{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":85517,"databundleVersionId":9677541,"sourceType":"competition"},{"sourceId":9672386,"sourceType":"datasetVersion","datasetId":5910912}],"dockerImageVersionId":30787,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n for filename in filenames:\n print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-10-20T07:08:00.728166Z","iopub.execute_input":"2024-10-20T07:08:00.728548Z","iopub.status.idle":"2024-10-20T07:08:00.75064Z","shell.execute_reply.started":"2024-10-20T07:08:00.728511Z","shell.execute_reply":"2024-10-20T07:08:00.749792Z"},"trusted":true},"execution_count":4,"outputs":[{"name":"stdout","text":"/kaggle/input/col-774-a-3/train.pkl\n/kaggle/input/col-774-a-3/test.pkl\n/kaggle/input/model-final/model_final.pth\n","output_type":"stream"}]},{"cell_type":"code","source":"import torch\nimport pickle\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.utils.data import DataLoader, random_split\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torchvision import datasets, transforms, models\nfrom torch.optim.lr_scheduler import CosineAnnealingLR\nimport torch\nimport pickle\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.utils.data import DataLoader, random_split, Subset\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torchvision import datasets, transforms, models\nfrom torch.optim.lr_scheduler import CosineAnnealingLR\nimport torch.nn.functional as F\nfrom sklearn.model_selection import StratifiedKFold\nfrom collections import defaultdict\nimport numpy as np\nfrom sklearn.metrics import precision_recall_curve, precision_score, accuracy_score\nfrom sklearn.metrics import confusion_matrix\nimport math\nimport random","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:00.7523Z","iopub.execute_input":"2024-10-20T07:08:00.752569Z","iopub.status.idle":"2024-10-20T07:08:04.032443Z","shell.execute_reply.started":"2024-10-20T07:08:00.752539Z","shell.execute_reply":"2024-10-20T07:08:04.031604Z"},"trusted":true},"execution_count":5,"outputs":[]},{"cell_type":"code","source":"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.033619Z","iopub.execute_input":"2024-10-20T07:08:04.034106Z","iopub.status.idle":"2024-10-20T07:08:04.074644Z","shell.execute_reply.started":"2024-10-20T07:08:04.034072Z","shell.execute_reply":"2024-10-20T07:08:04.073535Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"seed = 42\ntorch.manual_seed(seed)\ntorch.cuda.manual_seed(seed) # If using CUDA\nnp.random.seed(seed)\nrandom.seed(seed)\ntorch.backends.cudnn.deterministic = True # Enforce deterministic behavior\ntorch.backends.cudnn.benchmark = False","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.077679Z","iopub.execute_input":"2024-10-20T07:08:04.078101Z","iopub.status.idle":"2024-10-20T07:08:04.089745Z","shell.execute_reply.started":"2024-10-20T07:08:04.078057Z","shell.execute_reply":"2024-10-20T07:08:04.088948Z"},"trusted":true},"execution_count":7,"outputs":[]},{"cell_type":"code","source":"transform = transforms.Compose([\n transforms.RandomCrop(32, padding=4),\n transforms.RandomHorizontalFlip(),\n transforms.Normalize((0.5071, 0.4867, 0.4408), (0.2675, 0.2565, 0.2761)),\n])","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.090958Z","iopub.execute_input":"2024-10-20T07:08:04.091344Z","iopub.status.idle":"2024-10-20T07:08:04.099171Z","shell.execute_reply.started":"2024-10-20T07:08:04.091302Z","shell.execute_reply":"2024-10-20T07:08:04.098308Z"},"trusted":true},"execution_count":8,"outputs":[]},{"cell_type":"code","source":"import numpy as np\nimport torch\nimport torch.nn.functional as F\n\n# rank target entropy\ndef negative_entropy(data, normalize=False, max_value=None):\n softmax = F.softmax(data, dim=1)\n log_softmax = F.log_softmax(data, dim=1)\n entropy = softmax * log_softmax\n entropy = -1.0 * entropy.sum(dim=1)\n # normalize [0 ~ 1]\n if normalize:\n normalized_entropy = entropy / max_value\n return -normalized_entropy\n\n return -entropy\n\n# correctness history class\nclass History(object):\n def __init__(self, n_data):\n self.correctness = np.zeros((n_data))\n self.confidence = np.zeros((n_data))\n self.max_correctness = 1\n\n # correctness update\n def correctness_update(self, data_idx, correctness, output):\n probs = torch.nn.functional.softmax(output, dim=1)\n confidence, _ = probs.max(dim=1)\n data_idx = data_idx.cpu().numpy()\n\n self.correctness[data_idx] += correctness.cpu().numpy()\n self.confidence[data_idx] = confidence.cpu().detach().numpy()\n\n # max correctness update\n def max_correctness_update(self, epoch):\n if epoch > 1:\n self.max_correctness += 1\n\n # correctness normalize (0 ~ 1) range\n def correctness_normalize(self, data):\n data_min = self.correctness.min()\n data_max = float(self.max_correctness)\n\n return (data - data_min) / (data_max - data_min)\n\n # get target & margin\n def get_target_margin(self, data_idx1, data_idx2):\n data_idx1 = data_idx1.cpu().numpy()\n cum_correctness1 = self.correctness[data_idx1]\n cum_correctness2 = self.correctness[data_idx2]\n # normalize correctness values\n cum_correctness1 = self.correctness_normalize(cum_correctness1)\n cum_correctness2 = self.correctness_normalize(cum_correctness2)\n # make target pair\n n_pair = len(data_idx1)\n target1 = cum_correctness1[:n_pair]\n target2 = cum_correctness2[:n_pair]\n # calc target\n greater = np.array(target1 > target2, dtype='float')\n less = np.array(target1 < target2, dtype='float') * (-1)\n\n target = greater + less\n target = torch.from_numpy(target).float().cuda()\n # calc margin\n margin = abs(target1 - target2)\n margin = torch.from_numpy(margin).float().cuda()\n\n return target, margin","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.100599Z","iopub.execute_input":"2024-10-20T07:08:04.101003Z","iopub.status.idle":"2024-10-20T07:08:04.115654Z","shell.execute_reply.started":"2024-10-20T07:08:04.10097Z","shell.execute_reply":"2024-10-20T07:08:04.114765Z"},"trusted":true},"execution_count":9,"outputs":[]},{"cell_type":"code","source":"class CIFAR100Dataset(Dataset):\n def __init__(self, file_path, transform):\n self.transform = transform\n with open(file_path, 'rb') as f:\n self.data = pickle.load(f)\n\n def __len__(self):\n return len(self.data)\n\n def __getitem__(self, idx):\n image, label = self.data[idx]\n if self.transform:\n image = self.transform(image)\n return image, label, idx\n\n\n# Load CIFAR-100 dataset\ndef load_data(train_file, transform):\n trainset = CIFAR100Dataset(train_file, transform)\n print(f\"Size of the train set: {len(trainset)} samples\")\n return trainset","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.116854Z","iopub.execute_input":"2024-10-20T07:08:04.117156Z","iopub.status.idle":"2024-10-20T07:08:04.129221Z","shell.execute_reply.started":"2024-10-20T07:08:04.117119Z","shell.execute_reply":"2024-10-20T07:08:04.128319Z"},"trusted":true},"execution_count":10,"outputs":[]},{"cell_type":"code","source":"class DenseNetWithDropout(nn.Module):\n def __init__(self, dropout_rate=0.5):\n super(DenseNetWithDropout, self).__init__()\n # Load the pretrained DenseNet121 model\n self.densenet = models.densenet121(weights=None) # Set to True if pretrained is allowed\n\n # Add dropout after each dense block\n self.densenet.classifier = nn.Sequential(\n nn.Dropout(p=dropout_rate), # Dropout layer before the final classification layer\n nn.Linear(self.densenet.classifier.in_features, 100) # Adjust for CIFAR-100\n )\n\n def forward(self, x):\n return self.densenet(x)\n# model = DenseNetWithDropout() # No pre-training\nmodel = models.densenet121(weights=None)\n# Modify the classifier to output 100 classes for CIFAR-100\n# model.classifier[1] = torch.nn.Linear(model.classifier[1].in_features, 100)\nmodel.classifier = nn.Linear(model.classifier.in_features, 100)\n\n# Move the model to the appropriate device (GPU or CPU)\nmodel = model.to(device)\n\n# Loss function (Cross-Entropy with L2 regularization)\ncriterion = nn.CrossEntropyLoss()\n# criterion = FocalLoss()\n\n# Optimizer with L2 regularization\n# Assuming 'model' is your defined neural network\noptimizer = optim.SGD(model.parameters(),\n lr=0.1,\n momentum=0.9,\n weight_decay=0.0001,\n nesterov=False)\n\n# optimizer = optim.Adam(model.parameters(),lr=0.001, eps=1e-2)\n# class_thresholds = np.ones(100) * 0.7\n# scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='min', patience=2, factor=0.1)\n# scheduler = optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=200)\nscheduler = optim.lr_scheduler.MultiStepLR(optimizer,\n milestones=[150,250],\n gamma=0.1)\n\n","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.130228Z","iopub.execute_input":"2024-10-20T07:08:04.130524Z","iopub.status.idle":"2024-10-20T07:08:04.694669Z","shell.execute_reply.started":"2024-10-20T07:08:04.130483Z","shell.execute_reply":"2024-10-20T07:08:04.69366Z"},"trusted":true},"execution_count":11,"outputs":[]},{"cell_type":"code","source":"def accuracy(output, target, topk=(1,)):\n \"\"\"Computes the precision@k for the specified values of k\"\"\"\n maxk = max(topk)\n batch_size = target.size(0)\n\n _, pred = output.topk(maxk, 1, True, True)\n pred = pred.t()\n correct = pred.eq(target.view(1, -1).expand_as(pred))\n\n res = []\n for k in topk:\n correct_k = correct[:k].view(-1).float().sum(0)\n res.append(correct_k.mul_(100.0 / batch_size))\n return res[0], correct.squeeze()\n\nclass AverageMeter(object):\n def __init__(self):\n self.reset()\n\n def reset(self):\n self.val = 0\n self.avg = 0\n self.sum = 0\n self.count = 0\n\n def update(self, val, n=1):\n self.val = val\n self.sum += val * n\n self.count += n\n self.avg = self.sum / self.count","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.695761Z","iopub.execute_input":"2024-10-20T07:08:04.696074Z","iopub.status.idle":"2024-10-20T07:08:04.705125Z","shell.execute_reply.started":"2024-10-20T07:08:04.696042Z","shell.execute_reply":"2024-10-20T07:08:04.704268Z"},"trusted":true},"execution_count":12,"outputs":[]},{"cell_type":"code","source":"import time\ndef train_model(model, trainloader, criterion, optimizer, model_file,gamma,alpha,history, ranking_criterion,num_epochs):\n# criterion = nn.CrossEntropyLoss(weight=calculate_class_weights(val_loader, model, alpha=0.99, gamma=5))\n\n# best_val_loss = math.inf\n batch_time = AverageMeter()\n data_time = AverageMeter()\n total_losses = AverageMeter()\n top1 = AverageMeter()\n cls_losses = AverageMeter()\n ranking_losses = AverageMeter()\n end = time.time()\n model.train()\n for epoch in range(num_epochs):\n running_loss = 0.0\n correct_predictions = 0\n total_predictions = 0\n for i, (inputs, targets, idx) in enumerate(trainloader):\n data_time.update(time.time() - end)\n inputs, targets = inputs.to(device), targets.to(device)\n\n optimizer.zero_grad()\n\n output = model(inputs)\n # Modify the loss function to apply class weights based on the accuracy of each class\n conf = F.softmax(output, dim=1)\n confidence, _ = conf.max(dim=1)\n rank_input1 = confidence\n rank_input2 = torch.roll(confidence, -1)\n idx2 = torch.roll(idx, -1)\n\n\n rank_target, rank_margin = history.get_target_margin(idx, idx2)\n rank_target_nonzero = rank_target.clone()\n rank_target_nonzero[rank_target_nonzero == 0] = 1\n rank_input2 = rank_input2 + rank_margin / rank_target_nonzero\n\n # ranking loss\n ranking_loss = ranking_criterion(rank_input1,\n rank_input2,\n rank_target)\n\n # total loss\n cls_loss = criterion(output, targets)\n ranking_loss = 5 * ranking_loss\n loss = cls_loss + ranking_loss\n\n # loss = criterion(outputs, targets)\n\n # Add false positive penalty (penalizing classes with low precision)\n# fp_penalty = calculate_false_positive_penalty(outputs, targets, class_thresholds, gamma, alpha)\n# weighted_fp_penalty = gamma * fp_penalty # Scale down penalty, adjust weight as needed\n# loss += fp_penalty\n\n loss.backward()\n optimizer.step()\n\n prec, correct = accuracy(output, targets)\n total_losses.update(loss.item(), inputs.size(0))\n cls_losses.update(cls_loss.item(), inputs.size(0))\n ranking_losses.update(ranking_loss.item(), inputs.size(0))\n top1.update(prec.item(), inputs.size(0))\n\n batch_time.update(time.time() - end)\n end = time.time()\n if i % 100 == 0:\n print('Epoch: [{0}][{1}/{2}]\\t'\n 'Time {batch_time.val:.3f} ({batch_time.avg:.3f})\\t'\n 'Data {data_time.val:.3f} ({data_time.avg:.3f})\\t'\n 'Loss {loss.val:.4f} ({loss.avg:.4f})\\t'\n 'Cls Loss {cls_loss.val:.4f} ({cls_loss.avg:.4f})\\t'\n 'Rank Loss {rank_loss.val:.4f} ({rank_loss.avg:.4f})\\t'\n 'Prec {top1.val:.2f}% ({top1.avg:.2f}%)'.format(\n epoch, i, len(trainloader), batch_time=batch_time,\n data_time=data_time, loss=total_losses, cls_loss=cls_losses,\n rank_loss=ranking_losses,top1=top1))\n history.correctness_update(idx, correct, output)\n history.max_correctness_update(epoch)\n\n # print(f\"Epoch {epoch+1}/{num_epochs}, Loss: {running_loss/len(trainloader)}, Accuracy : {train_accuracy}\")\n# val_loss, _, val_accuracy = evaluate_model(model, val_loader)\n# print(f\"Validation Loss: {val_loss}, Validation Accuracy: {val_accuracy:.4f}\")\n scheduler.step()\n # Save the best model based on validation loss\n# if val_loss < best_val_loss:\n# best_val_loss = val_loss\n# torch.save(model.state_dict(), model_file)\n# print(\"Best model saved!\")\n torch.save(model.state_dict(), model_file)\n print(\"Model saved as model.pth\")","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.708024Z","iopub.execute_input":"2024-10-20T07:08:04.708327Z","iopub.status.idle":"2024-10-20T07:08:04.7243Z","shell.execute_reply.started":"2024-10-20T07:08:04.708293Z","shell.execute_reply":"2024-10-20T07:08:04.723358Z"},"trusted":true},"execution_count":13,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\ntest_transform = transforms.Compose([\n# transforms.ToTensor(),\n transforms.Normalize((0.5071, 0.4867, 0.4408), (0.2675, 0.2565, 0.2761)),\n])\ntrain_file = \"/kaggle/input/col-774-a-3/train.pkl\"\n# Load your data\nmodel_file = f\"model_fold.pth\"\ntrain_data = load_data(train_file, transform)\n# holdout_data = load_data(train_file, test_transform)\n\n# Extract labels\n# labels = [train_data[i][1] for i in range(len(train_data))]\n\n# Split the data into a training set (e.g., 80%) and a holdout set (e.g., 20%)\n# train_indices, holdout_indices = train_test_split(\n # range(len(train_data)), test_size=0.1, stratify=labels, random_state=42\n# )\n\n# Create Subsets for training and holdout data\n# train_subset = Subset(train_data, train_indices)\n# holdout_subset = Subset(holdout_data, holdout_indices)\n\n# Create DataLoaders for training and holdout sets\ntrain_loader = DataLoader(train_data, batch_size=128, shuffle=True)\n# holdout_loader = DataLoader(holdout_subset, batch_size=128, shuffle=False)\n\n# Check the sizes of your datasets\n# print(f\"Training Set Size: {len(train_subset)}\")\n# print(f\"Holdout Set Size: {len(holdout_subset)}\")\n","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:08:04.725626Z","iopub.execute_input":"2024-10-20T07:08:04.725938Z","iopub.status.idle":"2024-10-20T07:08:13.951414Z","shell.execute_reply.started":"2024-10-20T07:08:04.725894Z","shell.execute_reply":"2024-10-20T07:08:13.950424Z"},"trusted":true},"execution_count":14,"outputs":[{"name":"stderr","text":"/opt/conda/lib/python3.10/site-packages/torch/storage.py:414: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n return torch.load(io.BytesIO(b))\n","output_type":"stream"},{"name":"stdout","text":"Size of the train set: 40000 samples\n","output_type":"stream"}]},{"cell_type":"code","source":"gamma = 5\nalpha = 0.99\ncorrectness_history = History(len(train_loader.dataset))\nranking_criterion = nn.MarginRankingLoss(margin=0.0).cuda()\ntrain_model(model, train_loader, criterion, optimizer, model_file, gamma, alpha,correctness_history,ranking_criterion, num_epochs=200)","metadata":{"execution":{"iopub.status.busy":"2024-10-20T09:00:00.360222Z","iopub.execute_input":"2024-10-20T09:00:00.360713Z","iopub.status.idle":"2024-10-20T10:36:48.854179Z","shell.execute_reply.started":"2024-10-20T09:00:00.360658Z","shell.execute_reply":"2024-10-20T10:36:48.853171Z"},"trusted":true},"execution_count":20,"outputs":[{"name":"stdout","text":"Epoch: [0][0/313]\tTime 0.156 (0.156)\tData 0.052 (0.052)\tLoss 0.4920 (0.4920)\tCls Loss 0.4920 (0.4920)\tRank Loss 0.0000 (0.0000)\tPrec 89.06% (89.06%)\nEpoch: [0][100/313]\tTime 0.092 (0.096)\tData 0.027 (0.030)\tLoss 0.5177 (0.4773)\tCls Loss 0.5177 (0.4773)\tRank Loss 0.0000 (0.0000)\tPrec 83.59% (88.27%)\nEpoch: [0][200/313]\tTime 0.093 (0.095)\tData 0.027 (0.029)\tLoss 0.4820 (0.4951)\tCls Loss 0.4820 (0.4951)\tRank Loss 0.0000 (0.0000)\tPrec 85.94% (86.41%)\nEpoch: [0][300/313]\tTime 0.093 (0.095)\tData 0.028 (0.029)\tLoss 0.6153 (0.5190)\tCls Loss 0.6153 (0.5190)\tRank Loss 0.0000 (0.0000)\tPrec 78.91% (84.88%)\nEpoch: [1][0/313]\tTime 0.100 (0.095)\tData 0.034 (0.029)\tLoss 1.5465 (0.5255)\tCls Loss 0.4091 (0.5219)\tRank Loss 1.1374 (0.0036)\tPrec 89.06% (84.74%)\nEpoch: [1][100/313]\tTime 0.092 (0.095)\tData 0.027 (0.029)\tLoss 1.9578 (0.8747)\tCls Loss 0.9812 (0.6260)\tRank Loss 0.9766 (0.2487)\tPrec 66.41% (81.48%)\nEpoch: [1][200/313]\tTime 0.097 (0.095)\tData 0.030 (0.029)\tLoss 2.2146 (1.1307)\tCls Loss 1.2472 (0.7370)\tRank Loss 0.9674 (0.3936)\tPrec 61.72% (78.21%)\nEpoch: [1][300/313]\tTime 0.093 (0.095)\tData 0.028 (0.029)\tLoss 2.2859 (1.2986)\tCls Loss 1.2527 (0.8123)\tRank Loss 1.0332 (0.4863)\tPrec 64.84% (76.03%)\nEpoch: [2][0/313]\tTime 0.096 (0.095)\tData 0.032 (0.029)\tLoss 4.1170 (1.3223)\tCls Loss 1.1567 (0.8212)\tRank Loss 2.9603 (0.5012)\tPrec 64.84% (75.79%)\nEpoch: [2][100/313]\tTime 0.092 (0.095)\tData 0.027 (0.029)\tLoss 3.5358 (1.6759)\tCls Loss 1.2431 (0.8887)\tRank Loss 2.2928 (0.7872)\tPrec 65.62% (74.07%)\nEpoch: [2][200/313]\tTime 0.093 (0.095)\tData 0.028 (0.029)\tLoss 4.3524 (1.9650)\tCls Loss 1.5557 (0.9538)\tRank Loss 2.7967 (1.0112)\tPrec 54.69% (72.35%)\nEpoch: [2][300/313]\tTime 0.092 (0.095)\tData 0.027 (0.029)\tLoss 4.1456 (2.1991)\tCls Loss 1.3620 (1.0099)\tRank Loss 2.7836 (1.1892)\tPrec 60.94% (70.82%)\nEpoch: [3][0/313]\tTime 0.096 (0.095)\tData 0.032 (0.029)\tLoss 3.4009 (2.2228)\tCls Loss 1.3211 (1.0159)\tRank Loss 2.0798 (1.2068)\tPrec 60.16% (70.67%)\nEpoch: [3][100/313]\tTime 0.092 (0.095)\tData 0.028 (0.029)\tLoss 3.4858 (2.3159)\tCls Loss 1.5055 (1.0531)\tRank Loss 1.9803 (1.2628)\tPrec 61.72% (69.72%)\nEpoch: [3][200/313]\tTime 0.092 (0.094)\tData 0.028 (0.029)\tLoss 2.9928 (2.3970)\tCls Loss 1.3579 (1.0870)\tRank Loss 1.6349 (1.3100)\tPrec 57.81% (68.82%)\nEpoch: [3][300/313]\tTime 0.095 (0.094)\tData 0.028 (0.029)\tLoss 3.4542 (2.4705)\tCls Loss 1.6571 (1.1200)\tRank Loss 1.7971 (1.3506)\tPrec 49.22% (67.98%)\nEpoch: [4][0/313]\tTime 0.102 (0.094)\tData 0.034 (0.029)\tLoss 3.0933 (2.4809)\tCls Loss 1.4445 (1.1239)\tRank Loss 1.6487 (1.3570)\tPrec 56.25% (67.88%)\nEpoch: [4][100/313]\tTime 0.094 (0.094)\tData 0.027 (0.029)\tLoss 2.6102 (2.5135)\tCls Loss 1.2437 (1.1453)\tRank Loss 1.3665 (1.3682)\tPrec 63.28% (67.29%)\nEpoch: [4][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.029)\tLoss 3.0719 (2.5452)\tCls Loss 1.4434 (1.1644)\tRank Loss 1.6286 (1.3808)\tPrec 60.94% (66.80%)\nEpoch: [4][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.029)\tLoss 2.7327 (2.5773)\tCls Loss 1.4044 (1.1860)\tRank Loss 1.3284 (1.3913)\tPrec 59.38% (66.25%)\nEpoch: [5][0/313]\tTime 0.096 (0.094)\tData 0.030 (0.029)\tLoss 2.6711 (2.5806)\tCls Loss 1.3238 (1.1884)\tRank Loss 1.3473 (1.3922)\tPrec 64.84% (66.18%)\nEpoch: [5][100/313]\tTime 0.093 (0.094)\tData 0.027 (0.029)\tLoss 2.8142 (2.5915)\tCls Loss 1.4636 (1.2011)\tRank Loss 1.3505 (1.3904)\tPrec 54.69% (65.83%)\nEpoch: [5][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.029)\tLoss 3.4137 (2.6047)\tCls Loss 1.7601 (1.2140)\tRank Loss 1.6535 (1.3907)\tPrec 46.88% (65.47%)\nEpoch: [5][300/313]\tTime 0.094 (0.094)\tData 0.030 (0.029)\tLoss 3.2089 (2.6185)\tCls Loss 1.4001 (1.2269)\tRank Loss 1.8088 (1.3916)\tPrec 61.72% (65.13%)\nEpoch: [6][0/313]\tTime 0.098 (0.094)\tData 0.032 (0.029)\tLoss 2.6456 (2.6206)\tCls Loss 1.3387 (1.2286)\tRank Loss 1.3069 (1.3919)\tPrec 64.84% (65.09%)\nEpoch: [6][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.029)\tLoss 2.6957 (2.6211)\tCls Loss 1.5070 (1.2352)\tRank Loss 1.1887 (1.3858)\tPrec 57.81% (64.92%)\nEpoch: [6][200/313]\tTime 0.094 (0.094)\tData 0.029 (0.029)\tLoss 2.5226 (2.6232)\tCls Loss 1.2410 (1.2427)\tRank Loss 1.2815 (1.3805)\tPrec 66.41% (64.72%)\nEpoch: [6][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.029)\tLoss 2.6391 (2.6279)\tCls Loss 1.4689 (1.2514)\tRank Loss 1.1702 (1.3765)\tPrec 60.16% (64.45%)\nEpoch: [7][0/313]\tTime 0.095 (0.094)\tData 0.031 (0.029)\tLoss 2.4170 (2.6285)\tCls Loss 1.2764 (1.2523)\tRank Loss 1.1406 (1.3762)\tPrec 62.50% (64.42%)\nEpoch: [7][100/313]\tTime 0.094 (0.094)\tData 0.030 (0.029)\tLoss 2.4480 (2.6241)\tCls Loss 1.2617 (1.2562)\tRank Loss 1.1863 (1.3678)\tPrec 64.84% (64.31%)\nEpoch: [7][200/313]\tTime 0.089 (0.094)\tData 0.027 (0.029)\tLoss 2.4877 (2.6246)\tCls Loss 1.2991 (1.2617)\tRank Loss 1.1887 (1.3629)\tPrec 65.62% (64.16%)\nEpoch: [7][300/313]\tTime 0.094 (0.094)\tData 0.027 (0.029)\tLoss 2.6182 (2.6257)\tCls Loss 1.3487 (1.2676)\tRank Loss 1.2695 (1.3581)\tPrec 60.94% (63.99%)\nEpoch: [8][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.029)\tLoss 2.2899 (2.6258)\tCls Loss 1.2623 (1.2683)\tRank Loss 1.0276 (1.3574)\tPrec 64.06% (63.97%)\nEpoch: [8][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.029)\tLoss 2.2534 (2.6207)\tCls Loss 1.3298 (1.2710)\tRank Loss 0.9236 (1.3497)\tPrec 60.16% (63.89%)\nEpoch: [8][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.029)\tLoss 2.7573 (2.6184)\tCls Loss 1.4175 (1.2746)\tRank Loss 1.3398 (1.3438)\tPrec 61.72% (63.80%)\nEpoch: [8][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.029)\tLoss 2.3730 (2.6160)\tCls Loss 1.3266 (1.2787)\tRank Loss 1.0465 (1.3374)\tPrec 63.28% (63.70%)\nEpoch: [9][0/313]\tTime 0.097 (0.094)\tData 0.032 (0.029)\tLoss 2.1928 (2.6156)\tCls Loss 1.3626 (1.2793)\tRank Loss 0.8302 (1.3363)\tPrec 60.16% (63.68%)\nEpoch: [9][100/313]\tTime 0.092 (0.094)\tData 0.028 (0.029)\tLoss 2.1060 (2.6084)\tCls Loss 1.2286 (1.2798)\tRank Loss 0.8773 (1.3286)\tPrec 68.75% (63.66%)\nEpoch: [9][200/313]\tTime 0.092 (0.094)\tData 0.027 (0.029)\tLoss 2.3905 (2.6051)\tCls Loss 1.3358 (1.2825)\tRank Loss 1.0547 (1.3226)\tPrec 53.91% (63.58%)\nEpoch: [9][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.029)\tLoss 2.9819 (2.6019)\tCls Loss 1.6221 (1.2855)\tRank Loss 1.3597 (1.3163)\tPrec 55.47% (63.49%)\nEpoch: [10][0/313]\tTime 0.097 (0.094)\tData 0.031 (0.029)\tLoss 1.9404 (2.6018)\tCls Loss 1.0396 (1.2860)\tRank Loss 0.9007 (1.3158)\tPrec 70.31% (63.48%)\nEpoch: [10][100/313]\tTime 0.092 (0.094)\tData 0.028 (0.029)\tLoss 2.2988 (2.5951)\tCls Loss 1.2052 (1.2865)\tRank Loss 1.0936 (1.3086)\tPrec 64.06% (63.47%)\nEpoch: [10][200/313]\tTime 0.092 (0.094)\tData 0.027 (0.029)\tLoss 2.3146 (2.5890)\tCls Loss 1.3208 (1.2872)\tRank Loss 0.9938 (1.3018)\tPrec 60.94% (63.44%)\nEpoch: [10][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.029)\tLoss 2.6969 (2.5850)\tCls Loss 1.5794 (1.2892)\tRank Loss 1.1174 (1.2959)\tPrec 53.91% (63.39%)\nEpoch: [11][0/313]\tTime 0.104 (0.094)\tData 0.033 (0.029)\tLoss 2.2595 (2.5844)\tCls Loss 1.2747 (1.2895)\tRank Loss 0.9849 (1.2949)\tPrec 67.97% (63.38%)\nEpoch: [11][100/313]\tTime 0.091 (0.094)\tData 0.028 (0.028)\tLoss 2.3740 (2.5770)\tCls Loss 1.3325 (1.2894)\tRank Loss 1.0416 (1.2876)\tPrec 61.72% (63.37%)\nEpoch: [11][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.3429 (2.5707)\tCls Loss 1.2019 (1.2898)\tRank Loss 1.1411 (1.2809)\tPrec 70.31% (63.35%)\nEpoch: [11][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.5361 (2.5648)\tCls Loss 1.4170 (1.2900)\tRank Loss 1.1190 (1.2748)\tPrec 57.81% (63.34%)\nEpoch: [12][0/313]\tTime 0.105 (0.094)\tData 0.035 (0.028)\tLoss 2.5193 (2.5640)\tCls Loss 1.2681 (1.2899)\tRank Loss 1.2512 (1.2741)\tPrec 66.41% (63.34%)\nEpoch: [12][100/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.1081 (2.5565)\tCls Loss 1.1493 (1.2893)\tRank Loss 0.9588 (1.2671)\tPrec 67.19% (63.35%)\nEpoch: [12][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.029)\tLoss 2.1302 (2.5514)\tCls Loss 1.1754 (1.2898)\tRank Loss 0.9549 (1.2616)\tPrec 65.62% (63.34%)\nEpoch: [12][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.029)\tLoss 2.3037 (2.5474)\tCls Loss 1.2669 (1.2913)\tRank Loss 1.0368 (1.2561)\tPrec 62.50% (63.30%)\nEpoch: [13][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.029)\tLoss 2.1250 (2.5470)\tCls Loss 1.1718 (1.2914)\tRank Loss 0.9532 (1.2555)\tPrec 67.97% (63.29%)\nEpoch: [13][100/313]\tTime 0.086 (0.094)\tData 0.026 (0.028)\tLoss 1.9956 (2.5409)\tCls Loss 1.0878 (1.2909)\tRank Loss 0.9078 (1.2500)\tPrec 68.75% (63.32%)\nEpoch: [13][200/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 2.7885 (2.5351)\tCls Loss 1.4598 (1.2908)\tRank Loss 1.3287 (1.2443)\tPrec 60.94% (63.31%)\nEpoch: [13][300/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 2.7804 (2.5311)\tCls Loss 1.5279 (1.2914)\tRank Loss 1.2525 (1.2397)\tPrec 57.81% (63.30%)\nEpoch: [14][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.3755 (2.5305)\tCls Loss 1.3324 (1.2915)\tRank Loss 1.0431 (1.2389)\tPrec 60.94% (63.29%)\nEpoch: [14][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.9571 (2.5233)\tCls Loss 1.1374 (1.2902)\tRank Loss 0.8196 (1.2331)\tPrec 69.53% (63.32%)\nEpoch: [14][200/313]\tTime 0.094 (0.094)\tData 0.027 (0.028)\tLoss 2.4039 (2.5180)\tCls Loss 1.2323 (1.2896)\tRank Loss 1.1716 (1.2283)\tPrec 68.75% (63.33%)\nEpoch: [14][300/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.3995 (2.5138)\tCls Loss 1.4668 (1.2903)\tRank Loss 0.9327 (1.2235)\tPrec 60.94% (63.32%)\nEpoch: [15][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.0024 (2.5133)\tCls Loss 1.1173 (1.2904)\tRank Loss 0.8851 (1.2229)\tPrec 63.28% (63.32%)\nEpoch: [15][100/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.6297 (2.5065)\tCls Loss 1.4702 (1.2890)\tRank Loss 1.1595 (1.2175)\tPrec 61.72% (63.35%)\nEpoch: [15][200/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 1.8206 (2.5018)\tCls Loss 1.0101 (1.2888)\tRank Loss 0.8105 (1.2130)\tPrec 67.97% (63.35%)\nEpoch: [15][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.2335 (2.4984)\tCls Loss 1.3350 (1.2892)\tRank Loss 0.8985 (1.2093)\tPrec 59.38% (63.34%)\nEpoch: [16][0/313]\tTime 0.095 (0.094)\tData 0.031 (0.028)\tLoss 1.9090 (2.4980)\tCls Loss 1.0917 (1.2891)\tRank Loss 0.8173 (1.2089)\tPrec 70.31% (63.34%)\nEpoch: [16][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.8384 (2.4918)\tCls Loss 1.0808 (1.2876)\tRank Loss 0.7576 (1.2042)\tPrec 63.28% (63.38%)\nEpoch: [16][200/313]\tTime 0.094 (0.094)\tData 0.030 (0.028)\tLoss 2.2644 (2.4861)\tCls Loss 1.2866 (1.2868)\tRank Loss 0.9779 (1.1993)\tPrec 59.38% (63.40%)\nEpoch: [16][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.2427 (2.4815)\tCls Loss 1.2449 (1.2865)\tRank Loss 0.9978 (1.1950)\tPrec 62.50% (63.41%)\nEpoch: [17][0/313]\tTime 0.099 (0.094)\tData 0.033 (0.028)\tLoss 2.1297 (2.4814)\tCls Loss 1.2831 (1.2867)\tRank Loss 0.8466 (1.1947)\tPrec 64.06% (63.41%)\nEpoch: [17][100/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.5683 (2.4758)\tCls Loss 1.3398 (1.2853)\tRank Loss 1.2285 (1.1905)\tPrec 67.19% (63.45%)\nEpoch: [17][200/313]\tTime 0.091 (0.094)\tData 0.028 (0.028)\tLoss 2.2803 (2.4720)\tCls Loss 1.2625 (1.2850)\tRank Loss 1.0178 (1.1870)\tPrec 62.50% (63.45%)\nEpoch: [17][300/313]\tTime 0.091 (0.094)\tData 0.026 (0.028)\tLoss 2.6718 (2.4689)\tCls Loss 1.5665 (1.2852)\tRank Loss 1.1053 (1.1836)\tPrec 58.59% (63.44%)\nEpoch: [18][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.2939 (2.4685)\tCls Loss 1.1853 (1.2852)\tRank Loss 1.1086 (1.1833)\tPrec 61.72% (63.44%)\nEpoch: [18][100/313]\tTime 0.108 (0.094)\tData 0.029 (0.028)\tLoss 1.9531 (2.4622)\tCls Loss 1.1961 (1.2835)\tRank Loss 0.7569 (1.1787)\tPrec 66.41% (63.48%)\nEpoch: [18][200/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.1277 (2.4578)\tCls Loss 1.2278 (1.2829)\tRank Loss 0.9000 (1.1750)\tPrec 65.62% (63.50%)\nEpoch: [18][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.3163 (2.4540)\tCls Loss 1.3969 (1.2825)\tRank Loss 0.9193 (1.1714)\tPrec 58.59% (63.51%)\nEpoch: [19][0/313]\tTime 0.099 (0.094)\tData 0.032 (0.028)\tLoss 1.7830 (2.4533)\tCls Loss 1.0112 (1.2825)\tRank Loss 0.7718 (1.1708)\tPrec 71.88% (63.51%)\nEpoch: [19][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.4383 (2.4476)\tCls Loss 1.3118 (1.2809)\tRank Loss 1.1265 (1.1668)\tPrec 60.94% (63.54%)\nEpoch: [19][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8799 (2.4433)\tCls Loss 1.1828 (1.2801)\tRank Loss 0.6971 (1.1632)\tPrec 67.19% (63.56%)\nEpoch: [19][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.1528 (2.4405)\tCls Loss 1.2220 (1.2803)\tRank Loss 0.9308 (1.1603)\tPrec 65.62% (63.55%)\nEpoch: [20][0/313]\tTime 0.103 (0.094)\tData 0.033 (0.028)\tLoss 2.3500 (2.4404)\tCls Loss 1.3466 (1.2804)\tRank Loss 1.0034 (1.1600)\tPrec 58.59% (63.55%)\nEpoch: [20][100/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.2448 (2.4355)\tCls Loss 1.2089 (1.2792)\tRank Loss 1.0358 (1.1563)\tPrec 67.19% (63.58%)\nEpoch: [20][200/313]\tTime 0.095 (0.094)\tData 0.030 (0.028)\tLoss 2.2256 (2.4317)\tCls Loss 1.1788 (1.2786)\tRank Loss 1.0468 (1.1531)\tPrec 64.84% (63.59%)\nEpoch: [20][300/313]\tTime 0.120 (0.094)\tData 0.029 (0.028)\tLoss 2.0525 (2.4284)\tCls Loss 1.1897 (1.2783)\tRank Loss 0.8628 (1.1502)\tPrec 64.06% (63.60%)\nEpoch: [21][0/313]\tTime 0.104 (0.094)\tData 0.034 (0.028)\tLoss 2.2584 (2.4281)\tCls Loss 1.3201 (1.2783)\tRank Loss 0.9383 (1.1497)\tPrec 64.06% (63.59%)\nEpoch: [21][100/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.3617 (2.4239)\tCls Loss 1.2985 (1.2775)\tRank Loss 1.0631 (1.1464)\tPrec 64.84% (63.62%)\nEpoch: [21][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.4230 (2.4203)\tCls Loss 1.4020 (1.2769)\tRank Loss 1.0210 (1.1434)\tPrec 58.59% (63.63%)\nEpoch: [21][300/313]\tTime 0.108 (0.094)\tData 0.031 (0.028)\tLoss 2.2266 (2.4175)\tCls Loss 1.2441 (1.2769)\tRank Loss 0.9825 (1.1406)\tPrec 63.28% (63.63%)\nEpoch: [22][0/313]\tTime 0.104 (0.094)\tData 0.033 (0.028)\tLoss 1.7709 (2.4170)\tCls Loss 0.9330 (1.2768)\tRank Loss 0.8379 (1.1402)\tPrec 71.09% (63.63%)\nEpoch: [22][100/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 2.2645 (2.4124)\tCls Loss 1.1616 (1.2758)\tRank Loss 1.1029 (1.1366)\tPrec 66.41% (63.66%)\nEpoch: [22][200/313]\tTime 0.099 (0.094)\tData 0.030 (0.028)\tLoss 2.3704 (2.4098)\tCls Loss 1.3516 (1.2755)\tRank Loss 1.0188 (1.1343)\tPrec 64.84% (63.66%)\nEpoch: [22][300/313]\tTime 0.097 (0.094)\tData 0.030 (0.028)\tLoss 1.9854 (2.4071)\tCls Loss 1.1112 (1.2753)\tRank Loss 0.8742 (1.1318)\tPrec 67.19% (63.67%)\nEpoch: [23][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.2011 (2.4068)\tCls Loss 1.1599 (1.2753)\tRank Loss 1.0411 (1.1315)\tPrec 71.09% (63.67%)\nEpoch: [23][100/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 2.2099 (2.4028)\tCls Loss 1.3455 (1.2743)\tRank Loss 0.8644 (1.1285)\tPrec 60.94% (63.69%)\nEpoch: [23][200/313]\tTime 0.093 (0.094)\tData 0.029 (0.028)\tLoss 2.2415 (2.3992)\tCls Loss 1.2731 (1.2734)\tRank Loss 0.9683 (1.1259)\tPrec 60.94% (63.71%)\nEpoch: [23][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.2777 (2.3964)\tCls Loss 1.2051 (1.2730)\tRank Loss 1.0726 (1.1233)\tPrec 66.41% (63.71%)\nEpoch: [24][0/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 2.0386 (2.3960)\tCls Loss 1.1304 (1.2730)\tRank Loss 0.9082 (1.1229)\tPrec 67.97% (63.71%)\nEpoch: [24][100/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.1135 (2.3920)\tCls Loss 1.3171 (1.2719)\tRank Loss 0.7964 (1.1201)\tPrec 57.81% (63.74%)\nEpoch: [24][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.6917 (2.3885)\tCls Loss 0.9816 (1.2711)\tRank Loss 0.7101 (1.1174)\tPrec 69.53% (63.76%)\nEpoch: [24][300/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 1.8577 (2.3855)\tCls Loss 1.1426 (1.2707)\tRank Loss 0.7150 (1.1149)\tPrec 63.28% (63.77%)\nEpoch: [25][0/313]\tTime 0.095 (0.094)\tData 0.030 (0.028)\tLoss 2.0614 (2.3851)\tCls Loss 1.2116 (1.2706)\tRank Loss 0.8499 (1.1145)\tPrec 65.62% (63.77%)\nEpoch: [25][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.8156 (2.3815)\tCls Loss 1.0427 (1.2696)\tRank Loss 0.7728 (1.1119)\tPrec 68.75% (63.79%)\nEpoch: [25][200/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 2.3572 (2.3785)\tCls Loss 1.4440 (1.2690)\tRank Loss 0.9132 (1.1095)\tPrec 57.81% (63.81%)\nEpoch: [25][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8683 (2.3761)\tCls Loss 1.1415 (1.2689)\tRank Loss 0.7267 (1.1072)\tPrec 64.84% (63.81%)\nEpoch: [26][0/313]\tTime 0.098 (0.094)\tData 0.033 (0.028)\tLoss 1.8217 (2.3759)\tCls Loss 1.0253 (1.2690)\tRank Loss 0.7964 (1.1069)\tPrec 68.75% (63.81%)\nEpoch: [26][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.4374 (2.3721)\tCls Loss 1.3331 (1.2678)\tRank Loss 1.1042 (1.1043)\tPrec 67.19% (63.84%)\nEpoch: [26][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.3647 (2.3695)\tCls Loss 1.4268 (1.2673)\tRank Loss 0.9378 (1.1022)\tPrec 60.94% (63.85%)\nEpoch: [26][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.2166 (2.3670)\tCls Loss 1.3184 (1.2671)\tRank Loss 0.8982 (1.1000)\tPrec 63.28% (63.85%)\nEpoch: [27][0/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 2.2231 (2.3667)\tCls Loss 1.2294 (1.2670)\tRank Loss 0.9937 (1.0997)\tPrec 67.97% (63.85%)\nEpoch: [27][100/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 2.0424 (2.3631)\tCls Loss 1.0901 (1.2657)\tRank Loss 0.9523 (1.0974)\tPrec 69.53% (63.89%)\nEpoch: [27][200/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.7620 (2.3602)\tCls Loss 1.4791 (1.2648)\tRank Loss 1.2829 (1.0953)\tPrec 55.47% (63.91%)\nEpoch: [27][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.1809 (2.3577)\tCls Loss 1.2314 (1.2645)\tRank Loss 0.9495 (1.0933)\tPrec 63.28% (63.92%)\nEpoch: [28][0/313]\tTime 0.095 (0.094)\tData 0.031 (0.028)\tLoss 2.1326 (2.3574)\tCls Loss 1.2378 (1.2645)\tRank Loss 0.8948 (1.0930)\tPrec 67.19% (63.92%)\nEpoch: [28][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.0452 (2.3540)\tCls Loss 1.1300 (1.2634)\tRank Loss 0.9152 (1.0906)\tPrec 71.88% (63.95%)\nEpoch: [28][200/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 2.1165 (2.3510)\tCls Loss 1.1669 (1.2625)\tRank Loss 0.9496 (1.0885)\tPrec 67.19% (63.97%)\nEpoch: [28][300/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 1.7298 (2.3482)\tCls Loss 1.1149 (1.2620)\tRank Loss 0.6150 (1.0862)\tPrec 68.75% (63.98%)\nEpoch: [29][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 1.8788 (2.3480)\tCls Loss 0.9971 (1.2620)\tRank Loss 0.8817 (1.0860)\tPrec 70.31% (63.98%)\nEpoch: [29][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.9069 (2.3446)\tCls Loss 1.1841 (1.2610)\tRank Loss 0.7228 (1.0836)\tPrec 70.31% (64.00%)\nEpoch: [29][200/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 2.0745 (2.3421)\tCls Loss 1.2864 (1.2604)\tRank Loss 0.7881 (1.0817)\tPrec 59.38% (64.02%)\nEpoch: [29][300/313]\tTime 0.093 (0.094)\tData 0.029 (0.028)\tLoss 1.9707 (2.3397)\tCls Loss 1.0224 (1.2599)\tRank Loss 0.9482 (1.0797)\tPrec 72.66% (64.03%)\nEpoch: [30][0/313]\tTime 0.106 (0.094)\tData 0.035 (0.028)\tLoss 2.1583 (2.3395)\tCls Loss 1.1670 (1.2599)\tRank Loss 0.9912 (1.0796)\tPrec 71.09% (64.03%)\nEpoch: [30][100/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 1.9370 (2.3366)\tCls Loss 1.1592 (1.2588)\tRank Loss 0.7778 (1.0777)\tPrec 64.06% (64.06%)\nEpoch: [30][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.3212 (2.3344)\tCls Loss 1.3496 (1.2584)\tRank Loss 0.9717 (1.0760)\tPrec 56.25% (64.07%)\nEpoch: [30][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.1152 (2.3319)\tCls Loss 1.1902 (1.2579)\tRank Loss 0.9250 (1.0740)\tPrec 63.28% (64.08%)\nEpoch: [31][0/313]\tTime 0.100 (0.094)\tData 0.032 (0.028)\tLoss 1.9160 (2.3317)\tCls Loss 1.1876 (1.2579)\tRank Loss 0.7283 (1.0738)\tPrec 60.94% (64.08%)\nEpoch: [31][100/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 2.1474 (2.3285)\tCls Loss 1.2787 (1.2569)\tRank Loss 0.8686 (1.0716)\tPrec 62.50% (64.11%)\nEpoch: [31][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.0966 (2.3261)\tCls Loss 1.2217 (1.2562)\tRank Loss 0.8749 (1.0698)\tPrec 64.84% (64.12%)\nEpoch: [31][300/313]\tTime 0.098 (0.094)\tData 0.032 (0.028)\tLoss 1.9859 (2.3237)\tCls Loss 1.0419 (1.2557)\tRank Loss 0.9440 (1.0680)\tPrec 71.09% (64.13%)\nEpoch: [32][0/313]\tTime 0.102 (0.094)\tData 0.031 (0.028)\tLoss 1.7497 (2.3235)\tCls Loss 0.9461 (1.2557)\tRank Loss 0.8035 (1.0678)\tPrec 74.22% (64.13%)\nEpoch: [32][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.8240 (2.3210)\tCls Loss 1.1347 (1.2549)\tRank Loss 0.6893 (1.0661)\tPrec 65.62% (64.15%)\nEpoch: [32][200/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 1.7014 (2.3188)\tCls Loss 1.0543 (1.2544)\tRank Loss 0.6470 (1.0644)\tPrec 67.97% (64.16%)\nEpoch: [32][300/313]\tTime 0.094 (0.094)\tData 0.027 (0.028)\tLoss 1.6519 (2.3163)\tCls Loss 1.0034 (1.2538)\tRank Loss 0.6485 (1.0625)\tPrec 70.31% (64.17%)\nEpoch: [33][0/313]\tTime 0.101 (0.094)\tData 0.031 (0.028)\tLoss 1.7797 (2.3160)\tCls Loss 1.1029 (1.2537)\tRank Loss 0.6768 (1.0622)\tPrec 69.53% (64.18%)\nEpoch: [33][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.3636 (2.3131)\tCls Loss 1.1803 (1.2528)\tRank Loss 1.1832 (1.0603)\tPrec 67.97% (64.20%)\nEpoch: [33][200/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.0147 (2.3109)\tCls Loss 1.0230 (1.2522)\tRank Loss 0.9917 (1.0587)\tPrec 67.97% (64.22%)\nEpoch: [33][300/313]\tTime 0.093 (0.094)\tData 0.027 (0.028)\tLoss 1.5435 (2.3087)\tCls Loss 0.9161 (1.2518)\tRank Loss 0.6274 (1.0570)\tPrec 72.66% (64.23%)\nEpoch: [34][0/313]\tTime 0.101 (0.094)\tData 0.032 (0.028)\tLoss 2.0546 (2.3084)\tCls Loss 1.2330 (1.2517)\tRank Loss 0.8217 (1.0567)\tPrec 66.41% (64.23%)\nEpoch: [34][100/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.2680 (2.3052)\tCls Loss 1.2650 (1.2505)\tRank Loss 1.0029 (1.0547)\tPrec 64.84% (64.26%)\nEpoch: [34][200/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 1.6897 (2.3030)\tCls Loss 0.9920 (1.2500)\tRank Loss 0.6977 (1.0530)\tPrec 71.88% (64.27%)\nEpoch: [34][300/313]\tTime 0.093 (0.094)\tData 0.029 (0.028)\tLoss 2.3778 (2.3013)\tCls Loss 1.4944 (1.2498)\tRank Loss 0.8834 (1.0515)\tPrec 54.69% (64.28%)\nEpoch: [35][0/313]\tTime 0.096 (0.094)\tData 0.030 (0.028)\tLoss 1.9059 (2.3012)\tCls Loss 1.1776 (1.2498)\tRank Loss 0.7283 (1.0514)\tPrec 65.62% (64.28%)\nEpoch: [35][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.9699 (2.2987)\tCls Loss 1.1208 (1.2490)\tRank Loss 0.8491 (1.0497)\tPrec 66.41% (64.30%)\nEpoch: [35][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.1463 (2.2964)\tCls Loss 1.1237 (1.2482)\tRank Loss 1.0226 (1.0482)\tPrec 68.75% (64.32%)\nEpoch: [35][300/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.1232 (2.2945)\tCls Loss 1.2251 (1.2479)\tRank Loss 0.8981 (1.0466)\tPrec 63.28% (64.33%)\nEpoch: [36][0/313]\tTime 0.096 (0.094)\tData 0.030 (0.028)\tLoss 2.2022 (2.2943)\tCls Loss 1.2025 (1.2478)\tRank Loss 0.9997 (1.0465)\tPrec 67.97% (64.33%)\nEpoch: [36][100/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.9327 (2.2915)\tCls Loss 1.0648 (1.2468)\tRank Loss 0.8680 (1.0447)\tPrec 68.75% (64.36%)\nEpoch: [36][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.9136 (2.2895)\tCls Loss 1.0711 (1.2462)\tRank Loss 0.8425 (1.0433)\tPrec 65.62% (64.37%)\nEpoch: [36][300/313]\tTime 0.109 (0.094)\tData 0.041 (0.028)\tLoss 2.1544 (2.2878)\tCls Loss 1.3536 (1.2460)\tRank Loss 0.8008 (1.0417)\tPrec 59.38% (64.38%)\nEpoch: [37][0/313]\tTime 0.098 (0.094)\tData 0.033 (0.028)\tLoss 2.0569 (2.2875)\tCls Loss 1.0875 (1.2460)\tRank Loss 0.9694 (1.0415)\tPrec 71.09% (64.38%)\nEpoch: [37][100/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.3665 (2.2851)\tCls Loss 1.2872 (1.2452)\tRank Loss 1.0792 (1.0399)\tPrec 67.97% (64.40%)\nEpoch: [37][200/313]\tTime 0.102 (0.094)\tData 0.030 (0.028)\tLoss 2.0310 (2.2834)\tCls Loss 1.2527 (1.2447)\tRank Loss 0.7782 (1.0387)\tPrec 64.06% (64.41%)\nEpoch: [37][300/313]\tTime 0.097 (0.094)\tData 0.031 (0.028)\tLoss 2.1359 (2.2816)\tCls Loss 1.2014 (1.2442)\tRank Loss 0.9346 (1.0374)\tPrec 66.41% (64.42%)\nEpoch: [38][0/313]\tTime 0.096 (0.094)\tData 0.030 (0.028)\tLoss 1.7824 (2.2814)\tCls Loss 0.9107 (1.2442)\tRank Loss 0.8717 (1.0372)\tPrec 76.56% (64.42%)\nEpoch: [38][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.4040 (2.2795)\tCls Loss 1.4070 (1.2435)\tRank Loss 0.9971 (1.0359)\tPrec 60.16% (64.44%)\nEpoch: [38][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.2871 (2.2777)\tCls Loss 1.2672 (1.2432)\tRank Loss 1.0199 (1.0346)\tPrec 64.06% (64.45%)\nEpoch: [38][300/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 2.1829 (2.2761)\tCls Loss 1.2235 (1.2428)\tRank Loss 0.9593 (1.0332)\tPrec 63.28% (64.46%)\nEpoch: [39][0/313]\tTime 0.099 (0.094)\tData 0.032 (0.028)\tLoss 1.7673 (2.2758)\tCls Loss 1.0315 (1.2428)\tRank Loss 0.7358 (1.0331)\tPrec 72.66% (64.46%)\nEpoch: [39][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.9301 (2.2732)\tCls Loss 1.1628 (1.2418)\tRank Loss 0.7672 (1.0314)\tPrec 67.19% (64.48%)\nEpoch: [39][200/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 1.7666 (2.2711)\tCls Loss 1.2118 (1.2412)\tRank Loss 0.5548 (1.0299)\tPrec 62.50% (64.50%)\nEpoch: [39][300/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 1.8532 (2.2691)\tCls Loss 1.1465 (1.2407)\tRank Loss 0.7067 (1.0284)\tPrec 64.84% (64.51%)\nEpoch: [40][0/313]\tTime 0.099 (0.094)\tData 0.031 (0.028)\tLoss 1.7870 (2.2689)\tCls Loss 0.8932 (1.2406)\tRank Loss 0.8938 (1.0282)\tPrec 71.09% (64.52%)\nEpoch: [40][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.1705 (2.2664)\tCls Loss 1.1219 (1.2396)\tRank Loss 1.0486 (1.0268)\tPrec 66.41% (64.54%)\nEpoch: [40][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.4332 (2.2645)\tCls Loss 0.8638 (1.2391)\tRank Loss 0.5694 (1.0254)\tPrec 73.44% (64.56%)\nEpoch: [40][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.0856 (2.2627)\tCls Loss 1.1656 (1.2386)\tRank Loss 0.9199 (1.0241)\tPrec 66.41% (64.57%)\nEpoch: [41][0/313]\tTime 0.129 (0.094)\tData 0.043 (0.028)\tLoss 1.7230 (2.2626)\tCls Loss 0.9023 (1.2386)\tRank Loss 0.8207 (1.0240)\tPrec 77.34% (64.57%)\nEpoch: [41][100/313]\tTime 0.100 (0.094)\tData 0.032 (0.028)\tLoss 2.0842 (2.2604)\tCls Loss 1.2788 (1.2378)\tRank Loss 0.8054 (1.0226)\tPrec 64.84% (64.60%)\nEpoch: [41][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.8194 (2.2585)\tCls Loss 1.1317 (1.2372)\tRank Loss 0.6877 (1.0213)\tPrec 62.50% (64.61%)\nEpoch: [41][300/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 2.0298 (2.2573)\tCls Loss 1.2409 (1.2370)\tRank Loss 0.7889 (1.0203)\tPrec 64.84% (64.61%)\nEpoch: [42][0/313]\tTime 0.097 (0.094)\tData 0.030 (0.028)\tLoss 1.8052 (2.2572)\tCls Loss 0.9398 (1.2370)\tRank Loss 0.8653 (1.0202)\tPrec 68.75% (64.61%)\nEpoch: [42][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.6101 (2.2550)\tCls Loss 0.8935 (1.2361)\tRank Loss 0.7167 (1.0189)\tPrec 72.66% (64.64%)\nEpoch: [42][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.2154 (2.2533)\tCls Loss 1.2058 (1.2356)\tRank Loss 1.0096 (1.0177)\tPrec 67.19% (64.65%)\nEpoch: [42][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.9652 (2.2516)\tCls Loss 1.2281 (1.2352)\tRank Loss 0.7371 (1.0164)\tPrec 65.62% (64.66%)\nEpoch: [43][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.1324 (2.2514)\tCls Loss 1.1636 (1.2352)\tRank Loss 0.9688 (1.0162)\tPrec 64.84% (64.66%)\nEpoch: [43][100/313]\tTime 0.093 (0.094)\tData 0.029 (0.028)\tLoss 1.8920 (2.2493)\tCls Loss 1.1400 (1.2344)\tRank Loss 0.7520 (1.0149)\tPrec 66.41% (64.68%)\nEpoch: [43][200/313]\tTime 0.093 (0.094)\tData 0.027 (0.028)\tLoss 1.7041 (2.2473)\tCls Loss 0.9624 (1.2336)\tRank Loss 0.7417 (1.0137)\tPrec 71.88% (64.70%)\nEpoch: [43][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.1801 (2.2457)\tCls Loss 1.2719 (1.2331)\tRank Loss 0.9082 (1.0126)\tPrec 66.41% (64.71%)\nEpoch: [44][0/313]\tTime 0.097 (0.094)\tData 0.032 (0.028)\tLoss 2.0925 (2.2455)\tCls Loss 1.1392 (1.2331)\tRank Loss 0.9533 (1.0125)\tPrec 67.97% (64.71%)\nEpoch: [44][100/313]\tTime 0.093 (0.094)\tData 0.029 (0.028)\tLoss 2.2003 (2.2434)\tCls Loss 1.1346 (1.2323)\tRank Loss 1.0657 (1.0111)\tPrec 66.41% (64.73%)\nEpoch: [44][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.9732 (2.2419)\tCls Loss 1.2088 (1.2318)\tRank Loss 0.7644 (1.0101)\tPrec 66.41% (64.75%)\nEpoch: [44][300/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.9878 (2.2403)\tCls Loss 1.2233 (1.2312)\tRank Loss 0.7645 (1.0091)\tPrec 62.50% (64.76%)\nEpoch: [45][0/313]\tTime 0.094 (0.094)\tData 0.030 (0.028)\tLoss 1.5464 (2.2401)\tCls Loss 0.9723 (1.2312)\tRank Loss 0.5741 (1.0089)\tPrec 75.00% (64.76%)\nEpoch: [45][100/313]\tTime 0.096 (0.094)\tData 0.029 (0.028)\tLoss 1.6748 (2.2380)\tCls Loss 1.0157 (1.2303)\tRank Loss 0.6591 (1.0077)\tPrec 74.22% (64.79%)\nEpoch: [45][200/313]\tTime 0.093 (0.094)\tData 0.029 (0.028)\tLoss 1.8932 (2.2367)\tCls Loss 1.1269 (1.2299)\tRank Loss 0.7662 (1.0067)\tPrec 68.75% (64.80%)\nEpoch: [45][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.2283 (2.2354)\tCls Loss 1.3360 (1.2296)\tRank Loss 0.8923 (1.0058)\tPrec 60.94% (64.81%)\nEpoch: [46][0/313]\tTime 0.096 (0.094)\tData 0.032 (0.028)\tLoss 1.5689 (2.2352)\tCls Loss 0.8567 (1.2295)\tRank Loss 0.7122 (1.0057)\tPrec 74.22% (64.81%)\nEpoch: [46][100/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.0840 (2.2334)\tCls Loss 1.2119 (1.2289)\tRank Loss 0.8721 (1.0045)\tPrec 67.19% (64.83%)\nEpoch: [46][200/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 1.8452 (2.2316)\tCls Loss 1.1755 (1.2283)\tRank Loss 0.6696 (1.0034)\tPrec 64.84% (64.84%)\nEpoch: [46][300/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.8314 (2.2307)\tCls Loss 1.0868 (1.2282)\tRank Loss 0.7446 (1.0025)\tPrec 68.75% (64.84%)\nEpoch: [47][0/313]\tTime 0.099 (0.094)\tData 0.032 (0.028)\tLoss 1.7974 (2.2305)\tCls Loss 0.9497 (1.2282)\tRank Loss 0.8477 (1.0023)\tPrec 67.97% (64.84%)\nEpoch: [47][100/313]\tTime 0.093 (0.094)\tData 0.029 (0.028)\tLoss 1.7648 (2.2288)\tCls Loss 0.9907 (1.2274)\tRank Loss 0.7741 (1.0014)\tPrec 75.78% (64.86%)\nEpoch: [47][200/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.0127 (2.2274)\tCls Loss 1.1629 (1.2270)\tRank Loss 0.8498 (1.0004)\tPrec 66.41% (64.87%)\nEpoch: [47][300/313]\tTime 0.087 (0.094)\tData 0.026 (0.028)\tLoss 2.0668 (2.2258)\tCls Loss 1.2701 (1.2266)\tRank Loss 0.7967 (0.9992)\tPrec 64.84% (64.88%)\nEpoch: [48][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.2414 (2.2256)\tCls Loss 1.3162 (1.2265)\tRank Loss 0.9252 (0.9991)\tPrec 64.06% (64.88%)\nEpoch: [48][100/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 1.6584 (2.2236)\tCls Loss 0.8821 (1.2257)\tRank Loss 0.7763 (0.9979)\tPrec 75.00% (64.91%)\nEpoch: [48][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.0882 (2.2220)\tCls Loss 1.2416 (1.2252)\tRank Loss 0.8465 (0.9968)\tPrec 65.62% (64.92%)\nEpoch: [48][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.0299 (2.2207)\tCls Loss 1.1680 (1.2249)\tRank Loss 0.8619 (0.9959)\tPrec 62.50% (64.92%)\nEpoch: [49][0/313]\tTime 0.099 (0.094)\tData 0.032 (0.028)\tLoss 1.7123 (2.2206)\tCls Loss 0.9914 (1.2248)\tRank Loss 0.7209 (0.9958)\tPrec 71.88% (64.92%)\nEpoch: [49][100/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.6132 (2.2188)\tCls Loss 0.8259 (1.2240)\tRank Loss 0.7872 (0.9947)\tPrec 79.69% (64.95%)\nEpoch: [49][200/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 1.6921 (2.2173)\tCls Loss 1.0757 (1.2235)\tRank Loss 0.6164 (0.9938)\tPrec 67.19% (64.96%)\nEpoch: [49][300/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.9925 (2.2161)\tCls Loss 1.2155 (1.2232)\tRank Loss 0.7770 (0.9929)\tPrec 65.62% (64.96%)\nEpoch: [50][0/313]\tTime 0.100 (0.094)\tData 0.034 (0.028)\tLoss 1.8097 (2.2160)\tCls Loss 1.0336 (1.2232)\tRank Loss 0.7761 (0.9928)\tPrec 69.53% (64.96%)\nEpoch: [50][100/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 1.8517 (2.2142)\tCls Loss 1.0697 (1.2225)\tRank Loss 0.7820 (0.9917)\tPrec 65.62% (64.98%)\nEpoch: [50][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.9790 (2.2128)\tCls Loss 1.1460 (1.2221)\tRank Loss 0.8330 (0.9908)\tPrec 63.28% (65.00%)\nEpoch: [50][300/313]\tTime 0.094 (0.094)\tData 0.027 (0.028)\tLoss 2.5745 (2.2124)\tCls Loss 1.4491 (1.2222)\tRank Loss 1.1253 (0.9902)\tPrec 58.59% (65.00%)\nEpoch: [51][0/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 2.1343 (2.2123)\tCls Loss 1.1718 (1.2222)\tRank Loss 0.9625 (0.9901)\tPrec 68.75% (65.00%)\nEpoch: [51][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.6545 (2.2108)\tCls Loss 1.0038 (1.2216)\tRank Loss 0.6507 (0.9892)\tPrec 74.22% (65.01%)\nEpoch: [51][200/313]\tTime 0.096 (0.094)\tData 0.028 (0.028)\tLoss 2.0618 (2.2094)\tCls Loss 1.1560 (1.2211)\tRank Loss 0.9058 (0.9884)\tPrec 65.62% (65.02%)\nEpoch: [51][300/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 2.1005 (2.2086)\tCls Loss 1.1020 (1.2209)\tRank Loss 0.9986 (0.9876)\tPrec 68.75% (65.02%)\nEpoch: [52][0/313]\tTime 0.097 (0.094)\tData 0.031 (0.028)\tLoss 1.3706 (2.2084)\tCls Loss 0.9095 (1.2209)\tRank Loss 0.4611 (0.9875)\tPrec 76.56% (65.02%)\nEpoch: [52][100/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.0075 (2.2067)\tCls Loss 1.1831 (1.2202)\tRank Loss 0.8244 (0.9864)\tPrec 65.62% (65.04%)\nEpoch: [52][200/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 1.7085 (2.2052)\tCls Loss 1.0304 (1.2197)\tRank Loss 0.6781 (0.9855)\tPrec 71.88% (65.05%)\nEpoch: [52][300/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 1.8325 (2.2040)\tCls Loss 1.0793 (1.2194)\tRank Loss 0.7533 (0.9846)\tPrec 68.75% (65.06%)\nEpoch: [53][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.0661 (2.2038)\tCls Loss 1.1050 (1.2193)\tRank Loss 0.9611 (0.9845)\tPrec 71.88% (65.06%)\nEpoch: [53][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.6327 (2.2021)\tCls Loss 0.8915 (1.2186)\tRank Loss 0.7412 (0.9835)\tPrec 75.00% (65.08%)\nEpoch: [53][200/313]\tTime 0.100 (0.094)\tData 0.029 (0.028)\tLoss 2.2501 (2.2010)\tCls Loss 1.2302 (1.2183)\tRank Loss 1.0199 (0.9827)\tPrec 63.28% (65.09%)\nEpoch: [53][300/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.9867 (2.2002)\tCls Loss 1.2549 (1.2183)\tRank Loss 0.7318 (0.9820)\tPrec 63.28% (65.09%)\nEpoch: [54][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 1.9323 (2.2001)\tCls Loss 0.9539 (1.2182)\tRank Loss 0.9784 (0.9819)\tPrec 72.66% (65.09%)\nEpoch: [54][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.1514 (2.1988)\tCls Loss 1.2332 (1.2177)\tRank Loss 0.9182 (0.9811)\tPrec 66.41% (65.10%)\nEpoch: [54][200/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.9011 (2.1978)\tCls Loss 1.1537 (1.2174)\tRank Loss 0.7475 (0.9804)\tPrec 63.28% (65.11%)\nEpoch: [54][300/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 1.8675 (2.1969)\tCls Loss 1.3510 (1.2173)\tRank Loss 0.5165 (0.9796)\tPrec 59.38% (65.12%)\nEpoch: [55][0/313]\tTime 0.130 (0.094)\tData 0.031 (0.028)\tLoss 1.9130 (2.1968)\tCls Loss 1.0608 (1.2172)\tRank Loss 0.8522 (0.9796)\tPrec 70.31% (65.12%)\nEpoch: [55][100/313]\tTime 0.093 (0.094)\tData 0.029 (0.028)\tLoss 2.1614 (2.1951)\tCls Loss 1.2883 (1.2164)\tRank Loss 0.8732 (0.9787)\tPrec 63.28% (65.14%)\nEpoch: [55][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.3167 (2.1940)\tCls Loss 1.3321 (1.2161)\tRank Loss 0.9846 (0.9779)\tPrec 59.38% (65.15%)\nEpoch: [55][300/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.3226 (2.1931)\tCls Loss 1.4506 (1.2158)\tRank Loss 0.8720 (0.9773)\tPrec 60.94% (65.15%)\nEpoch: [56][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.0054 (2.1929)\tCls Loss 1.1426 (1.2157)\tRank Loss 0.8627 (0.9772)\tPrec 65.62% (65.15%)\nEpoch: [56][100/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 2.1022 (2.1916)\tCls Loss 1.1637 (1.2153)\tRank Loss 0.9385 (0.9763)\tPrec 68.75% (65.16%)\nEpoch: [56][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.9159 (2.1904)\tCls Loss 1.2574 (1.2148)\tRank Loss 0.6586 (0.9756)\tPrec 64.84% (65.18%)\nEpoch: [56][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.6264 (2.1892)\tCls Loss 0.9960 (1.2145)\tRank Loss 0.6305 (0.9747)\tPrec 67.19% (65.18%)\nEpoch: [57][0/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 2.1073 (2.1891)\tCls Loss 1.2320 (1.2145)\tRank Loss 0.8753 (0.9746)\tPrec 63.28% (65.18%)\nEpoch: [57][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.1598 (2.1876)\tCls Loss 1.2960 (1.2139)\tRank Loss 0.8638 (0.9737)\tPrec 58.59% (65.20%)\nEpoch: [57][200/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 2.1202 (2.1864)\tCls Loss 1.1516 (1.2134)\tRank Loss 0.9686 (0.9729)\tPrec 64.06% (65.21%)\nEpoch: [57][300/313]\tTime 0.090 (0.094)\tData 0.026 (0.028)\tLoss 1.6547 (2.1857)\tCls Loss 1.0926 (1.2134)\tRank Loss 0.5621 (0.9723)\tPrec 70.31% (65.22%)\nEpoch: [58][0/313]\tTime 0.093 (0.094)\tData 0.030 (0.028)\tLoss 1.6928 (2.1856)\tCls Loss 1.0873 (1.2133)\tRank Loss 0.6055 (0.9722)\tPrec 71.09% (65.22%)\nEpoch: [58][100/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 1.8575 (2.1842)\tCls Loss 1.0578 (1.2127)\tRank Loss 0.7996 (0.9715)\tPrec 68.75% (65.23%)\nEpoch: [58][200/313]\tTime 0.092 (0.094)\tData 0.026 (0.028)\tLoss 2.2486 (2.1832)\tCls Loss 1.4025 (1.2123)\tRank Loss 0.8460 (0.9709)\tPrec 58.59% (65.25%)\nEpoch: [58][300/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.8296 (2.1823)\tCls Loss 0.9851 (1.2122)\tRank Loss 0.8445 (0.9701)\tPrec 71.09% (65.25%)\nEpoch: [59][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 1.7926 (2.1822)\tCls Loss 0.9562 (1.2122)\tRank Loss 0.8364 (0.9701)\tPrec 75.78% (65.25%)\nEpoch: [59][100/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.4147 (2.1811)\tCls Loss 1.2934 (1.2117)\tRank Loss 1.1214 (0.9694)\tPrec 60.94% (65.26%)\nEpoch: [59][200/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 2.0074 (2.1798)\tCls Loss 1.0726 (1.2112)\tRank Loss 0.9348 (0.9685)\tPrec 74.22% (65.27%)\nEpoch: [59][300/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.0413 (2.1787)\tCls Loss 1.2226 (1.2109)\tRank Loss 0.8188 (0.9678)\tPrec 64.06% (65.28%)\nEpoch: [60][0/313]\tTime 0.100 (0.094)\tData 0.031 (0.028)\tLoss 1.6443 (2.1787)\tCls Loss 0.9166 (1.2109)\tRank Loss 0.7277 (0.9678)\tPrec 76.56% (65.28%)\nEpoch: [60][100/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.0181 (2.1772)\tCls Loss 1.2132 (1.2103)\tRank Loss 0.8050 (0.9669)\tPrec 66.41% (65.30%)\nEpoch: [60][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.0232 (2.1761)\tCls Loss 1.0941 (1.2099)\tRank Loss 0.9291 (0.9663)\tPrec 67.19% (65.31%)\nEpoch: [60][300/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 2.4190 (2.1751)\tCls Loss 1.2121 (1.2095)\tRank Loss 1.2069 (0.9656)\tPrec 70.31% (65.32%)\nEpoch: [61][0/313]\tTime 0.108 (0.094)\tData 0.035 (0.028)\tLoss 2.0282 (2.1750)\tCls Loss 1.1115 (1.2095)\tRank Loss 0.9166 (0.9655)\tPrec 68.75% (65.32%)\nEpoch: [61][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8509 (2.1736)\tCls Loss 0.9988 (1.2089)\tRank Loss 0.8521 (0.9647)\tPrec 71.88% (65.34%)\nEpoch: [61][200/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.0232 (2.1725)\tCls Loss 1.0477 (1.2085)\tRank Loss 0.9755 (0.9640)\tPrec 68.75% (65.35%)\nEpoch: [61][300/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.1968 (2.1717)\tCls Loss 1.2383 (1.2083)\tRank Loss 0.9585 (0.9634)\tPrec 69.53% (65.35%)\nEpoch: [62][0/313]\tTime 0.102 (0.094)\tData 0.034 (0.028)\tLoss 1.8764 (2.1716)\tCls Loss 1.1467 (1.2083)\tRank Loss 0.7297 (0.9633)\tPrec 64.06% (65.35%)\nEpoch: [62][100/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 1.7935 (2.1702)\tCls Loss 1.0157 (1.2077)\tRank Loss 0.7778 (0.9624)\tPrec 70.31% (65.37%)\nEpoch: [62][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8092 (2.1692)\tCls Loss 1.1458 (1.2074)\tRank Loss 0.6634 (0.9619)\tPrec 68.75% (65.38%)\nEpoch: [62][300/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.1204 (2.1681)\tCls Loss 1.1975 (1.2070)\tRank Loss 0.9228 (0.9611)\tPrec 67.97% (65.39%)\nEpoch: [63][0/313]\tTime 0.103 (0.094)\tData 0.033 (0.028)\tLoss 2.0110 (2.1681)\tCls Loss 1.0770 (1.2070)\tRank Loss 0.9340 (0.9610)\tPrec 70.31% (65.39%)\nEpoch: [63][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8096 (2.1669)\tCls Loss 1.0152 (1.2065)\tRank Loss 0.7944 (0.9603)\tPrec 71.88% (65.40%)\nEpoch: [63][200/313]\tTime 0.107 (0.094)\tData 0.032 (0.028)\tLoss 1.8565 (2.1656)\tCls Loss 1.0285 (1.2060)\tRank Loss 0.8280 (0.9596)\tPrec 71.09% (65.41%)\nEpoch: [63][300/313]\tTime 0.096 (0.094)\tData 0.029 (0.028)\tLoss 2.2866 (2.1649)\tCls Loss 1.3305 (1.2059)\tRank Loss 0.9562 (0.9590)\tPrec 62.50% (65.42%)\nEpoch: [64][0/313]\tTime 0.100 (0.094)\tData 0.032 (0.028)\tLoss 1.6666 (2.1648)\tCls Loss 0.9802 (1.2059)\tRank Loss 0.6864 (0.9589)\tPrec 71.88% (65.42%)\nEpoch: [64][100/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 1.9253 (2.1635)\tCls Loss 1.0648 (1.2053)\tRank Loss 0.8604 (0.9582)\tPrec 68.75% (65.43%)\nEpoch: [64][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.0931 (2.1624)\tCls Loss 1.0888 (1.2049)\tRank Loss 1.0042 (0.9576)\tPrec 69.53% (65.44%)\nEpoch: [64][300/313]\tTime 0.097 (0.094)\tData 0.029 (0.028)\tLoss 2.0606 (2.1617)\tCls Loss 1.1968 (1.2047)\tRank Loss 0.8638 (0.9570)\tPrec 62.50% (65.45%)\nEpoch: [65][0/313]\tTime 0.097 (0.094)\tData 0.030 (0.028)\tLoss 2.0467 (2.1616)\tCls Loss 1.0554 (1.2047)\tRank Loss 0.9914 (0.9569)\tPrec 71.09% (65.45%)\nEpoch: [65][100/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 1.7854 (2.1605)\tCls Loss 1.0920 (1.2042)\tRank Loss 0.6935 (0.9564)\tPrec 68.75% (65.46%)\nEpoch: [65][200/313]\tTime 0.096 (0.094)\tData 0.030 (0.028)\tLoss 2.0776 (2.1599)\tCls Loss 1.1982 (1.2040)\tRank Loss 0.8795 (0.9559)\tPrec 67.19% (65.46%)\nEpoch: [65][300/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.5939 (2.1592)\tCls Loss 1.5986 (1.2039)\tRank Loss 0.9953 (0.9553)\tPrec 57.81% (65.47%)\nEpoch: [66][0/313]\tTime 0.099 (0.094)\tData 0.033 (0.028)\tLoss 1.9294 (2.1591)\tCls Loss 1.0001 (1.2039)\tRank Loss 0.9293 (0.9552)\tPrec 72.66% (65.47%)\nEpoch: [66][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.6651 (2.1578)\tCls Loss 1.0085 (1.2033)\tRank Loss 0.6567 (0.9545)\tPrec 73.44% (65.48%)\nEpoch: [66][200/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.2393 (2.1568)\tCls Loss 1.2954 (1.2029)\tRank Loss 0.9440 (0.9539)\tPrec 64.06% (65.49%)\nEpoch: [66][300/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.0695 (2.1562)\tCls Loss 1.2839 (1.2028)\tRank Loss 0.7857 (0.9534)\tPrec 64.84% (65.50%)\nEpoch: [67][0/313]\tTime 0.107 (0.094)\tData 0.036 (0.028)\tLoss 1.8381 (2.1562)\tCls Loss 1.0481 (1.2028)\tRank Loss 0.7899 (0.9533)\tPrec 70.31% (65.50%)\nEpoch: [67][100/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 2.0110 (2.1549)\tCls Loss 1.2705 (1.2023)\tRank Loss 0.7406 (0.9526)\tPrec 61.72% (65.51%)\nEpoch: [67][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.8959 (2.1541)\tCls Loss 1.0761 (1.2020)\tRank Loss 0.8198 (0.9521)\tPrec 70.31% (65.52%)\nEpoch: [67][300/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.1200 (2.1533)\tCls Loss 1.2273 (1.2019)\tRank Loss 0.8928 (0.9514)\tPrec 61.72% (65.52%)\nEpoch: [68][0/313]\tTime 0.096 (0.094)\tData 0.032 (0.028)\tLoss 1.5813 (2.1532)\tCls Loss 0.9234 (1.2018)\tRank Loss 0.6579 (0.9513)\tPrec 75.00% (65.52%)\nEpoch: [68][100/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 1.8218 (2.1519)\tCls Loss 0.9629 (1.2013)\tRank Loss 0.8589 (0.9506)\tPrec 70.31% (65.54%)\nEpoch: [68][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.0253 (2.1511)\tCls Loss 1.1764 (1.2010)\tRank Loss 0.8489 (0.9501)\tPrec 71.09% (65.55%)\nEpoch: [68][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8780 (2.1504)\tCls Loss 1.1203 (1.2009)\tRank Loss 0.7577 (0.9496)\tPrec 67.97% (65.55%)\nEpoch: [69][0/313]\tTime 0.097 (0.094)\tData 0.032 (0.028)\tLoss 1.6884 (2.1504)\tCls Loss 0.9390 (1.2009)\tRank Loss 0.7495 (0.9495)\tPrec 72.66% (65.55%)\nEpoch: [69][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.1382 (2.1493)\tCls Loss 1.2584 (1.2004)\tRank Loss 0.8798 (0.9489)\tPrec 71.09% (65.56%)\nEpoch: [69][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.6396 (2.1482)\tCls Loss 1.0082 (1.2000)\tRank Loss 0.6315 (0.9483)\tPrec 67.97% (65.57%)\nEpoch: [69][300/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.2599 (2.1475)\tCls Loss 1.3482 (1.1998)\tRank Loss 0.9117 (0.9477)\tPrec 58.59% (65.57%)\nEpoch: [70][0/313]\tTime 0.099 (0.094)\tData 0.031 (0.028)\tLoss 2.1416 (2.1474)\tCls Loss 1.1835 (1.1998)\tRank Loss 0.9581 (0.9476)\tPrec 65.62% (65.57%)\nEpoch: [70][100/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 1.9900 (2.1462)\tCls Loss 1.2568 (1.1992)\tRank Loss 0.7332 (0.9470)\tPrec 62.50% (65.59%)\nEpoch: [70][200/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 1.7277 (2.1452)\tCls Loss 1.0728 (1.1989)\tRank Loss 0.6549 (0.9463)\tPrec 67.19% (65.60%)\nEpoch: [70][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.6283 (2.1444)\tCls Loss 0.8672 (1.1987)\tRank Loss 0.7612 (0.9458)\tPrec 75.00% (65.60%)\nEpoch: [71][0/313]\tTime 0.102 (0.094)\tData 0.033 (0.028)\tLoss 1.7569 (2.1444)\tCls Loss 0.9317 (1.1987)\tRank Loss 0.8253 (0.9457)\tPrec 70.31% (65.60%)\nEpoch: [71][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.6865 (2.1434)\tCls Loss 1.0397 (1.1982)\tRank Loss 0.6468 (0.9452)\tPrec 69.53% (65.61%)\nEpoch: [71][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.0010 (2.1424)\tCls Loss 1.1747 (1.1979)\tRank Loss 0.8263 (0.9446)\tPrec 67.97% (65.62%)\nEpoch: [71][300/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 2.0037 (2.1418)\tCls Loss 1.1874 (1.1977)\tRank Loss 0.8164 (0.9440)\tPrec 62.50% (65.62%)\nEpoch: [72][0/313]\tTime 0.101 (0.094)\tData 0.032 (0.028)\tLoss 1.6066 (2.1416)\tCls Loss 0.8853 (1.1977)\tRank Loss 0.7212 (0.9440)\tPrec 76.56% (65.63%)\nEpoch: [72][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.6983 (2.1405)\tCls Loss 0.8496 (1.1971)\tRank Loss 0.8487 (0.9434)\tPrec 76.56% (65.64%)\nEpoch: [72][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.0425 (2.1397)\tCls Loss 1.1213 (1.1968)\tRank Loss 0.9212 (0.9429)\tPrec 68.75% (65.65%)\nEpoch: [72][300/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.7148 (2.1389)\tCls Loss 0.9240 (1.1966)\tRank Loss 0.7909 (0.9423)\tPrec 75.78% (65.65%)\nEpoch: [73][0/313]\tTime 0.100 (0.094)\tData 0.032 (0.028)\tLoss 1.7309 (2.1388)\tCls Loss 1.0733 (1.1966)\tRank Loss 0.6577 (0.9422)\tPrec 71.88% (65.65%)\nEpoch: [73][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.0627 (2.1377)\tCls Loss 1.3340 (1.1961)\tRank Loss 0.7286 (0.9417)\tPrec 57.81% (65.67%)\nEpoch: [73][200/313]\tTime 0.094 (0.094)\tData 0.027 (0.028)\tLoss 1.9543 (2.1371)\tCls Loss 1.0747 (1.1959)\tRank Loss 0.8796 (0.9412)\tPrec 71.88% (65.67%)\nEpoch: [73][300/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.0798 (2.1365)\tCls Loss 1.2378 (1.1957)\tRank Loss 0.8419 (0.9408)\tPrec 64.06% (65.67%)\nEpoch: [74][0/313]\tTime 0.097 (0.094)\tData 0.031 (0.028)\tLoss 1.8025 (2.1365)\tCls Loss 1.0857 (1.1957)\tRank Loss 0.7168 (0.9407)\tPrec 67.97% (65.67%)\nEpoch: [74][100/313]\tTime 0.095 (0.094)\tData 0.030 (0.028)\tLoss 1.9574 (2.1354)\tCls Loss 1.0026 (1.1952)\tRank Loss 0.9547 (0.9402)\tPrec 72.66% (65.69%)\nEpoch: [74][200/313]\tTime 0.093 (0.094)\tData 0.027 (0.028)\tLoss 1.9372 (2.1346)\tCls Loss 1.1662 (1.1949)\tRank Loss 0.7710 (0.9396)\tPrec 68.75% (65.70%)\nEpoch: [74][300/313]\tTime 0.095 (0.094)\tData 0.027 (0.028)\tLoss 2.0872 (2.1340)\tCls Loss 1.1882 (1.1948)\tRank Loss 0.8991 (0.9392)\tPrec 66.41% (65.70%)\nEpoch: [75][0/313]\tTime 0.099 (0.094)\tData 0.032 (0.028)\tLoss 1.8168 (2.1339)\tCls Loss 1.0034 (1.1948)\tRank Loss 0.8134 (0.9391)\tPrec 67.97% (65.70%)\nEpoch: [75][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.1626 (2.1331)\tCls Loss 1.1616 (1.1944)\tRank Loss 1.0010 (0.9387)\tPrec 70.31% (65.71%)\nEpoch: [75][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.5537 (2.1322)\tCls Loss 0.9422 (1.1941)\tRank Loss 0.6114 (0.9381)\tPrec 75.00% (65.72%)\nEpoch: [75][300/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 1.8189 (2.1317)\tCls Loss 1.0509 (1.1940)\tRank Loss 0.7679 (0.9377)\tPrec 67.97% (65.72%)\nEpoch: [76][0/313]\tTime 0.096 (0.094)\tData 0.030 (0.028)\tLoss 2.1203 (2.1316)\tCls Loss 1.2343 (1.1940)\tRank Loss 0.8860 (0.9376)\tPrec 66.41% (65.72%)\nEpoch: [76][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.7560 (2.1308)\tCls Loss 1.0101 (1.1936)\tRank Loss 0.7459 (0.9372)\tPrec 71.88% (65.73%)\nEpoch: [76][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.9926 (2.1299)\tCls Loss 1.1807 (1.1932)\tRank Loss 0.8120 (0.9367)\tPrec 65.62% (65.74%)\nEpoch: [76][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.1951 (2.1293)\tCls Loss 1.3988 (1.1931)\tRank Loss 0.7963 (0.9362)\tPrec 59.38% (65.74%)\nEpoch: [77][0/313]\tTime 0.102 (0.094)\tData 0.033 (0.028)\tLoss 2.1487 (2.1292)\tCls Loss 1.1513 (1.1931)\tRank Loss 0.9974 (0.9361)\tPrec 66.41% (65.74%)\nEpoch: [77][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.1054 (2.1283)\tCls Loss 1.2297 (1.1927)\tRank Loss 0.8757 (0.9356)\tPrec 67.19% (65.75%)\nEpoch: [77][200/313]\tTime 0.093 (0.094)\tData 0.027 (0.028)\tLoss 1.8451 (2.1275)\tCls Loss 1.0424 (1.1924)\tRank Loss 0.8027 (0.9351)\tPrec 71.09% (65.76%)\nEpoch: [77][300/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.1112 (2.1268)\tCls Loss 1.1917 (1.1922)\tRank Loss 0.9195 (0.9346)\tPrec 68.75% (65.77%)\nEpoch: [78][0/313]\tTime 0.098 (0.094)\tData 0.032 (0.028)\tLoss 1.9467 (2.1267)\tCls Loss 1.1453 (1.1921)\tRank Loss 0.8013 (0.9346)\tPrec 68.75% (65.77%)\nEpoch: [78][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8423 (2.1255)\tCls Loss 0.9952 (1.1916)\tRank Loss 0.8471 (0.9339)\tPrec 70.31% (65.78%)\nEpoch: [78][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.0906 (2.1248)\tCls Loss 1.1273 (1.1913)\tRank Loss 0.9632 (0.9335)\tPrec 70.31% (65.79%)\nEpoch: [78][300/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.0997 (2.1242)\tCls Loss 1.2614 (1.1912)\tRank Loss 0.8382 (0.9331)\tPrec 63.28% (65.79%)\nEpoch: [79][0/313]\tTime 0.102 (0.094)\tData 0.036 (0.028)\tLoss 1.9591 (2.1241)\tCls Loss 1.1392 (1.1911)\tRank Loss 0.8199 (0.9330)\tPrec 66.41% (65.79%)\nEpoch: [79][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.6197 (2.1232)\tCls Loss 0.9944 (1.1907)\tRank Loss 0.6253 (0.9325)\tPrec 72.66% (65.80%)\nEpoch: [79][200/313]\tTime 0.096 (0.094)\tData 0.030 (0.028)\tLoss 1.9635 (2.1222)\tCls Loss 1.1901 (1.1904)\tRank Loss 0.7734 (0.9319)\tPrec 63.28% (65.81%)\nEpoch: [79][300/313]\tTime 0.097 (0.094)\tData 0.029 (0.028)\tLoss 2.0134 (2.1215)\tCls Loss 1.1780 (1.1902)\tRank Loss 0.8354 (0.9314)\tPrec 71.09% (65.82%)\nEpoch: [80][0/313]\tTime 0.099 (0.094)\tData 0.032 (0.028)\tLoss 1.8093 (2.1215)\tCls Loss 0.8781 (1.1901)\tRank Loss 0.9312 (0.9314)\tPrec 76.56% (65.82%)\nEpoch: [80][100/313]\tTime 0.096 (0.094)\tData 0.029 (0.028)\tLoss 2.2079 (2.1207)\tCls Loss 1.2963 (1.1898)\tRank Loss 0.9116 (0.9309)\tPrec 60.16% (65.83%)\nEpoch: [80][200/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 1.7123 (2.1200)\tCls Loss 0.9911 (1.1896)\tRank Loss 0.7212 (0.9304)\tPrec 75.00% (65.84%)\nEpoch: [80][300/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.8222 (2.1195)\tCls Loss 1.2152 (1.1895)\tRank Loss 0.6070 (0.9300)\tPrec 64.06% (65.84%)\nEpoch: [81][0/313]\tTime 0.104 (0.094)\tData 0.035 (0.028)\tLoss 1.6491 (2.1194)\tCls Loss 0.9158 (1.1895)\tRank Loss 0.7333 (0.9299)\tPrec 71.09% (65.84%)\nEpoch: [81][100/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 2.1902 (2.1185)\tCls Loss 1.2112 (1.1891)\tRank Loss 0.9790 (0.9294)\tPrec 64.06% (65.85%)\nEpoch: [81][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8783 (2.1178)\tCls Loss 1.1664 (1.1888)\tRank Loss 0.7119 (0.9289)\tPrec 66.41% (65.86%)\nEpoch: [81][300/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.1227 (2.1170)\tCls Loss 1.1034 (1.1886)\tRank Loss 1.0193 (0.9284)\tPrec 68.75% (65.86%)\nEpoch: [82][0/313]\tTime 0.098 (0.094)\tData 0.032 (0.028)\tLoss 1.9654 (2.1170)\tCls Loss 1.1232 (1.1886)\tRank Loss 0.8422 (0.9284)\tPrec 69.53% (65.86%)\nEpoch: [82][100/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 1.8837 (2.1161)\tCls Loss 1.1164 (1.1882)\tRank Loss 0.7674 (0.9279)\tPrec 67.97% (65.88%)\nEpoch: [82][200/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.5844 (2.1154)\tCls Loss 1.5846 (1.1879)\tRank Loss 0.9998 (0.9275)\tPrec 54.69% (65.88%)\nEpoch: [82][300/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 1.6386 (2.1149)\tCls Loss 1.0150 (1.1878)\tRank Loss 0.6237 (0.9271)\tPrec 72.66% (65.88%)\nEpoch: [83][0/313]\tTime 0.098 (0.094)\tData 0.031 (0.028)\tLoss 1.8560 (2.1149)\tCls Loss 1.1012 (1.1878)\tRank Loss 0.7548 (0.9271)\tPrec 64.06% (65.88%)\nEpoch: [83][100/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.0663 (2.1139)\tCls Loss 1.0524 (1.1874)\tRank Loss 1.0139 (0.9266)\tPrec 74.22% (65.90%)\nEpoch: [83][200/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.0670 (2.1133)\tCls Loss 1.2753 (1.1872)\tRank Loss 0.7918 (0.9261)\tPrec 64.06% (65.90%)\nEpoch: [83][300/313]\tTime 0.096 (0.094)\tData 0.029 (0.028)\tLoss 1.7444 (2.1126)\tCls Loss 1.0003 (1.1869)\tRank Loss 0.7441 (0.9256)\tPrec 71.09% (65.91%)\nEpoch: [84][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 2.1267 (2.1125)\tCls Loss 1.1941 (1.1869)\tRank Loss 0.9327 (0.9256)\tPrec 62.50% (65.91%)\nEpoch: [84][100/313]\tTime 0.096 (0.094)\tData 0.030 (0.028)\tLoss 2.0046 (2.1116)\tCls Loss 1.0276 (1.1865)\tRank Loss 0.9769 (0.9251)\tPrec 72.66% (65.92%)\nEpoch: [84][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.7422 (2.1108)\tCls Loss 1.0465 (1.1861)\tRank Loss 0.6957 (0.9246)\tPrec 73.44% (65.93%)\nEpoch: [84][300/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.8979 (2.1103)\tCls Loss 1.1869 (1.1860)\tRank Loss 0.7110 (0.9243)\tPrec 66.41% (65.94%)\nEpoch: [85][0/313]\tTime 0.104 (0.094)\tData 0.033 (0.028)\tLoss 2.0010 (2.1102)\tCls Loss 1.1227 (1.1860)\tRank Loss 0.8783 (0.9243)\tPrec 66.41% (65.94%)\nEpoch: [85][100/313]\tTime 0.097 (0.094)\tData 0.030 (0.028)\tLoss 1.9194 (2.1095)\tCls Loss 1.0985 (1.1856)\tRank Loss 0.8210 (0.9239)\tPrec 67.19% (65.95%)\nEpoch: [85][200/313]\tTime 0.095 (0.094)\tData 0.027 (0.028)\tLoss 1.9149 (2.1089)\tCls Loss 1.0865 (1.1854)\tRank Loss 0.8283 (0.9235)\tPrec 68.75% (65.95%)\nEpoch: [85][300/313]\tTime 0.098 (0.094)\tData 0.033 (0.028)\tLoss 2.2182 (2.1084)\tCls Loss 1.1735 (1.1853)\tRank Loss 1.0447 (0.9232)\tPrec 66.41% (65.96%)\nEpoch: [86][0/313]\tTime 0.100 (0.094)\tData 0.032 (0.028)\tLoss 1.5766 (2.1083)\tCls Loss 0.9701 (1.1852)\tRank Loss 0.6065 (0.9231)\tPrec 73.44% (65.96%)\nEpoch: [86][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.2217 (2.1075)\tCls Loss 1.1993 (1.1848)\tRank Loss 1.0224 (0.9227)\tPrec 67.97% (65.97%)\nEpoch: [86][200/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.7919 (2.1069)\tCls Loss 1.0079 (1.1846)\tRank Loss 0.7841 (0.9223)\tPrec 68.75% (65.98%)\nEpoch: [86][300/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 2.1205 (2.1064)\tCls Loss 1.2292 (1.1845)\tRank Loss 0.8913 (0.9219)\tPrec 64.06% (65.98%)\nEpoch: [87][0/313]\tTime 0.101 (0.094)\tData 0.032 (0.028)\tLoss 1.7313 (2.1064)\tCls Loss 0.9927 (1.1845)\tRank Loss 0.7387 (0.9219)\tPrec 75.00% (65.98%)\nEpoch: [87][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 1.8394 (2.1055)\tCls Loss 1.1739 (1.1841)\tRank Loss 0.6655 (0.9214)\tPrec 64.84% (65.99%)\nEpoch: [87][200/313]\tTime 0.108 (0.094)\tData 0.040 (0.028)\tLoss 1.9158 (2.1047)\tCls Loss 1.2145 (1.1838)\tRank Loss 0.7014 (0.9210)\tPrec 60.94% (66.00%)\nEpoch: [87][300/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.8508 (2.1041)\tCls Loss 1.1094 (1.1836)\tRank Loss 0.7414 (0.9205)\tPrec 66.41% (66.00%)\nEpoch: [88][0/313]\tTime 0.105 (0.094)\tData 0.033 (0.028)\tLoss 2.0285 (2.1040)\tCls Loss 1.1774 (1.1836)\tRank Loss 0.8511 (0.9204)\tPrec 64.84% (66.00%)\nEpoch: [88][100/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.8682 (2.1031)\tCls Loss 1.1186 (1.1832)\tRank Loss 0.7496 (0.9199)\tPrec 65.62% (66.01%)\nEpoch: [88][200/313]\tTime 0.098 (0.094)\tData 0.032 (0.028)\tLoss 1.8891 (2.1025)\tCls Loss 0.9989 (1.1829)\tRank Loss 0.8902 (0.9196)\tPrec 72.66% (66.02%)\nEpoch: [88][300/313]\tTime 0.094 (0.094)\tData 0.028 (0.028)\tLoss 1.9543 (2.1020)\tCls Loss 1.0957 (1.1828)\tRank Loss 0.8586 (0.9192)\tPrec 67.97% (66.02%)\nEpoch: [89][0/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 1.7026 (2.1020)\tCls Loss 1.0472 (1.1828)\tRank Loss 0.6554 (0.9192)\tPrec 69.53% (66.02%)\nEpoch: [89][100/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 1.6955 (2.1010)\tCls Loss 0.9992 (1.1823)\tRank Loss 0.6963 (0.9187)\tPrec 67.97% (66.04%)\nEpoch: [89][200/313]\tTime 0.094 (0.094)\tData 0.027 (0.028)\tLoss 1.9257 (2.1003)\tCls Loss 1.1518 (1.1820)\tRank Loss 0.7739 (0.9183)\tPrec 68.75% (66.04%)\nEpoch: [89][300/313]\tTime 0.100 (0.094)\tData 0.032 (0.028)\tLoss 2.0301 (2.0998)\tCls Loss 1.1877 (1.1819)\tRank Loss 0.8424 (0.9179)\tPrec 68.75% (66.05%)\nEpoch: [90][0/313]\tTime 0.097 (0.094)\tData 0.031 (0.028)\tLoss 1.7005 (2.0998)\tCls Loss 1.0396 (1.1819)\tRank Loss 0.6609 (0.9179)\tPrec 71.88% (66.05%)\nEpoch: [90][100/313]\tTime 0.098 (0.094)\tData 0.028 (0.028)\tLoss 1.6581 (2.0989)\tCls Loss 1.0131 (1.1815)\tRank Loss 0.6450 (0.9174)\tPrec 68.75% (66.06%)\nEpoch: [90][200/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.3705 (2.0982)\tCls Loss 1.3337 (1.1812)\tRank Loss 1.0368 (0.9170)\tPrec 66.41% (66.06%)\nEpoch: [90][300/313]\tTime 0.093 (0.094)\tData 0.027 (0.028)\tLoss 2.0916 (2.0977)\tCls Loss 1.1731 (1.1811)\tRank Loss 0.9185 (0.9166)\tPrec 67.97% (66.07%)\nEpoch: [91][0/313]\tTime 0.109 (0.094)\tData 0.031 (0.028)\tLoss 1.9796 (2.0977)\tCls Loss 1.1241 (1.1811)\tRank Loss 0.8555 (0.9166)\tPrec 69.53% (66.07%)\nEpoch: [91][100/313]\tTime 0.094 (0.094)\tData 0.027 (0.028)\tLoss 1.8754 (2.0969)\tCls Loss 1.1726 (1.1807)\tRank Loss 0.7028 (0.9162)\tPrec 63.28% (66.08%)\nEpoch: [91][200/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 2.0551 (2.0962)\tCls Loss 1.1937 (1.1805)\tRank Loss 0.8613 (0.9158)\tPrec 66.41% (66.08%)\nEpoch: [91][300/313]\tTime 0.095 (0.094)\tData 0.028 (0.028)\tLoss 2.2373 (2.0957)\tCls Loss 1.2544 (1.1803)\tRank Loss 0.9829 (0.9155)\tPrec 63.28% (66.09%)\nEpoch: [92][0/313]\tTime 0.106 (0.094)\tData 0.039 (0.028)\tLoss 2.3390 (2.0958)\tCls Loss 1.1936 (1.1803)\tRank Loss 1.1454 (0.9155)\tPrec 63.28% (66.09%)\nEpoch: [92][100/313]\tTime 0.110 (0.094)\tData 0.031 (0.028)\tLoss 1.7936 (2.0952)\tCls Loss 1.0275 (1.1801)\tRank Loss 0.7661 (0.9151)\tPrec 70.31% (66.09%)\nEpoch: [92][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.0531 (2.0946)\tCls Loss 1.2599 (1.1799)\tRank Loss 0.7932 (0.9147)\tPrec 63.28% (66.10%)\nEpoch: [92][300/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.0240 (2.0941)\tCls Loss 1.0603 (1.1797)\tRank Loss 0.9637 (0.9144)\tPrec 67.97% (66.11%)\nEpoch: [93][0/313]\tTime 0.100 (0.094)\tData 0.032 (0.028)\tLoss 1.9293 (2.0940)\tCls Loss 1.0765 (1.1797)\tRank Loss 0.8529 (0.9143)\tPrec 67.97% (66.11%)\nEpoch: [93][100/313]\tTime 0.091 (0.094)\tData 0.026 (0.028)\tLoss 1.7540 (2.0932)\tCls Loss 0.9610 (1.1793)\tRank Loss 0.7929 (0.9139)\tPrec 72.66% (66.12%)\nEpoch: [93][200/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.6988 (2.0925)\tCls Loss 1.0467 (1.1790)\tRank Loss 0.6520 (0.9135)\tPrec 70.31% (66.12%)\nEpoch: [93][300/313]\tTime 0.090 (0.094)\tData 0.026 (0.028)\tLoss 2.1953 (2.0921)\tCls Loss 1.2851 (1.1789)\tRank Loss 0.9101 (0.9132)\tPrec 66.41% (66.13%)\nEpoch: [94][0/313]\tTime 0.093 (0.094)\tData 0.030 (0.028)\tLoss 2.1520 (2.0920)\tCls Loss 1.1126 (1.1789)\tRank Loss 1.0393 (0.9131)\tPrec 67.97% (66.13%)\nEpoch: [94][100/313]\tTime 0.102 (0.094)\tData 0.034 (0.028)\tLoss 2.0104 (2.0913)\tCls Loss 1.1919 (1.1786)\tRank Loss 0.8185 (0.9128)\tPrec 64.06% (66.14%)\nEpoch: [94][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.0328 (2.0908)\tCls Loss 1.1134 (1.1784)\tRank Loss 0.9194 (0.9124)\tPrec 71.09% (66.14%)\nEpoch: [94][300/313]\tTime 0.096 (0.094)\tData 0.031 (0.028)\tLoss 1.8563 (2.0907)\tCls Loss 1.0638 (1.1785)\tRank Loss 0.7926 (0.9123)\tPrec 68.75% (66.14%)\nEpoch: [95][0/313]\tTime 0.100 (0.094)\tData 0.031 (0.028)\tLoss 1.6088 (2.0907)\tCls Loss 0.9321 (1.1785)\tRank Loss 0.6767 (0.9122)\tPrec 78.91% (66.14%)\nEpoch: [95][100/313]\tTime 0.091 (0.094)\tData 0.026 (0.028)\tLoss 1.9925 (2.0902)\tCls Loss 1.1256 (1.1783)\tRank Loss 0.8669 (0.9119)\tPrec 67.97% (66.14%)\nEpoch: [95][200/313]\tTime 0.090 (0.094)\tData 0.027 (0.028)\tLoss 1.9972 (2.0896)\tCls Loss 1.0913 (1.1780)\tRank Loss 0.9059 (0.9116)\tPrec 67.97% (66.15%)\nEpoch: [95][300/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.0775 (2.0893)\tCls Loss 1.1410 (1.1780)\tRank Loss 0.9365 (0.9112)\tPrec 67.19% (66.15%)\nEpoch: [96][0/313]\tTime 0.094 (0.094)\tData 0.030 (0.028)\tLoss 1.9280 (2.0892)\tCls Loss 0.9598 (1.1780)\tRank Loss 0.9682 (0.9112)\tPrec 76.56% (66.15%)\nEpoch: [96][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.7304 (2.0885)\tCls Loss 0.9987 (1.1776)\tRank Loss 0.7317 (0.9108)\tPrec 71.88% (66.16%)\nEpoch: [96][200/313]\tTime 0.092 (0.094)\tData 0.028 (0.028)\tLoss 1.8652 (2.0880)\tCls Loss 1.1641 (1.1775)\tRank Loss 0.7011 (0.9105)\tPrec 68.75% (66.16%)\nEpoch: [96][300/313]\tTime 0.091 (0.094)\tData 0.026 (0.028)\tLoss 1.9623 (2.0876)\tCls Loss 1.0672 (1.1774)\tRank Loss 0.8951 (0.9103)\tPrec 67.97% (66.16%)\nEpoch: [97][0/313]\tTime 0.095 (0.094)\tData 0.030 (0.028)\tLoss 2.1405 (2.0876)\tCls Loss 1.3298 (1.1774)\tRank Loss 0.8106 (0.9102)\tPrec 60.94% (66.16%)\nEpoch: [97][100/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 1.9365 (2.0869)\tCls Loss 1.1120 (1.1771)\tRank Loss 0.8245 (0.9099)\tPrec 63.28% (66.17%)\nEpoch: [97][200/313]\tTime 0.090 (0.094)\tData 0.026 (0.028)\tLoss 1.9284 (2.0866)\tCls Loss 1.2347 (1.1770)\tRank Loss 0.6936 (0.9096)\tPrec 65.62% (66.17%)\nEpoch: [97][300/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.2001 (2.0862)\tCls Loss 1.1452 (1.1769)\tRank Loss 1.0548 (0.9093)\tPrec 65.62% (66.18%)\nEpoch: [98][0/313]\tTime 0.095 (0.094)\tData 0.029 (0.028)\tLoss 1.8188 (2.0862)\tCls Loss 1.0644 (1.1769)\tRank Loss 0.7545 (0.9093)\tPrec 67.97% (66.18%)\nEpoch: [98][100/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.0716 (2.0857)\tCls Loss 1.0580 (1.1767)\tRank Loss 1.0136 (0.9091)\tPrec 72.66% (66.18%)\nEpoch: [98][200/313]\tTime 0.091 (0.094)\tData 0.027 (0.028)\tLoss 2.0832 (2.0852)\tCls Loss 1.1667 (1.1765)\tRank Loss 0.9166 (0.9087)\tPrec 67.19% (66.19%)\nEpoch: [98][300/313]\tTime 0.092 (0.094)\tData 0.027 (0.028)\tLoss 2.0682 (2.0848)\tCls Loss 1.0984 (1.1763)\tRank Loss 0.9698 (0.9084)\tPrec 71.88% (66.19%)\nEpoch: [99][0/313]\tTime 0.096 (0.094)\tData 0.030 (0.028)\tLoss 1.7302 (2.0847)\tCls Loss 1.1002 (1.1763)\tRank Loss 0.6300 (0.9083)\tPrec 67.19% (66.19%)\nEpoch: [99][100/313]\tTime 0.089 (0.094)\tData 0.027 (0.028)\tLoss 1.9514 (2.0840)\tCls Loss 1.0656 (1.1760)\tRank Loss 0.8858 (0.9080)\tPrec 71.88% (66.20%)\nEpoch: [99][200/313]\tTime 0.088 (0.094)\tData 0.028 (0.028)\tLoss 2.0466 (2.0834)\tCls Loss 1.2448 (1.1758)\tRank Loss 0.8018 (0.9076)\tPrec 67.19% (66.21%)\nEpoch: [99][300/313]\tTime 0.088 (0.094)\tData 0.027 (0.028)\tLoss 2.3848 (2.0829)\tCls Loss 1.4068 (1.1757)\tRank Loss 0.9780 (0.9073)\tPrec 60.16% (66.21%)\nEpoch: [100][0/313]\tTime 0.109 (0.094)\tData 0.036 (0.028)\tLoss 1.4913 (2.0828)\tCls Loss 0.9487 (1.1756)\tRank Loss 0.5426 (0.9072)\tPrec 69.53% (66.21%)\nEpoch: [100][100/313]\tTime 0.088 (0.094)\tData 0.028 (0.028)\tLoss 1.8385 (2.0821)\tCls Loss 1.0471 (1.1753)\tRank Loss 0.7914 (0.9068)\tPrec 69.53% (66.22%)\nEpoch: [100][200/313]\tTime 0.085 (0.094)\tData 0.025 (0.028)\tLoss 1.8952 (2.0816)\tCls Loss 1.1086 (1.1751)\tRank Loss 0.7867 (0.9064)\tPrec 71.09% (66.22%)\nEpoch: [100][300/313]\tTime 0.088 (0.094)\tData 0.027 (0.028)\tLoss 2.0446 (2.0812)\tCls Loss 1.2833 (1.1750)\tRank Loss 0.7613 (0.9061)\tPrec 60.16% (66.23%)\nEpoch: [101][0/313]\tTime 0.088 (0.094)\tData 0.028 (0.028)\tLoss 2.0302 (2.0811)\tCls Loss 1.1047 (1.1750)\tRank Loss 0.9254 (0.9061)\tPrec 71.09% (66.23%)\nEpoch: [101][100/313]\tTime 0.088 (0.094)\tData 0.027 (0.028)\tLoss 1.9821 (2.0804)\tCls Loss 1.1319 (1.1747)\tRank Loss 0.8502 (0.9057)\tPrec 70.31% (66.24%)\nEpoch: [101][200/313]\tTime 0.089 (0.094)\tData 0.027 (0.028)\tLoss 1.9387 (2.0798)\tCls Loss 1.0829 (1.1744)\tRank Loss 0.8558 (0.9053)\tPrec 68.75% (66.24%)\nEpoch: [101][300/313]\tTime 0.088 (0.094)\tData 0.026 (0.028)\tLoss 2.1668 (2.0793)\tCls Loss 1.2102 (1.1743)\tRank Loss 0.9567 (0.9050)\tPrec 64.06% (66.25%)\nEpoch: [102][0/313]\tTime 0.091 (0.094)\tData 0.030 (0.028)\tLoss 1.8493 (2.0792)\tCls Loss 1.1420 (1.1742)\tRank Loss 0.7073 (0.9050)\tPrec 64.06% (66.25%)\nEpoch: [102][100/313]\tTime 0.088 (0.094)\tData 0.026 (0.028)\tLoss 2.0681 (2.0785)\tCls Loss 1.2268 (1.1739)\tRank Loss 0.8412 (0.9046)\tPrec 61.72% (66.26%)\nEpoch: [102][200/313]\tTime 0.087 (0.094)\tData 0.026 (0.028)\tLoss 2.4061 (2.0781)\tCls Loss 1.3152 (1.1738)\tRank Loss 1.0909 (0.9043)\tPrec 63.28% (66.26%)\nEpoch: [102][300/313]\tTime 0.085 (0.094)\tData 0.026 (0.028)\tLoss 2.4625 (2.0774)\tCls Loss 1.4308 (1.1736)\tRank Loss 1.0316 (0.9038)\tPrec 60.94% (66.27%)\nEpoch: [103][0/313]\tTime 0.089 (0.094)\tData 0.029 (0.028)\tLoss 1.7799 (2.0774)\tCls Loss 1.0040 (1.1736)\tRank Loss 0.7759 (0.9038)\tPrec 71.09% (66.27%)\nEpoch: [103][100/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 1.8270 (2.0767)\tCls Loss 1.0684 (1.1733)\tRank Loss 0.7586 (0.9035)\tPrec 70.31% (66.27%)\nEpoch: [103][200/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 2.0612 (2.0760)\tCls Loss 1.2463 (1.1730)\tRank Loss 0.8149 (0.9030)\tPrec 64.06% (66.28%)\nEpoch: [103][300/313]\tTime 0.087 (0.094)\tData 0.026 (0.028)\tLoss 2.1196 (2.0756)\tCls Loss 1.2921 (1.1729)\tRank Loss 0.8275 (0.9027)\tPrec 64.06% (66.28%)\nEpoch: [104][0/313]\tTime 0.092 (0.094)\tData 0.032 (0.028)\tLoss 1.8339 (2.0756)\tCls Loss 1.1627 (1.1729)\tRank Loss 0.6712 (0.9027)\tPrec 68.75% (66.28%)\nEpoch: [104][100/313]\tTime 0.104 (0.094)\tData 0.038 (0.028)\tLoss 1.9843 (2.0749)\tCls Loss 1.1944 (1.1725)\tRank Loss 0.7899 (0.9024)\tPrec 67.97% (66.29%)\nEpoch: [104][200/313]\tTime 0.088 (0.094)\tData 0.027 (0.028)\tLoss 2.0178 (2.0743)\tCls Loss 1.2172 (1.1723)\tRank Loss 0.8006 (0.9020)\tPrec 65.62% (66.30%)\nEpoch: [104][300/313]\tTime 0.086 (0.094)\tData 0.026 (0.028)\tLoss 1.7470 (2.0738)\tCls Loss 1.0367 (1.1721)\tRank Loss 0.7102 (0.9017)\tPrec 71.09% (66.30%)\nEpoch: [105][0/313]\tTime 0.088 (0.094)\tData 0.029 (0.028)\tLoss 1.7163 (2.0738)\tCls Loss 1.0413 (1.1721)\tRank Loss 0.6751 (0.9017)\tPrec 70.31% (66.30%)\nEpoch: [105][100/313]\tTime 0.088 (0.094)\tData 0.028 (0.028)\tLoss 1.6772 (2.0731)\tCls Loss 1.1557 (1.1717)\tRank Loss 0.5215 (0.9014)\tPrec 67.19% (66.31%)\nEpoch: [105][200/313]\tTime 0.085 (0.094)\tData 0.026 (0.028)\tLoss 1.8570 (2.0724)\tCls Loss 1.0664 (1.1715)\tRank Loss 0.7906 (0.9010)\tPrec 67.97% (66.32%)\nEpoch: [105][300/313]\tTime 0.086 (0.094)\tData 0.026 (0.028)\tLoss 1.9392 (2.0720)\tCls Loss 1.1481 (1.1714)\tRank Loss 0.7911 (0.9007)\tPrec 63.28% (66.32%)\nEpoch: [106][0/313]\tTime 0.090 (0.094)\tData 0.029 (0.028)\tLoss 1.7005 (2.0720)\tCls Loss 0.9728 (1.1713)\tRank Loss 0.7277 (0.9006)\tPrec 69.53% (66.32%)\nEpoch: [106][100/313]\tTime 0.088 (0.094)\tData 0.028 (0.028)\tLoss 2.1361 (2.0713)\tCls Loss 1.2231 (1.1710)\tRank Loss 0.9130 (0.9003)\tPrec 67.97% (66.33%)\nEpoch: [106][200/313]\tTime 0.086 (0.094)\tData 0.026 (0.028)\tLoss 1.8138 (2.0708)\tCls Loss 1.0560 (1.1709)\tRank Loss 0.7579 (0.9000)\tPrec 69.53% (66.34%)\nEpoch: [106][300/313]\tTime 0.086 (0.094)\tData 0.026 (0.028)\tLoss 2.0169 (2.0706)\tCls Loss 1.1400 (1.1708)\tRank Loss 0.8769 (0.8998)\tPrec 70.31% (66.34%)\nEpoch: [107][0/313]\tTime 0.089 (0.094)\tData 0.029 (0.028)\tLoss 1.7397 (2.0705)\tCls Loss 1.0803 (1.1708)\tRank Loss 0.6594 (0.8998)\tPrec 67.19% (66.34%)\nEpoch: [107][100/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 1.8281 (2.0699)\tCls Loss 1.1604 (1.1705)\tRank Loss 0.6677 (0.8994)\tPrec 68.75% (66.35%)\nEpoch: [107][200/313]\tTime 0.087 (0.094)\tData 0.026 (0.028)\tLoss 2.2159 (2.0694)\tCls Loss 1.1467 (1.1703)\tRank Loss 1.0691 (0.8991)\tPrec 67.97% (66.35%)\nEpoch: [107][300/313]\tTime 0.088 (0.094)\tData 0.027 (0.028)\tLoss 1.6619 (2.0690)\tCls Loss 1.0223 (1.1701)\tRank Loss 0.6396 (0.8988)\tPrec 73.44% (66.35%)\nEpoch: [108][0/313]\tTime 0.093 (0.094)\tData 0.031 (0.028)\tLoss 2.0745 (2.0689)\tCls Loss 1.1188 (1.1701)\tRank Loss 0.9557 (0.8988)\tPrec 64.06% (66.35%)\nEpoch: [108][100/313]\tTime 0.093 (0.094)\tData 0.031 (0.028)\tLoss 1.8185 (2.0681)\tCls Loss 1.0087 (1.1697)\tRank Loss 0.8098 (0.8984)\tPrec 67.19% (66.36%)\nEpoch: [108][200/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 1.7942 (2.0676)\tCls Loss 1.1545 (1.1695)\tRank Loss 0.6397 (0.8981)\tPrec 68.75% (66.37%)\nEpoch: [108][300/313]\tTime 0.087 (0.094)\tData 0.026 (0.028)\tLoss 2.3804 (2.0672)\tCls Loss 1.2324 (1.1694)\tRank Loss 1.1480 (0.8978)\tPrec 67.19% (66.37%)\nEpoch: [109][0/313]\tTime 0.090 (0.094)\tData 0.028 (0.028)\tLoss 1.9028 (2.0671)\tCls Loss 1.1096 (1.1694)\tRank Loss 0.7932 (0.8978)\tPrec 67.97% (66.37%)\nEpoch: [109][100/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 1.9790 (2.0666)\tCls Loss 1.1613 (1.1691)\tRank Loss 0.8176 (0.8975)\tPrec 64.84% (66.38%)\nEpoch: [109][200/313]\tTime 0.099 (0.094)\tData 0.032 (0.028)\tLoss 2.1081 (2.0661)\tCls Loss 1.3179 (1.1689)\tRank Loss 0.7901 (0.8972)\tPrec 60.94% (66.39%)\nEpoch: [109][300/313]\tTime 0.093 (0.094)\tData 0.028 (0.028)\tLoss 2.4298 (2.0657)\tCls Loss 1.4002 (1.1688)\tRank Loss 1.0296 (0.8969)\tPrec 60.94% (66.39%)\nEpoch: [110][0/313]\tTime 0.090 (0.094)\tData 0.029 (0.028)\tLoss 1.8146 (2.0656)\tCls Loss 0.9607 (1.1688)\tRank Loss 0.8539 (0.8969)\tPrec 71.09% (66.39%)\nEpoch: [110][100/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 1.9091 (2.0650)\tCls Loss 1.0894 (1.1684)\tRank Loss 0.8197 (0.8966)\tPrec 71.09% (66.40%)\nEpoch: [110][200/313]\tTime 0.086 (0.094)\tData 0.026 (0.028)\tLoss 2.1605 (2.0644)\tCls Loss 1.2223 (1.1682)\tRank Loss 0.9382 (0.8962)\tPrec 64.84% (66.40%)\nEpoch: [110][300/313]\tTime 0.094 (0.094)\tData 0.032 (0.028)\tLoss 1.9252 (2.0641)\tCls Loss 1.2083 (1.1681)\tRank Loss 0.7169 (0.8960)\tPrec 67.19% (66.40%)\nEpoch: [111][0/313]\tTime 0.094 (0.094)\tData 0.030 (0.028)\tLoss 1.8120 (2.0641)\tCls Loss 1.0927 (1.1681)\tRank Loss 0.7193 (0.8959)\tPrec 68.75% (66.40%)\nEpoch: [111][100/313]\tTime 0.087 (0.094)\tData 0.027 (0.028)\tLoss 1.9445 (2.0634)\tCls Loss 1.0520 (1.1678)\tRank Loss 0.8925 (0.8956)\tPrec 67.19% (66.41%)\nEpoch: [111][200/313]\tTime 0.088 (0.094)\tData 0.027 (0.028)\tLoss 2.1876 (2.0629)\tCls Loss 1.3429 (1.1676)\tRank Loss 0.8447 (0.8953)\tPrec 61.72% (66.42%)\nEpoch: [111][300/313]\tTime 0.090 (0.094)\tData 0.028 (0.028)\tLoss 1.9342 (2.0626)\tCls Loss 1.1830 (1.1676)\tRank Loss 0.7513 (0.8950)\tPrec 67.97% (66.42%)\nEpoch: [112][0/313]\tTime 0.090 (0.094)\tData 0.029 (0.028)\tLoss 1.9366 (2.0625)\tCls Loss 1.0706 (1.1675)\tRank Loss 0.8660 (0.8950)\tPrec 71.88% (66.42%)\nEpoch: [112][100/313]\tTime 0.086 (0.094)\tData 0.026 (0.028)\tLoss 1.5716 (2.0619)\tCls Loss 0.8955 (1.1672)\tRank Loss 0.6761 (0.8946)\tPrec 71.09% (66.43%)\nEpoch: [112][200/313]\tTime 0.094 (0.094)\tData 0.029 (0.028)\tLoss 1.9885 (2.0614)\tCls Loss 1.1579 (1.1670)\tRank Loss 0.8306 (0.8944)\tPrec 65.62% (66.44%)\nEpoch: [112][300/313]\tTime 0.085 (0.093)\tData 0.026 (0.028)\tLoss 2.0104 (2.0609)\tCls Loss 1.2020 (1.1669)\tRank Loss 0.8084 (0.8941)\tPrec 64.06% (66.44%)\nEpoch: [113][0/313]\tTime 0.093 (0.093)\tData 0.030 (0.028)\tLoss 1.8696 (2.0608)\tCls Loss 1.0229 (1.1668)\tRank Loss 0.8467 (0.8940)\tPrec 71.09% (66.44%)\nEpoch: [113][100/313]\tTime 0.097 (0.093)\tData 0.032 (0.028)\tLoss 2.1285 (2.0602)\tCls Loss 1.2642 (1.1665)\tRank Loss 0.8643 (0.8937)\tPrec 67.97% (66.45%)\nEpoch: [113][200/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.7159 (2.0597)\tCls Loss 1.0157 (1.1663)\tRank Loss 0.7002 (0.8934)\tPrec 69.53% (66.46%)\nEpoch: [113][300/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.5823 (2.0592)\tCls Loss 0.9605 (1.1661)\tRank Loss 0.6218 (0.8931)\tPrec 73.44% (66.46%)\nEpoch: [114][0/313]\tTime 0.094 (0.093)\tData 0.030 (0.028)\tLoss 1.5296 (2.0591)\tCls Loss 0.9795 (1.1661)\tRank Loss 0.5501 (0.8930)\tPrec 74.22% (66.46%)\nEpoch: [114][100/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 1.7964 (2.0584)\tCls Loss 1.0489 (1.1658)\tRank Loss 0.7475 (0.8926)\tPrec 72.66% (66.47%)\nEpoch: [114][200/313]\tTime 0.090 (0.093)\tData 0.029 (0.028)\tLoss 1.7258 (2.0580)\tCls Loss 0.9542 (1.1656)\tRank Loss 0.7716 (0.8924)\tPrec 74.22% (66.47%)\nEpoch: [114][300/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.7759 (2.0576)\tCls Loss 1.1003 (1.1655)\tRank Loss 0.6757 (0.8921)\tPrec 69.53% (66.48%)\nEpoch: [115][0/313]\tTime 0.092 (0.093)\tData 0.031 (0.028)\tLoss 1.9631 (2.0576)\tCls Loss 1.1066 (1.1655)\tRank Loss 0.8565 (0.8921)\tPrec 66.41% (66.48%)\nEpoch: [115][100/313]\tTime 0.109 (0.093)\tData 0.041 (0.028)\tLoss 2.1862 (2.0570)\tCls Loss 1.1315 (1.1652)\tRank Loss 1.0547 (0.8918)\tPrec 65.62% (66.48%)\nEpoch: [115][200/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 1.9011 (2.0566)\tCls Loss 1.0096 (1.1650)\tRank Loss 0.8915 (0.8916)\tPrec 67.97% (66.49%)\nEpoch: [115][300/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.8086 (2.0563)\tCls Loss 0.9772 (1.1649)\tRank Loss 0.8314 (0.8914)\tPrec 71.09% (66.49%)\nEpoch: [116][0/313]\tTime 0.096 (0.093)\tData 0.033 (0.028)\tLoss 2.0007 (2.0562)\tCls Loss 1.0586 (1.1649)\tRank Loss 0.9421 (0.8913)\tPrec 71.09% (66.49%)\nEpoch: [116][100/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.5088 (2.0556)\tCls Loss 0.8811 (1.1646)\tRank Loss 0.6277 (0.8910)\tPrec 76.56% (66.50%)\nEpoch: [116][200/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.6854 (2.0550)\tCls Loss 1.0809 (1.1643)\tRank Loss 0.6046 (0.8907)\tPrec 68.75% (66.51%)\nEpoch: [116][300/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.5193 (2.0548)\tCls Loss 0.7724 (1.1643)\tRank Loss 0.7468 (0.8905)\tPrec 80.47% (66.51%)\nEpoch: [117][0/313]\tTime 0.099 (0.093)\tData 0.033 (0.028)\tLoss 1.6589 (2.0547)\tCls Loss 0.9541 (1.1642)\tRank Loss 0.7048 (0.8905)\tPrec 71.88% (66.51%)\nEpoch: [117][100/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.8103 (2.0542)\tCls Loss 1.0178 (1.1640)\tRank Loss 0.7924 (0.8902)\tPrec 74.22% (66.52%)\nEpoch: [117][200/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 1.9686 (2.0537)\tCls Loss 1.1170 (1.1638)\tRank Loss 0.8516 (0.8899)\tPrec 67.19% (66.53%)\nEpoch: [117][300/313]\tTime 0.090 (0.093)\tData 0.028 (0.028)\tLoss 2.0127 (2.0533)\tCls Loss 1.2347 (1.1637)\tRank Loss 0.7779 (0.8896)\tPrec 62.50% (66.53%)\nEpoch: [118][0/313]\tTime 0.090 (0.093)\tData 0.030 (0.028)\tLoss 1.5521 (2.0533)\tCls Loss 0.9597 (1.1637)\tRank Loss 0.5924 (0.8896)\tPrec 71.09% (66.53%)\nEpoch: [118][100/313]\tTime 0.086 (0.093)\tData 0.026 (0.028)\tLoss 2.2239 (2.0527)\tCls Loss 1.2824 (1.1634)\tRank Loss 0.9415 (0.8893)\tPrec 67.97% (66.53%)\nEpoch: [118][200/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 2.1464 (2.0524)\tCls Loss 1.2783 (1.1633)\tRank Loss 0.8681 (0.8891)\tPrec 64.84% (66.54%)\nEpoch: [118][300/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 1.6760 (2.0521)\tCls Loss 0.9911 (1.1632)\tRank Loss 0.6849 (0.8889)\tPrec 72.66% (66.54%)\nEpoch: [119][0/313]\tTime 0.090 (0.093)\tData 0.029 (0.028)\tLoss 1.5966 (2.0521)\tCls Loss 0.9747 (1.1632)\tRank Loss 0.6219 (0.8889)\tPrec 75.00% (66.54%)\nEpoch: [119][100/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 1.8050 (2.0514)\tCls Loss 1.0566 (1.1629)\tRank Loss 0.7484 (0.8885)\tPrec 69.53% (66.55%)\nEpoch: [119][200/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.7672 (2.0510)\tCls Loss 1.0340 (1.1627)\tRank Loss 0.7332 (0.8883)\tPrec 67.97% (66.55%)\nEpoch: [119][300/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 1.4325 (2.0508)\tCls Loss 0.9257 (1.1627)\tRank Loss 0.5069 (0.8881)\tPrec 75.78% (66.55%)\nEpoch: [120][0/313]\tTime 0.093 (0.093)\tData 0.032 (0.028)\tLoss 2.0783 (2.0507)\tCls Loss 1.0009 (1.1627)\tRank Loss 1.0774 (0.8880)\tPrec 71.09% (66.55%)\nEpoch: [120][100/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 2.0232 (2.0501)\tCls Loss 1.1649 (1.1624)\tRank Loss 0.8583 (0.8877)\tPrec 64.84% (66.56%)\nEpoch: [120][200/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.8993 (2.0496)\tCls Loss 1.1663 (1.1622)\tRank Loss 0.7329 (0.8875)\tPrec 60.16% (66.57%)\nEpoch: [120][300/313]\tTime 0.088 (0.093)\tData 0.028 (0.028)\tLoss 1.6663 (2.0494)\tCls Loss 1.0312 (1.1621)\tRank Loss 0.6351 (0.8873)\tPrec 73.44% (66.57%)\nEpoch: [121][0/313]\tTime 0.090 (0.093)\tData 0.029 (0.028)\tLoss 1.8581 (2.0493)\tCls Loss 1.0396 (1.1621)\tRank Loss 0.8185 (0.8872)\tPrec 69.53% (66.57%)\nEpoch: [121][100/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.9734 (2.0488)\tCls Loss 1.0328 (1.1618)\tRank Loss 0.9406 (0.8870)\tPrec 66.41% (66.58%)\nEpoch: [121][200/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 1.9255 (2.0484)\tCls Loss 1.1232 (1.1616)\tRank Loss 0.8023 (0.8868)\tPrec 66.41% (66.58%)\nEpoch: [121][300/313]\tTime 0.086 (0.093)\tData 0.026 (0.028)\tLoss 2.0488 (2.0480)\tCls Loss 1.2076 (1.1615)\tRank Loss 0.8411 (0.8865)\tPrec 62.50% (66.58%)\nEpoch: [122][0/313]\tTime 0.096 (0.093)\tData 0.030 (0.028)\tLoss 1.8624 (2.0480)\tCls Loss 0.9986 (1.1615)\tRank Loss 0.8639 (0.8865)\tPrec 66.41% (66.58%)\nEpoch: [122][100/313]\tTime 0.089 (0.093)\tData 0.028 (0.028)\tLoss 1.5571 (2.0474)\tCls Loss 0.9483 (1.1612)\tRank Loss 0.6088 (0.8862)\tPrec 74.22% (66.59%)\nEpoch: [122][200/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.9235 (2.0469)\tCls Loss 1.1078 (1.1610)\tRank Loss 0.8157 (0.8859)\tPrec 69.53% (66.60%)\nEpoch: [122][300/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.9699 (2.0466)\tCls Loss 1.2753 (1.1610)\tRank Loss 0.6946 (0.8857)\tPrec 63.28% (66.60%)\nEpoch: [123][0/313]\tTime 0.114 (0.093)\tData 0.041 (0.028)\tLoss 1.9947 (2.0466)\tCls Loss 1.0695 (1.1609)\tRank Loss 0.9253 (0.8857)\tPrec 68.75% (66.60%)\nEpoch: [123][100/313]\tTime 0.088 (0.093)\tData 0.028 (0.028)\tLoss 1.5867 (2.0461)\tCls Loss 0.9244 (1.1607)\tRank Loss 0.6623 (0.8854)\tPrec 74.22% (66.61%)\nEpoch: [123][200/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.8137 (2.0456)\tCls Loss 1.0581 (1.1605)\tRank Loss 0.7557 (0.8851)\tPrec 71.88% (66.61%)\nEpoch: [123][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 2.3582 (2.0453)\tCls Loss 1.4855 (1.1604)\tRank Loss 0.8727 (0.8849)\tPrec 57.81% (66.61%)\nEpoch: [124][0/313]\tTime 0.092 (0.093)\tData 0.030 (0.028)\tLoss 1.7700 (2.0453)\tCls Loss 0.8869 (1.1604)\tRank Loss 0.8831 (0.8849)\tPrec 76.56% (66.61%)\nEpoch: [124][100/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.8167 (2.0448)\tCls Loss 1.0333 (1.1602)\tRank Loss 0.7834 (0.8846)\tPrec 67.97% (66.62%)\nEpoch: [124][200/313]\tTime 0.086 (0.093)\tData 0.026 (0.028)\tLoss 1.9840 (2.0444)\tCls Loss 1.1633 (1.1600)\tRank Loss 0.8207 (0.8844)\tPrec 64.84% (66.62%)\nEpoch: [124][300/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.9206 (2.0442)\tCls Loss 1.1235 (1.1600)\tRank Loss 0.7971 (0.8842)\tPrec 69.53% (66.62%)\nEpoch: [125][0/313]\tTime 0.092 (0.093)\tData 0.030 (0.028)\tLoss 1.7221 (2.0442)\tCls Loss 0.9926 (1.1600)\tRank Loss 0.7295 (0.8842)\tPrec 72.66% (66.62%)\nEpoch: [125][100/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 1.9940 (2.0437)\tCls Loss 1.0755 (1.1597)\tRank Loss 0.9185 (0.8840)\tPrec 70.31% (66.63%)\nEpoch: [125][200/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.9108 (2.0433)\tCls Loss 1.0125 (1.1596)\tRank Loss 0.8984 (0.8837)\tPrec 69.53% (66.64%)\nEpoch: [125][300/313]\tTime 0.086 (0.093)\tData 0.026 (0.028)\tLoss 2.2718 (2.0429)\tCls Loss 1.2062 (1.1595)\tRank Loss 1.0655 (0.8835)\tPrec 62.50% (66.64%)\nEpoch: [126][0/313]\tTime 0.089 (0.093)\tData 0.029 (0.028)\tLoss 1.7047 (2.0429)\tCls Loss 0.9994 (1.1595)\tRank Loss 0.7053 (0.8834)\tPrec 74.22% (66.64%)\nEpoch: [126][100/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 2.0242 (2.0424)\tCls Loss 1.1480 (1.1593)\tRank Loss 0.8762 (0.8831)\tPrec 62.50% (66.65%)\nEpoch: [126][200/313]\tTime 0.088 (0.093)\tData 0.028 (0.028)\tLoss 1.7752 (2.0420)\tCls Loss 1.0004 (1.1591)\tRank Loss 0.7747 (0.8828)\tPrec 71.09% (66.65%)\nEpoch: [126][300/313]\tTime 0.087 (0.093)\tData 0.027 (0.028)\tLoss 1.4721 (2.0415)\tCls Loss 0.9578 (1.1590)\tRank Loss 0.5144 (0.8826)\tPrec 70.31% (66.65%)\nEpoch: [127][0/313]\tTime 0.091 (0.093)\tData 0.031 (0.028)\tLoss 1.5607 (2.0415)\tCls Loss 0.7925 (1.1590)\tRank Loss 0.7682 (0.8825)\tPrec 79.69% (66.65%)\nEpoch: [127][100/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 1.9582 (2.0411)\tCls Loss 1.1156 (1.1587)\tRank Loss 0.8425 (0.8824)\tPrec 67.97% (66.66%)\nEpoch: [127][200/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 2.0072 (2.0407)\tCls Loss 1.1654 (1.1586)\tRank Loss 0.8418 (0.8821)\tPrec 67.97% (66.67%)\nEpoch: [127][300/313]\tTime 0.089 (0.093)\tData 0.028 (0.028)\tLoss 1.7731 (2.0403)\tCls Loss 0.9979 (1.1584)\tRank Loss 0.7752 (0.8819)\tPrec 68.75% (66.67%)\nEpoch: [128][0/313]\tTime 0.093 (0.093)\tData 0.031 (0.028)\tLoss 1.7104 (2.0403)\tCls Loss 0.9745 (1.1584)\tRank Loss 0.7359 (0.8819)\tPrec 73.44% (66.67%)\nEpoch: [128][100/313]\tTime 0.086 (0.093)\tData 0.027 (0.028)\tLoss 1.9985 (2.0399)\tCls Loss 1.2174 (1.1582)\tRank Loss 0.7811 (0.8816)\tPrec 64.84% (66.67%)\nEpoch: [128][200/313]\tTime 0.091 (0.093)\tData 0.029 (0.028)\tLoss 2.3119 (2.0394)\tCls Loss 1.3121 (1.1580)\tRank Loss 0.9998 (0.8814)\tPrec 61.72% (66.68%)\nEpoch: [128][300/313]\tTime 0.085 (0.093)\tData 0.026 (0.028)\tLoss 2.3978 (2.0391)\tCls Loss 1.5694 (1.1579)\tRank Loss 0.8284 (0.8812)\tPrec 57.81% (66.68%)\nEpoch: [129][0/313]\tTime 0.104 (0.093)\tData 0.034 (0.028)\tLoss 2.0400 (2.0391)\tCls Loss 1.0853 (1.1579)\tRank Loss 0.9547 (0.8811)\tPrec 65.62% (66.68%)\nEpoch: [129][100/313]\tTime 0.086 (0.093)\tData 0.026 (0.028)\tLoss 1.8848 (2.0386)\tCls Loss 1.0341 (1.1577)\tRank Loss 0.8507 (0.8809)\tPrec 68.75% (66.69%)\nEpoch: [129][200/313]\tTime 0.110 (0.093)\tData 0.027 (0.028)\tLoss 1.8852 (2.0382)\tCls Loss 1.2695 (1.1575)\tRank Loss 0.6158 (0.8807)\tPrec 64.84% (66.69%)\nEpoch: [129][300/313]\tTime 0.100 (0.093)\tData 0.031 (0.028)\tLoss 2.0428 (2.0378)\tCls Loss 1.1611 (1.1574)\tRank Loss 0.8818 (0.8804)\tPrec 70.31% (66.70%)\nEpoch: [130][0/313]\tTime 0.094 (0.093)\tData 0.032 (0.028)\tLoss 1.8817 (2.0378)\tCls Loss 1.0392 (1.1574)\tRank Loss 0.8425 (0.8804)\tPrec 63.28% (66.70%)\nEpoch: [130][100/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 1.9153 (2.0373)\tCls Loss 1.1686 (1.1572)\tRank Loss 0.7467 (0.8802)\tPrec 63.28% (66.70%)\nEpoch: [130][200/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.7427 (2.0368)\tCls Loss 1.0131 (1.1569)\tRank Loss 0.7296 (0.8799)\tPrec 70.31% (66.71%)\nEpoch: [130][300/313]\tTime 0.087 (0.093)\tData 0.026 (0.028)\tLoss 2.1845 (2.0365)\tCls Loss 1.3538 (1.1568)\tRank Loss 0.8307 (0.8797)\tPrec 65.62% (66.71%)\nEpoch: [131][0/313]\tTime 0.090 (0.093)\tData 0.029 (0.028)\tLoss 2.1431 (2.0365)\tCls Loss 1.1796 (1.1568)\tRank Loss 0.9635 (0.8796)\tPrec 64.84% (66.71%)\nEpoch: [131][100/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 2.0999 (2.0360)\tCls Loss 1.2549 (1.1566)\tRank Loss 0.8450 (0.8794)\tPrec 65.62% (66.72%)\nEpoch: [131][200/313]\tTime 0.091 (0.093)\tData 0.030 (0.028)\tLoss 1.8077 (2.0356)\tCls Loss 0.9430 (1.1564)\tRank Loss 0.8648 (0.8791)\tPrec 70.31% (66.72%)\nEpoch: [131][300/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 1.8830 (2.0353)\tCls Loss 1.1227 (1.1563)\tRank Loss 0.7603 (0.8789)\tPrec 64.84% (66.72%)\nEpoch: [132][0/313]\tTime 0.099 (0.093)\tData 0.033 (0.028)\tLoss 1.5336 (2.0352)\tCls Loss 0.7686 (1.1563)\tRank Loss 0.7650 (0.8789)\tPrec 78.12% (66.72%)\nEpoch: [132][100/313]\tTime 0.115 (0.093)\tData 0.041 (0.028)\tLoss 1.8180 (2.0347)\tCls Loss 1.0165 (1.1561)\tRank Loss 0.8014 (0.8786)\tPrec 68.75% (66.73%)\nEpoch: [132][200/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 2.2308 (2.0343)\tCls Loss 1.3343 (1.1559)\tRank Loss 0.8965 (0.8784)\tPrec 64.84% (66.73%)\nEpoch: [132][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 2.1784 (2.0340)\tCls Loss 1.3405 (1.1558)\tRank Loss 0.8379 (0.8781)\tPrec 63.28% (66.74%)\nEpoch: [133][0/313]\tTime 0.095 (0.093)\tData 0.032 (0.028)\tLoss 1.9966 (2.0339)\tCls Loss 1.2627 (1.1558)\tRank Loss 0.7339 (0.8781)\tPrec 63.28% (66.74%)\nEpoch: [133][100/313]\tTime 0.093 (0.093)\tData 0.028 (0.028)\tLoss 2.0187 (2.0335)\tCls Loss 1.2859 (1.1556)\tRank Loss 0.7328 (0.8779)\tPrec 62.50% (66.74%)\nEpoch: [133][200/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 1.7344 (2.0330)\tCls Loss 1.0239 (1.1554)\tRank Loss 0.7105 (0.8776)\tPrec 69.53% (66.75%)\nEpoch: [133][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.4766 (2.0327)\tCls Loss 0.7799 (1.1553)\tRank Loss 0.6967 (0.8774)\tPrec 77.34% (66.75%)\nEpoch: [134][0/313]\tTime 0.093 (0.093)\tData 0.031 (0.028)\tLoss 1.9240 (2.0327)\tCls Loss 1.0458 (1.1553)\tRank Loss 0.8783 (0.8774)\tPrec 71.09% (66.75%)\nEpoch: [134][100/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.6944 (2.0321)\tCls Loss 1.0512 (1.1550)\tRank Loss 0.6432 (0.8771)\tPrec 68.75% (66.76%)\nEpoch: [134][200/313]\tTime 0.104 (0.093)\tData 0.034 (0.028)\tLoss 1.8462 (2.0316)\tCls Loss 1.0430 (1.1548)\tRank Loss 0.8033 (0.8769)\tPrec 70.31% (66.76%)\nEpoch: [134][300/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 2.1087 (2.0313)\tCls Loss 1.0258 (1.1547)\tRank Loss 1.0829 (0.8766)\tPrec 71.09% (66.77%)\nEpoch: [135][0/313]\tTime 0.096 (0.093)\tData 0.032 (0.028)\tLoss 2.0128 (2.0313)\tCls Loss 1.2102 (1.1547)\tRank Loss 0.8027 (0.8766)\tPrec 65.62% (66.77%)\nEpoch: [135][100/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 2.1598 (2.0308)\tCls Loss 1.1671 (1.1544)\tRank Loss 0.9928 (0.8764)\tPrec 65.62% (66.77%)\nEpoch: [135][200/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 1.8213 (2.0304)\tCls Loss 1.0669 (1.1543)\tRank Loss 0.7544 (0.8761)\tPrec 71.09% (66.78%)\nEpoch: [135][300/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 2.0677 (2.0301)\tCls Loss 1.0397 (1.1542)\tRank Loss 1.0280 (0.8760)\tPrec 71.09% (66.78%)\nEpoch: [136][0/313]\tTime 0.100 (0.093)\tData 0.033 (0.028)\tLoss 2.2442 (2.0301)\tCls Loss 1.2542 (1.1542)\tRank Loss 0.9900 (0.8759)\tPrec 67.19% (66.78%)\nEpoch: [136][100/313]\tTime 0.098 (0.093)\tData 0.029 (0.028)\tLoss 1.9462 (2.0296)\tCls Loss 1.1811 (1.1539)\tRank Loss 0.7651 (0.8757)\tPrec 67.19% (66.79%)\nEpoch: [136][200/313]\tTime 0.092 (0.093)\tData 0.029 (0.028)\tLoss 1.5515 (2.0292)\tCls Loss 0.8432 (1.1537)\tRank Loss 0.7083 (0.8754)\tPrec 74.22% (66.79%)\nEpoch: [136][300/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.9374 (2.0288)\tCls Loss 1.1208 (1.1536)\tRank Loss 0.8166 (0.8752)\tPrec 62.50% (66.79%)\nEpoch: [137][0/313]\tTime 0.094 (0.093)\tData 0.031 (0.028)\tLoss 1.6178 (2.0288)\tCls Loss 1.0027 (1.1536)\tRank Loss 0.6151 (0.8752)\tPrec 69.53% (66.79%)\nEpoch: [137][100/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 1.7041 (2.0282)\tCls Loss 1.0617 (1.1533)\tRank Loss 0.6424 (0.8750)\tPrec 71.88% (66.80%)\nEpoch: [137][200/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.7709 (2.0278)\tCls Loss 1.0486 (1.1531)\tRank Loss 0.7223 (0.8747)\tPrec 70.31% (66.81%)\nEpoch: [137][300/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 1.8683 (2.0275)\tCls Loss 1.1156 (1.1530)\tRank Loss 0.7527 (0.8745)\tPrec 67.97% (66.81%)\nEpoch: [138][0/313]\tTime 0.099 (0.093)\tData 0.032 (0.028)\tLoss 1.7503 (2.0275)\tCls Loss 0.9675 (1.1530)\tRank Loss 0.7828 (0.8745)\tPrec 70.31% (66.81%)\nEpoch: [138][100/313]\tTime 0.099 (0.093)\tData 0.033 (0.028)\tLoss 1.8078 (2.0270)\tCls Loss 0.9510 (1.1528)\tRank Loss 0.8567 (0.8742)\tPrec 71.09% (66.82%)\nEpoch: [138][200/313]\tTime 0.091 (0.093)\tData 0.029 (0.028)\tLoss 1.8486 (2.0268)\tCls Loss 1.0386 (1.1527)\tRank Loss 0.8099 (0.8741)\tPrec 68.75% (66.82%)\nEpoch: [138][300/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 2.2260 (2.0264)\tCls Loss 1.2265 (1.1525)\tRank Loss 0.9995 (0.8739)\tPrec 61.72% (66.82%)\nEpoch: [139][0/313]\tTime 0.093 (0.093)\tData 0.030 (0.028)\tLoss 1.9410 (2.0264)\tCls Loss 1.0484 (1.1525)\tRank Loss 0.8926 (0.8739)\tPrec 70.31% (66.82%)\nEpoch: [139][100/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.9328 (2.0259)\tCls Loss 1.0887 (1.1523)\tRank Loss 0.8441 (0.8736)\tPrec 68.75% (66.83%)\nEpoch: [139][200/313]\tTime 0.105 (0.093)\tData 0.031 (0.028)\tLoss 1.8319 (2.0255)\tCls Loss 0.9860 (1.1521)\tRank Loss 0.8459 (0.8734)\tPrec 69.53% (66.83%)\nEpoch: [139][300/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 1.8246 (2.0251)\tCls Loss 0.9515 (1.1520)\tRank Loss 0.8731 (0.8732)\tPrec 77.34% (66.84%)\nEpoch: [140][0/313]\tTime 0.128 (0.093)\tData 0.032 (0.028)\tLoss 2.0982 (2.0251)\tCls Loss 1.1906 (1.1520)\tRank Loss 0.9076 (0.8732)\tPrec 60.16% (66.84%)\nEpoch: [140][100/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 2.0094 (2.0247)\tCls Loss 1.1289 (1.1517)\tRank Loss 0.8805 (0.8729)\tPrec 69.53% (66.84%)\nEpoch: [140][200/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 2.1199 (2.0243)\tCls Loss 1.2348 (1.1516)\tRank Loss 0.8851 (0.8727)\tPrec 66.41% (66.85%)\nEpoch: [140][300/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 1.7052 (2.0241)\tCls Loss 1.0213 (1.1516)\tRank Loss 0.6839 (0.8725)\tPrec 71.09% (66.85%)\nEpoch: [141][0/313]\tTime 0.095 (0.093)\tData 0.031 (0.028)\tLoss 1.7456 (2.0241)\tCls Loss 1.0297 (1.1516)\tRank Loss 0.7159 (0.8725)\tPrec 67.97% (66.85%)\nEpoch: [141][100/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.9847 (2.0236)\tCls Loss 1.0820 (1.1513)\tRank Loss 0.9027 (0.8722)\tPrec 69.53% (66.86%)\nEpoch: [141][200/313]\tTime 0.097 (0.093)\tData 0.030 (0.028)\tLoss 2.0129 (2.0232)\tCls Loss 1.2182 (1.1512)\tRank Loss 0.7946 (0.8720)\tPrec 66.41% (66.86%)\nEpoch: [141][300/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 1.6698 (2.0228)\tCls Loss 0.9592 (1.1510)\tRank Loss 0.7106 (0.8718)\tPrec 68.75% (66.87%)\nEpoch: [142][0/313]\tTime 0.091 (0.093)\tData 0.030 (0.028)\tLoss 1.6712 (2.0228)\tCls Loss 0.9874 (1.1510)\tRank Loss 0.6838 (0.8718)\tPrec 73.44% (66.87%)\nEpoch: [142][100/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 1.6321 (2.0224)\tCls Loss 1.0309 (1.1508)\tRank Loss 0.6012 (0.8716)\tPrec 66.41% (66.87%)\nEpoch: [142][200/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.6703 (2.0220)\tCls Loss 1.0608 (1.1506)\tRank Loss 0.6095 (0.8713)\tPrec 72.66% (66.88%)\nEpoch: [142][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.8844 (2.0217)\tCls Loss 1.1443 (1.1506)\tRank Loss 0.7401 (0.8712)\tPrec 63.28% (66.88%)\nEpoch: [143][0/313]\tTime 0.093 (0.093)\tData 0.030 (0.028)\tLoss 1.7928 (2.0217)\tCls Loss 0.9785 (1.1505)\tRank Loss 0.8143 (0.8711)\tPrec 69.53% (66.88%)\nEpoch: [143][100/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 1.9404 (2.0212)\tCls Loss 1.0352 (1.1503)\tRank Loss 0.9052 (0.8709)\tPrec 71.09% (66.89%)\nEpoch: [143][200/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 1.4419 (2.0208)\tCls Loss 0.8617 (1.1501)\tRank Loss 0.5802 (0.8707)\tPrec 73.44% (66.89%)\nEpoch: [143][300/313]\tTime 0.094 (0.093)\tData 0.031 (0.028)\tLoss 1.8149 (2.0206)\tCls Loss 1.1169 (1.1501)\tRank Loss 0.6980 (0.8705)\tPrec 68.75% (66.89%)\nEpoch: [144][0/313]\tTime 0.099 (0.093)\tData 0.033 (0.028)\tLoss 1.9835 (2.0206)\tCls Loss 1.1607 (1.1501)\tRank Loss 0.8228 (0.8705)\tPrec 64.06% (66.89%)\nEpoch: [144][100/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 1.6207 (2.0200)\tCls Loss 0.8821 (1.1498)\tRank Loss 0.7387 (0.8702)\tPrec 76.56% (66.90%)\nEpoch: [144][200/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 2.0431 (2.0197)\tCls Loss 1.1857 (1.1497)\tRank Loss 0.8574 (0.8700)\tPrec 70.31% (66.90%)\nEpoch: [144][300/313]\tTime 0.090 (0.093)\tData 0.026 (0.028)\tLoss 1.6601 (2.0196)\tCls Loss 0.9901 (1.1497)\tRank Loss 0.6700 (0.8699)\tPrec 68.75% (66.90%)\nEpoch: [145][0/313]\tTime 0.091 (0.093)\tData 0.030 (0.028)\tLoss 1.9914 (2.0196)\tCls Loss 1.1148 (1.1497)\tRank Loss 0.8766 (0.8699)\tPrec 68.75% (66.90%)\nEpoch: [145][100/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 1.2605 (2.0187)\tCls Loss 0.6466 (1.1492)\tRank Loss 0.6139 (0.8695)\tPrec 80.47% (66.92%)\nEpoch: [145][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.2786 (2.0174)\tCls Loss 0.6569 (1.1485)\tRank Loss 0.6217 (0.8689)\tPrec 76.56% (66.94%)\nEpoch: [145][300/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.5115 (2.0160)\tCls Loss 0.8329 (1.1477)\tRank Loss 0.6786 (0.8683)\tPrec 68.75% (66.96%)\nEpoch: [146][0/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 1.3934 (2.0158)\tCls Loss 0.7772 (1.1476)\tRank Loss 0.6161 (0.8683)\tPrec 76.56% (66.96%)\nEpoch: [146][100/313]\tTime 0.092 (0.093)\tData 0.029 (0.028)\tLoss 1.2457 (2.0142)\tCls Loss 0.7730 (1.1467)\tRank Loss 0.4727 (0.8676)\tPrec 81.25% (66.99%)\nEpoch: [146][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.1423 (2.0126)\tCls Loss 0.7179 (1.1457)\tRank Loss 0.4244 (0.8669)\tPrec 78.12% (67.02%)\nEpoch: [146][300/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.1995 (2.0109)\tCls Loss 0.6642 (1.1447)\tRank Loss 0.5353 (0.8662)\tPrec 82.03% (67.05%)\nEpoch: [147][0/313]\tTime 0.092 (0.093)\tData 0.029 (0.028)\tLoss 1.1031 (2.0107)\tCls Loss 0.5630 (1.1446)\tRank Loss 0.5402 (0.8661)\tPrec 85.94% (67.05%)\nEpoch: [147][100/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.3455 (2.0089)\tCls Loss 0.7561 (1.1436)\tRank Loss 0.5893 (0.8653)\tPrec 80.47% (67.09%)\nEpoch: [147][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.2992 (2.0070)\tCls Loss 0.6493 (1.1425)\tRank Loss 0.6499 (0.8645)\tPrec 78.91% (67.12%)\nEpoch: [147][300/313]\tTime 0.093 (0.093)\tData 0.029 (0.028)\tLoss 1.2173 (2.0052)\tCls Loss 0.6472 (1.1415)\tRank Loss 0.5701 (0.8638)\tPrec 80.47% (67.15%)\nEpoch: [148][0/313]\tTime 0.100 (0.093)\tData 0.033 (0.028)\tLoss 1.0256 (2.0050)\tCls Loss 0.6349 (1.1413)\tRank Loss 0.3907 (0.8636)\tPrec 82.03% (67.16%)\nEpoch: [148][100/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.3672 (2.0031)\tCls Loss 0.7685 (1.1402)\tRank Loss 0.5986 (0.8629)\tPrec 76.56% (67.19%)\nEpoch: [148][200/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.9867 (2.0012)\tCls Loss 0.5818 (1.1391)\tRank Loss 0.4048 (0.8620)\tPrec 85.16% (67.23%)\nEpoch: [148][300/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.3115 (1.9993)\tCls Loss 0.8185 (1.1381)\tRank Loss 0.4930 (0.8612)\tPrec 77.34% (67.26%)\nEpoch: [149][0/313]\tTime 0.104 (0.093)\tData 0.035 (0.028)\tLoss 1.2064 (1.9991)\tCls Loss 0.6895 (1.1380)\tRank Loss 0.5169 (0.8611)\tPrec 83.59% (67.26%)\nEpoch: [149][100/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 1.2057 (1.9972)\tCls Loss 0.6386 (1.1369)\tRank Loss 0.5671 (0.8603)\tPrec 85.16% (67.30%)\nEpoch: [149][200/313]\tTime 0.106 (0.093)\tData 0.031 (0.028)\tLoss 0.9622 (1.9953)\tCls Loss 0.5372 (1.1358)\tRank Loss 0.4249 (0.8595)\tPrec 85.94% (67.33%)\nEpoch: [149][300/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.2048 (1.9933)\tCls Loss 0.7147 (1.1346)\tRank Loss 0.4901 (0.8587)\tPrec 80.47% (67.37%)\nEpoch: [150][0/313]\tTime 0.093 (0.093)\tData 0.030 (0.028)\tLoss 1.1919 (1.9931)\tCls Loss 0.7172 (1.1345)\tRank Loss 0.4747 (0.8586)\tPrec 84.38% (67.38%)\nEpoch: [150][100/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.3605 (1.9911)\tCls Loss 0.7266 (1.1334)\tRank Loss 0.6338 (0.8577)\tPrec 80.47% (67.41%)\nEpoch: [150][200/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.8788 (1.9891)\tCls Loss 0.5371 (1.1322)\tRank Loss 0.3416 (0.8569)\tPrec 89.06% (67.45%)\nEpoch: [150][300/313]\tTime 0.094 (0.093)\tData 0.030 (0.028)\tLoss 0.8238 (1.9872)\tCls Loss 0.4547 (1.1311)\tRank Loss 0.3691 (0.8560)\tPrec 91.41% (67.49%)\nEpoch: [151][0/313]\tTime 0.098 (0.093)\tData 0.033 (0.028)\tLoss 1.0654 (1.9869)\tCls Loss 0.5537 (1.1310)\tRank Loss 0.5117 (0.8559)\tPrec 89.06% (67.49%)\nEpoch: [151][100/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.8920 (1.9849)\tCls Loss 0.5412 (1.1299)\tRank Loss 0.3508 (0.8551)\tPrec 88.28% (67.53%)\nEpoch: [151][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.0303 (1.9830)\tCls Loss 0.5608 (1.1288)\tRank Loss 0.4695 (0.8542)\tPrec 86.72% (67.57%)\nEpoch: [151][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.0230 (1.9810)\tCls Loss 0.5318 (1.1276)\tRank Loss 0.4912 (0.8534)\tPrec 89.84% (67.60%)\nEpoch: [152][0/313]\tTime 0.101 (0.093)\tData 0.033 (0.028)\tLoss 0.9386 (1.9807)\tCls Loss 0.5393 (1.1275)\tRank Loss 0.3993 (0.8533)\tPrec 86.72% (67.61%)\nEpoch: [152][100/313]\tTime 0.093 (0.093)\tData 0.028 (0.028)\tLoss 0.8188 (1.9787)\tCls Loss 0.4591 (1.1263)\tRank Loss 0.3597 (0.8524)\tPrec 89.06% (67.65%)\nEpoch: [152][200/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 1.1212 (1.9767)\tCls Loss 0.6498 (1.1252)\tRank Loss 0.4715 (0.8515)\tPrec 80.47% (67.69%)\nEpoch: [152][300/313]\tTime 0.093 (0.093)\tData 0.029 (0.028)\tLoss 0.9544 (1.9747)\tCls Loss 0.5531 (1.1240)\tRank Loss 0.4013 (0.8507)\tPrec 87.50% (67.72%)\nEpoch: [153][0/313]\tTime 0.098 (0.093)\tData 0.033 (0.028)\tLoss 0.8227 (1.9744)\tCls Loss 0.5032 (1.1239)\tRank Loss 0.3195 (0.8505)\tPrec 90.62% (67.73%)\nEpoch: [153][100/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.0493 (1.9724)\tCls Loss 0.6050 (1.1227)\tRank Loss 0.4444 (0.8497)\tPrec 83.59% (67.77%)\nEpoch: [153][200/313]\tTime 0.111 (0.093)\tData 0.028 (0.028)\tLoss 1.1082 (1.9704)\tCls Loss 0.6160 (1.1216)\tRank Loss 0.4923 (0.8488)\tPrec 87.50% (67.81%)\nEpoch: [153][300/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 0.9532 (1.9683)\tCls Loss 0.5414 (1.1204)\tRank Loss 0.4118 (0.8479)\tPrec 88.28% (67.85%)\nEpoch: [154][0/313]\tTime 0.094 (0.093)\tData 0.031 (0.028)\tLoss 1.0856 (1.9681)\tCls Loss 0.5221 (1.1203)\tRank Loss 0.5635 (0.8478)\tPrec 90.62% (67.85%)\nEpoch: [154][100/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 1.0829 (1.9661)\tCls Loss 0.6053 (1.1191)\tRank Loss 0.4776 (0.8469)\tPrec 85.16% (67.89%)\nEpoch: [154][200/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 1.0413 (1.9641)\tCls Loss 0.5915 (1.1180)\tRank Loss 0.4498 (0.8460)\tPrec 85.16% (67.93%)\nEpoch: [154][300/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 0.9835 (1.9620)\tCls Loss 0.5585 (1.1169)\tRank Loss 0.4250 (0.8452)\tPrec 86.72% (67.97%)\nEpoch: [155][0/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 0.8513 (1.9618)\tCls Loss 0.5142 (1.1167)\tRank Loss 0.3371 (0.8451)\tPrec 89.06% (67.97%)\nEpoch: [155][100/313]\tTime 0.089 (0.093)\tData 0.028 (0.028)\tLoss 1.1364 (1.9597)\tCls Loss 0.6158 (1.1156)\tRank Loss 0.5206 (0.8442)\tPrec 85.94% (68.01%)\nEpoch: [155][200/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 0.9105 (1.9577)\tCls Loss 0.5523 (1.1144)\tRank Loss 0.3582 (0.8433)\tPrec 89.06% (68.05%)\nEpoch: [155][300/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.0842 (1.9557)\tCls Loss 0.5918 (1.1133)\tRank Loss 0.4924 (0.8424)\tPrec 86.72% (68.09%)\nEpoch: [156][0/313]\tTime 0.094 (0.093)\tData 0.030 (0.028)\tLoss 1.0484 (1.9554)\tCls Loss 0.6247 (1.1131)\tRank Loss 0.4237 (0.8423)\tPrec 85.16% (68.10%)\nEpoch: [156][100/313]\tTime 0.098 (0.093)\tData 0.032 (0.028)\tLoss 0.9391 (1.9534)\tCls Loss 0.5375 (1.1120)\tRank Loss 0.4016 (0.8414)\tPrec 84.38% (68.14%)\nEpoch: [156][200/313]\tTime 0.090 (0.093)\tData 0.026 (0.028)\tLoss 0.8297 (1.9513)\tCls Loss 0.4273 (1.1108)\tRank Loss 0.4024 (0.8405)\tPrec 88.28% (68.17%)\nEpoch: [156][300/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 0.9099 (1.9493)\tCls Loss 0.4911 (1.1097)\tRank Loss 0.4188 (0.8396)\tPrec 88.28% (68.21%)\nEpoch: [157][0/313]\tTime 0.092 (0.093)\tData 0.029 (0.028)\tLoss 0.8883 (1.9490)\tCls Loss 0.4879 (1.1096)\tRank Loss 0.4004 (0.8395)\tPrec 87.50% (68.22%)\nEpoch: [157][100/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.0641 (1.9470)\tCls Loss 0.5373 (1.1084)\tRank Loss 0.5268 (0.8386)\tPrec 87.50% (68.26%)\nEpoch: [157][200/313]\tTime 0.092 (0.093)\tData 0.029 (0.028)\tLoss 0.8929 (1.9449)\tCls Loss 0.5581 (1.1073)\tRank Loss 0.3348 (0.8377)\tPrec 86.72% (68.30%)\nEpoch: [157][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.7817 (1.9429)\tCls Loss 0.4297 (1.1061)\tRank Loss 0.3520 (0.8368)\tPrec 92.97% (68.34%)\nEpoch: [158][0/313]\tTime 0.098 (0.093)\tData 0.032 (0.028)\tLoss 1.0492 (1.9427)\tCls Loss 0.5722 (1.1060)\tRank Loss 0.4770 (0.8367)\tPrec 87.50% (68.34%)\nEpoch: [158][100/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 0.8942 (1.9406)\tCls Loss 0.5396 (1.1048)\tRank Loss 0.3546 (0.8358)\tPrec 86.72% (68.38%)\nEpoch: [158][200/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.8692 (1.9386)\tCls Loss 0.5766 (1.1037)\tRank Loss 0.2926 (0.8349)\tPrec 82.81% (68.42%)\nEpoch: [158][300/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.7950 (1.9366)\tCls Loss 0.4875 (1.1025)\tRank Loss 0.3074 (0.8340)\tPrec 91.41% (68.46%)\nEpoch: [159][0/313]\tTime 0.092 (0.093)\tData 0.030 (0.028)\tLoss 0.9211 (1.9363)\tCls Loss 0.4943 (1.1024)\tRank Loss 0.4268 (0.8339)\tPrec 89.84% (68.47%)\nEpoch: [159][100/313]\tTime 0.090 (0.093)\tData 0.026 (0.028)\tLoss 0.9061 (1.9343)\tCls Loss 0.6103 (1.1013)\tRank Loss 0.2958 (0.8330)\tPrec 85.16% (68.51%)\nEpoch: [159][200/313]\tTime 0.093 (0.093)\tData 0.029 (0.028)\tLoss 0.8984 (1.9322)\tCls Loss 0.4812 (1.1001)\tRank Loss 0.4172 (0.8321)\tPrec 92.19% (68.55%)\nEpoch: [159][300/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 0.9997 (1.9302)\tCls Loss 0.6149 (1.0990)\tRank Loss 0.3848 (0.8312)\tPrec 84.38% (68.59%)\nEpoch: [160][0/313]\tTime 0.093 (0.093)\tData 0.029 (0.028)\tLoss 0.9835 (1.9300)\tCls Loss 0.6075 (1.0988)\tRank Loss 0.3760 (0.8311)\tPrec 88.28% (68.59%)\nEpoch: [160][100/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 0.9010 (1.9279)\tCls Loss 0.4682 (1.0977)\tRank Loss 0.4328 (0.8302)\tPrec 91.41% (68.63%)\nEpoch: [160][200/313]\tTime 0.112 (0.093)\tData 0.027 (0.028)\tLoss 0.9112 (1.9259)\tCls Loss 0.5768 (1.0966)\tRank Loss 0.3344 (0.8293)\tPrec 84.38% (68.67%)\nEpoch: [160][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.9889 (1.9239)\tCls Loss 0.5222 (1.0955)\tRank Loss 0.4667 (0.8284)\tPrec 89.84% (68.71%)\nEpoch: [161][0/313]\tTime 0.094 (0.093)\tData 0.031 (0.028)\tLoss 0.9878 (1.9236)\tCls Loss 0.6149 (1.0953)\tRank Loss 0.3729 (0.8283)\tPrec 85.16% (68.72%)\nEpoch: [161][100/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.9097 (1.9216)\tCls Loss 0.5336 (1.0942)\tRank Loss 0.3761 (0.8274)\tPrec 83.59% (68.75%)\nEpoch: [161][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.9220 (1.9196)\tCls Loss 0.5031 (1.0930)\tRank Loss 0.4189 (0.8265)\tPrec 89.06% (68.79%)\nEpoch: [161][300/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 1.0040 (1.9175)\tCls Loss 0.6434 (1.0919)\tRank Loss 0.3605 (0.8256)\tPrec 88.28% (68.83%)\nEpoch: [162][0/313]\tTime 0.097 (0.093)\tData 0.032 (0.028)\tLoss 0.8645 (1.9173)\tCls Loss 0.5540 (1.0918)\tRank Loss 0.3105 (0.8255)\tPrec 89.06% (68.84%)\nEpoch: [162][100/313]\tTime 0.096 (0.093)\tData 0.029 (0.028)\tLoss 0.8751 (1.9153)\tCls Loss 0.4679 (1.0907)\tRank Loss 0.4073 (0.8246)\tPrec 93.75% (68.88%)\nEpoch: [162][200/313]\tTime 0.089 (0.093)\tData 0.027 (0.028)\tLoss 1.0457 (1.9133)\tCls Loss 0.5396 (1.0896)\tRank Loss 0.5061 (0.8237)\tPrec 87.50% (68.92%)\nEpoch: [162][300/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 0.7991 (1.9113)\tCls Loss 0.4837 (1.0885)\tRank Loss 0.3154 (0.8228)\tPrec 89.06% (68.96%)\nEpoch: [163][0/313]\tTime 0.091 (0.093)\tData 0.029 (0.028)\tLoss 0.8223 (1.9111)\tCls Loss 0.4730 (1.0883)\tRank Loss 0.3493 (0.8227)\tPrec 92.19% (68.96%)\nEpoch: [163][100/313]\tTime 0.090 (0.093)\tData 0.028 (0.028)\tLoss 0.7854 (1.9090)\tCls Loss 0.4626 (1.0872)\tRank Loss 0.3228 (0.8218)\tPrec 92.97% (69.00%)\nEpoch: [163][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.9320 (1.9070)\tCls Loss 0.5225 (1.0861)\tRank Loss 0.4095 (0.8210)\tPrec 88.28% (69.04%)\nEpoch: [163][300/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 0.8003 (1.9050)\tCls Loss 0.4762 (1.0850)\tRank Loss 0.3241 (0.8201)\tPrec 92.97% (69.08%)\nEpoch: [164][0/313]\tTime 0.093 (0.093)\tData 0.031 (0.028)\tLoss 0.8289 (1.9048)\tCls Loss 0.5054 (1.0848)\tRank Loss 0.3234 (0.8199)\tPrec 91.41% (69.09%)\nEpoch: [164][100/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.8457 (1.9028)\tCls Loss 0.5267 (1.0837)\tRank Loss 0.3190 (0.8191)\tPrec 91.41% (69.13%)\nEpoch: [164][200/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 0.9393 (1.9008)\tCls Loss 0.4414 (1.0826)\tRank Loss 0.4979 (0.8182)\tPrec 94.53% (69.17%)\nEpoch: [164][300/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 0.9267 (1.8988)\tCls Loss 0.5734 (1.0815)\tRank Loss 0.3533 (0.8173)\tPrec 88.28% (69.21%)\nEpoch: [165][0/313]\tTime 0.094 (0.093)\tData 0.031 (0.028)\tLoss 0.8113 (1.8986)\tCls Loss 0.4621 (1.0814)\tRank Loss 0.3492 (0.8172)\tPrec 91.41% (69.21%)\nEpoch: [165][100/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.8122 (1.8966)\tCls Loss 0.5178 (1.0803)\tRank Loss 0.2944 (0.8163)\tPrec 88.28% (69.25%)\nEpoch: [165][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.9166 (1.8946)\tCls Loss 0.4639 (1.0792)\tRank Loss 0.4527 (0.8154)\tPrec 92.97% (69.29%)\nEpoch: [165][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.8733 (1.8926)\tCls Loss 0.5364 (1.0781)\tRank Loss 0.3370 (0.8145)\tPrec 89.84% (69.33%)\nEpoch: [166][0/313]\tTime 0.092 (0.093)\tData 0.030 (0.028)\tLoss 0.7191 (1.8924)\tCls Loss 0.4120 (1.0780)\tRank Loss 0.3071 (0.8144)\tPrec 89.84% (69.33%)\nEpoch: [166][100/313]\tTime 0.088 (0.093)\tData 0.027 (0.028)\tLoss 0.8983 (1.8904)\tCls Loss 0.5501 (1.0769)\tRank Loss 0.3482 (0.8135)\tPrec 86.72% (69.37%)\nEpoch: [166][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.9287 (1.8885)\tCls Loss 0.4952 (1.0758)\tRank Loss 0.4335 (0.8127)\tPrec 88.28% (69.41%)\nEpoch: [166][300/313]\tTime 0.089 (0.093)\tData 0.028 (0.028)\tLoss 0.9325 (1.8865)\tCls Loss 0.5479 (1.0747)\tRank Loss 0.3846 (0.8118)\tPrec 88.28% (69.45%)\nEpoch: [167][0/313]\tTime 0.094 (0.093)\tData 0.031 (0.028)\tLoss 0.8436 (1.8863)\tCls Loss 0.5364 (1.0746)\tRank Loss 0.3072 (0.8117)\tPrec 85.16% (69.46%)\nEpoch: [167][100/313]\tTime 0.092 (0.093)\tData 0.029 (0.028)\tLoss 0.9213 (1.8843)\tCls Loss 0.5886 (1.0735)\tRank Loss 0.3327 (0.8108)\tPrec 89.06% (69.50%)\nEpoch: [167][200/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.8525 (1.8823)\tCls Loss 0.5133 (1.0724)\tRank Loss 0.3391 (0.8099)\tPrec 86.72% (69.54%)\nEpoch: [167][300/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.8242 (1.8803)\tCls Loss 0.5560 (1.0713)\tRank Loss 0.2682 (0.8090)\tPrec 85.16% (69.57%)\nEpoch: [168][0/313]\tTime 0.129 (0.093)\tData 0.042 (0.028)\tLoss 0.7444 (1.8801)\tCls Loss 0.4726 (1.0712)\tRank Loss 0.2718 (0.8089)\tPrec 88.28% (69.58%)\nEpoch: [168][100/313]\tTime 0.094 (0.093)\tData 0.030 (0.028)\tLoss 0.8746 (1.8781)\tCls Loss 0.5416 (1.0701)\tRank Loss 0.3330 (0.8080)\tPrec 86.72% (69.62%)\nEpoch: [168][200/313]\tTime 0.089 (0.093)\tData 0.028 (0.028)\tLoss 0.9230 (1.8762)\tCls Loss 0.5760 (1.0690)\tRank Loss 0.3471 (0.8072)\tPrec 89.84% (69.66%)\nEpoch: [168][300/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.8026 (1.8742)\tCls Loss 0.4405 (1.0679)\tRank Loss 0.3620 (0.8063)\tPrec 89.84% (69.69%)\nEpoch: [169][0/313]\tTime 0.101 (0.093)\tData 0.033 (0.028)\tLoss 0.7335 (1.8740)\tCls Loss 0.4695 (1.0678)\tRank Loss 0.2640 (0.8062)\tPrec 89.06% (69.70%)\nEpoch: [169][100/313]\tTime 0.091 (0.093)\tData 0.026 (0.028)\tLoss 0.9856 (1.8720)\tCls Loss 0.5745 (1.0668)\tRank Loss 0.4112 (0.8053)\tPrec 89.06% (69.74%)\nEpoch: [169][200/313]\tTime 0.095 (0.093)\tData 0.030 (0.028)\tLoss 0.8791 (1.8701)\tCls Loss 0.5452 (1.0657)\tRank Loss 0.3338 (0.8044)\tPrec 89.06% (69.78%)\nEpoch: [169][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.8585 (1.8681)\tCls Loss 0.5003 (1.0646)\tRank Loss 0.3583 (0.8035)\tPrec 89.06% (69.82%)\nEpoch: [170][0/313]\tTime 0.099 (0.093)\tData 0.032 (0.028)\tLoss 0.8660 (1.8679)\tCls Loss 0.5287 (1.0645)\tRank Loss 0.3374 (0.8034)\tPrec 89.84% (69.82%)\nEpoch: [170][100/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.9002 (1.8659)\tCls Loss 0.5104 (1.0634)\tRank Loss 0.3898 (0.8026)\tPrec 90.62% (69.86%)\nEpoch: [170][200/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 0.8099 (1.8640)\tCls Loss 0.4502 (1.0623)\tRank Loss 0.3597 (0.8017)\tPrec 91.41% (69.90%)\nEpoch: [170][300/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 0.8200 (1.8621)\tCls Loss 0.4666 (1.0613)\tRank Loss 0.3534 (0.8008)\tPrec 92.19% (69.94%)\nEpoch: [171][0/313]\tTime 0.095 (0.093)\tData 0.031 (0.028)\tLoss 0.7263 (1.8618)\tCls Loss 0.4148 (1.0611)\tRank Loss 0.3115 (0.8007)\tPrec 93.75% (69.94%)\nEpoch: [171][100/313]\tTime 0.093 (0.093)\tData 0.029 (0.028)\tLoss 0.8186 (1.8599)\tCls Loss 0.5333 (1.0601)\tRank Loss 0.2853 (0.7998)\tPrec 88.28% (69.98%)\nEpoch: [171][200/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.8081 (1.8580)\tCls Loss 0.4379 (1.0590)\tRank Loss 0.3702 (0.7990)\tPrec 89.84% (70.02%)\nEpoch: [171][300/313]\tTime 0.091 (0.093)\tData 0.027 (0.028)\tLoss 0.7756 (1.8561)\tCls Loss 0.4558 (1.0580)\tRank Loss 0.3199 (0.7981)\tPrec 92.19% (70.06%)\nEpoch: [172][0/313]\tTime 0.092 (0.093)\tData 0.030 (0.028)\tLoss 0.9059 (1.8558)\tCls Loss 0.4738 (1.0578)\tRank Loss 0.4321 (0.7980)\tPrec 91.41% (70.06%)\nEpoch: [172][100/313]\tTime 0.094 (0.093)\tData 0.030 (0.028)\tLoss 0.7514 (1.8539)\tCls Loss 0.5106 (1.0568)\tRank Loss 0.2407 (0.7971)\tPrec 91.41% (70.10%)\nEpoch: [172][200/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 0.7701 (1.8520)\tCls Loss 0.4448 (1.0557)\tRank Loss 0.3253 (0.7963)\tPrec 92.19% (70.14%)\nEpoch: [172][300/313]\tTime 0.090 (0.093)\tData 0.028 (0.028)\tLoss 0.9408 (1.8501)\tCls Loss 0.6447 (1.0547)\tRank Loss 0.2962 (0.7954)\tPrec 87.50% (70.18%)\nEpoch: [173][0/313]\tTime 0.096 (0.093)\tData 0.031 (0.028)\tLoss 0.7501 (1.8498)\tCls Loss 0.4414 (1.0545)\tRank Loss 0.3086 (0.7953)\tPrec 91.41% (70.18%)\nEpoch: [173][100/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.8565 (1.8479)\tCls Loss 0.5344 (1.0535)\tRank Loss 0.3220 (0.7944)\tPrec 89.84% (70.22%)\nEpoch: [173][200/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 0.7576 (1.8460)\tCls Loss 0.4738 (1.0525)\tRank Loss 0.2838 (0.7935)\tPrec 92.19% (70.26%)\nEpoch: [173][300/313]\tTime 0.095 (0.093)\tData 0.031 (0.028)\tLoss 0.8587 (1.8441)\tCls Loss 0.5210 (1.0514)\tRank Loss 0.3376 (0.7927)\tPrec 88.28% (70.30%)\nEpoch: [174][0/313]\tTime 0.125 (0.093)\tData 0.042 (0.028)\tLoss 0.8038 (1.8438)\tCls Loss 0.4692 (1.0513)\tRank Loss 0.3346 (0.7926)\tPrec 92.19% (70.30%)\nEpoch: [174][100/313]\tTime 0.089 (0.093)\tData 0.026 (0.028)\tLoss 0.7976 (1.8419)\tCls Loss 0.4456 (1.0502)\tRank Loss 0.3519 (0.7917)\tPrec 91.41% (70.34%)\nEpoch: [174][200/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 1.0658 (1.8400)\tCls Loss 0.5708 (1.0492)\tRank Loss 0.4951 (0.7908)\tPrec 87.50% (70.38%)\nEpoch: [174][300/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.9349 (1.8382)\tCls Loss 0.5920 (1.0482)\tRank Loss 0.3430 (0.7900)\tPrec 85.16% (70.42%)\nEpoch: [175][0/313]\tTime 0.097 (0.093)\tData 0.031 (0.028)\tLoss 0.7533 (1.8379)\tCls Loss 0.4759 (1.0481)\tRank Loss 0.2774 (0.7899)\tPrec 92.97% (70.42%)\nEpoch: [175][100/313]\tTime 0.092 (0.093)\tData 0.029 (0.028)\tLoss 0.8429 (1.8360)\tCls Loss 0.5160 (1.0470)\tRank Loss 0.3269 (0.7890)\tPrec 92.97% (70.46%)\nEpoch: [175][200/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.8419 (1.8342)\tCls Loss 0.4802 (1.0460)\tRank Loss 0.3617 (0.7882)\tPrec 92.19% (70.50%)\nEpoch: [175][300/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.8442 (1.8323)\tCls Loss 0.4832 (1.0450)\tRank Loss 0.3609 (0.7873)\tPrec 93.75% (70.53%)\nEpoch: [176][0/313]\tTime 0.097 (0.093)\tData 0.033 (0.028)\tLoss 0.8902 (1.8321)\tCls Loss 0.5715 (1.0449)\tRank Loss 0.3187 (0.7872)\tPrec 88.28% (70.54%)\nEpoch: [176][100/313]\tTime 0.101 (0.093)\tData 0.028 (0.028)\tLoss 0.7084 (1.8302)\tCls Loss 0.4114 (1.0438)\tRank Loss 0.2969 (0.7864)\tPrec 92.97% (70.58%)\nEpoch: [176][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.9310 (1.8283)\tCls Loss 0.5420 (1.0428)\tRank Loss 0.3889 (0.7855)\tPrec 91.41% (70.61%)\nEpoch: [176][300/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.7773 (1.8265)\tCls Loss 0.4924 (1.0418)\tRank Loss 0.2849 (0.7847)\tPrec 88.28% (70.65%)\nEpoch: [177][0/313]\tTime 0.093 (0.093)\tData 0.030 (0.028)\tLoss 0.5695 (1.8263)\tCls Loss 0.3648 (1.0417)\tRank Loss 0.2047 (0.7846)\tPrec 94.53% (70.66%)\nEpoch: [177][100/313]\tTime 0.090 (0.093)\tData 0.026 (0.028)\tLoss 0.7216 (1.8244)\tCls Loss 0.4635 (1.0407)\tRank Loss 0.2581 (0.7837)\tPrec 93.75% (70.69%)\nEpoch: [177][200/313]\tTime 0.096 (0.093)\tData 0.028 (0.028)\tLoss 0.7367 (1.8225)\tCls Loss 0.5104 (1.0397)\tRank Loss 0.2263 (0.7829)\tPrec 91.41% (70.73%)\nEpoch: [177][300/313]\tTime 0.092 (0.093)\tData 0.029 (0.028)\tLoss 0.8648 (1.8207)\tCls Loss 0.5433 (1.0387)\tRank Loss 0.3215 (0.7820)\tPrec 89.84% (70.77%)\nEpoch: [178][0/313]\tTime 0.093 (0.093)\tData 0.030 (0.028)\tLoss 0.8807 (1.8205)\tCls Loss 0.5635 (1.0385)\tRank Loss 0.3172 (0.7819)\tPrec 88.28% (70.77%)\nEpoch: [178][100/313]\tTime 0.090 (0.093)\tData 0.028 (0.028)\tLoss 0.7496 (1.8186)\tCls Loss 0.4888 (1.0375)\tRank Loss 0.2608 (0.7811)\tPrec 92.19% (70.81%)\nEpoch: [178][200/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.8144 (1.8167)\tCls Loss 0.5055 (1.0365)\tRank Loss 0.3089 (0.7802)\tPrec 92.19% (70.84%)\nEpoch: [178][300/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.8634 (1.8149)\tCls Loss 0.5504 (1.0355)\tRank Loss 0.3131 (0.7794)\tPrec 92.97% (70.88%)\nEpoch: [179][0/313]\tTime 0.094 (0.093)\tData 0.031 (0.028)\tLoss 0.9458 (1.8147)\tCls Loss 0.5953 (1.0354)\tRank Loss 0.3505 (0.7793)\tPrec 86.72% (70.89%)\nEpoch: [179][100/313]\tTime 0.091 (0.093)\tData 0.028 (0.028)\tLoss 0.8526 (1.8129)\tCls Loss 0.4730 (1.0344)\tRank Loss 0.3796 (0.7785)\tPrec 93.75% (70.92%)\nEpoch: [179][200/313]\tTime 0.090 (0.093)\tData 0.027 (0.028)\tLoss 0.8333 (1.8110)\tCls Loss 0.4827 (1.0334)\tRank Loss 0.3506 (0.7776)\tPrec 92.19% (70.96%)\nEpoch: [179][300/313]\tTime 0.090 (0.093)\tData 0.028 (0.028)\tLoss 0.7478 (1.8092)\tCls Loss 0.4549 (1.0324)\tRank Loss 0.2929 (0.7768)\tPrec 89.84% (71.00%)\nEpoch: [180][0/313]\tTime 0.096 (0.093)\tData 0.030 (0.028)\tLoss 0.7184 (1.8090)\tCls Loss 0.4681 (1.0323)\tRank Loss 0.2503 (0.7767)\tPrec 89.06% (71.00%)\nEpoch: [180][100/313]\tTime 0.088 (0.093)\tData 0.026 (0.028)\tLoss 0.7687 (1.8072)\tCls Loss 0.5067 (1.0313)\tRank Loss 0.2620 (0.7759)\tPrec 92.19% (71.04%)\nEpoch: [180][200/313]\tTime 0.089 (0.092)\tData 0.027 (0.028)\tLoss 0.6670 (1.8053)\tCls Loss 0.3951 (1.0303)\tRank Loss 0.2718 (0.7750)\tPrec 92.19% (71.07%)\nEpoch: [180][300/313]\tTime 0.092 (0.092)\tData 0.027 (0.028)\tLoss 0.6828 (1.8035)\tCls Loss 0.4259 (1.0293)\tRank Loss 0.2569 (0.7742)\tPrec 95.31% (71.11%)\nEpoch: [181][0/313]\tTime 0.098 (0.092)\tData 0.032 (0.028)\tLoss 0.8710 (1.8033)\tCls Loss 0.5552 (1.0292)\tRank Loss 0.3158 (0.7741)\tPrec 88.28% (71.11%)\nEpoch: [181][100/313]\tTime 0.096 (0.093)\tData 0.029 (0.028)\tLoss 0.8143 (1.8015)\tCls Loss 0.4627 (1.0282)\tRank Loss 0.3516 (0.7732)\tPrec 90.62% (71.15%)\nEpoch: [181][200/313]\tTime 0.095 (0.093)\tData 0.028 (0.028)\tLoss 0.6889 (1.7996)\tCls Loss 0.3395 (1.0272)\tRank Loss 0.3494 (0.7724)\tPrec 95.31% (71.19%)\nEpoch: [181][300/313]\tTime 0.092 (0.093)\tData 0.027 (0.028)\tLoss 0.6300 (1.7978)\tCls Loss 0.3955 (1.0263)\tRank Loss 0.2345 (0.7716)\tPrec 96.09% (71.22%)\nEpoch: [182][0/313]\tTime 0.096 (0.093)\tData 0.030 (0.028)\tLoss 0.6502 (1.7976)\tCls Loss 0.3810 (1.0261)\tRank Loss 0.2692 (0.7715)\tPrec 95.31% (71.23%)\nEpoch: [182][100/313]\tTime 0.094 (0.093)\tData 0.028 (0.028)\tLoss 0.5961 (1.7958)\tCls Loss 0.3190 (1.0251)\tRank Loss 0.2771 (0.7707)\tPrec 93.75% (71.26%)\nEpoch: [182][200/313]\tTime 0.093 (0.093)\tData 0.029 (0.028)\tLoss 0.6834 (1.7940)\tCls Loss 0.4212 (1.0242)\tRank Loss 0.2622 (0.7698)\tPrec 95.31% (71.30%)\nEpoch: [182][300/313]\tTime 0.092 (0.093)\tData 0.027 (0.028)\tLoss 0.7360 (1.7922)\tCls Loss 0.4216 (1.0232)\tRank Loss 0.3145 (0.7690)\tPrec 95.31% (71.33%)\nEpoch: [183][0/313]\tTime 0.097 (0.093)\tData 0.031 (0.028)\tLoss 0.6083 (1.7920)\tCls Loss 0.3206 (1.0231)\tRank Loss 0.2877 (0.7689)\tPrec 96.09% (71.34%)\nEpoch: [183][100/313]\tTime 0.093 (0.093)\tData 0.028 (0.028)\tLoss 0.7082 (1.7902)\tCls Loss 0.4910 (1.0221)\tRank Loss 0.2172 (0.7681)\tPrec 90.62% (71.38%)\nEpoch: [183][200/313]\tTime 0.095 (0.093)\tData 0.030 (0.028)\tLoss 0.7442 (1.7884)\tCls Loss 0.4121 (1.0211)\tRank Loss 0.3321 (0.7673)\tPrec 92.97% (71.41%)\nEpoch: [183][300/313]\tTime 0.096 (0.093)\tData 0.030 (0.028)\tLoss 0.8184 (1.7867)\tCls Loss 0.5237 (1.0202)\tRank Loss 0.2947 (0.7665)\tPrec 89.84% (71.45%)\nEpoch: [184][0/313]\tTime 0.109 (0.093)\tData 0.039 (0.028)\tLoss 0.6504 (1.7864)\tCls Loss 0.4310 (1.0201)\tRank Loss 0.2193 (0.7664)\tPrec 93.75% (71.45%)\nEpoch: [184][100/313]\tTime 0.093 (0.093)\tData 0.027 (0.028)\tLoss 0.8200 (1.7846)\tCls Loss 0.5228 (1.0191)\tRank Loss 0.2971 (0.7655)\tPrec 91.41% (71.49%)\nEpoch: [184][200/313]\tTime 0.094 (0.093)\tData 0.028 (0.028)\tLoss 0.9539 (1.7829)\tCls Loss 0.5294 (1.0181)\tRank Loss 0.4246 (0.7647)\tPrec 92.19% (71.52%)\nEpoch: [184][300/313]\tTime 0.095 (0.093)\tData 0.029 (0.028)\tLoss 0.7902 (1.7811)\tCls Loss 0.4506 (1.0172)\tRank Loss 0.3396 (0.7639)\tPrec 88.28% (71.56%)\nEpoch: [185][0/313]\tTime 0.098 (0.093)\tData 0.032 (0.028)\tLoss 0.8010 (1.7809)\tCls Loss 0.4584 (1.0170)\tRank Loss 0.3426 (0.7638)\tPrec 91.41% (71.56%)\nEpoch: [185][100/313]\tTime 0.093 (0.093)\tData 0.029 (0.028)\tLoss 0.6329 (1.7791)\tCls Loss 0.3872 (1.0161)\tRank Loss 0.2457 (0.7630)\tPrec 94.53% (71.60%)\nEpoch: [185][200/313]\tTime 0.095 (0.093)\tData 0.029 (0.028)\tLoss 0.6248 (1.7773)\tCls Loss 0.3773 (1.0151)\tRank Loss 0.2475 (0.7622)\tPrec 92.19% (71.63%)\nEpoch: [185][300/313]\tTime 0.434 (0.093)\tData 0.030 (0.028)\tLoss 0.6869 (1.7756)\tCls Loss 0.4443 (1.0142)\tRank Loss 0.2426 (0.7614)\tPrec 92.19% (71.67%)\nEpoch: [186][0/313]\tTime 0.096 (0.093)\tData 0.031 (0.028)\tLoss 0.7563 (1.7754)\tCls Loss 0.4414 (1.0141)\tRank Loss 0.3149 (0.7613)\tPrec 94.53% (71.67%)\nEpoch: [186][100/313]\tTime 0.097 (0.093)\tData 0.031 (0.028)\tLoss 0.6912 (1.7736)\tCls Loss 0.4358 (1.0131)\tRank Loss 0.2554 (0.7605)\tPrec 92.97% (71.71%)\nEpoch: [186][200/313]\tTime 0.101 (0.093)\tData 0.031 (0.028)\tLoss 0.7518 (1.7719)\tCls Loss 0.4255 (1.0122)\tRank Loss 0.3263 (0.7597)\tPrec 89.06% (71.74%)\nEpoch: [186][300/313]\tTime 0.092 (0.093)\tData 0.027 (0.028)\tLoss 0.7777 (1.7701)\tCls Loss 0.5022 (1.0112)\tRank Loss 0.2754 (0.7589)\tPrec 88.28% (71.78%)\nEpoch: [187][0/313]\tTime 0.097 (0.093)\tData 0.031 (0.028)\tLoss 0.8315 (1.7699)\tCls Loss 0.5474 (1.0111)\tRank Loss 0.2841 (0.7588)\tPrec 90.62% (71.78%)\nEpoch: [187][100/313]\tTime 0.095 (0.093)\tData 0.028 (0.028)\tLoss 0.7150 (1.7682)\tCls Loss 0.3974 (1.0102)\tRank Loss 0.3176 (0.7580)\tPrec 90.62% (71.82%)\nEpoch: [187][200/313]\tTime 0.092 (0.093)\tData 0.027 (0.028)\tLoss 0.7919 (1.7664)\tCls Loss 0.5699 (1.0092)\tRank Loss 0.2220 (0.7572)\tPrec 84.38% (71.85%)\nEpoch: [187][300/313]\tTime 0.096 (0.093)\tData 0.030 (0.028)\tLoss 0.7067 (1.7647)\tCls Loss 0.4954 (1.0083)\tRank Loss 0.2113 (0.7564)\tPrec 93.75% (71.89%)\nEpoch: [188][0/313]\tTime 0.096 (0.093)\tData 0.031 (0.028)\tLoss 0.7841 (1.7645)\tCls Loss 0.5038 (1.0082)\tRank Loss 0.2804 (0.7563)\tPrec 89.84% (71.89%)\nEpoch: [188][100/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 0.7243 (1.7627)\tCls Loss 0.4852 (1.0072)\tRank Loss 0.2392 (0.7555)\tPrec 87.50% (71.93%)\nEpoch: [188][200/313]\tTime 0.095 (0.093)\tData 0.028 (0.028)\tLoss 0.7555 (1.7610)\tCls Loss 0.4897 (1.0063)\tRank Loss 0.2658 (0.7547)\tPrec 91.41% (71.96%)\nEpoch: [188][300/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 0.7164 (1.7593)\tCls Loss 0.4548 (1.0054)\tRank Loss 0.2616 (0.7539)\tPrec 92.97% (72.00%)\nEpoch: [189][0/313]\tTime 0.097 (0.093)\tData 0.031 (0.028)\tLoss 0.8198 (1.7591)\tCls Loss 0.5185 (1.0053)\tRank Loss 0.3013 (0.7538)\tPrec 90.62% (72.00%)\nEpoch: [189][100/313]\tTime 0.093 (0.093)\tData 0.029 (0.028)\tLoss 0.6714 (1.7574)\tCls Loss 0.3942 (1.0043)\tRank Loss 0.2772 (0.7530)\tPrec 91.41% (72.04%)\nEpoch: [189][200/313]\tTime 0.096 (0.093)\tData 0.029 (0.028)\tLoss 0.7926 (1.7557)\tCls Loss 0.4757 (1.0034)\tRank Loss 0.3169 (0.7523)\tPrec 91.41% (72.07%)\nEpoch: [189][300/313]\tTime 0.092 (0.093)\tData 0.027 (0.028)\tLoss 0.7003 (1.7539)\tCls Loss 0.4558 (1.0025)\tRank Loss 0.2445 (0.7515)\tPrec 90.62% (72.10%)\nEpoch: [190][0/313]\tTime 0.097 (0.093)\tData 0.031 (0.028)\tLoss 0.7773 (1.7537)\tCls Loss 0.4660 (1.0024)\tRank Loss 0.3113 (0.7514)\tPrec 92.19% (72.11%)\nEpoch: [190][100/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 0.7001 (1.7520)\tCls Loss 0.3941 (1.0014)\tRank Loss 0.3060 (0.7506)\tPrec 95.31% (72.14%)\nEpoch: [190][200/313]\tTime 0.093 (0.093)\tData 0.028 (0.028)\tLoss 0.7292 (1.7503)\tCls Loss 0.4331 (1.0005)\tRank Loss 0.2962 (0.7498)\tPrec 95.31% (72.18%)\nEpoch: [190][300/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 0.7415 (1.7486)\tCls Loss 0.4520 (0.9996)\tRank Loss 0.2894 (0.7490)\tPrec 92.19% (72.21%)\nEpoch: [191][0/313]\tTime 0.097 (0.093)\tData 0.032 (0.028)\tLoss 0.7566 (1.7484)\tCls Loss 0.3945 (0.9995)\tRank Loss 0.3621 (0.7489)\tPrec 93.75% (72.22%)\nEpoch: [191][100/313]\tTime 0.096 (0.093)\tData 0.028 (0.028)\tLoss 0.8604 (1.7467)\tCls Loss 0.5762 (0.9986)\tRank Loss 0.2842 (0.7481)\tPrec 88.28% (72.25%)\nEpoch: [191][200/313]\tTime 0.094 (0.093)\tData 0.028 (0.028)\tLoss 0.7810 (1.7450)\tCls Loss 0.5051 (0.9976)\tRank Loss 0.2759 (0.7473)\tPrec 93.75% (72.28%)\nEpoch: [191][300/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 0.7227 (1.7433)\tCls Loss 0.5116 (0.9967)\tRank Loss 0.2111 (0.7466)\tPrec 89.84% (72.32%)\nEpoch: [192][0/313]\tTime 0.098 (0.093)\tData 0.032 (0.028)\tLoss 0.8092 (1.7431)\tCls Loss 0.5207 (0.9966)\tRank Loss 0.2885 (0.7465)\tPrec 89.84% (72.32%)\nEpoch: [192][100/313]\tTime 0.096 (0.093)\tData 0.031 (0.028)\tLoss 0.6663 (1.7414)\tCls Loss 0.3660 (0.9957)\tRank Loss 0.3003 (0.7457)\tPrec 98.44% (72.36%)\nEpoch: [192][200/313]\tTime 0.095 (0.093)\tData 0.029 (0.028)\tLoss 0.6888 (1.7397)\tCls Loss 0.3999 (0.9948)\tRank Loss 0.2889 (0.7449)\tPrec 95.31% (72.39%)\nEpoch: [192][300/313]\tTime 0.092 (0.093)\tData 0.027 (0.028)\tLoss 0.8069 (1.7381)\tCls Loss 0.4530 (0.9939)\tRank Loss 0.3539 (0.7442)\tPrec 92.19% (72.42%)\nEpoch: [193][0/313]\tTime 0.104 (0.093)\tData 0.033 (0.028)\tLoss 0.7945 (1.7379)\tCls Loss 0.5022 (0.9938)\tRank Loss 0.2923 (0.7441)\tPrec 92.97% (72.43%)\nEpoch: [193][100/313]\tTime 0.094 (0.093)\tData 0.029 (0.028)\tLoss 0.7130 (1.7362)\tCls Loss 0.4634 (0.9929)\tRank Loss 0.2496 (0.7433)\tPrec 90.62% (72.46%)\nEpoch: [193][200/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.7423 (1.7345)\tCls Loss 0.5152 (0.9920)\tRank Loss 0.2271 (0.7425)\tPrec 85.94% (72.50%)\nEpoch: [193][300/313]\tTime 0.093 (0.093)\tData 0.028 (0.028)\tLoss 0.7692 (1.7329)\tCls Loss 0.4643 (0.9911)\tRank Loss 0.3049 (0.7418)\tPrec 89.06% (72.53%)\nEpoch: [194][0/313]\tTime 0.109 (0.093)\tData 0.035 (0.028)\tLoss 0.6580 (1.7326)\tCls Loss 0.4577 (0.9910)\tRank Loss 0.2004 (0.7417)\tPrec 89.06% (72.53%)\nEpoch: [194][100/313]\tTime 0.097 (0.093)\tData 0.029 (0.028)\tLoss 0.8401 (1.7310)\tCls Loss 0.5023 (0.9901)\tRank Loss 0.3379 (0.7409)\tPrec 89.84% (72.57%)\nEpoch: [194][200/313]\tTime 0.093 (0.093)\tData 0.028 (0.028)\tLoss 0.6272 (1.7293)\tCls Loss 0.3578 (0.9892)\tRank Loss 0.2694 (0.7402)\tPrec 96.09% (72.60%)\nEpoch: [194][300/313]\tTime 0.098 (0.093)\tData 0.029 (0.028)\tLoss 0.7196 (1.7277)\tCls Loss 0.4458 (0.9883)\tRank Loss 0.2738 (0.7394)\tPrec 92.97% (72.63%)\nEpoch: [195][0/313]\tTime 0.104 (0.093)\tData 0.032 (0.028)\tLoss 0.6365 (1.7275)\tCls Loss 0.3994 (0.9882)\tRank Loss 0.2371 (0.7393)\tPrec 91.41% (72.64%)\nEpoch: [195][100/313]\tTime 0.092 (0.093)\tData 0.028 (0.028)\tLoss 0.5100 (1.7258)\tCls Loss 0.2859 (0.9873)\tRank Loss 0.2241 (0.7385)\tPrec 97.66% (72.67%)\nEpoch: [195][200/313]\tTime 0.094 (0.093)\tData 0.027 (0.028)\tLoss 0.6442 (1.7242)\tCls Loss 0.3837 (0.9864)\tRank Loss 0.2605 (0.7378)\tPrec 94.53% (72.70%)\nEpoch: [195][300/313]\tTime 0.093 (0.093)\tData 0.027 (0.028)\tLoss 0.7239 (1.7225)\tCls Loss 0.3891 (0.9855)\tRank Loss 0.3348 (0.7370)\tPrec 95.31% (72.74%)\nEpoch: [196][0/313]\tTime 0.103 (0.093)\tData 0.033 (0.028)\tLoss 0.7399 (1.7223)\tCls Loss 0.4685 (0.9854)\tRank Loss 0.2714 (0.7369)\tPrec 95.31% (72.74%)\nEpoch: [196][100/313]\tTime 0.094 (0.093)\tData 0.028 (0.028)\tLoss 0.6177 (1.7207)\tCls Loss 0.3801 (0.9845)\tRank Loss 0.2376 (0.7362)\tPrec 98.44% (72.77%)\nEpoch: [196][200/313]\tTime 0.095 (0.093)\tData 0.029 (0.028)\tLoss 0.6549 (1.7190)\tCls Loss 0.4163 (0.9836)\tRank Loss 0.2386 (0.7354)\tPrec 94.53% (72.81%)\nEpoch: [196][300/313]\tTime 0.096 (0.093)\tData 0.029 (0.028)\tLoss 0.7403 (1.7174)\tCls Loss 0.4404 (0.9827)\tRank Loss 0.3000 (0.7347)\tPrec 91.41% (72.84%)\nEpoch: [197][0/313]\tTime 0.099 (0.093)\tData 0.033 (0.028)\tLoss 0.6097 (1.7172)\tCls Loss 0.3654 (0.9826)\tRank Loss 0.2444 (0.7346)\tPrec 92.97% (72.84%)\nEpoch: [197][100/313]\tTime 0.096 (0.093)\tData 0.028 (0.028)\tLoss 0.6784 (1.7156)\tCls Loss 0.4451 (0.9818)\tRank Loss 0.2333 (0.7338)\tPrec 93.75% (72.88%)\nEpoch: [197][200/313]\tTime 0.095 (0.093)\tData 0.030 (0.028)\tLoss 0.6916 (1.7140)\tCls Loss 0.4319 (0.9809)\tRank Loss 0.2597 (0.7331)\tPrec 92.97% (72.91%)\nEpoch: [197][300/313]\tTime 0.095 (0.093)\tData 0.029 (0.028)\tLoss 0.7559 (1.7123)\tCls Loss 0.4347 (0.9800)\tRank Loss 0.3211 (0.7323)\tPrec 92.19% (72.94%)\nEpoch: [198][0/313]\tTime 0.099 (0.093)\tData 0.033 (0.028)\tLoss 0.6918 (1.7121)\tCls Loss 0.4025 (0.9799)\tRank Loss 0.2893 (0.7322)\tPrec 92.19% (72.95%)\nEpoch: [198][100/313]\tTime 0.096 (0.093)\tData 0.030 (0.028)\tLoss 0.6684 (1.7105)\tCls Loss 0.3049 (0.9790)\tRank Loss 0.3634 (0.7315)\tPrec 96.88% (72.98%)\nEpoch: [198][200/313]\tTime 0.095 (0.093)\tData 0.029 (0.028)\tLoss 0.6291 (1.7089)\tCls Loss 0.3867 (0.9781)\tRank Loss 0.2424 (0.7307)\tPrec 92.97% (73.01%)\nEpoch: [198][300/313]\tTime 0.098 (0.093)\tData 0.032 (0.028)\tLoss 0.6542 (1.7073)\tCls Loss 0.4433 (0.9773)\tRank Loss 0.2109 (0.7300)\tPrec 95.31% (73.04%)\nEpoch: [199][0/313]\tTime 0.097 (0.093)\tData 0.032 (0.028)\tLoss 0.7540 (1.7071)\tCls Loss 0.4248 (0.9772)\tRank Loss 0.3292 (0.7299)\tPrec 93.75% (73.05%)\nEpoch: [199][100/313]\tTime 0.109 (0.093)\tData 0.036 (0.028)\tLoss 0.6607 (1.7054)\tCls Loss 0.3719 (0.9763)\tRank Loss 0.2888 (0.7292)\tPrec 92.97% (73.08%)\nEpoch: [199][200/313]\tTime 0.106 (0.093)\tData 0.036 (0.028)\tLoss 0.7673 (1.7039)\tCls Loss 0.5115 (0.9754)\tRank Loss 0.2558 (0.7284)\tPrec 89.84% (73.11%)\nEpoch: [199][300/313]\tTime 0.095 (0.093)\tData 0.028 (0.028)\tLoss 0.8072 (1.7022)\tCls Loss 0.5377 (0.9746)\tRank Loss 0.2695 (0.7277)\tPrec 89.84% (73.14%)\nModel saved as model.pth\n","output_type":"stream"}]},{"cell_type":"code","source":"torch.save(model.state_dict(), \"model_final.pth\")","metadata":{"execution":{"iopub.status.busy":"2024-10-20T10:40:17.432095Z","iopub.execute_input":"2024-10-20T10:40:17.432564Z","iopub.status.idle":"2024-10-20T10:40:17.577119Z","shell.execute_reply.started":"2024-10-20T10:40:17.432524Z","shell.execute_reply":"2024-10-20T10:40:17.576004Z"},"trusted":true},"execution_count":22,"outputs":[]},{"cell_type":"code","source":"# add your credentials here \nimport os\nos.environ['KAGGLE_USERNAME'] = ''\nos.environ['KAGGLE_KEY'] = ''","metadata":{"execution":{"iopub.status.busy":"2024-10-20T07:10:55.649275Z","iopub.status.idle":"2024-10-20T07:10:55.649806Z","shell.execute_reply.started":"2024-10-20T07:10:55.649531Z","shell.execute_reply":"2024-10-20T07:10:55.649557Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 0.94\nimport pandas as pd\ntest_transform = transforms.Compose([\n# transforms.ToTensor(),\n transforms.Normalize((0.5071, 0.4867, 0.4408), (0.2675, 0.2565, 0.2761)),\n])\n\ndef predict_on_test(model, testloader, array):\n model.eval()\n predictions = []\n with torch.no_grad():\n for inputs,_,_ in testloader:\n inputs = inputs.to('cuda')\n outputs = model(inputs)\n logits = outputs\n probs = torch.softmax(logits, dim=1)\n\n preds = torch.argmax(probs, dim=1)\n for i in range(probs.size(0)):\n max_prob, max_class = torch.max(probs[i], dim=0)\n# print(f\"Max Probability for input {i}: {max_prob.item()}\")\n if max_prob < array[max_class]: # Use threshold to make confident predictions\n preds[i] = -1 # Classify as \"unpredicted\" (-1)\n predictions.extend(preds.cpu().numpy())\n\n return predictions\n\n# Get predictions on the test set using the loaded model\ntest_file = \"/kaggle/input/col-774-a-3/test.pkl\"\n# alpha = 0.99\n# gamma = 5\nmodel_file = \"/kaggle/working/model.pth/model_final.pth\"\nmodel.load_state_dict(torch.load(model_file,weights_only=True))\ntest_data = load_data(test_file,test_transform)\ntest_loader = DataLoader(test_data, batch_size=20000, shuffle=False)\n# train_model(model, train_loader, criterion, optimizer, num_epochs=20)\n# ths =[0.75,0.85,0.89,0.9,0.91,0.92,0.94,0.93,.95,0.96,0.97,0.98,0.99]\n# ths = [0.71,0,72,0.73,0.74,0.76,0.77,0.78,0.79]\n# test_predictions = predict_on_test(scaled_model, test_loader,th)\n# submission_df = pd.DataFrame({'ID': range(len(test_predictions)), 'Predicted_label': test_predictions})\n# submission_df.to_csv(f'submission5tunesthresholdsfinal.csv', index=False)\n# ths = [0.71,0.72,0.73,0.74,0.75,0.76,0.77,0.78,0.79,0.8,0.81,0.82,0.83,0.84,0.85,0.9]\n# ths = [0.721,0.722,0.723,0.724,0.725,0.726,0.727,0.728,0.729,0.73,0.731,0.732,0.733,0.734,0.735,0.736,0.737,0.738,0.739]\nths = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]\narray = np.full(100, 0.795)\narray[0] =0.1\narray[1] =0.1\narray[2] = 0.7\narray[3] =0.6\narray[4] = 0.5\narray[5] = 0.6\narray[6] = 0.3\narray[7] = 0.4\narray[8] = 0.1\narray[9] = 0.3\narray[10] = 0.5\nj = 11\nfor th in ths:\n array[j] = th\n test_predictions = predict_on_test(model, test_loader,array)\n submission_df = pd.DataFrame({'ID': range(len(test_predictions)), 'Predicted_label': test_predictions})\n submission_df.to_csv(f'submission{th}-{j}.csv', index=False)\nfor th in ths:\n !kaggle competitions submit -c col-774-a-3 -f submissionfinalscalednodiv{th}-{j}.csv -m \"Message\"\nprint('Submission file created: submission.csv')\n# print(\"Test predictions:\", test_predictions)","metadata":{"execution":{"iopub.status.busy":"2024-10-20T11:03:36.6455Z","iopub.execute_input":"2024-10-20T11:03:36.645965Z","iopub.status.idle":"2024-10-20T11:04:44.269297Z","shell.execute_reply.started":"2024-10-20T11:03:36.645922Z","shell.execute_reply":"2024-10-20T11:04:44.268182Z"},"trusted":true},"execution_count":24,"outputs":[{"name":"stdout","text":"Size of the train set: 20000 samples\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nTraceback (most recent call last):\n File \"/opt/conda/bin/kaggle\", line 5, in \n from kaggle.cli import main\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/__init__.py\", line 7, in \n api.authenticate()\n File \"/opt/conda/lib/python3.10/site-packages/kaggle/api/kaggle_api_extended.py\", line 407, in authenticate\n raise IOError('Could not find {}. Make sure it\\'s located in'\nOSError: Could not find kaggle.json. Make sure it's located in /root/.config/kaggle. Or use the environment method. See setup instructions at https://github.com/Kaggle/kaggle-api/\nSubmission file created: submission.csv\n","output_type":"stream"}]},{"cell_type":"code","source":"pip freeze","metadata":{"execution":{"iopub.status.busy":"2024-10-20T08:46:57.282413Z","iopub.execute_input":"2024-10-20T08:46:57.282813Z","iopub.status.idle":"2024-10-20T08:47:00.69313Z","shell.execute_reply.started":"2024-10-20T08:46:57.282761Z","shell.execute_reply":"2024-10-20T08:47:00.692074Z"},"trusted":true},"execution_count":19,"outputs":[{"name":"stdout","text":"absl-py==1.4.0\naccelerate==0.34.2\naiobotocore==2.15.1\naiofiles==22.1.0\naiohttp @ file:///home/conda/feedstock_root/build_artifacts/aiohttp_1713964853148/work\naioitertools==0.12.0\naiosignal @ file:///home/conda/feedstock_root/build_artifacts/aiosignal_1667935791922/work\naiosqlite==0.20.0\nalbucore==0.0.17\nalbumentations==1.4.17\nalembic==1.13.3\naltair==5.4.1\nannotated-types @ file:///home/conda/feedstock_root/build_artifacts/annotated-types_1716290248287/work\nannoy==1.17.3\nansicolors==1.1.8\nanyio @ file:///home/conda/feedstock_root/build_artifacts/anyio_1717693030552/work\napache-beam==2.46.0\nappdirs==1.4.4\narchspec @ file:///home/conda/feedstock_root/build_artifacts/archspec_1708969572489/work\nargon2-cffi @ file:///home/conda/feedstock_root/build_artifacts/argon2-cffi_1692818318753/work\nargon2-cffi-bindings @ file:///home/conda/feedstock_root/build_artifacts/argon2-cffi-bindings_1695386546427/work\narray_record==0.5.1\narrow @ file:///home/conda/feedstock_root/build_artifacts/arrow_1696128962909/work\narviz==0.20.0\nastroid==3.3.4\nasttokens @ file:///home/conda/feedstock_root/build_artifacts/asttokens_1698341106958/work\nastunparse==1.6.3\nasync-lru==2.0.4\nasync-timeout @ file:///home/conda/feedstock_root/build_artifacts/async-timeout_1691763562544/work\natpublic==4.1.0\nattrs @ file:///home/conda/feedstock_root/build_artifacts/attrs_1704011227531/work\naudioread==3.0.1\nautopep8==2.0.4\nBabel==2.15.0\nbackports.tarfile==1.2.0\nbayesian-optimization==1.5.1\nbeatrix_jupyterlab @ file:///home/kbuilder/miniconda3/conda-bld/dlenv-tf-2-16-gpu_1718248111274/work/packages/beatrix_jupyterlab-2024.66.154055.tar.gz#sha256=257afe97f249769790e978994d6554655e0c2be69c5faa3924a06c73bddbcab3\nbeautifulsoup4 @ file:///home/conda/feedstock_root/build_artifacts/beautifulsoup4_1705564648255/work\nbidict==0.23.1\nbigframes==0.22.0\nbleach @ file:///home/conda/feedstock_root/build_artifacts/bleach_1696630167146/work\nblessed==1.20.0\nblinker==1.8.2\nblis @ file:///home/conda/feedstock_root/build_artifacts/cython-blis_1696148805003/work\nblosc2==2.7.1\nbokeh @ file:///home/conda/feedstock_root/build_artifacts/bokeh_1724417487351/work\nboltons @ file:///home/conda/feedstock_root/build_artifacts/boltons_1711936407380/work\nBoruta==0.4.3\nboto3==1.26.100\nbotocore==1.35.23\n-e git+https://github.com/SohierDane/BigQuery_Helper@8615a7f6c1663e7f2d48aa2b32c2dbcb600a440f#egg=bq_helper\nbqplot==0.12.43\nbranca==0.8.0\nBrotli @ file:///home/conda/feedstock_root/build_artifacts/brotli-split_1695989787169/work\nbrotlipy==0.7.0\ncached-property @ file:///home/conda/feedstock_root/build_artifacts/cached_property_1615209429212/work\ncachetools==4.2.4\nCartopy @ file:///home/conda/feedstock_root/build_artifacts/cartopy_1726175359833/work\ncatalogue @ file:///home/conda/feedstock_root/build_artifacts/catalogue_1695626339626/work\ncatboost==1.2.7\ncategory-encoders==2.6.4\ncertifi @ file:///home/conda/feedstock_root/build_artifacts/certifi_1725278078093/work/certifi\ncesium==0.12.3\ncffi @ file:///home/conda/feedstock_root/build_artifacts/cffi_1696001684923/work\ncharset-normalizer @ file:///home/conda/feedstock_root/build_artifacts/charset-normalizer_1698833585322/work\nchex==0.1.86\nclick @ file:///home/conda/feedstock_root/build_artifacts/click_1692311806742/work\nclick-plugins==1.1.1\ncligj==0.7.2\ncloud-tpu-client==0.10\ncloud-tpu-profiler==2.4.0\ncloudpathlib @ file:///home/conda/feedstock_root/build_artifacts/cloudpathlib-meta_1725397841369/work\ncloudpickle @ file:///home/conda/feedstock_root/build_artifacts/cloudpickle_1697464713350/work\ncmdstanpy==1.2.4\ncolorama @ file:///home/conda/feedstock_root/build_artifacts/colorama_1666700638685/work\ncolorcet==3.1.0\ncolorful==0.5.6\ncolorlog==6.8.2\ncolorlover==0.3.0\ncomm @ file:///home/conda/feedstock_root/build_artifacts/comm_1710320294760/work\nconda @ file:///home/conda/feedstock_root/build_artifacts/conda_1727791761394/work\nconda-content-trust @ file:///tmp/build/80754af9/conda-content-trust_1617045594566/work\nconda-libmamba-solver @ file:///croot/conda-libmamba-solver_1702997573971/work/src\nconda-package-handling @ file:///home/conda/feedstock_root/build_artifacts/conda-package-handling_1717678605937/work\nconda_package_streaming @ file:///home/conda/feedstock_root/build_artifacts/conda-package-streaming_1717678526951/work\nconfection @ file:///home/conda/feedstock_root/build_artifacts/confection_1701179074719/work\ncontourpy==1.2.1\ncrcmod==1.7\ncryptography @ file:///home/conda/feedstock_root/build_artifacts/cryptography-split_1717559422169/work\ncuda-python @ file:///home/conda/feedstock_root/build_artifacts/cuda-python_1722658627184/work\ncudf @ file:///opt/conda/conda-bld/work/python/cudf\ncufflinks==0.17.3\ncuml @ file:///opt/conda/conda-bld/work/python/cuml\ncupy @ file:///home/conda/feedstock_root/build_artifacts/cupy-split_1724325730204/work\nCVXcanon==0.1.2\ncycler @ file:///home/conda/feedstock_root/build_artifacts/cycler_1696677705766/work\ncymem @ file:///home/conda/feedstock_root/build_artifacts/cymem_1695443485440/work\nCython==3.0.10\ncytoolz @ file:///home/conda/feedstock_root/build_artifacts/cytoolz_1706897049115/work\ndaal==2024.7.0\ndaal4py==2024.7.0\ndacite==1.8.1\ndask==2024.9.1\ndask-cuda @ file:///opt/conda/conda-bld/work\ndask-cudf @ file:///opt/conda/conda-bld/work/python/dask_cudf\ndask-expr==1.1.15\ndataclasses-json==0.6.7\ndataproc_jupyter_plugin==0.1.79\ndatasets==3.0.1\ndatashader==0.16.3\ndatatile==1.0.3\ndb-dtypes==1.2.0\ndeap==1.4.1\ndebugpy @ file:///home/conda/feedstock_root/build_artifacts/debugpy_1707444420542/work\ndecorator @ file:///home/conda/feedstock_root/build_artifacts/decorator_1641555617451/work\ndeepdiff==8.0.1\ndefusedxml @ file:///home/conda/feedstock_root/build_artifacts/defusedxml_1615232257335/work\nDeprecated==1.2.14\ndill==0.3.8\ndipy==1.9.0\ndistlib==0.3.8\ndistributed @ file:///home/conda/feedstock_root/build_artifacts/distributed_1721444339227/work\ndistributed-ucxx @ file:///opt/conda/conda-bld/work/python/distributed-ucxx\ndistro @ file:///home/conda/feedstock_root/build_artifacts/distro_1704321475663/work\ndm-tree==0.1.8\ndnspython==2.6.1\ndocker==7.1.0\ndocker-pycreds==0.4.0\ndocopt==0.6.2\ndocstring-to-markdown==0.15\ndocstring_parser==0.16\nearthengine-api==1.1.2\neasyocr==1.7.2\necos==2.0.14\neli5==0.13.0\nemail_validator==2.1.1\nemoji==2.13.2\nen-core-web-lg @ https://github.com/explosion/spacy-models/releases/download/en_core_web_lg-3.7.1/en_core_web_lg-3.7.1-py3-none-any.whl#sha256=ab70aeb6172cde82508f7739f35ebc9918a3d07debeed637403c8f794ba3d3dc\nen-core-web-sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.7.1/en_core_web_sm-3.7.1-py3-none-any.whl#sha256=86cc141f63942d4b2c5fcee06630fd6f904788d2f0ab005cce45aadb8fb73889\nentrypoints @ file:///home/conda/feedstock_root/build_artifacts/entrypoints_1643888246732/work\net-xmlfile==1.1.0\netils==1.7.0\neval_type_backport==0.2.0\nexceptiongroup @ file:///home/conda/feedstock_root/build_artifacts/exceptiongroup_1704921103267/work\nexecnb==0.1.6\nexecuting @ file:///home/conda/feedstock_root/build_artifacts/executing_1698579936712/work\nexplainable-ai-sdk==1.3.3\nFarama-Notifications==0.0.4\nfastai==2.7.17\nfastapi==0.111.0\nfastapi-cli==0.0.4\nfastavro==1.9.4\nfastcore==1.7.10\nfastdownload==0.0.7\nfasteners==0.19\nfastjsonschema @ file:///home/conda/feedstock_root/build_artifacts/python-fastjsonschema_1703780968325/work/dist\nfastprogress==1.0.3\nfastrlock @ file:///home/conda/feedstock_root/build_artifacts/fastrlock_1702696298817/work\nfasttext==0.9.3\nfeaturetools==1.31.0\nfilelock==3.15.1\nfiona==1.9.6\nflake8==7.1.1\nFlask==3.0.3\nflatbuffers==24.3.25\nflax==0.8.4\nfolium==0.17.0\nfonttools==4.53.0\nfqdn @ file:///home/conda/feedstock_root/build_artifacts/fqdn_1638810296540/work/dist\nfrozendict @ file:///home/conda/feedstock_root/build_artifacts/frozendict_1715092766944/work\nfrozenlist @ file:///home/conda/feedstock_root/build_artifacts/frozenlist_1702645481127/work\nfsspec==2024.6.1\nfuncy==2.0\nfury==0.11.0\nfuture==1.0.0\nfuzzywuzzy==0.18.0\ngast==0.5.4\ngatspy==0.3\ngcsfs==2024.6.1\ngensim==4.3.3\ngeographiclib==2.0\ngeojson==3.1.0\ngeopandas==0.14.4\ngeopy==2.4.1\nghapi==1.0.6\ngitdb==4.0.11\nGitPython==3.1.43\ngoogle-ai-generativelanguage==0.6.10\ngoogle-api-core==2.11.1\ngoogle-api-python-client==2.147.0\ngoogle-apitools==0.5.31\ngoogle-auth==2.30.0\ngoogle-auth-httplib2==0.2.0\ngoogle-auth-oauthlib==1.2.0\ngoogle-cloud-aiplatform==0.6.0a1\ngoogle-cloud-artifact-registry==1.11.3\ngoogle-cloud-automl==1.0.1\ngoogle-cloud-bigquery==2.34.4\ngoogle-cloud-bigquery-connection==1.15.3\ngoogle-cloud-bigtable==1.7.3\ngoogle-cloud-core==2.4.1\ngoogle-cloud-datastore==2.20.1\ngoogle-cloud-dlp==3.18.0\ngoogle-cloud-functions==1.16.3\ngoogle-cloud-iam==2.15.0\ngoogle-cloud-jupyter-config==0.0.10\ngoogle-cloud-language==2.14.0\ngoogle-cloud-monitoring==2.21.0\ngoogle-cloud-pubsub==2.21.3\ngoogle-cloud-pubsublite==1.10.0\ngoogle-cloud-recommendations-ai==0.7.1\ngoogle-cloud-resource-manager==1.12.3\ngoogle-cloud-spanner==3.47.0\ngoogle-cloud-storage==1.44.0\ngoogle-cloud-translate==3.12.1\ngoogle-cloud-videointelligence==2.13.5\ngoogle-cloud-vision==2.8.0\ngoogle-crc32c==1.5.0\ngoogle-generativeai==0.8.2\ngoogle-pasta==0.2.0\ngoogle-resumable-media==2.7.1\ngoogleapis-common-protos==1.63.1\ngpustat==1.0.0\ngpxpy==1.6.2\ngraphviz==0.20.3\ngreenlet==3.0.3\ngrpc-google-iam-v1==0.12.7\ngrpc-interceptor==0.15.4\ngrpcio @ file:///home/conda/feedstock_root/build_artifacts/grpc-split_1713388282847/work\ngrpcio-status @ file:///home/conda/feedstock_root/build_artifacts/grpcio-status_1659707318966/work\ngviz-api==1.10.0\ngym==0.26.2\ngym-notices==0.0.8\ngymnasium==0.29.0\nh11==0.14.0\nh2o==3.46.0.5\nh5netcdf==1.3.0\nh5py==3.11.0\nhaversine==2.8.1\nhdfs==2.7.3\nhep-ml==0.7.2\nholidays==0.57\nholoviews==1.19.1\nhtml5lib==1.1\nhtmlmin==0.1.12\nhttpcore==1.0.5\nhttplib2==0.21.0\nhttptools==0.6.1\nhttpx==0.27.0\nhuggingface-hub==0.25.1\nhumanize==4.9.0\nhyperopt==0.2.7\nibis-framework==7.1.0\nidna @ file:///home/conda/feedstock_root/build_artifacts/idna_1713279365350/work\nigraph==0.11.6\nImageHash==4.3.1\nimageio==2.34.1\nimbalanced-learn==0.12.3\nimgaug==0.4.0\nimmutabledict==4.2.0\nimportlib-metadata @ file:///home/conda/feedstock_root/build_artifacts/importlib-metadata_1701632192416/work\nimportlib_resources @ file:///home/conda/feedstock_root/build_artifacts/importlib_resources_1711040877059/work\niniconfig==2.0.0\nipykernel @ file:///home/conda/feedstock_root/build_artifacts/ipykernel_1717717528849/work\nipympl==0.7.0\nipython==8.21.0\nipython-genutils @ file:///home/conda/feedstock_root/build_artifacts/ipython_genutils_1716278396992/work\nipython-sql==0.5.0\nipywidgets==7.7.1\nisoduration @ file:///home/conda/feedstock_root/build_artifacts/isoduration_1638811571363/work/dist\nisort==5.13.2\nisoweek==1.3.3\nitsdangerous==2.2.0\nJanome==0.5.0\njaraco.classes==3.4.0\njaraco.context==5.3.0\njaraco.functools==4.0.1\njax==0.4.26\njax-jumpy==1.0.0\njaxlib @ file:///tmp/jax/jaxlib-0.4.26.dev20240620-cp310-cp310-manylinux2014_x86_64.whl#sha256=e8f732de2e5bbe5c9e137253af6ad079ec8f66073062ef10e7d6264f46d042cd\njedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1696326070614/work\njeepney==0.8.0\njieba==0.42.1\nJinja2 @ file:///home/conda/feedstock_root/build_artifacts/jinja2_1715127149914/work\njmespath==1.0.1\njoblib @ file:///home/conda/feedstock_root/build_artifacts/joblib_1714665484399/work\njson5==0.9.25\njsonpatch @ file:///home/conda/feedstock_root/build_artifacts/jsonpatch_1695536281965/work\njsonpointer @ file:///home/conda/feedstock_root/build_artifacts/jsonpointer_1695397238043/work\njsonschema @ file:///home/conda/feedstock_root/build_artifacts/jsonschema-meta_1714573116818/work\njsonschema-specifications @ file:///tmp/tmpkv1z7p57/src\njupyter-console==6.6.3\njupyter-events @ file:///home/conda/feedstock_root/build_artifacts/jupyter_events_1710805637316/work\njupyter-http-over-ws==0.0.8\njupyter-lsp==1.5.1\njupyter-server-mathjax==0.2.6\njupyter-ydoc==0.2.5\njupyter_client @ file:///home/conda/feedstock_root/build_artifacts/jupyter_client_1673615989977/work\njupyter_core @ file:///home/conda/feedstock_root/build_artifacts/jupyter_core_1710257277185/work\njupyter_server==2.12.5\njupyter_server_fileid==0.9.2\njupyter_server_proxy==4.2.0\njupyter_server_terminals @ file:///home/conda/feedstock_root/build_artifacts/jupyter_server_terminals_1710262634903/work\njupyter_server_ydoc==0.8.0\njupyterlab==4.2.5\njupyterlab-lsp==5.1.0\njupyterlab_git==0.44.0\njupyterlab_pygments @ file:///home/conda/feedstock_root/build_artifacts/jupyterlab_pygments_1707149102966/work\njupyterlab_server==2.27.2\njupyterlab_widgets==3.0.11\njupytext==1.16.2\nkaggle==1.6.17\nkaggle-environments==1.14.15\nkagglehub==0.3.1\nkeras==3.3.3\nkeras-core==0.1.7\nkeras-cv==0.9.0\nkeras-nlp==0.15.1\nkeras-tuner==1.4.7\nkernels-mixer==0.0.13\nkeyring==25.2.1\nkeyrings.google-artifactregistry-auth==1.1.2\nkfp==2.5.0\nkfp-pipeline-spec==0.2.2\nkfp-server-api==2.0.5\nkiwisolver==1.4.5\nkornia==0.7.3\nkornia_rs==0.1.5\nkt-legacy==1.0.5\nkubernetes==26.1.0\nlangcodes @ file:///home/conda/feedstock_root/build_artifacts/langcodes_1727275653768/work\nlangid==1.1.6\nlanguage_data @ file:///home/conda/feedstock_root/build_artifacts/language-data_1714193818885/work\nlazy_loader==0.4\nlearntools @ git+https://github.com/Kaggle/learntools@ca2a51ee0085e4943cadaf5e9fe7dce2ec947d3c\nleven==1.0.4\nlibclang==18.1.1\nlibmambapy @ file:///home/conda/feedstock_root/build_artifacts/mamba-split_1727077953944/work/libmambapy\nlibpysal==4.9.2\nlibrosa==0.10.2.post1\nlightgbm @ file:///tmp/lightgbm/lightgbm-4.2.0-py3-none-linux_x86_64.whl#sha256=56426202283a455f92734f93db5a771ac70c325384bbc871a1495f8322f3a445\nlightning-utilities==0.11.7\nlime==0.2.0.1\nline_profiler==4.1.3\nlinkify-it-py==2.0.3\nllvmlite==0.43.0\nlml==0.1.0\nlocket @ file:///home/conda/feedstock_root/build_artifacts/locket_1650660393415/work\nlxml==5.3.0\nlz4 @ file:///home/conda/feedstock_root/build_artifacts/lz4_1725089426044/work\nMako==1.3.5\nmamba @ file:///home/conda/feedstock_root/build_artifacts/mamba-split_1727077953944/work/mamba\nmarisa-trie @ file:///home/conda/feedstock_root/build_artifacts/marisa-trie_1706566476731/work\nMarkdown==3.6\nmarkdown-it-py @ file:///home/conda/feedstock_root/build_artifacts/markdown-it-py_1686175045316/work\nMarkupSafe @ file:///home/conda/feedstock_root/build_artifacts/markupsafe_1706899921127/work\nmarshmallow==3.22.0\nmatplotlib==3.7.5\nmatplotlib-inline @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-inline_1713250518406/work\nmatplotlib-venn==1.1.1\nmccabe==0.7.0\nmdit-py-plugins==0.4.1\nmdurl @ file:///home/conda/feedstock_root/build_artifacts/mdurl_1704317613764/work\nmemory-profiler==0.61.0\nmemray==1.12.0\nmenuinst @ file:///home/conda/feedstock_root/build_artifacts/menuinst_1718088294643/work\nmissingno==0.5.2\nmistune==0.8.4\nmizani==0.11.4\nml-dtypes==0.3.2\nmlcrate==0.2.0\nmlxtend==0.23.1\nmne==1.8.0\nmore-itertools==10.3.0\nmpld3==0.5.10\nmpmath==1.3.0\nmsgpack==1.0.8\nmultidict @ file:///home/conda/feedstock_root/build_artifacts/multidict_1707040698785/work\nmultimethod==1.11.2\nmultipledispatch==1.0.0\nmultiprocess==0.70.16\nmunkres==1.1.4\nmurmurhash @ file:///home/conda/feedstock_root/build_artifacts/murmurhash_1695449783955/work\nmypy-extensions==1.0.0\nnamex==0.0.8\nnarwhals==1.9.0\nnb_conda @ file:///home/conda/feedstock_root/build_artifacts/nb_conda_1704789357480/work\nnb_conda_kernels @ file:///home/conda/feedstock_root/build_artifacts/nb_conda_kernels_1714150048983/work\nnbclassic @ file:///home/conda/feedstock_root/build_artifacts/nbclassic_1716838762700/work\nnbclient==0.5.13\nnbconvert==6.4.5\nnbdev==2.3.31\nnbdime==3.2.0\nnbformat @ file:///home/conda/feedstock_root/build_artifacts/nbformat_1712238998817/work\nndindex==1.9.2\nnest-asyncio @ file:///home/conda/feedstock_root/build_artifacts/nest-asyncio_1705850609492/work\nnetworkx==3.3\nnibabel==5.2.1\nnilearn==0.10.4\nninja==1.11.1.1\nnltk==3.2.4\nnose==1.3.7\nnotebook @ file:///home/conda/feedstock_root/build_artifacts/notebook_1715848908871/work\nnotebook_executor @ file:///home/kbuilder/miniconda3/conda-bld/dlenv-tf-2-16-gpu_1718248111274/work/packages/notebook_executor\nnotebook_shim @ file:///home/conda/feedstock_root/build_artifacts/notebook-shim_1707957777232/work\nnumba @ file:///home/conda/feedstock_root/build_artifacts/numba_1718888013454/work\nnumexpr==2.10.1\nnumpy==1.26.4\nnvidia-ml-py==11.495.46\nnvtx @ file:///home/conda/feedstock_root/build_artifacts/nvtx_1727795570945/work\noauth2client==4.1.3\noauthlib==3.2.2\nobjsize==0.6.1\nodfpy==1.4.1\nolefile==0.47\nonnx==1.17.0\nopencensus==0.11.4\nopencensus-context==0.1.3\nopencv-contrib-python==4.10.0.84\nopencv-python==4.10.0.84\nopencv-python-headless==4.10.0.84\nopenpyxl==3.1.5\nopenslide-python==1.3.1\nopentelemetry-api==1.25.0\nopentelemetry-exporter-otlp==1.25.0\nopentelemetry-exporter-otlp-proto-common==1.25.0\nopentelemetry-exporter-otlp-proto-grpc==1.25.0\nopentelemetry-exporter-otlp-proto-http==1.25.0\nopentelemetry-proto==1.25.0\nopentelemetry-sdk==1.25.0\nopentelemetry-semantic-conventions==0.46b0\nopt-einsum==3.3.0\noptax==0.2.2\noptree==0.11.0\noptuna==4.0.0\norbax-checkpoint==0.6.4\norderly-set==5.2.2\norjson==3.10.4\noverrides @ file:///home/conda/feedstock_root/build_artifacts/overrides_1706394519472/work\npackaging==21.3\npandas @ file:///home/conda/feedstock_root/build_artifacts/pandas_1715897614105/work\npandas-datareader==0.10.0\npandas-profiling==3.6.6\npandas-summary==0.2.0\npandasql==0.7.3\npandocfilters @ file:///home/conda/feedstock_root/build_artifacts/pandocfilters_1631603243851/work\npanel==1.5.1\npapermill==2.6.0\nparam==2.1.1\nparso @ file:///home/conda/feedstock_root/build_artifacts/parso_1712320355065/work\nparsy==2.1\npartd @ file:///home/conda/feedstock_root/build_artifacts/partd_1715026491486/work\npath==17.0.0\npath.py==12.5.0\npathos==0.3.3\npatsy==0.5.6\npdf2image==1.17.0\npendulum==3.0.0\npettingzoo==1.24.0\npexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1706113125309/work\nphik==0.12.4\npickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1602536217715/work\npillow==10.3.0\npins==0.8.6\npkgutil_resolve_name @ file:///home/conda/feedstock_root/build_artifacts/pkgutil-resolve-name_1694617248815/work\nplatformdirs==3.11.0\nplotly==5.22.0\nplotly-express==0.4.1\nplotnine==0.13.6\npluggy @ file:///home/conda/feedstock_root/build_artifacts/pluggy_1713667077545/work\npolars==1.9.0\npooch==1.8.2\npox==0.3.5\nppft==1.7.6.9\npreprocessing==0.1.13\npreshed @ file:///home/conda/feedstock_root/build_artifacts/preshed_1695644760607/work\nprettytable==3.10.0\nprometheus_client @ file:///home/conda/feedstock_root/build_artifacts/prometheus_client_1707932675456/work\npromise==2.3\nprompt_toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1718047967974/work\nprophet==1.1.5\nproto-plus @ file:///home/conda/feedstock_root/build_artifacts/proto-plus_1702003338643/work\nprotobuf==3.20.3\npsutil==5.9.3\nptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1609419310487/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl\npudb==2024.1.2\npure-eval @ file:///home/conda/feedstock_root/build_artifacts/pure_eval_1642875951954/work\npy-cpuinfo==9.0.0\npy-spy==0.3.14\npy4j==0.10.9.7\npyaml==24.9.0\nPyArabic==0.6.15\npyarrow==16.1.0\npyarrow-hotfix @ file:///home/conda/feedstock_root/build_artifacts/pyarrow-hotfix_1700596371886/work\npyasn1 @ file:///home/conda/feedstock_root/build_artifacts/pyasn1_1713209357222/work\npyasn1_modules @ file:///home/conda/feedstock_root/build_artifacts/pyasn1-modules_1713209683338/work\npybind11==2.13.6\npyclipper==1.3.0.post5\npycodestyle==2.12.1\npycosat @ file:///home/conda/feedstock_root/build_artifacts/pycosat_1696355758174/work\npycparser @ file:///home/conda/feedstock_root/build_artifacts/pycparser_1711811537435/work\npycryptodome==3.20.0\npyct==0.5.0\npycuda==2024.1.2\npydantic @ file:///home/conda/feedstock_root/build_artifacts/pydantic_1726601062926/work\npydantic_core @ file:///home/conda/feedstock_root/build_artifacts/pydantic-core_1726524987213/work\npydata-google-auth==1.8.2\npydegensac==0.1.2\npydicom==3.0.1\npydocstyle==6.3.0\npydot==1.4.2\npydub==0.25.1\npyemd==1.0.0\npyexcel-io==0.6.6\npyexcel-ods==0.6.0\npyflakes==3.2.0\npygltflib==1.16.2\nPygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1714846767233/work\nPyJWT==2.8.0\npyLDAvis==3.4.1\npylibraft @ file:///opt/conda/conda-bld/work/python/pylibraft\npylint==3.3.1\npymc3==3.11.4\npymongo==3.13.0\nPympler==1.1\npynvjitlink-cu12 @ file:///opt/conda/conda-bld/work\npynvml @ file:///home/conda/feedstock_root/build_artifacts/pynvml_1639061605391/work\npynvrtc==9.2\npyOpenSSL @ file:///home/conda/feedstock_root/build_artifacts/pyopenssl_1706660063483/work\npyparsing==3.1.2\npypdf==5.0.1\npyproj==3.6.1\npyshp @ file:///home/conda/feedstock_root/build_artifacts/pyshp_1659002966020/work\nPySocks @ file:///home/builder/ci_310/pysocks_1640793678128/work\npytesseract==0.3.13\npytest==8.3.3\npython-bidi==0.6.0\npython-dateutil==2.9.0.post0\npython-dotenv==1.0.1\npython-json-logger @ file:///home/conda/feedstock_root/build_artifacts/python-json-logger_1677079630776/work\npython-louvain==0.16\npython-lsp-jsonrpc==1.1.2\npython-lsp-server==1.12.0\npython-multipart==0.0.9\npython-slugify==8.0.4\npytoolconfig==1.3.1\npytools==2024.1.14\npytorch-ignite==0.5.1\npytorch-lightning==2.4.0\npytz==2024.1\npyu2f @ file:///home/conda/feedstock_root/build_artifacts/pyu2f_1604248910016/work\nPyUpSet==0.1.1.post7\npyviz_comms==3.0.3\nPyWavelets==1.6.0\nPyYAML==6.0.2\npyzmq @ file:///home/conda/feedstock_root/build_artifacts/pyzmq_1715024398995/work\nqgrid==1.3.1\nqtconsole==5.6.0\nQtPy==2.4.1\nraft-dask @ file:///opt/conda/conda-bld/work/python/raft-dask\nrapids-dask-dependency @ file:///opt/conda/conda-bld/work\nray==2.24.0\nray-cpp==2.24.0\nreferencing @ file:///home/conda/feedstock_root/build_artifacts/referencing_1714619483868/work\nregex==2024.5.15\nrequests @ file:///home/conda/feedstock_root/build_artifacts/requests_1717057054362/work\nrequests-oauthlib==2.0.0\nrequests-toolbelt==0.10.1\nretrying==1.3.3\nrfc3339-validator @ file:///home/conda/feedstock_root/build_artifacts/rfc3339-validator_1638811747357/work\nrfc3986-validator @ file:///home/conda/feedstock_root/build_artifacts/rfc3986-validator_1598024191506/work\nrgf-python==3.12.0\nrich==13.7.1\nrmm @ file:///opt/conda/conda-bld/work/python/rmm\nrope==1.13.0\nrpds-py @ file:///home/conda/feedstock_root/build_artifacts/rpds-py_1715090007604/work\nrsa @ file:///home/conda/feedstock_root/build_artifacts/rsa_1658328885051/work\nRtree==1.3.0\nruamel-yaml-conda @ file:///home/builder/ci_310/ruamel_yaml_1640794439226/work\nruamel.yaml @ file:///home/conda/feedstock_root/build_artifacts/ruamel.yaml_1707298115475/work\nruamel.yaml.clib @ file:///home/conda/feedstock_root/build_artifacts/ruamel.yaml.clib_1707314473442/work\ns3fs==2024.6.1\ns3transfer==0.6.2\nsafetensors==0.4.5\nscikit-image==0.23.2\nscikit-learn==1.2.2\nscikit-learn-intelex==2024.7.0\nscikit-multilearn==0.2.0\nscikit-optimize==0.10.2\nscikit-plot==0.3.7\nscikit-surprise==1.1.4\nscipy @ file:///home/conda/feedstock_root/build_artifacts/scipy-split_1724327064660/work/dist/scipy-1.14.1-cp310-cp310-linux_x86_64.whl#sha256=b518850b2e690f597f0ae43dbed111989302770df900f6e2bf1c65111f1c67e6\nseaborn==0.12.2\nSecretStorage==3.3.3\nsegment_anything @ git+https://github.com/facebookresearch/segment-anything.git@dca509fe793f601edb92606367a655c15ac00fdf\nsemver==3.0.2\nSend2Trash @ file:///home/conda/feedstock_root/build_artifacts/send2trash_1712584999685/work\nsentencepiece==0.2.0\nsentry-sdk==2.15.0\nsetproctitle==1.3.3\nsetuptools-scm==8.1.0\nshap==0.44.1\nShapely==1.8.5.post1\nshellingham @ file:///home/conda/feedstock_root/build_artifacts/shellingham_1698144360966/work\nShimmy==1.3.0\nsimpervisor==1.0.0\nsimple_parsing==0.1.5\nSimpleITK==2.4.0\nsix @ file:///tmp/build/80754af9/six_1644875935023/work\nsklearn-pandas==2.2.0\nslicer==0.0.7\nsmart_open @ file:///home/conda/feedstock_root/build_artifacts/smart_open_split_1711455333245/work/dist\nsmmap==5.0.1\nsniffio @ file:///home/conda/feedstock_root/build_artifacts/sniffio_1708952932303/work\nsnowballstemmer==2.2.0\nsortedcontainers @ file:///home/conda/feedstock_root/build_artifacts/sortedcontainers_1621217038088/work\nsoundfile==0.12.1\nsoupsieve @ file:///home/conda/feedstock_root/build_artifacts/soupsieve_1693929250441/work\nsoxr==0.5.0.post1\nspacy @ file:///home/conda/feedstock_root/build_artifacts/spacy_1727007392007/work\nspacy-legacy @ file:///home/conda/feedstock_root/build_artifacts/spacy-legacy_1674550301837/work\nspacy-loggers @ file:///home/conda/feedstock_root/build_artifacts/spacy-loggers_1694527114282/work\nsphinx-rtd-theme==0.2.4\nSQLAlchemy==2.0.30\nsqlglot==19.9.0\nsqlparse==0.5.0\nsquarify==0.4.4\nsrsly @ file:///home/conda/feedstock_root/build_artifacts/srsly_1695653949688/work\nstable-baselines3==2.1.0\nstack-data @ file:///home/conda/feedstock_root/build_artifacts/stack_data_1669632077133/work\nstanio==0.5.1\nstarlette==0.37.2\nstatsmodels==0.14.2\nstopit==1.1.2\nstumpy==1.13.0\nsympy==1.13.3\ntables==3.10.1\ntabulate==0.9.0\ntangled-up-in-unicode==0.2.0\ntbb==2021.13.1\ntblib @ file:///home/conda/feedstock_root/build_artifacts/tblib_1702066284995/work\ntenacity==8.3.0\ntensorboard==2.16.2\ntensorboard-data-server==0.7.2\ntensorboard_plugin_profile==2.15.1\ntensorboardX==2.6.2.2\ntensorflow==2.16.1\ntensorflow-cloud==0.1.16\ntensorflow-datasets==4.9.6\ntensorflow-estimator==2.15.0\ntensorflow-hub==0.16.1\ntensorflow-io==0.37.0\ntensorflow-io-gcs-filesystem==0.37.0\ntensorflow-metadata==0.14.0\ntensorflow-probability==0.24.0\ntensorflow-serving-api==2.16.1\ntensorflow-text==2.16.1\ntensorflow-transform==0.14.0\ntensorflow_decision_forests==1.9.1\ntensorstore==0.1.66\ntermcolor==2.4.0\nterminado @ file:///home/conda/feedstock_root/build_artifacts/terminado_1710262609923/work\ntestpath==0.6.0\ntext-unidecode==1.3\ntextblob==0.18.0.post0\ntexttable==1.7.0\ntextual==0.67.1\ntf_keras==2.16.0\nTheano==1.0.5\nTheano-PyMC==1.1.2\nthinc @ file:///home/conda/feedstock_root/build_artifacts/thinc_1720971410934/work\nthreadpoolctl==3.5.0\ntifffile==2024.5.22\ntime-machine==2.14.1\ntimm==1.0.9\ntinycss2 @ file:///home/conda/feedstock_root/build_artifacts/tinycss2_1713974937325/work\ntokenizers==0.20.0\ntoml==0.10.2\ntomli==2.0.1\ntomlkit==0.13.2\ntoolz @ file:///home/conda/feedstock_root/build_artifacts/toolz_1706112571092/work\ntorch @ file:///tmp/torch/torch-2.4.0-cp310-cp310-linux_x86_64.whl#sha256=157f8afc1a2f90a80105b6836c27508e336245da0b320a3e08e9e4be580e5e21\ntorchaudio @ file:///tmp/torch/torchaudio-2.4.0-cp310-cp310-linux_x86_64.whl#sha256=f453b9cd1b154b5ed675d60514d99bdeaeb7537b4fe13496ae5f80804dc1e81b\ntorchinfo==1.8.0\ntorchmetrics==1.4.2\ntorchvision @ file:///tmp/torch/torchvision-0.19.0-cp310-cp310-linux_x86_64.whl#sha256=788a38a16aec820b0ad17655accc07f4ca1dabf428c57fbde8602f6788e240e9\ntornado @ file:///home/conda/feedstock_root/build_artifacts/tornado_1717722796999/work\nTPOT==0.12.1\ntqdm @ file:///home/conda/feedstock_root/build_artifacts/tqdm_1714854870413/work\ntraceml==1.0.8\ntraitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1713535121073/work\ntraittypes==0.2.1\ntransformers==4.45.1\ntreelite @ file:///home/conda/feedstock_root/build_artifacts/treelite_1721254174723/work/python\ntruststore @ file:///home/conda/feedstock_root/build_artifacts/truststore_1694154605758/work\ntrx-python==0.3\ntsfresh==0.20.3\ntypeguard==4.3.0\ntyper==0.12.3\ntyper-slim==0.12.5\ntypes-python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/types-python-dateutil_1710589910274/work\ntyping-inspect==0.9.0\ntyping-utils @ file:///home/conda/feedstock_root/build_artifacts/typing_utils_1622899189314/work\ntyping_extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1717802530399/work\ntzdata==2024.1\nuc-micro-py==1.0.3\nucx-py @ file:///opt/conda/conda-bld/work\nucxx @ file:///opt/conda/conda-bld/work/python\nujson==5.10.0\nunicodedata2 @ file:///home/conda/feedstock_root/build_artifacts/unicodedata2_1695847980273/work\nupdate-checker==0.18.0\nuri-template @ file:///home/conda/feedstock_root/build_artifacts/uri-template_1688655812972/work/dist\nuritemplate==3.0.1\nurllib3==1.26.18\nurwid==2.6.15\nurwid_readline==0.15.1\nuvicorn==0.30.1\nuvloop==0.19.0\nvec_noise==1.1.4\nvirtualenv==20.21.0\nvisions==0.7.5\nvtk==9.3.1\nWand==0.6.13\nwandb==0.18.3\nwasabi @ file:///home/conda/feedstock_root/build_artifacts/wasabi_1715409644734/work\nwatchdog==5.0.3\nwatchfiles==0.22.0\nwavio==0.0.9\nwcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1704731205417/work\nweasel @ file:///home/conda/feedstock_root/build_artifacts/weasel_1719987001521/work\nwebcolors @ file:///home/conda/feedstock_root/build_artifacts/webcolors_1717667289718/work\nwebencodings @ file:///home/conda/feedstock_root/build_artifacts/webencodings_1694681268211/work\nwebsocket-client @ file:///home/conda/feedstock_root/build_artifacts/websocket-client_1713923384721/work\nwebsockets==12.0\nWerkzeug==3.0.4\nwhatthepatch==1.0.6\nwidgetsnbextension==3.6.9\nwitwidget==1.8.1\nwoodwork==0.31.0\nwordcloud==1.9.3\nwrapt @ file:///home/conda/feedstock_root/build_artifacts/wrapt_1724957893583/work\nwurlitzer==3.1.1\nxarray==2024.9.0\nxarray-einstats==0.8.0\nxgboost==2.0.3\nxvfbwrapper==0.2.9\nxxhash==3.4.1\nxyzservices @ file:///home/conda/feedstock_root/build_artifacts/xyzservices_1725366347586/work\ny-py==0.6.2\nyapf==0.40.2\nyarl @ file:///home/conda/feedstock_root/build_artifacts/yarl_1705508292061/work\nydata-profiling==4.10.0\nydf==0.8.0\nyellowbrick==1.5\nypy-websocket==0.8.4\nzict @ file:///home/conda/feedstock_root/build_artifacts/zict_1681770155528/work\nzipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1718013267051/work\nzstandard==0.23.0\nNote: you may need to restart the kernel to use updated packages.\n","output_type":"stream"}]}]}