²⁹²⁄₃₁₂₅], train_loss:0.160009 Epoch [¹⁄₂], Iter [²⁹³⁄₃₁₂₅], train_loss:0.160868 Epoch [¹⁄₂], Iter [²⁹⁴⁄₃₁₂₅], train_loss:0.159037 Epoch [¹⁄₂], Iter [²⁹⁵⁄₃₁₂₅], train_loss:0.148768 Epoch [¹⁄₂], Iter [²⁹⁶⁄₃₁₂₅], train_loss:0.172005 Epoch [¹⁄₂], Iter [²⁹⁷⁄₃₁₂₅], train_loss:0.170369 Epoch [¹⁄₂], Iter [²⁹⁸⁄₃₁₂₅], train_loss:0.150250 Epoch [¹⁄₂], Iter [²⁹⁹⁄₃₁₂₅], train_loss:0.203501 Epoch [¹⁄₂], Iter [³⁰⁰⁄₃₁₂₅], train_loss:0.172398 Epoch [¹⁄₂], Iter [³⁰¹⁄₃₁₂₅], train_loss:0.184601 Epoch [¹⁄₂], Iter [³⁰²⁄₃₁₂₅], train_loss:0.156175 Epoch [¹⁄₂], Iter [³⁰³⁄₃₁₂₅], train_loss:0.161752 Epoch [¹⁄₂], Iter [³⁰⁴⁄₃₁₂₅], train_loss:0.154050 Epoch [¹⁄₂], Iter [³⁰⁵⁄₃₁₂₅], train_loss:0.151905 Epoch [¹⁄₂], Iter [³⁰⁶⁄₃₁₂₅], train_loss:0.154861 Epoch [¹⁄₂], Iter [³⁰⁷⁄₃₁₂₅], train_loss:0.157530 Epoch [¹⁄₂], Iter [³⁰⁸⁄₃₁₂₅], train_loss:0.162054 Epoch [¹⁄₂], Iter [³⁰⁹⁄₃₁₂₅], train_loss:0.172370 Epoch [¹⁄₂], Iter [³¹⁰⁄₃₁₂₅], train_loss:0.149971 Epoch [¹⁄₂], Iter [³¹¹⁄₃₁₂₅], train_loss:0.155449 Epoch [¹⁄₂], Iter [³¹²⁄₃₁₂₅], train_loss:0.168246 Epoch [¹⁄₂], Iter [³¹³⁄₃₁₂₅], train_loss:0.161156 Epoch [¹⁄₂], Iter [³¹⁴⁄₃₁₂₅], train_loss:0.182064 Epoch [¹⁄₂], Iter [³¹⁵⁄₃₁₂₅], train_loss:0.168014 Epoch [¹⁄₂], Iter [³¹⁶⁄₃₁₂₅], train_loss:0.155707 Epoch [¹⁄₂], Iter [³¹⁷⁄₃₁₂₅], train_loss:0.155345 Epoch [¹⁄₂], Iter [³¹⁸⁄₃₁₂₅], train_loss:0.157537 Epoch [¹⁄₂], Iter [³¹⁹⁄₃₁₂₅], train_loss:0.158657 Epoch [¹⁄₂], Iter [³²⁰⁄₃₁₂₅], train_loss:0.162647 Epoch [¹⁄₂], Iter [³²¹⁄₃₁₂₅], train_loss:0.165201 Epoch [¹⁄₂], Iter [³²²⁄₃₁₂₅], train_loss:0.187565 Epoch [¹⁄₂], Iter [³²³⁄₃₁₂₅], train_loss:0.153937 Epoch [¹⁄₂], Iter [³²⁴⁄₃₁₂₅], train_loss:0.147520 Epoch [¹⁄₂], Iter [³²⁵⁄₃₁₂₅], train_loss:0.139758 Epoch [¹⁄₂], Iter [³²⁶⁄₃₁₂₅], train_loss:0.177869 Epoch [¹⁄₂], Iter [³²⁷⁄₃₁₂₅], train_loss:0.178201 Epoch [¹⁄₂], Iter [³²⁸⁄₃₁₂₅], train_loss:0.154316 Epoch [¹⁄₂], Iter [³²⁹⁄₃₁₂₅], train_loss:0.178173 Epoch [¹⁄₂], Iter [³³⁰⁄₃₁₂₅], train_loss:0.159244 Epoch [¹⁄₂], Iter [³³¹⁄₃₁₂₅], train_loss:0.177582 Epoch [¹⁄₂], Iter [³³²⁄₃₁₂₅], train_loss:0.153592 Epoch [¹⁄₂], Iter [³³³⁄₃₁₂₅], train_loss:0.154490 Epoch [¹⁄₂], Iter [³³⁴⁄₃₁₂₅], train_loss:0.150733 Epoch [¹⁄₂], Iter [³³⁵⁄₃₁₂₅], train_loss:0.169697 Epoch [¹⁄₂], Iter [³³⁶⁄₃₁₂₅], train_loss:0.155575 Epoch [¹⁄₂], Iter [³³⁷⁄₃₁₂₅], train_loss:0.158214 Epoch [¹⁄₂], Iter [³³⁸⁄₃₁₂₅], train_loss:0.174536 Epoch [¹⁄₂], Iter [³³⁹⁄₃₁₂₅], train_loss:0.139395 Epoch [¹⁄₂], Iter [³⁴⁰⁄₃₁₂₅], train_loss:0.163447 Epoch [¹⁄₂], Iter [³⁴¹⁄₃₁₂₅], train_loss:0.146871 Epoch [¹⁄₂], Iter [³⁴²⁄₃₁₂₅], train_loss:0.160089 Epoch [¹⁄₂], Iter [³⁴³⁄₃₁₂₅], train_loss:0.161521 Epoch [¹⁄₂], Iter [³⁴⁴⁄₃₁₂₅], train_loss:0.148263 Epoch [¹⁄₂], Iter [³⁴⁵⁄₃₁₂₅], train_loss:0.156887 Epoch [¹⁄₂], Iter [³⁴⁶⁄₃₁₂₅], train_loss:0.163093 Epoch [¹⁄₂], Iter [³⁴⁷⁄₃₁₂₅], train_loss:0.130156 Epoch [¹⁄₂], Iter [³⁴⁸⁄₃₁₂₅], train_loss:0.153562 Epoch [¹⁄₂], Iter [³⁴⁹⁄₃₁₂₅], train_loss:0.183320 Epoch [¹⁄₂], Iter [³⁵⁰⁄₃₁₂₅], train_loss:0.151159 Epoch [¹⁄₂], Iter [³⁵¹⁄₃₁₂₅], train_loss:0.144421 Epoch [¹⁄₂], Iter [³⁵²⁄₃₁₂₅], train_loss:0.145968 Epoch [¹⁄₂], Iter [³⁵³⁄₃₁₂₅], train_loss:0.150598 Epoch [¹⁄₂], Iter [³⁵⁴⁄₃₁₂₅], train_loss:0.163271 Epoch [¹⁄₂], Iter [³⁵⁵⁄₃₁₂₅], train_loss:0.191171 Epoch [¹⁄₂], Iter [³⁵⁶⁄₃₁₂₅], train_loss:0.166442 Epoch [¹⁄₂], Iter [³⁵⁷⁄₃₁₂₅], train_loss:0.153268 Epoch [¹⁄₂], Iter [³⁵⁸⁄₃₁₂₅], train_loss:0.160086 Epoch [¹⁄₂], Iter [³⁵⁹⁄₃₁₂₅], train_loss:0.172394 Epoch [¹⁄₂], Iter [³⁶⁰⁄₃₁₂₅], train_loss:0.160697 Epoch [¹⁄₂], Iter [³⁶¹⁄₃₁₂₅], train_loss:0.158556 Epoch [¹⁄₂], Iter [³⁶²⁄₃₁₂₅], train_loss:0.148141 Epoch [¹⁄₂], Iter [³⁶³⁄₃₁₂₅], train_loss:0.161616 Epoch [¹⁄₂], Iter [³⁶⁴⁄₃₁₂₅], train_loss:0.164506 Epoch [¹⁄₂], Iter [³⁶⁵⁄₃₁₂₅], train_loss:0.153889 Epoch [¹⁄₂], Iter [³⁶⁶⁄₃₁₂₅], train_loss:0.149990 Epoch [¹⁄₂], Iter [³⁶⁷⁄₃₁₂₅], train_loss:0.172651 Epoch [¹⁄₂], Iter [³⁶⁸⁄₃₁₂₅], train_loss:0.167421 Epoch [¹⁄₂], Iter [³⁶⁹⁄₃₁₂₅], train_loss:0.157874 Epoch [¹⁄₂], Iter [³⁷⁰⁄₃₁₂₅], train_loss:0.175726 Epoch [¹⁄₂], Iter [³⁷¹⁄₃₁₂₅], train_loss:0.168166 Epoch [¹⁄₂], Iter [³⁷²⁄₃₁₂₅], train_loss:0.160632 Epoch [¹⁄₂], Iter [³⁷³⁄₃₁₂₅], train_loss:0.169915 Epoch [¹⁄₂], Iter [³⁷⁴⁄₃₁₂₅], train_loss:0.141351 Epoch [¹⁄₂], Iter [³⁷⁵⁄₃₁₂₅], train_loss:0.157579 Epoch [¹⁄₂], Iter [³⁷⁶⁄₃₁₂₅], train_loss:0.159373 Epoch [¹⁄₂], Iter [³⁷⁷⁄₃₁₂₅], train_loss:0.173719 Epoch [¹⁄₂], Iter [³⁷⁸⁄₃₁₂₅], train_loss:0.156862 Epoch [¹⁄₂], Iter [³⁷⁹⁄₃₁₂₅], train_loss:0.164567 Epoch [¹⁄₂], Iter [³⁸⁰⁄₃₁₂₅], train_loss:0.151420 Epoch [¹⁄₂], Iter [³⁸¹⁄₃₁₂₅], train_loss:0.155565 Epoch [¹⁄₂], Iter [³⁸²⁄₃₁₂₅], train_loss:0.156861 Epoch [¹⁄₂], Iter [³⁸³⁄₃₁₂₅], train_loss:0.162360 Epoch [¹⁄₂], Iter [³⁸⁴⁄₃₁₂₅], train_loss:0.155612 Epoch [¹⁄₂], Iter [³⁸⁵⁄₃₁₂₅], train_loss:0.187500 Epoch [¹⁄₂], Iter [³⁸⁶⁄₃₁₂₅], train_loss:0.167519 Epoch [¹⁄₂], Iter [³⁸⁷⁄₃₁₂₅], train_loss:0.150314 Epoch [¹⁄₂], Iter [³⁸⁸⁄₃₁₂₅], train_loss:0.171371 Epoch [¹⁄₂], Iter [³⁸⁹⁄₃₁₂₅], train_loss:0.170002 Epoch [¹⁄₂], Iter [³⁹⁰⁄₃₁₂₅], train_loss:0.171281 Epoch [¹⁄₂], Iter [³⁹¹⁄₃₁₂₅], train_loss:0.154229 Epoch [¹⁄₂], Iter [³⁹²⁄₃₁₂₅], train_loss:0.152277 Epoch [¹⁄₂], Iter [³⁹³⁄₃₁₂₅], train_loss:0.160335 Epoch [¹⁄₂], Iter [³⁹⁴⁄₃₁₂₅], train_loss:0.160123 Epoch [¹⁄₂], Iter [³⁹⁵⁄₃₁₂₅], train_loss:0.157730 Epoch [¹⁄₂], Iter [³⁹⁶⁄₃₁₂₅], train_loss:0.148626 Epoch [¹⁄₂], Iter [³⁹⁷⁄₃₁₂₅], train_loss:0.164090 Epoch [¹⁄₂], Iter [³⁹⁸⁄₃₁₂₅], train_loss:0.181123 Epoch [¹⁄₂], Iter [³⁹⁹⁄₃₁₂₅], train_loss:0.144987 Epoch [¹⁄₂], Iter [⁴⁰⁰⁄₃₁₂₅], train_loss:0.147743 Epoch [¹⁄₂], Iter [⁴⁰¹⁄₃₁₂₅], train_loss:0.156141 Epoch [¹⁄₂], Iter [⁴⁰²⁄₃₁₂₅], train_loss:0.182602 Epoch [¹⁄₂], Iter [⁴⁰³⁄₃₁₂₅], train_loss:0.186334 Epoch [¹⁄₂], Iter [⁴⁰⁴⁄₃₁₂₅], train_loss:0.158865 Epoch [¹⁄₂], Iter [⁴⁰⁵⁄₃₁₂₅], train_loss:0.157437 Epoch [¹⁄₂], Iter [⁴⁰⁶⁄₃₁₂₅], train_loss:0.151499 Epoch [¹⁄₂], Iter [⁴⁰⁷⁄₃₁₂₅], train_loss:0.155167 Epoch [¹⁄₂], Iter [⁴⁰⁸⁄₃₁₂₅], train_loss:0.158371 Epoch [¹⁄₂], Iter [⁴⁰⁹⁄₃₁₂₅], train_loss:0.170319 Epoch [¹⁄₂], Iter [⁴¹⁰⁄₃₁₂₅], train_loss:0.172921 Epoch [¹⁄₂], Iter [⁴¹¹⁄₃₁₂₅], train_loss:0.175661 Epoch [¹⁄₂], Iter [⁴¹²⁄₃₁₂₅], train_loss:0.170778 Epoch [¹⁄₂], Iter [⁴¹³⁄₃₁₂₅], train_loss:0.173227 Epoch [¹⁄₂], Iter [⁴¹⁴⁄₃₁₂₅], train_loss:0.162998 Epoch [¹⁄₂], Iter [⁴¹⁵⁄₃₁₂₅], train_loss:0.144094 Epoch [¹⁄₂], Iter [⁴¹⁶⁄₃₁₂₅], train_loss:0.154685 Epoch [¹⁄₂], Iter [⁴¹⁷⁄₃₁₂₅], train_loss:0.177953 Epoch [¹⁄₂], Iter [⁴¹⁸⁄₃₁₂₅], train_loss:0.151602 Epoch [¹⁄₂], Iter [⁴¹⁹⁄₃₁₂₅], train_loss:0.165047 Epoch [¹⁄₂], Iter [⁴²⁰⁄₃₁₂₅], train_loss:0.146441 Epoch [¹⁄₂], Iter [⁴²¹⁄₃₁₂₅], train_loss:0.155056 Epoch [¹⁄₂], Iter [⁴²²⁄₃₁₂₅], train_loss:0.144277 Epoch [¹⁄₂], Iter [⁴²³⁄₃₁₂₅], train_loss:0.156635 Epoch [¹⁄₂], Iter [⁴²⁴⁄₃₁₂₅], train_loss:0.154019 Epoch [¹⁄₂], Iter [⁴²⁵⁄₃₁₂₅], train_loss:0.161336 Epoch [¹⁄₂], Iter [⁴²⁶⁄₃₁₂₅], train_loss:0.203085 Epoch [¹⁄₂], Iter [⁴²⁷⁄₃₁₂₅], train_loss:0.146707 Epoch [¹⁄₂], Iter [⁴²⁸⁄₃₁₂₅], train_loss:0.158310 Epoch [¹⁄₂], Iter [⁴²⁹⁄₃₁₂₅], train_loss:0.171015 Epoch [¹⁄₂], Iter [⁴³⁰⁄₃₁₂₅], train_loss:0.142477 Epoch [¹⁄₂], Iter [⁴³¹⁄₃₁₂₅], train_loss:0.189910 Epoch [¹⁄₂], Iter [⁴³²⁄₃₁₂₅], train_loss:0.165581 Epoch [¹⁄₂], Iter [⁴³³⁄₃₁₂₅], train_loss:0.163553 Epoch [¹⁄₂], Iter [⁴³⁴⁄₃₁₂₅], train_loss:0.162628 Epoch [¹⁄₂], Iter [⁴³⁵⁄₃₁₂₅], train_loss:0.166308 Epoch [¹⁄₂], Iter [⁴³⁶⁄₃₁₂₅], train_loss:0.174060 Epoch [¹⁄₂], Iter [⁴³⁷⁄₃₁₂₅], train_loss:0.170486 Epoch [¹⁄₂], Iter [⁴³⁸⁄₃₁₂₅], train_loss:0.170334 Epoch [¹⁄₂], Iter [⁴³⁹⁄₃₁₂₅], train_loss:0.170027 Epoch [¹⁄₂], Iter [⁴⁴⁰⁄₃₁₂₅], train_loss:0.176327 Epoch [¹⁄₂], Iter [⁴⁴¹⁄₃₁₂₅], train_loss:0.185929 Epoch [¹⁄₂], Iter [⁴⁴²⁄₃₁₂₅], train_loss:0.164644 Epoch [¹⁄₂], Iter [⁴⁴³⁄₃₁₂₅], train_loss:0.155429 Epoch [¹⁄₂], Iter [⁴⁴⁴⁄₃₁₂₅], train_loss:0.156190 Epoch [¹⁄₂], Iter [⁴⁴⁵⁄₃₁₂₅], train_loss:0.183739 Epoch [¹⁄₂], Iter [⁴⁴⁶⁄₃₁₂₅], train_loss:0.168132 Epoch [¹⁄₂], Iter [⁴⁴⁷⁄₃₁₂₅], train_loss:0.156675 Epoch [¹⁄₂], Iter [⁴⁴⁸⁄₃₁₂₅], train_loss:0.174648 Epoch [¹⁄₂], Iter [⁴⁴⁹⁄₃₁₂₅], train_loss:0.176605 Epoch [¹⁄₂], Iter [⁴⁵⁰⁄₃₁₂₅], train_loss:0.165744 Epoch [¹⁄₂], Iter [⁴⁵¹⁄₃₁₂₅], train_loss:0.159427 Epoch [¹⁄₂], Iter [⁴⁵²⁄₃₁₂₅], train_loss:0.137918 Epoch [¹⁄₂], Iter [⁴⁵³⁄₃₁₂₅], train_loss:0.154664 Epoch [¹⁄₂], Iter [⁴⁵⁴⁄₃₁₂₅], train_loss:0.188046 Epoch [¹⁄₂], Iter [⁴⁵⁵⁄₃₁₂₅], train_loss:0.157990 Epoch [¹⁄₂], Iter [⁴⁵⁶⁄₃₁₂₅], train_loss:0.161434 Epoch [¹⁄₂], Iter [⁴⁵⁷⁄₃₁₂₅], train_loss:0.164751 Epoch [¹⁄₂], Iter [⁴⁵⁸⁄₃₁₂₅], train_loss:0.147707 Epoch [¹⁄₂], Iter [⁴⁵⁹⁄₃₁₂₅], train_loss:0.156135 Epoch [¹⁄₂], Iter [⁴⁶⁰⁄₃₁₂₅], train_loss:0.170298 Epoch [¹⁄₂], Iter [⁴⁶¹⁄₃₁₂₅], train_loss:0.157925 Epoch [¹⁄₂], Iter [⁴⁶²⁄₃₁₂₅], train_loss:0.161613 Epoch [¹⁄₂], Iter [⁴⁶³⁄₃₁₂₅], train_loss:0.156034 Epoch [¹⁄₂], Iter [⁴⁶⁴⁄₃₁₂₅], train_loss:0.154685 Epoch [¹⁄₂], Iter [⁴⁶⁵⁄₃₁₂₅], train_loss:0.159974 Epoch [¹⁄₂], Iter [⁴⁶⁶⁄₃₁₂₅], train_loss:0.137804 Epoch [¹⁄₂], Iter [⁴⁶⁷⁄₃₁₂₅], train_loss:0.173479 Epoch [¹⁄₂], Iter [⁴⁶⁸⁄₃₁₂₅], train_loss:0.160113 Epoch [¹⁄₂], Iter [⁴⁶⁹⁄₃₁₂₅], train_loss:0.181849 Epoch [¹⁄₂], Iter [⁴⁷⁰⁄₃₁₂₅], train_loss:0.154617 Epoch [¹⁄₂], Iter [⁴⁷¹⁄₃₁₂₅], train_loss:0.145756 Epoch [¹⁄₂], Iter [⁴⁷²⁄₃₁₂₅], train_loss:0.173865 Epoch [¹⁄₂], Iter [⁴⁷³⁄₃₁₂₅], train_loss:0.179762 Epoch [¹⁄₂], Iter [⁴⁷⁴⁄₃₁₂₅], train_loss:0.148816 Epoch [¹⁄₂], Iter [⁴⁷⁵⁄₃₁₂₅], train_loss:0.143284 Epoch [¹⁄₂], Iter [⁴⁷⁶⁄₃₁₂₅], train_loss:0.171798 Epoch [¹⁄₂], Iter [⁴⁷⁷⁄₃₁₂₅], train_loss:0.180198 Epoch [¹⁄₂], Iter [⁴⁷⁸⁄₃₁₂₅], train_loss:0.160204 Epoch [¹⁄₂], Iter [⁴⁷⁹⁄₃₁₂₅], train_loss:0.166848 Epoch [¹⁄₂], Iter [⁴⁸⁰⁄₃₁₂₅], train_loss:0.168912 Epoch [¹⁄₂], Iter [⁴⁸¹⁄₃₁₂₅], train_loss:0.151769 Epoch [¹⁄₂], Iter [⁴⁸²⁄₃₁₂₅], train_loss:0.164199 Epoch [¹⁄₂], Iter [⁴⁸³⁄₃₁₂₅], train_loss:0.159082 Epoch [¹⁄₂], Iter [⁴⁸⁴⁄₃₁₂₅], train_loss:0.157923 Epoch [¹⁄₂], Iter [⁴⁸⁵⁄₃₁₂₅], train_loss:0.175519 Epoch [¹⁄₂], Iter [⁴⁸⁶⁄₃₁₂₅], train_loss:0.161383 Epoch [¹⁄₂], Iter [⁴⁸⁷⁄₃₁₂₅], train_loss:0.162508 Epoch [¹⁄₂], Iter [⁴⁸⁸⁄₃₁₂₅], train_loss:0.165235 Epoch [¹⁄₂], Iter [⁴⁸⁹⁄₃₁₂₅], train_loss:0.179577 Epoch [¹⁄₂], Iter [⁴⁹⁰⁄₃₁₂₅], train_loss:0.151752 Epoch [¹⁄₂], Iter [⁴⁹¹⁄₃₁₂₅], train_loss:0.171913 Epoch [¹⁄₂], Iter [⁴⁹²⁄₃₁₂₅], train_loss:0.163084 Epoch [¹⁄₂], Iter [⁴⁹³⁄₃₁₂₅], train_loss:0.156714 Epoch [¹⁄₂], Iter [⁴⁹⁴⁄₃₁₂₅], train_loss:0.156022 Epoch [¹⁄₂], Iter [⁴⁹⁵⁄₃₁₂₅], train_loss:0.157305 Epoch [¹⁄₂], Iter [⁴⁹⁶⁄₃₁₂₅], train_loss:0.156836 Epoch [¹⁄₂], Iter [⁴⁹⁷⁄₃₁₂₅], train_loss:0.154605 Epoch [¹⁄₂], Iter [⁴⁹⁸⁄₃₁₂₅], train_loss:0.174036 Epoch [¹⁄₂], Iter [⁴⁹⁹⁄₃₁₂₅], train_loss:0.164733 Epoch [¹⁄₂], Iter [⁵⁰⁰⁄₃₁₂₅], train_loss:0.162918 Epoch [¹⁄₂], Iter [⁵⁰¹⁄₃₁₂₅], train_loss:0.149830 Epoch [¹⁄₂], Iter [⁵⁰²⁄₃₁₂₅], train_loss:0.186489 Epoch [¹⁄₂], Iter [⁵⁰³⁄₃₁₂₅], train_loss:0.145313 Epoch [¹⁄₂], Iter [⁵⁰⁴⁄₃₁₂₅], train_loss:0.152114 Epoch [¹⁄₂], Iter [⁵⁰⁵⁄₃₁₂₅], train_loss:0.150460 Epoch [¹⁄₂], Iter [⁵⁰⁶⁄₃₁₂₅], train_loss:0.172033 Epoch [¹⁄₂], Iter [⁵⁰⁷⁄₃₁₂₅], train_loss:0.156441 Epoch [¹⁄₂], Iter [⁵⁰⁸⁄₃₁₂₅], train_loss:0.151387 Epoch [¹⁄₂], Iter [⁵⁰⁹⁄₃₁₂₅], train_loss:0.174799 Epoch [¹⁄₂], Iter [⁵¹⁰⁄₃₁₂₅], train_loss:0.156212 Epoch [¹⁄₂], Iter [⁵¹¹⁄₃₁₂₅], train_loss:0.157743 Epoch [¹⁄₂], Iter [⁵¹²⁄₃₁₂₅], train_loss:0.171979 Epoch [¹⁄₂], Iter [⁵¹³⁄₃₁₂₅], train_loss:0.183507 Epoch [¹⁄₂], Iter [⁵¹⁴⁄₃₁₂₅], train_loss:0.174797 Epoch [¹⁄₂], Iter [⁵¹⁵⁄₃₁₂₅], train_loss:0.151998 Epoch [¹⁄₂], Iter [⁵¹⁶⁄₃₁₂₅], train_loss:0.164528 Epoch [¹⁄₂], Iter [⁵¹⁷⁄₃₁₂₅], train_loss:0.164061 Epoch [¹⁄₂], Iter [⁵¹⁸⁄₃₁₂₅], train_loss:0.184687 Epoch [¹⁄₂], Iter [⁵¹⁹⁄₃₁₂₅], train_loss:0.153723 Epoch [¹⁄₂], Iter [⁵²⁰⁄₃₁₂₅], train_loss:0.140085 Epoch [¹⁄₂], Iter [⁵²¹⁄₃₁₂₅], train_loss:0.161860 Epoch [¹⁄₂], Iter [⁵²²⁄₃₁₂₅], train_loss:0.142582 Epoch [¹⁄₂], Iter [⁵²³⁄₃₁₂₅], train_loss:0.158409 Epoch [¹⁄₂], Iter [⁵²⁴⁄₃₁₂₅], train_loss:0.197436 Epoch [¹⁄₂], Iter [⁵²⁵⁄₃₁₂₅], train_loss:0.170067 Epoch [¹⁄₂], Iter [⁵²⁶⁄₃₁₂₅], train_loss:0.150738 Epoch [¹⁄₂], Iter [⁵²⁷⁄₃₁₂₅], train_loss:0.164096 Epoch [¹⁄₂], Iter [⁵²⁸⁄₃₁₂₅], train_loss:0.159754 Epoch [¹⁄₂], Iter [⁵²⁹⁄₃₁₂₅], train_loss:0.152052 Epoch [¹⁄₂], Iter [⁵³⁰⁄₃₁₂₅], train_loss:0.161230 Epoch [¹⁄₂], Iter [⁵³¹⁄₃₁₂₅], train_loss:0.181889 Epoch [¹⁄₂], Iter [⁵³²⁄₃₁₂₅], train_loss:0.149528 Epoch [¹⁄₂], Iter [⁵³³⁄₃₁₂₅], train_loss:0.156530 Epoch [¹⁄₂], Iter [⁵³⁴⁄₃₁₂₅], train_loss:0.143401 Epoch [¹⁄₂], Iter [⁵³⁵⁄₃₁₂₅], train_loss:0.164431 Epoch [¹⁄₂], Iter [⁵³⁶⁄₃₁₂₅], train_loss:0.155525 Epoch [¹⁄₂], Iter [⁵³⁷⁄₃₁₂₅], train_loss:0.170614 Epoch [¹⁄₂], Iter [⁵³⁸⁄₃₁₂₅], train_loss:0.172353 Epoch [¹⁄₂], Iter [⁵³⁹⁄₃₁₂₅], train_loss:0.167426 Epoch [¹⁄₂], Iter [⁵⁴⁰⁄₃₁₂₅], train_loss:0.141499 Epoch [¹⁄₂], Iter [⁵⁴¹⁄₃₁₂₅], train_loss:0.165216 Epoch [¹⁄₂], Iter [⁵⁴²⁄₃₁₂₅], train_loss:0.164144 Epoch [¹⁄₂], Iter [⁵⁴³⁄₃₁₂₅], train_loss:0.149974 Epoch [¹⁄₂], Iter [⁵⁴⁴⁄₃₁₂₅], train_loss:0.157108 Epoch [¹⁄₂], Iter [⁵⁴⁵⁄₃₁₂₅], train_loss:0.169725 Epoch [¹⁄₂], Iter [⁵⁴⁶⁄₃₁₂₅], train_loss:0.181695 Epoch [¹⁄₂], Iter [⁵⁴⁷⁄₃₁₂₅], train_loss:0.161326 Epoch [¹⁄₂], Iter [⁵⁴⁸⁄₃₁₂₅], train_loss:0.187204 Epoch [¹⁄₂], Iter [⁵⁴⁹⁄₃₁₂₅], train_loss:0.152687 Epoch [¹⁄₂], Iter [⁵⁵⁰⁄₃₁₂₅], train_loss:0.144457 Epoch [¹⁄₂], Iter [⁵⁵¹⁄₃₁₂₅], train_loss:0.160662 Epoch [¹⁄₂], Iter [⁵⁵²⁄₃₁₂₅], train_loss:0.154854 Epoch [¹⁄₂], Iter [⁵⁵³⁄₃₁₂₅], train_loss:0.159735 Epoch [¹⁄₂], Iter [⁵⁵⁴⁄₃₁₂₅], train_loss:0.147193 Epoch [¹⁄₂], Iter [⁵⁵⁵⁄₃₁₂₅], train_loss:0.157361 Epoch [¹⁄₂], Iter [⁵⁵⁶⁄₃₁₂₅], train_loss:0.186600 Epoch [¹⁄₂], Iter [⁵⁵⁷⁄₃₁₂₅], train_loss:0.152398 Epoch [¹⁄₂], Iter [⁵⁵⁸⁄₃₁₂₅], train_loss:0.175364 Epoch [¹⁄₂], Iter [⁵⁵⁹⁄₃₁₂₅], train_loss:0.167578 Epoch [¹⁄₂], Iter [⁵⁶⁰⁄₃₁₂₅], train_loss:0.158512 Epoch [¹⁄₂], Iter [⁵⁶¹⁄₃₁₂₅], train_loss:0.173613 Epoch [¹⁄₂], Iter [⁵⁶²⁄₃₁₂₅], train_loss:0.160966 Epoch [¹⁄₂], Iter [⁵⁶³⁄₃₁₂₅], train_loss:0.172676 Epoch [¹⁄₂], Iter [⁵⁶⁴⁄₃₁₂₅], train_loss:0.158586 Epoch [¹⁄₂], Iter [⁵⁶⁵⁄₃₁₂₅], train_loss:0.180590 Epoch [¹⁄₂], Iter [⁵⁶⁶⁄₃₁₂₅], train_loss:0.192027 Epoch [¹⁄₂], Iter [⁵⁶⁷⁄₃₁₂₅], train_loss:0.157700 Epoch [¹⁄₂], Iter [⁵⁶⁸⁄₃₁₂₅], train_loss:0.162584 Epoch [¹⁄₂], Iter [⁵⁶⁹⁄₃₁₂₅], train_loss:0.183801 Epoch [¹⁄₂], Iter [⁵⁷⁰⁄₃₁₂₅], train_loss:0.167326 Epoch [¹⁄₂], Iter [⁵⁷¹⁄₃₁₂₅], train_loss:0.164745 Epoch [¹⁄₂], Iter [⁵⁷²⁄₃₁₂₅], train_loss:0.173292 Epoch [¹⁄₂], Iter [⁵⁷³⁄₃₁₂₅], train_loss:0.153456 Epoch [¹⁄₂], Iter [⁵⁷⁴⁄₃₁₂₅], train_loss:0.160368 Epoch [¹⁄₂], Iter [⁵⁷⁵⁄₃₁₂₅], train_loss:0.151965 Epoch [¹⁄₂], Iter [⁵⁷⁶⁄₃₁₂₅], train_loss:0.154746 Epoch [¹⁄₂], Iter [⁵⁷⁷⁄₃₁₂₅], train_loss:0.170880 Epoch [¹⁄₂], Iter [⁵⁷⁸⁄₃₁₂₅], train_loss:0.161438 Epoch [¹⁄₂], Iter [⁵⁷⁹⁄₃₁₂₅], train_loss:0.180224 Epoch [¹⁄₂], Iter [⁵⁸⁰⁄₃₁₂₅], train_loss:0.178791 Epoch [¹⁄₂], Iter [⁵⁸¹⁄₃₁₂₅], train_loss:0.145772 Epoch [¹⁄₂], Iter [⁵⁸²⁄₃₁₂₅], train_loss:0.160606 Epoch [¹⁄₂], Iter [⁵⁸³⁄₃₁₂₅], train_loss:0.176088 Epoch [¹⁄₂], Iter [⁵⁸⁴⁄₃₁₂₅], train_loss:0.164863 Epoch [¹⁄₂], Iter [⁵⁸⁵⁄₃₁₂₅], train_loss:0.181251 Epoch [¹⁄₂], Iter [⁵⁸⁶⁄₃₁₂₅], train_loss:0.151516 Epoch [¹⁄₂], Iter [⁵⁸⁷⁄₃₁₂₅], train_loss:0.176537 Epoch [¹⁄₂], Iter [⁵⁸⁸⁄₃₁₂₅], train_loss:0.159592 Epoch [¹⁄₂], Iter [⁵⁸⁹⁄₃₁₂₅], train_loss:0.156307 Epoch [¹⁄₂], Iter [⁵⁹⁰⁄₃₁₂₅], train_loss:0.149772 Epoch [¹⁄₂], Iter [⁵⁹¹⁄₃₁₂₅], train_loss:0.168533 Epoch [¹⁄₂], Iter [⁵⁹²⁄₃₁₂₅], train_loss:0.156289 Epoch [¹⁄₂], Iter [⁵⁹³⁄₃₁₂₅], train_loss:0.171735 Epoch [¹⁄₂], Iter [⁵⁹⁴⁄₃₁₂₅], train_loss:0.159490 Epoch [¹⁄₂], Iter [⁵⁹⁵⁄₃₁₂₅], train_loss:0.156549 Epoch [¹⁄₂], Iter [⁵⁹⁶⁄₃₁₂₅], train_loss:0.172349 Epoch [¹⁄₂], Iter [⁵⁹⁷⁄₃₁₂₅], train_loss:0.163044 Epoch [¹⁄₂], Iter [⁵⁹⁸⁄₃₁₂₅], train_loss:0.153242 Epoch [¹⁄₂], Iter [⁵⁹⁹⁄₃₁₂₅], train_loss:0.178958 Epoch [¹⁄₂], Iter [⁶⁰⁰⁄₃₁₂₅], train_loss:0.154345 Epoch [¹⁄₂], Iter [⁶⁰¹⁄₃₁₂₅], train_loss:0.169848 Epoch [¹⁄₂], Iter [⁶⁰²⁄₃₁₂₅], train_loss:0.148637 Epoch [¹⁄₂], Iter [⁶⁰³⁄₃₁₂₅], train_loss:0.168987 Epoch [¹⁄₂], Iter [⁶⁰⁴⁄₃₁₂₅], train_loss:0.181611 Epoch [¹⁄₂], Iter [⁶⁰⁵⁄₃₁₂₅], train_loss:0.155290 Epoch [¹⁄₂], Iter [⁶⁰⁶⁄₃₁₂₅], train_loss:0.159152 Epoch [¹⁄₂], Iter [⁶⁰⁷⁄₃₁₂₅], train_loss:0.158287 Epoch [¹⁄₂], Iter [⁶⁰⁸⁄₃₁₂₅], train_loss:0.165115 Epoch [¹⁄₂], Iter [⁶⁰⁹⁄₃₁₂₅], train_loss:0.170284 Epoch [¹⁄₂], Iter [⁶¹⁰⁄₃₁₂₅], train_loss:0.180462 Epoch [¹⁄₂], Iter [⁶¹¹⁄₃₁₂₅], train_loss:0.170581 Epoch [¹⁄₂], Iter [⁶¹²⁄₃₁₂₅], train_loss:0.156333 Epoch [¹⁄₂], Iter [⁶¹³⁄₃₁₂₅], train_loss:0.158744 Epoch [¹⁄₂], Iter [⁶¹⁴⁄₃₁₂₅], train_loss:0.151848 Epoch [¹⁄₂], Iter [⁶¹⁵⁄₃₁₂₅], train_loss:0.146951 Epoch [¹⁄₂], Iter [⁶¹⁶⁄₃₁₂₅], train_loss:0.164550 Epoch [¹⁄₂], Iter [⁶¹⁷⁄₃₁₂₅], train_loss:0.163717 Epoch [¹⁄₂], Iter [⁶¹⁸⁄₃₁₂₅], train_loss:0.143995 Epoch [¹⁄₂], Iter [⁶¹⁹⁄₃₁₂₅], train_loss:0.174511 Epoch [¹⁄₂], Iter [⁶²⁰⁄₃₁₂₅], train_loss:0.161177 Epoch [¹⁄₂], Iter [⁶²¹⁄₃₁₂₅], train_loss:0.178878 Epoch [¹⁄₂], Iter [⁶²²⁄₃₁₂₅], train_loss:0.170491 Epoch [¹⁄₂], Iter [⁶²³⁄₃₁₂₅], train_loss:0.172630 Epoch [¹⁄₂], Iter [⁶²⁴⁄₃₁₂₅], train_loss:0.185353 Epoch [¹⁄₂], Iter [⁶²⁵⁄₃₁₂₅], train_loss:0.162375 Epoch [¹⁄₂], Iter [⁶²⁶⁄₃₁₂₅], train_loss:0.166046 Epoch [¹⁄₂], Iter [⁶²⁷⁄₃₁₂₅], train_loss:0.187614 Epoch [¹⁄₂], Iter [⁶²⁸⁄₃₁₂₅], train_loss:0.171770 Epoch [¹⁄₂], Iter [⁶²⁹⁄₃₁₂₅], train_loss:0.137850 Epoch [¹⁄₂], Iter [⁶³⁰⁄₃₁₂₅], train_loss:0.160116 Epoch [¹⁄₂], Iter [⁶³¹⁄₃₁₂₅], train_loss:0.147122 Epoch [¹⁄₂], Iter [⁶³²⁄₃₁₂₅], train_loss:0.182244 Epoch [¹⁄₂], Iter [⁶³³⁄₃₁₂₅], train_loss:0.143999 Epoch [¹⁄₂], Iter [⁶³⁴⁄₃₁₂₅], train_loss:0.182345 Epoch [¹⁄₂], Iter [⁶³⁵⁄₃₁₂₅], train_loss:0.156759 Epoch [¹⁄₂], Iter [⁶³⁶⁄₃₁₂₅], train_loss:0.148806 Epoch [¹⁄₂], Iter [⁶³⁷⁄₃₁₂₅], train_loss:0.154144 Epoch [¹⁄₂], Iter [⁶³⁸⁄₃₁₂₅], train_loss:0.149763 Epoch [¹⁄₂], Iter [⁶³⁹⁄₃₁₂₅], train_loss:0.154106 Epoch [¹⁄₂], Iter [⁶⁴⁰⁄₃₁₂₅], train_loss:0.168608 Epoch [¹⁄₂], Iter [⁶⁴¹⁄₃₁₂₅], train_loss:0.152673 Epoch [¹⁄₂], Iter [⁶⁴²⁄₃₁₂₅], train_loss:0.173711 Epoch [¹⁄₂], Iter [⁶⁴³⁄₃₁₂₅], train_loss:0.168833 Epoch [¹⁄₂], Iter [⁶⁴⁴⁄₃₁₂₅], train_loss:0.169643 Epoch [¹⁄₂], Iter [⁶⁴⁵⁄₃₁₂₅], train_loss:0.155612 Epoch [¹⁄₂], Iter [⁶⁴⁶⁄₃₁₂₅], train_loss:0.161894 Epoch [¹⁄₂], Iter [⁶⁴⁷⁄₃₁₂₅], train_loss:0.173931 Epoch [¹⁄₂], Iter [⁶⁴⁸⁄₃₁₂₅], train_loss:0.195914 Epoch [¹⁄₂], Iter [⁶⁴⁹⁄₃₁₂₅], train_loss:0.156067 Epoch [¹⁄₂], Iter [⁶⁵⁰⁄₃₁₂₅], train_loss:0.182341 Epoch [¹⁄₂], Iter [⁶⁵¹⁄₃₁₂₅], train_loss:0.162687 Epoch [¹⁄₂], Iter [⁶⁵²⁄₃₁₂₅], train_loss:0.146367 Epoch [¹⁄₂], Iter [⁶⁵³⁄₃₁₂₅], train_loss:0.188726 Epoch [¹⁄₂], Iter [⁶⁵⁴⁄₃₁₂₅], train_loss:0.141544 Epoch [¹⁄₂], Iter [⁶⁵⁵⁄₃₁₂₅], train_loss:0.136832 Epoch [¹⁄₂], Iter [⁶⁵⁶⁄₃₁₂₅], train_loss:0.165494 Epoch [¹⁄₂], Iter [⁶⁵⁷⁄₃₁₂₅], train_loss:0.173287 Epoch [¹⁄₂], Iter [⁶⁵⁸⁄₃₁₂₅], train_loss:0.178410 Epoch [¹⁄₂], Iter [⁶⁵⁹⁄₃₁₂₅], train_loss:0.153449 Epoch [¹⁄₂], Iter [⁶⁶⁰⁄₃₁₂₅], train_loss:0.141325 Epoch [¹⁄₂], Iter [⁶⁶¹⁄₃₁₂₅], train_loss:0.160569 Epoch [¹⁄₂], Iter [⁶⁶²⁄₃₁₂₅], train_loss:0.168849 Epoch [¹⁄₂], Iter [⁶⁶³⁄₃₁₂₅], train_loss:0.170920 Epoch [¹⁄₂], Iter [⁶⁶⁴⁄₃₁₂₅], train_loss:0.168509 Epoch [¹⁄₂], Iter [⁶⁶⁵⁄₃₁₂₅], train_loss:0.174167 Epoch [¹⁄₂], Iter [⁶⁶⁶⁄₃₁₂₅], train_loss:0.165306 Epoch [¹⁄₂], Iter [⁶⁶⁷⁄₃₁₂₅], train_loss:0.173296 Epoch [¹⁄₂], Iter [⁶⁶⁸⁄₃₁₂₅], train_loss:0.161691 Epoch [¹⁄₂], Iter [⁶⁶⁹⁄₃₁₂₅], train_loss:0.164216 Epoch [¹⁄₂], Iter [⁶⁷⁰⁄₃₁₂₅], train_loss:0.153614 Epoch [¹⁄₂], Iter [⁶⁷¹⁄₃₁₂₅], train_loss:0.176628 Epoch [¹⁄₂], Iter [⁶⁷²⁄₃₁₂₅], train_loss:0.170113 Epoch [¹⁄₂], Iter [⁶⁷³⁄₃₁₂₅], train_loss:0.164020 Epoch [¹⁄₂], Iter [⁶⁷⁴⁄₃₁₂₅], train_loss:0.170262 Epoch [¹⁄₂], Iter [⁶⁷⁵⁄₃₁₂₅], train_loss:0.160252 Epoch [¹⁄₂], Iter [⁶⁷⁶⁄₃₁₂₅], train_loss:0.159595 Epoch [¹⁄₂], Iter [⁶⁷⁷⁄₃₁₂₅], train_loss:0.174482 Epoch [¹⁄₂], Iter [⁶⁷⁸⁄₃₁₂₅], train_loss:0.174136 Epoch [¹⁄₂], Iter [⁶⁷⁹⁄₃₁₂₅], train_loss:0.169684 Epoch [¹⁄₂], Iter [⁶⁸⁰⁄₃₁₂₅], train_loss:0.156718 Epoch [¹⁄₂], Iter [⁶⁸¹⁄₃₁₂₅], train_loss:0.172149 Epoch [¹⁄₂], Iter [⁶⁸²⁄₃₁₂₅], train_loss:0.153396 Epoch [¹⁄₂], Iter [⁶⁸³⁄₃₁₂₅], train_loss:0.152438 Epoch [¹⁄₂], Iter [⁶⁸⁴⁄₃₁₂₅], train_loss:0.175598 Epoch [¹⁄₂], Iter [⁶⁸⁵⁄₃₁₂₅], train_loss:0.144732 Epoch [¹⁄₂], Iter [⁶⁸⁶⁄₃₁₂₅], train_loss:0.146447 Epoch [¹⁄₂], Iter [⁶⁸⁷⁄₃₁₂₅], train_loss:0.149588 Epoch [¹⁄₂], Iter [⁶⁸⁸⁄₃₁₂₅], train_loss:0.158347 Epoch [¹⁄₂], Iter [⁶⁸⁹⁄₃₁₂₅], train_loss:0.173472 Epoch [¹⁄₂], Iter [⁶⁹⁰⁄₃₁₂₅], train_loss:0.164299 Epoch [¹⁄₂], Iter [⁶⁹¹⁄₃₁₂₅], train_loss:0.147107 Epoch [¹⁄₂], Iter [⁶⁹²⁄₃₁₂₅], train_loss:0.138865 Epoch [¹⁄₂], Iter [⁶⁹³⁄₃₁₂₅], train_loss:0.147721 Epoch [¹⁄₂], Iter [⁶⁹⁴⁄₃₁₂₅], train_loss:0.186929 Epoch [¹⁄₂], Iter [⁶⁹⁵⁄₃₁₂₅], train_loss:0.149825 Epoch [¹⁄₂], Iter [⁶⁹⁶⁄₃₁₂₅], train_loss:0.159169 Epoch [¹⁄₂], Iter [⁶⁹⁷⁄₃₁₂₅], train_loss:0.168211 Epoch [¹⁄₂], Iter [⁶⁹⁸⁄₃₁₂₅], train_loss:0.155869 Epoch [¹⁄₂], Iter [⁶⁹⁹⁄₃₁₂₅], train_loss:0.175861 Epoch [¹⁄₂], Iter [⁷⁰⁰⁄₃₁₂₅], train_loss:0.147055 Epoch [¹⁄₂], Iter [⁷⁰¹⁄₃₁₂₅], train_loss:0.152602 Epoch [¹⁄₂], Iter [⁷⁰²⁄₃₁₂₅], train_loss:0.165213 Epoch [¹⁄₂], Iter [⁷⁰³⁄₃₁₂₅], train_loss:0.155550 Epoch [¹⁄₂], Iter [⁷⁰⁴⁄₃₁₂₅], train_loss:0.165959 Epoch [¹⁄₂], Iter [⁷⁰⁵⁄₃₁₂₅], train_loss:0.184858 Epoch [¹⁄₂], Iter [⁷⁰⁶⁄₃₁₂₅], train_loss:0.156636 Epoch [¹⁄₂], Iter [⁷⁰⁷⁄₃₁₂₅], train_loss:0.141014 Epoch [¹⁄₂], Iter [⁷⁰⁸⁄₃₁₂₅], train_loss:0.172110 Epoch [¹⁄₂], Iter [⁷⁰⁹⁄₃₁₂₅], train_loss:0.166598 Epoch [¹⁄₂], Iter [⁷¹⁰⁄₃₁₂₅], train_loss:0.181486 Epoch [¹⁄₂], Iter [⁷¹¹⁄₃₁₂₅], train_loss:0.149520 Epoch [¹⁄₂], Iter [⁷¹²⁄₃₁₂₅], train_loss:0.141277 Epoch [¹⁄₂], Iter [⁷¹³⁄₃₁₂₅], train_loss:0.150582 Epoch [¹⁄₂], Iter [⁷¹⁴⁄₃₁₂₅], train_loss:0.170460 Epoch [¹⁄₂], Iter [⁷¹⁵⁄₃₁₂₅], train_loss:0.166523 Epoch [¹⁄₂], Iter [⁷¹⁶⁄₃₁₂₅], train_loss:0.140562 Epoch [¹⁄₂], Iter [⁷¹⁷⁄₃₁₂₅], train_loss:0.157862 Epoch [¹⁄₂], Iter [⁷¹⁸⁄₃₁₂₅], train_loss:0.158880 Epoch [¹⁄₂], Iter [⁷¹⁹⁄₃₁₂₅], train_loss:0.151162 Epoch [¹⁄₂], Iter [⁷²⁰⁄₃₁₂₅], train_loss:0.150862 Epoch [¹⁄₂], Iter [⁷²¹⁄₃₁₂₅], train_loss:0.172271 Epoch [¹⁄₂], Iter [⁷²²⁄₃₁₂₅], train_loss:0.167076 Epoch [¹⁄₂], Iter [⁷²³⁄₃₁₂₅], train_loss:0.160416 Epoch [¹⁄₂], Iter [⁷²⁴⁄₃₁₂₅], train_loss:0.164712 Epoch [¹⁄₂], Iter [⁷²⁵⁄₃₁₂₅], train_loss:0.155195 Epoch [¹⁄₂], Iter [⁷²⁶⁄₃₁₂₅], train_loss:0.173203 Epoch [¹⁄₂], Iter [⁷²⁷⁄₃₁₂₅], train_loss:0.203542 Epoch [¹⁄₂], Iter [⁷²⁸⁄₃₁₂₅], train_loss:0.132789 Epoch [¹⁄₂], Iter [⁷²⁹⁄₃₁₂₅], train_loss:0.170022 Epoch [¹⁄₂], Iter [⁷³⁰⁄₃₁₂₅], train_loss:0.150648 Epoch [¹⁄₂], Iter [⁷³¹⁄₃₁₂₅], train_loss:0.152137 Epoch [¹⁄₂], Iter [⁷³²⁄₃₁₂₅], train_loss:0.165179 Epoch [¹⁄₂], Iter [⁷³³⁄₃₁₂₅], train_loss:0.181513 Epoch [¹⁄₂], Iter [⁷³⁴⁄₃₁₂₅], train_loss:0.144627 Epoch [¹⁄₂], Iter [⁷³⁵⁄₃₁₂₅], train_loss:0.156241 Epoch [¹⁄₂], Iter [⁷³⁶⁄₃₁₂₅], train_loss:0.156647 Epoch [¹⁄₂], Iter [⁷³⁷⁄₃₁₂₅], train_loss:0.156439 Epoch [¹⁄₂], Iter [⁷³⁸⁄₃₁₂₅], train_loss:0.184127 Epoch [¹⁄₂], Iter [⁷³⁹⁄₃₁₂₅], train_loss:0.149900 Epoch [¹⁄₂], Iter [⁷⁴⁰⁄₃₁₂₅], train_loss:0.178831 Epoch [¹⁄₂], Iter [⁷⁴¹⁄₃₁₂₅], train_loss:0.154100 Epoch [¹⁄₂], Iter [⁷⁴²⁄₃₁₂₅], train_loss:0.173619 Epoch [¹⁄₂], Iter [⁷⁴³⁄₃₁₂₅], train_loss:0.174960 Epoch [¹⁄₂], Iter [⁷⁴⁴⁄₃₁₂₅], train_loss:0.158306 Epoch [¹⁄₂], Iter [⁷⁴⁵⁄₃₁₂₅], train_loss:0.157812 Epoch [¹⁄₂], Iter [⁷⁴⁶⁄₃₁₂₅], train_loss:0.170903 Epoch [¹⁄₂], Iter [⁷⁴⁷⁄₃₁₂₅], train_loss:0.158708 Epoch [¹⁄₂], Iter [⁷⁴⁸⁄₃₁₂₅], train_loss:0.177305 Epoch [¹⁄₂], Iter [⁷⁴⁹⁄₃₁₂₅], train_loss:0.157574 Epoch [¹⁄₂], Iter [⁷⁵⁰⁄₃₁₂₅], train_loss:0.163793 Epoch [¹⁄₂], Iter [⁷⁵¹⁄₃₁₂₅], train_loss:0.175222 Epoch [¹⁄₂], Iter [⁷⁵²⁄₃₁₂₅], train_loss:0.167615 Epoch [¹⁄₂], Iter [⁷⁵³⁄₃₁₂₅], train_loss:0.175142 Epoch [¹⁄₂], Iter [⁷⁵⁴⁄₃₁₂₅], train_loss:0.164994 Epoch [¹⁄₂], Iter [⁷⁵⁵⁄₃₁₂₅], train_loss:0.173740 Epoch [¹⁄₂], Iter [⁷⁵⁶⁄₃₁₂₅], train_loss:0.184293 Epoch [¹⁄₂], Iter [⁷⁵⁷⁄₃₁₂₅], train_loss:0.174505 Epoch [¹⁄₂], Iter [⁷⁵⁸⁄₃₁₂₅], train_loss:0.151717 Epoch [¹⁄₂], Iter [⁷⁵⁹⁄₃₁₂₅], train_loss:0.149027 Epoch [¹⁄₂], Iter [⁷⁶⁰⁄₃₁₂₅], train_loss:0.181634 Epoch [¹⁄₂], Iter [⁷⁶¹⁄₃₁₂₅], train_loss:0.157314 Epoch [¹⁄₂], Iter [⁷⁶²⁄₃₁₂₅], train_loss:0.137242 Epoch [¹⁄₂], Iter [⁷⁶³⁄₃₁₂₅], train_loss:0.168438 Epoch [¹⁄₂], Iter [⁷⁶⁴⁄₃₁₂₅], train_loss:0.141019 Epoch [¹⁄₂], Iter [⁷⁶⁵⁄₃₁₂₅], train_loss:0.154936 Epoch [¹⁄₂], Iter [⁷⁶⁶⁄₃₁₂₅], train_loss:0.155263 Epoch [¹⁄₂], Iter [⁷⁶⁷⁄₃₁₂₅], train_loss:0.156193 Epoch [¹⁄₂], Iter [⁷⁶⁸⁄₃₁₂₅], train_loss:0.154753 Epoch [¹⁄₂], Iter [⁷⁶⁹⁄₃₁₂₅], train_loss:0.152388 Epoch [¹⁄₂], Iter [⁷⁷⁰⁄₃₁₂₅], train_loss:0.154891 Epoch [¹⁄₂], Iter [⁷⁷¹⁄₃₁₂₅], train_loss:0.150887 Epoch [¹⁄₂], Iter [⁷⁷²⁄₃₁₂₅], train_loss:0.170387 Epoch [¹⁄₂], Iter [⁷⁷³⁄₃₁₂₅], train_loss:0.142415 Epoch [¹⁄₂], Iter [⁷⁷⁴⁄₃₁₂₅], train_loss:0.157543 Epoch [¹⁄₂], Iter [⁷⁷⁵⁄₃₁₂₅], train_loss:0.161519 Epoch [¹⁄₂], Iter [⁷⁷⁶⁄₃₁₂₅], train_loss:0.153466 Epoch [¹⁄₂], Iter [⁷⁷⁷⁄₃₁₂₅], train_loss:0.164538 Epoch [¹⁄₂], Iter [⁷⁷⁸⁄₃₁₂₅], train_loss:0.167005 Epoch [¹⁄₂], Iter [⁷⁷⁹⁄₃₁₂₅], train_loss:0.164542 Epoch [¹⁄₂], Iter [⁷⁸⁰⁄₃₁₂₅], train_loss:0.136895 Epoch [¹⁄₂], Iter [⁷⁸¹⁄₃₁₂₅], train_loss:0.143366 Epoch [¹⁄₂], Iter [⁷⁸²⁄₃₁₂₅], train_loss:0.159515 Epoch [¹⁄₂], Iter [⁷⁸³⁄₃₁₂₅], train_loss:0.159623 Epoch [¹⁄₂], Iter [⁷⁸⁴⁄₃₁₂₅], train_loss:0.175021 Epoch [¹⁄₂], Iter [⁷⁸⁵⁄₃₁₂₅], train_loss:0.188726 Epoch [¹⁄₂], Iter [⁷⁸⁶⁄₃₁₂₅], train_loss:0.167352 Epoch [¹⁄₂], Iter [⁷⁸⁷⁄₃₁₂₅], train_loss:0.159414 Epoch [¹⁄₂], Iter [⁷⁸⁸⁄₃₁₂₅], train_loss:0.143568 Epoch [¹⁄₂], Iter [⁷⁸⁹⁄₃₁₂₅], train_loss:0.157005 Epoch [¹⁄₂], Iter [⁷⁹⁰⁄₃₁₂₅], train_loss:0.150693 Epoch [¹⁄₂], Iter [⁷⁹¹⁄₃₁₂₅], train_loss:0.142032 Epoch [¹⁄₂], Iter [⁷⁹²⁄₃₁₂₅], train_loss:0.158453 Epoch [¹⁄₂], Iter [⁷⁹³⁄₃₁₂₅], train_loss:0.171967 Epoch [¹⁄₂], Iter [⁷⁹⁴⁄₃₁₂₅], train_loss:0.154673 Epoch [¹⁄₂], Iter [⁷⁹⁵⁄₃₁₂₅], train_loss:0.161099 Epoch [¹⁄₂], Iter [⁷⁹⁶⁄₃₁₂₅], train_loss:0.149141 Epoch [¹⁄₂], Iter [⁷⁹⁷⁄₃₁₂₅], train_loss:0.172768 Epoch [¹⁄₂], Iter [⁷⁹⁸⁄₃₁₂₅], train_loss:0.136935 Epoch [¹⁄₂], Iter [⁷⁹⁹⁄₃₁₂₅], train_loss:0.150901 Epoch [¹⁄₂], Iter [⁸⁰⁰⁄₃₁₂₅], train_loss:0.177802 Epoch [¹⁄₂], Iter [⁸⁰¹⁄₃₁₂₅], train_loss:0.151622 Epoch [¹⁄₂], Iter [⁸⁰²⁄₃₁₂₅], train_loss:0.175425 Epoch [¹⁄₂], Iter [⁸⁰³⁄₃₁₂₅], train_loss:0.158219 Epoch [¹⁄₂], Iter [⁸⁰⁴⁄₃₁₂₅], train_loss:0.160822 Epoch [¹⁄₂], Iter [⁸⁰⁵⁄₃₁₂₅], train_loss:0.171360 Epoch [¹⁄₂], Iter [⁸⁰⁶⁄₃₁₂₅], train_loss:0.173840 Epoch [¹⁄₂], Iter [⁸⁰⁷⁄₃₁₂₅], train_loss:0.170521 Epoch [¹⁄₂], Iter [⁸⁰⁸⁄₃₁₂₅], train_loss:0.155042 Epoch [¹⁄₂], Iter [⁸⁰⁹⁄₃₁₂₅], train_loss:0.201056 Epoch [¹⁄₂], Iter [⁸¹⁰⁄₃₁₂₅], train_loss:0.167513 Epoch [¹⁄₂], Iter [⁸¹¹⁄₃₁₂₅], train_loss:0.159135 Epoch [¹⁄₂], Iter [⁸¹²⁄₃₁₂₅], train_loss:0.161629 Epoch [¹⁄₂], Iter [⁸¹³⁄₃₁₂₅], train_loss:0.172826 Epoch [¹⁄₂], Iter [⁸¹⁴⁄₃₁₂₅], train_loss:0.148274 Epoch [¹⁄₂], Iter [⁸¹⁵⁄₃₁₂₅], train_loss:0.183451 Epoch [¹⁄₂], Iter [⁸¹⁶⁄₃₁₂₅], train_loss:0.164296 Epoch [¹⁄₂], Iter [⁸¹⁷⁄₃₁₂₅], train_loss:0.177334 Epoch [¹⁄₂], Iter [⁸¹⁸⁄₃₁₂₅], train_loss:0.154336 Epoch [¹⁄₂], Iter [⁸¹⁹⁄₃₁₂₅], train_loss:0.170955 Epoch [¹⁄₂], Iter [⁸²⁰⁄₃₁₂₅], train_loss:0.168194 Epoch [¹⁄₂], Iter [⁸²¹⁄₃₁₂₅], train_loss:0.165284 Epoch [¹⁄₂], Iter [⁸²²⁄₃₁₂₅], train_loss:0.153692 Epoch [¹⁄₂], Iter [⁸²³⁄₃₁₂₅], train_loss:0.164452 Epoch [¹⁄₂], Iter [⁸²⁴⁄₃₁₂₅], train_loss:0.160168 Epoch [¹⁄₂], Iter [⁸²⁵⁄₃₁₂₅], train_loss:0.143389 Epoch [¹⁄₂], Iter [⁸²⁶⁄₃₁₂₅], train_loss:0.125640 Epoch [¹⁄₂], Iter [⁸²⁷⁄₃₁₂₅], train_loss:0.154325 Epoch [¹⁄₂], Iter [⁸²⁸⁄₃₁₂₅], train_loss:0.170027 Epoch [¹⁄₂], Iter [⁸²⁹⁄₃₁₂₅], train_loss:0.163227 Epoch [¹⁄₂], Iter [⁸³⁰⁄₃₁₂₅], train_loss:0.180084 Epoch [¹⁄₂], Iter [⁸³¹⁄₃₁₂₅], train_loss:0.153447 Epoch [¹⁄₂], Iter [⁸³²⁄₃₁₂₅], train_loss:0.174136 Epoch [¹⁄₂], Iter [⁸³³⁄₃₁₂₅], train_loss:0.166332 Epoch [¹⁄₂], Iter [⁸³⁴⁄₃₁₂₅], train_loss:0.157354 Epoch [¹⁄₂], Iter [⁸³⁵⁄₃₁₂₅], train_loss:0.120264 Epoch [¹⁄₂], Iter [⁸³⁶⁄₃₁₂₅], train_loss:0.148319 Epoch [¹⁄₂], Iter [⁸³⁷⁄₃₁₂₅], train_loss:0.156353 Epoch [¹⁄₂], Iter [⁸³⁸⁄₃₁₂₅], train_loss:0.153210 Epoch [¹⁄₂], Iter [⁸³⁹⁄₃₁₂₅], train_loss:0.169396 Epoch [¹⁄₂], Iter [⁸⁴⁰⁄₃₁₂₅], train_loss:0.163863 Epoch [¹⁄₂], Iter [⁸⁴¹⁄₃₁₂₅], train_loss:0.156365 Epoch [¹⁄₂], Iter [⁸⁴²⁄₃₁₂₅], train_loss:0.166741 Epoch [¹⁄₂], Iter [⁸⁴³⁄₃₁₂₅], train_loss:0.153688 Epoch [¹⁄₂], Iter [⁸⁴⁴⁄₃₁₂₅], train_loss:0.173625 Epoch [¹⁄₂], Iter [⁸⁴⁵⁄₃₁₂₅], train_loss:0.167021 Epoch [¹⁄₂], Iter [⁸⁴⁶⁄₃₁₂₅], train_loss:0.149013 Epoch [¹⁄₂], Iter [⁸⁴⁷⁄₃₁₂₅], train_loss:0.165667 Epoch [¹⁄₂], Iter [⁸⁴⁸⁄₃₁₂₅], train_loss:0.153663 Epoch [¹⁄₂], Iter [⁸⁴⁹⁄₃₁₂₅], train_loss:0.179361 Epoch [¹⁄₂], Iter [⁸⁵⁰⁄₃₁₂₅], train_loss:0.175290 Epoch [¹⁄₂], Iter [⁸⁵¹⁄₃₁₂₅], train_loss:0.168034 Epoch [¹⁄₂], Iter [⁸⁵²⁄₃₁₂₅], train_loss:0.161994 Epoch [¹⁄₂], Iter [⁸⁵³⁄₃₁₂₅], train_loss:0.171823 Epoch [¹⁄₂], Iter [⁸⁵⁴⁄₃₁₂₅], train_loss:0.147653 Epoch [¹⁄₂], Iter [⁸⁵⁵⁄₃₁₂₅], train_loss:0.159570 Epoch [¹⁄₂], Iter [⁸⁵⁶⁄₃₁₂₅], train_loss:0.157177 Epoch [¹⁄₂], Iter [⁸⁵⁷⁄₃₁₂₅], train_loss:0.155356 Epoch [¹⁄₂], Iter [⁸⁵⁸⁄₃₁₂₅], train_loss:0.159401 Epoch [¹⁄₂], Iter [⁸⁵⁹⁄₃₁₂₅], train_loss:0.179499 Epoch [¹⁄₂], Iter [⁸⁶⁰⁄₃₁₂₅], train_loss:0.153504 Epoch [¹⁄₂], Iter [⁸⁶¹⁄₃₁₂₅], train_loss:0.174314 Epoch [¹⁄₂], Iter [⁸⁶²⁄₃₁₂₅], train_loss:0.145309 Epoch [¹⁄₂], Iter [⁸⁶³⁄₃₁₂₅], train_loss:0.170880 Epoch [¹⁄₂], Iter [⁸⁶⁴⁄₃₁₂₅], train_loss:0.171654 Epoch [¹⁄₂], Iter [⁸⁶⁵⁄₃₁₂₅], train_loss:0.125795 Epoch [¹⁄₂], Iter [⁸⁶⁶⁄₃₁₂₅], train_loss:0.161326 Epoch [¹⁄₂], Iter [⁸⁶⁷⁄₃₁₂₅], train_loss:0.170622 Epoch [¹⁄₂], Iter [⁸⁶⁸⁄₃₁₂₅], train_loss:0.164444 Epoch [¹⁄₂], Iter [⁸⁶⁹⁄₃₁₂₅], train_loss:0.138547 Epoch [¹⁄₂], Iter [⁸⁷⁰⁄₃₁₂₅], train_loss:0.158241 Epoch [¹⁄₂], Iter [⁸⁷¹⁄₃₁₂₅], train_loss:0.158963 Epoch [¹⁄₂], Iter [⁸⁷²⁄₃₁₂₅], train_loss:0.198872 Epoch [¹⁄₂], Iter [⁸⁷³⁄₃₁₂₅], train_loss:0.171953 Epoch [¹⁄₂], Iter [⁸⁷⁴⁄₃₁₂₅], train_loss:0.135011 Epoch [¹⁄₂], Iter [⁸⁷⁵⁄₃₁₂₅], train_loss:0.187574 Epoch [¹⁄₂], Iter [⁸⁷⁶⁄₃₁₂₅], train_loss:0.183588 Epoch [¹⁄₂], Iter [⁸⁷⁷⁄₃₁₂₅], train_loss:0.172207 Epoch [¹⁄₂], Iter [⁸⁷⁸⁄₃₁₂₅], train_loss:0.163572 Epoch [¹⁄₂], Iter [⁸⁷⁹⁄₃₁₂₅], train_loss:0.177148 Epoch [¹⁄₂], Iter [⁸⁸⁰⁄₃₁₂₅], train_loss:0.156533 Epoch [¹⁄₂], Iter [⁸⁸¹⁄₃₁₂₅], train_loss:0.164676 Epoch [¹⁄₂], Iter [⁸⁸²⁄₃₁₂₅], train_loss:0.155344 Epoch [¹⁄₂], Iter [⁸⁸³⁄₃₁₂₅], train_loss:0.179421 Epoch [¹⁄₂], Iter [⁸⁸⁴⁄₃₁₂₅], train_loss:0.152775 Epoch [¹⁄₂], Iter [⁸⁸⁵⁄₃₁₂₅], train_loss:0.183656 Epoch [¹⁄₂], Iter [⁸⁸⁶⁄₃₁₂₅], train_loss:0.178685 Epoch [¹⁄₂], Iter [⁸⁸⁷⁄₃₁₂₅], train_loss:0.174813 Epoch [¹⁄₂], Iter [⁸⁸⁸⁄₃₁₂₅], train_loss:0.164418 Epoch [¹⁄₂], Iter [⁸⁸⁹⁄₃₁₂₅], train_loss:0.151287 Epoch [¹⁄₂], Iter [⁸⁹⁰⁄₃₁₂₅], train_loss:0.159186 Epoch [¹⁄₂], Iter [⁸⁹¹⁄₃₁₂₅], train_loss:0.176169 Epoch [¹⁄₂], Iter [⁸⁹²⁄₃₁₂₅], train_loss:0.153548 Epoch [¹⁄₂], Iter [⁸⁹³⁄₃₁₂₅], train_loss:0.163016 Epoch [¹⁄₂], Iter [⁸⁹⁴⁄₃₁₂₅], train_loss:0.152066 Epoch [¹⁄₂], Iter [⁸⁹⁵⁄₃₁₂₅], train_loss:0.161777 Epoch [¹⁄₂], Iter [⁸⁹⁶⁄₃₁₂₅], train_loss:0.147675 Epoch [¹⁄₂], Iter [⁸⁹⁷⁄₃₁₂₅], train_loss:0.176385 Epoch [¹⁄₂], Iter [⁸⁹⁸⁄₃₁₂₅], train_loss:0.163108 Epoch [¹⁄₂], Iter [⁸⁹⁹⁄₃₁₂₅], train_loss:0.157772 Epoch [¹⁄₂], Iter [⁹⁰⁰⁄₃₁₂₅], train_loss:0.176365 Epoch [¹⁄₂], Iter [⁹⁰¹⁄₃₁₂₅], train_loss:0.163414 Epoch [¹⁄₂], Iter [⁹⁰²⁄₃₁₂₅], train_loss:0.152687 Epoch [¹⁄₂], Iter [⁹⁰³⁄₃₁₂₅], train_loss:0.149312 Epoch [¹⁄₂], Iter [⁹⁰⁴⁄₃₁₂₅], train_loss:0.145944 Epoch [¹⁄₂], Iter [⁹⁰⁵⁄₃₁₂₅], train_loss:0.183935 Epoch [¹⁄₂], Iter [⁹⁰⁶⁄₃₁₂₅], train_loss:0.141416 Epoch [¹⁄₂], Iter [⁹⁰⁷⁄₃₁₂₅], train_loss:0.148432 Epoch [¹⁄₂], Iter [⁹⁰⁸⁄₃₁₂₅], train_loss:0.161458 Epoch [¹⁄₂], Iter [⁹⁰⁹⁄₃₁₂₅], train_loss:0.159551 Epoch [¹⁄₂], Iter [⁹¹⁰⁄₃₁₂₅], train_loss:0.147279 Epoch [¹⁄₂], Iter [⁹¹¹⁄₃₁₂₅], train_loss:0.149100 Epoch [¹⁄₂], Iter [⁹¹²⁄₃₁₂₅], train_loss:0.147561 Epoch [¹⁄₂], Iter [⁹¹³⁄₃₁₂₅], train_loss:0.153887 Epoch [¹⁄₂], Iter [⁹¹⁴⁄₃₁₂₅], train_loss:0.155617 Epoch [¹⁄₂], Iter [⁹¹⁵⁄₃₁₂₅], train_loss:0.138967 Epoch [¹⁄₂], Iter [⁹¹⁶⁄₃₁₂₅], train_loss:0.187655 Epoch [¹⁄₂], Iter [⁹¹⁷⁄₃₁₂₅], train_loss:0.189089 Epoch [¹⁄₂], Iter [⁹¹⁸⁄₃₁₂₅], train_loss:0.185985 Epoch [¹⁄₂], Iter [⁹¹⁹⁄₃₁₂₅], train_loss:0.159035 Epoch [¹⁄₂], Iter [⁹²⁰⁄₃₁₂₅], train_loss:0.158106 Epoch [¹⁄₂], Iter [⁹²¹⁄₃₁₂₅], train_loss:0.160929 Epoch [¹⁄₂], Iter [⁹²²⁄₃₁₂₅], train_loss:0.165616 Epoch [¹⁄₂], Iter [⁹²³⁄₃₁₂₅], train_loss:0.159126 Epoch [¹⁄₂], Iter [⁹²⁴⁄₃₁₂₅], train_loss:0.166481 Epoch [¹⁄₂], Iter [⁹²⁵⁄₃₁₂₅], train_loss:0.166022 Epoch [¹⁄₂], Iter [⁹²⁶⁄₃₁₂₅], train_loss:0.143194 Epoch [¹⁄₂], Iter [⁹²⁷⁄₃₁₂₅], train_loss:0.166617 Epoch [¹⁄₂], Iter [⁹²⁸⁄₃₁₂₅], train_loss:0.165519 Epoch [¹⁄₂], Iter [⁹²⁹⁄₃₁₂₅], train_loss:0.149431 Epoch [¹⁄₂], Iter [⁹³⁰⁄₃₁₂₅], train_loss:0.158727 Epoch [¹⁄₂], Iter [⁹³¹⁄₃₁₂₅], train_loss:0.143095 Epoch [¹⁄₂], Iter [⁹³²⁄₃₁₂₅], train_loss:0.153236 Epoch [¹⁄₂], Iter [⁹³³⁄₃₁₂₅], train_loss:0.148599 Epoch [¹⁄₂], Iter [⁹³⁴⁄₃₁₂₅], train_loss:0.159922 Epoch [¹⁄₂], Iter [⁹³⁵⁄₃₁₂₅], train_loss:0.168778 Epoch [¹⁄₂], Iter [⁹³⁶⁄₃₁₂₅], train_loss:0.149560 Epoch [¹⁄₂], Iter [⁹³⁷⁄₃₁₂₅], train_loss:0.160552 Epoch [¹⁄₂], Iter [⁹³⁸⁄₃₁₂₅], train_loss:0.151009 Epoch [¹⁄₂], Iter [⁹³⁹⁄₃₁₂₅], train_loss:0.171371 Epoch [¹⁄₂], Iter [⁹⁴⁰⁄₃₁₂₅], train_loss:0.156552 Epoch [¹⁄₂], Iter [⁹⁴¹⁄₃₁₂₅], train_loss:0.153480 Epoch [¹⁄₂], Iter [⁹⁴²⁄₃₁₂₅], train_loss:0.144583 Epoch [¹⁄₂], Iter [⁹⁴³⁄₃₁₂₅], train_loss:0.156411 Epoch [¹⁄₂], Iter [⁹⁴⁴⁄₃₁₂₅], train_loss:0.153091 Epoch [¹⁄₂], Iter [⁹⁴⁵⁄₃₁₂₅], train_loss:0.158801 Epoch [¹⁄₂], Iter [⁹⁴⁶⁄₃₁₂₅], train_loss:0.139097 Epoch [¹⁄₂], Iter [⁹⁴⁷⁄₃₁₂₅], train_loss:0.171316 Epoch [¹⁄₂], Iter [⁹⁴⁸⁄₃₁₂₅], train_loss:0.179716 Epoch [¹⁄₂], Iter [⁹⁴⁹⁄₃₁₂₅], train_loss:0.150855 Epoch [¹⁄₂], Iter [⁹⁵⁰⁄₃₁₂₅], train_loss:0.159264 Epoch [¹⁄₂], Iter [⁹⁵¹⁄₃₁₂₅], train_loss:0.178506 Epoch [¹⁄₂], Iter [⁹⁵²⁄₃₁₂₅], train_loss:0.165264 Epoch [¹⁄₂], Iter [⁹⁵³⁄₃₁₂₅], train_loss:0.163345 Epoch [¹⁄₂], Iter [⁹⁵⁴⁄₃₁₂₅], train_loss:0.163006 Epoch [¹⁄₂], Iter [⁹⁵⁵⁄₃₁₂₅], train_loss:0.180055 Epoch [¹⁄₂], Iter [⁹⁵⁶⁄₃₁₂₅], train_loss:0.152678 Epoch [¹⁄₂], Iter [⁹⁵⁷⁄₃₁₂₅], train_loss:0.149015 Epoch [¹⁄₂], Iter [⁹⁵⁸⁄₃₁₂₅], train_loss:0.167205 Epoch [¹⁄₂], Iter [⁹⁵⁹⁄₃₁₂₅], train_loss:0.159652 Epoch [¹⁄₂], Iter [⁹⁶⁰⁄₃₁₂₅], train_loss:0.172454 Epoch [¹⁄₂], Iter [⁹⁶¹⁄₃₁₂₅], train_loss:0.152453 Epoch [¹⁄₂], Iter [⁹⁶²⁄₃₁₂₅], train_loss:0.159779 Epoch [¹⁄₂], Iter [⁹⁶³⁄₃₁₂₅], train_loss:0.157254 Epoch [¹⁄₂], Iter [⁹⁶⁴⁄₃₁₂₅], train_loss:0.171195 Epoch [¹⁄₂], Iter [⁹⁶⁵⁄₃₁₂₅], train_loss:0.129605 Epoch [¹⁄₂], Iter [⁹⁶⁶⁄₃₁₂₅], train_loss:0.171718 Epoch [¹⁄₂], Iter [⁹⁶⁷⁄₃₁₂₅], train_loss:0.135528 Epoch [¹⁄₂], Iter [⁹⁶⁸⁄₃₁₂₅], train_loss:0.171078 Epoch [¹⁄₂], Iter [⁹⁶⁹⁄₃₁₂₅], train_loss:0.177459 Epoch [¹⁄₂], Iter [⁹⁷⁰⁄₃₁₂₅], train_loss:0.155430 Epoch [¹⁄₂], Iter [⁹⁷¹⁄₃₁₂₅], train_loss:0.162782 Epoch [¹⁄₂], Iter [⁹⁷²⁄₃₁₂₅], train_loss:0.179943 Epoch [¹⁄₂], Iter [⁹⁷³⁄₃₁₂₅], train_loss:0.159568 Epoch [¹⁄₂], Iter [⁹⁷⁴⁄₃₁₂₅], train_loss:0.145395 Epoch [¹⁄₂], Iter [⁹⁷⁵⁄₃₁₂₅], train_loss:0.162883 Epoch [¹⁄₂], Iter [⁹⁷⁶⁄₃₁₂₅], train_loss:0.152242 Epoch [¹⁄₂], Iter [⁹⁷⁷⁄₃₁₂₅], train_loss:0.178401 Epoch [¹⁄₂], Iter [⁹⁷⁸⁄₃₁₂₅], train_loss:0.149824 Epoch [¹⁄₂], Iter [⁹⁷⁹⁄₃₁₂₅], train_loss:0.164016 Epoch [¹⁄₂], Iter [⁹⁸⁰⁄₃₁₂₅], train_loss:0.173642 Epoch [¹⁄₂], Iter [⁹⁸¹⁄₃₁₂₅], train_loss:0.184837 Epoch [¹⁄₂], Iter [⁹⁸²⁄₃₁₂₅], train_loss:0.157643 Epoch [¹⁄₂], Iter [⁹⁸³⁄₃₁₂₅], train_loss:0.170323 Epoch [¹⁄₂], Iter [⁹⁸⁴⁄₃₁₂₅], train_loss:0.145053 Epoch [¹⁄₂], Iter [⁹⁸⁵⁄₃₁₂₅], train_loss:0.177159 Epoch [¹⁄₂], Iter [⁹⁸⁶⁄₃₁₂₅], train_loss:0.170435 Epoch [¹⁄₂], Iter [⁹⁸⁷⁄₃₁₂₅], train_loss:0.140393 Epoch [¹⁄₂], Iter [⁹⁸⁸⁄₃₁₂₅], train_loss:0.170333 Epoch [¹⁄₂], Iter [⁹⁸⁹⁄₃₁₂₅], train_loss:0.154973 Epoch [¹⁄₂], Iter [⁹⁹⁰⁄₃₁₂₅], train_loss:0.168512 Epoch [¹⁄₂], Iter [⁹⁹¹⁄₃₁₂₅], train_loss:0.171748 Epoch [¹⁄₂], Iter [⁹⁹²⁄₃₁₂₅], train_loss:0.191529 Epoch [¹⁄₂], Iter [⁹⁹³⁄₃₁₂₅], train_loss:0.164100 Epoch [¹⁄₂], Iter [⁹⁹⁴⁄₃₁₂₅], train_loss:0.169794 Epoch [¹⁄₂], Iter [⁹⁹⁵⁄₃₁₂₅], train_loss:0.161297 Epoch [¹⁄₂], Iter [⁹⁹⁶⁄₃₁₂₅], train_loss:0.154997 Epoch [¹⁄₂], Iter [⁹⁹⁷⁄₃₁₂₅], train_loss:0.174858 Epoch [¹⁄₂], Iter [⁹⁹⁸⁄₃₁₂₅], train_loss:0.131562 Epoch [¹⁄₂], Iter [⁹⁹⁹⁄₃₁₂₅], train_loss:0.170373 Epoch [¹⁄₂], Iter [¹⁰⁰⁰⁄₃₁₂₅], train_loss:0.174953 Epoch [¹⁄₂], Iter [¹⁰⁰¹⁄₃₁₂₅], train_loss:0.171201 Epoch [¹⁄₂], Iter [¹⁰⁰²⁄₃₁₂₅], train_loss:0.157745 Epoch [¹⁄₂], Iter [¹⁰⁰³⁄₃₁₂₅], train_loss:0.165321 Epoch [¹⁄₂], Iter [¹⁰⁰⁴⁄₃₁₂₅], train_loss:0.166191 Epoch [¹⁄₂], Iter [¹⁰⁰⁵⁄₃₁₂₅], train_loss:0.161590 Epoch [¹⁄₂], Iter [¹⁰⁰⁶⁄₃₁₂₅], train_loss:0.155218 Epoch [¹⁄₂], Iter [¹⁰⁰⁷⁄₃₁₂₅], train_loss:0.161306 Epoch [¹⁄₂], Iter [¹⁰⁰⁸⁄₃₁₂₅], train_loss:0.160885 Epoch [¹⁄₂], Iter [¹⁰⁰⁹⁄₃₁₂₅], train_loss:0.150420 Epoch [¹⁄₂], Iter [¹⁰¹⁰⁄₃₁₂₅], train_loss:0.180716 Epoch [¹⁄₂], Iter [¹⁰¹¹⁄₃₁₂₅], train_loss:0.170864 Epoch [¹⁄₂], Iter [¹⁰¹²⁄₃₁₂₅], train_loss:0.155604 Epoch [¹⁄₂], Iter [¹⁰¹³⁄₃₁₂₅], train_loss:0.138882 Epoch [¹⁄₂], Iter [¹⁰¹⁴⁄₃₁₂₅], train_loss:0.163906 Epoch [¹⁄₂], Iter [¹⁰¹⁵⁄₃₁₂₅], train_loss:0.157286 Epoch [¹⁄₂], Iter [¹⁰¹⁶⁄₃₁₂₅], train_loss:0.176689 Epoch [¹⁄₂], Iter [¹⁰¹⁷⁄₃₁₂₅], train_loss:0.164429 Epoch [¹⁄₂], Iter [¹⁰¹⁸⁄₃₁₂₅], train_loss:0.151421 Epoch [¹⁄₂], Iter [¹⁰¹⁹⁄₃₁₂₅], train_loss:0.173269 Epoch [¹⁄₂], Iter [¹⁰²⁰⁄₃₁₂₅], train_loss:0.159520 Epoch [¹⁄₂], Iter [¹⁰²¹⁄₃₁₂₅], train_loss:0.136108 Epoch [¹⁄₂], Iter [¹⁰²²⁄₃₁₂₅], train_loss:0.168635 Epoch [¹⁄₂], Iter [¹⁰²³⁄₃₁₂₅], train_loss:0.172606 Epoch [¹⁄₂], Iter [¹⁰²⁴⁄₃₁₂₅], train_loss:0.169962 Epoch [¹⁄₂], Iter [¹⁰²⁵⁄₃₁₂₅], train_loss:0.171667 Epoch [¹⁄₂], Iter [¹⁰²⁶⁄₃₁₂₅], train_loss:0.186360 Epoch [¹⁄₂], Iter [¹⁰²⁷⁄₃₁₂₅], train_loss:0.154808 Epoch [¹⁄₂], Iter [¹⁰²⁸⁄₃₁₂₅], train_loss:0.162741 Epoch [¹⁄₂], Iter [¹⁰²⁹⁄₃₁₂₅], train_loss:0.168956 Epoch [¹⁄₂], Iter [¹⁰³⁰⁄₃₁₂₅], train_loss:0.167106 Epoch [¹⁄₂], Iter [¹⁰³¹⁄₃₁₂₅], train_loss:0.150996 Epoch [¹⁄₂], Iter [¹⁰³²⁄₃₁₂₅], train_loss:0.148269 Epoch [¹⁄₂], Iter [¹⁰³³⁄₃₁₂₅], train_loss:0.159704 Epoch [¹⁄₂], Iter [¹⁰³⁴⁄₃₁₂₅], train_loss:0.169828 Epoch [¹⁄₂], Iter [¹⁰³⁵⁄₃₁₂₅], train_loss:0.170876 Epoch [¹⁄₂], Iter [¹⁰³⁶⁄₃₁₂₅], train_loss:0.152638 Epoch [¹⁄₂], Iter [¹⁰³⁷⁄₃₁₂₅], train_loss:0.156386 Epoch [¹⁄₂], Iter [¹⁰³⁸⁄₃₁₂₅], train_loss:0.158583 Epoch [¹⁄₂], Iter [¹⁰³⁹⁄₃₁₂₅], train_loss:0.131727 Epoch [¹⁄₂], Iter [¹⁰⁴⁰⁄₃₁₂₅], train_loss:0.159804 Epoch [¹⁄₂], Iter [¹⁰⁴¹⁄₃₁₂₅], train_loss:0.150478 Epoch [¹⁄₂], Iter [¹⁰⁴²⁄₃₁₂₅], train_loss:0.172487 Epoch [¹⁄₂], Iter [¹⁰⁴³⁄₃₁₂₅], train_loss:0.172604 Epoch [¹⁄₂], Iter [¹⁰⁴⁴⁄₃₁₂₅], train_loss:0.176825 Epoch [¹⁄₂], Iter [¹⁰⁴⁵⁄₃₁₂₅], train_loss:0.155156 Epoch [¹⁄₂], Iter [¹⁰⁴⁶⁄₃₁₂₅], train_loss:0.159919 Epoch [¹⁄₂], Iter [¹⁰⁴⁷⁄₃₁₂₅], train_loss:0.158133 Epoch [¹⁄₂], Iter [¹⁰⁴⁸⁄₃₁₂₅], train_loss:0.171692 Epoch [¹⁄₂], Iter [¹⁰⁴⁹⁄₃₁₂₅], train_loss:0.148961 Epoch [¹⁄₂], Iter [¹⁰⁵⁰⁄₃₁₂₅], train_loss:0.145803 Epoch [¹⁄₂], Iter [¹⁰⁵¹⁄₃₁₂₅], train_loss:0.166840 Epoch [¹⁄₂], Iter [¹⁰⁵²⁄₃₁₂₅], train_loss:0.144305 Epoch [¹⁄₂], Iter [¹⁰⁵³⁄₃₁₂₅], train_loss:0.148482 Epoch [¹⁄₂], Iter [¹⁰⁵⁴⁄₃₁₂₅], train_loss:0.159671 Epoch [¹⁄₂], Iter [¹⁰⁵⁵⁄₃₁₂₅], train_loss:0.160208 Epoch [¹⁄₂], Iter [¹⁰⁵⁶⁄₃₁₂₅], train_loss:0.167555 Epoch [¹⁄₂], Iter [¹⁰⁵⁷⁄₃₁₂₅], train_loss:0.161161 Epoch [¹⁄₂], Iter [¹⁰⁵⁸⁄₃₁₂₅], train_loss:0.149388 Epoch [¹⁄₂], Iter [¹⁰⁵⁹⁄₃₁₂₅], train_loss:0.181070 Epoch [¹⁄₂], Iter [¹⁰⁶⁰⁄₃₁₂₅], train_loss:0.171973 Epoch [¹⁄₂], Iter [¹⁰⁶¹⁄₃₁₂₅], train_loss:0.180709 Epoch [¹⁄₂], Iter [¹⁰⁶²⁄₃₁₂₅], train_loss:0.153507 Epoch [¹⁄₂], Iter [¹⁰⁶³⁄₃₁₂₅], train_loss:0.145896 Epoch [¹⁄₂], Iter [¹⁰⁶⁴⁄₃₁₂₅], train_loss:0.166199 Epoch [¹⁄₂], Iter [¹⁰⁶⁵⁄₃₁₂₅], train_loss:0.166107 Epoch [¹⁄₂], Iter [¹⁰⁶⁶⁄₃₁₂₅], train_loss:0.155540 Epoch [¹⁄₂], Iter [¹⁰⁶⁷⁄₃₁₂₅], train_loss:0.154284 Epoch [¹⁄₂], Iter [¹⁰⁶⁸⁄₃₁₂₅], train_loss:0.187118 Epoch [¹⁄₂], Iter [¹⁰⁶⁹⁄₃₁₂₅], train_loss:0.159748 Epoch [¹⁄₂], Iter [¹⁰⁷⁰⁄₃₁₂₅], train_loss:0.164387 Epoch [¹⁄₂], Iter [¹⁰⁷¹⁄₃₁₂₅], train_loss:0.142183 Epoch [¹⁄₂], Iter [¹⁰⁷²⁄₃₁₂₅], train_loss:0.138724 Epoch [¹⁄₂], Iter [¹⁰⁷³⁄₃₁₂₅], train_loss:0.146154 Epoch [¹⁄₂], Iter [¹⁰⁷⁴⁄₃₁₂₅], train_loss:0.162630 Epoch [¹⁄₂], Iter [¹⁰⁷⁵⁄₃₁₂₅], train_loss:0.185121 Epoch [¹⁄₂], Iter [¹⁰⁷⁶⁄₃₁₂₅], train_loss:0.160997 Epoch [¹⁄₂], Iter [¹⁰⁷⁷⁄₃₁₂₅], train_loss:0.179530 Epoch [¹⁄₂], Iter [¹⁰⁷⁸⁄₃₁₂₅], train_loss:0.153985 Epoch [¹⁄₂], Iter [¹⁰⁷⁹⁄₃₁₂₅], train_loss:0.147778 Epoch [¹⁄₂], Iter [¹⁰⁸⁰⁄₃₁₂₅], train_loss:0.149064 Epoch [¹⁄₂], Iter [¹⁰⁸¹⁄₃₁₂₅], train_loss:0.151860 Epoch [¹⁄₂], Iter [¹⁰⁸²⁄₃₁₂₅], train_loss:0.161012 Epoch [¹⁄₂], Iter [¹⁰⁸³⁄₃₁₂₅], train_loss:0.197195 Epoch [¹⁄₂], Iter [¹⁰⁸⁴⁄₃₁₂₅], train_loss:0.157916 Epoch [¹⁄₂], Iter [¹⁰⁸⁵⁄₃₁₂₅], train_loss:0.162013 Epoch [¹⁄₂], Iter [¹⁰⁸⁶⁄₃₁₂₅], train_loss:0.160678 Epoch [¹⁄₂], Iter [¹⁰⁸⁷⁄₃₁₂₅], train_loss:0.168688 Epoch [¹⁄₂], Iter [¹⁰⁸⁸⁄₃₁₂₅], train_loss:0.139971 Epoch [¹⁄₂], Iter [¹⁰⁸⁹⁄₃₁₂₅], train_loss:0.184158 Epoch [¹⁄₂], Iter [¹⁰⁹⁰⁄₃₁₂₅], train_loss:0.184676 Epoch [¹⁄₂], Iter [¹⁰⁹¹⁄₃₁₂₅], train_loss:0.150608 Epoch [¹⁄₂], Iter [¹⁰⁹²⁄₃₁₂₅], train_loss:0.151490 Epoch [¹⁄₂], Iter [¹⁰⁹³⁄₃₁₂₅], train_loss:0.176660 Epoch [¹⁄₂], Iter [¹⁰⁹⁴⁄₃₁₂₅], train_loss:0.153394 Epoch [¹⁄₂], Iter [¹⁰⁹⁵⁄₃₁₂₅], train_loss:0.163054 Epoch [¹⁄₂], Iter [¹⁰⁹⁶⁄₃₁₂₅], train_loss:0.144125 Epoch [¹⁄₂], Iter [¹⁰⁹⁷⁄₃₁₂₅], train_loss:0.167320 Epoch [¹⁄₂], Iter [¹⁰⁹⁸⁄₃₁₂₅], train_loss:0.158095 Epoch [¹⁄₂], Iter [¹⁰⁹⁹⁄₃₁₂₅], train_loss:0.150448 Epoch [¹⁄₂], Iter [¹¹⁰⁰⁄₃₁₂₅], train_loss:0.167379 Epoch [¹⁄₂], Iter [¹¹⁰¹⁄₃₁₂₅], train_loss:0.151696 Epoch [¹⁄₂], Iter [¹¹⁰²⁄₃₁₂₅], train_loss:0.174957 Epoch [¹⁄₂], Iter [¹¹⁰³⁄₃₁₂₅], train_loss:0.159035 Epoch [¹⁄₂], Iter [¹¹⁰⁴⁄₃₁₂₅], train_loss:0.163059 Epoch [¹⁄₂], Iter [¹¹⁰⁵⁄₃₁₂₅], train_loss:0.170439 Epoch [¹⁄₂], Iter [¹¹⁰⁶⁄₃₁₂₅], train_loss:0.163471 Epoch [¹⁄₂], Iter [¹¹⁰⁷⁄₃₁₂₅], train_loss:0.180205 Epoch [¹⁄₂], Iter [¹¹⁰⁸⁄₃₁₂₅], train_loss:0.148346 Epoch [¹⁄₂], Iter [¹¹⁰⁹⁄₃₁₂₅], train_loss:0.170757 Epoch [¹⁄₂], Iter [¹¹¹⁰⁄₃₁₂₅], train_loss:0.155306 Epoch [¹⁄₂], Iter [¹¹¹¹⁄₃₁₂₅], train_loss:0.173857 Epoch [¹⁄₂], Iter [¹¹¹²⁄₃₁₂₅], train_loss:0.149888 Epoch [¹⁄₂], Iter [¹¹¹³⁄₃₁₂₅], train_loss:0.164874 Epoch [¹⁄₂], Iter [¹¹¹⁴⁄₃₁₂₅], train_loss:0.165291 Epoch [¹⁄₂], Iter [¹¹¹⁵⁄₃₁₂₅], train_loss:0.143524 Epoch [¹⁄₂], Iter [¹¹¹⁶⁄₃₁₂₅], train_loss:0.151315 Epoch [¹⁄₂], Iter [¹¹¹⁷⁄₃₁₂₅], train_loss:0.169421 Epoch [¹⁄₂], Iter [¹¹¹⁸⁄₃₁₂₅], train_loss:0.166722 Epoch [¹⁄₂], Iter [¹¹¹⁹⁄₃₁₂₅], train_loss:0.167637 Epoch [¹⁄₂], Iter [¹¹²⁰⁄₃₁₂₅], train_loss:0.155744 Epoch [¹⁄₂], Iter [¹¹²¹⁄₃₁₂₅], train_loss:0.162011 Epoch [¹⁄₂], Iter [¹¹²²⁄₃₁₂₅], train_loss:0.160295 Epoch [¹⁄₂], Iter [¹¹²³⁄₃₁₂₅], train_loss:0.154625 Epoch [¹⁄₂], Iter [¹¹²⁴⁄₃₁₂₅], train_loss:0.151765 Epoch [¹⁄₂], Iter [¹¹²⁵⁄₃₁₂₅], train_loss:0.170621 Epoch [¹⁄₂], Iter [¹¹²⁶⁄₃₁₂₅], train_loss:0.155552 Epoch [¹⁄₂], Iter [¹¹²⁷⁄₃₁₂₅], train_loss:0.173134 Epoch [¹⁄₂], Iter [¹¹²⁸⁄₃₁₂₅], train_loss:0.153150 Epoch [¹⁄₂], Iter [¹¹²⁹⁄₃₁₂₅], train_loss:0.145719 Epoch [¹⁄₂], Iter [¹¹³⁰⁄₃₁₂₅], train_loss:0.187136 Epoch [¹⁄₂], Iter [¹¹³¹⁄₃₁₂₅], train_loss:0.169417 Epoch [¹⁄₂], Iter [¹¹³²⁄₃₁₂₅], train_loss:0.178974 Epoch [¹⁄₂], Iter [¹¹³³⁄₃₁₂₅], train_loss:0.149931 Epoch [¹⁄₂], Iter [¹¹³⁴⁄₃₁₂₅], train_loss:0.155474 Epoch [¹⁄₂], Iter [¹¹³⁵⁄₃₁₂₅], train_loss:0.161715 Epoch [¹⁄₂], Iter [¹¹³⁶⁄₃₁₂₅], train_loss:0.165408 Epoch [¹⁄₂], Iter [¹¹³⁷⁄₃₁₂₅], train_loss:0.170022 Epoch [¹⁄₂], Iter [¹¹³⁸⁄₃₁₂₅], train_loss:0.147393 Epoch [¹⁄₂], Iter [¹¹³⁹⁄₃₁₂₅], train_loss:0.175394 Epoch [¹⁄₂], Iter [¹¹⁴⁰⁄₃₁₂₅], train_loss:0.157841 Epoch [¹⁄₂], Iter [¹¹⁴¹⁄₃₁₂₅], train_loss:0.164718 Epoch [¹⁄₂], Iter [¹¹⁴²⁄₃₁₂₅], train_loss:0.154701 Epoch [¹⁄₂], Iter [¹¹⁴³⁄₃₁₂₅], train_loss:0.168679 Epoch [¹⁄₂], Iter [¹¹⁴⁴⁄₃₁₂₅], train_loss:0.181446 Epoch [¹⁄₂], Iter [¹¹⁴⁵⁄₃₁₂₅], train_loss:0.148103 Epoch [¹⁄₂], Iter [¹¹⁴⁶⁄₃₁₂₅], train_loss:0.151220 Epoch [¹⁄₂], Iter [¹¹⁴⁷⁄₃₁₂₅], train_loss:0.186586 Epoch [¹⁄₂], Iter [¹¹⁴⁸⁄₃₁₂₅], train_loss:0.174347 Epoch [¹⁄₂], Iter [¹¹⁴⁹⁄₃₁₂₅], train_loss:0.170932 Epoch [¹⁄₂], Iter [¹¹⁵⁰⁄₃₁₂₅], train_loss:0.165207 Epoch [¹⁄₂], Iter [¹¹⁵¹⁄₃₁₂₅], train_loss:0.158725 Epoch [¹⁄₂], Iter [¹¹⁵²⁄₃₁₂₅], train_loss:0.155164 Epoch [¹⁄₂], Iter [¹¹⁵³⁄₃₁₂₅], train_loss:0.171893 Epoch [¹⁄₂], Iter [¹¹⁵⁴⁄₃₁₂₅], train_loss:0.162601 Epoch [¹⁄₂], Iter [¹¹⁵⁵⁄₃₁₂₅], train_loss:0.160125 Epoch [¹⁄₂], Iter [¹¹⁵⁶⁄₃₁₂₅], train_loss:0.181936 Epoch [¹⁄₂], Iter [¹¹⁵⁷⁄₃₁₂₅], train_loss:0.172337 Epoch [¹⁄₂], Iter [¹¹⁵⁸⁄₃₁₂₅], train_loss:0.147319 Epoch [¹⁄₂], Iter [¹¹⁵⁹⁄₃₁₂₅], train_loss:0.183120 Epoch [¹⁄₂], Iter [¹¹⁶⁰⁄₃₁₂₅], train_loss:0.168000 Epoch [¹⁄₂], Iter [¹¹⁶¹⁄₃₁₂₅], train_loss:0.163454 Epoch [¹⁄₂], Iter [¹¹⁶²⁄₃₁₂₅], train_loss:0.158614 Epoch [¹⁄₂], Iter [¹¹⁶³⁄₃₁₂₅], train_loss:0.170988 Epoch [¹⁄₂], Iter [¹¹⁶⁴⁄₃₁₂₅], train_loss:0.162558 Epoch [¹⁄₂], Iter [¹¹⁶⁵⁄₃₁₂₅], train_loss:0.164345 Epoch [¹⁄₂], Iter [¹¹⁶⁶⁄₃₁₂₅], train_loss:0.151922 Epoch [¹⁄₂], Iter [¹¹⁶⁷⁄₃₁₂₅], train_loss:0.182245 Epoch [¹⁄₂], Iter [¹¹⁶⁸⁄₃₁₂₅], train_loss:0.162371 Epoch [¹⁄₂], Iter [¹¹⁶⁹⁄₃₁₂₅], train_loss:0.155639 Epoch [¹⁄₂], Iter [¹¹⁷⁰⁄₃₁₂₅], train_loss:0.157078 Epoch [¹⁄₂], Iter [¹¹⁷¹⁄₃₁₂₅], train_loss:0.168648 Epoch [¹⁄₂], Iter [¹¹⁷²⁄₃₁₂₅], train_loss:0.160894 Epoch [¹⁄₂], Iter [¹¹⁷³⁄₃₁₂₅], train_loss:0.172699 Epoch [¹⁄₂], Iter [¹¹⁷⁴⁄₃₁₂₅], train_loss:0.186120 Epoch [¹⁄₂], Iter [¹¹⁷⁵⁄₃₁₂₅], train_loss:0.163291 Epoch [¹⁄₂], Iter [¹¹⁷⁶⁄₃₁₂₅], train_loss:0.160210 Epoch [¹⁄₂], Iter [¹¹⁷⁷⁄₃₁₂₅], train_loss:0.157460 Epoch [¹⁄₂], Iter [¹¹⁷⁸⁄₃₁₂₅], train_loss:0.169464 Epoch [¹⁄₂], Iter [¹¹⁷⁹⁄₃₁₂₅], train_loss:0.155117 Epoch [¹⁄₂], Iter [¹¹⁸⁰⁄₃₁₂₅], train_loss:0.175044 Epoch [¹⁄₂], Iter [¹¹⁸¹⁄₃₁₂₅], train_loss:0.171335 Epoch [¹⁄₂], Iter [¹¹⁸²⁄₃₁₂₅], train_loss:0.156485 Epoch [¹⁄₂], Iter [¹¹⁸³⁄₃₁₂₅], train_loss:0.166067 Epoch [¹⁄₂], Iter [¹¹⁸⁴⁄₃₁₂₅], train_loss:0.161618 Epoch [¹⁄₂], Iter [¹¹⁸⁵⁄₃₁₂₅], train_loss:0.158961 Epoch [¹⁄₂], Iter [¹¹⁸⁶⁄₃₁₂₅], train_loss:0.158767 Epoch [¹⁄₂], Iter [¹¹⁸⁷⁄₃₁₂₅], train_loss:0.158581 Epoch [¹⁄₂], Iter [¹¹⁸⁸⁄₃₁₂₅], train_loss:0.150107 Epoch [¹⁄₂], Iter [¹¹⁸⁹⁄₃₁₂₅], train_loss:0.151393 Epoch [¹⁄₂], Iter [¹¹⁹⁰⁄₃₁₂₅], train_loss:0.157746 Epoch [¹⁄₂], Iter [¹¹⁹¹⁄₃₁₂₅], train_loss:0.162504 Epoch [¹⁄₂], Iter [¹¹⁹²⁄₃₁₂₅], train_loss:0.162217 Epoch [¹⁄₂], Iter [¹¹⁹³⁄₃₁₂₅], train_loss:0.184125 Epoch [¹⁄₂], Iter [¹¹⁹⁴⁄₃₁₂₅], train_loss:0.155755 Epoch [¹⁄₂], Iter [¹¹⁹⁵⁄₃₁₂₅], train_loss:0.163561 Epoch [¹⁄₂], Iter [¹¹⁹⁶⁄₃₁₂₅], train_loss:0.169904 Epoch [¹⁄₂], Iter [¹¹⁹⁷⁄₃₁₂₅], train_loss:0.163287 Epoch [¹⁄₂], Iter [¹¹⁹⁸⁄₃₁₂₅], train_loss:0.162994 Epoch [¹⁄₂], Iter [¹¹⁹⁹⁄₃₁₂₅], train_loss:0.179970 Epoch [¹⁄₂], Iter [¹²⁰⁰⁄₃₁₂₅], train_loss:0.175508 Epoch [¹⁄₂], Iter [¹²⁰¹⁄₃₁₂₅], train_loss:0.171165 Epoch [¹⁄₂], Iter [¹²⁰²⁄₃₁₂₅], train_loss:0.157112 Epoch [¹⁄₂], Iter [¹²⁰³⁄₃₁₂₅], train_loss:0.162217 Epoch [¹⁄₂], Iter [¹²⁰⁴⁄₃₁₂₅], train_loss:0.168821 Epoch [¹⁄₂], Iter [¹²⁰⁵⁄₃₁₂₅], train_loss:0.197255 Epoch [¹⁄₂], Iter [¹²⁰⁶⁄₃₁₂₅], train_loss:0.160194 Epoch [¹⁄₂], Iter [¹²⁰⁷⁄₃₁₂₅], train_loss:0.151903 Epoch [¹⁄₂], Iter [¹²⁰⁸⁄₃₁₂₅], train_loss:0.149178 Epoch [¹⁄₂], Iter [¹²⁰⁹⁄₃₁₂₅], train_loss:0.146489 Epoch [¹⁄₂], Iter [¹²¹⁰⁄₃₁₂₅], train_loss:0.154193 Epoch [¹⁄₂], Iter [¹²¹¹⁄₃₁₂₅], train_loss:0.157028 Epoch [¹⁄₂], Iter [¹²¹²⁄₃₁₂₅], train_loss:0.162961 Epoch [¹⁄₂], Iter [¹²¹³⁄₃₁₂₅], train_loss:0.176358 Epoch [¹⁄₂], Iter [¹²¹⁴⁄₃₁₂₅], train_loss:0.170513 Epoch [¹⁄₂], Iter [¹²¹⁵⁄₃₁₂₅], train_loss:0.166415 Epoch [¹⁄₂], Iter [¹²¹⁶⁄₃₁₂₅], train_loss:0.150504 Epoch [¹⁄₂], Iter [¹²¹⁷⁄₃₁₂₅], train_loss:0.169194 Epoch [¹⁄₂], Iter [¹²¹⁸⁄₃₁₂₅], train_loss:0.173286 Epoch [¹⁄₂], Iter [¹²¹⁹⁄₃₁₂₅], train_loss:0.170073 Epoch [¹⁄₂], Iter [¹²²⁰⁄₃₁₂₅], train_loss:0.157464 Epoch [¹⁄₂], Iter [¹²²¹⁄₃₁₂₅], train_loss:0.153022 Epoch [¹⁄₂], Iter [¹²²²⁄₃₁₂₅], train_loss:0.164855 Epoch [¹⁄₂], Iter [¹²²³⁄₃₁₂₅], train_loss:0.155083 Epoch [¹⁄₂], Iter [¹²²⁴⁄₃₁₂₅], train_loss:0.165551 Epoch [¹⁄₂], Iter [¹²²⁵⁄₃₁₂₅], train_loss:0.185195 Epoch [¹⁄₂], Iter [¹²²⁶⁄₃₁₂₅], train_loss:0.177821 Epoch [¹⁄₂], Iter [¹²²⁷⁄₃₁₂₅], train_loss:0.154561 Epoch [¹⁄₂], Iter [¹²²⁸⁄₃₁₂₅], train_loss:0.159085 Epoch [¹⁄₂], Iter [¹²²⁹⁄₃₁₂₅], train_loss:0.171906 Epoch [¹⁄₂], Iter [¹²³⁰⁄₃₁₂₅], train_loss:0.160470 Epoch [¹⁄₂], Iter [¹²³¹⁄₃₁₂₅], train_loss:0.151237 Epoch [¹⁄₂], Iter [¹²³²⁄₃₁₂₅], train_loss:0.135055 Epoch [¹⁄₂], Iter [¹²³³⁄₃₁₂₅], train_loss:0.140605 Epoch [¹⁄₂], Iter [¹²³⁴⁄₃₁₂₅], train_loss:0.183646 Epoch [¹⁄₂], Iter [¹²³⁵⁄₃₁₂₅], train_loss:0.158728 Epoch [¹⁄₂], Iter [¹²³⁶⁄₃₁₂₅], train_loss:0.163355 Epoch [¹⁄₂], Iter [¹²³⁷⁄₃₁₂₅], train_loss:0.148448 Epoch [¹⁄₂], Iter [¹²³⁸⁄₃₁₂₅], train_loss:0.165396 Epoch [¹⁄₂], Iter [¹²³⁹⁄₃₁₂₅], train_loss:0.181543 Epoch [¹⁄₂], Iter [¹²⁴⁰⁄₃₁₂₅], train_loss:0.166355 Epoch [¹⁄₂], Iter [¹²⁴¹⁄₃₁₂₅], train_loss:0.158869 Epoch [¹⁄₂], Iter [¹²⁴²⁄₃₁₂₅], train_loss:0.153979 Epoch [¹⁄₂], Iter [¹²⁴³⁄₃₁₂₅], train_loss:0.155492 Epoch [¹⁄₂], Iter [¹²⁴⁴⁄₃₁₂₅], train_loss:0.170940 Epoch [¹⁄₂], Iter [¹²⁴⁵⁄₃₁₂₅], train_loss:0.166005 Epoch [¹⁄₂], Iter [¹²⁴⁶⁄₃₁₂₅], train_loss:0.158416 Epoch [¹⁄₂], Iter [¹²⁴⁷⁄₃₁₂₅], train_loss:0.154584 Epoch [¹⁄₂], Iter [¹²⁴⁸⁄₃₁₂₅], train_loss:0.152003 Epoch [¹⁄₂], Iter [¹²⁴⁹⁄₃₁₂₅], train_loss:0.168855 Epoch [¹⁄₂], Iter [¹²⁵⁰⁄₃₁₂₅], train_loss:0.148871 Epoch [¹⁄₂], Iter [¹²⁵¹⁄₃₁₂₅], train_loss:0.175113 Epoch [¹⁄₂], Iter [¹²⁵²⁄₃₁₂₅], train_loss:0.149920 Epoch [¹⁄₂], Iter [¹²⁵³⁄₃₁₂₅], train_loss:0.151580 Epoch [¹⁄₂], Iter [¹²⁵⁴⁄₃₁₂₅], train_loss:0.168768 Epoch [¹⁄₂], Iter [¹²⁵⁵⁄₃₁₂₅], train_loss:0.166119 Epoch [¹⁄₂], Iter [¹²⁵⁶⁄₃₁₂₅], train_loss:0.140963 Epoch [¹⁄₂], Iter [¹²⁵⁷⁄₃₁₂₅], train_loss:0.168684 Epoch [¹⁄₂], Iter [¹²⁵⁸⁄₃₁₂₅], train_loss:0.158394 Epoch [¹⁄₂], Iter [¹²⁵⁹⁄₃₁₂₅], train_loss:0.161410 Epoch [¹⁄₂], Iter [¹²⁶⁰⁄₃₁₂₅], train_loss:0.148364 Epoch [¹⁄₂], Iter [¹²⁶¹⁄₃₁₂₅], train_loss:0.165485 Epoch [¹⁄₂], Iter [¹²⁶²⁄₃₁₂₅], train_loss:0.153689 Epoch [¹⁄₂], Iter [¹²⁶³⁄₃₁₂₅], train_loss:0.171761 Epoch [¹⁄₂], Iter [¹²⁶⁴⁄₃₁₂₅], train_loss:0.163797 Epoch [¹⁄₂], Iter [¹²⁶⁵⁄₃₁₂₅], train_loss:0.146530 Epoch [¹⁄₂], Iter [¹²⁶⁶⁄₃₁₂₅], train_loss:0.158110 Epoch [¹⁄₂], Iter [¹²⁶⁷⁄₃₁₂₅], train_loss:0.160058 Epoch [¹⁄₂], Iter [¹²⁶⁸⁄₃₁₂₅], train_loss:0.157368 Epoch [¹⁄₂], Iter [¹²⁶⁹⁄₃₁₂₅], train_loss:0.151690 Epoch [¹⁄₂], Iter [¹²⁷⁰⁄₃₁₂₅], train_loss:0.142817 Epoch [¹⁄₂], Iter [¹²⁷¹⁄₃₁₂₅], train_loss:0.153046 Epoch [¹⁄₂], Iter [¹²⁷²⁄₃₁₂₅], train_loss:0.162205 Epoch [¹⁄₂], Iter [¹²⁷³⁄₃₁₂₅], train_loss:0.179852 Epoch [¹⁄₂], Iter [¹²⁷⁴⁄₃₁₂₅], train_loss:0.156627 Epoch [¹⁄₂], Iter [¹²⁷⁵⁄₃₁₂₅], train_loss:0.158944 Epoch [¹⁄₂], Iter [¹²⁷⁶⁄₃₁₂₅], train_loss:0.148821 Epoch [¹⁄₂], Iter [¹²⁷⁷⁄₃₁₂₅], train_loss:0.157448 Epoch [¹⁄₂], Iter [¹²⁷⁸⁄₃₁₂₅], train_loss:0.178943 Epoch [¹⁄₂], Iter [¹²⁷⁹⁄₃₁₂₅], train_loss:0.170738 Epoch [¹⁄₂], Iter [¹²⁸⁰⁄₃₁₂₅], train_loss:0.146238 Epoch [¹⁄₂], Iter [¹²⁸¹⁄₃₁₂₅], train_loss:0.166454 Epoch [¹⁄₂], Iter [¹²⁸²⁄₃₁₂₅], train_loss:0.147360 Epoch [¹⁄₂], Iter [¹²⁸³⁄₃₁₂₅], train_loss:0.166235 Epoch [¹⁄₂], Iter [¹²⁸⁴⁄₃₁₂₅], train_loss:0.160503 Epoch [¹⁄₂], Iter [¹²⁸⁵⁄₃₁₂₅], train_loss:0.155493 Epoch [¹⁄₂], Iter [¹²⁸⁶⁄₃₁₂₅], train_loss:0.164259 Epoch [¹⁄₂], Iter [¹²⁸⁷⁄₃₁₂₅], train_loss:0.159880 Epoch [¹⁄₂], Iter [¹²⁸⁸⁄₃₁₂₅], train_loss:0.174088 Epoch [¹⁄₂], Iter [¹²⁸⁹⁄₃₁₂₅], train_loss:0.158363 Epoch [¹⁄₂], Iter [¹²⁹⁰⁄₃₁₂₅], train_loss:0.160815 Epoch [¹⁄₂], Iter [¹²⁹¹⁄₃₁₂₅], train_loss:0.168558 Epoch [¹⁄₂], Iter [¹²⁹²⁄₃₁₂₅], train_loss:0.155379 Epoch [¹⁄₂], Iter [¹²⁹³⁄₃₁₂₅], train_loss:0.158657 Epoch [¹⁄₂], Iter [¹²⁹⁴⁄₃₁₂₅], train_loss:0.152092 Epoch [¹⁄₂], Iter [¹²⁹⁵⁄₃₁₂₅], train_loss:0.151002 Epoch [¹⁄₂], Iter [¹²⁹⁶⁄₃₁₂₅], train_loss:0.177545 Epoch [¹⁄₂], Iter [¹²⁹⁷⁄₃₁₂₅], train_loss:0.155996 Epoch [¹⁄₂], Iter [¹²⁹⁸⁄₃₁₂₅], train_loss:0.153431 Epoch [¹⁄₂], Iter [¹²⁹⁹⁄₃₁₂₅], train_loss:0.160402 Epoch [¹⁄₂], Iter [¹³⁰⁰⁄₃₁₂₅], train_loss:0.164605 Epoch [¹⁄₂], Iter [¹³⁰¹⁄₃₁₂₅], train_loss:0.181966 Epoch [¹⁄₂], Iter [¹³⁰²⁄₃₁₂₅], train_loss:0.150270 Epoch [¹⁄₂], Iter [¹³⁰³⁄₃₁₂₅], train_loss:0.153899 Epoch [¹⁄₂], Iter [¹³⁰⁴⁄₃₁₂₅], train_loss:0.167255 Epoch [¹⁄₂], Iter [¹³⁰⁵⁄₃₁₂₅], train_loss:0.164807 Epoch [¹⁄₂], Iter [¹³⁰⁶⁄₃₁₂₅], train_loss:0.176301 Epoch [¹⁄₂], Iter [¹³⁰⁷⁄₃₁₂₅], train_loss:0.155036 Epoch [¹⁄₂], Iter [¹³⁰⁸⁄₃₁₂₅], train_loss:0.167926 Epoch [¹⁄₂], Iter [¹³⁰⁹⁄₃₁₂₅], train_loss:0.176630 Epoch [¹⁄₂], Iter [¹³¹⁰⁄₃₁₂₅], train_loss:0.160102 Epoch [¹⁄₂], Iter [¹³¹¹⁄₃₁₂₅], train_loss:0.173452 Epoch [¹⁄₂], Iter [¹³¹²⁄₃₁₂₅], train_loss:0.172366 Epoch [¹⁄₂], Iter [¹³¹³⁄₃₁₂₅], train_loss:0.156772 Epoch [¹⁄₂], Iter [¹³¹⁴⁄₃₁₂₅], train_loss:0.168792 Epoch [¹⁄₂], Iter [¹³¹⁵⁄₃₁₂₅], train_loss:0.178687 Epoch [¹⁄₂], Iter [¹³¹⁶⁄₃₁₂₅], train_loss:0.181647 Epoch [¹⁄₂], Iter [¹³¹⁷⁄₃₁₂₅], train_loss:0.154158 Epoch [¹⁄₂], Iter [¹³¹⁸⁄₃₁₂₅], train_loss:0.151710 Epoch [¹⁄₂], Iter [¹³¹⁹⁄₃₁₂₅], train_loss:0.183539 Epoch [¹⁄₂], Iter [¹³²⁰⁄₃₁₂₅], train_loss:0.160138 Epoch [¹⁄₂], Iter [¹³²¹⁄₃₁₂₅], train_loss:0.177658 Epoch [¹⁄₂], Iter [¹³²²⁄₃₁₂₅], train_loss:0.146497 Epoch [¹⁄₂], Iter [¹³²³⁄₃₁₂₅], train_loss:0.196226 Epoch [¹⁄₂], Iter [¹³²⁴⁄₃₁₂₅], train_loss:0.165244 Epoch [¹⁄₂], Iter [¹³²⁵⁄₃₁₂₅], train_loss:0.197831 Epoch [¹⁄₂], Iter [¹³²⁶⁄₃₁₂₅], train_loss:0.175092 Epoch [¹⁄₂], Iter [¹³²⁷⁄₃₁₂₅], train_loss:0.184453 Epoch [¹⁄₂], Iter [¹³²⁸⁄₃₁₂₅], train_loss:0.165453 Epoch [¹⁄₂], Iter [¹³²⁹⁄₃₁₂₅], train_loss:0.145549 Epoch [¹⁄₂], Iter [¹³³⁰⁄₃₁₂₅], train_loss:0.173061 Epoch [¹⁄₂], Iter [¹³³¹⁄₃₁₂₅], train_loss:0.166073 Epoch [¹⁄₂], Iter [¹³³²⁄₃₁₂₅], train_loss:0.156471 Epoch [¹⁄₂], Iter [¹³³³⁄₃₁₂₅], train_loss:0.152220 Epoch [¹⁄₂], Iter [¹³³⁴⁄₃₁₂₅], train_loss:0.156158 Epoch [¹⁄₂], Iter [¹³³⁵⁄₃₁₂₅], train_loss:0.165017 Epoch [¹⁄₂], Iter [¹³³⁶⁄₃₁₂₅], train_loss:0.183256 Epoch [¹⁄₂], Iter [¹³³⁷⁄₃₁₂₅], train_loss:0.167704 Epoch [¹⁄₂], Iter [¹³³⁸⁄₃₁₂₅], train_loss:0.154254 Epoch [¹⁄₂], Iter [¹³³⁹⁄₃₁₂₅], train_loss:0.162098 Epoch [¹⁄₂], Iter [¹³⁴⁰⁄₃₁₂₅], train_loss:0.161697 Epoch [¹⁄₂], Iter [¹³⁴¹⁄₃₁₂₅], train_loss:0.164405 Epoch [¹⁄₂], Iter [¹³⁴²⁄₃₁₂₅], train_loss:0.149967 Epoch [¹⁄₂], Iter [¹³⁴³⁄₃₁₂₅], train_loss:0.171982 Epoch [¹⁄₂], Iter [¹³⁴⁴⁄₃₁₂₅], train_loss:0.155723 Epoch [¹⁄₂], Iter [¹³⁴⁵⁄₃₁₂₅], train_loss:0.147691 Epoch [¹⁄₂], Iter [¹³⁴⁶⁄₃₁₂₅], train_loss:0.160214 Epoch [¹⁄₂], Iter [¹³⁴⁷⁄₃₁₂₅], train_loss:0.154677 Epoch [¹⁄₂], Iter [¹³⁴⁸⁄₃₁₂₅], train_loss:0.152759 Epoch [¹⁄₂], Iter [¹³⁴⁹⁄₃₁₂₅], train_loss:0.166476 Epoch [¹⁄₂], Iter [¹³⁵⁰⁄₃₁₂₅], train_loss:0.163566 Epoch [¹⁄₂], Iter [¹³⁵¹⁄₃₁₂₅], train_loss:0.150434 Epoch [¹⁄₂], Iter [¹³⁵²⁄₃₁₂₅], train_loss:0.168793 Epoch [¹⁄₂], Iter [¹³⁵³⁄₃₁₂₅], train_loss:0.162513 Epoch [¹⁄₂], Iter [¹³⁵⁴⁄₃₁₂₅], train_loss:0.169711 Epoch [¹⁄₂], Iter [¹³⁵⁵⁄₃₁₂₅], train_loss:0.158046 Epoch [¹⁄₂], Iter [¹³⁵⁶⁄₃₁₂₅], train_loss:0.151754 Epoch [¹⁄₂], Iter [¹³⁵⁷⁄₃₁₂₅], train_loss:0.170661 Epoch [¹⁄₂], Iter [¹³⁵⁸⁄₃₁₂₅], train_loss:0.152679 Epoch [¹⁄₂], Iter [¹³⁵⁹⁄₃₁₂₅], train_loss:0.167173 Epoch [¹⁄₂], Iter [¹³⁶⁰⁄₃₁₂₅], train_loss:0.156606 Epoch [¹⁄₂], Iter [¹³⁶¹⁄₃₁₂₅], train_loss:0.183170 Epoch [¹⁄₂], Iter [¹³⁶²⁄₃₁₂₅], train_loss:0.142545 Epoch [¹⁄₂], Iter [¹³⁶³⁄₃₁₂₅], train_loss:0.159119 Epoch [¹⁄₂], Iter [¹³⁶⁴⁄₃₁₂₅], train_loss:0.164405 Epoch [¹⁄₂], Iter [¹³⁶⁵⁄₃₁₂₅], train_loss:0.159609 Epoch [¹⁄₂], Iter [¹³⁶⁶⁄₃₁₂₅], train_loss:0.161490 Epoch [¹⁄₂], Iter [¹³⁶⁷⁄₃₁₂₅], train_loss:0.167248 Epoch [¹⁄₂], Iter [¹³⁶⁸⁄₃₁₂₅], train_loss:0.165266 Epoch [¹⁄₂], Iter [¹³⁶⁹⁄₃₁₂₅], train_loss:0.164672 Epoch [¹⁄₂], Iter [¹³⁷⁰⁄₃₁₂₅], train_loss:0.178968 Epoch [¹⁄₂], Iter [¹³⁷¹⁄₃₁₂₅], train_loss:0.139022 Epoch [¹⁄₂], Iter [¹³⁷²⁄₃₁₂₅], train_loss:0.157129 Epoch [¹⁄₂], Iter [¹³⁷³⁄₃₁₂₅], train_loss:0.170236 Epoch [¹⁄₂], Iter [¹³⁷⁴⁄₃₁₂₅], train_loss:0.172654 Epoch [¹⁄₂], Iter [¹³⁷⁵⁄₃₁₂₅], train_loss:0.154364 Epoch [¹⁄₂], Iter [¹³⁷⁶⁄₃₁₂₅], train_loss:0.191031 Epoch [¹⁄₂], Iter [¹³⁷⁷⁄₃₁₂₅], train_loss:0.154899 Epoch [¹⁄₂], Iter [¹³⁷⁸⁄₃₁₂₅], train_loss:0.154030 Epoch [¹⁄₂], Iter [¹³⁷⁹⁄₃₁₂₅], train_loss:0.164986 Epoch [¹⁄₂], Iter [¹³⁸⁰⁄₃₁₂₅], train_loss:0.149888 Epoch [¹⁄₂], Iter [¹³⁸¹⁄₃₁₂₅], train_loss:0.161112 Epoch [¹⁄₂], Iter [¹³⁸²⁄₃₁₂₅], train_loss:0.177446 Epoch [¹⁄₂], Iter [¹³⁸³⁄₃₁₂₅], train_loss:0.181748 Epoch [¹⁄₂], Iter [¹³⁸⁴⁄₃₁₂₅], train_loss:0.148632 Epoch [¹⁄₂], Iter [¹³⁸⁵⁄₃₁₂₅], train_loss:0.171001 Epoch [¹⁄₂], Iter [¹³⁸⁶⁄₃₁₂₅], train_loss:0.146871 Epoch [¹⁄₂], Iter [¹³⁸⁷⁄₃₁₂₅], train_loss:0.152815 Epoch [¹⁄₂], Iter [¹³⁸⁸⁄₃₁₂₅], train_loss:0.153880 Epoch [¹⁄₂], Iter [¹³⁸⁹⁄₃₁₂₅], train_loss:0.167807 Epoch [¹⁄₂], Iter [¹³⁹⁰⁄₃₁₂₅], train_loss:0.163647 Epoch [¹⁄₂], Iter [¹³⁹¹⁄₃₁₂₅], train_loss:0.159752 Epoch [¹⁄₂], Iter [¹³⁹²⁄₃₁₂₅], train_loss:0.148706 Epoch [¹⁄₂], Iter [¹³⁹³⁄₃₁₂₅], train_loss:0.145519 Epoch [¹⁄₂], Iter [¹³⁹⁴⁄₃₁₂₅], train_loss:0.149635 Epoch [¹⁄₂], Iter [¹³⁹⁵⁄₃₁₂₅], train_loss:0.156076 Epoch [¹⁄₂], Iter [¹³⁹⁶⁄₃₁₂₅], train_loss:0.156446 Epoch [¹⁄₂], Iter [¹³⁹⁷⁄₃₁₂₅], train_loss:0.165825 Epoch [¹⁄₂], Iter [¹³⁹⁸⁄₃₁₂₅], train_loss:0.145675 Epoch [¹⁄₂], Iter [¹³⁹⁹⁄₃₁₂₅], train_loss:0.142919 Epoch [¹⁄₂], Iter [¹⁴⁰⁰⁄₃₁₂₅], train_loss:0.163214 Epoch [¹⁄₂], Iter [¹⁴⁰¹⁄₃₁₂₅], train_loss:0.155447 Epoch [¹⁄₂], Iter [¹⁴⁰²⁄₃₁₂₅], train_loss:0.164264 Epoch [¹⁄₂], Iter [¹⁴⁰³⁄₃₁₂₅], train_loss:0.168581 Epoch [¹⁄₂], Iter [¹⁴⁰⁴⁄₃₁₂₅], train_loss:0.149629 Epoch [¹⁄₂], Iter [¹⁴⁰⁵⁄₃₁₂₅], train_loss:0.164211 Epoch [¹⁄₂], Iter [¹⁴⁰⁶⁄₃₁₂₅], train_loss:0.168869 Epoch [¹⁄₂], Iter [¹⁴⁰⁷⁄₃₁₂₅], train_loss:0.153973 Epoch [¹⁄₂], Iter [¹⁴⁰⁸⁄₃₁₂₅], train_loss:0.173186 Epoch [¹⁄₂], Iter [¹⁴⁰⁹⁄₃₁₂₅], train_loss:0.174420 Epoch [¹⁄₂], Iter [¹⁴¹⁰⁄₃₁₂₅], train_loss:0.154398 Epoch [¹⁄₂], Iter [¹⁴¹¹⁄₃₁₂₅], train_loss:0.147271 Epoch [¹⁄₂], Iter [¹⁴¹²⁄₃₁₂₅], train_loss:0.172150 Epoch [¹⁄₂], Iter [¹⁴¹³⁄₃₁₂₅], train_loss:0.144826 Epoch [¹⁄₂], Iter [¹⁴¹⁴⁄₃₁₂₅], train_loss:0.160246 Epoch [¹⁄₂], Iter [¹⁴¹⁵⁄₃₁₂₅], train_loss:0.166100 Epoch [¹⁄₂], Iter [¹⁴¹⁶⁄₃₁₂₅], train_loss:0.151365 Epoch [¹⁄₂], Iter [¹⁴¹⁷⁄₃₁₂₅], train_loss:0.144425 Epoch [¹⁄₂], Iter [¹⁴¹⁸⁄₃₁₂₅], train_loss:0.145632 Epoch [¹⁄₂], Iter [¹⁴¹⁹⁄₃₁₂₅], train_loss:0.167284 Epoch [¹⁄₂], Iter [¹⁴²⁰⁄₃₁₂₅], train_loss:0.162896 Epoch [¹⁄₂], Iter [¹⁴²¹⁄₃₁₂₅], train_loss:0.168027 Epoch [¹⁄₂], Iter [¹⁴²²⁄₃₁₂₅], train_loss:0.160721 Epoch [¹⁄₂], Iter [¹⁴²³⁄₃₁₂₅], train_loss:0.164672 Epoch [¹⁄₂], Iter [¹⁴²⁴⁄₃₁₂₅], train_loss:0.162177 Epoch [¹⁄₂], Iter [¹⁴²⁵⁄₃₁₂₅], train_loss:0.166051 Epoch [¹⁄₂], Iter [¹⁴²⁶⁄₃₁₂₅], train_loss:0.146067 Epoch [¹⁄₂], Iter [¹⁴²⁷⁄₃₁₂₅], train_loss:0.159922 Epoch [¹⁄₂], Iter [¹⁴²⁸⁄₃₁₂₅], train_loss:0.152642 Epoch [¹⁄₂], Iter [¹⁴²⁹⁄₃₁₂₅], train_loss:0.148200 Epoch [¹⁄₂], Iter [¹⁴³⁰⁄₃₁₂₅], train_loss:0.158262 Epoch [¹⁄₂], Iter [¹⁴³¹⁄₃₁₂₅], train_loss:0.149659 Epoch [¹⁄₂], Iter [¹⁴³²⁄₃₁₂₅], train_loss:0.163230 Epoch [¹⁄₂], Iter [¹⁴³³⁄₃₁₂₅], train_loss:0.145847 Epoch [¹⁄₂], Iter [¹⁴³⁴⁄₃₁₂₅], train_loss:0.173391 Epoch [¹⁄₂], Iter [¹⁴³⁵⁄₃₁₂₅], train_loss:0.125152 Epoch [¹⁄₂], Iter [¹⁴³⁶⁄₃₁₂₅], train_loss:0.156048 Epoch [¹⁄₂], Iter [¹⁴³⁷⁄₃₁₂₅], train_loss:0.157051 Epoch [¹⁄₂], Iter [¹⁴³⁸⁄₃₁₂₅], train_loss:0.158350 Epoch [¹⁄₂], Iter [¹⁴³⁹⁄₃₁₂₅], train_loss:0.192877 Epoch [¹⁄₂], Iter [¹⁴⁴⁰⁄₃₁₂₅], train_loss:0.167545 Epoch [¹⁄₂], Iter [¹⁴⁴¹⁄₃₁₂₅], train_loss:0.197214 Epoch [¹⁄₂], Iter [¹⁴⁴²⁄₃₁₂₅], train_loss:0.192135 Epoch [¹⁄₂], Iter [¹⁴⁴³⁄₃₁₂₅], train_loss:0.172984 Epoch [¹⁄₂], Iter [¹⁴⁴⁴⁄₃₁₂₅], train_loss:0.173254 Epoch [¹⁄₂], Iter [¹⁴⁴⁵⁄₃₁₂₅], train_loss:0.144135 Epoch [¹⁄₂], Iter [¹⁴⁴⁶⁄₃₁₂₅], train_loss:0.169613 Epoch [¹⁄₂], Iter [¹⁴⁴⁷⁄₃₁₂₅], train_loss:0.167091 Epoch [¹⁄₂], Iter [¹⁴⁴⁸⁄₃₁₂₅], train_loss:0.158223 Epoch [¹⁄₂], Iter [¹⁴⁴⁹⁄₃₁₂₅], train_loss:0.172568 Epoch [¹⁄₂], Iter [¹⁴⁵⁰⁄₃₁₂₅], train_loss:0.162713 Epoch [¹⁄₂], Iter [¹⁴⁵¹⁄₃₁₂₅], train_loss:0.168839 Epoch [¹⁄₂], Iter [¹⁴⁵²⁄₃₁₂₅], train_loss:0.168881 Epoch [¹⁄₂], Iter [¹⁴⁵³⁄₃₁₂₅], train_loss:0.166082 Epoch [¹⁄₂], Iter [¹⁴⁵⁴⁄₃₁₂₅], train_loss:0.137113 Epoch [¹⁄₂], Iter [¹⁴⁵⁵⁄₃₁₂₅], train_loss:0.156944 Epoch [¹⁄₂], Iter [¹⁴⁵⁶⁄₃₁₂₅], train_loss:0.176010 Epoch [¹⁄₂], Iter [¹⁴⁵⁷⁄₃₁₂₅], train_loss:0.165683 Epoch [¹⁄₂], Iter [¹⁴⁵⁸⁄₃₁₂₅], train_loss:0.166721 Epoch [¹⁄₂], Iter [¹⁴⁵⁹⁄₃₁₂₅], train_loss:0.177907 Epoch [¹⁄₂], Iter [¹⁴⁶⁰⁄₃₁₂₅], train_loss:0.148519 Epoch [¹⁄₂], Iter [¹⁴⁶¹⁄₃₁₂₅], train_loss:0.178192 Epoch [¹⁄₂], Iter [¹⁴⁶²⁄₃₁₂₅], train_loss:0.163624 Epoch [¹⁄₂], Iter [¹⁴⁶³⁄₃₁₂₅], train_loss:0.160104 Epoch [¹⁄₂], Iter [¹⁴⁶⁴⁄₃₁₂₅], train_loss:0.175325 Epoch [¹⁄₂], Iter [¹⁴⁶⁵⁄₃₁₂₅], train_loss:0.173073 Epoch [¹⁄₂], Iter [¹⁴⁶⁶⁄₃₁₂₅], train_loss:0.167916 Epoch [¹⁄₂], Iter [¹⁴⁶⁷⁄₃₁₂₅], train_loss:0.161516 Epoch [¹⁄₂], Iter [¹⁴⁶⁸⁄₃₁₂₅], train_loss:0.168107 Epoch [¹⁄₂], Iter [¹⁴⁶⁹⁄₃₁₂₅], train_loss:0.169824 Epoch [¹⁄₂], Iter [¹⁴⁷⁰⁄₃₁₂₅], train_loss:0.160803 Epoch [¹⁄₂], Iter [¹⁴⁷¹⁄₃₁₂₅], train_loss:0.170264 Epoch [¹⁄₂], Iter [¹⁴⁷²⁄₃₁₂₅], train_loss:0.168911 Epoch [¹⁄₂], Iter [¹⁴⁷³⁄₃₁₂₅], train_loss:0.143244 Epoch [¹⁄₂], Iter [¹⁴⁷⁴⁄₃₁₂₅], train_loss:0.154688 Epoch [¹⁄₂], Iter [¹⁴⁷⁵⁄₃₁₂₅], train_loss:0.152704 Epoch [¹⁄₂], Iter [¹⁴⁷⁶⁄₃₁₂₅], train_loss:0.153546 Epoch [¹⁄₂], Iter [¹⁴⁷⁷⁄₃₁₂₅], train_loss:0.180169 Epoch [¹⁄₂], Iter [¹⁴⁷⁸⁄₃₁₂₅], train_loss:0.150831 Epoch [¹⁄₂], Iter [¹⁴⁷⁹⁄₃₁₂₅], train_loss:0.171316 Epoch [¹⁄₂], Iter [¹⁴⁸⁰⁄₃₁₂₅], train_loss:0.168213 Epoch [¹⁄₂], Iter [¹⁴⁸¹⁄₃₁₂₅], train_loss:0.172205 Epoch [¹⁄₂], Iter [¹⁴⁸²⁄₃₁₂₅], train_loss:0.142973 Epoch [¹⁄₂], Iter [¹⁴⁸³⁄₃₁₂₅], train_loss:0.157204 Epoch [¹⁄₂], Iter [¹⁴⁸⁴⁄₃₁₂₅], train_loss:0.172524 Epoch [¹⁄₂], Iter [¹⁴⁸⁵⁄₃₁₂₅], train_loss:0.157539 Epoch [¹⁄₂], Iter [¹⁴⁸⁶⁄₃₁₂₅], train_loss:0.143420 Epoch [¹⁄₂], Iter [¹⁴⁸⁷⁄₃₁₂₅], train_loss:0.162053 Epoch [¹⁄₂], Iter [¹⁴⁸⁸⁄₃₁₂₅], train_loss:0.167251 Epoch [¹⁄₂], Iter [¹⁴⁸⁹⁄₃₁₂₅], train_loss:0.172743 Epoch [¹⁄₂], Iter [¹⁴⁹⁰⁄₃₁₂₅], train_loss:0.166958 Epoch [¹⁄₂], Iter [¹⁴⁹¹⁄₃₁₂₅], train_loss:0.168802 Epoch [¹⁄₂], Iter [¹⁴⁹²⁄₃₁₂₅], train_loss:0.160231 Epoch [¹⁄₂], Iter [¹⁴⁹³⁄₃₁₂₅], train_loss:0.171343 Epoch [¹⁄₂], Iter [¹⁴⁹⁴⁄₃₁₂₅], train_loss:0.167754 Epoch [¹⁄₂], Iter [¹⁴⁹⁵⁄₃₁₂₅], train_loss:0.166312 Epoch [¹⁄₂], Iter [¹⁴⁹⁶⁄₃₁₂₅], train_loss:0.162917 Epoch [¹⁄₂], Iter [¹⁴⁹⁷⁄₃₁₂₅], train_loss:0.162183 Epoch [¹⁄₂], Iter [¹⁴⁹⁸⁄₃₁₂₅], train_loss:0.170274 Epoch [¹⁄₂], Iter [¹⁴⁹⁹⁄₃₁₂₅], train_loss:0.177937 Epoch [¹⁄₂], Iter [¹⁵⁰⁰⁄₃₁₂₅], train_loss:0.142511 Epoch [¹⁄₂], Iter [¹⁵⁰¹⁄₃₁₂₅], train_loss:0.146676 Epoch [¹⁄₂], Iter [¹⁵⁰²⁄₃₁₂₅], train_loss:0.165919 Epoch [¹⁄₂], Iter [¹⁵⁰³⁄₃₁₂₅], train_loss:0.153276 Epoch [¹⁄₂], Iter [¹⁵⁰⁴⁄₃₁₂₅], train_loss:0.169737 Epoch [¹⁄₂], Iter [¹⁵⁰⁵⁄₃₁₂₅], train_loss:0.155799 Epoch [¹⁄₂], Iter [¹⁵⁰⁶⁄₃₁₂₅], train_loss:0.160062 Epoch [¹⁄₂], Iter [¹⁵⁰⁷⁄₃₁₂₅], train_loss:0.156737 Epoch [¹⁄₂], Iter [¹⁵⁰⁸⁄₃₁₂₅], train_loss:0.171055 Epoch [¹⁄₂], Iter [¹⁵⁰⁹⁄₃₁₂₅], train_loss:0.155235 Epoch [¹⁄₂], Iter [¹⁵¹⁰⁄₃₁₂₅], train_loss:0.144856 Epoch [¹⁄₂], Iter [¹⁵¹¹⁄₃₁₂₅], train_loss:0.154941 Epoch [¹⁄₂], Iter [¹⁵¹²⁄₃₁₂₅], train_loss:0.141613 Epoch [¹⁄₂], Iter [¹⁵¹³⁄₃₁₂₅], train_loss:0.169685 Epoch [¹⁄₂], Iter [¹⁵¹⁴⁄₃₁₂₅], train_loss:0.153574 Epoch [¹⁄₂], Iter [¹⁵¹⁵⁄₃₁₂₅], train_loss:0.165675 Epoch [¹⁄₂], Iter [¹⁵¹⁶⁄₃₁₂₅], train_loss:0.194039 Epoch [¹⁄₂], Iter [¹⁵¹⁷⁄₃₁₂₅], train_loss:0.136731 Epoch [¹⁄₂], Iter [¹⁵¹⁸⁄₃₁₂₅], train_loss:0.162655 Epoch [¹⁄₂], Iter [¹⁵¹⁹⁄₃₁₂₅], train_loss:0.157449 Epoch [¹⁄₂], Iter [¹⁵²⁰⁄₃₁₂₅], train_loss:0.172672 Epoch [¹⁄₂], Iter [¹⁵²¹⁄₃₁₂₅], train_loss:0.185573 Epoch [¹⁄₂], Iter [¹⁵²²⁄₃₁₂₅], train_loss:0.177209 Epoch [¹⁄₂], Iter [¹⁵²³⁄₃₁₂₅], train_loss:0.144910 Epoch [¹⁄₂], Iter [¹⁵²⁴⁄₃₁₂₅], train_loss:0.160207 Epoch [¹⁄₂], Iter [¹⁵²⁵⁄₃₁₂₅], train_loss:0.163809 Epoch [¹⁄₂], Iter [¹⁵²⁶⁄₃₁₂₅], train_loss:0.161429 Epoch [¹⁄₂], Iter [¹⁵²⁷⁄₃₁₂₅], train_loss:0.149817 Epoch [¹⁄₂], Iter [¹⁵²⁸⁄₃₁₂₅], train_loss:0.182072 Epoch [¹⁄₂], Iter [¹⁵²⁹⁄₃₁₂₅], train_loss:0.175234 Epoch [¹⁄₂], Iter [¹⁵³⁰⁄₃₁₂₅], train_loss:0.170426 Epoch [¹⁄₂], Iter [¹⁵³¹⁄₃₁₂₅], train_loss:0.155083 Epoch [¹⁄₂], Iter [¹⁵³²⁄₃₁₂₅], train_loss:0.180693 Epoch [¹⁄₂], Iter [¹⁵³³⁄₃₁₂₅], train_loss:0.168464 Epoch [¹⁄₂], Iter [¹⁵³⁴⁄₃₁₂₅], train_loss:0.159503 Epoch [¹⁄₂], Iter [¹⁵³⁵⁄₃₁₂₅], train_loss:0.161271 Epoch [¹⁄₂], Iter [¹⁵³⁶⁄₃₁₂₅], train_loss:0.141511 Epoch [¹⁄₂], Iter [¹⁵³⁷⁄₃₁₂₅], train_loss:0.166983 Epoch [¹⁄₂], Iter [¹⁵³⁸⁄₃₁₂₅], train_loss:0.146959 Epoch [¹⁄₂], Iter [¹⁵³⁹⁄₃₁₂₅], train_loss:0.161491 Epoch [¹⁄₂], Iter [¹⁵⁴⁰⁄₃₁₂₅], train_loss:0.166418 Epoch [¹⁄₂], Iter [¹⁵⁴¹⁄₃₁₂₅], train_loss:0.158611 Epoch [¹⁄₂], Iter [¹⁵⁴²⁄₃₁₂₅], train_loss:0.152136 Epoch [¹⁄₂], Iter [¹⁵⁴³⁄₃₁₂₅], train_loss:0.172768 Epoch [¹⁄₂], Iter [¹⁵⁴⁴⁄₃₁₂₅], train_loss:0.152095 Epoch [¹⁄₂], Iter [¹⁵⁴⁵⁄₃₁₂₅], train_loss:0.142310 Epoch [¹⁄₂], Iter [¹⁵⁴⁶⁄₃₁₂₅], train_loss:0.150826 Epoch [¹⁄₂], Iter [¹⁵⁴⁷⁄₃₁₂₅], train_loss:0.147781 Epoch [¹⁄₂], Iter [¹⁵⁴⁸⁄₃₁₂₅], train_loss:0.171356 Epoch [¹⁄₂], Iter [¹⁵⁴⁹⁄₃₁₂₅], train_loss:0.149514 Epoch [¹⁄₂], Iter [¹⁵⁵⁰⁄₃₁₂₅], train_loss:0.156635 Epoch [¹⁄₂], Iter [¹⁵⁵¹⁄₃₁₂₅], train_loss:0.172591 Epoch [¹⁄₂], Iter [¹⁵⁵²⁄₃₁₂₅], train_loss:0.178937 Epoch [¹⁄₂], Iter [¹⁵⁵³⁄₃₁₂₅], train_loss:0.165982 Epoch [¹⁄₂], Iter [¹⁵⁵⁴⁄₃₁₂₅], train_loss:0.169758 Epoch [¹⁄₂], Iter [¹⁵⁵⁵⁄₃₁₂₅], train_loss:0.170617 Epoch [¹⁄₂], Iter [¹⁵⁵⁶⁄₃₁₂₅], train_loss:0.168998 Epoch [¹⁄₂], Iter [¹⁵⁵⁷⁄₃₁₂₅], train_loss:0.165370 Epoch [¹⁄₂], Iter [¹⁵⁵⁸⁄₃₁₂₅], train_loss:0.161071 Epoch [¹⁄₂], Iter [¹⁵⁵⁹⁄₃₁₂₅], train_loss:0.158345 Epoch [¹⁄₂], Iter [¹⁵⁶⁰⁄₃₁₂₅], train_loss:0.186070 Epoch [¹⁄₂], Iter [¹⁵⁶¹⁄₃₁₂₅], train_loss:0.160171 Epoch [¹⁄₂], Iter [¹⁵⁶²⁄₃₁₂₅], train_loss:0.179954 Epoch [¹⁄₂], Iter [¹⁵⁶³⁄₃₁₂₅], train_loss:0.172075 Epoch [¹⁄₂], Iter [¹⁵⁶⁴⁄₃₁₂₅], train_loss:0.151861 Epoch [¹⁄₂], Iter [¹⁵⁶⁵⁄₃₁₂₅], train_loss:0.173611 Epoch [¹⁄₂], Iter [¹⁵⁶⁶⁄₃₁₂₅], train_loss:0.167420 Epoch [¹⁄₂], Iter [¹⁵⁶⁷⁄₃₁₂₅], train_loss:0.149860 Epoch [¹⁄₂], Iter [¹⁵⁶⁸⁄₃₁₂₅], train_loss:0.154862 Epoch [¹⁄₂], Iter [¹⁵⁶⁹⁄₃₁₂₅], train_loss:0.168478 Epoch [¹⁄₂], Iter [¹⁵⁷⁰⁄₃₁₂₅], train_loss:0.159789 Epoch [¹⁄₂], Iter [¹⁵⁷¹⁄₃₁₂₅], train_loss:0.145618 Epoch [¹⁄₂], Iter [¹⁵⁷²⁄₃₁₂₅], train_loss:0.171799 Epoch [¹⁄₂], Iter [¹⁵⁷³⁄₃₁₂₅], train_loss:0.146416 Epoch [¹⁄₂], Iter [¹⁵⁷⁴⁄₃₁₂₅], train_loss:0.151151 Epoch [¹⁄₂], Iter [¹⁵⁷⁵⁄₃₁₂₅], train_loss:0.179502 Epoch [¹⁄₂], Iter [¹⁵⁷⁶⁄₃₁₂₅], train_loss:0.169216 Epoch [¹⁄₂], Iter [¹⁵⁷⁷⁄₃₁₂₅], train_loss:0.162661 Epoch [¹⁄₂], Iter [¹⁵⁷⁸⁄₃₁₂₅], train_loss:0.155157 Epoch [¹⁄₂], Iter [¹⁵⁷⁹⁄₃₁₂₅], train_loss:0.155743 Epoch [¹⁄₂], Iter [¹⁵⁸⁰⁄₃₁₂₅], train_loss:0.189926 Epoch [¹⁄₂], Iter [¹⁵⁸¹⁄₃₁₂₅], train_loss:0.164597 Epoch [¹⁄₂], Iter [¹⁵⁸²⁄₃₁₂₅], train_loss:0.137085 Epoch [¹⁄₂], Iter [¹⁵⁸³⁄₃₁₂₅], train_loss:0.160498 Epoch [¹⁄₂], Iter [¹⁵⁸⁴⁄₃₁₂₅], train_loss:0.179899 Epoch [¹⁄₂], Iter [¹⁵⁸⁵⁄₃₁₂₅], train_loss:0.145678 Epoch [¹⁄₂], Iter [¹⁵⁸⁶⁄₃₁₂₅], train_loss:0.157172 Epoch [¹⁄₂], Iter [¹⁵⁸⁷⁄₃₁₂₅], train_loss:0.168524 Epoch [¹⁄₂], Iter [¹⁵⁸⁸⁄₃₁₂₅], train_loss:0.156430 Epoch [¹⁄₂], Iter [¹⁵⁸⁹⁄₃₁₂₅], train_loss:0.133350 Epoch [¹⁄₂], Iter [¹⁵⁹⁰⁄₃₁₂₅], train_loss:0.176202 Epoch [¹⁄₂], Iter [¹⁵⁹¹⁄₃₁₂₅], train_loss:0.169190 Epoch [¹⁄₂], Iter [¹⁵⁹²⁄₃₁₂₅], train_loss:0.175895 Epoch [¹⁄₂], Iter [¹⁵⁹³⁄₃₁₂₅], train_loss:0.174856 Epoch [¹⁄₂], Iter [¹⁵⁹⁴⁄₃₁₂₅], train_loss:0.163053 Epoch [¹⁄₂], Iter [¹⁵⁹⁵⁄₃₁₂₅], train_loss:0.181598 Epoch [¹⁄₂], Iter [¹⁵⁹⁶⁄₃₁₂₅], train_loss:0.144885 Epoch [¹⁄₂], Iter [¹⁵⁹⁷⁄₃₁₂₅], train_loss:0.170181 Epoch [¹⁄₂], Iter [¹⁵⁹⁸⁄₃₁₂₅], train_loss:0.171142 Epoch [¹⁄₂], Iter [¹⁵⁹⁹⁄₃₁₂₅], train_loss:0.141454 Epoch [¹⁄₂], Iter [¹⁶⁰⁰⁄₃₁₂₅], train_loss:0.145220 Epoch [¹⁄₂], Iter [¹⁶⁰¹⁄₃₁₂₅], train_loss:0.141769 Epoch [¹⁄₂], Iter [¹⁶⁰²⁄₃₁₂₅], train_loss:0.154418 Epoch [¹⁄₂], Iter [¹⁶⁰³⁄₃₁₂₅], train_loss:0.160915 Epoch [¹⁄₂], Iter [¹⁶⁰⁴⁄₃₁₂₅], train_loss:0.168919 Epoch [¹⁄₂], Iter [¹⁶⁰⁵⁄₃₁₂₅], train_loss:0.180826 Epoch [¹⁄₂], Iter [¹⁶⁰⁶⁄₃₁₂₅], train_loss:0.152858 Epoch [¹⁄₂], Iter [¹⁶⁰⁷⁄₃₁₂₅], train_loss:0.164291 Epoch [¹⁄₂], Iter [¹⁶⁰⁸⁄₃₁₂₅], train_loss:0.163692 Epoch [¹⁄₂], Iter [¹⁶⁰⁹⁄₃₁₂₅], train_loss:0.147713 Epoch [¹⁄₂], Iter [¹⁶¹⁰⁄₃₁₂₅], train_loss:0.157055 Epoch [¹⁄₂], Iter [¹⁶¹¹⁄₃₁₂₅], train_loss:0.194847 Epoch [¹⁄₂], Iter [¹⁶¹²⁄₃₁₂₅], train_loss:0.158709 Epoch [¹⁄₂], Iter [¹⁶¹³⁄₃₁₂₅], train_loss:0.166231 Epoch [¹⁄₂], Iter [¹⁶¹⁴⁄₃₁₂₅], train_loss:0.186130 Epoch [¹⁄₂], Iter [¹⁶¹⁵⁄₃₁₂₅], train_loss:0.192118 Epoch [¹⁄₂], Iter [¹⁶¹⁶⁄₃₁₂₅], train_loss:0.167463 Epoch [¹⁄₂], Iter [¹⁶¹⁷⁄₃₁₂₅], train_loss:0.137858 Epoch [¹⁄₂], Iter [¹⁶¹⁸⁄₃₁₂₅], train_loss:0.146418 Epoch [¹⁄₂], Iter [¹⁶¹⁹⁄₃₁₂₅], train_loss:0.173478 Epoch [¹⁄₂], Iter [¹⁶²⁰⁄₃₁₂₅], train_loss:0.161725 Epoch [¹⁄₂], Iter [¹⁶²¹⁄₃₁₂₅], train_loss:0.152998 Epoch [¹⁄₂], Iter [¹⁶²²⁄₃₁₂₅], train_loss:0.185276 Epoch [¹⁄₂], Iter [¹⁶²³⁄₃₁₂₅], train_loss:0.152323 Epoch [¹⁄₂], Iter [¹⁶²⁴⁄₃₁₂₅], train_loss:0.145322 Epoch [¹⁄₂], Iter [¹⁶²⁵⁄₃₁₂₅], train_loss:0.161513 Epoch [¹⁄₂], Iter [¹⁶²⁶⁄₃₁₂₅], train_loss:0.153024 Epoch [¹⁄₂], Iter [¹⁶²⁷⁄₃₁₂₅], train_loss:0.164977 Epoch [¹⁄₂], Iter [¹⁶²⁸⁄₃₁₂₅], train_loss:0.165822 Epoch [¹⁄₂], Iter [¹⁶²⁹⁄₃₁₂₅], train_loss:0.151458 Epoch [¹⁄₂], Iter [¹⁶³⁰⁄₃₁₂₅], train_loss:0.168540 Epoch [¹⁄₂], Iter [¹⁶³¹⁄₃₁₂₅], train_loss:0.181315 Epoch [¹⁄₂], Iter [¹⁶³²⁄₃₁₂₅], train_loss:0.169901 Epoch [¹⁄₂], Iter [¹⁶³³⁄₃₁₂₅], train_loss:0.169646 Epoch [¹⁄₂], Iter [¹⁶³⁴⁄₃₁₂₅], train_loss:0.161900 Epoch [¹⁄₂], Iter [¹⁶³⁵⁄₃₁₂₅], train_loss:0.141304 Epoch [¹⁄₂], Iter [¹⁶³⁶⁄₃₁₂₅], train_loss:0.144623 Epoch [¹⁄₂], Iter [¹⁶³⁷⁄₃₁₂₅], train_loss:0.156594 Epoch [¹⁄₂], Iter [¹⁶³⁸⁄₃₁₂₅], train_loss:0.150709 Epoch [¹⁄₂], Iter [¹⁶³⁹⁄₃₁₂₅], train_loss:0.137099 Epoch [¹⁄₂], Iter [¹⁶⁴⁰⁄₃₁₂₅], train_loss:0.153333 Epoch [¹⁄₂], Iter [¹⁶⁴¹⁄₃₁₂₅], train_loss:0.157802 Epoch [¹⁄₂], Iter [¹⁶⁴²⁄₃₁₂₅], train_loss:0.143059 Epoch [¹⁄₂], Iter [¹⁶⁴³⁄₃₁₂₅], train_loss:0.189253 Epoch [¹⁄₂], Iter [¹⁶⁴⁴⁄₃₁₂₅], train_loss:0.155171 Epoch [¹⁄₂], Iter [¹⁶⁴⁵⁄₃₁₂₅], train_loss:0.152370 Epoch [¹⁄₂], Iter [¹⁶⁴⁶⁄₃₁₂₅], train_loss:0.166632 Epoch [¹⁄₂], Iter [¹⁶⁴⁷⁄₃₁₂₅], train_loss:0.179730 Epoch [¹⁄₂], Iter [¹⁶⁴⁸⁄₃₁₂₅], train_loss:0.172416 Epoch [¹⁄₂], Iter [¹⁶⁴⁹⁄₃₁₂₅], train_loss:0.178696 Epoch [¹⁄₂], Iter [¹⁶⁵⁰⁄₃₁₂₅], train_loss:0.160341 Epoch [¹⁄₂], Iter [¹⁶⁵¹⁄₃₁₂₅], train_loss:0.144308 Epoch [¹⁄₂], Iter [¹⁶⁵²⁄₃₁₂₅], train_loss:0.154410 Epoch [¹⁄₂], Iter [¹⁶⁵³⁄₃₁₂₅], train_loss:0.173912 Epoch [¹⁄₂], Iter [¹⁶⁵⁴⁄₃₁₂₅], train_loss:0.168114 Epoch [¹⁄₂], Iter [¹⁶⁵⁵⁄₃₁₂₅], train_loss:0.161952 Epoch [¹⁄₂], Iter [¹⁶⁵⁶⁄₃₁₂₅], train_loss:0.169061 Epoch [¹⁄₂], Iter [¹⁶⁵⁷⁄₃₁₂₅], train_loss:0.159440 Epoch [¹⁄₂], Iter [¹⁶⁵⁸⁄₃₁₂₅], train_loss:0.138091 Epoch [¹⁄₂], Iter [¹⁶⁵⁹⁄₃₁₂₅], train_loss:0.155012 Epoch [¹⁄₂], Iter [¹⁶⁶⁰⁄₃₁₂₅], train_loss:0.172804 Epoch [¹⁄₂], Iter [¹⁶⁶¹⁄₃₁₂₅], train_loss:0.143058 Epoch [¹⁄₂], Iter [¹⁶⁶²⁄₃₁₂₅], train_loss:0.162421 Epoch [¹⁄₂], Iter [¹⁶⁶³⁄₃₁₂₅], train_loss:0.143751 Epoch [¹⁄₂], Iter [¹⁶⁶⁴⁄₃₁₂₅], train_loss:0.140241 Epoch [¹⁄₂], Iter [¹⁶⁶⁵⁄₃₁₂₅], train_loss:0.172097 Epoch [¹⁄₂], Iter [¹⁶⁶⁶⁄₃₁₂₅], train_loss:0.163913 Epoch [¹⁄₂], Iter [¹⁶⁶⁷⁄₃₁₂₅], train_loss:0.165221 Epoch [¹⁄₂], Iter [¹⁶⁶⁸⁄₃₁₂₅], train_loss:0.174985 Epoch [¹⁄₂], Iter [¹⁶⁶⁹⁄₃₁₂₅], train_loss:0.157103 Epoch [¹⁄₂], Iter [¹⁶⁷⁰⁄₃₁₂₅], train_loss:0.171044 Epoch [¹⁄₂], Iter [¹⁶⁷¹⁄₃₁₂₅], train_loss:0.179402 Epoch [¹⁄₂], Iter [¹⁶⁷²⁄₃₁₂₅], train_loss:0.166310 Epoch [¹⁄₂], Iter [¹⁶⁷³⁄₃₁₂₅], train_loss:0.161387 Epoch [¹⁄₂], Iter [¹⁶⁷⁴⁄₃₁₂₅], train_loss:0.159246 Epoch [¹⁄₂], Iter [¹⁶⁷⁵⁄₃₁₂₅], train_loss:0.159077 Epoch [¹⁄₂], Iter [¹⁶⁷⁶⁄₃₁₂₅], train_loss:0.156243 Epoch [¹⁄₂], Iter [¹⁶⁷⁷⁄₃₁₂₅], train_loss:0.177382 Epoch [¹⁄₂], Iter [¹⁶⁷⁸⁄₃₁₂₅], train_loss:0.161576 Epoch [¹⁄₂], Iter [¹⁶⁷⁹⁄₃₁₂₅], train_loss:0.155681 Epoch [¹⁄₂], Iter [¹⁶⁸⁰⁄₃₁₂₅], train_loss:0.182101 Epoch [¹⁄₂], Iter [¹⁶⁸¹⁄₃₁₂₅], train_loss:0.168359 Epoch [¹⁄₂], Iter [¹⁶⁸²⁄₃₁₂₅], train_loss:0.162136 Epoch [¹⁄₂], Iter [¹⁶⁸³⁄₃₁₂₅], train_loss:0.175528 Epoch [¹⁄₂], Iter [¹⁶⁸⁴⁄₃₁₂₅], train_loss:0.139192 Epoch [¹⁄₂], Iter [¹⁶⁸⁵⁄₃₁₂₅], train_loss:0.149815 Epoch [¹⁄₂], Iter [¹⁶⁸⁶⁄₃₁₂₅], train_loss:0.182981 Epoch [¹⁄₂], Iter [¹⁶⁸⁷⁄₃₁₂₅], train_loss:0.160774 Epoch [¹⁄₂], Iter [¹⁶⁸⁸⁄₃₁₂₅], train_loss:0.145968 Epoch [¹⁄₂], Iter [¹⁶⁸⁹⁄₃₁₂₅], train_loss:0.158807 Epoch [¹⁄₂], Iter [¹⁶⁹⁰⁄₃₁₂₅], train_loss:0.158910 Epoch [¹⁄₂], Iter [¹⁶⁹¹⁄₃₁₂₅], train_loss:0.174940 Epoch [¹⁄₂], Iter [¹⁶⁹²⁄₃₁₂₅], train_loss:0.155379 Epoch [¹⁄₂], Iter [¹⁶⁹³⁄₃₁₂₅], train_loss:0.170327 Epoch [¹⁄₂], Iter [¹⁶⁹⁴⁄₃₁₂₅], train_loss:0.161909 Epoch [¹⁄₂], Iter [¹⁶⁹⁵⁄₃₁₂₅], train_loss:0.150474 Epoch [¹⁄₂], Iter [¹⁶⁹⁶⁄₃₁₂₅], train_loss:0.170937 Epoch [¹⁄₂], Iter [¹⁶⁹⁷⁄₃₁₂₅], train_loss:0.152703 Epoch [¹⁄₂], Iter [¹⁶⁹⁸⁄₃₁₂₅], train_loss:0.168881 Epoch [¹⁄₂], Iter [¹⁶⁹⁹⁄₃₁₂₅], train_loss:0.172118 Epoch [¹⁄₂], Iter [¹⁷⁰⁰⁄₃₁₂₅], train_loss:0.157837 Epoch [¹⁄₂], Iter [¹⁷⁰¹⁄₃₁₂₅], train_loss:0.160279 Epoch [¹⁄₂], Iter [¹⁷⁰²⁄₃₁₂₅], train_loss:0.181616 Epoch [¹⁄₂], Iter [¹⁷⁰³⁄₃₁₂₅], train_loss:0.147026 Epoch [¹⁄₂], Iter [¹⁷⁰⁴⁄₃₁₂₅], train_loss:0.157656 Epoch [¹⁄₂], Iter [¹⁷⁰⁵⁄₃₁₂₅], train_loss:0.179791 Epoch [¹⁄₂], Iter [¹⁷⁰⁶⁄₃₁₂₅], train_loss:0.171684 Epoch [¹⁄₂], Iter [¹⁷⁰⁷⁄₃₁₂₅], train_loss:0.138092 Epoch [¹⁄₂], Iter [¹⁷⁰⁸⁄₃₁₂₅], train_loss:0.177978 Epoch [¹⁄₂], Iter [¹⁷⁰⁹⁄₃₁₂₅], train_loss:0.175673 Epoch [¹⁄₂], Iter [¹⁷¹⁰⁄₃₁₂₅], train_loss:0.151395 Epoch [¹⁄₂], Iter [¹⁷¹¹⁄₃₁₂₅], train_loss:0.159401 Epoch [¹⁄₂], Iter [¹⁷¹²⁄₃₁₂₅], train_loss:0.168381 Epoch [¹⁄₂], Iter [¹⁷¹³⁄₃₁₂₅], train_loss:0.166301 Epoch [¹⁄₂], Iter [¹⁷¹⁴⁄₃₁₂₅], train_loss:0.156766 Epoch [¹⁄₂], Iter [¹⁷¹⁵⁄₃₁₂₅], train_loss:0.168902 Epoch [¹⁄₂], Iter [¹⁷¹⁶⁄₃₁₂₅], train_loss:0.169495 Epoch [¹⁄₂], Iter [¹⁷¹⁷⁄₃₁₂₅], train_loss:0.159896 Epoch [¹⁄₂], Iter [¹⁷¹⁸⁄₃₁₂₅], train_loss:0.165244 Epoch [¹⁄₂], Iter [¹⁷¹⁹⁄₃₁₂₅], train_loss:0.145941 Epoch [¹⁄₂], Iter [¹⁷²⁰⁄₃₁₂₅], train_loss:0.166384 Epoch [¹⁄₂], Iter [¹⁷²¹⁄₃₁₂₅], train_loss:0.174706 Epoch [¹⁄₂], Iter [¹⁷²²⁄₃₁₂₅], train_loss:0.141559 Epoch [¹⁄₂], Iter [¹⁷²³⁄₃₁₂₅], train_loss:0.174502 Epoch [¹⁄₂], Iter [¹⁷²⁴⁄₃₁₂₅], train_loss:0.149242 Epoch [¹⁄₂], Iter [¹⁷²⁵⁄₃₁₂₅], train_loss:0.143743 Epoch [¹⁄₂], Iter [¹⁷²⁶⁄₃₁₂₅], train_loss:0.159536 Epoch [¹⁄₂], Iter [¹⁷²⁷⁄₃₁₂₅], train_loss:0.173931 Epoch [¹⁄₂], Iter [¹⁷²⁸⁄₃₁₂₅], train_loss:0.152694 Epoch [¹⁄₂], Iter [¹⁷²⁹⁄₃₁₂₅], train_loss:0.167123 Epoch [¹⁄₂], Iter [¹⁷³⁰⁄₃₁₂₅], train_loss:0.174618 Epoch [¹⁄₂], Iter [¹⁷³¹⁄₃₁₂₅], train_loss:0.187746 Epoch [¹⁄₂], Iter [¹⁷³²⁄₃₁₂₅], train_loss:0.188053 Epoch [¹⁄₂], Iter [¹⁷³³⁄₃₁₂₅], train_loss:0.161420 Epoch [¹⁄₂], Iter [¹⁷³⁴⁄₃₁₂₅], train_loss:0.143247 Epoch [¹⁄₂], Iter [¹⁷³⁵⁄₃₁₂₅], train_loss:0.164306 Epoch [¹⁄₂], Iter [¹⁷³⁶⁄₃₁₂₅], train_loss:0.149670 Epoch [¹⁄₂], Iter [¹⁷³⁷⁄₃₁₂₅], train_loss:0.180123 Epoch [¹⁄₂], Iter [¹⁷³⁸⁄₃₁₂₅], train_loss:0.158347 Epoch [¹⁄₂], Iter [¹⁷³⁹⁄₃₁₂₅], train_loss:0.175313 Epoch [¹⁄₂], Iter [¹⁷⁴⁰⁄₃₁₂₅], train_loss:0.154087 Epoch [¹⁄₂], Iter [¹⁷⁴¹⁄₃₁₂₅], train_loss:0.180090 Epoch [¹⁄₂], Iter [¹⁷⁴²⁄₃₁₂₅], train_loss:0.162183 Epoch [¹⁄₂], Iter [¹⁷⁴³⁄₃₁₂₅], train_loss:0.164401 Epoch [¹⁄₂], Iter [¹⁷⁴⁴⁄₃₁₂₅], train_loss:0.164047 Epoch [¹⁄₂], Iter [¹⁷⁴⁵⁄₃₁₂₅], train_loss:0.164262 Epoch [¹⁄₂], Iter [¹⁷⁴⁶⁄₃₁₂₅], train_loss:0.155122 Epoch [¹⁄₂], Iter [¹⁷⁴⁷⁄₃₁₂₅], train_loss:0.164472 Epoch [¹⁄₂], Iter [¹⁷⁴⁸⁄₃₁₂₅], train_loss:0.161191 Epoch [¹⁄₂], Iter [¹⁷⁴⁹⁄₃₁₂₅], train_loss:0.160144 Epoch [¹⁄₂], Iter [¹⁷⁵⁰⁄₃₁₂₅], train_loss:0.161302 Epoch [¹⁄₂], Iter [¹⁷⁵¹⁄₃₁₂₅], train_loss:0.160503 Epoch [¹⁄₂], Iter [¹⁷⁵²⁄₃₁₂₅], train_loss:0.155728 Epoch [¹⁄₂], Iter [¹⁷⁵³⁄₃₁₂₅], train_loss:0.140759 Epoch [¹⁄₂], Iter [¹⁷⁵⁴⁄₃₁₂₅], train_loss:0.145626 Epoch [¹⁄₂], Iter [¹⁷⁵⁵⁄₃₁₂₅], train_loss:0.164837 Epoch [¹⁄₂], Iter [¹⁷⁵⁶⁄₃₁₂₅], train_loss:0.157151 Epoch [¹⁄₂], Iter [¹⁷⁵⁷⁄₃₁₂₅], train_loss:0.179853 Epoch [¹⁄₂], Iter [¹⁷⁵⁸⁄₃₁₂₅], train_loss:0.150290 Epoch [¹⁄₂], Iter [¹⁷⁵⁹⁄₃₁₂₅], train_loss:0.144776 Epoch [¹⁄₂], Iter [¹⁷⁶⁰⁄₃₁₂₅], train_loss:0.163736 Epoch [¹⁄₂], Iter [¹⁷⁶¹⁄₃₁₂₅], train_loss:0.161901 Epoch [¹⁄₂], Iter [¹⁷⁶²⁄₃₁₂₅], train_loss:0.137393 Epoch [¹⁄₂], Iter [¹⁷⁶³⁄₃₁₂₅], train_loss:0.157102 Epoch [¹⁄₂], Iter [¹⁷⁶⁴⁄₃₁₂₅], train_loss:0.147714 Epoch [¹⁄₂], Iter [¹⁷⁶⁵⁄₃₁₂₅], train_loss:0.168851 Epoch [¹⁄₂], Iter [¹⁷⁶⁶⁄₃₁₂₅], train_loss:0.180556 Epoch [¹⁄₂], Iter [¹⁷⁶⁷⁄₃₁₂₅], train_loss:0.145371 Epoch [¹⁄₂], Iter [¹⁷⁶⁸⁄₃₁₂₅], train_loss:0.182627 Epoch [¹⁄₂], Iter [¹⁷⁶⁹⁄₃₁₂₅], train_loss:0.155184 Epoch [¹⁄₂], Iter [¹⁷⁷⁰⁄₃₁₂₅], train_loss:0.170251 Epoch [¹⁄₂], Iter [¹⁷⁷¹⁄₃₁₂₅], train_loss:0.156243 Epoch [¹⁄₂], Iter [¹⁷⁷²⁄₃₁₂₅], train_loss:0.157432 Epoch [¹⁄₂], Iter [¹⁷⁷³⁄₃₁₂₅], train_loss:0.165467 Epoch [¹⁄₂], Iter [¹⁷⁷⁴⁄₃₁₂₅], train_loss:0.166601 Epoch [¹⁄₂], Iter [¹⁷⁷⁵⁄₃₁₂₅], train_loss:0.177986 Epoch [¹⁄₂], Iter [¹⁷⁷⁶⁄₃₁₂₅], train_loss:0.165314 Epoch [¹⁄₂], Iter [¹⁷⁷⁷⁄₃₁₂₅], train_loss:0.171132 Epoch [¹⁄₂], Iter [¹⁷⁷⁸⁄₃₁₂₅], train_loss:0.190048 Epoch [¹⁄₂], Iter [¹⁷⁷⁹⁄₃₁₂₅], train_loss:0.165800 Epoch [¹⁄₂], Iter [¹⁷⁸⁰⁄₃₁₂₅], train_loss:0.160303 Epoch [¹⁄₂], Iter [¹⁷⁸¹⁄₃₁₂₅], train_loss:0.155642 Epoch [¹⁄₂], Iter [¹⁷⁸²⁄₃₁₂₅], train_loss:0.146157 Epoch [¹⁄₂], Iter [¹⁷⁸³⁄₃₁₂₅], train_loss:0.160654 Epoch [¹⁄₂], Iter [¹⁷⁸⁴⁄₃₁₂₅], train_loss:0.176773 Epoch [¹⁄₂], Iter [¹⁷⁸⁵⁄₃₁₂₅], train_loss:0.169321 Epoch [¹⁄₂], Iter [¹⁷⁸⁶⁄₃₁₂₅], train_loss:0.150362 Epoch [¹⁄₂], Iter [¹⁷⁸⁷⁄₃₁₂₅], train_loss:0.167345 Epoch [¹⁄₂], Iter [¹⁷⁸⁸⁄₃₁₂₅], train_loss:0.145898 Epoch [¹⁄₂], Iter [¹⁷⁸⁹⁄₃₁₂₅], train_loss:0.150497 Epoch [¹⁄₂], Iter [¹⁷⁹⁰⁄₃₁₂₅], train_loss:0.166425 Epoch [¹⁄₂], Iter [¹⁷⁹¹⁄₃₁₂₅], train_loss:0.171549 Epoch [¹⁄₂], Iter [¹⁷⁹²⁄₃₁₂₅], train_loss:0.154176 Epoch [¹⁄₂], Iter [¹⁷⁹³⁄₃₁₂₅], train_loss:0.166127 Epoch [¹⁄₂], Iter [¹⁷⁹⁴⁄₃₁₂₅], train_loss:0.165764 Epoch [¹⁄₂], Iter [¹⁷⁹⁵⁄₃₁₂₅], train_loss:0.162320 Epoch [¹⁄₂], Iter [¹⁷⁹⁶⁄₃₁₂₅], train_loss:0.194941 Epoch [¹⁄₂], Iter [¹⁷⁹⁷⁄₃₁₂₅], train_loss:0.157635 Epoch [¹⁄₂], Iter [¹⁷⁹⁸⁄₃₁₂₅], train_loss:0.163641 Epoch [¹⁄₂], Iter [¹⁷⁹⁹⁄₃₁₂₅], train_loss:0.167187 Epoch [¹⁄₂], Iter [¹⁸⁰⁰⁄₃₁₂₅], train_loss:0.145284 Epoch [¹⁄₂], Iter [¹⁸⁰¹⁄₃₁₂₅], train_loss:0.161971 Epoch [¹⁄₂], Iter [¹⁸⁰²⁄₃₁₂₅], train_loss:0.164058 Epoch [¹⁄₂], Iter [¹⁸⁰³⁄₃₁₂₅], train_loss:0.142048 Epoch [¹⁄₂], Iter [¹⁸⁰⁴⁄₃₁₂₅], train_loss:0.160427 Epoch [¹⁄₂], Iter [¹⁸⁰⁵⁄₃₁₂₅], train_loss:0.161583 Epoch [¹⁄₂], Iter [¹⁸⁰⁶⁄₃₁₂₅], train_loss:0.155377 Epoch [¹⁄₂], Iter [¹⁸⁰⁷⁄₃₁₂₅], train_loss:0.191237 Epoch [¹⁄₂], Iter [¹⁸⁰⁸⁄₃₁₂₅], train_loss:0.163925 Epoch [¹⁄₂], Iter [¹⁸⁰⁹⁄₃₁₂₅], train_loss:0.190522 Epoch [¹⁄₂], Iter [¹⁸¹⁰⁄₃₁₂₅], train_loss:0.160186 Epoch [¹⁄₂], Iter [¹⁸¹¹⁄₃₁₂₅], train_loss:0.176043 Epoch [¹⁄₂], Iter [¹⁸¹²⁄₃₁₂₅], train_loss:0.170882 Epoch [¹⁄₂], Iter [¹⁸¹³⁄₃₁₂₅], train_loss:0.168062 Epoch [¹⁄₂], Iter [¹⁸¹⁴⁄₃₁₂₅], train_loss:0.162766 Epoch [¹⁄₂], Iter [¹⁸¹⁵⁄₃₁₂₅], train_loss:0.168871 Epoch [¹⁄₂], Iter [¹⁸¹⁶⁄₃₁₂₅], train_loss:0.161266 Epoch [¹⁄₂], Iter [¹⁸¹⁷⁄₃₁₂₅], train_loss:0.155407 Epoch [¹⁄₂], Iter [¹⁸¹⁸⁄₃₁₂₅], train_loss:0.145036 Epoch [¹⁄₂], Iter [¹⁸¹⁹⁄₃₁₂₅], train_loss:0.166525 Epoch [¹⁄₂], Iter [¹⁸²⁰⁄₃₁₂₅], train_loss:0.161894 Epoch [¹⁄₂], Iter [¹⁸²¹⁄₃₁₂₅], train_loss:0.179618 Epoch [¹⁄₂], Iter [¹⁸²²⁄₃₁₂₅], train_loss:0.165360 Epoch [¹⁄₂], Iter [¹⁸²³⁄₃₁₂₅], train_loss:0.179443 Epoch [¹⁄₂], Iter [¹⁸²⁴⁄₃₁₂₅], train_loss:0.182535 Epoch [¹⁄₂], Iter [¹⁸²⁵⁄₃₁₂₅], train_loss:0.183849 Epoch [¹⁄₂], Iter [¹⁸²⁶⁄₃₁₂₅], train_loss:0.160797 Epoch [¹⁄₂], Iter [¹⁸²⁷⁄₃₁₂₅], train_loss:0.155679 Epoch [¹⁄₂], Iter [¹⁸²⁸⁄₃₁₂₅], train_loss:0.163237 Epoch [¹⁄₂], Iter [¹⁸²⁹⁄₃₁₂₅], train_loss:0.155929 Epoch [¹⁄₂], Iter [¹⁸³⁰⁄₃₁₂₅], train_loss:0.169370 Epoch [¹⁄₂], Iter [¹⁸³¹⁄₃₁₂₅], train_loss:0.181343 Epoch [¹⁄₂], Iter [¹⁸³²⁄₃₁₂₅], train_loss:0.150245 Epoch [¹⁄₂], Iter [¹⁸³³⁄₃₁₂₅], train_loss:0.173141 Epoch [¹⁄₂], Iter [¹⁸³⁴⁄₃₁₂₅], train_loss:0.163475 Epoch [¹⁄₂], Iter [¹⁸³⁵⁄₃₁₂₅], train_loss:0.163326 Epoch [¹⁄₂], Iter [¹⁸³⁶⁄₃₁₂₅], train_loss:0.157031 Epoch [¹⁄₂], Iter [¹⁸³⁷⁄₃₁₂₅], train_loss:0.166926 Epoch [¹⁄₂], Iter [¹⁸³⁸⁄₃₁₂₅], train_loss:0.181456 Epoch [¹⁄₂], Iter [¹⁸³⁹⁄₃₁₂₅], train_loss:0.166013 Epoch [¹⁄₂], Iter [¹⁸⁴⁰⁄₃₁₂₅], train_loss:0.151755 Epoch [¹⁄₂], Iter [¹⁸⁴¹⁄₃₁₂₅], train_loss:0.172941 Epoch [¹⁄₂], Iter [¹⁸⁴²⁄₃₁₂₅], train_loss:0.175330 Epoch [¹⁄₂], Iter [¹⁸⁴³⁄₃₁₂₅], train_loss:0.147175 Epoch [¹⁄₂], Iter [¹⁸⁴⁴⁄₃₁₂₅], train_loss:0.178653 Epoch [¹⁄₂], Iter [¹⁸⁴⁵⁄₃₁₂₅], train_loss:0.152745 Epoch [¹⁄₂], Iter [¹⁸⁴⁶⁄₃₁₂₅], train_loss:0.142007 Epoch [¹⁄₂], Iter [¹⁸⁴⁷⁄₃₁₂₅], train_loss:0.148765 Epoch [¹⁄₂], Iter [¹⁸⁴⁸⁄₃₁₂₅], train_loss:0.166682 Epoch [¹⁄₂], Iter [¹⁸⁴⁹⁄₃₁₂₅], train_loss:0.156195 Epoch [¹⁄₂], Iter [¹⁸⁵⁰⁄₃₁₂₅], train_loss:0.156262 Epoch [¹⁄₂], Iter [¹⁸⁵¹⁄₃₁₂₅], train_loss:0.160495 Epoch [¹⁄₂], Iter [¹⁸⁵²⁄₃₁₂₅], train_loss:0.162996 Epoch [¹⁄₂], Iter [¹⁸⁵³⁄₃₁₂₅], train_loss:0.162435 Epoch [¹⁄₂], Iter [¹⁸⁵⁴⁄₃₁₂₅], train_loss:0.161346 Epoch [¹⁄₂], Iter [¹⁸⁵⁵⁄₃₁₂₅], train_loss:0.171397 Epoch [¹⁄₂], Iter [¹⁸⁵⁶⁄₃₁₂₅], train_loss:0.177385 Epoch [¹⁄₂], Iter [¹⁸⁵⁷⁄₃₁₂₅], train_loss:0.130351 Epoch [¹⁄₂], Iter [¹⁸⁵⁸⁄₃₁₂₅], train_loss:0.151499 Epoch [¹⁄₂], Iter [¹⁸⁵⁹⁄₃₁₂₅], train_loss:0.149441 Epoch [¹⁄₂], Iter [¹⁸⁶⁰⁄₃₁₂₅], train_loss:0.164405 Epoch [¹⁄₂], Iter [¹⁸⁶¹⁄₃₁₂₅], train_loss:0.163205 Epoch [¹⁄₂], Iter [¹⁸⁶²⁄₃₁₂₅], train_loss:0.177325 Epoch [¹⁄₂], Iter [¹⁸⁶³⁄₃₁₂₅], train_loss:0.155396 Epoch [¹⁄₂], Iter [¹⁸⁶⁴⁄₃₁₂₅], train_loss:0.162093 Epoch [¹⁄₂], Iter [¹⁸⁶⁵⁄₃₁₂₅], train_loss:0.155531 Epoch [¹⁄₂], Iter [¹⁸⁶⁶⁄₃₁₂₅], train_loss:0.147332 Epoch [¹⁄₂], Iter [¹⁸⁶⁷⁄₃₁₂₅], train_loss:0.150838 Epoch [¹⁄₂], Iter [¹⁸⁶⁸⁄₃₁₂₅], train_loss:0.154241 Epoch [¹⁄₂], Iter [¹⁸⁶⁹⁄₃₁₂₅], train_loss:0.142730 Epoch [¹⁄₂], Iter [¹⁸⁷⁰⁄₃₁₂₅], train_loss:0.154984 Epoch [¹⁄₂], Iter [¹⁸⁷¹⁄₃₁₂₅], train_loss:0.141732 Epoch [¹⁄₂], Iter [¹⁸⁷²⁄₃₁₂₅], train_loss:0.169305 Epoch [¹⁄₂], Iter [¹⁸⁷³⁄₃₁₂₅], train_loss:0.158314 Epoch [¹⁄₂], Iter [¹⁸⁷⁴⁄₃₁₂₅], train_loss:0.155676 Epoch [¹⁄₂], Iter [¹⁸⁷⁵⁄₃₁₂₅], train_loss:0.162900 Epoch [¹⁄₂], Iter [¹⁸⁷⁶⁄₃₁₂₅], train_loss:0.174867 Epoch [¹⁄₂], Iter [¹⁸⁷⁷⁄₃₁₂₅], train_loss:0.165536 Epoch [¹⁄₂], Iter [¹⁸⁷⁸⁄₃₁₂₅], train_loss:0.153315 Epoch [¹⁄₂], Iter [¹⁸⁷⁹⁄₃₁₂₅], train_loss:0.150544 Epoch [¹⁄₂], Iter [¹⁸⁸⁰⁄₃₁₂₅], train_loss:0.183719 Epoch [¹⁄₂], Iter [¹⁸⁸¹⁄₃₁₂₅], train_loss:0.160276 Epoch [¹⁄₂], Iter [¹⁸⁸²⁄₃₁₂₅], train_loss:0.169111 Epoch [¹⁄₂], Iter [¹⁸⁸³⁄₃₁₂₅], train_loss:0.162062 Epoch [¹⁄₂], Iter [¹⁸⁸⁴⁄₃₁₂₅], train_loss:0.136829 Epoch [¹⁄₂], Iter [¹⁸⁸⁵⁄₃₁₂₅], train_loss:0.152484 Epoch [¹⁄₂], Iter [¹⁸⁸⁶⁄₃₁₂₅], train_loss:0.157395 Epoch [¹⁄₂], Iter [¹⁸⁸⁷⁄₃₁₂₅], train_loss:0.153584 Epoch [¹⁄₂], Iter [¹⁸⁸⁸⁄₃₁₂₅], train_loss:0.184233 Epoch [¹⁄₂], Iter [¹⁸⁸⁹⁄₃₁₂₅], train_loss:0.158605 Epoch [¹⁄₂], Iter [¹⁸⁹⁰⁄₃₁₂₅], train_loss:0.160698 Epoch [¹⁄₂], Iter [¹⁸⁹¹⁄₃₁₂₅], train_loss:0.160876 Epoch [¹⁄₂], Iter [¹⁸⁹²⁄₃₁₂₅], train_loss:0.169683 Epoch [¹⁄₂], Iter [¹⁸⁹³⁄₃₁₂₅], train_loss:0.157519 Epoch [¹⁄₂], Iter [¹⁸⁹⁴⁄₃₁₂₅], train_loss:0.159938 Epoch [¹⁄₂], Iter [¹⁸⁹⁵⁄₃₁₂₅], train_loss:0.170259 Epoch [¹⁄₂], Iter [¹⁸⁹⁶⁄₃₁₂₅], train_loss:0.184046 Epoch [¹⁄₂], Iter [¹⁸⁹⁷⁄₃₁₂₅], train_loss:0.153115 Epoch [¹⁄₂], Iter [¹⁸⁹⁸⁄₃₁₂₅], train_loss:0.157097 Epoch [¹⁄₂], Iter [¹⁸⁹⁹⁄₃₁₂₅], train_loss:0.162475 Epoch [¹⁄₂], Iter [¹⁹⁰⁰⁄₃₁₂₅], train_loss:0.161365 Epoch [¹⁄₂], Iter [¹⁹⁰¹⁄₃₁₂₅], train_loss:0.173105 Epoch [¹⁄₂], Iter [¹⁹⁰²⁄₃₁₂₅], train_loss:0.148295 Epoch [¹⁄₂], Iter [¹⁹⁰³⁄₃₁₂₅], train_loss:0.165971 Epoch [¹⁄₂], Iter [¹⁹⁰⁴⁄₃₁₂₅], train_loss:0.158941 Epoch [¹⁄₂], Iter [¹⁹⁰⁵⁄₃₁₂₅], train_loss:0.167976 Epoch [¹⁄₂], Iter [¹⁹⁰⁶⁄₃₁₂₅], train_loss:0.161314 Epoch [¹⁄₂], Iter [¹⁹⁰⁷⁄₃₁₂₅], train_loss:0.142002 Epoch [¹⁄₂], Iter [¹⁹⁰⁸⁄₃₁₂₅], train_loss:0.155992 Epoch [¹⁄₂], Iter [¹⁹⁰⁹⁄₃₁₂₅], train_loss:0.159452 Epoch [¹⁄₂], Iter [¹⁹¹⁰⁄₃₁₂₅], train_loss:0.167375 Epoch [¹⁄₂], Iter [¹⁹¹¹⁄₃₁₂₅], train_loss:0.160087 Epoch [¹⁄₂], Iter [¹⁹¹²⁄₃₁₂₅], train_loss:0.162730 Epoch [¹⁄₂], Iter [¹⁹¹³⁄₃₁₂₅], train_loss:0.166080 Epoch [¹⁄₂], Iter [¹⁹¹⁴⁄₃₁₂₅], train_loss:0.186217 Epoch [¹⁄₂], Iter [¹⁹¹⁵⁄₃₁₂₅], train_loss:0.151830 Epoch [¹⁄₂], Iter [¹⁹¹⁶⁄₃₁₂₅], train_loss:0.168950 Epoch [¹⁄₂], Iter [¹⁹¹⁷⁄₃₁₂₅], train_loss:0.153571 Epoch [¹⁄₂], Iter [¹⁹¹⁸⁄₃₁₂₅], train_loss:0.164015 Epoch [¹⁄₂], Iter [¹⁹¹⁹⁄₃₁₂₅], train_loss:0.159809 Epoch [¹⁄₂], Iter [¹⁹²⁰⁄₃₁₂₅], train_loss:0.146458 Epoch [¹⁄₂], Iter [¹⁹²¹⁄₃₁₂₅], train_loss:0.160593 Epoch [¹⁄₂], Iter [¹⁹²²⁄₃₁₂₅], train_loss:0.152458 Epoch [¹⁄₂], Iter [¹⁹²³⁄₃₁₂₅], train_loss:0.170881 Epoch [¹⁄₂], Iter [¹⁹²⁴⁄₃₁₂₅], train_loss:0.158566 Epoch [¹⁄₂], Iter [¹⁹²⁵⁄₃₁₂₅], train_loss:0.155870 Epoch [¹⁄₂], Iter [¹⁹²⁶⁄₃₁₂₅], train_loss:0.188001 Epoch [¹⁄₂], Iter [¹⁹²⁷⁄₃₁₂₅], train_loss:0.169803 Epoch [¹⁄₂], Iter [¹⁹²⁸⁄₃₁₂₅], train_loss:0.150111 Epoch [¹⁄₂], Iter [¹⁹²⁹⁄₃₁₂₅], train_loss:0.163295 Epoch [¹⁄₂], Iter [¹⁹³⁰⁄₃₁₂₅], train_loss:0.145743 Epoch [¹⁄₂], Iter [¹⁹³¹⁄₃₁₂₅], train_loss:0.154151 Epoch [¹⁄₂], Iter [¹⁹³²⁄₃₁₂₅], train_loss:0.160207 Epoch [¹⁄₂], Iter [¹⁹³³⁄₃₁₂₅], train_loss:0.158596 Epoch [¹⁄₂], Iter [¹⁹³⁴⁄₃₁₂₅], train_loss:0.173918 Epoch [¹⁄₂], Iter [¹⁹³⁵⁄₃₁₂₅], train_loss:0.184682 Epoch [¹⁄₂], Iter [¹⁹³⁶⁄₃₁₂₅], train_loss:0.184060 Epoch [¹⁄₂], Iter [¹⁹³⁷⁄₃₁₂₅], train_loss:0.165681 Epoch [¹⁄₂], Iter [¹⁹³⁸⁄₃₁₂₅], train_loss:0.172499 Epoch [¹⁄₂], Iter [¹⁹³⁹⁄₃₁₂₅], train_loss:0.154547 Epoch [¹⁄₂], Iter [¹⁹⁴⁰⁄₃₁₂₅], train_loss:0.147814 Epoch [¹⁄₂], Iter [¹⁹⁴¹⁄₃₁₂₅], train_loss:0.161590 Epoch [¹⁄₂], Iter [¹⁹⁴²⁄₃₁₂₅], train_loss:0.141166 Epoch [¹⁄₂], Iter [¹⁹⁴³⁄₃₁₂₅], train_loss:0.151419 Epoch [¹⁄₂], Iter [¹⁹⁴⁴⁄₃₁₂₅], train_loss:0.152621 Epoch [¹⁄₂], Iter [¹⁹⁴⁵⁄₃₁₂₅], train_loss:0.164691 Epoch [¹⁄₂], Iter [¹⁹⁴⁶⁄₃₁₂₅], train_loss:0.146373 Epoch [¹⁄₂], Iter [¹⁹⁴⁷⁄₃₁₂₅], train_loss:0.148736 Epoch [¹⁄₂], Iter [¹⁹⁴⁸⁄₃₁₂₅], train_loss:0.199945 Epoch [¹⁄₂], Iter [¹⁹⁴⁹⁄₃₁₂₅], train_loss:0.154226 Epoch [¹⁄₂], Iter [¹⁹⁵⁰⁄₃₁₂₅], train_loss:0.173260 Epoch [¹⁄₂], Iter [¹⁹⁵¹⁄₃₁₂₅], train_loss:0.161090 Epoch [¹⁄₂], Iter [¹⁹⁵²⁄₃₁₂₅], train_loss:0.169187 Epoch [¹⁄₂], Iter [¹⁹⁵³⁄₃₁₂₅], train_loss:0.164385 Epoch [¹⁄₂], Iter [¹⁹⁵⁴⁄₃₁₂₅], train_loss:0.151662 Epoch [¹⁄₂], Iter [¹⁹⁵⁵⁄₃₁₂₅], train_loss:0.165125 Epoch [¹⁄₂], Iter [¹⁹⁵⁶⁄₃₁₂₅], train_loss:0.154994 Epoch [¹⁄₂], Iter [¹⁹⁵⁷⁄₃₁₂₅], train_loss:0.173068 Epoch [¹⁄₂], Iter [¹⁹⁵⁸⁄₃₁₂₅], train_loss:0.175447 Epoch [¹⁄₂], Iter [¹⁹⁵⁹⁄₃₁₂₅], train_loss:0.170935 Epoch [¹⁄₂], Iter [¹⁹⁶⁰⁄₃₁₂₅], train_loss:0.167173 Epoch [¹⁄₂], Iter [¹⁹⁶¹⁄₃₁₂₅], train_loss:0.181798 Epoch [¹⁄₂], Iter [¹⁹⁶²⁄₃₁₂₅], train_loss:0.149530 Epoch [¹⁄₂], Iter [¹⁹⁶³⁄₃₁₂₅], train_loss:0.162909 Epoch [¹⁄₂], Iter [¹⁹⁶⁴⁄₃₁₂₅], train_loss:0.159980 Epoch [¹⁄₂], Iter [¹⁹⁶⁵⁄₃₁₂₅], train_loss:0.152192 Epoch [¹⁄₂], Iter [¹⁹⁶⁶⁄₃₁₂₅], train_loss:0.178360 Epoch [¹⁄₂], Iter [¹⁹⁶⁷⁄₃₁₂₅], train_loss:0.146795 Epoch [¹⁄₂], Iter [¹⁹⁶⁸⁄₃₁₂₅], train_loss:0.143748 Epoch [¹⁄₂], Iter [¹⁹⁶⁹⁄₃₁₂₅], train_loss:0.181524 Epoch [¹⁄₂], Iter [¹⁹⁷⁰⁄₃₁₂₅], train_loss:0.156961 Epoch [¹⁄₂], Iter [¹⁹⁷¹⁄₃₁₂₅], train_loss:0.157196 Epoch [¹⁄₂], Iter [¹⁹⁷²⁄₃₁₂₅], train_loss:0.156264 Epoch [¹⁄₂], Iter [¹⁹⁷³⁄₃₁₂₅], train_loss:0.155585 Epoch [¹⁄₂], Iter [¹⁹⁷⁴⁄₃₁₂₅], train_loss:0.165857 Epoch [¹⁄₂], Iter [¹⁹⁷⁵⁄₃₁₂₅], train_loss:0.179051 Epoch [¹⁄₂], Iter [¹⁹⁷⁶⁄₃₁₂₅], train_loss:0.154581 Epoch [¹⁄₂], Iter [¹⁹⁷⁷⁄₃₁₂₅], train_loss:0.169368 Epoch [¹⁄₂], Iter [¹⁹⁷⁸⁄₃₁₂₅], train_loss:0.144383 Epoch [¹⁄₂], Iter [¹⁹⁷⁹⁄₃₁₂₅], train_loss:0.152714 Epoch [¹⁄₂], Iter [¹⁹⁸⁰⁄₃₁₂₅], train_loss:0.148939 Epoch [¹⁄₂], Iter [¹⁹⁸¹⁄₃₁₂₅], train_loss:0.175638 Epoch [¹⁄₂], Iter [¹⁹⁸²⁄₃₁₂₅], train_loss:0.168751 Epoch [¹⁄₂], Iter [¹⁹⁸³⁄₃₁₂₅], train_loss:0.162145 Epoch [¹⁄₂], Iter [¹⁹⁸⁴⁄₃₁₂₅], train_loss:0.182724 Epoch [¹⁄₂], Iter [¹⁹⁸⁵⁄₃₁₂₅], train_loss:0.155977 Epoch [¹⁄₂], Iter [¹⁹⁸⁶⁄₃₁₂₅], train_loss:0.155561 Epoch [¹⁄₂], Iter [¹⁹⁸⁷⁄₃₁₂₅], train_loss:0.191799 Epoch [¹⁄₂], Iter [¹⁹⁸⁸⁄₃₁₂₅], train_loss:0.167943 Epoch [¹⁄₂], Iter [¹⁹⁸⁹⁄₃₁₂₅], train_loss:0.163147 Epoch [¹⁄₂], Iter [¹⁹⁹⁰⁄₃₁₂₅], train_loss:0.176683 Epoch [¹⁄₂], Iter [¹⁹⁹¹⁄₃₁₂₅], train_loss:0.158023 Epoch [¹⁄₂], Iter [¹⁹⁹²⁄₃₁₂₅], train_loss:0.160804 Epoch [¹⁄₂], Iter [¹⁹⁹³⁄₃₁₂₅], train_loss:0.158202 Epoch [¹⁄₂], Iter [¹⁹⁹⁴⁄₃₁₂₅], train_loss:0.170246 Epoch [¹⁄₂], Iter [¹⁹⁹⁵⁄₃₁₂₅], train_loss:0.165867 Epoch [¹⁄₂], Iter [¹⁹⁹⁶⁄₃₁₂₅], train_loss:0.144000 Epoch [¹⁄₂], Iter [¹⁹⁹⁷⁄₃₁₂₅], train_loss:0.162011 Epoch [¹⁄₂], Iter [¹⁹⁹⁸⁄₃₁₂₅], train_loss:0.168511 Epoch [¹⁄₂], Iter [¹⁹⁹⁹⁄₃₁₂₅], train_loss:0.156590 Epoch [¹⁄₂], Iter [²⁰⁰⁰⁄₃₁₂₅], train_loss:0.151475 Epoch [¹⁄₂], Iter [²⁰⁰¹⁄₃₁₂₅], train_loss:0.172778 Epoch [¹⁄₂], Iter [²⁰⁰²⁄₃₁₂₅], train_loss:0.174170 Epoch [¹⁄₂], Iter [²⁰⁰³⁄₃₁₂₅], train_loss:0.172485 Epoch [¹⁄₂], Iter [²⁰⁰⁴⁄₃₁₂₅], train_loss:0.151658 Epoch [¹⁄₂], Iter [²⁰⁰⁵⁄₃₁₂₅], train_loss:0.165962 Epoch [¹⁄₂], Iter [²⁰⁰⁶⁄₃₁₂₅], train_loss:0.143169 Epoch [¹⁄₂], Iter [²⁰⁰⁷⁄₃₁₂₅], train_loss:0.170595 Epoch [¹⁄₂], Iter [²⁰⁰⁸⁄₃₁₂₅], train_loss:0.200333 Epoch [¹⁄₂], Iter [²⁰⁰⁹⁄₃₁₂₅], train_loss:0.163445 Epoch [¹⁄₂], Iter [²⁰¹⁰⁄₃₁₂₅], train_loss:0.150004 Epoch [¹⁄₂], Iter [²⁰¹¹⁄₃₁₂₅], train_loss:0.157552 Epoch [¹⁄₂], Iter [²⁰¹²⁄₃₁₂₅], train_loss:0.168187 Epoch [¹⁄₂], Iter [²⁰¹³⁄₃₁₂₅], train_loss:0.153843 Epoch [¹⁄₂], Iter [²⁰¹⁴⁄₃₁₂₅], train_loss:0.169956 Epoch [¹⁄₂], Iter [²⁰¹⁵⁄₃₁₂₅], train_loss:0.171310 Epoch [¹⁄₂], Iter [²⁰¹⁶⁄₃₁₂₅], train_loss:0.152466 Epoch [¹⁄₂], Iter [²⁰¹⁷⁄₃₁₂₅], train_loss:0.173650 Epoch [¹⁄₂], Iter [²⁰¹⁸⁄₃₁₂₅], train_loss:0.162068 Epoch [¹⁄₂], Iter [²⁰¹⁹⁄₃₁₂₅], train_loss:0.130321 Epoch [¹⁄₂], Iter [²⁰²⁰⁄₃₁₂₅], train_loss:0.124815 Epoch [¹⁄₂], Iter [²⁰²¹⁄₃₁₂₅], train_loss:0.145361 Epoch [¹⁄₂], Iter [²⁰²²⁄₃₁₂₅], train_loss:0.146677 Epoch [¹⁄₂], Iter [²⁰²³⁄₃₁₂₅], train_loss:0.165708 Epoch [¹⁄₂], Iter [²⁰²⁴⁄₃₁₂₅], train_loss:0.176067 Epoch [¹⁄₂], Iter [²⁰²⁵⁄₃₁₂₅], train_loss:0.168302 Epoch [¹⁄₂], Iter [²⁰²⁶⁄₃₁₂₅], train_loss:0.154875 Epoch [¹⁄₂], Iter [²⁰²⁷⁄₃₁₂₅], train_loss:0.164601 Epoch [¹⁄₂], Iter [²⁰²⁸⁄₃₁₂₅], train_loss:0.171662 Epoch [¹⁄₂], Iter [²⁰²⁹⁄₃₁₂₅], train_loss:0.151342 Epoch [¹⁄₂], Iter [²⁰³⁰⁄₃₁₂₅], train_loss:0.162905 Epoch [¹⁄₂], Iter [²⁰³¹⁄₃₁₂₅], train_loss:0.155055 Epoch [¹⁄₂], Iter [²⁰³²⁄₃₁₂₅], train_loss:0.133530 Epoch [¹⁄₂], Iter [²⁰³³⁄₃₁₂₅], train_loss:0.145367 Epoch [¹⁄₂], Iter [²⁰³⁴⁄₃₁₂₅], train_loss:0.140172 Epoch [¹⁄₂], Iter [²⁰³⁵⁄₃₁₂₅], train_loss:0.166013 Epoch [¹⁄₂], Iter [²⁰³⁶⁄₃₁₂₅], train_loss:0.160138 Epoch [¹⁄₂], Iter [²⁰³⁷⁄₃₁₂₅], train_loss:0.149895 Epoch [¹⁄₂], Iter [²⁰³⁸⁄₃₁₂₅], train_loss:0.158618 Epoch [¹⁄₂], Iter [²⁰³⁹⁄₃₁₂₅], train_loss:0.182976 Epoch [¹⁄₂], Iter [²⁰⁴⁰⁄₃₁₂₅], train_loss:0.163650 Epoch [¹⁄₂], Iter [²⁰⁴¹⁄₃₁₂₅], train_loss:0.156669 Epoch [¹⁄₂], Iter [²⁰⁴²⁄₃₁₂₅], train_loss:0.161290 Epoch [¹⁄₂], Iter [²⁰⁴³⁄₃₁₂₅], train_loss:0.162484 Epoch [¹⁄₂], Iter [²⁰⁴⁴⁄₃₁₂₅], train_loss:0.167114 Epoch [¹⁄₂], Iter [²⁰⁴⁵⁄₃₁₂₅], train_loss:0.170945 Epoch [¹⁄₂], Iter [²⁰⁴⁶⁄₃₁₂₅], train_loss:0.155789 Epoch [¹⁄₂], Iter [²⁰⁴⁷⁄₃₁₂₅], train_loss:0.164060 Epoch [¹⁄₂], Iter [²⁰⁴⁸⁄₃₁₂₅], train_loss:0.186333 Epoch [¹⁄₂], Iter [²⁰⁴⁹⁄₃₁₂₅], train_loss:0.160162 Epoch [¹⁄₂], Iter [²⁰⁵⁰⁄₃₁₂₅], train_loss:0.159823 Epoch [¹⁄₂], Iter [²⁰⁵¹⁄₃₁₂₅], train_loss:0.158371 Epoch [¹⁄₂], Iter [²⁰⁵²⁄₃₁₂₅], train_loss:0.159072 Epoch [¹⁄₂], Iter [²⁰⁵³⁄₃₁₂₅], train_loss:0.173952 Epoch [¹⁄₂], Iter [²⁰⁵⁴⁄₃₁₂₅], train_loss:0.161498 Epoch [¹⁄₂], Iter [²⁰⁵⁵⁄₃₁₂₅], train_loss:0.147181 Epoch [¹⁄₂], Iter [²⁰⁵⁶⁄₃₁₂₅], train_loss:0.176381 Epoch [¹⁄₂], Iter [²⁰⁵⁷⁄₃₁₂₅], train_loss:0.133942 Epoch [¹⁄₂], Iter [²⁰⁵⁸⁄₃₁₂₅], train_loss:0.144585 Epoch [¹⁄₂], Iter [²⁰⁵⁹⁄₃₁₂₅], train_loss:0.162973 Epoch [¹⁄₂], Iter [²⁰⁶⁰⁄₃₁₂₅], train_loss:0.165241 Epoch [¹⁄₂], Iter [²⁰⁶¹⁄₃₁₂₅], train_loss:0.174846 Epoch [¹⁄₂], Iter [²⁰⁶²⁄₃₁₂₅], train_loss:0.180418 Epoch [¹⁄₂], Iter [²⁰⁶³⁄₃₁₂₅], train_loss:0.182369 Epoch [¹⁄₂], Iter [²⁰⁶⁴⁄₃₁₂₅], train_loss:0.148855 Epoch [¹⁄₂], Iter [²⁰⁶⁵⁄₃₁₂₅], train_loss:0.180047 Epoch [¹⁄₂], Iter [²⁰⁶⁶⁄₃₁₂₅], train_loss:0.131797 Epoch [¹⁄₂], Iter [²⁰⁶⁷⁄₃₁₂₅], train_loss:0.161162 Epoch [¹⁄₂], Iter [²⁰⁶⁸⁄₃₁₂₅], train_loss:0.153623 Epoch [¹⁄₂], Iter [²⁰⁶⁹⁄₃₁₂₅], train_loss:0.177079 Epoch [¹⁄₂], Iter [²⁰⁷⁰⁄₃₁₂₅], train_loss:0.166252 Epoch [¹⁄₂], Iter [²⁰⁷¹⁄₃₁₂₅], train_loss:0.167907 Epoch [¹⁄₂], Iter [²⁰⁷²⁄₃₁₂₅], train_loss:0.168837 Epoch [¹⁄₂], Iter [²⁰⁷³⁄₃₁₂₅], train_loss:0.178388 Epoch [¹⁄₂], Iter [²⁰⁷⁴⁄₃₁₂₅], train_loss:0.167471 Epoch [¹⁄₂], Iter [²⁰⁷⁵⁄₃₁₂₅], train_loss:0.182263 Epoch [¹⁄₂], Iter [²⁰⁷⁶⁄₃₁₂₅], train_loss:0.164933 Epoch [¹⁄₂], Iter [²⁰⁷⁷⁄₃₁₂₅], train_loss:0.159932 Epoch [¹⁄₂], Iter [²⁰⁷⁸⁄₃₁₂₅], train_loss:0.165879 Epoch [¹⁄₂], Iter [²⁰⁷⁹⁄₃₁₂₅], train_loss:0.168112 Epoch [¹⁄₂], Iter [²⁰⁸⁰⁄₃₁₂₅], train_loss:0.164080 Epoch [¹⁄₂], Iter [²⁰⁸¹⁄₃₁₂₅], train_loss:0.177289 Epoch [¹⁄₂], Iter [²⁰⁸²⁄₃₁₂₅], train_loss:0.156052 Epoch [¹⁄₂], Iter [²⁰⁸³⁄₃₁₂₅], train_loss:0.150370 Epoch [¹⁄₂], Iter [²⁰⁸⁴⁄₃₁₂₅], train_loss:0.157389 Epoch [¹⁄₂], Iter [²⁰⁸⁵⁄₃₁₂₅], train_loss:0.164571 Epoch [¹⁄₂], Iter [²⁰⁸⁶⁄₃₁₂₅], train_loss:0.165030 Epoch [¹⁄₂], Iter [²⁰⁸⁷⁄₃₁₂₅], train_loss:0.165491 Epoch [¹⁄₂], Iter [²⁰⁸⁸⁄₃₁₂₅], train_loss:0.157076 Epoch [¹⁄₂], Iter [²⁰⁸⁹⁄₃₁₂₅], train_loss:0.157584 Epoch [¹⁄₂], Iter [²⁰⁹⁰⁄₃₁₂₅], train_loss:0.142475 Epoch [¹⁄₂], Iter [²⁰⁹¹⁄₃₁₂₅], train_loss:0.161959 Epoch [¹⁄₂], Iter [²⁰⁹²⁄₃₁₂₅], train_loss:0.150067 Epoch [¹⁄₂], Iter [²⁰⁹³⁄₃₁₂₅], train_loss:0.169877 Epoch [¹⁄₂], Iter [²⁰⁹⁴⁄₃₁₂₅], train_loss:0.175256 Epoch [¹⁄₂], Iter [²⁰⁹⁵⁄₃₁₂₅], train_loss:0.150007 Epoch [¹⁄₂], Iter [²⁰⁹⁶⁄₃₁₂₅], train_loss:0.175035 Epoch [¹⁄₂], Iter [²⁰⁹⁷⁄₃₁₂₅], train_loss:0.143745 Epoch [¹⁄₂], Iter [²⁰⁹⁸⁄₃₁₂₅], train_loss:0.175930 Epoch [¹⁄₂], Iter [²⁰⁹⁹⁄₃₁₂₅], train_loss:0.148834 Epoch [¹⁄₂], Iter [²¹⁰⁰⁄₃₁₂₅], train_loss:0.165045 Epoch [¹⁄₂], Iter [²¹⁰¹⁄₃₁₂₅], train_loss:0.142969 Epoch [¹⁄₂], Iter [²¹⁰²⁄₃₁₂₅], train_loss:0.147515 Epoch [¹⁄₂], Iter [²¹⁰³⁄₃₁₂₅], train_loss:0.144696 Epoch [¹⁄₂], Iter [²¹⁰⁴⁄₃₁₂₅], train_loss:0.170307 Epoch [¹⁄₂], Iter [²¹⁰⁵⁄₃₁₂₅], train_loss:0.153275 Epoch [¹⁄₂], Iter [²¹⁰⁶⁄₃₁₂₅], train_loss:0.174566 Epoch [¹⁄₂], Iter [²¹⁰⁷⁄₃₁₂₅], train_loss:0.168739 Epoch [¹⁄₂], Iter [²¹⁰⁸⁄₃₁₂₅], train_loss:0.168275 Epoch [¹⁄₂], Iter [²¹⁰⁹⁄₃₁₂₅], train_loss:0.156382 Epoch [¹⁄₂], Iter [²¹¹⁰⁄₃₁₂₅], train_loss:0.180446 Epoch [¹⁄₂], Iter [²¹¹¹⁄₃₁₂₅], train_loss:0.168478 Epoch [¹⁄₂], Iter [²¹¹²⁄₃₁₂₅], train_loss:0.161389 Epoch [¹⁄₂], Iter [²¹¹³⁄₃₁₂₅], train_loss:0.166829 Epoch [¹⁄₂], Iter [²¹¹⁴⁄₃₁₂₅], train_loss:0.144316 Epoch [¹⁄₂], Iter [²¹¹⁵⁄₃₁₂₅], train_loss:0.180950 Epoch [¹⁄₂], Iter [²¹¹⁶⁄₃₁₂₅], train_loss:0.160766 Epoch [¹⁄₂], Iter [²¹¹⁷⁄₃₁₂₅], train_loss:0.134064 Epoch [¹⁄₂], Iter [²¹¹⁸⁄₃₁₂₅], train_loss:0.133301 Epoch [¹⁄₂], Iter [²¹¹⁹⁄₃₁₂₅], train_loss:0.156353 Epoch [¹⁄₂], Iter [²¹²⁰⁄₃₁₂₅], train_loss:0.155335 Epoch [¹⁄₂], Iter [²¹²¹⁄₃₁₂₅], train_loss:0.156238 Epoch [¹⁄₂], Iter [²¹²²⁄₃₁₂₅], train_loss:0.167666 Epoch [¹⁄₂], Iter [²¹²³⁄₃₁₂₅], train_loss:0.139103 Epoch [¹⁄₂], Iter [²¹²⁴⁄₃₁₂₅], train_loss:0.164919 Epoch [¹⁄₂], Iter [²¹²⁵⁄₃₁₂₅], train_loss:0.172402 Epoch [¹⁄₂], Iter [²¹²⁶⁄₃₁₂₅], train_loss:0.156982 Epoch [¹⁄₂], Iter [²¹²⁷⁄₃₁₂₅], train_loss:0.174418 Epoch [¹⁄₂], Iter [²¹²⁸⁄₃₁₂₅], train_loss:0.163564 Epoch [¹⁄₂], Iter [²¹²⁹⁄₃₁₂₅], train_loss:0.155914 Epoch [¹⁄₂], Iter [²¹³⁰⁄₃₁₂₅], train_loss:0.155929 Epoch [¹⁄₂], Iter [²¹³¹⁄₃₁₂₅], train_loss:0.164747 Epoch [¹⁄₂], Iter [²¹³²⁄₃₁₂₅], train_loss:0.169162 Epoch [¹⁄₂], Iter [²¹³³⁄₃₁₂₅], train_loss:0.176287 Epoch [¹⁄₂], Iter [²¹³⁴⁄₃₁₂₅], train_loss:0.145140 Epoch [¹⁄₂], Iter [²¹³⁵⁄₃₁₂₅], train_loss:0.172772 Epoch [¹⁄₂], Iter [²¹³⁶⁄₃₁₂₅], train_loss:0.172442 Epoch [¹⁄₂], Iter [²¹³⁷⁄₃₁₂₅], train_loss:0.166545 Epoch [¹⁄₂], Iter [²¹³⁸⁄₃₁₂₅], train_loss:0.155658 Epoch [¹⁄₂], Iter [²¹³⁹⁄₃₁₂₅], train_loss:0.144825 Epoch [¹⁄₂], Iter [²¹⁴⁰⁄₃₁₂₅], train_loss:0.165197 Epoch [¹⁄₂], Iter [²¹⁴¹⁄₃₁₂₅], train_loss:0.179990 Epoch [¹⁄₂], Iter [²¹⁴²⁄₃₁₂₅], train_loss:0.155233 Epoch [¹⁄₂], Iter [²¹⁴³⁄₃₁₂₅], train_loss:0.162739 Epoch [¹⁄₂], Iter [²¹⁴⁴⁄₃₁₂₅], train_loss:0.156480 Epoch [¹⁄₂], Iter [²¹⁴⁵⁄₃₁₂₅], train_loss:0.155214 Epoch [¹⁄₂], Iter [²¹⁴⁶⁄₃₁₂₅], train_loss:0.162011 Epoch [¹⁄₂], Iter [²¹⁴⁷⁄₃₁₂₅], train_loss:0.163268 Epoch [¹⁄₂], Iter [²¹⁴⁸⁄₃₁₂₅], train_loss:0.180236 Epoch [¹⁄₂], Iter [²¹⁴⁹⁄₃₁₂₅], train_loss:0.173788 Epoch [¹⁄₂], Iter [²¹⁵⁰⁄₃₁₂₅], train_loss:0.155130 Epoch [¹⁄₂], Iter [²¹⁵¹⁄₃₁₂₅], train_loss:0.165528 Epoch [¹⁄₂], Iter [²¹⁵²⁄₃₁₂₅], train_loss:0.176281 Epoch [¹⁄₂], Iter [²¹⁵³⁄₃₁₂₅], train_loss:0.151886 Epoch [¹⁄₂], Iter [²¹⁵⁴⁄₃₁₂₅], train_loss:0.145217 Epoch [¹⁄₂], Iter [²¹⁵⁵⁄₃₁₂₅], train_loss:0.162727 Epoch [¹⁄₂], Iter [²¹⁵⁶⁄₃₁₂₅], train_loss:0.167274 Epoch [¹⁄₂], Iter [²¹⁵⁷⁄₃₁₂₅], train_loss:0.192076 Epoch [¹⁄₂], Iter [²¹⁵⁸⁄₃₁₂₅], train_loss:0.163333 Epoch [¹⁄₂], Iter [²¹⁵⁹⁄₃₁₂₅], train_loss:0.162825 Epoch [¹⁄₂], Iter [²¹⁶⁰⁄₃₁₂₅], train_loss:0.187321 Epoch [¹⁄₂], Iter [²¹⁶¹⁄₃₁₂₅], train_loss:0.158406 Epoch [¹⁄₂], Iter [²¹⁶²⁄₃₁₂₅], train_loss:0.179870 Epoch [¹⁄₂], Iter [²¹⁶³⁄₃₁₂₅], train_loss:0.138683 Epoch [¹⁄₂], Iter [²¹⁶⁴⁄₃₁₂₅], train_loss:0.150967 Epoch [¹⁄₂], Iter [²¹⁶⁵⁄₃₁₂₅], train_loss:0.131095 Epoch [¹⁄₂], Iter [²¹⁶⁶⁄₃₁₂₅], train_loss:0.183638 Epoch [¹⁄₂], Iter [²¹⁶⁷⁄₃₁₂₅], train_loss:0.159978 Epoch [¹⁄₂], Iter [²¹⁶⁸⁄₃₁₂₅], train_loss:0.186739 Epoch [¹⁄₂], Iter [²¹⁶⁹⁄₃₁₂₅], train_loss:0.181425 Epoch [¹⁄₂], Iter [²¹⁷⁰⁄₃₁₂₅], train_loss:0.168422 Epoch [¹⁄₂], Iter [²¹⁷¹⁄₃₁₂₅], train_loss:0.167889 Epoch [¹⁄₂], Iter [²¹⁷²⁄₃₁₂₅], train_loss:0.140880 Epoch [¹⁄₂], Iter [²¹⁷³⁄₃₁₂₅], train_loss:0.181237 Epoch [¹⁄₂], Iter [²¹⁷⁴⁄₃₁₂₅], train_loss:0.159820 Epoch [¹⁄₂], Iter [²¹⁷⁵⁄₃₁₂₅], train_loss:0.157872 Epoch [¹⁄₂], Iter [²¹⁷⁶⁄₃₁₂₅], train_loss:0.158261 Epoch [¹⁄₂], Iter [²¹⁷⁷⁄₃₁₂₅], train_loss:0.142904 Epoch [¹⁄₂], Iter [²¹⁷⁸⁄₃₁₂₅], train_loss:0.172463 Epoch [¹⁄₂], Iter [²¹⁷⁹⁄₃₁₂₅], train_loss:0.149298 Epoch [¹⁄₂], Iter [²¹⁸⁰⁄₃₁₂₅], train_loss:0.159796 Epoch [¹⁄₂], Iter [²¹⁸¹⁄₃₁₂₅], train_loss:0.169302 Epoch [¹⁄₂], Iter [²¹⁸²⁄₃₁₂₅], train_loss:0.185946 Epoch [¹⁄₂], Iter [²¹⁸³⁄₃₁₂₅], train_loss:0.158634 Epoch [¹⁄₂], Iter [²¹⁸⁴⁄₃₁₂₅], train_loss:0.163283 Epoch [¹⁄₂], Iter [²¹⁸⁵⁄₃₁₂₅], train_loss:0.147155 Epoch [¹⁄₂], Iter [²¹⁸⁶⁄₃₁₂₅], train_loss:0.169214 Epoch [¹⁄₂], Iter [²¹⁸⁷⁄₃₁₂₅], train_loss:0.170750 Epoch [¹⁄₂], Iter [²¹⁸⁸⁄₃₁₂₅], train_loss:0.164639 Epoch [¹⁄₂], Iter [²¹⁸⁹⁄₃₁₂₅], train_loss:0.167140 Epoch [¹⁄₂], Iter [²¹⁹⁰⁄₃₁₂₅], train_loss:0.165556 Epoch [¹⁄₂], Iter [²¹⁹¹⁄₃₁₂₅], train_loss:0.173164 Epoch [¹⁄₂], Iter [²¹⁹²⁄₃₁₂₅], train_loss:0.158743 Epoch [¹⁄₂], Iter [²¹⁹³⁄₃₁₂₅], train_loss:0.165279 Epoch [¹⁄₂], Iter [²¹⁹⁴⁄₃₁₂₅], train_loss:0.151960 Epoch [¹⁄₂], Iter [²¹⁹⁵⁄₃₁₂₅], train_loss:0.149383 Epoch [¹⁄₂], Iter [²¹⁹⁶⁄₃₁₂₅], train_loss:0.157849 Epoch [¹⁄₂], Iter [²¹⁹⁷⁄₃₁₂₅], train_loss:0.168340 Epoch [¹⁄₂], Iter [²¹⁹⁸⁄₃₁₂₅], train_loss:0.156435 Epoch [¹⁄₂], Iter [²¹⁹⁹⁄₃₁₂₅], train_loss:0.139338 Epoch [¹⁄₂], Iter [²²⁰⁰⁄₃₁₂₅], train_loss:0.160937 Epoch [¹⁄₂], Iter [²²⁰¹⁄₃₁₂₅], train_loss:0.155327 Epoch [¹⁄₂], Iter [²²⁰²⁄₃₁₂₅], train_loss:0.177210 Epoch [¹⁄₂], Iter [²²⁰³⁄₃₁₂₅], train_loss:0.178461 Epoch [¹⁄₂], Iter [²²⁰⁴⁄₃₁₂₅], train_loss:0.171101 Epoch [¹⁄₂], Iter [²²⁰⁵⁄₃₁₂₅], train_loss:0.184354 Epoch [¹⁄₂], Iter [²²⁰⁶⁄₃₁₂₅], train_loss:0.144931 Epoch [¹⁄₂], Iter [²²⁰⁷⁄₃₁₂₅], train_loss:0.163896 Epoch [¹⁄₂], Iter [²²⁰⁸⁄₃₁₂₅], train_loss:0.169595 Epoch [¹⁄₂], Iter [²²⁰⁹⁄₃₁₂₅], train_loss:0.157569 Epoch [¹⁄₂], Iter [²²¹⁰⁄₃₁₂₅], train_loss:0.178770 Epoch [¹⁄₂], Iter [²²¹¹⁄₃₁₂₅], train_loss:0.143887 Epoch [¹⁄₂], Iter [²²¹²⁄₃₁₂₅], train_loss:0.161863 Epoch [¹⁄₂], Iter [²²¹³⁄₃₁₂₅], train_loss:0.141911 Epoch [¹⁄₂], Iter [²²¹⁴⁄₃₁₂₅], train_loss:0.141126 Epoch [¹⁄₂], Iter [²²¹⁵⁄₃₁₂₅], train_loss:0.181017 Epoch [¹⁄₂], Iter [²²¹⁶⁄₃₁₂₅], train_loss:0.147786 Epoch [¹⁄₂], Iter [²²¹⁷⁄₃₁₂₅], train_loss:0.141503 Epoch [¹⁄₂], Iter [²²¹⁸⁄₃₁₂₅], train_loss:0.157903 Epoch [¹⁄₂], Iter [²²¹⁹⁄₃₁₂₅], train_loss:0.154843 Epoch [¹⁄₂], Iter [²²²⁰⁄₃₁₂₅], train_loss:0.148844 Epoch [¹⁄₂], Iter [²²²¹⁄₃₁₂₅], train_loss:0.161168 Epoch [¹⁄₂], Iter [²²²²⁄₃₁₂₅], train_loss:0.171695 Epoch [¹⁄₂], Iter [²²²³⁄₃₁₂₅], train_loss:0.163227 Epoch [¹⁄₂], Iter [²²²⁴⁄₃₁₂₅], train_loss:0.159965 Epoch [¹⁄₂], Iter [²²²⁵⁄₃₁₂₅], train_loss:0.162049 Epoch [¹⁄₂], Iter [²²²⁶⁄₃₁₂₅], train_loss:0.172635 Epoch [¹⁄₂], Iter [²²²⁷⁄₃₁₂₅], train_loss:0.152669 Epoch [¹⁄₂], Iter [²²²⁸⁄₃₁₂₅], train_loss:0.154830 Epoch [¹⁄₂], Iter [²²²⁹⁄₃₁₂₅], train_loss:0.163990 Epoch [¹⁄₂], Iter [²²³⁰⁄₃₁₂₅], train_loss:0.168742 Epoch [¹⁄₂], Iter [²²³¹⁄₃₁₂₅], train_loss:0.183449 Epoch [¹⁄₂], Iter [²²³²⁄₃₁₂₅], train_loss:0.148132 Epoch [¹⁄₂], Iter [²²³³⁄₃₁₂₅], train_loss:0.175107 Epoch [¹⁄₂], Iter [²²³⁴⁄₃₁₂₅], train_loss:0.157387 Epoch [¹⁄₂], Iter [²²³⁵⁄₃₁₂₅], train_loss:0.150439 Epoch [¹⁄₂], Iter [²²³⁶⁄₃₁₂₅], train_loss:0.141313 Epoch [¹⁄₂], Iter [²²³⁷⁄₃₁₂₅], train_loss:0.150460 Epoch [¹⁄₂], Iter [²²³⁸⁄₃₁₂₅], train_loss:0.157583 Epoch [¹⁄₂], Iter [²²³⁹⁄₃₁₂₅], train_loss:0.160917 Epoch [¹⁄₂], Iter [²²⁴⁰⁄₃₁₂₅], train_loss:0.175020 Epoch [¹⁄₂], Iter [²²⁴¹⁄₃₁₂₅], train_loss:0.172231 Epoch [¹⁄₂], Iter [²²⁴²⁄₃₁₂₅], train_loss:0.158164 Epoch [¹⁄₂], Iter [²²⁴³⁄₃₁₂₅], train_loss:0.149750 Epoch [¹⁄₂], Iter [²²⁴⁴⁄₃₁₂₅], train_loss:0.160434 Epoch [¹⁄₂], Iter [²²⁴⁵⁄₃₁₂₅], train_loss:0.163752 Epoch [¹⁄₂], Iter [²²⁴⁶⁄₃₁₂₅], train_loss:0.146884 Epoch [¹⁄₂], Iter [²²⁴⁷⁄₃₁₂₅], train_loss:0.158364 Epoch [¹⁄₂], Iter [²²⁴⁸⁄₃₁₂₅], train_loss:0.156011 Epoch [¹⁄₂], Iter [²²⁴⁹⁄₃₁₂₅], train_loss:0.173126 Epoch [¹⁄₂], Iter [²²⁵⁰⁄₃₁₂₅], train_loss:0.193422 Epoch [¹⁄₂], Iter [²²⁵¹⁄₃₁₂₅], train_loss:0.158470 Epoch [¹⁄₂], Iter [²²⁵²⁄₃₁₂₅], train_loss:0.151245 Epoch [¹⁄₂], Iter [²²⁵³⁄₃₁₂₅], train_loss:0.158039 Epoch [¹⁄₂], Iter [²²⁵⁴⁄₃₁₂₅], train_loss:0.152211 Epoch [¹⁄₂], Iter [²²⁵⁵⁄₃₁₂₅], train_loss:0.167252 Epoch [¹⁄₂], Iter [²²⁵⁶⁄₃₁₂₅], train_loss:0.156284 Epoch [¹⁄₂], Iter [²²⁵⁷⁄₃₁₂₅], train_loss:0.157557 Epoch [¹⁄₂], Iter [²²⁵⁸⁄₃₁₂₅], train_loss:0.149407 Epoch [¹⁄₂], Iter [²²⁵⁹⁄₃₁₂₅], train_loss:0.166932 Epoch [¹⁄₂], Iter [²²⁶⁰⁄₃₁₂₅], train_loss:0.174253 Epoch [¹⁄₂], Iter [²²⁶¹⁄₃₁₂₅], train_loss:0.171375 Epoch [¹⁄₂], Iter [²²⁶²⁄₃₁₂₅], train_loss:0.166366 Epoch [¹⁄₂], Iter [²²⁶³⁄₃₁₂₅], train_loss:0.149717 Epoch [¹⁄₂], Iter [²²⁶⁴⁄₃₁₂₅], train_loss:0.166810 Epoch [¹⁄₂], Iter [²²⁶⁵⁄₃₁₂₅], train_loss:0.162488 Epoch [¹⁄₂], Iter [²²⁶⁶⁄₃₁₂₅], train_loss:0.165728 Epoch [¹⁄₂], Iter [²²⁶⁷⁄₃₁₂₅], train_loss:0.168702 Epoch [¹⁄₂], Iter [²²⁶⁸⁄₃₁₂₅], train_loss:0.143795 Epoch [¹⁄₂], Iter [²²⁶⁹⁄₃₁₂₅], train_loss:0.125662 Epoch [¹⁄₂], Iter [²²⁷⁰⁄₃₁₂₅], train_loss:0.152566 Epoch [¹⁄₂], Iter [²²⁷¹⁄₃₁₂₅], train_loss:0.166331 Epoch [¹⁄₂], Iter [²²⁷²⁄₃₁₂₅], train_loss:0.146904 Epoch [¹⁄₂], Iter [²²⁷³⁄₃₁₂₅], train_loss:0.176470 Epoch [¹⁄₂], Iter [²²⁷⁴⁄₃₁₂₅], train_loss:0.166159 Epoch [¹⁄₂], Iter [²²⁷⁵⁄₃₁₂₅], train_loss:0.164638 Epoch [¹⁄₂], Iter [²²⁷⁶⁄₃₁₂₅], train_loss:0.174697 Epoch [¹⁄₂], Iter [²²⁷⁷⁄₃₁₂₅], train_loss:0.172518 Epoch [¹⁄₂], Iter [²²⁷⁸⁄₃₁₂₅], train_loss:0.179059 Epoch [¹⁄₂], Iter [²²⁷⁹⁄₃₁₂₅], train_loss:0.153997 Epoch [¹⁄₂], Iter [²²⁸⁰⁄₃₁₂₅], train_loss:0.164288 Epoch [¹⁄₂], Iter [²²⁸¹⁄₃₁₂₅], train_loss:0.156835 Epoch [¹⁄₂], Iter [²²⁸²⁄₃₁₂₅], train_loss:0.172427 Epoch [¹⁄₂], Iter [²²⁸³⁄₃₁₂₅], train_loss:0.140807 Epoch [¹⁄₂], Iter [²²⁸⁴⁄₃₁₂₅], train_loss:0.176298 Epoch [¹⁄₂], Iter [²²⁸⁵⁄₃₁₂₅], train_loss:0.167197 Epoch [¹⁄₂], Iter [²²⁸⁶⁄₃₁₂₅], train_loss:0.155124 Epoch [¹⁄₂], Iter [²²⁸⁷⁄₃₁₂₅], train_loss:0.168967 Epoch [¹⁄₂], Iter [²²⁸⁸⁄₃₁₂₅], train_loss:0.155021 Epoch [¹⁄₂], Iter [²²⁸⁹⁄₃₁₂₅], train_loss:0.200430 Epoch [¹⁄₂], Iter [²²⁹⁰⁄₃₁₂₅], train_loss:0.168794 Epoch [¹⁄₂], Iter [²²⁹¹⁄₃₁₂₅], train_loss:0.180748 Epoch [¹⁄₂], Iter [²²⁹²⁄₃₁₂₅], train_loss:0.151308 Epoch [¹⁄₂], Iter [²²⁹³⁄₃₁₂₅], train_loss:0.168426 Epoch [¹⁄₂], Iter [²²⁹⁴⁄₃₁₂₅], train_loss:0.160170 Epoch [¹⁄₂], Iter [²²⁹⁵⁄₃₁₂₅], train_loss:0.170112 Epoch [¹⁄₂], Iter [²²⁹⁶⁄₃₁₂₅], train_loss:0.182302 Epoch [¹⁄₂], Iter [²²⁹⁷⁄₃₁₂₅], train_loss:0.165573 Epoch [¹⁄₂], Iter [²²⁹⁸⁄₃₁₂₅], train_loss:0.154088 Epoch [¹⁄₂], Iter [²²⁹⁹⁄₃₁₂₅], train_loss:0.157324 Epoch [¹⁄₂], Iter [²³⁰⁰⁄₃₁₂₅], train_loss:0.186557 Epoch [¹⁄₂], Iter [²³⁰¹⁄₃₁₂₅], train_loss:0.159513 Epoch [¹⁄₂], Iter [²³⁰²⁄₃₁₂₅], train_loss:0.159842 Epoch [¹⁄₂], Iter [²³⁰³⁄₃₁₂₅], train_loss:0.196757 Epoch [¹⁄₂], Iter [²³⁰⁴⁄₃₁₂₅], train_loss:0.164728 Epoch [¹⁄₂], Iter [²³⁰⁵⁄₃₁₂₅], train_loss:0.159394 Epoch [¹⁄₂], Iter [²³⁰⁶⁄₃₁₂₅], train_loss:0.162070 Epoch [¹⁄₂], Iter [²³⁰⁷⁄₃₁₂₅], train_loss:0.150942 Epoch [¹⁄₂], Iter [²³⁰⁸⁄₃₁₂₅], train_loss:0.178885 Epoch [¹⁄₂], Iter [²³⁰⁹⁄₃₁₂₅], train_loss:0.167701 Epoch [¹⁄₂], Iter [²³¹⁰⁄₃₁₂₅], train_loss:0.172832 Epoch [¹⁄₂], Iter [²³¹¹⁄₃₁₂₅], train_loss:0.151420 Epoch [¹⁄₂], Iter [²³¹²⁄₃₁₂₅], train_loss:0.177722 Epoch [¹⁄₂], Iter [²³¹³⁄₃₁₂₅], train_loss:0.152966 Epoch [¹⁄₂], Iter [²³¹⁴⁄₃₁₂₅], train_loss:0.144942 Epoch [¹⁄₂], Iter [²³¹⁵⁄₃₁₂₅], train_loss:0.166451 Epoch [¹⁄₂], Iter [²³¹⁶⁄₃₁₂₅], train_loss:0.167570 Epoch [¹⁄₂], Iter [²³¹⁷⁄₃₁₂₅], train_loss:0.173486 Epoch [¹⁄₂], Iter [²³¹⁸⁄₃₁₂₅], train_loss:0.167726 Epoch [¹⁄₂], Iter [²³¹⁹⁄₃₁₂₅], train_loss:0.150083 Epoch [¹⁄₂], Iter [²³²⁰⁄₃₁₂₅], train_loss:0.161335 Epoch [¹⁄₂], Iter [²³²¹⁄₃₁₂₅], train_loss:0.163541 Epoch [¹⁄₂], Iter [²³²²⁄₃₁₂₅], train_loss:0.139134 Epoch [¹⁄₂], Iter [²³²³⁄₃₁₂₅], train_loss:0.172992 Epoch [¹⁄₂], Iter [²³²⁴⁄₃₁₂₅], train_loss:0.166975 Epoch [¹⁄₂], Iter [²³²⁵⁄₃₁₂₅], train_loss:0.161279 Epoch [¹⁄₂], Iter [²³²⁶⁄₃₁₂₅], train_loss:0.152028 Epoch [¹⁄₂], Iter [²³²⁷⁄₃₁₂₅], train_loss:0.157792 Epoch [¹⁄₂], Iter [²³²⁸⁄₃₁₂₅], train_loss:0.146232 Epoch [¹⁄₂], Iter [²³²⁹⁄₃₁₂₅], train_loss:0.169053 Epoch [¹⁄₂], Iter [²³³⁰⁄₃₁₂₅], train_loss:0.137772 Epoch [¹⁄₂], Iter [²³³¹⁄₃₁₂₅], train_loss:0.153836 Epoch [¹⁄₂], Iter [²³³²⁄₃₁₂₅], train_loss:0.173346 Epoch [¹⁄₂], Iter [²³³³⁄₃₁₂₅], train_loss:0.170181 Epoch [¹⁄₂], Iter [²³³⁴⁄₃₁₂₅], train_loss:0.153624 Epoch [¹⁄₂], Iter [²³³⁵⁄₃₁₂₅], train_loss:0.164155 Epoch [¹⁄₂], Iter [²³³⁶⁄₃₁₂₅], train_loss:0.162456 Epoch [¹⁄₂], Iter [²³³⁷⁄₃₁₂₅], train_loss:0.165626 Epoch [¹⁄₂], Iter [²³³⁸⁄₃₁₂₅], train_loss:0.165643 Epoch [¹⁄₂], Iter [²³³⁹⁄₃₁₂₅], train_loss:0.152838 Epoch [¹⁄₂], Iter [²³⁴⁰⁄₃₁₂₅], train_loss:0.166339 Epoch [¹⁄₂], Iter [²³⁴¹⁄₃₁₂₅], train_loss:0.162481 Epoch [¹⁄₂], Iter [²³⁴²⁄₃₁₂₅], train_loss:0.155828 Epoch [¹⁄₂], Iter [²³⁴³⁄₃₁₂₅], train_loss:0.180035 Epoch [¹⁄₂], Iter [²³⁴⁴⁄₃₁₂₅], train_loss:0.155793 Epoch [¹⁄₂], Iter [²³⁴⁵⁄₃₁₂₅], train_loss:0.141963 Epoch [¹⁄₂], Iter [²³⁴⁶⁄₃₁₂₅], train_loss:0.175218 Epoch [¹⁄₂], Iter [²³⁴⁷⁄₃₁₂₅], train_loss:0.172332 Epoch [¹⁄₂], Iter [²³⁴⁸⁄₃₁₂₅], train_loss:0.170206 Epoch [¹⁄₂], Iter [²³⁴⁹⁄₃₁₂₅], train_loss:0.158258 Epoch [¹⁄₂], Iter [²³⁵⁰⁄₃₁₂₅], train_loss:0.135423 Epoch [¹⁄₂], Iter [²³⁵¹⁄₃₁₂₅], train_loss:0.158765 Epoch [¹⁄₂], Iter [²³⁵²⁄₃₁₂₅], train_loss:0.161856 Epoch [¹⁄₂], Iter [²³⁵³⁄₃₁₂₅], train_loss:0.165698 Epoch [¹⁄₂], Iter [²³⁵⁴⁄₃₁₂₅], train_loss:0.166844 Epoch [¹⁄₂], Iter [²³⁵⁵⁄₃₁₂₅], train_loss:0.167199 Epoch [¹⁄₂], Iter [²³⁵⁶⁄₃₁₂₅], train_loss:0.168643 Epoch [¹⁄₂], Iter [²³⁵⁷⁄₃₁₂₅], train_loss:0.145062 Epoch [¹⁄₂], Iter [²³⁵⁸⁄₃₁₂₅], train_loss:0.159673 Epoch [¹⁄₂], Iter [²³⁵⁹⁄₃₁₂₅], train_loss:0.172321 Epoch [¹⁄₂], Iter [²³⁶⁰⁄₃₁₂₅], train_loss:0.162261 Epoch [¹⁄₂], Iter [²³⁶¹⁄₃₁₂₅], train_loss:0.160964 Epoch [¹⁄₂], Iter [²³⁶²⁄₃₁₂₅], train_loss:0.170365 Epoch [¹⁄₂], Iter [²³⁶³⁄₃₁₂₅], train_loss:0.158219 Epoch [¹⁄₂], Iter [²³⁶⁴⁄₃₁₂₅], train_loss:0.151682 Epoch [¹⁄₂], Iter [²³⁶⁵⁄₃₁₂₅], train_loss:0.173451 Epoch [¹⁄₂], Iter [²³⁶⁶⁄₃₁₂₅], train_loss:0.186411 Epoch [¹⁄₂], Iter [²³⁶⁷⁄₃₁₂₅], train_loss:0.151850 Epoch [¹⁄₂], Iter [²³⁶⁸⁄₃₁₂₅], train_loss:0.153410 Epoch [¹⁄₂], Iter [²³⁶⁹⁄₃₁₂₅], train_loss:0.150387 Epoch [¹⁄₂], Iter [²³⁷⁰⁄₃₁₂₅], train_loss:0.151061 Epoch [¹⁄₂], Iter [²³⁷¹⁄₃₁₂₅], train_loss:0.155576 Epoch [¹⁄₂], Iter [²³⁷²⁄₃₁₂₅], train_loss:0.171615 Epoch [¹⁄₂], Iter [²³⁷³⁄₃₁₂₅], train_loss:0.152891 Epoch [¹⁄₂], Iter [²³⁷⁴⁄₃₁₂₅], train_loss:0.173333 Epoch [¹⁄₂], Iter [²³⁷⁵⁄₃₁₂₅], train_loss:0.178193 Epoch [¹⁄₂], Iter [²³⁷⁶⁄₃₁₂₅], train_loss:0.158169 Epoch [¹⁄₂], Iter [²³⁷⁷⁄₃₁₂₅], train_loss:0.171027 Epoch [¹⁄₂], Iter [²³⁷⁸⁄₃₁₂₅], train_loss:0.183264 Epoch [¹⁄₂], Iter [²³⁷⁹⁄₃₁₂₅], train_loss:0.153622 Epoch [¹⁄₂], Iter [²³⁸⁰⁄₃₁₂₅], train_loss:0.167066 Epoch [¹⁄₂], Iter [²³⁸¹⁄₃₁₂₅], train_loss:0.151149 Epoch [¹⁄₂], Iter [²³⁸²⁄₃₁₂₅], train_loss:0.149457 Epoch [¹⁄₂], Iter [²³⁸³⁄₃₁₂₅], train_loss:0.151908 Epoch [¹⁄₂], Iter [²³⁸⁴⁄₃₁₂₅], train_loss:0.167173 Epoch [¹⁄₂], Iter [²³⁸⁵⁄₃₁₂₅], train_loss:0.146533 Epoch [¹⁄₂], Iter [²³⁸⁶⁄₃₁₂₅], train_loss:0.140869 Epoch [¹⁄₂], Iter [²³⁸⁷⁄₃₁₂₅], train_loss:0.161093 Epoch [¹⁄₂], Iter [²³⁸⁸⁄₃₁₂₅], train_loss:0.174047 Epoch [¹⁄₂], Iter [²³⁸⁹⁄₃₁₂₅], train_loss:0.169243 Epoch [¹⁄₂], Iter [²³⁹⁰⁄₃₁₂₅], train_loss:0.153055 Epoch [¹⁄₂], Iter [²³⁹¹⁄₃₁₂₅], train_loss:0.166778 Epoch [¹⁄₂], Iter [²³⁹²⁄₃₁₂₅], train_loss:0.171477 Epoch [¹⁄₂], Iter [²³⁹³⁄₃₁₂₅], train_loss:0.148076 Epoch [¹⁄₂], Iter [²³⁹⁴⁄₃₁₂₅], train_loss:0.174037 Epoch [¹⁄₂], Iter [²³⁹⁵⁄₃₁₂₅], train_loss:0.152578 Epoch [¹⁄₂], Iter [²³⁹⁶⁄₃₁₂₅], train_loss:0.184196 Epoch [¹⁄₂], Iter [²³⁹⁷⁄₃₁₂₅], train_loss:0.167483 Epoch [¹⁄₂], Iter [²³⁹⁸⁄₃₁₂₅], train_loss:0.164854 Epoch [¹⁄₂], Iter [²³⁹⁹⁄₃₁₂₅], train_loss:0.173233 Epoch [¹⁄₂], Iter [²⁴⁰⁰⁄₃₁₂₅], train_loss:0.138813 Epoch [¹⁄₂], Iter [²⁴⁰¹⁄₃₁₂₅], train_loss:0.152254 Epoch [¹⁄₂], Iter [²⁴⁰²⁄₃₁₂₅], train_loss:0.168025 Epoch [¹⁄₂], Iter [²⁴⁰³⁄₃₁₂₅], train_loss:0.157279 Epoch [¹⁄₂], Iter [²⁴⁰⁴⁄₃₁₂₅], train_loss:0.148963 Epoch [¹⁄₂], Iter [²⁴⁰⁵⁄₃₁₂₅], train_loss:0.144112 Epoch [¹⁄₂], Iter [²⁴⁰⁶⁄₃₁₂₅], train_loss:0.169978 Epoch [¹⁄₂], Iter [²⁴⁰⁷⁄₃₁₂₅], train_loss:0.153412 Epoch [¹⁄₂], Iter [²⁴⁰⁸⁄₃₁₂₅], train_loss:0.173826 Epoch [¹⁄₂], Iter [²⁴⁰⁹⁄₃₁₂₅], train_loss:0.169680 Epoch [¹⁄₂], Iter [²⁴¹⁰⁄₃₁₂₅], train_loss:0.162930 Epoch [¹⁄₂], Iter [²⁴¹¹⁄₃₁₂₅], train_loss:0.139202 Epoch [¹⁄₂], Iter [²⁴¹²⁄₃₁₂₅], train_loss:0.154762 Epoch [¹⁄₂], Iter [²⁴¹³⁄₃₁₂₅], train_loss:0.154299 Epoch [¹⁄₂], Iter [²⁴¹⁴⁄₃₁₂₅], train_loss:0.167414 Epoch [¹⁄₂], Iter [²⁴¹⁵⁄₃₁₂₅], train_loss:0.178091 Epoch [¹⁄₂], Iter [²⁴¹⁶⁄₃₁₂₅], train_loss:0.173954 Epoch [¹⁄₂], Iter [²⁴¹⁷⁄₃₁₂₅], train_loss:0.166982 Epoch [¹⁄₂], Iter [²⁴¹⁸⁄₃₁₂₅], train_loss:0.170560 Epoch [¹⁄₂], Iter [²⁴¹⁹⁄₃₁₂₅], train_loss:0.170997 Epoch [¹⁄₂], Iter [²⁴²⁰⁄₃₁₂₅], train_loss:0.153861 Epoch [¹⁄₂], Iter [²⁴²¹⁄₃₁₂₅], train_loss:0.177754 Epoch [¹⁄₂], Iter [²⁴²²⁄₃₁₂₅], train_loss:0.168872 Epoch [¹⁄₂], Iter [²⁴²³⁄₃₁₂₅], train_loss:0.144303 Epoch [¹⁄₂], Iter [²⁴²⁴⁄₃₁₂₅], train_loss:0.164720 Epoch [¹⁄₂], Iter [²⁴²⁵⁄₃₁₂₅], train_loss:0.186620 Epoch [¹⁄₂], Iter [²⁴²⁶⁄₃₁₂₅], train_loss:0.158638 Epoch [¹⁄₂], Iter [²⁴²⁷⁄₃₁₂₅], train_loss:0.172386 Epoch [¹⁄₂], Iter [²⁴²⁸⁄₃₁₂₅], train_loss:0.167100 Epoch [¹⁄₂], Iter [²⁴²⁹⁄₃₁₂₅], train_loss:0.167147 Epoch [¹⁄₂], Iter [²⁴³⁰⁄₃₁₂₅], train_loss:0.182128 Epoch [¹⁄₂], Iter [²⁴³¹⁄₃₁₂₅], train_loss:0.165804 Epoch [¹⁄₂], Iter [²⁴³²⁄₃₁₂₅], train_loss:0.180088 Epoch [¹⁄₂], Iter [²⁴³³⁄₃₁₂₅], train_loss:0.165245 Epoch [¹⁄₂], Iter [²⁴³⁴⁄₃₁₂₅], train_loss:0.159391 Epoch [¹⁄₂], Iter [²⁴³⁵⁄₃₁₂₅], train_loss:0.152686 Epoch [¹⁄₂], Iter [²⁴³⁶⁄₃₁₂₅], train_loss:0.161874 Epoch [¹⁄₂], Iter [²⁴³⁷⁄₃₁₂₅], train_loss:0.165142 Epoch [¹⁄₂], Iter [²⁴³⁸⁄₃₁₂₅], train_loss:0.160963 Epoch [¹⁄₂], Iter [²⁴³⁹⁄₃₁₂₅], train_loss:0.166472 Epoch [¹⁄₂], Iter [²⁴⁴⁰⁄₃₁₂₅], train_loss:0.158173 Epoch [¹⁄₂], Iter [²⁴⁴¹⁄₃₁₂₅], train_loss:0.173994 Epoch [¹⁄₂], Iter [²⁴⁴²⁄₃₁₂₅], train_loss:0.151297 Epoch [¹⁄₂], Iter [²⁴⁴³⁄₃₁₂₅], train_loss:0.152010 Epoch [¹⁄₂], Iter [²⁴⁴⁴⁄₃₁₂₅], train_loss:0.160982 Epoch [¹⁄₂], Iter [²⁴⁴⁵⁄₃₁₂₅], train_loss:0.182511 Epoch [¹⁄₂], Iter [²⁴⁴⁶⁄₃₁₂₅], train_loss:0.171740 Epoch [¹⁄₂], Iter [²⁴⁴⁷⁄₃₁₂₅], train_loss:0.169194 Epoch [¹⁄₂], Iter [²⁴⁴⁸⁄₃₁₂₅], train_loss:0.160217 Epoch [¹⁄₂], Iter [²⁴⁴⁹⁄₃₁₂₅], train_loss:0.170634 Epoch [¹⁄₂], Iter [²⁴⁵⁰⁄₃₁₂₅], train_loss:0.174725 Epoch [¹⁄₂], Iter [²⁴⁵¹⁄₃₁₂₅], train_loss:0.162844 Epoch [¹⁄₂], Iter [²⁴⁵²⁄₃₁₂₅], train_loss:0.179684 Epoch [¹⁄₂], Iter [²⁴⁵³⁄₃₁₂₅], train_loss:0.165793 Epoch [¹⁄₂], Iter [²⁴⁵⁴⁄₃₁₂₅], train_loss:0.147170 Epoch [¹⁄₂], Iter [²⁴⁵⁵⁄₃₁₂₅], train_loss:0.167428 Epoch [¹⁄₂], Iter [²⁴⁵⁶⁄₃₁₂₅], train_loss:0.156832 Epoch [¹⁄₂], Iter [²⁴⁵⁷⁄₃₁₂₅], train_loss:0.163711 Epoch [¹⁄₂], Iter [²⁴⁵⁸⁄₃₁₂₅], train_loss:0.163635 Epoch [¹⁄₂], Iter [²⁴⁵⁹⁄₃₁₂₅], train_loss:0.169788 Epoch [¹⁄₂], Iter [²⁴⁶⁰⁄₃₁₂₅], train_loss:0.161291 Epoch [¹⁄₂], Iter [²⁴⁶¹⁄₃₁₂₅], train_loss:0.176288 Epoch [¹⁄₂], Iter [²⁴⁶²⁄₃₁₂₅], train_loss:0.173527 Epoch [¹⁄₂], Iter [²⁴⁶³⁄₃₁₂₅], train_loss:0.198670 Epoch [¹⁄₂], Iter [²⁴⁶⁴⁄₃₁₂₅], train_loss:0.163765 Epoch [¹⁄₂], Iter [²⁴⁶⁵⁄₃₁₂₅], train_loss:0.155121 Epoch [¹⁄₂], Iter [²⁴⁶⁶⁄₃₁₂₅], train_loss:0.157210 Epoch [¹⁄₂], Iter [²⁴⁶⁷⁄₃₁₂₅], train_loss:0.158318 Epoch [¹⁄₂], Iter [²⁴⁶⁸⁄₃₁₂₅], train_loss:0.190069 Epoch [¹⁄₂], Iter [²⁴⁶⁹⁄₃₁₂₅], train_loss:0.157674 Epoch [¹⁄₂], Iter [²⁴⁷⁰⁄₃₁₂₅], train_loss:0.153022 Epoch [¹⁄₂], Iter [²⁴⁷¹⁄₃₁₂₅], train_loss:0.178211 Epoch [¹⁄₂], Iter [²⁴⁷²⁄₃₁₂₅], train_loss:0.165668 Epoch [¹⁄₂], Iter [²⁴⁷³⁄₃₁₂₅], train_loss:0.170597 Epoch [¹⁄₂], Iter [²⁴⁷⁴⁄₃₁₂₅], train_loss:0.148514 Epoch [¹⁄₂], Iter [²⁴⁷⁵⁄₃₁₂₅], train_loss:0.161165 Epoch [¹⁄₂], Iter [²⁴⁷⁶⁄₃₁₂₅], train_loss:0.159940 Epoch [¹⁄₂], Iter [²⁴⁷⁷⁄₃₁₂₅], train_loss:0.163364 Epoch [¹⁄₂], Iter [²⁴⁷⁸⁄₃₁₂₅], train_loss:0.160939 Epoch [¹⁄₂], Iter [²⁴⁷⁹⁄₃₁₂₅], train_loss:0.188242 Epoch [¹⁄₂], Iter [²⁴⁸⁰⁄₃₁₂₅], train_loss:0.170161 Epoch [¹⁄₂], Iter [²⁴⁸¹⁄₃₁₂₅], train_loss:0.166997 Epoch [¹⁄₂], Iter [²⁴⁸²⁄₃₁₂₅], train_loss:0.173182 Epoch [¹⁄₂], Iter [²⁴⁸³⁄₃₁₂₅], train_loss:0.156736 Epoch [¹⁄₂], Iter [²⁴⁸⁴⁄₃₁₂₅], train_loss:0.162785 Epoch [¹⁄₂], Iter [²⁴⁸⁵⁄₃₁₂₅], train_loss:0.159454 Epoch [¹⁄₂], Iter [²⁴⁸⁶⁄₃₁₂₅], train_loss:0.172418 Epoch [¹⁄₂], Iter [²⁴⁸⁷⁄₃₁₂₅], train_loss:0.166055 Epoch [¹⁄₂], Iter [²⁴⁸⁸⁄₃₁₂₅], train_loss:0.166522 Epoch [¹⁄₂], Iter [²⁴⁸⁹⁄₃₁₂₅], train_loss:0.157236 Epoch [¹⁄₂], Iter [²⁴⁹⁰⁄₃₁₂₅], train_loss:0.173360 Epoch [¹⁄₂], Iter [²⁴⁹¹⁄₃₁₂₅], train_loss:0.147073 Epoch [¹⁄₂], Iter [²⁴⁹²⁄₃₁₂₅], train_loss:0.154806 Epoch [¹⁄₂], Iter [²⁴⁹³⁄₃₁₂₅], train_loss:0.159782 Epoch [¹⁄₂], Iter [²⁴⁹⁴⁄₃₁₂₅], train_loss:0.175359 Epoch [¹⁄₂], Iter [²⁴⁹⁵⁄₃₁₂₅], train_loss:0.152874 Epoch [¹⁄₂], Iter [²⁴⁹⁶⁄₃₁₂₅], train_loss:0.175603 Epoch [¹⁄₂], Iter [²⁴⁹⁷⁄₃₁₂₅], train_loss:0.151182 Epoch [¹⁄₂], Iter [²⁴⁹⁸⁄₃₁₂₅], train_loss:0.133273 Epoch [¹⁄₂], Iter [²⁴⁹⁹⁄₃₁₂₅], train_loss:0.162480 Epoch [¹⁄₂], Iter [²⁵⁰⁰⁄₃₁₂₅], train_loss:0.172038 Epoch [¹⁄₂], Iter [²⁵⁰¹⁄₃₁₂₅], train_loss:0.163592 Epoch [¹⁄₂], Iter [²⁵⁰²⁄₃₁₂₅], train_loss:0.168842 Epoch [¹⁄₂], Iter [²⁵⁰³⁄₃₁₂₅], train_loss:0.167579 Epoch [¹⁄₂], Iter [²⁵⁰⁴⁄₃₁₂₅], train_loss:0.169892 Epoch [¹⁄₂], Iter [²⁵⁰⁵⁄₃₁₂₅], train_loss:0.184179 Epoch [¹⁄₂], Iter [²⁵⁰⁶⁄₃₁₂₅], train_loss:0.172049 Epoch [¹⁄₂], Iter [²⁵⁰⁷⁄₃₁₂₅], train_loss:0.181183 Epoch [¹⁄₂], Iter [²⁵⁰⁸⁄₃₁₂₅], train_loss:0.157703 Epoch [¹⁄₂], Iter [²⁵⁰⁹⁄₃₁₂₅], train_loss:0.156251 Epoch [¹⁄₂], Iter [²⁵¹⁰⁄₃₁₂₅], train_loss:0.140083 Epoch [¹⁄₂], Iter [²⁵¹¹⁄₃₁₂₅], train_loss:0.155766 Epoch [¹⁄₂], Iter [²⁵¹²⁄₃₁₂₅], train_loss:0.171320 Epoch [¹⁄₂], Iter [²⁵¹³⁄₃₁₂₅], train_loss:0.165249 Epoch [¹⁄₂], Iter [²⁵¹⁴⁄₃₁₂₅], train_loss:0.144336 Epoch [¹⁄₂], Iter [²⁵¹⁵⁄₃₁₂₅], train_loss:0.169332 Epoch [¹⁄₂], Iter [²⁵¹⁶⁄₃₁₂₅], train_loss:0.152470 Epoch [¹⁄₂], Iter [²⁵¹⁷⁄₃₁₂₅], train_loss:0.161122 Epoch [¹⁄₂], Iter [²⁵¹⁸⁄₃₁₂₅], train_loss:0.182971 Epoch [¹⁄₂], Iter [²⁵¹⁹⁄₃₁₂₅], train_loss:0.164621 Epoch [¹⁄₂], Iter [²⁵²⁰⁄₃₁₂₅], train_loss:0.175796 Epoch [¹⁄₂], Iter [²⁵²¹⁄₃₁₂₅], train_loss:0.176611 Epoch [¹⁄₂], Iter [²⁵²²⁄₃₁₂₅], train_loss:0.161589 Epoch [¹⁄₂], Iter [²⁵²³⁄₃₁₂₅], train_loss:0.153558 Epoch [¹⁄₂], Iter [²⁵²⁴⁄₃₁₂₅], train_loss:0.177934 Epoch [¹⁄₂], Iter [²⁵²⁵⁄₃₁₂₅], train_loss:0.140108 Epoch [¹⁄₂], Iter [²⁵²⁶⁄₃₁₂₅], train_loss:0.170537 Epoch [¹⁄₂], Iter [²⁵²⁷⁄₃₁₂₅], train_loss:0.190064 Epoch [¹⁄₂], Iter [²⁵²⁸⁄₃₁₂₅], train_loss:0.150987 Epoch [¹⁄₂], Iter [²⁵²⁹⁄₃₁₂₅], train_loss:0.153076 Epoch [¹⁄₂], Iter [²⁵³⁰⁄₃₁₂₅], train_loss:0.153231 Epoch [¹⁄₂], Iter [²⁵³¹⁄₃₁₂₅], train_loss:0.151433 Epoch [¹⁄₂], Iter [²⁵³²⁄₃₁₂₅], train_loss:0.165380 Epoch [¹⁄₂], Iter [²⁵³³⁄₃₁₂₅], train_loss:0.154326 Epoch [¹⁄₂], Iter [²⁵³⁴⁄₃₁₂₅], train_loss:0.148860 Epoch [¹⁄₂], Iter [²⁵³⁵⁄₃₁₂₅], train_loss:0.182532 Epoch [¹⁄₂], Iter [²⁵³⁶⁄₃₁₂₅], train_loss:0.184858 Epoch [¹⁄₂], Iter [²⁵³⁷⁄₃₁₂₅], train_loss:0.144190 Epoch [¹⁄₂], Iter [²⁵³⁸⁄₃₁₂₅], train_loss:0.160582 Epoch [¹⁄₂], Iter [²⁵³⁹⁄₃₁₂₅], train_loss:0.150244 Epoch [¹⁄₂], Iter [²⁵⁴⁰⁄₃₁₂₅], train_loss:0.163084 Epoch [¹⁄₂], Iter [²⁵⁴¹⁄₃₁₂₅], train_loss:0.173798 Epoch [¹⁄₂], Iter [²⁵⁴²⁄₃₁₂₅], train_loss:0.180224 Epoch [¹⁄₂], Iter [²⁵⁴³⁄₃₁₂₅], train_loss:0.171645 Epoch [¹⁄₂], Iter [²⁵⁴⁴⁄₃₁₂₅], train_loss:0.170542 Epoch [¹⁄₂], Iter [²⁵⁴⁵⁄₃₁₂₅], train_loss:0.150921 Epoch [¹⁄₂], Iter [²⁵⁴⁶⁄₃₁₂₅], train_loss:0.141499 Epoch [¹⁄₂], Iter [²⁵⁴⁷⁄₃₁₂₅], train_loss:0.154087 Epoch [¹⁄₂], Iter [²⁵⁴⁸⁄₃₁₂₅], train_loss:0.146057 Epoch [¹⁄₂], Iter [²⁵⁴⁹⁄₃₁₂₅], train_loss:0.179915 Epoch [¹⁄₂], Iter [²⁵⁵⁰⁄₃₁₂₅], train_loss:0.178421 Epoch [¹⁄₂], Iter [²⁵⁵¹⁄₃₁₂₅], train_loss:0.162338 Epoch [¹⁄₂], Iter [²⁵⁵²⁄₃₁₂₅], train_loss:0.159943 Epoch [¹⁄₂], Iter [²⁵⁵³⁄₃₁₂₅], train_loss:0.166942 Epoch [¹⁄₂], Iter [²⁵⁵⁴⁄₃₁₂₅], train_loss:0.161777 Epoch [¹⁄₂], Iter [²⁵⁵⁵⁄₃₁₂₅], train_loss:0.173371 Epoch [¹⁄₂], Iter [²⁵⁵⁶⁄₃₁₂₅], train_loss:0.149645 Epoch [¹⁄₂], Iter [²⁵⁵⁷⁄₃₁₂₅], train_loss:0.150998 Epoch [¹⁄₂], Iter [²⁵⁵⁸⁄₃₁₂₅], train_loss:0.168478 Epoch [¹⁄₂], Iter [²⁵⁵⁹⁄₃₁₂₅], train_loss:0.161073 Epoch [¹⁄₂], Iter [²⁵⁶⁰⁄₃₁₂₅], train_loss:0.153746 Epoch [¹⁄₂], Iter [²⁵⁶¹⁄₃₁₂₅], train_loss:0.156996 Epoch [¹⁄₂], Iter [²⁵⁶²⁄₃₁₂₅], train_loss:0.175018 Epoch [¹⁄₂], Iter [²⁵⁶³⁄₃₁₂₅], train_loss:0.161457 Epoch [¹⁄₂], Iter [²⁵⁶⁴⁄₃₁₂₅], train_loss:0.181512 Epoch [¹⁄₂], Iter [²⁵⁶⁵⁄₃₁₂₅], train_loss:0.159499 Epoch [¹⁄₂], Iter [²⁵⁶⁶⁄₃₁₂₅], train_loss:0.155685 Epoch [¹⁄₂], Iter [²⁵⁶⁷⁄₃₁₂₅], train_loss:0.160816 Epoch [¹⁄₂], Iter [²⁵⁶⁸⁄₃₁₂₅], train_loss:0.167257 Epoch [¹⁄₂], Iter [²⁵⁶⁹⁄₃₁₂₅], train_loss:0.168003 Epoch [¹⁄₂], Iter [²⁵⁷⁰⁄₃₁₂₅], train_loss:0.156276 Epoch [¹⁄₂], Iter [²⁵⁷¹⁄₃₁₂₅], train_loss:0.166197 Epoch [¹⁄₂], Iter [²⁵⁷²⁄₃₁₂₅], train_loss:0.171228 Epoch [¹⁄₂], Iter [²⁵⁷³⁄₃₁₂₅], train_loss:0.169274 Epoch [¹⁄₂], Iter [²⁵⁷⁴⁄₃₁₂₅], train_loss:0.178607 Epoch [¹⁄₂], Iter [²⁵⁷⁵⁄₃₁₂₅], train_loss:0.180143 Epoch [¹⁄₂], Iter [²⁵⁷⁶⁄₃₁₂₅], train_loss:0.165496 Epoch [¹⁄₂], Iter [²⁵⁷⁷⁄₃₁₂₅], train_loss:0.164666 Epoch [¹⁄₂], Iter [²⁵⁷⁸⁄₃₁₂₅], train_loss:0.172761 Epoch [¹⁄₂], Iter [²⁵⁷⁹⁄₃₁₂₅], train_loss:0.142597 Epoch [¹⁄₂], Iter [²⁵⁸⁰⁄₃₁₂₅], train_loss:0.166856 Epoch [¹⁄₂], Iter [²⁵⁸¹⁄₃₁₂₅], train_loss:0.180629 Epoch [¹⁄₂], Iter [²⁵⁸²⁄₃₁₂₅], train_loss:0.155988 Epoch [¹⁄₂], Iter [²⁵⁸³⁄₃₁₂₅], train_loss:0.190004 Epoch [¹⁄₂], Iter [²⁵⁸⁴⁄₃₁₂₅], train_loss:0.153131 Epoch [¹⁄₂], Iter [²⁵⁸⁵⁄₃₁₂₅], train_loss:0.149209 Epoch [¹⁄₂], Iter [²⁵⁸⁶⁄₃₁₂₅], train_loss:0.182763 Epoch [¹⁄₂], Iter [²⁵⁸⁷⁄₃₁₂₅], train_loss:0.163803 Epoch [¹⁄₂], Iter [²⁵⁸⁸⁄₃₁₂₅], train_loss:0.164377 Epoch [¹⁄₂], Iter [²⁵⁸⁹⁄₃₁₂₅], train_loss:0.165225 Epoch [¹⁄₂], Iter [²⁵⁹⁰⁄₃₁₂₅], train_loss:0.132286 Epoch [¹⁄₂], Iter [²⁵⁹¹⁄₃₁₂₅], train_loss:0.157618 Epoch [¹⁄₂], Iter [²⁵⁹²⁄₃₁₂₅], train_loss:0.180062 Epoch [¹⁄₂], Iter [²⁵⁹³⁄₃₁₂₅], train_loss:0.149064 Epoch [¹⁄₂], Iter [²⁵⁹⁴⁄₃₁₂₅], train_loss:0.182419 Epoch [¹⁄₂], Iter [²⁵⁹⁵⁄₃₁₂₅], train_loss:0.152154 Epoch [¹⁄₂], Iter [²⁵⁹⁶⁄₃₁₂₅], train_loss:0.156817 Epoch [¹⁄₂], Iter [²⁵⁹⁷⁄₃₁₂₅], train_loss:0.158894 Epoch [¹⁄₂], Iter [²⁵⁹⁸⁄₃₁₂₅], train_loss:0.174006 Epoch [¹⁄₂], Iter [²⁵⁹⁹⁄₃₁₂₅], train_loss:0.170469 Epoch [¹⁄₂], Iter [²⁶⁰⁰⁄₃₁₂₅], train_loss:0.163272 Epoch [¹⁄₂], Iter [²⁶⁰¹⁄₃₁₂₅], train_loss:0.165293 Epoch [¹⁄₂], Iter [²⁶⁰²⁄₃₁₂₅], train_loss:0.132606 Epoch [¹⁄₂], Iter [²⁶⁰³⁄₃₁₂₅], train_loss:0.181648 Epoch [¹⁄₂], Iter [²⁶⁰⁴⁄₃₁₂₅], train_loss:0.172091 Epoch [¹⁄₂], Iter [²⁶⁰⁵⁄₃₁₂₅], train_loss:0.145725 Epoch [¹⁄₂], Iter [²⁶⁰⁶⁄₃₁₂₅], train_loss:0.159542 Epoch [¹⁄₂], Iter [²⁶⁰⁷⁄₃₁₂₅], train_loss:0.166341 Epoch [¹⁄₂], Iter [²⁶⁰⁸⁄₃₁₂₅], train_loss:0.144378 Epoch [¹⁄₂], Iter [²⁶⁰⁹⁄₃₁₂₅], train_loss:0.174001 Epoch [¹⁄₂], Iter [²⁶¹⁰⁄₃₁₂₅], train_loss:0.154200 Epoch [¹⁄₂], Iter [²⁶¹¹⁄₃₁₂₅], train_loss:0.168938 Epoch [¹⁄₂], Iter [²⁶¹²⁄₃₁₂₅], train_loss:0.151330 Epoch [¹⁄₂], Iter [²⁶¹³⁄₃₁₂₅], train_loss:0.158763 Epoch [¹⁄₂], Iter [²⁶¹⁴⁄₃₁₂₅], train_loss:0.154259 Epoch [¹⁄₂], Iter [²⁶¹⁵⁄₃₁₂₅], train_loss:0.155223 Epoch [¹⁄₂], Iter [²⁶¹⁶⁄₃₁₂₅], train_loss:0.173738 Epoch [¹⁄₂], Iter [²⁶¹⁷⁄₃₁₂₅], train_loss:0.164574 Epoch [¹⁄₂], Iter [²⁶¹⁸⁄₃₁₂₅], train_loss:0.171280 Epoch [¹⁄₂], Iter [²⁶¹⁹⁄₃₁₂₅], train_loss:0.167967 Epoch [¹⁄₂], Iter [²⁶²⁰⁄₃₁₂₅], train_loss:0.165825 Epoch [¹⁄₂], Iter [²⁶²¹⁄₃₁₂₅], train_loss:0.163001 Epoch [¹⁄₂], Iter [²⁶²²⁄₃₁₂₅], train_loss:0.166808 Epoch [¹⁄₂], Iter [²⁶²³⁄₃₁₂₅], train_loss:0.158262 Epoch [¹⁄₂], Iter [²⁶²⁴⁄₃₁₂₅], train_loss:0.152927 Epoch [¹⁄₂], Iter [²⁶²⁵⁄₃₁₂₅], train_loss:0.151799 Epoch [¹⁄₂], Iter [²⁶²⁶⁄₃₁₂₅], train_loss:0.153348 Epoch [¹⁄₂], Iter [²⁶²⁷⁄₃₁₂₅], train_loss:0.145824 Epoch [¹⁄₂], Iter [²⁶²⁸⁄₃₁₂₅], train_loss:0.149315 Epoch [¹⁄₂], Iter [²⁶²⁹⁄₃₁₂₅], train_loss:0.183911 Epoch [¹⁄₂], Iter [²⁶³⁰⁄₃₁₂₅], train_loss:0.153068 Epoch [¹⁄₂], Iter [²⁶³¹⁄₃₁₂₅], train_loss:0.163764 Epoch [¹⁄₂], Iter [²⁶³²⁄₃₁₂₅], train_loss:0.161556 Epoch [¹⁄₂], Iter [²⁶³³⁄₃₁₂₅], train_loss:0.177212 Epoch [¹⁄₂], Iter [²⁶³⁴⁄₃₁₂₅], train_loss:0.149619 Epoch [¹⁄₂], Iter [²⁶³⁵⁄₃₁₂₅], train_loss:0.160023 Epoch [¹⁄₂], Iter [²⁶³⁶⁄₃₁₂₅], train_loss:0.169547 Epoch [¹⁄₂], Iter [²⁶³⁷⁄₃₁₂₅], train_loss:0.147591 Epoch [¹⁄₂], Iter [²⁶³⁸⁄₃₁₂₅], train_loss:0.156738 Epoch [¹⁄₂], Iter [²⁶³⁹⁄₃₁₂₅], train_loss:0.148298 Epoch [¹⁄₂], Iter [²⁶⁴⁰⁄₃₁₂₅], train_loss:0.161786 Epoch [¹⁄₂], Iter [²⁶⁴¹⁄₃₁₂₅], train_loss:0.162544 Epoch [¹⁄₂], Iter [²⁶⁴²⁄₃₁₂₅], train_loss:0.168581 Epoch [¹⁄₂], Iter [²⁶⁴³⁄₃₁₂₅], train_loss:0.167225 Epoch [¹⁄₂], Iter [²⁶⁴⁴⁄₃₁₂₅], train_loss:0.160467 Epoch [¹⁄₂], Iter [²⁶⁴⁵⁄₃₁₂₅], train_loss:0.166200 Epoch [¹⁄₂], Iter [²⁶⁴⁶⁄₃₁₂₅], train_loss:0.167931 Epoch [¹⁄₂], Iter [²⁶⁴⁷⁄₃₁₂₅], train_loss:0.157258 Epoch [¹⁄₂], Iter [²⁶⁴⁸⁄₃₁₂₅], train_loss:0.142979 Epoch [¹⁄₂], Iter [²⁶⁴⁹⁄₃₁₂₅], train_loss:0.169719 Epoch [¹⁄₂], Iter [²⁶⁵⁰⁄₃₁₂₅], train_loss:0.179859 Epoch [¹⁄₂], Iter [²⁶⁵¹⁄₃₁₂₅], train_loss:0.154542 Epoch [¹⁄₂], Iter [²⁶⁵²⁄₃₁₂₅], train_loss:0.157200 Epoch [¹⁄₂], Iter [²⁶⁵³⁄₃₁₂₅], train_loss:0.178602 Epoch [¹⁄₂], Iter [²⁶⁵⁴⁄₃₁₂₅], train_loss:0.145348 Epoch [¹⁄₂], Iter [²⁶⁵⁵⁄₃₁₂₅], train_loss:0.156349 Epoch [¹⁄₂], Iter [²⁶⁵⁶⁄₃₁₂₅], train_loss:0.148944 Epoch [¹⁄₂], Iter [²⁶⁵⁷⁄₃₁₂₅], train_loss:0.157309 Epoch [¹⁄₂], Iter [²⁶⁵⁸⁄₃₁₂₅], train_loss:0.162670 Epoch [¹⁄₂], Iter [²⁶⁵⁹⁄₃₁₂₅], train_loss:0.150020 Epoch [¹⁄₂], Iter [²⁶⁶⁰⁄₃₁₂₅], train_loss:0.157252 Epoch [¹⁄₂], Iter [²⁶⁶¹⁄₃₁₂₅], train_loss:0.166470 Epoch [¹⁄₂], Iter [²⁶⁶²⁄₃₁₂₅], train_loss:0.178597 Epoch [¹⁄₂], Iter [²⁶⁶³⁄₃₁₂₅], train_loss:0.145679 Epoch [¹⁄₂], Iter [²⁶⁶⁴⁄₃₁₂₅], train_loss:0.142497 Epoch [¹⁄₂], Iter [²⁶⁶⁵⁄₃₁₂₅], train_loss:0.153192 Epoch [¹⁄₂], Iter [²⁶⁶⁶⁄₃₁₂₅], train_loss:0.155716 Epoch [¹⁄₂], Iter [²⁶⁶⁷⁄₃₁₂₅], train_loss:0.174556 Epoch [¹⁄₂], Iter [²⁶⁶⁸⁄₃₁₂₅], train_loss:0.152721 Epoch [¹⁄₂], Iter [²⁶⁶⁹⁄₃₁₂₅], train_loss:0.169619 Epoch [¹⁄₂], Iter [²⁶⁷⁰⁄₃₁₂₅], train_loss:0.167028 Epoch [¹⁄₂], Iter [²⁶⁷¹⁄₃₁₂₅], train_loss:0.154183 Epoch [¹⁄₂], Iter [²⁶⁷²⁄₃₁₂₅], train_loss:0.175002 Epoch [¹⁄₂], Iter [²⁶⁷³⁄₃₁₂₅], train_loss:0.139364 Epoch [¹⁄₂], Iter [²⁶⁷⁴⁄₃₁₂₅], train_loss:0.162451 Epoch [¹⁄₂], Iter [²⁶⁷⁵⁄₃₁₂₅], train_loss:0.157143 Epoch [¹⁄₂], Iter [²⁶⁷⁶⁄₃₁₂₅], train_loss:0.166282 Epoch [¹⁄₂], Iter [²⁶⁷⁷⁄₃₁₂₅], train_loss:0.150420 Epoch [¹⁄₂], Iter [²⁶⁷⁸⁄₃₁₂₅], train_loss:0.172134 Epoch [¹⁄₂], Iter [²⁶⁷⁹⁄₃₁₂₅], train_loss:0.170172 Epoch [¹⁄₂], Iter [²⁶⁸⁰⁄₃₁₂₅], train_loss:0.188591 Epoch [¹⁄₂], Iter [²⁶⁸¹⁄₃₁₂₅], train_loss:0.133006 Epoch [¹⁄₂], Iter [²⁶⁸²⁄₃₁₂₅], train_loss:0.154428 Epoch [¹⁄₂], Iter [²⁶⁸³⁄₃₁₂₅], train_loss:0.146256 Epoch [¹⁄₂], Iter [²⁶⁸⁴⁄₃₁₂₅], train_loss:0.140180 Epoch [¹⁄₂], Iter [²⁶⁸⁵⁄₃₁₂₅], train_loss:0.150448 Epoch [¹⁄₂], Iter [²⁶⁸⁶⁄₃₁₂₅], train_loss:0.166966 Epoch [¹⁄₂], Iter [²⁶⁸⁷⁄₃₁₂₅], train_loss:0.163846 Epoch [¹⁄₂], Iter [²⁶⁸⁸⁄₃₁₂₅], train_loss:0.151998 Epoch [¹⁄₂], Iter [²⁶⁸⁹⁄₃₁₂₅], train_loss:0.177917 Epoch [¹⁄₂], Iter [²⁶⁹⁰⁄₃₁₂₅], train_loss:0.164405 Epoch [¹⁄₂], Iter [²⁶⁹¹⁄₃₁₂₅], train_loss:0.149646 Epoch [¹⁄₂], Iter [²⁶⁹²⁄₃₁₂₅], train_loss:0.155895 Epoch [¹⁄₂], Iter [²⁶⁹³⁄₃₁₂₅], train_loss:0.133467 Epoch [¹⁄₂], Iter [²⁶⁹⁴⁄₃₁₂₅], train_loss:0.181978 Epoch [¹⁄₂], Iter [²⁶⁹⁵⁄₃₁₂₅], train_loss:0.178019 Epoch [¹⁄₂], Iter [²⁶⁹⁶⁄₃₁₂₅], train_loss:0.164970 Epoch [¹⁄₂], Iter [²⁶⁹⁷⁄₃₁₂₅], train_loss:0.153656 Epoch [¹⁄₂], Iter [²⁶⁹⁸⁄₃₁₂₅], train_loss:0.158283 Epoch [¹⁄₂], Iter [²⁶⁹⁹⁄₃₁₂₅], train_loss:0.166151 Epoch [¹⁄₂], Iter [²⁷⁰⁰⁄₃₁₂₅], train_loss:0.152899 Epoch [¹⁄₂], Iter [²⁷⁰¹⁄₃₁₂₅], train_loss:0.150675 Epoch [¹⁄₂], Iter [²⁷⁰²⁄₃₁₂₅], train_loss:0.161370 Epoch [¹⁄₂], Iter [²⁷⁰³⁄₃₁₂₅], train_loss:0.162690 Epoch [¹⁄₂], Iter [²⁷⁰⁴⁄₃₁₂₅], train_loss:0.146854 Epoch [¹⁄₂], Iter [²⁷⁰⁵⁄₃₁₂₅], train_loss:0.168728 Epoch [¹⁄₂], Iter [²⁷⁰⁶⁄₃₁₂₅], train_loss:0.156361 Epoch [¹⁄₂], Iter [²⁷⁰⁷⁄₃₁₂₅], train_loss:0.162295 Epoch [¹⁄₂], Iter [²⁷⁰⁸⁄₃₁₂₅], train_loss:0.154698 Epoch [¹⁄₂], Iter [²⁷⁰⁹⁄₃₁₂₅], train_loss:0.162639 Epoch [¹⁄₂], Iter [²⁷¹⁰⁄₃₁₂₅], train_loss:0.170419 Epoch [¹⁄₂], Iter [²⁷¹¹⁄₃₁₂₅], train_loss:0.182608 Epoch [¹⁄₂], Iter [²⁷¹²⁄₃₁₂₅], train_loss:0.174881 Epoch [¹⁄₂], Iter [²⁷¹³⁄₃₁₂₅], train_loss:0.163568 Epoch [¹⁄₂], Iter [²⁷¹⁴⁄₃₁₂₅], train_loss:0.172464 Epoch [¹⁄₂], Iter [²⁷¹⁵⁄₃₁₂₅], train_loss:0.152963 Epoch [¹⁄₂], Iter [²⁷¹⁶⁄₃₁₂₅], train_loss:0.174935 Epoch [¹⁄₂], Iter [²⁷¹⁷⁄₃₁₂₅], train_loss:0.163978 Epoch [¹⁄₂], Iter [²⁷¹⁸⁄₃₁₂₅], train_loss:0.149811 Epoch [¹⁄₂], Iter [²⁷¹⁹⁄₃₁₂₅], train_loss:0.168551 Epoch [¹⁄₂], Iter [²⁷²⁰⁄₃₁₂₅], train_loss:0.187687 Epoch [¹⁄₂], Iter [²⁷²¹⁄₃₁₂₅], train_loss:0.170561 Epoch [¹⁄₂], Iter [²⁷²²⁄₃₁₂₅], train_loss:0.157643 Epoch [¹⁄₂], Iter [²⁷²³⁄₃₁₂₅], train_loss:0.183448 Epoch [¹⁄₂], Iter [²⁷²⁴⁄₃₁₂₅], train_loss:0.156940 Epoch [¹⁄₂], Iter [²⁷²⁵⁄₃₁₂₅], train_loss:0.176922 Epoch [¹⁄₂], Iter [²⁷²⁶⁄₃₁₂₅], train_loss:0.170941 Epoch [¹⁄₂], Iter [²⁷²⁷⁄₃₁₂₅], train_loss:0.161215 Epoch [¹⁄₂], Iter [²⁷²⁸⁄₃₁₂₅], train_loss:0.157638 Epoch [¹⁄₂], Iter [²⁷²⁹⁄₃₁₂₅], train_loss:0.146765 Epoch [¹⁄₂], Iter [²⁷³⁰⁄₃₁₂₅], train_loss:0.186415 Epoch [¹⁄₂], Iter [²⁷³¹⁄₃₁₂₅], train_loss:0.179016 Epoch [¹⁄₂], Iter [²⁷³²⁄₃₁₂₅], train_loss:0.146862 Epoch [¹⁄₂], Iter [²⁷³³⁄₃₁₂₅], train_loss:0.160904 Epoch [¹⁄₂], Iter [²⁷³⁴⁄₃₁₂₅], train_loss:0.184066 Epoch [¹⁄₂], Iter [²⁷³⁵⁄₃₁₂₅], train_loss:0.170018 Epoch [¹⁄₂], Iter [²⁷³⁶⁄₃₁₂₅], train_loss:0.151466 Epoch [¹⁄₂], Iter [²⁷³⁷⁄₃₁₂₅], train_loss:0.155503 Epoch [¹⁄₂], Iter [²⁷³⁸⁄₃₁₂₅], train_loss:0.178504 Epoch [¹⁄₂], Iter [²⁷³⁹⁄₃₁₂₅], train_loss:0.182733 Epoch [¹⁄₂], Iter [²⁷⁴⁰⁄₃₁₂₅], train_loss:0.178885 Epoch [¹⁄₂], Iter [²⁷⁴¹⁄₃₁₂₅], train_loss:0.158115 Epoch [¹⁄₂], Iter [²⁷⁴²⁄₃₁₂₅], train_loss:0.166074 Epoch [¹⁄₂], Iter [²⁷⁴³⁄₃₁₂₅], train_loss:0.175153 Epoch [¹⁄₂], Iter [²⁷⁴⁴⁄₃₁₂₅], train_loss:0.173695 Epoch [¹⁄₂], Iter [²⁷⁴⁵⁄₃₁₂₅], train_loss:0.140103 Epoch [¹⁄₂], Iter [²⁷⁴⁶⁄₃₁₂₅], train_loss:0.164165 Epoch [¹⁄₂], Iter [²⁷⁴⁷⁄₃₁₂₅], train_loss:0.195799 Epoch [¹⁄₂], Iter [²⁷⁴⁸⁄₃₁₂₅], train_loss:0.165051 Epoch [¹⁄₂], Iter [²⁷⁴⁹⁄₃₁₂₅], train_loss:0.168219 Epoch [¹⁄₂], Iter [²⁷⁵⁰⁄₃₁₂₅], train_loss:0.145761 Epoch [¹⁄₂], Iter [²⁷⁵¹⁄₃₁₂₅], train_loss:0.184619 Epoch [¹⁄₂], Iter [²⁷⁵²⁄₃₁₂₅], train_loss:0.183593 Epoch [¹⁄₂], Iter [²⁷⁵³⁄₃₁₂₅], train_loss:0.161479 Epoch [¹⁄₂], Iter [²⁷⁵⁴⁄₃₁₂₅], train_loss:0.165525 Epoch [¹⁄₂], Iter [²⁷⁵⁵⁄₃₁₂₅], train_loss:0.152368 Epoch [¹⁄₂], Iter [²⁷⁵⁶⁄₃₁₂₅], train_loss:0.156252 Epoch [¹⁄₂], Iter [²⁷⁵⁷⁄₃₁₂₅], train_loss:0.160543 Epoch [¹⁄₂], Iter [²⁷⁵⁸⁄₃₁₂₅], train_loss:0.169057 Epoch [¹⁄₂], Iter [²⁷⁵⁹⁄₃₁₂₅], train_loss:0.185539 Epoch [¹⁄₂], Iter [²⁷⁶⁰⁄₃₁₂₅], train_loss:0.150664 Epoch [¹⁄₂], Iter [²⁷⁶¹⁄₃₁₂₅], train_loss:0.168148 Epoch [¹⁄₂], Iter [²⁷⁶²⁄₃₁₂₅], train_loss:0.150886 Epoch [¹⁄₂], Iter [²⁷⁶³⁄₃₁₂₅], train_loss:0.153608 Epoch [¹⁄₂], Iter [²⁷⁶⁴⁄₃₁₂₅], train_loss:0.173608 Epoch [¹⁄₂], Iter [²⁷⁶⁵⁄₃₁₂₅], train_loss:0.156316 Epoch [¹⁄₂], Iter [²⁷⁶⁶⁄₃₁₂₅], train_loss:0.155580 Epoch [¹⁄₂], Iter [²⁷⁶⁷⁄₃₁₂₅], train_loss:0.170365 Epoch [¹⁄₂], Iter [²⁷⁶⁸⁄₃₁₂₅], train_loss:0.160952 Epoch [¹⁄₂], Iter [²⁷⁶⁹⁄₃₁₂₅], train_loss:0.178418 Epoch [¹⁄₂], Iter [²⁷⁷⁰⁄₃₁₂₅], train_loss:0.161754 Epoch [¹⁄₂], Iter [²⁷⁷¹⁄₃₁₂₅], train_loss:0.175010 Epoch [¹⁄₂], Iter [²⁷⁷²⁄₃₁₂₅], train_loss:0.177170 Epoch [¹⁄₂], Iter [²⁷⁷³⁄₃₁₂₅], train_loss:0.156224 Epoch [¹⁄₂], Iter [²⁷⁷⁴⁄₃₁₂₅], train_loss:0.171853 Epoch [¹⁄₂], Iter [²⁷⁷⁵⁄₃₁₂₅], train_loss:0.175113 Epoch [¹⁄₂], Iter [²⁷⁷⁶⁄₃₁₂₅], train_loss:0.153226 Epoch [¹⁄₂], Iter [²⁷⁷⁷⁄₃₁₂₅], train_loss:0.167736 Epoch [¹⁄₂], Iter [²⁷⁷⁸⁄₃₁₂₅], train_loss:0.160811 Epoch [¹⁄₂], Iter [²⁷⁷⁹⁄₃₁₂₅], train_loss:0.174287 Epoch [¹⁄₂], Iter [²⁷⁸⁰⁄₃₁₂₅], train_loss:0.158126 Epoch [¹⁄₂], Iter [²⁷⁸¹⁄₃₁₂₅], train_loss:0.170792 Epoch [¹⁄₂], Iter [²⁷⁸²⁄₃₁₂₅], train_loss:0.165518 Epoch [¹⁄₂], Iter [²⁷⁸³⁄₃₁₂₅], train_loss:0.162349 Epoch [¹⁄₂], Iter [²⁷⁸⁴⁄₃₁₂₅], train_loss:0.145470 Epoch [¹⁄₂], Iter [²⁷⁸⁵⁄₃₁₂₅], train_loss:0.159157 Epoch [¹⁄₂], Iter [²⁷⁸⁶⁄₃₁₂₅], train_loss:0.147954 Epoch [¹⁄₂], Iter [²⁷⁸⁷⁄₃₁₂₅], train_loss:0.170489 Epoch [¹⁄₂], Iter [²⁷⁸⁸⁄₃₁₂₅], train_loss:0.165043 Epoch [¹⁄₂], Iter [²⁷⁸⁹⁄₃₁₂₅], train_loss:0.163622 Epoch [¹⁄₂], Iter [²⁷⁹⁰⁄₃₁₂₅], train_loss:0.154899 Epoch [¹⁄₂], Iter [²⁷⁹¹⁄₃₁₂₅], train_loss:0.160961 Epoch [¹⁄₂], Iter [²⁷⁹²⁄₃₁₂₅], train_loss:0.165133 Epoch [¹⁄₂], Iter [²⁷⁹³⁄₃₁₂₅], train_loss:0.183820 Epoch [¹⁄₂], Iter [²⁷⁹⁴⁄₃₁₂₅], train_loss:0.170000 Epoch [¹⁄₂], Iter [²⁷⁹⁵⁄₃₁₂₅], train_loss:0.164589 Epoch [¹⁄₂], Iter [²⁷⁹⁶⁄₃₁₂₅], train_loss:0.180219 Epoch [¹⁄₂], Iter [²⁷⁹⁷⁄₃₁₂₅], train_loss:0.144782 Epoch [¹⁄₂], Iter [²⁷⁹⁸⁄₃₁₂₅], train_loss:0.175786 Epoch [¹⁄₂], Iter [²⁷⁹⁹⁄₃₁₂₅], train_loss:0.128005 Epoch [¹⁄₂], Iter [²⁸⁰⁰⁄₃₁₂₅], train_loss:0.156003 Epoch [¹⁄₂], Iter [²⁸⁰¹⁄₃₁₂₅], train_loss:0.151638 Epoch [¹⁄₂], Iter [²⁸⁰²⁄₃₁₂₅], train_loss:0.162846 Epoch [¹⁄₂], Iter [²⁸⁰³⁄₃₁₂₅], train_loss:0.162985 Epoch [¹⁄₂], Iter [²⁸⁰⁴⁄₃₁₂₅], train_loss:0.160361 Epoch [¹⁄₂], Iter [²⁸⁰⁵⁄₃₁₂₅], train_loss:0.151148 Epoch [¹⁄₂], Iter [²⁸⁰⁶⁄₃₁₂₅], train_loss:0.164542 Epoch [¹⁄₂], Iter [²⁸⁰⁷⁄₃₁₂₅], train_loss:0.142881 Epoch [¹⁄₂], Iter [²⁸⁰⁸⁄₃₁₂₅], train_loss:0.156098 Epoch [¹⁄₂], Iter [²⁸⁰⁹⁄₃₁₂₅], train_loss:0.133754 Epoch [¹⁄₂], Iter [²⁸¹⁰⁄₃₁₂₅], train_loss:0.170719 Epoch [¹⁄₂], Iter [²⁸¹¹⁄₃₁₂₅], train_loss:0.149624 Epoch [¹⁄₂], Iter [²⁸¹²⁄₃₁₂₅], train_loss:0.175666 Epoch [¹⁄₂], Iter [²⁸¹³⁄₃₁₂₅], train_loss:0.178650 Epoch [¹⁄₂], Iter [²⁸¹⁴⁄₃₁₂₅], train_loss:0.160231 Epoch [¹⁄₂], Iter [²⁸¹⁵⁄₃₁₂₅], train_loss:0.181755 Epoch [¹⁄₂], Iter [²⁸¹⁶⁄₃₁₂₅], train_loss:0.177022 Epoch [¹⁄₂], Iter [²⁸¹⁷⁄₃₁₂₅], train_loss:0.143955 Epoch [¹⁄₂], Iter [²⁸¹⁸⁄₃₁₂₅], train_loss:0.182202 Epoch [¹⁄₂], Iter [²⁸¹⁹⁄₃₁₂₅], train_loss:0.156804 Epoch [¹⁄₂], Iter [²⁸²⁰⁄₃₁₂₅], train_loss:0.158852 Epoch [¹⁄₂], Iter [²⁸²¹⁄₃₁₂₅], train_loss:0.159252 Epoch [¹⁄₂], Iter [²⁸²²⁄₃₁₂₅], train_loss:0.159138 Epoch [¹⁄₂], Iter [²⁸²³⁄₃₁₂₅], train_loss:0.158014 Epoch [¹⁄₂], Iter [²⁸²⁴⁄₃₁₂₅], train_loss:0.173861 Epoch [¹⁄₂], Iter [²⁸²⁵⁄₃₁₂₅], train_loss:0.163103 Epoch [¹⁄₂], Iter [²⁸²⁶⁄₃₁₂₅], train_loss:0.169961 Epoch [¹⁄₂], Iter [²⁸²⁷⁄₃₁₂₅], train_loss:0.160450 Epoch [¹⁄₂], Iter [²⁸²⁸⁄₃₁₂₅], train_loss:0.168754 Epoch [¹⁄₂], Iter [²⁸²⁹⁄₃₁₂₅], train_loss:0.145734 Epoch [¹⁄₂], Iter [²⁸³⁰⁄₃₁₂₅], train_loss:0.171105 Epoch [¹⁄₂], Iter [²⁸³¹⁄₃₁₂₅], train_loss:0.149704 Epoch [¹⁄₂], Iter [²⁸³²⁄₃₁₂₅], train_loss:0.157235 Epoch [¹⁄₂], Iter [²⁸³³⁄₃₁₂₅], train_loss:0.168647 Epoch [¹⁄₂], Iter [²⁸³⁴⁄₃₁₂₅], train_loss:0.170278 Epoch [¹⁄₂], Iter [²⁸³⁵⁄₃₁₂₅], train_loss:0.164118 Epoch [¹⁄₂], Iter [²⁸³⁶⁄₃₁₂₅], train_loss:0.160487 Epoch [¹⁄₂], Iter [²⁸³⁷⁄₃₁₂₅], train_loss:0.170349 Epoch [¹⁄₂], Iter [²⁸³⁸⁄₃₁₂₅], train_loss:0.153062 Epoch [¹⁄₂], Iter [²⁸³⁹⁄₃₁₂₅], train_loss:0.179919 Epoch [¹⁄₂], Iter [²⁸⁴⁰⁄₃₁₂₅], train_loss:0.165033 Epoch [¹⁄₂], Iter [²⁸⁴¹⁄₃₁₂₅], train_loss:0.159011 Epoch [¹⁄₂], Iter [²⁸⁴²⁄₃₁₂₅], train_loss:0.141699 Epoch [¹⁄₂], Iter [²⁸⁴³⁄₃₁₂₅], train_loss:0.155806 Epoch [¹⁄₂], Iter [²⁸⁴⁴⁄₃₁₂₅], train_loss:0.180037 Epoch [¹⁄₂], Iter [²⁸⁴⁵⁄₃₁₂₅], train_loss:0.172654 Epoch [¹⁄₂], Iter [²⁸⁴⁶⁄₃₁₂₅], train_loss:0.162126 Epoch [¹⁄₂], Iter [²⁸⁴⁷⁄₃₁₂₅], train_loss:0.174910 Epoch [¹⁄₂], Iter [²⁸⁴⁸⁄₃₁₂₅], train_loss:0.190180 Epoch [¹⁄₂], Iter [²⁸⁴⁹⁄₃₁₂₅], train_loss:0.167382 Epoch [¹⁄₂], Iter [²⁸⁵⁰⁄₃₁₂₅], train_loss:0.140893 Epoch [¹⁄₂], Iter [²⁸⁵¹⁄₃₁₂₅], train_loss:0.169695 Epoch [¹⁄₂], Iter [²⁸⁵²⁄₃₁₂₅], train_loss:0.149698 Epoch [¹⁄₂], Iter [²⁸⁵³⁄₃₁₂₅], train_loss:0.150947 Epoch [¹⁄₂], Iter [²⁸⁵⁴⁄₃₁₂₅], train_loss:0.160250 Epoch [¹⁄₂], Iter [²⁸⁵⁵⁄₃₁₂₅], train_loss:0.167571 Epoch [¹⁄₂], Iter [²⁸⁵⁶⁄₃₁₂₅], train_loss:0.158384 Epoch [¹⁄₂], Iter [²⁸⁵⁷⁄₃₁₂₅], train_loss:0.137086 Epoch [¹⁄₂], Iter [²⁸⁵⁸⁄₃₁₂₅], train_loss:0.177784 Epoch [¹⁄₂], Iter [²⁸⁵⁹⁄₃₁₂₅], train_loss:0.172647 Epoch [¹⁄₂], Iter [²⁸⁶⁰⁄₃₁₂₅], train_loss:0.169255 Epoch [¹⁄₂], Iter [²⁸⁶¹⁄₃₁₂₅], train_loss:0.169094 Epoch [¹⁄₂], Iter [²⁸⁶²⁄₃₁₂₅], train_loss:0.159690 Epoch [¹⁄₂], Iter [²⁸⁶³⁄₃₁₂₅], train_loss:0.162201 Epoch [¹⁄₂], Iter [²⁸⁶⁴⁄₃₁₂₅], train_loss:0.167594 Epoch [¹⁄₂], Iter [²⁸⁶⁵⁄₃₁₂₅], train_loss:0.167401 Epoch [¹⁄₂], Iter [²⁸⁶⁶⁄₃₁₂₅], train_loss:0.164989 Epoch [¹⁄₂], Iter [²⁸⁶⁷⁄₃₁₂₅], train_loss:0.138895 Epoch [¹⁄₂], Iter [²⁸⁶⁸⁄₃₁₂₅], train_loss:0.155665 Epoch [¹⁄₂], Iter [²⁸⁶⁹⁄₃₁₂₅], train_loss:0.178687 Epoch [¹⁄₂], Iter [²⁸⁷⁰⁄₃₁₂₅], train_loss:0.142473 Epoch [¹⁄₂], Iter [²⁸⁷¹⁄₃₁₂₅], train_loss:0.167332 Epoch [¹⁄₂], Iter [²⁸⁷²⁄₃₁₂₅], train_loss:0.179365 Epoch [¹⁄₂], Iter [²⁸⁷³⁄₃₁₂₅], train_loss:0.167223 Epoch [¹⁄₂], Iter [²⁸⁷⁴⁄₃₁₂₅], train_loss:0.178953 Epoch [¹⁄₂], Iter [²⁸⁷⁵⁄₃₁₂₅], train_loss:0.157346 Epoch [¹⁄₂], Iter [²⁸⁷⁶⁄₃₁₂₅], train_loss:0.182048 Epoch [¹⁄₂], Iter [²⁸⁷⁷⁄₃₁₂₅], train_loss:0.172396 Epoch [¹⁄₂], Iter [²⁸⁷⁸⁄₃₁₂₅], train_loss:0.175423 Epoch [¹⁄₂], Iter [²⁸⁷⁹⁄₃₁₂₅], train_loss:0.161872 Epoch [¹⁄₂], Iter [²⁸⁸⁰⁄₃₁₂₅], train_loss:0.169045 Epoch [¹⁄₂], Iter [²⁸⁸¹⁄₃₁₂₅], train_loss:0.169418 Epoch [¹⁄₂], Iter [²⁸⁸²⁄₃₁₂₅], train_loss:0.160182 Epoch [¹⁄₂], Iter [²⁸⁸³⁄₃₁₂₅], train_loss:0.186741 Epoch [¹⁄₂], Iter [²⁸⁸⁴⁄₃₁₂₅], train_loss:0.157193 Epoch [¹⁄₂], Iter [²⁸⁸⁵⁄₃₁₂₅], train_loss:0.138638 Epoch [¹⁄₂], Iter [²⁸⁸⁶⁄₃₁₂₅], train_loss:0.150510 Epoch [¹⁄₂], Iter [²⁸⁸⁷⁄₃₁₂₅], train_loss:0.176207 Epoch [¹⁄₂], Iter [²⁸⁸⁸⁄₃₁₂₅], train_loss:0.155249 Epoch [¹⁄₂], Iter [²⁸⁸⁹⁄₃₁₂₅], train_loss:0.159106 Epoch [¹⁄₂], Iter [²⁸⁹⁰⁄₃₁₂₅], train_loss:0.162412 Epoch [¹⁄₂], Iter [²⁸⁹¹⁄₃₁₂₅], train_loss:0.152091 Epoch [¹⁄₂], Iter [²⁸⁹²⁄₃₁₂₅], train_loss:0.176883 Epoch [¹⁄₂], Iter [²⁸⁹³⁄₃₁₂₅], train_loss:0.146511 Epoch [¹⁄₂], Iter [²⁸⁹⁴⁄₃₁₂₅], train_loss:0.163757 Epoch [¹⁄₂], Iter [²⁸⁹⁵⁄₃₁₂₅], train_loss:0.160787 Epoch [¹⁄₂], Iter [²⁸⁹⁶⁄₃₁₂₅], train_loss:0.160858 Epoch [¹⁄₂], Iter [²⁸⁹⁷⁄₃₁₂₅], train_loss:0.155350 Epoch [¹⁄₂], Iter [²⁸⁹⁸⁄₃₁₂₅], train_loss:0.169348 Epoch [¹⁄₂], Iter [²⁸⁹⁹⁄₃₁₂₅], train_loss:0.144282 Epoch [¹⁄₂], Iter [²⁹⁰⁰⁄₃₁₂₅], train_loss:0.167706 Epoch [¹⁄₂], Iter [²⁹⁰¹⁄₃₁₂₅], train_loss:0.182318 Epoch [¹⁄₂], Iter [²⁹⁰²⁄₃₁₂₅], train_loss:0.171248 Epoch [¹⁄₂], Iter [²⁹⁰³⁄₃₁₂₅], train_loss:0.165353 Epoch [¹⁄₂], Iter [²⁹⁰⁴⁄₃₁₂₅], train_loss:0.151637 Epoch [¹⁄₂], Iter [²⁹⁰⁵⁄₃₁₂₅], train_loss:0.161721 Epoch [¹⁄₂], Iter [²⁹⁰⁶⁄₃₁₂₅], train_loss:0.153006 Epoch [¹⁄₂], Iter [²⁹⁰⁷⁄₃₁₂₅], train_loss:0.161867 Epoch [¹⁄₂], Iter [²⁹⁰⁸⁄₃₁₂₅], train_loss:0.156607 Epoch [¹⁄₂], Iter [²⁹⁰⁹⁄₃₁₂₅], train_loss:0.178779 Epoch [¹⁄₂], Iter [²⁹¹⁰⁄₃₁₂₅], train_loss:0.192463 Epoch [¹⁄₂], Iter [²⁹¹¹⁄₃₁₂₅], train_loss:0.148583 Epoch [¹⁄₂], Iter [²⁹¹²⁄₃₁₂₅], train_loss:0.170696 Epoch [¹⁄₂], Iter [²⁹¹³⁄₃₁₂₅], train_loss:0.168631 Epoch [¹⁄₂], Iter [²⁹¹⁴⁄₃₁₂₅], train_loss:0.168608 Epoch [¹⁄₂], Iter [²⁹¹⁵⁄₃₁₂₅], train_loss:0.166084 Epoch [¹⁄₂], Iter [²⁹¹⁶⁄₃₁₂₅], train_loss:0.164468 Epoch [¹⁄₂], Iter [²⁹¹⁷⁄₃₁₂₅], train_loss:0.154483 Epoch [¹⁄₂], Iter [²⁹¹⁸⁄₃₁₂₅], train_loss:0.166607 Epoch [¹⁄₂], Iter [²⁹¹⁹⁄₃₁₂₅], train_loss:0.175541 Epoch [¹⁄₂], Iter [²⁹²⁰⁄₃₁₂₅], train_loss:0.146106 Epoch [¹⁄₂], Iter [²⁹²¹⁄₃₁₂₅], train_loss:0.186289 Epoch [¹⁄₂], Iter [²⁹²²⁄₃₁₂₅], train_loss:0.148206 Epoch [¹⁄₂], Iter [²⁹²³⁄₃₁₂₅], train_loss:0.180759 Epoch [¹⁄₂], Iter [²⁹²⁴⁄₃₁₂₅], train_loss:0.148458 Epoch [¹⁄₂], Iter [²⁹²⁵⁄₃₁₂₅], train_loss:0.153044 Epoch [¹⁄₂], Iter [²⁹²⁶⁄₃₁₂₅], train_loss:0.173843 Epoch [¹⁄₂], Iter [²⁹²⁷⁄₃₁₂₅], train_loss:0.173281 Epoch [¹⁄₂], Iter [²⁹²⁸⁄₃₁₂₅], train_loss:0.173701 Epoch [¹⁄₂], Iter [²⁹²⁹⁄₃₁₂₅], train_loss:0.165718 Epoch [¹⁄₂], Iter [²⁹³⁰⁄₃₁₂₅], train_loss:0.173092 Epoch [¹⁄₂], Iter [²⁹³¹⁄₃₁₂₅], train_loss:0.171520 Epoch [¹⁄₂], Iter [²⁹³²⁄₃₁₂₅], train_loss:0.148433 Epoch [¹⁄₂], Iter [²⁹³³⁄₃₁₂₅], train_loss:0.149291 Epoch [¹⁄₂], Iter [²⁹³⁴⁄₃₁₂₅], train_loss:0.173039 Epoch [¹⁄₂], Iter [²⁹³⁵⁄₃₁₂₅], train_loss:0.167303 Epoch [¹⁄₂], Iter [²⁹³⁶⁄₃₁₂₅], train_loss:0.148045 Epoch [¹⁄₂], Iter [²⁹³⁷⁄₃₁₂₅], train_loss:0.160600 Epoch [¹⁄₂], Iter [²⁹³⁸⁄₃₁₂₅], train_loss:0.175791 Epoch [¹⁄₂], Iter [²⁹³⁹⁄₃₁₂₅], train_loss:0.170290 Epoch [¹⁄₂], Iter [²⁹⁴⁰⁄₃₁₂₅], train_loss:0.168750 Epoch [¹⁄₂], Iter [²⁹⁴¹⁄₃₁₂₅], train_loss:0.174851 Epoch [¹⁄₂], Iter [²⁹⁴²⁄₃₁₂₅], train_loss:0.167067 Epoch [¹⁄₂], Iter [²⁹⁴³⁄₃₁₂₅], train_loss:0.147908 Epoch [¹⁄₂], Iter [²⁹⁴⁴⁄₃₁₂₅], train_loss:0.161702 Epoch [¹⁄₂], Iter [²⁹⁴⁵⁄₃₁₂₅], train_loss:0.166226 Epoch [¹⁄₂], Iter [²⁹⁴⁶⁄₃₁₂₅], train_loss:0.152965 Epoch [¹⁄₂], Iter [²⁹⁴⁷⁄₃₁₂₅], train_loss:0.151126 Epoch [¹⁄₂], Iter [²⁹⁴⁸⁄₃₁₂₅], train_loss:0.159228 Epoch [¹⁄₂], Iter [²⁹⁴⁹⁄₃₁₂₅], train_loss:0.147525 Epoch [¹⁄₂], Iter [²⁹⁵⁰⁄₃₁₂₅], train_loss:0.186010 Epoch [¹⁄₂], Iter [²⁹⁵¹⁄₃₁₂₅], train_loss:0.144456 Epoch [¹⁄₂], Iter [²⁹⁵²⁄₃₁₂₅], train_loss:0.144571 Epoch [¹⁄₂], Iter [²⁹⁵³⁄₃₁₂₅], train_loss:0.149504 Epoch [¹⁄₂], Iter [²⁹⁵⁴⁄₃₁₂₅], train_loss:0.155754 Epoch [¹⁄₂], Iter [²⁹⁵⁵⁄₃₁₂₅], train_loss:0.157044 Epoch [¹⁄₂], Iter [²⁹⁵⁶⁄₃₁₂₅], train_loss:0.164638 Epoch [¹⁄₂], Iter [²⁹⁵⁷⁄₃₁₂₅], train_loss:0.161717 Epoch [¹⁄₂], Iter [²⁹⁵⁸⁄₃₁₂₅], train_loss:0.150048 Epoch [¹⁄₂], Iter [²⁹⁵⁹⁄₃₁₂₅], train_loss:0.161040 Epoch [¹⁄₂], Iter [²⁹⁶⁰⁄₃₁₂₅], train_loss:0.147002 Epoch [¹⁄₂], Iter [²⁹⁶¹⁄₃₁₂₅], train_loss:0.168605 Epoch [¹⁄₂], Iter [²⁹⁶²⁄₃₁₂₅], train_loss:0.160989 Epoch [¹⁄₂], Iter [²⁹⁶³⁄₃₁₂₅], train_loss:0.179867 Epoch [¹⁄₂], Iter [²⁹⁶⁴⁄₃₁₂₅], train_loss:0.173219 Epoch [¹⁄₂], Iter [²⁹⁶⁵⁄₃₁₂₅], train_loss:0.166897 Epoch [¹⁄₂], Iter [²⁹⁶⁶⁄₃₁₂₅], train_loss:0.160661 Epoch [¹⁄₂], Iter [²⁹⁶⁷⁄₃₁₂₅], train_loss:0.161262 Epoch [¹⁄₂], Iter [²⁹⁶⁸⁄₃₁₂₅], train_loss:0.164723 Epoch [¹⁄₂], Iter [²⁹⁶⁹⁄₃₁₂₅], train_loss:0.142853 Epoch [¹⁄₂], Iter [²⁹⁷⁰⁄₃₁₂₅], train_loss:0.171715 Epoch [¹⁄₂], Iter [²⁹⁷¹⁄₃₁₂₅], train_loss:0.158447 Epoch [¹⁄₂], Iter [²⁹⁷²⁄₃₁₂₅], train_loss:0.164181 Epoch [¹⁄₂], Iter [²⁹⁷³⁄₃₁₂₅], train_loss:0.177048 Epoch [¹⁄₂], Iter [²⁹⁷⁴⁄₃₁₂₅], train_loss:0.167190 Epoch [¹⁄₂], Iter [²⁹⁷⁵⁄₃₁₂₅], train_loss:0.158204 Epoch [¹⁄₂], Iter [²⁹⁷⁶⁄₃₁₂₅], train_loss:0.151028 Epoch [¹⁄₂], Iter [²⁹⁷⁷⁄₃₁₂₅], train_loss:0.162853 Epoch [¹⁄₂], Iter [²⁹⁷⁸⁄₃₁₂₅], train_loss:0.165735 Epoch [¹⁄₂], Iter [²⁹⁷⁹⁄₃₁₂₅], train_loss:0.173848 Epoch [¹⁄₂], Iter [²⁹⁸⁰⁄₃₁₂₅], train_loss:0.149452 Epoch [¹⁄₂], Iter [²⁹⁸¹⁄₃₁₂₅], train_loss:0.152468 Epoch [¹⁄₂], Iter [²⁹⁸²⁄₃₁₂₅], train_loss:0.168138 Epoch [¹⁄₂], Iter [²⁹⁸³⁄₃₁₂₅], train_loss:0.163172 Epoch [¹⁄₂], Iter [²⁹⁸⁴⁄₃₁₂₅], train_loss:0.162576 Epoch [¹⁄₂], Iter [²⁹⁸⁵⁄₃₁₂₅], train_loss:0.188783 Epoch [¹⁄₂], Iter [²⁹⁸⁶⁄₃₁₂₅], train_loss:0.161452 Epoch [¹⁄₂], Iter [²⁹⁸⁷⁄₃₁₂₅], train_loss:0.136657 Epoch [¹⁄₂], Iter [²⁹⁸⁸⁄₃₁₂₅], train_loss:0.145196 Epoch [¹⁄₂], Iter [²⁹⁸⁹⁄₃₁₂₅], train_loss:0.183863 Epoch [¹⁄₂], Iter [²⁹⁹⁰⁄₃₁₂₅], train_loss:0.170865 Epoch [¹⁄₂], Iter [²⁹⁹¹⁄₃₁₂₅], train_loss:0.155084 Epoch [¹⁄₂], Iter [²⁹⁹²⁄₃₁₂₅], train_loss:0.175260 Epoch [¹⁄₂], Iter [²⁹⁹³⁄₃₁₂₅], train_loss:0.177893 Epoch [¹⁄₂], Iter [²⁹⁹⁴⁄₃₁₂₅], train_loss:0.171074 Epoch [¹⁄₂], Iter [²⁹⁹⁵⁄₃₁₂₅], train_loss:0.166262 Epoch [¹⁄₂], Iter [²⁹⁹⁶⁄₃₁₂₅], train_loss:0.168631 Epoch [¹⁄₂], Iter [²⁹⁹⁷⁄₃₁₂₅], train_loss:0.142343 Epoch [¹⁄₂], Iter [²⁹⁹⁸⁄₃₁₂₅], train_loss:0.176656 Epoch [¹⁄₂], Iter [²⁹⁹⁹⁄₃₁₂₅], train_loss:0.181024 Epoch [¹⁄₂], Iter [³⁰⁰⁰⁄₃₁₂₅], train_loss:0.164563 Epoch [¹⁄₂], Iter [³⁰⁰¹⁄₃₁₂₅], train_loss:0.181617 Epoch [¹⁄₂], Iter [³⁰⁰²⁄₃₁₂₅], train_loss:0.172865 Epoch [¹⁄₂], Iter [³⁰⁰³⁄₃₁₂₅], train_loss:0.179876 Epoch [¹⁄₂], Iter [³⁰⁰⁴⁄₃₁₂₅], train_loss:0.165719 Epoch [¹⁄₂], Iter [³⁰⁰⁵⁄₃₁₂₅], train_loss:0.177486 Epoch [¹⁄₂], Iter [³⁰⁰⁶⁄₃₁₂₅], train_loss:0.176950 Epoch [¹⁄₂], Iter [³⁰⁰⁷⁄₃₁₂₅], train_loss:0.178203 Epoch [¹⁄₂], Iter [³⁰⁰⁸⁄₃₁₂₅], train_loss:0.178196 Epoch [¹⁄₂], Iter [³⁰⁰⁹⁄₃₁₂₅], train_loss:0.171647 Epoch [¹⁄₂], Iter [³⁰¹⁰⁄₃₁₂₅], train_loss:0.173414 Epoch [¹⁄₂], Iter [³⁰¹¹⁄₃₁₂₅], train_loss:0.164811 Epoch [¹⁄₂], Iter [³⁰¹²⁄₃₁₂₅], train_loss:0.147020 Epoch [¹⁄₂], Iter [³⁰¹³⁄₃₁₂₅], train_loss:0.166289 Epoch [¹⁄₂], Iter [³⁰¹⁴⁄₃₁₂₅], train_loss:0.161090 Epoch [¹⁄₂], Iter [³⁰¹⁵⁄₃₁₂₅], train_loss:0.162289 Epoch [¹⁄₂], Iter [³⁰¹⁶⁄₃₁₂₅], train_loss:0.130393 Epoch [¹⁄₂], Iter [³⁰¹⁷⁄₃₁₂₅], train_loss:0.132035 Epoch [¹⁄₂], Iter [³⁰¹⁸⁄₃₁₂₅], train_loss:0.174404 Epoch [¹⁄₂], Iter [³⁰¹⁹⁄₃₁₂₅], train_loss:0.157980 Epoch [¹⁄₂], Iter [³⁰²⁰⁄₃₁₂₅], train_loss:0.158861 Epoch [¹⁄₂], Iter [³⁰²¹⁄₃₁₂₅], train_loss:0.182830 Epoch [¹⁄₂], Iter [³⁰²²⁄₃₁₂₅], train_loss:0.158150 Epoch [¹⁄₂], Iter [³⁰²³⁄₃₁₂₅], train_loss:0.156165 Epoch [¹⁄₂], Iter [³⁰²⁴⁄₃₁₂₅], train_loss:0.145425 Epoch [¹⁄₂], Iter [³⁰²⁵⁄₃₁₂₅], train_loss:0.176111 Epoch [¹⁄₂], Iter [³⁰²⁶⁄₃₁₂₅], train_loss:0.186718 Epoch [¹⁄₂], Iter [³⁰²⁷⁄₃₁₂₅], train_loss:0.150117 Epoch [¹⁄₂], Iter [³⁰²⁸⁄₃₁₂₅], train_loss:0.173456 Epoch [¹⁄₂], Iter [³⁰²⁹⁄₃₁₂₅], train_loss:0.156002 Epoch [¹⁄₂], Iter [³⁰³⁰⁄₃₁₂₅], train_loss:0.175069 Epoch [¹⁄₂], Iter [³⁰³¹⁄₃₁₂₅], train_loss:0.150203 Epoch [¹⁄₂], Iter [³⁰³²⁄₃₁₂₅], train_loss:0.170119 Epoch [¹⁄₂], Iter [³⁰³³⁄₃₁₂₅], train_loss:0.161877 Epoch [¹⁄₂], Iter [³⁰³⁴⁄₃₁₂₅], train_loss:0.154505 Epoch [¹⁄₂], Iter [³⁰³⁵⁄₃₁₂₅], train_loss:0.170968 Epoch [¹⁄₂], Iter [³⁰³⁶⁄₃₁₂₅], train_loss:0.143941 Epoch [¹⁄₂], Iter [³⁰³⁷⁄₃₁₂₅], train_loss:0.171731 Epoch [¹⁄₂], Iter [³⁰³⁸⁄₃₁₂₅], train_loss:0.150052 Epoch [¹⁄₂], Iter [³⁰³⁹⁄₃₁₂₅], train_loss:0.155370 Epoch [¹⁄₂], Iter [³⁰⁴⁰⁄₃₁₂₅], train_loss:0.154070 Epoch [¹⁄₂], Iter [³⁰⁴¹⁄₃₁₂₅], train_loss:0.169434 Epoch [¹⁄₂], Iter [³⁰⁴²⁄₃₁₂₅], train_loss:0.153931 Epoch [¹⁄₂], Iter [³⁰⁴³⁄₃₁₂₅], train_loss:0.167334 Epoch [¹⁄₂], Iter [³⁰⁴⁴⁄₃₁₂₅], train_loss:0.160416 Epoch [¹⁄₂], Iter [³⁰⁴⁵⁄₃₁₂₅], train_loss:0.161101 Epoch [¹⁄₂], Iter [³⁰⁴⁶⁄₃₁₂₅], train_loss:0.153652 Epoch [¹⁄₂], Iter [³⁰⁴⁷⁄₃₁₂₅], train_loss:0.166452 Epoch [¹⁄₂], Iter [³⁰⁴⁸⁄₃₁₂₅], train_loss:0.148719 Epoch [¹⁄₂], Iter [³⁰⁴⁹⁄₃₁₂₅], train_loss:0.153907 Epoch [¹⁄₂], Iter [³⁰⁵⁰⁄₃₁₂₅], train_loss:0.165748 Epoch [¹⁄₂], Iter [³⁰⁵¹⁄₃₁₂₅], train_loss:0.177738 Epoch [¹⁄₂], Iter [³⁰⁵²⁄₃₁₂₅], train_loss:0.162658 Epoch [¹⁄₂], Iter [³⁰⁵³⁄₃₁₂₅], train_loss:0.157725 Epoch [¹⁄₂], Iter [³⁰⁵⁴⁄₃₁₂₅], train_loss:0.168763 Epoch [¹⁄₂], Iter [³⁰⁵⁵⁄₃₁₂₅], train_loss:0.169479 Epoch [¹⁄₂], Iter [³⁰⁵⁶⁄₃₁₂₅], train_loss:0.160464 Epoch [¹⁄₂], Iter [³⁰⁵⁷⁄₃₁₂₅], train_loss:0.165181 Epoch [¹⁄₂], Iter [³⁰⁵⁸⁄₃₁₂₅], train_loss:0.158833 Epoch [¹⁄₂], Iter [³⁰⁵⁹⁄₃₁₂₅], train_loss:0.174259 Epoch [¹⁄₂], Iter [³⁰⁶⁰⁄₃₁₂₅], train_loss:0.197122 Epoch [¹⁄₂], Iter [³⁰⁶¹⁄₃₁₂₅], train_loss:0.157540 Epoch [¹⁄₂], Iter [³⁰⁶²⁄₃₁₂₅], train_loss:0.153574 Epoch [¹⁄₂], Iter [³⁰⁶³⁄₃₁₂₅], train_loss:0.158650 Epoch [¹⁄₂], Iter [³⁰⁶⁴⁄₃₁₂₅], train_loss:0.159368 Epoch [¹⁄₂], Iter [³⁰⁶⁵⁄₃₁₂₅], train_loss:0.126841 Epoch [¹⁄₂], Iter [³⁰⁶⁶⁄₃₁₂₅], train_loss:0.190723 Epoch [¹⁄₂], Iter [³⁰⁶⁷⁄₃₁₂₅], train_loss:0.161133 Epoch [¹⁄₂], Iter [³⁰⁶⁸⁄₃₁₂₅], train_loss:0.147794 Epoch [¹⁄₂], Iter [³⁰⁶⁹⁄₃₁₂₅], train_loss:0.154277 Epoch [¹⁄₂], Iter [³⁰⁷⁰⁄₃₁₂₅], train_loss:0.160044 Epoch [¹⁄₂], Iter [³⁰⁷¹⁄₃₁₂₅], train_loss:0.157531 Epoch [¹⁄₂], Iter [³⁰⁷²⁄₃₁₂₅], train_loss:0.168389 Epoch [¹⁄₂], Iter [³⁰⁷³⁄₃₁₂₅], train_loss:0.172469 Epoch [¹⁄₂], Iter [³⁰⁷⁴⁄₃₁₂₅], train_loss:0.155994 Epoch [¹⁄₂], Iter [³⁰⁷⁵⁄₃₁₂₅], train_loss:0.147720 Epoch [¹⁄₂], Iter [³⁰⁷⁶⁄₃₁₂₅], train_loss:0.137509 Epoch [¹⁄₂], Iter [³⁰⁷⁷⁄₃₁₂₅], train_loss:0.181711 Epoch [¹⁄₂], Iter [³⁰⁷⁸⁄₃₁₂₅], train_loss:0.177348 Epoch [¹⁄₂], Iter [³⁰⁷⁹⁄₃₁₂₅], train_loss:0.148808 Epoch [¹⁄₂], Iter [³⁰⁸⁰⁄₃₁₂₅], train_loss:0.175595 Epoch [¹⁄₂], Iter [³⁰⁸¹⁄₃₁₂₅], train_loss:0.165768 Epoch [¹⁄₂], Iter [³⁰⁸²⁄₃₁₂₅], train_loss:0.142488 Epoch [¹⁄₂], Iter [³⁰⁸³⁄₃₁₂₅], train_loss:0.147224 Epoch [¹⁄₂], Iter [³⁰⁸⁴⁄₃₁₂₅], train_loss:0.168570 Epoch [¹⁄₂], Iter [³⁰⁸⁵⁄₃₁₂₅], train_loss:0.155916 Epoch [¹⁄₂], Iter [³⁰⁸⁶⁄₃₁₂₅], train_loss:0.169448 Epoch [¹⁄₂], Iter [³⁰⁸⁷⁄₃₁₂₅], train_loss:0.148978 Epoch [¹⁄₂], Iter [³⁰⁸⁸⁄₃₁₂₅], train_loss:0.158718 Epoch [¹⁄₂], Iter [³⁰⁸⁹⁄₃₁₂₅], train_loss:0.139569 Epoch [¹⁄₂], Iter [³⁰⁹⁰⁄₃₁₂₅], train_loss:0.179602 Epoch [¹⁄₂], Iter [³⁰⁹¹⁄₃₁₂₅], train_loss:0.172581 Epoch [¹⁄₂], Iter [³⁰⁹²⁄₃₁₂₅], train_loss:0.172989 Epoch [¹⁄₂], Iter [³⁰⁹³⁄₃₁₂₅], train_loss:0.174835 Epoch [¹⁄₂], Iter [³⁰⁹⁴⁄₃₁₂₅], train_loss:0.162024 Epoch [¹⁄₂], Iter [³⁰⁹⁵⁄₃₁₂₅], train_loss:0.149372 Epoch [¹⁄₂], Iter [³⁰⁹⁶⁄₃₁₂₅], train_loss:0.182143 Epoch [¹⁄₂], Iter [³⁰⁹⁷⁄₃₁₂₅], train_loss:0.173537 Epoch [¹⁄₂], Iter [³⁰⁹⁸⁄₃₁₂₅], train_loss:0.180467 Epoch [¹⁄₂], Iter [³⁰⁹⁹⁄₃₁₂₅], train_loss:0.138658 Epoch [¹⁄₂], Iter [³¹⁰⁰⁄₃₁₂₅], train_loss:0.167943 Epoch [¹⁄₂], Iter [³¹⁰¹⁄₃₁₂₅], train_loss:0.179498 Epoch [¹⁄₂], Iter [³¹⁰²⁄₃₁₂₅], train_loss:0.168319 Epoch [¹⁄₂], Iter [³¹⁰³⁄₃₁₂₅], train_loss:0.159227 Epoch [¹⁄₂], Iter [³¹⁰⁴⁄₃₁₂₅], train_loss:0.143851 Epoch [¹⁄₂], Iter [³¹⁰⁵⁄₃₁₂₅], train_loss:0.162043 Epoch [¹⁄₂], Iter [³¹⁰⁶⁄₃₁₂₅], train_loss:0.173713 Epoch [¹⁄₂], Iter [³¹⁰⁷⁄₃₁₂₅], train_loss:0.160019 Epoch [¹⁄₂], Iter [³¹⁰⁸⁄₃₁₂₅], train_loss:0.187196 Epoch [¹⁄₂], Iter [³¹⁰⁹⁄₃₁₂₅], train_loss:0.178457 Epoch [¹⁄₂], Iter [³¹¹⁰⁄₃₁₂₅], train_loss:0.166758 Epoch [¹⁄₂], Iter [³¹¹¹⁄₃₁₂₅], train_loss:0.162495 Epoch [¹⁄₂], Iter [³¹¹²⁄₃₁₂₅], train_loss:0.144868 Epoch [¹⁄₂], Iter [³¹¹³⁄₃₁₂₅], train_loss:0.170601 Epoch [¹⁄₂], Iter [³¹¹⁴⁄₃₁₂₅], train_loss:0.152794 Epoch [¹⁄₂], Iter [³¹¹⁵⁄₃₁₂₅], train_loss:0.166172 Epoch [¹⁄₂], Iter [³¹¹⁶⁄₃₁₂₅], train_loss:0.150413 Epoch [¹⁄₂], Iter [³¹¹⁷⁄₃₁₂₅], train_loss:0.146555 Epoch [¹⁄₂], Iter [³¹¹⁸⁄₃₁₂₅], train_loss:0.158817 Epoch [¹⁄₂], Iter [³¹¹⁹⁄₃₁₂₅], train_loss:0.179008 Epoch [¹⁄₂], Iter [³¹²⁰⁄₃₁₂₅], train_loss:0.183372 Epoch [¹⁄₂], Iter [³¹²¹⁄₃₁₂₅], train_loss:0.165688 Epoch [¹⁄₂], Iter [³¹²²⁄₃₁₂₅], train_loss:0.151766 Epoch [¹⁄₂], Iter [³¹²³⁄₃₁₂₅], train_loss:0.147575 Epoch [¹⁄₂], Iter [³¹²⁴⁄₃₁₂₅], train_loss:0.140461 Epoch [¹⁄₂], Iter [³¹²⁵⁄₃₁₂₅], train_loss:0.166029 Epoch [¹⁄₂], train_loss:0.1625, train_acc:9.7080%, test_loss:0.1695, test_acc:10.6200% Epoch [²⁄₂], Iter [¹⁄₃₁₂₅], train_loss:0.146202 Epoch [²⁄₂], Iter [²⁄₃₁₂₅], train_loss:0.173672 Epoch [²⁄₂], Iter [³⁄₃₁₂₅], train_loss:0.165151 Epoch [²⁄₂], Iter [⁴⁄₃₁₂₅], train_loss:0.158770 Epoch [²⁄₂], Iter [⁵⁄₃₁₂₅], train_loss:0.175999 Epoch [²⁄₂], Iter [⁶⁄₃₁₂₅], train_loss:0.163998 Epoch [²⁄₂], Iter [⁷⁄₃₁₂₅], train_loss:0.165410 Epoch [²⁄₂], Iter [⁸⁄₃₁₂₅], train_loss:0.161637 Epoch [²⁄₂], Iter [⁹⁄₃₁₂₅], train_loss:0.148239 Epoch [²⁄₂], Iter [¹⁰⁄₃₁₂₅], train_loss:0.162426 Epoch [²⁄₂], Iter [¹¹⁄₃₁₂₅], train_loss:0.168900 Epoch [²⁄₂], Iter [¹²⁄₃₁₂₅], train_loss:0.149848 Epoch [²⁄₂], Iter [¹³⁄₃₁₂₅], train_loss:0.147608 Epoch [²⁄₂], Iter [¹⁴⁄₃₁₂₅], train_loss:0.160673 Epoch [²⁄₂], Iter [¹⁵⁄₃₁₂₅], train_loss:0.172021 Epoch [²⁄₂], Iter [¹⁶⁄₃₁₂₅], train_loss:0.162101 Epoch [²⁄₂], Iter [¹⁷⁄₃₁₂₅], train_loss:0.150480 Epoch [²⁄₂], Iter [¹⁸⁄₃₁₂₅], train_loss:0.154776 Epoch [²⁄₂], Iter [¹⁹⁄₃₁₂₅], train_loss:0.163754 Epoch [²⁄₂], Iter [²⁰⁄₃₁₂₅], train_loss:0.177525 Epoch [²⁄₂], Iter [²¹⁄₃₁₂₅], train_loss:0.168097 Epoch [²⁄₂], Iter [²²⁄₃₁₂₅], train_loss:0.156192 Epoch [²⁄₂], Iter [²³⁄₃₁₂₅], train_loss:0.166126 Epoch [²⁄₂], Iter [²⁴⁄₃₁₂₅], train_loss:0.147863 Epoch [²⁄₂], Iter [²⁵⁄₃₁₂₅], train_loss:0.176202 Epoch [²⁄₂], Iter [²⁶⁄₃₁₂₅], train_loss:0.159570 Epoch [²⁄₂], Iter [²⁷⁄₃₁₂₅], train_loss:0.168702 Epoch [²⁄₂], Iter [²⁸⁄₃₁₂₅], train_loss:0.151392 Epoch [²⁄₂], Iter [²⁹⁄₃₁₂₅], train_loss:0.162362 Epoch [²⁄₂], Iter [³⁰⁄₃₁₂₅], train_loss:0.147167 Epoch [²⁄₂], Iter [³¹⁄₃₁₂₅], train_loss:0.155992 Epoch [²⁄₂], Iter [³²⁄₃₁₂₅], train_loss:0.143932 Epoch [²⁄₂], Iter [³³⁄₃₁₂₅], train_loss:0.167568 Epoch [²⁄₂], Iter [³⁴⁄₃₁₂₅], train_loss:0.156876 Epoch [²⁄₂], Iter [³⁵⁄₃₁₂₅], train_loss:0.149783 Epoch [²⁄₂], Iter [³⁶⁄₃₁₂₅], train_loss:0.184439 Epoch [²⁄₂], Iter [³⁷⁄₃₁₂₅], train_loss:0.162946 Epoch [²⁄₂], Iter [³⁸⁄₃₁₂₅], train_loss:0.148541 Epoch [²⁄₂], Iter [³⁹⁄₃₁₂₅], train_loss:0.165627 Epoch [²⁄₂], Iter [⁴⁰⁄₃₁₂₅], train_loss:0.169342 Epoch [²⁄₂], Iter [⁴¹⁄₃₁₂₅], train_loss:0.165507 Epoch [²⁄₂], Iter [⁴²⁄₃₁₂₅], train_loss:0.166825 Epoch [²⁄₂], Iter [⁴³⁄₃₁₂₅], train_loss:0.180178 Epoch [²⁄₂], Iter [⁴⁴⁄₃₁₂₅], train_loss:0.174066 Epoch [²⁄₂], Iter [⁴⁵⁄₃₁₂₅], train_loss:0.175319 Epoch [²⁄₂], Iter [⁴⁶⁄₃₁₂₅], train_loss:0.159672 Epoch [²⁄₂], Iter [⁴⁷⁄₃₁₂₅], train_loss:0.155855 Epoch [²⁄₂], Iter [⁴⁸⁄₃₁₂₅], train_loss:0.166862 Epoch [²⁄₂], Iter [⁴⁹⁄₃₁₂₅], train_loss:0.157197 Epoch [²⁄₂], Iter [⁵⁰⁄₃₁₂₅], train_loss:0.154708 Epoch [²⁄₂], Iter [⁵¹⁄₃₁₂₅], train_loss:0.169141 Epoch [²⁄₂], Iter [⁵²⁄₃₁₂₅], train_loss:0.189146 Epoch [²⁄₂], Iter [⁵³⁄₃₁₂₅], train_loss:0.147940 Epoch [²⁄₂], Iter [⁵⁴⁄₃₁₂₅], train_loss:0.173229 Epoch [²⁄₂], Iter [⁵⁵⁄₃₁₂₅], train_loss:0.147851 Epoch [²⁄₂], Iter [⁵⁶⁄₃₁₂₅], train_loss:0.166568 Epoch [²⁄₂], Iter [⁵⁷⁄₃₁₂₅], train_loss:0.157517 Epoch [²⁄₂], Iter [⁵⁸⁄₃₁₂₅], train_loss:0.157088 Epoch [²⁄₂], Iter [⁵⁹⁄₃₁₂₅], train_loss:0.170904 Epoch [²⁄₂], Iter [⁶⁰⁄₃₁₂₅], train_loss:0.130077 Epoch [²⁄₂], Iter [⁶¹⁄₃₁₂₅], train_loss:0.162462 Epoch [²⁄₂], Iter [⁶²⁄₃₁₂₅], train_loss:0.167202 Epoch [²⁄₂], Iter [⁶³⁄₃₁₂₅], train_loss:0.144449 Epoch [²⁄₂], Iter [⁶⁴⁄₃₁₂₅], train_loss:0.147543 Epoch [²⁄₂], Iter [⁶⁵⁄₃₁₂₅], train_loss:0.178345 Epoch [²⁄₂], Iter [⁶⁶⁄₃₁₂₅], train_loss:0.171756 Epoch [²⁄₂], Iter [⁶⁷⁄₃₁₂₅], train_loss:0.182125 Epoch [²⁄₂], Iter [⁶⁸⁄₃₁₂₅], train_loss:0.163568 Epoch [²⁄₂], Iter [⁶⁹⁄₃₁₂₅], train_loss:0.168720 Epoch [²⁄₂], Iter [⁷⁰⁄₃₁₂₅], train_loss:0.166233 Epoch [²⁄₂], Iter [⁷¹⁄₃₁₂₅], train_loss:0.165497 Epoch [²⁄₂], Iter [⁷²⁄₃₁₂₅], train_loss:0.158568 Epoch [²⁄₂], Iter [⁷³⁄₃₁₂₅], train_loss:0.158017 Epoch [²⁄₂], Iter [⁷⁴⁄₃₁₂₅], train_loss:0.146704 Epoch [²⁄₂], Iter [⁷⁵⁄₃₁₂₅], train_loss:0.168960 Epoch [²⁄₂], Iter [⁷⁶⁄₃₁₂₅], train_loss:0.176339 Epoch [²⁄₂], Iter [⁷⁷⁄₃₁₂₅], train_loss:0.157601 Epoch [²⁄₂], Iter [⁷⁸⁄₃₁₂₅], train_loss:0.150234 Epoch [²⁄₂], Iter [⁷⁹⁄₃₁₂₅], train_loss:0.171131 Epoch [²⁄₂], Iter [⁸⁰⁄₃₁₂₅], train_loss:0.168470 Epoch [²⁄₂], Iter [⁸¹⁄₃₁₂₅], train_loss:0.165504 Epoch [²⁄₂], Iter [⁸²⁄₃₁₂₅], train_loss:0.182929 Epoch [²⁄₂], Iter [⁸³⁄₃₁₂₅], train_loss:0.149121 Epoch [²⁄₂], Iter [⁸⁴⁄₃₁₂₅], train_loss:0.170251 Epoch [²⁄₂], Iter [⁸⁵⁄₃₁₂₅], train_loss:0.176452 Epoch [²⁄₂], Iter [⁸⁶⁄₃₁₂₅], train_loss:0.163143 Epoch [²⁄₂], Iter [⁸⁷⁄₃₁₂₅], train_loss:0.149888 Epoch [²⁄₂], Iter [⁸⁸⁄₃₁₂₅], train_loss:0.158223 Epoch [²⁄₂], Iter [⁸⁹⁄₃₁₂₅], train_loss:0.165219 Epoch [²⁄₂], Iter [⁹⁰⁄₃₁₂₅], train_loss:0.175566 Epoch [²⁄₂], Iter [⁹¹⁄₃₁₂₅], train_loss:0.172680 Epoch [²⁄₂], Iter [⁹²⁄₃₁₂₅], train_loss:0.157610 Epoch [²⁄₂], Iter [⁹³⁄₃₁₂₅], train_loss:0.149683 Epoch [²⁄₂], Iter [⁹⁴⁄₃₁₂₅], train_loss:0.150491 Epoch [²⁄₂], Iter [⁹⁵⁄₃₁₂₅], train_loss:0.143823 Epoch [²⁄₂], Iter [⁹⁶⁄₃₁₂₅], train_loss:0.147380 Epoch [²⁄₂], Iter [⁹⁷⁄₃₁₂₅], train_loss:0.162991 Epoch [²⁄₂], Iter [⁹⁸⁄₃₁₂₅], train_loss:0.142088 Epoch [²⁄₂], Iter [⁹⁹⁄₃₁₂₅], train_loss:0.165098 Epoch [²⁄₂], Iter [¹⁰⁰⁄₃₁₂₅], train_loss:0.142414 Epoch [²⁄₂], Iter [¹⁰¹⁄₃₁₂₅], train_loss:0.171030 Epoch [²⁄₂], Iter [¹⁰²⁄₃₁₂₅], train_loss:0.164070 Epoch [²⁄₂], Iter [¹⁰³⁄₃₁₂₅], train_loss:0.155812 Epoch [²⁄₂], Iter [¹⁰⁴⁄₃₁₂₅], train_loss:0.166394 Epoch [²⁄₂], Iter [¹⁰⁵⁄₃₁₂₅], train_loss:0.162388 Epoch [²⁄₂], Iter [¹⁰⁶⁄₃₁₂₅], train_loss:0.156700 Epoch [²⁄₂], Iter [¹⁰⁷⁄₃₁₂₅], train_loss:0.153787 Epoch [²⁄₂], Iter [¹⁰⁸⁄₃₁₂₅], train_loss:0.146724 Epoch [²⁄₂], Iter [¹⁰⁹⁄₃₁₂₅], train_loss:0.146993 Epoch [²⁄₂], Iter [¹¹⁰⁄₃₁₂₅], train_loss:0.161078 Epoch [²⁄₂], Iter [¹¹¹⁄₃₁₂₅], train_loss:0.141862 Epoch [²⁄₂], Iter [¹¹²⁄₃₁₂₅], train_loss:0.164413 Epoch [²⁄₂], Iter [¹¹³⁄₃₁₂₅], train_loss:0.172509 Epoch [²⁄₂], Iter [¹¹⁴⁄₃₁₂₅], train_loss:0.133704 Epoch [²⁄₂], Iter [¹¹⁵⁄₃₁₂₅], train_loss:0.156570 Epoch [²⁄₂], Iter [¹¹⁶⁄₃₁₂₅], train_loss:0.149274 Epoch [²⁄₂], Iter [¹¹⁷⁄₃₁₂₅], train_loss:0.172428 Epoch [²⁄₂], Iter [¹¹⁸⁄₃₁₂₅], train_loss:0.158011 Epoch [²⁄₂], Iter [¹¹⁹⁄₃₁₂₅], train_loss:0.180269 Epoch [²⁄₂], Iter [¹²⁰⁄₃₁₂₅], train_loss:0.133947 Epoch [²⁄₂], Iter [¹²¹⁄₃₁₂₅], train_loss:0.160919 Epoch [²⁄₂], Iter [¹²²⁄₃₁₂₅], train_loss:0.160910 Epoch [²⁄₂], Iter [¹²³⁄₃₁₂₅], train_loss:0.156073 Epoch [²⁄₂], Iter [¹²⁴⁄₃₁₂₅], train_loss:0.170647 Epoch [²⁄₂], Iter [¹²⁵⁄₃₁₂₅], train_loss:0.168909 Epoch [²⁄₂], Iter [¹²⁶⁄₃₁₂₅], train_loss:0.163942 Epoch [²⁄₂], Iter [¹²⁷⁄₃₁₂₅], train_loss:0.185147 Epoch [²⁄₂], Iter [¹²⁸⁄₃₁₂₅], train_loss:0.147694 Epoch [²⁄₂], Iter [¹²⁹⁄₃₁₂₅], train_loss:0.154867 Epoch [²⁄₂], Iter [¹³⁰⁄₃₁₂₅], train_loss:0.156400 Epoch [²⁄₂], Iter [¹³¹⁄₃₁₂₅], train_loss:0.159859 Epoch [²⁄₂], Iter [¹³²⁄₃₁₂₅], train_loss:0.163676 Epoch [²⁄₂], Iter [¹³³⁄₃₁₂₅], train_loss:0.164885 Epoch [²⁄₂], Iter [¹³⁴⁄₃₁₂₅], train_loss:0.157290 Epoch [²⁄₂], Iter [¹³⁵⁄₃₁₂₅], train_loss:0.153076 Epoch [²⁄₂], Iter [¹³⁶⁄₃₁₂₅], train_loss:0.170953 Epoch [²⁄₂], Iter [¹³⁷⁄₃₁₂₅], train_loss:0.161285 Epoch [²⁄₂], Iter [¹³⁸⁄₃₁₂₅], train_loss:0.176708 Epoch [²⁄₂], Iter [¹³⁹⁄₃₁₂₅], train_loss:0.164216 Epoch [²⁄₂], Iter [¹⁴⁰⁄₃₁₂₅], train_loss:0.157998 Epoch [²⁄₂], Iter [¹⁴¹⁄₃₁₂₅], train_loss:0.161874 Epoch [²⁄₂], Iter [¹⁴²⁄₃₁₂₅], train_loss:0.165788 Epoch [²⁄₂], Iter [¹⁴³⁄₃₁₂₅], train_loss:0.147918 Epoch [²⁄₂], Iter [¹⁴⁴⁄₃₁₂₅], train_loss:0.168310 Epoch [²⁄₂], Iter [¹⁴⁵⁄₃₁₂₅], train_loss:0.157749 Epoch [²⁄₂], Iter [¹⁴⁶⁄₃₁₂₅], train_loss:0.170075 Epoch [²⁄₂], Iter [¹⁴⁷⁄₃₁₂₅], train_loss:0.162752 Epoch [²⁄₂], Iter [¹⁴⁸⁄₃₁₂₅], train_loss:0.170934 Epoch [²⁄₂], Iter [¹⁴⁹⁄₃₁₂₅], train_loss:0.184253 Epoch [²⁄₂], Iter [¹⁵⁰⁄₃₁₂₅], train_loss:0.178670 Epoch [²⁄₂], Iter [¹⁵¹⁄₃₁₂₅], train_loss:0.168679 Epoch [²⁄₂], Iter [¹⁵²⁄₃₁₂₅], train_loss:0.175516 Epoch [²⁄₂], Iter [¹⁵³⁄₃₁₂₅], train_loss:0.155538 Epoch [²⁄₂], Iter [¹⁵⁴⁄₃₁₂₅], train_loss:0.161324 Epoch [²⁄₂], Iter [¹⁵⁵⁄₃₁₂₅], train_loss:0.156795 Epoch [²⁄₂], Iter [¹⁵⁶⁄₃₁₂₅], train_loss:0.154852 Epoch [²⁄₂], Iter [¹⁵⁷⁄₃₁₂₅], train_loss:0.156921 Epoch [²⁄₂], Iter [¹⁵⁸⁄₃₁₂₅], train_loss:0.163482 Epoch [²⁄₂], Iter [¹⁵⁹⁄₃₁₂₅], train_loss:0.173362 Epoch [²⁄₂], Iter [¹⁶⁰⁄₃₁₂₅], train_loss:0.167319 Epoch [²⁄₂], Iter [¹⁶¹⁄₃₁₂₅], train_loss:0.173615 Epoch [²⁄₂], Iter [¹⁶²⁄₃₁₂₅], train_loss:0.160354 Epoch [²⁄₂], Iter [¹⁶³⁄₃₁₂₅], train_loss:0.167696 Epoch [²⁄₂], Iter [¹⁶⁴⁄₃₁₂₅], train_loss:0.161250 Epoch [²⁄₂], Iter [¹⁶⁵⁄₃₁₂₅], train_loss:0.160384 Epoch [²⁄₂], Iter [¹⁶⁶⁄₃₁₂₅], train_loss:0.164563 Epoch [²⁄₂], Iter [¹⁶⁷⁄₃₁₂₅], train_loss:0.161137 Epoch [²⁄₂], Iter [¹⁶⁸⁄₃₁₂₅], train_loss:0.169574 Epoch [²⁄₂], Iter [¹⁶⁹⁄₃₁₂₅], train_loss:0.175531 Epoch [²⁄₂], Iter [¹⁷⁰⁄₃₁₂₅], train_loss:0.169590 Epoch [²⁄₂], Iter [¹⁷¹⁄₃₁₂₅], train_loss:0.157394 Epoch [²⁄₂], Iter [¹⁷²⁄₃₁₂₅], train_loss:0.156446 Epoch [²⁄₂], Iter [¹⁷³⁄₃₁₂₅], train_loss:0.176099 Epoch [²⁄₂], Iter [¹⁷⁴⁄₃₁₂₅], train_loss:0.169188 Epoch [²⁄₂], Iter [¹⁷⁵⁄₃₁₂₅], train_loss:0.181089 Epoch [²⁄₂], Iter [¹⁷⁶⁄₃₁₂₅], train_loss:0.157710 Epoch [²⁄₂], Iter [¹⁷⁷⁄₃₁₂₅], train_loss:0.154907 Epoch [²⁄₂], Iter [¹⁷⁸⁄₃₁₂₅], train_loss:0.139118 Epoch [²⁄₂], Iter [¹⁷⁹⁄₃₁₂₅], train_loss:0.148639 Epoch [²⁄₂], Iter [¹⁸⁰⁄₃₁₂₅], train_loss:0.149552 Epoch [²⁄₂], Iter [¹⁸¹⁄₃₁₂₅], train_loss:0.181338 Epoch [²⁄₂], Iter [¹⁸²⁄₃₁₂₅], train_loss:0.162902 Epoch [²⁄₂], Iter [¹⁸³⁄₃₁₂₅], train_loss:0.173415 Epoch [²⁄₂], Iter [¹⁸⁴⁄₃₁₂₅], train_loss:0.163751 Epoch [²⁄₂], Iter [¹⁸⁵⁄₃₁₂₅], train_loss:0.148597 Epoch [²⁄₂], Iter [¹⁸⁶⁄₃₁₂₅], train_loss:0.174917 Epoch [²⁄₂], Iter [¹⁸⁷⁄₃₁₂₅], train_loss:0.182508 Epoch [²⁄₂], Iter [¹⁸⁸⁄₃₁₂₅], train_loss:0.152830 Epoch [²⁄₂], Iter [¹⁸⁹⁄₃₁₂₅], train_loss:0.153870 Epoch [²⁄₂], Iter [¹⁹⁰⁄₃₁₂₅], train_loss:0.163149 Epoch [²⁄₂], Iter [¹⁹¹⁄₃₁₂₅], train_loss:0.148616 Epoch [²⁄₂], Iter [¹⁹²⁄₃₁₂₅], train_loss:0.148913 Epoch [²⁄₂], Iter [¹⁹³⁄₃₁₂₅], train_loss:0.187292 Epoch [²⁄₂], Iter [¹⁹⁴⁄₃₁₂₅], train_loss:0.163163 Epoch [²⁄₂], Iter [¹⁹⁵⁄₃₁₂₅], train_loss:0.157831 Epoch [²⁄₂], Iter [¹⁹⁶⁄₃₁₂₅], train_loss:0.183797 Epoch [²⁄₂], Iter [¹⁹⁷⁄₃₁₂₅], train_loss:0.171313 Epoch [²⁄₂], Iter [¹⁹⁸⁄₃₁₂₅], train_loss:0.157854 Epoch [²⁄₂], Iter [¹⁹⁹⁄₃₁₂₅], train_loss:0.162880 Epoch [²⁄₂], Iter [²⁰⁰⁄₃₁₂₅], train_loss:0.176139 Epoch [²⁄₂], Iter [²⁰¹⁄₃₁₂₅], train_loss:0.170941 Epoch [²⁄₂], Iter [²⁰²⁄₃₁₂₅], train_loss:0.177162 Epoch [²⁄₂], Iter [²⁰³⁄₃₁₂₅], train_loss:0.150648 Epoch [²⁄₂], Iter [²⁰⁴⁄₃₁₂₅], train_loss:0.171486 Epoch [²⁄₂], Iter [²⁰⁵⁄₃₁₂₅], train_loss:0.150289 Epoch [²⁄₂], Iter [²⁰⁶⁄₃₁₂₅], train_loss:0.168230 Epoch [²⁄₂], Iter [²⁰⁷⁄₃₁₂₅], train_loss:0.163843 Epoch [²⁄₂], Iter [²⁰⁸⁄₃₁₂₅], train_loss:0.162255 Epoch [²⁄₂], Iter [²⁰⁹⁄₃₁₂₅], train_loss:0.162224 Epoch [²⁄₂], Iter [²¹⁰⁄₃₁₂₅], train_loss:0.147608 Epoch [²⁄₂], Iter [²¹¹⁄₃₁₂₅], train_loss:0.153870 Epoch [²⁄₂], Iter [²¹²⁄₃₁₂₅], train_loss:0.141862 Epoch [²⁄₂], Iter [²¹³⁄₃₁₂₅], train_loss:0.148429 Epoch [²⁄₂], Iter [²¹⁴⁄₃₁₂₅], train_loss:0.156956 Epoch [²⁄₂], Iter [²¹⁵⁄₃₁₂₅], train_loss:0.160064 Epoch [²⁄₂], Iter [²¹⁶⁄₃₁₂₅], train_loss:0.155396 Epoch [²⁄₂], Iter [²¹⁷⁄₃₁₂₅], train_loss:0.158974 Epoch [²⁄₂], Iter [²¹⁸⁄₃₁₂₅], train_loss:0.164166 Epoch [²⁄₂], Iter [²¹⁹⁄₃₁₂₅], train_loss:0.150157 Epoch [²⁄₂], Iter [²²⁰⁄₃₁₂₅], train_loss:0.159278 Epoch [²⁄₂], Iter [²²¹⁄₃₁₂₅], train_loss:0.145524 Epoch [²⁄₂], Iter [²²²⁄₃₁₂₅], train_loss:0.153799 Epoch [²⁄₂], Iter [²²³⁄₃₁₂₅], train_loss:0.156198 Epoch [²⁄₂], Iter [²²⁴⁄₃₁₂₅], train_loss:0.161148 Epoch [²⁄₂], Iter [²²⁵⁄₃₁₂₅], train_loss:0.142585 Epoch [²⁄₂], Iter [²²⁶⁄₃₁₂₅], train_loss:0.146489 Epoch [²⁄₂], Iter [²²⁷⁄₃₁₂₅], train_loss:0.172975 Epoch [²⁄₂], Iter [²²⁸⁄₃₁₂₅], train_loss:0.194386 Epoch [²⁄₂], Iter [²²⁹⁄₃₁₂₅], train_loss:0.172534 Epoch [²⁄₂], Iter [²³⁰⁄₃₁₂₅], train_loss:0.147119 Epoch [²⁄₂], Iter [²³¹⁄₃₁₂₅], train_loss:0.153974 Epoch [²⁄₂], Iter [²³²⁄₃₁₂₅], train_loss:0.156483 Epoch [²⁄₂], Iter [²³³⁄₃₁₂₅], train_loss:0.153530 Epoch [²⁄₂], Iter [²³⁴⁄₃₁₂₅], train_loss:0.164038 Epoch [²⁄₂], Iter [²³⁵⁄₃₁₂₅], train_loss:0.173976 Epoch [²⁄₂], Iter [²³⁶⁄₃₁₂₅], train_loss:0.174818 Epoch [²⁄₂], Iter [²³⁷⁄₃₁₂₅], train_loss:0.156790 Epoch [²⁄₂], Iter [²³⁸⁄₃₁₂₅], train_loss:0.164833 Epoch [²⁄₂], Iter [²³⁹⁄₃₁₂₅], train_loss:0.142041 Epoch [²⁄₂], Iter [²⁴⁰⁄₃₁₂₅], train_loss:0.151814 Epoch [²⁄₂], Iter [²⁴¹⁄₃₁₂₅], train_loss:0.178047 Epoch [²⁄₂], Iter [²⁴²⁄₃₁₂₅], train_loss:0.177161 Epoch [²⁄₂], Iter [²⁴³⁄₃₁₂₅], train_loss:0.183264 Epoch [²⁄₂], Iter [²⁴⁴⁄₃₁₂₅], train_loss:0.149528 Epoch [²⁄₂], Iter [²⁴⁵⁄₃₁₂₅], train_loss:0.148756 Epoch [²⁄₂], Iter [²⁴⁶⁄₃₁₂₅], train_loss:0.190471 Epoch [²⁄₂], Iter [²⁴⁷⁄₃₁₂₅], train_loss:0.176104 Epoch [²⁄₂], Iter [²⁴⁸⁄₃₁₂₅], train_loss:0.156350 Epoch [²⁄₂], Iter [²⁴⁹⁄₃₁₂₅], train_loss:0.142632 Epoch [²⁄₂], Iter [²⁵⁰⁄₃₁₂₅], train_loss:0.174584 Epoch [²⁄₂], Iter [²⁵¹⁄₃₁₂₅], train_loss:0.154501 Epoch [²⁄₂], Iter [²⁵²⁄₃₁₂₅], train_loss:0.163151 Epoch [²⁄₂], Iter [²⁵³⁄₃₁₂₅], train_loss:0.166830 Epoch [²⁄₂], Iter [²⁵⁴⁄₃₁₂₅], train_loss:0.151940 Epoch [²⁄₂], Iter [²⁵⁵⁄₃₁₂₅], train_loss:0.172570 Epoch [²⁄₂], Iter [²⁵⁶⁄₃₁₂₅], train_loss:0.149426 Epoch [²⁄₂], Iter [²⁵⁷⁄₃₁₂₅], train_loss:0.167744 Epoch [²⁄₂], Iter [²⁵⁸⁄₃₁₂₅], train_loss:0.167243 Epoch [²⁄₂], Iter [²⁵⁹⁄₃₁₂₅], train_loss:0.150426 Epoch [²⁄₂], Iter [²⁶⁰⁄₃₁₂₅], train_loss:0.143742 Epoch [²⁄₂], Iter [²⁶¹⁄₃₁₂₅], train_loss:0.154619 Epoch [²⁄₂], Iter [²⁶²⁄₃₁₂₅], train_loss:0.177493 Epoch [²⁄₂], Iter [²⁶³⁄₃₁₂₅], train_loss:0.149127 Epoch [²⁄₂], Iter [²⁶⁴⁄₃₁₂₅], train_loss:0.145748 Epoch [²⁄₂], Iter [²⁶⁵⁄₃₁₂₅], train_loss:0.159908 Epoch [²⁄₂], Iter [²⁶⁶⁄₃₁₂₅], train_loss:0.173237 Epoch [²⁄₂], Iter [²⁶⁷⁄₃₁₂₅], train_loss:0.148302 Epoch [²⁄₂], Iter [²⁶⁸⁄₃₁₂₅], train_loss:0.153039 Epoch [²⁄₂], Iter [²⁶⁹⁄₃₁₂₅], train_loss:0.153943 Epoch [²⁄₂], Iter [²⁷⁰⁄₃₁₂₅], train_loss:0.159962 Epoch [²⁄₂], Iter [²⁷¹⁄₃₁₂₅], train_loss:0.168486 Epoch [²⁄₂], Iter [²⁷²⁄₃₁₂₅], train_loss:0.174194 Epoch [²⁄₂], Iter [²⁷³⁄₃₁₂₅], train_loss:0.177417 Epoch [²⁄₂], Iter [²⁷⁴⁄₃₁₂₅], train_loss:0.169610 Epoch [²⁄₂], Iter [²⁷⁵⁄₃₁₂₅], train_loss:0.153916 Epoch [²⁄₂], Iter [²⁷⁶⁄₃₁₂₅], train_loss:0.162009 Epoch [²⁄₂], Iter [²⁷⁷⁄₃₁₂₅], train_loss:0.173930 Epoch [²⁄₂], Iter [²⁷⁸⁄₃₁₂₅], train_loss:0.154844 Epoch [²⁄₂], Iter [²⁷⁹⁄₃₁₂₅], train_loss:0.144510 Epoch [²⁄₂], Iter [²⁸⁰⁄₃₁₂₅], train_loss:0.174670 Epoch [²⁄₂], Iter [²⁸¹⁄₃₁₂₅], train_loss:0.147663 Epoch [²⁄₂], Iter [²⁸²⁄₃₁₂₅], train_loss:0.161231 Epoch [²⁄₂], Iter [²⁸³⁄₃₁₂₅], train_loss:0.164567 Epoch [²⁄₂], Iter [²⁸⁴⁄₃₁₂₅], train_loss:0.148298 Epoch [²⁄₂], Iter [²⁸⁵⁄₃₁₂₅], train_loss:0.174240 Epoch [²⁄₂], Iter [²⁸⁶⁄₃₁₂₅], train_loss:0.151915 Epoch [²⁄₂], Iter [²⁸⁷⁄₃₁₂₅], train_loss:0.164254 Epoch [²⁄₂], Iter [²⁸⁸⁄₃₁₂₅], train_loss:0.174495 Epoch [²⁄₂], Iter [²⁸⁹⁄₃₁₂₅], train_loss:0.142919 Epoch [²⁄₂], Iter [²⁹⁰⁄₃₁₂₅], train_loss:0.164818 Epoch [²⁄₂], Iter [²⁹¹⁄₃₁₂₅], train_loss:0.148046 Epoch [²⁄₂], Iter [²⁹²⁄₃₁₂₅], train_loss:0.133363 Epoch [²⁄₂], Iter [²⁹³⁄₃₁₂₅], train_loss:0.160022 Epoch [²⁄₂], Iter [²⁹⁴⁄₃₁₂₅], train_loss:0.155773 Epoch [²⁄₂], Iter [²⁹⁵⁄₃₁₂₅], train_loss:0.176180 Epoch [²⁄₂], Iter [²⁹⁶⁄₃₁₂₅], train_loss:0.164451 Epoch [²⁄₂], Iter [²⁹⁷⁄₃₁₂₅], train_loss:0.167795 Epoch [²⁄₂], Iter [²⁹⁸⁄₃₁₂₅], train_loss:0.165779 Epoch [²⁄₂], Iter [²⁹⁹⁄₃₁₂₅], train_loss:0.176171 Epoch [²⁄₂], Iter [³⁰⁰⁄₃₁₂₅], train_loss:0.171345 Epoch [²⁄₂], Iter [³⁰¹⁄₃₁₂₅], train_loss:0.184329 Epoch [²⁄₂], Iter [³⁰²⁄₃₁₂₅], train_loss:0.172903 Epoch [²⁄₂], Iter [³⁰³⁄₃₁₂₅], train_loss:0.178375 Epoch [²⁄₂], Iter [³⁰⁴⁄₃₁₂₅], train_loss:0.155158 Epoch [²⁄₂], Iter [³⁰⁵⁄₃₁₂₅], train_loss:0.171172 Epoch [²⁄₂], Iter [³⁰⁶⁄₃₁₂₅], train_loss:0.154146 Epoch [²⁄₂], Iter [³⁰⁷⁄₃₁₂₅], train_loss:0.162431 Epoch [²⁄₂], Iter [³⁰⁸⁄₃₁₂₅], train_loss:0.163887 Epoch [²⁄₂], Iter [³⁰⁹⁄₃₁₂₅], train_loss:0.174687 Epoch [²⁄₂], Iter [³¹⁰⁄₃₁₂₅], train_loss:0.165460 Epoch [²⁄₂], Iter [³¹¹⁄₃₁₂₅], train_loss:0.181555 Epoch [²⁄₂], Iter [³¹²⁄₃₁₂₅], train_loss:0.150162 Epoch [²⁄₂], Iter [³¹³⁄₃₁₂₅], train_loss:0.153412 Epoch [²⁄₂], Iter [³¹⁴⁄₃₁₂₅], train_loss:0.149629 Epoch [²⁄₂], Iter [³¹⁵⁄₃₁₂₅], train_loss:0.158892 Epoch [²⁄₂], Iter [³¹⁶⁄₃₁₂₅], train_loss:0.156130 Epoch [²⁄₂], Iter [³¹⁷⁄₃₁₂₅], train_loss:0.187546 Epoch [²⁄₂], Iter [³¹⁸⁄₃₁₂₅], train_loss:0.153912 Epoch [²⁄₂], Iter [³¹⁹⁄₃₁₂₅], train_loss:0.151770 Epoch [²⁄₂], Iter [³²⁰⁄₃₁₂₅], train_loss:0.176303 Epoch [²⁄₂], Iter [³²¹⁄₃₁₂₅], train_loss:0.167846 Epoch [²⁄₂], Iter [³²²⁄₃₁₂₅], train_loss:0.150853 Epoch [²⁄₂], Iter [³²³⁄₃₁₂₅], train_loss:0.174334 Epoch [²⁄₂], Iter [³²⁴⁄₃₁₂₅], train_loss:0.152363 Epoch [²⁄₂], Iter [³²⁵⁄₃₁₂₅], train_loss:0.182887 Epoch [²⁄₂], Iter [³²⁶⁄₃₁₂₅], train_loss:0.149897 Epoch [²⁄₂], Iter [³²⁷⁄₃₁₂₅], train_loss:0.170501 Epoch [²⁄₂], Iter [³²⁸⁄₃₁₂₅], train_loss:0.186834 Epoch [²⁄₂], Iter [³²⁹⁄₃₁₂₅], train_loss:0.163417 Epoch [²⁄₂], Iter [³³⁰⁄₃₁₂₅], train_loss:0.182607 Epoch [²⁄₂], Iter [³³¹⁄₃₁₂₅], train_loss:0.167527 Epoch [²⁄₂], Iter [³³²⁄₃₁₂₅], train_loss:0.171005 Epoch [²⁄₂], Iter [³³³⁄₃₁₂₅], train_loss:0.162520 Epoch [²⁄₂], Iter [³³⁴⁄₃₁₂₅], train_loss:0.160567 Epoch [²⁄₂], Iter [³³⁵⁄₃₁₂₅], train_loss:0.165600 Epoch [²⁄₂], Iter [³³⁶⁄₃₁₂₅], train_loss:0.155164 Epoch [²⁄₂], Iter [³³⁷⁄₃₁₂₅], train_loss:0.175315 Epoch [²⁄₂], Iter [³³⁸⁄₃₁₂₅], train_loss:0.171219 Epoch [²⁄₂], Iter [³³⁹⁄₃₁₂₅], train_loss:0.162644 Epoch [²⁄₂], Iter [³⁴⁰⁄₃₁₂₅], train_loss:0.159048 Epoch [²⁄₂], Iter [³⁴¹⁄₃₁₂₅], train_loss:0.162782 Epoch [²⁄₂], Iter [³⁴²⁄₃₁₂₅], train_loss:0.165438 Epoch [²⁄₂], Iter [³⁴³⁄₃₁₂₅], train_loss:0.153910 Epoch [²⁄₂], Iter [³⁴⁴⁄₃₁₂₅], train_loss:0.174372 Epoch [²⁄₂], Iter [³⁴⁵⁄₃₁₂₅], train_loss:0.177340 Epoch [²⁄₂], Iter [³⁴⁶⁄₃₁₂₅], train_loss:0.177186 Epoch [²⁄₂], Iter [³⁴⁷⁄₃₁₂₅], train_loss:0.163347 Epoch [²⁄₂], Iter [³⁴⁸⁄₃₁₂₅], train_loss:0.164975 Epoch [²⁄₂], Iter [³⁴⁹⁄₃₁₂₅], train_loss:0.202241 Epoch [²⁄₂], Iter [³⁵⁰⁄₃₁₂₅], train_loss:0.176461 Epoch [²⁄₂], Iter [³⁵¹⁄₃₁₂₅], train_loss:0.155909 Epoch [²⁄₂], Iter [³⁵²⁄₃₁₂₅], train_loss:0.161746 Epoch [²⁄₂], Iter [³⁵³⁄₃₁₂₅], train_loss:0.161433 Epoch [²⁄₂], Iter [³⁵⁴⁄₃₁₂₅], train_loss:0.161199 Epoch [²⁄₂], Iter [³⁵⁵⁄₃₁₂₅], train_loss:0.176037 Epoch [²⁄₂], Iter [³⁵⁶⁄₃₁₂₅], train_loss:0.165718 Epoch [²⁄₂], Iter [³⁵⁷⁄₃₁₂₅], train_loss:0.144140 Epoch [²⁄₂], Iter [³⁵⁸⁄₃₁₂₅], train_loss:0.142182 Epoch [²⁄₂], Iter [³⁵⁹⁄₃₁₂₅], train_loss:0.151589 Epoch [²⁄₂], Iter [³⁶⁰⁄₃₁₂₅], train_loss:0.170065 Epoch [²⁄₂], Iter [³⁶¹⁄₃₁₂₅], train_loss:0.155288 Epoch [²⁄₂], Iter [³⁶²⁄₃₁₂₅], train_loss:0.153488 Epoch [²⁄₂], Iter [³⁶³⁄₃₁₂₅], train_loss:0.156576 Epoch [²⁄₂], Iter [³⁶⁴⁄₃₁₂₅], train_loss:0.161076 Epoch [²⁄₂], Iter [³⁶⁵⁄₃₁₂₅], train_loss:0.161203 Epoch [²⁄₂], Iter [³⁶⁶⁄₃₁₂₅], train_loss:0.164802 Epoch [²⁄₂], Iter [³⁶⁷⁄₃₁₂₅], train_loss:0.166324 Epoch [²⁄₂], Iter [³⁶⁸⁄₃₁₂₅], train_loss:0.178081 Epoch [²⁄₂], Iter [³⁶⁹⁄₃₁₂₅], train_loss:0.144357 Epoch [²⁄₂], Iter [³⁷⁰⁄₃₁₂₅], train_loss:0.174453 Epoch [²⁄₂], Iter [³⁷¹⁄₃₁₂₅], train_loss:0.168766 Epoch [²⁄₂], Iter [³⁷²⁄₃₁₂₅], train_loss:0.147773 Epoch [²⁄₂], Iter [³⁷³⁄₃₁₂₅], train_loss:0.143407 Epoch [²⁄₂], Iter [³⁷⁴⁄₃₁₂₅], train_loss:0.154440 Epoch [²⁄₂], Iter [³⁷⁵⁄₃₁₂₅], train_loss:0.144308 Epoch [²⁄₂], Iter [³⁷⁶⁄₃₁₂₅], train_loss:0.146517 Epoch [²⁄₂], Iter [³⁷⁷⁄₃₁₂₅], train_loss:0.168994 Epoch [²⁄₂], Iter [³⁷⁸⁄₃₁₂₅], train_loss:0.155020 Epoch [²⁄₂], Iter [³⁷⁹⁄₃₁₂₅], train_loss:0.136322 Epoch [²⁄₂], Iter [³⁸⁰⁄₃₁₂₅], train_loss:0.165164 Epoch [²⁄₂], Iter [³⁸¹⁄₃₁₂₅], train_loss:0.165966 Epoch [²⁄₂], Iter [³⁸²⁄₃₁₂₅], train_loss:0.149831 Epoch [²⁄₂], Iter [³⁸³⁄₃₁₂₅], train_loss:0.153939 Epoch [²⁄₂], Iter [³⁸⁴⁄₃₁₂₅], train_loss:0.150713 Epoch [²⁄₂], Iter [³⁸⁵⁄₃₁₂₅], train_loss:0.149525 Epoch [²⁄₂], Iter [³⁸⁶⁄₃₁₂₅], train_loss:0.186537 Epoch [²⁄₂], Iter [³⁸⁷⁄₃₁₂₅], train_loss:0.155550 Epoch [²⁄₂], Iter [³⁸⁸⁄₃₁₂₅], train_loss:0.130376 Epoch [²⁄₂], Iter [³⁸⁹⁄₃₁₂₅], train_loss:0.168143 Epoch [²⁄₂], Iter [³⁹⁰⁄₃₁₂₅], train_loss:0.153200 Epoch [²⁄₂], Iter [³⁹¹⁄₃₁₂₅], train_loss:0.156268 Epoch [²⁄₂], Iter [³⁹²⁄₃₁₂₅], train_loss:0.138514 Epoch [²⁄₂], Iter [³⁹³⁄₃₁₂₅], train_loss:0.186347 Epoch [²⁄₂], Iter [³⁹⁴⁄₃₁₂₅], train_loss:0.167708 Epoch [²⁄₂], Iter [³⁹⁵⁄₃₁₂₅], train_loss:0.156236 Epoch [²⁄₂], Iter [³⁹⁶⁄₃₁₂₅], train_loss:0.161214 Epoch [²⁄₂], Iter [³⁹⁷⁄₃₁₂₅], train_loss:0.164827 Epoch [²⁄₂], Iter [³⁹⁸⁄₃₁₂₅], train_loss:0.162833 Epoch [²⁄₂], Iter [³⁹⁹⁄₃₁₂₅], train_loss:0.148330 Epoch [²⁄₂], Iter [⁴⁰⁰⁄₃₁₂₅], train_loss:0.151244 Epoch [²⁄₂], Iter [⁴⁰¹⁄₃₁₂₅], train_loss:0.175030 Epoch [²⁄₂], Iter [⁴⁰²⁄₃₁₂₅], train_loss:0.167966 Epoch [²⁄₂], Iter [⁴⁰³⁄₃₁₂₅], train_loss:0.174009 Epoch [²⁄₂], Iter [⁴⁰⁴⁄₃₁₂₅], train_loss:0.133342 Epoch [²⁄₂], Iter [⁴⁰⁵⁄₃₁₂₅], train_loss:0.160444 Epoch [²⁄₂], Iter [⁴⁰⁶⁄₃₁₂₅], train_loss:0.173592 Epoch [²⁄₂], Iter [⁴⁰⁷⁄₃₁₂₅], train_loss:0.176786 Epoch [²⁄₂], Iter [⁴⁰⁸⁄₃₁₂₅], train_loss:0.161026 Epoch [²⁄₂], Iter [⁴⁰⁹⁄₃₁₂₅], train_loss:0.173543 Epoch [²⁄₂], Iter [⁴¹⁰⁄₃₁₂₅], train_loss:0.147663 Epoch [²⁄₂], Iter [⁴¹¹⁄₃₁₂₅], train_loss:0.170319 Epoch [²⁄₂], Iter [⁴¹²⁄₃₁₂₅], train_loss:0.185939 Epoch [²⁄₂], Iter [⁴¹³⁄₃₁₂₅], train_loss:0.165246 Epoch [²⁄₂], Iter [⁴¹⁴⁄₃₁₂₅], train_loss:0.185627 Epoch [²⁄₂], Iter [⁴¹⁵⁄₃₁₂₅], train_loss:0.131443 Epoch [²⁄₂], Iter [⁴¹⁶⁄₃₁₂₅], train_loss:0.150096 Epoch [²⁄₂], Iter [⁴¹⁷⁄₃₁₂₅], train_loss:0.143120 Epoch [²⁄₂], Iter [⁴¹⁸⁄₃₁₂₅], train_loss:0.193534 Epoch [²⁄₂], Iter [⁴¹⁹⁄₃₁₂₅], train_loss:0.152602 Epoch [²⁄₂], Iter [⁴²⁰⁄₃₁₂₅], train_loss:0.170830 Epoch [²⁄₂], Iter [⁴²¹⁄₃₁₂₅], train_loss:0.174716 Epoch [²⁄₂], Iter [⁴²²⁄₃₁₂₅], train_loss:0.174463 Epoch [²⁄₂], Iter [⁴²³⁄₃₁₂₅], train_loss:0.169858 Epoch [²⁄₂], Iter [⁴²⁴⁄₃₁₂₅], train_loss:0.142388 Epoch [²⁄₂], Iter [⁴²⁵⁄₃₁₂₅], train_loss:0.172615 Epoch [²⁄₂], Iter [⁴²⁶⁄₃₁₂₅], train_loss:0.177286 Epoch [²⁄₂], Iter [⁴²⁷⁄₃₁₂₅], train_loss:0.167227 Epoch [²⁄₂], Iter [⁴²⁸⁄₃₁₂₅], train_loss:0.157363 Epoch [²⁄₂], Iter [⁴²⁹⁄₃₁₂₅], train_loss:0.166516 Epoch [²⁄₂], Iter [⁴³⁰⁄₃₁₂₅], train_loss:0.172313 Epoch [²⁄₂], Iter [⁴³¹⁄₃₁₂₅], train_loss:0.161539 Epoch [²⁄₂], Iter [⁴³²⁄₃₁₂₅], train_loss:0.163159 Epoch [²⁄₂], Iter [⁴³³⁄₃₁₂₅], train_loss:0.144575 Epoch [²⁄₂], Iter [⁴³⁴⁄₃₁₂₅], train_loss:0.168186 Epoch [²⁄₂], Iter [⁴³⁵⁄₃₁₂₅], train_loss:0.157193 Epoch [²⁄₂], Iter [⁴³⁶⁄₃₁₂₅], train_loss:0.161615 Epoch [²⁄₂], Iter [⁴³⁷⁄₃₁₂₅], train_loss:0.169740 Epoch [²⁄₂], Iter [⁴³⁸⁄₃₁₂₅], train_loss:0.165369 Epoch [²⁄₂], Iter [⁴³⁹⁄₃₁₂₅], train_loss:0.171216 Epoch [²⁄₂], Iter [⁴⁴⁰⁄₃₁₂₅], train_loss:0.162590 Epoch [²⁄₂], Iter [⁴⁴¹⁄₃₁₂₅], train_loss:0.185242 Epoch [²⁄₂], Iter [⁴⁴²⁄₃₁₂₅], train_loss:0.161350 Epoch [²⁄₂], Iter [⁴⁴³⁄₃₁₂₅], train_loss:0.160137 Epoch [²⁄₂], Iter [⁴⁴⁴⁄₃₁₂₅], train_loss:0.151255 Epoch [²⁄₂], Iter [⁴⁴⁵⁄₃₁₂₅], train_loss:0.174243 Epoch [²⁄₂], Iter [⁴⁴⁶⁄₃₁₂₅], train_loss:0.163636 Epoch [²⁄₂], Iter [⁴⁴⁷⁄₃₁₂₅], train_loss:0.155706 Epoch [²⁄₂], Iter [⁴⁴⁸⁄₃₁₂₅], train_loss:0.165992 Epoch [²⁄₂], Iter [⁴⁴⁹⁄₃₁₂₅], train_loss:0.157281 Epoch [²⁄₂], Iter [⁴⁵⁰⁄₃₁₂₅], train_loss:0.180386 Epoch [²⁄₂], Iter [⁴⁵¹⁄₃₁₂₅], train_loss:0.180637 Epoch [²⁄₂], Iter [⁴⁵²⁄₃₁₂₅], train_loss:0.159181 Epoch [²⁄₂], Iter [⁴⁵³⁄₃₁₂₅], train_loss:0.167303 Epoch [²⁄₂], Iter [⁴⁵⁴⁄₃₁₂₅], train_loss:0.161755 Epoch [²⁄₂], Iter [⁴⁵⁵⁄₃₁₂₅], train_loss:0.154677 Epoch [²⁄₂], Iter [⁴⁵⁶⁄₃₁₂₅], train_loss:0.167636 Epoch [²⁄₂], Iter [⁴⁵⁷⁄₃₁₂₅], train_loss:0.180807 Epoch [²⁄₂], Iter [⁴⁵⁸⁄₃₁₂₅], train_loss:0.139945 Epoch [²⁄₂], Iter [⁴⁵⁹⁄₃₁₂₅], train_loss:0.165975 Epoch [²⁄₂], Iter [⁴⁶⁰⁄₃₁₂₅], train_loss:0.153326 Epoch [²⁄₂], Iter [⁴⁶¹⁄₃₁₂₅], train_loss:0.187807 Epoch [²⁄₂], Iter [⁴⁶²⁄₃₁₂₅], train_loss:0.166080 Epoch [²⁄₂], Iter [⁴⁶³⁄₃₁₂₅], train_loss:0.164084 Epoch [²⁄₂], Iter [⁴⁶⁴⁄₃₁₂₅], train_loss:0.178732 Epoch [²⁄₂], Iter [⁴⁶⁵⁄₃₁₂₅], train_loss:0.139112 Epoch [²⁄₂], Iter [⁴⁶⁶⁄₃₁₂₅], train_loss:0.154262 Epoch [²⁄₂], Iter [⁴⁶⁷⁄₃₁₂₅], train_loss:0.156984 Epoch [²⁄₂], Iter [⁴⁶⁸⁄₃₁₂₅], train_loss:0.153696 Epoch [²⁄₂], Iter [⁴⁶⁹⁄₃₁₂₅], train_loss:0.167890 Epoch [²⁄₂], Iter [⁴⁷⁰⁄₃₁₂₅], train_loss:0.146530 Epoch [²⁄₂], Iter [⁴⁷¹⁄₃₁₂₅], train_loss:0.173568 Epoch [²⁄₂], Iter [⁴⁷²⁄₃₁₂₅], train_loss:0.172920 Epoch [²⁄₂], Iter [⁴⁷³⁄₃₁₂₅], train_loss:0.172191 Epoch [²⁄₂], Iter [⁴⁷⁴⁄₃₁₂₅], train_loss:0.177066 Epoch [²⁄₂], Iter [⁴⁷⁵⁄₃₁₂₅], train_loss:0.166096 Epoch [²⁄₂], Iter [⁴⁷⁶⁄₃₁₂₅], train_loss:0.145177 Epoch [²⁄₂], Iter [⁴⁷⁷⁄₃₁₂₅], train_loss:0.154965 Epoch [²⁄₂], Iter [⁴⁷⁸⁄₃₁₂₅], train_loss:0.154901 Epoch [²⁄₂], Iter [⁴⁷⁹⁄₃₁₂₅], train_loss:0.161373 Epoch [²⁄₂], Iter [⁴⁸⁰⁄₃₁₂₅], train_loss:0.164218 Epoch [²⁄₂], Iter [⁴⁸¹⁄₃₁₂₅], train_loss:0.163394 Epoch [²⁄₂], Iter [⁴⁸²⁄₃₁₂₅], train_loss:0.179960 Epoch [²⁄₂], Iter [⁴⁸³⁄₃₁₂₅], train_loss:0.152761 Epoch [²⁄₂], Iter [⁴⁸⁴⁄₃₁₂₅], train_loss:0.148085 Epoch [²⁄₂], Iter [⁴⁸⁵⁄₃₁₂₅], train_loss:0.158129 Epoch [²⁄₂], Iter [⁴⁸⁶⁄₃₁₂₅], train_loss:0.164468 Epoch [²⁄₂], Iter [⁴⁸⁷⁄₃₁₂₅], train_loss:0.140875 Epoch [²⁄₂], Iter [⁴⁸⁸⁄₃₁₂₅], train_loss:0.153898 Epoch [²⁄₂], Iter [⁴⁸⁹⁄₃₁₂₅], train_loss:0.183179 Epoch [²⁄₂], Iter [⁴⁹⁰⁄₃₁₂₅], train_loss:0.159658 Epoch [²⁄₂], Iter [⁴⁹¹⁄₃₁₂₅], train_loss:0.149543 Epoch [²⁄₂], Iter [⁴⁹²⁄₃₁₂₅], train_loss:0.162857 Epoch [²⁄₂], Iter [⁴⁹³⁄₃₁₂₅], train_loss:0.146819 Epoch [²⁄₂], Iter [⁴⁹⁴⁄₃₁₂₅], train_loss:0.162568 Epoch [²⁄₂], Iter [⁴⁹⁵⁄₃₁₂₅], train_loss:0.186698 Epoch [²⁄₂], Iter [⁴⁹⁶⁄₃₁₂₅], train_loss:0.152870 Epoch [²⁄₂], Iter [⁴⁹⁷⁄₃₁₂₅], train_loss:0.160796 Epoch [²⁄₂], Iter [⁴⁹⁸⁄₃₁₂₅], train_loss:0.150789 Epoch [²⁄₂], Iter [⁴⁹⁹⁄₃₁₂₅], train_loss:0.143901 Epoch [²⁄₂], Iter [⁵⁰⁰⁄₃₁₂₅], train_loss:0.146307 Epoch [²⁄₂], Iter [⁵⁰¹⁄₃₁₂₅], train_loss:0.156505 Epoch [²⁄₂], Iter [⁵⁰²⁄₃₁₂₅], train_loss:0.170537 Epoch [²⁄₂], Iter [⁵⁰³⁄₃₁₂₅], train_loss:0.165219 Epoch [²⁄₂], Iter [⁵⁰⁴⁄₃₁₂₅], train_loss:0.131376 Epoch [²⁄₂], Iter [⁵⁰⁵⁄₃₁₂₅], train_loss:0.150592 Epoch [²⁄₂], Iter [⁵⁰⁶⁄₃₁₂₅], train_loss:0.154510 Epoch [²⁄₂], Iter [⁵⁰⁷⁄₃₁₂₅], train_loss:0.185317 Epoch [²⁄₂], Iter [⁵⁰⁸⁄₃₁₂₅], train_loss:0.155880 Epoch [²⁄₂], Iter [⁵⁰⁹⁄₃₁₂₅], train_loss:0.166343 Epoch [²⁄₂], Iter [⁵¹⁰⁄₃₁₂₅], train_loss:0.170775 Epoch [²⁄₂], Iter [⁵¹¹⁄₃₁₂₅], train_loss:0.158124 Epoch [²⁄₂], Iter [⁵¹²⁄₃₁₂₅], train_loss:0.162436 Epoch [²⁄₂], Iter [⁵¹³⁄₃₁₂₅], train_loss:0.171975 Epoch [²⁄₂], Iter [⁵¹⁴⁄₃₁₂₅], train_loss:0.158008 Epoch [²⁄₂], Iter [⁵¹⁵⁄₃₁₂₅], train_loss:0.180108 Epoch [²⁄₂], Iter [⁵¹⁶⁄₃₁₂₅], train_loss:0.166079 Epoch [²⁄₂], Iter [⁵¹⁷⁄₃₁₂₅], train_loss:0.187777 Epoch [²⁄₂], Iter [⁵¹⁸⁄₃₁₂₅], train_loss:0.179959 Epoch [²⁄₂], Iter [⁵¹⁹⁄₃₁₂₅], train_loss:0.174720 Epoch [²⁄₂], Iter [⁵²⁰⁄₃₁₂₅], train_loss:0.159333 Epoch [²⁄₂], Iter [⁵²¹⁄₃₁₂₅], train_loss:0.170574 Epoch [²⁄₂], Iter [⁵²²⁄₃₁₂₅], train_loss:0.162373 Epoch [²⁄₂], Iter [⁵²³⁄₃₁₂₅], train_loss:0.165549 Epoch [²⁄₂], Iter [⁵²⁴⁄₃₁₂₅], train_loss:0.171584 Epoch [²⁄₂], Iter [⁵²⁵⁄₃₁₂₅], train_loss:0.174756 Epoch [²⁄₂], Iter [⁵²⁶⁄₃₁₂₅], train_loss:0.161434 Epoch [²⁄₂], Iter [⁵²⁷⁄₃₁₂₅], train_loss:0.168083 Epoch [²⁄₂], Iter [⁵²⁸⁄₃₁₂₅], train_loss:0.167138 Epoch [²⁄₂], Iter [⁵²⁹⁄₃₁₂₅], train_loss:0.140973 Epoch [²⁄₂], Iter [⁵³⁰⁄₃₁₂₅], train_loss:0.159618 Epoch [²⁄₂], Iter [⁵³¹⁄₃₁₂₅], train_loss:0.176200 Epoch [²⁄₂], Iter [⁵³²⁄₃₁₂₅], train_loss:0.162572 Epoch [²⁄₂], Iter [⁵³³⁄₃₁₂₅], train_loss:0.168972 Epoch [²⁄₂], Iter [⁵³⁴⁄₃₁₂₅], train_loss:0.173325 Epoch [²⁄₂], Iter [⁵³⁵⁄₃₁₂₅], train_loss:0.163866 Epoch [²⁄₂], Iter [⁵³⁶⁄₃₁₂₅], train_loss:0.163720 Epoch [²⁄₂], Iter [⁵³⁷⁄₃₁₂₅], train_loss:0.168137 Epoch [²⁄₂], Iter [⁵³⁸⁄₃₁₂₅], train_loss:0.175345 Epoch [²⁄₂], Iter [⁵³⁹⁄₃₁₂₅], train_loss:0.158390 Epoch [²⁄₂], Iter [⁵⁴⁰⁄₃₁₂₅], train_loss:0.159162 Epoch [²⁄₂], Iter [⁵⁴¹⁄₃₁₂₅], train_loss:0.144704 Epoch [²⁄₂], Iter [⁵⁴²⁄₃₁₂₅], train_loss:0.149428 Epoch [²⁄₂], Iter [⁵⁴³⁄₃₁₂₅], train_loss:0.158572 Epoch [²⁄₂], Iter [⁵⁴⁴⁄₃₁₂₅], train_loss:0.172126 Epoch [²⁄₂], Iter [⁵⁴⁵⁄₃₁₂₅], train_loss:0.176276 Epoch [²⁄₂], Iter [⁵⁴⁶⁄₃₁₂₅], train_loss:0.177032 Epoch [²⁄₂], Iter [⁵⁴⁷⁄₃₁₂₅], train_loss:0.173978 Epoch [²⁄₂], Iter [⁵⁴⁸⁄₃₁₂₅], train_loss:0.164149 Epoch [²⁄₂], Iter [⁵⁴⁹⁄₃₁₂₅], train_loss:0.160977 Epoch [²⁄₂], Iter [⁵⁵⁰⁄₃₁₂₅], train_loss:0.141250 Epoch [²⁄₂], Iter [⁵⁵¹⁄₃₁₂₅], train_loss:0.167351 Epoch [²⁄₂], Iter [⁵⁵²⁄₃₁₂₅], train_loss:0.154863 Epoch [²⁄₂], Iter [⁵⁵³⁄₃₁₂₅], train_loss:0.176878 Epoch [²⁄₂], Iter [⁵⁵⁴⁄₃₁₂₅], train_loss:0.152597 Epoch [²⁄₂], Iter [⁵⁵⁵⁄₃₁₂₅], train_loss:0.173390 Epoch [²⁄₂], Iter [⁵⁵⁶⁄₃₁₂₅], train_loss:0.163720 Epoch [²⁄₂], Iter [⁵⁵⁷⁄₃₁₂₅], train_loss:0.160260 Epoch [²⁄₂], Iter [⁵⁵⁸⁄₃₁₂₅], train_loss:0.178257 Epoch [²⁄₂], Iter [⁵⁵⁹⁄₃₁₂₅], train_loss:0.175589 Epoch [²⁄₂], Iter [⁵⁶⁰⁄₃₁₂₅], train_loss:0.148475 Epoch [²⁄₂], Iter [⁵⁶¹⁄₃₁₂₅], train_loss:0.173594 Epoch [²⁄₂], Iter [⁵⁶²⁄₃₁₂₅], train_loss:0.165406 Epoch [²⁄₂], Iter [⁵⁶³⁄₃₁₂₅], train_loss:0.171584 Epoch [²⁄₂], Iter [⁵⁶⁴⁄₃₁₂₅], train_loss:0.167694 Epoch [²⁄₂], Iter [⁵⁶⁵⁄₃₁₂₅], train_loss:0.163094 Epoch [²⁄₂], Iter [⁵⁶⁶⁄₃₁₂₅], train_loss:0.157451 Epoch [²⁄₂], Iter [⁵⁶⁷⁄₃₁₂₅], train_loss:0.163195 Epoch [²⁄₂], Iter [⁵⁶⁸⁄₃₁₂₅], train_loss:0.145743 Epoch [²⁄₂], Iter [⁵⁶⁹⁄₃₁₂₅], train_loss:0.165041 Epoch [²⁄₂], Iter [⁵⁷⁰⁄₃₁₂₅], train_loss:0.155912 Epoch [²⁄₂], Iter [⁵⁷¹⁄₃₁₂₅], train_loss:0.150290 Epoch [²⁄₂], Iter [⁵⁷²⁄₃₁₂₅], train_loss:0.162542 Epoch [²⁄₂], Iter [⁵⁷³⁄₃₁₂₅], train_loss:0.147671 Epoch [²⁄₂], Iter [⁵⁷⁴⁄₃₁₂₅], train_loss:0.153121 Epoch [²⁄₂], Iter [⁵⁷⁵⁄₃₁₂₅], train_loss:0.151718 Epoch [²⁄₂], Iter [⁵⁷⁶⁄₃₁₂₅], train_loss:0.167825 Epoch [²⁄₂], Iter [⁵⁷⁷⁄₃₁₂₅], train_loss:0.148835 Epoch [²⁄₂], Iter [⁵⁷⁸⁄₃₁₂₅], train_loss:0.151512 Epoch [²⁄₂], Iter [⁵⁷⁹⁄₃₁₂₅], train_loss:0.187779 Epoch [²⁄₂], Iter [⁵⁸⁰⁄₃₁₂₅], train_loss:0.157333 Epoch [²⁄₂], Iter [⁵⁸¹⁄₃₁₂₅], train_loss:0.165742 Epoch [²⁄₂], Iter [⁵⁸²⁄₃₁₂₅], train_loss:0.167597 Epoch [²⁄₂], Iter [⁵⁸³⁄₃₁₂₅], train_loss:0.163270 Epoch [²⁄₂], Iter [⁵⁸⁴⁄₃₁₂₅], train_loss:0.144670 Epoch [²⁄₂], Iter [⁵⁸⁵⁄₃₁₂₅], train_loss:0.149435 Epoch [²⁄₂], Iter [⁵⁸⁶⁄₃₁₂₅], train_loss:0.170580 Epoch [²⁄₂], Iter [⁵⁸⁷⁄₃₁₂₅], train_loss:0.160914 Epoch [²⁄₂], Iter [⁵⁸⁸⁄₃₁₂₅], train_loss:0.151355 Epoch [²⁄₂], Iter [⁵⁸⁹⁄₃₁₂₅], train_loss:0.167059 Epoch [²⁄₂], Iter [⁵⁹⁰⁄₃₁₂₅], train_loss:0.151443 Epoch [²⁄₂], Iter [⁵⁹¹⁄₃₁₂₅], train_loss:0.147637 Epoch [²⁄₂], Iter [⁵⁹²⁄₃₁₂₅], train_loss:0.173933 Epoch [²⁄₂], Iter [⁵⁹³⁄₃₁₂₅], train_loss:0.157407 Epoch [²⁄₂], Iter [⁵⁹⁴⁄₃₁₂₅], train_loss:0.169269 Epoch [²⁄₂], Iter [⁵⁹⁵⁄₃₁₂₅], train_loss:0.155772 Epoch [²⁄₂], Iter [⁵⁹⁶⁄₃₁₂₅], train_loss:0.189058 Epoch [²⁄₂], Iter [⁵⁹⁷⁄₃₁₂₅], train_loss:0.147937 Epoch [²⁄₂], Iter [⁵⁹⁸⁄₃₁₂₅], train_loss:0.179247 Epoch [²⁄₂], Iter [⁵⁹⁹⁄₃₁₂₅], train_loss:0.167485 Epoch [²⁄₂], Iter [⁶⁰⁰⁄₃₁₂₅], train_loss:0.153575 Epoch [²⁄₂], Iter [⁶⁰¹⁄₃₁₂₅], train_loss:0.143053 Epoch [²⁄₂], Iter [⁶⁰²⁄₃₁₂₅], train_loss:0.150471 Epoch [²⁄₂], Iter [⁶⁰³⁄₃₁₂₅], train_loss:0.143764 Epoch [²⁄₂], Iter [⁶⁰⁴⁄₃₁₂₅], train_loss:0.161357 Epoch [²⁄₂], Iter [⁶⁰⁵⁄₃₁₂₅], train_loss:0.177912 Epoch [²⁄₂], Iter [⁶⁰⁶⁄₃₁₂₅], train_loss:0.193015 Epoch [²⁄₂], Iter [⁶⁰⁷⁄₃₁₂₅], train_loss:0.165355 Epoch [²⁄₂], Iter [⁶⁰⁸⁄₃₁₂₅], train_loss:0.160645 Epoch [²⁄₂], Iter [⁶⁰⁹⁄₃₁₂₅], train_loss:0.153148 Epoch [²⁄₂], Iter [⁶¹⁰⁄₃₁₂₅], train_loss:0.161745 Epoch [²⁄₂], Iter [⁶¹¹⁄₃₁₂₅], train_loss:0.177804 Epoch [²⁄₂], Iter [⁶¹²⁄₃₁₂₅], train_loss:0.169567 Epoch [²⁄₂], Iter [⁶¹³⁄₃₁₂₅], train_loss:0.163330 Epoch [²⁄₂], Iter [⁶¹⁴⁄₃₁₂₅], train_loss:0.156796 Epoch [²⁄₂], Iter [⁶¹⁵⁄₃₁₂₅], train_loss:0.176123 Epoch [²⁄₂], Iter [⁶¹⁶⁄₃₁₂₅], train_loss:0.154425 Epoch [²⁄₂], Iter [⁶¹⁷⁄₃₁₂₅], train_loss:0.152680 Epoch [²⁄₂], Iter [⁶¹⁸⁄₃₁₂₅], train_loss:0.150936 Epoch [²⁄₂], Iter [⁶¹⁹⁄₃₁₂₅], train_loss:0.174734 Epoch [²⁄₂], Iter [⁶²⁰⁄₃₁₂₅], train_loss:0.164248 Epoch [²⁄₂], Iter [⁶²¹⁄₃₁₂₅], train_loss:0.154376 Epoch [²⁄₂], Iter [⁶²²⁄₃₁₂₅], train_loss:0.181289 Epoch [²⁄₂], Iter [⁶²³⁄₃₁₂₅], train_loss:0.154710 Epoch [²⁄₂], Iter [⁶²⁴⁄₃₁₂₅], train_loss:0.173619 Epoch [²⁄₂], Iter [⁶²⁵⁄₃₁₂₅], train_loss:0.160207 Epoch [²⁄₂], Iter [⁶²⁶⁄₃₁₂₅], train_loss:0.164651 Epoch [²⁄₂], Iter [⁶²⁷⁄₃₁₂₅], train_loss:0.168672 Epoch [²⁄₂], Iter [⁶²⁸⁄₃₁₂₅], train_loss:0.152033 Epoch [²⁄₂], Iter [⁶²⁹⁄₃₁₂₅], train_loss:0.145318 Epoch [²⁄₂], Iter [⁶³⁰⁄₃₁₂₅], train_loss:0.153201 Epoch [²⁄₂], Iter [⁶³¹⁄₃₁₂₅], train_loss:0.136641 Epoch [²⁄₂], Iter [⁶³²⁄₃₁₂₅], train_loss:0.165298 Epoch [²⁄₂], Iter [⁶³³⁄₃₁₂₅], train_loss:0.146980 Epoch [²⁄₂], Iter [⁶³⁴⁄₃₁₂₅], train_loss:0.157089 Epoch [²⁄₂], Iter [⁶³⁵⁄₃₁₂₅], train_loss:0.153481 Epoch [²⁄₂], Iter [⁶³⁶⁄₃₁₂₅], train_loss:0.180023 Epoch [²⁄₂], Iter [⁶³⁷⁄₃₁₂₅], train_loss:0.177965 Epoch [²⁄₂], Iter [⁶³⁸⁄₃₁₂₅], train_loss:0.168382 Epoch [²⁄₂], Iter [⁶³⁹⁄₃₁₂₅], train_loss:0.170590 Epoch [²⁄₂], Iter [⁶⁴⁰⁄₃₁₂₅], train_loss:0.146684 Epoch [²⁄₂], Iter [⁶⁴¹⁄₃₁₂₅], train_loss:0.154656 Epoch [²⁄₂], Iter [⁶⁴²⁄₃₁₂₅], train_loss:0.148962 Epoch [²⁄₂], Iter [⁶⁴³⁄₃₁₂₅], train_loss:0.162826 Epoch [²⁄₂], Iter [⁶⁴⁴⁄₃₁₂₅], train_loss:0.154299 Epoch [²⁄₂], Iter [⁶⁴⁵⁄₃₁₂₅], train_loss:0.140432 Epoch [²⁄₂], Iter [⁶⁴⁶⁄₃₁₂₅], train_loss:0.169591 Epoch [²⁄₂], Iter [⁶⁴⁷⁄₃₁₂₅], train_loss:0.160964 Epoch [²⁄₂], Iter [⁶⁴⁸⁄₃₁₂₅], train_loss:0.163820 Epoch [²⁄₂], Iter [⁶⁴⁹⁄₃₁₂₅], train_loss:0.180686 Epoch [²⁄₂], Iter [⁶⁵⁰⁄₃₁₂₅], train_loss:0.149200 Epoch [²⁄₂], Iter [⁶⁵¹⁄₃₁₂₅], train_loss:0.165878 Epoch [²⁄₂], Iter [⁶⁵²⁄₃₁₂₅], train_loss:0.153168 Epoch [²⁄₂], Iter [⁶⁵³⁄₃₁₂₅], train_loss:0.158429 Epoch [²⁄₂], Iter [⁶⁵⁴⁄₃₁₂₅], train_loss:0.164462 Epoch [²⁄₂], Iter [⁶⁵⁵⁄₃₁₂₅], train_loss:0.173659 Epoch [²⁄₂], Iter [⁶⁵⁶⁄₃₁₂₅], train_loss:0.158212 Epoch [²⁄₂], Iter [⁶⁵⁷⁄₃₁₂₅], train_loss:0.147685 Epoch [²⁄₂], Iter [⁶⁵⁸⁄₃₁₂₅], train_loss:0.165053 Epoch [²⁄₂], Iter [⁶⁵⁹⁄₃₁₂₅], train_loss:0.147815 Epoch [²⁄₂], Iter [⁶⁶⁰⁄₃₁₂₅], train_loss:0.156994 Epoch [²⁄₂], Iter [⁶⁶¹⁄₃₁₂₅], train_loss:0.166037 Epoch [²⁄₂], Iter [⁶⁶²⁄₃₁₂₅], train_loss:0.172137 Epoch [²⁄₂], Iter [⁶⁶³⁄₃₁₂₅], train_loss:0.164935 Epoch [²⁄₂], Iter [⁶⁶⁴⁄₃₁₂₅], train_loss:0.135215 Epoch [²⁄₂], Iter [⁶⁶⁵⁄₃₁₂₅], train_loss:0.158562 Epoch [²⁄₂], Iter [⁶⁶⁶⁄₃₁₂₅], train_loss:0.160104 Epoch [²⁄₂], Iter [⁶⁶⁷⁄₃₁₂₅], train_loss:0.151053 Epoch [²⁄₂], Iter [⁶⁶⁸⁄₃₁₂₅], train_loss:0.170116 Epoch [²⁄₂], Iter [⁶⁶⁹⁄₃₁₂₅], train_loss:0.137139 Epoch [²⁄₂], Iter [⁶⁷⁰⁄₃₁₂₅], train_loss:0.157071 Epoch [²⁄₂], Iter [⁶⁷¹⁄₃₁₂₅], train_loss:0.188446 Epoch [²⁄₂], Iter [⁶⁷²⁄₃₁₂₅], train_loss:0.161760 Epoch [²⁄₂], Iter [⁶⁷³⁄₃₁₂₅], train_loss:0.155279 Epoch [²⁄₂], Iter [⁶⁷⁴⁄₃₁₂₅], train_loss:0.179824 Epoch [²⁄₂], Iter [⁶⁷⁵⁄₃₁₂₅], train_loss:0.167790 Epoch [²⁄₂], Iter [⁶⁷⁶⁄₃₁₂₅], train_loss:0.146095 Epoch [²⁄₂], Iter [⁶⁷⁷⁄₃₁₂₅], train_loss:0.177003 Epoch [²⁄₂], Iter [⁶⁷⁸⁄₃₁₂₅], train_loss:0.148537 Epoch [²⁄₂], Iter [⁶⁷⁹⁄₃₁₂₅], train_loss:0.152893 Epoch [²⁄₂], Iter [⁶⁸⁰⁄₃₁₂₅], train_loss:0.159080 Epoch [²⁄₂], Iter [⁶⁸¹⁄₃₁₂₅], train_loss:0.156266 Epoch [²⁄₂], Iter [⁶⁸²⁄₃₁₂₅], train_loss:0.166901 Epoch [²⁄₂], Iter [⁶⁸³⁄₃₁₂₅], train_loss:0.168217 Epoch [²⁄₂], Iter [⁶⁸⁴⁄₃₁₂₅], train_loss:0.169070 Epoch [²⁄₂], Iter [⁶⁸⁵⁄₃₁₂₅], train_loss:0.162491 Epoch [²⁄₂], Iter [⁶⁸⁶⁄₃₁₂₅], train_loss:0.168951 Epoch [²⁄₂], Iter [⁶⁸⁷⁄₃₁₂₅], train_loss:0.125869 Epoch [²⁄₂], Iter [⁶⁸⁸⁄₃₁₂₅], train_loss:0.181195 Epoch [²⁄₂], Iter [⁶⁸⁹⁄₃₁₂₅], train_loss:0.177369 Epoch [²⁄₂], Iter [⁶⁹⁰⁄₃₁₂₅], train_loss:0.161117 Epoch [²⁄₂], Iter [⁶⁹¹⁄₃₁₂₅], train_loss:0.157555 Epoch [²⁄₂], Iter [⁶⁹²⁄₃₁₂₅], train_loss:0.159016 Epoch [²⁄₂], Iter [⁶⁹³⁄₃₁₂₅], train_loss:0.157256 Epoch [²⁄₂], Iter [⁶⁹⁴⁄₃₁₂₅], train_loss:0.164547 Epoch [²⁄₂], Iter [⁶⁹⁵⁄₃₁₂₅], train_loss:0.165163 Epoch [²⁄₂], Iter [⁶⁹⁶⁄₃₁₂₅], train_loss:0.168598 Epoch [²⁄₂], Iter [⁶⁹⁷⁄₃₁₂₅], train_loss:0.167152 Epoch [²⁄₂], Iter [⁶⁹⁸⁄₃₁₂₅], train_loss:0.174982 Epoch [²⁄₂], Iter [⁶⁹⁹⁄₃₁₂₅], train_loss:0.150731 Epoch [²⁄₂], Iter [⁷⁰⁰⁄₃₁₂₅], train_loss:0.144726 Epoch [²⁄₂], Iter [⁷⁰¹⁄₃₁₂₅], train_loss:0.161515 Epoch [²⁄₂], Iter [⁷⁰²⁄₃₁₂₅], train_loss:0.168019 Epoch [²⁄₂], Iter [⁷⁰³⁄₃₁₂₅], train_loss:0.151221 Epoch [²⁄₂], Iter [⁷⁰⁴⁄₃₁₂₅], train_loss:0.155330 Epoch [²⁄₂], Iter [⁷⁰⁵⁄₃₁₂₅], train_loss:0.162497 Epoch [²⁄₂], Iter [⁷⁰⁶⁄₃₁₂₅], train_loss:0.146891 Epoch [²⁄₂], Iter [⁷⁰⁷⁄₃₁₂₅], train_loss:0.144152 Epoch [²⁄₂], Iter [⁷⁰⁸⁄₃₁₂₅], train_loss:0.169863 Epoch [²⁄₂], Iter [⁷⁰⁹⁄₃₁₂₅], train_loss:0.151497 Epoch [²⁄₂], Iter [⁷¹⁰⁄₃₁₂₅], train_loss:0.171949 Epoch [²⁄₂], Iter [⁷¹¹⁄₃₁₂₅], train_loss:0.144536 Epoch [²⁄₂], Iter [⁷¹²⁄₃₁₂₅], train_loss:0.174258 Epoch [²⁄₂], Iter [⁷¹³⁄₃₁₂₅], train_loss:0.156956 Epoch [²⁄₂], Iter [⁷¹⁴⁄₃₁₂₅], train_loss:0.143885 Epoch [²⁄₂], Iter [⁷¹⁵⁄₃₁₂₅], train_loss:0.154764 Epoch [²⁄₂], Iter [⁷¹⁶⁄₃₁₂₅], train_loss:0.158947 Epoch [²⁄₂], Iter [⁷¹⁷⁄₃₁₂₅], train_loss:0.169612 Epoch [²⁄₂], Iter [⁷¹⁸⁄₃₁₂₅], train_loss:0.183921 Epoch [²⁄₂], Iter [⁷¹⁹⁄₃₁₂₅], train_loss:0.164853 Epoch [²⁄₂], Iter [⁷²⁰⁄₃₁₂₅], train_loss:0.152667 Epoch [²⁄₂], Iter [⁷²¹⁄₃₁₂₅], train_loss:0.164879 Epoch [²⁄₂], Iter [⁷²²⁄₃₁₂₅], train_loss:0.162339 Epoch [²⁄₂], Iter [⁷²³⁄₃₁₂₅], train_loss:0.155902 Epoch [²⁄₂], Iter [⁷²⁴⁄₃₁₂₅], train_loss:0.166309 Epoch [²⁄₂], Iter [⁷²⁵⁄₃₁₂₅], train_loss:0.169535 Epoch [²⁄₂], Iter [⁷²⁶⁄₃₁₂₅], train_loss:0.157821 Epoch [²⁄₂], Iter [⁷²⁷⁄₃₁₂₅], train_loss:0.177206 Epoch [²⁄₂], Iter [⁷²⁸⁄₃₁₂₅], train_loss:0.161878 Epoch [²⁄₂], Iter [⁷²⁹⁄₃₁₂₅], train_loss:0.165634 Epoch [²⁄₂], Iter [⁷³⁰⁄₃₁₂₅], train_loss:0.162080 Epoch [²⁄₂], Iter [⁷³¹⁄₃₁₂₅], train_loss:0.149615 Epoch [²⁄₂], Iter [⁷³²⁄₃₁₂₅], train_loss:0.157824 Epoch [²⁄₂], Iter [⁷³³⁄₃₁₂₅], train_loss:0.160058 Epoch [²⁄₂], Iter [⁷³⁴⁄₃₁₂₅], train_loss:0.164464 Epoch [²⁄₂], Iter [⁷³⁵⁄₃₁₂₅], train_loss:0.173593 Epoch [²⁄₂], Iter [⁷³⁶⁄₃₁₂₅], train_loss:0.177152 Epoch [²⁄₂], Iter [⁷³⁷⁄₃₁₂₅], train_loss:0.185746 Epoch [²⁄₂], Iter [⁷³⁸⁄₃₁₂₅], train_loss:0.161387 Epoch [²⁄₂], Iter [⁷³⁹⁄₃₁₂₅], train_loss:0.163264 Epoch [²⁄₂], Iter [⁷⁴⁰⁄₃₁₂₅], train_loss:0.165813 Epoch [²⁄₂], Iter [⁷⁴¹⁄₃₁₂₅], train_loss:0.172456 Epoch [²⁄₂], Iter [⁷⁴²⁄₃₁₂₅], train_loss:0.173366 Epoch [²⁄₂], Iter [⁷⁴³⁄₃₁₂₅], train_loss:0.167722 Epoch [²⁄₂], Iter [⁷⁴⁴⁄₃₁₂₅], train_loss:0.152204 Epoch [²⁄₂], Iter [⁷⁴⁵⁄₃₁₂₅], train_loss:0.162796 Epoch [²⁄₂], Iter [⁷⁴⁶⁄₃₁₂₅], train_loss:0.148085 Epoch [²⁄₂], Iter [⁷⁴⁷⁄₃₁₂₅], train_loss:0.138988 Epoch [²⁄₂], Iter [⁷⁴⁸⁄₃₁₂₅], train_loss:0.165154 Epoch [²⁄₂], Iter [⁷⁴⁹⁄₃₁₂₅], train_loss:0.163704 Epoch [²⁄₂], Iter [⁷⁵⁰⁄₃₁₂₅], train_loss:0.139482 Epoch [²⁄₂], Iter [⁷⁵¹⁄₃₁₂₅], train_loss:0.146638 Epoch [²⁄₂], Iter [⁷⁵²⁄₃₁₂₅], train_loss:0.179230 Epoch [²⁄₂], Iter [⁷⁵³⁄₃₁₂₅], train_loss:0.168096 Epoch [²⁄₂], Iter [⁷⁵⁴⁄₃₁₂₅], train_loss:0.157946 Epoch [²⁄₂], Iter [⁷⁵⁵⁄₃₁₂₅], train_loss:0.121326 Epoch [²⁄₂], Iter [⁷⁵⁶⁄₃₁₂₅], train_loss:0.160800 Epoch [²⁄₂], Iter [⁷⁵⁷⁄₃₁₂₅], train_loss:0.143741 Epoch [²⁄₂], Iter [⁷⁵⁸⁄₃₁₂₅], train_loss:0.164546 Epoch [²⁄₂], Iter [⁷⁵⁹⁄₃₁₂₅], train_loss:0.153188 Epoch [²⁄₂], Iter [⁷⁶⁰⁄₃₁₂₅], train_loss:0.153755 Epoch [²⁄₂], Iter [⁷⁶¹⁄₃₁₂₅], train_loss:0.156617 Epoch [²⁄₂], Iter [⁷⁶²⁄₃₁₂₅], train_loss:0.165343 Epoch [²⁄₂], Iter [⁷⁶³⁄₃₁₂₅], train_loss:0.152439 Epoch [²⁄₂], Iter [⁷⁶⁴⁄₃₁₂₅], train_loss:0.150895 Epoch [²⁄₂], Iter [⁷⁶⁵⁄₃₁₂₅], train_loss:0.171088 Epoch [²⁄₂], Iter [⁷⁶⁶⁄₃₁₂₅], train_loss:0.152008 Epoch [²⁄₂], Iter [⁷⁶⁷⁄₃₁₂₅], train_loss:0.159565 Epoch [²⁄₂], Iter [⁷⁶⁸⁄₃₁₂₅], train_loss:0.141178 Epoch [²⁄₂], Iter [⁷⁶⁹⁄₃₁₂₅], train_loss:0.151271 Epoch [²⁄₂], Iter [⁷⁷⁰⁄₃₁₂₅], train_loss:0.141239 Epoch [²⁄₂], Iter [⁷⁷¹⁄₃₁₂₅], train_loss:0.178049 Epoch [²⁄₂], Iter [⁷⁷²⁄₃₁₂₅], train_loss:0.181188 Epoch [²⁄₂], Iter [⁷⁷³⁄₃₁₂₅], train_loss:0.173826 Epoch [²⁄₂], Iter [⁷⁷⁴⁄₃₁₂₅], train_loss:0.175326 Epoch [²⁄₂], Iter [⁷⁷⁵⁄₃₁₂₅], train_loss:0.167236 Epoch [²⁄₂], Iter [⁷⁷⁶⁄₃₁₂₅], train_loss:0.149285 Epoch [²⁄₂], Iter [⁷⁷⁷⁄₃₁₂₅], train_loss:0.153321 Epoch [²⁄₂], Iter [⁷⁷⁸⁄₃₁₂₅],

上一篇：呼和浩特网站优化公司网站模版属于侵权吗
下一篇：呼市网站制作招聘网站建设表格

呼伦贝尔网站设计百度中搜到网站名字

批次的大小

优化器的学习率

方案二使用“device”后续对要使用GPU的变量用.to(device)即可

下载预训练模型 restnet50

print(test_total_correct: str(test_total_correct))return test_total_correcttotal_correct cal_predict_correct(resnet34)

定义损失函数和优化器

损失函数自定义损失函数

优化器

相关文章

呼和浩特网站优化公司网站模版属于侵权吗

呼和浩特网站建设哪家好Wordpress判断来路显示

呼和浩特网站建设电话上国外网站速度慢

呼市网站制作招聘网站建设表格

壶关网站建设wordpress目录标题

壶关网站建设小型加工厂管理软件

WordPress建站 – WordPress大学

后台定制 – WordPress大学

为 WordPress 分类描述添加可视化编辑器，支持自定义分类法

优化首次内容绘制 (FCP) ，提高 WordPress 网站速度得分

WordPress开发 – WordPress大学

新手入门 – WordPress大学

呼伦贝尔网站设计百度中搜到网站名字

批次的大小

优化器的学习率

方案二使用“device”后续对要使用GPU的变量用.to(device)即可

下载预训练模型 restnet50

print(test_total_correct: str(test_total_correct))return test_total_correcttotal_correct cal_predict_correct(resnet34)

定义损失函数和优化器

损失函数自定义损失函数

优化器

相关文章

呼和浩特网站优化公司网站模版属于侵权吗

呼和浩特网站建设哪家好Wordpress判断来路 显示

呼和浩特网站建设电话上国外网站速度慢

呼市网站制作招聘网站建设表格

壶关网站建设wordpress目录标题

壶关网站建设小型加工厂管理软件

WordPress建站 – WordPress大学

后台定制 – WordPress大学

为 WordPress 分类描述添加可视化编辑器，支持自定义分类法

优化首次内容绘制 (FCP) ，提高 WordPress 网站速度得分

WordPress开发 – WordPress大学

新手入门 – WordPress大学

呼和浩特网站建设哪家好Wordpress判断来路显示