Make necessary imports


In [1]:
import sys
sys.path.insert(0, '../')

In [2]:
import time
import numpy as np
np.set_printoptions(precision=3, linewidth=200, suppress=True)
import tensorflow as tf

In [3]:
from library.datasets.cifar10 import CIFAR10
from library.plot_tools import plot
from library.utils import file_utils
from library.tf.models.linear_classifier import LinearClassifier

Select Tensorflow device


In [4]:
# from tensorflow.python.client import device_lib
# local_device_protos = device_lib.list_local_devices()
# cpu_devices = [x.name for x in local_device_protos if x.device_type == 'CPU']
# gpu_devices = [x.name for x in local_device_protos if x.device_type == 'GPU']
# print('Available CPU Devices: ', end='')
# print(cpu_devices)
# print('Available GPU Devices: ', end='')
# print(gpu_devices)
# if len(gpu_devices) == 0:
#     if len(cpu_devices) > 0:
#         device_name = '/cpu:0'
#         print('Using CPU: %s' %device_name)
#     else:
#         print('No CPU present in the system!!!')
# else:
#     device_name = '/gpu:0'
#     print('Using GPU: %s' %device_name)

In [5]:
total_time = 0

Experiment


In [6]:
exp_no = 6
data_source = 'Website'
num_images_required = 1.0
file_no = 101

Parameters for experiment


In [7]:
device_name = '/gpu:0'
learn_rate = 0.01
train_epochs = 10000
display_step = 1
reg_const = 0.01
train_val_split_data = None
train_val_split = 0.8
transform = True
transform_method = 'StandardScaler'
learn_rate_type = 'constant'
dataset = 'cifar10'

Log directories


In [8]:
log_dir = '../logs/' + dataset + '/' + str(file_no).zfill(3) + '_tf_linear_raw/exp_no_' + str(exp_no).zfill(3) + '/'
log_file = log_dir + 'linear_classifier.ckpt'
model_file = log_dir + 'linear_classifier.pb'
print('Writing tensorboard logs to %s' % log_file)
print('View logs by running tensorboard: ', end='')
print('\"tensorboard --logdir=\'./%s/101_tf_linear_raw/\' --port 61111\"' %dataset)


Writing tensorboard logs to ../logs/cifar10/101_tf_linear_raw/exp_no_006/linear_classifier.ckpt
View logs by running tensorboard: "tensorboard --logdir='./cifar10/101_tf_linear_raw/' --port 61111"

Step 1: Load CIFAR 10 Dataset


In [9]:
start = time.time()
one_hot = True
cifar10 = CIFAR10(one_hot_encode=one_hot, num_images=num_images_required, preprocess='StandardScaler',
                  train_validate_split=train_val_split_data, endian='little')
cifar10.load_data(train=True, test=True, data_directory='./datasets/cifar10/')
end = time.time()
print('[ Step 1] Loaded CIFAR 10 Dataset in %.4f ms' %((end-start)*1000))
total_time += (end-start)


Loading CIFAR 10 Dataset
Downloading and extracting CIFAR 10 file
MD5sum of the file: ./datasets/cifar10/cifar-10.tar.gz is verified
Loading 50000 train images
Loading CIFAR 10 Training Dataset
Reading unpicked data file: ./datasets/cifar10/cifar-10-batches/data_batch_1
Reading unpicked data file: ./datasets/cifar10/cifar-10-batches/data_batch_2
Reading unpicked data file: ./datasets/cifar10/cifar-10-batches/data_batch_3
Reading unpicked data file: ./datasets/cifar10/cifar-10-batches/data_batch_4
Reading unpicked data file: ./datasets/cifar10/cifar-10-batches/data_batch_5
/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/sklearn/utils/validation.py:429: DataConversionWarning: Data with input dtype uint8 was converted to float64 by StandardScaler.
  warnings.warn(msg, _DataConversionWarning)
Loading 10000 test images
Loading CIFAR 10 Test Dataset
Unpickling test file: ./datasets/cifar10/cifar-10-batches/test_batch
Reading unpicked test file: ./datasets/cifar10/cifar-10-batches/test_batch
Loaded CIFAR 10 Dataset in 8.0137 seconds
[ Step 1] Loaded CIFAR 10 Dataset in 8014.5056 ms

In [10]:
print('Train data shape:', cifar10.train.data.shape)
if one_hot is True:
    print('Train labels shape:', cifar10.train.one_hot_labels.shape)
print('Train class labels shape:', cifar10.train.class_labels.shape)
if train_val_split_data is not None:
    print('Validate data shape:', cifar10.validate.data.shape)
    if one_hot is True:
        print('Validate labels shape:', cifar10.validate.one_hot_labels.shape)
    print('Validate class labels shape:', cifar10.validate.class_labels.shape)
print('Test data shape:', cifar10.test.data.shape)
if one_hot is True:
    print('Test labels shape:', cifar10.test.one_hot_labels.shape)
print('Test class labels shape:', cifar10.test.class_labels.shape)


Train data shape: (50000, 3072)
Train labels shape: (50000, 10)
Train class labels shape: (50000,)
Test data shape: (10000, 3072)
Test labels shape: (10000, 10)
Test class labels shape: (10000,)

In [11]:
print('Training images')
print(cifar10.train.data[:5])
if one_hot is True:
    print('Training labels')
    print(cifar10.train.one_hot_labels[:5])
print('Training classes')
print(cifar10.train.class_labels[:5])
print('Testing images')
print(cifar10.test.data[:5])
if one_hot is True:
    print('Testing labels')
    print(cifar10.test.one_hot_labels[:5])
print('Testing classes')
print(cifar10.test.class_labels[:5])


Training images
[[-0.977 -1.203 -1.122 ...,  0.403 -0.459 -0.641]
 [ 0.317 -0.057 -0.361 ...,  0.388  0.431  0.448]
 [ 1.693  1.696  1.688 ..., -0.475 -0.474 -0.46 ]
 [-1.399 -1.286 -1.288 ..., -1.323 -1.179 -1.035]
 [ 0.535  0.523  0.636 ..., -0.491 -0.551 -0.52 ]]
Training labels
[[ 0.  0.  0.  0.  0.  0.  1.  0.  0.  0.]
 [ 0.  0.  0.  0.  0.  0.  0.  0.  0.  1.]
 [ 0.  0.  0.  0.  0.  0.  0.  0.  0.  1.]
 [ 0.  0.  0.  0.  1.  0.  0.  0.  0.  0.]
 [ 0.  1.  0.  0.  0.  0.  0.  0.  0.  0.]]
Training classes
[6 9 9 4 1]
Testing images
[[ 0.375  0.401  0.468 ...,  0.142  0.219 -0.081]
 [ 1.425  1.395  1.395 ...,  0.98   1.174  1.274]
 [ 0.375  0.387  0.109 ..., -1.658 -1.722 -1.65 ]
 [ 0.334  0.511  0.621 ..., -1.006 -0.967 -0.995]
 [-0.894 -0.829 -1.15  ...,  0.328  0.481  0.025]]
Testing labels
[[ 0.  0.  0.  1.  0.  0.  0.  0.  0.  0.]
 [ 0.  0.  0.  0.  0.  0.  0.  0.  1.  0.]
 [ 0.  0.  0.  0.  0.  0.  0.  0.  1.  0.]
 [ 1.  0.  0.  0.  0.  0.  0.  0.  0.  0.]
 [ 0.  0.  0.  0.  0.  0.  1.  0.  0.  0.]]
Testing classes
[3 8 8 0 6]

Step 1.1 Load sample images


In [12]:
cifar10.plot_sample(plot_data=True, plot_test=True, fig_size=(7, 7))


Plotting CIFAR 10 Train Dataset
Plotting CIFAR 10 Test Dataset

In [13]:
cifar10.plot_images(cifar10.train.data[:50, :], cifar10.train.class_names[:50], 
                    nrows=5, ncols=10, fig_size=(20,50), fontsize=35, convert=True)


Out[13]:
True

Step 2: Linear Regression

Step 2.1: Model linear regression y = Wx + b


In [14]:
num_features = cifar10.train.data.shape[1]
num_classes = 10

In [15]:
network_config = {'weight': {'type': 'zeros', 'name': 'Weight'},
                  'bias': {'type': 'ones', 'name': 'Bias'},
                  'activation_fn': 'relu',
                  'descent_method': 'adam'}

In [16]:
lc = LinearClassifier(verbose=False, device=device_name, session_type='interactive', num_iter=train_epochs, 
                      err_tolerance=1e-7, train_validate_split=train_val_split, display_step=display_step,
                      learn_step=10, learn_rate_type=learn_rate_type, learn_rate=learn_rate, reg_const=reg_const, 
                      logs=True, log_dir=log_dir, test_log=True, save_model=True, checkpoint_filename=log_file, 
                      save_checkpoint=True, restore=False, model_name=model_file, config=network_config)

Step 2.2: Create the tensorflow graph


In [17]:
start = time.time()
lc.create_graph(num_features=num_features, num_classes=num_classes)
end = time.time()
print('Generated the tensorflow graph in %.4f ms' % ((end-start)*1000))
total_time = (end-start)


Session: <tensorflow.python.client.session.InteractiveSession object at 0x7f239cdb2ac8>
Model has been trained for 0 iterations
Tensorflow graph created in 0.8735 seconds
Generated the tensorflow graph in 874.7673 ms

In [ ]:
lc.print_parameters()


Parameters for Linear classifier
>> Input Parameters
Input                  : Tensor("Inputs/Data/X_input:0", shape=(?, 3072), dtype=float32, device=/device:GPU:0) 
True one hot labels    : Tensor("Inputs/Train_Labels/y_true_one_hot_label:0", shape=(?, 10), dtype=float32, device=/device:GPU:0) 
True class             : Tensor("Inputs/Train_Labels/y_true_class:0", shape=(?,), dtype=int64, device=/device:GPU:0) 
Predict one hot labels : Tensor("Predictions/one_hot:0", shape=(?, 10), dtype=float32, device=/device:GPU:0) 
Predict class          : Tensor("Predictions/predict_class:0", shape=(?,), dtype=int64, device=/device:GPU:0) 
>> Model params
last_successful_epoch/initial_value
last_successful_epoch
last_successful_epoch/Assign
last_successful_epoch/read
add/y
add
assign_updated_epoch
Inputs/Data/X_input
Inputs/Train_Labels/y_true_one_hot_label
Inputs/Train_Labels/y_true_class
Parameters/Weights/zeros
Parameters/Weights/Weight
Parameters/Weights/Weight/Assign
Parameters/Weights/Weight/read
Parameters/Bias/ones
Parameters/Bias/Bias
Parameters/Bias/Bias/Assign
Parameters/Bias/Bias/read
Predictions/mlp_layer/MatMul
Predictions/mlp_layer
Predictions/mlp_layer_1
Predictions/Softmax
Predictions/predict_class/dimension
Predictions/predict_class
Predictions/one_hot/Const
Predictions/one_hot/Const_1
Predictions/one_hot/depth
Predictions/one_hot/on_value
Predictions/one_hot/off_value
Predictions/one_hot
Cross_Entropy/Rank
Cross_Entropy/Shape
Cross_Entropy/Rank_1
Cross_Entropy/Shape_1
Cross_Entropy/Sub/y
Cross_Entropy/Sub
Cross_Entropy/Slice/begin
Cross_Entropy/Slice/size
Cross_Entropy/Slice
Cross_Entropy/concat/values_0
Cross_Entropy/concat/axis
Cross_Entropy/concat
Cross_Entropy/Reshape
Cross_Entropy/Rank_2
Cross_Entropy/Shape_2
Cross_Entropy/Sub_1/y
Cross_Entropy/Sub_1
Cross_Entropy/Slice_1/begin
Cross_Entropy/Slice_1/size
Cross_Entropy/Slice_1
Cross_Entropy/concat_1/values_0
Cross_Entropy/concat_1/axis
Cross_Entropy/concat_1
Cross_Entropy/Reshape_1
Cross_Entropy/SoftmaxCrossEntropyWithLogits
Cross_Entropy/Sub_2/y
Cross_Entropy/Sub_2
Cross_Entropy/Slice_2/begin
Cross_Entropy/Slice_2/size
Cross_Entropy/Slice_2
Cross_Entropy/Reshape_2
Loss_Function/Const
Loss_Function/Square
Loss_Function/Const_1
Loss_Function/Mean
Loss_Function/Const_2
Loss_Function/Mean_1
Loss_Function/Mul
Loss_Function/Add
Loss_Function/train_loss_list/initial_value
Loss_Function/train_loss_list
Loss_Function/train_loss_list/Assign
Loss_Function/train_loss_list/read
Loss_Function/Assign/value
Loss_Function/Assign
Loss_Function/train_error/tags
Loss_Function/train_error
Loss_Function/validate_loss_list/initial_value
Loss_Function/validate_loss_list
Loss_Function/validate_loss_list/Assign
Loss_Function/validate_loss_list/read
Loss_Function/Assign_1/value
Loss_Function/Assign_1
Loss_Function/validate_error/tags
Loss_Function/validate_error
Optimizer/learning_rate_progress/initial_value
Optimizer/learning_rate_progress
Optimizer/learning_rate_progress/Assign
Optimizer/learning_rate_progress/read
Optimizer/Assign/value
Optimizer/Assign
Optimizer/learning_rate/tags
Optimizer/learning_rate/values
Optimizer/learning_rate
Optimizer/gradients/Shape
Optimizer/gradients/Const
Optimizer/gradients/Fill
Optimizer/gradients/Loss_Function/Add_grad/Shape
Optimizer/gradients/Loss_Function/Add_grad/Shape_1
Optimizer/gradients/Loss_Function/Add_grad/BroadcastGradientArgs
Optimizer/gradients/Loss_Function/Add_grad/Sum
Optimizer/gradients/Loss_Function/Add_grad/Reshape
Optimizer/gradients/Loss_Function/Add_grad/Sum_1
Optimizer/gradients/Loss_Function/Add_grad/Reshape_1
Optimizer/gradients/Loss_Function/Add_grad/tuple/group_deps
Optimizer/gradients/Loss_Function/Add_grad/tuple/control_dependency
Optimizer/gradients/Loss_Function/Add_grad/tuple/control_dependency_1
Optimizer/gradients/Loss_Function/Mean_1_grad/Reshape/shape
Optimizer/gradients/Loss_Function/Mean_1_grad/Reshape
Optimizer/gradients/Loss_Function/Mean_1_grad/Shape
Optimizer/gradients/Loss_Function/Mean_1_grad/Tile
Optimizer/gradients/Loss_Function/Mean_1_grad/Shape_1
Optimizer/gradients/Loss_Function/Mean_1_grad/Shape_2
Optimizer/gradients/Loss_Function/Mean_1_grad/Const
Optimizer/gradients/Loss_Function/Mean_1_grad/Prod
Optimizer/gradients/Loss_Function/Mean_1_grad/Const_1
Optimizer/gradients/Loss_Function/Mean_1_grad/Prod_1
Optimizer/gradients/Loss_Function/Mean_1_grad/Maximum/y
Optimizer/gradients/Loss_Function/Mean_1_grad/Maximum
Optimizer/gradients/Loss_Function/Mean_1_grad/floordiv
Optimizer/gradients/Loss_Function/Mean_1_grad/Cast
Optimizer/gradients/Loss_Function/Mean_1_grad/truediv
Optimizer/gradients/Loss_Function/Mul_grad/Shape
Optimizer/gradients/Loss_Function/Mul_grad/Shape_1
Optimizer/gradients/Loss_Function/Mul_grad/BroadcastGradientArgs
Optimizer/gradients/Loss_Function/Mul_grad/mul
Optimizer/gradients/Loss_Function/Mul_grad/Sum
Optimizer/gradients/Loss_Function/Mul_grad/Reshape
Optimizer/gradients/Loss_Function/Mul_grad/mul_1
Optimizer/gradients/Loss_Function/Mul_grad/Sum_1
Optimizer/gradients/Loss_Function/Mul_grad/Reshape_1
Optimizer/gradients/Loss_Function/Mul_grad/tuple/group_deps
Optimizer/gradients/Loss_Function/Mul_grad/tuple/control_dependency
Optimizer/gradients/Loss_Function/Mul_grad/tuple/control_dependency_1
Optimizer/gradients/Cross_Entropy/Reshape_2_grad/Shape
Optimizer/gradients/Cross_Entropy/Reshape_2_grad/Reshape
Optimizer/gradients/Loss_Function/Mean_grad/Reshape/shape
Optimizer/gradients/Loss_Function/Mean_grad/Reshape
Optimizer/gradients/Loss_Function/Mean_grad/Tile/multiples
Optimizer/gradients/Loss_Function/Mean_grad/Tile
Optimizer/gradients/Loss_Function/Mean_grad/Shape
Optimizer/gradients/Loss_Function/Mean_grad/Shape_1
Optimizer/gradients/Loss_Function/Mean_grad/Const
Optimizer/gradients/Loss_Function/Mean_grad/Prod
Optimizer/gradients/Loss_Function/Mean_grad/Const_1
Optimizer/gradients/Loss_Function/Mean_grad/Prod_1
Optimizer/gradients/Loss_Function/Mean_grad/Maximum/y
Optimizer/gradients/Loss_Function/Mean_grad/Maximum
Optimizer/gradients/Loss_Function/Mean_grad/floordiv
Optimizer/gradients/Loss_Function/Mean_grad/Cast
Optimizer/gradients/Loss_Function/Mean_grad/truediv
Optimizer/gradients/zeros_like
Optimizer/gradients/Cross_Entropy/SoftmaxCrossEntropyWithLogits_grad/PreventGradient
Optimizer/gradients/Cross_Entropy/SoftmaxCrossEntropyWithLogits_grad/ExpandDims/dim
Optimizer/gradients/Cross_Entropy/SoftmaxCrossEntropyWithLogits_grad/ExpandDims
Optimizer/gradients/Cross_Entropy/SoftmaxCrossEntropyWithLogits_grad/mul
Optimizer/gradients/Loss_Function/Square_grad/mul/x
Optimizer/gradients/Loss_Function/Square_grad/mul
Optimizer/gradients/Loss_Function/Square_grad/mul_1
Optimizer/gradients/Cross_Entropy/Reshape_grad/Shape
Optimizer/gradients/Cross_Entropy/Reshape_grad/Reshape
Optimizer/gradients/Predictions/Softmax_grad/mul
Optimizer/gradients/Predictions/Softmax_grad/Sum/reduction_indices
Optimizer/gradients/Predictions/Softmax_grad/Sum
Optimizer/gradients/Predictions/Softmax_grad/Reshape/shape
Optimizer/gradients/Predictions/Softmax_grad/Reshape
Optimizer/gradients/Predictions/Softmax_grad/sub
Optimizer/gradients/Predictions/Softmax_grad/mul_1
Optimizer/gradients/Predictions/mlp_layer_1_grad/ReluGrad
Optimizer/gradients/Predictions/mlp_layer_grad/BiasAddGrad
Optimizer/gradients/Predictions/mlp_layer_grad/tuple/group_deps
Optimizer/gradients/Predictions/mlp_layer_grad/tuple/control_dependency
Optimizer/gradients/Predictions/mlp_layer_grad/tuple/control_dependency_1
Optimizer/gradients/Predictions/mlp_layer/MatMul_grad/MatMul
Optimizer/gradients/Predictions/mlp_layer/MatMul_grad/MatMul_1
Optimizer/gradients/Predictions/mlp_layer/MatMul_grad/tuple/group_deps
Optimizer/gradients/Predictions/mlp_layer/MatMul_grad/tuple/control_dependency
Optimizer/gradients/Predictions/mlp_layer/MatMul_grad/tuple/control_dependency_1
Optimizer/gradients/AddN
Optimizer/GradientDescent/learning_rate
Optimizer/GradientDescent/update_Parameters/Weights/Weight/ApplyGradientDescent
Optimizer/GradientDescent/update_Parameters/Bias/Bias/ApplyGradientDescent
Optimizer/GradientDescent
Equal
Accuracy/Cast
Accuracy/Const
Accuracy/Mean
Accuracy/train_accuracy_list/initial_value
Accuracy/train_accuracy_list
Accuracy/train_accuracy_list/Assign
Accuracy/train_accuracy_list/read
Accuracy/Assign/value
Accuracy/Assign
Accuracy/train_accuracy/tags
Accuracy/train_accuracy
Accuracy/Cast_1
Accuracy/Const_1
Accuracy/Mean_1
Accuracy/validate_accuracy_list/initial_value
Accuracy/validate_accuracy_list
Accuracy/validate_accuracy_list/Assign
Accuracy/validate_accuracy_list/read
Accuracy/Assign_1/value
Accuracy/Assign_1
Accuracy/validate_accuracy/tags
Accuracy/validate_accuracy
Accuracy/Cast_2
Accuracy/Const_2
Accuracy/Mean_2
Accuracy/test_accuracy_list/initial_value
Accuracy/test_accuracy_list
Accuracy/test_accuracy_list/Assign
Accuracy/test_accuracy_list/read
Accuracy/Assign_2/value
Accuracy/Assign_2
Accuracy/test_accuracy/tags
Accuracy/test_accuracy
init/NoOp
init/NoOp_1
init
Merge/MergeSummary
save/Const
save/SaveV2/tensor_names
save/SaveV2/shape_and_slices
save/SaveV2
save/control_dependency
save/RestoreV2/tensor_names
save/RestoreV2/shape_and_slices
save/RestoreV2
save/Assign
save/RestoreV2_1/tensor_names
save/RestoreV2_1/shape_and_slices
save/RestoreV2_1
save/Assign_1
save/RestoreV2_2/tensor_names
save/RestoreV2_2/shape_and_slices
save/RestoreV2_2
save/Assign_2
save/RestoreV2_3/tensor_names
save/RestoreV2_3/shape_and_slices
save/RestoreV2_3
save/Assign_3
save/RestoreV2_4/tensor_names
save/RestoreV2_4/shape_and_slices
save/RestoreV2_4
save/Assign_4
save/RestoreV2_5/tensor_names
save/RestoreV2_5/shape_and_slices
save/RestoreV2_5
save/Assign_5
save/RestoreV2_6/tensor_names
save/RestoreV2_6/shape_and_slices
save/RestoreV2_6
save/Assign_6
save/RestoreV2_7/tensor_names
save/RestoreV2_7/shape_and_slices
save/RestoreV2_7
save/Assign_7
save/RestoreV2_8/tensor_names
save/RestoreV2_8/shape_and_slices
save/RestoreV2_8
save/Assign_8
save/restore_all/NoOp
save/restore_all/NoOp_1
save/restore_all
Output Logits  : Tensor("Predictions/Softmax:0", shape=(?, 10), dtype=float32, device=/device:GPU:0)
Entropy        : Tensor("Cross_Entropy/Reshape_2:0", shape=(?,), dtype=float32, device=/device:GPU:0)
Predictions    : Tensor("Equal:0", shape=(?,), dtype=bool, device=/device:GPU:0) 
Optimizer      : name: "Optimizer/GradientDescent"
op: "NoOp"
input: "^Optimizer/GradientDescent/update_Parameters/Weights/Weight/ApplyGradientDescent"
input: "^Optimizer/GradientDescent/update_Parameters/Bias/Bias/ApplyGradientDescent"
device: "/device:GPU:0"
 
>> Model info
Train loss     : Tensor("Loss_Function/Add:0", shape=(), dtype=float32, device=/device:GPU:0)
Train accuracy : Tensor("Accuracy/Mean:0", shape=(), dtype=float32, device=/device:GPU:0)
Val. loss      : Tensor("Loss_Function/Add:0", shape=(), dtype=float32, device=/device:GPU:0)
Val. accuracy  : Tensor("Accuracy/Mean_1:0", shape=(), dtype=float32, device=/device:GPU:0)
>> Summary params
Train loss     : Tensor("Loss_Function/train_error:0", shape=(), dtype=string, device=/device:GPU:0)
Train accuracy : Tensor("Accuracy/train_accuracy:0", shape=(), dtype=string, device=/device:GPU:0)
Val. loss      : Tensor("Loss_Function/validate_error:0", shape=(), dtype=string, device=/device:GPU:0)
Val. accuracy  : Tensor("Accuracy/validate_accuracy:0", shape=(), dtype=string, device=/device:GPU:0)

Step 2.3: Fit the model/training


In [ ]:
start = time.time()
lc.fit(cifar10.train.data, cifar10.train.one_hot_labels, cifar10.train.class_labels,
       test_data=cifar10.test.data, test_labels=cifar10.test.one_hot_labels, test_classes=cifar10.test.class_labels)
end = time.time()
print('Fit completed in %.4f seconds' % (end-start))


Length of train loss          : 0
Length of train accuracy      : 0
Length of validate loss       : 0
Length of validate accuracy   : 0
Length of test accuracy       : 0
Restoring training from epoch : 0
>>> Epoch [    0/10000]
train_loss: 2.3026 | train_acc: 0.1004 | val_loss: 2.3006 | val_acc: 0.2530 | test_acc: 0.2560 | Time: 1.0220 s
>>> Epoch [    1/10000]
train_loss: 2.3006 | train_acc: 0.2488 | val_loss: 2.2986 | val_acc: 0.2520 | test_acc: 0.2556 | Time: 0.6559 s
>>> Epoch [    2/10000]
train_loss: 2.2986 | train_acc: 0.2481 | val_loss: 2.2965 | val_acc: 0.2517 | test_acc: 0.2555 | Time: 0.7532 s
>>> Epoch [    3/10000]
train_loss: 2.2965 | train_acc: 0.2471 | val_loss: 2.2942 | val_acc: 0.2506 | test_acc: 0.2540 | Time: 0.7103 s
>>> Epoch [    4/10000]
train_loss: 2.2943 | train_acc: 0.2459 | val_loss: 2.2919 | val_acc: 0.2487 | test_acc: 0.2524 | Time: 0.7355 s
>>> Epoch [    5/10000]
train_loss: 2.2919 | train_acc: 0.2447 | val_loss: 2.2895 | val_acc: 0.2477 | test_acc: 0.2501 | Time: 0.7769 s
>>> Epoch [    6/10000]
train_loss: 2.2895 | train_acc: 0.2441 | val_loss: 2.2870 | val_acc: 0.2459 | test_acc: 0.2481 | Time: 0.7937 s
>>> Epoch [    7/10000]
train_loss: 2.2870 | train_acc: 0.2431 | val_loss: 2.2845 | val_acc: 0.2438 | test_acc: 0.2475 | Time: 0.7347 s
>>> Epoch [    8/10000]
train_loss: 2.2844 | train_acc: 0.2427 | val_loss: 2.2819 | val_acc: 0.2422 | test_acc: 0.2463 | Time: 0.7850 s
>>> Epoch [    9/10000]
train_loss: 2.2818 | train_acc: 0.2418 | val_loss: 2.2793 | val_acc: 0.2418 | test_acc: 0.2464 | Time: 0.7691 s
>>> Epoch [   10/10000]
train_loss: 2.2791 | train_acc: 0.2412 | val_loss: 2.2767 | val_acc: 0.2421 | test_acc: 0.2457 | Time: 0.7562 s
>>> Epoch [   11/10000]
train_loss: 2.2765 | train_acc: 0.2411 | val_loss: 2.2741 | val_acc: 0.2422 | test_acc: 0.2449 | Time: 0.7369 s
>>> Epoch [   12/10000]
train_loss: 2.2739 | train_acc: 0.2409 | val_loss: 2.2717 | val_acc: 0.2425 | test_acc: 0.2444 | Time: 0.6610 s
>>> Epoch [   13/10000]
train_loss: 2.2714 | train_acc: 0.2415 | val_loss: 2.2693 | val_acc: 0.2429 | test_acc: 0.2449 | Time: 0.7540 s
>>> Epoch [   14/10000]
train_loss: 2.2690 | train_acc: 0.2421 | val_loss: 2.2670 | val_acc: 0.2440 | test_acc: 0.2454 | Time: 0.7092 s
>>> Epoch [   15/10000]
train_loss: 2.2667 | train_acc: 0.2424 | val_loss: 2.2648 | val_acc: 0.2450 | test_acc: 0.2468 | Time: 0.7372 s
>>> Epoch [   16/10000]
train_loss: 2.2645 | train_acc: 0.2431 | val_loss: 2.2626 | val_acc: 0.2468 | test_acc: 0.2486 | Time: 0.7032 s
>>> Epoch [   17/10000]
train_loss: 2.2624 | train_acc: 0.2436 | val_loss: 2.2606 | val_acc: 0.2467 | test_acc: 0.2499 | Time: 0.7548 s
>>> Epoch [   18/10000]
train_loss: 2.2604 | train_acc: 0.2447 | val_loss: 2.2586 | val_acc: 0.2484 | test_acc: 0.2508 | Time: 0.7695 s
>>> Epoch [   19/10000]
train_loss: 2.2584 | train_acc: 0.2455 | val_loss: 2.2566 | val_acc: 0.2500 | test_acc: 0.2523 | Time: 0.7487 s
>>> Epoch [   20/10000]
train_loss: 2.2565 | train_acc: 0.2462 | val_loss: 2.2547 | val_acc: 0.2501 | test_acc: 0.2539 | Time: 0.7772 s
>>> Epoch [   21/10000]
train_loss: 2.2546 | train_acc: 0.2471 | val_loss: 2.2528 | val_acc: 0.2507 | test_acc: 0.2556 | Time: 0.7212 s
>>> Epoch [   22/10000]
train_loss: 2.2527 | train_acc: 0.2482 | val_loss: 2.2510 | val_acc: 0.2515 | test_acc: 0.2553 | Time: 0.7216 s
>>> Epoch [   23/10000]
train_loss: 2.2509 | train_acc: 0.2492 | val_loss: 2.2492 | val_acc: 0.2533 | test_acc: 0.2566 | Time: 0.8347 s
>>> Epoch [   24/10000]
train_loss: 2.2492 | train_acc: 0.2500 | val_loss: 2.2474 | val_acc: 0.2540 | test_acc: 0.2574 | Time: 0.7235 s
>>> Epoch [   25/10000]
train_loss: 2.2474 | train_acc: 0.2506 | val_loss: 2.2457 | val_acc: 0.2542 | test_acc: 0.2587 | Time: 0.7660 s
>>> Epoch [   26/10000]
train_loss: 2.2457 | train_acc: 0.2517 | val_loss: 2.2439 | val_acc: 0.2557 | test_acc: 0.2602 | Time: 0.7576 s
>>> Epoch [   27/10000]
train_loss: 2.2441 | train_acc: 0.2523 | val_loss: 2.2423 | val_acc: 0.2556 | test_acc: 0.2610 | Time: 0.7840 s
>>> Epoch [   28/10000]
train_loss: 2.2424 | train_acc: 0.2534 | val_loss: 2.2406 | val_acc: 0.2570 | test_acc: 0.2616 | Time: 0.7462 s
>>> Epoch [   29/10000]
train_loss: 2.2408 | train_acc: 0.2541 | val_loss: 2.2390 | val_acc: 0.2571 | test_acc: 0.2614 | Time: 0.7184 s
>>> Epoch [   30/10000]
train_loss: 2.2392 | train_acc: 0.2554 | val_loss: 2.2374 | val_acc: 0.2584 | test_acc: 0.2618 | Time: 0.7915 s
>>> Epoch [   31/10000]
train_loss: 2.2377 | train_acc: 0.2562 | val_loss: 2.2359 | val_acc: 0.2592 | test_acc: 0.2631 | Time: 0.8027 s
>>> Epoch [   32/10000]
train_loss: 2.2362 | train_acc: 0.2574 | val_loss: 2.2344 | val_acc: 0.2598 | test_acc: 0.2640 | Time: 0.8299 s
>>> Epoch [   33/10000]
train_loss: 2.2347 | train_acc: 0.2585 | val_loss: 2.2329 | val_acc: 0.2611 | test_acc: 0.2655 | Time: 0.7484 s
>>> Epoch [   34/10000]
train_loss: 2.2333 | train_acc: 0.2591 | val_loss: 2.2314 | val_acc: 0.2620 | test_acc: 0.2666 | Time: 0.8394 s
>>> Epoch [   35/10000]
train_loss: 2.2318 | train_acc: 0.2602 | val_loss: 2.2300 | val_acc: 0.2636 | test_acc: 0.2677 | Time: 0.7460 s
>>> Epoch [   36/10000]
train_loss: 2.2305 | train_acc: 0.2612 | val_loss: 2.2287 | val_acc: 0.2645 | test_acc: 0.2688 | Time: 0.7654 s
>>> Epoch [   37/10000]
train_loss: 2.2291 | train_acc: 0.2620 | val_loss: 2.2273 | val_acc: 0.2645 | test_acc: 0.2694 | Time: 0.8430 s
>>> Epoch [   38/10000]
train_loss: 2.2278 | train_acc: 0.2627 | val_loss: 2.2260 | val_acc: 0.2648 | test_acc: 0.2699 | Time: 0.8052 s
>>> Epoch [   39/10000]
train_loss: 2.2265 | train_acc: 0.2635 | val_loss: 2.2247 | val_acc: 0.2662 | test_acc: 0.2705 | Time: 0.7847 s
>>> Epoch [   40/10000]
train_loss: 2.2252 | train_acc: 0.2639 | val_loss: 2.2235 | val_acc: 0.2662 | test_acc: 0.2717 | Time: 0.6980 s
>>> Epoch [   41/10000]
train_loss: 2.2240 | train_acc: 0.2647 | val_loss: 2.2223 | val_acc: 0.2670 | test_acc: 0.2727 | Time: 0.8306 s
>>> Epoch [   42/10000]
train_loss: 2.2228 | train_acc: 0.2651 | val_loss: 2.2211 | val_acc: 0.2679 | test_acc: 0.2738 | Time: 0.7973 s
>>> Epoch [   43/10000]
train_loss: 2.2216 | train_acc: 0.2656 | val_loss: 2.2199 | val_acc: 0.2682 | test_acc: 0.2743 | Time: 0.7308 s
>>> Epoch [   44/10000]
train_loss: 2.2204 | train_acc: 0.2667 | val_loss: 2.2188 | val_acc: 0.2690 | test_acc: 0.2744 | Time: 0.7977 s
>>> Epoch [   45/10000]
train_loss: 2.2193 | train_acc: 0.2675 | val_loss: 2.2177 | val_acc: 0.2704 | test_acc: 0.2750 | Time: 0.7537 s
>>> Epoch [   46/10000]
train_loss: 2.2182 | train_acc: 0.2686 | val_loss: 2.2166 | val_acc: 0.2717 | test_acc: 0.2762 | Time: 0.8993 s
>>> Epoch [   47/10000]
train_loss: 2.2171 | train_acc: 0.2696 | val_loss: 2.2155 | val_acc: 0.2728 | test_acc: 0.2776 | Time: 0.8401 s
>>> Epoch [   48/10000]
train_loss: 2.2160 | train_acc: 0.2702 | val_loss: 2.2145 | val_acc: 0.2734 | test_acc: 0.2793 | Time: 0.8695 s
>>> Epoch [   49/10000]
train_loss: 2.2150 | train_acc: 0.2708 | val_loss: 2.2135 | val_acc: 0.2743 | test_acc: 0.2807 | Time: 0.8850 s
>>> Epoch [   50/10000]
train_loss: 2.2140 | train_acc: 0.2717 | val_loss: 2.2125 | val_acc: 0.2749 | test_acc: 0.2820 | Time: 0.7849 s
>>> Epoch [   51/10000]
train_loss: 2.2130 | train_acc: 0.2725 | val_loss: 2.2115 | val_acc: 0.2762 | test_acc: 0.2828 | Time: 0.8696 s
>>> Epoch [   52/10000]
train_loss: 2.2120 | train_acc: 0.2734 | val_loss: 2.2106 | val_acc: 0.2758 | test_acc: 0.2840 | Time: 0.8288 s
>>> Epoch [   53/10000]
train_loss: 2.2110 | train_acc: 0.2743 | val_loss: 2.2096 | val_acc: 0.2772 | test_acc: 0.2854 | Time: 0.8067 s
>>> Epoch [   54/10000]
train_loss: 2.2101 | train_acc: 0.2751 | val_loss: 2.2087 | val_acc: 0.2783 | test_acc: 0.2859 | Time: 0.7687 s
>>> Epoch [   55/10000]
train_loss: 2.2091 | train_acc: 0.2758 | val_loss: 2.2078 | val_acc: 0.2788 | test_acc: 0.2863 | Time: 0.8471 s
>>> Epoch [   56/10000]
train_loss: 2.2082 | train_acc: 0.2767 | val_loss: 2.2070 | val_acc: 0.2796 | test_acc: 0.2869 | Time: 0.7629 s
>>> Epoch [   57/10000]
train_loss: 2.2073 | train_acc: 0.2775 | val_loss: 2.2061 | val_acc: 0.2804 | test_acc: 0.2879 | Time: 0.8827 s
>>> Epoch [   58/10000]
train_loss: 2.2065 | train_acc: 0.2785 | val_loss: 2.2053 | val_acc: 0.2810 | test_acc: 0.2888 | Time: 0.7619 s
>>> Epoch [   59/10000]
train_loss: 2.2056 | train_acc: 0.2793 | val_loss: 2.2044 | val_acc: 0.2818 | test_acc: 0.2890 | Time: 0.8396 s
>>> Epoch [   60/10000]
train_loss: 2.2047 | train_acc: 0.2801 | val_loss: 2.2036 | val_acc: 0.2825 | test_acc: 0.2900 | Time: 0.9003 s
>>> Epoch [   61/10000]
train_loss: 2.2039 | train_acc: 0.2809 | val_loss: 2.2028 | val_acc: 0.2834 | test_acc: 0.2900 | Time: 0.7669 s
>>> Epoch [   62/10000]
train_loss: 2.2031 | train_acc: 0.2816 | val_loss: 2.2020 | val_acc: 0.2833 | test_acc: 0.2908 | Time: 0.8344 s
>>> Epoch [   63/10000]
train_loss: 2.2023 | train_acc: 0.2822 | val_loss: 2.2013 | val_acc: 0.2837 | test_acc: 0.2918 | Time: 0.9210 s
>>> Epoch [   64/10000]
train_loss: 2.2015 | train_acc: 0.2832 | val_loss: 2.2005 | val_acc: 0.2845 | test_acc: 0.2929 | Time: 0.8620 s
>>> Epoch [   65/10000]
train_loss: 2.2007 | train_acc: 0.2841 | val_loss: 2.1998 | val_acc: 0.2853 | test_acc: 0.2932 | Time: 0.7932 s
>>> Epoch [   66/10000]
train_loss: 2.1999 | train_acc: 0.2849 | val_loss: 2.1990 | val_acc: 0.2864 | test_acc: 0.2939 | Time: 0.9095 s
>>> Epoch [   67/10000]
train_loss: 2.1991 | train_acc: 0.2860 | val_loss: 2.1983 | val_acc: 0.2864 | test_acc: 0.2946 | Time: 0.7478 s
>>> Epoch [   68/10000]
train_loss: 2.1984 | train_acc: 0.2872 | val_loss: 2.1976 | val_acc: 0.2867 | test_acc: 0.2954 | Time: 0.8020 s
>>> Epoch [   69/10000]
train_loss: 2.1976 | train_acc: 0.2881 | val_loss: 2.1969 | val_acc: 0.2874 | test_acc: 0.2965 | Time: 0.8015 s
>>> Epoch [   70/10000]
train_loss: 2.1969 | train_acc: 0.2890 | val_loss: 2.1962 | val_acc: 0.2885 | test_acc: 0.2971 | Time: 0.7764 s
>>> Epoch [   71/10000]
train_loss: 2.1962 | train_acc: 0.2896 | val_loss: 2.1955 | val_acc: 0.2894 | test_acc: 0.2981 | Time: 0.9365 s
>>> Epoch [   72/10000]
train_loss: 2.1954 | train_acc: 0.2904 | val_loss: 2.1949 | val_acc: 0.2898 | test_acc: 0.2992 | Time: 0.8929 s
>>> Epoch [   73/10000]
train_loss: 2.1947 | train_acc: 0.2917 | val_loss: 2.1942 | val_acc: 0.2903 | test_acc: 0.2996 | Time: 0.8729 s
>>> Epoch [   74/10000]
train_loss: 2.1940 | train_acc: 0.2925 | val_loss: 2.1935 | val_acc: 0.2906 | test_acc: 0.3001 | Time: 0.8601 s
>>> Epoch [   75/10000]
train_loss: 2.1933 | train_acc: 0.2931 | val_loss: 2.1929 | val_acc: 0.2914 | test_acc: 0.3008 | Time: 0.8936 s
>>> Epoch [   76/10000]
train_loss: 2.1926 | train_acc: 0.2939 | val_loss: 2.1923 | val_acc: 0.2920 | test_acc: 0.3022 | Time: 0.8128 s
>>> Epoch [   77/10000]
train_loss: 2.1920 | train_acc: 0.2945 | val_loss: 2.1916 | val_acc: 0.2933 | test_acc: 0.3030 | Time: 0.8404 s
>>> Epoch [   78/10000]
train_loss: 2.1913 | train_acc: 0.2955 | val_loss: 2.1910 | val_acc: 0.2939 | test_acc: 0.3035 | Time: 0.9273 s
>>> Epoch [   79/10000]
train_loss: 2.1906 | train_acc: 0.2962 | val_loss: 2.1904 | val_acc: 0.2946 | test_acc: 0.3046 | Time: 0.8466 s
>>> Epoch [   80/10000]
train_loss: 2.1900 | train_acc: 0.2968 | val_loss: 2.1898 | val_acc: 0.2945 | test_acc: 0.3051 | Time: 0.9116 s
>>> Epoch [   81/10000]
train_loss: 2.1893 | train_acc: 0.2973 | val_loss: 2.1892 | val_acc: 0.2952 | test_acc: 0.3053 | Time: 0.8857 s
>>> Epoch [   82/10000]
train_loss: 2.1887 | train_acc: 0.2981 | val_loss: 2.1886 | val_acc: 0.2957 | test_acc: 0.3058 | Time: 0.8440 s
>>> Epoch [   83/10000]
train_loss: 2.1881 | train_acc: 0.2990 | val_loss: 2.1880 | val_acc: 0.2968 | test_acc: 0.3063 | Time: 0.9128 s
>>> Epoch [   84/10000]
train_loss: 2.1874 | train_acc: 0.3002 | val_loss: 2.1875 | val_acc: 0.2977 | test_acc: 0.3068 | Time: 0.8891 s
>>> Epoch [   85/10000]
train_loss: 2.1868 | train_acc: 0.3010 | val_loss: 2.1869 | val_acc: 0.2981 | test_acc: 0.3072 | Time: 0.9514 s
>>> Epoch [   86/10000]
train_loss: 2.1862 | train_acc: 0.3018 | val_loss: 2.1863 | val_acc: 0.2985 | test_acc: 0.3080 | Time: 0.9101 s
>>> Epoch [   87/10000]
train_loss: 2.1856 | train_acc: 0.3024 | val_loss: 2.1858 | val_acc: 0.2993 | test_acc: 0.3092 | Time: 0.9586 s
>>> Epoch [   88/10000]
train_loss: 2.1850 | train_acc: 0.3032 | val_loss: 2.1852 | val_acc: 0.3003 | test_acc: 0.3099 | Time: 0.8046 s
>>> Epoch [   89/10000]
train_loss: 2.1844 | train_acc: 0.3042 | val_loss: 2.1847 | val_acc: 0.3005 | test_acc: 0.3100 | Time: 0.8458 s
>>> Epoch [   90/10000]
train_loss: 2.1838 | train_acc: 0.3044 | val_loss: 2.1842 | val_acc: 0.3013 | test_acc: 0.3105 | Time: 0.8994 s
>>> Epoch [   91/10000]
train_loss: 2.1832 | train_acc: 0.3048 | val_loss: 2.1836 | val_acc: 0.3014 | test_acc: 0.3117 | Time: 0.9672 s
>>> Epoch [   92/10000]
train_loss: 2.1826 | train_acc: 0.3054 | val_loss: 2.1831 | val_acc: 0.3023 | test_acc: 0.3122 | Time: 0.8849 s
>>> Epoch [   93/10000]
train_loss: 2.1821 | train_acc: 0.3061 | val_loss: 2.1826 | val_acc: 0.3030 | test_acc: 0.3124 | Time: 1.0041 s
>>> Epoch [   94/10000]
train_loss: 2.1815 | train_acc: 0.3066 | val_loss: 2.1821 | val_acc: 0.3037 | test_acc: 0.3127 | Time: 0.8176 s
>>> Epoch [   95/10000]
train_loss: 2.1809 | train_acc: 0.3071 | val_loss: 2.1816 | val_acc: 0.3047 | test_acc: 0.3133 | Time: 0.8854 s
>>> Epoch [   96/10000]
train_loss: 2.1804 | train_acc: 0.3077 | val_loss: 2.1811 | val_acc: 0.3052 | test_acc: 0.3135 | Time: 0.9693 s
>>> Epoch [   97/10000]
train_loss: 2.1798 | train_acc: 0.3085 | val_loss: 2.1806 | val_acc: 0.3055 | test_acc: 0.3136 | Time: 0.8503 s
>>> Epoch [   98/10000]
train_loss: 2.1793 | train_acc: 0.3089 | val_loss: 2.1801 | val_acc: 0.3056 | test_acc: 0.3143 | Time: 0.9476 s
>>> Epoch [   99/10000]
train_loss: 2.1788 | train_acc: 0.3094 | val_loss: 2.1796 | val_acc: 0.3057 | test_acc: 0.3147 | Time: 0.9423 s
>>> Epoch [  100/10000]
train_loss: 2.1782 | train_acc: 0.3098 | val_loss: 2.1791 | val_acc: 0.3066 | test_acc: 0.3155 | Time: 0.8870 s
>>> Epoch [  101/10000]
train_loss: 2.1777 | train_acc: 0.3107 | val_loss: 2.1787 | val_acc: 0.3074 | test_acc: 0.3150 | Time: 0.9088 s
>>> Epoch [  102/10000]
train_loss: 2.1772 | train_acc: 0.3113 | val_loss: 2.1782 | val_acc: 0.3081 | test_acc: 0.3154 | Time: 0.9149 s
>>> Epoch [  103/10000]
train_loss: 2.1767 | train_acc: 0.3118 | val_loss: 2.1777 | val_acc: 0.3084 | test_acc: 0.3160 | Time: 0.8223 s
>>> Epoch [  104/10000]
train_loss: 2.1762 | train_acc: 0.3122 | val_loss: 2.1773 | val_acc: 0.3086 | test_acc: 0.3163 | Time: 0.9902 s
>>> Epoch [  105/10000]
train_loss: 2.1757 | train_acc: 0.3127 | val_loss: 2.1768 | val_acc: 0.3092 | test_acc: 0.3165 | Time: 0.9359 s
>>> Epoch [  106/10000]
train_loss: 2.1752 | train_acc: 0.3130 | val_loss: 2.1764 | val_acc: 0.3093 | test_acc: 0.3171 | Time: 0.9355 s
>>> Epoch [  107/10000]
train_loss: 2.1747 | train_acc: 0.3136 | val_loss: 2.1759 | val_acc: 0.3098 | test_acc: 0.3175 | Time: 0.9987 s
>>> Epoch [  108/10000]
train_loss: 2.1742 | train_acc: 0.3141 | val_loss: 2.1755 | val_acc: 0.3100 | test_acc: 0.3177 | Time: 0.9046 s
>>> Epoch [  109/10000]
train_loss: 2.1737 | train_acc: 0.3142 | val_loss: 2.1750 | val_acc: 0.3100 | test_acc: 0.3183 | Time: 0.9144 s
>>> Epoch [  110/10000]
train_loss: 2.1732 | train_acc: 0.3145 | val_loss: 2.1746 | val_acc: 0.3106 | test_acc: 0.3186 | Time: 0.9798 s
>>> Epoch [  111/10000]
train_loss: 2.1727 | train_acc: 0.3149 | val_loss: 2.1742 | val_acc: 0.3108 | test_acc: 0.3195 | Time: 0.9150 s
>>> Epoch [  112/10000]
train_loss: 2.1723 | train_acc: 0.3153 | val_loss: 2.1737 | val_acc: 0.3112 | test_acc: 0.3196 | Time: 0.8609 s
>>> Epoch [  113/10000]
train_loss: 2.1718 | train_acc: 0.3156 | val_loss: 2.1733 | val_acc: 0.3113 | test_acc: 0.3195 | Time: 0.8685 s
>>> Epoch [  114/10000]
train_loss: 2.1713 | train_acc: 0.3161 | val_loss: 2.1729 | val_acc: 0.3115 | test_acc: 0.3198 | Time: 1.0374 s
>>> Epoch [  115/10000]
train_loss: 2.1709 | train_acc: 0.3166 | val_loss: 2.1725 | val_acc: 0.3118 | test_acc: 0.3201 | Time: 1.0734 s
>>> Epoch [  116/10000]
train_loss: 2.1704 | train_acc: 0.3171 | val_loss: 2.1721 | val_acc: 0.3125 | test_acc: 0.3203 | Time: 1.0254 s
>>> Epoch [  117/10000]
train_loss: 2.1700 | train_acc: 0.3175 | val_loss: 2.1717 | val_acc: 0.3127 | test_acc: 0.3209 | Time: 0.9984 s
>>> Epoch [  118/10000]
train_loss: 2.1695 | train_acc: 0.3179 | val_loss: 2.1713 | val_acc: 0.3131 | test_acc: 0.3214 | Time: 0.8778 s
>>> Epoch [  119/10000]
train_loss: 2.1691 | train_acc: 0.3185 | val_loss: 2.1709 | val_acc: 0.3133 | test_acc: 0.3216 | Time: 0.9507 s
>>> Epoch [  120/10000]
train_loss: 2.1687 | train_acc: 0.3188 | val_loss: 2.1705 | val_acc: 0.3138 | test_acc: 0.3220 | Time: 0.9448 s
>>> Epoch [  121/10000]
train_loss: 2.1682 | train_acc: 0.3190 | val_loss: 2.1701 | val_acc: 0.3137 | test_acc: 0.3226 | Time: 1.0069 s
>>> Epoch [  122/10000]
train_loss: 2.1678 | train_acc: 0.3195 | val_loss: 2.1697 | val_acc: 0.3136 | test_acc: 0.3228 | Time: 1.0014 s
>>> Epoch [  123/10000]
train_loss: 2.1674 | train_acc: 0.3201 | val_loss: 2.1693 | val_acc: 0.3138 | test_acc: 0.3234 | Time: 1.0091 s
>>> Epoch [  124/10000]
train_loss: 2.1670 | train_acc: 0.3203 | val_loss: 2.1690 | val_acc: 0.3143 | test_acc: 0.3234 | Time: 0.8972 s
>>> Epoch [  125/10000]
train_loss: 2.1665 | train_acc: 0.3210 | val_loss: 2.1686 | val_acc: 0.3147 | test_acc: 0.3236 | Time: 1.0009 s
>>> Epoch [  126/10000]
train_loss: 2.1661 | train_acc: 0.3212 | val_loss: 2.1682 | val_acc: 0.3155 | test_acc: 0.3239 | Time: 1.0580 s
>>> Epoch [  127/10000]
train_loss: 2.1657 | train_acc: 0.3216 | val_loss: 2.1678 | val_acc: 0.3159 | test_acc: 0.3239 | Time: 1.0103 s
>>> Epoch [  128/10000]
train_loss: 2.1653 | train_acc: 0.3221 | val_loss: 2.1675 | val_acc: 0.3160 | test_acc: 0.3242 | Time: 0.9964 s
>>> Epoch [  129/10000]
train_loss: 2.1649 | train_acc: 0.3226 | val_loss: 2.1671 | val_acc: 0.3162 | test_acc: 0.3244 | Time: 1.0223 s
>>> Epoch [  130/10000]
train_loss: 2.1645 | train_acc: 0.3231 | val_loss: 2.1668 | val_acc: 0.3162 | test_acc: 0.3250 | Time: 0.9598 s
>>> Epoch [  131/10000]
train_loss: 2.1641 | train_acc: 0.3233 | val_loss: 2.1664 | val_acc: 0.3169 | test_acc: 0.3253 | Time: 1.0615 s
>>> Epoch [  132/10000]
train_loss: 2.1637 | train_acc: 0.3237 | val_loss: 2.1660 | val_acc: 0.3170 | test_acc: 0.3263 | Time: 0.9630 s
>>> Epoch [  133/10000]
train_loss: 2.1634 | train_acc: 0.3240 | val_loss: 2.1657 | val_acc: 0.3171 | test_acc: 0.3266 | Time: 0.8764 s
>>> Epoch [  134/10000]
train_loss: 2.1630 | train_acc: 0.3244 | val_loss: 2.1654 | val_acc: 0.3177 | test_acc: 0.3268 | Time: 1.0532 s
>>> Epoch [  135/10000]
train_loss: 2.1626 | train_acc: 0.3245 | val_loss: 2.1650 | val_acc: 0.3180 | test_acc: 0.3270 | Time: 0.9974 s
>>> Epoch [  136/10000]
train_loss: 2.1622 | train_acc: 0.3248 | val_loss: 2.1647 | val_acc: 0.3185 | test_acc: 0.3278 | Time: 0.8851 s
>>> Epoch [  137/10000]
train_loss: 2.1619 | train_acc: 0.3250 | val_loss: 2.1643 | val_acc: 0.3190 | test_acc: 0.3279 | Time: 1.0639 s
>>> Epoch [  138/10000]
train_loss: 2.1615 | train_acc: 0.3249 | val_loss: 2.1640 | val_acc: 0.3195 | test_acc: 0.3282 | Time: 1.0628 s
>>> Epoch [  139/10000]
train_loss: 2.1611 | train_acc: 0.3251 | val_loss: 2.1637 | val_acc: 0.3198 | test_acc: 0.3283 | Time: 0.9578 s
>>> Epoch [  140/10000]
train_loss: 2.1608 | train_acc: 0.3252 | val_loss: 2.1633 | val_acc: 0.3198 | test_acc: 0.3284 | Time: 1.0500 s
>>> Epoch [  141/10000]
train_loss: 2.1604 | train_acc: 0.3255 | val_loss: 2.1630 | val_acc: 0.3200 | test_acc: 0.3290 | Time: 1.0220 s
>>> Epoch [  142/10000]
train_loss: 2.1601 | train_acc: 0.3256 | val_loss: 2.1627 | val_acc: 0.3202 | test_acc: 0.3294 | Time: 1.0020 s
>>> Epoch [  143/10000]
train_loss: 2.1597 | train_acc: 0.3257 | val_loss: 2.1624 | val_acc: 0.3206 | test_acc: 0.3299 | Time: 1.0263 s
>>> Epoch [  144/10000]
train_loss: 2.1594 | train_acc: 0.3260 | val_loss: 2.1621 | val_acc: 0.3212 | test_acc: 0.3299 | Time: 0.9514 s
>>> Epoch [  145/10000]
train_loss: 2.1590 | train_acc: 0.3263 | val_loss: 2.1617 | val_acc: 0.3217 | test_acc: 0.3299 | Time: 1.0857 s
>>> Epoch [  146/10000]
train_loss: 2.1587 | train_acc: 0.3265 | val_loss: 2.1614 | val_acc: 0.3219 | test_acc: 0.3303 | Time: 1.0388 s
>>> Epoch [  147/10000]
train_loss: 2.1583 | train_acc: 0.3268 | val_loss: 2.1611 | val_acc: 0.3220 | test_acc: 0.3303 | Time: 0.9153 s
>>> Epoch [  148/10000]
train_loss: 2.1580 | train_acc: 0.3270 | val_loss: 2.1608 | val_acc: 0.3218 | test_acc: 0.3299 | Time: 1.0424 s
>>> Epoch [  149/10000]
train_loss: 2.1577 | train_acc: 0.3271 | val_loss: 2.1605 | val_acc: 0.3221 | test_acc: 0.3300 | Time: 0.9206 s
>>> Epoch [  150/10000]
train_loss: 2.1573 | train_acc: 0.3272 | val_loss: 2.1602 | val_acc: 0.3226 | test_acc: 0.3299 | Time: 1.0645 s
>>> Epoch [  151/10000]
train_loss: 2.1570 | train_acc: 0.3276 | val_loss: 2.1599 | val_acc: 0.3229 | test_acc: 0.3303 | Time: 1.0367 s
>>> Epoch [  152/10000]
train_loss: 2.1567 | train_acc: 0.3279 | val_loss: 2.1596 | val_acc: 0.3230 | test_acc: 0.3305 | Time: 0.9516 s
>>> Epoch [  153/10000]
train_loss: 2.1563 | train_acc: 0.3281 | val_loss: 2.1593 | val_acc: 0.3232 | test_acc: 0.3306 | Time: 0.9424 s
>>> Epoch [  154/10000]
train_loss: 2.1560 | train_acc: 0.3286 | val_loss: 2.1590 | val_acc: 0.3233 | test_acc: 0.3310 | Time: 1.1100 s
>>> Epoch [  155/10000]
train_loss: 2.1557 | train_acc: 0.3288 | val_loss: 2.1587 | val_acc: 0.3234 | test_acc: 0.3309 | Time: 0.9626 s
>>> Epoch [  156/10000]
train_loss: 2.1554 | train_acc: 0.3291 | val_loss: 2.1584 | val_acc: 0.3237 | test_acc: 0.3312 | Time: 0.9714 s
>>> Epoch [  157/10000]
train_loss: 2.1551 | train_acc: 0.3294 | val_loss: 2.1582 | val_acc: 0.3239 | test_acc: 0.3315 | Time: 1.0273 s
>>> Epoch [  158/10000]
train_loss: 2.1548 | train_acc: 0.3296 | val_loss: 2.1579 | val_acc: 0.3243 | test_acc: 0.3316 | Time: 1.0125 s
>>> Epoch [  159/10000]
train_loss: 2.1545 | train_acc: 0.3299 | val_loss: 2.1576 | val_acc: 0.3246 | test_acc: 0.3314 | Time: 1.0804 s
>>> Epoch [  160/10000]
train_loss: 2.1542 | train_acc: 0.3303 | val_loss: 2.1573 | val_acc: 0.3246 | test_acc: 0.3315 | Time: 1.0469 s
>>> Epoch [  161/10000]
train_loss: 2.1539 | train_acc: 0.3306 | val_loss: 2.1570 | val_acc: 0.3245 | test_acc: 0.3318 | Time: 1.0837 s
>>> Epoch [  162/10000]
train_loss: 2.1536 | train_acc: 0.3309 | val_loss: 2.1568 | val_acc: 0.3249 | test_acc: 0.3316 | Time: 1.0752 s
>>> Epoch [  163/10000]
train_loss: 2.1533 | train_acc: 0.3311 | val_loss: 2.1565 | val_acc: 0.3256 | test_acc: 0.3319 | Time: 1.0578 s
>>> Epoch [  164/10000]
train_loss: 2.1530 | train_acc: 0.3311 | val_loss: 2.1562 | val_acc: 0.3256 | test_acc: 0.3327 | Time: 1.0323 s
>>> Epoch [  165/10000]
train_loss: 2.1527 | train_acc: 0.3314 | val_loss: 2.1560 | val_acc: 0.3261 | test_acc: 0.3331 | Time: 1.1841 s
>>> Epoch [  166/10000]
train_loss: 2.1524 | train_acc: 0.3315 | val_loss: 2.1557 | val_acc: 0.3264 | test_acc: 0.3331 | Time: 1.0645 s
>>> Epoch [  167/10000]
train_loss: 2.1521 | train_acc: 0.3318 | val_loss: 2.1554 | val_acc: 0.3264 | test_acc: 0.3334 | Time: 1.0520 s
>>> Epoch [  168/10000]
train_loss: 2.1518 | train_acc: 0.3319 | val_loss: 2.1552 | val_acc: 0.3264 | test_acc: 0.3336 | Time: 1.0136 s
>>> Epoch [  169/10000]
train_loss: 2.1515 | train_acc: 0.3321 | val_loss: 2.1549 | val_acc: 0.3268 | test_acc: 0.3340 | Time: 1.1093 s
>>> Epoch [  170/10000]
train_loss: 2.1512 | train_acc: 0.3322 | val_loss: 2.1547 | val_acc: 0.3271 | test_acc: 0.3340 | Time: 1.0844 s
>>> Epoch [  171/10000]
train_loss: 2.1510 | train_acc: 0.3326 | val_loss: 2.1544 | val_acc: 0.3277 | test_acc: 0.3341 | Time: 1.1460 s
>>> Epoch [  172/10000]
train_loss: 2.1507 | train_acc: 0.3328 | val_loss: 2.1541 | val_acc: 0.3276 | test_acc: 0.3343 | Time: 1.0823 s
>>> Epoch [  173/10000]
train_loss: 2.1504 | train_acc: 0.3331 | val_loss: 2.1539 | val_acc: 0.3281 | test_acc: 0.3346 | Time: 1.1165 s
>>> Epoch [  174/10000]
train_loss: 2.1501 | train_acc: 0.3334 | val_loss: 2.1536 | val_acc: 0.3283 | test_acc: 0.3352 | Time: 1.1659 s
>>> Epoch [  175/10000]
train_loss: 2.1499 | train_acc: 0.3335 | val_loss: 2.1534 | val_acc: 0.3287 | test_acc: 0.3354 | Time: 1.0037 s
>>> Epoch [  176/10000]
train_loss: 2.1496 | train_acc: 0.3338 | val_loss: 2.1531 | val_acc: 0.3290 | test_acc: 0.3361 | Time: 1.1013 s
>>> Epoch [  177/10000]
train_loss: 2.1493 | train_acc: 0.3338 | val_loss: 2.1529 | val_acc: 0.3293 | test_acc: 0.3362 | Time: 1.0372 s
>>> Epoch [  178/10000]
train_loss: 2.1491 | train_acc: 0.3338 | val_loss: 2.1527 | val_acc: 0.3294 | test_acc: 0.3364 | Time: 1.0720 s
>>> Epoch [  179/10000]
train_loss: 2.1488 | train_acc: 0.3341 | val_loss: 2.1524 | val_acc: 0.3298 | test_acc: 0.3366 | Time: 1.2508 s
>>> Epoch [  180/10000]
train_loss: 2.1485 | train_acc: 0.3343 | val_loss: 2.1522 | val_acc: 0.3299 | test_acc: 0.3368 | Time: 1.0641 s
>>> Epoch [  181/10000]
train_loss: 2.1483 | train_acc: 0.3346 | val_loss: 2.1519 | val_acc: 0.3301 | test_acc: 0.3367 | Time: 1.2009 s
>>> Epoch [  182/10000]
train_loss: 2.1480 | train_acc: 0.3348 | val_loss: 2.1517 | val_acc: 0.3303 | test_acc: 0.3371 | Time: 1.1321 s
>>> Epoch [  183/10000]
train_loss: 2.1478 | train_acc: 0.3351 | val_loss: 2.1515 | val_acc: 0.3308 | test_acc: 0.3373 | Time: 1.0912 s
>>> Epoch [  184/10000]
train_loss: 2.1475 | train_acc: 0.3353 | val_loss: 2.1512 | val_acc: 0.3307 | test_acc: 0.3375 | Time: 1.1862 s
>>> Epoch [  185/10000]
train_loss: 2.1473 | train_acc: 0.3356 | val_loss: 2.1510 | val_acc: 0.3310 | test_acc: 0.3376 | Time: 1.1236 s
>>> Epoch [  186/10000]
train_loss: 2.1470 | train_acc: 0.3359 | val_loss: 2.1508 | val_acc: 0.3312 | test_acc: 0.3376 | Time: 1.1532 s
>>> Epoch [  187/10000]
train_loss: 2.1468 | train_acc: 0.3361 | val_loss: 2.1505 | val_acc: 0.3315 | test_acc: 0.3374 | Time: 1.1235 s
>>> Epoch [  188/10000]
train_loss: 2.1465 | train_acc: 0.3363 | val_loss: 2.1503 | val_acc: 0.3317 | test_acc: 0.3375 | Time: 0.9901 s
>>> Epoch [  189/10000]
train_loss: 2.1463 | train_acc: 0.3365 | val_loss: 2.1501 | val_acc: 0.3319 | test_acc: 0.3376 | Time: 1.1735 s
>>> Epoch [  190/10000]
train_loss: 2.1460 | train_acc: 0.3368 | val_loss: 2.1499 | val_acc: 0.3322 | test_acc: 0.3381 | Time: 1.1650 s
>>> Epoch [  191/10000]
train_loss: 2.1458 | train_acc: 0.3371 | val_loss: 2.1496 | val_acc: 0.3323 | test_acc: 0.3384 | Time: 1.2062 s
>>> Epoch [  192/10000]
train_loss: 2.1455 | train_acc: 0.3374 | val_loss: 2.1494 | val_acc: 0.3322 | test_acc: 0.3383 | Time: 1.0414 s
>>> Epoch [  193/10000]
train_loss: 2.1453 | train_acc: 0.3375 | val_loss: 2.1492 | val_acc: 0.3322 | test_acc: 0.3384 | Time: 1.0868 s
>>> Epoch [  194/10000]
train_loss: 2.1451 | train_acc: 0.3378 | val_loss: 2.1490 | val_acc: 0.3325 | test_acc: 0.3386 | Time: 0.9376 s
>>> Epoch [  195/10000]
train_loss: 2.1448 | train_acc: 0.3380 | val_loss: 2.1488 | val_acc: 0.3325 | test_acc: 0.3387 | Time: 0.9612 s
>>> Epoch [  196/10000]
train_loss: 2.1446 | train_acc: 0.3382 | val_loss: 2.1486 | val_acc: 0.3325 | test_acc: 0.3389 | Time: 1.0040 s
>>> Epoch [  197/10000]
train_loss: 2.1444 | train_acc: 0.3383 | val_loss: 2.1483 | val_acc: 0.3323 | test_acc: 0.3391 | Time: 1.0620 s
>>> Epoch [  198/10000]
train_loss: 2.1441 | train_acc: 0.3386 | val_loss: 2.1481 | val_acc: 0.3323 | test_acc: 0.3391 | Time: 1.7380 s
>>> Epoch [  199/10000]
train_loss: 2.1439 | train_acc: 0.3389 | val_loss: 2.1479 | val_acc: 0.3323 | test_acc: 0.3394 | Time: 1.8962 s
>>> Epoch [  200/10000]
train_loss: 2.1437 | train_acc: 0.3390 | val_loss: 2.1477 | val_acc: 0.3323 | test_acc: 0.3399 | Time: 1.7246 s
>>> Epoch [  201/10000]
train_loss: 2.1435 | train_acc: 0.3391 | val_loss: 2.1475 | val_acc: 0.3324 | test_acc: 0.3399 | Time: 1.8892 s
>>> Epoch [  202/10000]
train_loss: 2.1432 | train_acc: 0.3393 | val_loss: 2.1473 | val_acc: 0.3323 | test_acc: 0.3401 | Time: 1.6702 s
>>> Epoch [  203/10000]
train_loss: 2.1430 | train_acc: 0.3394 | val_loss: 2.1471 | val_acc: 0.3328 | test_acc: 0.3407 | Time: 1.8444 s
>>> Epoch [  204/10000]
train_loss: 2.1428 | train_acc: 0.3395 | val_loss: 2.1469 | val_acc: 0.3332 | test_acc: 0.3410 | Time: 1.4379 s
>>> Epoch [  205/10000]
train_loss: 2.1426 | train_acc: 0.3399 | val_loss: 2.1467 | val_acc: 0.3334 | test_acc: 0.3411 | Time: 1.7663 s
>>> Epoch [  206/10000]
train_loss: 2.1424 | train_acc: 0.3399 | val_loss: 2.1465 | val_acc: 0.3334 | test_acc: 0.3409 | Time: 1.3330 s
>>> Epoch [  207/10000]
train_loss: 2.1421 | train_acc: 0.3401 | val_loss: 2.1463 | val_acc: 0.3333 | test_acc: 0.3410 | Time: 1.7456 s
>>> Epoch [  208/10000]
train_loss: 2.1419 | train_acc: 0.3399 | val_loss: 2.1461 | val_acc: 0.3332 | test_acc: 0.3414 | Time: 1.6026 s
>>> Epoch [  209/10000]
train_loss: 2.1417 | train_acc: 0.3403 | val_loss: 2.1459 | val_acc: 0.3335 | test_acc: 0.3412 | Time: 1.7238 s
>>> Epoch [  210/10000]
train_loss: 2.1415 | train_acc: 0.3406 | val_loss: 2.1457 | val_acc: 0.3336 | test_acc: 0.3413 | Time: 1.0315 s
>>> Epoch [  211/10000]
train_loss: 2.1413 | train_acc: 0.3408 | val_loss: 2.1455 | val_acc: 0.3336 | test_acc: 0.3417 | Time: 1.8145 s
>>> Epoch [  212/10000]
train_loss: 2.1411 | train_acc: 0.3409 | val_loss: 2.1453 | val_acc: 0.3338 | test_acc: 0.3421 | Time: 1.7781 s
>>> Epoch [  213/10000]
train_loss: 2.1409 | train_acc: 0.3410 | val_loss: 2.1451 | val_acc: 0.3340 | test_acc: 0.3423 | Time: 1.7468 s
>>> Epoch [  214/10000]
train_loss: 2.1407 | train_acc: 0.3411 | val_loss: 2.1449 | val_acc: 0.3345 | test_acc: 0.3426 | Time: 1.8813 s
>>> Epoch [  215/10000]
train_loss: 2.1404 | train_acc: 0.3414 | val_loss: 2.1447 | val_acc: 0.3342 | test_acc: 0.3430 | Time: 1.8381 s
>>> Epoch [  216/10000]
train_loss: 2.1402 | train_acc: 0.3416 | val_loss: 2.1445 | val_acc: 0.3344 | test_acc: 0.3431 | Time: 1.8167 s
>>> Epoch [  217/10000]
train_loss: 2.1400 | train_acc: 0.3417 | val_loss: 2.1444 | val_acc: 0.3347 | test_acc: 0.3435 | Time: 1.7213 s
>>> Epoch [  218/10000]
train_loss: 2.1398 | train_acc: 0.3419 | val_loss: 2.1442 | val_acc: 0.3352 | test_acc: 0.3438 | Time: 1.8289 s
>>> Epoch [  219/10000]
train_loss: 2.1396 | train_acc: 0.3422 | val_loss: 2.1440 | val_acc: 0.3353 | test_acc: 0.3439 | Time: 1.7632 s
>>> Epoch [  220/10000]
train_loss: 2.1394 | train_acc: 0.3422 | val_loss: 2.1438 | val_acc: 0.3355 | test_acc: 0.3438 | Time: 1.7043 s
>>> Epoch [  221/10000]
train_loss: 2.1392 | train_acc: 0.3424 | val_loss: 2.1436 | val_acc: 0.3357 | test_acc: 0.3438 | Time: 1.7699 s
>>> Epoch [  222/10000]
train_loss: 2.1390 | train_acc: 0.3425 | val_loss: 2.1434 | val_acc: 0.3356 | test_acc: 0.3438 | Time: 1.5726 s
>>> Epoch [  223/10000]
train_loss: 2.1388 | train_acc: 0.3426 | val_loss: 2.1433 | val_acc: 0.3367 | test_acc: 0.3440 | Time: 1.0755 s
>>> Epoch [  224/10000]
train_loss: 2.1387 | train_acc: 0.3428 | val_loss: 2.1431 | val_acc: 0.3368 | test_acc: 0.3445 | Time: 1.1176 s
>>> Epoch [  225/10000]
train_loss: 2.1385 | train_acc: 0.3430 | val_loss: 2.1429 | val_acc: 0.3371 | test_acc: 0.3446 | Time: 1.0232 s
>>> Epoch [  226/10000]
train_loss: 2.1383 | train_acc: 0.3431 | val_loss: 2.1427 | val_acc: 0.3374 | test_acc: 0.3446 | Time: 1.0277 s
>>> Epoch [  227/10000]
train_loss: 2.1381 | train_acc: 0.3434 | val_loss: 2.1426 | val_acc: 0.3376 | test_acc: 0.3452 | Time: 1.0360 s
>>> Epoch [  228/10000]
train_loss: 2.1379 | train_acc: 0.3436 | val_loss: 2.1424 | val_acc: 0.3376 | test_acc: 0.3455 | Time: 1.0587 s
>>> Epoch [  229/10000]
train_loss: 2.1377 | train_acc: 0.3437 | val_loss: 2.1422 | val_acc: 0.3377 | test_acc: 0.3456 | Time: 1.0382 s
>>> Epoch [  230/10000]
train_loss: 2.1375 | train_acc: 0.3441 | val_loss: 2.1420 | val_acc: 0.3380 | test_acc: 0.3455 | Time: 1.0349 s
>>> Epoch [  231/10000]
train_loss: 2.1373 | train_acc: 0.3445 | val_loss: 2.1419 | val_acc: 0.3387 | test_acc: 0.3458 | Time: 1.1516 s
>>> Epoch [  232/10000]
train_loss: 2.1371 | train_acc: 0.3447 | val_loss: 2.1417 | val_acc: 0.3388 | test_acc: 0.3463 | Time: 1.0232 s
>>> Epoch [  233/10000]
train_loss: 2.1370 | train_acc: 0.3449 | val_loss: 2.1415 | val_acc: 0.3389 | test_acc: 0.3467 | Time: 1.2630 s
>>> Epoch [  234/10000]
train_loss: 2.1368 | train_acc: 0.3452 | val_loss: 2.1414 | val_acc: 0.3389 | test_acc: 0.3468 | Time: 1.1781 s
>>> Epoch [  235/10000]
train_loss: 2.1366 | train_acc: 0.3454 | val_loss: 2.1412 | val_acc: 0.3390 | test_acc: 0.3467 | Time: 1.1903 s
>>> Epoch [  236/10000]
train_loss: 2.1364 | train_acc: 0.3455 | val_loss: 2.1410 | val_acc: 0.3389 | test_acc: 0.3469 | Time: 1.1343 s
>>> Epoch [  237/10000]
train_loss: 2.1362 | train_acc: 0.3455 | val_loss: 2.1409 | val_acc: 0.3389 | test_acc: 0.3469 | Time: 1.2062 s
>>> Epoch [  238/10000]
train_loss: 2.1360 | train_acc: 0.3458 | val_loss: 2.1407 | val_acc: 0.3388 | test_acc: 0.3471 | Time: 1.1900 s
>>> Epoch [  239/10000]
train_loss: 2.1359 | train_acc: 0.3458 | val_loss: 2.1405 | val_acc: 0.3392 | test_acc: 0.3472 | Time: 1.1502 s
>>> Epoch [  240/10000]
train_loss: 2.1357 | train_acc: 0.3458 | val_loss: 2.1404 | val_acc: 0.3394 | test_acc: 0.3475 | Time: 1.0684 s
>>> Epoch [  241/10000]
train_loss: 2.1355 | train_acc: 0.3463 | val_loss: 2.1402 | val_acc: 0.3396 | test_acc: 0.3472 | Time: 1.1937 s
>>> Epoch [  242/10000]
train_loss: 2.1353 | train_acc: 0.3464 | val_loss: 2.1400 | val_acc: 0.3395 | test_acc: 0.3471 | Time: 1.2281 s
>>> Epoch [  243/10000]
train_loss: 2.1352 | train_acc: 0.3466 | val_loss: 2.1399 | val_acc: 0.3398 | test_acc: 0.3472 | Time: 1.1022 s
>>> Epoch [  244/10000]
train_loss: 2.1350 | train_acc: 0.3466 | val_loss: 2.1397 | val_acc: 0.3397 | test_acc: 0.3472 | Time: 1.1582 s
>>> Epoch [  245/10000]
train_loss: 2.1348 | train_acc: 0.3468 | val_loss: 2.1396 | val_acc: 0.3396 | test_acc: 0.3470 | Time: 1.1908 s
>>> Epoch [  246/10000]
train_loss: 2.1347 | train_acc: 0.3471 | val_loss: 2.1394 | val_acc: 0.3398 | test_acc: 0.3473 | Time: 1.1227 s
>>> Epoch [  247/10000]
train_loss: 2.1345 | train_acc: 0.3473 | val_loss: 2.1393 | val_acc: 0.3401 | test_acc: 0.3474 | Time: 1.1969 s
>>> Epoch [  248/10000]
train_loss: 2.1343 | train_acc: 0.3475 | val_loss: 2.1391 | val_acc: 0.3402 | test_acc: 0.3475 | Time: 1.1475 s
>>> Epoch [  249/10000]
train_loss: 2.1341 | train_acc: 0.3476 | val_loss: 2.1389 | val_acc: 0.3403 | test_acc: 0.3478 | Time: 1.1897 s
>>> Epoch [  250/10000]
train_loss: 2.1340 | train_acc: 0.3478 | val_loss: 2.1388 | val_acc: 0.3402 | test_acc: 0.3478 | Time: 1.2144 s
>>> Epoch [  251/10000]
train_loss: 2.1338 | train_acc: 0.3479 | val_loss: 2.1386 | val_acc: 0.3405 | test_acc: 0.3479 | Time: 1.2386 s
>>> Epoch [  252/10000]
train_loss: 2.1337 | train_acc: 0.3481 | val_loss: 2.1385 | val_acc: 0.3407 | test_acc: 0.3482 | Time: 1.2572 s
>>> Epoch [  253/10000]
train_loss: 2.1335 | train_acc: 0.3482 | val_loss: 2.1383 | val_acc: 0.3409 | test_acc: 0.3480 | Time: 1.2125 s
>>> Epoch [  254/10000]
train_loss: 2.1333 | train_acc: 0.3482 | val_loss: 2.1382 | val_acc: 0.3409 | test_acc: 0.3481 | Time: 1.2105 s
>>> Epoch [  255/10000]
train_loss: 2.1332 | train_acc: 0.3484 | val_loss: 2.1380 | val_acc: 0.3408 | test_acc: 0.3483 | Time: 1.1775 s
>>> Epoch [  256/10000]
train_loss: 2.1330 | train_acc: 0.3484 | val_loss: 2.1379 | val_acc: 0.3410 | test_acc: 0.3484 | Time: 1.2515 s
>>> Epoch [  257/10000]
train_loss: 2.1328 | train_acc: 0.3484 | val_loss: 2.1377 | val_acc: 0.3412 | test_acc: 0.3486 | Time: 1.2675 s
>>> Epoch [  258/10000]
train_loss: 2.1327 | train_acc: 0.3486 | val_loss: 2.1376 | val_acc: 0.3411 | test_acc: 0.3485 | Time: 1.2127 s
>>> Epoch [  259/10000]
train_loss: 2.1325 | train_acc: 0.3488 | val_loss: 2.1375 | val_acc: 0.3410 | test_acc: 0.3484 | Time: 1.2219 s
>>> Epoch [  260/10000]
train_loss: 2.1324 | train_acc: 0.3487 | val_loss: 2.1373 | val_acc: 0.3413 | test_acc: 0.3487 | Time: 1.1275 s
>>> Epoch [  261/10000]
train_loss: 2.1322 | train_acc: 0.3489 | val_loss: 2.1372 | val_acc: 0.3413 | test_acc: 0.3490 | Time: 1.2799 s
>>> Epoch [  262/10000]
train_loss: 2.1321 | train_acc: 0.3491 | val_loss: 2.1370 | val_acc: 0.3412 | test_acc: 0.3491 | Time: 1.3096 s
>>> Epoch [  263/10000]
train_loss: 2.1319 | train_acc: 0.3491 | val_loss: 2.1369 | val_acc: 0.3414 | test_acc: 0.3493 | Time: 1.2404 s
>>> Epoch [  264/10000]
train_loss: 2.1317 | train_acc: 0.3492 | val_loss: 2.1367 | val_acc: 0.3415 | test_acc: 0.3498 | Time: 1.2497 s
>>> Epoch [  265/10000]
train_loss: 2.1316 | train_acc: 0.3493 | val_loss: 2.1366 | val_acc: 0.3415 | test_acc: 0.3496 | Time: 1.3339 s
>>> Epoch [  266/10000]
train_loss: 2.1314 | train_acc: 0.3494 | val_loss: 2.1365 | val_acc: 0.3415 | test_acc: 0.3498 | Time: 1.2799 s
>>> Epoch [  267/10000]
train_loss: 2.1313 | train_acc: 0.3493 | val_loss: 2.1363 | val_acc: 0.3416 | test_acc: 0.3499 | Time: 1.3488 s
>>> Epoch [  268/10000]
train_loss: 2.1311 | train_acc: 0.3494 | val_loss: 2.1362 | val_acc: 0.3417 | test_acc: 0.3499 | Time: 1.1828 s
>>> Epoch [  269/10000]
train_loss: 2.1310 | train_acc: 0.3495 | val_loss: 2.1360 | val_acc: 0.3418 | test_acc: 0.3499 | Time: 1.2014 s
>>> Epoch [  270/10000]
train_loss: 2.1308 | train_acc: 0.3495 | val_loss: 2.1359 | val_acc: 0.3419 | test_acc: 0.3501 | Time: 1.2620 s
>>> Epoch [  271/10000]
train_loss: 2.1307 | train_acc: 0.3497 | val_loss: 2.1358 | val_acc: 0.3419 | test_acc: 0.3502 | Time: 1.2457 s
>>> Epoch [  272/10000]
train_loss: 2.1305 | train_acc: 0.3498 | val_loss: 2.1356 | val_acc: 0.3421 | test_acc: 0.3505 | Time: 1.3066 s
>>> Epoch [  273/10000]
train_loss: 2.1304 | train_acc: 0.3501 | val_loss: 2.1355 | val_acc: 0.3421 | test_acc: 0.3506 | Time: 1.2799 s
>>> Epoch [  274/10000]
train_loss: 2.1302 | train_acc: 0.3502 | val_loss: 2.1354 | val_acc: 0.3423 | test_acc: 0.3508 | Time: 1.3540 s
>>> Epoch [  275/10000]
train_loss: 2.1301 | train_acc: 0.3503 | val_loss: 2.1352 | val_acc: 0.3426 | test_acc: 0.3511 | Time: 1.2026 s
>>> Epoch [  276/10000]
train_loss: 2.1300 | train_acc: 0.3505 | val_loss: 2.1351 | val_acc: 0.3426 | test_acc: 0.3515 | Time: 1.3627 s
>>> Epoch [  277/10000]
train_loss: 2.1298 | train_acc: 0.3506 | val_loss: 2.1350 | val_acc: 0.3427 | test_acc: 0.3516 | Time: 1.3666 s
>>> Epoch [  278/10000]
train_loss: 2.1297 | train_acc: 0.3508 | val_loss: 2.1348 | val_acc: 0.3426 | test_acc: 0.3520 | Time: 1.1625 s
>>> Epoch [  279/10000]
train_loss: 2.1295 | train_acc: 0.3509 | val_loss: 2.1347 | val_acc: 0.3428 | test_acc: 0.3520 | Time: 1.3348 s
>>> Epoch [  280/10000]
train_loss: 2.1294 | train_acc: 0.3509 | val_loss: 2.1346 | val_acc: 0.3430 | test_acc: 0.3520 | Time: 1.2426 s
>>> Epoch [  281/10000]
train_loss: 2.1292 | train_acc: 0.3511 | val_loss: 2.1344 | val_acc: 0.3432 | test_acc: 0.3526 | Time: 1.3334 s
>>> Epoch [  282/10000]
train_loss: 2.1291 | train_acc: 0.3512 | val_loss: 2.1343 | val_acc: 0.3433 | test_acc: 0.3526 | Time: 1.3651 s
>>> Epoch [  283/10000]
train_loss: 2.1290 | train_acc: 0.3514 | val_loss: 2.1342 | val_acc: 0.3435 | test_acc: 0.3528 | Time: 1.3353 s
>>> Epoch [  284/10000]
train_loss: 2.1288 | train_acc: 0.3514 | val_loss: 2.1341 | val_acc: 0.3436 | test_acc: 0.3528 | Time: 1.1948 s
>>> Epoch [  285/10000]
train_loss: 2.1287 | train_acc: 0.3515 | val_loss: 2.1339 | val_acc: 0.3437 | test_acc: 0.3530 | Time: 1.4964 s
>>> Epoch [  286/10000]
train_loss: 2.1285 | train_acc: 0.3516 | val_loss: 2.1338 | val_acc: 0.3439 | test_acc: 0.3530 | Time: 1.3368 s
>>> Epoch [  287/10000]
train_loss: 2.1284 | train_acc: 0.3518 | val_loss: 2.1337 | val_acc: 0.3443 | test_acc: 0.3531 | Time: 1.2773 s
>>> Epoch [  288/10000]
train_loss: 2.1283 | train_acc: 0.3518 | val_loss: 2.1336 | val_acc: 0.3444 | test_acc: 0.3534 | Time: 1.2754 s
>>> Epoch [  289/10000]
train_loss: 2.1281 | train_acc: 0.3518 | val_loss: 2.1334 | val_acc: 0.3444 | test_acc: 0.3536 | Time: 1.4325 s
>>> Epoch [  290/10000]
train_loss: 2.1280 | train_acc: 0.3520 | val_loss: 2.1333 | val_acc: 0.3445 | test_acc: 0.3539 | Time: 1.2231 s
>>> Epoch [  291/10000]
train_loss: 2.1279 | train_acc: 0.3521 | val_loss: 2.1332 | val_acc: 0.3446 | test_acc: 0.3542 | Time: 1.3300 s
>>> Epoch [  292/10000]
train_loss: 2.1277 | train_acc: 0.3523 | val_loss: 2.1331 | val_acc: 0.3449 | test_acc: 0.3542 | Time: 1.3680 s
>>> Epoch [  293/10000]
train_loss: 2.1276 | train_acc: 0.3524 | val_loss: 2.1329 | val_acc: 0.3451 | test_acc: 0.3544 | Time: 1.3575 s
>>> Epoch [  294/10000]
train_loss: 2.1275 | train_acc: 0.3525 | val_loss: 2.1328 | val_acc: 0.3453 | test_acc: 0.3548 | Time: 1.3474 s
>>> Epoch [  295/10000]
train_loss: 2.1273 | train_acc: 0.3525 | val_loss: 2.1327 | val_acc: 0.3454 | test_acc: 0.3553 | Time: 1.3541 s
>>> Epoch [  296/10000]
train_loss: 2.1272 | train_acc: 0.3525 | val_loss: 2.1326 | val_acc: 0.3457 | test_acc: 0.3557 | Time: 1.1535 s
>>> Epoch [  297/10000]
train_loss: 2.1271 | train_acc: 0.3527 | val_loss: 2.1325 | val_acc: 0.3457 | test_acc: 0.3558 | Time: 1.3353 s
>>> Epoch [  298/10000]
train_loss: 2.1269 | train_acc: 0.3527 | val_loss: 2.1323 | val_acc: 0.3457 | test_acc: 0.3560 | Time: 1.3087 s
>>> Epoch [  299/10000]
train_loss: 2.1268 | train_acc: 0.3529 | val_loss: 2.1322 | val_acc: 0.3456 | test_acc: 0.3558 | Time: 1.4176 s
>>> Epoch [  300/10000]
train_loss: 2.1267 | train_acc: 0.3531 | val_loss: 2.1321 | val_acc: 0.3460 | test_acc: 0.3559 | Time: 1.2779 s
>>> Epoch [  301/10000]
train_loss: 2.1266 | train_acc: 0.3533 | val_loss: 2.1320 | val_acc: 0.3461 | test_acc: 0.3559 | Time: 1.3909 s
>>> Epoch [  302/10000]
train_loss: 2.1264 | train_acc: 0.3534 | val_loss: 2.1319 | val_acc: 0.3461 | test_acc: 0.3561 | Time: 1.3337 s
>>> Epoch [  303/10000]
train_loss: 2.1263 | train_acc: 0.3535 | val_loss: 2.1317 | val_acc: 0.3462 | test_acc: 0.3562 | Time: 1.4516 s
>>> Epoch [  304/10000]
train_loss: 2.1262 | train_acc: 0.3538 | val_loss: 2.1316 | val_acc: 0.3462 | test_acc: 0.3562 | Time: 1.3042 s
>>> Epoch [  305/10000]
train_loss: 2.1260 | train_acc: 0.3538 | val_loss: 2.1315 | val_acc: 0.3463 | test_acc: 0.3560 | Time: 1.3849 s
>>> Epoch [  306/10000]
train_loss: 2.1259 | train_acc: 0.3539 | val_loss: 2.1314 | val_acc: 0.3463 | test_acc: 0.3563 | Time: 1.2571 s
>>> Epoch [  307/10000]
train_loss: 2.1258 | train_acc: 0.3539 | val_loss: 2.1313 | val_acc: 0.3465 | test_acc: 0.3564 | Time: 1.4182 s
>>> Epoch [  308/10000]
train_loss: 2.1257 | train_acc: 0.3540 | val_loss: 2.1312 | val_acc: 0.3469 | test_acc: 0.3564 | Time: 1.3137 s
>>> Epoch [  309/10000]
train_loss: 2.1255 | train_acc: 0.3540 | val_loss: 2.1311 | val_acc: 0.3468 | test_acc: 0.3565 | Time: 1.4141 s
>>> Epoch [  310/10000]
train_loss: 2.1254 | train_acc: 0.3542 | val_loss: 2.1309 | val_acc: 0.3471 | test_acc: 0.3567 | Time: 1.2881 s
>>> Epoch [  311/10000]
train_loss: 2.1253 | train_acc: 0.3544 | val_loss: 2.1308 | val_acc: 0.3469 | test_acc: 0.3568 | Time: 1.4051 s
>>> Epoch [  312/10000]
train_loss: 2.1252 | train_acc: 0.3544 | val_loss: 2.1307 | val_acc: 0.3471 | test_acc: 0.3570 | Time: 1.3331 s
>>> Epoch [  313/10000]
train_loss: 2.1251 | train_acc: 0.3545 | val_loss: 2.1306 | val_acc: 0.3473 | test_acc: 0.3571 | Time: 1.3054 s
>>> Epoch [  314/10000]
train_loss: 2.1249 | train_acc: 0.3546 | val_loss: 2.1305 | val_acc: 0.3472 | test_acc: 0.3571 | Time: 1.4215 s
>>> Epoch [  315/10000]
train_loss: 2.1248 | train_acc: 0.3548 | val_loss: 2.1304 | val_acc: 0.3472 | test_acc: 0.3570 | Time: 1.4377 s
>>> Epoch [  316/10000]
train_loss: 2.1247 | train_acc: 0.3548 | val_loss: 2.1303 | val_acc: 0.3471 | test_acc: 0.3569 | Time: 1.4495 s
>>> Epoch [  317/10000]
train_loss: 2.1246 | train_acc: 0.3548 | val_loss: 2.1302 | val_acc: 0.3472 | test_acc: 0.3571 | Time: 1.3049 s
>>> Epoch [  318/10000]
train_loss: 2.1244 | train_acc: 0.3551 | val_loss: 2.1301 | val_acc: 0.3474 | test_acc: 0.3570 | Time: 1.3334 s
>>> Epoch [  319/10000]
train_loss: 2.1243 | train_acc: 0.3551 | val_loss: 2.1300 | val_acc: 0.3475 | test_acc: 0.3569 | Time: 1.3698 s
>>> Epoch [  320/10000]
train_loss: 2.1242 | train_acc: 0.3552 | val_loss: 2.1298 | val_acc: 0.3477 | test_acc: 0.3567 | Time: 1.2671 s
>>> Epoch [  321/10000]
train_loss: 2.1241 | train_acc: 0.3553 | val_loss: 2.1297 | val_acc: 0.3478 | test_acc: 0.3569 | Time: 1.4157 s
>>> Epoch [  322/10000]
train_loss: 2.1240 | train_acc: 0.3554 | val_loss: 2.1296 | val_acc: 0.3479 | test_acc: 0.3572 | Time: 1.2443 s
>>> Epoch [  323/10000]
train_loss: 2.1239 | train_acc: 0.3553 | val_loss: 2.1295 | val_acc: 0.3483 | test_acc: 0.3573 | Time: 1.4819 s
>>> Epoch [  324/10000]
train_loss: 2.1237 | train_acc: 0.3554 | val_loss: 2.1294 | val_acc: 0.3483 | test_acc: 0.3572 | Time: 1.3379 s
>>> Epoch [  325/10000]
train_loss: 2.1236 | train_acc: 0.3554 | val_loss: 2.1293 | val_acc: 0.3487 | test_acc: 0.3573 | Time: 1.2897 s
>>> Epoch [  326/10000]
train_loss: 2.1235 | train_acc: 0.3555 | val_loss: 2.1292 | val_acc: 0.3490 | test_acc: 0.3576 | Time: 1.4219 s
>>> Epoch [  327/10000]
train_loss: 2.1234 | train_acc: 0.3557 | val_loss: 2.1291 | val_acc: 0.3491 | test_acc: 0.3578 | Time: 1.3148 s
>>> Epoch [  328/10000]
train_loss: 2.1233 | train_acc: 0.3558 | val_loss: 2.1290 | val_acc: 0.3494 | test_acc: 0.3578 | Time: 1.2702 s
>>> Epoch [  329/10000]
train_loss: 2.1232 | train_acc: 0.3559 | val_loss: 2.1289 | val_acc: 0.3496 | test_acc: 0.3578 | Time: 1.4027 s
>>> Epoch [  330/10000]
train_loss: 2.1230 | train_acc: 0.3560 | val_loss: 2.1288 | val_acc: 0.3496 | test_acc: 0.3579 | Time: 1.3840 s
>>> Epoch [  331/10000]
train_loss: 2.1229 | train_acc: 0.3560 | val_loss: 2.1287 | val_acc: 0.3499 | test_acc: 0.3578 | Time: 1.3512 s
>>> Epoch [  332/10000]
train_loss: 2.1228 | train_acc: 0.3560 | val_loss: 2.1286 | val_acc: 0.3499 | test_acc: 0.3579 | Time: 1.1119 s
>>> Epoch [  333/10000]
train_loss: 2.1227 | train_acc: 0.3561 | val_loss: 2.1285 | val_acc: 0.3501 | test_acc: 0.3580 | Time: 1.2937 s
>>> Epoch [  334/10000]
train_loss: 2.1226 | train_acc: 0.3563 | val_loss: 2.1284 | val_acc: 0.3501 | test_acc: 0.3584 | Time: 1.3613 s
>>> Epoch [  335/10000]
train_loss: 2.1225 | train_acc: 0.3563 | val_loss: 2.1283 | val_acc: 0.3502 | test_acc: 0.3585 | Time: 1.3591 s
>>> Epoch [  336/10000]
train_loss: 2.1224 | train_acc: 0.3564 | val_loss: 2.1282 | val_acc: 0.3504 | test_acc: 0.3585 | Time: 1.2652 s
>>> Epoch [  337/10000]
train_loss: 2.1223 | train_acc: 0.3565 | val_loss: 2.1281 | val_acc: 0.3505 | test_acc: 0.3585 | Time: 1.3686 s
>>> Epoch [  338/10000]
train_loss: 2.1221 | train_acc: 0.3566 | val_loss: 2.1280 | val_acc: 0.3507 | test_acc: 0.3586 | Time: 1.4059 s
>>> Epoch [  339/10000]
train_loss: 2.1220 | train_acc: 0.3567 | val_loss: 2.1279 | val_acc: 0.3508 | test_acc: 0.3587 | Time: 1.3498 s
>>> Epoch [  340/10000]
train_loss: 2.1219 | train_acc: 0.3568 | val_loss: 2.1278 | val_acc: 0.3508 | test_acc: 0.3587 | Time: 1.4212 s
>>> Epoch [  341/10000]
train_loss: 2.1218 | train_acc: 0.3569 | val_loss: 2.1277 | val_acc: 0.3509 | test_acc: 0.3590 | Time: 1.3425 s
>>> Epoch [  342/10000]
train_loss: 2.1217 | train_acc: 0.3570 | val_loss: 2.1276 | val_acc: 0.3511 | test_acc: 0.3591 | Time: 1.4403 s
>>> Epoch [  343/10000]
train_loss: 2.1216 | train_acc: 0.3571 | val_loss: 2.1275 | val_acc: 0.3512 | test_acc: 0.3591 | Time: 1.3302 s
>>> Epoch [  344/10000]
train_loss: 2.1215 | train_acc: 0.3571 | val_loss: 2.1274 | val_acc: 0.3515 | test_acc: 0.3593 | Time: 1.2572 s
>>> Epoch [  345/10000]
train_loss: 2.1214 | train_acc: 0.3572 | val_loss: 2.1273 | val_acc: 0.3517 | test_acc: 0.3593 | Time: 1.3241 s
>>> Epoch [  346/10000]
train_loss: 2.1213 | train_acc: 0.3574 | val_loss: 2.1272 | val_acc: 0.3517 | test_acc: 0.3596 | Time: 1.2867 s
>>> Epoch [  347/10000]
train_loss: 2.1212 | train_acc: 0.3574 | val_loss: 2.1271 | val_acc: 0.3518 | test_acc: 0.3597 | Time: 1.3061 s
>>> Epoch [  348/10000]
train_loss: 2.1211 | train_acc: 0.3575 | val_loss: 2.1270 | val_acc: 0.3517 | test_acc: 0.3602 | Time: 1.3431 s
>>> Epoch [  349/10000]
train_loss: 2.1210 | train_acc: 0.3576 | val_loss: 2.1269 | val_acc: 0.3516 | test_acc: 0.3603 | Time: 1.5245 s
>>> Epoch [  350/10000]
train_loss: 2.1208 | train_acc: 0.3578 | val_loss: 2.1268 | val_acc: 0.3517 | test_acc: 0.3602 | Time: 1.3930 s
>>> Epoch [  351/10000]
train_loss: 2.1207 | train_acc: 0.3579 | val_loss: 2.1267 | val_acc: 0.3517 | test_acc: 0.3603 | Time: 1.2561 s
>>> Epoch [  352/10000]
train_loss: 2.1206 | train_acc: 0.3581 | val_loss: 2.1266 | val_acc: 0.3517 | test_acc: 0.3603 | Time: 1.5067 s
>>> Epoch [  353/10000]
train_loss: 2.1205 | train_acc: 0.3581 | val_loss: 2.1265 | val_acc: 0.3515 | test_acc: 0.3602 | Time: 1.3038 s
>>> Epoch [  354/10000]
train_loss: 2.1204 | train_acc: 0.3582 | val_loss: 2.1264 | val_acc: 0.3515 | test_acc: 0.3602 | Time: 1.4195 s
>>> Epoch [  355/10000]
train_loss: 2.1203 | train_acc: 0.3583 | val_loss: 2.1263 | val_acc: 0.3515 | test_acc: 0.3605 | Time: 1.3637 s
>>> Epoch [  356/10000]
train_loss: 2.1202 | train_acc: 0.3584 | val_loss: 2.1262 | val_acc: 0.3514 | test_acc: 0.3606 | Time: 1.4976 s
>>> Epoch [  357/10000]
train_loss: 2.1201 | train_acc: 0.3584 | val_loss: 2.1261 | val_acc: 0.3514 | test_acc: 0.3606 | Time: 1.3541 s
>>> Epoch [  358/10000]
train_loss: 2.1200 | train_acc: 0.3585 | val_loss: 2.1260 | val_acc: 0.3513 | test_acc: 0.3608 | Time: 1.4364 s
>>> Epoch [  359/10000]
train_loss: 2.1199 | train_acc: 0.3586 | val_loss: 2.1259 | val_acc: 0.3513 | test_acc: 0.3608 | Time: 1.4265 s
>>> Epoch [  360/10000]
train_loss: 2.1198 | train_acc: 0.3587 | val_loss: 2.1259 | val_acc: 0.3514 | test_acc: 0.3606 | Time: 1.3947 s
>>> Epoch [  361/10000]
train_loss: 2.1197 | train_acc: 0.3587 | val_loss: 2.1258 | val_acc: 0.3515 | test_acc: 0.3606 | Time: 1.3589 s
>>> Epoch [  362/10000]
train_loss: 2.1196 | train_acc: 0.3591 | val_loss: 2.1257 | val_acc: 0.3517 | test_acc: 0.3606 | Time: 1.3956 s
>>> Epoch [  363/10000]
train_loss: 2.1195 | train_acc: 0.3592 | val_loss: 2.1256 | val_acc: 0.3519 | test_acc: 0.3607 | Time: 1.4872 s
>>> Epoch [  364/10000]
train_loss: 2.1194 | train_acc: 0.3592 | val_loss: 2.1255 | val_acc: 0.3521 | test_acc: 0.3609 | Time: 1.3166 s
>>> Epoch [  365/10000]
train_loss: 2.1193 | train_acc: 0.3593 | val_loss: 2.1254 | val_acc: 0.3524 | test_acc: 0.3609 | Time: 1.4238 s
>>> Epoch [  366/10000]
train_loss: 2.1192 | train_acc: 0.3594 | val_loss: 2.1253 | val_acc: 0.3527 | test_acc: 0.3608 | Time: 1.3854 s
>>> Epoch [  367/10000]
train_loss: 2.1191 | train_acc: 0.3593 | val_loss: 2.1252 | val_acc: 0.3530 | test_acc: 0.3608 | Time: 1.4310 s
>>> Epoch [  368/10000]
train_loss: 2.1190 | train_acc: 0.3595 | val_loss: 2.1251 | val_acc: 0.3531 | test_acc: 0.3609 | Time: 1.4770 s
>>> Epoch [  369/10000]
train_loss: 2.1189 | train_acc: 0.3595 | val_loss: 2.1250 | val_acc: 0.3533 | test_acc: 0.3611 | Time: 1.3882 s
>>> Epoch [  370/10000]
train_loss: 2.1188 | train_acc: 0.3596 | val_loss: 2.1249 | val_acc: 0.3532 | test_acc: 0.3613 | Time: 1.4411 s
>>> Epoch [  371/10000]
train_loss: 2.1187 | train_acc: 0.3596 | val_loss: 2.1249 | val_acc: 0.3531 | test_acc: 0.3614 | Time: 1.2661 s
>>> Epoch [  372/10000]
train_loss: 2.1186 | train_acc: 0.3598 | val_loss: 2.1248 | val_acc: 0.3533 | test_acc: 0.3616 | Time: 1.3731 s
>>> Epoch [  373/10000]
train_loss: 2.1185 | train_acc: 0.3599 | val_loss: 2.1247 | val_acc: 0.3534 | test_acc: 0.3618 | Time: 1.4294 s
>>> Epoch [  374/10000]
train_loss: 2.1184 | train_acc: 0.3600 | val_loss: 2.1246 | val_acc: 0.3534 | test_acc: 0.3618 | Time: 1.5050 s
>>> Epoch [  375/10000]
train_loss: 2.1183 | train_acc: 0.3601 | val_loss: 2.1245 | val_acc: 0.3534 | test_acc: 0.3621 | Time: 1.2513 s
>>> Epoch [  376/10000]
train_loss: 2.1182 | train_acc: 0.3601 | val_loss: 2.1244 | val_acc: 0.3534 | test_acc: 0.3623 | Time: 1.4263 s
>>> Epoch [  377/10000]
train_loss: 2.1181 | train_acc: 0.3602 | val_loss: 2.1243 | val_acc: 0.3534 | test_acc: 0.3625 | Time: 1.3793 s
>>> Epoch [  378/10000]
train_loss: 2.1180 | train_acc: 0.3603 | val_loss: 2.1242 | val_acc: 0.3535 | test_acc: 0.3625 | Time: 1.5177 s
>>> Epoch [  379/10000]
train_loss: 2.1179 | train_acc: 0.3604 | val_loss: 2.1242 | val_acc: 0.3535 | test_acc: 0.3626 | Time: 1.4296 s
>>> Epoch [  380/10000]
train_loss: 2.1178 | train_acc: 0.3607 | val_loss: 2.1241 | val_acc: 0.3536 | test_acc: 0.3625 | Time: 1.4379 s
>>> Epoch [  381/10000]
train_loss: 2.1177 | train_acc: 0.3608 | val_loss: 2.1240 | val_acc: 0.3535 | test_acc: 0.3625 | Time: 1.5786 s
>>> Epoch [  382/10000]
train_loss: 2.1176 | train_acc: 0.3609 | val_loss: 2.1239 | val_acc: 0.3537 | test_acc: 0.3626 | Time: 1.2922 s
>>> Epoch [  383/10000]
train_loss: 2.1175 | train_acc: 0.3609 | val_loss: 2.1238 | val_acc: 0.3538 | test_acc: 0.3625 | Time: 1.5524 s
>>> Epoch [  384/10000]
train_loss: 2.1174 | train_acc: 0.3611 | val_loss: 2.1237 | val_acc: 0.3537 | test_acc: 0.3624 | Time: 1.3993 s
>>> Epoch [  385/10000]
train_loss: 2.1173 | train_acc: 0.3612 | val_loss: 2.1236 | val_acc: 0.3537 | test_acc: 0.3622 | Time: 1.1372 s
>>> Epoch [  386/10000]
train_loss: 2.1173 | train_acc: 0.3612 | val_loss: 2.1236 | val_acc: 0.3539 | test_acc: 0.3625 | Time: 1.1451 s
>>> Epoch [  387/10000]
train_loss: 2.1172 | train_acc: 0.3613 | val_loss: 2.1235 | val_acc: 0.3541 | test_acc: 0.3623 | Time: 1.1340 s
>>> Epoch [  388/10000]
train_loss: 2.1171 | train_acc: 0.3616 | val_loss: 2.1234 | val_acc: 0.3542 | test_acc: 0.3624 | Time: 2.2798 s
>>> Epoch [  389/10000]
train_loss: 2.1170 | train_acc: 0.3616 | val_loss: 2.1233 | val_acc: 0.3545 | test_acc: 0.3624 | Time: 1.8620 s
>>> Epoch [  390/10000]
train_loss: 2.1169 | train_acc: 0.3617 | val_loss: 2.1232 | val_acc: 0.3545 | test_acc: 0.3627 | Time: 2.3147 s
>>> Epoch [  391/10000]
train_loss: 2.1168 | train_acc: 0.3618 | val_loss: 2.1231 | val_acc: 0.3545 | test_acc: 0.3628 | Time: 2.0953 s
>>> Epoch [  392/10000]
train_loss: 2.1167 | train_acc: 0.3620 | val_loss: 2.1231 | val_acc: 0.3545 | test_acc: 0.3629 | Time: 2.0535 s
>>> Epoch [  393/10000]
train_loss: 2.1166 | train_acc: 0.3621 | val_loss: 2.1230 | val_acc: 0.3545 | test_acc: 0.3630 | Time: 2.2465 s
>>> Epoch [  394/10000]
train_loss: 2.1165 | train_acc: 0.3622 | val_loss: 2.1229 | val_acc: 0.3543 | test_acc: 0.3631 | Time: 1.8422 s
>>> Epoch [  395/10000]
train_loss: 2.1164 | train_acc: 0.3623 | val_loss: 2.1228 | val_acc: 0.3542 | test_acc: 0.3629 | Time: 2.1101 s
>>> Epoch [  396/10000]
train_loss: 2.1163 | train_acc: 0.3624 | val_loss: 2.1227 | val_acc: 0.3544 | test_acc: 0.3629 | Time: 2.1199 s
>>> Epoch [  397/10000]
train_loss: 2.1162 | train_acc: 0.3626 | val_loss: 2.1227 | val_acc: 0.3544 | test_acc: 0.3629 | Time: 1.3826 s
>>> Epoch [  398/10000]
train_loss: 2.1161 | train_acc: 0.3626 | val_loss: 2.1226 | val_acc: 0.3544 | test_acc: 0.3631 | Time: 2.2993 s
>>> Epoch [  399/10000]
train_loss: 2.1161 | train_acc: 0.3627 | val_loss: 2.1225 | val_acc: 0.3547 | test_acc: 0.3633 | Time: 1.9253 s
>>> Epoch [  400/10000]
train_loss: 2.1160 | train_acc: 0.3628 | val_loss: 2.1224 | val_acc: 0.3550 | test_acc: 0.3634 | Time: 2.2652 s
>>> Epoch [  401/10000]
train_loss: 2.1159 | train_acc: 0.3628 | val_loss: 2.1223 | val_acc: 0.3551 | test_acc: 0.3635 | Time: 2.4339 s
>>> Epoch [  402/10000]
train_loss: 2.1158 | train_acc: 0.3630 | val_loss: 2.1223 | val_acc: 0.3552 | test_acc: 0.3632 | Time: 1.8426 s
>>> Epoch [  403/10000]
train_loss: 2.1157 | train_acc: 0.3631 | val_loss: 2.1222 | val_acc: 0.3551 | test_acc: 0.3635 | Time: 2.0968 s
>>> Epoch [  404/10000]
train_loss: 2.1156 | train_acc: 0.3633 | val_loss: 2.1221 | val_acc: 0.3551 | test_acc: 0.3634 | Time: 2.1082 s
>>> Epoch [  405/10000]
train_loss: 2.1155 | train_acc: 0.3633 | val_loss: 2.1220 | val_acc: 0.3552 | test_acc: 0.3634 | Time: 2.0372 s
>>> Epoch [  406/10000]
train_loss: 2.1154 | train_acc: 0.3633 | val_loss: 2.1219 | val_acc: 0.3553 | test_acc: 0.3634 | Time: 1.9960 s
>>> Epoch [  407/10000]
train_loss: 2.1153 | train_acc: 0.3634 | val_loss: 2.1219 | val_acc: 0.3554 | test_acc: 0.3634 | Time: 1.3423 s
>>> Epoch [  408/10000]
train_loss: 2.1153 | train_acc: 0.3636 | val_loss: 2.1218 | val_acc: 0.3554 | test_acc: 0.3635 | Time: 1.3857 s
>>> Epoch [  409/10000]
train_loss: 2.1152 | train_acc: 0.3637 | val_loss: 2.1217 | val_acc: 0.3555 | test_acc: 0.3635 | Time: 1.3640 s
>>> Epoch [  410/10000]
train_loss: 2.1151 | train_acc: 0.3637 | val_loss: 2.1216 | val_acc: 0.3555 | test_acc: 0.3636 | Time: 1.2450 s
>>> Epoch [  411/10000]
train_loss: 2.1150 | train_acc: 0.3638 | val_loss: 2.1215 | val_acc: 0.3556 | test_acc: 0.3639 | Time: 1.3089 s
>>> Epoch [  412/10000]
train_loss: 2.1149 | train_acc: 0.3639 | val_loss: 2.1215 | val_acc: 0.3556 | test_acc: 0.3639 | Time: 1.4308 s
>>> Epoch [  413/10000]
train_loss: 2.1148 | train_acc: 0.3641 | val_loss: 2.1214 | val_acc: 0.3558 | test_acc: 0.3639 | Time: 1.3889 s
>>> Epoch [  414/10000]
train_loss: 2.1147 | train_acc: 0.3641 | val_loss: 2.1213 | val_acc: 0.3561 | test_acc: 0.3641 | Time: 1.4811 s
>>> Epoch [  415/10000]
train_loss: 2.1146 | train_acc: 0.3642 | val_loss: 2.1212 | val_acc: 0.3561 | test_acc: 0.3642 | Time: 1.4641 s
>>> Epoch [  416/10000]
train_loss: 2.1146 | train_acc: 0.3643 | val_loss: 2.1212 | val_acc: 0.3562 | test_acc: 0.3644 | Time: 1.3850 s
>>> Epoch [  417/10000]
train_loss: 2.1145 | train_acc: 0.3643 | val_loss: 2.1211 | val_acc: 0.3562 | test_acc: 0.3646 | Time: 1.3476 s
>>> Epoch [  418/10000]
train_loss: 2.1144 | train_acc: 0.3644 | val_loss: 2.1210 | val_acc: 0.3564 | test_acc: 0.3644 | Time: 1.5135 s
>>> Epoch [  419/10000]
train_loss: 2.1143 | train_acc: 0.3647 | val_loss: 2.1209 | val_acc: 0.3565 | test_acc: 0.3644 | Time: 1.4365 s
>>> Epoch [  420/10000]
train_loss: 2.1142 | train_acc: 0.3648 | val_loss: 2.1209 | val_acc: 0.3564 | test_acc: 0.3644 | Time: 1.4461 s
>>> Epoch [  421/10000]
train_loss: 2.1141 | train_acc: 0.3648 | val_loss: 2.1208 | val_acc: 0.3565 | test_acc: 0.3643 | Time: 1.4555 s
>>> Epoch [  422/10000]
train_loss: 2.1140 | train_acc: 0.3650 | val_loss: 2.1207 | val_acc: 0.3564 | test_acc: 0.3645 | Time: 1.4271 s
>>> Epoch [  423/10000]
train_loss: 2.1140 | train_acc: 0.3650 | val_loss: 2.1206 | val_acc: 0.3566 | test_acc: 0.3645 | Time: 1.3741 s
>>> Epoch [  424/10000]
train_loss: 2.1139 | train_acc: 0.3650 | val_loss: 2.1206 | val_acc: 0.3565 | test_acc: 0.3646 | Time: 1.4132 s
>>> Epoch [  425/10000]
train_loss: 2.1138 | train_acc: 0.3651 | val_loss: 2.1205 | val_acc: 0.3569 | test_acc: 0.3647 | Time: 1.4973 s
>>> Epoch [  426/10000]
train_loss: 2.1137 | train_acc: 0.3651 | val_loss: 2.1204 | val_acc: 0.3569 | test_acc: 0.3649 | Time: 1.4765 s
>>> Epoch [  427/10000]
train_loss: 2.1136 | train_acc: 0.3653 | val_loss: 2.1203 | val_acc: 0.3572 | test_acc: 0.3647 | Time: 1.4494 s
>>> Epoch [  428/10000]
train_loss: 2.1135 | train_acc: 0.3653 | val_loss: 2.1203 | val_acc: 0.3573 | test_acc: 0.3650 | Time: 1.5737 s
>>> Epoch [  429/10000]
train_loss: 2.1135 | train_acc: 0.3653 | val_loss: 2.1202 | val_acc: 0.3576 | test_acc: 0.3651 | Time: 1.4989 s
>>> Epoch [  430/10000]
train_loss: 2.1134 | train_acc: 0.3653 | val_loss: 2.1201 | val_acc: 0.3574 | test_acc: 0.3654 | Time: 1.5379 s
>>> Epoch [  431/10000]
train_loss: 2.1133 | train_acc: 0.3653 | val_loss: 2.1200 | val_acc: 0.3576 | test_acc: 0.3654 | Time: 1.5895 s
>>> Epoch [  432/10000]
train_loss: 2.1132 | train_acc: 0.3654 | val_loss: 2.1200 | val_acc: 0.3577 | test_acc: 0.3654 | Time: 1.4488 s
>>> Epoch [  433/10000]
train_loss: 2.1131 | train_acc: 0.3655 | val_loss: 2.1199 | val_acc: 0.3578 | test_acc: 0.3654 | Time: 1.6181 s
>>> Epoch [  434/10000]
train_loss: 2.1131 | train_acc: 0.3655 | val_loss: 2.1198 | val_acc: 0.3581 | test_acc: 0.3655 | Time: 1.6046 s
>>> Epoch [  435/10000]
train_loss: 2.1130 | train_acc: 0.3655 | val_loss: 2.1198 | val_acc: 0.3581 | test_acc: 0.3656 | Time: 1.5174 s
>>> Epoch [  436/10000]
train_loss: 2.1129 | train_acc: 0.3657 | val_loss: 2.1197 | val_acc: 0.3581 | test_acc: 0.3657 | Time: 1.6315 s
>>> Epoch [  437/10000]
train_loss: 2.1128 | train_acc: 0.3657 | val_loss: 2.1196 | val_acc: 0.3580 | test_acc: 0.3659 | Time: 1.4605 s
>>> Epoch [  438/10000]
train_loss: 2.1127 | train_acc: 0.3658 | val_loss: 2.1195 | val_acc: 0.3580 | test_acc: 0.3661 | Time: 1.4857 s
>>> Epoch [  439/10000]
train_loss: 2.1126 | train_acc: 0.3660 | val_loss: 2.1195 | val_acc: 0.3581 | test_acc: 0.3661 | Time: 1.5362 s
>>> Epoch [  440/10000]
train_loss: 2.1126 | train_acc: 0.3660 | val_loss: 2.1194 | val_acc: 0.3581 | test_acc: 0.3663 | Time: 1.4914 s
>>> Epoch [  441/10000]
train_loss: 2.1125 | train_acc: 0.3660 | val_loss: 2.1193 | val_acc: 0.3581 | test_acc: 0.3663 | Time: 1.4941 s
>>> Epoch [  442/10000]
train_loss: 2.1124 | train_acc: 0.3661 | val_loss: 2.1193 | val_acc: 0.3582 | test_acc: 0.3661 | Time: 1.5742 s
>>> Epoch [  443/10000]
train_loss: 2.1123 | train_acc: 0.3661 | val_loss: 2.1192 | val_acc: 0.3582 | test_acc: 0.3661 | Time: 1.6504 s
>>> Epoch [  444/10000]
train_loss: 2.1122 | train_acc: 0.3663 | val_loss: 2.1191 | val_acc: 0.3581 | test_acc: 0.3661 | Time: 1.5488 s
>>> Epoch [  445/10000]
train_loss: 2.1122 | train_acc: 0.3664 | val_loss: 2.1191 | val_acc: 0.3582 | test_acc: 0.3661 | Time: 1.6231 s
>>> Epoch [  446/10000]
train_loss: 2.1121 | train_acc: 0.3664 | val_loss: 2.1190 | val_acc: 0.3584 | test_acc: 0.3660 | Time: 1.5100 s
>>> Epoch [  447/10000]
train_loss: 2.1120 | train_acc: 0.3665 | val_loss: 2.1189 | val_acc: 0.3586 | test_acc: 0.3660 | Time: 1.4842 s
>>> Epoch [  448/10000]
train_loss: 2.1119 | train_acc: 0.3666 | val_loss: 2.1188 | val_acc: 0.3586 | test_acc: 0.3660 | Time: 1.6189 s
>>> Epoch [  449/10000]
train_loss: 2.1119 | train_acc: 0.3666 | val_loss: 2.1188 | val_acc: 0.3588 | test_acc: 0.3660 | Time: 1.5144 s
>>> Epoch [  450/10000]
train_loss: 2.1118 | train_acc: 0.3668 | val_loss: 2.1187 | val_acc: 0.3588 | test_acc: 0.3661 | Time: 1.6267 s
>>> Epoch [  451/10000]
train_loss: 2.1117 | train_acc: 0.3669 | val_loss: 2.1186 | val_acc: 0.3588 | test_acc: 0.3660 | Time: 1.6023 s
>>> Epoch [  452/10000]
train_loss: 2.1116 | train_acc: 0.3670 | val_loss: 2.1186 | val_acc: 0.3588 | test_acc: 0.3660 | Time: 1.3741 s
>>> Epoch [  453/10000]
train_loss: 2.1115 | train_acc: 0.3669 | val_loss: 2.1185 | val_acc: 0.3589 | test_acc: 0.3658 | Time: 1.5139 s
>>> Epoch [  454/10000]
train_loss: 2.1115 | train_acc: 0.3669 | val_loss: 2.1184 | val_acc: 0.3589 | test_acc: 0.3657 | Time: 1.7349 s
>>> Epoch [  455/10000]
train_loss: 2.1114 | train_acc: 0.3669 | val_loss: 2.1184 | val_acc: 0.3589 | test_acc: 0.3655 | Time: 1.5553 s
>>> Epoch [  456/10000]
train_loss: 2.1113 | train_acc: 0.3670 | val_loss: 2.1183 | val_acc: 0.3594 | test_acc: 0.3655 | Time: 1.6584 s
>>> Epoch [  457/10000]
train_loss: 2.1112 | train_acc: 0.3670 | val_loss: 2.1182 | val_acc: 0.3593 | test_acc: 0.3657 | Time: 1.6551 s
>>> Epoch [  458/10000]
train_loss: 2.1112 | train_acc: 0.3671 | val_loss: 2.1182 | val_acc: 0.3593 | test_acc: 0.3659 | Time: 1.4186 s
>>> Epoch [  459/10000]
train_loss: 2.1111 | train_acc: 0.3672 | val_loss: 2.1181 | val_acc: 0.3593 | test_acc: 0.3661 | Time: 1.5896 s
>>> Epoch [  460/10000]
train_loss: 2.1110 | train_acc: 0.3673 | val_loss: 2.1180 | val_acc: 0.3592 | test_acc: 0.3660 | Time: 1.5703 s
>>> Epoch [  461/10000]
train_loss: 2.1109 | train_acc: 0.3674 | val_loss: 2.1180 | val_acc: 0.3592 | test_acc: 0.3660 | Time: 1.5635 s
>>> Epoch [  462/10000]
train_loss: 2.1109 | train_acc: 0.3676 | val_loss: 2.1179 | val_acc: 0.3592 | test_acc: 0.3659 | Time: 1.6069 s
>>> Epoch [  463/10000]
train_loss: 2.1108 | train_acc: 0.3677 | val_loss: 2.1178 | val_acc: 0.3592 | test_acc: 0.3662 | Time: 1.4785 s
>>> Epoch [  464/10000]
train_loss: 2.1107 | train_acc: 0.3678 | val_loss: 2.1178 | val_acc: 0.3594 | test_acc: 0.3662 | Time: 1.6674 s
>>> Epoch [  465/10000]
train_loss: 2.1106 | train_acc: 0.3678 | val_loss: 2.1177 | val_acc: 0.3593 | test_acc: 0.3662 | Time: 1.7782 s
>>> Epoch [  466/10000]
train_loss: 2.1105 | train_acc: 0.3679 | val_loss: 2.1176 | val_acc: 0.3592 | test_acc: 0.3662 | Time: 1.5133 s
>>> Epoch [  467/10000]
train_loss: 2.1105 | train_acc: 0.3679 | val_loss: 2.1176 | val_acc: 0.3594 | test_acc: 0.3661 | Time: 1.5061 s
>>> Epoch [  468/10000]
train_loss: 2.1104 | train_acc: 0.3680 | val_loss: 2.1175 | val_acc: 0.3597 | test_acc: 0.3662 | Time: 1.6001 s
>>> Epoch [  469/10000]
train_loss: 2.1103 | train_acc: 0.3681 | val_loss: 2.1174 | val_acc: 0.3600 | test_acc: 0.3664 | Time: 1.6355 s
>>> Epoch [  470/10000]
train_loss: 2.1103 | train_acc: 0.3682 | val_loss: 2.1174 | val_acc: 0.3601 | test_acc: 0.3665 | Time: 1.7812 s
>>> Epoch [  471/10000]
train_loss: 2.1102 | train_acc: 0.3683 | val_loss: 2.1173 | val_acc: 0.3602 | test_acc: 0.3665 | Time: 1.5694 s
>>> Epoch [  472/10000]
train_loss: 2.1101 | train_acc: 0.3683 | val_loss: 2.1173 | val_acc: 0.3603 | test_acc: 0.3664 | Time: 1.6282 s
>>> Epoch [  473/10000]
train_loss: 2.1100 | train_acc: 0.3684 | val_loss: 2.1172 | val_acc: 0.3601 | test_acc: 0.3663 | Time: 1.5797 s
>>> Epoch [  474/10000]
train_loss: 2.1100 | train_acc: 0.3685 | val_loss: 2.1171 | val_acc: 0.3606 | test_acc: 0.3663 | Time: 1.4100 s
>>> Epoch [  475/10000]
train_loss: 2.1099 | train_acc: 0.3685 | val_loss: 2.1171 | val_acc: 0.3606 | test_acc: 0.3664 | Time: 1.5681 s
>>> Epoch [  476/10000]
train_loss: 2.1098 | train_acc: 0.3685 | val_loss: 2.1170 | val_acc: 0.3606 | test_acc: 0.3664 | Time: 1.6365 s
>>> Epoch [  477/10000]
train_loss: 2.1097 | train_acc: 0.3686 | val_loss: 2.1169 | val_acc: 0.3608 | test_acc: 0.3664 | Time: 1.6276 s
>>> Epoch [  478/10000]
train_loss: 2.1097 | train_acc: 0.3687 | val_loss: 2.1169 | val_acc: 0.3609 | test_acc: 0.3666 | Time: 1.6137 s
>>> Epoch [  479/10000]
train_loss: 2.1096 | train_acc: 0.3687 | val_loss: 2.1168 | val_acc: 0.3609 | test_acc: 0.3665 | Time: 1.5442 s
>>> Epoch [  480/10000]
train_loss: 2.1095 | train_acc: 0.3687 | val_loss: 2.1167 | val_acc: 0.3609 | test_acc: 0.3665 | Time: 1.7417 s
>>> Epoch [  481/10000]
train_loss: 2.1094 | train_acc: 0.3688 | val_loss: 2.1167 | val_acc: 0.3607 | test_acc: 0.3663 | Time: 1.6458 s
>>> Epoch [  482/10000]
train_loss: 2.1094 | train_acc: 0.3689 | val_loss: 2.1166 | val_acc: 0.3607 | test_acc: 0.3662 | Time: 1.5044 s
>>> Epoch [  483/10000]
train_loss: 2.1093 | train_acc: 0.3689 | val_loss: 2.1166 | val_acc: 0.3607 | test_acc: 0.3661 | Time: 1.7301 s
>>> Epoch [  484/10000]
train_loss: 2.1092 | train_acc: 0.3689 | val_loss: 2.1165 | val_acc: 0.3608 | test_acc: 0.3662 | Time: 1.6647 s
>>> Epoch [  485/10000]
train_loss: 2.1092 | train_acc: 0.3690 | val_loss: 2.1164 | val_acc: 0.3609 | test_acc: 0.3661 | Time: 1.6193 s
>>> Epoch [  486/10000]
train_loss: 2.1091 | train_acc: 0.3692 | val_loss: 2.1164 | val_acc: 0.3611 | test_acc: 0.3660 | Time: 1.7261 s
>>> Epoch [  487/10000]
train_loss: 2.1090 | train_acc: 0.3692 | val_loss: 2.1163 | val_acc: 0.3609 | test_acc: 0.3661 | Time: 1.6818 s
>>> Epoch [  488/10000]
train_loss: 2.1089 | train_acc: 0.3693 | val_loss: 2.1162 | val_acc: 0.3609 | test_acc: 0.3662 | Time: 1.6005 s
>>> Epoch [  489/10000]
train_loss: 2.1089 | train_acc: 0.3694 | val_loss: 2.1162 | val_acc: 0.3611 | test_acc: 0.3661 | Time: 1.5702 s
>>> Epoch [  490/10000]
train_loss: 2.1088 | train_acc: 0.3695 | val_loss: 2.1161 | val_acc: 0.3611 | test_acc: 0.3661 | Time: 1.7056 s
>>> Epoch [  491/10000]
train_loss: 2.1087 | train_acc: 0.3697 | val_loss: 2.1161 | val_acc: 0.3612 | test_acc: 0.3660 | Time: 1.6414 s
>>> Epoch [  492/10000]
train_loss: 2.1087 | train_acc: 0.3697 | val_loss: 2.1160 | val_acc: 0.3611 | test_acc: 0.3660 | Time: 1.7212 s
>>> Epoch [  493/10000]
train_loss: 2.1086 | train_acc: 0.3697 | val_loss: 2.1159 | val_acc: 0.3609 | test_acc: 0.3660 | Time: 1.6732 s
>>> Epoch [  494/10000]
train_loss: 2.1085 | train_acc: 0.3698 | val_loss: 2.1159 | val_acc: 0.3610 | test_acc: 0.3662 | Time: 1.5670 s
>>> Epoch [  495/10000]
train_loss: 2.1085 | train_acc: 0.3699 | val_loss: 2.1158 | val_acc: 0.3610 | test_acc: 0.3665 | Time: 1.6882 s
>>> Epoch [  496/10000]
train_loss: 2.1084 | train_acc: 0.3700 | val_loss: 2.1158 | val_acc: 0.3609 | test_acc: 0.3666 | Time: 1.6930 s
>>> Epoch [  497/10000]
train_loss: 2.1083 | train_acc: 0.3701 | val_loss: 2.1157 | val_acc: 0.3609 | test_acc: 0.3666 | Time: 1.6592 s
>>> Epoch [  498/10000]
train_loss: 2.1082 | train_acc: 0.3701 | val_loss: 2.1156 | val_acc: 0.3609 | test_acc: 0.3667 | Time: 1.6878 s
>>> Epoch [  499/10000]
train_loss: 2.1082 | train_acc: 0.3703 | val_loss: 2.1156 | val_acc: 0.3613 | test_acc: 0.3667 | Time: 1.7615 s
>>> Epoch [  500/10000]
train_loss: 2.1081 | train_acc: 0.3704 | val_loss: 2.1155 | val_acc: 0.3614 | test_acc: 0.3666 | Time: 1.4898 s
>>> Epoch [  501/10000]
train_loss: 2.1080 | train_acc: 0.3704 | val_loss: 2.1155 | val_acc: 0.3617 | test_acc: 0.3668 | Time: 1.7191 s
>>> Epoch [  502/10000]
train_loss: 2.1080 | train_acc: 0.3705 | val_loss: 2.1154 | val_acc: 0.3615 | test_acc: 0.3669 | Time: 1.7318 s
>>> Epoch [  503/10000]
train_loss: 2.1079 | train_acc: 0.3706 | val_loss: 2.1153 | val_acc: 0.3615 | test_acc: 0.3670 | Time: 1.5248 s
>>> Epoch [  504/10000]
train_loss: 2.1078 | train_acc: 0.3707 | val_loss: 2.1153 | val_acc: 0.3616 | test_acc: 0.3670 | Time: 1.7623 s
>>> Epoch [  505/10000]
train_loss: 2.1078 | train_acc: 0.3707 | val_loss: 2.1152 | val_acc: 0.3615 | test_acc: 0.3670 | Time: 1.6255 s
>>> Epoch [  506/10000]
train_loss: 2.1077 | train_acc: 0.3707 | val_loss: 2.1152 | val_acc: 0.3617 | test_acc: 0.3671 | Time: 1.7745 s
>>> Epoch [  507/10000]
train_loss: 2.1076 | train_acc: 0.3706 | val_loss: 2.1151 | val_acc: 0.3616 | test_acc: 0.3671 | Time: 1.6280 s
>>> Epoch [  508/10000]
train_loss: 2.1076 | train_acc: 0.3707 | val_loss: 2.1151 | val_acc: 0.3617 | test_acc: 0.3673 | Time: 1.7014 s
>>> Epoch [  509/10000]
train_loss: 2.1075 | train_acc: 0.3708 | val_loss: 2.1150 | val_acc: 0.3619 | test_acc: 0.3673 | Time: 1.6441 s
>>> Epoch [  510/10000]
train_loss: 2.1074 | train_acc: 0.3709 | val_loss: 2.1149 | val_acc: 0.3618 | test_acc: 0.3674 | Time: 1.5721 s
>>> Epoch [  511/10000]
train_loss: 2.1074 | train_acc: 0.3711 | val_loss: 2.1149 | val_acc: 0.3618 | test_acc: 0.3674 | Time: 1.7253 s
>>> Epoch [  512/10000]
train_loss: 2.1073 | train_acc: 0.3711 | val_loss: 2.1148 | val_acc: 0.3619 | test_acc: 0.3675 | Time: 1.6068 s
>>> Epoch [  513/10000]
train_loss: 2.1072 | train_acc: 0.3712 | val_loss: 2.1148 | val_acc: 0.3621 | test_acc: 0.3674 | Time: 1.6549 s
>>> Epoch [  514/10000]
train_loss: 2.1072 | train_acc: 0.3712 | val_loss: 2.1147 | val_acc: 0.3622 | test_acc: 0.3676 | Time: 1.8261 s
>>> Epoch [  515/10000]
train_loss: 2.1071 | train_acc: 0.3714 | val_loss: 2.1147 | val_acc: 0.3623 | test_acc: 0.3677 | Time: 1.8169 s
>>> Epoch [  516/10000]
train_loss: 2.1070 | train_acc: 0.3715 | val_loss: 2.1146 | val_acc: 0.3623 | test_acc: 0.3677 | Time: 1.8041 s
>>> Epoch [  517/10000]
train_loss: 2.1070 | train_acc: 0.3715 | val_loss: 2.1145 | val_acc: 0.3624 | test_acc: 0.3677 | Time: 1.7846 s
>>> Epoch [  518/10000]
train_loss: 2.1069 | train_acc: 0.3715 | val_loss: 2.1145 | val_acc: 0.3626 | test_acc: 0.3679 | Time: 1.7300 s
>>> Epoch [  519/10000]
train_loss: 2.1068 | train_acc: 0.3715 | val_loss: 2.1144 | val_acc: 0.3630 | test_acc: 0.3680 | Time: 1.7304 s
>>> Epoch [  520/10000]
train_loss: 2.1068 | train_acc: 0.3716 | val_loss: 2.1144 | val_acc: 0.3630 | test_acc: 0.3679 | Time: 1.7731 s
>>> Epoch [  521/10000]
train_loss: 2.1067 | train_acc: 0.3716 | val_loss: 2.1143 | val_acc: 0.3632 | test_acc: 0.3680 | Time: 1.7084 s
>>> Epoch [  522/10000]
train_loss: 2.1066 | train_acc: 0.3716 | val_loss: 2.1143 | val_acc: 0.3635 | test_acc: 0.3679 | Time: 1.4796 s
>>> Epoch [  523/10000]
train_loss: 2.1066 | train_acc: 0.3716 | val_loss: 2.1142 | val_acc: 0.3636 | test_acc: 0.3677 | Time: 1.6388 s
>>> Epoch [  524/10000]
train_loss: 2.1065 | train_acc: 0.3716 | val_loss: 2.1141 | val_acc: 0.3638 | test_acc: 0.3678 | Time: 1.8033 s
>>> Epoch [  525/10000]
train_loss: 2.1064 | train_acc: 0.3717 | val_loss: 2.1141 | val_acc: 0.3638 | test_acc: 0.3677 | Time: 1.8101 s
>>> Epoch [  526/10000]
train_loss: 2.1064 | train_acc: 0.3718 | val_loss: 2.1140 | val_acc: 0.3640 | test_acc: 0.3676 | Time: 1.7423 s
>>> Epoch [  527/10000]
train_loss: 2.1063 | train_acc: 0.3718 | val_loss: 2.1140 | val_acc: 0.3640 | test_acc: 0.3676 | Time: 1.8188 s
>>> Epoch [  528/10000]
train_loss: 2.1062 | train_acc: 0.3719 | val_loss: 2.1139 | val_acc: 0.3640 | test_acc: 0.3677 | Time: 1.7164 s
>>> Epoch [  529/10000]
train_loss: 2.1062 | train_acc: 0.3720 | val_loss: 2.1139 | val_acc: 0.3640 | test_acc: 0.3677 | Time: 1.3885 s
>>> Epoch [  530/10000]
train_loss: 2.1061 | train_acc: 0.3720 | val_loss: 2.1138 | val_acc: 0.3641 | test_acc: 0.3677 | Time: 1.9926 s
>>> Epoch [  531/10000]
train_loss: 2.1060 | train_acc: 0.3721 | val_loss: 2.1138 | val_acc: 0.3641 | test_acc: 0.3678 | Time: 2.6453 s
>>> Epoch [  532/10000]
train_loss: 2.1060 | train_acc: 0.3720 | val_loss: 2.1137 | val_acc: 0.3643 | test_acc: 0.3677 | Time: 2.7311 s
>>> Epoch [  533/10000]
train_loss: 2.1059 | train_acc: 0.3720 | val_loss: 2.1137 | val_acc: 0.3642 | test_acc: 0.3678 | Time: 2.6288 s
>>> Epoch [  534/10000]
train_loss: 2.1058 | train_acc: 0.3720 | val_loss: 2.1136 | val_acc: 0.3643 | test_acc: 0.3680 | Time: 2.4031 s
>>> Epoch [  535/10000]
train_loss: 2.1058 | train_acc: 0.3722 | val_loss: 2.1135 | val_acc: 0.3640 | test_acc: 0.3680 | Time: 2.2785 s
>>> Epoch [  536/10000]
train_loss: 2.1057 | train_acc: 0.3722 | val_loss: 2.1135 | val_acc: 0.3639 | test_acc: 0.3679 | Time: 2.5149 s
>>> Epoch [  537/10000]
train_loss: 2.1057 | train_acc: 0.3722 | val_loss: 2.1134 | val_acc: 0.3642 | test_acc: 0.3680 | Time: 2.4794 s
>>> Epoch [  538/10000]
train_loss: 2.1056 | train_acc: 0.3724 | val_loss: 2.1134 | val_acc: 0.3642 | test_acc: 0.3680 | Time: 2.0144 s
>>> Epoch [  539/10000]
train_loss: 2.1055 | train_acc: 0.3725 | val_loss: 2.1133 | val_acc: 0.3643 | test_acc: 0.3680 | Time: 2.6031 s
>>> Epoch [  540/10000]
train_loss: 2.1055 | train_acc: 0.3726 | val_loss: 2.1133 | val_acc: 0.3643 | test_acc: 0.3679 | Time: 2.7631 s
>>> Epoch [  541/10000]
train_loss: 2.1054 | train_acc: 0.3727 | val_loss: 2.1132 | val_acc: 0.3644 | test_acc: 0.3682 | Time: 2.7543 s
>>> Epoch [  542/10000]
train_loss: 2.1053 | train_acc: 0.3728 | val_loss: 2.1132 | val_acc: 0.3643 | test_acc: 0.3684 | Time: 2.3753 s
>>> Epoch [  543/10000]
train_loss: 2.1053 | train_acc: 0.3728 | val_loss: 2.1131 | val_acc: 0.3645 | test_acc: 0.3684 | Time: 2.3519 s
>>> Epoch [  544/10000]
train_loss: 2.1052 | train_acc: 0.3729 | val_loss: 2.1131 | val_acc: 0.3645 | test_acc: 0.3682 | Time: 2.4513 s
>>> Epoch [  545/10000]
train_loss: 2.1051 | train_acc: 0.3730 | val_loss: 2.1130 | val_acc: 0.3644 | test_acc: 0.3682 | Time: 2.2532 s
>>> Epoch [  546/10000]
train_loss: 2.1051 | train_acc: 0.3730 | val_loss: 2.1130 | val_acc: 0.3645 | test_acc: 0.3680 | Time: 1.5120 s
>>> Epoch [  547/10000]
train_loss: 2.1050 | train_acc: 0.3730 | val_loss: 2.1129 | val_acc: 0.3645 | test_acc: 0.3682 | Time: 1.5854 s
>>> Epoch [  548/10000]
train_loss: 2.1050 | train_acc: 0.3731 | val_loss: 2.1128 | val_acc: 0.3647 | test_acc: 0.3683 | Time: 1.5619 s
>>> Epoch [  549/10000]
train_loss: 2.1049 | train_acc: 0.3731 | val_loss: 2.1128 | val_acc: 0.3647 | test_acc: 0.3684 | Time: 1.6148 s
>>> Epoch [  550/10000]
train_loss: 2.1048 | train_acc: 0.3731 | val_loss: 2.1127 | val_acc: 0.3648 | test_acc: 0.3685 | Time: 1.5423 s
>>> Epoch [  551/10000]
train_loss: 2.1048 | train_acc: 0.3732 | val_loss: 2.1127 | val_acc: 0.3648 | test_acc: 0.3684 | Time: 1.7460 s
>>> Epoch [  552/10000]
train_loss: 2.1047 | train_acc: 0.3733 | val_loss: 2.1126 | val_acc: 0.3649 | test_acc: 0.3684 | Time: 1.8236 s
>>> Epoch [  553/10000]
train_loss: 2.1047 | train_acc: 0.3734 | val_loss: 2.1126 | val_acc: 0.3649 | test_acc: 0.3685 | Time: 1.6922 s
>>> Epoch [  554/10000]
train_loss: 2.1046 | train_acc: 0.3735 | val_loss: 2.1125 | val_acc: 0.3649 | test_acc: 0.3686 | Time: 1.6589 s
>>> Epoch [  555/10000]
train_loss: 2.1045 | train_acc: 0.3736 | val_loss: 2.1125 | val_acc: 0.3649 | test_acc: 0.3687 | Time: 1.7616 s
>>> Epoch [  556/10000]
train_loss: 2.1045 | train_acc: 0.3737 | val_loss: 2.1124 | val_acc: 0.3648 | test_acc: 0.3687 | Time: 1.6243 s
>>> Epoch [  557/10000]
train_loss: 2.1044 | train_acc: 0.3737 | val_loss: 2.1124 | val_acc: 0.3651 | test_acc: 0.3688 | Time: 1.7082 s
>>> Epoch [  558/10000]
train_loss: 2.1043 | train_acc: 0.3738 | val_loss: 2.1123 | val_acc: 0.3652 | test_acc: 0.3687 | Time: 1.7731 s
>>> Epoch [  559/10000]
train_loss: 2.1043 | train_acc: 0.3739 | val_loss: 2.1123 | val_acc: 0.3654 | test_acc: 0.3688 | Time: 1.8529 s
>>> Epoch [  560/10000]
train_loss: 2.1042 | train_acc: 0.3738 | val_loss: 2.1122 | val_acc: 0.3654 | test_acc: 0.3687 | Time: 1.6242 s
>>> Epoch [  561/10000]
train_loss: 2.1042 | train_acc: 0.3739 | val_loss: 2.1122 | val_acc: 0.3654 | test_acc: 0.3686 | Time: 1.9186 s
>>> Epoch [  562/10000]
train_loss: 2.1041 | train_acc: 0.3740 | val_loss: 2.1121 | val_acc: 0.3655 | test_acc: 0.3686 | Time: 1.8399 s
>>> Epoch [  563/10000]
train_loss: 2.1040 | train_acc: 0.3740 | val_loss: 2.1121 | val_acc: 0.3654 | test_acc: 0.3687 | Time: 1.9448 s
>>> Epoch [  564/10000]
train_loss: 2.1040 | train_acc: 0.3741 | val_loss: 2.1120 | val_acc: 0.3657 | test_acc: 0.3686 | Time: 1.6485 s
>>> Epoch [  565/10000]
train_loss: 2.1039 | train_acc: 0.3742 | val_loss: 2.1120 | val_acc: 0.3657 | test_acc: 0.3687 | Time: 1.8532 s
>>> Epoch [  566/10000]
train_loss: 2.1039 | train_acc: 0.3743 | val_loss: 2.1119 | val_acc: 0.3658 | test_acc: 0.3686 | Time: 1.8800 s
>>> Epoch [  567/10000]
train_loss: 2.1038 | train_acc: 0.3744 | val_loss: 2.1119 | val_acc: 0.3659 | test_acc: 0.3687 | Time: 1.8296 s
>>> Epoch [  568/10000]
train_loss: 2.1037 | train_acc: 0.3745 | val_loss: 2.1118 | val_acc: 0.3660 | test_acc: 0.3687 | Time: 1.9342 s
>>> Epoch [  569/10000]
train_loss: 2.1037 | train_acc: 0.3745 | val_loss: 2.1118 | val_acc: 0.3660 | test_acc: 0.3687 | Time: 1.8253 s
>>> Epoch [  570/10000]
train_loss: 2.1036 | train_acc: 0.3745 | val_loss: 2.1117 | val_acc: 0.3659 | test_acc: 0.3687 | Time: 1.7752 s
>>> Epoch [  571/10000]
train_loss: 2.1036 | train_acc: 0.3745 | val_loss: 2.1117 | val_acc: 0.3658 | test_acc: 0.3687 | Time: 1.8523 s
>>> Epoch [  572/10000]
train_loss: 2.1035 | train_acc: 0.3746 | val_loss: 2.1116 | val_acc: 0.3659 | test_acc: 0.3685 | Time: 1.8831 s
>>> Epoch [  573/10000]
train_loss: 2.1034 | train_acc: 0.3747 | val_loss: 2.1116 | val_acc: 0.3659 | test_acc: 0.3688 | Time: 1.8810 s
>>> Epoch [  574/10000]
train_loss: 2.1034 | train_acc: 0.3747 | val_loss: 2.1115 | val_acc: 0.3662 | test_acc: 0.3686 | Time: 1.7776 s
>>> Epoch [  575/10000]
train_loss: 2.1033 | train_acc: 0.3747 | val_loss: 2.1115 | val_acc: 0.3664 | test_acc: 0.3686 | Time: 1.8449 s
>>> Epoch [  576/10000]
train_loss: 2.1033 | train_acc: 0.3747 | val_loss: 2.1114 | val_acc: 0.3664 | test_acc: 0.3688 | Time: 1.8536 s
>>> Epoch [  577/10000]
train_loss: 2.1032 | train_acc: 0.3748 | val_loss: 2.1114 | val_acc: 0.3662 | test_acc: 0.3687 | Time: 1.8314 s
>>> Epoch [  578/10000]
train_loss: 2.1032 | train_acc: 0.3749 | val_loss: 2.1113 | val_acc: 0.3662 | test_acc: 0.3687 | Time: 1.7988 s
>>> Epoch [  579/10000]
train_loss: 2.1031 | train_acc: 0.3750 | val_loss: 2.1113 | val_acc: 0.3662 | test_acc: 0.3687 | Time: 1.8540 s
>>> Epoch [  580/10000]
train_loss: 2.1030 | train_acc: 0.3750 | val_loss: 2.1112 | val_acc: 0.3662 | test_acc: 0.3687 | Time: 1.7432 s
>>> Epoch [  581/10000]
train_loss: 2.1030 | train_acc: 0.3750 | val_loss: 2.1112 | val_acc: 0.3663 | test_acc: 0.3686 | Time: 1.9091 s
>>> Epoch [  582/10000]
train_loss: 2.1029 | train_acc: 0.3752 | val_loss: 2.1111 | val_acc: 0.3664 | test_acc: 0.3686 | Time: 1.8332 s
>>> Epoch [  583/10000]
train_loss: 2.1029 | train_acc: 0.3752 | val_loss: 2.1111 | val_acc: 0.3663 | test_acc: 0.3686 | Time: 1.7585 s
>>> Epoch [  584/10000]
train_loss: 2.1028 | train_acc: 0.3752 | val_loss: 2.1110 | val_acc: 0.3662 | test_acc: 0.3687 | Time: 1.8280 s
>>> Epoch [  585/10000]
train_loss: 2.1027 | train_acc: 0.3752 | val_loss: 2.1110 | val_acc: 0.3664 | test_acc: 0.3687 | Time: 1.8629 s
>>> Epoch [  586/10000]
train_loss: 2.1027 | train_acc: 0.3752 | val_loss: 2.1109 | val_acc: 0.3664 | test_acc: 0.3687 | Time: 1.7956 s
>>> Epoch [  587/10000]
train_loss: 2.1026 | train_acc: 0.3754 | val_loss: 2.1109 | val_acc: 0.3665 | test_acc: 0.3688 | Time: 1.8459 s
>>> Epoch [  588/10000]
train_loss: 2.1026 | train_acc: 0.3755 | val_loss: 2.1108 | val_acc: 0.3667 | test_acc: 0.3688 | Time: 2.0036 s
>>> Epoch [  589/10000]
train_loss: 2.1025 | train_acc: 0.3755 | val_loss: 2.1108 | val_acc: 0.3668 | test_acc: 0.3690 | Time: 2.0355 s
>>> Epoch [  590/10000]
train_loss: 2.1025 | train_acc: 0.3755 | val_loss: 2.1107 | val_acc: 0.3668 | test_acc: 0.3691 | Time: 1.8621 s
>>> Epoch [  591/10000]
train_loss: 2.1024 | train_acc: 0.3756 | val_loss: 2.1107 | val_acc: 0.3669 | test_acc: 0.3693 | Time: 1.7379 s
>>> Epoch [  592/10000]
train_loss: 2.1023 | train_acc: 0.3757 | val_loss: 2.1106 | val_acc: 0.3669 | test_acc: 0.3692 | Time: 1.9171 s
>>> Epoch [  593/10000]
train_loss: 2.1023 | train_acc: 0.3759 | val_loss: 2.1106 | val_acc: 0.3670 | test_acc: 0.3691 | Time: 1.9465 s
>>> Epoch [  594/10000]
train_loss: 2.1022 | train_acc: 0.3759 | val_loss: 2.1106 | val_acc: 0.3671 | test_acc: 0.3690 | Time: 1.8238 s
>>> Epoch [  595/10000]
train_loss: 2.1022 | train_acc: 0.3760 | val_loss: 2.1105 | val_acc: 0.3671 | test_acc: 0.3692 | Time: 1.8038 s
>>> Epoch [  596/10000]
train_loss: 2.1021 | train_acc: 0.3760 | val_loss: 2.1105 | val_acc: 0.3672 | test_acc: 0.3693 | Time: 1.9478 s
>>> Epoch [  597/10000]
train_loss: 2.1021 | train_acc: 0.3759 | val_loss: 2.1104 | val_acc: 0.3671 | test_acc: 0.3694 | Time: 2.0354 s
>>> Epoch [  598/10000]
train_loss: 2.1020 | train_acc: 0.3759 | val_loss: 2.1104 | val_acc: 0.3671 | test_acc: 0.3695 | Time: 1.8225 s
>>> Epoch [  599/10000]
train_loss: 2.1019 | train_acc: 0.3761 | val_loss: 2.1103 | val_acc: 0.3675 | test_acc: 0.3695 | Time: 1.7327 s
>>> Epoch [  600/10000]
train_loss: 2.1019 | train_acc: 0.3761 | val_loss: 2.1103 | val_acc: 0.3677 | test_acc: 0.3695 | Time: 1.8961 s
>>> Epoch [  601/10000]
train_loss: 2.1018 | train_acc: 0.3761 | val_loss: 2.1102 | val_acc: 0.3677 | test_acc: 0.3698 | Time: 2.0031 s
>>> Epoch [  602/10000]
train_loss: 2.1018 | train_acc: 0.3762 | val_loss: 2.1102 | val_acc: 0.3678 | test_acc: 0.3699 | Time: 1.8343 s
>>> Epoch [  603/10000]
train_loss: 2.1017 | train_acc: 0.3763 | val_loss: 2.1101 | val_acc: 0.3681 | test_acc: 0.3699 | Time: 1.7419 s
>>> Epoch [  604/10000]
train_loss: 2.1017 | train_acc: 0.3764 | val_loss: 2.1101 | val_acc: 0.3681 | test_acc: 0.3699 | Time: 1.8586 s
>>> Epoch [  605/10000]
train_loss: 2.1016 | train_acc: 0.3764 | val_loss: 2.1100 | val_acc: 0.3680 | test_acc: 0.3698 | Time: 1.9025 s
>>> Epoch [  606/10000]
train_loss: 2.1016 | train_acc: 0.3766 | val_loss: 2.1100 | val_acc: 0.3683 | test_acc: 0.3696 | Time: 1.9214 s
>>> Epoch [  607/10000]
train_loss: 2.1015 | train_acc: 0.3765 | val_loss: 2.1099 | val_acc: 0.3684 | test_acc: 0.3698 | Time: 1.7006 s
>>> Epoch [  608/10000]
train_loss: 2.1014 | train_acc: 0.3766 | val_loss: 2.1099 | val_acc: 0.3686 | test_acc: 0.3700 | Time: 1.8303 s
>>> Epoch [  609/10000]
train_loss: 2.1014 | train_acc: 0.3766 | val_loss: 2.1099 | val_acc: 0.3685 | test_acc: 0.3702 | Time: 2.0671 s
>>> Epoch [  610/10000]
train_loss: 2.1013 | train_acc: 0.3766 | val_loss: 2.1098 | val_acc: 0.3684 | test_acc: 0.3705 | Time: 1.8728 s
>>> Epoch [  611/10000]
train_loss: 2.1013 | train_acc: 0.3766 | val_loss: 2.1098 | val_acc: 0.3684 | test_acc: 0.3705 | Time: 1.8636 s
>>> Epoch [  612/10000]
train_loss: 2.1012 | train_acc: 0.3766 | val_loss: 2.1097 | val_acc: 0.3684 | test_acc: 0.3705 | Time: 1.8610 s
>>> Epoch [  613/10000]
train_loss: 2.1012 | train_acc: 0.3766 | val_loss: 2.1097 | val_acc: 0.3684 | test_acc: 0.3706 | Time: 1.9947 s
>>> Epoch [  614/10000]
train_loss: 2.1011 | train_acc: 0.3766 | val_loss: 2.1096 | val_acc: 0.3685 | test_acc: 0.3706 | Time: 1.8591 s
>>> Epoch [  615/10000]
train_loss: 2.1011 | train_acc: 0.3766 | val_loss: 2.1096 | val_acc: 0.3686 | test_acc: 0.3707 | Time: 1.8902 s
>>> Epoch [  616/10000]
train_loss: 2.1010 | train_acc: 0.3767 | val_loss: 2.1095 | val_acc: 0.3686 | test_acc: 0.3707 | Time: 1.8996 s
>>> Epoch [  617/10000]
train_loss: 2.1009 | train_acc: 0.3768 | val_loss: 2.1095 | val_acc: 0.3685 | test_acc: 0.3709 | Time: 1.7991 s
>>> Epoch [  618/10000]
train_loss: 2.1009 | train_acc: 0.3768 | val_loss: 2.1094 | val_acc: 0.3686 | test_acc: 0.3709 | Time: 2.0033 s
>>> Epoch [  619/10000]
train_loss: 2.1008 | train_acc: 0.3768 | val_loss: 2.1094 | val_acc: 0.3684 | test_acc: 0.3709 | Time: 2.0373 s
>>> Epoch [  620/10000]
train_loss: 2.1008 | train_acc: 0.3769 | val_loss: 2.1093 | val_acc: 0.3684 | test_acc: 0.3709 | Time: 2.1686 s
>>> Epoch [  621/10000]
train_loss: 2.1007 | train_acc: 0.3770 | val_loss: 2.1093 | val_acc: 0.3686 | test_acc: 0.3709 | Time: 1.8483 s
>>> Epoch [  622/10000]
train_loss: 2.1007 | train_acc: 0.3770 | val_loss: 2.1093 | val_acc: 0.3687 | test_acc: 0.3708 | Time: 1.8479 s
>>> Epoch [  623/10000]
train_loss: 2.1006 | train_acc: 0.3770 | val_loss: 2.1092 | val_acc: 0.3688 | test_acc: 0.3706 | Time: 1.8599 s
>>> Epoch [  624/10000]
train_loss: 2.1006 | train_acc: 0.3771 | val_loss: 2.1092 | val_acc: 0.3687 | test_acc: 0.3707 | Time: 1.9509 s
>>> Epoch [  625/10000]
train_loss: 2.1005 | train_acc: 0.3771 | val_loss: 2.1091 | val_acc: 0.3688 | test_acc: 0.3707 | Time: 1.9170 s
>>> Epoch [  626/10000]
train_loss: 2.1005 | train_acc: 0.3772 | val_loss: 2.1091 | val_acc: 0.3688 | test_acc: 0.3705 | Time: 2.0149 s
>>> Epoch [  627/10000]
train_loss: 2.1004 | train_acc: 0.3773 | val_loss: 2.1090 | val_acc: 0.3687 | test_acc: 0.3706 | Time: 1.7763 s
>>> Epoch [  628/10000]
train_loss: 2.1004 | train_acc: 0.3773 | val_loss: 2.1090 | val_acc: 0.3687 | test_acc: 0.3706 | Time: 1.8645 s
>>> Epoch [  629/10000]
train_loss: 2.1003 | train_acc: 0.3774 | val_loss: 2.1089 | val_acc: 0.3688 | test_acc: 0.3708 | Time: 1.8169 s
>>> Epoch [  630/10000]
train_loss: 2.1002 | train_acc: 0.3775 | val_loss: 2.1089 | val_acc: 0.3689 | test_acc: 0.3711 | Time: 1.7602 s
>>> Epoch [  631/10000]
train_loss: 2.1002 | train_acc: 0.3776 | val_loss: 2.1089 | val_acc: 0.3688 | test_acc: 0.3712 | Time: 1.8792 s
>>> Epoch [  632/10000]
train_loss: 2.1001 | train_acc: 0.3777 | val_loss: 2.1088 | val_acc: 0.3686 | test_acc: 0.3714 | Time: 1.9343 s
>>> Epoch [  633/10000]
train_loss: 2.1001 | train_acc: 0.3778 | val_loss: 2.1088 | val_acc: 0.3687 | test_acc: 0.3716 | Time: 1.9840 s
>>> Epoch [  634/10000]
train_loss: 2.1000 | train_acc: 0.3778 | val_loss: 2.1087 | val_acc: 0.3687 | test_acc: 0.3718 | Time: 1.9267 s
>>> Epoch [  635/10000]
train_loss: 2.1000 | train_acc: 0.3780 | val_loss: 2.1087 | val_acc: 0.3686 | test_acc: 0.3720 | Time: 1.8854 s
>>> Epoch [  636/10000]
train_loss: 2.0999 | train_acc: 0.3779 | val_loss: 2.1086 | val_acc: 0.3687 | test_acc: 0.3722 | Time: 1.8745 s
>>> Epoch [  637/10000]
train_loss: 2.0999 | train_acc: 0.3779 | val_loss: 2.1086 | val_acc: 0.3687 | test_acc: 0.3722 | Time: 1.9655 s
>>> Epoch [  638/10000]
train_loss: 2.0998 | train_acc: 0.3779 | val_loss: 2.1086 | val_acc: 0.3687 | test_acc: 0.3723 | Time: 1.9045 s
>>> Epoch [  639/10000]
train_loss: 2.0998 | train_acc: 0.3779 | val_loss: 2.1085 | val_acc: 0.3686 | test_acc: 0.3723 | Time: 1.9944 s
>>> Epoch [  640/10000]
train_loss: 2.0997 | train_acc: 0.3780 | val_loss: 2.1085 | val_acc: 0.3686 | test_acc: 0.3722 | Time: 1.9891 s
>>> Epoch [  641/10000]
train_loss: 2.0997 | train_acc: 0.3780 | val_loss: 2.1084 | val_acc: 0.3685 | test_acc: 0.3723 | Time: 1.9252 s
>>> Epoch [  642/10000]
train_loss: 2.0996 | train_acc: 0.3780 | val_loss: 2.1084 | val_acc: 0.3684 | test_acc: 0.3725 | Time: 1.9153 s
>>> Epoch [  643/10000]
train_loss: 2.0996 | train_acc: 0.3781 | val_loss: 2.1083 | val_acc: 0.3684 | test_acc: 0.3726 | Time: 2.0912 s
>>> Epoch [  644/10000]
train_loss: 2.0995 | train_acc: 0.3780 | val_loss: 2.1083 | val_acc: 0.3685 | test_acc: 0.3727 | Time: 1.5957 s
>>> Epoch [  645/10000]
train_loss: 2.0995 | train_acc: 0.3781 | val_loss: 2.1082 | val_acc: 0.3682 | test_acc: 0.3728 | Time: 1.4860 s
>>> Epoch [  646/10000]
train_loss: 2.0994 | train_acc: 0.3782 | val_loss: 2.1082 | val_acc: 0.3682 | test_acc: 0.3728 | Time: 1.5222 s
>>> Epoch [  647/10000]
train_loss: 2.0994 | train_acc: 0.3783 | val_loss: 2.1082 | val_acc: 0.3682 | test_acc: 0.3727 | Time: 1.5300 s
>>> Epoch [  648/10000]
train_loss: 2.0993 | train_acc: 0.3784 | val_loss: 2.1081 | val_acc: 0.3683 | test_acc: 0.3730 | Time: 1.7075 s
>>> Epoch [  649/10000]
train_loss: 2.0993 | train_acc: 0.3784 | val_loss: 2.1081 | val_acc: 0.3683 | test_acc: 0.3729 | Time: 1.6117 s
>>> Epoch [  650/10000]
train_loss: 2.0992 | train_acc: 0.3785 | val_loss: 2.1080 | val_acc: 0.3683 | test_acc: 0.3730 | Time: 1.6628 s
>>> Epoch [  651/10000]
train_loss: 2.0991 | train_acc: 0.3786 | val_loss: 2.1080 | val_acc: 0.3682 | test_acc: 0.3731 | Time: 1.7046 s
>>> Epoch [  652/10000]
train_loss: 2.0991 | train_acc: 0.3785 | val_loss: 2.1079 | val_acc: 0.3684 | test_acc: 0.3730 | Time: 1.7717 s
>>> Epoch [  653/10000]
train_loss: 2.0990 | train_acc: 0.3786 | val_loss: 2.1079 | val_acc: 0.3683 | test_acc: 0.3730 | Time: 2.1403 s
>>> Epoch [  654/10000]
train_loss: 2.0990 | train_acc: 0.3786 | val_loss: 2.1079 | val_acc: 0.3683 | test_acc: 0.3728 | Time: 2.1669 s
>>> Epoch [  655/10000]
train_loss: 2.0989 | train_acc: 0.3787 | val_loss: 2.1078 | val_acc: 0.3686 | test_acc: 0.3726 | Time: 1.9653 s
>>> Epoch [  656/10000]
train_loss: 2.0989 | train_acc: 0.3787 | val_loss: 2.1078 | val_acc: 0.3688 | test_acc: 0.3727 | Time: 2.0388 s
>>> Epoch [  657/10000]
train_loss: 2.0988 | train_acc: 0.3788 | val_loss: 2.1077 | val_acc: 0.3688 | test_acc: 0.3728 | Time: 1.7608 s
>>> Epoch [  658/10000]
train_loss: 2.0988 | train_acc: 0.3788 | val_loss: 2.1077 | val_acc: 0.3688 | test_acc: 0.3728 | Time: 1.7983 s
>>> Epoch [  659/10000]
train_loss: 2.0987 | train_acc: 0.3788 | val_loss: 2.1077 | val_acc: 0.3688 | test_acc: 0.3729 | Time: 2.8647 s
>>> Epoch [  660/10000]
train_loss: 2.0987 | train_acc: 0.3789 | val_loss: 2.1076 | val_acc: 0.3690 | test_acc: 0.3729 | Time: 3.0213 s
>>> Epoch [  661/10000]
train_loss: 2.0986 | train_acc: 0.3789 | val_loss: 2.1076 | val_acc: 0.3691 | test_acc: 0.3729 | Time: 2.4449 s
>>> Epoch [  662/10000]
train_loss: 2.0986 | train_acc: 0.3790 | val_loss: 2.1075 | val_acc: 0.3691 | test_acc: 0.3730 | Time: 2.2026 s
>>> Epoch [  663/10000]
train_loss: 2.0985 | train_acc: 0.3791 | val_loss: 2.1075 | val_acc: 0.3692 | test_acc: 0.3730 | Time: 2.1624 s
>>> Epoch [  664/10000]
train_loss: 2.0985 | train_acc: 0.3792 | val_loss: 2.1074 | val_acc: 0.3693 | test_acc: 0.3732 | Time: 2.9188 s
>>> Epoch [  665/10000]
train_loss: 2.0984 | train_acc: 0.3792 | val_loss: 2.1074 | val_acc: 0.3693 | test_acc: 0.3734 | Time: 2.8144 s
>>> Epoch [  666/10000]
train_loss: 2.0984 | train_acc: 0.3792 | val_loss: 2.1074 | val_acc: 0.3693 | test_acc: 0.3735 | Time: 2.4955 s
>>> Epoch [  667/10000]
train_loss: 2.0983 | train_acc: 0.3792 | val_loss: 2.1073 | val_acc: 0.3692 | test_acc: 0.3735 | Time: 2.0321 s
>>> Epoch [  668/10000]
train_loss: 2.0983 | train_acc: 0.3793 | val_loss: 2.1073 | val_acc: 0.3692 | test_acc: 0.3732 | Time: 1.9430 s
>>> Epoch [  669/10000]
train_loss: 2.0982 | train_acc: 0.3794 | val_loss: 2.1072 | val_acc: 0.3692 | test_acc: 0.3734 | Time: 1.7233 s
>>> Epoch [  670/10000]
train_loss: 2.0982 | train_acc: 0.3795 | val_loss: 2.1072 | val_acc: 0.3692 | test_acc: 0.3734 | Time: 1.8218 s
>>> Epoch [  671/10000]
train_loss: 2.0981 | train_acc: 0.3794 | val_loss: 2.1072 | val_acc: 0.3693 | test_acc: 0.3733 | Time: 1.6732 s
>>> Epoch [  672/10000]
train_loss: 2.0981 | train_acc: 0.3795 | val_loss: 2.1071 | val_acc: 0.3693 | test_acc: 0.3733 | Time: 2.2469 s
>>> Epoch [  673/10000]
train_loss: 2.0980 | train_acc: 0.3796 | val_loss: 2.1071 | val_acc: 0.3693 | test_acc: 0.3736 | Time: 2.1222 s
>>> Epoch [  674/10000]
train_loss: 2.0980 | train_acc: 0.3796 | val_loss: 2.1070 | val_acc: 0.3693 | test_acc: 0.3737 | Time: 1.9936 s
>>> Epoch [  675/10000]
train_loss: 2.0979 | train_acc: 0.3798 | val_loss: 2.1070 | val_acc: 0.3695 | test_acc: 0.3737 | Time: 2.0525 s
>>> Epoch [  676/10000]
train_loss: 2.0979 | train_acc: 0.3798 | val_loss: 2.1070 | val_acc: 0.3695 | test_acc: 0.3736 | Time: 1.8116 s
>>> Epoch [  677/10000]
train_loss: 2.0978 | train_acc: 0.3797 | val_loss: 2.1069 | val_acc: 0.3696 | test_acc: 0.3737 | Time: 1.7972 s
>>> Epoch [  678/10000]
train_loss: 2.0978 | train_acc: 0.3798 | val_loss: 2.1069 | val_acc: 0.3696 | test_acc: 0.3737 | Time: 2.5081 s
>>> Epoch [  679/10000]
train_loss: 2.0977 | train_acc: 0.3798 | val_loss: 2.1068 | val_acc: 0.3697 | test_acc: 0.3738 | Time: 2.5412 s
>>> Epoch [  680/10000]
train_loss: 2.0977 | train_acc: 0.3798 | val_loss: 2.1068 | val_acc: 0.3697 | test_acc: 0.3736 | Time: 1.8675 s
>>> Epoch [  681/10000]
train_loss: 2.0976 | train_acc: 0.3799 | val_loss: 2.1067 | val_acc: 0.3698 | test_acc: 0.3738 | Time: 1.9476 s
>>> Epoch [  682/10000]
train_loss: 2.0976 | train_acc: 0.3798 | val_loss: 2.1067 | val_acc: 0.3698 | test_acc: 0.3738 | Time: 1.9707 s
>>> Epoch [  683/10000]
train_loss: 2.0976 | train_acc: 0.3799 | val_loss: 2.1067 | val_acc: 0.3698 | test_acc: 0.3737 | Time: 2.0730 s
>>> Epoch [  684/10000]
train_loss: 2.0975 | train_acc: 0.3799 | val_loss: 2.1066 | val_acc: 0.3698 | test_acc: 0.3739 | Time: 2.1282 s
>>> Epoch [  685/10000]
train_loss: 2.0975 | train_acc: 0.3799 | val_loss: 2.1066 | val_acc: 0.3698 | test_acc: 0.3737 | Time: 2.0246 s
>>> Epoch [  686/10000]
train_loss: 2.0974 | train_acc: 0.3800 | val_loss: 2.1065 | val_acc: 0.3697 | test_acc: 0.3737 | Time: 2.0408 s
>>> Epoch [  687/10000]
train_loss: 2.0974 | train_acc: 0.3800 | val_loss: 2.1065 | val_acc: 0.3697 | test_acc: 0.3737 | Time: 1.9962 s
>>> Epoch [  688/10000]
train_loss: 2.0973 | train_acc: 0.3800 | val_loss: 2.1065 | val_acc: 0.3698 | test_acc: 0.3735 | Time: 1.9725 s
>>> Epoch [  689/10000]
train_loss: 2.0973 | train_acc: 0.3801 | val_loss: 2.1064 | val_acc: 0.3698 | test_acc: 0.3736 | Time: 2.0441 s
>>> Epoch [  690/10000]
train_loss: 2.0972 | train_acc: 0.3801 | val_loss: 2.1064 | val_acc: 0.3700 | test_acc: 0.3737 | Time: 2.1047 s
>>> Epoch [  691/10000]
train_loss: 2.0972 | train_acc: 0.3800 | val_loss: 2.1063 | val_acc: 0.3701 | test_acc: 0.3738 | Time: 2.0551 s
>>> Epoch [  692/10000]
train_loss: 2.0971 | train_acc: 0.3801 | val_loss: 2.1063 | val_acc: 0.3702 | test_acc: 0.3738 | Time: 1.9154 s
>>> Epoch [  693/10000]
train_loss: 2.0971 | train_acc: 0.3801 | val_loss: 2.1063 | val_acc: 0.3704 | test_acc: 0.3738 | Time: 2.1203 s
>>> Epoch [  694/10000]
train_loss: 2.0970 | train_acc: 0.3802 | val_loss: 2.1062 | val_acc: 0.3704 | test_acc: 0.3740 | Time: 2.0892 s
>>> Epoch [  695/10000]
train_loss: 2.0970 | train_acc: 0.3803 | val_loss: 2.1062 | val_acc: 0.3703 | test_acc: 0.3740 | Time: 2.0573 s
>>> Epoch [  696/10000]
train_loss: 2.0969 | train_acc: 0.3804 | val_loss: 2.1061 | val_acc: 0.3704 | test_acc: 0.3742 | Time: 2.1828 s
>>> Epoch [  697/10000]
train_loss: 2.0969 | train_acc: 0.3805 | val_loss: 2.1061 | val_acc: 0.3706 | test_acc: 0.3745 | Time: 2.1623 s
>>> Epoch [  698/10000]
train_loss: 2.0968 | train_acc: 0.3805 | val_loss: 2.1061 | val_acc: 0.3706 | test_acc: 0.3745 | Time: 2.1007 s
>>> Epoch [  699/10000]
train_loss: 2.0968 | train_acc: 0.3806 | val_loss: 2.1060 | val_acc: 0.3708 | test_acc: 0.3744 | Time: 2.0272 s
>>> Epoch [  700/10000]
train_loss: 2.0967 | train_acc: 0.3807 | val_loss: 2.1060 | val_acc: 0.3708 | test_acc: 0.3746 | Time: 1.9176 s
>>> Epoch [  701/10000]
train_loss: 2.0967 | train_acc: 0.3807 | val_loss: 2.1060 | val_acc: 0.3708 | test_acc: 0.3747 | Time: 2.0499 s
>>> Epoch [  702/10000]
train_loss: 2.0966 | train_acc: 0.3808 | val_loss: 2.1059 | val_acc: 0.3709 | test_acc: 0.3748 | Time: 2.0326 s
>>> Epoch [  703/10000]
train_loss: 2.0966 | train_acc: 0.3809 | val_loss: 2.1059 | val_acc: 0.3710 | test_acc: 0.3747 | Time: 2.1019 s
>>> Epoch [  704/10000]
train_loss: 2.0966 | train_acc: 0.3808 | val_loss: 2.1058 | val_acc: 0.3710 | test_acc: 0.3750 | Time: 2.0410 s
>>> Epoch [  705/10000]
train_loss: 2.0965 | train_acc: 0.3809 | val_loss: 2.1058 | val_acc: 0.3710 | test_acc: 0.3752 | Time: 2.0391 s
>>> Epoch [  706/10000]
train_loss: 2.0965 | train_acc: 0.3808 | val_loss: 2.1058 | val_acc: 0.3711 | test_acc: 0.3753 | Time: 2.0798 s
>>> Epoch [  707/10000]
train_loss: 2.0964 | train_acc: 0.3808 | val_loss: 2.1057 | val_acc: 0.3711 | test_acc: 0.3754 | Time: 2.0279 s
>>> Epoch [  708/10000]
train_loss: 2.0964 | train_acc: 0.3809 | val_loss: 2.1057 | val_acc: 0.3711 | test_acc: 0.3755 | Time: 2.2045 s
>>> Epoch [  709/10000]
train_loss: 2.0963 | train_acc: 0.3810 | val_loss: 2.1056 | val_acc: 0.3711 | test_acc: 0.3755 | Time: 2.1442 s
>>> Epoch [  710/10000]
train_loss: 2.0963 | train_acc: 0.3810 | val_loss: 2.1056 | val_acc: 0.3710 | test_acc: 0.3755 | Time: 2.0123 s
>>> Epoch [  711/10000]
train_loss: 2.0962 | train_acc: 0.3810 | val_loss: 2.1056 | val_acc: 0.3709 | test_acc: 0.3756 | Time: 1.8611 s
>>> Epoch [  712/10000]
train_loss: 2.0962 | train_acc: 0.3812 | val_loss: 2.1055 | val_acc: 0.3710 | test_acc: 0.3757 | Time: 2.1691 s
>>> Epoch [  713/10000]
train_loss: 2.0961 | train_acc: 0.3812 | val_loss: 2.1055 | val_acc: 0.3708 | test_acc: 0.3757 | Time: 2.1197 s
>>> Epoch [  714/10000]
train_loss: 2.0961 | train_acc: 0.3813 | val_loss: 2.1054 | val_acc: 0.3709 | test_acc: 0.3757 | Time: 2.2324 s
>>> Epoch [  715/10000]
train_loss: 2.0960 | train_acc: 0.3813 | val_loss: 2.1054 | val_acc: 0.3709 | test_acc: 0.3756 | Time: 1.9831 s
>>> Epoch [  716/10000]
train_loss: 2.0960 | train_acc: 0.3813 | val_loss: 2.1054 | val_acc: 0.3709 | test_acc: 0.3756 | Time: 2.0544 s
>>> Epoch [  717/10000]
train_loss: 2.0959 | train_acc: 0.3813 | val_loss: 2.1053 | val_acc: 0.3709 | test_acc: 0.3756 | Time: 1.9736 s
>>> Epoch [  718/10000]
train_loss: 2.0959 | train_acc: 0.3813 | val_loss: 2.1053 | val_acc: 0.3709 | test_acc: 0.3756 | Time: 2.1283 s
>>> Epoch [  719/10000]
train_loss: 2.0959 | train_acc: 0.3813 | val_loss: 2.1053 | val_acc: 0.3708 | test_acc: 0.3757 | Time: 2.1906 s
>>> Epoch [  720/10000]
train_loss: 2.0958 | train_acc: 0.3814 | val_loss: 2.1052 | val_acc: 0.3708 | test_acc: 0.3756 | Time: 2.2947 s
>>> Epoch [  721/10000]
train_loss: 2.0958 | train_acc: 0.3814 | val_loss: 2.1052 | val_acc: 0.3707 | test_acc: 0.3756 | Time: 2.0889 s
>>> Epoch [  722/10000]
train_loss: 2.0957 | train_acc: 0.3815 | val_loss: 2.1051 | val_acc: 0.3706 | test_acc: 0.3756 | Time: 1.9848 s
>>> Epoch [  723/10000]
train_loss: 2.0957 | train_acc: 0.3816 | val_loss: 2.1051 | val_acc: 0.3703 | test_acc: 0.3756 | Time: 2.0720 s
>>> Epoch [  724/10000]
train_loss: 2.0956 | train_acc: 0.3816 | val_loss: 2.1051 | val_acc: 0.3704 | test_acc: 0.3756 | Time: 2.1407 s
>>> Epoch [  725/10000]
train_loss: 2.0956 | train_acc: 0.3816 | val_loss: 2.1050 | val_acc: 0.3704 | test_acc: 0.3754 | Time: 2.1973 s
>>> Epoch [  726/10000]
train_loss: 2.0955 | train_acc: 0.3817 | val_loss: 2.1050 | val_acc: 0.3704 | test_acc: 0.3754 | Time: 2.0248 s
>>> Epoch [  727/10000]
train_loss: 2.0955 | train_acc: 0.3820 | val_loss: 2.1050 | val_acc: 0.3707 | test_acc: 0.3754 | Time: 2.0511 s
>>> Epoch [  728/10000]
train_loss: 2.0954 | train_acc: 0.3819 | val_loss: 2.1049 | val_acc: 0.3707 | test_acc: 0.3754 | Time: 2.2463 s
>>> Epoch [  729/10000]
train_loss: 2.0954 | train_acc: 0.3820 | val_loss: 2.1049 | val_acc: 0.3709 | test_acc: 0.3754 | Time: 2.0788 s
>>> Epoch [  730/10000]
train_loss: 2.0954 | train_acc: 0.3821 | val_loss: 2.1048 | val_acc: 0.3708 | test_acc: 0.3755 | Time: 2.2203 s
>>> Epoch [  731/10000]
train_loss: 2.0953 | train_acc: 0.3821 | val_loss: 2.1048 | val_acc: 0.3709 | test_acc: 0.3755 | Time: 2.2014 s
>>> Epoch [  732/10000]
train_loss: 2.0953 | train_acc: 0.3821 | val_loss: 2.1048 | val_acc: 0.3709 | test_acc: 0.3755 | Time: 2.1917 s
>>> Epoch [  733/10000]
train_loss: 2.0952 | train_acc: 0.3821 | val_loss: 2.1047 | val_acc: 0.3709 | test_acc: 0.3754 | Time: 2.1056 s
>>> Epoch [  734/10000]
train_loss: 2.0952 | train_acc: 0.3821 | val_loss: 2.1047 | val_acc: 0.3710 | test_acc: 0.3754 | Time: 2.1202 s
>>> Epoch [  735/10000]
train_loss: 2.0951 | train_acc: 0.3822 | val_loss: 2.1047 | val_acc: 0.3712 | test_acc: 0.3754 | Time: 2.1330 s
>>> Epoch [  736/10000]
train_loss: 2.0951 | train_acc: 0.3822 | val_loss: 2.1046 | val_acc: 0.3714 | test_acc: 0.3756 | Time: 2.0715 s
>>> Epoch [  737/10000]
train_loss: 2.0950 | train_acc: 0.3822 | val_loss: 2.1046 | val_acc: 0.3716 | test_acc: 0.3756 | Time: 2.1026 s
>>> Epoch [  738/10000]
train_loss: 2.0950 | train_acc: 0.3822 | val_loss: 2.1045 | val_acc: 0.3717 | test_acc: 0.3756 | Time: 2.2031 s
>>> Epoch [  739/10000]
train_loss: 2.0950 | train_acc: 0.3822 | val_loss: 2.1045 | val_acc: 0.3717 | test_acc: 0.3757 | Time: 2.0179 s
>>> Epoch [  740/10000]
train_loss: 2.0949 | train_acc: 0.3823 | val_loss: 2.1045 | val_acc: 0.3717 | test_acc: 0.3757 | Time: 2.1661 s
>>> Epoch [  741/10000]
train_loss: 2.0949 | train_acc: 0.3824 | val_loss: 2.1044 | val_acc: 0.3717 | test_acc: 0.3757 | Time: 2.1279 s
>>> Epoch [  742/10000]
train_loss: 2.0948 | train_acc: 0.3824 | val_loss: 2.1044 | val_acc: 0.3718 | test_acc: 0.3758 | Time: 2.0639 s
>>> Epoch [  743/10000]
train_loss: 2.0948 | train_acc: 0.3823 | val_loss: 2.1044 | val_acc: 0.3718 | test_acc: 0.3758 | Time: 2.1664 s
>>> Epoch [  744/10000]
train_loss: 2.0947 | train_acc: 0.3823 | val_loss: 2.1043 | val_acc: 0.3717 | test_acc: 0.3757 | Time: 2.1756 s
>>> Epoch [  745/10000]
train_loss: 2.0947 | train_acc: 0.3824 | val_loss: 2.1043 | val_acc: 0.3718 | test_acc: 0.3758 | Time: 2.2136 s
>>> Epoch [  746/10000]
train_loss: 2.0947 | train_acc: 0.3824 | val_loss: 2.1043 | val_acc: 0.3718 | test_acc: 0.3759 | Time: 2.2104 s
>>> Epoch [  747/10000]
train_loss: 2.0946 | train_acc: 0.3824 | val_loss: 2.1042 | val_acc: 0.3718 | test_acc: 0.3759 | Time: 2.1761 s
>>> Epoch [  748/10000]
train_loss: 2.0946 | train_acc: 0.3824 | val_loss: 2.1042 | val_acc: 0.3718 | test_acc: 0.3760 | Time: 2.1156 s
>>> Epoch [  749/10000]
train_loss: 2.0945 | train_acc: 0.3825 | val_loss: 2.1041 | val_acc: 0.3718 | test_acc: 0.3761 | Time: 2.1657 s
>>> Epoch [  750/10000]
train_loss: 2.0945 | train_acc: 0.3826 | val_loss: 2.1041 | val_acc: 0.3718 | test_acc: 0.3761 | Time: 2.2723 s
>>> Epoch [  751/10000]
train_loss: 2.0944 | train_acc: 0.3828 | val_loss: 2.1041 | val_acc: 0.3718 | test_acc: 0.3762 | Time: 2.0985 s
>>> Epoch [  752/10000]
train_loss: 2.0944 | train_acc: 0.3828 | val_loss: 2.1040 | val_acc: 0.3718 | test_acc: 0.3761 | Time: 2.2290 s
>>> Epoch [  753/10000]
train_loss: 2.0943 | train_acc: 0.3828 | val_loss: 2.1040 | val_acc: 0.3720 | test_acc: 0.3762 | Time: 2.0817 s
>>> Epoch [  754/10000]
train_loss: 2.0943 | train_acc: 0.3829 | val_loss: 2.1040 | val_acc: 0.3721 | test_acc: 0.3761 | Time: 1.9773 s
>>> Epoch [  755/10000]
train_loss: 2.0943 | train_acc: 0.3829 | val_loss: 2.1039 | val_acc: 0.3720 | test_acc: 0.3761 | Time: 2.0935 s
>>> Epoch [  756/10000]
train_loss: 2.0942 | train_acc: 0.3828 | val_loss: 2.1039 | val_acc: 0.3721 | test_acc: 0.3759 | Time: 2.9027 s
>>> Epoch [  757/10000]
train_loss: 2.0942 | train_acc: 0.3828 | val_loss: 2.1039 | val_acc: 0.3721 | test_acc: 0.3761 | Time: 3.1546 s
>>> Epoch [  758/10000]
train_loss: 2.0941 | train_acc: 0.3829 | val_loss: 2.1038 | val_acc: 0.3720 | test_acc: 0.3761 | Time: 3.3667 s
>>> Epoch [  759/10000]
train_loss: 2.0941 | train_acc: 0.3830 | val_loss: 2.1038 | val_acc: 0.3720 | test_acc: 0.3762 | Time: 3.4156 s
>>> Epoch [  760/10000]
train_loss: 2.0940 | train_acc: 0.3830 | val_loss: 2.1037 | val_acc: 0.3721 | test_acc: 0.3764 | Time: 3.4571 s
>>> Epoch [  761/10000]
train_loss: 2.0940 | train_acc: 0.3830 | val_loss: 2.1037 | val_acc: 0.3723 | test_acc: 0.3764 | Time: 3.3018 s
>>> Epoch [  762/10000]
train_loss: 2.0940 | train_acc: 0.3830 | val_loss: 2.1037 | val_acc: 0.3724 | test_acc: 0.3764 | Time: 2.0120 s
>>> Epoch [  763/10000]
train_loss: 2.0939 | train_acc: 0.3830 | val_loss: 2.1036 | val_acc: 0.3723 | test_acc: 0.3765 | Time: 1.9357 s
>>> Epoch [  764/10000]
train_loss: 2.0939 | train_acc: 0.3831 | val_loss: 2.1036 | val_acc: 0.3725 | test_acc: 0.3767 | Time: 1.8733 s
>>> Epoch [  765/10000]
train_loss: 2.0938 | train_acc: 0.3831 | val_loss: 2.1036 | val_acc: 0.3724 | test_acc: 0.3769 | Time: 2.0794 s
>>> Epoch [  766/10000]
train_loss: 2.0938 | train_acc: 0.3831 | val_loss: 2.1035 | val_acc: 0.3725 | test_acc: 0.3769 | Time: 1.9760 s
>>> Epoch [  767/10000]
train_loss: 2.0937 | train_acc: 0.3831 | val_loss: 2.1035 | val_acc: 0.3725 | test_acc: 0.3769 | Time: 2.0615 s
>>> Epoch [  768/10000]
train_loss: 2.0937 | train_acc: 0.3831 | val_loss: 2.1035 | val_acc: 0.3725 | test_acc: 0.3771 | Time: 2.0526 s
>>> Epoch [  769/10000]
train_loss: 2.0937 | train_acc: 0.3831 | val_loss: 2.1034 | val_acc: 0.3724 | test_acc: 0.3772 | Time: 2.0378 s
>>> Epoch [  770/10000]
train_loss: 2.0936 | train_acc: 0.3832 | val_loss: 2.1034 | val_acc: 0.3723 | test_acc: 0.3773 | Time: 2.0720 s
>>> Epoch [  771/10000]
train_loss: 2.0936 | train_acc: 0.3833 | val_loss: 2.1034 | val_acc: 0.3723 | test_acc: 0.3774 | Time: 2.0236 s
>>> Epoch [  772/10000]
train_loss: 2.0935 | train_acc: 0.3833 | val_loss: 2.1033 | val_acc: 0.3723 | test_acc: 0.3774 | Time: 1.8705 s
>>> Epoch [  773/10000]
train_loss: 2.0935 | train_acc: 0.3833 | val_loss: 2.1033 | val_acc: 0.3723 | test_acc: 0.3775 | Time: 2.0061 s
>>> Epoch [  774/10000]
train_loss: 2.0935 | train_acc: 0.3834 | val_loss: 2.1033 | val_acc: 0.3723 | test_acc: 0.3776 | Time: 2.0865 s
>>> Epoch [  775/10000]
train_loss: 2.0934 | train_acc: 0.3834 | val_loss: 2.1032 | val_acc: 0.3723 | test_acc: 0.3776 | Time: 2.0354 s
>>> Epoch [  776/10000]
train_loss: 2.0934 | train_acc: 0.3834 | val_loss: 2.1032 | val_acc: 0.3721 | test_acc: 0.3777 | Time: 1.8922 s
>>> Epoch [  777/10000]
train_loss: 2.0933 | train_acc: 0.3834 | val_loss: 2.1031 | val_acc: 0.3721 | test_acc: 0.3778 | Time: 2.0035 s
>>> Epoch [  778/10000]
train_loss: 2.0933 | train_acc: 0.3835 | val_loss: 2.1031 | val_acc: 0.3721 | test_acc: 0.3779 | Time: 2.0140 s
>>> Epoch [  779/10000]
train_loss: 2.0932 | train_acc: 0.3835 | val_loss: 2.1031 | val_acc: 0.3722 | test_acc: 0.3779 | Time: 2.0902 s
>>> Epoch [  780/10000]
train_loss: 2.0932 | train_acc: 0.3835 | val_loss: 2.1030 | val_acc: 0.3722 | test_acc: 0.3779 | Time: 1.9776 s
>>> Epoch [  781/10000]
train_loss: 2.0932 | train_acc: 0.3835 | val_loss: 2.1030 | val_acc: 0.3723 | test_acc: 0.3778 | Time: 2.1948 s
>>> Epoch [  782/10000]
train_loss: 2.0931 | train_acc: 0.3836 | val_loss: 2.1030 | val_acc: 0.3725 | test_acc: 0.3780 | Time: 2.0178 s
>>> Epoch [  783/10000]
train_loss: 2.0931 | train_acc: 0.3836 | val_loss: 2.1029 | val_acc: 0.3726 | test_acc: 0.3781 | Time: 2.0334 s
>>> Epoch [  784/10000]
train_loss: 2.0930 | train_acc: 0.3837 | val_loss: 2.1029 | val_acc: 0.3726 | test_acc: 0.3780 | Time: 2.1202 s
>>> Epoch [  785/10000]
train_loss: 2.0930 | train_acc: 0.3836 | val_loss: 2.1029 | val_acc: 0.3725 | test_acc: 0.3780 | Time: 2.1098 s
>>> Epoch [  786/10000]
train_loss: 2.0930 | train_acc: 0.3837 | val_loss: 2.1028 | val_acc: 0.3725 | test_acc: 0.3781 | Time: 2.0563 s
>>> Epoch [  787/10000]
train_loss: 2.0929 | train_acc: 0.3837 | val_loss: 2.1028 | val_acc: 0.3725 | test_acc: 0.3781 | Time: 2.1303 s
>>> Epoch [  788/10000]
train_loss: 2.0929 | train_acc: 0.3837 | val_loss: 2.1028 | val_acc: 0.3724 | test_acc: 0.3782 | Time: 2.0800 s
>>> Epoch [  789/10000]
train_loss: 2.0928 | train_acc: 0.3837 | val_loss: 2.1027 | val_acc: 0.3723 | test_acc: 0.3782 | Time: 2.0068 s
>>> Epoch [  790/10000]
train_loss: 2.0928 | train_acc: 0.3837 | val_loss: 2.1027 | val_acc: 0.3723 | test_acc: 0.3784 | Time: 2.0118 s
>>> Epoch [  791/10000]
train_loss: 2.0927 | train_acc: 0.3838 | val_loss: 2.1027 | val_acc: 0.3724 | test_acc: 0.3783 | Time: 1.9512 s
>>> Epoch [  792/10000]
train_loss: 2.0927 | train_acc: 0.3840 | val_loss: 2.1026 | val_acc: 0.3722 | test_acc: 0.3783 | Time: 2.1802 s
>>> Epoch [  793/10000]
train_loss: 2.0927 | train_acc: 0.3840 | val_loss: 2.1026 | val_acc: 0.3721 | test_acc: 0.3783 | Time: 2.0761 s
>>> Epoch [  794/10000]
train_loss: 2.0926 | train_acc: 0.3840 | val_loss: 2.1026 | val_acc: 0.3721 | test_acc: 0.3783 | Time: 1.9560 s
>>> Epoch [  795/10000]
train_loss: 2.0926 | train_acc: 0.3840 | val_loss: 2.1025 | val_acc: 0.3722 | test_acc: 0.3783 | Time: 2.9267 s
>>> Epoch [  796/10000]
train_loss: 2.0925 | train_acc: 0.3840 | val_loss: 2.1025 | val_acc: 0.3723 | test_acc: 0.3783 | Time: 3.3039 s
>>> Epoch [  797/10000]
train_loss: 2.0925 | train_acc: 0.3841 | val_loss: 2.1025 | val_acc: 0.3724 | test_acc: 0.3784 | Time: 3.4723 s
>>> Epoch [  798/10000]
train_loss: 2.0925 | train_acc: 0.3841 | val_loss: 2.1024 | val_acc: 0.3725 | test_acc: 0.3784 | Time: 3.4798 s
>>> Epoch [  799/10000]
train_loss: 2.0924 | train_acc: 0.3840 | val_loss: 2.1024 | val_acc: 0.3724 | test_acc: 0.3783 | Time: 3.4876 s
>>> Epoch [  800/10000]
train_loss: 2.0924 | train_acc: 0.3839 | val_loss: 2.1024 | val_acc: 0.3724 | test_acc: 0.3783 | Time: 3.5521 s
>>> Epoch [  801/10000]
train_loss: 2.0923 | train_acc: 0.3840 | val_loss: 2.1023 | val_acc: 0.3726 | test_acc: 0.3783 | Time: 2.1152 s
>>> Epoch [  802/10000]
train_loss: 2.0923 | train_acc: 0.3840 | val_loss: 2.1023 | val_acc: 0.3725 | test_acc: 0.3783 | Time: 2.1326 s
>>> Epoch [  803/10000]
train_loss: 2.0923 | train_acc: 0.3840 | val_loss: 2.1023 | val_acc: 0.3725 | test_acc: 0.3783 | Time: 2.2686 s
>>> Epoch [  804/10000]
train_loss: 2.0922 | train_acc: 0.3840 | val_loss: 2.1022 | val_acc: 0.3724 | test_acc: 0.3782 | Time: 2.1385 s
>>> Epoch [  805/10000]
train_loss: 2.0922 | train_acc: 0.3840 | val_loss: 2.1022 | val_acc: 0.3724 | test_acc: 0.3783 | Time: 2.1633 s
>>> Epoch [  806/10000]
train_loss: 2.0921 | train_acc: 0.3841 | val_loss: 2.1022 | val_acc: 0.3724 | test_acc: 0.3786 | Time: 2.1453 s
>>> Epoch [  807/10000]
train_loss: 2.0921 | train_acc: 0.3842 | val_loss: 2.1021 | val_acc: 0.3725 | test_acc: 0.3788 | Time: 2.2138 s
>>> Epoch [  808/10000]
train_loss: 2.0921 | train_acc: 0.3843 | val_loss: 2.1021 | val_acc: 0.3725 | test_acc: 0.3788 | Time: 2.2088 s
>>> Epoch [  809/10000]
train_loss: 2.0920 | train_acc: 0.3843 | val_loss: 2.1021 | val_acc: 0.3726 | test_acc: 0.3789 | Time: 2.1590 s
>>> Epoch [  810/10000]
train_loss: 2.0920 | train_acc: 0.3843 | val_loss: 2.1020 | val_acc: 0.3726 | test_acc: 0.3791 | Time: 2.1937 s
>>> Epoch [  811/10000]
train_loss: 2.0919 | train_acc: 0.3844 | val_loss: 2.1020 | val_acc: 0.3726 | test_acc: 0.3791 | Time: 2.2530 s
>>> Epoch [  812/10000]
train_loss: 2.0919 | train_acc: 0.3844 | val_loss: 2.1020 | val_acc: 0.3726 | test_acc: 0.3792 | Time: 2.1415 s
>>> Epoch [  813/10000]
train_loss: 2.0919 | train_acc: 0.3845 | val_loss: 2.1019 | val_acc: 0.3726 | test_acc: 0.3792 | Time: 2.1640 s
>>> Epoch [  814/10000]
train_loss: 2.0918 | train_acc: 0.3846 | val_loss: 2.1019 | val_acc: 0.3726 | test_acc: 0.3792 | Time: 2.1082 s
>>> Epoch [  815/10000]
train_loss: 2.0918 | train_acc: 0.3846 | val_loss: 2.1019 | val_acc: 0.3726 | test_acc: 0.3792 | Time: 2.0540 s
>>> Epoch [  816/10000]
train_loss: 2.0917 | train_acc: 0.3846 | val_loss: 2.1018 | val_acc: 0.3728 | test_acc: 0.3793 | Time: 2.1646 s
>>> Epoch [  817/10000]
train_loss: 2.0917 | train_acc: 0.3846 | val_loss: 2.1018 | val_acc: 0.3731 | test_acc: 0.3794 | Time: 2.3103 s
>>> Epoch [  818/10000]
train_loss: 2.0917 | train_acc: 0.3846 | val_loss: 2.1018 | val_acc: 0.3731 | test_acc: 0.3794 | Time: 2.2991 s
>>> Epoch [  819/10000]
train_loss: 2.0916 | train_acc: 0.3846 | val_loss: 2.1017 | val_acc: 0.3732 | test_acc: 0.3795 | Time: 2.2744 s
>>> Epoch [  820/10000]
train_loss: 2.0916 | train_acc: 0.3846 | val_loss: 2.1017 | val_acc: 0.3729 | test_acc: 0.3795 | Time: 2.2401 s
>>> Epoch [  821/10000]
train_loss: 2.0916 | train_acc: 0.3847 | val_loss: 2.1017 | val_acc: 0.3731 | test_acc: 0.3796 | Time: 2.2557 s
>>> Epoch [  822/10000]
train_loss: 2.0915 | train_acc: 0.3847 | val_loss: 2.1016 | val_acc: 0.3731 | test_acc: 0.3797 | Time: 2.1600 s
>>> Epoch [  823/10000]
train_loss: 2.0915 | train_acc: 0.3847 | val_loss: 2.1016 | val_acc: 0.3730 | test_acc: 0.3799 | Time: 2.2980 s
>>> Epoch [  824/10000]
train_loss: 2.0914 | train_acc: 0.3848 | val_loss: 2.1016 | val_acc: 0.3730 | test_acc: 0.3799 | Time: 2.2144 s
>>> Epoch [  825/10000]
train_loss: 2.0914 | train_acc: 0.3848 | val_loss: 2.1015 | val_acc: 0.3730 | test_acc: 0.3800 | Time: 2.2503 s
>>> Epoch [  826/10000]
train_loss: 2.0914 | train_acc: 0.3848 | val_loss: 2.1015 | val_acc: 0.3730 | test_acc: 0.3802 | Time: 2.1539 s
>>> Epoch [  827/10000]
train_loss: 2.0913 | train_acc: 0.3849 | val_loss: 2.1015 | val_acc: 0.3730 | test_acc: 0.3802 | Time: 2.1895 s
>>> Epoch [  828/10000]
train_loss: 2.0913 | train_acc: 0.3849 | val_loss: 2.1014 | val_acc: 0.3730 | test_acc: 0.3801 | Time: 2.1173 s
>>> Epoch [  829/10000]
train_loss: 2.0912 | train_acc: 0.3849 | val_loss: 2.1014 | val_acc: 0.3731 | test_acc: 0.3800 | Time: 2.2896 s
>>> Epoch [  830/10000]
train_loss: 2.0912 | train_acc: 0.3850 | val_loss: 2.1014 | val_acc: 0.3731 | test_acc: 0.3801 | Time: 2.1134 s
>>> Epoch [  831/10000]
train_loss: 2.0912 | train_acc: 0.3849 | val_loss: 2.1013 | val_acc: 0.3730 | test_acc: 0.3802 | Time: 2.0759 s
>>> Epoch [  832/10000]
train_loss: 2.0911 | train_acc: 0.3849 | val_loss: 2.1013 | val_acc: 0.3733 | test_acc: 0.3803 | Time: 2.1164 s
>>> Epoch [  833/10000]
train_loss: 2.0911 | train_acc: 0.3850 | val_loss: 2.1013 | val_acc: 0.3733 | test_acc: 0.3803 | Time: 2.0243 s
>>> Epoch [  834/10000]
train_loss: 2.0910 | train_acc: 0.3850 | val_loss: 2.1012 | val_acc: 0.3732 | test_acc: 0.3803 | Time: 2.0534 s
>>> Epoch [  835/10000]
train_loss: 2.0910 | train_acc: 0.3851 | val_loss: 2.1012 | val_acc: 0.3731 | test_acc: 0.3801 | Time: 2.0391 s
>>> Epoch [  836/10000]
train_loss: 2.0910 | train_acc: 0.3851 | val_loss: 2.1012 | val_acc: 0.3732 | test_acc: 0.3801 | Time: 1.9998 s
>>> Epoch [  837/10000]
train_loss: 2.0909 | train_acc: 0.3852 | val_loss: 2.1011 | val_acc: 0.3732 | test_acc: 0.3800 | Time: 2.1894 s
>>> Epoch [  838/10000]
train_loss: 2.0909 | train_acc: 0.3853 | val_loss: 2.1011 | val_acc: 0.3732 | test_acc: 0.3800 | Time: 2.1060 s
>>> Epoch [  839/10000]
train_loss: 2.0909 | train_acc: 0.3852 | val_loss: 2.1011 | val_acc: 0.3732 | test_acc: 0.3800 | Time: 2.2627 s
>>> Epoch [  840/10000]
train_loss: 2.0908 | train_acc: 0.3853 | val_loss: 2.1010 | val_acc: 0.3731 | test_acc: 0.3800 | Time: 2.2960 s
>>> Epoch [  841/10000]
train_loss: 2.0908 | train_acc: 0.3853 | val_loss: 2.1010 | val_acc: 0.3732 | test_acc: 0.3801 | Time: 2.1911 s
>>> Epoch [  842/10000]
train_loss: 2.0907 | train_acc: 0.3854 | val_loss: 2.1010 | val_acc: 0.3731 | test_acc: 0.3802 | Time: 2.3663 s
>>> Epoch [  843/10000]
train_loss: 2.0907 | train_acc: 0.3854 | val_loss: 2.1009 | val_acc: 0.3733 | test_acc: 0.3803 | Time: 2.2897 s
>>> Epoch [  844/10000]
train_loss: 2.0907 | train_acc: 0.3854 | val_loss: 2.1009 | val_acc: 0.3733 | test_acc: 0.3803 | Time: 2.2165 s
>>> Epoch [  845/10000]
train_loss: 2.0906 | train_acc: 0.3854 | val_loss: 2.1009 | val_acc: 0.3735 | test_acc: 0.3803 | Time: 2.3125 s
>>> Epoch [  846/10000]
train_loss: 2.0906 | train_acc: 0.3854 | val_loss: 2.1009 | val_acc: 0.3736 | test_acc: 0.3803 | Time: 2.1617 s
>>> Epoch [  847/10000]
train_loss: 2.0906 | train_acc: 0.3855 | val_loss: 2.1008 | val_acc: 0.3738 | test_acc: 0.3803 | Time: 2.2465 s
>>> Epoch [  848/10000]
train_loss: 2.0905 | train_acc: 0.3855 | val_loss: 2.1008 | val_acc: 0.3738 | test_acc: 0.3803 | Time: 2.3416 s
>>> Epoch [  849/10000]
train_loss: 2.0905 | train_acc: 0.3856 | val_loss: 2.1008 | val_acc: 0.3737 | test_acc: 0.3803 | Time: 2.3643 s
>>> Epoch [  850/10000]
train_loss: 2.0904 | train_acc: 0.3856 | val_loss: 2.1007 | val_acc: 0.3738 | test_acc: 0.3802 | Time: 2.4438 s
>>> Epoch [  851/10000]
train_loss: 2.0904 | train_acc: 0.3856 | val_loss: 2.1007 | val_acc: 0.3738 | test_acc: 0.3804 | Time: 2.3280 s
>>> Epoch [  852/10000]
train_loss: 2.0904 | train_acc: 0.3856 | val_loss: 2.1007 | val_acc: 0.3738 | test_acc: 0.3805 | Time: 2.3982 s
>>> Epoch [  853/10000]
train_loss: 2.0903 | train_acc: 0.3856 | val_loss: 2.1006 | val_acc: 0.3739 | test_acc: 0.3804 | Time: 2.1969 s
>>> Epoch [  854/10000]
train_loss: 2.0903 | train_acc: 0.3856 | val_loss: 2.1006 | val_acc: 0.3739 | test_acc: 0.3803 | Time: 2.3435 s
>>> Epoch [  855/10000]
train_loss: 2.0903 | train_acc: 0.3855 | val_loss: 2.1006 | val_acc: 0.3739 | test_acc: 0.3805 | Time: 2.2947 s
>>> Epoch [  856/10000]
train_loss: 2.0902 | train_acc: 0.3856 | val_loss: 2.1005 | val_acc: 0.3739 | test_acc: 0.3805 | Time: 2.3202 s
>>> Epoch [  857/10000]
train_loss: 2.0902 | train_acc: 0.3856 | val_loss: 2.1005 | val_acc: 0.3738 | test_acc: 0.3805 | Time: 2.4364 s
>>> Epoch [  858/10000]
train_loss: 2.0901 | train_acc: 0.3856 | val_loss: 2.1005 | val_acc: 0.3736 | test_acc: 0.3805 | Time: 2.2105 s
>>> Epoch [  859/10000]
train_loss: 2.0901 | train_acc: 0.3856 | val_loss: 2.1004 | val_acc: 0.3735 | test_acc: 0.3804 | Time: 2.5798 s
>>> Epoch [  860/10000]
train_loss: 2.0901 | train_acc: 0.3857 | val_loss: 2.1004 | val_acc: 0.3736 | test_acc: 0.3804 | Time: 2.4943 s
>>> Epoch [  861/10000]
train_loss: 2.0900 | train_acc: 0.3856 | val_loss: 2.1004 | val_acc: 0.3737 | test_acc: 0.3804 | Time: 2.2746 s
>>> Epoch [  862/10000]
train_loss: 2.0900 | train_acc: 0.3857 | val_loss: 2.1004 | val_acc: 0.3737 | test_acc: 0.3804 | Time: 2.4159 s
>>> Epoch [  863/10000]
train_loss: 2.0900 | train_acc: 0.3857 | val_loss: 2.1003 | val_acc: 0.3739 | test_acc: 0.3803 | Time: 2.4254 s
>>> Epoch [  864/10000]
train_loss: 2.0899 | train_acc: 0.3857 | val_loss: 2.1003 | val_acc: 0.3739 | test_acc: 0.3803 | Time: 2.3725 s
>>> Epoch [  865/10000]
train_loss: 2.0899 | train_acc: 0.3858 | val_loss: 2.1003 | val_acc: 0.3740 | test_acc: 0.3801 | Time: 2.4389 s
>>> Epoch [  866/10000]
train_loss: 2.0898 | train_acc: 0.3858 | val_loss: 2.1002 | val_acc: 0.3740 | test_acc: 0.3801 | Time: 2.5376 s
>>> Epoch [  867/10000]
train_loss: 2.0898 | train_acc: 0.3858 | val_loss: 2.1002 | val_acc: 0.3741 | test_acc: 0.3801 | Time: 2.3754 s
>>> Epoch [  868/10000]
train_loss: 2.0898 | train_acc: 0.3858 | val_loss: 2.1002 | val_acc: 0.3743 | test_acc: 0.3801 | Time: 2.1134 s
>>> Epoch [  869/10000]
train_loss: 2.0897 | train_acc: 0.3858 | val_loss: 2.1001 | val_acc: 0.3742 | test_acc: 0.3803 | Time: 2.2943 s
>>> Epoch [  870/10000]
train_loss: 2.0897 | train_acc: 0.3858 | val_loss: 2.1001 | val_acc: 0.3743 | test_acc: 0.3803 | Time: 2.4343 s
>>> Epoch [  871/10000]
train_loss: 2.0897 | train_acc: 0.3858 | val_loss: 2.1001 | val_acc: 0.3742 | test_acc: 0.3804 | Time: 2.4671 s
>>> Epoch [  872/10000]
train_loss: 2.0896 | train_acc: 0.3859 | val_loss: 2.1000 | val_acc: 0.3741 | test_acc: 0.3805 | Time: 2.3962 s
>>> Epoch [  873/10000]
train_loss: 2.0896 | train_acc: 0.3859 | val_loss: 2.1000 | val_acc: 0.3742 | test_acc: 0.3805 | Time: 2.3579 s
>>> Epoch [  874/10000]
train_loss: 2.0896 | train_acc: 0.3860 | val_loss: 2.1000 | val_acc: 0.3743 | test_acc: 0.3805 | Time: 2.3861 s
>>> Epoch [  875/10000]
train_loss: 2.0895 | train_acc: 0.3861 | val_loss: 2.0999 | val_acc: 0.3743 | test_acc: 0.3805 | Time: 2.3792 s
>>> Epoch [  876/10000]
train_loss: 2.0895 | train_acc: 0.3861 | val_loss: 2.0999 | val_acc: 0.3743 | test_acc: 0.3807 | Time: 2.3359 s
>>> Epoch [  877/10000]
train_loss: 2.0894 | train_acc: 0.3860 | val_loss: 2.0999 | val_acc: 0.3743 | test_acc: 0.3808 | Time: 2.3676 s
>>> Epoch [  878/10000]
train_loss: 2.0894 | train_acc: 0.3861 | val_loss: 2.0999 | val_acc: 0.3744 | test_acc: 0.3809 | Time: 2.5557 s
>>> Epoch [  879/10000]
train_loss: 2.0894 | train_acc: 0.3861 | val_loss: 2.0998 | val_acc: 0.3743 | test_acc: 0.3808 | Time: 2.5775 s
>>> Epoch [  880/10000]
train_loss: 2.0893 | train_acc: 0.3861 | val_loss: 2.0998 | val_acc: 0.3742 | test_acc: 0.3807 | Time: 2.4998 s
>>> Epoch [  881/10000]
train_loss: 2.0893 | train_acc: 0.3861 | val_loss: 2.0998 | val_acc: 0.3741 | test_acc: 0.3808 | Time: 2.5813 s
>>> Epoch [  882/10000]
train_loss: 2.0893 | train_acc: 0.3862 | val_loss: 2.0997 | val_acc: 0.3740 | test_acc: 0.3808 | Time: 2.4838 s
>>> Epoch [  883/10000]
train_loss: 2.0892 | train_acc: 0.3862 | val_loss: 2.0997 | val_acc: 0.3739 | test_acc: 0.3810 | Time: 2.5646 s
>>> Epoch [  884/10000]
train_loss: 2.0892 | train_acc: 0.3862 | val_loss: 2.0997 | val_acc: 0.3739 | test_acc: 0.3810 | Time: 2.4307 s
>>> Epoch [  885/10000]
train_loss: 2.0892 | train_acc: 0.3863 | val_loss: 2.0996 | val_acc: 0.3738 | test_acc: 0.3809 | Time: 2.4238 s
>>> Epoch [  886/10000]
train_loss: 2.0891 | train_acc: 0.3863 | val_loss: 2.0996 | val_acc: 0.3738 | test_acc: 0.3810 | Time: 2.3737 s
>>> Epoch [  887/10000]
train_loss: 2.0891 | train_acc: 0.3864 | val_loss: 2.0996 | val_acc: 0.3738 | test_acc: 0.3811 | Time: 2.4613 s
>>> Epoch [  888/10000]
train_loss: 2.0891 | train_acc: 0.3864 | val_loss: 2.0996 | val_acc: 0.3738 | test_acc: 0.3811 | Time: 2.5507 s
>>> Epoch [  889/10000]
train_loss: 2.0890 | train_acc: 0.3865 | val_loss: 2.0995 | val_acc: 0.3739 | test_acc: 0.3811 | Time: 2.6453 s
>>> Epoch [  890/10000]
train_loss: 2.0890 | train_acc: 0.3865 | val_loss: 2.0995 | val_acc: 0.3738 | test_acc: 0.3811 | Time: 2.5268 s
>>> Epoch [  891/10000]
train_loss: 2.0889 | train_acc: 0.3865 | val_loss: 2.0995 | val_acc: 0.3738 | test_acc: 0.3813 | Time: 2.3141 s
>>> Epoch [  892/10000]
train_loss: 2.0889 | train_acc: 0.3865 | val_loss: 2.0994 | val_acc: 0.3739 | test_acc: 0.3813 | Time: 2.4992 s
>>> Epoch [  893/10000]
train_loss: 2.0889 | train_acc: 0.3866 | val_loss: 2.0994 | val_acc: 0.3740 | test_acc: 0.3812 | Time: 2.5193 s
>>> Epoch [  894/10000]
train_loss: 2.0888 | train_acc: 0.3866 | val_loss: 2.0994 | val_acc: 0.3740 | test_acc: 0.3812 | Time: 2.5484 s
>>> Epoch [  895/10000]
train_loss: 2.0888 | train_acc: 0.3866 | val_loss: 2.0993 | val_acc: 0.3742 | test_acc: 0.3811 | Time: 2.5929 s
>>> Epoch [  896/10000]
train_loss: 2.0888 | train_acc: 0.3866 | val_loss: 2.0993 | val_acc: 0.3742 | test_acc: 0.3811 | Time: 2.5055 s
>>> Epoch [  897/10000]
train_loss: 2.0887 | train_acc: 0.3866 | val_loss: 2.0993 | val_acc: 0.3743 | test_acc: 0.3810 | Time: 2.5155 s
>>> Epoch [  898/10000]
train_loss: 2.0887 | train_acc: 0.3867 | val_loss: 2.0993 | val_acc: 0.3744 | test_acc: 0.3809 | Time: 2.4659 s
>>> Epoch [  899/10000]
train_loss: 2.0887 | train_acc: 0.3867 | val_loss: 2.0992 | val_acc: 0.3744 | test_acc: 0.3809 | Time: 2.4667 s
>>> Epoch [  900/10000]
train_loss: 2.0886 | train_acc: 0.3867 | val_loss: 2.0992 | val_acc: 0.3744 | test_acc: 0.3809 | Time: 2.3578 s
>>> Epoch [  901/10000]
train_loss: 2.0886 | train_acc: 0.3867 | val_loss: 2.0992 | val_acc: 0.3745 | test_acc: 0.3808 | Time: 2.4858 s
>>> Epoch [  902/10000]
train_loss: 2.0886 | train_acc: 0.3868 | val_loss: 2.0991 | val_acc: 0.3744 | test_acc: 0.3807 | Time: 2.7162 s
>>> Epoch [  903/10000]
train_loss: 2.0885 | train_acc: 0.3868 | val_loss: 2.0991 | val_acc: 0.3745 | test_acc: 0.3808 | Time: 2.4041 s
>>> Epoch [  904/10000]
train_loss: 2.0885 | train_acc: 0.3869 | val_loss: 2.0991 | val_acc: 0.3745 | test_acc: 0.3808 | Time: 2.4331 s
>>> Epoch [  905/10000]
train_loss: 2.0885 | train_acc: 0.3869 | val_loss: 2.0991 | val_acc: 0.3745 | test_acc: 0.3808 | Time: 2.6498 s
>>> Epoch [  906/10000]
train_loss: 2.0884 | train_acc: 0.3869 | val_loss: 2.0990 | val_acc: 0.3746 | test_acc: 0.3808 | Time: 2.5895 s
>>> Epoch [  907/10000]
train_loss: 2.0884 | train_acc: 0.3869 | val_loss: 2.0990 | val_acc: 0.3744 | test_acc: 0.3808 | Time: 2.5382 s
>>> Epoch [  908/10000]
train_loss: 2.0883 | train_acc: 0.3869 | val_loss: 2.0990 | val_acc: 0.3746 | test_acc: 0.3808 | Time: 2.5287 s
>>> Epoch [  909/10000]
train_loss: 2.0883 | train_acc: 0.3869 | val_loss: 2.0989 | val_acc: 0.3746 | test_acc: 0.3807 | Time: 2.4703 s
>>> Epoch [  910/10000]
train_loss: 2.0883 | train_acc: 0.3869 | val_loss: 2.0989 | val_acc: 0.3746 | test_acc: 0.3808 | Time: 2.4372 s
>>> Epoch [  911/10000]
train_loss: 2.0882 | train_acc: 0.3870 | val_loss: 2.0989 | val_acc: 0.3746 | test_acc: 0.3808 | Time: 2.4611 s
>>> Epoch [  912/10000]
train_loss: 2.0882 | train_acc: 0.3869 | val_loss: 2.0988 | val_acc: 0.3746 | test_acc: 0.3807 | Time: 2.5334 s
>>> Epoch [  913/10000]
train_loss: 2.0882 | train_acc: 0.3869 | val_loss: 2.0988 | val_acc: 0.3745 | test_acc: 0.3807 | Time: 2.6091 s
>>> Epoch [  914/10000]
train_loss: 2.0881 | train_acc: 0.3870 | val_loss: 2.0988 | val_acc: 0.3747 | test_acc: 0.3806 | Time: 2.4998 s
>>> Epoch [  915/10000]
train_loss: 2.0881 | train_acc: 0.3870 | val_loss: 2.0988 | val_acc: 0.3747 | test_acc: 0.3806 | Time: 2.5195 s
>>> Epoch [  916/10000]
train_loss: 2.0881 | train_acc: 0.3870 | val_loss: 2.0987 | val_acc: 0.3746 | test_acc: 0.3805 | Time: 2.7541 s
>>> Epoch [  917/10000]
train_loss: 2.0880 | train_acc: 0.3870 | val_loss: 2.0987 | val_acc: 0.3747 | test_acc: 0.3805 | Time: 2.6686 s
>>> Epoch [  918/10000]
train_loss: 2.0880 | train_acc: 0.3871 | val_loss: 2.0987 | val_acc: 0.3748 | test_acc: 0.3806 | Time: 2.6303 s
>>> Epoch [  919/10000]
train_loss: 2.0880 | train_acc: 0.3872 | val_loss: 2.0986 | val_acc: 0.3748 | test_acc: 0.3806 | Time: 3.6854 s
>>> Epoch [  920/10000]
train_loss: 2.0879 | train_acc: 0.3872 | val_loss: 2.0986 | val_acc: 0.3749 | test_acc: 0.3807 | Time: 4.0014 s
>>> Epoch [  921/10000]
train_loss: 2.0879 | train_acc: 0.3872 | val_loss: 2.0986 | val_acc: 0.3749 | test_acc: 0.3808 | Time: 3.7042 s
>>> Epoch [  922/10000]
train_loss: 2.0879 | train_acc: 0.3872 | val_loss: 2.0986 | val_acc: 0.3749 | test_acc: 0.3808 | Time: 3.4407 s
>>> Epoch [  923/10000]
train_loss: 2.0878 | train_acc: 0.3872 | val_loss: 2.0985 | val_acc: 0.3749 | test_acc: 0.3809 | Time: 3.4873 s
>>> Epoch [  924/10000]
train_loss: 2.0878 | train_acc: 0.3872 | val_loss: 2.0985 | val_acc: 0.3751 | test_acc: 0.3810 | Time: 3.3733 s
>>> Epoch [  925/10000]
train_loss: 2.0878 | train_acc: 0.3873 | val_loss: 2.0985 | val_acc: 0.3751 | test_acc: 0.3810 | Time: 3.7646 s
>>> Epoch [  926/10000]
train_loss: 2.0877 | train_acc: 0.3873 | val_loss: 2.0984 | val_acc: 0.3752 | test_acc: 0.3811 | Time: 3.9035 s
>>> Epoch [  927/10000]
train_loss: 2.0877 | train_acc: 0.3873 | val_loss: 2.0984 | val_acc: 0.3752 | test_acc: 0.3811 | Time: 3.6852 s
>>> Epoch [  928/10000]
train_loss: 2.0877 | train_acc: 0.3874 | val_loss: 2.0984 | val_acc: 0.3752 | test_acc: 0.3812 | Time: 3.7317 s
>>> Epoch [  929/10000]
train_loss: 2.0876 | train_acc: 0.3874 | val_loss: 2.0984 | val_acc: 0.3752 | test_acc: 0.3814 | Time: 2.2665 s
>>> Epoch [  930/10000]
train_loss: 2.0876 | train_acc: 0.3874 | val_loss: 2.0983 | val_acc: 0.3754 | test_acc: 0.3815 | Time: 2.2254 s
>>> Epoch [  931/10000]
train_loss: 2.0876 | train_acc: 0.3875 | val_loss: 2.0983 | val_acc: 0.3753 | test_acc: 0.3814 | Time: 2.4248 s
>>> Epoch [  932/10000]
train_loss: 2.0875 | train_acc: 0.3875 | val_loss: 2.0983 | val_acc: 0.3755 | test_acc: 0.3814 | Time: 2.2091 s
>>> Epoch [  933/10000]
train_loss: 2.0875 | train_acc: 0.3875 | val_loss: 2.0982 | val_acc: 0.3755 | test_acc: 0.3815 | Time: 2.2428 s
>>> Epoch [  934/10000]
train_loss: 2.0875 | train_acc: 0.3876 | val_loss: 2.0982 | val_acc: 0.3756 | test_acc: 0.3815 | Time: 2.1925 s
>>> Epoch [  935/10000]
train_loss: 2.0874 | train_acc: 0.3876 | val_loss: 2.0982 | val_acc: 0.3757 | test_acc: 0.3815 | Time: 2.3775 s
>>> Epoch [  936/10000]
train_loss: 2.0874 | train_acc: 0.3877 | val_loss: 2.0982 | val_acc: 0.3757 | test_acc: 0.3815 | Time: 2.5098 s
>>> Epoch [  937/10000]
train_loss: 2.0874 | train_acc: 0.3877 | val_loss: 2.0981 | val_acc: 0.3758 | test_acc: 0.3817 | Time: 2.3629 s
>>> Epoch [  938/10000]
train_loss: 2.0873 | train_acc: 0.3877 | val_loss: 2.0981 | val_acc: 0.3759 | test_acc: 0.3818 | Time: 2.5096 s
>>> Epoch [  939/10000]
train_loss: 2.0873 | train_acc: 0.3876 | val_loss: 2.0981 | val_acc: 0.3759 | test_acc: 0.3818 | Time: 2.4300 s
>>> Epoch [  940/10000]
train_loss: 2.0873 | train_acc: 0.3877 | val_loss: 2.0980 | val_acc: 0.3759 | test_acc: 0.3818 | Time: 2.4792 s
>>> Epoch [  941/10000]
train_loss: 2.0872 | train_acc: 0.3877 | val_loss: 2.0980 | val_acc: 0.3760 | test_acc: 0.3818 | Time: 2.6104 s
>>> Epoch [  942/10000]
train_loss: 2.0872 | train_acc: 0.3877 | val_loss: 2.0980 | val_acc: 0.3760 | test_acc: 0.3818 | Time: 2.3551 s
>>> Epoch [  943/10000]
train_loss: 2.0872 | train_acc: 0.3878 | val_loss: 2.0980 | val_acc: 0.3761 | test_acc: 0.3818 | Time: 2.4115 s
>>> Epoch [  944/10000]
train_loss: 2.0871 | train_acc: 0.3878 | val_loss: 2.0979 | val_acc: 0.3761 | test_acc: 0.3818 | Time: 2.4106 s
>>> Epoch [  945/10000]
train_loss: 2.0871 | train_acc: 0.3878 | val_loss: 2.0979 | val_acc: 0.3761 | test_acc: 0.3818 | Time: 2.4471 s
>>> Epoch [  946/10000]
train_loss: 2.0871 | train_acc: 0.3879 | val_loss: 2.0979 | val_acc: 0.3762 | test_acc: 0.3818 | Time: 2.7465 s
>>> Epoch [  947/10000]
train_loss: 2.0870 | train_acc: 0.3880 | val_loss: 2.0978 | val_acc: 0.3764 | test_acc: 0.3818 | Time: 2.7615 s
>>> Epoch [  948/10000]
train_loss: 2.0870 | train_acc: 0.3880 | val_loss: 2.0978 | val_acc: 0.3765 | test_acc: 0.3818 | Time: 2.7397 s
>>> Epoch [  949/10000]
train_loss: 2.0870 | train_acc: 0.3881 | val_loss: 2.0978 | val_acc: 0.3766 | test_acc: 0.3818 | Time: 2.4456 s
>>> Epoch [  950/10000]
train_loss: 2.0869 | train_acc: 0.3882 | val_loss: 2.0978 | val_acc: 0.3766 | test_acc: 0.3820 | Time: 2.4431 s
>>> Epoch [  951/10000]
train_loss: 2.0869 | train_acc: 0.3884 | val_loss: 2.0977 | val_acc: 0.3765 | test_acc: 0.3819 | Time: 2.6214 s
>>> Epoch [  952/10000]
train_loss: 2.0869 | train_acc: 0.3884 | val_loss: 2.0977 | val_acc: 0.3764 | test_acc: 0.3819 | Time: 2.4689 s
>>> Epoch [  953/10000]
train_loss: 2.0868 | train_acc: 0.3884 | val_loss: 2.0977 | val_acc: 0.3764 | test_acc: 0.3820 | Time: 2.6080 s
>>> Epoch [  954/10000]
train_loss: 2.0868 | train_acc: 0.3884 | val_loss: 2.0976 | val_acc: 0.3764 | test_acc: 0.3819 | Time: 2.5850 s
>>> Epoch [  955/10000]
train_loss: 2.0868 | train_acc: 0.3884 | val_loss: 2.0976 | val_acc: 0.3764 | test_acc: 0.3818 | Time: 2.8458 s
>>> Epoch [  956/10000]
train_loss: 2.0867 | train_acc: 0.3885 | val_loss: 2.0976 | val_acc: 0.3764 | test_acc: 0.3818 | Time: 2.5539 s
>>> Epoch [  957/10000]
train_loss: 2.0867 | train_acc: 0.3885 | val_loss: 2.0976 | val_acc: 0.3763 | test_acc: 0.3818 | Time: 2.4569 s
>>> Epoch [  958/10000]
train_loss: 2.0867 | train_acc: 0.3886 | val_loss: 2.0975 | val_acc: 0.3763 | test_acc: 0.3818 | Time: 2.5306 s
>>> Epoch [  959/10000]
train_loss: 2.0866 | train_acc: 0.3886 | val_loss: 2.0975 | val_acc: 0.3763 | test_acc: 0.3817 | Time: 2.6506 s
>>> Epoch [  960/10000]
train_loss: 2.0866 | train_acc: 0.3886 | val_loss: 2.0975 | val_acc: 0.3761 | test_acc: 0.3818 | Time: 2.4535 s
>>> Epoch [  961/10000]
train_loss: 2.0866 | train_acc: 0.3887 | val_loss: 2.0975 | val_acc: 0.3762 | test_acc: 0.3820 | Time: 2.5805 s
>>> Epoch [  962/10000]
train_loss: 2.0865 | train_acc: 0.3887 | val_loss: 2.0974 | val_acc: 0.3762 | test_acc: 0.3821 | Time: 2.8019 s
>>> Epoch [  963/10000]
train_loss: 2.0865 | train_acc: 0.3887 | val_loss: 2.0974 | val_acc: 0.3764 | test_acc: 0.3822 | Time: 2.5578 s
>>> Epoch [  964/10000]
train_loss: 2.0865 | train_acc: 0.3887 | val_loss: 2.0974 | val_acc: 0.3764 | test_acc: 0.3821 | Time: 2.6538 s
>>> Epoch [  965/10000]
train_loss: 2.0864 | train_acc: 0.3887 | val_loss: 2.0973 | val_acc: 0.3762 | test_acc: 0.3820 | Time: 2.5062 s
>>> Epoch [  966/10000]
train_loss: 2.0864 | train_acc: 0.3888 | val_loss: 2.0973 | val_acc: 0.3762 | test_acc: 0.3820 | Time: 2.6357 s
>>> Epoch [  967/10000]
train_loss: 2.0864 | train_acc: 0.3887 | val_loss: 2.0973 | val_acc: 0.3763 | test_acc: 0.3820 | Time: 2.7095 s
>>> Epoch [  968/10000]
train_loss: 2.0863 | train_acc: 0.3888 | val_loss: 2.0973 | val_acc: 0.3764 | test_acc: 0.3819 | Time: 2.5578 s
>>> Epoch [  969/10000]
train_loss: 2.0863 | train_acc: 0.3889 | val_loss: 2.0972 | val_acc: 0.3765 | test_acc: 0.3818 | Time: 2.7752 s
>>> Epoch [  970/10000]
train_loss: 2.0863 | train_acc: 0.3889 | val_loss: 2.0972 | val_acc: 0.3765 | test_acc: 0.3817 | Time: 2.5187 s
>>> Epoch [  971/10000]
train_loss: 2.0862 | train_acc: 0.3888 | val_loss: 2.0972 | val_acc: 0.3767 | test_acc: 0.3817 | Time: 2.6152 s
>>> Epoch [  972/10000]
train_loss: 2.0862 | train_acc: 0.3888 | val_loss: 2.0972 | val_acc: 0.3769 | test_acc: 0.3819 | Time: 2.6331 s
>>> Epoch [  973/10000]
train_loss: 2.0862 | train_acc: 0.3888 | val_loss: 2.0971 | val_acc: 0.3769 | test_acc: 0.3820 | Time: 2.7878 s
>>> Epoch [  974/10000]
train_loss: 2.0861 | train_acc: 0.3889 | val_loss: 2.0971 | val_acc: 0.3769 | test_acc: 0.3820 | Time: 2.7002 s
>>> Epoch [  975/10000]
train_loss: 2.0861 | train_acc: 0.3890 | val_loss: 2.0971 | val_acc: 0.3769 | test_acc: 0.3820 | Time: 2.6478 s
>>> Epoch [  976/10000]
train_loss: 2.0861 | train_acc: 0.3890 | val_loss: 2.0970 | val_acc: 0.3768 | test_acc: 0.3819 | Time: 2.5468 s
>>> Epoch [  977/10000]
train_loss: 2.0861 | train_acc: 0.3890 | val_loss: 2.0970 | val_acc: 0.3768 | test_acc: 0.3819 | Time: 2.4320 s
>>> Epoch [  978/10000]
train_loss: 2.0860 | train_acc: 0.3891 | val_loss: 2.0970 | val_acc: 0.3768 | test_acc: 0.3820 | Time: 2.5580 s
>>> Epoch [  979/10000]
train_loss: 2.0860 | train_acc: 0.3891 | val_loss: 2.0970 | val_acc: 0.3769 | test_acc: 0.3820 | Time: 2.9260 s
>>> Epoch [  980/10000]
train_loss: 2.0860 | train_acc: 0.3891 | val_loss: 2.0969 | val_acc: 0.3770 | test_acc: 0.3821 | Time: 2.5921 s
>>> Epoch [  981/10000]
train_loss: 2.0859 | train_acc: 0.3891 | val_loss: 2.0969 | val_acc: 0.3770 | test_acc: 0.3821 | Time: 2.6655 s
>>> Epoch [  982/10000]
train_loss: 2.0859 | train_acc: 0.3892 | val_loss: 2.0969 | val_acc: 0.3770 | test_acc: 0.3822 | Time: 2.4771 s
>>> Epoch [  983/10000]
train_loss: 2.0859 | train_acc: 0.3892 | val_loss: 2.0969 | val_acc: 0.3770 | test_acc: 0.3821 | Time: 2.6841 s
>>> Epoch [  984/10000]
train_loss: 2.0858 | train_acc: 0.3892 | val_loss: 2.0968 | val_acc: 0.3769 | test_acc: 0.3821 | Time: 2.7838 s
>>> Epoch [  985/10000]
train_loss: 2.0858 | train_acc: 0.3892 | val_loss: 2.0968 | val_acc: 0.3771 | test_acc: 0.3820 | Time: 2.6553 s
>>> Epoch [  986/10000]
train_loss: 2.0858 | train_acc: 0.3893 | val_loss: 2.0968 | val_acc: 0.3771 | test_acc: 0.3818 | Time: 2.5546 s
>>> Epoch [  987/10000]
train_loss: 2.0857 | train_acc: 0.3894 | val_loss: 2.0967 | val_acc: 0.3772 | test_acc: 0.3819 | Time: 2.7019 s
>>> Epoch [  988/10000]
train_loss: 2.0857 | train_acc: 0.3895 | val_loss: 2.0967 | val_acc: 0.3773 | test_acc: 0.3819 | Time: 2.5086 s
>>> Epoch [  989/10000]
train_loss: 2.0857 | train_acc: 0.3896 | val_loss: 2.0967 | val_acc: 0.3773 | test_acc: 0.3819 | Time: 2.5336 s
>>> Epoch [  990/10000]
train_loss: 2.0856 | train_acc: 0.3895 | val_loss: 2.0967 | val_acc: 0.3772 | test_acc: 0.3818 | Time: 2.7663 s
>>> Epoch [  991/10000]
train_loss: 2.0856 | train_acc: 0.3896 | val_loss: 2.0966 | val_acc: 0.3772 | test_acc: 0.3818 | Time: 2.6505 s
>>> Epoch [  992/10000]
train_loss: 2.0856 | train_acc: 0.3897 | val_loss: 2.0966 | val_acc: 0.3775 | test_acc: 0.3816 | Time: 2.6904 s
>>> Epoch [  993/10000]
train_loss: 2.0855 | train_acc: 0.3897 | val_loss: 2.0966 | val_acc: 0.3775 | test_acc: 0.3816 | Time: 2.7049 s
>>> Epoch [  994/10000]
train_loss: 2.0855 | train_acc: 0.3897 | val_loss: 2.0966 | val_acc: 0.3776 | test_acc: 0.3816 | Time: 2.5151 s
>>> Epoch [  995/10000]
train_loss: 2.0855 | train_acc: 0.3898 | val_loss: 2.0965 | val_acc: 0.3775 | test_acc: 0.3815 | Time: 2.5877 s
>>> Epoch [  996/10000]
train_loss: 2.0855 | train_acc: 0.3899 | val_loss: 2.0965 | val_acc: 0.3775 | test_acc: 0.3815 | Time: 2.6793 s
>>> Epoch [  997/10000]
train_loss: 2.0854 | train_acc: 0.3898 | val_loss: 2.0965 | val_acc: 0.3777 | test_acc: 0.3816 | Time: 2.5364 s
>>> Epoch [  998/10000]
train_loss: 2.0854 | train_acc: 0.3899 | val_loss: 2.0965 | val_acc: 0.3776 | test_acc: 0.3817 | Time: 2.6503 s
>>> Epoch [  999/10000]
train_loss: 2.0854 | train_acc: 0.3900 | val_loss: 2.0964 | val_acc: 0.3776 | test_acc: 0.3817 | Time: 2.7940 s
>>> Epoch [ 1000/10000]
train_loss: 2.0853 | train_acc: 0.3901 | val_loss: 2.0964 | val_acc: 0.3777 | test_acc: 0.3818 | Time: 2.7344 s
>>> Epoch [ 1001/10000]
train_loss: 2.0853 | train_acc: 0.3902 | val_loss: 2.0964 | val_acc: 0.3777 | test_acc: 0.3819 | Time: 2.8452 s
>>> Epoch [ 1002/10000]
train_loss: 2.0853 | train_acc: 0.3902 | val_loss: 2.0963 | val_acc: 0.3777 | test_acc: 0.3819 | Time: 2.6271 s
>>> Epoch [ 1003/10000]
train_loss: 2.0852 | train_acc: 0.3902 | val_loss: 2.0963 | val_acc: 0.3778 | test_acc: 0.3819 | Time: 2.7565 s
>>> Epoch [ 1004/10000]
train_loss: 2.0852 | train_acc: 0.3902 | val_loss: 2.0963 | val_acc: 0.3779 | test_acc: 0.3819 | Time: 3.3352 s
>>> Epoch [ 1005/10000]
train_loss: 2.0852 | train_acc: 0.3902 | val_loss: 2.0963 | val_acc: 0.3779 | test_acc: 0.3819 | Time: 3.9932 s
>>> Epoch [ 1006/10000]
train_loss: 2.0851 | train_acc: 0.3902 | val_loss: 2.0962 | val_acc: 0.3779 | test_acc: 0.3819 | Time: 4.0414 s
>>> Epoch [ 1007/10000]
train_loss: 2.0851 | train_acc: 0.3902 | val_loss: 2.0962 | val_acc: 0.3779 | test_acc: 0.3819 | Time: 3.7498 s
>>> Epoch [ 1008/10000]
train_loss: 2.0851 | train_acc: 0.3903 | val_loss: 2.0962 | val_acc: 0.3778 | test_acc: 0.3817 | Time: 3.7392 s
>>> Epoch [ 1009/10000]
train_loss: 2.0850 | train_acc: 0.3903 | val_loss: 2.0962 | val_acc: 0.3778 | test_acc: 0.3818 | Time: 3.9899 s
>>> Epoch [ 1010/10000]
train_loss: 2.0850 | train_acc: 0.3904 | val_loss: 2.0961 | val_acc: 0.3778 | test_acc: 0.3818 | Time: 4.3197 s
>>> Epoch [ 1011/10000]
train_loss: 2.0850 | train_acc: 0.3905 | val_loss: 2.0961 | val_acc: 0.3778 | test_acc: 0.3820 | Time: 3.9330 s
>>> Epoch [ 1012/10000]
train_loss: 2.0850 | train_acc: 0.3905 | val_loss: 2.0961 | val_acc: 0.3778 | test_acc: 0.3821 | Time: 3.5942 s
>>> Epoch [ 1013/10000]
train_loss: 2.0849 | train_acc: 0.3906 | val_loss: 2.0961 | val_acc: 0.3778 | test_acc: 0.3821 | Time: 3.7801 s
>>> Epoch [ 1014/10000]
train_loss: 2.0849 | train_acc: 0.3906 | val_loss: 2.0960 | val_acc: 0.3779 | test_acc: 0.3821 | Time: 2.4522 s
>>> Epoch [ 1015/10000]
train_loss: 2.0849 | train_acc: 0.3906 | val_loss: 2.0960 | val_acc: 0.3780 | test_acc: 0.3821 | Time: 2.4031 s
>>> Epoch [ 1016/10000]
train_loss: 2.0848 | train_acc: 0.3906 | val_loss: 2.0960 | val_acc: 0.3780 | test_acc: 0.3821 | Time: 2.2716 s
>>> Epoch [ 1017/10000]
train_loss: 2.0848 | train_acc: 0.3906 | val_loss: 2.0960 | val_acc: 0.3781 | test_acc: 0.3821 | Time: 2.4993 s
>>> Epoch [ 1018/10000]
train_loss: 2.0848 | train_acc: 0.3906 | val_loss: 2.0959 | val_acc: 0.3781 | test_acc: 0.3823 | Time: 2.6291 s
>>> Epoch [ 1019/10000]
train_loss: 2.0847 | train_acc: 0.3907 | val_loss: 2.0959 | val_acc: 0.3781 | test_acc: 0.3821 | Time: 2.5410 s
>>> Epoch [ 1020/10000]
train_loss: 2.0847 | train_acc: 0.3907 | val_loss: 2.0959 | val_acc: 0.3781 | test_acc: 0.3820 | Time: 2.6419 s
>>> Epoch [ 1021/10000]
train_loss: 2.0847 | train_acc: 0.3908 | val_loss: 2.0959 | val_acc: 0.3781 | test_acc: 0.3820 | Time: 2.4689 s
>>> Epoch [ 1022/10000]
train_loss: 2.0847 | train_acc: 0.3908 | val_loss: 2.0958 | val_acc: 0.3782 | test_acc: 0.3820 | Time: 2.5414 s
>>> Epoch [ 1023/10000]
train_loss: 2.0846 | train_acc: 0.3909 | val_loss: 2.0958 | val_acc: 0.3781 | test_acc: 0.3821 | Time: 2.7528 s
>>> Epoch [ 1024/10000]
train_loss: 2.0846 | train_acc: 0.3909 | val_loss: 2.0958 | val_acc: 0.3781 | test_acc: 0.3821 | Time: 2.8673 s
>>> Epoch [ 1025/10000]
train_loss: 2.0846 | train_acc: 0.3910 | val_loss: 2.0958 | val_acc: 0.3781 | test_acc: 0.3821 | Time: 2.7407 s
>>> Epoch [ 1026/10000]
train_loss: 2.0845 | train_acc: 0.3910 | val_loss: 2.0957 | val_acc: 0.3780 | test_acc: 0.3821 | Time: 2.8018 s
>>> Epoch [ 1027/10000]
train_loss: 2.0845 | train_acc: 0.3910 | val_loss: 2.0957 | val_acc: 0.3781 | test_acc: 0.3821 | Time: 2.9402 s
>>> Epoch [ 1028/10000]
train_loss: 2.0845 | train_acc: 0.3910 | val_loss: 2.0957 | val_acc: 0.3780 | test_acc: 0.3821 | Time: 2.9069 s
>>> Epoch [ 1029/10000]
train_loss: 2.0844 | train_acc: 0.3910 | val_loss: 2.0956 | val_acc: 0.3779 | test_acc: 0.3823 | Time: 2.9183 s
>>> Epoch [ 1030/10000]
train_loss: 2.0844 | train_acc: 0.3910 | val_loss: 2.0956 | val_acc: 0.3777 | test_acc: 0.3823 | Time: 2.6974 s
>>> Epoch [ 1031/10000]
train_loss: 2.0844 | train_acc: 0.3910 | val_loss: 2.0956 | val_acc: 0.3778 | test_acc: 0.3824 | Time: 2.7202 s
>>> Epoch [ 1032/10000]
train_loss: 2.0844 | train_acc: 0.3911 | val_loss: 2.0956 | val_acc: 0.3779 | test_acc: 0.3825 | Time: 2.6971 s
>>> Epoch [ 1033/10000]
train_loss: 2.0843 | train_acc: 0.3911 | val_loss: 2.0955 | val_acc: 0.3778 | test_acc: 0.3825 | Time: 2.7843 s
>>> Epoch [ 1034/10000]
train_loss: 2.0843 | train_acc: 0.3911 | val_loss: 2.0955 | val_acc: 0.3778 | test_acc: 0.3825 | Time: 2.7732 s
>>> Epoch [ 1035/10000]
train_loss: 2.0843 | train_acc: 0.3911 | val_loss: 2.0955 | val_acc: 0.3777 | test_acc: 0.3825 | Time: 2.8792 s
>>> Epoch [ 1036/10000]
train_loss: 2.0842 | train_acc: 0.3911 | val_loss: 2.0955 | val_acc: 0.3777 | test_acc: 0.3827 | Time: 2.9420 s
>>> Epoch [ 1037/10000]
train_loss: 2.0842 | train_acc: 0.3911 | val_loss: 2.0954 | val_acc: 0.3776 | test_acc: 0.3827 | Time: 2.7973 s
>>> Epoch [ 1038/10000]
train_loss: 2.0842 | train_acc: 0.3911 | val_loss: 2.0954 | val_acc: 0.3776 | test_acc: 0.3827 | Time: 2.6434 s
>>> Epoch [ 1039/10000]
train_loss: 2.0841 | train_acc: 0.3910 | val_loss: 2.0954 | val_acc: 0.3776 | test_acc: 0.3827 | Time: 2.7017 s
>>> Epoch [ 1040/10000]
train_loss: 2.0841 | train_acc: 0.3910 | val_loss: 2.0954 | val_acc: 0.3776 | test_acc: 0.3827 | Time: 2.9690 s
>>> Epoch [ 1041/10000]
train_loss: 2.0841 | train_acc: 0.3910 | val_loss: 2.0953 | val_acc: 0.3776 | test_acc: 0.3827 | Time: 2.8906 s
>>> Epoch [ 1042/10000]
train_loss: 2.0841 | train_acc: 0.3910 | val_loss: 2.0953 | val_acc: 0.3776 | test_acc: 0.3830 | Time: 2.8373 s
>>> Epoch [ 1043/10000]
train_loss: 2.0840 | train_acc: 0.3911 | val_loss: 2.0953 | val_acc: 0.3776 | test_acc: 0.3830 | Time: 2.8159 s
>>> Epoch [ 1044/10000]
train_loss: 2.0840 | train_acc: 0.3911 | val_loss: 2.0953 | val_acc: 0.3775 | test_acc: 0.3830 | Time: 2.7154 s
>>> Epoch [ 1045/10000]
train_loss: 2.0840 | train_acc: 0.3911 | val_loss: 2.0952 | val_acc: 0.3774 | test_acc: 0.3830 | Time: 2.7441 s
>>> Epoch [ 1046/10000]
train_loss: 2.0839 | train_acc: 0.3911 | val_loss: 2.0952 | val_acc: 0.3775 | test_acc: 0.3830 | Time: 2.8063 s
>>> Epoch [ 1047/10000]
train_loss: 2.0839 | train_acc: 0.3910 | val_loss: 2.0952 | val_acc: 0.3776 | test_acc: 0.3830 | Time: 2.7789 s
>>> Epoch [ 1048/10000]
train_loss: 2.0839 | train_acc: 0.3910 | val_loss: 2.0952 | val_acc: 0.3777 | test_acc: 0.3830 | Time: 3.0056 s
>>> Epoch [ 1049/10000]
train_loss: 2.0838 | train_acc: 0.3911 | val_loss: 2.0951 | val_acc: 0.3778 | test_acc: 0.3829 | Time: 2.9025 s
>>> Epoch [ 1050/10000]
train_loss: 2.0838 | train_acc: 0.3910 | val_loss: 2.0951 | val_acc: 0.3778 | test_acc: 0.3829 | Time: 2.7262 s
>>> Epoch [ 1051/10000]
train_loss: 2.0838 | train_acc: 0.3910 | val_loss: 2.0951 | val_acc: 0.3778 | test_acc: 0.3831 | Time: 2.8339 s
>>> Epoch [ 1052/10000]
train_loss: 2.0838 | train_acc: 0.3911 | val_loss: 2.0951 | val_acc: 0.3779 | test_acc: 0.3831 | Time: 2.8983 s
>>> Epoch [ 1053/10000]
train_loss: 2.0837 | train_acc: 0.3911 | val_loss: 2.0950 | val_acc: 0.3778 | test_acc: 0.3830 | Time: 2.8143 s
>>> Epoch [ 1054/10000]
train_loss: 2.0837 | train_acc: 0.3911 | val_loss: 2.0950 | val_acc: 0.3778 | test_acc: 0.3831 | Time: 2.8090 s
>>> Epoch [ 1055/10000]
train_loss: 2.0837 | train_acc: 0.3911 | val_loss: 2.0950 | val_acc: 0.3778 | test_acc: 0.3830 | Time: 2.7530 s
>>> Epoch [ 1056/10000]
train_loss: 2.0836 | train_acc: 0.3912 | val_loss: 2.0950 | val_acc: 0.3777 | test_acc: 0.3831 | Time: 2.6452 s
>>> Epoch [ 1057/10000]
train_loss: 2.0836 | train_acc: 0.3912 | val_loss: 2.0949 | val_acc: 0.3777 | test_acc: 0.3831 | Time: 2.8540 s
>>> Epoch [ 1058/10000]
train_loss: 2.0836 | train_acc: 0.3913 | val_loss: 2.0949 | val_acc: 0.3777 | test_acc: 0.3831 | Time: 2.8969 s
>>> Epoch [ 1059/10000]
train_loss: 2.0836 | train_acc: 0.3913 | val_loss: 2.0949 | val_acc: 0.3777 | test_acc: 0.3832 | Time: 2.7490 s
>>> Epoch [ 1060/10000]
train_loss: 2.0835 | train_acc: 0.3913 | val_loss: 2.0949 | val_acc: 0.3777 | test_acc: 0.3832 | Time: 2.6636 s
>>> Epoch [ 1061/10000]
train_loss: 2.0835 | train_acc: 0.3914 | val_loss: 2.0948 | val_acc: 0.3776 | test_acc: 0.3832 | Time: 2.9448 s
>>> Epoch [ 1062/10000]
train_loss: 2.0835 | train_acc: 0.3913 | val_loss: 2.0948 | val_acc: 0.3776 | test_acc: 0.3833 | Time: 2.7601 s
>>> Epoch [ 1063/10000]
train_loss: 2.0834 | train_acc: 0.3913 | val_loss: 2.0948 | val_acc: 0.3777 | test_acc: 0.3833 | Time: 2.7259 s
>>> Epoch [ 1064/10000]
train_loss: 2.0834 | train_acc: 0.3913 | val_loss: 2.0948 | val_acc: 0.3777 | test_acc: 0.3832 | Time: 2.9729 s
>>> Epoch [ 1065/10000]
train_loss: 2.0834 | train_acc: 0.3914 | val_loss: 2.0947 | val_acc: 0.3778 | test_acc: 0.3832 | Time: 3.0175 s
>>> Epoch [ 1066/10000]
train_loss: 2.0834 | train_acc: 0.3914 | val_loss: 2.0947 | val_acc: 0.3779 | test_acc: 0.3833 | Time: 2.7870 s
>>> Epoch [ 1067/10000]
train_loss: 2.0833 | train_acc: 0.3915 | val_loss: 2.0947 | val_acc: 0.3779 | test_acc: 0.3833 | Time: 2.8272 s
>>> Epoch [ 1068/10000]
train_loss: 2.0833 | train_acc: 0.3915 | val_loss: 2.0947 | val_acc: 0.3780 | test_acc: 0.3832 | Time: 2.7614 s
>>> Epoch [ 1069/10000]
train_loss: 2.0833 | train_acc: 0.3916 | val_loss: 2.0946 | val_acc: 0.3780 | test_acc: 0.3830 | Time: 2.9440 s
>>> Epoch [ 1070/10000]
train_loss: 2.0832 | train_acc: 0.3915 | val_loss: 2.0946 | val_acc: 0.3780 | test_acc: 0.3831 | Time: 2.8192 s
>>> Epoch [ 1071/10000]
train_loss: 2.0832 | train_acc: 0.3915 | val_loss: 2.0946 | val_acc: 0.3780 | test_acc: 0.3832 | Time: 2.9779 s
>>> Epoch [ 1072/10000]
train_loss: 2.0832 | train_acc: 0.3916 | val_loss: 2.0946 | val_acc: 0.3782 | test_acc: 0.3832 | Time: 2.9644 s
>>> Epoch [ 1073/10000]
train_loss: 2.0832 | train_acc: 0.3916 | val_loss: 2.0945 | val_acc: 0.3781 | test_acc: 0.3833 | Time: 2.9468 s
>>> Epoch [ 1074/10000]
train_loss: 2.0831 | train_acc: 0.3916 | val_loss: 2.0945 | val_acc: 0.3782 | test_acc: 0.3833 | Time: 2.8459 s
>>> Epoch [ 1075/10000]
train_loss: 2.0831 | train_acc: 0.3916 | val_loss: 2.0945 | val_acc: 0.3782 | test_acc: 0.3834 | Time: 2.7788 s
>>> Epoch [ 1076/10000]
train_loss: 2.0831 | train_acc: 0.3917 | val_loss: 2.0945 | val_acc: 0.3781 | test_acc: 0.3835 | Time: 2.9137 s
>>> Epoch [ 1077/10000]
train_loss: 2.0830 | train_acc: 0.3918 | val_loss: 2.0944 | val_acc: 0.3782 | test_acc: 0.3835 | Time: 3.0515 s
>>> Epoch [ 1078/10000]
train_loss: 2.0830 | train_acc: 0.3918 | val_loss: 2.0944 | val_acc: 0.3782 | test_acc: 0.3835 | Time: 3.9998 s
>>> Epoch [ 1079/10000]
train_loss: 2.0830 | train_acc: 0.3918 | val_loss: 2.0944 | val_acc: 0.3782 | test_acc: 0.3835 | Time: 4.4302 s
>>> Epoch [ 1080/10000]
train_loss: 2.0830 | train_acc: 0.3917 | val_loss: 2.0944 | val_acc: 0.3782 | test_acc: 0.3836 | Time: 4.0776 s
>>> Epoch [ 1081/10000]
train_loss: 2.0829 | train_acc: 0.3918 | val_loss: 2.0944 | val_acc: 0.3782 | test_acc: 0.3838 | Time: 4.0918 s
>>> Epoch [ 1082/10000]
train_loss: 2.0829 | train_acc: 0.3918 | val_loss: 2.0943 | val_acc: 0.3782 | test_acc: 0.3839 | Time: 3.7249 s
>>> Epoch [ 1083/10000]
train_loss: 2.0829 | train_acc: 0.3918 | val_loss: 2.0943 | val_acc: 0.3782 | test_acc: 0.3840 | Time: 4.4783 s
>>> Epoch [ 1084/10000]
train_loss: 2.0828 | train_acc: 0.3919 | val_loss: 2.0943 | val_acc: 0.3783 | test_acc: 0.3840 | Time: 4.5422 s
>>> Epoch [ 1085/10000]
train_loss: 2.0828 | train_acc: 0.3919 | val_loss: 2.0943 | val_acc: 0.3782 | test_acc: 0.3840 | Time: 3.8791 s
>>> Epoch [ 1086/10000]
train_loss: 2.0828 | train_acc: 0.3920 | val_loss: 2.0942 | val_acc: 0.3781 | test_acc: 0.3840 | Time: 4.0603 s
>>> Epoch [ 1087/10000]
train_loss: 2.0828 | train_acc: 0.3921 | val_loss: 2.0942 | val_acc: 0.3783 | test_acc: 0.3840 | Time: 2.5733 s
>>> Epoch [ 1088/10000]
train_loss: 2.0827 | train_acc: 0.3921 | val_loss: 2.0942 | val_acc: 0.3783 | test_acc: 0.3839 | Time: 2.4761 s
>>> Epoch [ 1089/10000]
train_loss: 2.0827 | train_acc: 0.3921 | val_loss: 2.0942 | val_acc: 0.3783 | test_acc: 0.3839 | Time: 2.5259 s
>>> Epoch [ 1090/10000]
train_loss: 2.0827 | train_acc: 0.3921 | val_loss: 2.0941 | val_acc: 0.3783 | test_acc: 0.3839 | Time: 2.6622 s
>>> Epoch [ 1091/10000]
train_loss: 2.0826 | train_acc: 0.3922 | val_loss: 2.0941 | val_acc: 0.3783 | test_acc: 0.3839 | Time: 2.7386 s
>>> Epoch [ 1092/10000]
train_loss: 2.0826 | train_acc: 0.3923 | val_loss: 2.0941 | val_acc: 0.3784 | test_acc: 0.3839 | Time: 2.7406 s
>>> Epoch [ 1093/10000]
train_loss: 2.0826 | train_acc: 0.3923 | val_loss: 2.0941 | val_acc: 0.3784 | test_acc: 0.3840 | Time: 2.9146 s
>>> Epoch [ 1094/10000]
train_loss: 2.0826 | train_acc: 0.3924 | val_loss: 2.0940 | val_acc: 0.3784 | test_acc: 0.3841 | Time: 2.7949 s
>>> Epoch [ 1095/10000]
train_loss: 2.0825 | train_acc: 0.3924 | val_loss: 2.0940 | val_acc: 0.3782 | test_acc: 0.3843 | Time: 2.7657 s
>>> Epoch [ 1096/10000]
train_loss: 2.0825 | train_acc: 0.3924 | val_loss: 2.0940 | val_acc: 0.3782 | test_acc: 0.3843 | Time: 2.7498 s
>>> Epoch [ 1097/10000]
train_loss: 2.0825 | train_acc: 0.3924 | val_loss: 2.0940 | val_acc: 0.3782 | test_acc: 0.3843 | Time: 2.8428 s
>>> Epoch [ 1098/10000]
train_loss: 2.0824 | train_acc: 0.3925 | val_loss: 2.0939 | val_acc: 0.3781 | test_acc: 0.3844 | Time: 2.9101 s
>>> Epoch [ 1099/10000]
train_loss: 2.0824 | train_acc: 0.3925 | val_loss: 2.0939 | val_acc: 0.3782 | test_acc: 0.3844 | Time: 2.8280 s
>>> Epoch [ 1100/10000]
train_loss: 2.0824 | train_acc: 0.3926 | val_loss: 2.0939 | val_acc: 0.3782 | test_acc: 0.3845 | Time: 3.0153 s
>>> Epoch [ 1101/10000]
train_loss: 2.0824 | train_acc: 0.3926 | val_loss: 2.0939 | val_acc: 0.3781 | test_acc: 0.3845 | Time: 2.8490 s
>>> Epoch [ 1102/10000]
train_loss: 2.0823 | train_acc: 0.3927 | val_loss: 2.0938 | val_acc: 0.3781 | test_acc: 0.3845 | Time: 3.0280 s
>>> Epoch [ 1103/10000]
train_loss: 2.0823 | train_acc: 0.3926 | val_loss: 2.0938 | val_acc: 0.3781 | test_acc: 0.3846 | Time: 2.9639 s
>>> Epoch [ 1104/10000]
train_loss: 2.0823 | train_acc: 0.3927 | val_loss: 2.0938 | val_acc: 0.3780 | test_acc: 0.3845 | Time: 2.9677 s
>>> Epoch [ 1105/10000]
train_loss: 2.0823 | train_acc: 0.3927 | val_loss: 2.0938 | val_acc: 0.3780 | test_acc: 0.3846 | Time: 2.9332 s
>>> Epoch [ 1106/10000]
train_loss: 2.0822 | train_acc: 0.3927 | val_loss: 2.0938 | val_acc: 0.3780 | test_acc: 0.3847 | Time: 2.7817 s
>>> Epoch [ 1107/10000]
train_loss: 2.0822 | train_acc: 0.3927 | val_loss: 2.0937 | val_acc: 0.3782 | test_acc: 0.3846 | Time: 2.9390 s
>>> Epoch [ 1108/10000]
train_loss: 2.0822 | train_acc: 0.3928 | val_loss: 2.0937 | val_acc: 0.3781 | test_acc: 0.3847 | Time: 2.8897 s
>>> Epoch [ 1109/10000]
train_loss: 2.0821 | train_acc: 0.3928 | val_loss: 2.0937 | val_acc: 0.3780 | test_acc: 0.3847 | Time: 2.9186 s
>>> Epoch [ 1110/10000]
train_loss: 2.0821 | train_acc: 0.3929 | val_loss: 2.0937 | val_acc: 0.3781 | test_acc: 0.3848 | Time: 2.8675 s
>>> Epoch [ 1111/10000]
train_loss: 2.0821 | train_acc: 0.3929 | val_loss: 2.0936 | val_acc: 0.3781 | test_acc: 0.3849 | Time: 3.0652 s
>>> Epoch [ 1112/10000]
train_loss: 2.0821 | train_acc: 0.3929 | val_loss: 2.0936 | val_acc: 0.3781 | test_acc: 0.3848 | Time: 3.2222 s
>>> Epoch [ 1113/10000]
train_loss: 2.0820 | train_acc: 0.3930 | val_loss: 2.0936 | val_acc: 0.3781 | test_acc: 0.3848 | Time: 3.0767 s
>>> Epoch [ 1114/10000]
train_loss: 2.0820 | train_acc: 0.3930 | val_loss: 2.0936 | val_acc: 0.3783 | test_acc: 0.3848 | Time: 2.8624 s
>>> Epoch [ 1115/10000]
train_loss: 2.0820 | train_acc: 0.3930 | val_loss: 2.0935 | val_acc: 0.3783 | test_acc: 0.3849 | Time: 2.9851 s
>>> Epoch [ 1116/10000]
train_loss: 2.0819 | train_acc: 0.3930 | val_loss: 2.0935 | val_acc: 0.3783 | test_acc: 0.3850 | Time: 3.0046 s
>>> Epoch [ 1117/10000]
train_loss: 2.0819 | train_acc: 0.3930 | val_loss: 2.0935 | val_acc: 0.3783 | test_acc: 0.3851 | Time: 2.8200 s
>>> Epoch [ 1118/10000]
train_loss: 2.0819 | train_acc: 0.3930 | val_loss: 2.0935 | val_acc: 0.3786 | test_acc: 0.3851 | Time: 3.0111 s
>>> Epoch [ 1119/10000]
train_loss: 2.0819 | train_acc: 0.3930 | val_loss: 2.0934 | val_acc: 0.3786 | test_acc: 0.3851 | Time: 3.0151 s
>>> Epoch [ 1120/10000]
train_loss: 2.0818 | train_acc: 0.3930 | val_loss: 2.0934 | val_acc: 0.3786 | test_acc: 0.3851 | Time: 3.0358 s
>>> Epoch [ 1121/10000]
train_loss: 2.0818 | train_acc: 0.3930 | val_loss: 2.0934 | val_acc: 0.3787 | test_acc: 0.3851 | Time: 2.9531 s
>>> Epoch [ 1122/10000]
train_loss: 2.0818 | train_acc: 0.3930 | val_loss: 2.0934 | val_acc: 0.3786 | test_acc: 0.3851 | Time: 2.8747 s
>>> Epoch [ 1123/10000]
train_loss: 2.0818 | train_acc: 0.3931 | val_loss: 2.0933 | val_acc: 0.3786 | test_acc: 0.3851 | Time: 3.0258 s
>>> Epoch [ 1124/10000]
train_loss: 2.0817 | train_acc: 0.3931 | val_loss: 2.0933 | val_acc: 0.3786 | test_acc: 0.3851 | Time: 3.1049 s
>>> Epoch [ 1125/10000]
train_loss: 2.0817 | train_acc: 0.3931 | val_loss: 2.0933 | val_acc: 0.3788 | test_acc: 0.3851 | Time: 2.9464 s
>>> Epoch [ 1126/10000]
train_loss: 2.0817 | train_acc: 0.3931 | val_loss: 2.0933 | val_acc: 0.3788 | test_acc: 0.3850 | Time: 2.9727 s
>>> Epoch [ 1127/10000]
train_loss: 2.0817 | train_acc: 0.3931 | val_loss: 2.0933 | val_acc: 0.3789 | test_acc: 0.3849 | Time: 3.1173 s
>>> Epoch [ 1128/10000]
train_loss: 2.0816 | train_acc: 0.3931 | val_loss: 2.0932 | val_acc: 0.3788 | test_acc: 0.3848 | Time: 2.9795 s
>>> Epoch [ 1129/10000]
train_loss: 2.0816 | train_acc: 0.3931 | val_loss: 2.0932 | val_acc: 0.3788 | test_acc: 0.3847 | Time: 3.1845 s
>>> Epoch [ 1130/10000]
train_loss: 2.0816 | train_acc: 0.3932 | val_loss: 2.0932 | val_acc: 0.3788 | test_acc: 0.3847 | Time: 2.9329 s
>>> Epoch [ 1131/10000]
train_loss: 2.0815 | train_acc: 0.3931 | val_loss: 2.0932 | val_acc: 0.3788 | test_acc: 0.3847 | Time: 2.9480 s
>>> Epoch [ 1132/10000]
train_loss: 2.0815 | train_acc: 0.3931 | val_loss: 2.0931 | val_acc: 0.3787 | test_acc: 0.3847 | Time: 3.0902 s
>>> Epoch [ 1133/10000]
train_loss: 2.0815 | train_acc: 0.3931 | val_loss: 2.0931 | val_acc: 0.3789 | test_acc: 0.3847 | Time: 3.0629 s
>>> Epoch [ 1134/10000]
train_loss: 2.0815 | train_acc: 0.3931 | val_loss: 2.0931 | val_acc: 0.3788 | test_acc: 0.3848 | Time: 3.0037 s
>>> Epoch [ 1135/10000]
train_loss: 2.0814 | train_acc: 0.3931 | val_loss: 2.0931 | val_acc: 0.3789 | test_acc: 0.3849 | Time: 2.9942 s
>>> Epoch [ 1136/10000]
train_loss: 2.0814 | train_acc: 0.3932 | val_loss: 2.0930 | val_acc: 0.3787 | test_acc: 0.3849 | Time: 3.0979 s
>>> Epoch [ 1137/10000]
train_loss: 2.0814 | train_acc: 0.3933 | val_loss: 2.0930 | val_acc: 0.3787 | test_acc: 0.3851 | Time: 2.9615 s
>>> Epoch [ 1138/10000]
train_loss: 2.0814 | train_acc: 0.3932 | val_loss: 2.0930 | val_acc: 0.3786 | test_acc: 0.3849 | Time: 2.8540 s
>>> Epoch [ 1139/10000]
train_loss: 2.0813 | train_acc: 0.3933 | val_loss: 2.0930 | val_acc: 0.3786 | test_acc: 0.3850 | Time: 3.1755 s
>>> Epoch [ 1140/10000]
train_loss: 2.0813 | train_acc: 0.3934 | val_loss: 2.0930 | val_acc: 0.3786 | test_acc: 0.3850 | Time: 3.0316 s
>>> Epoch [ 1141/10000]
train_loss: 2.0813 | train_acc: 0.3934 | val_loss: 2.0929 | val_acc: 0.3787 | test_acc: 0.3851 | Time: 3.0057 s
>>> Epoch [ 1142/10000]
train_loss: 2.0812 | train_acc: 0.3934 | val_loss: 2.0929 | val_acc: 0.3787 | test_acc: 0.3851 | Time: 2.8940 s
>>> Epoch [ 1143/10000]
train_loss: 2.0812 | train_acc: 0.3934 | val_loss: 2.0929 | val_acc: 0.3788 | test_acc: 0.3850 | Time: 3.0769 s
>>> Epoch [ 1144/10000]
train_loss: 2.0812 | train_acc: 0.3935 | val_loss: 2.0929 | val_acc: 0.3788 | test_acc: 0.3852 | Time: 3.0661 s
>>> Epoch [ 1145/10000]
train_loss: 2.0812 | train_acc: 0.3935 | val_loss: 2.0928 | val_acc: 0.3789 | test_acc: 0.3852 | Time: 2.9470 s
>>> Epoch [ 1146/10000]
train_loss: 2.0811 | train_acc: 0.3935 | val_loss: 2.0928 | val_acc: 0.3789 | test_acc: 0.3851 | Time: 2.9576 s
>>> Epoch [ 1147/10000]
train_loss: 2.0811 | train_acc: 0.3935 | val_loss: 2.0928 | val_acc: 0.3789 | test_acc: 0.3852 | Time: 3.0104 s
>>> Epoch [ 1148/10000]
train_loss: 2.0811 | train_acc: 0.3935 | val_loss: 2.0928 | val_acc: 0.3789 | test_acc: 0.3853 | Time: 4.8188 s
>>> Epoch [ 1149/10000]
train_loss: 2.0811 | train_acc: 0.3935 | val_loss: 2.0927 | val_acc: 0.3789 | test_acc: 0.3854 | Time: 4.8064 s
>>> Epoch [ 1150/10000]
train_loss: 2.0810 | train_acc: 0.3935 | val_loss: 2.0927 | val_acc: 0.3789 | test_acc: 0.3854 | Time: 4.2366 s
>>> Epoch [ 1151/10000]
train_loss: 2.0810 | train_acc: 0.3935 | val_loss: 2.0927 | val_acc: 0.3790 | test_acc: 0.3854 | Time: 4.4178 s
>>> Epoch [ 1152/10000]
train_loss: 2.0810 | train_acc: 0.3935 | val_loss: 2.0927 | val_acc: 0.3790 | test_acc: 0.3854 | Time: 4.6591 s
>>> Epoch [ 1153/10000]
train_loss: 2.0810 | train_acc: 0.3935 | val_loss: 2.0927 | val_acc: 0.3790 | test_acc: 0.3854 | Time: 4.7963 s
>>> Epoch [ 1154/10000]
train_loss: 2.0809 | train_acc: 0.3935 | val_loss: 2.0926 | val_acc: 0.3790 | test_acc: 0.3855 | Time: 4.2833 s
>>> Epoch [ 1155/10000]
train_loss: 2.0809 | train_acc: 0.3935 | val_loss: 2.0926 | val_acc: 0.3791 | test_acc: 0.3853 | Time: 4.2525 s
>>> Epoch [ 1156/10000]
train_loss: 2.0809 | train_acc: 0.3936 | val_loss: 2.0926 | val_acc: 0.3791 | test_acc: 0.3853 | Time: 2.8909 s
>>> Epoch [ 1157/10000]
train_loss: 2.0809 | train_acc: 0.3936 | val_loss: 2.0926 | val_acc: 0.3791 | test_acc: 0.3854 | Time: 2.6672 s
>>> Epoch [ 1158/10000]
train_loss: 2.0808 | train_acc: 0.3936 | val_loss: 2.0925 | val_acc: 0.3791 | test_acc: 0.3854 | Time: 3.0233 s
>>> Epoch [ 1159/10000]
train_loss: 2.0808 | train_acc: 0.3937 | val_loss: 2.0925 | val_acc: 0.3791 | test_acc: 0.3854 | Time: 2.9731 s
>>> Epoch [ 1160/10000]
train_loss: 2.0808 | train_acc: 0.3937 | val_loss: 2.0925 | val_acc: 0.3792 | test_acc: 0.3854 | Time: 2.9694 s
>>> Epoch [ 1161/10000]
train_loss: 2.0807 | train_acc: 0.3937 | val_loss: 2.0925 | val_acc: 0.3792 | test_acc: 0.3853 | Time: 3.0448 s
>>> Epoch [ 1162/10000]
train_loss: 2.0807 | train_acc: 0.3937 | val_loss: 2.0925 | val_acc: 0.3792 | test_acc: 0.3854 | Time: 2.8791 s
>>> Epoch [ 1163/10000]
train_loss: 2.0807 | train_acc: 0.3936 | val_loss: 2.0924 | val_acc: 0.3793 | test_acc: 0.3854 | Time: 3.1355 s
>>> Epoch [ 1164/10000]
train_loss: 2.0807 | train_acc: 0.3937 | val_loss: 2.0924 | val_acc: 0.3793 | test_acc: 0.3853 | Time: 3.0252 s
>>> Epoch [ 1165/10000]
train_loss: 2.0806 | train_acc: 0.3937 | val_loss: 2.0924 | val_acc: 0.3792 | test_acc: 0.3854 | Time: 3.1028 s
>>> Epoch [ 1166/10000]
train_loss: 2.0806 | train_acc: 0.3938 | val_loss: 2.0924 | val_acc: 0.3793 | test_acc: 0.3854 | Time: 3.0198 s
>>> Epoch [ 1167/10000]
train_loss: 2.0806 | train_acc: 0.3938 | val_loss: 2.0923 | val_acc: 0.3794 | test_acc: 0.3854 | Time: 3.1750 s
>>> Epoch [ 1168/10000]
train_loss: 2.0806 | train_acc: 0.3938 | val_loss: 2.0923 | val_acc: 0.3794 | test_acc: 0.3853 | Time: 3.0882 s
>>> Epoch [ 1169/10000]
train_loss: 2.0805 | train_acc: 0.3938 | val_loss: 2.0923 | val_acc: 0.3794 | test_acc: 0.3853 | Time: 3.1242 s
>>> Epoch [ 1170/10000]
train_loss: 2.0805 | train_acc: 0.3939 | val_loss: 2.0923 | val_acc: 0.3792 | test_acc: 0.3853 | Time: 3.2278 s
>>> Epoch [ 1171/10000]
train_loss: 2.0805 | train_acc: 0.3939 | val_loss: 2.0923 | val_acc: 0.3792 | test_acc: 0.3853 | Time: 3.0549 s
>>> Epoch [ 1172/10000]
train_loss: 2.0805 | train_acc: 0.3939 | val_loss: 2.0922 | val_acc: 0.3792 | test_acc: 0.3854 | Time: 3.1189 s
>>> Epoch [ 1173/10000]
train_loss: 2.0804 | train_acc: 0.3940 | val_loss: 2.0922 | val_acc: 0.3791 | test_acc: 0.3854 | Time: 3.1979 s
>>> Epoch [ 1174/10000]
train_loss: 2.0804 | train_acc: 0.3940 | val_loss: 2.0922 | val_acc: 0.3791 | test_acc: 0.3854 | Time: 3.2404 s
>>> Epoch [ 1175/10000]
train_loss: 2.0804 | train_acc: 0.3940 | val_loss: 2.0922 | val_acc: 0.3790 | test_acc: 0.3854 | Time: 3.1522 s
>>> Epoch [ 1176/10000]
train_loss: 2.0804 | train_acc: 0.3940 | val_loss: 2.0921 | val_acc: 0.3791 | test_acc: 0.3853 | Time: 3.2240 s
>>> Epoch [ 1177/10000]
train_loss: 2.0803 | train_acc: 0.3940 | val_loss: 2.0921 | val_acc: 0.3790 | test_acc: 0.3853 | Time: 3.0030 s
>>> Epoch [ 1178/10000]
train_loss: 2.0803 | train_acc: 0.3940 | val_loss: 2.0921 | val_acc: 0.3791 | test_acc: 0.3853 | Time: 3.0956 s
>>> Epoch [ 1179/10000]
train_loss: 2.0803 | train_acc: 0.3941 | val_loss: 2.0921 | val_acc: 0.3792 | test_acc: 0.3854 | Time: 3.2002 s
>>> Epoch [ 1180/10000]
train_loss: 2.0803 | train_acc: 0.3940 | val_loss: 2.0921 | val_acc: 0.3791 | test_acc: 0.3854 | Time: 3.0463 s
>>> Epoch [ 1181/10000]
train_loss: 2.0802 | train_acc: 0.3941 | val_loss: 2.0920 | val_acc: 0.3792 | test_acc: 0.3855 | Time: 3.2425 s
>>> Epoch [ 1182/10000]
train_loss: 2.0802 | train_acc: 0.3941 | val_loss: 2.0920 | val_acc: 0.3792 | test_acc: 0.3855 | Time: 3.0999 s
>>> Epoch [ 1183/10000]
train_loss: 2.0802 | train_acc: 0.3941 | val_loss: 2.0920 | val_acc: 0.3793 | test_acc: 0.3856 | Time: 3.1059 s
>>> Epoch [ 1184/10000]
train_loss: 2.0802 | train_acc: 0.3941 | val_loss: 2.0920 | val_acc: 0.3792 | test_acc: 0.3856 | Time: 3.2628 s
>>> Epoch [ 1185/10000]
train_loss: 2.0801 | train_acc: 0.3941 | val_loss: 2.0919 | val_acc: 0.3791 | test_acc: 0.3856 | Time: 3.1757 s
>>> Epoch [ 1186/10000]
train_loss: 2.0801 | train_acc: 0.3941 | val_loss: 2.0919 | val_acc: 0.3790 | test_acc: 0.3858 | Time: 3.0837 s
>>> Epoch [ 1187/10000]
train_loss: 2.0801 | train_acc: 0.3941 | val_loss: 2.0919 | val_acc: 0.3792 | test_acc: 0.3858 | Time: 2.9705 s
>>> Epoch [ 1188/10000]
train_loss: 2.0801 | train_acc: 0.3941 | val_loss: 2.0919 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 3.2718 s
>>> Epoch [ 1189/10000]
train_loss: 2.0800 | train_acc: 0.3941 | val_loss: 2.0919 | val_acc: 0.3790 | test_acc: 0.3858 | Time: 3.1598 s
>>> Epoch [ 1190/10000]
train_loss: 2.0800 | train_acc: 0.3941 | val_loss: 2.0918 | val_acc: 0.3790 | test_acc: 0.3858 | Time: 3.5458 s
>>> Epoch [ 1191/10000]
train_loss: 2.0800 | train_acc: 0.3941 | val_loss: 2.0918 | val_acc: 0.3790 | test_acc: 0.3858 | Time: 3.2451 s
>>> Epoch [ 1192/10000]
train_loss: 2.0800 | train_acc: 0.3941 | val_loss: 2.0918 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 2.9756 s
>>> Epoch [ 1193/10000]
train_loss: 2.0799 | train_acc: 0.3941 | val_loss: 2.0918 | val_acc: 0.3791 | test_acc: 0.3858 | Time: 3.2422 s
>>> Epoch [ 1194/10000]
train_loss: 2.0799 | train_acc: 0.3941 | val_loss: 2.0917 | val_acc: 0.3790 | test_acc: 0.3858 | Time: 3.1733 s
>>> Epoch [ 1195/10000]
train_loss: 2.0799 | train_acc: 0.3942 | val_loss: 2.0917 | val_acc: 0.3790 | test_acc: 0.3858 | Time: 3.1054 s
>>> Epoch [ 1196/10000]
train_loss: 2.0799 | train_acc: 0.3942 | val_loss: 2.0917 | val_acc: 0.3790 | test_acc: 0.3857 | Time: 3.3798 s
>>> Epoch [ 1197/10000]
train_loss: 2.0798 | train_acc: 0.3943 | val_loss: 2.0917 | val_acc: 0.3790 | test_acc: 0.3857 | Time: 3.0357 s
>>> Epoch [ 1198/10000]
train_loss: 2.0798 | train_acc: 0.3942 | val_loss: 2.0917 | val_acc: 0.3790 | test_acc: 0.3857 | Time: 3.2313 s
>>> Epoch [ 1199/10000]
train_loss: 2.0798 | train_acc: 0.3943 | val_loss: 2.0916 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 3.2241 s
>>> Epoch [ 1200/10000]
train_loss: 2.0798 | train_acc: 0.3943 | val_loss: 2.0916 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 3.1996 s
>>> Epoch [ 1201/10000]
train_loss: 2.0797 | train_acc: 0.3944 | val_loss: 2.0916 | val_acc: 0.3791 | test_acc: 0.3858 | Time: 3.2510 s
>>> Epoch [ 1202/10000]
train_loss: 2.0797 | train_acc: 0.3944 | val_loss: 2.0916 | val_acc: 0.3791 | test_acc: 0.3858 | Time: 3.1606 s
>>> Epoch [ 1203/10000]
train_loss: 2.0797 | train_acc: 0.3945 | val_loss: 2.0915 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 3.2137 s
>>> Epoch [ 1204/10000]
train_loss: 2.0797 | train_acc: 0.3945 | val_loss: 2.0915 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 3.4120 s
>>> Epoch [ 1205/10000]
train_loss: 2.0796 | train_acc: 0.3945 | val_loss: 2.0915 | val_acc: 0.3790 | test_acc: 0.3857 | Time: 3.1556 s
>>> Epoch [ 1206/10000]
train_loss: 2.0796 | train_acc: 0.3945 | val_loss: 2.0915 | val_acc: 0.3792 | test_acc: 0.3857 | Time: 3.5430 s
>>> Epoch [ 1207/10000]
train_loss: 2.0796 | train_acc: 0.3946 | val_loss: 2.0915 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 3.1054 s
>>> Epoch [ 1208/10000]
train_loss: 2.0796 | train_acc: 0.3946 | val_loss: 2.0914 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 3.3004 s
>>> Epoch [ 1209/10000]
train_loss: 2.0795 | train_acc: 0.3947 | val_loss: 2.0914 | val_acc: 0.3791 | test_acc: 0.3857 | Time: 3.4997 s
>>> Epoch [ 1210/10000]
train_loss: 2.0795 | train_acc: 0.3947 | val_loss: 2.0914 | val_acc: 0.3794 | test_acc: 0.3858 | Time: 3.2363 s
>>> Epoch [ 1211/10000]
train_loss: 2.0795 | train_acc: 0.3948 | val_loss: 2.0914 | val_acc: 0.3794 | test_acc: 0.3858 | Time: 3.0759 s
>>> Epoch [ 1212/10000]
train_loss: 2.0795 | train_acc: 0.3948 | val_loss: 2.0914 | val_acc: 0.3794 | test_acc: 0.3857 | Time: 3.0102 s
>>> Epoch [ 1213/10000]
train_loss: 2.0794 | train_acc: 0.3948 | val_loss: 2.0913 | val_acc: 0.3794 | test_acc: 0.3857 | Time: 2.8900 s
>>> Epoch [ 1214/10000]
train_loss: 2.0794 | train_acc: 0.3948 | val_loss: 2.0913 | val_acc: 0.3794 | test_acc: 0.3858 | Time: 2.9690 s
>>> Epoch [ 1215/10000]
train_loss: 2.0794 | train_acc: 0.3948 | val_loss: 2.0913 | val_acc: 0.3795 | test_acc: 0.3857 | Time: 3.4704 s
>>> Epoch [ 1216/10000]
train_loss: 2.0794 | train_acc: 0.3948 | val_loss: 2.0913 | val_acc: 0.3795 | test_acc: 0.3856 | Time: 3.4916 s
>>> Epoch [ 1217/10000]
train_loss: 2.0793 | train_acc: 0.3948 | val_loss: 2.0912 | val_acc: 0.3794 | test_acc: 0.3857 | Time: 2.8957 s
>>> Epoch [ 1218/10000]
train_loss: 2.0793 | train_acc: 0.3949 | val_loss: 2.0912 | val_acc: 0.3794 | test_acc: 0.3857 | Time: 4.8298 s
>>> Epoch [ 1219/10000]
train_loss: 2.0793 | train_acc: 0.3949 | val_loss: 2.0912 | val_acc: 0.3793 | test_acc: 0.3857 | Time: 4.5505 s
>>> Epoch [ 1220/10000]
train_loss: 2.0793 | train_acc: 0.3949 | val_loss: 2.0912 | val_acc: 0.3794 | test_acc: 0.3857 | Time: 3.0680 s
>>> Epoch [ 1221/10000]
train_loss: 2.0792 | train_acc: 0.3949 | val_loss: 2.0912 | val_acc: 0.3794 | test_acc: 0.3858 | Time: 4.4341 s
>>> Epoch [ 1222/10000]
train_loss: 2.0792 | train_acc: 0.3950 | val_loss: 2.0911 | val_acc: 0.3795 | test_acc: 0.3858 | Time: 4.8011 s
>>> Epoch [ 1223/10000]
train_loss: 2.0792 | train_acc: 0.3950 | val_loss: 2.0911 | val_acc: 0.3794 | test_acc: 0.3858 | Time: 3.4066 s
>>> Epoch [ 1224/10000]
train_loss: 2.0792 | train_acc: 0.3950 | val_loss: 2.0911 | val_acc: 0.3793 | test_acc: 0.3858 | Time: 2.8747 s
>>> Epoch [ 1225/10000]
train_loss: 2.0791 | train_acc: 0.3951 | val_loss: 2.0911 | val_acc: 0.3794 | test_acc: 0.3859 | Time: 2.8881 s
>>> Epoch [ 1226/10000]
train_loss: 2.0791 | train_acc: 0.3952 | val_loss: 2.0910 | val_acc: 0.3794 | test_acc: 0.3860 | Time: 3.4352 s
>>> Epoch [ 1227/10000]
train_loss: 2.0791 | train_acc: 0.3951 | val_loss: 2.0910 | val_acc: 0.3794 | test_acc: 0.3860 | Time: 3.5506 s
>>> Epoch [ 1228/10000]
train_loss: 2.0791 | train_acc: 0.3952 | val_loss: 2.0910 | val_acc: 0.3794 | test_acc: 0.3860 | Time: 2.6883 s
>>> Epoch [ 1229/10000]
train_loss: 2.0790 | train_acc: 0.3952 | val_loss: 2.0910 | val_acc: 0.3794 | test_acc: 0.3860 | Time: 3.8289 s
>>> Epoch [ 1230/10000]
train_loss: 2.0790 | train_acc: 0.3952 | val_loss: 2.0910 | val_acc: 0.3794 | test_acc: 0.3861 | Time: 3.3482 s
>>> Epoch [ 1231/10000]
train_loss: 2.0790 | train_acc: 0.3953 | val_loss: 2.0909 | val_acc: 0.3794 | test_acc: 0.3861 | Time: 3.0738 s
>>> Epoch [ 1232/10000]
train_loss: 2.0790 | train_acc: 0.3953 | val_loss: 2.0909 | val_acc: 0.3794 | test_acc: 0.3861 | Time: 3.2223 s
>>> Epoch [ 1233/10000]
train_loss: 2.0789 | train_acc: 0.3953 | val_loss: 2.0909 | val_acc: 0.3794 | test_acc: 0.3861 | Time: 3.2333 s
>>> Epoch [ 1234/10000]
train_loss: 2.0789 | train_acc: 0.3954 | val_loss: 2.0909 | val_acc: 0.3794 | test_acc: 0.3862 | Time: 3.1533 s
>>> Epoch [ 1235/10000]
train_loss: 2.0789 | train_acc: 0.3954 | val_loss: 2.0909 | val_acc: 0.3794 | test_acc: 0.3862 | Time: 3.1438 s
>>> Epoch [ 1236/10000]
train_loss: 2.0789 | train_acc: 0.3954 | val_loss: 2.0908 | val_acc: 0.3794 | test_acc: 0.3863 | Time: 3.3084 s
>>> Epoch [ 1237/10000]
train_loss: 2.0788 | train_acc: 0.3955 | val_loss: 2.0908 | val_acc: 0.3794 | test_acc: 0.3864 | Time: 3.1770 s
>>> Epoch [ 1238/10000]
train_loss: 2.0788 | train_acc: 0.3955 | val_loss: 2.0908 | val_acc: 0.3794 | test_acc: 0.3864 | Time: 3.2333 s
>>> Epoch [ 1239/10000]
train_loss: 2.0788 | train_acc: 0.3955 | val_loss: 2.0908 | val_acc: 0.3795 | test_acc: 0.3864 | Time: 3.1541 s
>>> Epoch [ 1240/10000]
train_loss: 2.0788 | train_acc: 0.3955 | val_loss: 2.0908 | val_acc: 0.3796 | test_acc: 0.3864 | Time: 3.1331 s
>>> Epoch [ 1241/10000]
train_loss: 2.0787 | train_acc: 0.3955 | val_loss: 2.0907 | val_acc: 0.3797 | test_acc: 0.3865 | Time: 3.3282 s
>>> Epoch [ 1242/10000]
train_loss: 2.0787 | train_acc: 0.3955 | val_loss: 2.0907 | val_acc: 0.3797 | test_acc: 0.3865 | Time: 3.1963 s
>>> Epoch [ 1243/10000]
train_loss: 2.0787 | train_acc: 0.3955 | val_loss: 2.0907 | val_acc: 0.3798 | test_acc: 0.3864 | Time: 3.4266 s
>>> Epoch [ 1244/10000]
train_loss: 2.0787 | train_acc: 0.3955 | val_loss: 2.0907 | val_acc: 0.3798 | test_acc: 0.3865 | Time: 3.3761 s
>>> Epoch [ 1245/10000]
train_loss: 2.0786 | train_acc: 0.3955 | val_loss: 2.0906 | val_acc: 0.3798 | test_acc: 0.3865 | Time: 3.3578 s
>>> Epoch [ 1246/10000]
train_loss: 2.0786 | train_acc: 0.3955 | val_loss: 2.0906 | val_acc: 0.3798 | test_acc: 0.3865 | Time: 3.2665 s
>>> Epoch [ 1247/10000]
train_loss: 2.0786 | train_acc: 0.3955 | val_loss: 2.0906 | val_acc: 0.3798 | test_acc: 0.3865 | Time: 3.3290 s
>>> Epoch [ 1248/10000]
train_loss: 2.0786 | train_acc: 0.3956 | val_loss: 2.0906 | val_acc: 0.3798 | test_acc: 0.3865 | Time: 3.3932 s
>>> Epoch [ 1249/10000]
train_loss: 2.0785 | train_acc: 0.3957 | val_loss: 2.0906 | val_acc: 0.3798 | test_acc: 0.3865 | Time: 3.4287 s
>>> Epoch [ 1250/10000]
train_loss: 2.0785 | train_acc: 0.3957 | val_loss: 2.0905 | val_acc: 0.3798 | test_acc: 0.3865 | Time: 3.3628 s
>>> Epoch [ 1251/10000]
train_loss: 2.0785 | train_acc: 0.3957 | val_loss: 2.0905 | val_acc: 0.3799 | test_acc: 0.3865 | Time: 3.3315 s
>>> Epoch [ 1252/10000]
train_loss: 2.0785 | train_acc: 0.3957 | val_loss: 2.0905 | val_acc: 0.3799 | test_acc: 0.3865 | Time: 3.3362 s
>>> Epoch [ 1253/10000]
train_loss: 2.0785 | train_acc: 0.3958 | val_loss: 2.0905 | val_acc: 0.3800 | test_acc: 0.3865 | Time: 3.3181 s
>>> Epoch [ 1254/10000]
train_loss: 2.0784 | train_acc: 0.3958 | val_loss: 2.0905 | val_acc: 0.3800 | test_acc: 0.3863 | Time: 3.3571 s
>>> Epoch [ 1255/10000]
train_loss: 2.0784 | train_acc: 0.3958 | val_loss: 2.0904 | val_acc: 0.3800 | test_acc: 0.3863 | Time: 3.3459 s
>>> Epoch [ 1256/10000]
train_loss: 2.0784 | train_acc: 0.3958 | val_loss: 2.0904 | val_acc: 0.3801 | test_acc: 0.3862 | Time: 3.4955 s
>>> Epoch [ 1257/10000]
train_loss: 2.0784 | train_acc: 0.3958 | val_loss: 2.0904 | val_acc: 0.3801 | test_acc: 0.3862 | Time: 3.4009 s
>>> Epoch [ 1258/10000]
train_loss: 2.0783 | train_acc: 0.3959 | val_loss: 2.0904 | val_acc: 0.3801 | test_acc: 0.3862 | Time: 3.5283 s
>>> Epoch [ 1259/10000]
train_loss: 2.0783 | train_acc: 0.3959 | val_loss: 2.0904 | val_acc: 0.3801 | test_acc: 0.3862 | Time: 3.1365 s
>>> Epoch [ 1260/10000]
train_loss: 2.0783 | train_acc: 0.3960 | val_loss: 2.0903 | val_acc: 0.3801 | test_acc: 0.3863 | Time: 3.4463 s
>>> Epoch [ 1261/10000]
train_loss: 2.0783 | train_acc: 0.3960 | val_loss: 2.0903 | val_acc: 0.3802 | test_acc: 0.3864 | Time: 3.2386 s
>>> Epoch [ 1262/10000]
train_loss: 2.0782 | train_acc: 0.3960 | val_loss: 2.0903 | val_acc: 0.3803 | test_acc: 0.3864 | Time: 3.4837 s
>>> Epoch [ 1263/10000]
train_loss: 2.0782 | train_acc: 0.3961 | val_loss: 2.0903 | val_acc: 0.3803 | test_acc: 0.3865 | Time: 3.3947 s
>>> Epoch [ 1264/10000]
train_loss: 2.0782 | train_acc: 0.3961 | val_loss: 2.0903 | val_acc: 0.3803 | test_acc: 0.3866 | Time: 3.3220 s
>>> Epoch [ 1265/10000]
train_loss: 2.0782 | train_acc: 0.3962 | val_loss: 2.0902 | val_acc: 0.3804 | test_acc: 0.3866 | Time: 3.4566 s
>>> Epoch [ 1266/10000]
train_loss: 2.0781 | train_acc: 0.3962 | val_loss: 2.0902 | val_acc: 0.3804 | test_acc: 0.3865 | Time: 3.2352 s
>>> Epoch [ 1267/10000]
train_loss: 2.0781 | train_acc: 0.3962 | val_loss: 2.0902 | val_acc: 0.3806 | test_acc: 0.3865 | Time: 3.2424 s
>>> Epoch [ 1268/10000]
train_loss: 2.0781 | train_acc: 0.3962 | val_loss: 2.0902 | val_acc: 0.3806 | test_acc: 0.3865 | Time: 3.3123 s
>>> Epoch [ 1269/10000]
train_loss: 2.0781 | train_acc: 0.3962 | val_loss: 2.0901 | val_acc: 0.3806 | test_acc: 0.3866 | Time: 3.4424 s
>>> Epoch [ 1270/10000]
train_loss: 2.0780 | train_acc: 0.3962 | val_loss: 2.0901 | val_acc: 0.3806 | test_acc: 0.3866 | Time: 3.4084 s
>>> Epoch [ 1271/10000]
train_loss: 2.0780 | train_acc: 0.3962 | val_loss: 2.0901 | val_acc: 0.3806 | test_acc: 0.3866 | Time: 3.5920 s
>>> Epoch [ 1272/10000]
train_loss: 2.0780 | train_acc: 0.3962 | val_loss: 2.0901 | val_acc: 0.3805 | test_acc: 0.3865 | Time: 3.4084 s
>>> Epoch [ 1273/10000]
train_loss: 2.0780 | train_acc: 0.3962 | val_loss: 2.0901 | val_acc: 0.3804 | test_acc: 0.3865 | Time: 3.2773 s
>>> Epoch [ 1274/10000]
train_loss: 2.0780 | train_acc: 0.3962 | val_loss: 2.0900 | val_acc: 0.3803 | test_acc: 0.3865 | Time: 3.2580 s
>>> Epoch [ 1275/10000]
train_loss: 2.0779 | train_acc: 0.3962 | val_loss: 2.0900 | val_acc: 0.3804 | test_acc: 0.3865 | Time: 3.3961 s
>>> Epoch [ 1276/10000]
train_loss: 2.0779 | train_acc: 0.3963 | val_loss: 2.0900 | val_acc: 0.3805 | test_acc: 0.3865 | Time: 3.2419 s
>>> Epoch [ 1277/10000]
train_loss: 2.0779 | train_acc: 0.3964 | val_loss: 2.0900 | val_acc: 0.3806 | test_acc: 0.3865 | Time: 4.9812 s
>>> Epoch [ 1278/10000]
train_loss: 2.0779 | train_acc: 0.3964 | val_loss: 2.0900 | val_acc: 0.3805 | test_acc: 0.3867 | Time: 5.2671 s
>>> Epoch [ 1279/10000]
train_loss: 2.0778 | train_acc: 0.3965 | val_loss: 2.0899 | val_acc: 0.3805 | test_acc: 0.3868 | Time: 4.6925 s
>>> Epoch [ 1280/10000]
train_loss: 2.0778 | train_acc: 0.3965 | val_loss: 2.0899 | val_acc: 0.3804 | test_acc: 0.3869 | Time: 4.7109 s
>>> Epoch [ 1281/10000]
train_loss: 2.0778 | train_acc: 0.3965 | val_loss: 2.0899 | val_acc: 0.3805 | test_acc: 0.3870 | Time: 3.0890 s
>>> Epoch [ 1282/10000]
train_loss: 2.0778 | train_acc: 0.3965 | val_loss: 2.0899 | val_acc: 0.3805 | test_acc: 0.3869 | Time: 3.1120 s
>>> Epoch [ 1283/10000]
train_loss: 2.0777 | train_acc: 0.3964 | val_loss: 2.0899 | val_acc: 0.3805 | test_acc: 0.3870 | Time: 3.1517 s
>>> Epoch [ 1284/10000]
train_loss: 2.0777 | train_acc: 0.3965 | val_loss: 2.0898 | val_acc: 0.3805 | test_acc: 0.3869 | Time: 3.1973 s
>>> Epoch [ 1285/10000]
train_loss: 2.0777 | train_acc: 0.3965 | val_loss: 2.0898 | val_acc: 0.3805 | test_acc: 0.3869 | Time: 3.3027 s
>>> Epoch [ 1286/10000]
train_loss: 2.0777 | train_acc: 0.3965 | val_loss: 2.0898 | val_acc: 0.3806 | test_acc: 0.3870 | Time: 3.2556 s
>>> Epoch [ 1287/10000]
train_loss: 2.0777 | train_acc: 0.3965 | val_loss: 2.0898 | val_acc: 0.3806 | test_acc: 0.3870 | Time: 3.2693 s
>>> Epoch [ 1288/10000]
train_loss: 2.0776 | train_acc: 0.3966 | val_loss: 2.0898 | val_acc: 0.3805 | test_acc: 0.3869 | Time: 3.2510 s
>>> Epoch [ 1289/10000]
train_loss: 2.0776 | train_acc: 0.3966 | val_loss: 2.0897 | val_acc: 0.3805 | test_acc: 0.3869 | Time: 3.3536 s
>>> Epoch [ 1290/10000]
train_loss: 2.0776 | train_acc: 0.3967 | val_loss: 2.0897 | val_acc: 0.3806 | test_acc: 0.3869 | Time: 3.3751 s
>>> Epoch [ 1291/10000]
train_loss: 2.0776 | train_acc: 0.3967 | val_loss: 2.0897 | val_acc: 0.3806 | test_acc: 0.3869 | Time: 3.2264 s
>>> Epoch [ 1292/10000]
train_loss: 2.0775 | train_acc: 0.3966 | val_loss: 2.0897 | val_acc: 0.3806 | test_acc: 0.3869 | Time: 3.2435 s
>>> Epoch [ 1293/10000]
train_loss: 2.0775 | train_acc: 0.3966 | val_loss: 2.0897 | val_acc: 0.3806 | test_acc: 0.3869 | Time: 3.2976 s
>>> Epoch [ 1294/10000]
train_loss: 2.0775 | train_acc: 0.3967 | val_loss: 2.0896 | val_acc: 0.3806 | test_acc: 0.3869 | Time: 3.3049 s
>>> Epoch [ 1295/10000]
train_loss: 2.0775 | train_acc: 0.3967 | val_loss: 2.0896 | val_acc: 0.3806 | test_acc: 0.3869 | Time: 3.2065 s
>>> Epoch [ 1296/10000]
train_loss: 2.0774 | train_acc: 0.3968 | val_loss: 2.0896 | val_acc: 0.3806 | test_acc: 0.3869 | Time: 3.2327 s
>>> Epoch [ 1297/10000]
train_loss: 2.0774 | train_acc: 0.3967 | val_loss: 2.0896 | val_acc: 0.3807 | test_acc: 0.3869 | Time: 3.3310 s
>>> Epoch [ 1298/10000]
train_loss: 2.0774 | train_acc: 0.3967 | val_loss: 2.0896 | val_acc: 0.3808 | test_acc: 0.3869 | Time: 3.3303 s
>>> Epoch [ 1299/10000]
train_loss: 2.0774 | train_acc: 0.3968 | val_loss: 2.0895 | val_acc: 0.3808 | test_acc: 0.3869 | Time: 3.3066 s
>>> Epoch [ 1300/10000]
train_loss: 2.0774 | train_acc: 0.3968 | val_loss: 2.0895 | val_acc: 0.3808 | test_acc: 0.3869 | Time: 3.3982 s
>>> Epoch [ 1301/10000]
train_loss: 2.0773 | train_acc: 0.3968 | val_loss: 2.0895 | val_acc: 0.3808 | test_acc: 0.3869 | Time: 3.2360 s
>>> Epoch [ 1302/10000]
train_loss: 2.0773 | train_acc: 0.3968 | val_loss: 2.0895 | val_acc: 0.3808 | test_acc: 0.3871 | Time: 3.2311 s
>>> Epoch [ 1303/10000]
train_loss: 2.0773 | train_acc: 0.3968 | val_loss: 2.0895 | val_acc: 0.3809 | test_acc: 0.3872 | Time: 3.2288 s
>>> Epoch [ 1304/10000]
train_loss: 2.0773 | train_acc: 0.3968 | val_loss: 2.0894 | val_acc: 0.3809 | test_acc: 0.3872 | Time: 3.1377 s
>>> Epoch [ 1305/10000]
train_loss: 2.0772 | train_acc: 0.3969 | val_loss: 2.0894 | val_acc: 0.3808 | test_acc: 0.3871 | Time: 4.1890 s
>>> Epoch [ 1306/10000]
train_loss: 2.0772 | train_acc: 0.3970 | val_loss: 2.0894 | val_acc: 0.3808 | test_acc: 0.3872 | Time: 5.2439 s
>>> Epoch [ 1307/10000]
train_loss: 2.0772 | train_acc: 0.3970 | val_loss: 2.0894 | val_acc: 0.3809 | test_acc: 0.3875 | Time: 4.9012 s
>>> Epoch [ 1308/10000]
train_loss: 2.0772 | train_acc: 0.3970 | val_loss: 2.0894 | val_acc: 0.3809 | test_acc: 0.3875 | Time: 4.8149 s
>>> Epoch [ 1309/10000]
train_loss: 2.0771 | train_acc: 0.3971 | val_loss: 2.0893 | val_acc: 0.3810 | test_acc: 0.3877 | Time: 3.0908 s
>>> Epoch [ 1310/10000]
train_loss: 2.0771 | train_acc: 0.3971 | val_loss: 2.0893 | val_acc: 0.3810 | test_acc: 0.3877 | Time: 3.1571 s
>>> Epoch [ 1311/10000]
train_loss: 2.0771 | train_acc: 0.3971 | val_loss: 2.0893 | val_acc: 0.3810 | test_acc: 0.3877 | Time: 3.1464 s
>>> Epoch [ 1312/10000]
train_loss: 2.0771 | train_acc: 0.3972 | val_loss: 2.0893 | val_acc: 0.3810 | test_acc: 0.3878 | Time: 3.1159 s
>>> Epoch [ 1313/10000]
train_loss: 2.0771 | train_acc: 0.3971 | val_loss: 2.0893 | val_acc: 0.3810 | test_acc: 0.3878 | Time: 3.0209 s
>>> Epoch [ 1314/10000]
train_loss: 2.0770 | train_acc: 0.3972 | val_loss: 2.0892 | val_acc: 0.3810 | test_acc: 0.3879 | Time: 3.1410 s
>>> Epoch [ 1315/10000]
train_loss: 2.0770 | train_acc: 0.3972 | val_loss: 2.0892 | val_acc: 0.3810 | test_acc: 0.3879 | Time: 3.1077 s
>>> Epoch [ 1316/10000]
train_loss: 2.0770 | train_acc: 0.3972 | val_loss: 2.0892 | val_acc: 0.3810 | test_acc: 0.3878 | Time: 3.0671 s
>>> Epoch [ 1317/10000]
train_loss: 2.0770 | train_acc: 0.3972 | val_loss: 2.0892 | val_acc: 0.3810 | test_acc: 0.3878 | Time: 3.1137 s
>>> Epoch [ 1318/10000]
train_loss: 2.0769 | train_acc: 0.3972 | val_loss: 2.0892 | val_acc: 0.3810 | test_acc: 0.3878 | Time: 3.0649 s
>>> Epoch [ 1319/10000]
train_loss: 2.0769 | train_acc: 0.3972 | val_loss: 2.0891 | val_acc: 0.3810 | test_acc: 0.3878 | Time: 3.2189 s
>>> Epoch [ 1320/10000]
train_loss: 2.0769 | train_acc: 0.3972 | val_loss: 2.0891 | val_acc: 0.3812 | test_acc: 0.3878 | Time: 3.2261 s
>>> Epoch [ 1321/10000]
train_loss: 2.0769 | train_acc: 0.3972 | val_loss: 2.0891 | val_acc: 0.3812 | test_acc: 0.3879 | Time: 3.1919 s
>>> Epoch [ 1322/10000]
train_loss: 2.0769 | train_acc: 0.3972 | val_loss: 2.0891 | val_acc: 0.3812 | test_acc: 0.3880 | Time: 3.0634 s
>>> Epoch [ 1323/10000]
train_loss: 2.0768 | train_acc: 0.3972 | val_loss: 2.0891 | val_acc: 0.3812 | test_acc: 0.3880 | Time: 3.0591 s
>>> Epoch [ 1324/10000]
train_loss: 2.0768 | train_acc: 0.3972 | val_loss: 2.0890 | val_acc: 0.3811 | test_acc: 0.3879 | Time: 3.0539 s
>>> Epoch [ 1325/10000]
train_loss: 2.0768 | train_acc: 0.3972 | val_loss: 2.0890 | val_acc: 0.3811 | test_acc: 0.3879 | Time: 3.1027 s
>>> Epoch [ 1326/10000]
train_loss: 2.0768 | train_acc: 0.3972 | val_loss: 2.0890 | val_acc: 0.3810 | test_acc: 0.3878 | Time: 3.1331 s
>>> Epoch [ 1327/10000]
train_loss: 2.0767 | train_acc: 0.3972 | val_loss: 2.0890 | val_acc: 0.3810 | test_acc: 0.3878 | Time: 3.1042 s
>>> Epoch [ 1328/10000]
train_loss: 2.0767 | train_acc: 0.3973 | val_loss: 2.0890 | val_acc: 0.3809 | test_acc: 0.3878 | Time: 3.0961 s
>>> Epoch [ 1329/10000]
train_loss: 2.0767 | train_acc: 0.3972 | val_loss: 2.0889 | val_acc: 0.3809 | test_acc: 0.3880 | Time: 3.1322 s
>>> Epoch [ 1330/10000]
train_loss: 2.0767 | train_acc: 0.3972 | val_loss: 2.0889 | val_acc: 0.3810 | test_acc: 0.3880 | Time: 3.1063 s
>>> Epoch [ 1331/10000]
train_loss: 2.0767 | train_acc: 0.3971 | val_loss: 2.0889 | val_acc: 0.3809 | test_acc: 0.3881 | Time: 3.1018 s
>>> Epoch [ 1332/10000]
train_loss: 2.0766 | train_acc: 0.3971 | val_loss: 2.0889 | val_acc: 0.3809 | test_acc: 0.3882 | Time: 3.2391 s
>>> Epoch [ 1333/10000]
train_loss: 2.0766 | train_acc: 0.3971 | val_loss: 2.0889 | val_acc: 0.3809 | test_acc: 0.3883 | Time: 3.0690 s
>>> Epoch [ 1334/10000]
train_loss: 2.0766 | train_acc: 0.3971 | val_loss: 2.0888 | val_acc: 0.3809 | test_acc: 0.3883 | Time: 3.4404 s
>>> Epoch [ 1335/10000]
train_loss: 2.0766 | train_acc: 0.3972 | val_loss: 2.0888 | val_acc: 0.3811 | test_acc: 0.3883 | Time: 3.3249 s
>>> Epoch [ 1336/10000]
train_loss: 2.0765 | train_acc: 0.3971 | val_loss: 2.0888 | val_acc: 0.3812 | test_acc: 0.3883 | Time: 3.2105 s
>>> Epoch [ 1337/10000]
train_loss: 2.0765 | train_acc: 0.3971 | val_loss: 2.0888 | val_acc: 0.3812 | test_acc: 0.3883 | Time: 3.2881 s
>>> Epoch [ 1338/10000]
train_loss: 2.0765 | train_acc: 0.3971 | val_loss: 2.0888 | val_acc: 0.3813 | test_acc: 0.3883 | Time: 3.2799 s
>>> Epoch [ 1339/10000]
train_loss: 2.0765 | train_acc: 0.3970 | val_loss: 2.0887 | val_acc: 0.3812 | test_acc: 0.3883 | Time: 3.2905 s
>>> Epoch [ 1340/10000]
train_loss: 2.0765 | train_acc: 0.3970 | val_loss: 2.0887 | val_acc: 0.3812 | test_acc: 0.3884 | Time: 3.5413 s
>>> Epoch [ 1341/10000]
train_loss: 2.0764 | train_acc: 0.3970 | val_loss: 2.0887 | val_acc: 0.3813 | test_acc: 0.3885 | Time: 3.2336 s
>>> Epoch [ 1342/10000]
train_loss: 2.0764 | train_acc: 0.3970 | val_loss: 2.0887 | val_acc: 0.3813 | test_acc: 0.3885 | Time: 3.1292 s
>>> Epoch [ 1343/10000]
train_loss: 2.0764 | train_acc: 0.3970 | val_loss: 2.0887 | val_acc: 0.3813 | test_acc: 0.3885 | Time: 3.3738 s
>>> Epoch [ 1344/10000]
train_loss: 2.0764 | train_acc: 0.3971 | val_loss: 2.0886 | val_acc: 0.3812 | test_acc: 0.3883 | Time: 3.4296 s
>>> Epoch [ 1345/10000]
train_loss: 2.0763 | train_acc: 0.3970 | val_loss: 2.0886 | val_acc: 0.3811 | test_acc: 0.3882 | Time: 3.2460 s
>>> Epoch [ 1346/10000]
train_loss: 2.0763 | train_acc: 0.3971 | val_loss: 2.0886 | val_acc: 0.3812 | test_acc: 0.3883 | Time: 3.4780 s
>>> Epoch [ 1347/10000]
train_loss: 2.0763 | train_acc: 0.3971 | val_loss: 2.0886 | val_acc: 0.3814 | test_acc: 0.3883 | Time: 3.2692 s
>>> Epoch [ 1348/10000]
train_loss: 2.0763 | train_acc: 0.3972 | val_loss: 2.0886 | val_acc: 0.3814 | test_acc: 0.3883 | Time: 3.4334 s
>>> Epoch [ 1349/10000]
train_loss: 2.0763 | train_acc: 0.3972 | val_loss: 2.0885 | val_acc: 0.3814 | test_acc: 0.3883 | Time: 3.5152 s
>>> Epoch [ 1350/10000]
train_loss: 2.0762 | train_acc: 0.3971 | val_loss: 2.0885 | val_acc: 0.3814 | test_acc: 0.3882 | Time: 3.5029 s
>>> Epoch [ 1351/10000]
train_loss: 2.0762 | train_acc: 0.3972 | val_loss: 2.0885 | val_acc: 0.3813 | test_acc: 0.3882 | Time: 3.5692 s
>>> Epoch [ 1352/10000]
train_loss: 2.0762 | train_acc: 0.3972 | val_loss: 2.0885 | val_acc: 0.3814 | test_acc: 0.3883 | Time: 3.6391 s
>>> Epoch [ 1353/10000]
train_loss: 2.0762 | train_acc: 0.3971 | val_loss: 2.0885 | val_acc: 0.3814 | test_acc: 0.3883 | Time: 3.3791 s
>>> Epoch [ 1354/10000]
train_loss: 2.0761 | train_acc: 0.3971 | val_loss: 2.0885 | val_acc: 0.3815 | test_acc: 0.3883 | Time: 3.6184 s
>>> Epoch [ 1355/10000]
train_loss: 2.0761 | train_acc: 0.3971 | val_loss: 2.0884 | val_acc: 0.3815 | test_acc: 0.3885 | Time: 3.5129 s
>>> Epoch [ 1356/10000]
train_loss: 2.0761 | train_acc: 0.3972 | val_loss: 2.0884 | val_acc: 0.3816 | test_acc: 0.3885 | Time: 3.5452 s
>>> Epoch [ 1357/10000]
train_loss: 2.0761 | train_acc: 0.3972 | val_loss: 2.0884 | val_acc: 0.3816 | test_acc: 0.3885 | Time: 3.7539 s
>>> Epoch [ 1358/10000]
train_loss: 2.0761 | train_acc: 0.3972 | val_loss: 2.0884 | val_acc: 0.3816 | test_acc: 0.3886 | Time: 3.4179 s
>>> Epoch [ 1359/10000]
train_loss: 2.0760 | train_acc: 0.3972 | val_loss: 2.0884 | val_acc: 0.3816 | test_acc: 0.3885 | Time: 3.7041 s
>>> Epoch [ 1360/10000]
train_loss: 2.0760 | train_acc: 0.3972 | val_loss: 2.0883 | val_acc: 0.3816 | test_acc: 0.3884 | Time: 3.6337 s
>>> Epoch [ 1361/10000]
train_loss: 2.0760 | train_acc: 0.3972 | val_loss: 2.0883 | val_acc: 0.3817 | test_acc: 0.3884 | Time: 3.5073 s
>>> Epoch [ 1362/10000]
train_loss: 2.0760 | train_acc: 0.3973 | val_loss: 2.0883 | val_acc: 0.3818 | test_acc: 0.3885 | Time: 3.6012 s
>>> Epoch [ 1363/10000]
train_loss: 2.0759 | train_acc: 0.3973 | val_loss: 2.0883 | val_acc: 0.3819 | test_acc: 0.3885 | Time: 3.4742 s
>>> Epoch [ 1364/10000]
train_loss: 2.0759 | train_acc: 0.3973 | val_loss: 2.0883 | val_acc: 0.3820 | test_acc: 0.3885 | Time: 3.3926 s
>>> Epoch [ 1365/10000]
train_loss: 2.0759 | train_acc: 0.3973 | val_loss: 2.0882 | val_acc: 0.3820 | test_acc: 0.3886 | Time: 3.6386 s
>>> Epoch [ 1366/10000]
train_loss: 2.0759 | train_acc: 0.3973 | val_loss: 2.0882 | val_acc: 0.3823 | test_acc: 0.3886 | Time: 3.5783 s
>>> Epoch [ 1367/10000]
train_loss: 2.0759 | train_acc: 0.3973 | val_loss: 2.0882 | val_acc: 0.3823 | test_acc: 0.3886 | Time: 3.6001 s
>>> Epoch [ 1368/10000]
train_loss: 2.0758 | train_acc: 0.3973 | val_loss: 2.0882 | val_acc: 0.3825 | test_acc: 0.3886 | Time: 3.6508 s
>>> Epoch [ 1369/10000]
train_loss: 2.0758 | train_acc: 0.3974 | val_loss: 2.0882 | val_acc: 0.3825 | test_acc: 0.3886 | Time: 3.5656 s
>>> Epoch [ 1370/10000]
train_loss: 2.0758 | train_acc: 0.3974 | val_loss: 2.0881 | val_acc: 0.3826 | test_acc: 0.3886 | Time: 3.8047 s
>>> Epoch [ 1371/10000]
train_loss: 2.0758 | train_acc: 0.3975 | val_loss: 2.0881 | val_acc: 0.3826 | test_acc: 0.3887 | Time: 3.5161 s
>>> Epoch [ 1372/10000]
train_loss: 2.0758 | train_acc: 0.3975 | val_loss: 2.0881 | val_acc: 0.3826 | test_acc: 0.3887 | Time: 3.8349 s
>>> Epoch [ 1373/10000]
train_loss: 2.0757 | train_acc: 0.3975 | val_loss: 2.0881 | val_acc: 0.3826 | test_acc: 0.3887 | Time: 3.6044 s
>>> Epoch [ 1374/10000]
train_loss: 2.0757 | train_acc: 0.3975 | val_loss: 2.0881 | val_acc: 0.3825 | test_acc: 0.3888 | Time: 3.6612 s
>>> Epoch [ 1375/10000]
train_loss: 2.0757 | train_acc: 0.3976 | val_loss: 2.0881 | val_acc: 0.3825 | test_acc: 0.3888 | Time: 3.6632 s
>>> Epoch [ 1376/10000]
train_loss: 2.0757 | train_acc: 0.3976 | val_loss: 2.0880 | val_acc: 0.3825 | test_acc: 0.3888 | Time: 3.6138 s
>>> Epoch [ 1377/10000]
train_loss: 2.0756 | train_acc: 0.3976 | val_loss: 2.0880 | val_acc: 0.3825 | test_acc: 0.3888 | Time: 3.2520 s
>>> Epoch [ 1378/10000]
train_loss: 2.0756 | train_acc: 0.3976 | val_loss: 2.0880 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.6755 s
>>> Epoch [ 1379/10000]
train_loss: 2.0756 | train_acc: 0.3976 | val_loss: 2.0880 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.6438 s
>>> Epoch [ 1380/10000]
train_loss: 2.0756 | train_acc: 0.3976 | val_loss: 2.0880 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.6623 s
>>> Epoch [ 1381/10000]
train_loss: 2.0756 | train_acc: 0.3976 | val_loss: 2.0879 | val_acc: 0.3822 | test_acc: 0.3888 | Time: 3.6923 s
>>> Epoch [ 1382/10000]
train_loss: 2.0755 | train_acc: 0.3976 | val_loss: 2.0879 | val_acc: 0.3823 | test_acc: 0.3889 | Time: 3.7646 s
>>> Epoch [ 1383/10000]
train_loss: 2.0755 | train_acc: 0.3976 | val_loss: 2.0879 | val_acc: 0.3823 | test_acc: 0.3889 | Time: 3.6253 s
>>> Epoch [ 1384/10000]
train_loss: 2.0755 | train_acc: 0.3976 | val_loss: 2.0879 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.4013 s
>>> Epoch [ 1385/10000]
train_loss: 2.0755 | train_acc: 0.3975 | val_loss: 2.0879 | val_acc: 0.3822 | test_acc: 0.3888 | Time: 3.7895 s
>>> Epoch [ 1386/10000]
train_loss: 2.0755 | train_acc: 0.3976 | val_loss: 2.0878 | val_acc: 0.3822 | test_acc: 0.3888 | Time: 3.6457 s
>>> Epoch [ 1387/10000]
train_loss: 2.0754 | train_acc: 0.3976 | val_loss: 2.0878 | val_acc: 0.3822 | test_acc: 0.3888 | Time: 3.4615 s
>>> Epoch [ 1388/10000]
train_loss: 2.0754 | train_acc: 0.3976 | val_loss: 2.0878 | val_acc: 0.3823 | test_acc: 0.3889 | Time: 3.5377 s
>>> Epoch [ 1389/10000]
train_loss: 2.0754 | train_acc: 0.3976 | val_loss: 2.0878 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.6332 s
>>> Epoch [ 1390/10000]
train_loss: 2.0754 | train_acc: 0.3976 | val_loss: 2.0878 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.7077 s
>>> Epoch [ 1391/10000]
train_loss: 2.0753 | train_acc: 0.3977 | val_loss: 2.0877 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 5.5376 s
>>> Epoch [ 1392/10000]
train_loss: 2.0753 | train_acc: 0.3977 | val_loss: 2.0877 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 5.3571 s
>>> Epoch [ 1393/10000]
train_loss: 2.0753 | train_acc: 0.3977 | val_loss: 2.0877 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 5.3145 s
>>> Epoch [ 1394/10000]
train_loss: 2.0753 | train_acc: 0.3977 | val_loss: 2.0877 | val_acc: 0.3822 | test_acc: 0.3889 | Time: 5.3001 s
>>> Epoch [ 1395/10000]
train_loss: 2.0753 | train_acc: 0.3978 | val_loss: 2.0877 | val_acc: 0.3822 | test_acc: 0.3888 | Time: 5.6666 s
>>> Epoch [ 1396/10000]
train_loss: 2.0752 | train_acc: 0.3977 | val_loss: 2.0877 | val_acc: 0.3822 | test_acc: 0.3887 | Time: 5.2607 s
>>> Epoch [ 1397/10000]
train_loss: 2.0752 | train_acc: 0.3977 | val_loss: 2.0876 | val_acc: 0.3822 | test_acc: 0.3887 | Time: 4.0655 s
>>> Epoch [ 1398/10000]
train_loss: 2.0752 | train_acc: 0.3978 | val_loss: 2.0876 | val_acc: 0.3822 | test_acc: 0.3887 | Time: 3.3810 s
>>> Epoch [ 1399/10000]
train_loss: 2.0752 | train_acc: 0.3978 | val_loss: 2.0876 | val_acc: 0.3823 | test_acc: 0.3886 | Time: 3.3816 s
>>> Epoch [ 1400/10000]
train_loss: 2.0752 | train_acc: 0.3978 | val_loss: 2.0876 | val_acc: 0.3823 | test_acc: 0.3886 | Time: 3.4368 s
>>> Epoch [ 1401/10000]
train_loss: 2.0751 | train_acc: 0.3979 | val_loss: 2.0876 | val_acc: 0.3824 | test_acc: 0.3887 | Time: 3.6078 s
>>> Epoch [ 1402/10000]
train_loss: 2.0751 | train_acc: 0.3979 | val_loss: 2.0875 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.3840 s
>>> Epoch [ 1403/10000]
train_loss: 2.0751 | train_acc: 0.3980 | val_loss: 2.0875 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.3898 s
>>> Epoch [ 1404/10000]
train_loss: 2.0751 | train_acc: 0.3980 | val_loss: 2.0875 | val_acc: 0.3823 | test_acc: 0.3888 | Time: 3.5575 s
>>> Epoch [ 1405/10000]
train_loss: 2.0751 | train_acc: 0.3980 | val_loss: 2.0875 | val_acc: 0.3824 | test_acc: 0.3888 | Time: 3.5127 s
>>> Epoch [ 1406/10000]
train_loss: 2.0750 | train_acc: 0.3980 | val_loss: 2.0875 | val_acc: 0.3825 | test_acc: 0.3889 | Time: 3.6205 s
>>> Epoch [ 1407/10000]
train_loss: 2.0750 | train_acc: 0.3980 | val_loss: 2.0875 | val_acc: 0.3826 | test_acc: 0.3888 | Time: 3.5259 s
>>> Epoch [ 1408/10000]
train_loss: 2.0750 | train_acc: 0.3980 | val_loss: 2.0874 | val_acc: 0.3825 | test_acc: 0.3888 | Time: 3.5926 s
>>> Epoch [ 1409/10000]
train_loss: 2.0750 | train_acc: 0.3981 | val_loss: 2.0874 | val_acc: 0.3825 | test_acc: 0.3887 | Time: 3.8666 s
>>> Epoch [ 1410/10000]
train_loss: 2.0749 | train_acc: 0.3981 | val_loss: 2.0874 | val_acc: 0.3825 | test_acc: 0.3887 | Time: 3.5777 s
>>> Epoch [ 1411/10000]
train_loss: 2.0749 | train_acc: 0.3982 | val_loss: 2.0874 | val_acc: 0.3826 | test_acc: 0.3887 | Time: 3.7272 s
>>> Epoch [ 1412/10000]
train_loss: 2.0749 | train_acc: 0.3982 | val_loss: 2.0874 | val_acc: 0.3827 | test_acc: 0.3886 | Time: 3.6410 s
>>> Epoch [ 1413/10000]
train_loss: 2.0749 | train_acc: 0.3982 | val_loss: 2.0873 | val_acc: 0.3827 | test_acc: 0.3885 | Time: 3.8062 s
>>> Epoch [ 1414/10000]
train_loss: 2.0749 | train_acc: 0.3982 | val_loss: 2.0873 | val_acc: 0.3827 | test_acc: 0.3885 | Time: 3.6241 s
>>> Epoch [ 1415/10000]
train_loss: 2.0748 | train_acc: 0.3983 | val_loss: 2.0873 | val_acc: 0.3827 | test_acc: 0.3884 | Time: 3.6434 s
>>> Epoch [ 1416/10000]
train_loss: 2.0748 | train_acc: 0.3984 | val_loss: 2.0873 | val_acc: 0.3827 | test_acc: 0.3885 | Time: 3.6619 s
>>> Epoch [ 1417/10000]
train_loss: 2.0748 | train_acc: 0.3984 | val_loss: 2.0873 | val_acc: 0.3827 | test_acc: 0.3886 | Time: 3.7487 s
>>> Epoch [ 1418/10000]
train_loss: 2.0748 | train_acc: 0.3985 | val_loss: 2.0872 | val_acc: 0.3828 | test_acc: 0.3886 | Time: 3.7237 s
>>> Epoch [ 1419/10000]
train_loss: 2.0748 | train_acc: 0.3985 | val_loss: 2.0872 | val_acc: 0.3829 | test_acc: 0.3886 | Time: 3.9721 s
>>> Epoch [ 1420/10000]
train_loss: 2.0747 | train_acc: 0.3985 | val_loss: 2.0872 | val_acc: 0.3830 | test_acc: 0.3886 | Time: 3.6757 s
>>> Epoch [ 1421/10000]
train_loss: 2.0747 | train_acc: 0.3985 | val_loss: 2.0872 | val_acc: 0.3830 | test_acc: 0.3886 | Time: 3.6474 s
>>> Epoch [ 1422/10000]
train_loss: 2.0747 | train_acc: 0.3985 | val_loss: 2.0872 | val_acc: 0.3831 | test_acc: 0.3887 | Time: 3.5530 s
>>> Epoch [ 1423/10000]
train_loss: 2.0747 | train_acc: 0.3985 | val_loss: 2.0872 | val_acc: 0.3831 | test_acc: 0.3888 | Time: 3.8141 s
>>> Epoch [ 1424/10000]
train_loss: 2.0747 | train_acc: 0.3986 | val_loss: 2.0871 | val_acc: 0.3830 | test_acc: 0.3888 | Time: 3.5558 s
>>> Epoch [ 1425/10000]
train_loss: 2.0746 | train_acc: 0.3986 | val_loss: 2.0871 | val_acc: 0.3830 | test_acc: 0.3887 | Time: 3.5834 s
>>> Epoch [ 1426/10000]
train_loss: 2.0746 | train_acc: 0.3987 | val_loss: 2.0871 | val_acc: 0.3831 | test_acc: 0.3886 | Time: 3.6030 s
>>> Epoch [ 1427/10000]
train_loss: 2.0746 | train_acc: 0.3987 | val_loss: 2.0871 | val_acc: 0.3834 | test_acc: 0.3886 | Time: 3.7906 s
>>> Epoch [ 1428/10000]
train_loss: 2.0746 | train_acc: 0.3987 | val_loss: 2.0871 | val_acc: 0.3834 | test_acc: 0.3889 | Time: 3.6957 s
>>> Epoch [ 1429/10000]
train_loss: 2.0746 | train_acc: 0.3987 | val_loss: 2.0870 | val_acc: 0.3833 | test_acc: 0.3889 | Time: 3.6892 s
>>> Epoch [ 1430/10000]
train_loss: 2.0745 | train_acc: 0.3987 | val_loss: 2.0870 | val_acc: 0.3833 | test_acc: 0.3889 | Time: 3.6959 s
>>> Epoch [ 1431/10000]
train_loss: 2.0745 | train_acc: 0.3988 | val_loss: 2.0870 | val_acc: 0.3834 | test_acc: 0.3889 | Time: 4.0182 s
>>> Epoch [ 1432/10000]
train_loss: 2.0745 | train_acc: 0.3988 | val_loss: 2.0870 | val_acc: 0.3835 | test_acc: 0.3890 | Time: 4.0852 s
>>> Epoch [ 1433/10000]
train_loss: 2.0745 | train_acc: 0.3988 | val_loss: 2.0870 | val_acc: 0.3835 | test_acc: 0.3890 | Time: 3.6565 s
>>> Epoch [ 1434/10000]
train_loss: 2.0744 | train_acc: 0.3989 | val_loss: 2.0870 | val_acc: 0.3834 | test_acc: 0.3891 | Time: 3.6366 s
>>> Epoch [ 1435/10000]
train_loss: 2.0744 | train_acc: 0.3989 | val_loss: 2.0869 | val_acc: 0.3835 | test_acc: 0.3891 | Time: 3.7926 s
>>> Epoch [ 1436/10000]
train_loss: 2.0744 | train_acc: 0.3989 | val_loss: 2.0869 | val_acc: 0.3835 | test_acc: 0.3891 | Time: 3.7146 s
>>> Epoch [ 1437/10000]
train_loss: 2.0744 | train_acc: 0.3989 | val_loss: 2.0869 | val_acc: 0.3835 | test_acc: 0.3891 | Time: 3.5484 s
>>> Epoch [ 1438/10000]
train_loss: 2.0744 | train_acc: 0.3989 | val_loss: 2.0869 | val_acc: 0.3835 | test_acc: 0.3891 | Time: 3.8484 s
>>> Epoch [ 1439/10000]
train_loss: 2.0743 | train_acc: 0.3990 | val_loss: 2.0869 | val_acc: 0.3836 | test_acc: 0.3891 | Time: 3.7409 s
>>> Epoch [ 1440/10000]
train_loss: 2.0743 | train_acc: 0.3989 | val_loss: 2.0868 | val_acc: 0.3836 | test_acc: 0.3891 | Time: 3.6292 s
>>> Epoch [ 1441/10000]
train_loss: 2.0743 | train_acc: 0.3989 | val_loss: 2.0868 | val_acc: 0.3837 | test_acc: 0.3892 | Time: 3.5086 s
>>> Epoch [ 1442/10000]
train_loss: 2.0743 | train_acc: 0.3989 | val_loss: 2.0868 | val_acc: 0.3837 | test_acc: 0.3892 | Time: 3.5262 s
>>> Epoch [ 1443/10000]
train_loss: 2.0743 | train_acc: 0.3990 | val_loss: 2.0868 | val_acc: 0.3837 | test_acc: 0.3892 | Time: 3.8999 s
>>> Epoch [ 1444/10000]
train_loss: 2.0742 | train_acc: 0.3990 | val_loss: 2.0868 | val_acc: 0.3837 | test_acc: 0.3893 | Time: 3.9878 s
>>> Epoch [ 1445/10000]
train_loss: 2.0742 | train_acc: 0.3991 | val_loss: 2.0868 | val_acc: 0.3838 | test_acc: 0.3893 | Time: 3.7057 s
>>> Epoch [ 1446/10000]
train_loss: 2.0742 | train_acc: 0.3992 | val_loss: 2.0867 | val_acc: 0.3838 | test_acc: 0.3893 | Time: 3.7349 s
>>> Epoch [ 1447/10000]
train_loss: 2.0742 | train_acc: 0.3992 | val_loss: 2.0867 | val_acc: 0.3839 | test_acc: 0.3894 | Time: 5.4660 s
>>> Epoch [ 1448/10000]
train_loss: 2.0742 | train_acc: 0.3992 | val_loss: 2.0867 | val_acc: 0.3838 | test_acc: 0.3893 | Time: 5.6514 s
>>> Epoch [ 1449/10000]
train_loss: 2.0741 | train_acc: 0.3992 | val_loss: 2.0867 | val_acc: 0.3839 | test_acc: 0.3893 | Time: 5.1834 s
>>> Epoch [ 1450/10000]
train_loss: 2.0741 | train_acc: 0.3991 | val_loss: 2.0867 | val_acc: 0.3838 | test_acc: 0.3894 | Time: 4.6178 s
>>> Epoch [ 1451/10000]
train_loss: 2.0741 | train_acc: 0.3991 | val_loss: 2.0867 | val_acc: 0.3839 | test_acc: 0.3894 | Time: 5.6378 s
>>> Epoch [ 1452/10000]
train_loss: 2.0741 | train_acc: 0.3991 | val_loss: 2.0866 | val_acc: 0.3839 | test_acc: 0.3894 | Time: 5.3004 s
>>> Epoch [ 1453/10000]
train_loss: 2.0741 | train_acc: 0.3992 | val_loss: 2.0866 | val_acc: 0.3839 | test_acc: 0.3894 | Time: 5.1764 s
>>> Epoch [ 1454/10000]
train_loss: 2.0740 | train_acc: 0.3992 | val_loss: 2.0866 | val_acc: 0.3839 | test_acc: 0.3894 | Time: 3.4551 s
>>> Epoch [ 1455/10000]
train_loss: 2.0740 | train_acc: 0.3991 | val_loss: 2.0866 | val_acc: 0.3839 | test_acc: 0.3894 | Time: 3.3569 s
>>> Epoch [ 1456/10000]
train_loss: 2.0740 | train_acc: 0.3992 | val_loss: 2.0866 | val_acc: 0.3839 | test_acc: 0.3894 | Time: 3.6803 s
>>> Epoch [ 1457/10000]
train_loss: 2.0740 | train_acc: 0.3992 | val_loss: 2.0865 | val_acc: 0.3839 | test_acc: 0.3896 | Time: 3.5821 s
>>> Epoch [ 1458/10000]
train_loss: 2.0740 | train_acc: 0.3992 | val_loss: 2.0865 | val_acc: 0.3840 | test_acc: 0.3897 | Time: 3.5343 s
>>> Epoch [ 1459/10000]
train_loss: 2.0739 | train_acc: 0.3992 | val_loss: 2.0865 | val_acc: 0.3840 | test_acc: 0.3897 | Time: 3.7465 s
>>> Epoch [ 1460/10000]
train_loss: 2.0739 | train_acc: 0.3992 | val_loss: 2.0865 | val_acc: 0.3840 | test_acc: 0.3896 | Time: 3.8943 s
>>> Epoch [ 1461/10000]
train_loss: 2.0739 | train_acc: 0.3993 | val_loss: 2.0865 | val_acc: 0.3840 | test_acc: 0.3896 | Time: 3.6992 s
>>> Epoch [ 1462/10000]
train_loss: 2.0739 | train_acc: 0.3993 | val_loss: 2.0865 | val_acc: 0.3839 | test_acc: 0.3898 | Time: 3.7907 s
>>> Epoch [ 1463/10000]
train_loss: 2.0739 | train_acc: 0.3993 | val_loss: 2.0864 | val_acc: 0.3841 | test_acc: 0.3898 | Time: 3.7993 s
>>> Epoch [ 1464/10000]
train_loss: 2.0738 | train_acc: 0.3993 | val_loss: 2.0864 | val_acc: 0.3841 | test_acc: 0.3898 | Time: 3.7877 s
>>> Epoch [ 1465/10000]
train_loss: 2.0738 | train_acc: 0.3994 | val_loss: 2.0864 | val_acc: 0.3840 | test_acc: 0.3898 | Time: 3.8990 s
>>> Epoch [ 1466/10000]
train_loss: 2.0738 | train_acc: 0.3993 | val_loss: 2.0864 | val_acc: 0.3841 | test_acc: 0.3899 | Time: 4.1324 s
>>> Epoch [ 1467/10000]
train_loss: 2.0738 | train_acc: 0.3994 | val_loss: 2.0864 | val_acc: 0.3843 | test_acc: 0.3899 | Time: 3.9908 s
>>> Epoch [ 1468/10000]
train_loss: 2.0738 | train_acc: 0.3994 | val_loss: 2.0863 | val_acc: 0.3844 | test_acc: 0.3900 | Time: 3.7079 s
>>> Epoch [ 1469/10000]
train_loss: 2.0737 | train_acc: 0.3994 | val_loss: 2.0863 | val_acc: 0.3845 | test_acc: 0.3901 | Time: 3.6446 s
>>> Epoch [ 1470/10000]
train_loss: 2.0737 | train_acc: 0.3994 | val_loss: 2.0863 | val_acc: 0.3845 | test_acc: 0.3901 | Time: 3.8684 s
>>> Epoch [ 1471/10000]
train_loss: 2.0737 | train_acc: 0.3994 | val_loss: 2.0863 | val_acc: 0.3845 | test_acc: 0.3901 | Time: 3.8341 s
>>> Epoch [ 1472/10000]
train_loss: 2.0737 | train_acc: 0.3994 | val_loss: 2.0863 | val_acc: 0.3846 | test_acc: 0.3901 | Time: 3.7894 s
>>> Epoch [ 1473/10000]
train_loss: 2.0737 | train_acc: 0.3994 | val_loss: 2.0863 | val_acc: 0.3846 | test_acc: 0.3902 | Time: 3.8662 s
>>> Epoch [ 1474/10000]
train_loss: 2.0736 | train_acc: 0.3994 | val_loss: 2.0862 | val_acc: 0.3847 | test_acc: 0.3901 | Time: 3.7449 s
>>> Epoch [ 1475/10000]
train_loss: 2.0736 | train_acc: 0.3994 | val_loss: 2.0862 | val_acc: 0.3848 | test_acc: 0.3900 | Time: 4.1038 s
>>> Epoch [ 1476/10000]
train_loss: 2.0736 | train_acc: 0.3994 | val_loss: 2.0862 | val_acc: 0.3847 | test_acc: 0.3900 | Time: 3.7765 s
>>> Epoch [ 1477/10000]
train_loss: 2.0736 | train_acc: 0.3994 | val_loss: 2.0862 | val_acc: 0.3847 | test_acc: 0.3900 | Time: 3.8598 s
>>> Epoch [ 1478/10000]
train_loss: 2.0736 | train_acc: 0.3994 | val_loss: 2.0862 | val_acc: 0.3847 | test_acc: 0.3900 | Time: 3.6069 s
>>> Epoch [ 1479/10000]
train_loss: 2.0735 | train_acc: 0.3995 | val_loss: 2.0862 | val_acc: 0.3847 | test_acc: 0.3899 | Time: 3.9606 s
>>> Epoch [ 1480/10000]
train_loss: 2.0735 | train_acc: 0.3994 | val_loss: 2.0861 | val_acc: 0.3846 | test_acc: 0.3900 | Time: 3.9585 s
>>> Epoch [ 1481/10000]
train_loss: 2.0735 | train_acc: 0.3995 | val_loss: 2.0861 | val_acc: 0.3846 | test_acc: 0.3900 | Time: 3.9033 s
>>> Epoch [ 1482/10000]
train_loss: 2.0735 | train_acc: 0.3995 | val_loss: 2.0861 | val_acc: 0.3846 | test_acc: 0.3901 | Time: 3.6591 s
>>> Epoch [ 1483/10000]
train_loss: 2.0735 | train_acc: 0.3995 | val_loss: 2.0861 | val_acc: 0.3846 | test_acc: 0.3902 | Time: 3.7476 s
>>> Epoch [ 1484/10000]
train_loss: 2.0734 | train_acc: 0.3995 | val_loss: 2.0861 | val_acc: 0.3845 | test_acc: 0.3902 | Time: 3.8060 s
>>> Epoch [ 1485/10000]
train_loss: 2.0734 | train_acc: 0.3995 | val_loss: 2.0860 | val_acc: 0.3845 | test_acc: 0.3902 | Time: 3.7352 s
>>> Epoch [ 1486/10000]
train_loss: 2.0734 | train_acc: 0.3995 | val_loss: 2.0860 | val_acc: 0.3846 | test_acc: 0.3903 | Time: 3.7267 s
>>> Epoch [ 1487/10000]
train_loss: 2.0734 | train_acc: 0.3996 | val_loss: 2.0860 | val_acc: 0.3846 | test_acc: 0.3903 | Time: 3.8300 s
>>> Epoch [ 1488/10000]
train_loss: 2.0734 | train_acc: 0.3996 | val_loss: 2.0860 | val_acc: 0.3847 | test_acc: 0.3903 | Time: 4.0590 s
>>> Epoch [ 1489/10000]
train_loss: 2.0733 | train_acc: 0.3997 | val_loss: 2.0860 | val_acc: 0.3848 | test_acc: 0.3903 | Time: 3.9593 s
>>> Epoch [ 1490/10000]
train_loss: 2.0733 | train_acc: 0.3997 | val_loss: 2.0860 | val_acc: 0.3848 | test_acc: 0.3903 | Time: 3.8987 s
>>> Epoch [ 1491/10000]
train_loss: 2.0733 | train_acc: 0.3997 | val_loss: 2.0859 | val_acc: 0.3848 | test_acc: 0.3903 | Time: 3.6644 s
>>> Epoch [ 1492/10000]
train_loss: 2.0733 | train_acc: 0.3998 | val_loss: 2.0859 | val_acc: 0.3849 | test_acc: 0.3903 | Time: 3.9842 s
>>> Epoch [ 1493/10000]
train_loss: 2.0733 | train_acc: 0.3998 | val_loss: 2.0859 | val_acc: 0.3849 | test_acc: 0.3904 | Time: 3.7808 s
>>> Epoch [ 1494/10000]
train_loss: 2.0732 | train_acc: 0.3998 | val_loss: 2.0859 | val_acc: 0.3849 | test_acc: 0.3904 | Time: 3.9164 s
>>> Epoch [ 1495/10000]
train_loss: 2.0732 | train_acc: 0.3998 | val_loss: 2.0859 | val_acc: 0.3851 | test_acc: 0.3904 | Time: 3.7886 s
>>> Epoch [ 1496/10000]
train_loss: 2.0732 | train_acc: 0.3997 | val_loss: 2.0859 | val_acc: 0.3850 | test_acc: 0.3903 | Time: 3.8919 s
>>> Epoch [ 1497/10000]
train_loss: 2.0732 | train_acc: 0.3998 | val_loss: 2.0858 | val_acc: 0.3850 | test_acc: 0.3903 | Time: 3.8938 s
>>> Epoch [ 1498/10000]
train_loss: 2.0732 | train_acc: 0.3998 | val_loss: 2.0858 | val_acc: 0.3850 | test_acc: 0.3903 | Time: 4.1347 s
>>> Epoch [ 1499/10000]
train_loss: 2.0731 | train_acc: 0.3998 | val_loss: 2.0858 | val_acc: 0.3850 | test_acc: 0.3903 | Time: 4.0890 s
>>> Epoch [ 1500/10000]
train_loss: 2.0731 | train_acc: 0.3997 | val_loss: 2.0858 | val_acc: 0.3850 | test_acc: 0.3902 | Time: 3.2103 s
>>> Epoch [ 1501/10000]
train_loss: 2.0731 | train_acc: 0.3998 | val_loss: 2.0858 | val_acc: 0.3849 | test_acc: 0.3903 | Time: 3.1714 s
>>> Epoch [ 1502/10000]
train_loss: 2.0731 | train_acc: 0.3998 | val_loss: 2.0858 | val_acc: 0.3848 | test_acc: 0.3903 | Time: 3.2071 s
>>> Epoch [ 1503/10000]
train_loss: 2.0731 | train_acc: 0.3999 | val_loss: 2.0857 | val_acc: 0.3847 | test_acc: 0.3903 | Time: 3.2407 s
>>> Epoch [ 1504/10000]
train_loss: 2.0730 | train_acc: 0.3999 | val_loss: 2.0857 | val_acc: 0.3847 | test_acc: 0.3903 | Time: 3.2461 s
>>> Epoch [ 1505/10000]
train_loss: 2.0730 | train_acc: 0.3999 | val_loss: 2.0857 | val_acc: 0.3846 | test_acc: 0.3904 | Time: 3.2071 s
>>> Epoch [ 1506/10000]
train_loss: 2.0730 | train_acc: 0.4000 | val_loss: 2.0857 | val_acc: 0.3845 | test_acc: 0.3904 | Time: 3.1818 s
>>> Epoch [ 1507/10000]
train_loss: 2.0730 | train_acc: 0.4001 | val_loss: 2.0857 | val_acc: 0.3846 | test_acc: 0.3904 | Time: 3.0805 s
>>> Epoch [ 1508/10000]
train_loss: 2.0730 | train_acc: 0.4001 | val_loss: 2.0857 | val_acc: 0.3847 | test_acc: 0.3904 | Time: 3.1529 s
>>> Epoch [ 1509/10000]
train_loss: 2.0730 | train_acc: 0.4001 | val_loss: 2.0856 | val_acc: 0.3847 | test_acc: 0.3904 | Time: 3.0228 s
>>> Epoch [ 1510/10000]
train_loss: 2.0729 | train_acc: 0.4001 | val_loss: 2.0856 | val_acc: 0.3847 | test_acc: 0.3904 | Time: 3.3759 s
>>> Epoch [ 1511/10000]
train_loss: 2.0729 | train_acc: 0.4002 | val_loss: 2.0856 | val_acc: 0.3847 | test_acc: 0.3904 | Time: 3.1331 s
>>> Epoch [ 1512/10000]
train_loss: 2.0729 | train_acc: 0.4001 | val_loss: 2.0856 | val_acc: 0.3846 | test_acc: 0.3904 | Time: 3.0525 s
>>> Epoch [ 1513/10000]
train_loss: 2.0729 | train_acc: 0.4001 | val_loss: 2.0856 | val_acc: 0.3846 | test_acc: 0.3905 | Time: 3.1240 s
>>> Epoch [ 1514/10000]
train_loss: 2.0729 | train_acc: 0.4001 | val_loss: 2.0855 | val_acc: 0.3846 | test_acc: 0.3906 | Time: 3.1899 s
>>> Epoch [ 1515/10000]
train_loss: 2.0728 | train_acc: 0.4000 | val_loss: 2.0855 | val_acc: 0.3846 | test_acc: 0.3906 | Time: 3.1867 s
>>> Epoch [ 1516/10000]
train_loss: 2.0728 | train_acc: 0.4001 | val_loss: 2.0855 | val_acc: 0.3845 | test_acc: 0.3906 | Time: 3.2913 s
>>> Epoch [ 1517/10000]
train_loss: 2.0728 | train_acc: 0.4001 | val_loss: 2.0855 | val_acc: 0.3845 | test_acc: 0.3906 | Time: 3.1570 s
>>> Epoch [ 1518/10000]
train_loss: 2.0728 | train_acc: 0.4001 | val_loss: 2.0855 | val_acc: 0.3845 | test_acc: 0.3906 | Time: 3.2153 s
>>> Epoch [ 1519/10000]
train_loss: 2.0728 | train_acc: 0.4001 | val_loss: 2.0855 | val_acc: 0.3845 | test_acc: 0.3906 | Time: 3.2116 s
>>> Epoch [ 1520/10000]
train_loss: 2.0727 | train_acc: 0.4002 | val_loss: 2.0854 | val_acc: 0.3845 | test_acc: 0.3906 | Time: 3.2713 s
>>> Epoch [ 1521/10000]
train_loss: 2.0727 | train_acc: 0.4002 | val_loss: 2.0854 | val_acc: 0.3845 | test_acc: 0.3907 | Time: 3.1479 s
>>> Epoch [ 1522/10000]
train_loss: 2.0727 | train_acc: 0.4002 | val_loss: 2.0854 | val_acc: 0.3846 | test_acc: 0.3906 | Time: 3.2794 s
>>> Epoch [ 1523/10000]
train_loss: 2.0727 | train_acc: 0.4002 | val_loss: 2.0854 | val_acc: 0.3846 | test_acc: 0.3906 | Time: 3.2425 s
>>> Epoch [ 1524/10000]
train_loss: 2.0727 | train_acc: 0.4002 | val_loss: 2.0854 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 3.3165 s
>>> Epoch [ 1525/10000]
train_loss: 2.0726 | train_acc: 0.4003 | val_loss: 2.0854 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 3.2561 s
>>> Epoch [ 1526/10000]
train_loss: 2.0726 | train_acc: 0.4003 | val_loss: 2.0853 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 3.2355 s
>>> Epoch [ 1527/10000]
train_loss: 2.0726 | train_acc: 0.4004 | val_loss: 2.0853 | val_acc: 0.3847 | test_acc: 0.3905 | Time: 3.1915 s
>>> Epoch [ 1528/10000]
train_loss: 2.0726 | train_acc: 0.4004 | val_loss: 2.0853 | val_acc: 0.3847 | test_acc: 0.3905 | Time: 3.3108 s
>>> Epoch [ 1529/10000]
train_loss: 2.0726 | train_acc: 0.4004 | val_loss: 2.0853 | val_acc: 0.3847 | test_acc: 0.3904 | Time: 3.2110 s
>>> Epoch [ 1530/10000]
train_loss: 2.0725 | train_acc: 0.4004 | val_loss: 2.0853 | val_acc: 0.3846 | test_acc: 0.3904 | Time: 3.1745 s
>>> Epoch [ 1531/10000]
train_loss: 2.0725 | train_acc: 0.4005 | val_loss: 2.0853 | val_acc: 0.3846 | test_acc: 0.3903 | Time: 3.1969 s
>>> Epoch [ 1532/10000]
train_loss: 2.0725 | train_acc: 0.4005 | val_loss: 2.0852 | val_acc: 0.3847 | test_acc: 0.3903 | Time: 3.2444 s
>>> Epoch [ 1533/10000]
train_loss: 2.0725 | train_acc: 0.4005 | val_loss: 2.0852 | val_acc: 0.3847 | test_acc: 0.3903 | Time: 3.3938 s
>>> Epoch [ 1534/10000]
train_loss: 2.0725 | train_acc: 0.4005 | val_loss: 2.0852 | val_acc: 0.3846 | test_acc: 0.3903 | Time: 3.2814 s
>>> Epoch [ 1535/10000]
train_loss: 2.0724 | train_acc: 0.4005 | val_loss: 2.0852 | val_acc: 0.3846 | test_acc: 0.3904 | Time: 3.2569 s
>>> Epoch [ 1536/10000]
train_loss: 2.0724 | train_acc: 0.4006 | val_loss: 2.0852 | val_acc: 0.3847 | test_acc: 0.3903 | Time: 3.3502 s
>>> Epoch [ 1537/10000]
train_loss: 2.0724 | train_acc: 0.4006 | val_loss: 2.0852 | val_acc: 0.3847 | test_acc: 0.3904 | Time: 3.3447 s
>>> Epoch [ 1538/10000]
train_loss: 2.0724 | train_acc: 0.4006 | val_loss: 2.0851 | val_acc: 0.3845 | test_acc: 0.3903 | Time: 3.3003 s
>>> Epoch [ 1539/10000]
train_loss: 2.0724 | train_acc: 0.4006 | val_loss: 2.0851 | val_acc: 0.3845 | test_acc: 0.3902 | Time: 3.2664 s
>>> Epoch [ 1540/10000]
train_loss: 2.0724 | train_acc: 0.4007 | val_loss: 2.0851 | val_acc: 0.3845 | test_acc: 0.3902 | Time: 3.3311 s
>>> Epoch [ 1541/10000]
train_loss: 2.0723 | train_acc: 0.4007 | val_loss: 2.0851 | val_acc: 0.3846 | test_acc: 0.3902 | Time: 3.1866 s
>>> Epoch [ 1542/10000]
train_loss: 2.0723 | train_acc: 0.4007 | val_loss: 2.0851 | val_acc: 0.3846 | test_acc: 0.3901 | Time: 3.2445 s
>>> Epoch [ 1543/10000]
train_loss: 2.0723 | train_acc: 0.4007 | val_loss: 2.0851 | val_acc: 0.3846 | test_acc: 0.3902 | Time: 3.1559 s
>>> Epoch [ 1544/10000]
train_loss: 2.0723 | train_acc: 0.4007 | val_loss: 2.0850 | val_acc: 0.3846 | test_acc: 0.3904 | Time: 3.2006 s
>>> Epoch [ 1545/10000]
train_loss: 2.0723 | train_acc: 0.4007 | val_loss: 2.0850 | val_acc: 0.3846 | test_acc: 0.3905 | Time: 3.2724 s
>>> Epoch [ 1546/10000]
train_loss: 2.0722 | train_acc: 0.4008 | val_loss: 2.0850 | val_acc: 0.3847 | test_acc: 0.3905 | Time: 3.2315 s
>>> Epoch [ 1547/10000]
train_loss: 2.0722 | train_acc: 0.4007 | val_loss: 2.0850 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 3.2663 s
>>> Epoch [ 1548/10000]
train_loss: 2.0722 | train_acc: 0.4008 | val_loss: 2.0850 | val_acc: 0.3847 | test_acc: 0.3907 | Time: 5.8004 s
>>> Epoch [ 1549/10000]
train_loss: 2.0722 | train_acc: 0.4007 | val_loss: 2.0850 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 5.8841 s
>>> Epoch [ 1550/10000]
train_loss: 2.0722 | train_acc: 0.4008 | val_loss: 2.0849 | val_acc: 0.3849 | test_acc: 0.3904 | Time: 5.9837 s
>>> Epoch [ 1551/10000]
train_loss: 2.0721 | train_acc: 0.4008 | val_loss: 2.0849 | val_acc: 0.3848 | test_acc: 0.3905 | Time: 5.9238 s
>>> Epoch [ 1552/10000]
train_loss: 2.0721 | train_acc: 0.4008 | val_loss: 2.0849 | val_acc: 0.3848 | test_acc: 0.3905 | Time: 6.0624 s
>>> Epoch [ 1553/10000]
train_loss: 2.0721 | train_acc: 0.4008 | val_loss: 2.0849 | val_acc: 0.3848 | test_acc: 0.3906 | Time: 5.7856 s
>>> Epoch [ 1554/10000]
train_loss: 2.0721 | train_acc: 0.4008 | val_loss: 2.0849 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 5.8891 s
>>> Epoch [ 1555/10000]
train_loss: 2.0721 | train_acc: 0.4008 | val_loss: 2.0849 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 5.4221 s
>>> Epoch [ 1556/10000]
train_loss: 2.0721 | train_acc: 0.4009 | val_loss: 2.0848 | val_acc: 0.3846 | test_acc: 0.3907 | Time: 4.3230 s
>>> Epoch [ 1557/10000]
train_loss: 2.0720 | train_acc: 0.4009 | val_loss: 2.0848 | val_acc: 0.3845 | test_acc: 0.3908 | Time: 3.5699 s
>>> Epoch [ 1558/10000]
train_loss: 2.0720 | train_acc: 0.4009 | val_loss: 2.0848 | val_acc: 0.3845 | test_acc: 0.3908 | Time: 3.6153 s
>>> Epoch [ 1559/10000]
train_loss: 2.0720 | train_acc: 0.4009 | val_loss: 2.0848 | val_acc: 0.3844 | test_acc: 0.3908 | Time: 3.6139 s
>>> Epoch [ 1560/10000]
train_loss: 2.0720 | train_acc: 0.4010 | val_loss: 2.0848 | val_acc: 0.3841 | test_acc: 0.3908 | Time: 4.0722 s
>>> Epoch [ 1561/10000]
train_loss: 2.0720 | train_acc: 0.4009 | val_loss: 2.0848 | val_acc: 0.3841 | test_acc: 0.3907 | Time: 3.9588 s
>>> Epoch [ 1562/10000]
train_loss: 2.0719 | train_acc: 0.4010 | val_loss: 2.0847 | val_acc: 0.3841 | test_acc: 0.3907 | Time: 4.5449 s
>>> Epoch [ 1563/10000]
train_loss: 2.0719 | train_acc: 0.4010 | val_loss: 2.0847 | val_acc: 0.3841 | test_acc: 0.3908 | Time: 5.8613 s
>>> Epoch [ 1564/10000]
train_loss: 2.0719 | train_acc: 0.4011 | val_loss: 2.0847 | val_acc: 0.3843 | test_acc: 0.3908 | Time: 4.3592 s
>>> Epoch [ 1565/10000]
train_loss: 2.0719 | train_acc: 0.4011 | val_loss: 2.0847 | val_acc: 0.3843 | test_acc: 0.3908 | Time: 5.6015 s
>>> Epoch [ 1566/10000]
train_loss: 2.0719 | train_acc: 0.4011 | val_loss: 2.0847 | val_acc: 0.3844 | test_acc: 0.3909 | Time: 5.7893 s
>>> Epoch [ 1567/10000]
train_loss: 2.0718 | train_acc: 0.4012 | val_loss: 2.0847 | val_acc: 0.3844 | test_acc: 0.3909 | Time: 3.9358 s
>>> Epoch [ 1568/10000]
train_loss: 2.0718 | train_acc: 0.4011 | val_loss: 2.0846 | val_acc: 0.3845 | test_acc: 0.3909 | Time: 3.6344 s
>>> Epoch [ 1569/10000]
train_loss: 2.0718 | train_acc: 0.4011 | val_loss: 2.0846 | val_acc: 0.3845 | test_acc: 0.3907 | Time: 3.9909 s
>>> Epoch [ 1570/10000]
train_loss: 2.0718 | train_acc: 0.4011 | val_loss: 2.0846 | val_acc: 0.3846 | test_acc: 0.3905 | Time: 4.0361 s
>>> Epoch [ 1571/10000]
train_loss: 2.0718 | train_acc: 0.4011 | val_loss: 2.0846 | val_acc: 0.3846 | test_acc: 0.3905 | Time: 3.5375 s
>>> Epoch [ 1572/10000]
train_loss: 2.0718 | train_acc: 0.4012 | val_loss: 2.0846 | val_acc: 0.3846 | test_acc: 0.3905 | Time: 4.7911 s
>>> Epoch [ 1573/10000]
train_loss: 2.0717 | train_acc: 0.4012 | val_loss: 2.0846 | val_acc: 0.3846 | test_acc: 0.3905 | Time: 3.5202 s
>>> Epoch [ 1574/10000]
train_loss: 2.0717 | train_acc: 0.4012 | val_loss: 2.0845 | val_acc: 0.3846 | test_acc: 0.3906 | Time: 4.0364 s
>>> Epoch [ 1575/10000]
train_loss: 2.0717 | train_acc: 0.4012 | val_loss: 2.0845 | val_acc: 0.3846 | test_acc: 0.3906 | Time: 4.0056 s
>>> Epoch [ 1576/10000]
train_loss: 2.0717 | train_acc: 0.4013 | val_loss: 2.0845 | val_acc: 0.3846 | test_acc: 0.3906 | Time: 4.0174 s
>>> Epoch [ 1577/10000]
train_loss: 2.0717 | train_acc: 0.4012 | val_loss: 2.0845 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 3.9431 s
>>> Epoch [ 1578/10000]
train_loss: 2.0716 | train_acc: 0.4013 | val_loss: 2.0845 | val_acc: 0.3847 | test_acc: 0.3905 | Time: 4.0629 s
>>> Epoch [ 1579/10000]
train_loss: 2.0716 | train_acc: 0.4014 | val_loss: 2.0845 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 4.0613 s
>>> Epoch [ 1580/10000]
train_loss: 2.0716 | train_acc: 0.4014 | val_loss: 2.0844 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 4.1129 s
>>> Epoch [ 1581/10000]
train_loss: 2.0716 | train_acc: 0.4014 | val_loss: 2.0844 | val_acc: 0.3847 | test_acc: 0.3906 | Time: 4.0146 s
>>> Epoch [ 1582/10000]
train_loss: 2.0716 | train_acc: 0.4014 | val_loss: 2.0844 | val_acc: 0.3849 | test_acc: 0.3905 | Time: 4.0220 s
>>> Epoch [ 1583/10000]
train_loss: 2.0715 | train_acc: 0.4014 | val_loss: 2.0844 | val_acc: 0.3849 | test_acc: 0.3905 | Time: 3.8461 s
>>> Epoch [ 1584/10000]
train_loss: 2.0715 | train_acc: 0.4014 | val_loss: 2.0844 | val_acc: 0.3851 | test_acc: 0.3905 | Time: 4.2278 s
>>> Epoch [ 1585/10000]
train_loss: 2.0715 | train_acc: 0.4015 | val_loss: 2.0844 | val_acc: 0.3851 | test_acc: 0.3905 | Time: 4.0829 s
>>> Epoch [ 1586/10000]
train_loss: 2.0715 | train_acc: 0.4015 | val_loss: 2.0843 | val_acc: 0.3851 | test_acc: 0.3905 | Time: 3.9862 s
>>> Epoch [ 1587/10000]
train_loss: 2.0715 | train_acc: 0.4015 | val_loss: 2.0843 | val_acc: 0.3851 | test_acc: 0.3905 | Time: 3.9686 s
>>> Epoch [ 1588/10000]
train_loss: 2.0715 | train_acc: 0.4015 | val_loss: 2.0843 | val_acc: 0.3851 | test_acc: 0.3905 | Time: 4.1879 s
>>> Epoch [ 1589/10000]
train_loss: 2.0714 | train_acc: 0.4015 | val_loss: 2.0843 | val_acc: 0.3851 | test_acc: 0.3906 | Time: 4.0566 s
>>> Epoch [ 1590/10000]
train_loss: 2.0714 | train_acc: 0.4015 | val_loss: 2.0843 | val_acc: 0.3850 | test_acc: 0.3906 | Time: 3.9109 s
>>> Epoch [ 1591/10000]
train_loss: 2.0714 | train_acc: 0.4015 | val_loss: 2.0843 | val_acc: 0.3850 | test_acc: 0.3906 | Time: 3.9669 s
>>> Epoch [ 1592/10000]
train_loss: 2.0714 | train_acc: 0.4016 | val_loss: 2.0842 | val_acc: 0.3850 | test_acc: 0.3906 | Time: 4.1734 s
>>> Epoch [ 1593/10000]
train_loss: 2.0714 | train_acc: 0.4016 | val_loss: 2.0842 | val_acc: 0.3850 | test_acc: 0.3906 | Time: 4.0005 s
>>> Epoch [ 1594/10000]
train_loss: 2.0713 | train_acc: 0.4016 | val_loss: 2.0842 | val_acc: 0.3850 | test_acc: 0.3907 | Time: 4.0676 s
>>> Epoch [ 1595/10000]
train_loss: 2.0713 | train_acc: 0.4016 | val_loss: 2.0842 | val_acc: 0.3850 | test_acc: 0.3907 | Time: 4.1360 s
>>> Epoch [ 1596/10000]
train_loss: 2.0713 | train_acc: 0.4016 | val_loss: 2.0842 | val_acc: 0.3850 | test_acc: 0.3907 | Time: 3.9119 s
>>> Epoch [ 1597/10000]
train_loss: 2.0713 | train_acc: 0.4016 | val_loss: 2.0842 | val_acc: 0.3850 | test_acc: 0.3907 | Time: 3.8332 s
>>> Epoch [ 1598/10000]
train_loss: 2.0713 | train_acc: 0.4015 | val_loss: 2.0842 | val_acc: 0.3850 | test_acc: 0.3907 | Time: 4.1101 s
>>> Epoch [ 1599/10000]
train_loss: 2.0713 | train_acc: 0.4016 | val_loss: 2.0841 | val_acc: 0.3850 | test_acc: 0.3907 | Time: 4.1653 s
>>> Epoch [ 1600/10000]
train_loss: 2.0712 | train_acc: 0.4016 | val_loss: 2.0841 | val_acc: 0.3850 | test_acc: 0.3908 | Time: 4.0734 s
>>> Epoch [ 1601/10000]
train_loss: 2.0712 | train_acc: 0.4017 | val_loss: 2.0841 | val_acc: 0.3850 | test_acc: 0.3908 | Time: 4.1163 s
>>> Epoch [ 1602/10000]
train_loss: 2.0712 | train_acc: 0.4017 | val_loss: 2.0841 | val_acc: 0.3850 | test_acc: 0.3909 | Time: 4.1950 s
>>> Epoch [ 1603/10000]
train_loss: 2.0712 | train_acc: 0.4017 | val_loss: 2.0841 | val_acc: 0.3850 | test_acc: 0.3909 | Time: 4.0115 s
>>> Epoch [ 1604/10000]
train_loss: 2.0712 | train_acc: 0.4018 | val_loss: 2.0841 | val_acc: 0.3850 | test_acc: 0.3909 | Time: 4.1079 s
>>> Epoch [ 1605/10000]
train_loss: 2.0711 | train_acc: 0.4018 | val_loss: 2.0840 | val_acc: 0.3851 | test_acc: 0.3910 | Time: 4.2199 s
>>> Epoch [ 1606/10000]
train_loss: 2.0711 | train_acc: 0.4018 | val_loss: 2.0840 | val_acc: 0.3851 | test_acc: 0.3910 | Time: 4.0426 s
>>> Epoch [ 1607/10000]
train_loss: 2.0711 | train_acc: 0.4018 | val_loss: 2.0840 | val_acc: 0.3851 | test_acc: 0.3910 | Time: 3.9550 s
>>> Epoch [ 1608/10000]
train_loss: 2.0711 | train_acc: 0.4018 | val_loss: 2.0840 | val_acc: 0.3852 | test_acc: 0.3910 | Time: 4.2056 s
>>> Epoch [ 1609/10000]
train_loss: 2.0711 | train_acc: 0.4018 | val_loss: 2.0840 | val_acc: 0.3852 | test_acc: 0.3909 | Time: 4.1210 s
>>> Epoch [ 1610/10000]
train_loss: 2.0711 | train_acc: 0.4018 | val_loss: 2.0840 | val_acc: 0.3852 | test_acc: 0.3909 | Time: 4.0383 s
>>> Epoch [ 1611/10000]
train_loss: 2.0710 | train_acc: 0.4018 | val_loss: 2.0839 | val_acc: 0.3852 | test_acc: 0.3910 | Time: 3.8416 s
>>> Epoch [ 1612/10000]
train_loss: 2.0710 | train_acc: 0.4019 | val_loss: 2.0839 | val_acc: 0.3852 | test_acc: 0.3910 | Time: 5.5911 s
>>> Epoch [ 1613/10000]
train_loss: 2.0710 | train_acc: 0.4019 | val_loss: 2.0839 | val_acc: 0.3852 | test_acc: 0.3908 | Time: 6.1368 s
>>> Epoch [ 1614/10000]
train_loss: 2.0710 | train_acc: 0.4019 | val_loss: 2.0839 | val_acc: 0.3851 | test_acc: 0.3908 | Time: 6.1847 s
>>> Epoch [ 1615/10000]
train_loss: 2.0710 | train_acc: 0.4019 | val_loss: 2.0839 | val_acc: 0.3851 | test_acc: 0.3908 | Time: 4.1339 s
>>> Epoch [ 1616/10000]
train_loss: 2.0709 | train_acc: 0.4020 | val_loss: 2.0839 | val_acc: 0.3851 | test_acc: 0.3908 | Time: 3.8988 s
>>> Epoch [ 1617/10000]
train_loss: 2.0709 | train_acc: 0.4020 | val_loss: 2.0838 | val_acc: 0.3851 | test_acc: 0.3908 | Time: 3.7689 s
>>> Epoch [ 1618/10000]
train_loss: 2.0709 | train_acc: 0.4020 | val_loss: 2.0838 | val_acc: 0.3851 | test_acc: 0.3908 | Time: 3.6885 s
>>> Epoch [ 1619/10000]
train_loss: 2.0709 | train_acc: 0.4020 | val_loss: 2.0838 | val_acc: 0.3851 | test_acc: 0.3908 | Time: 3.7045 s
>>> Epoch [ 1620/10000]
train_loss: 2.0709 | train_acc: 0.4020 | val_loss: 2.0838 | val_acc: 0.3851 | test_acc: 0.3909 | Time: 3.8168 s
>>> Epoch [ 1621/10000]
train_loss: 2.0709 | train_acc: 0.4021 | val_loss: 2.0838 | val_acc: 0.3851 | test_acc: 0.3909 | Time: 3.7963 s
>>> Epoch [ 1622/10000]
train_loss: 2.0708 | train_acc: 0.4020 | val_loss: 2.0838 | val_acc: 0.3850 | test_acc: 0.3909 | Time: 3.7618 s
>>> Epoch [ 1623/10000]
train_loss: 2.0708 | train_acc: 0.4021 | val_loss: 2.0838 | val_acc: 0.3850 | test_acc: 0.3910 | Time: 3.7306 s
>>> Epoch [ 1624/10000]
train_loss: 2.0708 | train_acc: 0.4021 | val_loss: 2.0837 | val_acc: 0.3851 | test_acc: 0.3911 | Time: 3.6637 s
>>> Epoch [ 1625/10000]
train_loss: 2.0708 | train_acc: 0.4022 | val_loss: 2.0837 | val_acc: 0.3851 | test_acc: 0.3911 | Time: 3.4947 s
>>> Epoch [ 1626/10000]
train_loss: 2.0708 | train_acc: 0.4022 | val_loss: 2.0837 | val_acc: 0.3851 | test_acc: 0.3912 | Time: 3.6984 s
>>> Epoch [ 1627/10000]
train_loss: 2.0707 | train_acc: 0.4022 | val_loss: 2.0837 | val_acc: 0.3852 | test_acc: 0.3912 | Time: 3.9539 s
>>> Epoch [ 1628/10000]
train_loss: 2.0707 | train_acc: 0.4022 | val_loss: 2.0837 | val_acc: 0.3853 | test_acc: 0.3911 | Time: 3.8217 s
>>> Epoch [ 1629/10000]
train_loss: 2.0707 | train_acc: 0.4021 | val_loss: 2.0837 | val_acc: 0.3853 | test_acc: 0.3911 | Time: 3.9005 s
>>> Epoch [ 1630/10000]
train_loss: 2.0707 | train_acc: 0.4021 | val_loss: 2.0836 | val_acc: 0.3853 | test_acc: 0.3912 | Time: 3.6838 s
>>> Epoch [ 1631/10000]
train_loss: 2.0707 | train_acc: 0.4021 | val_loss: 2.0836 | val_acc: 0.3855 | test_acc: 0.3912 | Time: 3.6477 s
>>> Epoch [ 1632/10000]
train_loss: 2.0707 | train_acc: 0.4022 | val_loss: 2.0836 | val_acc: 0.3855 | test_acc: 0.3911 | Time: 5.7750 s
>>> Epoch [ 1633/10000]
train_loss: 2.0706 | train_acc: 0.4022 | val_loss: 2.0836 | val_acc: 0.3855 | test_acc: 0.3911 | Time: 6.0408 s
>>> Epoch [ 1634/10000]
train_loss: 2.0706 | train_acc: 0.4022 | val_loss: 2.0836 | val_acc: 0.3857 | test_acc: 0.3911 | Time: 6.2678 s
>>> Epoch [ 1635/10000]
train_loss: 2.0706 | train_acc: 0.4023 | val_loss: 2.0836 | val_acc: 0.3857 | test_acc: 0.3911 | Time: 4.4888 s
>>> Epoch [ 1636/10000]
train_loss: 2.0706 | train_acc: 0.4023 | val_loss: 2.0835 | val_acc: 0.3857 | test_acc: 0.3911 | Time: 4.0974 s
>>> Epoch [ 1637/10000]
train_loss: 2.0706 | train_acc: 0.4024 | val_loss: 2.0835 | val_acc: 0.3856 | test_acc: 0.3911 | Time: 4.0804 s
>>> Epoch [ 1638/10000]
train_loss: 2.0706 | train_acc: 0.4025 | val_loss: 2.0835 | val_acc: 0.3857 | test_acc: 0.3911 | Time: 4.1456 s
>>> Epoch [ 1639/10000]
train_loss: 2.0705 | train_acc: 0.4025 | val_loss: 2.0835 | val_acc: 0.3858 | test_acc: 0.3912 | Time: 4.1562 s
>>> Epoch [ 1640/10000]
train_loss: 2.0705 | train_acc: 0.4025 | val_loss: 2.0835 | val_acc: 0.3860 | test_acc: 0.3912 | Time: 4.2706 s
>>> Epoch [ 1641/10000]
train_loss: 2.0705 | train_acc: 0.4025 | val_loss: 2.0835 | val_acc: 0.3862 | test_acc: 0.3910 | Time: 4.3126 s
>>> Epoch [ 1642/10000]
train_loss: 2.0705 | train_acc: 0.4025 | val_loss: 2.0835 | val_acc: 0.3862 | test_acc: 0.3911 | Time: 4.1959 s
>>> Epoch [ 1643/10000]
train_loss: 2.0705 | train_acc: 0.4024 | val_loss: 2.0834 | val_acc: 0.3863 | test_acc: 0.3911 | Time: 4.2365 s
>>> Epoch [ 1644/10000]
train_loss: 2.0704 | train_acc: 0.4025 | val_loss: 2.0834 | val_acc: 0.3863 | test_acc: 0.3911 | Time: 4.2748 s
>>> Epoch [ 1645/10000]
train_loss: 2.0704 | train_acc: 0.4024 | val_loss: 2.0834 | val_acc: 0.3862 | test_acc: 0.3911 | Time: 4.1054 s
>>> Epoch [ 1646/10000]
train_loss: 2.0704 | train_acc: 0.4025 | val_loss: 2.0834 | val_acc: 0.3862 | test_acc: 0.3912 | Time: 4.0962 s
>>> Epoch [ 1647/10000]
train_loss: 2.0704 | train_acc: 0.4025 | val_loss: 2.0834 | val_acc: 0.3862 | test_acc: 0.3913 | Time: 4.2499 s
>>> Epoch [ 1648/10000]
train_loss: 2.0704 | train_acc: 0.4026 | val_loss: 2.0834 | val_acc: 0.3862 | test_acc: 0.3913 | Time: 3.9887 s
>>> Epoch [ 1649/10000]
train_loss: 2.0704 | train_acc: 0.4025 | val_loss: 2.0833 | val_acc: 0.3862 | test_acc: 0.3913 | Time: 4.1727 s
>>> Epoch [ 1650/10000]
train_loss: 2.0703 | train_acc: 0.4026 | val_loss: 2.0833 | val_acc: 0.3862 | test_acc: 0.3912 | Time: 4.1341 s
>>> Epoch [ 1651/10000]
train_loss: 2.0703 | train_acc: 0.4026 | val_loss: 2.0833 | val_acc: 0.3862 | test_acc: 0.3912 | Time: 3.9078 s
>>> Epoch [ 1652/10000]
train_loss: 2.0703 | train_acc: 0.4026 | val_loss: 2.0833 | val_acc: 0.3862 | test_acc: 0.3910 | Time: 3.8221 s
>>> Epoch [ 1653/10000]
train_loss: 2.0703 | train_acc: 0.4026 | val_loss: 2.0833 | val_acc: 0.3862 | test_acc: 0.3910 | Time: 3.6001 s
>>> Epoch [ 1654/10000]
train_loss: 2.0703 | train_acc: 0.4026 | val_loss: 2.0833 | val_acc: 0.3862 | test_acc: 0.3910 | Time: 3.8017 s
>>> Epoch [ 1655/10000]
train_loss: 2.0702 | train_acc: 0.4027 | val_loss: 2.0833 | val_acc: 0.3862 | test_acc: 0.3910 | Time: 3.9365 s
>>> Epoch [ 1656/10000]
train_loss: 2.0702 | train_acc: 0.4027 | val_loss: 2.0832 | val_acc: 0.3862 | test_acc: 0.3910 | Time: 3.9979 s
>>> Epoch [ 1657/10000]
train_loss: 2.0702 | train_acc: 0.4027 | val_loss: 2.0832 | val_acc: 0.3861 | test_acc: 0.3911 | Time: 3.9082 s
>>> Epoch [ 1658/10000]
train_loss: 2.0702 | train_acc: 0.4027 | val_loss: 2.0832 | val_acc: 0.3861 | test_acc: 0.3911 | Time: 3.9509 s
>>> Epoch [ 1659/10000]
train_loss: 2.0702 | train_acc: 0.4027 | val_loss: 2.0832 | val_acc: 0.3863 | test_acc: 0.3911 | Time: 3.8645 s
>>> Epoch [ 1660/10000]
train_loss: 2.0702 | train_acc: 0.4028 | val_loss: 2.0832 | val_acc: 0.3863 | test_acc: 0.3911 | Time: 3.9757 s
>>> Epoch [ 1661/10000]
train_loss: 2.0701 | train_acc: 0.4028 | val_loss: 2.0832 | val_acc: 0.3864 | test_acc: 0.3910 | Time: 3.9925 s
>>> Epoch [ 1662/10000]
train_loss: 2.0701 | train_acc: 0.4028 | val_loss: 2.0831 | val_acc: 0.3864 | test_acc: 0.3912 | Time: 4.0319 s
>>> Epoch [ 1663/10000]
train_loss: 2.0701 | train_acc: 0.4027 | val_loss: 2.0831 | val_acc: 0.3864 | test_acc: 0.3912 | Time: 4.0883 s
>>> Epoch [ 1664/10000]
train_loss: 2.0701 | train_acc: 0.4028 | val_loss: 2.0831 | val_acc: 0.3863 | test_acc: 0.3912 | Time: 4.0515 s
>>> Epoch [ 1665/10000]
train_loss: 2.0701 | train_acc: 0.4028 | val_loss: 2.0831 | val_acc: 0.3863 | test_acc: 0.3912 | Time: 3.8743 s
>>> Epoch [ 1666/10000]
train_loss: 2.0701 | train_acc: 0.4028 | val_loss: 2.0831 | val_acc: 0.3863 | test_acc: 0.3912 | Time: 4.2713 s
>>> Epoch [ 1667/10000]
train_loss: 2.0700 | train_acc: 0.4028 | val_loss: 2.0831 | val_acc: 0.3863 | test_acc: 0.3913 | Time: 4.1280 s
>>> Epoch [ 1668/10000]
train_loss: 2.0700 | train_acc: 0.4028 | val_loss: 2.0831 | val_acc: 0.3863 | test_acc: 0.3914 | Time: 4.1893 s
>>> Epoch [ 1669/10000]
train_loss: 2.0700 | train_acc: 0.4028 | val_loss: 2.0830 | val_acc: 0.3863 | test_acc: 0.3914 | Time: 4.2674 s
>>> Epoch [ 1670/10000]
train_loss: 2.0700 | train_acc: 0.4028 | val_loss: 2.0830 | val_acc: 0.3863 | test_acc: 0.3914 | Time: 4.3543 s
>>> Epoch [ 1671/10000]
train_loss: 2.0700 | train_acc: 0.4028 | val_loss: 2.0830 | val_acc: 0.3864 | test_acc: 0.3914 | Time: 4.0693 s
>>> Epoch [ 1672/10000]
train_loss: 2.0700 | train_acc: 0.4028 | val_loss: 2.0830 | val_acc: 0.3864 | test_acc: 0.3914 | Time: 4.2144 s
>>> Epoch [ 1673/10000]
train_loss: 2.0699 | train_acc: 0.4028 | val_loss: 2.0830 | val_acc: 0.3863 | test_acc: 0.3915 | Time: 4.0660 s
>>> Epoch [ 1674/10000]
train_loss: 2.0699 | train_acc: 0.4029 | val_loss: 2.0830 | val_acc: 0.3863 | test_acc: 0.3915 | Time: 4.1319 s
>>> Epoch [ 1675/10000]
train_loss: 2.0699 | train_acc: 0.4029 | val_loss: 2.0829 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.1815 s
>>> Epoch [ 1676/10000]
train_loss: 2.0699 | train_acc: 0.4029 | val_loss: 2.0829 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.3577 s
>>> Epoch [ 1677/10000]
train_loss: 2.0699 | train_acc: 0.4030 | val_loss: 2.0829 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.3042 s
>>> Epoch [ 1678/10000]
train_loss: 2.0698 | train_acc: 0.4029 | val_loss: 2.0829 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.3942 s
>>> Epoch [ 1679/10000]
train_loss: 2.0698 | train_acc: 0.4030 | val_loss: 2.0829 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.1535 s
>>> Epoch [ 1680/10000]
train_loss: 2.0698 | train_acc: 0.4030 | val_loss: 2.0829 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.0023 s
>>> Epoch [ 1681/10000]
train_loss: 2.0698 | train_acc: 0.4030 | val_loss: 2.0829 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.3366 s
>>> Epoch [ 1682/10000]
train_loss: 2.0698 | train_acc: 0.4030 | val_loss: 2.0828 | val_acc: 0.3866 | test_acc: 0.3915 | Time: 4.0512 s
>>> Epoch [ 1683/10000]
train_loss: 2.0698 | train_acc: 0.4030 | val_loss: 2.0828 | val_acc: 0.3866 | test_acc: 0.3915 | Time: 4.2727 s
>>> Epoch [ 1684/10000]
train_loss: 2.0697 | train_acc: 0.4030 | val_loss: 2.0828 | val_acc: 0.3866 | test_acc: 0.3915 | Time: 4.1891 s
>>> Epoch [ 1685/10000]
train_loss: 2.0697 | train_acc: 0.4030 | val_loss: 2.0828 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.4087 s
>>> Epoch [ 1686/10000]
train_loss: 2.0697 | train_acc: 0.4030 | val_loss: 2.0828 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.3990 s
>>> Epoch [ 1687/10000]
train_loss: 2.0697 | train_acc: 0.4030 | val_loss: 2.0828 | val_acc: 0.3866 | test_acc: 0.3915 | Time: 4.2803 s
>>> Epoch [ 1688/10000]
train_loss: 2.0697 | train_acc: 0.4030 | val_loss: 2.0827 | val_acc: 0.3866 | test_acc: 0.3915 | Time: 4.1980 s
>>> Epoch [ 1689/10000]
train_loss: 2.0697 | train_acc: 0.4030 | val_loss: 2.0827 | val_acc: 0.3866 | test_acc: 0.3915 | Time: 4.3109 s
>>> Epoch [ 1690/10000]
train_loss: 2.0696 | train_acc: 0.4030 | val_loss: 2.0827 | val_acc: 0.3866 | test_acc: 0.3915 | Time: 4.3718 s
>>> Epoch [ 1691/10000]
train_loss: 2.0696 | train_acc: 0.4030 | val_loss: 2.0827 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.3886 s
>>> Epoch [ 1692/10000]
train_loss: 2.0696 | train_acc: 0.4030 | val_loss: 2.0827 | val_acc: 0.3865 | test_acc: 0.3914 | Time: 4.1896 s
>>> Epoch [ 1693/10000]
train_loss: 2.0696 | train_acc: 0.4030 | val_loss: 2.0827 | val_acc: 0.3866 | test_acc: 0.3914 | Time: 4.1945 s
>>> Epoch [ 1694/10000]
train_loss: 2.0696 | train_acc: 0.4030 | val_loss: 2.0827 | val_acc: 0.3865 | test_acc: 0.3914 | Time: 4.5048 s
>>> Epoch [ 1695/10000]
train_loss: 2.0696 | train_acc: 0.4031 | val_loss: 2.0826 | val_acc: 0.3865 | test_acc: 0.3914 | Time: 4.3260 s
>>> Epoch [ 1696/10000]
train_loss: 2.0695 | train_acc: 0.4031 | val_loss: 2.0826 | val_acc: 0.3865 | test_acc: 0.3915 | Time: 4.2545 s
>>> Epoch [ 1697/10000]
train_loss: 2.0695 | train_acc: 0.4030 | val_loss: 2.0826 | val_acc: 0.3866 | test_acc: 0.3915 | Time: 4.2326 s
>>> Epoch [ 1698/10000]
train_loss: 2.0695 | train_acc: 0.4030 | val_loss: 2.0826 | val_acc: 0.3864 | test_acc: 0.3916 | Time: 4.2936 s
>>> Epoch [ 1699/10000]
train_loss: 2.0695 | train_acc: 0.4031 | val_loss: 2.0826 | val_acc: 0.3864 | test_acc: 0.3916 | Time: 4.2766 s
>>> Epoch [ 1700/10000]
train_loss: 2.0695 | train_acc: 0.4031 | val_loss: 2.0826 | val_acc: 0.3863 | test_acc: 0.3916 | Time: 4.2781 s
>>> Epoch [ 1701/10000]
train_loss: 2.0695 | train_acc: 0.4032 | val_loss: 2.0826 | val_acc: 0.3863 | test_acc: 0.3915 | Time: 4.2449 s
>>> Epoch [ 1702/10000]
train_loss: 2.0694 | train_acc: 0.4032 | val_loss: 2.0825 | val_acc: 0.3863 | test_acc: 0.3915 | Time: 3.7618 s
>>> Epoch [ 1703/10000]
train_loss: 2.0694 | train_acc: 0.4032 | val_loss: 2.0825 | val_acc: 0.3863 | test_acc: 0.3915 | Time: 5.7797 s
>>> Epoch [ 1704/10000]
train_loss: 2.0694 | train_acc: 0.4033 | val_loss: 2.0825 | val_acc: 0.3863 | test_acc: 0.3916 | Time: 6.0756 s
>>> Epoch [ 1705/10000]
train_loss: 2.0694 | train_acc: 0.4033 | val_loss: 2.0825 | val_acc: 0.3862 | test_acc: 0.3916 | Time: 5.7793 s
>>> Epoch [ 1706/10000]
train_loss: 2.0694 | train_acc: 0.4032 | val_loss: 2.0825 | val_acc: 0.3863 | test_acc: 0.3916 | Time: 5.8944 s
>>> Epoch [ 1707/10000]
train_loss: 2.0693 | train_acc: 0.4033 | val_loss: 2.0825 | val_acc: 0.3863 | test_acc: 0.3916 | Time: 6.3364 s
>>> Epoch [ 1708/10000]
train_loss: 2.0693 | train_acc: 0.4033 | val_loss: 2.0824 | val_acc: 0.3863 | test_acc: 0.3916 | Time: 5.9564 s
>>> Epoch [ 1709/10000]
train_loss: 2.0693 | train_acc: 0.4033 | val_loss: 2.0824 | val_acc: 0.3864 | test_acc: 0.3916 | Time: 3.7430 s
>>> Epoch [ 1710/10000]
train_loss: 2.0693 | train_acc: 0.4034 | val_loss: 2.0824 | val_acc: 0.3864 | test_acc: 0.3917 | Time: 3.8064 s
>>> Epoch [ 1711/10000]
train_loss: 2.0693 | train_acc: 0.4034 | val_loss: 2.0824 | val_acc: 0.3866 | test_acc: 0.3917 | Time: 3.8744 s
>>> Epoch [ 1712/10000]
train_loss: 2.0693 | train_acc: 0.4034 | val_loss: 2.0824 | val_acc: 0.3865 | test_acc: 0.3917 | Time: 3.9851 s
>>> Epoch [ 1713/10000]
train_loss: 2.0692 | train_acc: 0.4034 | val_loss: 2.0824 | val_acc: 0.3867 | test_acc: 0.3917 | Time: 3.9238 s
>>> Epoch [ 1714/10000]
train_loss: 2.0692 | train_acc: 0.4034 | val_loss: 2.0824 | val_acc: 0.3867 | test_acc: 0.3916 | Time: 4.0529 s
>>> Epoch [ 1715/10000]
train_loss: 2.0692 | train_acc: 0.4034 | val_loss: 2.0823 | val_acc: 0.3868 | test_acc: 0.3917 | Time: 3.9415 s
>>> Epoch [ 1716/10000]
train_loss: 2.0692 | train_acc: 0.4034 | val_loss: 2.0823 | val_acc: 0.3868 | test_acc: 0.3917 | Time: 4.2318 s
>>> Epoch [ 1717/10000]
train_loss: 2.0692 | train_acc: 0.4035 | val_loss: 2.0823 | val_acc: 0.3867 | test_acc: 0.3915 | Time: 4.0116 s
>>> Epoch [ 1718/10000]
train_loss: 2.0692 | train_acc: 0.4035 | val_loss: 2.0823 | val_acc: 0.3866 | test_acc: 0.3916 | Time: 3.9530 s
>>> Epoch [ 1719/10000]
train_loss: 2.0691 | train_acc: 0.4036 | val_loss: 2.0823 | val_acc: 0.3866 | test_acc: 0.3916 | Time: 4.2151 s
>>> Epoch [ 1720/10000]
train_loss: 2.0691 | train_acc: 0.4036 | val_loss: 2.0823 | val_acc: 0.3866 | test_acc: 0.3917 | Time: 4.2433 s
>>> Epoch [ 1721/10000]
train_loss: 2.0691 | train_acc: 0.4036 | val_loss: 2.0823 | val_acc: 0.3866 | test_acc: 0.3917 | Time: 4.2859 s
>>> Epoch [ 1722/10000]
train_loss: 2.0691 | train_acc: 0.4036 | val_loss: 2.0822 | val_acc: 0.3865 | test_acc: 0.3917 | Time: 4.0719 s
>>> Epoch [ 1723/10000]
train_loss: 2.0691 | train_acc: 0.4036 | val_loss: 2.0822 | val_acc: 0.3864 | test_acc: 0.3917 | Time: 4.2343 s
>>> Epoch [ 1724/10000]
train_loss: 2.0691 | train_acc: 0.4036 | val_loss: 2.0822 | val_acc: 0.3864 | test_acc: 0.3917 | Time: 4.1203 s
>>> Epoch [ 1725/10000]
train_loss: 2.0690 | train_acc: 0.4036 | val_loss: 2.0822 | val_acc: 0.3864 | test_acc: 0.3917 | Time: 4.1876 s
>>> Epoch [ 1726/10000]
train_loss: 2.0690 | train_acc: 0.4036 | val_loss: 2.0822 | val_acc: 0.3864 | test_acc: 0.3917 | Time: 4.2228 s
>>> Epoch [ 1727/10000]
train_loss: 2.0690 | train_acc: 0.4036 | val_loss: 2.0822 | val_acc: 0.3864 | test_acc: 0.3918 | Time: 4.2252 s
>>> Epoch [ 1728/10000]
train_loss: 2.0690 | train_acc: 0.4036 | val_loss: 2.0822 | val_acc: 0.3864 | test_acc: 0.3918 | Time: 4.2780 s
>>> Epoch [ 1729/10000]
train_loss: 2.0690 | train_acc: 0.4037 | val_loss: 2.0821 | val_acc: 0.3864 | test_acc: 0.3918 | Time: 4.5090 s
>>> Epoch [ 1730/10000]
train_loss: 2.0690 | train_acc: 0.4037 | val_loss: 2.0821 | val_acc: 0.3864 | test_acc: 0.3920 | Time: 4.2361 s
>>> Epoch [ 1731/10000]
train_loss: 2.0689 | train_acc: 0.4037 | val_loss: 2.0821 | val_acc: 0.3864 | test_acc: 0.3921 | Time: 4.4610 s
>>> Epoch [ 1732/10000]
train_loss: 2.0689 | train_acc: 0.4037 | val_loss: 2.0821 | val_acc: 0.3864 | test_acc: 0.3921 | Time: 4.2620 s
>>> Epoch [ 1733/10000]
train_loss: 2.0689 | train_acc: 0.4037 | val_loss: 2.0821 | val_acc: 0.3864 | test_acc: 0.3921 | Time: 4.1975 s
>>> Epoch [ 1734/10000]
train_loss: 2.0689 | train_acc: 0.4037 | val_loss: 2.0821 | val_acc: 0.3864 | test_acc: 0.3921 | Time: 4.4579 s
>>> Epoch [ 1735/10000]
train_loss: 2.0689 | train_acc: 0.4037 | val_loss: 2.0821 | val_acc: 0.3864 | test_acc: 0.3921 | Time: 4.3778 s
>>> Epoch [ 1736/10000]
train_loss: 2.0689 | train_acc: 0.4038 | val_loss: 2.0820 | val_acc: 0.3866 | test_acc: 0.3921 | Time: 4.3856 s
>>> Epoch [ 1737/10000]
train_loss: 2.0688 | train_acc: 0.4038 | val_loss: 2.0820 | val_acc: 0.3867 | test_acc: 0.3921 | Time: 4.2969 s
>>> Epoch [ 1738/10000]
train_loss: 2.0688 | train_acc: 0.4038 | val_loss: 2.0820 | val_acc: 0.3868 | test_acc: 0.3921 | Time: 4.3826 s
>>> Epoch [ 1739/10000]
train_loss: 2.0688 | train_acc: 0.4037 | val_loss: 2.0820 | val_acc: 0.3868 | test_acc: 0.3921 | Time: 4.3622 s
>>> Epoch [ 1740/10000]
train_loss: 2.0688 | train_acc: 0.4038 | val_loss: 2.0820 | val_acc: 0.3868 | test_acc: 0.3922 | Time: 4.2192 s
>>> Epoch [ 1741/10000]
train_loss: 2.0688 | train_acc: 0.4039 | val_loss: 2.0820 | val_acc: 0.3868 | test_acc: 0.3922 | Time: 4.2837 s
>>> Epoch [ 1742/10000]
train_loss: 2.0688 | train_acc: 0.4039 | val_loss: 2.0819 | val_acc: 0.3868 | test_acc: 0.3922 | Time: 4.3056 s
>>> Epoch [ 1743/10000]
train_loss: 2.0687 | train_acc: 0.4039 | val_loss: 2.0819 | val_acc: 0.3868 | test_acc: 0.3922 | Time: 4.3224 s
>>> Epoch [ 1744/10000]
train_loss: 2.0687 | train_acc: 0.4041 | val_loss: 2.0819 | val_acc: 0.3869 | test_acc: 0.3922 | Time: 4.1524 s
>>> Epoch [ 1745/10000]
train_loss: 2.0687 | train_acc: 0.4040 | val_loss: 2.0819 | val_acc: 0.3869 | test_acc: 0.3923 | Time: 4.2882 s
>>> Epoch [ 1746/10000]
train_loss: 2.0687 | train_acc: 0.4040 | val_loss: 2.0819 | val_acc: 0.3869 | test_acc: 0.3923 | Time: 4.4297 s
>>> Epoch [ 1747/10000]
train_loss: 2.0687 | train_acc: 0.4040 | val_loss: 2.0819 | val_acc: 0.3868 | test_acc: 0.3923 | Time: 4.5585 s
>>> Epoch [ 1748/10000]
train_loss: 2.0687 | train_acc: 0.4040 | val_loss: 2.0819 | val_acc: 0.3869 | test_acc: 0.3924 | Time: 4.5430 s
>>> Epoch [ 1749/10000]
train_loss: 2.0686 | train_acc: 0.4041 | val_loss: 2.0818 | val_acc: 0.3869 | test_acc: 0.3925 | Time: 4.7542 s
>>> Epoch [ 1750/10000]
train_loss: 2.0686 | train_acc: 0.4041 | val_loss: 2.0818 | val_acc: 0.3870 | test_acc: 0.3925 | Time: 4.5438 s
>>> Epoch [ 1751/10000]
train_loss: 2.0686 | train_acc: 0.4041 | val_loss: 2.0818 | val_acc: 0.3870 | test_acc: 0.3926 | Time: 4.4378 s
>>> Epoch [ 1752/10000]
train_loss: 2.0686 | train_acc: 0.4041 | val_loss: 2.0818 | val_acc: 0.3870 | test_acc: 0.3926 | Time: 4.3372 s
>>> Epoch [ 1753/10000]
train_loss: 2.0686 | train_acc: 0.4042 | val_loss: 2.0818 | val_acc: 0.3871 | test_acc: 0.3926 | Time: 4.3738 s
>>> Epoch [ 1754/10000]
train_loss: 2.0686 | train_acc: 0.4042 | val_loss: 2.0818 | val_acc: 0.3872 | test_acc: 0.3925 | Time: 4.5188 s
>>> Epoch [ 1755/10000]
train_loss: 2.0685 | train_acc: 0.4042 | val_loss: 2.0818 | val_acc: 0.3872 | test_acc: 0.3924 | Time: 3.8085 s
>>> Epoch [ 1756/10000]
train_loss: 2.0685 | train_acc: 0.4042 | val_loss: 2.0817 | val_acc: 0.3872 | test_acc: 0.3924 | Time: 6.5042 s
>>> Epoch [ 1757/10000]
train_loss: 2.0685 | train_acc: 0.4043 | val_loss: 2.0817 | val_acc: 0.3873 | test_acc: 0.3924 | Time: 6.1375 s
>>> Epoch [ 1758/10000]
train_loss: 2.0685 | train_acc: 0.4043 | val_loss: 2.0817 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 5.1050 s
>>> Epoch [ 1759/10000]
train_loss: 2.0685 | train_acc: 0.4043 | val_loss: 2.0817 | val_acc: 0.3875 | test_acc: 0.3925 | Time: 6.5415 s
>>> Epoch [ 1760/10000]
train_loss: 2.0685 | train_acc: 0.4043 | val_loss: 2.0817 | val_acc: 0.3874 | test_acc: 0.3925 | Time: 5.6952 s
>>> Epoch [ 1761/10000]
train_loss: 2.0684 | train_acc: 0.4043 | val_loss: 2.0817 | val_acc: 0.3874 | test_acc: 0.3925 | Time: 5.4422 s
>>> Epoch [ 1762/10000]
train_loss: 2.0684 | train_acc: 0.4044 | val_loss: 2.0817 | val_acc: 0.3874 | test_acc: 0.3924 | Time: 3.9496 s
>>> Epoch [ 1763/10000]
train_loss: 2.0684 | train_acc: 0.4045 | val_loss: 2.0816 | val_acc: 0.3876 | test_acc: 0.3926 | Time: 3.8761 s
>>> Epoch [ 1764/10000]
train_loss: 2.0684 | train_acc: 0.4045 | val_loss: 2.0816 | val_acc: 0.3875 | test_acc: 0.3925 | Time: 3.9690 s
>>> Epoch [ 1765/10000]
train_loss: 2.0684 | train_acc: 0.4045 | val_loss: 2.0816 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.2475 s
>>> Epoch [ 1766/10000]
train_loss: 2.0684 | train_acc: 0.4045 | val_loss: 2.0816 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.2779 s
>>> Epoch [ 1767/10000]
train_loss: 2.0683 | train_acc: 0.4045 | val_loss: 2.0816 | val_acc: 0.3874 | test_acc: 0.3924 | Time: 4.1246 s
>>> Epoch [ 1768/10000]
train_loss: 2.0683 | train_acc: 0.4045 | val_loss: 2.0816 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.0265 s
>>> Epoch [ 1769/10000]
train_loss: 2.0683 | train_acc: 0.4045 | val_loss: 2.0816 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.2391 s
>>> Epoch [ 1770/10000]
train_loss: 2.0683 | train_acc: 0.4045 | val_loss: 2.0815 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.2328 s
>>> Epoch [ 1771/10000]
train_loss: 2.0683 | train_acc: 0.4045 | val_loss: 2.0815 | val_acc: 0.3876 | test_acc: 0.3923 | Time: 4.4183 s
>>> Epoch [ 1772/10000]
train_loss: 2.0683 | train_acc: 0.4046 | val_loss: 2.0815 | val_acc: 0.3876 | test_acc: 0.3924 | Time: 4.4506 s
>>> Epoch [ 1773/10000]
train_loss: 2.0682 | train_acc: 0.4046 | val_loss: 2.0815 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.3577 s
>>> Epoch [ 1774/10000]
train_loss: 2.0682 | train_acc: 0.4046 | val_loss: 2.0815 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.4574 s
>>> Epoch [ 1775/10000]
train_loss: 2.0682 | train_acc: 0.4046 | val_loss: 2.0815 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.3325 s
>>> Epoch [ 1776/10000]
train_loss: 2.0682 | train_acc: 0.4047 | val_loss: 2.0815 | val_acc: 0.3876 | test_acc: 0.3924 | Time: 4.3727 s
>>> Epoch [ 1777/10000]
train_loss: 2.0682 | train_acc: 0.4048 | val_loss: 2.0814 | val_acc: 0.3876 | test_acc: 0.3924 | Time: 4.4722 s
>>> Epoch [ 1778/10000]
train_loss: 2.0682 | train_acc: 0.4048 | val_loss: 2.0814 | val_acc: 0.3876 | test_acc: 0.3923 | Time: 4.4427 s
>>> Epoch [ 1779/10000]
train_loss: 2.0681 | train_acc: 0.4049 | val_loss: 2.0814 | val_acc: 0.3876 | test_acc: 0.3923 | Time: 4.2587 s
>>> Epoch [ 1780/10000]
train_loss: 2.0681 | train_acc: 0.4049 | val_loss: 2.0814 | val_acc: 0.3876 | test_acc: 0.3923 | Time: 4.3065 s
>>> Epoch [ 1781/10000]
train_loss: 2.0681 | train_acc: 0.4049 | val_loss: 2.0814 | val_acc: 0.3876 | test_acc: 0.3922 | Time: 4.5041 s
>>> Epoch [ 1782/10000]
train_loss: 2.0681 | train_acc: 0.4049 | val_loss: 2.0814 | val_acc: 0.3876 | test_acc: 0.3923 | Time: 4.4612 s
>>> Epoch [ 1783/10000]
train_loss: 2.0681 | train_acc: 0.4049 | val_loss: 2.0814 | val_acc: 0.3876 | test_acc: 0.3924 | Time: 4.5179 s
>>> Epoch [ 1784/10000]
train_loss: 2.0681 | train_acc: 0.4049 | val_loss: 2.0813 | val_acc: 0.3875 | test_acc: 0.3924 | Time: 4.6550 s
>>> Epoch [ 1785/10000]
train_loss: 2.0680 | train_acc: 0.4049 | val_loss: 2.0813 | val_acc: 0.3875 | test_acc: 0.3925 | Time: 4.3826 s
>>> Epoch [ 1786/10000]
train_loss: 2.0680 | train_acc: 0.4049 | val_loss: 2.0813 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.4276 s
>>> Epoch [ 1787/10000]
train_loss: 2.0680 | train_acc: 0.4049 | val_loss: 2.0813 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.4325 s
>>> Epoch [ 1788/10000]
train_loss: 2.0680 | train_acc: 0.4050 | val_loss: 2.0813 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.5401 s
>>> Epoch [ 1789/10000]
train_loss: 2.0680 | train_acc: 0.4050 | val_loss: 2.0813 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.4825 s
>>> Epoch [ 1790/10000]
train_loss: 2.0680 | train_acc: 0.4050 | val_loss: 2.0813 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.3703 s
>>> Epoch [ 1791/10000]
train_loss: 2.0680 | train_acc: 0.4050 | val_loss: 2.0812 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.3536 s
>>> Epoch [ 1792/10000]
train_loss: 2.0679 | train_acc: 0.4051 | val_loss: 2.0812 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.2597 s
>>> Epoch [ 1793/10000]
train_loss: 2.0679 | train_acc: 0.4051 | val_loss: 2.0812 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.6145 s
>>> Epoch [ 1794/10000]
train_loss: 2.0679 | train_acc: 0.4051 | val_loss: 2.0812 | val_acc: 0.3877 | test_acc: 0.3925 | Time: 4.4362 s
>>> Epoch [ 1795/10000]
train_loss: 2.0679 | train_acc: 0.4051 | val_loss: 2.0812 | val_acc: 0.3878 | test_acc: 0.3925 | Time: 4.4320 s
>>> Epoch [ 1796/10000]
train_loss: 2.0679 | train_acc: 0.4051 | val_loss: 2.0812 | val_acc: 0.3878 | test_acc: 0.3924 | Time: 4.3497 s
>>> Epoch [ 1797/10000]
train_loss: 2.0679 | train_acc: 0.4051 | val_loss: 2.0812 | val_acc: 0.3877 | test_acc: 0.3924 | Time: 4.2385 s
>>> Epoch [ 1798/10000]
train_loss: 2.0678 | train_acc: 0.4051 | val_loss: 2.0811 | val_acc: 0.3877 | test_acc: 0.3924 | Time: 4.3136 s
>>> Epoch [ 1799/10000]
train_loss: 2.0678 | train_acc: 0.4051 | val_loss: 2.0811 | val_acc: 0.3877 | test_acc: 0.3925 | Time: 4.5293 s
>>> Epoch [ 1800/10000]
train_loss: 2.0678 | train_acc: 0.4051 | val_loss: 2.0811 | val_acc: 0.3876 | test_acc: 0.3925 | Time: 4.5044 s
>>> Epoch [ 1801/10000]
train_loss: 2.0678 | train_acc: 0.4051 | val_loss: 2.0811 | val_acc: 0.3875 | test_acc: 0.3925 | Time: 4.5281 s
>>> Epoch [ 1802/10000]
train_loss: 2.0678 | train_acc: 0.4051 | val_loss: 2.0811 | val_acc: 0.3875 | test_acc: 0.3925 | Time: 4.4365 s
>>> Epoch [ 1803/10000]
train_loss: 2.0678 | train_acc: 0.4052 | val_loss: 2.0811 | val_acc: 0.3875 | test_acc: 0.3925 | Time: 4.5203 s
>>> Epoch [ 1804/10000]
train_loss: 2.0677 | train_acc: 0.4052 | val_loss: 2.0811 | val_acc: 0.3874 | test_acc: 0.3925 | Time: 4.3676 s
>>> Epoch [ 1805/10000]
train_loss: 2.0677 | train_acc: 0.4053 | val_loss: 2.0811 | val_acc: 0.3873 | test_acc: 0.3925 | Time: 4.5153 s
>>> Epoch [ 1806/10000]
train_loss: 2.0677 | train_acc: 0.4053 | val_loss: 2.0810 | val_acc: 0.3873 | test_acc: 0.3925 | Time: 3.7894 s
>>> Epoch [ 1807/10000]
train_loss: 2.0677 | train_acc: 0.4053 | val_loss: 2.0810 | val_acc: 0.3873 | test_acc: 0.3925 | Time: 6.8060 s
>>> Epoch [ 1808/10000]
train_loss: 2.0677 | train_acc: 0.4053 | val_loss: 2.0810 | val_acc: 0.3873 | test_acc: 0.3926 | Time: 6.4716 s
>>> Epoch [ 1809/10000]
train_loss: 2.0677 | train_acc: 0.4053 | val_loss: 2.0810 | val_acc: 0.3875 | test_acc: 0.3929 | Time: 6.0264 s
>>> Epoch [ 1810/10000]
train_loss: 2.0676 | train_acc: 0.4053 | val_loss: 2.0810 | val_acc: 0.3875 | test_acc: 0.3929 | Time: 6.5011 s
>>> Epoch [ 1811/10000]
train_loss: 2.0676 | train_acc: 0.4053 | val_loss: 2.0810 | val_acc: 0.3876 | test_acc: 0.3930 | Time: 6.3703 s
>>> Epoch [ 1812/10000]
train_loss: 2.0676 | train_acc: 0.4053 | val_loss: 2.0810 | val_acc: 0.3876 | test_acc: 0.3930 | Time: 5.3922 s
>>> Epoch [ 1813/10000]
train_loss: 2.0676 | train_acc: 0.4054 | val_loss: 2.0809 | val_acc: 0.3875 | test_acc: 0.3930 | Time: 3.8131 s
>>> Epoch [ 1814/10000]
train_loss: 2.0676 | train_acc: 0.4054 | val_loss: 2.0809 | val_acc: 0.3875 | test_acc: 0.3929 | Time: 3.9780 s
>>> Epoch [ 1815/10000]
train_loss: 2.0676 | train_acc: 0.4053 | val_loss: 2.0809 | val_acc: 0.3875 | test_acc: 0.3930 | Time: 4.0123 s
>>> Epoch [ 1816/10000]
train_loss: 2.0675 | train_acc: 0.4054 | val_loss: 2.0809 | val_acc: 0.3875 | test_acc: 0.3932 | Time: 4.2772 s
>>> Epoch [ 1817/10000]
train_loss: 2.0675 | train_acc: 0.4054 | val_loss: 2.0809 | val_acc: 0.3877 | test_acc: 0.3932 | Time: 4.1565 s
>>> Epoch [ 1818/10000]
train_loss: 2.0675 | train_acc: 0.4055 | val_loss: 2.0809 | val_acc: 0.3877 | test_acc: 0.3932 | Time: 4.1977 s
>>> Epoch [ 1819/10000]
train_loss: 2.0675 | train_acc: 0.4056 | val_loss: 2.0809 | val_acc: 0.3877 | test_acc: 0.3932 | Time: 4.5464 s
>>> Epoch [ 1820/10000]
train_loss: 2.0675 | train_acc: 0.4056 | val_loss: 2.0808 | val_acc: 0.3877 | test_acc: 0.3933 | Time: 4.4745 s
>>> Epoch [ 1821/10000]
train_loss: 2.0675 | train_acc: 0.4057 | val_loss: 2.0808 | val_acc: 0.3876 | test_acc: 0.3933 | Time: 4.3961 s
>>> Epoch [ 1822/10000]
train_loss: 2.0675 | train_acc: 0.4057 | val_loss: 2.0808 | val_acc: 0.3877 | test_acc: 0.3933 | Time: 4.5078 s
>>> Epoch [ 1823/10000]
train_loss: 2.0674 | train_acc: 0.4058 | val_loss: 2.0808 | val_acc: 0.3877 | test_acc: 0.3933 | Time: 4.3295 s
>>> Epoch [ 1824/10000]
train_loss: 2.0674 | train_acc: 0.4058 | val_loss: 2.0808 | val_acc: 0.3878 | test_acc: 0.3934 | Time: 4.5152 s
>>> Epoch [ 1825/10000]
train_loss: 2.0674 | train_acc: 0.4058 | val_loss: 2.0808 | val_acc: 0.3878 | test_acc: 0.3934 | Time: 4.5049 s
>>> Epoch [ 1826/10000]
train_loss: 2.0674 | train_acc: 0.4058 | val_loss: 2.0808 | val_acc: 0.3878 | test_acc: 0.3934 | Time: 4.5612 s
>>> Epoch [ 1827/10000]
train_loss: 2.0674 | train_acc: 0.4059 | val_loss: 2.0807 | val_acc: 0.3879 | test_acc: 0.3933 | Time: 4.4966 s
>>> Epoch [ 1828/10000]
train_loss: 2.0674 | train_acc: 0.4059 | val_loss: 2.0807 | val_acc: 0.3879 | test_acc: 0.3933 | Time: 4.4969 s
>>> Epoch [ 1829/10000]
train_loss: 2.0673 | train_acc: 0.4059 | val_loss: 2.0807 | val_acc: 0.3879 | test_acc: 0.3933 | Time: 4.4507 s
>>> Epoch [ 1830/10000]
train_loss: 2.0673 | train_acc: 0.4059 | val_loss: 2.0807 | val_acc: 0.3879 | test_acc: 0.3932 | Time: 4.5913 s
>>> Epoch [ 1831/10000]
train_loss: 2.0673 | train_acc: 0.4059 | val_loss: 2.0807 | val_acc: 0.3880 | test_acc: 0.3932 | Time: 4.3457 s
>>> Epoch [ 1832/10000]
train_loss: 2.0673 | train_acc: 0.4059 | val_loss: 2.0807 | val_acc: 0.3880 | test_acc: 0.3932 | Time: 4.5033 s
>>> Epoch [ 1833/10000]
train_loss: 2.0673 | train_acc: 0.4060 | val_loss: 2.0807 | val_acc: 0.3880 | test_acc: 0.3933 | Time: 4.6722 s
>>> Epoch [ 1834/10000]
train_loss: 2.0673 | train_acc: 0.4060 | val_loss: 2.0807 | val_acc: 0.3879 | test_acc: 0.3933 | Time: 4.3312 s
>>> Epoch [ 1835/10000]
train_loss: 2.0672 | train_acc: 0.4061 | val_loss: 2.0806 | val_acc: 0.3878 | test_acc: 0.3933 | Time: 4.5062 s
>>> Epoch [ 1836/10000]
train_loss: 2.0672 | train_acc: 0.4061 | val_loss: 2.0806 | val_acc: 0.3879 | test_acc: 0.3933 | Time: 4.7618 s
>>> Epoch [ 1837/10000]
train_loss: 2.0672 | train_acc: 0.4060 | val_loss: 2.0806 | val_acc: 0.3879 | test_acc: 0.3933 | Time: 4.3231 s
>>> Epoch [ 1838/10000]
train_loss: 2.0672 | train_acc: 0.4061 | val_loss: 2.0806 | val_acc: 0.3880 | test_acc: 0.3933 | Time: 4.3294 s
>>> Epoch [ 1839/10000]
train_loss: 2.0672 | train_acc: 0.4061 | val_loss: 2.0806 | val_acc: 0.3880 | test_acc: 0.3932 | Time: 4.3587 s
>>> Epoch [ 1840/10000]
train_loss: 2.0672 | train_acc: 0.4061 | val_loss: 2.0806 | val_acc: 0.3880 | test_acc: 0.3932 | Time: 4.6527 s
>>> Epoch [ 1841/10000]
train_loss: 2.0672 | train_acc: 0.4061 | val_loss: 2.0806 | val_acc: 0.3880 | test_acc: 0.3931 | Time: 4.5142 s
>>> Epoch [ 1842/10000]
train_loss: 2.0671 | train_acc: 0.4061 | val_loss: 2.0805 | val_acc: 0.3880 | test_acc: 0.3931 | Time: 4.7769 s
>>> Epoch [ 1843/10000]
train_loss: 2.0671 | train_acc: 0.4061 | val_loss: 2.0805 | val_acc: 0.3880 | test_acc: 0.3931 | Time: 4.5905 s
>>> Epoch [ 1844/10000]
train_loss: 2.0671 | train_acc: 0.4060 | val_loss: 2.0805 | val_acc: 0.3880 | test_acc: 0.3931 | Time: 4.5098 s
>>> Epoch [ 1845/10000]
train_loss: 2.0671 | train_acc: 0.4060 | val_loss: 2.0805 | val_acc: 0.3881 | test_acc: 0.3932 | Time: 4.6935 s
>>> Epoch [ 1846/10000]
train_loss: 2.0671 | train_acc: 0.4060 | val_loss: 2.0805 | val_acc: 0.3881 | test_acc: 0.3933 | Time: 4.5205 s
>>> Epoch [ 1847/10000]
train_loss: 2.0671 | train_acc: 0.4060 | val_loss: 2.0805 | val_acc: 0.3881 | test_acc: 0.3934 | Time: 4.4211 s
>>> Epoch [ 1848/10000]
train_loss: 2.0670 | train_acc: 0.4060 | val_loss: 2.0805 | val_acc: 0.3881 | test_acc: 0.3934 | Time: 4.6677 s
>>> Epoch [ 1849/10000]
train_loss: 2.0670 | train_acc: 0.4059 | val_loss: 2.0804 | val_acc: 0.3882 | test_acc: 0.3935 | Time: 4.4160 s
>>> Epoch [ 1850/10000]
train_loss: 2.0670 | train_acc: 0.4060 | val_loss: 2.0804 | val_acc: 0.3882 | test_acc: 0.3935 | Time: 4.8572 s
>>> Epoch [ 1851/10000]
train_loss: 2.0670 | train_acc: 0.4059 | val_loss: 2.0804 | val_acc: 0.3882 | test_acc: 0.3935 | Time: 4.5476 s
>>> Epoch [ 1852/10000]
train_loss: 2.0670 | train_acc: 0.4059 | val_loss: 2.0804 | val_acc: 0.3882 | test_acc: 0.3935 | Time: 4.5116 s
>>> Epoch [ 1853/10000]
train_loss: 2.0670 | train_acc: 0.4059 | val_loss: 2.0804 | val_acc: 0.3883 | test_acc: 0.3934 | Time: 4.4974 s
>>> Epoch [ 1854/10000]
train_loss: 2.0669 | train_acc: 0.4059 | val_loss: 2.0804 | val_acc: 0.3884 | test_acc: 0.3934 | Time: 3.7526 s
>>> Epoch [ 1855/10000]
train_loss: 2.0669 | train_acc: 0.4059 | val_loss: 2.0804 | val_acc: 0.3883 | test_acc: 0.3934 | Time: 6.9176 s
>>> Epoch [ 1856/10000]
train_loss: 2.0669 | train_acc: 0.4059 | val_loss: 2.0804 | val_acc: 0.3883 | test_acc: 0.3932 | Time: 6.2784 s
>>> Epoch [ 1857/10000]
train_loss: 2.0669 | train_acc: 0.4059 | val_loss: 2.0803 | val_acc: 0.3882 | test_acc: 0.3932 | Time: 5.9119 s
>>> Epoch [ 1858/10000]
train_loss: 2.0669 | train_acc: 0.4059 | val_loss: 2.0803 | val_acc: 0.3883 | test_acc: 0.3932 | Time: 7.1269 s
>>> Epoch [ 1859/10000]
train_loss: 2.0669 | train_acc: 0.4059 | val_loss: 2.0803 | val_acc: 0.3883 | test_acc: 0.3932 | Time: 6.5218 s
>>> Epoch [ 1860/10000]
train_loss: 2.0669 | train_acc: 0.4059 | val_loss: 2.0803 | val_acc: 0.3883 | test_acc: 0.3932 | Time: 4.3296 s
>>> Epoch [ 1861/10000]
train_loss: 2.0668 | train_acc: 0.4059 | val_loss: 2.0803 | val_acc: 0.3883 | test_acc: 0.3932 | Time: 3.9160 s
>>> Epoch [ 1862/10000]
train_loss: 2.0668 | train_acc: 0.4059 | val_loss: 2.0803 | val_acc: 0.3883 | test_acc: 0.3931 | Time: 4.3459 s
>>> Epoch [ 1863/10000]
train_loss: 2.0668 | train_acc: 0.4060 | val_loss: 2.0803 | val_acc: 0.3883 | test_acc: 0.3931 | Time: 4.2790 s
>>> Epoch [ 1864/10000]
train_loss: 2.0668 | train_acc: 0.4060 | val_loss: 2.0802 | val_acc: 0.3883 | test_acc: 0.3931 | Time: 4.3180 s
>>> Epoch [ 1865/10000]
train_loss: 2.0668 | train_acc: 0.4060 | val_loss: 2.0802 | val_acc: 0.3883 | test_acc: 0.3931 | Time: 4.6099 s
>>> Epoch [ 1866/10000]
train_loss: 2.0668 | train_acc: 0.4060 | val_loss: 2.0802 | val_acc: 0.3883 | test_acc: 0.3932 | Time: 4.4966 s
>>> Epoch [ 1867/10000]
train_loss: 2.0667 | train_acc: 0.4060 | val_loss: 2.0802 | val_acc: 0.3884 | test_acc: 0.3932 | Time: 4.6919 s
>>> Epoch [ 1868/10000]
train_loss: 2.0667 | train_acc: 0.4060 | val_loss: 2.0802 | val_acc: 0.3884 | test_acc: 0.3932 | Time: 4.5287 s
>>> Epoch [ 1869/10000]
train_loss: 2.0667 | train_acc: 0.4060 | val_loss: 2.0802 | val_acc: 0.3885 | test_acc: 0.3932 | Time: 4.6757 s
>>> Epoch [ 1870/10000]
train_loss: 2.0667 | train_acc: 0.4060 | val_loss: 2.0802 | val_acc: 0.3885 | test_acc: 0.3931 | Time: 4.3028 s
>>> Epoch [ 1871/10000]
train_loss: 2.0667 | train_acc: 0.4060 | val_loss: 2.0802 | val_acc: 0.3885 | test_acc: 0.3931 | Time: 4.5450 s
>>> Epoch [ 1872/10000]
train_loss: 2.0667 | train_acc: 0.4059 | val_loss: 2.0801 | val_acc: 0.3885 | test_acc: 0.3931 | Time: 4.5890 s
>>> Epoch [ 1873/10000]
train_loss: 2.0667 | train_acc: 0.4059 | val_loss: 2.0801 | val_acc: 0.3885 | test_acc: 0.3930 | Time: 4.6595 s
>>> Epoch [ 1874/10000]
train_loss: 2.0666 | train_acc: 0.4060 | val_loss: 2.0801 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.6107 s
>>> Epoch [ 1875/10000]
train_loss: 2.0666 | train_acc: 0.4060 | val_loss: 2.0801 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.3760 s
>>> Epoch [ 1876/10000]
train_loss: 2.0666 | train_acc: 0.4060 | val_loss: 2.0801 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.5077 s
>>> Epoch [ 1877/10000]
train_loss: 2.0666 | train_acc: 0.4061 | val_loss: 2.0801 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.4203 s
>>> Epoch [ 1878/10000]
train_loss: 2.0666 | train_acc: 0.4061 | val_loss: 2.0801 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.4214 s
>>> Epoch [ 1879/10000]
train_loss: 2.0666 | train_acc: 0.4061 | val_loss: 2.0800 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.4773 s
>>> Epoch [ 1880/10000]
train_loss: 2.0665 | train_acc: 0.4061 | val_loss: 2.0800 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.5046 s
>>> Epoch [ 1881/10000]
train_loss: 2.0665 | train_acc: 0.4061 | val_loss: 2.0800 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.6288 s
>>> Epoch [ 1882/10000]
train_loss: 2.0665 | train_acc: 0.4062 | val_loss: 2.0800 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.4912 s
>>> Epoch [ 1883/10000]
train_loss: 2.0665 | train_acc: 0.4061 | val_loss: 2.0800 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.5784 s
>>> Epoch [ 1884/10000]
train_loss: 2.0665 | train_acc: 0.4061 | val_loss: 2.0800 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.6420 s
>>> Epoch [ 1885/10000]
train_loss: 2.0665 | train_acc: 0.4061 | val_loss: 2.0800 | val_acc: 0.3884 | test_acc: 0.3929 | Time: 4.7265 s
>>> Epoch [ 1886/10000]
train_loss: 2.0665 | train_acc: 0.4061 | val_loss: 2.0800 | val_acc: 0.3885 | test_acc: 0.3930 | Time: 4.4678 s
>>> Epoch [ 1887/10000]
train_loss: 2.0664 | train_acc: 0.4061 | val_loss: 2.0799 | val_acc: 0.3886 | test_acc: 0.3930 | Time: 4.4808 s
>>> Epoch [ 1888/10000]
train_loss: 2.0664 | train_acc: 0.4062 | val_loss: 2.0799 | val_acc: 0.3886 | test_acc: 0.3930 | Time: 4.5172 s
>>> Epoch [ 1889/10000]
train_loss: 2.0664 | train_acc: 0.4062 | val_loss: 2.0799 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.6358 s
>>> Epoch [ 1890/10000]
train_loss: 2.0664 | train_acc: 0.4062 | val_loss: 2.0799 | val_acc: 0.3885 | test_acc: 0.3931 | Time: 4.6554 s
>>> Epoch [ 1891/10000]
train_loss: 2.0664 | train_acc: 0.4062 | val_loss: 2.0799 | val_acc: 0.3885 | test_acc: 0.3931 | Time: 4.5071 s
>>> Epoch [ 1892/10000]
train_loss: 2.0664 | train_acc: 0.4062 | val_loss: 2.0799 | val_acc: 0.3885 | test_acc: 0.3930 | Time: 4.5959 s
>>> Epoch [ 1893/10000]
train_loss: 2.0663 | train_acc: 0.4062 | val_loss: 2.0799 | val_acc: 0.3885 | test_acc: 0.3930 | Time: 4.5933 s
>>> Epoch [ 1894/10000]
train_loss: 2.0663 | train_acc: 0.4063 | val_loss: 2.0799 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.5079 s
>>> Epoch [ 1895/10000]
train_loss: 2.0663 | train_acc: 0.4062 | val_loss: 2.0798 | val_acc: 0.3884 | test_acc: 0.3929 | Time: 4.5573 s
>>> Epoch [ 1896/10000]
train_loss: 2.0663 | train_acc: 0.4063 | val_loss: 2.0798 | val_acc: 0.3884 | test_acc: 0.3929 | Time: 4.5417 s
>>> Epoch [ 1897/10000]
train_loss: 2.0663 | train_acc: 0.4063 | val_loss: 2.0798 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.5845 s
>>> Epoch [ 1898/10000]
train_loss: 2.0663 | train_acc: 0.4063 | val_loss: 2.0798 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.7521 s
>>> Epoch [ 1899/10000]
train_loss: 2.0663 | train_acc: 0.4063 | val_loss: 2.0798 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.4584 s
>>> Epoch [ 1900/10000]
train_loss: 2.0662 | train_acc: 0.4063 | val_loss: 2.0798 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 3.8480 s
>>> Epoch [ 1901/10000]
train_loss: 2.0662 | train_acc: 0.4063 | val_loss: 2.0798 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.1223 s
>>> Epoch [ 1902/10000]
train_loss: 2.0662 | train_acc: 0.4063 | val_loss: 2.0797 | val_acc: 0.3884 | test_acc: 0.3930 | Time: 4.1204 s
>>> Epoch [ 1903/10000]
train_loss: 2.0662 | train_acc: 0.4063 | val_loss: 2.0797 | val_acc: 0.3884 | test_acc: 0.3929 | Time: 4.3934 s
>>> Epoch [ 1904/10000]
train_loss: 2.0662 | train_acc: 0.4063 | val_loss: 2.0797 | val_acc: 0.3884 | test_acc: 0.3929 | Time: 4.6714 s
>>> Epoch [ 1905/10000]
train_loss: 2.0662 | train_acc: 0.4064 | val_loss: 2.0797 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.1647 s
>>> Epoch [ 1906/10000]
train_loss: 2.0661 | train_acc: 0.4064 | val_loss: 2.0797 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 6.8877 s
>>> Epoch [ 1907/10000]
train_loss: 2.0661 | train_acc: 0.4064 | val_loss: 2.0797 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.8476 s
>>> Epoch [ 1908/10000]
train_loss: 2.0661 | train_acc: 0.4064 | val_loss: 2.0797 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 6.8635 s
>>> Epoch [ 1909/10000]
train_loss: 2.0661 | train_acc: 0.4064 | val_loss: 2.0797 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 5.9790 s
>>> Epoch [ 1910/10000]
train_loss: 2.0661 | train_acc: 0.4065 | val_loss: 2.0796 | val_acc: 0.3885 | test_acc: 0.3929 | Time: 4.1390 s
>>> Epoch [ 1911/10000]
train_loss: 2.0661 | train_acc: 0.4065 | val_loss: 2.0796 | val_acc: 0.3885 | test_acc: 0.3928 | Time: 4.1895 s
>>> Epoch [ 1912/10000]
train_loss: 2.0661 | train_acc: 0.4065 | val_loss: 2.0796 | val_acc: 0.3885 | test_acc: 0.3928 | Time: 4.9363 s
>>> Epoch [ 1913/10000]
train_loss: 2.0660 | train_acc: 0.4066 | val_loss: 2.0796 | val_acc: 0.3886 | test_acc: 0.3927 | Time: 4.6791 s
>>> Epoch [ 1914/10000]
train_loss: 2.0660 | train_acc: 0.4066 | val_loss: 2.0796 | val_acc: 0.3886 | test_acc: 0.3926 | Time: 5.0649 s
>>> Epoch [ 1915/10000]
train_loss: 2.0660 | train_acc: 0.4067 | val_loss: 2.0796 | val_acc: 0.3886 | test_acc: 0.3926 | Time: 4.1645 s
>>> Epoch [ 1916/10000]
train_loss: 2.0660 | train_acc: 0.4067 | val_loss: 2.0796 | val_acc: 0.3887 | test_acc: 0.3925 | Time: 4.8693 s
>>> Epoch [ 1917/10000]
train_loss: 2.0660 | train_acc: 0.4067 | val_loss: 2.0796 | val_acc: 0.3887 | test_acc: 0.3925 | Time: 4.7221 s
>>> Epoch [ 1918/10000]
train_loss: 2.0660 | train_acc: 0.4067 | val_loss: 2.0795 | val_acc: 0.3887 | test_acc: 0.3925 | Time: 4.6670 s
>>> Epoch [ 1919/10000]
train_loss: 2.0660 | train_acc: 0.4067 | val_loss: 2.0795 | val_acc: 0.3887 | test_acc: 0.3926 | Time: 5.0081 s
>>> Epoch [ 1920/10000]
train_loss: 2.0659 | train_acc: 0.4067 | val_loss: 2.0795 | val_acc: 0.3887 | test_acc: 0.3926 | Time: 4.9414 s
>>> Epoch [ 1921/10000]
train_loss: 2.0659 | train_acc: 0.4067 | val_loss: 2.0795 | val_acc: 0.3887 | test_acc: 0.3927 | Time: 4.5489 s
>>> Epoch [ 1922/10000]
train_loss: 2.0659 | train_acc: 0.4067 | val_loss: 2.0795 | val_acc: 0.3888 | test_acc: 0.3926 | Time: 4.9136 s
>>> Epoch [ 1923/10000]
train_loss: 2.0659 | train_acc: 0.4067 | val_loss: 2.0795 | val_acc: 0.3887 | test_acc: 0.3926 | Time: 4.7360 s
>>> Epoch [ 1924/10000]
train_loss: 2.0659 | train_acc: 0.4068 | val_loss: 2.0795 | val_acc: 0.3887 | test_acc: 0.3926 | Time: 4.6082 s
>>> Epoch [ 1925/10000]
train_loss: 2.0659 | train_acc: 0.4068 | val_loss: 2.0794 | val_acc: 0.3887 | test_acc: 0.3926 | Time: 4.6731 s
>>> Epoch [ 1926/10000]
train_loss: 2.0658 | train_acc: 0.4068 | val_loss: 2.0794 | val_acc: 0.3888 | test_acc: 0.3927 | Time: 4.6542 s
>>> Epoch [ 1927/10000]
train_loss: 2.0658 | train_acc: 0.4069 | val_loss: 2.0794 | val_acc: 0.3889 | test_acc: 0.3928 | Time: 4.8659 s
>>> Epoch [ 1928/10000]
train_loss: 2.0658 | train_acc: 0.4069 | val_loss: 2.0794 | val_acc: 0.3889 | test_acc: 0.3928 | Time: 4.6283 s
>>> Epoch [ 1929/10000]
train_loss: 2.0658 | train_acc: 0.4070 | val_loss: 2.0794 | val_acc: 0.3888 | test_acc: 0.3929 | Time: 4.5949 s
>>> Epoch [ 1930/10000]
train_loss: 2.0658 | train_acc: 0.4070 | val_loss: 2.0794 | val_acc: 0.3889 | test_acc: 0.3928 | Time: 4.7610 s
>>> Epoch [ 1931/10000]
train_loss: 2.0658 | train_acc: 0.4070 | val_loss: 2.0794 | val_acc: 0.3889 | test_acc: 0.3928 | Time: 4.7475 s
>>> Epoch [ 1932/10000]
train_loss: 2.0658 | train_acc: 0.4070 | val_loss: 2.0794 | val_acc: 0.3889 | test_acc: 0.3928 | Time: 4.7242 s
>>> Epoch [ 1933/10000]
train_loss: 2.0657 | train_acc: 0.4070 | val_loss: 2.0793 | val_acc: 0.3889 | test_acc: 0.3929 | Time: 4.7940 s
>>> Epoch [ 1934/10000]
train_loss: 2.0657 | train_acc: 0.4070 | val_loss: 2.0793 | val_acc: 0.3889 | test_acc: 0.3928 | Time: 4.7266 s
>>> Epoch [ 1935/10000]
train_loss: 2.0657 | train_acc: 0.4070 | val_loss: 2.0793 | val_acc: 0.3889 | test_acc: 0.3928 | Time: 4.6336 s
>>> Epoch [ 1936/10000]
train_loss: 2.0657 | train_acc: 0.4071 | val_loss: 2.0793 | val_acc: 0.3891 | test_acc: 0.3928 | Time: 4.7083 s
>>> Epoch [ 1937/10000]
train_loss: 2.0657 | train_acc: 0.4071 | val_loss: 2.0793 | val_acc: 0.3891 | test_acc: 0.3928 | Time: 4.6730 s
>>> Epoch [ 1938/10000]
train_loss: 2.0657 | train_acc: 0.4071 | val_loss: 2.0793 | val_acc: 0.3891 | test_acc: 0.3927 | Time: 4.6540 s
>>> Epoch [ 1939/10000]
train_loss: 2.0657 | train_acc: 0.4071 | val_loss: 2.0793 | val_acc: 0.3892 | test_acc: 0.3927 | Time: 4.6130 s
>>> Epoch [ 1940/10000]
train_loss: 2.0656 | train_acc: 0.4071 | val_loss: 2.0793 | val_acc: 0.3891 | test_acc: 0.3927 | Time: 4.6059 s
>>> Epoch [ 1941/10000]
train_loss: 2.0656 | train_acc: 0.4071 | val_loss: 2.0792 | val_acc: 0.3891 | test_acc: 0.3927 | Time: 4.7140 s
>>> Epoch [ 1942/10000]
train_loss: 2.0656 | train_acc: 0.4071 | val_loss: 2.0792 | val_acc: 0.3892 | test_acc: 0.3927 | Time: 4.6077 s
>>> Epoch [ 1943/10000]
train_loss: 2.0656 | train_acc: 0.4071 | val_loss: 2.0792 | val_acc: 0.3891 | test_acc: 0.3927 | Time: 4.5377 s
>>> Epoch [ 1944/10000]
train_loss: 2.0656 | train_acc: 0.4071 | val_loss: 2.0792 | val_acc: 0.3891 | test_acc: 0.3927 | Time: 4.6138 s
>>> Epoch [ 1945/10000]
train_loss: 2.0656 | train_acc: 0.4071 | val_loss: 2.0792 | val_acc: 0.3891 | test_acc: 0.3927 | Time: 4.8319 s
>>> Epoch [ 1946/10000]
train_loss: 2.0655 | train_acc: 0.4072 | val_loss: 2.0792 | val_acc: 0.3892 | test_acc: 0.3927 | Time: 4.6046 s
>>> Epoch [ 1947/10000]
train_loss: 2.0655 | train_acc: 0.4072 | val_loss: 2.0792 | val_acc: 0.3893 | test_acc: 0.3927 | Time: 4.5656 s
>>> Epoch [ 1948/10000]
train_loss: 2.0655 | train_acc: 0.4072 | val_loss: 2.0792 | val_acc: 0.3893 | test_acc: 0.3927 | Time: 4.5010 s
>>> Epoch [ 1949/10000]
train_loss: 2.0655 | train_acc: 0.4072 | val_loss: 2.0791 | val_acc: 0.3894 | test_acc: 0.3928 | Time: 4.5761 s
>>> Epoch [ 1950/10000]
train_loss: 2.0655 | train_acc: 0.4072 | val_loss: 2.0791 | val_acc: 0.3894 | test_acc: 0.3927 | Time: 6.7833 s
>>> Epoch [ 1951/10000]
train_loss: 2.0655 | train_acc: 0.4072 | val_loss: 2.0791 | val_acc: 0.3894 | test_acc: 0.3927 | Time: 7.2455 s
>>> Epoch [ 1952/10000]
train_loss: 2.0655 | train_acc: 0.4073 | val_loss: 2.0791 | val_acc: 0.3894 | test_acc: 0.3926 | Time: 6.2255 s
>>> Epoch [ 2060/10000]
train_loss: 2.0639 | train_acc: 0.4089 | val_loss: 2.0778 | val_acc: 0.3895 | test_acc: 0.3928 | Time: 5.2848 s
>>> Epoch [ 2061/10000]
train_loss: 2.0639 | train_acc: 0.4089 | val_loss: 2.0778 | val_acc: 0.3895 | test_acc: 0.3929 | Time: 4.8528 s
>>> Epoch [ 2062/10000]
train_loss: 2.0639 | train_acc: 0.4089 | val_loss: 2.0778 | val_acc: 0.3895 | test_acc: 0.3931 | Time: 4.9499 s
>>> Epoch [ 2063/10000]
train_loss: 2.0639 | train_acc: 0.4089 | val_loss: 2.0778 | val_acc: 0.3896 | test_acc: 0.3931 | Time: 5.1445 s
>>> Epoch [ 2064/10000]
train_loss: 2.0639 | train_acc: 0.4089 | val_loss: 2.0778 | val_acc: 0.3896 | test_acc: 0.3931 | Time: 5.0984 s
>>> Epoch [ 2065/10000]
train_loss: 2.0638 | train_acc: 0.4089 | val_loss: 2.0777 | val_acc: 0.3898 | test_acc: 0.3931 | Time: 5.1548 s
>>> Epoch [ 2081/10000]
train_loss: 2.0636 | train_acc: 0.4089 | val_loss: 2.0776 | val_acc: 0.3900 | test_acc: 0.3932 | Time: 5.0653 s
>>> Epoch [ 2082/10000]
train_loss: 2.0636 | train_acc: 0.4089 | val_loss: 2.0775 | val_acc: 0.3900 | test_acc: 0.3932 | Time: 4.7573 s
>>> Epoch [ 2083/10000]
train_loss: 2.0636 | train_acc: 0.4090 | val_loss: 2.0775 | val_acc: 0.3900 | test_acc: 0.3932 | Time: 5.0394 s
>>> Epoch [ 2084/10000]
train_loss: 2.0636 | train_acc: 0.4090 | val_loss: 2.0775 | val_acc: 0.3900 | test_acc: 0.3932 | Time: 4.9709 s
>>> Epoch [ 2085/10000]
train_loss: 2.0636 | train_acc: 0.4090 | val_loss: 2.0775 | val_acc: 0.3902 | test_acc: 0.3932 | Time: 5.0903 s
>>> Epoch [ 2086/10000]
train_loss: 2.0635 | train_acc: 0.4090 | val_loss: 2.0775 | val_acc: 0.3903 | test_acc: 0.3933 | Time: 5.0809 s
>>> Epoch [ 2087/10000]
train_loss: 2.0635 | train_acc: 0.4090 | val_loss: 2.0775 | val_acc: 0.3902 | test_acc: 0.3933 | Time: 5.0216 s
>>> Epoch [ 2088/10000]
train_loss: 2.0635 | train_acc: 0.4090 | val_loss: 2.0775 | val_acc: 0.3900 | test_acc: 0.3933 | Time: 4.9477 s
>>> Epoch [ 2089/10000]
train_loss: 2.0635 | train_acc: 0.4090 | val_loss: 2.0775 | val_acc: 0.3900 | test_acc: 0.3934 | Time: 5.0842 s
>>> Epoch [ 2090/10000]
train_loss: 2.0635 | train_acc: 0.4090 | val_loss: 2.0775 | val_acc: 0.3899 | test_acc: 0.3934 | Time: 5.0750 s
>>> Epoch [ 2091/10000]
train_loss: 2.0635 | train_acc: 0.4090 | val_loss: 2.0774 | val_acc: 0.3899 | test_acc: 0.3934 | Time: 4.9401 s
>>> Epoch [ 2092/10000]
train_loss: 2.0635 | train_acc: 0.4090 | val_loss: 2.0774 | val_acc: 0.3899 | test_acc: 0.3936 | Time: 5.0889 s
>>> Epoch [ 2093/10000]
train_loss: 2.0635 | train_acc: 0.4090 | val_loss: 2.0774 | val_acc: 0.3899 | test_acc: 0.3937 | Time: 5.0381 s
>>> Epoch [ 2094/10000]
train_loss: 2.0634 | train_acc: 0.4090 | val_loss: 2.0774 | val_acc: 0.3899 | test_acc: 0.3937 | Time: 5.0671 s
>>> Epoch [ 2095/10000]
train_loss: 2.0634 | train_acc: 0.4090 | val_loss: 2.0774 | val_acc: 0.3899 | test_acc: 0.3937 | Time: 5.4288 s
>>> Epoch [ 2096/10000]
train_loss: 2.0634 | train_acc: 0.4090 | val_loss: 2.0774 | val_acc: 0.3900 | test_acc: 0.3938 | Time: 4.9145 s
>>> Epoch [ 2097/10000]
train_loss: 2.0634 | train_acc: 0.4090 | val_loss: 2.0774 | val_acc: 0.3900 | test_acc: 0.3939 | Time: 5.0366 s
>>> Epoch [ 2098/10000]
train_loss: 2.0634 | train_acc: 0.4090 | val_loss: 2.0774 | val_acc: 0.3900 | test_acc: 0.3939 | Time: 5.1917 s
>>> Epoch [ 2099/10000]
train_loss: 2.0634 | train_acc: 0.4090 | val_loss: 2.0773 | val_acc: 0.3900 | test_acc: 0.3939 | Time: 5.3155 s
>>> Epoch [ 2100/10000]
train_loss: 2.0634 | train_acc: 0.4090 | val_loss: 2.0773 | val_acc: 0.3901 | test_acc: 0.3938 | Time: 5.2282 s
>>> Epoch [ 2101/10000]
train_loss: 2.0633 | train_acc: 0.4090 | val_loss: 2.0773 | val_acc: 0.3901 | test_acc: 0.3938 | Time: 4.8362 s
>>> Epoch [ 2102/10000]
train_loss: 2.0633 | train_acc: 0.4090 | val_loss: 2.0773 | val_acc: 0.3901 | test_acc: 0.3939 | Time: 5.0058 s
>>> Epoch [ 2103/10000]
train_loss: 2.0633 | train_acc: 0.4091 | val_loss: 2.0773 | val_acc: 0.3901 | test_acc: 0.3940 | Time: 4.7982 s
>>> Epoch [ 2104/10000]
train_loss: 2.0633 | train_acc: 0.4091 | val_loss: 2.0773 | val_acc: 0.3901 | test_acc: 0.3940 | Time: 5.1091 s
>>> Epoch [ 2105/10000]
train_loss: 2.0633 | train_acc: 0.4091 | val_loss: 2.0773 | val_acc: 0.3901 | test_acc: 0.3941 | Time: 4.9122 s
>>> Epoch [ 2106/10000]
train_loss: 2.0633 | train_acc: 0.4091 | val_loss: 2.0773 | val_acc: 0.3901 | test_acc: 0.3941 | Time: 4.9564 s
>>> Epoch [ 2107/10000]
train_loss: 2.0633 | train_acc: 0.4092 | val_loss: 2.0773 | val_acc: 0.3902 | test_acc: 0.3941 | Time: 4.9326 s
>>> Epoch [ 2108/10000]
train_loss: 2.0632 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3902 | test_acc: 0.3941 | Time: 5.4274 s
>>> Epoch [ 2109/10000]
train_loss: 2.0632 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3902 | test_acc: 0.3941 | Time: 5.1999 s
>>> Epoch [ 2110/10000]
train_loss: 2.0632 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3901 | test_acc: 0.3941 | Time: 5.0223 s
>>> Epoch [ 2111/10000]
train_loss: 2.0632 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3901 | test_acc: 0.3941 | Time: 5.0138 s
>>> Epoch [ 2112/10000]
train_loss: 2.0632 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3901 | test_acc: 0.3941 | Time: 5.1557 s
>>> Epoch [ 2113/10000]
train_loss: 2.0632 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3901 | test_acc: 0.3940 | Time: 5.1882 s
>>> Epoch [ 2114/10000]
train_loss: 2.0632 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3901 | test_acc: 0.3941 | Time: 5.1591 s
>>> Epoch [ 2115/10000]
train_loss: 2.0632 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3901 | test_acc: 0.3942 | Time: 4.5290 s
>>> Epoch [ 2116/10000]
train_loss: 2.0631 | train_acc: 0.4092 | val_loss: 2.0772 | val_acc: 0.3901 | test_acc: 0.3942 | Time: 4.4498 s
>>> Epoch [ 2117/10000]
train_loss: 2.0631 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3901 | test_acc: 0.3943 | Time: 5.1644 s
>>> Epoch [ 2118/10000]
train_loss: 2.0631 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3900 | test_acc: 0.3942 | Time: 5.0296 s
>>> Epoch [ 2119/10000]
train_loss: 2.0631 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3900 | test_acc: 0.3943 | Time: 7.0559 s
>>> Epoch [ 2120/10000]
train_loss: 2.0631 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3900 | test_acc: 0.3943 | Time: 6.4933 s
>>> Epoch [ 2121/10000]
train_loss: 2.0631 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3900 | test_acc: 0.3944 | Time: 6.5218 s
>>> Epoch [ 2122/10000]
train_loss: 2.0631 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3900 | test_acc: 0.3945 | Time: 7.4760 s
>>> Epoch [ 2123/10000]
train_loss: 2.0630 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3900 | test_acc: 0.3946 | Time: 4.8639 s
>>> Epoch [ 2124/10000]
train_loss: 2.0630 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3900 | test_acc: 0.3946 | Time: 4.8186 s
>>> Epoch [ 2125/10000]
train_loss: 2.0630 | train_acc: 0.4092 | val_loss: 2.0771 | val_acc: 0.3900 | test_acc: 0.3946 | Time: 5.3729 s
>>> Epoch [ 2126/10000]
train_loss: 2.0630 | train_acc: 0.4092 | val_loss: 2.0770 | val_acc: 0.3901 | test_acc: 0.3946 | Time: 4.6006 s
>>> Epoch [ 2127/10000]
train_loss: 2.0630 | train_acc: 0.4092 | val_loss: 2.0770 | val_acc: 0.3901 | test_acc: 0.3946 | Time: 5.6526 s
>>> Epoch [ 2128/10000]
train_loss: 2.0630 | train_acc: 0.4092 | val_loss: 2.0770 | val_acc: 0.3902 | test_acc: 0.3947 | Time: 5.3562 s
>>> Epoch [ 2129/10000]
train_loss: 2.0630 | train_acc: 0.4092 | val_loss: 2.0770 | val_acc: 0.3902 | test_acc: 0.3946 | Time: 5.0166 s
>>> Epoch [ 2130/10000]
train_loss: 2.0629 | train_acc: 0.4092 | val_loss: 2.0770 | val_acc: 0.3902 | test_acc: 0.3946 | Time: 5.1133 s
>>> Epoch [ 2131/10000]
train_loss: 2.0629 | train_acc: 0.4093 | val_loss: 2.0770 | val_acc: 0.3902 | test_acc: 0.3945 | Time: 5.1985 s
>>> Epoch [ 2132/10000]
train_loss: 2.0629 | train_acc: 0.4093 | val_loss: 2.0770 | val_acc: 0.3902 | test_acc: 0.3945 | Time: 5.0596 s
>>> Epoch [ 2133/10000]
train_loss: 2.0629 | train_acc: 0.4093 | val_loss: 2.0770 | val_acc: 0.3902 | test_acc: 0.3945 | Time: 5.3117 s
>>> Epoch [ 2134/10000]
train_loss: 2.0629 | train_acc: 0.4093 | val_loss: 2.0770 | val_acc: 0.3902 | test_acc: 0.3945 | Time: 5.1893 s
>>> Epoch [ 2135/10000]
train_loss: 2.0629 | train_acc: 0.4094 | val_loss: 2.0769 | val_acc: 0.3901 | test_acc: 0.3944 | Time: 5.1904 s
>>> Epoch [ 2136/10000]
train_loss: 2.0629 | train_acc: 0.4094 | val_loss: 2.0769 | val_acc: 0.3904 | test_acc: 0.3943 | Time: 5.1825 s
>>> Epoch [ 2137/10000]
train_loss: 2.0629 | train_acc: 0.4094 | val_loss: 2.0769 | val_acc: 0.3904 | test_acc: 0.3943 | Time: 5.2435 s
>>> Epoch [ 2138/10000]
train_loss: 2.0628 | train_acc: 0.4095 | val_loss: 2.0769 | val_acc: 0.3903 | test_acc: 0.3944 | Time: 5.1707 s
>>> Epoch [ 2139/10000]
train_loss: 2.0628 | train_acc: 0.4095 | val_loss: 2.0769 | val_acc: 0.3903 | test_acc: 0.3944 | Time: 5.2314 s
>>> Epoch [ 2140/10000]
train_loss: 2.0628 | train_acc: 0.4095 | val_loss: 2.0769 | val_acc: 0.3902 | test_acc: 0.3944 | Time: 4.9980 s
>>> Epoch [ 2141/10000]
train_loss: 2.0628 | train_acc: 0.4096 | val_loss: 2.0769 | val_acc: 0.3902 | test_acc: 0.3944 | Time: 5.1320 s
>>> Epoch [ 2142/10000]
train_loss: 2.0628 | train_acc: 0.4096 | val_loss: 2.0769 | val_acc: 0.3902 | test_acc: 0.3944 | Time: 5.0059 s
>>> Epoch [ 2143/10000]
train_loss: 2.0628 | train_acc: 0.4096 | val_loss: 2.0769 | val_acc: 0.3902 | test_acc: 0.3944 | Time: 4.9928 s
>>> Epoch [ 2144/10000]
train_loss: 2.0628 | train_acc: 0.4096 | val_loss: 2.0768 | val_acc: 0.3903 | test_acc: 0.3944 | Time: 5.3325 s
>>> Epoch [ 2145/10000]
train_loss: 2.0627 | train_acc: 0.4096 | val_loss: 2.0768 | val_acc: 0.3905 | test_acc: 0.3944 | Time: 5.1760 s
>>> Epoch [ 2146/10000]
train_loss: 2.0627 | train_acc: 0.4096 | val_loss: 2.0768 | val_acc: 0.3905 | test_acc: 0.3944 | Time: 5.1339 s
>>> Epoch [ 2147/10000]
train_loss: 2.0627 | train_acc: 0.4096 | val_loss: 2.0768 | val_acc: 0.3906 | test_acc: 0.3944 | Time: 5.1334 s
>>> Epoch [ 2148/10000]
train_loss: 2.0627 | train_acc: 0.4096 | val_loss: 2.0768 | val_acc: 0.3907 | test_acc: 0.3944 | Time: 5.5053 s
>>> Epoch [ 2149/10000]
train_loss: 2.0627 | train_acc: 0.4096 | val_loss: 2.0768 | val_acc: 0.3907 | test_acc: 0.3945 | Time: 5.4518 s
>>> Epoch [ 2150/10000]
train_loss: 2.0627 | train_acc: 0.4096 | val_loss: 2.0768 | val_acc: 0.3907 | test_acc: 0.3945 | Time: 5.2738 s
>>> Epoch [ 2151/10000]
train_loss: 2.0627 | train_acc: 0.4097 | val_loss: 2.0768 | val_acc: 0.3908 | test_acc: 0.3944 | Time: 5.2708 s
>>> Epoch [ 2152/10000]
train_loss: 2.0627 | train_acc: 0.4098 | val_loss: 2.0768 | val_acc: 0.3908 | test_acc: 0.3942 | Time: 5.2822 s
>>> Epoch [ 2153/10000]
train_loss: 2.0626 | train_acc: 0.4098 | val_loss: 2.0767 | val_acc: 0.3908 | test_acc: 0.3941 | Time: 5.4645 s
>>> Epoch [ 2154/10000]
train_loss: 2.0626 | train_acc: 0.4099 | val_loss: 2.0767 | val_acc: 0.3908 | test_acc: 0.3941 | Time: 5.1948 s
>>> Epoch [ 2155/10000]
train_loss: 2.0626 | train_acc: 0.4099 | val_loss: 2.0767 | val_acc: 0.3908 | test_acc: 0.3941 | Time: 5.5739 s
>>> Epoch [ 2156/10000]
train_loss: 2.0626 | train_acc: 0.4099 | val_loss: 2.0767 | val_acc: 0.3908 | test_acc: 0.3940 | Time: 5.1910 s
>>> Epoch [ 2157/10000]
train_loss: 2.0626 | train_acc: 0.4100 | val_loss: 2.0767 | val_acc: 0.3908 | test_acc: 0.3940 | Time: 5.4068 s
>>> Epoch [ 2158/10000]
train_loss: 2.0626 | train_acc: 0.4100 | val_loss: 2.0767 | val_acc: 0.3908 | test_acc: 0.3940 | Time: 5.2113 s
>>> Epoch [ 2159/10000]
train_loss: 2.0626 | train_acc: 0.4100 | val_loss: 2.0767 | val_acc: 0.3908 | test_acc: 0.3940 | Time: 6.2547 s
>>> Epoch [ 2160/10000]
train_loss: 2.0625 | train_acc: 0.4100 | val_loss: 2.0767 | val_acc: 0.3907 | test_acc: 0.3940 | Time: 8.1934 s
>>> Epoch [ 2161/10000]
train_loss: 2.0625 | train_acc: 0.4101 | val_loss: 2.0767 | val_acc: 0.3907 | test_acc: 0.3940 | Time: 7.2514 s
>>> Epoch [ 2162/10000]
train_loss: 2.0625 | train_acc: 0.4101 | val_loss: 2.0766 | val_acc: 0.3909 | test_acc: 0.3939 | Time: 4.9875 s
>>> Epoch [ 2163/10000]
train_loss: 2.0625 | train_acc: 0.4101 | val_loss: 2.0766 | val_acc: 0.3909 | test_acc: 0.3938 | Time: 5.1674 s
>>> Epoch [ 2164/10000]
train_loss: 2.0625 | train_acc: 0.4101 | val_loss: 2.0766 | val_acc: 0.3909 | test_acc: 0.3938 | Time: 4.8816 s
>>> Epoch [ 2165/10000]
train_loss: 2.0625 | train_acc: 0.4102 | val_loss: 2.0766 | val_acc: 0.3909 | test_acc: 0.3939 | Time: 5.0021 s
>>> Epoch [ 2166/10000]
train_loss: 2.0625 | train_acc: 0.4102 | val_loss: 2.0766 | val_acc: 0.3910 | test_acc: 0.3940 | Time: 4.9966 s
>>> Epoch [ 2167/10000]
train_loss: 2.0625 | train_acc: 0.4101 | val_loss: 2.0766 | val_acc: 0.3912 | test_acc: 0.3940 | Time: 4.9695 s
>>> Epoch [ 2168/10000]
train_loss: 2.0624 | train_acc: 0.4101 | val_loss: 2.0766 | val_acc: 0.3912 | test_acc: 0.3941 | Time: 4.8313 s
>>> Epoch [ 2169/10000]
train_loss: 2.0624 | train_acc: 0.4101 | val_loss: 2.0766 | val_acc: 0.3912 | test_acc: 0.3941 | Time: 4.8717 s
>>> Epoch [ 2170/10000]
train_loss: 2.0624 | train_acc: 0.4101 | val_loss: 2.0766 | val_acc: 0.3913 | test_acc: 0.3941 | Time: 5.0092 s
>>> Epoch [ 2171/10000]
train_loss: 2.0624 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3913 | test_acc: 0.3941 | Time: 5.1586 s
>>> Epoch [ 2172/10000]
train_loss: 2.0624 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3913 | test_acc: 0.3941 | Time: 4.8713 s
>>> Epoch [ 2173/10000]
train_loss: 2.0624 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3914 | test_acc: 0.3941 | Time: 5.0129 s
>>> Epoch [ 2174/10000]
train_loss: 2.0624 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3915 | test_acc: 0.3941 | Time: 5.0315 s
>>> Epoch [ 2175/10000]
train_loss: 2.0624 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3914 | test_acc: 0.3941 | Time: 4.7001 s
>>> Epoch [ 2176/10000]
train_loss: 2.0623 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3914 | test_acc: 0.3942 | Time: 4.9319 s
>>> Epoch [ 2177/10000]
train_loss: 2.0623 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3914 | test_acc: 0.3942 | Time: 4.5932 s
>>> Epoch [ 2178/10000]
train_loss: 2.0623 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3915 | test_acc: 0.3942 | Time: 4.9050 s
>>> Epoch [ 2179/10000]
train_loss: 2.0623 | train_acc: 0.4102 | val_loss: 2.0765 | val_acc: 0.3915 | test_acc: 0.3943 | Time: 6.0028 s
>>> Epoch [ 2180/10000]
train_loss: 2.0623 | train_acc: 0.4102 | val_loss: 2.0764 | val_acc: 0.3915 | test_acc: 0.3944 | Time: 8.3665 s
>>> Epoch [ 2181/10000]
train_loss: 2.0623 | train_acc: 0.4102 | val_loss: 2.0764 | val_acc: 0.3916 | test_acc: 0.3944 | Time: 7.5357 s
>>> Epoch [ 2182/10000]
train_loss: 2.0623 | train_acc: 0.4102 | val_loss: 2.0764 | val_acc: 0.3916 | test_acc: 0.3943 | Time: 5.0830 s
>>> Epoch [ 2183/10000]
train_loss: 2.0622 | train_acc: 0.4102 | val_loss: 2.0764 | val_acc: 0.3916 | test_acc: 0.3943 | Time: 5.1059 s
>>> Epoch [ 2184/10000]
train_loss: 2.0622 | train_acc: 0.4102 | val_loss: 2.0764 | val_acc: 0.3916 | test_acc: 0.3943 | Time: 5.3498 s
>>> Epoch [ 2185/10000]
train_loss: 2.0622 | train_acc: 0.4102 | val_loss: 2.0764 | val_acc: 0.3916 | test_acc: 0.3943 | Time: 5.1712 s
>>> Epoch [ 2186/10000]
train_loss: 2.0622 | train_acc: 0.4102 | val_loss: 2.0764 | val_acc: 0.3915 | test_acc: 0.3943 | Time: 5.1395 s
>>> Epoch [ 2187/10000]
train_loss: 2.0622 | train_acc: 0.4102 | val_loss: 2.0764 | val_acc: 0.3915 | test_acc: 0.3943 | Time: 5.3751 s
>>> Epoch [ 2188/10000]
train_loss: 2.0622 | train_acc: 0.4103 | val_loss: 2.0764 | val_acc: 0.3915 | test_acc: 0.3943 | Time: 5.4703 s
>>> Epoch [ 2189/10000]
train_loss: 2.0622 | train_acc: 0.4103 | val_loss: 2.0764 | val_acc: 0.3916 | test_acc: 0.3943 | Time: 5.1684 s
>>> Epoch [ 2190/10000]
train_loss: 2.0622 | train_acc: 0.4103 | val_loss: 2.0763 | val_acc: 0.3916 | test_acc: 0.3943 | Time: 5.1661 s
>>> Epoch [ 2191/10000]
train_loss: 2.0621 | train_acc: 0.4104 | val_loss: 2.0763 | val_acc: 0.3917 | test_acc: 0.3943 | Time: 5.1769 s
>>> Epoch [ 2192/10000]
train_loss: 2.0621 | train_acc: 0.4105 | val_loss: 2.0763 | val_acc: 0.3917 | test_acc: 0.3943 | Time: 5.5388 s
>>> Epoch [ 2193/10000]
train_loss: 2.0621 | train_acc: 0.4104 | val_loss: 2.0763 | val_acc: 0.3917 | test_acc: 0.3943 | Time: 5.4344 s
>>> Epoch [ 2194/10000]
train_loss: 2.0621 | train_acc: 0.4105 | val_loss: 2.0763 | val_acc: 0.3918 | test_acc: 0.3943 | Time: 5.4134 s
>>> Epoch [ 2195/10000]
train_loss: 2.0621 | train_acc: 0.4105 | val_loss: 2.0763 | val_acc: 0.3918 | test_acc: 0.3943 | Time: 4.9769 s
>>> Epoch [ 2196/10000]
train_loss: 2.0621 | train_acc: 0.4105 | val_loss: 2.0763 | val_acc: 0.3918 | test_acc: 0.3945 | Time: 4.8967 s
>>> Epoch [ 2197/10000]
train_loss: 2.0621 | train_acc: 0.4106 | val_loss: 2.0763 | val_acc: 0.3918 | test_acc: 0.3945 | Time: 4.8290 s
>>> Epoch [ 2198/10000]
train_loss: 2.0621 | train_acc: 0.4105 | val_loss: 2.0763 | val_acc: 0.3918 | test_acc: 0.3945 | Time: 4.7232 s
>>> Epoch [ 2199/10000]
train_loss: 2.0620 | train_acc: 0.4105 | val_loss: 2.0762 | val_acc: 0.3918 | test_acc: 0.3944 | Time: 4.6899 s
>>> Epoch [ 2200/10000]
train_loss: 2.0620 | train_acc: 0.4106 | val_loss: 2.0762 | val_acc: 0.3918 | test_acc: 0.3944 | Time: 5.2306 s
>>> Epoch [ 2201/10000]
train_loss: 2.0620 | train_acc: 0.4106 | val_loss: 2.0762 | val_acc: 0.3919 | test_acc: 0.3944 | Time: 5.1213 s
>>> Epoch [ 2202/10000]
train_loss: 2.0620 | train_acc: 0.4106 | val_loss: 2.0762 | val_acc: 0.3919 | test_acc: 0.3945 | Time: 5.0946 s
>>> Epoch [ 2203/10000]
train_loss: 2.0620 | train_acc: 0.4106 | val_loss: 2.0762 | val_acc: 0.3919 | test_acc: 0.3945 | Time: 5.0943 s
>>> Epoch [ 2204/10000]
train_loss: 2.0620 | train_acc: 0.4106 | val_loss: 2.0762 | val_acc: 0.3919 | test_acc: 0.3945 | Time: 5.1508 s
>>> Epoch [ 2205/10000]
train_loss: 2.0620 | train_acc: 0.4106 | val_loss: 2.0762 | val_acc: 0.3919 | test_acc: 0.3944 | Time: 5.1647 s
>>> Epoch [ 2206/10000]
train_loss: 2.0619 | train_acc: 0.4106 | val_loss: 2.0762 | val_acc: 0.3919 | test_acc: 0.3944 | Time: 5.0482 s
>>> Epoch [ 2207/10000]
train_loss: 2.0619 | train_acc: 0.4106 | val_loss: 2.0762 | val_acc: 0.3919 | test_acc: 0.3944 | Time: 4.8724 s
>>> Epoch [ 2208/10000]
train_loss: 2.0619 | train_acc: 0.4106 | val_loss: 2.0761 | val_acc: 0.3918 | test_acc: 0.3944 | Time: 5.3219 s
>>> Epoch [ 2209/10000]
train_loss: 2.0619 | train_acc: 0.4106 | val_loss: 2.0761 | val_acc: 0.3918 | test_acc: 0.3944 | Time: 5.5334 s
>>> Epoch [ 2210/10000]
train_loss: 2.0619 | train_acc: 0.4106 | val_loss: 2.0761 | val_acc: 0.3918 | test_acc: 0.3944 | Time: 5.2945 s
>>> Epoch [ 2211/10000]
train_loss: 2.0619 | train_acc: 0.4105 | val_loss: 2.0761 | val_acc: 0.3917 | test_acc: 0.3944 | Time: 5.2012 s
>>> Epoch [ 2212/10000]
train_loss: 2.0619 | train_acc: 0.4105 | val_loss: 2.0761 | val_acc: 0.3917 | test_acc: 0.3944 | Time: 5.4274 s
>>> Epoch [ 2213/10000]
train_loss: 2.0619 | train_acc: 0.4106 | val_loss: 2.0761 | val_acc: 0.3918 | test_acc: 0.3944 | Time: 5.2848 s
>>> Epoch [ 2214/10000]
train_loss: 2.0618 | train_acc: 0.4106 | val_loss: 2.0761 | val_acc: 0.3918 | test_acc: 0.3944 | Time: 5.1421 s
>>> Epoch [ 2215/10000]
train_loss: 2.0618 | train_acc: 0.4106 | val_loss: 2.0761 | val_acc: 0.3918 | test_acc: 0.3945 | Time: 5.2553 s
>>> Epoch [ 2216/10000]
train_loss: 2.0618 | train_acc: 0.4106 | val_loss: 2.0761 | val_acc: 0.3918 | test_acc: 0.3945 | Time: 5.2863 s
>>> Epoch [ 2217/10000]
train_loss: 2.0618 | train_acc: 0.4107 | val_loss: 2.0761 | val_acc: 0.3918 | test_acc: 0.3945 | Time: 5.3515 s
>>> Epoch [ 2218/10000]
train_loss: 2.0618 | train_acc: 0.4106 | val_loss: 2.0760 | val_acc: 0.3919 | test_acc: 0.3945 | Time: 5.6278 s
>>> Epoch [ 2219/10000]
train_loss: 2.0618 | train_acc: 0.4106 | val_loss: 2.0760 | val_acc: 0.3919 | test_acc: 0.3945 | Time: 5.3549 s
>>> Epoch [ 2220/10000]
train_loss: 2.0618 | train_acc: 0.4107 | val_loss: 2.0760 | val_acc: 0.3918 | test_acc: 0.3945 | Time: 5.3203 s
>>> Epoch [ 2221/10000]
train_loss: 2.0618 | train_acc: 0.4106 | val_loss: 2.0760 | val_acc: 0.3918 | test_acc: 0.3943 | Time: 5.4428 s
>>> Epoch [ 2222/10000]
train_loss: 2.0617 | train_acc: 0.4106 | val_loss: 2.0760 | val_acc: 0.3917 | test_acc: 0.3943 | Time: 5.4144 s
>>> Epoch [ 2223/10000]
train_loss: 2.0617 | train_acc: 0.4106 | val_loss: 2.0760 | val_acc: 0.3917 | test_acc: 0.3943 | Time: 5.1094 s
>>> Epoch [ 2224/10000]
train_loss: 2.0617 | train_acc: 0.4107 | val_loss: 2.0760 | val_acc: 0.3916 | test_acc: 0.3944 | Time: 5.5148 s
>>> Epoch [ 2225/10000]
train_loss: 2.0617 | train_acc: 0.4107 | val_loss: 2.0760 | val_acc: 0.3916 | test_acc: 0.3944 | Time: 5.6977 s
>>> Epoch [ 2226/10000]
train_loss: 2.0617 | train_acc: 0.4107 | val_loss: 2.0760 | val_acc: 0.3917 | test_acc: 0.3944 | Time: 5.4476 s
>>> Epoch [ 2227/10000]
train_loss: 2.0617 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3916 | test_acc: 0.3944 | Time: 5.1880 s
>>> Epoch [ 2228/10000]
train_loss: 2.0617 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3917 | test_acc: 0.3944 | Time: 5.6092 s
>>> Epoch [ 2229/10000]
train_loss: 2.0617 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3917 | test_acc: 0.3944 | Time: 5.5177 s
>>> Epoch [ 2230/10000]
train_loss: 2.0616 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3918 | test_acc: 0.3944 | Time: 5.6536 s
>>> Epoch [ 2231/10000]
train_loss: 2.0616 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3919 | test_acc: 0.3944 | Time: 5.4032 s
>>> Epoch [ 2232/10000]
train_loss: 2.0616 | train_acc: 0.4106 | val_loss: 2.0759 | val_acc: 0.3919 | test_acc: 0.3944 | Time: 5.5456 s
>>> Epoch [ 2233/10000]
train_loss: 2.0616 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3919 | test_acc: 0.3945 | Time: 5.3629 s
>>> Epoch [ 2234/10000]
train_loss: 2.0616 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3919 | test_acc: 0.3945 | Time: 5.4120 s
>>> Epoch [ 2235/10000]
train_loss: 2.0616 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3922 | test_acc: 0.3945 | Time: 5.4843 s
>>> Epoch [ 2236/10000]
train_loss: 2.0616 | train_acc: 0.4107 | val_loss: 2.0759 | val_acc: 0.3921 | test_acc: 0.3945 | Time: 5.2115 s
>>> Epoch [ 2237/10000]
train_loss: 2.0615 | train_acc: 0.4108 | val_loss: 2.0758 | val_acc: 0.3920 | test_acc: 0.3945 | Time: 5.4506 s
>>> Epoch [ 2238/10000]
train_loss: 2.0615 | train_acc: 0.4108 | val_loss: 2.0758 | val_acc: 0.3920 | test_acc: 0.3945 | Time: 5.6168 s
>>> Epoch [ 2239/10000]
train_loss: 2.0615 | train_acc: 0.4107 | val_loss: 2.0758 | val_acc: 0.3920 | test_acc: 0.3947 | Time: 8.4846 s
>>> Epoch [ 2240/10000]
train_loss: 2.0615 | train_acc: 0.4107 | val_loss: 2.0758 | val_acc: 0.3920 | test_acc: 0.3947 | Time: 7.8056 s
>>> Epoch [ 2241/10000]
train_loss: 2.0615 | train_acc: 0.4107 | val_loss: 2.0758 | val_acc: 0.3923 | test_acc: 0.3948 | Time: 8.5688 s
>>> Epoch [ 2242/10000]
train_loss: 2.0615 | train_acc: 0.4107 | val_loss: 2.0758 | val_acc: 0.3923 | test_acc: 0.3948 | Time: 8.0206 s
>>> Epoch [ 2243/10000]
train_loss: 2.0615 | train_acc: 0.4107 | val_loss: 2.0758 | val_acc: 0.3923 | test_acc: 0.3948 | Time: 5.0510 s
>>> Epoch [ 2244/10000]
train_loss: 2.0615 | train_acc: 0.4107 | val_loss: 2.0758 | val_acc: 0.3923 | test_acc: 0.3948 | Time: 5.4878 s
>>> Epoch [ 2245/10000]
train_loss: 2.0614 | train_acc: 0.4107 | val_loss: 2.0758 | val_acc: 0.3922 | test_acc: 0.3948 | Time: 5.0519 s
>>> Epoch [ 2246/10000]
train_loss: 2.0614 | train_acc: 0.4108 | val_loss: 2.0758 | val_acc: 0.3922 | test_acc: 0.3948 | Time: 5.3531 s
>>> Epoch [ 2247/10000]
train_loss: 2.0614 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3922 | test_acc: 0.3948 | Time: 5.1262 s
>>> Epoch [ 2248/10000]
train_loss: 2.0614 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3922 | test_acc: 0.3948 | Time: 5.2093 s
>>> Epoch [ 2249/10000]
train_loss: 2.0614 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3922 | test_acc: 0.3948 | Time: 5.6182 s
>>> Epoch [ 2250/10000]
train_loss: 2.0614 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3924 | test_acc: 0.3948 | Time: 5.4136 s
>>> Epoch [ 2251/10000]
train_loss: 2.0614 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3925 | test_acc: 0.3948 | Time: 5.6251 s
>>> Epoch [ 2252/10000]
train_loss: 2.0614 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3924 | test_acc: 0.3948 | Time: 5.4980 s
>>> Epoch [ 2253/10000]
train_loss: 2.0613 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3925 | test_acc: 0.3948 | Time: 5.4748 s
>>> Epoch [ 2254/10000]
train_loss: 2.0613 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3926 | test_acc: 0.3948 | Time: 5.4089 s
>>> Epoch [ 2255/10000]
train_loss: 2.0613 | train_acc: 0.4108 | val_loss: 2.0757 | val_acc: 0.3926 | test_acc: 0.3948 | Time: 5.3880 s
>>> Epoch [ 2256/10000]
train_loss: 2.0613 | train_acc: 0.4108 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3948 | Time: 5.6346 s
>>> Epoch [ 2257/10000]
train_loss: 2.0613 | train_acc: 0.4109 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3948 | Time: 5.2591 s
>>> Epoch [ 2258/10000]
train_loss: 2.0613 | train_acc: 0.4110 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3949 | Time: 5.3401 s
>>> Epoch [ 2259/10000]
train_loss: 2.0613 | train_acc: 0.4110 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3949 | Time: 5.4108 s
>>> Epoch [ 2260/10000]
train_loss: 2.0613 | train_acc: 0.4110 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3949 | Time: 5.1606 s
>>> Epoch [ 2261/10000]
train_loss: 2.0612 | train_acc: 0.4111 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3949 | Time: 5.3007 s
>>> Epoch [ 2262/10000]
train_loss: 2.0612 | train_acc: 0.4111 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3949 | Time: 5.4608 s
>>> Epoch [ 2263/10000]
train_loss: 2.0612 | train_acc: 0.4110 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3950 | Time: 5.5484 s
>>> Epoch [ 2264/10000]
train_loss: 2.0612 | train_acc: 0.4111 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3950 | Time: 5.3395 s
>>> Epoch [ 2265/10000]
train_loss: 2.0612 | train_acc: 0.4111 | val_loss: 2.0756 | val_acc: 0.3928 | test_acc: 0.3950 | Time: 5.4458 s
>>> Epoch [ 2266/10000]
train_loss: 2.0612 | train_acc: 0.4111 | val_loss: 2.0755 | val_acc: 0.3928 | test_acc: 0.3950 | Time: 5.5088 s
>>> Epoch [ 2267/10000]
train_loss: 2.0612 | train_acc: 0.4111 | val_loss: 2.0755 | val_acc: 0.3928 | test_acc: 0.3950 | Time: 5.5995 s
>>> Epoch [ 2268/10000]
train_loss: 2.0612 | train_acc: 0.4111 | val_loss: 2.0755 | val_acc: 0.3928 | test_acc: 0.3950 | Time: 5.4054 s
>>> Epoch [ 2269/10000]
train_loss: 2.0611 | train_acc: 0.4111 | val_loss: 2.0755 | val_acc: 0.3928 | test_acc: 0.3949 | Time: 5.3096 s
>>> Epoch [ 2270/10000]
train_loss: 2.0611 | train_acc: 0.4112 | val_loss: 2.0755 | val_acc: 0.3928 | test_acc: 0.3948 | Time: 5.4418 s
>>> Epoch [ 2271/10000]
train_loss: 2.0611 | train_acc: 0.4112 | val_loss: 2.0755 | val_acc: 0.3929 | test_acc: 0.3948 | Time: 5.6167 s
>>> Epoch [ 2272/10000]
train_loss: 2.0611 | train_acc: 0.4112 | val_loss: 2.0755 | val_acc: 0.3929 | test_acc: 0.3948 | Time: 5.3412 s
>>> Epoch [ 2273/10000]
train_loss: 2.0611 | train_acc: 0.4112 | val_loss: 2.0755 | val_acc: 0.3929 | test_acc: 0.3947 | Time: 5.4189 s
>>> Epoch [ 2274/10000]
train_loss: 2.0611 | train_acc: 0.4112 | val_loss: 2.0755 | val_acc: 0.3929 | test_acc: 0.3947 | Time: 5.6666 s
>>> Epoch [ 2275/10000]
train_loss: 2.0611 | train_acc: 0.4112 | val_loss: 2.0755 | val_acc: 0.3930 | test_acc: 0.3947 | Time: 5.6536 s
>>> Epoch [ 2276/10000]
train_loss: 2.0611 | train_acc: 0.4113 | val_loss: 2.0754 | val_acc: 0.3930 | test_acc: 0.3946 | Time: 5.2282 s
>>> Epoch [ 2277/10000]
train_loss: 2.0610 | train_acc: 0.4113 | val_loss: 2.0754 | val_acc: 0.3929 | test_acc: 0.3947 | Time: 5.6141 s
>>> Epoch [ 2278/10000]
train_loss: 2.0610 | train_acc: 0.4113 | val_loss: 2.0754 | val_acc: 0.3929 | test_acc: 0.3949 | Time: 5.3877 s
>>> Epoch [ 2279/10000]
train_loss: 2.0610 | train_acc: 0.4113 | val_loss: 2.0754 | val_acc: 0.3928 | test_acc: 0.3949 | Time: 5.5163 s
>>> Epoch [ 2280/10000]
train_loss: 2.0610 | train_acc: 0.4114 | val_loss: 2.0754 | val_acc: 0.3928 | test_acc: 0.3950 | Time: 8.6641 s
>>> Epoch [ 2281/10000]
train_loss: 2.0610 | train_acc: 0.4113 | val_loss: 2.0754 | val_acc: 0.3928 | test_acc: 0.3950 | Time: 7.7018 s
>>> Epoch [ 2282/10000]
train_loss: 2.0610 | train_acc: 0.4114 | val_loss: 2.0754 | val_acc: 0.3928 | test_acc: 0.3949 | Time: 8.5011 s
>>> Epoch [ 2283/10000]
train_loss: 2.0610 | train_acc: 0.4113 | val_loss: 2.0754 | val_acc: 0.3929 | test_acc: 0.3949 | Time: 7.7792 s
>>> Epoch [ 2284/10000]
train_loss: 2.0610 | train_acc: 0.4113 | val_loss: 2.0754 | val_acc: 0.3930 | test_acc: 0.3949 | Time: 5.0746 s
>>> Epoch [ 2285/10000]
train_loss: 2.0609 | train_acc: 0.4114 | val_loss: 2.0754 | val_acc: 0.3930 | test_acc: 0.3951 | Time: 5.1946 s
>>> Epoch [ 2286/10000]
train_loss: 2.0609 | train_acc: 0.4114 | val_loss: 2.0753 | val_acc: 0.3929 | test_acc: 0.3950 | Time: 5.2342 s
>>> Epoch [ 2287/10000]
train_loss: 2.0609 | train_acc: 0.4115 | val_loss: 2.0753 | val_acc: 0.3929 | test_acc: 0.3950 | Time: 5.3741 s
>>> Epoch [ 2288/10000]
train_loss: 2.0609 | train_acc: 0.4115 | val_loss: 2.0753 | val_acc: 0.3929 | test_acc: 0.3950 | Time: 5.3639 s
>>> Epoch [ 2289/10000]
train_loss: 2.0609 | train_acc: 0.4115 | val_loss: 2.0753 | val_acc: 0.3929 | test_acc: 0.3950 | Time: 5.6724 s
>>> Epoch [ 2290/10000]
train_loss: 2.0609 | train_acc: 0.4114 | val_loss: 2.0753 | val_acc: 0.3929 | test_acc: 0.3951 | Time: 5.3683 s
>>> Epoch [ 2291/10000]
train_loss: 2.0609 | train_acc: 0.4114 | val_loss: 2.0753 | val_acc: 0.3930 | test_acc: 0.3951 | Time: 5.4995 s
>>> Epoch [ 2292/10000]
train_loss: 2.0609 | train_acc: 0.4114 | val_loss: 2.0753 | val_acc: 0.3930 | test_acc: 0.3952 | Time: 6.0048 s
>>> Epoch [ 2293/10000]
train_loss: 2.0608 | train_acc: 0.4114 | val_loss: 2.0753 | val_acc: 0.3930 | test_acc: 0.3952 | Time: 5.6601 s
>>> Epoch [ 2294/10000]
train_loss: 2.0608 | train_acc: 0.4114 | val_loss: 2.0753 | val_acc: 0.3931 | test_acc: 0.3952 | Time: 5.3861 s
>>> Epoch [ 2295/10000]
train_loss: 2.0608 | train_acc: 0.4115 | val_loss: 2.0753 | val_acc: 0.3931 | test_acc: 0.3952 | Time: 5.5774 s
>>> Epoch [ 2296/10000]
train_loss: 2.0608 | train_acc: 0.4115 | val_loss: 2.0752 | val_acc: 0.3931 | test_acc: 0.3952 | Time: 5.4143 s
>>> Epoch [ 2297/10000]
train_loss: 2.0608 | train_acc: 0.4115 | val_loss: 2.0752 | val_acc: 0.3931 | test_acc: 0.3952 | Time: 5.4194 s
>>> Epoch [ 2298/10000]
train_loss: 2.0608 | train_acc: 0.4116 | val_loss: 2.0752 | val_acc: 0.3932 | test_acc: 0.3952 | Time: 5.4820 s
>>> Epoch [ 2299/10000]
train_loss: 2.0608 | train_acc: 0.4115 | val_loss: 2.0752 | val_acc: 0.3932 | test_acc: 0.3951 | Time: 5.4889 s
>>> Epoch [ 2300/10000]
train_loss: 2.0608 | train_acc: 0.4115 | val_loss: 2.0752 | val_acc: 0.3933 | test_acc: 0.3951 | Time: 5.5775 s
>>> Epoch [ 2301/10000]
train_loss: 2.0607 | train_acc: 0.4115 | val_loss: 2.0752 | val_acc: 0.3933 | test_acc: 0.3951 | Time: 5.4947 s
>>> Epoch [ 2302/10000]
train_loss: 2.0607 | train_acc: 0.4115 | val_loss: 2.0752 | val_acc: 0.3933 | test_acc: 0.3951 | Time: 5.4621 s
>>> Epoch [ 2303/10000]
train_loss: 2.0607 | train_acc: 0.4116 | val_loss: 2.0752 | val_acc: 0.3933 | test_acc: 0.3951 | Time: 5.8077 s
>>> Epoch [ 2304/10000]
train_loss: 2.0607 | train_acc: 0.4116 | val_loss: 2.0752 | val_acc: 0.3933 | test_acc: 0.3950 | Time: 5.5978 s
>>> Epoch [ 2305/10000]
train_loss: 2.0607 | train_acc: 0.4116 | val_loss: 2.0752 | val_acc: 0.3933 | test_acc: 0.3950 | Time: 5.8357 s
>>> Epoch [ 2306/10000]
train_loss: 2.0607 | train_acc: 0.4117 | val_loss: 2.0751 | val_acc: 0.3933 | test_acc: 0.3950 | Time: 5.4528 s
>>> Epoch [ 2307/10000]
train_loss: 2.0607 | train_acc: 0.4117 | val_loss: 2.0751 | val_acc: 0.3933 | test_acc: 0.3950 | Time: 5.7729 s
>>> Epoch [ 2308/10000]
train_loss: 2.0607 | train_acc: 0.4117 | val_loss: 2.0751 | val_acc: 0.3935 | test_acc: 0.3950 | Time: 5.3760 s
>>> Epoch [ 2309/10000]
train_loss: 2.0606 | train_acc: 0.4117 | val_loss: 2.0751 | val_acc: 0.3933 | test_acc: 0.3950 | Time: 5.5978 s
>>> Epoch [ 2310/10000]
train_loss: 2.0606 | train_acc: 0.4117 | val_loss: 2.0751 | val_acc: 0.3935 | test_acc: 0.3950 | Time: 5.3783 s
>>> Epoch [ 2311/10000]
train_loss: 2.0606 | train_acc: 0.4117 | val_loss: 2.0751 | val_acc: 0.3935 | test_acc: 0.3950 | Time: 5.6568 s
>>> Epoch [ 2312/10000]
train_loss: 2.0606 | train_acc: 0.4117 | val_loss: 2.0751 | val_acc: 0.3936 | test_acc: 0.3950 | Time: 5.2996 s
>>> Epoch [ 2313/10000]
train_loss: 2.0606 | train_acc: 0.4118 | val_loss: 2.0751 | val_acc: 0.3936 | test_acc: 0.3950 | Time: 5.5079 s
>>> Epoch [ 2314/10000]
train_loss: 2.0606 | train_acc: 0.4118 | val_loss: 2.0751 | val_acc: 0.3936 | test_acc: 0.3949 | Time: 5.5883 s
>>> Epoch [ 2315/10000]
train_loss: 2.0606 | train_acc: 0.4118 | val_loss: 2.0751 | val_acc: 0.3936 | test_acc: 0.3949 | Time: 5.8003 s
>>> Epoch [ 2316/10000]
train_loss: 2.0606 | train_acc: 0.4118 | val_loss: 2.0750 | val_acc: 0.3936 | test_acc: 0.3949 | Time: 5.3757 s
>>> Epoch [ 2317/10000]
train_loss: 2.0605 | train_acc: 0.4119 | val_loss: 2.0750 | val_acc: 0.3936 | test_acc: 0.3950 | Time: 5.4833 s
>>> Epoch [ 2318/10000]
train_loss: 2.0605 | train_acc: 0.4119 | val_loss: 2.0750 | val_acc: 0.3936 | test_acc: 0.3950 | Time: 5.5423 s
>>> Epoch [ 2319/10000]
train_loss: 2.0605 | train_acc: 0.4120 | val_loss: 2.0750 | val_acc: 0.3937 | test_acc: 0.3950 | Time: 8.7817 s
>>> Epoch [ 2320/10000]
train_loss: 2.0605 | train_acc: 0.4119 | val_loss: 2.0750 | val_acc: 0.3937 | test_acc: 0.3951 | Time: 7.9920 s
>>> Epoch [ 2321/10000]
train_loss: 2.0605 | train_acc: 0.4120 | val_loss: 2.0750 | val_acc: 0.3937 | test_acc: 0.3951 | Time: 7.7334 s
>>> Epoch [ 2322/10000]
train_loss: 2.0605 | train_acc: 0.4119 | val_loss: 2.0750 | val_acc: 0.3937 | test_acc: 0.3951 | Time: 7.8966 s
>>> Epoch [ 2323/10000]
train_loss: 2.0605 | train_acc: 0.4120 | val_loss: 2.0750 | val_acc: 0.3937 | test_acc: 0.3952 | Time: 6.3051 s
>>> Epoch [ 2324/10000]
train_loss: 2.0605 | train_acc: 0.4120 | val_loss: 2.0750 | val_acc: 0.3937 | test_acc: 0.3951 | Time: 5.1523 s
>>> Epoch [ 2325/10000]
train_loss: 2.0604 | train_acc: 0.4121 | val_loss: 2.0750 | val_acc: 0.3938 | test_acc: 0.3951 | Time: 5.3479 s
>>> Epoch [ 2326/10000]
train_loss: 2.0604 | train_acc: 0.4121 | val_loss: 2.0749 | val_acc: 0.3939 | test_acc: 0.3951 | Time: 5.4035 s
>>> Epoch [ 2327/10000]
train_loss: 2.0604 | train_acc: 0.4121 | val_loss: 2.0749 | val_acc: 0.3940 | test_acc: 0.3951 | Time: 5.1325 s
>>> Epoch [ 2328/10000]
train_loss: 2.0604 | train_acc: 0.4122 | val_loss: 2.0749 | val_acc: 0.3940 | test_acc: 0.3951 | Time: 5.7382 s
>>> Epoch [ 2329/10000]
train_loss: 2.0604 | train_acc: 0.4122 | val_loss: 2.0749 | val_acc: 0.3940 | test_acc: 0.3951 | Time: 5.5204 s
>>> Epoch [ 2330/10000]
train_loss: 2.0604 | train_acc: 0.4121 | val_loss: 2.0749 | val_acc: 0.3940 | test_acc: 0.3952 | Time: 5.6952 s
>>> Epoch [ 2331/10000]
train_loss: 2.0604 | train_acc: 0.4122 | val_loss: 2.0749 | val_acc: 0.3940 | test_acc: 0.3952 | Time: 5.6045 s
>>> Epoch [ 2332/10000]
train_loss: 2.0604 | train_acc: 0.4121 | val_loss: 2.0749 | val_acc: 0.3940 | test_acc: 0.3953 | Time: 5.7978 s
>>> Epoch [ 2333/10000]
train_loss: 2.0604 | train_acc: 0.4121 | val_loss: 2.0749 | val_acc: 0.3939 | test_acc: 0.3954 | Time: 5.8230 s
>>> Epoch [ 2334/10000]
train_loss: 2.0603 | train_acc: 0.4121 | val_loss: 2.0749 | val_acc: 0.3939 | test_acc: 0.3954 | Time: 5.6051 s
>>> Epoch [ 2335/10000]
train_loss: 2.0603 | train_acc: 0.4121 | val_loss: 2.0749 | val_acc: 0.3939 | test_acc: 0.3955 | Time: 5.7249 s
>>> Epoch [ 2336/10000]
train_loss: 2.0603 | train_acc: 0.4121 | val_loss: 2.0748 | val_acc: 0.3940 | test_acc: 0.3955 | Time: 5.5716 s
>>> Epoch [ 2337/10000]
train_loss: 2.0603 | train_acc: 0.4122 | val_loss: 2.0748 | val_acc: 0.3940 | test_acc: 0.3955 | Time: 5.6795 s
>>> Epoch [ 2338/10000]
train_loss: 2.0603 | train_acc: 0.4122 | val_loss: 2.0748 | val_acc: 0.3940 | test_acc: 0.3955 | Time: 5.7602 s
>>> Epoch [ 2339/10000]
train_loss: 2.0603 | train_acc: 0.4122 | val_loss: 2.0748 | val_acc: 0.3940 | test_acc: 0.3956 | Time: 5.7916 s
>>> Epoch [ 2340/10000]
train_loss: 2.0603 | train_acc: 0.4122 | val_loss: 2.0748 | val_acc: 0.3939 | test_acc: 0.3955 | Time: 5.7767 s
>>> Epoch [ 2341/10000]
train_loss: 2.0603 | train_acc: 0.4122 | val_loss: 2.0748 | val_acc: 0.3939 | test_acc: 0.3955 | Time: 5.7646 s
>>> Epoch [ 2342/10000]
train_loss: 2.0602 | train_acc: 0.4122 | val_loss: 2.0748 | val_acc: 0.3939 | test_acc: 0.3956 | Time: 5.8268 s
>>> Epoch [ 2343/10000]
train_loss: 2.0602 | train_acc: 0.4121 | val_loss: 2.0748 | val_acc: 0.3940 | test_acc: 0.3957 | Time: 5.5696 s
>>> Epoch [ 2344/10000]
train_loss: 2.0602 | train_acc: 0.4122 | val_loss: 2.0748 | val_acc: 0.3940 | test_acc: 0.3957 | Time: 5.6009 s
>>> Epoch [ 2345/10000]
train_loss: 2.0602 | train_acc: 0.4122 | val_loss: 2.0748 | val_acc: 0.3940 | test_acc: 0.3958 | Time: 5.6506 s
>>> Epoch [ 2346/10000]
train_loss: 2.0602 | train_acc: 0.4122 | val_loss: 2.0747 | val_acc: 0.3941 | test_acc: 0.3958 | Time: 5.4255 s
>>> Epoch [ 2347/10000]
train_loss: 2.0602 | train_acc: 0.4122 | val_loss: 2.0747 | val_acc: 0.3941 | test_acc: 0.3958 | Time: 5.6193 s
>>> Epoch [ 2348/10000]
train_loss: 2.0602 | train_acc: 0.4122 | val_loss: 2.0747 | val_acc: 0.3941 | test_acc: 0.3958 | Time: 5.9944 s
>>> Epoch [ 2349/10000]
train_loss: 2.0602 | train_acc: 0.4122 | val_loss: 2.0747 | val_acc: 0.3942 | test_acc: 0.3958 | Time: 5.5461 s
>>> Epoch [ 2350/10000]
train_loss: 2.0601 | train_acc: 0.4122 | val_loss: 2.0747 | val_acc: 0.3942 | test_acc: 0.3958 | Time: 5.5043 s
>>> Epoch [ 2351/10000]
train_loss: 2.0601 | train_acc: 0.4122 | val_loss: 2.0747 | val_acc: 0.3942 | test_acc: 0.3958 | Time: 5.4686 s
>>> Epoch [ 2352/10000]
train_loss: 2.0601 | train_acc: 0.4123 | val_loss: 2.0747 | val_acc: 0.3942 | test_acc: 0.3958 | Time: 5.6409 s
>>> Epoch [ 2353/10000]
train_loss: 2.0601 | train_acc: 0.4123 | val_loss: 2.0747 | val_acc: 0.3942 | test_acc: 0.3959 | Time: 5.7823 s
>>> Epoch [ 2354/10000]
train_loss: 2.0601 | train_acc: 0.4123 | val_loss: 2.0747 | val_acc: 0.3942 | test_acc: 0.3959 | Time: 5.6909 s
>>> Epoch [ 2355/10000]
train_loss: 2.0601 | train_acc: 0.4123 | val_loss: 2.0747 | val_acc: 0.3943 | test_acc: 0.3959 | Time: 5.5371 s
>>> Epoch [ 2356/10000]
train_loss: 2.0601 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3943 | test_acc: 0.3959 | Time: 5.5656 s
>>> Epoch [ 2357/10000]
train_loss: 2.0601 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3944 | test_acc: 0.3958 | Time: 6.2719 s
>>> Epoch [ 2358/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3945 | test_acc: 0.3958 | Time: 8.8176 s
>>> Epoch [ 2359/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3945 | test_acc: 0.3959 | Time: 7.2376 s
>>> Epoch [ 2360/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3946 | test_acc: 0.3959 | Time: 8.8207 s
>>> Epoch [ 2361/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3946 | test_acc: 0.3959 | Time: 8.2201 s
>>> Epoch [ 2362/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3947 | test_acc: 0.3960 | Time: 5.1385 s
>>> Epoch [ 2363/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3947 | test_acc: 0.3960 | Time: 5.4289 s
>>> Epoch [ 2364/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3947 | test_acc: 0.3961 | Time: 5.2169 s
>>> Epoch [ 2365/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3947 | test_acc: 0.3961 | Time: 5.4270 s
>>> Epoch [ 2366/10000]
train_loss: 2.0600 | train_acc: 0.4123 | val_loss: 2.0746 | val_acc: 0.3947 | test_acc: 0.3961 | Time: 5.5114 s
>>> Epoch [ 2367/10000]
train_loss: 2.0599 | train_acc: 0.4123 | val_loss: 2.0745 | val_acc: 0.3948 | test_acc: 0.3961 | Time: 5.5483 s
>>> Epoch [ 2368/10000]
train_loss: 2.0599 | train_acc: 0.4123 | val_loss: 2.0745 | val_acc: 0.3948 | test_acc: 0.3961 | Time: 5.5580 s
>>> Epoch [ 2369/10000]
train_loss: 2.0599 | train_acc: 0.4123 | val_loss: 2.0745 | val_acc: 0.3948 | test_acc: 0.3961 | Time: 5.6185 s
>>> Epoch [ 2370/10000]
train_loss: 2.0599 | train_acc: 0.4123 | val_loss: 2.0745 | val_acc: 0.3948 | test_acc: 0.3961 | Time: 5.8413 s
>>> Epoch [ 2371/10000]
train_loss: 2.0599 | train_acc: 0.4123 | val_loss: 2.0745 | val_acc: 0.3949 | test_acc: 0.3961 | Time: 5.7922 s
>>> Epoch [ 2372/10000]
train_loss: 2.0599 | train_acc: 0.4123 | val_loss: 2.0745 | val_acc: 0.3949 | test_acc: 0.3961 | Time: 6.0200 s
>>> Epoch [ 2373/10000]
train_loss: 2.0599 | train_acc: 0.4124 | val_loss: 2.0745 | val_acc: 0.3950 | test_acc: 0.3961 | Time: 5.4186 s
>>> Epoch [ 2374/10000]
train_loss: 2.0599 | train_acc: 0.4124 | val_loss: 2.0745 | val_acc: 0.3950 | test_acc: 0.3961 | Time: 5.6642 s
>>> Epoch [ 2375/10000]
train_loss: 2.0598 | train_acc: 0.4124 | val_loss: 2.0745 | val_acc: 0.3951 | test_acc: 0.3961 | Time: 5.6489 s
>>> Epoch [ 2376/10000]
train_loss: 2.0598 | train_acc: 0.4125 | val_loss: 2.0745 | val_acc: 0.3951 | test_acc: 0.3961 | Time: 5.8204 s
>>> Epoch [ 2377/10000]
train_loss: 2.0598 | train_acc: 0.4125 | val_loss: 2.0744 | val_acc: 0.3951 | test_acc: 0.3962 | Time: 5.6269 s
>>> Epoch [ 2378/10000]
train_loss: 2.0598 | train_acc: 0.4125 | val_loss: 2.0744 | val_acc: 0.3951 | test_acc: 0.3962 | Time: 5.5175 s
>>> Epoch [ 2379/10000]
train_loss: 2.0598 | train_acc: 0.4126 | val_loss: 2.0744 | val_acc: 0.3951 | test_acc: 0.3962 | Time: 5.7311 s
>>> Epoch [ 2380/10000]
train_loss: 2.0598 | train_acc: 0.4125 | val_loss: 2.0744 | val_acc: 0.3951 | test_acc: 0.3963 | Time: 5.9472 s
>>> Epoch [ 2381/10000]
train_loss: 2.0598 | train_acc: 0.4126 | val_loss: 2.0744 | val_acc: 0.3951 | test_acc: 0.3963 | Time: 5.6762 s
>>> Epoch [ 2382/10000]
train_loss: 2.0598 | train_acc: 0.4125 | val_loss: 2.0744 | val_acc: 0.3951 | test_acc: 0.3964 | Time: 5.9520 s
>>> Epoch [ 2383/10000]
train_loss: 2.0598 | train_acc: 0.4125 | val_loss: 2.0744 | val_acc: 0.3950 | test_acc: 0.3964 | Time: 5.5593 s
>>> Epoch [ 2384/10000]
train_loss: 2.0597 | train_acc: 0.4125 | val_loss: 2.0744 | val_acc: 0.3950 | test_acc: 0.3964 | Time: 5.7897 s
>>> Epoch [ 2385/10000]
train_loss: 2.0597 | train_acc: 0.4125 | val_loss: 2.0744 | val_acc: 0.3950 | test_acc: 0.3964 | Time: 5.8997 s
>>> Epoch [ 2386/10000]
train_loss: 2.0597 | train_acc: 0.4125 | val_loss: 2.0744 | val_acc: 0.3950 | test_acc: 0.3964 | Time: 5.8041 s
>>> Epoch [ 2387/10000]
train_loss: 2.0597 | train_acc: 0.4126 | val_loss: 2.0744 | val_acc: 0.3951 | test_acc: 0.3963 | Time: 5.8605 s
>>> Epoch [ 2388/10000]
train_loss: 2.0597 | train_acc: 0.4126 | val_loss: 2.0743 | val_acc: 0.3951 | test_acc: 0.3963 | Time: 5.9348 s
>>> Epoch [ 2389/10000]
train_loss: 2.0597 | train_acc: 0.4126 | val_loss: 2.0743 | val_acc: 0.3951 | test_acc: 0.3963 | Time: 5.6350 s
>>> Epoch [ 2390/10000]
train_loss: 2.0597 | train_acc: 0.4126 | val_loss: 2.0743 | val_acc: 0.3951 | test_acc: 0.3963 | Time: 5.8283 s
>>> Epoch [ 2391/10000]
train_loss: 2.0597 | train_acc: 0.4127 | val_loss: 2.0743 | val_acc: 0.3951 | test_acc: 0.3962 | Time: 5.6958 s
>>> Epoch [ 2392/10000]
train_loss: 2.0596 | train_acc: 0.4127 | val_loss: 2.0743 | val_acc: 0.3952 | test_acc: 0.3962 | Time: 5.9499 s
>>> Epoch [ 2393/10000]
train_loss: 2.0596 | train_acc: 0.4127 | val_loss: 2.0743 | val_acc: 0.3952 | test_acc: 0.3962 | Time: 5.8294 s
>>> Epoch [ 2394/10000]
train_loss: 2.0596 | train_acc: 0.4127 | val_loss: 2.0743 | val_acc: 0.3952 | test_acc: 0.3962 | Time: 5.7374 s
>>> Epoch [ 2395/10000]
train_loss: 2.0596 | train_acc: 0.4127 | val_loss: 2.0743 | val_acc: 0.3952 | test_acc: 0.3962 | Time: 5.0581 s
>>> Epoch [ 2396/10000]
train_loss: 2.0596 | train_acc: 0.4127 | val_loss: 2.0743 | val_acc: 0.3952 | test_acc: 0.3963 | Time: 4.7966 s
>>> Epoch [ 2397/10000]
train_loss: 2.0596 | train_acc: 0.4127 | val_loss: 2.0743 | val_acc: 0.3953 | test_acc: 0.3963 | Time: 4.6947 s
>>> Epoch [ 2398/10000]
train_loss: 2.0596 | train_acc: 0.4127 | val_loss: 2.0742 | val_acc: 0.3952 | test_acc: 0.3963 | Time: 4.7685 s
>>> Epoch [ 2399/10000]
train_loss: 2.0596 | train_acc: 0.4127 | val_loss: 2.0742 | val_acc: 0.3952 | test_acc: 0.3963 | Time: 5.0304 s
>>> Epoch [ 2400/10000]
train_loss: 2.0595 | train_acc: 0.4127 | val_loss: 2.0742 | val_acc: 0.3952 | test_acc: 0.3963 | Time: 4.7397 s
>>> Epoch [ 2401/10000]
train_loss: 2.0595 | train_acc: 0.4127 | val_loss: 2.0742 | val_acc: 0.3952 | test_acc: 0.3963 | Time: 4.8751 s
>>> Epoch [ 2402/10000]
train_loss: 2.0595 | train_acc: 0.4127 | val_loss: 2.0742 | val_acc: 0.3952 | test_acc: 0.3965 | Time: 4.8458 s
>>> Epoch [ 2403/10000]
train_loss: 2.0595 | train_acc: 0.4127 | val_loss: 2.0742 | val_acc: 0.3952 | test_acc: 0.3966 | Time: 4.8087 s
>>> Epoch [ 2404/10000]
train_loss: 2.0595 | train_acc: 0.4126 | val_loss: 2.0742 | val_acc: 0.3952 | test_acc: 0.3967 | Time: 5.0153 s
>>> Epoch [ 2405/10000]
train_loss: 2.0595 | train_acc: 0.4126 | val_loss: 2.0742 | val_acc: 0.3952 | test_acc: 0.3967 | Time: 4.9189 s
>>> Epoch [ 2406/10000]
train_loss: 2.0595 | train_acc: 0.4127 | val_loss: 2.0742 | val_acc: 0.3953 | test_acc: 0.3968 | Time: 4.7844 s
>>> Epoch [ 2407/10000]
train_loss: 2.0595 | train_acc: 0.4127 | val_loss: 2.0742 | val_acc: 0.3953 | test_acc: 0.3969 | Time: 4.9067 s
>>> Epoch [ 2408/10000]
train_loss: 2.0595 | train_acc: 0.4128 | val_loss: 2.0742 | val_acc: 0.3954 | test_acc: 0.3969 | Time: 4.9423 s
>>> Epoch [ 2409/10000]
train_loss: 2.0594 | train_acc: 0.4128 | val_loss: 2.0741 | val_acc: 0.3955 | test_acc: 0.3970 | Time: 4.7807 s
>>> Epoch [ 2410/10000]
train_loss: 2.0594 | train_acc: 0.4129 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3970 | Time: 4.6367 s
>>> Epoch [ 2411/10000]
train_loss: 2.0594 | train_acc: 0.4128 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3970 | Time: 4.9899 s
>>> Epoch [ 2412/10000]
train_loss: 2.0594 | train_acc: 0.4129 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3969 | Time: 4.9082 s
>>> Epoch [ 2413/10000]
train_loss: 2.0594 | train_acc: 0.4130 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3969 | Time: 4.9727 s
>>> Epoch [ 2414/10000]
train_loss: 2.0594 | train_acc: 0.4130 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3969 | Time: 4.7934 s
>>> Epoch [ 2415/10000]
train_loss: 2.0594 | train_acc: 0.4130 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3970 | Time: 4.9823 s
>>> Epoch [ 2416/10000]
train_loss: 2.0594 | train_acc: 0.4130 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3970 | Time: 4.8867 s
>>> Epoch [ 2417/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3970 | Time: 4.9406 s
>>> Epoch [ 2418/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0741 | val_acc: 0.3956 | test_acc: 0.3969 | Time: 4.7967 s
>>> Epoch [ 2419/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3956 | test_acc: 0.3969 | Time: 5.0564 s
>>> Epoch [ 2420/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 4.8607 s
>>> Epoch [ 2421/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 4.8476 s
>>> Epoch [ 2422/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 4.7474 s
>>> Epoch [ 2423/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 4.8195 s
>>> Epoch [ 2424/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 4.9188 s
>>> Epoch [ 2425/10000]
train_loss: 2.0593 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 4.8321 s
>>> Epoch [ 2426/10000]
train_loss: 2.0592 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 4.8111 s
>>> Epoch [ 2427/10000]
train_loss: 2.0592 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 4.9059 s
>>> Epoch [ 2428/10000]
train_loss: 2.0592 | train_acc: 0.4131 | val_loss: 2.0740 | val_acc: 0.3957 | test_acc: 0.3970 | Time: 9.3623 s
>>> Epoch [ 2429/10000]
train_loss: 2.0592 | train_acc: 0.4132 | val_loss: 2.0740 | val_acc: 0.3957 | test_acc: 0.3970 | Time: 9.5508 s
>>> Epoch [ 2430/10000]
train_loss: 2.0592 | train_acc: 0.4132 | val_loss: 2.0739 | val_acc: 0.3957 | test_acc: 0.3970 | Time: 9.2302 s
>>> Epoch [ 2431/10000]
train_loss: 2.0592 | train_acc: 0.4131 | val_loss: 2.0739 | val_acc: 0.3957 | test_acc: 0.3969 | Time: 9.4652 s
>>> Epoch [ 2432/10000]
train_loss: 2.0592 | train_acc: 0.4131 | val_loss: 2.0739 | val_acc: 0.3956 | test_acc: 0.3969 | Time: 9.1150 s
>>> Epoch [ 2433/10000]
train_loss: 2.0592 | train_acc: 0.4131 | val_loss: 2.0739 | val_acc: 0.3955 | test_acc: 0.3969 | Time: 5.7987 s
>>> Epoch [ 2434/10000]
train_loss: 2.0592 | train_acc: 0.4131 | val_loss: 2.0739 | val_acc: 0.3956 | test_acc: 0.3969 | Time: 5.1882 s
>>> Epoch [ 2435/10000]
train_loss: 2.0591 | train_acc: 0.4132 | val_loss: 2.0739 | val_acc: 0.3956 | test_acc: 0.3969 | Time: 5.6695 s
>>> Epoch [ 2436/10000]
train_loss: 2.0591 | train_acc: 0.4131 | val_loss: 2.0739 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.1806 s
>>> Epoch [ 2437/10000]
train_loss: 2.0591 | train_acc: 0.4132 | val_loss: 2.0739 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 7.7291 s
>>> Epoch [ 2438/10000]
train_loss: 2.0591 | train_acc: 0.4132 | val_loss: 2.0739 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 8.3995 s
>>> Epoch [ 2439/10000]
train_loss: 2.0591 | train_acc: 0.4133 | val_loss: 2.0739 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 9.0501 s
>>> Epoch [ 2440/10000]
train_loss: 2.0591 | train_acc: 0.4133 | val_loss: 2.0739 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.0725 s
>>> Epoch [ 2441/10000]
train_loss: 2.0591 | train_acc: 0.4133 | val_loss: 2.0738 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 5.5453 s
>>> Epoch [ 2442/10000]
train_loss: 2.0591 | train_acc: 0.4133 | val_loss: 2.0738 | val_acc: 0.3959 | test_acc: 0.3969 | Time: 5.9420 s
>>> Epoch [ 2443/10000]
train_loss: 2.0590 | train_acc: 0.4133 | val_loss: 2.0738 | val_acc: 0.3959 | test_acc: 0.3969 | Time: 6.0658 s
>>> Epoch [ 2444/10000]
train_loss: 2.0590 | train_acc: 0.4133 | val_loss: 2.0738 | val_acc: 0.3960 | test_acc: 0.3968 | Time: 5.4928 s
>>> Epoch [ 2445/10000]
train_loss: 2.0590 | train_acc: 0.4133 | val_loss: 2.0738 | val_acc: 0.3960 | test_acc: 0.3968 | Time: 5.8622 s
>>> Epoch [ 2446/10000]
train_loss: 2.0590 | train_acc: 0.4133 | val_loss: 2.0738 | val_acc: 0.3960 | test_acc: 0.3967 | Time: 5.7832 s
>>> Epoch [ 2447/10000]
train_loss: 2.0590 | train_acc: 0.4133 | val_loss: 2.0738 | val_acc: 0.3960 | test_acc: 0.3967 | Time: 6.0474 s
>>> Epoch [ 2448/10000]
train_loss: 2.0590 | train_acc: 0.4133 | val_loss: 2.0738 | val_acc: 0.3961 | test_acc: 0.3966 | Time: 6.1321 s
>>> Epoch [ 2449/10000]
train_loss: 2.0590 | train_acc: 0.4134 | val_loss: 2.0738 | val_acc: 0.3961 | test_acc: 0.3965 | Time: 6.0145 s
>>> Epoch [ 2450/10000]
train_loss: 2.0590 | train_acc: 0.4134 | val_loss: 2.0738 | val_acc: 0.3961 | test_acc: 0.3965 | Time: 5.8022 s
>>> Epoch [ 2451/10000]
train_loss: 2.0590 | train_acc: 0.4134 | val_loss: 2.0738 | val_acc: 0.3961 | test_acc: 0.3965 | Time: 6.0222 s
>>> Epoch [ 2452/10000]
train_loss: 2.0589 | train_acc: 0.4135 | val_loss: 2.0737 | val_acc: 0.3962 | test_acc: 0.3965 | Time: 5.8985 s
>>> Epoch [ 2453/10000]
train_loss: 2.0589 | train_acc: 0.4134 | val_loss: 2.0737 | val_acc: 0.3963 | test_acc: 0.3964 | Time: 5.9434 s
>>> Epoch [ 2454/10000]
train_loss: 2.0589 | train_acc: 0.4134 | val_loss: 2.0737 | val_acc: 0.3963 | test_acc: 0.3964 | Time: 6.1673 s
>>> Epoch [ 2455/10000]
train_loss: 2.0589 | train_acc: 0.4134 | val_loss: 2.0737 | val_acc: 0.3964 | test_acc: 0.3963 | Time: 6.0917 s
>>> Epoch [ 2456/10000]
train_loss: 2.0589 | train_acc: 0.4133 | val_loss: 2.0737 | val_acc: 0.3965 | test_acc: 0.3962 | Time: 6.0551 s
>>> Epoch [ 2457/10000]
train_loss: 2.0589 | train_acc: 0.4133 | val_loss: 2.0737 | val_acc: 0.3965 | test_acc: 0.3962 | Time: 6.0159 s
>>> Epoch [ 2458/10000]
train_loss: 2.0589 | train_acc: 0.4133 | val_loss: 2.0737 | val_acc: 0.3965 | test_acc: 0.3962 | Time: 5.9553 s
>>> Epoch [ 2459/10000]
train_loss: 2.0589 | train_acc: 0.4133 | val_loss: 2.0737 | val_acc: 0.3965 | test_acc: 0.3962 | Time: 5.7455 s
>>> Epoch [ 2460/10000]
train_loss: 2.0588 | train_acc: 0.4134 | val_loss: 2.0737 | val_acc: 0.3965 | test_acc: 0.3962 | Time: 5.9854 s
>>> Epoch [ 2461/10000]
train_loss: 2.0588 | train_acc: 0.4134 | val_loss: 2.0737 | val_acc: 0.3966 | test_acc: 0.3962 | Time: 6.0183 s
>>> Epoch [ 2462/10000]
train_loss: 2.0588 | train_acc: 0.4135 | val_loss: 2.0737 | val_acc: 0.3966 | test_acc: 0.3962 | Time: 5.9489 s
>>> Epoch [ 2463/10000]
train_loss: 2.0588 | train_acc: 0.4135 | val_loss: 2.0736 | val_acc: 0.3966 | test_acc: 0.3962 | Time: 6.1672 s
>>> Epoch [ 2464/10000]
train_loss: 2.0588 | train_acc: 0.4134 | val_loss: 2.0736 | val_acc: 0.3965 | test_acc: 0.3964 | Time: 5.9729 s
>>> Epoch [ 2465/10000]
train_loss: 2.0588 | train_acc: 0.4134 | val_loss: 2.0736 | val_acc: 0.3966 | test_acc: 0.3964 | Time: 6.2300 s
>>> Epoch [ 2466/10000]
train_loss: 2.0588 | train_acc: 0.4134 | val_loss: 2.0736 | val_acc: 0.3966 | test_acc: 0.3964 | Time: 5.8970 s
>>> Epoch [ 2467/10000]
train_loss: 2.0588 | train_acc: 0.4135 | val_loss: 2.0736 | val_acc: 0.3966 | test_acc: 0.3964 | Time: 6.0289 s
>>> Epoch [ 2468/10000]
train_loss: 2.0588 | train_acc: 0.4135 | val_loss: 2.0736 | val_acc: 0.3967 | test_acc: 0.3963 | Time: 5.9243 s
>>> Epoch [ 2469/10000]
train_loss: 2.0587 | train_acc: 0.4136 | val_loss: 2.0736 | val_acc: 0.3967 | test_acc: 0.3962 | Time: 6.0751 s
>>> Epoch [ 2470/10000]
train_loss: 2.0587 | train_acc: 0.4136 | val_loss: 2.0736 | val_acc: 0.3967 | test_acc: 0.3963 | Time: 5.9679 s
>>> Epoch [ 2471/10000]
train_loss: 2.0587 | train_acc: 0.4137 | val_loss: 2.0736 | val_acc: 0.3967 | test_acc: 0.3963 | Time: 6.1374 s
>>> Epoch [ 2472/10000]
train_loss: 2.0587 | train_acc: 0.4137 | val_loss: 2.0736 | val_acc: 0.3967 | test_acc: 0.3963 | Time: 6.1367 s
>>> Epoch [ 2473/10000]
train_loss: 2.0587 | train_acc: 0.4138 | val_loss: 2.0736 | val_acc: 0.3967 | test_acc: 0.3962 | Time: 5.8898 s
>>> Epoch [ 2474/10000]
train_loss: 2.0587 | train_acc: 0.4138 | val_loss: 2.0735 | val_acc: 0.3967 | test_acc: 0.3961 | Time: 9.4129 s
>>> Epoch [ 2475/10000]
train_loss: 2.0587 | train_acc: 0.4138 | val_loss: 2.0735 | val_acc: 0.3967 | test_acc: 0.3961 | Time: 9.2763 s
>>> Epoch [ 2476/10000]
train_loss: 2.0587 | train_acc: 0.4138 | val_loss: 2.0735 | val_acc: 0.3967 | test_acc: 0.3961 | Time: 8.6580 s
>>> Epoch [ 2477/10000]
train_loss: 2.0587 | train_acc: 0.4138 | val_loss: 2.0735 | val_acc: 0.3967 | test_acc: 0.3961 | Time: 8.6521 s
>>> Epoch [ 2478/10000]
train_loss: 2.0586 | train_acc: 0.4138 | val_loss: 2.0735 | val_acc: 0.3967 | test_acc: 0.3962 | Time: 8.7100 s
>>> Epoch [ 2479/10000]
train_loss: 2.0586 | train_acc: 0.4139 | val_loss: 2.0735 | val_acc: 0.3968 | test_acc: 0.3962 | Time: 8.6072 s
>>> Epoch [ 2480/10000]
train_loss: 2.0586 | train_acc: 0.4139 | val_loss: 2.0735 | val_acc: 0.3968 | test_acc: 0.3964 | Time: 8.6761 s
>>> Epoch [ 2481/10000]
train_loss: 2.0586 | train_acc: 0.4139 | val_loss: 2.0735 | val_acc: 0.3968 | test_acc: 0.3964 | Time: 8.6653 s
>>> Epoch [ 2482/10000]
train_loss: 2.0586 | train_acc: 0.4139 | val_loss: 2.0735 | val_acc: 0.3968 | test_acc: 0.3964 | Time: 8.6409 s
>>> Epoch [ 2483/10000]
train_loss: 2.0586 | train_acc: 0.4139 | val_loss: 2.0735 | val_acc: 0.3968 | test_acc: 0.3964 | Time: 8.6177 s
>>> Epoch [ 2484/10000]
train_loss: 2.0586 | train_acc: 0.4139 | val_loss: 2.0735 | val_acc: 0.3968 | test_acc: 0.3965 | Time: 7.9835 s
>>> Epoch [ 2485/10000]
train_loss: 2.0586 | train_acc: 0.4139 | val_loss: 2.0734 | val_acc: 0.3968 | test_acc: 0.3964 | Time: 7.5384 s
>>> Epoch [ 2486/10000]
train_loss: 2.0586 | train_acc: 0.4140 | val_loss: 2.0734 | val_acc: 0.3968 | test_acc: 0.3964 | Time: 7.0134 s
>>> Epoch [ 2487/10000]
train_loss: 2.0585 | train_acc: 0.4141 | val_loss: 2.0734 | val_acc: 0.3968 | test_acc: 0.3964 | Time: 6.9917 s
>>> Epoch [ 2488/10000]
train_loss: 2.0585 | train_acc: 0.4141 | val_loss: 2.0734 | val_acc: 0.3967 | test_acc: 0.3964 | Time: 5.9699 s
>>> Epoch [ 2489/10000]
train_loss: 2.0585 | train_acc: 0.4141 | val_loss: 2.0734 | val_acc: 0.3967 | test_acc: 0.3964 | Time: 5.8597 s
>>> Epoch [ 2490/10000]
train_loss: 2.0585 | train_acc: 0.4141 | val_loss: 2.0734 | val_acc: 0.3967 | test_acc: 0.3964 | Time: 5.8397 s
>>> Epoch [ 2491/10000]
train_loss: 2.0585 | train_acc: 0.4142 | val_loss: 2.0734 | val_acc: 0.3967 | test_acc: 0.3964 | Time: 5.6447 s
>>> Epoch [ 2492/10000]
train_loss: 2.0585 | train_acc: 0.4142 | val_loss: 2.0734 | val_acc: 0.3966 | test_acc: 0.3967 | Time: 8.0267 s
>>> Epoch [ 2493/10000]
train_loss: 2.0585 | train_acc: 0.4142 | val_loss: 2.0734 | val_acc: 0.3965 | test_acc: 0.3969 | Time: 9.1676 s
>>> Epoch [ 2494/10000]
train_loss: 2.0585 | train_acc: 0.4142 | val_loss: 2.0734 | val_acc: 0.3965 | test_acc: 0.3969 | Time: 7.7284 s
>>> Epoch [ 2495/10000]
train_loss: 2.0585 | train_acc: 0.4142 | val_loss: 2.0734 | val_acc: 0.3965 | test_acc: 0.3969 | Time: 7.1584 s
>>> Epoch [ 2496/10000]
train_loss: 2.0584 | train_acc: 0.4142 | val_loss: 2.0733 | val_acc: 0.3965 | test_acc: 0.3968 | Time: 7.1617 s
>>> Epoch [ 2497/10000]
train_loss: 2.0584 | train_acc: 0.4143 | val_loss: 2.0733 | val_acc: 0.3965 | test_acc: 0.3968 | Time: 7.1344 s
>>> Epoch [ 2498/10000]
train_loss: 2.0584 | train_acc: 0.4143 | val_loss: 2.0733 | val_acc: 0.3965 | test_acc: 0.3968 | Time: 7.0876 s
>>> Epoch [ 2499/10000]
train_loss: 2.0584 | train_acc: 0.4143 | val_loss: 2.0733 | val_acc: 0.3964 | test_acc: 0.3969 | Time: 7.2256 s
>>> Epoch [ 2500/10000]
train_loss: 2.0584 | train_acc: 0.4144 | val_loss: 2.0733 | val_acc: 0.3964 | test_acc: 0.3969 | Time: 7.0116 s
>>> Epoch [ 2501/10000]
train_loss: 2.0584 | train_acc: 0.4143 | val_loss: 2.0733 | val_acc: 0.3964 | test_acc: 0.3969 | Time: 7.0543 s
>>> Epoch [ 2502/10000]
train_loss: 2.0584 | train_acc: 0.4144 | val_loss: 2.0733 | val_acc: 0.3964 | test_acc: 0.3969 | Time: 7.1799 s
>>> Epoch [ 2503/10000]
train_loss: 2.0584 | train_acc: 0.4143 | val_loss: 2.0733 | val_acc: 0.3965 | test_acc: 0.3969 | Time: 7.0387 s
>>> Epoch [ 2504/10000]
train_loss: 2.0583 | train_acc: 0.4144 | val_loss: 2.0733 | val_acc: 0.3965 | test_acc: 0.3968 | Time: 7.0719 s
>>> Epoch [ 2505/10000]
train_loss: 2.0583 | train_acc: 0.4144 | val_loss: 2.0733 | val_acc: 0.3965 | test_acc: 0.3968 | Time: 6.5194 s
>>> Epoch [ 2506/10000]
train_loss: 2.0583 | train_acc: 0.4144 | val_loss: 2.0733 | val_acc: 0.3965 | test_acc: 0.3968 | Time: 5.9447 s
>>> Epoch [ 2507/10000]
train_loss: 2.0583 | train_acc: 0.4145 | val_loss: 2.0732 | val_acc: 0.3965 | test_acc: 0.3968 | Time: 5.6418 s
>>> Epoch [ 2508/10000]
train_loss: 2.0583 | train_acc: 0.4145 | val_loss: 2.0732 | val_acc: 0.3964 | test_acc: 0.3968 | Time: 5.4208 s
>>> Epoch [ 2509/10000]
train_loss: 2.0583 | train_acc: 0.4145 | val_loss: 2.0732 | val_acc: 0.3964 | test_acc: 0.3968 | Time: 5.8127 s
>>> Epoch [ 2510/10000]
train_loss: 2.0583 | train_acc: 0.4146 | val_loss: 2.0732 | val_acc: 0.3962 | test_acc: 0.3968 | Time: 6.0938 s
>>> Epoch [ 2511/10000]
train_loss: 2.0583 | train_acc: 0.4146 | val_loss: 2.0732 | val_acc: 0.3962 | test_acc: 0.3968 | Time: 5.6786 s
>>> Epoch [ 2512/10000]
train_loss: 2.0583 | train_acc: 0.4146 | val_loss: 2.0732 | val_acc: 0.3963 | test_acc: 0.3967 | Time: 5.7585 s
>>> Epoch [ 2513/10000]
train_loss: 2.0582 | train_acc: 0.4146 | val_loss: 2.0732 | val_acc: 0.3963 | test_acc: 0.3967 | Time: 5.9593 s
>>> Epoch [ 2514/10000]
train_loss: 2.0582 | train_acc: 0.4147 | val_loss: 2.0732 | val_acc: 0.3963 | test_acc: 0.3967 | Time: 5.7523 s
>>> Epoch [ 2515/10000]
train_loss: 2.0582 | train_acc: 0.4147 | val_loss: 2.0732 | val_acc: 0.3963 | test_acc: 0.3967 | Time: 5.8418 s
>>> Epoch [ 2516/10000]
train_loss: 2.0582 | train_acc: 0.4147 | val_loss: 2.0732 | val_acc: 0.3963 | test_acc: 0.3967 | Time: 5.9784 s
>>> Epoch [ 2517/10000]
train_loss: 2.0582 | train_acc: 0.4147 | val_loss: 2.0732 | val_acc: 0.3963 | test_acc: 0.3968 | Time: 5.8413 s
>>> Epoch [ 2518/10000]
train_loss: 2.0582 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3961 | test_acc: 0.3968 | Time: 6.1308 s
>>> Epoch [ 2519/10000]
train_loss: 2.0582 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3962 | test_acc: 0.3967 | Time: 6.3691 s
>>> Epoch [ 2520/10000]
train_loss: 2.0582 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3962 | test_acc: 0.3968 | Time: 6.1239 s
>>> Epoch [ 2521/10000]
train_loss: 2.0582 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3963 | test_acc: 0.3968 | Time: 6.3387 s
>>> Epoch [ 2522/10000]
train_loss: 2.0581 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3964 | test_acc: 0.3967 | Time: 6.0407 s
>>> Epoch [ 2523/10000]
train_loss: 2.0581 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3964 | test_acc: 0.3967 | Time: 5.9942 s
>>> Epoch [ 2524/10000]
train_loss: 2.0581 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3965 | test_acc: 0.3967 | Time: 6.4436 s
>>> Epoch [ 2525/10000]
train_loss: 2.0581 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3965 | test_acc: 0.3967 | Time: 6.2334 s
>>> Epoch [ 2526/10000]
train_loss: 2.0581 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3965 | test_acc: 0.3967 | Time: 6.3076 s
>>> Epoch [ 2527/10000]
train_loss: 2.0581 | train_acc: 0.4149 | val_loss: 2.0731 | val_acc: 0.3966 | test_acc: 0.3967 | Time: 6.1857 s
>>> Epoch [ 2528/10000]
train_loss: 2.0581 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3966 | test_acc: 0.3967 | Time: 6.1139 s
>>> Epoch [ 2529/10000]
train_loss: 2.0581 | train_acc: 0.4148 | val_loss: 2.0731 | val_acc: 0.3966 | test_acc: 0.3967 | Time: 6.0120 s
>>> Epoch [ 2530/10000]
train_loss: 2.0581 | train_acc: 0.4148 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3967 | Time: 6.0562 s
>>> Epoch [ 2531/10000]
train_loss: 2.0580 | train_acc: 0.4148 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3969 | Time: 6.2037 s
>>> Epoch [ 2532/10000]
train_loss: 2.0580 | train_acc: 0.4149 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3969 | Time: 5.9054 s
>>> Epoch [ 2533/10000]
train_loss: 2.0580 | train_acc: 0.4149 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3969 | Time: 6.0803 s
>>> Epoch [ 2534/10000]
train_loss: 2.0580 | train_acc: 0.4150 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3970 | Time: 6.0190 s
>>> Epoch [ 2535/10000]
train_loss: 2.0580 | train_acc: 0.4150 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3970 | Time: 6.0175 s
>>> Epoch [ 2536/10000]
train_loss: 2.0580 | train_acc: 0.4150 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3970 | Time: 5.9723 s
>>> Epoch [ 2537/10000]
train_loss: 2.0580 | train_acc: 0.4150 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3970 | Time: 6.0252 s
>>> Epoch [ 2538/10000]
train_loss: 2.0580 | train_acc: 0.4150 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3970 | Time: 6.2675 s
>>> Epoch [ 2539/10000]
train_loss: 2.0580 | train_acc: 0.4150 | val_loss: 2.0730 | val_acc: 0.3966 | test_acc: 0.3970 | Time: 5.9633 s
>>> Epoch [ 2540/10000]
train_loss: 2.0579 | train_acc: 0.4151 | val_loss: 2.0730 | val_acc: 0.3965 | test_acc: 0.3970 | Time: 6.0932 s
>>> Epoch [ 2541/10000]
train_loss: 2.0579 | train_acc: 0.4151 | val_loss: 2.0729 | val_acc: 0.3966 | test_acc: 0.3970 | Time: 6.1964 s
>>> Epoch [ 2542/10000]
train_loss: 2.0579 | train_acc: 0.4151 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3971 | Time: 6.2792 s
>>> Epoch [ 2543/10000]
train_loss: 2.0579 | train_acc: 0.4151 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3972 | Time: 6.0353 s
>>> Epoch [ 2544/10000]
train_loss: 2.0579 | train_acc: 0.4151 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3971 | Time: 6.2088 s
>>> Epoch [ 2545/10000]
train_loss: 2.0579 | train_acc: 0.4151 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3972 | Time: 6.2940 s
>>> Epoch [ 2546/10000]
train_loss: 2.0579 | train_acc: 0.4150 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3972 | Time: 7.0992 s
>>> Epoch [ 2547/10000]
train_loss: 2.0579 | train_acc: 0.4150 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3972 | Time: 9.2531 s
>>> Epoch [ 2548/10000]
train_loss: 2.0579 | train_acc: 0.4150 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3972 | Time: 6.8174 s
>>> Epoch [ 2549/10000]
train_loss: 2.0578 | train_acc: 0.4150 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3972 | Time: 5.4436 s
>>> Epoch [ 2550/10000]
train_loss: 2.0578 | train_acc: 0.4150 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3972 | Time: 5.5024 s
>>> Epoch [ 2551/10000]
train_loss: 2.0578 | train_acc: 0.4150 | val_loss: 2.0729 | val_acc: 0.3967 | test_acc: 0.3972 | Time: 5.6425 s
>>> Epoch [ 2552/10000]
train_loss: 2.0578 | train_acc: 0.4150 | val_loss: 2.0729 | val_acc: 0.3966 | test_acc: 0.3972 | Time: 5.8627 s
>>> Epoch [ 2553/10000]
train_loss: 2.0578 | train_acc: 0.4150 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3972 | Time: 9.7858 s
>>> Epoch [ 2554/10000]
train_loss: 2.0578 | train_acc: 0.4150 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 9.5327 s
>>> Epoch [ 2555/10000]
train_loss: 2.0578 | train_acc: 0.4150 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3971 | Time: 5.4300 s
>>> Epoch [ 2556/10000]
train_loss: 2.0578 | train_acc: 0.4151 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.5315 s
>>> Epoch [ 2557/10000]
train_loss: 2.0578 | train_acc: 0.4152 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.6726 s
>>> Epoch [ 2558/10000]
train_loss: 2.0577 | train_acc: 0.4152 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.6515 s
>>> Epoch [ 2559/10000]
train_loss: 2.0577 | train_acc: 0.4151 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.5369 s
>>> Epoch [ 2560/10000]
train_loss: 2.0577 | train_acc: 0.4151 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.5278 s
>>> Epoch [ 2561/10000]
train_loss: 2.0577 | train_acc: 0.4152 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.5043 s
>>> Epoch [ 2562/10000]
train_loss: 2.0577 | train_acc: 0.4152 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.5926 s
>>> Epoch [ 2563/10000]
train_loss: 2.0577 | train_acc: 0.4152 | val_loss: 2.0728 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.4934 s
>>> Epoch [ 2564/10000]
train_loss: 2.0577 | train_acc: 0.4152 | val_loss: 2.0727 | val_acc: 0.3965 | test_acc: 0.3971 | Time: 5.5347 s
>>> Epoch [ 2565/10000]
train_loss: 2.0577 | train_acc: 0.4152 | val_loss: 2.0727 | val_acc: 0.3965 | test_acc: 0.3970 | Time: 5.6952 s
>>> Epoch [ 2566/10000]
train_loss: 2.0577 | train_acc: 0.4152 | val_loss: 2.0727 | val_acc: 0.3965 | test_acc: 0.3970 | Time: 5.5704 s
>>> Epoch [ 2567/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3965 | test_acc: 0.3970 | Time: 5.4629 s
>>> Epoch [ 2568/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3964 | test_acc: 0.3970 | Time: 5.9647 s
>>> Epoch [ 2569/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3964 | test_acc: 0.3968 | Time: 5.9443 s
>>> Epoch [ 2570/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3964 | test_acc: 0.3969 | Time: 5.9499 s
>>> Epoch [ 2571/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3964 | test_acc: 0.3969 | Time: 5.9761 s
>>> Epoch [ 2572/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3964 | test_acc: 0.3969 | Time: 5.8330 s
>>> Epoch [ 2573/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3963 | test_acc: 0.3969 | Time: 5.7664 s
>>> Epoch [ 2574/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3963 | test_acc: 0.3970 | Time: 6.4048 s
>>> Epoch [ 2575/10000]
train_loss: 2.0576 | train_acc: 0.4153 | val_loss: 2.0727 | val_acc: 0.3963 | test_acc: 0.3969 | Time: 6.2184 s
>>> Epoch [ 2576/10000]
train_loss: 2.0575 | train_acc: 0.4153 | val_loss: 2.0726 | val_acc: 0.3962 | test_acc: 0.3969 | Time: 6.1525 s
>>> Epoch [ 2577/10000]
train_loss: 2.0575 | train_acc: 0.4153 | val_loss: 2.0726 | val_acc: 0.3962 | test_acc: 0.3967 | Time: 6.1733 s
>>> Epoch [ 2578/10000]
train_loss: 2.0575 | train_acc: 0.4154 | val_loss: 2.0726 | val_acc: 0.3961 | test_acc: 0.3968 | Time: 6.3146 s
>>> Epoch [ 2579/10000]
train_loss: 2.0575 | train_acc: 0.4154 | val_loss: 2.0726 | val_acc: 0.3961 | test_acc: 0.3969 | Time: 6.3125 s
>>> Epoch [ 2580/10000]
train_loss: 2.0575 | train_acc: 0.4155 | val_loss: 2.0726 | val_acc: 0.3961 | test_acc: 0.3969 | Time: 6.2354 s
>>> Epoch [ 2581/10000]
train_loss: 2.0575 | train_acc: 0.4155 | val_loss: 2.0726 | val_acc: 0.3961 | test_acc: 0.3970 | Time: 6.2966 s
>>> Epoch [ 2582/10000]
train_loss: 2.0575 | train_acc: 0.4155 | val_loss: 2.0726 | val_acc: 0.3961 | test_acc: 0.3970 | Time: 6.3111 s
>>> Epoch [ 2583/10000]
train_loss: 2.0575 | train_acc: 0.4155 | val_loss: 2.0726 | val_acc: 0.3962 | test_acc: 0.3970 | Time: 6.4433 s
>>> Epoch [ 2584/10000]
train_loss: 2.0575 | train_acc: 0.4155 | val_loss: 2.0726 | val_acc: 0.3961 | test_acc: 0.3971 | Time: 6.0618 s
>>> Epoch [ 2585/10000]
train_loss: 2.0575 | train_acc: 0.4155 | val_loss: 2.0726 | val_acc: 0.3960 | test_acc: 0.3971 | Time: 6.4054 s
>>> Epoch [ 2586/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0726 | val_acc: 0.3960 | test_acc: 0.3972 | Time: 6.3745 s
>>> Epoch [ 2587/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0726 | val_acc: 0.3960 | test_acc: 0.3972 | Time: 6.3410 s
>>> Epoch [ 2588/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3960 | test_acc: 0.3971 | Time: 6.2294 s
>>> Epoch [ 2589/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3960 | test_acc: 0.3971 | Time: 6.4622 s
>>> Epoch [ 2590/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3960 | test_acc: 0.3971 | Time: 6.2320 s
>>> Epoch [ 2591/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3960 | test_acc: 0.3972 | Time: 6.3669 s
>>> Epoch [ 2592/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3960 | test_acc: 0.3972 | Time: 6.1791 s
>>> Epoch [ 2593/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3960 | test_acc: 0.3972 | Time: 6.0555 s
>>> Epoch [ 2594/10000]
train_loss: 2.0574 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3960 | test_acc: 0.3973 | Time: 6.2665 s
>>> Epoch [ 2595/10000]
train_loss: 2.0573 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3960 | test_acc: 0.3972 | Time: 6.4543 s
>>> Epoch [ 2596/10000]
train_loss: 2.0573 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.3225 s
>>> Epoch [ 2597/10000]
train_loss: 2.0573 | train_acc: 0.4155 | val_loss: 2.0725 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.0118 s
>>> Epoch [ 2598/10000]
train_loss: 2.0573 | train_acc: 0.4156 | val_loss: 2.0725 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.2454 s
>>> Epoch [ 2599/10000]
train_loss: 2.0573 | train_acc: 0.4156 | val_loss: 2.0724 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.1745 s
>>> Epoch [ 2600/10000]
train_loss: 2.0573 | train_acc: 0.4156 | val_loss: 2.0724 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 6.4449 s
>>> Epoch [ 2601/10000]
train_loss: 2.0573 | train_acc: 0.4157 | val_loss: 2.0724 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 6.3828 s
>>> Epoch [ 2602/10000]
train_loss: 2.0573 | train_acc: 0.4157 | val_loss: 2.0724 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 9.9683 s
>>> Epoch [ 2603/10000]
train_loss: 2.0573 | train_acc: 0.4157 | val_loss: 2.0724 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 9.4131 s
>>> Epoch [ 2604/10000]
train_loss: 2.0572 | train_acc: 0.4157 | val_loss: 2.0724 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 9.7897 s
>>> Epoch [ 2605/10000]
train_loss: 2.0572 | train_acc: 0.4157 | val_loss: 2.0724 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 9.1879 s
>>> Epoch [ 2606/10000]
train_loss: 2.0572 | train_acc: 0.4157 | val_loss: 2.0724 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 5.7722 s
>>> Epoch [ 2607/10000]
train_loss: 2.0572 | train_acc: 0.4158 | val_loss: 2.0724 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.1406 s
>>> Epoch [ 2608/10000]
train_loss: 2.0572 | train_acc: 0.4158 | val_loss: 2.0724 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.1503 s
>>> Epoch [ 2609/10000]
train_loss: 2.0572 | train_acc: 0.4158 | val_loss: 2.0724 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.1277 s
>>> Epoch [ 2610/10000]
train_loss: 2.0572 | train_acc: 0.4158 | val_loss: 2.0724 | val_acc: 0.3959 | test_acc: 0.3969 | Time: 6.0599 s
>>> Epoch [ 2611/10000]
train_loss: 2.0572 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 6.4073 s
>>> Epoch [ 2612/10000]
train_loss: 2.0572 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 6.5304 s
>>> Epoch [ 2613/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3958 | test_acc: 0.3971 | Time: 6.3821 s
>>> Epoch [ 2614/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3958 | test_acc: 0.3971 | Time: 6.2053 s
>>> Epoch [ 2615/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3958 | test_acc: 0.3972 | Time: 6.3608 s
>>> Epoch [ 2616/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3959 | test_acc: 0.3972 | Time: 6.2148 s
>>> Epoch [ 2617/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3959 | test_acc: 0.3972 | Time: 6.5710 s
>>> Epoch [ 2618/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3959 | test_acc: 0.3972 | Time: 6.2283 s
>>> Epoch [ 2619/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3959 | test_acc: 0.3972 | Time: 6.4752 s
>>> Epoch [ 2620/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3959 | test_acc: 0.3972 | Time: 6.3007 s
>>> Epoch [ 2621/10000]
train_loss: 2.0571 | train_acc: 0.4159 | val_loss: 2.0723 | val_acc: 0.3959 | test_acc: 0.3972 | Time: 6.2310 s
>>> Epoch [ 2622/10000]
train_loss: 2.0571 | train_acc: 0.4160 | val_loss: 2.0723 | val_acc: 0.3959 | test_acc: 0.3972 | Time: 6.3029 s
>>> Epoch [ 2623/10000]
train_loss: 2.0570 | train_acc: 0.4160 | val_loss: 2.0722 | val_acc: 0.3959 | test_acc: 0.3972 | Time: 6.2821 s
>>> Epoch [ 2624/10000]
train_loss: 2.0570 | train_acc: 0.4160 | val_loss: 2.0722 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.4654 s
>>> Epoch [ 2625/10000]
train_loss: 2.0570 | train_acc: 0.4160 | val_loss: 2.0722 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.4797 s
>>> Epoch [ 2626/10000]
train_loss: 2.0570 | train_acc: 0.4161 | val_loss: 2.0722 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.2283 s
>>> Epoch [ 2627/10000]
train_loss: 2.0570 | train_acc: 0.4161 | val_loss: 2.0722 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.1058 s
>>> Epoch [ 2628/10000]
train_loss: 2.0570 | train_acc: 0.4161 | val_loss: 2.0722 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 6.3596 s
>>> Epoch [ 2629/10000]
train_loss: 2.0570 | train_acc: 0.4161 | val_loss: 2.0722 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 6.5752 s
>>> Epoch [ 2630/10000]
train_loss: 2.0570 | train_acc: 0.4161 | val_loss: 2.0722 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 6.3648 s
>>> Epoch [ 2631/10000]
train_loss: 2.0570 | train_acc: 0.4162 | val_loss: 2.0722 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 6.4661 s
>>> Epoch [ 2632/10000]
train_loss: 2.0569 | train_acc: 0.4161 | val_loss: 2.0722 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 6.5607 s
>>> Epoch [ 2633/10000]
train_loss: 2.0569 | train_acc: 0.4162 | val_loss: 2.0722 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.3381 s
>>> Epoch [ 2634/10000]
train_loss: 2.0569 | train_acc: 0.4162 | val_loss: 2.0722 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.1775 s
>>> Epoch [ 2635/10000]
train_loss: 2.0569 | train_acc: 0.4162 | val_loss: 2.0721 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.4473 s
>>> Epoch [ 2636/10000]
train_loss: 2.0569 | train_acc: 0.4163 | val_loss: 2.0721 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.1474 s
>>> Epoch [ 2637/10000]
train_loss: 2.0569 | train_acc: 0.4163 | val_loss: 2.0721 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 6.0077 s
>>> Epoch [ 2638/10000]
train_loss: 2.0569 | train_acc: 0.4163 | val_loss: 2.0721 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 5.1543 s
>>> Epoch [ 2639/10000]
train_loss: 2.0569 | train_acc: 0.4163 | val_loss: 2.0721 | val_acc: 0.3958 | test_acc: 0.3970 | Time: 9.1164 s
>>> Epoch [ 2640/10000]
train_loss: 2.0569 | train_acc: 0.4163 | val_loss: 2.0721 | val_acc: 0.3958 | test_acc: 0.3969 | Time: 8.8852 s
>>> Epoch [ 2641/10000]
train_loss: 2.0568 | train_acc: 0.4163 | val_loss: 2.0721 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 8.9769 s
>>> Epoch [ 2642/10000]
train_loss: 2.0568 | train_acc: 0.4163 | val_loss: 2.0721 | val_acc: 0.3959 | test_acc: 0.3969 | Time: 5.8994 s
>>> Epoch [ 2643/10000]
train_loss: 2.0568 | train_acc: 0.4164 | val_loss: 2.0721 | val_acc: 0.3959 | test_acc: 0.3969 | Time: 5.6905 s
>>> Epoch [ 2644/10000]
train_loss: 2.0568 | train_acc: 0.4164 | val_loss: 2.0721 | val_acc: 0.3959 | test_acc: 0.3969 | Time: 5.7557 s
>>> Epoch [ 2645/10000]
train_loss: 2.0568 | train_acc: 0.4165 | val_loss: 2.0721 | val_acc: 0.3959 | test_acc: 0.3969 | Time: 5.7895 s
>>> Epoch [ 2646/10000]
train_loss: 2.0568 | train_acc: 0.4165 | val_loss: 2.0721 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 5.8804 s
>>> Epoch [ 2647/10000]
train_loss: 2.0568 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3959 | test_acc: 0.3969 | Time: 5.9655 s
>>> Epoch [ 2648/10000]
train_loss: 2.0568 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 6.5351 s
>>> Epoch [ 2649/10000]
train_loss: 2.0568 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3959 | test_acc: 0.3970 | Time: 5.9395 s
>>> Epoch [ 2650/10000]
train_loss: 2.0568 | train_acc: 0.4164 | val_loss: 2.0720 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.3887 s
>>> Epoch [ 2651/10000]
train_loss: 2.0567 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.4791 s
>>> Epoch [ 2652/10000]
train_loss: 2.0567 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3959 | test_acc: 0.3971 | Time: 6.1569 s
>>> Epoch [ 2653/10000]
train_loss: 2.0567 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3958 | test_acc: 0.3971 | Time: 6.4836 s
>>> Epoch [ 2654/10000]
train_loss: 2.0567 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3958 | test_acc: 0.3972 | Time: 6.1648 s
>>> Epoch [ 2655/10000]
train_loss: 2.0567 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3958 | test_acc: 0.3972 | Time: 6.0796 s
>>> Epoch [ 2656/10000]
train_loss: 2.0567 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3958 | test_acc: 0.3973 | Time: 6.2075 s
>>> Epoch [ 2657/10000]
train_loss: 2.0567 | train_acc: 0.4166 | val_loss: 2.0720 | val_acc: 0.3958 | test_acc: 0.3974 | Time: 6.0820 s
>>> Epoch [ 2658/10000]
train_loss: 2.0567 | train_acc: 0.4165 | val_loss: 2.0720 | val_acc: 0.3959 | test_acc: 0.3974 | Time: 6.1021 s
>>> Epoch [ 2659/10000]
train_loss: 2.0567 | train_acc: 0.4166 | val_loss: 2.0720 | val_acc: 0.3959 | test_acc: 0.3974 | Time: 6.2830 s
>>> Epoch [ 2660/10000]
train_loss: 2.0566 | train_acc: 0.4166 | val_loss: 2.0719 | val_acc: 0.3959 | test_acc: 0.3974 | Time: 6.4571 s
>>> Epoch [ 2661/10000]
train_loss: 2.0566 | train_acc: 0.4166 | val_loss: 2.0719 | val_acc: 0.3959 | test_acc: 0.3975 | Time: 6.2662 s
>>> Epoch [ 2662/10000]
train_loss: 2.0566 | train_acc: 0.4166 | val_loss: 2.0719 | val_acc: 0.3960 | test_acc: 0.3975 | Time: 6.1995 s
>>> Epoch [ 2663/10000]
train_loss: 2.0566 | train_acc: 0.4167 | val_loss: 2.0719 | val_acc: 0.3960 | test_acc: 0.3975 | Time: 6.1201 s
>>> Epoch [ 2664/10000]
train_loss: 2.0566 | train_acc: 0.4167 | val_loss: 2.0719 | val_acc: 0.3960 | test_acc: 0.3973 | Time: 6.1015 s
>>> Epoch [ 2665/10000]
train_loss: 2.0566 | train_acc: 0.4167 | val_loss: 2.0719 | val_acc: 0.3960 | test_acc: 0.3973 | Time: 6.1475 s
>>> Epoch [ 2666/10000]
train_loss: 2.0566 | train_acc: 0.4167 | val_loss: 2.0719 | val_acc: 0.3960 | test_acc: 0.3973 | Time: 6.1726 s
>>> Epoch [ 2667/10000]
train_loss: 2.0566 | train_acc: 0.4168 | val_loss: 2.0719 | val_acc: 0.3960 | test_acc: 0.3973 | Time: 6.4901 s
>>> Epoch [ 2668/10000]
train_loss: 2.0566 | train_acc: 0.4167 | val_loss: 2.0719 | val_acc: 0.3960 | test_acc: 0.3973 | Time: 6.1301 s
>>> Epoch [ 2669/10000]
train_loss: 2.0566 | train_acc: 0.4167 | val_loss: 2.0719 | val_acc: 0.3961 | test_acc: 0.3973 | Time: 6.4434 s
>>> Epoch [ 2670/10000]
train_loss: 2.0565 | train_acc: 0.4167 | val_loss: 2.0719 | val_acc: 0.3961 | test_acc: 0.3973 | Time: 6.1395 s
>>> Epoch [ 2671/10000]
train_loss: 2.0565 | train_acc: 0.4167 | val_loss: 2.0719 | val_acc: 0.3961 | test_acc: 0.3973 | Time: 6.5475 s
>>> Epoch [ 2672/10000]
train_loss: 2.0565 | train_acc: 0.4167 | val_loss: 2.0718 | val_acc: 0.3961 | test_acc: 0.3974 | Time: 5.8890 s
>>> Epoch [ 2673/10000]
train_loss: 2.0565 | train_acc: 0.4167 | val_loss: 2.0718 | val_acc: 0.3961 | test_acc: 0.3974 | Time: 9.6287 s
>>> Epoch [ 2674/10000]
train_loss: 2.0565 | train_acc: 0.4167 | val_loss: 2.0718 | val_acc: 0.3961 | test_acc: 0.3974 | Time: 8.8927 s
>>> Epoch [ 2675/10000]
train_loss: 2.0565 | train_acc: 0.4168 | val_loss: 2.0718 | val_acc: 0.3962 | test_acc: 0.3974 | Time: 9.6130 s
>>> Epoch [ 2676/10000]
train_loss: 2.0565 | train_acc: 0.4168 | val_loss: 2.0718 | val_acc: 0.3963 | test_acc: 0.3974 | Time: 8.8333 s
>>> Epoch [ 2677/10000]
train_loss: 2.0565 | train_acc: 0.4168 | val_loss: 2.0718 | val_acc: 0.3964 | test_acc: 0.3974 | Time: 5.5790 s
>>> Epoch [ 2678/10000]
train_loss: 2.0565 | train_acc: 0.4169 | val_loss: 2.0718 | val_acc: 0.3964 | test_acc: 0.3974 | Time: 6.0090 s
>>> Epoch [ 2679/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0718 | val_acc: 0.3963 | test_acc: 0.3975 | Time: 5.7818 s
>>> Epoch [ 2680/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0718 | val_acc: 0.3962 | test_acc: 0.3975 | Time: 6.2241 s
>>> Epoch [ 2681/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0718 | val_acc: 0.3962 | test_acc: 0.3975 | Time: 6.1551 s
>>> Epoch [ 2682/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0718 | val_acc: 0.3962 | test_acc: 0.3976 | Time: 6.3625 s
>>> Epoch [ 2683/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0718 | val_acc: 0.3963 | test_acc: 0.3976 | Time: 6.1245 s
>>> Epoch [ 2684/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3964 | test_acc: 0.3976 | Time: 6.2102 s
>>> Epoch [ 2685/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3964 | test_acc: 0.3977 | Time: 6.1447 s
>>> Epoch [ 2686/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3964 | test_acc: 0.3977 | Time: 6.4693 s
>>> Epoch [ 2687/10000]
train_loss: 2.0564 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3964 | test_acc: 0.3977 | Time: 6.3045 s
>>> Epoch [ 2688/10000]
train_loss: 2.0564 | train_acc: 0.4168 | val_loss: 2.0717 | val_acc: 0.3964 | test_acc: 0.3977 | Time: 6.2752 s
>>> Epoch [ 2689/10000]
train_loss: 2.0563 | train_acc: 0.4168 | val_loss: 2.0717 | val_acc: 0.3965 | test_acc: 0.3976 | Time: 6.1393 s
>>> Epoch [ 2690/10000]
train_loss: 2.0563 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3965 | test_acc: 0.3976 | Time: 6.1825 s
>>> Epoch [ 2691/10000]
train_loss: 2.0563 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3965 | test_acc: 0.3976 | Time: 6.1674 s
>>> Epoch [ 2692/10000]
train_loss: 2.0563 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3965 | test_acc: 0.3976 | Time: 6.3170 s
>>> Epoch [ 2693/10000]
train_loss: 2.0563 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3965 | test_acc: 0.3976 | Time: 6.4898 s
>>> Epoch [ 2694/10000]
train_loss: 2.0563 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3965 | test_acc: 0.3976 | Time: 6.2606 s
>>> Epoch [ 2695/10000]
train_loss: 2.0563 | train_acc: 0.4169 | val_loss: 2.0717 | val_acc: 0.3966 | test_acc: 0.3976 | Time: 6.1970 s
>>> Epoch [ 2696/10000]
train_loss: 2.0563 | train_acc: 0.4170 | val_loss: 2.0717 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 6.3238 s
>>> Epoch [ 2697/10000]
train_loss: 2.0563 | train_acc: 0.4170 | val_loss: 2.0716 | val_acc: 0.3968 | test_acc: 0.3976 | Time: 6.4035 s
>>> Epoch [ 2698/10000]
train_loss: 2.0562 | train_acc: 0.4170 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 6.2272 s
>>> Epoch [ 2699/10000]
train_loss: 2.0562 | train_acc: 0.4170 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 6.3922 s
>>> Epoch [ 2700/10000]
train_loss: 2.0562 | train_acc: 0.4170 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 6.1168 s
>>> Epoch [ 2701/10000]
train_loss: 2.0562 | train_acc: 0.4170 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 6.5302 s
>>> Epoch [ 2702/10000]
train_loss: 2.0562 | train_acc: 0.4170 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 6.3222 s
>>> Epoch [ 2703/10000]
train_loss: 2.0562 | train_acc: 0.4171 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3977 | Time: 6.3775 s
>>> Epoch [ 2704/10000]
train_loss: 2.0562 | train_acc: 0.4171 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3977 | Time: 6.4818 s
>>> Epoch [ 2705/10000]
train_loss: 2.0562 | train_acc: 0.4171 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 5.4358 s
>>> Epoch [ 2706/10000]
train_loss: 2.0562 | train_acc: 0.4171 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 5.5135 s
>>> Epoch [ 2707/10000]
train_loss: 2.0562 | train_acc: 0.4171 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 6.0721 s
>>> Epoch [ 2708/10000]
train_loss: 2.0561 | train_acc: 0.4171 | val_loss: 2.0716 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 6.4636 s
>>> Epoch [ 2709/10000]
train_loss: 2.0561 | train_acc: 0.4172 | val_loss: 2.0715 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 9.1617 s
>>> Epoch [ 2710/10000]
train_loss: 2.0561 | train_acc: 0.4172 | val_loss: 2.0715 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 6.6841 s
>>> Epoch [ 2711/10000]
train_loss: 2.0561 | train_acc: 0.4172 | val_loss: 2.0715 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 9.9895 s
>>> Epoch [ 2712/10000]
train_loss: 2.0561 | train_acc: 0.4172 | val_loss: 2.0715 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 5.7269 s
>>> Epoch [ 2713/10000]
train_loss: 2.0561 | train_acc: 0.4171 | val_loss: 2.0715 | val_acc: 0.3968 | test_acc: 0.3976 | Time: 6.3916 s
>>> Epoch [ 2714/10000]
train_loss: 2.0561 | train_acc: 0.4172 | val_loss: 2.0715 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 6.2017 s
>>> Epoch [ 2715/10000]
train_loss: 2.0561 | train_acc: 0.4172 | val_loss: 2.0715 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 7.3692 s
>>> Epoch [ 2716/10000]
train_loss: 2.0561 | train_acc: 0.4172 | val_loss: 2.0715 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 6.3285 s
>>> Epoch [ 2717/10000]
train_loss: 2.0561 | train_acc: 0.4172 | val_loss: 2.0715 | val_acc: 0.3969 | test_acc: 0.3976 | Time: 6.3317 s
>>> Epoch [ 2718/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0715 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 6.3113 s
>>> Epoch [ 2719/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0715 | val_acc: 0.3969 | test_acc: 0.3975 | Time: 6.2920 s
>>> Epoch [ 2720/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0715 | val_acc: 0.3969 | test_acc: 0.3972 | Time: 6.3258 s
>>> Epoch [ 2721/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0715 | val_acc: 0.3969 | test_acc: 0.3973 | Time: 6.5521 s
>>> Epoch [ 2722/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3969 | test_acc: 0.3974 | Time: 6.3783 s
>>> Epoch [ 2723/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3969 | test_acc: 0.3974 | Time: 6.4103 s
>>> Epoch [ 2724/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3969 | test_acc: 0.3974 | Time: 6.4576 s
>>> Epoch [ 2725/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 6.5525 s
>>> Epoch [ 2726/10000]
train_loss: 2.0560 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 6.2593 s
>>> Epoch [ 2727/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 6.5655 s
>>> Epoch [ 2728/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 6.3716 s
>>> Epoch [ 2729/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 6.5133 s
>>> Epoch [ 2730/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3966 | test_acc: 0.3975 | Time: 6.5467 s
>>> Epoch [ 2731/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3965 | test_acc: 0.3975 | Time: 6.5013 s
>>> Epoch [ 2732/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3965 | test_acc: 0.3975 | Time: 6.4688 s
>>> Epoch [ 2733/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0714 | val_acc: 0.3966 | test_acc: 0.3975 | Time: 6.3284 s
>>> Epoch [ 2734/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0713 | val_acc: 0.3966 | test_acc: 0.3974 | Time: 6.3470 s
>>> Epoch [ 2735/10000]
train_loss: 2.0559 | train_acc: 0.4174 | val_loss: 2.0713 | val_acc: 0.3966 | test_acc: 0.3974 | Time: 6.2149 s
>>> Epoch [ 2736/10000]
train_loss: 2.0559 | train_acc: 0.4173 | val_loss: 2.0713 | val_acc: 0.3966 | test_acc: 0.3974 | Time: 6.4139 s
>>> Epoch [ 2737/10000]
train_loss: 2.0558 | train_acc: 0.4172 | val_loss: 2.0713 | val_acc: 0.3967 | test_acc: 0.3974 | Time: 6.4825 s
>>> Epoch [ 2738/10000]
train_loss: 2.0558 | train_acc: 0.4173 | val_loss: 2.0713 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 6.4885 s
>>> Epoch [ 2739/10000]
train_loss: 2.0558 | train_acc: 0.4173 | val_loss: 2.0713 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 6.1935 s
>>> Epoch [ 2740/10000]
train_loss: 2.0558 | train_acc: 0.4173 | val_loss: 2.0713 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 6.3666 s
>>> Epoch [ 2741/10000]
train_loss: 2.0558 | train_acc: 0.4173 | val_loss: 2.0713 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 8.6015 s
>>> Epoch [ 2742/10000]
train_loss: 2.0558 | train_acc: 0.4173 | val_loss: 2.0713 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 10.1824 s
>>> Epoch [ 2743/10000]
train_loss: 2.0558 | train_acc: 0.4174 | val_loss: 2.0713 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 10.0728 s
>>> Epoch [ 2744/10000]
train_loss: 2.0558 | train_acc: 0.4174 | val_loss: 2.0713 | val_acc: 0.3968 | test_acc: 0.3975 | Time: 9.2751 s
>>> Epoch [ 2745/10000]
train_loss: 2.0558 | train_acc: 0.4174 | val_loss: 2.0713 | val_acc: 0.3967 | test_acc: 0.3975 | Time: 9.2682 s
>>> Epoch [ 2746/10000]
train_loss: 2.0558 | train_acc: 0.4174 | val_loss: 2.0713 | val_acc: 0.3967 | test_acc: 0.3976 | Time: 9.4117 s
>>> Epoch [ 2747/10000]
train_loss: 2.0557 | train_acc: 0.4174 | val_loss: 2.0712 | val_acc: 0.3967 | test_acc: 0.3977 | Time: 9.2067 s
>>> Epoch [ 2748/10000]
train_loss: 2.0557 | train_acc: 0.4174 | val_loss: 2.0712 | val_acc: 0.3967 | test_acc: 0.3977 | Time: 9.1135 s
>>> Epoch [ 2749/10000]
train_loss: 2.0557 | train_acc: 0.4174 | val_loss: 2.0712 | val_acc: 0.3967 | test_acc: 0.3977 | Time: 9.2204 s
>>> Epoch [ 2750/10000]
train_loss: 2.0557 | train_acc: 0.4175 | val_loss: 2.0712 | val_acc: 0.3967 | test_acc: 0.3977 | Time: 8.5526 s
>>> Epoch [ 2751/10000]
train_loss: 2.0557 | train_acc: 0.4175 | val_loss: 2.0712 | val_acc: 0.3967 | test_acc: 0.3978 | Time: 8.0018 s
>>> Epoch [ 2752/10000]
train_loss: 2.0557 | train_acc: 0.4175 | val_loss: 2.0712 | val_acc: 0.3967 | test_acc: 0.3978 | Time: 7.1621 s
>>> Epoch [ 2753/10000]
train_loss: 2.0557 | train_acc: 0.4175 | val_loss: 2.0712 | val_acc: 0.3968 | test_acc: 0.3978 | Time: 6.9472 s
>>> Epoch [ 2754/10000]
train_loss: 2.0557 | train_acc: 0.4176 | val_loss: 2.0712 | val_acc: 0.3967 | test_acc: 0.3978 | Time: 6.4364 s
>>> Epoch [ 2755/10000]
train_loss: 2.0557 | train_acc: 0.4176 | val_loss: 2.0712 | val_acc: 0.3968 | test_acc: 0.3978 | Time: 10.2179 s
>>> Epoch [ 2756/10000]
train_loss: 2.0557 | train_acc: 0.4176 | val_loss: 2.0712 | val_acc: 0.3968 | test_acc: 0.3978 | Time: 8.2501 s
>>> Epoch [ 2757/10000]
train_loss: 2.0556 | train_acc: 0.4176 | val_loss: 2.0712 | val_acc: 0.3968 | test_acc: 0.3978 | Time: 7.0425 s
>>> Epoch [ 2758/10000]
train_loss: 2.0556 | train_acc: 0.4176 | val_loss: 2.0712 | val_acc: 0.3968 | test_acc: 0.3978 | Time: 6.9176 s
>>> Epoch [ 2759/10000]
train_loss: 2.0556 | train_acc: 0.4176 | val_loss: 2.0712 | val_acc: 0.3968 | test_acc: 0.3978 | Time: 7.0102 s
>>> Epoch [ 2760/10000]
train_loss: 2.0556 | train_acc: 0.4177 | val_loss: 2.0711 | val_acc: 0.3969 | test_acc: 0.3978 | Time: 6.8421 s
>>> Epoch [ 2761/10000]
train_loss: 2.0556 | train_acc: 0.4177 | val_loss: 2.0711 | val_acc: 0.3970 | test_acc: 0.3978 | Time: 6.9562 s
>>> Epoch [ 2762/10000]
train_loss: 2.0556 | train_acc: 0.4177 | val_loss: 2.0711 | val_acc: 0.3970 | test_acc: 0.3978 | Time: 6.9565 s
>>> Epoch [ 2763/10000]
train_loss: 2.0556 | train_acc: 0.4178 | val_loss: 2.0711 | val_acc: 0.3970 | test_acc: 0.3978 | Time: 6.8462 s
>>> Epoch [ 2764/10000]
train_loss: 2.0556 | train_acc: 0.4178 | val_loss: 2.0711 | val_acc: 0.3969 | test_acc: 0.3978 | Time: 7.0062 s
>>> Epoch [ 2765/10000]
train_loss: 2.0556 | train_acc: 0.4178 | val_loss: 2.0711 | val_acc: 0.3969 | test_acc: 0.3978 | Time: 6.9777 s
>>> Epoch [ 2766/10000]
train_loss: 2.0556 | train_acc: 0.4177 | val_loss: 2.0711 | val_acc: 0.3969 | test_acc: 0.3978 | Time: 6.9851 s
>>> Epoch [ 2767/10000]
train_loss: 2.0555 | train_acc: 0.4177 | val_loss: 2.0711 | val_acc: 0.3970 | test_acc: 0.3978 | Time: 6.5068 s
>>> Epoch [ 2768/10000]
train_loss: 2.0555 | train_acc: 0.4177 | val_loss: 2.0711 | val_acc: 0.3970 | test_acc: 0.3978 | Time: 6.5613 s
>>> Epoch [ 2769/10000]
train_loss: 2.0555 | train_acc: 0.4178 | val_loss: 2.0711 | val_acc: 0.3971 | test_acc: 0.3978 | Time: 6.2334 s
>>> Epoch [ 2770/10000]
train_loss: 2.0555 | train_acc: 0.4178 | val_loss: 2.0711 | val_acc: 0.3971 | test_acc: 0.3978 | Time: 5.8132 s
>>> Epoch [ 2771/10000]
train_loss: 2.0555 | train_acc: 0.4178 | val_loss: 2.0711 | val_acc: 0.3971 | test_acc: 0.3978 | Time: 5.9622 s
>>> Epoch [ 2772/10000]
train_loss: 2.0555 | train_acc: 0.4178 | val_loss: 2.0711 | val_acc: 0.3971 | test_acc: 0.3978 | Time: 6.1448 s
>>> Epoch [ 2773/10000]
train_loss: 2.0555 | train_acc: 0.4178 | val_loss: 2.0710 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 5.8907 s
>>> Epoch [ 2774/10000]
train_loss: 2.0555 | train_acc: 0.4178 | val_loss: 2.0710 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.0184 s
>>> Epoch [ 2775/10000]
train_loss: 2.0555 | train_acc: 0.4178 | val_loss: 2.0710 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.0266 s
>>> Epoch [ 2776/10000]
train_loss: 2.0555 | train_acc: 0.4178 | val_loss: 2.0710 | val_acc: 0.3971 | test_acc: 0.3978 | Time: 6.1329 s
>>> Epoch [ 2777/10000]
train_loss: 2.0554 | train_acc: 0.4178 | val_loss: 2.0710 | val_acc: 0.3971 | test_acc: 0.3978 | Time: 6.1820 s
>>> Epoch [ 2778/10000]
train_loss: 2.0554 | train_acc: 0.4179 | val_loss: 2.0710 | val_acc: 0.3971 | test_acc: 0.3978 | Time: 5.8200 s
>>> Epoch [ 2779/10000]
train_loss: 2.0554 | train_acc: 0.4178 | val_loss: 2.0710 | val_acc: 0.3971 | test_acc: 0.3979 | Time: 5.8015 s
>>> Epoch [ 2780/10000]
train_loss: 2.0554 | train_acc: 0.4179 | val_loss: 2.0710 | val_acc: 0.3971 | test_acc: 0.3979 | Time: 6.1591 s
>>> Epoch [ 2781/10000]
train_loss: 2.0554 | train_acc: 0.4179 | val_loss: 2.0710 | val_acc: 0.3971 | test_acc: 0.3979 | Time: 6.3282 s
>>> Epoch [ 2782/10000]
train_loss: 2.0554 | train_acc: 0.4179 | val_loss: 2.0710 | val_acc: 0.3970 | test_acc: 0.3979 | Time: 6.0689 s
>>> Epoch [ 2783/10000]
train_loss: 2.0554 | train_acc: 0.4180 | val_loss: 2.0710 | val_acc: 0.3969 | test_acc: 0.3979 | Time: 6.2297 s
>>> Epoch [ 2784/10000]
train_loss: 2.0554 | train_acc: 0.4180 | val_loss: 2.0710 | val_acc: 0.3969 | test_acc: 0.3979 | Time: 6.3293 s
>>> Epoch [ 2785/10000]
train_loss: 2.0554 | train_acc: 0.4180 | val_loss: 2.0710 | val_acc: 0.3969 | test_acc: 0.3979 | Time: 6.0735 s
>>> Epoch [ 2786/10000]
train_loss: 2.0554 | train_acc: 0.4180 | val_loss: 2.0709 | val_acc: 0.3969 | test_acc: 0.3979 | Time: 6.2119 s
>>> Epoch [ 2787/10000]
train_loss: 2.0553 | train_acc: 0.4180 | val_loss: 2.0709 | val_acc: 0.3969 | test_acc: 0.3979 | Time: 6.6201 s
>>> Epoch [ 2788/10000]
train_loss: 2.0553 | train_acc: 0.4180 | val_loss: 2.0709 | val_acc: 0.3969 | test_acc: 0.3979 | Time: 6.6452 s
>>> Epoch [ 2789/10000]
train_loss: 2.0553 | train_acc: 0.4181 | val_loss: 2.0709 | val_acc: 0.3969 | test_acc: 0.3979 | Time: 6.5243 s
>>> Epoch [ 2790/10000]
train_loss: 2.0553 | train_acc: 0.4180 | val_loss: 2.0709 | val_acc: 0.3970 | test_acc: 0.3979 | Time: 6.5099 s
>>> Epoch [ 2791/10000]
train_loss: 2.0553 | train_acc: 0.4180 | val_loss: 2.0709 | val_acc: 0.3971 | test_acc: 0.3979 | Time: 6.7445 s
>>> Epoch [ 2792/10000]
train_loss: 2.0553 | train_acc: 0.4181 | val_loss: 2.0709 | val_acc: 0.3971 | test_acc: 0.3979 | Time: 6.6913 s
>>> Epoch [ 2793/10000]
train_loss: 2.0553 | train_acc: 0.4181 | val_loss: 2.0709 | val_acc: 0.3972 | test_acc: 0.3979 | Time: 6.5996 s
>>> Epoch [ 2794/10000]
train_loss: 2.0553 | train_acc: 0.4181 | val_loss: 2.0709 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.6862 s
>>> Epoch [ 2795/10000]
train_loss: 2.0553 | train_acc: 0.4181 | val_loss: 2.0709 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.6038 s
>>> Epoch [ 2796/10000]
train_loss: 2.0553 | train_acc: 0.4181 | val_loss: 2.0709 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.6659 s
>>> Epoch [ 2797/10000]
train_loss: 2.0552 | train_acc: 0.4181 | val_loss: 2.0709 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.6374 s
>>> Epoch [ 2798/10000]
train_loss: 2.0552 | train_acc: 0.4181 | val_loss: 2.0709 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.6080 s
>>> Epoch [ 2799/10000]
train_loss: 2.0552 | train_acc: 0.4181 | val_loss: 2.0708 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.4331 s
>>> Epoch [ 2800/10000]
train_loss: 2.0552 | train_acc: 0.4181 | val_loss: 2.0708 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.3984 s
>>> Epoch [ 2801/10000]
train_loss: 2.0552 | train_acc: 0.4181 | val_loss: 2.0708 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.2412 s
>>> Epoch [ 2802/10000]
train_loss: 2.0552 | train_acc: 0.4181 | val_loss: 2.0708 | val_acc: 0.3972 | test_acc: 0.3978 | Time: 6.7977 s
>>> Epoch [ 2803/10000]
train_loss: 2.0552 | train_acc: 0.4181 | val_loss: 2.0708 | val_acc: 0.3973 | test_acc: 0.3977 | Time: 6.3578 s
>>> Epoch [ 2804/10000]
train_loss: 2.0552 | train_acc: 0.4181 | val_loss: 2.0708 | val_acc: 0.3974 | test_acc: 0.3977 | Time: 6.5538 s
>>> Epoch [ 2805/10000]
train_loss: 2.0552 | train_acc: 0.4182 | val_loss: 2.0708 | val_acc: 0.3975 | test_acc: 0.3976 | Time: 6.6026 s
>>> Epoch [ 2806/10000]
train_loss: 2.0552 | train_acc: 0.4182 | val_loss: 2.0708 | val_acc: 0.3975 | test_acc: 0.3976 | Time: 6.6447 s
>>> Epoch [ 2807/10000]
train_loss: 2.0551 | train_acc: 0.4182 | val_loss: 2.0708 | val_acc: 0.3975 | test_acc: 0.3976 | Time: 6.4529 s
>>> Epoch [ 2808/10000]
train_loss: 2.0551 | train_acc: 0.4182 | val_loss: 2.0708 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 6.4943 s
>>> Epoch [ 2809/10000]
train_loss: 2.0551 | train_acc: 0.4181 | val_loss: 2.0708 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 6.6291 s
>>> Epoch [ 2810/10000]
train_loss: 2.0551 | train_acc: 0.4182 | val_loss: 2.0708 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 6.8445 s
>>> Epoch [ 2811/10000]
train_loss: 2.0551 | train_acc: 0.4182 | val_loss: 2.0708 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 6.5091 s
>>> Epoch [ 2812/10000]
train_loss: 2.0551 | train_acc: 0.4182 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 10.5530 s
>>> Epoch [ 2813/10000]
train_loss: 2.0551 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 9.0734 s
>>> Epoch [ 2814/10000]
train_loss: 2.0551 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3976 | test_acc: 0.3975 | Time: 10.4081 s
>>> Epoch [ 2815/10000]
train_loss: 2.0551 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 7.9961 s
>>> Epoch [ 2816/10000]
train_loss: 2.0551 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 5.8495 s
>>> Epoch [ 2817/10000]
train_loss: 2.0550 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.0863 s
>>> Epoch [ 2818/10000]
train_loss: 2.0550 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.2011 s
>>> Epoch [ 2819/10000]
train_loss: 2.0550 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.5800 s
>>> Epoch [ 2820/10000]
train_loss: 2.0550 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.1793 s
>>> Epoch [ 2821/10000]
train_loss: 2.0550 | train_acc: 0.4184 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.4431 s
>>> Epoch [ 2822/10000]
train_loss: 2.0550 | train_acc: 0.4184 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.4216 s
>>> Epoch [ 2823/10000]
train_loss: 2.0550 | train_acc: 0.4184 | val_loss: 2.0707 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 6.4881 s
>>> Epoch [ 2824/10000]
train_loss: 2.0550 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3976 | test_acc: 0.3975 | Time: 6.6117 s
>>> Epoch [ 2825/10000]
train_loss: 2.0550 | train_acc: 0.4183 | val_loss: 2.0707 | val_acc: 0.3976 | test_acc: 0.3975 | Time: 6.6700 s
>>> Epoch [ 2826/10000]
train_loss: 2.0550 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3976 | test_acc: 0.3975 | Time: 6.7486 s
>>> Epoch [ 2827/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 6.5532 s
>>> Epoch [ 2828/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3974 | test_acc: 0.3975 | Time: 6.6928 s
>>> Epoch [ 2829/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3974 | test_acc: 0.3975 | Time: 6.5873 s
>>> Epoch [ 2830/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3974 | test_acc: 0.3975 | Time: 6.5832 s
>>> Epoch [ 2831/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3974 | test_acc: 0.3975 | Time: 6.5521 s
>>> Epoch [ 2832/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3974 | test_acc: 0.3975 | Time: 6.7026 s
>>> Epoch [ 2833/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3974 | test_acc: 0.3975 | Time: 6.8166 s
>>> Epoch [ 2834/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3974 | test_acc: 0.3975 | Time: 6.7993 s
>>> Epoch [ 2835/10000]
train_loss: 2.0549 | train_acc: 0.4183 | val_loss: 2.0706 | val_acc: 0.3974 | test_acc: 0.3975 | Time: 6.6547 s
>>> Epoch [ 2836/10000]
train_loss: 2.0549 | train_acc: 0.4184 | val_loss: 2.0706 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.8031 s
>>> Epoch [ 2837/10000]
train_loss: 2.0548 | train_acc: 0.4184 | val_loss: 2.0706 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.5016 s
>>> Epoch [ 2838/10000]
train_loss: 2.0548 | train_acc: 0.4184 | val_loss: 2.0706 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.5284 s
>>> Epoch [ 2839/10000]
train_loss: 2.0548 | train_acc: 0.4185 | val_loss: 2.0705 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.4319 s
>>> Epoch [ 2840/10000]
train_loss: 2.0548 | train_acc: 0.4185 | val_loss: 2.0705 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 6.5704 s
>>> Epoch [ 2841/10000]
train_loss: 2.0548 | train_acc: 0.4185 | val_loss: 2.0705 | val_acc: 0.3976 | test_acc: 0.3974 | Time: 6.6370 s
>>> Epoch [ 2842/10000]
train_loss: 2.0548 | train_acc: 0.4185 | val_loss: 2.0705 | val_acc: 0.3976 | test_acc: 0.3974 | Time: 6.6534 s
>>> Epoch [ 2843/10000]
train_loss: 2.0548 | train_acc: 0.4184 | val_loss: 2.0705 | val_acc: 0.3976 | test_acc: 0.3974 | Time: 6.6525 s
>>> Epoch [ 2844/10000]
train_loss: 2.0548 | train_acc: 0.4185 | val_loss: 2.0705 | val_acc: 0.3976 | test_acc: 0.3973 | Time: 6.4696 s
>>> Epoch [ 2845/10000]
train_loss: 2.0548 | train_acc: 0.4185 | val_loss: 2.0705 | val_acc: 0.3976 | test_acc: 0.3973 | Time: 6.5909 s
>>> Epoch [ 2846/10000]
train_loss: 2.0548 | train_acc: 0.4185 | val_loss: 2.0705 | val_acc: 0.3976 | test_acc: 0.3973 | Time: 6.6675 s
>>> Epoch [ 2847/10000]
train_loss: 2.0547 | train_acc: 0.4186 | val_loss: 2.0705 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 7.6875 s
>>> Epoch [ 2848/10000]
train_loss: 2.0547 | train_acc: 0.4187 | val_loss: 2.0705 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 10.0838 s
>>> Epoch [ 2849/10000]
train_loss: 2.0547 | train_acc: 0.4186 | val_loss: 2.0705 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 10.1756 s
>>> Epoch [ 2850/10000]
train_loss: 2.0547 | train_acc: 0.4186 | val_loss: 2.0705 | val_acc: 0.3975 | test_acc: 0.3975 | Time: 9.4385 s
>>> Epoch [ 2851/10000]
train_loss: 2.0547 | train_acc: 0.4186 | val_loss: 2.0705 | val_acc: 0.3975 | test_acc: 0.3974 | Time: 5.9688 s
>>> Epoch [ 2852/10000]
train_loss: 2.0547 | train_acc: 0.4187 | val_loss: 2.0704 | val_acc: 0.3975 | test_acc: 0.3972 | Time: 5.8336 s
>>> Epoch [ 2853/10000]
train_loss: 2.0547 | train_acc: 0.4187 | val_loss: 2.0704 | val_acc: 0.3975 | test_acc: 0.3971 | Time: 6.2125 s
>>> Epoch [ 2854/10000]
train_loss: 2.0547 | train_acc: 0.4187 | val_loss: 2.0704 | val_acc: 0.3975 | test_acc: 0.3971 | Time: 6.2956 s
>>> Epoch [ 2855/10000]
train_loss: 2.0547 | train_acc: 0.4187 | val_loss: 2.0704 | val_acc: 0.3975 | test_acc: 0.3971 | Time: 6.2114 s
>>> Epoch [ 2856/10000]
train_loss: 2.0547 | train_acc: 0.4187 | val_loss: 2.0704 | val_acc: 0.3975 | test_acc: 0.3971 | Time: 6.7106 s
>>> Epoch [ 2857/10000]
train_loss: 2.0546 | train_acc: 0.4187 | val_loss: 2.0704 | val_acc: 0.3975 | test_acc: 0.3970 | Time: 6.6202 s
>>> Epoch [ 2858/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0704 | val_acc: 0.3975 | test_acc: 0.3970 | Time: 6.7763 s
>>> Epoch [ 2859/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0704 | val_acc: 0.3975 | test_acc: 0.3971 | Time: 6.9475 s
>>> Epoch [ 2860/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0704 | val_acc: 0.3974 | test_acc: 0.3971 | Time: 6.9063 s
>>> Epoch [ 2861/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0704 | val_acc: 0.3974 | test_acc: 0.3970 | Time: 6.8218 s
>>> Epoch [ 2862/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0704 | val_acc: 0.3974 | test_acc: 0.3970 | Time: 6.7115 s
>>> Epoch [ 2863/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0704 | val_acc: 0.3974 | test_acc: 0.3970 | Time: 6.8715 s
>>> Epoch [ 2864/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0704 | val_acc: 0.3974 | test_acc: 0.3970 | Time: 6.9521 s
>>> Epoch [ 2865/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0704 | val_acc: 0.3974 | test_acc: 0.3970 | Time: 6.8618 s
>>> Epoch [ 2866/10000]
train_loss: 2.0546 | train_acc: 0.4188 | val_loss: 2.0703 | val_acc: 0.3974 | test_acc: 0.3969 | Time: 6.6264 s
>>> Epoch [ 2867/10000]
train_loss: 2.0545 | train_acc: 0.4188 | val_loss: 2.0703 | val_acc: 0.3974 | test_acc: 0.3969 | Time: 6.5486 s
>>> Epoch [ 2868/10000]
train_loss: 2.0545 | train_acc: 0.4188 | val_loss: 2.0703 | val_acc: 0.3974 | test_acc: 0.3969 | Time: 6.6030 s
>>> Epoch [ 2869/10000]
train_loss: 2.0545 | train_acc: 0.4189 | val_loss: 2.0703 | val_acc: 0.3974 | test_acc: 0.3969 | Time: 6.7966 s
>>> Epoch [ 2870/10000]
train_loss: 2.0545 | train_acc: 0.4190 | val_loss: 2.0703 | val_acc: 0.3974 | test_acc: 0.3968 | Time: 6.9166 s
>>> Epoch [ 2871/10000]
train_loss: 2.0545 | train_acc: 0.4190 | val_loss: 2.0703 | val_acc: 0.3975 | test_acc: 0.3968 | Time: 6.8519 s
>>> Epoch [ 2872/10000]
train_loss: 2.0545 | train_acc: 0.4190 | val_loss: 2.0703 | val_acc: 0.3975 | test_acc: 0.3967 | Time: 7.0408 s
>>> Epoch [ 2873/10000]
train_loss: 2.0545 | train_acc: 0.4191 | val_loss: 2.0703 | val_acc: 0.3976 | test_acc: 0.3968 | Time: 6.7040 s
>>> Epoch [ 2874/10000]
train_loss: 2.0545 | train_acc: 0.4191 | val_loss: 2.0703 | val_acc: 0.3976 | test_acc: 0.3968 | Time: 6.9009 s
>>> Epoch [ 2875/10000]
train_loss: 2.0545 | train_acc: 0.4191 | val_loss: 2.0703 | val_acc: 0.3979 | test_acc: 0.3968 | Time: 6.8647 s
>>> Epoch [ 2876/10000]
train_loss: 2.0545 | train_acc: 0.4193 | val_loss: 2.0703 | val_acc: 0.3981 | test_acc: 0.3968 | Time: 6.5995 s
>>> Epoch [ 2877/10000]
train_loss: 2.0545 | train_acc: 0.4193 | val_loss: 2.0703 | val_acc: 0.3981 | test_acc: 0.3968 | Time: 6.9749 s
>>> Epoch [ 2878/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0703 | val_acc: 0.3981 | test_acc: 0.3968 | Time: 6.7421 s
>>> Epoch [ 2879/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0703 | val_acc: 0.3981 | test_acc: 0.3968 | Time: 6.7160 s
>>> Epoch [ 2880/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0702 | val_acc: 0.3981 | test_acc: 0.3969 | Time: 6.6853 s
>>> Epoch [ 2881/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0702 | val_acc: 0.3981 | test_acc: 0.3969 | Time: 10.9218 s
>>> Epoch [ 2882/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0702 | val_acc: 0.3981 | test_acc: 0.3969 | Time: 9.8132 s
>>> Epoch [ 2883/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0702 | val_acc: 0.3982 | test_acc: 0.3969 | Time: 10.0821 s
>>> Epoch [ 2884/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0702 | val_acc: 0.3980 | test_acc: 0.3969 | Time: 6.9241 s
>>> Epoch [ 2885/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0702 | val_acc: 0.3980 | test_acc: 0.3969 | Time: 6.1138 s
>>> Epoch [ 2886/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0702 | val_acc: 0.3980 | test_acc: 0.3969 | Time: 6.5002 s
>>> Epoch [ 2887/10000]
train_loss: 2.0544 | train_acc: 0.4193 | val_loss: 2.0702 | val_acc: 0.3980 | test_acc: 0.3968 | Time: 6.5230 s
>>> Epoch [ 2888/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0702 | val_acc: 0.3981 | test_acc: 0.3967 | Time: 6.5379 s
>>> Epoch [ 2889/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0702 | val_acc: 0.3981 | test_acc: 0.3967 | Time: 6.6384 s
>>> Epoch [ 2890/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0702 | val_acc: 0.3983 | test_acc: 0.3967 | Time: 7.1357 s
>>> Epoch [ 2891/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0702 | val_acc: 0.3982 | test_acc: 0.3968 | Time: 6.9665 s
>>> Epoch [ 2892/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0702 | val_acc: 0.3982 | test_acc: 0.3968 | Time: 6.9434 s
>>> Epoch [ 2893/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0701 | val_acc: 0.3982 | test_acc: 0.3968 | Time: 6.6039 s
>>> Epoch [ 2894/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 6.6271 s
>>> Epoch [ 2895/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 6.8007 s
>>> Epoch [ 2896/10000]
train_loss: 2.0543 | train_acc: 0.4193 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 6.4902 s
>>> Epoch [ 2897/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 7.1682 s
>>> Epoch [ 2898/10000]
train_loss: 2.0543 | train_acc: 0.4194 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 7.1384 s
>>> Epoch [ 2899/10000]
train_loss: 2.0542 | train_acc: 0.4194 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 6.9118 s
>>> Epoch [ 2900/10000]
train_loss: 2.0542 | train_acc: 0.4194 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 6.8297 s
>>> Epoch [ 2901/10000]
train_loss: 2.0542 | train_acc: 0.4195 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 6.9185 s
>>> Epoch [ 2902/10000]
train_loss: 2.0542 | train_acc: 0.4195 | val_loss: 2.0701 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 6.7909 s
>>> Epoch [ 2903/10000]
train_loss: 2.0542 | train_acc: 0.4195 | val_loss: 2.0701 | val_acc: 0.3984 | test_acc: 0.3968 | Time: 6.9807 s
>>> Epoch [ 2904/10000]
train_loss: 2.0542 | train_acc: 0.4195 | val_loss: 2.0701 | val_acc: 0.3984 | test_acc: 0.3967 | Time: 6.9064 s
>>> Epoch [ 2905/10000]
train_loss: 2.0542 | train_acc: 0.4195 | val_loss: 2.0701 | val_acc: 0.3984 | test_acc: 0.3967 | Time: 6.9666 s
>>> Epoch [ 2906/10000]
train_loss: 2.0542 | train_acc: 0.4195 | val_loss: 2.0701 | val_acc: 0.3984 | test_acc: 0.3967 | Time: 6.8983 s
>>> Epoch [ 2907/10000]
train_loss: 2.0542 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3983 | test_acc: 0.3967 | Time: 6.8574 s
>>> Epoch [ 2908/10000]
train_loss: 2.0542 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3983 | test_acc: 0.3966 | Time: 6.8199 s
>>> Epoch [ 2909/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3983 | test_acc: 0.3966 | Time: 6.6794 s
>>> Epoch [ 2910/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3966 | Time: 6.6814 s
>>> Epoch [ 2911/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3966 | Time: 6.9076 s
>>> Epoch [ 2912/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 6.9094 s
>>> Epoch [ 2913/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 6.7653 s
>>> Epoch [ 2914/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 10.9260 s
>>> Epoch [ 2915/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 9.7927 s
>>> Epoch [ 2916/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 10.7072 s
>>> Epoch [ 2917/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 7.8128 s
>>> Epoch [ 2918/10000]
train_loss: 2.0541 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3966 | Time: 6.4380 s
>>> Epoch [ 2919/10000]
train_loss: 2.0540 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3966 | Time: 6.5487 s
>>> Epoch [ 2920/10000]
train_loss: 2.0540 | train_acc: 0.4195 | val_loss: 2.0700 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 6.4916 s
>>> Epoch [ 2921/10000]
train_loss: 2.0540 | train_acc: 0.4196 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3966 | Time: 7.0880 s
>>> Epoch [ 2922/10000]
train_loss: 2.0540 | train_acc: 0.4196 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3966 | Time: 6.8337 s
>>> Epoch [ 2923/10000]
train_loss: 2.0540 | train_acc: 0.4196 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3967 | Time: 6.8294 s
>>> Epoch [ 2924/10000]
train_loss: 2.0540 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3968 | Time: 6.8033 s
>>> Epoch [ 2925/10000]
train_loss: 2.0540 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3982 | test_acc: 0.3968 | Time: 6.9725 s
>>> Epoch [ 2926/10000]
train_loss: 2.0540 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 6.3589 s
>>> Epoch [ 2927/10000]
train_loss: 2.0540 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3982 | test_acc: 0.3967 | Time: 7.0331 s
>>> Epoch [ 2928/10000]
train_loss: 2.0540 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3967 | Time: 6.5701 s
>>> Epoch [ 2929/10000]
train_loss: 2.0540 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3967 | Time: 6.4139 s
>>> Epoch [ 2930/10000]
train_loss: 2.0539 | train_acc: 0.4196 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3967 | Time: 6.6563 s
>>> Epoch [ 2931/10000]
train_loss: 2.0539 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3966 | Time: 6.5816 s
>>> Epoch [ 2932/10000]
train_loss: 2.0539 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3967 | Time: 6.5443 s
>>> Epoch [ 2933/10000]
train_loss: 2.0539 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3983 | test_acc: 0.3967 | Time: 6.4905 s
>>> Epoch [ 2934/10000]
train_loss: 2.0539 | train_acc: 0.4195 | val_loss: 2.0699 | val_acc: 0.3984 | test_acc: 0.3967 | Time: 6.7505 s
>>> Epoch [ 2935/10000]
train_loss: 2.0539 | train_acc: 0.4195 | val_loss: 2.0698 | val_acc: 0.3985 | test_acc: 0.3967 | Time: 6.6619 s
>>> Epoch [ 2936/10000]
train_loss: 2.0539 | train_acc: 0.4195 | val_loss: 2.0698 | val_acc: 0.3984 | test_acc: 0.3967 | Time: 6.5200 s
>>> Epoch [ 2937/10000]
train_loss: 2.0539 | train_acc: 0.4195 | val_loss: 2.0698 | val_acc: 0.3984 | test_acc: 0.3967 | Time: 6.6148 s
>>> Epoch [ 2938/10000]
train_loss: 2.0539 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3984 | test_acc: 0.3967 | Time: 6.7914 s
>>> Epoch [ 2939/10000]
train_loss: 2.0539 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3985 | test_acc: 0.3966 | Time: 6.4621 s
>>> Epoch [ 2940/10000]
train_loss: 2.0538 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3985 | test_acc: 0.3967 | Time: 6.4551 s
>>> Epoch [ 2941/10000]
train_loss: 2.0538 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3985 | test_acc: 0.3967 | Time: 6.8047 s
>>> Epoch [ 2942/10000]
train_loss: 2.0538 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3985 | test_acc: 0.3967 | Time: 6.0323 s
>>> Epoch [ 2943/10000]
train_loss: 2.0538 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3985 | test_acc: 0.3968 | Time: 5.7361 s
>>> Epoch [ 2944/10000]
train_loss: 2.0538 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3986 | test_acc: 0.3968 | Time: 6.7577 s
>>> Epoch [ 2945/10000]
train_loss: 2.0538 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3986 | test_acc: 0.3968 | Time: 8.7136 s
>>> Epoch [ 2946/10000]
train_loss: 2.0538 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3986 | test_acc: 0.3968 | Time: 7.3841 s
>>> Epoch [ 2947/10000]
train_loss: 2.0538 | train_acc: 0.4196 | val_loss: 2.0698 | val_acc: 0.3986 | test_acc: 0.3967 | Time: 9.6057 s
>>> Epoch [ 2948/10000]
train_loss: 2.0538 | train_acc: 0.4197 | val_loss: 2.0698 | val_acc: 0.3985 | test_acc: 0.3967 | Time: 6.2432 s
>>> Epoch [ 2949/10000]
train_loss: 2.0538 | train_acc: 0.4197 | val_loss: 2.0697 | val_acc: 0.3985 | test_acc: 0.3966 | Time: 6.5780 s
>>> Epoch [ 2950/10000]
train_loss: 2.0538 | train_acc: 0.4197 | val_loss: 2.0697 | val_acc: 0.3985 | test_acc: 0.3966 | Time: 6.1583 s
>>> Epoch [ 2951/10000]
train_loss: 2.0537 | train_acc: 0.4197 | val_loss: 2.0697 | val_acc: 0.3985 | test_acc: 0.3965 | Time: 6.5711 s
>>> Epoch [ 2952/10000]
train_loss: 2.0537 | train_acc: 0.4197 | val_loss: 2.0697 | val_acc: 0.3985 | test_acc: 0.3965 | Time: 6.4901 s
>>> Epoch [ 2953/10000]
train_loss: 2.0537 | train_acc: 0.4197 | val_loss: 2.0697 | val_acc: 0.3986 | test_acc: 0.3965 | Time: 6.5450 s
>>> Epoch [ 2954/10000]
train_loss: 2.0537 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3986 | test_acc: 0.3965 | Time: 6.4839 s
>>> Epoch [ 2955/10000]
train_loss: 2.0537 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3986 | test_acc: 0.3965 | Time: 6.2787 s
>>> Epoch [ 2956/10000]
train_loss: 2.0537 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3986 | test_acc: 0.3965 | Time: 6.2633 s
>>> Epoch [ 2957/10000]
train_loss: 2.0537 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3987 | test_acc: 0.3965 | Time: 6.4949 s
>>> Epoch [ 2958/10000]
train_loss: 2.0537 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3987 | test_acc: 0.3964 | Time: 6.4715 s
>>> Epoch [ 2959/10000]
train_loss: 2.0537 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3986 | test_acc: 0.3964 | Time: 6.3794 s
>>> Epoch [ 2960/10000]
train_loss: 2.0537 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.7850 s
>>> Epoch [ 2961/10000]
train_loss: 2.0537 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.8278 s
>>> Epoch [ 2962/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0697 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.5153 s
>>> Epoch [ 2963/10000]
train_loss: 2.0536 | train_acc: 0.4198 | val_loss: 2.0697 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.3752 s
>>> Epoch [ 2964/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0696 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.7831 s
>>> Epoch [ 2965/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0696 | val_acc: 0.3985 | test_acc: 0.3963 | Time: 6.4000 s
>>> Epoch [ 2966/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0696 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.4117 s
>>> Epoch [ 2967/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0696 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.6527 s
>>> Epoch [ 2968/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0696 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.6045 s
>>> Epoch [ 2969/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0696 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.4847 s
>>> Epoch [ 2970/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0696 | val_acc: 0.3985 | test_acc: 0.3964 | Time: 6.7849 s
>>> Epoch [ 2971/10000]
train_loss: 2.0536 | train_acc: 0.4199 | val_loss: 2.0696 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 6.4625 s
>>> Epoch [ 2972/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0696 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 6.5638 s
>>> Epoch [ 2973/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0696 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 6.6797 s
>>> Epoch [ 2974/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0696 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 6.4935 s
>>> Epoch [ 2975/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0696 | val_acc: 0.3984 | test_acc: 0.3964 | Time: 10.4338 s
>>> Epoch [ 2976/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0696 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 8.9745 s
>>> Epoch [ 2977/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0696 | val_acc: 0.3984 | test_acc: 0.3964 | Time: 7.8809 s
>>> Epoch [ 2978/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3983 | test_acc: 0.3963 | Time: 7.5037 s
>>> Epoch [ 2979/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 7.6712 s
>>> Epoch [ 2980/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 7.6861 s
>>> Epoch [ 2981/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 7.5062 s
>>> Epoch [ 2982/10000]
train_loss: 2.0535 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3963 | Time: 7.8368 s
>>> Epoch [ 2983/10000]
train_loss: 2.0534 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3962 | Time: 8.0145 s
>>> Epoch [ 2984/10000]
train_loss: 2.0534 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3962 | Time: 7.2170 s
>>> Epoch [ 2985/10000]
train_loss: 2.0534 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3962 | Time: 7.3017 s
>>> Epoch [ 2986/10000]
train_loss: 2.0534 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3961 | Time: 6.6628 s
>>> Epoch [ 2987/10000]
train_loss: 2.0534 | train_acc: 0.4200 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3961 | Time: 6.0266 s
>>> Epoch [ 2988/10000]
train_loss: 2.0534 | train_acc: 0.4201 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3961 | Time: 6.3076 s
>>> Epoch [ 2989/10000]
train_loss: 2.0534 | train_acc: 0.4201 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3961 | Time: 9.9862 s
>>> Epoch [ 2990/10000]
train_loss: 2.0534 | train_acc: 0.4201 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3961 | Time: 8.8226 s
>>> Epoch [ 2991/10000]
train_loss: 2.0534 | train_acc: 0.4201 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3960 | Time: 7.6073 s
>>> Epoch [ 2992/10000]
train_loss: 2.0534 | train_acc: 0.4201 | val_loss: 2.0695 | val_acc: 0.3984 | test_acc: 0.3960 | Time: 7.6249 s
>>> Epoch [ 2993/10000]
train_loss: 2.0534 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3984 | test_acc: 0.3960 | Time: 7.6936 s
>>> Epoch [ 2994/10000]
train_loss: 2.0533 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3984 | test_acc: 0.3960 | Time: 7.5921 s
>>> Epoch [ 2995/10000]
train_loss: 2.0533 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3984 | test_acc: 0.3960 | Time: 7.6622 s
>>> Epoch [ 2996/10000]
train_loss: 2.0533 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3984 | test_acc: 0.3959 | Time: 7.6318 s
>>> Epoch [ 2997/10000]
train_loss: 2.0533 | train_acc: 0.4200 | val_loss: 2.0694 | val_acc: 0.3984 | test_acc: 0.3959 | Time: 7.5126 s
>>> Epoch [ 2998/10000]
train_loss: 2.0533 | train_acc: 0.4200 | val_loss: 2.0694 | val_acc: 0.3984 | test_acc: 0.3960 | Time: 7.5517 s
>>> Epoch [ 2999/10000]
train_loss: 2.0533 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3984 | test_acc: 0.3960 | Time: 7.3918 s
>>> Epoch [ 3000/10000]
train_loss: 2.0533 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3985 | test_acc: 0.3960 | Time: 6.4617 s
>>> Epoch [ 3001/10000]
train_loss: 2.0533 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3985 | test_acc: 0.3961 | Time: 6.4432 s
>>> Epoch [ 3002/10000]
train_loss: 2.0533 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3985 | test_acc: 0.3959 | Time: 6.4419 s
>>> Epoch [ 3003/10000]
train_loss: 2.0533 | train_acc: 0.4201 | val_loss: 2.0694 | val_acc: 0.3985 | test_acc: 0.3959 | Time: 6.6593 s
>>> Epoch [ 3004/10000]
train_loss: 2.0533 | train_acc: 0.4202 | val_loss: 2.0694 | val_acc: 0.3987 | test_acc: 0.3960 | Time: 6.2800 s
>>> Epoch [ 3005/10000]
train_loss: 2.0532 | train_acc: 0.4202 | val_loss: 2.0694 | val_acc: 0.3987 | test_acc: 0.3961 | Time: 6.0556 s
>>> Epoch [ 3006/10000]
train_loss: 2.0532 | train_acc: 0.4202 | val_loss: 2.0694 | val_acc: 0.3987 | test_acc: 0.3961 | Time: 5.9383 s
>>> Epoch [ 3007/10000]
train_loss: 2.0532 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3987 | test_acc: 0.3961 | Time: 5.9254 s
>>> Epoch [ 3008/10000]
train_loss: 2.0532 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3988 | test_acc: 0.3961 | Time: 5.9466 s
>>> Epoch [ 3009/10000]
train_loss: 2.0532 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3989 | test_acc: 0.3961 | Time: 5.8607 s
>>> Epoch [ 3010/10000]
train_loss: 2.0532 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3989 | test_acc: 0.3960 | Time: 6.1165 s
>>> Epoch [ 3011/10000]
train_loss: 2.0532 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3989 | test_acc: 0.3961 | Time: 6.0082 s
>>> Epoch [ 3012/10000]
train_loss: 2.0532 | train_acc: 0.4203 | val_loss: 2.0693 | val_acc: 0.3988 | test_acc: 0.3962 | Time: 6.3291 s
>>> Epoch [ 3013/10000]
train_loss: 2.0532 | train_acc: 0.4203 | val_loss: 2.0693 | val_acc: 0.3988 | test_acc: 0.3962 | Time: 6.4232 s
>>> Epoch [ 3014/10000]
train_loss: 2.0532 | train_acc: 0.4203 | val_loss: 2.0693 | val_acc: 0.3988 | test_acc: 0.3962 | Time: 6.2511 s
>>> Epoch [ 3015/10000]
train_loss: 2.0531 | train_acc: 0.4203 | val_loss: 2.0693 | val_acc: 0.3988 | test_acc: 0.3962 | Time: 6.1173 s
>>> Epoch [ 3016/10000]
train_loss: 2.0531 | train_acc: 0.4203 | val_loss: 2.0693 | val_acc: 0.3988 | test_acc: 0.3962 | Time: 6.1644 s
>>> Epoch [ 3017/10000]
train_loss: 2.0531 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3988 | test_acc: 0.3962 | Time: 6.3299 s
>>> Epoch [ 3018/10000]
train_loss: 2.0531 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3989 | test_acc: 0.3962 | Time: 6.4620 s
>>> Epoch [ 3019/10000]
train_loss: 2.0531 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3989 | test_acc: 0.3961 | Time: 6.6345 s
>>> Epoch [ 3020/10000]
train_loss: 2.0531 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3989 | test_acc: 0.3961 | Time: 6.8097 s
>>> Epoch [ 3021/10000]
train_loss: 2.0531 | train_acc: 0.4202 | val_loss: 2.0693 | val_acc: 0.3988 | test_acc: 0.3961 | Time: 6.6060 s
>>> Epoch [ 3022/10000]
train_loss: 2.0531 | train_acc: 0.4202 | val_loss: 2.0692 | val_acc: 0.3987 | test_acc: 0.3961 | Time: 6.5407 s
>>> Epoch [ 3023/10000]
train_loss: 2.0531 | train_acc: 0.4202 | val_loss: 2.0692 | val_acc: 0.3987 | test_acc: 0.3961 | Time: 6.3807 s
>>> Epoch [ 3024/10000]
train_loss: 2.0531 | train_acc: 0.4203 | val_loss: 2.0692 | val_acc: 0.3987 | test_acc: 0.3961 | Time: 6.5621 s
>>> Epoch [ 3025/10000]
train_loss: 2.0531 | train_acc: 0.4203 | val_loss: 2.0692 | val_acc: 0.3986 | test_acc: 0.3961 | Time: 6.5073 s
>>> Epoch [ 3026/10000]
train_loss: 2.0530 | train_acc: 0.4203 | val_loss: 2.0692 | val_acc: 0.3986 | test_acc: 0.3962 | Time: 6.4518 s
>>> Epoch [ 3027/10000]
train_loss: 2.0530 | train_acc: 0.4203 | val_loss: 2.0692 | val_acc: 0.3986 | test_acc: 0.3962 | Time: 6.7838 s
>>> Epoch [ 3028/10000]
train_loss: 2.0530 | train_acc: 0.4203 | val_loss: 2.0692 | val_acc: 0.3986 | test_acc: 0.3963 | Time: 6.5753 s
>>> Epoch [ 3029/10000]
train_loss: 2.0530 | train_acc: 0.4203 | val_loss: 2.0692 | val_acc: 0.3986 | test_acc: 0.3963 | Time: 6.7013 s
>>> Epoch [ 3030/10000]
train_loss: 2.0530 | train_acc: 0.4204 | val_loss: 2.0692 | val_acc: 0.3986 | test_acc: 0.3963 | Time: 6.5633 s
>>> Epoch [ 3031/10000]
train_loss: 2.0530 | train_acc: 0.4204 | val_loss: 2.0692 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.6694 s
>>> Epoch [ 3032/10000]
train_loss: 2.0530 | train_acc: 0.4204 | val_loss: 2.0692 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.4867 s
>>> Epoch [ 3033/10000]
train_loss: 2.0530 | train_acc: 0.4203 | val_loss: 2.0692 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.7035 s
>>> Epoch [ 3034/10000]
train_loss: 2.0530 | train_acc: 0.4203 | val_loss: 2.0692 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.6441 s
>>> Epoch [ 3035/10000]
train_loss: 2.0530 | train_acc: 0.4204 | val_loss: 2.0692 | val_acc: 0.3986 | test_acc: 0.3962 | Time: 6.5604 s
>>> Epoch [ 3036/10000]
train_loss: 2.0530 | train_acc: 0.4204 | val_loss: 2.0692 | val_acc: 0.3986 | test_acc: 0.3962 | Time: 6.6215 s
>>> Epoch [ 3037/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3961 | Time: 6.6397 s
>>> Epoch [ 3038/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3961 | Time: 6.4342 s
>>> Epoch [ 3039/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3961 | Time: 6.4851 s
>>> Epoch [ 3040/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3961 | Time: 6.3672 s
>>> Epoch [ 3041/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3961 | Time: 6.5648 s
>>> Epoch [ 3042/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3961 | Time: 6.8235 s
>>> Epoch [ 3043/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3962 | Time: 9.7957 s
>>> Epoch [ 3044/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3962 | Time: 9.7348 s
>>> Epoch [ 3045/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3962 | Time: 10.3042 s
>>> Epoch [ 3046/10000]
train_loss: 2.0529 | train_acc: 0.4205 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3962 | Time: 8.2116 s
>>> Epoch [ 3047/10000]
train_loss: 2.0529 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3963 | Time: 6.2491 s
>>> Epoch [ 3048/10000]
train_loss: 2.0528 | train_acc: 0.4205 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3963 | Time: 6.4155 s
>>> Epoch [ 3049/10000]
train_loss: 2.0528 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3963 | Time: 6.4015 s
>>> Epoch [ 3050/10000]
train_loss: 2.0528 | train_acc: 0.4204 | val_loss: 2.0691 | val_acc: 0.3986 | test_acc: 0.3963 | Time: 6.3010 s
>>> Epoch [ 3051/10000]
train_loss: 2.0528 | train_acc: 0.4204 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.2604 s
>>> Epoch [ 3052/10000]
train_loss: 2.0528 | train_acc: 0.4204 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.2909 s
>>> Epoch [ 3053/10000]
train_loss: 2.0528 | train_acc: 0.4204 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.5213 s
>>> Epoch [ 3054/10000]
train_loss: 2.0528 | train_acc: 0.4204 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.8470 s
>>> Epoch [ 3055/10000]
train_loss: 2.0528 | train_acc: 0.4205 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.8531 s
>>> Epoch [ 3056/10000]
train_loss: 2.0528 | train_acc: 0.4205 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.5979 s
>>> Epoch [ 3057/10000]
train_loss: 2.0528 | train_acc: 0.4205 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.7352 s
>>> Epoch [ 3058/10000]
train_loss: 2.0528 | train_acc: 0.4205 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.7426 s
>>> Epoch [ 3059/10000]
train_loss: 2.0527 | train_acc: 0.4205 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3963 | Time: 6.7474 s
>>> Epoch [ 3060/10000]
train_loss: 2.0527 | train_acc: 0.4206 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3964 | Time: 6.7554 s
>>> Epoch [ 3061/10000]
train_loss: 2.0527 | train_acc: 0.4206 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3964 | Time: 6.6844 s
>>> Epoch [ 3062/10000]
train_loss: 2.0527 | train_acc: 0.4206 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3964 | Time: 6.6388 s
>>> Epoch [ 3063/10000]
train_loss: 2.0527 | train_acc: 0.4206 | val_loss: 2.0690 | val_acc: 0.3987 | test_acc: 0.3964 | Time: 6.5385 s
>>> Epoch [ 3064/10000]
train_loss: 2.0527 | train_acc: 0.4206 | val_loss: 2.0690 | val_acc: 0.3988 | test_acc: 0.3964 | Time: 6.7430 s
>>> Epoch [ 3065/10000]
train_loss: 2.0527 | train_acc: 0.4207 | val_loss: 2.0690 | val_acc: 0.3988 | test_acc: 0.3964 | Time: 6.7761 s
>>> Epoch [ 3066/10000]
train_loss: 2.0527 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3964 | Time: 6.8793 s
>>> Epoch [ 3067/10000]
train_loss: 2.0527 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3964 | Time: 6.8725 s
>>> Epoch [ 3068/10000]
train_loss: 2.0527 | train_acc: 0.4206 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3964 | Time: 6.5048 s
>>> Epoch [ 3069/10000]
train_loss: 2.0527 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3964 | Time: 6.7513 s
>>> Epoch [ 3070/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3987 | test_acc: 0.3965 | Time: 6.8897 s
>>> Epoch [ 3071/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3987 | test_acc: 0.3965 | Time: 6.7760 s
>>> Epoch [ 3072/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3987 | test_acc: 0.3965 | Time: 6.4647 s
>>> Epoch [ 3073/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3965 | Time: 6.9094 s
>>> Epoch [ 3074/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3965 | Time: 6.8468 s
>>> Epoch [ 3075/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3965 | Time: 6.6641 s
>>> Epoch [ 3076/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3965 | Time: 6.7381 s
>>> Epoch [ 3077/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3965 | Time: 6.8773 s
>>> Epoch [ 3078/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3966 | Time: 10.4706 s
>>> Epoch [ 3079/10000]
train_loss: 2.0526 | train_acc: 0.4207 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3966 | Time: 9.1455 s
>>> Epoch [ 3080/10000]
train_loss: 2.0526 | train_acc: 0.4208 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3966 | Time: 11.0332 s
>>> Epoch [ 3081/10000]
train_loss: 2.0525 | train_acc: 0.4208 | val_loss: 2.0689 | val_acc: 0.3988 | test_acc: 0.3966 | Time: 7.5776 s
>>> Epoch [ 3082/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3988 | test_acc: 0.3966 | Time: 6.2609 s
>>> Epoch [ 3083/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3988 | test_acc: 0.3966 | Time: 6.6412 s
>>> Epoch [ 3084/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3988 | test_acc: 0.3966 | Time: 6.5690 s
>>> Epoch [ 3085/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3988 | test_acc: 0.3967 | Time: 6.6363 s
>>> Epoch [ 3086/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3988 | test_acc: 0.3967 | Time: 6.9812 s
>>> Epoch [ 3087/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3988 | test_acc: 0.3967 | Time: 6.6127 s
>>> Epoch [ 3088/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3988 | test_acc: 0.3967 | Time: 6.5567 s
>>> Epoch [ 3089/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3989 | test_acc: 0.3967 | Time: 6.9734 s
>>> Epoch [ 3090/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3989 | test_acc: 0.3968 | Time: 6.6939 s
>>> Epoch [ 3091/10000]
train_loss: 2.0525 | train_acc: 0.4208 | val_loss: 2.0688 | val_acc: 0.3989 | test_acc: 0.3968 | Time: 6.7699 s
>>> Epoch [ 3092/10000]
train_loss: 2.0525 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3989 | test_acc: 0.3968 | Time: 6.7840 s
>>> Epoch [ 3093/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3989 | test_acc: 0.3968 | Time: 6.6559 s
>>> Epoch [ 3094/10000]
train_loss: 2.0524 | train_acc: 0.4206 | val_loss: 2.0688 | val_acc: 0.3989 | test_acc: 0.3969 | Time: 6.6565 s
>>> Epoch [ 3095/10000]
train_loss: 2.0524 | train_acc: 0.4206 | val_loss: 2.0688 | val_acc: 0.3989 | test_acc: 0.3970 | Time: 6.5139 s
>>> Epoch [ 3096/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0688 | val_acc: 0.3989 | test_acc: 0.3970 | Time: 6.5559 s
>>> Epoch [ 3097/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3989 | test_acc: 0.3970 | Time: 6.9480 s
>>> Epoch [ 3098/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3989 | test_acc: 0.3970 | Time: 6.6205 s
>>> Epoch [ 3099/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3989 | test_acc: 0.3970 | Time: 6.9488 s
>>> Epoch [ 3100/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3991 | test_acc: 0.3969 | Time: 6.7485 s
>>> Epoch [ 3101/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3991 | test_acc: 0.3969 | Time: 6.6281 s
>>> Epoch [ 3102/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3992 | test_acc: 0.3968 | Time: 6.7331 s
>>> Epoch [ 3103/10000]
train_loss: 2.0524 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3993 | test_acc: 0.3968 | Time: 6.5949 s
>>> Epoch [ 3104/10000]
train_loss: 2.0523 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3994 | test_acc: 0.3969 | Time: 6.5928 s
>>> Epoch [ 3105/10000]
train_loss: 2.0523 | train_acc: 0.4207 | val_loss: 2.0687 | val_acc: 0.3994 | test_acc: 0.3969 | Time: 6.7622 s
>>> Epoch [ 3106/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0687 | val_acc: 0.3994 | test_acc: 0.3970 | Time: 6.4682 s
>>> Epoch [ 3107/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0687 | val_acc: 0.3994 | test_acc: 0.3970 | Time: 6.8906 s
>>> Epoch [ 3108/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0687 | val_acc: 0.3994 | test_acc: 0.3970 | Time: 6.8860 s
>>> Epoch [ 3109/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0687 | val_acc: 0.3994 | test_acc: 0.3971 | Time: 6.7470 s
>>> Epoch [ 3110/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0687 | val_acc: 0.3994 | test_acc: 0.3971 | Time: 6.6535 s
>>> Epoch [ 3111/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0687 | val_acc: 0.3994 | test_acc: 0.3971 | Time: 6.1138 s
>>> Epoch [ 3112/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3971 | Time: 6.0935 s
>>> Epoch [ 3113/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3972 | Time: 6.0461 s
>>> Epoch [ 3114/10000]
train_loss: 2.0523 | train_acc: 0.4208 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3972 | Time: 5.9051 s
>>> Epoch [ 3115/10000]
train_loss: 2.0522 | train_acc: 0.4208 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3972 | Time: 6.0287 s
>>> Epoch [ 3116/10000]
train_loss: 2.0522 | train_acc: 0.4208 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3972 | Time: 5.8076 s
>>> Epoch [ 3117/10000]
train_loss: 2.0522 | train_acc: 0.4208 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3972 | Time: 5.8266 s
>>> Epoch [ 3118/10000]
train_loss: 2.0522 | train_acc: 0.4208 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 5.8124 s
>>> Epoch [ 3119/10000]
train_loss: 2.0522 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 6.1460 s
>>> Epoch [ 3120/10000]
train_loss: 2.0522 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 5.7782 s
>>> Epoch [ 3121/10000]
train_loss: 2.0522 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 5.9430 s
>>> Epoch [ 3122/10000]
train_loss: 2.0522 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 5.9263 s
>>> Epoch [ 3123/10000]
train_loss: 2.0522 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 5.8133 s
>>> Epoch [ 3124/10000]
train_loss: 2.0522 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 6.0028 s
>>> Epoch [ 3125/10000]
train_loss: 2.0522 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 5.7900 s
>>> Epoch [ 3126/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3993 | test_acc: 0.3972 | Time: 5.8144 s
>>> Epoch [ 3127/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0686 | val_acc: 0.3992 | test_acc: 0.3972 | Time: 6.1191 s
>>> Epoch [ 3128/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0685 | val_acc: 0.3992 | test_acc: 0.3972 | Time: 6.0416 s
>>> Epoch [ 3129/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0685 | val_acc: 0.3992 | test_acc: 0.3972 | Time: 5.8998 s
>>> Epoch [ 3130/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0685 | val_acc: 0.3992 | test_acc: 0.3972 | Time: 5.7815 s
>>> Epoch [ 3131/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0685 | val_acc: 0.3992 | test_acc: 0.3971 | Time: 5.8463 s
>>> Epoch [ 3132/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0685 | val_acc: 0.3992 | test_acc: 0.3973 | Time: 6.0199 s
>>> Epoch [ 3133/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0685 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 5.8754 s
>>> Epoch [ 3134/10000]
train_loss: 2.0521 | train_acc: 0.4209 | val_loss: 2.0685 | val_acc: 0.3993 | test_acc: 0.3973 | Time: 10.6111 s
>>> Epoch [ 3135/10000]
train_loss: 2.0521 | train_acc: 0.4210 | val_loss: 2.0685 | val_acc: 0.3993 | test_acc: 0.3974 | Time: 10.7220 s
>>> Epoch [ 3136/10000]
train_loss: 2.0521 | train_acc: 0.4210 | val_loss: 2.0685 | val_acc: 0.3993 | test_acc: 0.3974 | Time: 11.2734 s
>>> Epoch [ 3137/10000]
train_loss: 2.0521 | train_acc: 0.4210 | val_loss: 2.0685 | val_acc: 0.3993 | test_acc: 0.3974 | Time: 10.4432 s
>>> Epoch [ 3138/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0685 | val_acc: 0.3994 | test_acc: 0.3974 | Time: 6.8954 s
>>> Epoch [ 3139/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0685 | val_acc: 0.3995 | test_acc: 0.3975 | Time: 6.2643 s
>>> Epoch [ 3140/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0685 | val_acc: 0.3995 | test_acc: 0.3975 | Time: 6.9189 s
>>> Epoch [ 3141/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0685 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.5138 s
>>> Epoch [ 3142/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0685 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 9.6000 s
>>> Epoch [ 3143/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 9.7844 s
>>> Epoch [ 3144/10000]
train_loss: 2.0520 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.4828 s
>>> Epoch [ 3145/10000]
train_loss: 2.0520 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.8874 s
>>> Epoch [ 3146/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3975 | Time: 6.7572 s
>>> Epoch [ 3147/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3975 | Time: 7.3689 s
>>> Epoch [ 3148/10000]
train_loss: 2.0520 | train_acc: 0.4210 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3975 | Time: 7.0971 s
>>> Epoch [ 3149/10000]
train_loss: 2.0519 | train_acc: 0.4210 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3975 | Time: 6.9360 s
>>> Epoch [ 3150/10000]
train_loss: 2.0519 | train_acc: 0.4210 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3975 | Time: 7.1863 s
>>> Epoch [ 3151/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3975 | Time: 6.8224 s
>>> Epoch [ 3152/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.7131 s
>>> Epoch [ 3153/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.8516 s
>>> Epoch [ 3154/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.6694 s
>>> Epoch [ 3155/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.8089 s
>>> Epoch [ 3156/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.7993 s
>>> Epoch [ 3157/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.9074 s
>>> Epoch [ 3158/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0684 | val_acc: 0.3997 | test_acc: 0.3976 | Time: 6.9051 s
>>> Epoch [ 3159/10000]
train_loss: 2.0519 | train_acc: 0.4211 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3976 | Time: 6.7852 s
>>> Epoch [ 3160/10000]
train_loss: 2.0518 | train_acc: 0.4211 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3975 | Time: 6.9968 s
>>> Epoch [ 3161/10000]
train_loss: 2.0518 | train_acc: 0.4211 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3976 | Time: 7.0743 s
>>> Epoch [ 3162/10000]
train_loss: 2.0518 | train_acc: 0.4212 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3976 | Time: 7.0399 s
>>> Epoch [ 3163/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3976 | Time: 6.9527 s
>>> Epoch [ 3164/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 7.1131 s
>>> Epoch [ 3165/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.9416 s
>>> Epoch [ 3166/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 6.7007 s
>>> Epoch [ 3167/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3976 | Time: 6.7783 s
>>> Epoch [ 3168/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3975 | Time: 7.0500 s
>>> Epoch [ 3169/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3975 | Time: 6.7234 s
>>> Epoch [ 3170/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3975 | Time: 6.7268 s
>>> Epoch [ 3171/10000]
train_loss: 2.0518 | train_acc: 0.4213 | val_loss: 2.0683 | val_acc: 0.3997 | test_acc: 0.3975 | Time: 6.9506 s
>>> Epoch [ 3172/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0683 | val_acc: 0.3996 | test_acc: 0.3975 | Time: 11.5063 s
>>> Epoch [ 3173/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0683 | val_acc: 0.3996 | test_acc: 0.3975 | Time: 10.7217 s
>>> Epoch [ 3174/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0683 | val_acc: 0.3996 | test_acc: 0.3974 | Time: 9.1591 s
>>> Epoch [ 3175/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0682 | val_acc: 0.3996 | test_acc: 0.3974 | Time: 8.9956 s
>>> Epoch [ 3176/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0682 | val_acc: 0.3996 | test_acc: 0.3974 | Time: 8.8262 s
>>> Epoch [ 3177/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0682 | val_acc: 0.3996 | test_acc: 0.3974 | Time: 8.8374 s
>>> Epoch [ 3178/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0682 | val_acc: 0.3996 | test_acc: 0.3974 | Time: 8.9165 s
>>> Epoch [ 3179/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0682 | val_acc: 0.3996 | test_acc: 0.3974 | Time: 8.7543 s
>>> Epoch [ 3180/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3973 | Time: 8.7001 s
>>> Epoch [ 3181/10000]
train_loss: 2.0517 | train_acc: 0.4214 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3973 | Time: 7.7509 s
>>> Epoch [ 3182/10000]
train_loss: 2.0517 | train_acc: 0.4215 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3974 | Time: 7.6309 s
>>> Epoch [ 3183/10000]
train_loss: 2.0516 | train_acc: 0.4215 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3974 | Time: 7.3501 s
>>> Epoch [ 3184/10000]
train_loss: 2.0516 | train_acc: 0.4215 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3975 | Time: 6.9965 s
>>> Epoch [ 3185/10000]
train_loss: 2.0516 | train_acc: 0.4215 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3975 | Time: 6.4150 s
>>> Epoch [ 3186/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3975 | Time: 6.3320 s
>>> Epoch [ 3187/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3975 | Time: 6.4171 s
>>> Epoch [ 3188/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0682 | val_acc: 0.3994 | test_acc: 0.3975 | Time: 11.3968 s
>>> Epoch [ 3189/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0682 | val_acc: 0.3994 | test_acc: 0.3975 | Time: 8.4546 s
>>> Epoch [ 3190/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0682 | val_acc: 0.3995 | test_acc: 0.3975 | Time: 7.2547 s
>>> Epoch [ 3191/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0681 | val_acc: 0.3995 | test_acc: 0.3976 | Time: 7.4014 s
>>> Epoch [ 3192/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0681 | val_acc: 0.3995 | test_acc: 0.3976 | Time: 7.4862 s
>>> Epoch [ 3193/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0681 | val_acc: 0.3995 | test_acc: 0.3976 | Time: 7.1964 s
>>> Epoch [ 3194/10000]
train_loss: 2.0516 | train_acc: 0.4216 | val_loss: 2.0681 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 7.1135 s
>>> Epoch [ 3195/10000]
train_loss: 2.0515 | train_acc: 0.4216 | val_loss: 2.0681 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 7.2756 s
>>> Epoch [ 3196/10000]
train_loss: 2.0515 | train_acc: 0.4216 | val_loss: 2.0681 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 7.4834 s
>>> Epoch [ 3197/10000]
train_loss: 2.0515 | train_acc: 0.4216 | val_loss: 2.0681 | val_acc: 0.3996 | test_acc: 0.3976 | Time: 7.1743 s
>>> Epoch [ 3198/10000]
train_loss: 2.0515 | train_acc: 0.4216 | val_loss: 2.0681 | val_acc: 0.3998 | test_acc: 0.3976 | Time: 7.0802 s
>>> Epoch [ 3199/10000]
train_loss: 2.0515 | train_acc: 0.4217 | val_loss: 2.0681 | val_acc: 0.3998 | test_acc: 0.3976 | Time: 6.6023 s
>>> Epoch [ 3200/10000]
train_loss: 2.0515 | train_acc: 0.4217 | val_loss: 2.0681 | val_acc: 0.3999 | test_acc: 0.3977 | Time: 6.3738 s
>>> Epoch [ 3201/10000]
train_loss: 2.0515 | train_acc: 0.4217 | val_loss: 2.0681 | val_acc: 0.3999 | test_acc: 0.3977 | Time: 6.3439 s
>>> Epoch [ 3202/10000]
train_loss: 2.0515 | train_acc: 0.4218 | val_loss: 2.0681 | val_acc: 0.3999 | test_acc: 0.3977 | Time: 6.8314 s
>>> Epoch [ 3203/10000]
train_loss: 2.0515 | train_acc: 0.4218 | val_loss: 2.0681 | val_acc: 0.3999 | test_acc: 0.3977 | Time: 6.5616 s
>>> Epoch [ 3204/10000]
train_loss: 2.0515 | train_acc: 0.4218 | val_loss: 2.0681 | val_acc: 0.3999 | test_acc: 0.3978 | Time: 6.8112 s
>>> Epoch [ 3205/10000]
train_loss: 2.0515 | train_acc: 0.4218 | val_loss: 2.0681 | val_acc: 0.3999 | test_acc: 0.3978 | Time: 6.7768 s
>>> Epoch [ 3206/10000]
train_loss: 2.0515 | train_acc: 0.4218 | val_loss: 2.0681 | val_acc: 0.3999 | test_acc: 0.3978 | Time: 6.5784 s
>>> Epoch [ 3207/10000]
train_loss: 2.0514 | train_acc: 0.4218 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3978 | Time: 6.5764 s
>>> Epoch [ 3208/10000]
train_loss: 2.0514 | train_acc: 0.4218 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3978 | Time: 7.1464 s
>>> Epoch [ 3209/10000]
train_loss: 2.0514 | train_acc: 0.4218 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3978 | Time: 7.1421 s
>>> Epoch [ 3210/10000]
train_loss: 2.0514 | train_acc: 0.4218 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3978 | Time: 6.8142 s
>>> Epoch [ 3211/10000]
train_loss: 2.0514 | train_acc: 0.4218 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3979 | Time: 7.2963 s
>>> Epoch [ 3212/10000]
train_loss: 2.0514 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3980 | Time: 7.0076 s
>>> Epoch [ 3213/10000]
train_loss: 2.0514 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3980 | Time: 6.7848 s
>>> Epoch [ 3214/10000]
train_loss: 2.0514 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3980 | Time: 7.0607 s
>>> Epoch [ 3215/10000]
train_loss: 2.0514 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3979 | Time: 7.1032 s
>>> Epoch [ 3216/10000]
train_loss: 2.0514 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3979 | Time: 7.1600 s
>>> Epoch [ 3217/10000]
train_loss: 2.0514 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.3999 | test_acc: 0.3980 | Time: 7.3631 s
>>> Epoch [ 3218/10000]
train_loss: 2.0513 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.4000 | test_acc: 0.3980 | Time: 7.1859 s
>>> Epoch [ 3219/10000]
train_loss: 2.0513 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.4001 | test_acc: 0.3980 | Time: 7.1277 s
>>> Epoch [ 3220/10000]
train_loss: 2.0513 | train_acc: 0.4219 | val_loss: 2.0680 | val_acc: 0.4001 | test_acc: 0.3980 | Time: 6.8444 s
>>> Epoch [ 3221/10000]
train_loss: 2.0513 | train_acc: 0.4220 | val_loss: 2.0680 | val_acc: 0.4001 | test_acc: 0.3980 | Time: 7.0219 s
>>> Epoch [ 3222/10000]
train_loss: 2.0513 | train_acc: 0.4220 | val_loss: 2.0680 | val_acc: 0.4001 | test_acc: 0.3980 | Time: 7.0694 s
>>> Epoch [ 3223/10000]
train_loss: 2.0513 | train_acc: 0.4220 | val_loss: 2.0679 | val_acc: 0.4001 | test_acc: 0.3980 | Time: 6.9540 s
>>> Epoch [ 3224/10000]
train_loss: 2.0513 | train_acc: 0.4221 | val_loss: 2.0679 | val_acc: 0.4002 | test_acc: 0.3980 | Time: 7.4279 s
>>> Epoch [ 3225/10000]
train_loss: 2.0513 | train_acc: 0.4221 | val_loss: 2.0679 | val_acc: 0.4002 | test_acc: 0.3980 | Time: 6.9325 s
>>> Epoch [ 3226/10000]
train_loss: 2.0513 | train_acc: 0.4221 | val_loss: 2.0679 | val_acc: 0.4004 | test_acc: 0.3980 | Time: 7.2862 s
>>> Epoch [ 3227/10000]
train_loss: 2.0513 | train_acc: 0.4221 | val_loss: 2.0679 | val_acc: 0.4004 | test_acc: 0.3980 | Time: 7.2146 s
>>> Epoch [ 3228/10000]
train_loss: 2.0513 | train_acc: 0.4222 | val_loss: 2.0679 | val_acc: 0.4004 | test_acc: 0.3980 | Time: 7.1444 s
>>> Epoch [ 3229/10000]
train_loss: 2.0513 | train_acc: 0.4222 | val_loss: 2.0679 | val_acc: 0.4004 | test_acc: 0.3980 | Time: 7.1782 s
>>> Epoch [ 3230/10000]
train_loss: 2.0512 | train_acc: 0.4222 | val_loss: 2.0679 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 6.7762 s
>>> Epoch [ 3231/10000]
train_loss: 2.0512 | train_acc: 0.4222 | val_loss: 2.0679 | val_acc: 0.4004 | test_acc: 0.3980 | Time: 7.5703 s
>>> Epoch [ 3232/10000]
train_loss: 2.0512 | train_acc: 0.4222 | val_loss: 2.0679 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 10.7241 s
>>> Epoch [ 3233/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0679 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 10.3552 s
>>> Epoch [ 3234/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0679 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 9.7588 s
>>> Epoch [ 3235/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0679 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 6.4911 s
>>> Epoch [ 3236/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0679 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 6.9714 s
>>> Epoch [ 3237/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0679 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 6.7123 s
>>> Epoch [ 3238/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0679 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 6.8281 s
>>> Epoch [ 3239/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0678 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 7.2117 s
>>> Epoch [ 3240/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0678 | val_acc: 0.4005 | test_acc: 0.3980 | Time: 7.0176 s
>>> Epoch [ 3241/10000]
train_loss: 2.0512 | train_acc: 0.4223 | val_loss: 2.0678 | val_acc: 0.4005 | test_acc: 0.3979 | Time: 7.0240 s
>>> Epoch [ 3242/10000]
train_loss: 2.0511 | train_acc: 0.4223 | val_loss: 2.0678 | val_acc: 0.4005 | test_acc: 0.3979 | Time: 7.0243 s
>>> Epoch [ 3243/10000]
train_loss: 2.0511 | train_acc: 0.4223 | val_loss: 2.0678 | val_acc: 0.4005 | test_acc: 0.3979 | Time: 6.9255 s
>>> Epoch [ 3244/10000]
train_loss: 2.0511 | train_acc: 0.4223 | val_loss: 2.0678 | val_acc: 0.4006 | test_acc: 0.3980 | Time: 7.3288 s
>>> Epoch [ 3245/10000]
train_loss: 2.0511 | train_acc: 0.4223 | val_loss: 2.0678 | val_acc: 0.4006 | test_acc: 0.3980 | Time: 7.3428 s
>>> Epoch [ 3246/10000]
train_loss: 2.0511 | train_acc: 0.4224 | val_loss: 2.0678 | val_acc: 0.4007 | test_acc: 0.3980 | Time: 7.1000 s
>>> Epoch [ 3247/10000]
train_loss: 2.0511 | train_acc: 0.4224 | val_loss: 2.0678 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 7.4616 s
>>> Epoch [ 3248/10000]
train_loss: 2.0511 | train_acc: 0.4224 | val_loss: 2.0678 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 7.1018 s
>>> Epoch [ 3249/10000]
train_loss: 2.0511 | train_acc: 0.4224 | val_loss: 2.0678 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 7.0684 s
>>> Epoch [ 3250/10000]
train_loss: 2.0511 | train_acc: 0.4224 | val_loss: 2.0678 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 7.0865 s
>>> Epoch [ 3251/10000]
train_loss: 2.0511 | train_acc: 0.4224 | val_loss: 2.0678 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 7.0896 s
>>> Epoch [ 3252/10000]
train_loss: 2.0511 | train_acc: 0.4224 | val_loss: 2.0678 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 6.9683 s
>>> Epoch [ 3253/10000]
train_loss: 2.0511 | train_acc: 0.4223 | val_loss: 2.0678 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 6.9069 s
>>> Epoch [ 3254/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0678 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 6.9115 s
>>> Epoch [ 3255/10000]
train_loss: 2.0510 | train_acc: 0.4223 | val_loss: 2.0677 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 7.1465 s
>>> Epoch [ 3256/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 7.5955 s
>>> Epoch [ 3257/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4008 | test_acc: 0.3980 | Time: 7.3811 s
>>> Epoch [ 3258/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4009 | test_acc: 0.3979 | Time: 7.2390 s
>>> Epoch [ 3259/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4009 | test_acc: 0.3979 | Time: 7.2028 s
>>> Epoch [ 3260/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4009 | test_acc: 0.3979 | Time: 7.0509 s
>>> Epoch [ 3261/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4009 | test_acc: 0.3980 | Time: 7.0692 s
>>> Epoch [ 3262/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4009 | test_acc: 0.3980 | Time: 7.1479 s
>>> Epoch [ 3263/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4009 | test_acc: 0.3980 | Time: 6.9402 s
>>> Epoch [ 3264/10000]
train_loss: 2.0510 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4010 | test_acc: 0.3980 | Time: 11.3000 s
>>> Epoch [ 3265/10000]
train_loss: 2.0509 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4010 | test_acc: 0.3980 | Time: 10.0657 s
>>> Epoch [ 3266/10000]
train_loss: 2.0509 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4010 | test_acc: 0.3980 | Time: 11.0994 s
>>> Epoch [ 3267/10000]
train_loss: 2.0509 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4010 | test_acc: 0.3979 | Time: 6.4544 s
>>> Epoch [ 3268/10000]
train_loss: 2.0509 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4010 | test_acc: 0.3979 | Time: 6.9542 s
>>> Epoch [ 3269/10000]
train_loss: 2.0509 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4010 | test_acc: 0.3979 | Time: 6.9471 s
>>> Epoch [ 3270/10000]
train_loss: 2.0509 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4010 | test_acc: 0.3979 | Time: 7.1620 s
>>> Epoch [ 3271/10000]
train_loss: 2.0509 | train_acc: 0.4224 | val_loss: 2.0677 | val_acc: 0.4010 | test_acc: 0.3980 | Time: 7.4011 s
>>> Epoch [ 3272/10000]
train_loss: 2.0509 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4010 | test_acc: 0.3980 | Time: 7.2192 s
>>> Epoch [ 3273/10000]
train_loss: 2.0509 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4010 | test_acc: 0.3980 | Time: 7.1739 s
>>> Epoch [ 3274/10000]
train_loss: 2.0509 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3980 | Time: 7.0125 s
>>> Epoch [ 3275/10000]
train_loss: 2.0509 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3980 | Time: 7.1482 s
>>> Epoch [ 3276/10000]
train_loss: 2.0509 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.4750 s
>>> Epoch [ 3277/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.1442 s
>>> Epoch [ 3278/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.2210 s
>>> Epoch [ 3279/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.3617 s
>>> Epoch [ 3280/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.4111 s
>>> Epoch [ 3281/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.2282 s
>>> Epoch [ 3282/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.4887 s
>>> Epoch [ 3283/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.3894 s
>>> Epoch [ 3284/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3980 | Time: 7.0832 s
>>> Epoch [ 3285/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.4495 s
>>> Epoch [ 3286/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.2993 s
>>> Epoch [ 3287/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.3120 s
>>> Epoch [ 3288/10000]
train_loss: 2.0508 | train_acc: 0.4225 | val_loss: 2.0676 | val_acc: 0.4011 | test_acc: 0.3981 | Time: 7.4180 s
>>> Epoch [ 3289/10000]
train_loss: 2.0507 | train_acc: 0.4225 | val_loss: 2.0675 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.3378 s
>>> Epoch [ 3290/10000]
train_loss: 2.0507 | train_acc: 0.4225 | val_loss: 2.0675 | val_acc: 0.4012 | test_acc: 0.3982 | Time: 7.2479 s
>>> Epoch [ 3291/10000]
train_loss: 2.0507 | train_acc: 0.4225 | val_loss: 2.0675 | val_acc: 0.4012 | test_acc: 0.3982 | Time: 7.1888 s
>>> Epoch [ 3292/10000]
train_loss: 2.0507 | train_acc: 0.4225 | val_loss: 2.0675 | val_acc: 0.4012 | test_acc: 0.3982 | Time: 7.4366 s
>>> Epoch [ 3293/10000]
train_loss: 2.0507 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4013 | test_acc: 0.3982 | Time: 7.4459 s
>>> Epoch [ 3294/10000]
train_loss: 2.0507 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4014 | test_acc: 0.3982 | Time: 8.6133 s
>>> Epoch [ 3295/10000]
train_loss: 2.0507 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4013 | test_acc: 0.3982 | Time: 10.7536 s
>>> Epoch [ 3296/10000]
train_loss: 2.0507 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4013 | test_acc: 0.3982 | Time: 11.5166 s
>>> Epoch [ 3297/10000]
train_loss: 2.0507 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4014 | test_acc: 0.3982 | Time: 8.8298 s
>>> Epoch [ 3298/10000]
train_loss: 2.0507 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4013 | test_acc: 0.3982 | Time: 6.8082 s
>>> Epoch [ 3299/10000]
train_loss: 2.0507 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4014 | test_acc: 0.3981 | Time: 7.1167 s
>>> Epoch [ 3300/10000]
train_loss: 2.0507 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4014 | test_acc: 0.3981 | Time: 6.8583 s
>>> Epoch [ 3301/10000]
train_loss: 2.0506 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4014 | test_acc: 0.3981 | Time: 6.9775 s
>>> Epoch [ 3302/10000]
train_loss: 2.0506 | train_acc: 0.4226 | val_loss: 2.0675 | val_acc: 0.4014 | test_acc: 0.3981 | Time: 7.1425 s
>>> Epoch [ 3303/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0675 | val_acc: 0.4013 | test_acc: 0.3981 | Time: 7.5419 s
>>> Epoch [ 3304/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0675 | val_acc: 0.4013 | test_acc: 0.3981 | Time: 7.2868 s
>>> Epoch [ 3305/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0675 | val_acc: 0.4013 | test_acc: 0.3981 | Time: 7.1529 s
>>> Epoch [ 3306/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.4484 s
>>> Epoch [ 3307/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.3495 s
>>> Epoch [ 3308/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.3890 s
>>> Epoch [ 3309/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.1916 s
>>> Epoch [ 3310/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.4210 s
>>> Epoch [ 3311/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.6285 s
>>> Epoch [ 3312/10000]
train_loss: 2.0506 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.4539 s
>>> Epoch [ 3313/10000]
train_loss: 2.0505 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.7090 s
>>> Epoch [ 3314/10000]
train_loss: 2.0505 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.3778 s
>>> Epoch [ 3315/10000]
train_loss: 2.0505 | train_acc: 0.4226 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.3374 s
>>> Epoch [ 3316/10000]
train_loss: 2.0505 | train_acc: 0.4226 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.3687 s
>>> Epoch [ 3317/10000]
train_loss: 2.0505 | train_acc: 0.4226 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3981 | Time: 7.6031 s
>>> Epoch [ 3318/10000]
train_loss: 2.0505 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3982 | Time: 7.7105 s
>>> Epoch [ 3319/10000]
train_loss: 2.0505 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3982 | Time: 7.6077 s
>>> Epoch [ 3320/10000]
train_loss: 2.0505 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3982 | Time: 7.4350 s
>>> Epoch [ 3321/10000]
train_loss: 2.0505 | train_acc: 0.4227 | val_loss: 2.0674 | val_acc: 0.4012 | test_acc: 0.3982 | Time: 7.2971 s
>>> Epoch [ 3322/10000]
train_loss: 2.0505 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4013 | test_acc: 0.3982 | Time: 7.2175 s
>>> Epoch [ 3323/10000]
train_loss: 2.0505 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4013 | test_acc: 0.3982 | Time: 7.2281 s
>>> Epoch [ 3324/10000]
train_loss: 2.0505 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3983 | Time: 6.8675 s
>>> Epoch [ 3325/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3983 | Time: 11.6585 s
>>> Epoch [ 3326/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3983 | Time: 10.6942 s
>>> Epoch [ 3327/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3983 | Time: 10.5121 s
>>> Epoch [ 3328/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3983 | Time: 6.9299 s
>>> Epoch [ 3329/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3983 | Time: 7.3176 s
>>> Epoch [ 3330/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3983 | Time: 7.2979 s
>>> Epoch [ 3331/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3982 | Time: 7.2645 s
>>> Epoch [ 3332/10000]
train_loss: 2.0504 | train_acc: 0.4229 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3982 | Time: 7.2782 s
>>> Epoch [ 3333/10000]
train_loss: 2.0504 | train_acc: 0.4229 | val_loss: 2.0673 | val_acc: 0.4013 | test_acc: 0.3982 | Time: 7.5579 s
>>> Epoch [ 3334/10000]
train_loss: 2.0504 | train_acc: 0.4229 | val_loss: 2.0673 | val_acc: 0.4013 | test_acc: 0.3982 | Time: 7.3495 s
>>> Epoch [ 3335/10000]
train_loss: 2.0504 | train_acc: 0.4229 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3982 | Time: 7.4872 s
>>> Epoch [ 3336/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3982 | Time: 7.6294 s
>>> Epoch [ 3337/10000]
train_loss: 2.0504 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4014 | test_acc: 0.3983 | Time: 7.1904 s
>>> Epoch [ 3338/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4015 | test_acc: 0.3983 | Time: 7.3184 s
>>> Epoch [ 3339/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0673 | val_acc: 0.4015 | test_acc: 0.3983 | Time: 7.3716 s
>>> Epoch [ 3340/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3983 | Time: 7.1951 s
>>> Epoch [ 3341/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3983 | Time: 7.4941 s
>>> Epoch [ 3342/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3983 | Time: 7.3042 s
>>> Epoch [ 3343/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3983 | Time: 7.2634 s
>>> Epoch [ 3344/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3984 | Time: 7.2650 s
>>> Epoch [ 3345/10000]
train_loss: 2.0503 | train_acc: 0.4227 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3984 | Time: 7.1696 s
>>> Epoch [ 3346/10000]
train_loss: 2.0503 | train_acc: 0.4227 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3984 | Time: 7.6936 s
>>> Epoch [ 3347/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3984 | Time: 7.3258 s
>>> Epoch [ 3348/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4015 | test_acc: 0.3984 | Time: 7.5765 s
>>> Epoch [ 3349/10000]
train_loss: 2.0503 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4016 | test_acc: 0.3984 | Time: 7.6448 s
>>> Epoch [ 3350/10000]
train_loss: 2.0502 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4016 | test_acc: 0.3984 | Time: 7.5095 s
>>> Epoch [ 3351/10000]
train_loss: 2.0502 | train_acc: 0.4228 | val_loss: 2.0672 | val_acc: 0.4016 | test_acc: 0.3984 | Time: 7.7313 s
>>> Epoch [ 3352/10000]
train_loss: 2.0502 | train_acc: 0.4229 | val_loss: 2.0672 | val_acc: 0.4016 | test_acc: 0.3983 | Time: 7.3864 s
>>> Epoch [ 3353/10000]
train_loss: 2.0502 | train_acc: 0.4229 | val_loss: 2.0672 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 7.7084 s
>>> Epoch [ 3354/10000]
train_loss: 2.0502 | train_acc: 0.4229 | val_loss: 2.0672 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 6.6657 s
>>> Epoch [ 3355/10000]
train_loss: 2.0502 | train_acc: 0.4229 | val_loss: 2.0672 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 7.0019 s
>>> Epoch [ 3356/10000]
train_loss: 2.0502 | train_acc: 0.4229 | val_loss: 2.0672 | val_acc: 0.4018 | test_acc: 0.3983 | Time: 7.3935 s
>>> Epoch [ 3357/10000]
train_loss: 2.0502 | train_acc: 0.4229 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 7.4396 s
>>> Epoch [ 3358/10000]
train_loss: 2.0502 | train_acc: 0.4230 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 9.0743 s
>>> Epoch [ 3359/10000]
train_loss: 2.0502 | train_acc: 0.4230 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 10.6461 s
>>> Epoch [ 3360/10000]
train_loss: 2.0502 | train_acc: 0.4230 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 7.1127 s
>>> Epoch [ 3361/10000]
train_loss: 2.0502 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.5065 s
>>> Epoch [ 3362/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 8.8391 s
>>> Epoch [ 3363/10000]
train_loss: 2.0501 | train_acc: 0.4230 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.5866 s
>>> Epoch [ 3364/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.5070 s
>>> Epoch [ 3365/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.5634 s
>>> Epoch [ 3366/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.7384 s
>>> Epoch [ 3367/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.6237 s
>>> Epoch [ 3368/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.7238 s
>>> Epoch [ 3369/10000]
train_loss: 2.0501 | train_acc: 0.4230 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.5921 s
>>> Epoch [ 3370/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3984 | Time: 7.8723 s
>>> Epoch [ 3371/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 7.8713 s
>>> Epoch [ 3372/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 7.5966 s
>>> Epoch [ 3373/10000]
train_loss: 2.0501 | train_acc: 0.4231 | val_loss: 2.0671 | val_acc: 0.4017 | test_acc: 0.3983 | Time: 7.6066 s
>>> Epoch [ 3374/10000]
train_loss: 2.0500 | train_acc: 0.4231 | val_loss: 2.0670 | val_acc: 0.4018 | test_acc: 0.3983 | Time: 7.5209 s
>>> Epoch [ 3375/10000]
train_loss: 2.0500 | train_acc: 0.4231 | val_loss: 2.0670 | val_acc: 0.4018 | test_acc: 0.3983 | Time: 7.7167 s
>>> Epoch [ 3376/10000]
train_loss: 2.0500 | train_acc: 0.4231 | val_loss: 2.0670 | val_acc: 0.4019 | test_acc: 0.3983 | Time: 7.3050 s
>>> Epoch [ 3377/10000]
train_loss: 2.0500 | train_acc: 0.4231 | val_loss: 2.0670 | val_acc: 0.4019 | test_acc: 0.3984 | Time: 7.5580 s
>>> Epoch [ 3378/10000]
train_loss: 2.0500 | train_acc: 0.4231 | val_loss: 2.0670 | val_acc: 0.4019 | test_acc: 0.3984 | Time: 7.7959 s
>>> Epoch [ 3379/10000]
train_loss: 2.0500 | train_acc: 0.4231 | val_loss: 2.0670 | val_acc: 0.4019 | test_acc: 0.3984 | Time: 7.5538 s
>>> Epoch [ 3380/10000]
train_loss: 2.0500 | train_acc: 0.4231 | val_loss: 2.0670 | val_acc: 0.4018 | test_acc: 0.3984 | Time: 7.5418 s
>>> Epoch [ 3381/10000]
train_loss: 2.0500 | train_acc: 0.4231 | val_loss: 2.0670 | val_acc: 0.4018 | test_acc: 0.3984 | Time: 7.4713 s
>>> Epoch [ 3382/10000]
train_loss: 2.0500 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4018 | test_acc: 0.3983 | Time: 7.3196 s
>>> Epoch [ 3383/10000]
train_loss: 2.0500 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4019 | test_acc: 0.3984 | Time: 7.5511 s
>>> Epoch [ 3384/10000]
train_loss: 2.0500 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4019 | test_acc: 0.3984 | Time: 7.4670 s
>>> Epoch [ 3385/10000]
train_loss: 2.0500 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4019 | test_acc: 0.3984 | Time: 9.9529 s
>>> Epoch [ 3386/10000]
train_loss: 2.0500 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4020 | test_acc: 0.3984 | Time: 12.1499 s
>>> Epoch [ 3387/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4020 | test_acc: 0.3983 | Time: 9.4703 s
>>> Epoch [ 3388/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4020 | test_acc: 0.3983 | Time: 9.0315 s
>>> Epoch [ 3389/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4020 | test_acc: 0.3983 | Time: 8.8153 s
>>> Epoch [ 3390/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4021 | test_acc: 0.3983 | Time: 8.8264 s
>>> Epoch [ 3391/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0670 | val_acc: 0.4020 | test_acc: 0.3983 | Time: 9.0970 s
>>> Epoch [ 3392/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0669 | val_acc: 0.4020 | test_acc: 0.3983 | Time: 9.0160 s
>>> Epoch [ 3393/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0669 | val_acc: 0.4021 | test_acc: 0.3983 | Time: 9.0344 s
>>> Epoch [ 3394/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0669 | val_acc: 0.4022 | test_acc: 0.3983 | Time: 8.3689 s
>>> Epoch [ 3395/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0669 | val_acc: 0.4022 | test_acc: 0.3983 | Time: 8.1563 s
>>> Epoch [ 3396/10000]
train_loss: 2.0499 | train_acc: 0.4233 | val_loss: 2.0669 | val_acc: 0.4022 | test_acc: 0.3983 | Time: 8.7225 s
>>> Epoch [ 3397/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0669 | val_acc: 0.4022 | test_acc: 0.3983 | Time: 11.6091 s
>>> Epoch [ 3398/10000]
train_loss: 2.0499 | train_acc: 0.4232 | val_loss: 2.0669 | val_acc: 0.4023 | test_acc: 0.3983 | Time: 7.6895 s
>>> Epoch [ 3399/10000]
train_loss: 2.0498 | train_acc: 0.4233 | val_loss: 2.0669 | val_acc: 0.4023 | test_acc: 0.3983 | Time: 7.6485 s
>>> Epoch [ 3400/10000]
train_loss: 2.0498 | train_acc: 0.4233 | val_loss: 2.0669 | val_acc: 0.4024 | test_acc: 0.3983 | Time: 7.8922 s
>>> Epoch [ 3401/10000]
train_loss: 2.0498 | train_acc: 0.4233 | val_loss: 2.0669 | val_acc: 0.4024 | test_acc: 0.3983 | Time: 7.7525 s
>>> Epoch [ 3402/10000]
train_loss: 2.0498 | train_acc: 0.4233 | val_loss: 2.0669 | val_acc: 0.4025 | test_acc: 0.3983 | Time: 7.8868 s
>>> Epoch [ 3403/10000]
train_loss: 2.0498 | train_acc: 0.4233 | val_loss: 2.0669 | val_acc: 0.4025 | test_acc: 0.3983 | Time: 7.8231 s
>>> Epoch [ 3404/10000]
train_loss: 2.0498 | train_acc: 0.4234 | val_loss: 2.0669 | val_acc: 0.4025 | test_acc: 0.3982 | Time: 7.6552 s
>>> Epoch [ 3405/10000]
train_loss: 2.0498 | train_acc: 0.4234 | val_loss: 2.0669 | val_acc: 0.4025 | test_acc: 0.3982 | Time: 7.5728 s
>>> Epoch [ 3406/10000]
train_loss: 2.0498 | train_acc: 0.4234 | val_loss: 2.0669 | val_acc: 0.4025 | test_acc: 0.3982 | Time: 7.3471 s
>>> Epoch [ 3407/10000]
train_loss: 2.0498 | train_acc: 0.4234 | val_loss: 2.0669 | val_acc: 0.4025 | test_acc: 0.3983 | Time: 7.3520 s
>>> Epoch [ 3408/10000]
train_loss: 2.0498 | train_acc: 0.4234 | val_loss: 2.0669 | val_acc: 0.4025 | test_acc: 0.3983 | Time: 7.1973 s
>>> Epoch [ 3409/10000]
train_loss: 2.0498 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4025 | test_acc: 0.3983 | Time: 7.5066 s
>>> Epoch [ 3410/10000]
train_loss: 2.0498 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4025 | test_acc: 0.3983 | Time: 7.4280 s
>>> Epoch [ 3411/10000]
train_loss: 2.0498 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4026 | test_acc: 0.3984 | Time: 7.3398 s
>>> Epoch [ 3412/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4026 | test_acc: 0.3984 | Time: 7.5285 s
>>> Epoch [ 3413/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4026 | test_acc: 0.3983 | Time: 7.3455 s
>>> Epoch [ 3414/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4026 | test_acc: 0.3983 | Time: 7.2461 s
>>> Epoch [ 3415/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4026 | test_acc: 0.3983 | Time: 7.2023 s
>>> Epoch [ 3416/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4026 | test_acc: 0.3982 | Time: 6.8598 s
>>> Epoch [ 3417/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4026 | test_acc: 0.3982 | Time: 6.9902 s
>>> Epoch [ 3418/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4027 | test_acc: 0.3983 | Time: 7.1024 s
>>> Epoch [ 3419/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4026 | test_acc: 0.3983 | Time: 7.6230 s
>>> Epoch [ 3420/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.4718 s
>>> Epoch [ 3421/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.1797 s
>>> Epoch [ 3422/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.4253 s
>>> Epoch [ 3423/10000]
train_loss: 2.0497 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.3680 s
>>> Epoch [ 3424/10000]
train_loss: 2.0496 | train_acc: 0.4235 | val_loss: 2.0668 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.7612 s
>>> Epoch [ 3425/10000]
train_loss: 2.0496 | train_acc: 0.4235 | val_loss: 2.0668 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.7878 s
>>> Epoch [ 3426/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0668 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.6514 s
>>> Epoch [ 3427/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.6857 s
>>> Epoch [ 3428/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.6167 s
>>> Epoch [ 3429/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.8675 s
>>> Epoch [ 3430/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.6551 s
>>> Epoch [ 3431/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.5906 s
>>> Epoch [ 3432/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.9182 s
>>> Epoch [ 3433/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3984 | Time: 7.8450 s
>>> Epoch [ 3434/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 7.7223 s
>>> Epoch [ 3435/10000]
train_loss: 2.0496 | train_acc: 0.4234 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 7.5179 s
>>> Epoch [ 3436/10000]
train_loss: 2.0496 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 7.8088 s
>>> Epoch [ 3437/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 7.6305 s
>>> Epoch [ 3438/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4029 | test_acc: 0.3985 | Time: 7.8153 s
>>> Epoch [ 3439/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4029 | test_acc: 0.3985 | Time: 7.6867 s
>>> Epoch [ 3440/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4029 | test_acc: 0.3985 | Time: 7.6049 s
>>> Epoch [ 3441/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4029 | test_acc: 0.3985 | Time: 7.6724 s
>>> Epoch [ 3442/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4029 | test_acc: 0.3985 | Time: 7.4807 s
>>> Epoch [ 3443/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4029 | test_acc: 0.3986 | Time: 7.8670 s
>>> Epoch [ 3444/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0667 | val_acc: 0.4029 | test_acc: 0.3986 | Time: 7.6401 s
>>> Epoch [ 3445/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4029 | test_acc: 0.3985 | Time: 7.6365 s
>>> Epoch [ 3446/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 11.6114 s
>>> Epoch [ 3447/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 10.7030 s
>>> Epoch [ 3448/10000]
train_loss: 2.0495 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 11.4868 s
>>> Epoch [ 3449/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 6.8838 s
>>> Epoch [ 3450/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3985 | Time: 7.4432 s
>>> Epoch [ 3451/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3986 | Time: 7.6583 s
>>> Epoch [ 3452/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4029 | test_acc: 0.3986 | Time: 7.5766 s
>>> Epoch [ 3453/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4029 | test_acc: 0.3986 | Time: 7.7527 s
>>> Epoch [ 3454/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3986 | Time: 7.7041 s
>>> Epoch [ 3455/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3986 | Time: 7.8613 s
>>> Epoch [ 3456/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3986 | Time: 7.9393 s
>>> Epoch [ 3457/10000]
train_loss: 2.0494 | train_acc: 0.4235 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3986 | Time: 7.6837 s
>>> Epoch [ 3458/10000]
train_loss: 2.0494 | train_acc: 0.4236 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3986 | Time: 7.9085 s
>>> Epoch [ 3459/10000]
train_loss: 2.0494 | train_acc: 0.4236 | val_loss: 2.0666 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.8795 s
>>> Epoch [ 3460/10000]
train_loss: 2.0494 | train_acc: 0.4236 | val_loss: 2.0666 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.8651 s
>>> Epoch [ 3461/10000]
train_loss: 2.0494 | train_acc: 0.4236 | val_loss: 2.0666 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.9656 s
>>> Epoch [ 3462/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0666 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.8797 s
>>> Epoch [ 3463/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.6926 s
>>> Epoch [ 3464/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.5995 s
>>> Epoch [ 3465/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.7791 s
>>> Epoch [ 3466/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.6541 s
>>> Epoch [ 3467/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.7924 s
>>> Epoch [ 3468/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.7695 s
>>> Epoch [ 3469/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 8.0535 s
>>> Epoch [ 3470/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 8.0193 s
>>> Epoch [ 3471/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.9221 s
>>> Epoch [ 3472/10000]
train_loss: 2.0493 | train_acc: 0.4237 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.6442 s
>>> Epoch [ 3473/10000]
train_loss: 2.0493 | train_acc: 0.4237 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 8.2110 s
>>> Epoch [ 3474/10000]
train_loss: 2.0493 | train_acc: 0.4236 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 8.0584 s
>>> Epoch [ 3475/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 8.0210 s
>>> Epoch [ 3476/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 10.8581 s
>>> Epoch [ 3477/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3987 | Time: 9.8212 s
>>> Epoch [ 3478/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3987 | Time: 12.2412 s
>>> Epoch [ 3479/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.5687 s
>>> Epoch [ 3480/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0665 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.7228 s
>>> Epoch [ 3481/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.5221 s
>>> Epoch [ 3482/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.5328 s
>>> Epoch [ 3483/10000]
train_loss: 2.0492 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4031 | test_acc: 0.3988 | Time: 7.8003 s
>>> Epoch [ 3484/10000]
train_loss: 2.0492 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4031 | test_acc: 0.3988 | Time: 7.7780 s
>>> Epoch [ 3485/10000]
train_loss: 2.0492 | train_acc: 0.4237 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.7352 s
>>> Epoch [ 3486/10000]
train_loss: 2.0492 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.5590 s
>>> Epoch [ 3487/10000]
train_loss: 2.0491 | train_acc: 0.4237 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.8405 s
>>> Epoch [ 3488/10000]
train_loss: 2.0491 | train_acc: 0.4237 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 7.9284 s
>>> Epoch [ 3489/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 8.1961 s
>>> Epoch [ 3490/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3988 | Time: 8.0436 s
>>> Epoch [ 3491/10000]
train_loss: 2.0491 | train_acc: 0.4237 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3989 | Time: 7.5168 s
>>> Epoch [ 3492/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3989 | Time: 7.6470 s
>>> Epoch [ 3493/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3989 | Time: 8.2694 s
>>> Epoch [ 3494/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3989 | Time: 7.7882 s
>>> Epoch [ 3495/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3989 | Time: 7.7687 s
>>> Epoch [ 3496/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3989 | Time: 7.7996 s
>>> Epoch [ 3497/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4030 | test_acc: 0.3989 | Time: 7.7026 s
>>> Epoch [ 3498/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0664 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 8.0823 s
>>> Epoch [ 3499/10000]
train_loss: 2.0491 | train_acc: 0.4238 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 7.9778 s
>>> Epoch [ 3500/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 7.9761 s
>>> Epoch [ 3501/10000]
train_loss: 2.0490 | train_acc: 0.4238 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 7.6667 s
>>> Epoch [ 3502/10000]
train_loss: 2.0490 | train_acc: 0.4238 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 8.0980 s
>>> Epoch [ 3503/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 7.9791 s
>>> Epoch [ 3504/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 7.8886 s
>>> Epoch [ 3505/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 7.3042 s
>>> Epoch [ 3506/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.6706 s
>>> Epoch [ 3507/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 7.4831 s
>>> Epoch [ 3508/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 9.9589 s
>>> Epoch [ 3509/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 11.3959 s
>>> Epoch [ 3510/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.4745 s
>>> Epoch [ 3511/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 8.0308 s
>>> Epoch [ 3512/10000]
train_loss: 2.0490 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 9.1023 s
>>> Epoch [ 3513/10000]
train_loss: 2.0489 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.8454 s
>>> Epoch [ 3514/10000]
train_loss: 2.0489 | train_acc: 0.4239 | val_loss: 2.0663 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.7904 s
>>> Epoch [ 3515/10000]
train_loss: 2.0489 | train_acc: 0.4240 | val_loss: 2.0663 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.9694 s
>>> Epoch [ 3516/10000]
train_loss: 2.0489 | train_acc: 0.4240 | val_loss: 2.0663 | val_acc: 0.4027 | test_acc: 0.3988 | Time: 7.8701 s
>>> Epoch [ 3517/10000]
train_loss: 2.0489 | train_acc: 0.4240 | val_loss: 2.0663 | val_acc: 0.4027 | test_acc: 0.3988 | Time: 7.7217 s
>>> Epoch [ 3518/10000]
train_loss: 2.0489 | train_acc: 0.4240 | val_loss: 2.0662 | val_acc: 0.4027 | test_acc: 0.3988 | Time: 7.8901 s
>>> Epoch [ 3519/10000]
train_loss: 2.0489 | train_acc: 0.4240 | val_loss: 2.0662 | val_acc: 0.4027 | test_acc: 0.3989 | Time: 8.1207 s
>>> Epoch [ 3520/10000]
train_loss: 2.0489 | train_acc: 0.4240 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 7.7346 s
>>> Epoch [ 3521/10000]
train_loss: 2.0489 | train_acc: 0.4241 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 7.7066 s
>>> Epoch [ 3522/10000]
train_loss: 2.0489 | train_acc: 0.4241 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 7.9757 s
>>> Epoch [ 3523/10000]
train_loss: 2.0489 | train_acc: 0.4241 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 7.8534 s
>>> Epoch [ 3524/10000]
train_loss: 2.0489 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 7.9675 s
>>> Epoch [ 3525/10000]
train_loss: 2.0489 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 7.7122 s
>>> Epoch [ 3526/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3990 | Time: 8.2431 s
>>> Epoch [ 3527/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 7.9302 s
>>> Epoch [ 3528/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 7.9969 s
>>> Epoch [ 3529/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 8.0684 s
>>> Epoch [ 3530/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 7.9525 s
>>> Epoch [ 3531/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 7.9247 s
>>> Epoch [ 3532/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 8.0161 s
>>> Epoch [ 3533/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 8.1690 s
>>> Epoch [ 3534/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4029 | test_acc: 0.3988 | Time: 9.4545 s
>>> Epoch [ 3535/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0662 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 12.4111 s
>>> Epoch [ 3536/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0661 | val_acc: 0.4028 | test_acc: 0.3988 | Time: 9.7846 s
>>> Epoch [ 3537/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0661 | val_acc: 0.4028 | test_acc: 0.3989 | Time: 9.5904 s
>>> Epoch [ 3538/10000]
train_loss: 2.0488 | train_acc: 0.4242 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 9.6868 s
>>> Epoch [ 3539/10000]
train_loss: 2.0487 | train_acc: 0.4242 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 9.6316 s
>>> Epoch [ 3540/10000]
train_loss: 2.0487 | train_acc: 0.4243 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 9.7383 s
>>> Epoch [ 3541/10000]
train_loss: 2.0487 | train_acc: 0.4243 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 9.7104 s
>>> Epoch [ 3542/10000]
train_loss: 2.0487 | train_acc: 0.4243 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3989 | Time: 9.5459 s
>>> Epoch [ 3543/10000]
train_loss: 2.0487 | train_acc: 0.4243 | val_loss: 2.0661 | val_acc: 0.4030 | test_acc: 0.3990 | Time: 9.0005 s
>>> Epoch [ 3544/10000]
train_loss: 2.0487 | train_acc: 0.4243 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3990 | Time: 8.3691 s
>>> Epoch [ 3545/10000]
train_loss: 2.0487 | train_acc: 0.4243 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3990 | Time: 7.3318 s
>>> Epoch [ 3546/10000]
train_loss: 2.0487 | train_acc: 0.4244 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3991 | Time: 12.3893 s
>>> Epoch [ 3547/10000]
train_loss: 2.0487 | train_acc: 0.4244 | val_loss: 2.0661 | val_acc: 0.4028 | test_acc: 0.3991 | Time: 9.8448 s
>>> Epoch [ 3548/10000]
train_loss: 2.0487 | train_acc: 0.4244 | val_loss: 2.0661 | val_acc: 0.4028 | test_acc: 0.3991 | Time: 8.8998 s
>>> Epoch [ 3549/10000]
train_loss: 2.0487 | train_acc: 0.4243 | val_loss: 2.0661 | val_acc: 0.4028 | test_acc: 0.3991 | Time: 8.8876 s
>>> Epoch [ 3550/10000]
train_loss: 2.0487 | train_acc: 0.4243 | val_loss: 2.0661 | val_acc: 0.4028 | test_acc: 0.3993 | Time: 8.8367 s
>>> Epoch [ 3551/10000]
train_loss: 2.0487 | train_acc: 0.4244 | val_loss: 2.0661 | val_acc: 0.4028 | test_acc: 0.3993 | Time: 8.9259 s
>>> Epoch [ 3552/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3993 | Time: 9.0540 s
>>> Epoch [ 3553/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3993 | Time: 8.7524 s
>>> Epoch [ 3554/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0661 | val_acc: 0.4029 | test_acc: 0.3993 | Time: 8.5754 s
>>> Epoch [ 3555/10000]
train_loss: 2.0486 | train_acc: 0.4245 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3993 | Time: 7.7998 s
>>> Epoch [ 3556/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3993 | Time: 7.7955 s
>>> Epoch [ 3557/10000]
train_loss: 2.0486 | train_acc: 0.4245 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3993 | Time: 7.6918 s
>>> Epoch [ 3558/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3994 | Time: 7.3584 s
>>> Epoch [ 3559/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3994 | Time: 7.9818 s
>>> Epoch [ 3560/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3994 | Time: 8.0125 s
>>> Epoch [ 3561/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4028 | test_acc: 0.3994 | Time: 7.8550 s
>>> Epoch [ 3562/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4028 | test_acc: 0.3994 | Time: 7.9946 s
>>> Epoch [ 3563/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4028 | test_acc: 0.3995 | Time: 7.8580 s
>>> Epoch [ 3564/10000]
train_loss: 2.0486 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4028 | test_acc: 0.3995 | Time: 7.7190 s
>>> Epoch [ 3565/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4028 | test_acc: 0.3995 | Time: 8.1253 s
>>> Epoch [ 3566/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4028 | test_acc: 0.3995 | Time: 8.2012 s
>>> Epoch [ 3567/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4028 | test_acc: 0.3995 | Time: 8.2402 s
>>> Epoch [ 3568/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4030 | test_acc: 0.3995 | Time: 8.2888 s
>>> Epoch [ 3569/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3995 | Time: 8.0179 s
>>> Epoch [ 3570/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3995 | Time: 8.0590 s
>>> Epoch [ 3571/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3995 | Time: 7.9033 s
>>> Epoch [ 3572/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3995 | Time: 7.9421 s
>>> Epoch [ 3573/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0660 | val_acc: 0.4029 | test_acc: 0.3995 | Time: 8.2224 s
>>> Epoch [ 3574/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3995 | Time: 8.3488 s
>>> Epoch [ 3575/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.6244 s
>>> Epoch [ 3576/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 7.9735 s
>>> Epoch [ 3577/10000]
train_loss: 2.0485 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.1765 s
>>> Epoch [ 3578/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.2552 s
>>> Epoch [ 3579/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.1602 s
>>> Epoch [ 3580/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 7.9744 s
>>> Epoch [ 3581/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.0264 s
>>> Epoch [ 3582/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.3262 s
>>> Epoch [ 3583/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3997 | Time: 8.1235 s
>>> Epoch [ 3584/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3997 | Time: 7.9435 s
>>> Epoch [ 3585/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3997 | Time: 8.2714 s
>>> Epoch [ 3586/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3997 | Time: 12.0665 s
>>> Epoch [ 3587/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3996 | Time: 10.3515 s
>>> Epoch [ 3588/10000]
train_loss: 2.0484 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3996 | Time: 12.0201 s
>>> Epoch [ 3589/10000]
train_loss: 2.0484 | train_acc: 0.4245 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3996 | Time: 7.6848 s
>>> Epoch [ 3590/10000]
train_loss: 2.0484 | train_acc: 0.4245 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3995 | Time: 8.2228 s
>>> Epoch [ 3591/10000]
train_loss: 2.0484 | train_acc: 0.4245 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3995 | Time: 8.0472 s
>>> Epoch [ 3592/10000]
train_loss: 2.0483 | train_acc: 0.4244 | val_loss: 2.0659 | val_acc: 0.4030 | test_acc: 0.3995 | Time: 7.9088 s
>>> Epoch [ 3593/10000]
train_loss: 2.0483 | train_acc: 0.4244 | val_loss: 2.0658 | val_acc: 0.4030 | test_acc: 0.3995 | Time: 8.1431 s
>>> Epoch [ 3594/10000]
train_loss: 2.0483 | train_acc: 0.4244 | val_loss: 2.0658 | val_acc: 0.4030 | test_acc: 0.3996 | Time: 8.1551 s
>>> Epoch [ 3595/10000]
train_loss: 2.0483 | train_acc: 0.4244 | val_loss: 2.0658 | val_acc: 0.4030 | test_acc: 0.3996 | Time: 8.2882 s
>>> Epoch [ 3596/10000]
train_loss: 2.0483 | train_acc: 0.4244 | val_loss: 2.0658 | val_acc: 0.4030 | test_acc: 0.3996 | Time: 8.2312 s
>>> Epoch [ 3597/10000]
train_loss: 2.0483 | train_acc: 0.4245 | val_loss: 2.0658 | val_acc: 0.4030 | test_acc: 0.3996 | Time: 8.1292 s
>>> Epoch [ 3598/10000]
train_loss: 2.0483 | train_acc: 0.4245 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3996 | Time: 8.2253 s
>>> Epoch [ 3599/10000]
train_loss: 2.0483 | train_acc: 0.4245 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3996 | Time: 8.2450 s
>>> Epoch [ 3600/10000]
train_loss: 2.0483 | train_acc: 0.4246 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.1805 s
>>> Epoch [ 3601/10000]
train_loss: 2.0483 | train_acc: 0.4246 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 7.9342 s
>>> Epoch [ 3602/10000]
train_loss: 2.0483 | train_acc: 0.4246 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.1664 s
>>> Epoch [ 3603/10000]
train_loss: 2.0483 | train_acc: 0.4246 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.2560 s
>>> Epoch [ 3604/10000]
train_loss: 2.0483 | train_acc: 0.4246 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.1504 s
>>> Epoch [ 3605/10000]
train_loss: 2.0482 | train_acc: 0.4246 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.4781 s
>>> Epoch [ 3606/10000]
train_loss: 2.0482 | train_acc: 0.4246 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.1096 s
>>> Epoch [ 3607/10000]
train_loss: 2.0482 | train_acc: 0.4246 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3997 | Time: 8.1035 s
>>> Epoch [ 3608/10000]
train_loss: 2.0482 | train_acc: 0.4247 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3999 | Time: 8.3255 s
>>> Epoch [ 3609/10000]
train_loss: 2.0482 | train_acc: 0.4247 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3999 | Time: 8.1483 s
>>> Epoch [ 3610/10000]
train_loss: 2.0482 | train_acc: 0.4247 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3999 | Time: 7.8012 s
>>> Epoch [ 3611/10000]
train_loss: 2.0482 | train_acc: 0.4247 | val_loss: 2.0658 | val_acc: 0.4029 | test_acc: 0.3999 | Time: 8.3717 s
>>> Epoch [ 3612/10000]
train_loss: 2.0482 | train_acc: 0.4247 | val_loss: 2.0657 | val_acc: 0.4029 | test_acc: 0.4000 | Time: 8.2119 s
>>> Epoch [ 3613/10000]
train_loss: 2.0482 | train_acc: 0.4246 | val_loss: 2.0657 | val_acc: 0.4029 | test_acc: 0.4000 | Time: 7.9898 s
>>> Epoch [ 3614/10000]
train_loss: 2.0482 | train_acc: 0.4246 | val_loss: 2.0657 | val_acc: 0.4030 | test_acc: 0.4000 | Time: 8.2651 s
>>> Epoch [ 3615/10000]
train_loss: 2.0482 | train_acc: 0.4247 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4000 | Time: 8.1316 s
>>> Epoch [ 3616/10000]
train_loss: 2.0482 | train_acc: 0.4247 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4000 | Time: 12.4566 s
>>> Epoch [ 3617/10000]
train_loss: 2.0482 | train_acc: 0.4247 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4000 | Time: 10.6882 s
>>> Epoch [ 3618/10000]
train_loss: 2.0481 | train_acc: 0.4247 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4000 | Time: 7.5632 s
>>> Epoch [ 3619/10000]
train_loss: 2.0481 | train_acc: 0.4247 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4000 | Time: 7.7857 s
>>> Epoch [ 3620/10000]
train_loss: 2.0481 | train_acc: 0.4247 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4001 | Time: 7.9618 s
>>> Epoch [ 3621/10000]
train_loss: 2.0481 | train_acc: 0.4247 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4001 | Time: 8.1138 s
>>> Epoch [ 3622/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 8.2719 s
>>> Epoch [ 3623/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 8.3300 s
>>> Epoch [ 3624/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 8.0001 s
>>> Epoch [ 3625/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 7.9632 s
>>> Epoch [ 3626/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4030 | test_acc: 0.4002 | Time: 8.1663 s
>>> Epoch [ 3627/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4030 | test_acc: 0.4002 | Time: 8.2581 s
>>> Epoch [ 3628/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 8.3506 s
>>> Epoch [ 3629/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 8.1846 s
>>> Epoch [ 3630/10000]
train_loss: 2.0481 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 8.2472 s
>>> Epoch [ 3631/10000]
train_loss: 2.0480 | train_acc: 0.4248 | val_loss: 2.0657 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 8.2889 s
>>> Epoch [ 3632/10000]
train_loss: 2.0480 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4030 | test_acc: 0.4002 | Time: 8.2132 s
>>> Epoch [ 3633/10000]
train_loss: 2.0480 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4031 | test_acc: 0.4002 | Time: 8.5085 s
>>> Epoch [ 3634/10000]
train_loss: 2.0480 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4032 | test_acc: 0.4002 | Time: 8.4489 s
>>> Epoch [ 3635/10000]
train_loss: 2.0480 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4002 | Time: 8.1526 s
>>> Epoch [ 3636/10000]
train_loss: 2.0480 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4002 | Time: 8.4577 s
>>> Epoch [ 3637/10000]
train_loss: 2.0480 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 8.2501 s
>>> Epoch [ 3638/10000]
train_loss: 2.0480 | train_acc: 0.4250 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 8.3309 s
>>> Epoch [ 3639/10000]
train_loss: 2.0480 | train_acc: 0.4250 | val_loss: 2.0656 | val_acc: 0.4032 | test_acc: 0.4004 | Time: 8.1036 s
>>> Epoch [ 3640/10000]
train_loss: 2.0480 | train_acc: 0.4250 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 8.3227 s
>>> Epoch [ 3641/10000]
train_loss: 2.0480 | train_acc: 0.4250 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 8.3765 s
>>> Epoch [ 3642/10000]
train_loss: 2.0480 | train_acc: 0.4250 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 7.2171 s
>>> Epoch [ 3643/10000]
train_loss: 2.0480 | train_acc: 0.4250 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 7.2135 s
>>> Epoch [ 3644/10000]
train_loss: 2.0480 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 7.2633 s
>>> Epoch [ 3645/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 7.0797 s
>>> Epoch [ 3646/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4033 | test_acc: 0.4004 | Time: 7.2561 s
>>> Epoch [ 3647/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4032 | test_acc: 0.4004 | Time: 7.3014 s
>>> Epoch [ 3648/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4031 | test_acc: 0.4004 | Time: 7.0140 s
>>> Epoch [ 3649/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4031 | test_acc: 0.4004 | Time: 7.2714 s
>>> Epoch [ 3650/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0656 | val_acc: 0.4031 | test_acc: 0.4005 | Time: 7.3169 s
>>> Epoch [ 3651/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0655 | val_acc: 0.4031 | test_acc: 0.4005 | Time: 7.1824 s
>>> Epoch [ 3652/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0655 | val_acc: 0.4031 | test_acc: 0.4004 | Time: 7.6125 s
>>> Epoch [ 3653/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0655 | val_acc: 0.4030 | test_acc: 0.4004 | Time: 7.3864 s
>>> Epoch [ 3654/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0655 | val_acc: 0.4030 | test_acc: 0.4004 | Time: 7.4083 s
>>> Epoch [ 3655/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4004 | Time: 7.1601 s
>>> Epoch [ 3656/10000]
train_loss: 2.0479 | train_acc: 0.4249 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4003 | Time: 7.2455 s
>>> Epoch [ 3657/10000]
train_loss: 2.0479 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4003 | Time: 7.2013 s
>>> Epoch [ 3658/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4003 | Time: 7.1581 s
>>> Epoch [ 3659/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4003 | Time: 7.2570 s
>>> Epoch [ 3660/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4003 | Time: 12.8394 s
>>> Epoch [ 3661/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4003 | Time: 12.5466 s
>>> Epoch [ 3662/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4003 | Time: 12.1821 s
>>> Epoch [ 3663/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4003 | Time: 10.1999 s
>>> Epoch [ 3664/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4004 | Time: 7.7663 s
>>> Epoch [ 3665/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4004 | Time: 8.3768 s
>>> Epoch [ 3666/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4004 | Time: 12.7669 s
>>> Epoch [ 3667/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4005 | Time: 12.2777 s
>>> Epoch [ 3668/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4005 | Time: 7.6878 s
>>> Epoch [ 3669/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4005 | Time: 8.7321 s
>>> Epoch [ 3670/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0655 | val_acc: 0.4032 | test_acc: 0.4006 | Time: 9.0794 s
>>> Epoch [ 3671/10000]
train_loss: 2.0478 | train_acc: 0.4250 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4006 | Time: 8.1819 s
>>> Epoch [ 3672/10000]
train_loss: 2.0477 | train_acc: 0.4250 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4006 | Time: 8.3866 s
>>> Epoch [ 3673/10000]
train_loss: 2.0477 | train_acc: 0.4250 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4006 | Time: 8.1762 s
>>> Epoch [ 3674/10000]
train_loss: 2.0477 | train_acc: 0.4250 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4006 | Time: 8.0253 s
>>> Epoch [ 3675/10000]
train_loss: 2.0477 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4006 | Time: 8.2912 s
>>> Epoch [ 3676/10000]
train_loss: 2.0477 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4006 | Time: 8.4813 s
>>> Epoch [ 3677/10000]
train_loss: 2.0477 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4005 | Time: 8.0463 s
>>> Epoch [ 3678/10000]
train_loss: 2.0477 | train_acc: 0.4250 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4006 | Time: 8.2557 s
>>> Epoch [ 3679/10000]
train_loss: 2.0477 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4007 | Time: 8.3634 s
>>> Epoch [ 3680/10000]
train_loss: 2.0477 | train_acc: 0.4250 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4007 | Time: 8.6517 s
>>> Epoch [ 3681/10000]
train_loss: 2.0477 | train_acc: 0.4250 | val_loss: 2.0654 | val_acc: 0.4033 | test_acc: 0.4007 | Time: 8.2519 s
>>> Epoch [ 3682/10000]
train_loss: 2.0477 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4032 | test_acc: 0.4008 | Time: 8.2855 s
>>> Epoch [ 3683/10000]
train_loss: 2.0477 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 8.3734 s
>>> Epoch [ 3684/10000]
train_loss: 2.0477 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4031 | test_acc: 0.4006 | Time: 8.1531 s
>>> Epoch [ 3685/10000]
train_loss: 2.0477 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 8.3736 s
>>> Epoch [ 3686/10000]
train_loss: 2.0476 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 8.1692 s
>>> Epoch [ 3687/10000]
train_loss: 2.0476 | train_acc: 0.4251 | val_loss: 2.0654 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 8.4748 s
>>> Epoch [ 3688/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0654 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 8.1147 s
>>> Epoch [ 3689/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0654 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 8.1592 s
>>> Epoch [ 3690/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0654 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 8.2613 s
>>> Epoch [ 3691/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 8.3880 s
>>> Epoch [ 3692/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 11.7351 s
>>> Epoch [ 3693/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4030 | test_acc: 0.4007 | Time: 11.2701 s
>>> Epoch [ 3694/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4030 | test_acc: 0.4007 | Time: 8.9084 s
>>> Epoch [ 3695/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4030 | test_acc: 0.4007 | Time: 8.9173 s
>>> Epoch [ 3696/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4030 | test_acc: 0.4007 | Time: 8.8617 s
>>> Epoch [ 3697/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4031 | test_acc: 0.4007 | Time: 9.0767 s
>>> Epoch [ 3698/10000]
train_loss: 2.0476 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4031 | test_acc: 0.4008 | Time: 8.9617 s
>>> Epoch [ 3699/10000]
train_loss: 2.0475 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4031 | test_acc: 0.4008 | Time: 8.4609 s
>>> Epoch [ 3700/10000]
train_loss: 2.0475 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4032 | test_acc: 0.4008 | Time: 8.2010 s
>>> Epoch [ 3701/10000]
train_loss: 2.0475 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4032 | test_acc: 0.4008 | Time: 8.3904 s
>>> Epoch [ 3702/10000]
train_loss: 2.0475 | train_acc: 0.4253 | val_loss: 2.0653 | val_acc: 0.4032 | test_acc: 0.4008 | Time: 8.2367 s
>>> Epoch [ 3703/10000]
train_loss: 2.0475 | train_acc: 0.4253 | val_loss: 2.0653 | val_acc: 0.4032 | test_acc: 0.4008 | Time: 7.9456 s
>>> Epoch [ 3704/10000]
train_loss: 2.0475 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4032 | test_acc: 0.4009 | Time: 7.8723 s
>>> Epoch [ 3705/10000]
train_loss: 2.0475 | train_acc: 0.4252 | val_loss: 2.0653 | val_acc: 0.4033 | test_acc: 0.4009 | Time: 8.1240 s
>>> Epoch [ 3706/10000]
train_loss: 2.0475 | train_acc: 0.4253 | val_loss: 2.0653 | val_acc: 0.4033 | test_acc: 0.4009 | Time: 7.9492 s
>>> Epoch [ 3707/10000]
train_loss: 2.0475 | train_acc: 0.4253 | val_loss: 2.0653 | val_acc: 0.4033 | test_acc: 0.4009 | Time: 8.0719 s
>>> Epoch [ 3708/10000]
train_loss: 2.0475 | train_acc: 0.4253 | val_loss: 2.0653 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 7.8338 s
>>> Epoch [ 3709/10000]
train_loss: 2.0475 | train_acc: 0.4254 | val_loss: 2.0653 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 7.7981 s
>>> Epoch [ 3710/10000]
train_loss: 2.0475 | train_acc: 0.4254 | val_loss: 2.0653 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 7.5948 s
>>> Epoch [ 3711/10000]
train_loss: 2.0475 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 7.5487 s
>>> Epoch [ 3712/10000]
train_loss: 2.0475 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 7.7045 s
>>> Epoch [ 3713/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 7.8134 s
>>> Epoch [ 3714/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 12.6809 s
>>> Epoch [ 3715/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 8.8632 s
>>> Epoch [ 3716/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 8.1318 s
>>> Epoch [ 3717/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4034 | test_acc: 0.4009 | Time: 8.2303 s
>>> Epoch [ 3718/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4009 | Time: 8.3598 s
>>> Epoch [ 3719/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4009 | Time: 8.2060 s
>>> Epoch [ 3720/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4009 | Time: 8.3711 s
>>> Epoch [ 3721/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4009 | Time: 8.3904 s
>>> Epoch [ 3722/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4009 | Time: 7.8361 s
>>> Epoch [ 3723/10000]
train_loss: 2.0474 | train_acc: 0.4253 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4010 | Time: 7.9259 s
>>> Epoch [ 3724/10000]
train_loss: 2.0474 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4012 | Time: 7.7687 s
>>> Epoch [ 3725/10000]
train_loss: 2.0474 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4012 | Time: 7.8683 s
>>> Epoch [ 3726/10000]
train_loss: 2.0474 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4012 | Time: 8.0863 s
>>> Epoch [ 3727/10000]
train_loss: 2.0473 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4036 | test_acc: 0.4012 | Time: 7.9242 s
>>> Epoch [ 3728/10000]
train_loss: 2.0473 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4035 | test_acc: 0.4012 | Time: 7.8344 s
>>> Epoch [ 3729/10000]
train_loss: 2.0473 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4035 | test_acc: 0.4012 | Time: 7.7428 s
>>> Epoch [ 3730/10000]
train_loss: 2.0473 | train_acc: 0.4254 | val_loss: 2.0652 | val_acc: 0.4035 | test_acc: 0.4014 | Time: 7.7275 s
>>> Epoch [ 3731/10000]
train_loss: 2.0473 | train_acc: 0.4254 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4014 | Time: 7.7917 s
>>> Epoch [ 3732/10000]
train_loss: 2.0473 | train_acc: 0.4254 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4014 | Time: 8.1981 s
>>> Epoch [ 3733/10000]
train_loss: 2.0473 | train_acc: 0.4255 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4014 | Time: 8.2345 s
>>> Epoch [ 3734/10000]
train_loss: 2.0473 | train_acc: 0.4255 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4014 | Time: 8.3140 s
>>> Epoch [ 3735/10000]
train_loss: 2.0473 | train_acc: 0.4255 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4014 | Time: 8.2031 s
>>> Epoch [ 3736/10000]
train_loss: 2.0473 | train_acc: 0.4255 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4014 | Time: 8.2859 s
>>> Epoch [ 3737/10000]
train_loss: 2.0473 | train_acc: 0.4255 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4014 | Time: 8.6199 s
>>> Epoch [ 3738/10000]
train_loss: 2.0473 | train_acc: 0.4255 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4013 | Time: 8.5254 s
>>> Epoch [ 3739/10000]
train_loss: 2.0473 | train_acc: 0.4256 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4013 | Time: 8.4442 s
>>> Epoch [ 3740/10000]
train_loss: 2.0473 | train_acc: 0.4256 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4013 | Time: 8.5708 s
>>> Epoch [ 3741/10000]
train_loss: 2.0472 | train_acc: 0.4256 | val_loss: 2.0651 | val_acc: 0.4035 | test_acc: 0.4013 | Time: 8.6426 s
>>> Epoch [ 3742/10000]
train_loss: 2.0472 | train_acc: 0.4256 | val_loss: 2.0651 | val_acc: 0.4036 | test_acc: 0.4013 | Time: 8.2145 s
>>> Epoch [ 3743/10000]
train_loss: 2.0472 | train_acc: 0.4255 | val_loss: 2.0651 | val_acc: 0.4036 | test_acc: 0.4013 | Time: 8.5044 s
>>> Epoch [ 3744/10000]
train_loss: 2.0472 | train_acc: 0.4256 | val_loss: 2.0651 | val_acc: 0.4036 | test_acc: 0.4013 | Time: 8.5054 s
>>> Epoch [ 3745/10000]
train_loss: 2.0472 | train_acc: 0.4256 | val_loss: 2.0651 | val_acc: 0.4036 | test_acc: 0.4012 | Time: 8.5288 s
>>> Epoch [ 3746/10000]
train_loss: 2.0472 | train_acc: 0.4256 | val_loss: 2.0651 | val_acc: 0.4036 | test_acc: 0.4012 | Time: 8.5819 s
>>> Epoch [ 3747/10000]
train_loss: 2.0472 | train_acc: 0.4257 | val_loss: 2.0651 | val_acc: 0.4037 | test_acc: 0.4012 | Time: 8.1599 s
>>> Epoch [ 3748/10000]
train_loss: 2.0472 | train_acc: 0.4257 | val_loss: 2.0651 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.6603 s
>>> Epoch [ 3749/10000]
train_loss: 2.0472 | train_acc: 0.4257 | val_loss: 2.0651 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.3718 s
>>> Epoch [ 3750/10000]
train_loss: 2.0472 | train_acc: 0.4257 | val_loss: 2.0651 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.7565 s
>>> Epoch [ 3751/10000]
train_loss: 2.0472 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.5094 s
>>> Epoch [ 3752/10000]
train_loss: 2.0472 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.6902 s
>>> Epoch [ 3753/10000]
train_loss: 2.0472 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.4738 s
>>> Epoch [ 3754/10000]
train_loss: 2.0471 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.3269 s
>>> Epoch [ 3755/10000]
train_loss: 2.0471 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.4370 s
>>> Epoch [ 3756/10000]
train_loss: 2.0471 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.2590 s
>>> Epoch [ 3757/10000]
train_loss: 2.0471 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.4262 s
>>> Epoch [ 3758/10000]
train_loss: 2.0471 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 11.9674 s
>>> Epoch [ 3759/10000]
train_loss: 2.0471 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.9326 s
>>> Epoch [ 3760/10000]
train_loss: 2.0471 | train_acc: 0.4257 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 7.8407 s
>>> Epoch [ 3761/10000]
train_loss: 2.0471 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 7.6853 s
>>> Epoch [ 3762/10000]
train_loss: 2.0471 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 7.6281 s
>>> Epoch [ 3763/10000]
train_loss: 2.0471 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 10.0393 s
>>> Epoch [ 3764/10000]
train_loss: 2.0471 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 12.2780 s
>>> Epoch [ 3765/10000]
train_loss: 2.0471 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 7.8994 s
>>> Epoch [ 3766/10000]
train_loss: 2.0471 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.3969 s
>>> Epoch [ 3767/10000]
train_loss: 2.0471 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.2866 s
>>> Epoch [ 3768/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.0678 s
>>> Epoch [ 3769/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.0811 s
>>> Epoch [ 3770/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.4912 s
>>> Epoch [ 3771/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0650 | val_acc: 0.4037 | test_acc: 0.4014 | Time: 8.4575 s
>>> Epoch [ 3772/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0649 | val_acc: 0.4037 | test_acc: 0.4014 | Time: 8.7317 s
>>> Epoch [ 3773/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0649 | val_acc: 0.4037 | test_acc: 0.4014 | Time: 8.4690 s
>>> Epoch [ 3774/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0649 | val_acc: 0.4037 | test_acc: 0.4014 | Time: 8.4388 s
>>> Epoch [ 3775/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0649 | val_acc: 0.4037 | test_acc: 0.4014 | Time: 8.4869 s
>>> Epoch [ 3776/10000]
train_loss: 2.0470 | train_acc: 0.4258 | val_loss: 2.0649 | val_acc: 0.4037 | test_acc: 0.4014 | Time: 8.4258 s
>>> Epoch [ 3777/10000]
train_loss: 2.0470 | train_acc: 0.4259 | val_loss: 2.0649 | val_acc: 0.4037 | test_acc: 0.4014 | Time: 8.5823 s
>>> Epoch [ 3778/10000]
train_loss: 2.0470 | train_acc: 0.4259 | val_loss: 2.0649 | val_acc: 0.4037 | test_acc: 0.4013 | Time: 8.3960 s
>>> Epoch [ 3779/10000]
train_loss: 2.0470 | train_acc: 0.4259 | val_loss: 2.0649 | val_acc: 0.4037 | test_acc: 0.4013 | Time: 8.4753 s
>>> Epoch [ 3780/10000]
train_loss: 2.0470 | train_acc: 0.4260 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.6560 s
>>> Epoch [ 3781/10000]
train_loss: 2.0470 | train_acc: 0.4260 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.5395 s
>>> Epoch [ 3782/10000]
train_loss: 2.0469 | train_acc: 0.4260 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.3715 s
>>> Epoch [ 3783/10000]
train_loss: 2.0469 | train_acc: 0.4260 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.7926 s
>>> Epoch [ 3784/10000]
train_loss: 2.0469 | train_acc: 0.4260 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.5546 s
>>> Epoch [ 3785/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.3396 s
>>> Epoch [ 3786/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.7803 s
>>> Epoch [ 3787/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.5439 s
>>> Epoch [ 3788/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.8022 s
>>> Epoch [ 3789/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.2747 s
>>> Epoch [ 3790/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4011 | Time: 7.9743 s
>>> Epoch [ 3791/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0649 | val_acc: 0.4038 | test_acc: 0.4011 | Time: 12.7162 s
>>> Epoch [ 3792/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 12.8987 s
>>> Epoch [ 3793/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4010 | Time: 9.3665 s
>>> Epoch [ 3794/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4010 | Time: 8.2213 s
>>> Epoch [ 3795/10000]
train_loss: 2.0469 | train_acc: 0.4261 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4010 | Time: 8.3092 s
>>> Epoch [ 3796/10000]
train_loss: 2.0468 | train_acc: 0.4261 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4010 | Time: 8.2863 s
>>> Epoch [ 3797/10000]
train_loss: 2.0468 | train_acc: 0.4262 | val_loss: 2.0648 | val_acc: 0.4038 | test_acc: 0.4011 | Time: 8.5490 s
>>> Epoch [ 3798/10000]
train_loss: 2.0468 | train_acc: 0.4262 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 8.4714 s
>>> Epoch [ 3799/10000]
train_loss: 2.0468 | train_acc: 0.4263 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 8.4553 s
>>> Epoch [ 3800/10000]
train_loss: 2.0468 | train_acc: 0.4262 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 8.5441 s
>>> Epoch [ 3801/10000]
train_loss: 2.0468 | train_acc: 0.4263 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 8.6919 s
>>> Epoch [ 3802/10000]
train_loss: 2.0468 | train_acc: 0.4263 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 8.5859 s
>>> Epoch [ 3803/10000]
train_loss: 2.0468 | train_acc: 0.4263 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 8.7585 s
>>> Epoch [ 3804/10000]
train_loss: 2.0468 | train_acc: 0.4264 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 8.6933 s
>>> Epoch [ 3805/10000]
train_loss: 2.0468 | train_acc: 0.4263 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4011 | Time: 8.6053 s
>>> Epoch [ 3806/10000]
train_loss: 2.0468 | train_acc: 0.4263 | val_loss: 2.0648 | val_acc: 0.4038 | test_acc: 0.4011 | Time: 8.6594 s
>>> Epoch [ 3807/10000]
train_loss: 2.0468 | train_acc: 0.4264 | val_loss: 2.0648 | val_acc: 0.4038 | test_acc: 0.4012 | Time: 8.9478 s
>>> Epoch [ 3808/10000]
train_loss: 2.0468 | train_acc: 0.4264 | val_loss: 2.0648 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.4020 s
>>> Epoch [ 3809/10000]
train_loss: 2.0468 | train_acc: 0.4264 | val_loss: 2.0648 | val_acc: 0.4038 | test_acc: 0.4013 | Time: 8.5470 s
>>> Epoch [ 3810/10000]
train_loss: 2.0468 | train_acc: 0.4264 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4013 | Time: 8.7330 s
>>> Epoch [ 3811/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0648 | val_acc: 0.4039 | test_acc: 0.4013 | Time: 8.4982 s
>>> Epoch [ 3812/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0648 | val_acc: 0.4040 | test_acc: 0.4013 | Time: 8.5543 s
>>> Epoch [ 3813/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4041 | test_acc: 0.4013 | Time: 8.7105 s
>>> Epoch [ 3814/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4042 | test_acc: 0.4013 | Time: 8.7927 s
>>> Epoch [ 3815/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4042 | test_acc: 0.4013 | Time: 8.6489 s
>>> Epoch [ 3816/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4042 | test_acc: 0.4013 | Time: 10.2860 s
>>> Epoch [ 3817/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4042 | test_acc: 0.4013 | Time: 11.8579 s
>>> Epoch [ 3818/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4042 | test_acc: 0.4012 | Time: 12.9604 s
>>> Epoch [ 3819/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4043 | test_acc: 0.4012 | Time: 7.9181 s
>>> Epoch [ 3820/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4043 | test_acc: 0.4012 | Time: 8.4282 s
>>> Epoch [ 3821/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4043 | test_acc: 0.4012 | Time: 8.7280 s
>>> Epoch [ 3822/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4043 | test_acc: 0.4012 | Time: 8.6156 s
>>> Epoch [ 3823/10000]
train_loss: 2.0467 | train_acc: 0.4264 | val_loss: 2.0647 | val_acc: 0.4043 | test_acc: 0.4013 | Time: 8.6396 s
>>> Epoch [ 3824/10000]
train_loss: 2.0467 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4043 | test_acc: 0.4013 | Time: 8.9174 s
>>> Epoch [ 3825/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4044 | test_acc: 0.4013 | Time: 8.6554 s
>>> Epoch [ 3826/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4044 | test_acc: 0.4013 | Time: 8.9587 s
>>> Epoch [ 3827/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4045 | test_acc: 0.4014 | Time: 8.4868 s
>>> Epoch [ 3828/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4045 | test_acc: 0.4015 | Time: 8.9479 s
>>> Epoch [ 3829/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4045 | test_acc: 0.4015 | Time: 8.6943 s
>>> Epoch [ 3830/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4045 | test_acc: 0.4015 | Time: 8.7174 s
>>> Epoch [ 3831/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4045 | test_acc: 0.4016 | Time: 8.8790 s
>>> Epoch [ 3832/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4045 | test_acc: 0.4016 | Time: 8.3323 s
>>> Epoch [ 3833/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0647 | val_acc: 0.4045 | test_acc: 0.4017 | Time: 8.4118 s
>>> Epoch [ 3834/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4018 | Time: 8.9399 s
>>> Epoch [ 3835/10000]
train_loss: 2.0466 | train_acc: 0.4265 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4018 | Time: 8.5313 s
>>> Epoch [ 3836/10000]
train_loss: 2.0466 | train_acc: 0.4266 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4018 | Time: 8.5788 s
>>> Epoch [ 3837/10000]
train_loss: 2.0466 | train_acc: 0.4266 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4018 | Time: 8.6446 s
>>> Epoch [ 3838/10000]
train_loss: 2.0466 | train_acc: 0.4266 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4018 | Time: 8.5941 s
>>> Epoch [ 3839/10000]
train_loss: 2.0465 | train_acc: 0.4266 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4018 | Time: 8.5353 s
>>> Epoch [ 3840/10000]
train_loss: 2.0465 | train_acc: 0.4266 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4019 | Time: 8.7641 s
>>> Epoch [ 3841/10000]
train_loss: 2.0465 | train_acc: 0.4266 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4019 | Time: 8.8123 s
>>> Epoch [ 3842/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4019 | Time: 8.0645 s
>>> Epoch [ 3843/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4019 | Time: 8.6259 s
>>> Epoch [ 3844/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4018 | Time: 13.0334 s
>>> Epoch [ 3845/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4019 | Time: 12.5334 s
>>> Epoch [ 3846/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4019 | Time: 8.1904 s
>>> Epoch [ 3847/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4020 | Time: 8.8942 s
>>> Epoch [ 3848/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4020 | Time: 8.9059 s
>>> Epoch [ 3849/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4020 | Time: 8.9513 s
>>> Epoch [ 3850/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4045 | test_acc: 0.4020 | Time: 8.5692 s
>>> Epoch [ 3851/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4020 | Time: 8.7435 s
>>> Epoch [ 3852/10000]
train_loss: 2.0465 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4020 | Time: 8.8889 s
>>> Epoch [ 3853/10000]
train_loss: 2.0464 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4021 | Time: 8.8900 s
>>> Epoch [ 3854/10000]
train_loss: 2.0464 | train_acc: 0.4267 | val_loss: 2.0646 | val_acc: 0.4044 | test_acc: 0.4021 | Time: 8.6535 s
>>> Epoch [ 3855/10000]
train_loss: 2.0464 | train_acc: 0.4267 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.9278 s
>>> Epoch [ 3856/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.5530 s
>>> Epoch [ 3857/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.9546 s
>>> Epoch [ 3858/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.4093 s
>>> Epoch [ 3859/10000]
train_loss: 2.0464 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.7053 s
>>> Epoch [ 3860/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.6004 s
>>> Epoch [ 3861/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.7979 s
>>> Epoch [ 3862/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.6166 s
>>> Epoch [ 3863/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.9111 s
>>> Epoch [ 3864/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.7044 s
>>> Epoch [ 3865/10000]
train_loss: 2.0464 | train_acc: 0.4268 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.6896 s
>>> Epoch [ 3866/10000]
train_loss: 2.0464 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.7952 s
>>> Epoch [ 3867/10000]
train_loss: 2.0464 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.4211 s
>>> Epoch [ 3868/10000]
train_loss: 2.0463 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 9.3463 s
>>> Epoch [ 3869/10000]
train_loss: 2.0463 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4043 | test_acc: 0.4021 | Time: 13.1912 s
>>> Epoch [ 3870/10000]
train_loss: 2.0463 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4043 | test_acc: 0.4021 | Time: 9.5980 s
>>> Epoch [ 3871/10000]
train_loss: 2.0463 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4043 | test_acc: 0.4021 | Time: 9.4826 s
>>> Epoch [ 3872/10000]
train_loss: 2.0463 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4043 | test_acc: 0.4021 | Time: 9.5437 s
>>> Epoch [ 3873/10000]
train_loss: 2.0463 | train_acc: 0.4269 | val_loss: 2.0645 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 9.5462 s
>>> Epoch [ 3874/10000]
train_loss: 2.0463 | train_acc: 0.4270 | val_loss: 2.0645 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 9.4776 s
>>> Epoch [ 3875/10000]
train_loss: 2.0463 | train_acc: 0.4270 | val_loss: 2.0645 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 9.3617 s
>>> Epoch [ 3876/10000]
train_loss: 2.0463 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 8.6885 s
>>> Epoch [ 3877/10000]
train_loss: 2.0463 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 8.3998 s
>>> Epoch [ 3878/10000]
train_loss: 2.0463 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 8.1826 s
>>> Epoch [ 3879/10000]
train_loss: 2.0463 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 8.1841 s
>>> Epoch [ 3880/10000]
train_loss: 2.0463 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4021 | Time: 8.2233 s
>>> Epoch [ 3881/10000]
train_loss: 2.0463 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 11.2763 s
>>> Epoch [ 3882/10000]
train_loss: 2.0462 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 12.5918 s
>>> Epoch [ 3883/10000]
train_loss: 2.0462 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4020 | Time: 10.9146 s
>>> Epoch [ 3884/10000]
train_loss: 2.0462 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4019 | Time: 11.1390 s
>>> Epoch [ 3885/10000]
train_loss: 2.0462 | train_acc: 0.4270 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4019 | Time: 10.9498 s
>>> Epoch [ 3886/10000]
train_loss: 2.0462 | train_acc: 0.4271 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4019 | Time: 10.9490 s
>>> Epoch [ 3887/10000]
train_loss: 2.0462 | train_acc: 0.4271 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4019 | Time: 11.0049 s
>>> Epoch [ 3888/10000]
train_loss: 2.0462 | train_acc: 0.4271 | val_loss: 2.0644 | val_acc: 0.4043 | test_acc: 0.4019 | Time: 11.1237 s
>>> Epoch [ 3889/10000]
train_loss: 2.0462 | train_acc: 0.4271 | val_loss: 2.0644 | val_acc: 0.4042 | test_acc: 0.4019 | Time: 10.8700 s
>>> Epoch [ 3890/10000]
train_loss: 2.0462 | train_acc: 0.4271 | val_loss: 2.0644 | val_acc: 0.4042 | test_acc: 0.4019 | Time: 9.6712 s
>>> Epoch [ 3891/10000]
train_loss: 2.0462 | train_acc: 0.4271 | val_loss: 2.0644 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.2351 s
>>> Epoch [ 3892/10000]
train_loss: 2.0462 | train_acc: 0.4271 | val_loss: 2.0644 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.1143 s
>>> Epoch [ 3893/10000]
train_loss: 2.0462 | train_acc: 0.4272 | val_loss: 2.0644 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.3876 s
>>> Epoch [ 3894/10000]
train_loss: 2.0462 | train_acc: 0.4272 | val_loss: 2.0644 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.2004 s
>>> Epoch [ 3895/10000]
train_loss: 2.0462 | train_acc: 0.4272 | val_loss: 2.0644 | val_acc: 0.4041 | test_acc: 0.4020 | Time: 7.8645 s
>>> Epoch [ 3896/10000]
train_loss: 2.0462 | train_acc: 0.4272 | val_loss: 2.0644 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 7.8081 s
>>> Epoch [ 3897/10000]
train_loss: 2.0461 | train_acc: 0.4273 | val_loss: 2.0644 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.2802 s
>>> Epoch [ 3898/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4041 | test_acc: 0.4020 | Time: 8.4884 s
>>> Epoch [ 3899/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4041 | test_acc: 0.4020 | Time: 8.5487 s
>>> Epoch [ 3900/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4041 | test_acc: 0.4020 | Time: 8.4457 s
>>> Epoch [ 3901/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4041 | test_acc: 0.4020 | Time: 8.6163 s
>>> Epoch [ 3902/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4041 | test_acc: 0.4020 | Time: 8.4521 s
>>> Epoch [ 3903/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 9.0414 s
>>> Epoch [ 3904/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.8126 s
>>> Epoch [ 3905/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.7724 s
>>> Epoch [ 3906/10000]
train_loss: 2.0461 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.9373 s
>>> Epoch [ 3907/10000]
train_loss: 2.0461 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.8625 s
>>> Epoch [ 3908/10000]
train_loss: 2.0461 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4020 | Time: 8.5996 s
>>> Epoch [ 3909/10000]
train_loss: 2.0461 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.9823 s
>>> Epoch [ 3910/10000]
train_loss: 2.0461 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.9403 s
>>> Epoch [ 3911/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 8.7663 s
>>> Epoch [ 3912/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 9.1359 s
>>> Epoch [ 3913/10000]
train_loss: 2.0460 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.9857 s
>>> Epoch [ 3914/10000]
train_loss: 2.0460 | train_acc: 0.4272 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.8825 s
>>> Epoch [ 3915/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.7872 s
>>> Epoch [ 3916/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.7224 s
>>> Epoch [ 3917/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.9888 s
>>> Epoch [ 3918/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0643 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.8493 s
>>> Epoch [ 3919/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.7896 s
>>> Epoch [ 3920/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 9.2564 s
>>> Epoch [ 3921/10000]
train_loss: 2.0460 | train_acc: 0.4273 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.9361 s
>>> Epoch [ 3922/10000]
train_loss: 2.0460 | train_acc: 0.4274 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 11.9213 s
>>> Epoch [ 3923/10000]
train_loss: 2.0460 | train_acc: 0.4274 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 10.1464 s
>>> Epoch [ 3924/10000]
train_loss: 2.0460 | train_acc: 0.4274 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 13.5343 s
>>> Epoch [ 3925/10000]
train_loss: 2.0460 | train_acc: 0.4274 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.2330 s
>>> Epoch [ 3926/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.7777 s
>>> Epoch [ 3927/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.7500 s
>>> Epoch [ 3928/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 8.6898 s
>>> Epoch [ 3929/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 8.5221 s
>>> Epoch [ 3930/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 8.5175 s
>>> Epoch [ 3931/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 8.6993 s
>>> Epoch [ 3932/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 9.0009 s
>>> Epoch [ 3933/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.7306 s
>>> Epoch [ 3934/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.5443 s
>>> Epoch [ 3935/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.9617 s
>>> Epoch [ 3936/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.8334 s
>>> Epoch [ 3937/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 9.1835 s
>>> Epoch [ 3938/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 9.0726 s
>>> Epoch [ 3939/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 8.5559 s
>>> Epoch [ 3940/10000]
train_loss: 2.0459 | train_acc: 0.4275 | val_loss: 2.0642 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 8.6484 s
>>> Epoch [ 3941/10000]
train_loss: 2.0458 | train_acc: 0.4275 | val_loss: 2.0641 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 9.0947 s
>>> Epoch [ 3942/10000]
train_loss: 2.0458 | train_acc: 0.4275 | val_loss: 2.0641 | val_acc: 0.4042 | test_acc: 0.4024 | Time: 8.5575 s
>>> Epoch [ 3943/10000]
train_loss: 2.0458 | train_acc: 0.4275 | val_loss: 2.0641 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.5127 s
>>> Epoch [ 3944/10000]
train_loss: 2.0458 | train_acc: 0.4276 | val_loss: 2.0641 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.5610 s
>>> Epoch [ 3945/10000]
train_loss: 2.0458 | train_acc: 0.4276 | val_loss: 2.0641 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 8.9220 s
>>> Epoch [ 3946/10000]
train_loss: 2.0458 | train_acc: 0.4276 | val_loss: 2.0641 | val_acc: 0.4042 | test_acc: 0.4023 | Time: 9.0380 s
>>> Epoch [ 3947/10000]
train_loss: 2.0458 | train_acc: 0.4276 | val_loss: 2.0641 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.9694 s
>>> Epoch [ 3948/10000]
train_loss: 2.0458 | train_acc: 0.4277 | val_loss: 2.0641 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 9.1049 s
>>> Epoch [ 3972/10000]
train_loss: 2.0456 | train_acc: 0.4278 | val_loss: 2.0640 | val_acc: 0.4039 | test_acc: 0.4020 | Time: 9.0910 s
>>> Epoch [ 3973/10000]
train_loss: 2.0456 | train_acc: 0.4278 | val_loss: 2.0640 | val_acc: 0.4039 | test_acc: 0.4021 | Time: 8.7176 s
>>> Epoch [ 3974/10000]
train_loss: 2.0456 | train_acc: 0.4279 | val_loss: 2.0640 | val_acc: 0.4039 | test_acc: 0.4021 | Time: 8.9681 s
>>> Epoch [ 3975/10000]
train_loss: 2.0456 | train_acc: 0.4279 | val_loss: 2.0640 | val_acc: 0.4039 | test_acc: 0.4021 | Time: 11.0715 s
>>> Epoch [ 3976/10000]
train_loss: 2.0456 | train_acc: 0.4279 | val_loss: 2.0640 | val_acc: 0.4039 | test_acc: 0.4021 | Time: 11.6591 s
>>> Epoch [ 3977/10000]
train_loss: 2.0456 | train_acc: 0.4279 | val_loss: 2.0640 | val_acc: 0.4039 | test_acc: 0.4022 | Time: 13.0355 s
>>> Epoch [ 3978/10000]
train_loss: 2.0456 | train_acc: 0.4279 | val_loss: 2.0640 | val_acc: 0.4040 | test_acc: 0.4022 | Time: 8.2515 s
>>> Epoch [ 3979/10000]
train_loss: 2.0456 | train_acc: 0.4279 | val_loss: 2.0640 | val_acc: 0.4040 | test_acc: 0.4021 | Time: 8.6094 s
>>> Epoch [ 3980/10000]
train_loss: 2.0456 | train_acc: 0.4279 | val_loss: 2.0640 | val_acc: 0.4040 | test_acc: 0.4021 | Time: 8.8517 s
>>> Epoch [ 3981/10000]
train_loss: 2.0456 | train_acc: 0.4280 | val_loss: 2.0640 | val_acc: 0.4040 | test_acc: 0.4021 | Time: 9.0217 s
>>> Epoch [ 3982/10000]
train_loss: 2.0456 | train_acc: 0.4280 | val_loss: 2.0640 | val_acc: 0.4040 | test_acc: 0.4021 | Time: 9.0194 s
>>> Epoch [ 3983/10000]
train_loss: 2.0456 | train_acc: 0.4280 | val_loss: 2.0640 | val_acc: 0.4040 | test_acc: 0.4021 | Time: 8.9853 s
>>> Epoch [ 3984/10000]
train_loss: 2.0456 | train_acc: 0.4280 | val_loss: 2.0640 | val_acc: 0.4040 | test_acc: 0.4021 | Time: 8.7217 s
>>> Epoch [ 3985/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4041 | test_acc: 0.4021 | Time: 8.7148 s
>>> Epoch [ 3986/10000]
train_loss: 2.0455 | train_acc: 0.4281 | val_loss: 2.0639 | val_acc: 0.4041 | test_acc: 0.4021 | Time: 9.1004 s
>>> Epoch [ 3987/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 9.1100 s
>>> Epoch [ 3988/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4021 | Time: 9.0761 s
>>> Epoch [ 3989/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 9.1766 s
>>> Epoch [ 3990/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.9289 s
>>> Epoch [ 3991/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.8702 s
>>> Epoch [ 3992/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 9.2271 s
>>> Epoch [ 3993/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 9.0351 s
>>> Epoch [ 3994/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.8187 s
>>> Epoch [ 3995/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.7650 s
>>> Epoch [ 3996/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.9990 s
>>> Epoch [ 3997/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 9.2038 s
>>> Epoch [ 3998/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 8.9463 s
>>> Epoch [ 3999/10000]
train_loss: 2.0455 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4042 | test_acc: 0.4022 | Time: 9.0236 s
>>> Epoch [ 4000/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4044 | test_acc: 0.4022 | Time: 8.9129 s
>>> Epoch [ 4001/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4044 | test_acc: 0.4023 | Time: 8.7379 s
>>> Epoch [ 4002/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 8.8185 s
>>> Epoch [ 4003/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 10.8181 s
>>> Epoch [ 4004/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 10.0880 s
>>> Epoch [ 4005/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 8.9621 s
>>> Epoch [ 4006/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0639 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 9.2255 s
>>> Epoch [ 4007/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0638 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 8.8916 s
>>> Epoch [ 4008/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0638 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 8.8797 s
>>> Epoch [ 4009/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0638 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 9.0259 s
>>> Epoch [ 4010/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0638 | val_acc: 0.4043 | test_acc: 0.4024 | Time: 9.1913 s
>>> Epoch [ 4011/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0638 | val_acc: 0.4044 | test_acc: 0.4024 | Time: 9.2379 s
>>> Epoch [ 4012/10000]
train_loss: 2.0454 | train_acc: 0.4280 | val_loss: 2.0638 | val_acc: 0.4044 | test_acc: 0.4024 | Time: 8.9328 s
>>> Epoch [ 4013/10000]
train_loss: 2.0454 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4044 | test_acc: 0.4024 | Time: 8.9268 s
>>> Epoch [ 4014/10000]
train_loss: 2.0454 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4044 | test_acc: 0.4024 | Time: 9.0605 s
>>> Epoch [ 4015/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4044 | test_acc: 0.4024 | Time: 9.1686 s
>>> Epoch [ 4016/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4044 | test_acc: 0.4024 | Time: 9.0688 s
>>> Epoch [ 4017/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4045 | test_acc: 0.4025 | Time: 9.0390 s
>>> Epoch [ 4018/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 9.0273 s
>>> Epoch [ 4019/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 8.8338 s
>>> Epoch [ 4020/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 8.9512 s
>>> Epoch [ 4021/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 9.0109 s
>>> Epoch [ 4022/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4024 | Time: 8.6669 s
>>> Epoch [ 4023/10000]
train_loss: 2.0453 | train_acc: 0.4281 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4024 | Time: 8.9915 s
>>> Epoch [ 4024/10000]
train_loss: 2.0453 | train_acc: 0.4282 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4024 | Time: 9.0491 s
>>> Epoch [ 4025/10000]
train_loss: 2.0453 | train_acc: 0.4282 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4024 | Time: 8.8578 s
>>> Epoch [ 4026/10000]
train_loss: 2.0453 | train_acc: 0.4282 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 12.1519 s
>>> Epoch [ 4027/10000]
train_loss: 2.0453 | train_acc: 0.4282 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 11.5126 s
>>> Epoch [ 4028/10000]
train_loss: 2.0453 | train_acc: 0.4282 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 9.3850 s
>>> Epoch [ 4029/10000]
train_loss: 2.0453 | train_acc: 0.4282 | val_loss: 2.0638 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 9.2873 s
>>> Epoch [ 4030/10000]
train_loss: 2.0452 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 9.4246 s
>>> Epoch [ 4031/10000]
train_loss: 2.0452 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 9.3587 s
>>> Epoch [ 4032/10000]
train_loss: 2.0452 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 9.2241 s
>>> Epoch [ 4033/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 9.1735 s
>>> Epoch [ 4034/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 8.4664 s
>>> Epoch [ 4035/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4025 | Time: 13.5909 s
>>> Epoch [ 4036/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 11.6824 s
>>> Epoch [ 4037/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 11.2226 s
>>> Epoch [ 4038/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 11.4557 s
>>> Epoch [ 4039/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 11.4059 s
>>> Epoch [ 4040/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 11.1582 s
>>> Epoch [ 4041/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 11.4855 s
>>> Epoch [ 4042/10000]
train_loss: 2.0452 | train_acc: 0.4282 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 11.1377 s
>>> Epoch [ 4043/10000]
train_loss: 2.0452 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 9.6700 s
>>> Epoch [ 4044/10000]
train_loss: 2.0452 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 8.6370 s
>>> Epoch [ 4045/10000]
train_loss: 2.0451 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4046 | test_acc: 0.4026 | Time: 8.5531 s
>>> Epoch [ 4046/10000]
train_loss: 2.0451 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4047 | test_acc: 0.4026 | Time: 8.4526 s
>>> Epoch [ 4047/10000]
train_loss: 2.0451 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4047 | test_acc: 0.4026 | Time: 7.4533 s
>>> Epoch [ 4048/10000]
train_loss: 2.0451 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4047 | test_acc: 0.4026 | Time: 7.9824 s
>>> Epoch [ 4049/10000]
train_loss: 2.0451 | train_acc: 0.4283 | val_loss: 2.0637 | val_acc: 0.4047 | test_acc: 0.4026 | Time: 7.5737 s
>>> Epoch [ 4050/10000]
train_loss: 2.0451 | train_acc: 0.4284 | val_loss: 2.0637 | val_acc: 0.4047 | test_acc: 0.4026 | Time: 8.1389 s
>>> Epoch [ 4051/10000]
train_loss: 2.0451 | train_acc: 0.4284 | val_loss: 2.0637 | val_acc: 0.4047 | test_acc: 0.4026 | Time: 7.9446 s
>>> Epoch [ 4052/10000]
train_loss: 2.0451 | train_acc: 0.4284 | val_loss: 2.0637 | val_acc: 0.4047 | test_acc: 0.4027 | Time: 8.1266 s
>>> Epoch [ 4053/10000]
train_loss: 2.0451 | train_acc: 0.4284 | val_loss: 2.0636 | val_acc: 0.4047 | test_acc: 0.4027 | Time: 8.0427 s
>>> Epoch [ 4054/10000]
train_loss: 2.0451 | train_acc: 0.4284 | val_loss: 2.0636 | val_acc: 0.4047 | test_acc: 0.4026 | Time: 7.7058 s
>>> Epoch [ 4055/10000]
train_loss: 2.0451 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4047 | test_acc: 0.4026 | Time: 8.4735 s
>>> Epoch [ 4056/10000]
train_loss: 2.0451 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4048 | test_acc: 0.4026 | Time: 8.6012 s
>>> Epoch [ 4057/10000]
train_loss: 2.0451 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4049 | test_acc: 0.4026 | Time: 8.4012 s
>>> Epoch [ 4058/10000]
train_loss: 2.0451 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4049 | test_acc: 0.4026 | Time: 8.5949 s
>>> Epoch [ 4059/10000]
train_loss: 2.0451 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4050 | test_acc: 0.4026 | Time: 8.5122 s
>>> Epoch [ 4060/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4050 | test_acc: 0.4026 | Time: 8.5628 s
>>> Epoch [ 4061/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4050 | test_acc: 0.4026 | Time: 8.5038 s
>>> Epoch [ 4062/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4050 | test_acc: 0.4026 | Time: 8.5060 s
>>> Epoch [ 4063/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4050 | test_acc: 0.4026 | Time: 8.5537 s
>>> Epoch [ 4064/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4026 | Time: 8.4009 s
>>> Epoch [ 4065/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4026 | Time: 8.4524 s
>>> Epoch [ 4066/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4025 | Time: 8.6592 s
>>> Epoch [ 4067/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4025 | Time: 8.2361 s
>>> Epoch [ 4068/10000]
train_loss: 2.0450 | train_acc: 0.4285 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4026 | Time: 8.3841 s
>>> Epoch [ 4069/10000]
train_loss: 2.0450 | train_acc: 0.4286 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4026 | Time: 8.8329 s
>>> Epoch [ 4070/10000]
train_loss: 2.0450 | train_acc: 0.4286 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4026 | Time: 12.6486 s
>>> Epoch [ 4071/10000]
train_loss: 2.0450 | train_acc: 0.4286 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4026 | Time: 7.4323 s
>>> Epoch [ 4072/10000]
train_loss: 2.0450 | train_acc: 0.4286 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4026 | Time: 7.8210 s
>>> Epoch [ 4073/10000]
train_loss: 2.0450 | train_acc: 0.4286 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4027 | Time: 7.6018 s
>>> Epoch [ 4074/10000]
train_loss: 2.0450 | train_acc: 0.4286 | val_loss: 2.0636 | val_acc: 0.4051 | test_acc: 0.4027 | Time: 7.6206 s
>>> Epoch [ 4075/10000]
train_loss: 2.0450 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4051 | test_acc: 0.4027 | Time: 7.5559 s
>>> Epoch [ 4076/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4051 | test_acc: 0.4027 | Time: 9.7311 s
>>> Epoch [ 4077/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4051 | test_acc: 0.4027 | Time: 11.7029 s
>>> Epoch [ 4078/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4051 | test_acc: 0.4027 | Time: 7.8225 s
>>> Epoch [ 4079/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4051 | test_acc: 0.4027 | Time: 8.1589 s
>>> Epoch [ 4080/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.1854 s
>>> Epoch [ 4081/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.0370 s
>>> Epoch [ 4082/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.1104 s
>>> Epoch [ 4083/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.4345 s
>>> Epoch [ 4084/10000]
train_loss: 2.0449 | train_acc: 0.4287 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.6838 s
>>> Epoch [ 4085/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.3359 s
>>> Epoch [ 4086/10000]
train_loss: 2.0449 | train_acc: 0.4287 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.4791 s
>>> Epoch [ 4087/10000]
train_loss: 2.0449 | train_acc: 0.4287 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.7575 s
>>> Epoch [ 4088/10000]
train_loss: 2.0449 | train_acc: 0.4287 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.3709 s
>>> Epoch [ 4089/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.6897 s
>>> Epoch [ 4090/10000]
train_loss: 2.0449 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.5805 s
>>> Epoch [ 4091/10000]
train_loss: 2.0448 | train_acc: 0.4286 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.7470 s
>>> Epoch [ 4092/10000]
train_loss: 2.0448 | train_acc: 0.4287 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.7260 s
>>> Epoch [ 4093/10000]
train_loss: 2.0448 | train_acc: 0.4287 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.8620 s
>>> Epoch [ 4094/10000]
train_loss: 2.0448 | train_acc: 0.4288 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.4596 s
>>> Epoch [ 4095/10000]
train_loss: 2.0448 | train_acc: 0.4288 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.5818 s
>>> Epoch [ 4096/10000]
train_loss: 2.0448 | train_acc: 0.4288 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.7919 s
>>> Epoch [ 4097/10000]
train_loss: 2.0448 | train_acc: 0.4288 | val_loss: 2.0635 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.5577 s
>>> Epoch [ 4098/10000]
train_loss: 2.0448 | train_acc: 0.4288 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 12.7614 s
>>> Epoch [ 4099/10000]
train_loss: 2.0448 | train_acc: 0.4288 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 11.4518 s
>>> Epoch [ 4100/10000]
train_loss: 2.0448 | train_acc: 0.4288 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 10.8702 s
>>> Epoch [ 4101/10000]
train_loss: 2.0448 | train_acc: 0.4288 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 7.7044 s
>>> Epoch [ 4102/10000]
train_loss: 2.0448 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.2052 s
>>> Epoch [ 4103/10000]
train_loss: 2.0448 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 7.9491 s
>>> Epoch [ 4104/10000]
train_loss: 2.0448 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.6196 s
>>> Epoch [ 4105/10000]
train_loss: 2.0448 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.5083 s
>>> Epoch [ 4106/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.7323 s
>>> Epoch [ 4107/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.5583 s
>>> Epoch [ 4108/10000]
train_loss: 2.0447 | train_acc: 0.4290 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.5475 s
>>> Epoch [ 4109/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.6308 s
>>> Epoch [ 4110/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.5228 s
>>> Epoch [ 4111/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.6428 s
>>> Epoch [ 4112/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.4945 s
>>> Epoch [ 4113/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.5156 s
>>> Epoch [ 4114/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.4364 s
>>> Epoch [ 4115/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.4376 s
>>> Epoch [ 4116/10000]
train_loss: 2.0447 | train_acc: 0.4289 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.6268 s
>>> Epoch [ 4117/10000]
train_loss: 2.0447 | train_acc: 0.4290 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.4050 s
>>> Epoch [ 4118/10000]
train_loss: 2.0447 | train_acc: 0.4290 | val_loss: 2.0634 | val_acc: 0.4052 | test_acc: 0.4027 | Time: 8.9009 s
>>> Epoch [ 4119/10000]
train_loss: 2.0447 | train_acc: 0.4290 | val_loss: 2.0634 | val_acc: 0.4053 | test_acc: 0.4027 | Time: 12.2218 s
---------------------------------------------------------------------------
ResourceExhaustedError                    Traceback (most recent call last)
<ipython-input-19-458245b6132c> in <module>()
      1 start = time.time()
      2 lc.fit(cifar10.train.data, cifar10.train.one_hot_labels, cifar10.train.class_labels,
----> 3        test_data=cifar10.test.data, test_labels=cifar10.test.one_hot_labels, test_classes=cifar10.test.class_labels)
      4 end = time.time()
      5 print('Fit completed in %.4f seconds' % (end-start))

/net/voxel03/misc/me/praneethas/PycharmProjects/object-recognition/library/tf/models/linear_classifier.py in fit(self, data, labels, classes, test_data, test_labels, test_classes)
    295                        validate_data=validate_data, validate_labels=validate_labels,
    296                        validate_classes=validate_classes, test_data=test_data,
--> 297                        test_labels=test_labels, test_classes=test_classes)
    298 
    299     def learn(self, train_data, train_labels, train_classes,

/net/voxel03/misc/me/praneethas/PycharmProjects/object-recognition/library/tf/models/linear_classifier.py in learn(self, train_data, train_labels, train_classes, validate_data, validate_labels, validate_classes, test_data, test_labels, test_classes)
    392                 model_directory = os.path.dirname(self.checkpoint_filename)
    393                 file_utils.mkdir_p(model_directory)
--> 394                 self.model.save(self.session, self.checkpoint_filename, global_step=epoch)
    395             if epoch == 0:
    396                 prev_cost = train_loss

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py in save(self, sess, save_path, global_step, latest_filename, meta_graph_suffix, write_meta_graph, write_state)
   1373           checkpoint_file, meta_graph_suffix=meta_graph_suffix)
   1374       with sess.graph.as_default():
-> 1375         self.export_meta_graph(meta_graph_filename)
   1376 
   1377     if self._is_empty:

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py in export_meta_graph(self, filename, collection_list, as_text, export_scope, clear_devices)
   1406         as_text=as_text,
   1407         export_scope=export_scope,
-> 1408         clear_devices=clear_devices)
   1409 
   1410   def restore(self, sess, save_path):

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/saver.py in export_meta_graph(filename, meta_info_def, graph_def, saver_def, collection_list, as_text, graph, export_scope, clear_devices, **kwargs)
   1628       export_scope=export_scope,
   1629       clear_devices=clear_devices,
-> 1630       **kwargs)
   1631   return meta_graph_def
   1632 

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/meta_graph.py in export_scoped_meta_graph(filename, graph_def, graph, export_scope, as_text, unbound_inputs_col_name, clear_devices, **kwargs)
    645         os.path.dirname(filename),
    646         os.path.basename(filename),
--> 647         as_text=as_text)
    648 
    649   return scoped_meta_graph_def, var_list

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/graph_io.py in write_graph(graph_or_graph_def, logdir, name, as_text)
     67     file_io.atomic_write_string_to_file(path, str(graph_def))
     68   else:
---> 69     file_io.atomic_write_string_to_file(path, graph_def.SerializeToString())
     70   return path

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/lib/io/file_io.py in atomic_write_string_to_file(filename, contents)
    350   """
    351   temp_pathname = filename + ".tmp" + uuid.uuid4().hex
--> 352   write_string_to_file(temp_pathname, contents)
    353   rename(temp_pathname, filename, overwrite=True)
    354 

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/lib/io/file_io.py in write_string_to_file(filename, file_content)
    247   """
    248   with FileIO(filename, mode="w") as f:
--> 249     f.write(file_content)
    250 
    251 

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/lib/io/file_io.py in __exit__(self, unused_type, unused_value, unused_traceback)
    148   def __exit__(self, unused_type, unused_value, unused_traceback):
    149     """Make usable with "with" statement."""
--> 150     self.close()
    151 
    152   def __iter__(self):

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/lib/io/file_io.py in close(self)
    180       with errors.raise_exception_on_not_ok_status() as status:
    181         ret_status = self._writable_file.Close()
--> 182         pywrap_tensorflow.Set_TF_Status_from_Status(status, ret_status)
    183     self._writable_file = None
    184 

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/contextlib.py in __exit__(self, type, value, traceback)
     87         if type is None:
     88             try:
---> 89                 next(self.gen)
     90             except StopIteration:
     91                 return

/net/voxel03/misc/me/praneethas/Softwares/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
    464           None, None,
    465           compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 466           pywrap_tensorflow.TF_GetCode(status))
    467   finally:
    468     pywrap_tensorflow.TF_DeleteStatus(status)

ResourceExhaustedError: ../logs/cifar10/101_tf_linear_raw/exp_no_006/linear_classifier.ckpt-4119.meta.tmp8334d74b3f234080b477e9d655173261

Step 2.4: Make the predictions


In [ ]:
prediction_numbers = lc.predict(cifar10.test.data)
prediction_classes = []
num_test_images = cifar10.test.data.shape[0]
for i in range(num_test_images):
    prediction_classes.append(cifar10.classes[int(prediction_numbers[i])])

In [ ]:
cifar10.plot_images(cifar10.test.data[:50], cifar10.test.class_names[:50], cls_pred=prediction_classes[:50], 
                    nrows=5, ncols=10, fig_size=(20,50), fontsize=30, convert=True)

Step 2.5: Print the results


In [ ]:
test_accuracy = lc.score(cifar10.test.data, cifar10.test.class_labels)
print('Accuracy of the linear classifier on test dataset: %.4f' % test_accuracy)

In [ ]:
lc.print_classification_results(cifar10.test.data, cifar10.test.one_hot_labels, cifar10.test.class_labels,
                                test_class_names=cifar10.classes, normalize=True)

Step 2.6: Plot results


In [ ]:
lc.plot_loss()

In [ ]:
lc.plot_accuracy()

In [ ]:
lc.plot_weights(classes=cifar10.classes)

Step 2.7: Close the session


In [ ]:
lc.close()

Step 3: Write to file


In [ ]:
def output_HTML(read_file, output_file):
    from nbconvert import HTMLExporter
    import codecs
    import nbformat
    exporter = HTMLExporter()
    output_notebook = nbformat.read(read_file, as_version=4)
    print()
    output, resources = exporter.from_notebook_node(output_notebook)
    codecs.open(output_file, 'w', encoding='utf-8').write(output)

In [ ]:
%%javascript
var notebook = IPython.notebook
notebook.save_notebook()

In [ ]:
%%javascript
var kernel = IPython.notebook.kernel;
var thename = window.document.getElementById("notebook_name").innerHTML;
var command = "theNotebook = " + "'"+thename+"'";
kernel.execute(command);

In [ ]:
current_file = './' + theNotebook + '.ipynb'
output_file = log_dir + str(file_no).zfill(3) + '_exp_no_' + str(exp_no).zfill(3) + '_' + theNotebook + '.html'
print('Current file: ' + str(current_file))
print('Output file: ' + str(output_file))
file_utils.mkdir_p(log_dir) 
output_HTML(current_file, output_file)

In [ ]:


In [ ]: