DIGITS-CNN/cars/architecture-investigations/conv/nonlinear/l5/4parts/caffe_output.log

I0412 12:48:31.490209  6895 upgrade_proto.cpp:1082] Attempting to upgrade input file specified using deprecated 'solver_type' field (enum)': /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210412-124829-f869/solver.prototxt
I0412 12:48:31.490355  6895 upgrade_proto.cpp:1089] Successfully upgraded file specified using deprecated 'solver_type' field (enum) to 'type' field (string).
W0412 12:48:31.490360  6895 upgrade_proto.cpp:1091] Note that future Caffe releases will only support 'type' field (string) for a solver's type.
I0412 12:48:31.490418  6895 caffe.cpp:218] Using GPUs 2
I0412 12:48:31.504951  6895 caffe.cpp:223] GPU 2: GeForce GTX 1080 Ti
I0412 12:48:31.798967  6895 solver.cpp:44] Initializing solver from parameters:
test_iter: 51
test_interval: 102
base_lr: 0.01
display: 12
max_iter: 10200
lr_policy: "exp"
gamma: 0.99980193
momentum: 0.9
weight_decay: 0.0001
snapshot: 102
snapshot_prefix: "snapshot"
solver_mode: GPU
device_id: 2
net: "train_val.prototxt"
train_state {
level: 0
stage: ""
}
type: "SGD"
I0412 12:48:31.799770  6895 solver.cpp:87] Creating training net from net file: train_val.prototxt
I0412 12:48:31.800387  6895 net.cpp:294] The NetState phase (0) differed from the phase (1) specified by a rule in layer val-data
I0412 12:48:31.800403  6895 net.cpp:294] The NetState phase (0) differed from the phase (1) specified by a rule in layer accuracy
I0412 12:48:31.800571  6895 net.cpp:51] Initializing net from parameters:
state {
phase: TRAIN
level: 0
stage: ""
}
layer {
name: "train-data"
type: "Data"
top: "data"
top: "label"
include {
phase: TRAIN
}
transform_param {
mirror: true
crop_size: 227
mean_file: "/mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/mean.binaryproto"
}
data_param {
source: "/mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/train_db"
batch_size: 128
backend: LMDB
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "norm2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "conv5.2"
type: "Convolution"
bottom: "conv5"
top: "conv5.2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5.2"
type: "ReLU"
bottom: "conv5.2"
top: "conv5.2"
}
layer {
name: "conv5.3"
type: "Convolution"
bottom: "conv5.2"
top: "conv5.3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5.3"
type: "ReLU"
bottom: "conv5.3"
top: "conv5.3"
}
layer {
name: "conv5.4"
type: "Convolution"
bottom: "conv5.3"
top: "conv5.4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5.4"
type: "ReLU"
bottom: "conv5.4"
top: "conv5.4"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5.4"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 196
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8"
bottom: "label"
top: "loss"
}
I0412 12:48:31.800668  6895 layer_factory.hpp:77] Creating layer train-data
I0412 12:48:31.802726  6895 db_lmdb.cpp:35] Opened lmdb /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/train_db
I0412 12:48:31.802932  6895 net.cpp:84] Creating Layer train-data
I0412 12:48:31.802942  6895 net.cpp:380] train-data -> data
I0412 12:48:31.802963  6895 net.cpp:380] train-data -> label
I0412 12:48:31.802973  6895 data_transformer.cpp:25] Loading mean file from: /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/mean.binaryproto
I0412 12:48:31.807654  6895 data_layer.cpp:45] output data size: 128,3,227,227
I0412 12:48:31.939566  6895 net.cpp:122] Setting up train-data
I0412 12:48:31.939589  6895 net.cpp:129] Top shape: 128 3 227 227 (19787136)
I0412 12:48:31.939594  6895 net.cpp:129] Top shape: 128 (128)
I0412 12:48:31.939597  6895 net.cpp:137] Memory required for data: 79149056
I0412 12:48:31.939607  6895 layer_factory.hpp:77] Creating layer conv1
I0412 12:48:31.939627  6895 net.cpp:84] Creating Layer conv1
I0412 12:48:31.939632  6895 net.cpp:406] conv1 <- data
I0412 12:48:31.939644  6895 net.cpp:380] conv1 -> conv1
I0412 12:48:32.483711  6895 net.cpp:122] Setting up conv1
I0412 12:48:32.483733  6895 net.cpp:129] Top shape: 128 96 55 55 (37171200)
I0412 12:48:32.483737  6895 net.cpp:137] Memory required for data: 227833856
I0412 12:48:32.483755  6895 layer_factory.hpp:77] Creating layer relu1
I0412 12:48:32.483765  6895 net.cpp:84] Creating Layer relu1
I0412 12:48:32.483769  6895 net.cpp:406] relu1 <- conv1
I0412 12:48:32.483776  6895 net.cpp:367] relu1 -> conv1 (in-place)
I0412 12:48:32.484066  6895 net.cpp:122] Setting up relu1
I0412 12:48:32.484076  6895 net.cpp:129] Top shape: 128 96 55 55 (37171200)
I0412 12:48:32.484079  6895 net.cpp:137] Memory required for data: 376518656
I0412 12:48:32.484083  6895 layer_factory.hpp:77] Creating layer norm1
I0412 12:48:32.484091  6895 net.cpp:84] Creating Layer norm1
I0412 12:48:32.484095  6895 net.cpp:406] norm1 <- conv1
I0412 12:48:32.484100  6895 net.cpp:380] norm1 -> norm1
I0412 12:48:32.484557  6895 net.cpp:122] Setting up norm1
I0412 12:48:32.484568  6895 net.cpp:129] Top shape: 128 96 55 55 (37171200)
I0412 12:48:32.484571  6895 net.cpp:137] Memory required for data: 525203456
I0412 12:48:32.484575  6895 layer_factory.hpp:77] Creating layer pool1
I0412 12:48:32.484583  6895 net.cpp:84] Creating Layer pool1
I0412 12:48:32.484586  6895 net.cpp:406] pool1 <- norm1
I0412 12:48:32.484591  6895 net.cpp:380] pool1 -> pool1
I0412 12:48:32.484627  6895 net.cpp:122] Setting up pool1
I0412 12:48:32.484633  6895 net.cpp:129] Top shape: 128 96 27 27 (8957952)
I0412 12:48:32.484637  6895 net.cpp:137] Memory required for data: 561035264
I0412 12:48:32.484640  6895 layer_factory.hpp:77] Creating layer conv2
I0412 12:48:32.484649  6895 net.cpp:84] Creating Layer conv2
I0412 12:48:32.484653  6895 net.cpp:406] conv2 <- pool1
I0412 12:48:32.484658  6895 net.cpp:380] conv2 -> conv2
I0412 12:48:32.491274  6895 net.cpp:122] Setting up conv2
I0412 12:48:32.491288  6895 net.cpp:129] Top shape: 128 256 27 27 (23887872)
I0412 12:48:32.491292  6895 net.cpp:137] Memory required for data: 656586752
I0412 12:48:32.491302  6895 layer_factory.hpp:77] Creating layer relu2
I0412 12:48:32.491307  6895 net.cpp:84] Creating Layer relu2
I0412 12:48:32.491312  6895 net.cpp:406] relu2 <- conv2
I0412 12:48:32.491317  6895 net.cpp:367] relu2 -> conv2 (in-place)
I0412 12:48:32.491741  6895 net.cpp:122] Setting up relu2
I0412 12:48:32.491751  6895 net.cpp:129] Top shape: 128 256 27 27 (23887872)
I0412 12:48:32.491755  6895 net.cpp:137] Memory required for data: 752138240
I0412 12:48:32.491758  6895 layer_factory.hpp:77] Creating layer norm2
I0412 12:48:32.491765  6895 net.cpp:84] Creating Layer norm2
I0412 12:48:32.491768  6895 net.cpp:406] norm2 <- conv2
I0412 12:48:32.491775  6895 net.cpp:380] norm2 -> norm2
I0412 12:48:32.492069  6895 net.cpp:122] Setting up norm2
I0412 12:48:32.492077  6895 net.cpp:129] Top shape: 128 256 27 27 (23887872)
I0412 12:48:32.492080  6895 net.cpp:137] Memory required for data: 847689728
I0412 12:48:32.492084  6895 layer_factory.hpp:77] Creating layer pool2
I0412 12:48:32.492091  6895 net.cpp:84] Creating Layer pool2
I0412 12:48:32.492094  6895 net.cpp:406] pool2 <- norm2
I0412 12:48:32.492100  6895 net.cpp:380] pool2 -> pool2
I0412 12:48:32.492125  6895 net.cpp:122] Setting up pool2
I0412 12:48:32.492130  6895 net.cpp:129] Top shape: 128 256 13 13 (5537792)
I0412 12:48:32.492133  6895 net.cpp:137] Memory required for data: 869840896
I0412 12:48:32.492136  6895 layer_factory.hpp:77] Creating layer conv3
I0412 12:48:32.492164  6895 net.cpp:84] Creating Layer conv3
I0412 12:48:32.492168  6895 net.cpp:406] conv3 <- pool2
I0412 12:48:32.492173  6895 net.cpp:380] conv3 -> conv3
I0412 12:48:32.501987  6895 net.cpp:122] Setting up conv3
I0412 12:48:32.502000  6895 net.cpp:129] Top shape: 128 384 13 13 (8306688)
I0412 12:48:32.502004  6895 net.cpp:137] Memory required for data: 903067648
I0412 12:48:32.502013  6895 layer_factory.hpp:77] Creating layer relu3
I0412 12:48:32.502020  6895 net.cpp:84] Creating Layer relu3
I0412 12:48:32.502024  6895 net.cpp:406] relu3 <- conv3
I0412 12:48:32.502029  6895 net.cpp:367] relu3 -> conv3 (in-place)
I0412 12:48:32.502449  6895 net.cpp:122] Setting up relu3
I0412 12:48:32.502458  6895 net.cpp:129] Top shape: 128 384 13 13 (8306688)
I0412 12:48:32.502461  6895 net.cpp:137] Memory required for data: 936294400
I0412 12:48:32.502465  6895 layer_factory.hpp:77] Creating layer conv4
I0412 12:48:32.502473  6895 net.cpp:84] Creating Layer conv4
I0412 12:48:32.502477  6895 net.cpp:406] conv4 <- conv3
I0412 12:48:32.502482  6895 net.cpp:380] conv4 -> conv4
I0412 12:48:32.512389  6895 net.cpp:122] Setting up conv4
I0412 12:48:32.512403  6895 net.cpp:129] Top shape: 128 384 13 13 (8306688)
I0412 12:48:32.512408  6895 net.cpp:137] Memory required for data: 969521152
I0412 12:48:32.512415  6895 layer_factory.hpp:77] Creating layer relu4
I0412 12:48:32.512423  6895 net.cpp:84] Creating Layer relu4
I0412 12:48:32.512426  6895 net.cpp:406] relu4 <- conv4
I0412 12:48:32.512431  6895 net.cpp:367] relu4 -> conv4 (in-place)
I0412 12:48:32.512706  6895 net.cpp:122] Setting up relu4
I0412 12:48:32.512714  6895 net.cpp:129] Top shape: 128 384 13 13 (8306688)
I0412 12:48:32.512718  6895 net.cpp:137] Memory required for data: 1002747904
I0412 12:48:32.512722  6895 layer_factory.hpp:77] Creating layer conv5
I0412 12:48:32.512730  6895 net.cpp:84] Creating Layer conv5
I0412 12:48:32.512733  6895 net.cpp:406] conv5 <- conv4
I0412 12:48:32.512739  6895 net.cpp:380] conv5 -> conv5
I0412 12:48:32.517105  6895 net.cpp:122] Setting up conv5
I0412 12:48:32.517117  6895 net.cpp:129] Top shape: 128 64 13 13 (1384448)
I0412 12:48:32.517119  6895 net.cpp:137] Memory required for data: 1008285696
I0412 12:48:32.517129  6895 layer_factory.hpp:77] Creating layer relu5
I0412 12:48:32.517135  6895 net.cpp:84] Creating Layer relu5
I0412 12:48:32.517139  6895 net.cpp:406] relu5 <- conv5
I0412 12:48:32.517144  6895 net.cpp:367] relu5 -> conv5 (in-place)
I0412 12:48:32.517562  6895 net.cpp:122] Setting up relu5
I0412 12:48:32.517572  6895 net.cpp:129] Top shape: 128 64 13 13 (1384448)
I0412 12:48:32.517575  6895 net.cpp:137] Memory required for data: 1013823488
I0412 12:48:32.517580  6895 layer_factory.hpp:77] Creating layer conv5.2
I0412 12:48:32.517587  6895 net.cpp:84] Creating Layer conv5.2
I0412 12:48:32.517591  6895 net.cpp:406] conv5.2 <- conv5
I0412 12:48:32.517596  6895 net.cpp:380] conv5.2 -> conv5.2
I0412 12:48:32.520401  6895 net.cpp:122] Setting up conv5.2
I0412 12:48:32.520411  6895 net.cpp:129] Top shape: 128 64 13 13 (1384448)
I0412 12:48:32.520416  6895 net.cpp:137] Memory required for data: 1019361280
I0412 12:48:32.520421  6895 layer_factory.hpp:77] Creating layer relu5.2
I0412 12:48:32.520429  6895 net.cpp:84] Creating Layer relu5.2
I0412 12:48:32.520432  6895 net.cpp:406] relu5.2 <- conv5.2
I0412 12:48:32.520437  6895 net.cpp:367] relu5.2 -> conv5.2 (in-place)
I0412 12:48:32.520860  6895 net.cpp:122] Setting up relu5.2
I0412 12:48:32.520869  6895 net.cpp:129] Top shape: 128 64 13 13 (1384448)
I0412 12:48:32.520874  6895 net.cpp:137] Memory required for data: 1024899072
I0412 12:48:32.520876  6895 layer_factory.hpp:77] Creating layer conv5.3
I0412 12:48:32.520885  6895 net.cpp:84] Creating Layer conv5.3
I0412 12:48:32.520889  6895 net.cpp:406] conv5.3 <- conv5.2
I0412 12:48:32.520895  6895 net.cpp:380] conv5.3 -> conv5.3
I0412 12:48:32.524489  6895 net.cpp:122] Setting up conv5.3
I0412 12:48:32.524500  6895 net.cpp:129] Top shape: 128 64 13 13 (1384448)
I0412 12:48:32.524504  6895 net.cpp:137] Memory required for data: 1030436864
I0412 12:48:32.524528  6895 layer_factory.hpp:77] Creating layer relu5.3
I0412 12:48:32.524535  6895 net.cpp:84] Creating Layer relu5.3
I0412 12:48:32.524538  6895 net.cpp:406] relu5.3 <- conv5.3
I0412 12:48:32.524544  6895 net.cpp:367] relu5.3 -> conv5.3 (in-place)
I0412 12:48:32.525038  6895 net.cpp:122] Setting up relu5.3
I0412 12:48:32.525048  6895 net.cpp:129] Top shape: 128 64 13 13 (1384448)
I0412 12:48:32.525051  6895 net.cpp:137] Memory required for data: 1035974656
I0412 12:48:32.525055  6895 layer_factory.hpp:77] Creating layer conv5.4
I0412 12:48:32.525064  6895 net.cpp:84] Creating Layer conv5.4
I0412 12:48:32.525068  6895 net.cpp:406] conv5.4 <- conv5.3
I0412 12:48:32.525074  6895 net.cpp:380] conv5.4 -> conv5.4
I0412 12:48:32.529206  6895 net.cpp:122] Setting up conv5.4
I0412 12:48:32.529215  6895 net.cpp:129] Top shape: 128 64 13 13 (1384448)
I0412 12:48:32.529219  6895 net.cpp:137] Memory required for data: 1041512448
I0412 12:48:32.529225  6895 layer_factory.hpp:77] Creating layer relu5.4
I0412 12:48:32.529232  6895 net.cpp:84] Creating Layer relu5.4
I0412 12:48:32.529237  6895 net.cpp:406] relu5.4 <- conv5.4
I0412 12:48:32.529242  6895 net.cpp:367] relu5.4 -> conv5.4 (in-place)
I0412 12:48:32.529736  6895 net.cpp:122] Setting up relu5.4
I0412 12:48:32.529745  6895 net.cpp:129] Top shape: 128 64 13 13 (1384448)
I0412 12:48:32.529748  6895 net.cpp:137] Memory required for data: 1047050240
I0412 12:48:32.529752  6895 layer_factory.hpp:77] Creating layer pool5
I0412 12:48:32.529759  6895 net.cpp:84] Creating Layer pool5
I0412 12:48:32.529762  6895 net.cpp:406] pool5 <- conv5.4
I0412 12:48:32.529769  6895 net.cpp:380] pool5 -> pool5
I0412 12:48:32.529804  6895 net.cpp:122] Setting up pool5
I0412 12:48:32.529810  6895 net.cpp:129] Top shape: 128 64 6 6 (294912)
I0412 12:48:32.529814  6895 net.cpp:137] Memory required for data: 1048229888
I0412 12:48:32.529817  6895 layer_factory.hpp:77] Creating layer fc6
I0412 12:48:32.529824  6895 net.cpp:84] Creating Layer fc6
I0412 12:48:32.529826  6895 net.cpp:406] fc6 <- pool5
I0412 12:48:32.529832  6895 net.cpp:380] fc6 -> fc6
I0412 12:48:32.619758  6895 net.cpp:122] Setting up fc6
I0412 12:48:32.619781  6895 net.cpp:129] Top shape: 128 4096 (524288)
I0412 12:48:32.619783  6895 net.cpp:137] Memory required for data: 1050327040
I0412 12:48:32.619798  6895 layer_factory.hpp:77] Creating layer relu6
I0412 12:48:32.619807  6895 net.cpp:84] Creating Layer relu6
I0412 12:48:32.619812  6895 net.cpp:406] relu6 <- fc6
I0412 12:48:32.619819  6895 net.cpp:367] relu6 -> fc6 (in-place)
I0412 12:48:32.620450  6895 net.cpp:122] Setting up relu6
I0412 12:48:32.620460  6895 net.cpp:129] Top shape: 128 4096 (524288)
I0412 12:48:32.620463  6895 net.cpp:137] Memory required for data: 1052424192
I0412 12:48:32.620466  6895 layer_factory.hpp:77] Creating layer drop6
I0412 12:48:32.620473  6895 net.cpp:84] Creating Layer drop6
I0412 12:48:32.620477  6895 net.cpp:406] drop6 <- fc6
I0412 12:48:32.620482  6895 net.cpp:367] drop6 -> fc6 (in-place)
I0412 12:48:32.620509  6895 net.cpp:122] Setting up drop6
I0412 12:48:32.620515  6895 net.cpp:129] Top shape: 128 4096 (524288)
I0412 12:48:32.620519  6895 net.cpp:137] Memory required for data: 1054521344
I0412 12:48:32.620523  6895 layer_factory.hpp:77] Creating layer fc7
I0412 12:48:32.620532  6895 net.cpp:84] Creating Layer fc7
I0412 12:48:32.620535  6895 net.cpp:406] fc7 <- fc6
I0412 12:48:32.620540  6895 net.cpp:380] fc7 -> fc7
I0412 12:48:32.782341  6895 net.cpp:122] Setting up fc7
I0412 12:48:32.782361  6895 net.cpp:129] Top shape: 128 4096 (524288)
I0412 12:48:32.782363  6895 net.cpp:137] Memory required for data: 1056618496
I0412 12:48:32.782373  6895 layer_factory.hpp:77] Creating layer relu7
I0412 12:48:32.782382  6895 net.cpp:84] Creating Layer relu7
I0412 12:48:32.782387  6895 net.cpp:406] relu7 <- fc7
I0412 12:48:32.782393  6895 net.cpp:367] relu7 -> fc7 (in-place)
I0412 12:48:32.782811  6895 net.cpp:122] Setting up relu7
I0412 12:48:32.782820  6895 net.cpp:129] Top shape: 128 4096 (524288)
I0412 12:48:32.782824  6895 net.cpp:137] Memory required for data: 1058715648
I0412 12:48:32.782845  6895 layer_factory.hpp:77] Creating layer drop7
I0412 12:48:32.782852  6895 net.cpp:84] Creating Layer drop7
I0412 12:48:32.782855  6895 net.cpp:406] drop7 <- fc7
I0412 12:48:32.782861  6895 net.cpp:367] drop7 -> fc7 (in-place)
I0412 12:48:32.782886  6895 net.cpp:122] Setting up drop7
I0412 12:48:32.782891  6895 net.cpp:129] Top shape: 128 4096 (524288)
I0412 12:48:32.782893  6895 net.cpp:137] Memory required for data: 1060812800
I0412 12:48:32.782896  6895 layer_factory.hpp:77] Creating layer fc8
I0412 12:48:32.782904  6895 net.cpp:84] Creating Layer fc8
I0412 12:48:32.782907  6895 net.cpp:406] fc8 <- fc7
I0412 12:48:32.782913  6895 net.cpp:380] fc8 -> fc8
I0412 12:48:32.790649  6895 net.cpp:122] Setting up fc8
I0412 12:48:32.790659  6895 net.cpp:129] Top shape: 128 196 (25088)
I0412 12:48:32.790663  6895 net.cpp:137] Memory required for data: 1060913152
I0412 12:48:32.790669  6895 layer_factory.hpp:77] Creating layer loss
I0412 12:48:32.790676  6895 net.cpp:84] Creating Layer loss
I0412 12:48:32.790680  6895 net.cpp:406] loss <- fc8
I0412 12:48:32.790684  6895 net.cpp:406] loss <- label
I0412 12:48:32.790691  6895 net.cpp:380] loss -> loss
I0412 12:48:32.790699  6895 layer_factory.hpp:77] Creating layer loss
I0412 12:48:32.791342  6895 net.cpp:122] Setting up loss
I0412 12:48:32.791352  6895 net.cpp:129] Top shape: (1)
I0412 12:48:32.791354  6895 net.cpp:132]     with loss weight 1
I0412 12:48:32.791373  6895 net.cpp:137] Memory required for data: 1060913156
I0412 12:48:32.791375  6895 net.cpp:198] loss needs backward computation.
I0412 12:48:32.791383  6895 net.cpp:198] fc8 needs backward computation.
I0412 12:48:32.791385  6895 net.cpp:198] drop7 needs backward computation.
I0412 12:48:32.791388  6895 net.cpp:198] relu7 needs backward computation.
I0412 12:48:32.791393  6895 net.cpp:198] fc7 needs backward computation.
I0412 12:48:32.791395  6895 net.cpp:198] drop6 needs backward computation.
I0412 12:48:32.791399  6895 net.cpp:198] relu6 needs backward computation.
I0412 12:48:32.791402  6895 net.cpp:198] fc6 needs backward computation.
I0412 12:48:32.791406  6895 net.cpp:198] pool5 needs backward computation.
I0412 12:48:32.791409  6895 net.cpp:198] relu5.4 needs backward computation.
I0412 12:48:32.791414  6895 net.cpp:198] conv5.4 needs backward computation.
I0412 12:48:32.791416  6895 net.cpp:198] relu5.3 needs backward computation.
I0412 12:48:32.791420  6895 net.cpp:198] conv5.3 needs backward computation.
I0412 12:48:32.791424  6895 net.cpp:198] relu5.2 needs backward computation.
I0412 12:48:32.791426  6895 net.cpp:198] conv5.2 needs backward computation.
I0412 12:48:32.791430  6895 net.cpp:198] relu5 needs backward computation.
I0412 12:48:32.791433  6895 net.cpp:198] conv5 needs backward computation.
I0412 12:48:32.791438  6895 net.cpp:198] relu4 needs backward computation.
I0412 12:48:32.791441  6895 net.cpp:198] conv4 needs backward computation.
I0412 12:48:32.791445  6895 net.cpp:198] relu3 needs backward computation.
I0412 12:48:32.791448  6895 net.cpp:198] conv3 needs backward computation.
I0412 12:48:32.791452  6895 net.cpp:198] pool2 needs backward computation.
I0412 12:48:32.791456  6895 net.cpp:198] norm2 needs backward computation.
I0412 12:48:32.791460  6895 net.cpp:198] relu2 needs backward computation.
I0412 12:48:32.791463  6895 net.cpp:198] conv2 needs backward computation.
I0412 12:48:32.791467  6895 net.cpp:198] pool1 needs backward computation.
I0412 12:48:32.791471  6895 net.cpp:198] norm1 needs backward computation.
I0412 12:48:32.791474  6895 net.cpp:198] relu1 needs backward computation.
I0412 12:48:32.791477  6895 net.cpp:198] conv1 needs backward computation.
I0412 12:48:32.791481  6895 net.cpp:200] train-data does not need backward computation.
I0412 12:48:32.791484  6895 net.cpp:242] This network produces output loss
I0412 12:48:32.791501  6895 net.cpp:255] Network initialization done.
I0412 12:48:32.792008  6895 solver.cpp:172] Creating test net (#0) specified by net file: train_val.prototxt
I0412 12:48:32.792043  6895 net.cpp:294] The NetState phase (1) differed from the phase (0) specified by a rule in layer train-data
I0412 12:48:32.792225  6895 net.cpp:51] Initializing net from parameters:
state {
phase: TEST
}
layer {
name: "val-data"
type: "Data"
top: "data"
top: "label"
include {
phase: TEST
}
transform_param {
crop_size: 227
mean_file: "/mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/mean.binaryproto"
}
data_param {
source: "/mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/val_db"
batch_size: 32
backend: LMDB
}
}
layer {
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 96
kernel_size: 11
stride: 4
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu1"
type: "ReLU"
bottom: "conv1"
top: "conv1"
}
layer {
name: "norm1"
type: "LRN"
bottom: "conv1"
top: "norm1"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool1"
type: "Pooling"
bottom: "norm1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 256
pad: 2
kernel_size: 5
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu2"
type: "ReLU"
bottom: "conv2"
top: "conv2"
}
layer {
name: "norm2"
type: "LRN"
bottom: "conv2"
top: "norm2"
lrn_param {
local_size: 5
alpha: 0.0001
beta: 0.75
}
}
layer {
name: "pool2"
type: "Pooling"
bottom: "norm2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "relu3"
type: "ReLU"
bottom: "conv3"
top: "conv3"
}
layer {
name: "conv4"
type: "Convolution"
bottom: "conv3"
top: "conv4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 384
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu4"
type: "ReLU"
bottom: "conv4"
top: "conv4"
}
layer {
name: "conv5"
type: "Convolution"
bottom: "conv4"
top: "conv5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5"
type: "ReLU"
bottom: "conv5"
top: "conv5"
}
layer {
name: "conv5.2"
type: "Convolution"
bottom: "conv5"
top: "conv5.2"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5.2"
type: "ReLU"
bottom: "conv5.2"
top: "conv5.2"
}
layer {
name: "conv5.3"
type: "Convolution"
bottom: "conv5.2"
top: "conv5.3"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5.3"
type: "ReLU"
bottom: "conv5.3"
top: "conv5.3"
}
layer {
name: "conv5.4"
type: "Convolution"
bottom: "conv5.3"
top: "conv5.4"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
convolution_param {
num_output: 64
pad: 1
kernel_size: 3
group: 2
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu5.4"
type: "ReLU"
bottom: "conv5.4"
top: "conv5.4"
}
layer {
name: "pool5"
type: "Pooling"
bottom: "conv5.4"
top: "pool5"
pooling_param {
pool: MAX
kernel_size: 3
stride: 2
}
}
layer {
name: "fc6"
type: "InnerProduct"
bottom: "pool5"
top: "fc6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu6"
type: "ReLU"
bottom: "fc6"
top: "fc6"
}
layer {
name: "drop6"
type: "Dropout"
bottom: "fc6"
top: "fc6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7"
type: "InnerProduct"
bottom: "fc6"
top: "fc7"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 4096
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7"
type: "ReLU"
bottom: "fc7"
top: "fc7"
}
layer {
name: "drop7"
type: "Dropout"
bottom: "fc7"
top: "fc7"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7"
top: "fc8"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 196
weight_filler {
type: "gaussian"
std: 0.01
}
bias_filler {
type: "constant"
value: 0
}
}
}
layer {
name: "accuracy"
type: "Accuracy"
bottom: "fc8"
bottom: "label"
top: "accuracy"
include {
phase: TEST
}
}
layer {
name: "loss"
type: "SoftmaxWithLoss"
bottom: "fc8"
bottom: "label"
top: "loss"
}
I0412 12:48:32.792325  6895 layer_factory.hpp:77] Creating layer val-data
I0412 12:48:32.793843  6895 db_lmdb.cpp:35] Opened lmdb /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/val_db
I0412 12:48:32.794049  6895 net.cpp:84] Creating Layer val-data
I0412 12:48:32.794057  6895 net.cpp:380] val-data -> data
I0412 12:48:32.794065  6895 net.cpp:380] val-data -> label
I0412 12:48:32.794071  6895 data_transformer.cpp:25] Loading mean file from: /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/mean.binaryproto
I0412 12:48:32.798063  6895 data_layer.cpp:45] output data size: 32,3,227,227
I0412 12:48:32.830011  6895 net.cpp:122] Setting up val-data
I0412 12:48:32.830031  6895 net.cpp:129] Top shape: 32 3 227 227 (4946784)
I0412 12:48:32.830036  6895 net.cpp:129] Top shape: 32 (32)
I0412 12:48:32.830039  6895 net.cpp:137] Memory required for data: 19787264
I0412 12:48:32.830046  6895 layer_factory.hpp:77] Creating layer label_val-data_1_split
I0412 12:48:32.830057  6895 net.cpp:84] Creating Layer label_val-data_1_split
I0412 12:48:32.830062  6895 net.cpp:406] label_val-data_1_split <- label
I0412 12:48:32.830068  6895 net.cpp:380] label_val-data_1_split -> label_val-data_1_split_0
I0412 12:48:32.830077  6895 net.cpp:380] label_val-data_1_split -> label_val-data_1_split_1
I0412 12:48:32.830121  6895 net.cpp:122] Setting up label_val-data_1_split
I0412 12:48:32.830125  6895 net.cpp:129] Top shape: 32 (32)
I0412 12:48:32.830129  6895 net.cpp:129] Top shape: 32 (32)
I0412 12:48:32.830149  6895 net.cpp:137] Memory required for data: 19787520
I0412 12:48:32.830153  6895 layer_factory.hpp:77] Creating layer conv1
I0412 12:48:32.830164  6895 net.cpp:84] Creating Layer conv1
I0412 12:48:32.830168  6895 net.cpp:406] conv1 <- data
I0412 12:48:32.830173  6895 net.cpp:380] conv1 -> conv1
I0412 12:48:32.832204  6895 net.cpp:122] Setting up conv1
I0412 12:48:32.832216  6895 net.cpp:129] Top shape: 32 96 55 55 (9292800)
I0412 12:48:32.832219  6895 net.cpp:137] Memory required for data: 56958720
I0412 12:48:32.832228  6895 layer_factory.hpp:77] Creating layer relu1
I0412 12:48:32.832235  6895 net.cpp:84] Creating Layer relu1
I0412 12:48:32.832238  6895 net.cpp:406] relu1 <- conv1
I0412 12:48:32.832243  6895 net.cpp:367] relu1 -> conv1 (in-place)
I0412 12:48:32.832870  6895 net.cpp:122] Setting up relu1
I0412 12:48:32.832878  6895 net.cpp:129] Top shape: 32 96 55 55 (9292800)
I0412 12:48:32.832881  6895 net.cpp:137] Memory required for data: 94129920
I0412 12:48:32.832885  6895 layer_factory.hpp:77] Creating layer norm1
I0412 12:48:32.832893  6895 net.cpp:84] Creating Layer norm1
I0412 12:48:32.832896  6895 net.cpp:406] norm1 <- conv1
I0412 12:48:32.832901  6895 net.cpp:380] norm1 -> norm1
I0412 12:48:32.834375  6895 net.cpp:122] Setting up norm1
I0412 12:48:32.834386  6895 net.cpp:129] Top shape: 32 96 55 55 (9292800)
I0412 12:48:32.834389  6895 net.cpp:137] Memory required for data: 131301120
I0412 12:48:32.834393  6895 layer_factory.hpp:77] Creating layer pool1
I0412 12:48:32.834400  6895 net.cpp:84] Creating Layer pool1
I0412 12:48:32.834403  6895 net.cpp:406] pool1 <- norm1
I0412 12:48:32.834409  6895 net.cpp:380] pool1 -> pool1
I0412 12:48:32.834439  6895 net.cpp:122] Setting up pool1
I0412 12:48:32.834443  6895 net.cpp:129] Top shape: 32 96 27 27 (2239488)
I0412 12:48:32.834446  6895 net.cpp:137] Memory required for data: 140259072
I0412 12:48:32.834450  6895 layer_factory.hpp:77] Creating layer conv2
I0412 12:48:32.834457  6895 net.cpp:84] Creating Layer conv2
I0412 12:48:32.834460  6895 net.cpp:406] conv2 <- pool1
I0412 12:48:32.834465  6895 net.cpp:380] conv2 -> conv2
I0412 12:48:32.843268  6895 net.cpp:122] Setting up conv2
I0412 12:48:32.843281  6895 net.cpp:129] Top shape: 32 256 27 27 (5971968)
I0412 12:48:32.843284  6895 net.cpp:137] Memory required for data: 164146944
I0412 12:48:32.843293  6895 layer_factory.hpp:77] Creating layer relu2
I0412 12:48:32.843299  6895 net.cpp:84] Creating Layer relu2
I0412 12:48:32.843303  6895 net.cpp:406] relu2 <- conv2
I0412 12:48:32.843312  6895 net.cpp:367] relu2 -> conv2 (in-place)
I0412 12:48:32.843817  6895 net.cpp:122] Setting up relu2
I0412 12:48:32.843827  6895 net.cpp:129] Top shape: 32 256 27 27 (5971968)
I0412 12:48:32.843830  6895 net.cpp:137] Memory required for data: 188034816
I0412 12:48:32.843833  6895 layer_factory.hpp:77] Creating layer norm2
I0412 12:48:32.843843  6895 net.cpp:84] Creating Layer norm2
I0412 12:48:32.843847  6895 net.cpp:406] norm2 <- conv2
I0412 12:48:32.843853  6895 net.cpp:380] norm2 -> norm2
I0412 12:48:32.844216  6895 net.cpp:122] Setting up norm2
I0412 12:48:32.844225  6895 net.cpp:129] Top shape: 32 256 27 27 (5971968)
I0412 12:48:32.844228  6895 net.cpp:137] Memory required for data: 211922688
I0412 12:48:32.844233  6895 layer_factory.hpp:77] Creating layer pool2
I0412 12:48:32.844238  6895 net.cpp:84] Creating Layer pool2
I0412 12:48:32.844241  6895 net.cpp:406] pool2 <- norm2
I0412 12:48:32.844249  6895 net.cpp:380] pool2 -> pool2
I0412 12:48:32.844277  6895 net.cpp:122] Setting up pool2
I0412 12:48:32.844282  6895 net.cpp:129] Top shape: 32 256 13 13 (1384448)
I0412 12:48:32.844285  6895 net.cpp:137] Memory required for data: 217460480
I0412 12:48:32.844288  6895 layer_factory.hpp:77] Creating layer conv3
I0412 12:48:32.844300  6895 net.cpp:84] Creating Layer conv3
I0412 12:48:32.844302  6895 net.cpp:406] conv3 <- pool2
I0412 12:48:32.844307  6895 net.cpp:380] conv3 -> conv3
I0412 12:48:32.855630  6895 net.cpp:122] Setting up conv3
I0412 12:48:32.855648  6895 net.cpp:129] Top shape: 32 384 13 13 (2076672)
I0412 12:48:32.855669  6895 net.cpp:137] Memory required for data: 225767168
I0412 12:48:32.855680  6895 layer_factory.hpp:77] Creating layer relu3
I0412 12:48:32.855688  6895 net.cpp:84] Creating Layer relu3
I0412 12:48:32.855692  6895 net.cpp:406] relu3 <- conv3
I0412 12:48:32.855698  6895 net.cpp:367] relu3 -> conv3 (in-place)
I0412 12:48:32.856218  6895 net.cpp:122] Setting up relu3
I0412 12:48:32.856228  6895 net.cpp:129] Top shape: 32 384 13 13 (2076672)
I0412 12:48:32.856231  6895 net.cpp:137] Memory required for data: 234073856
I0412 12:48:32.856235  6895 layer_factory.hpp:77] Creating layer conv4
I0412 12:48:32.856246  6895 net.cpp:84] Creating Layer conv4
I0412 12:48:32.856251  6895 net.cpp:406] conv4 <- conv3
I0412 12:48:32.856256  6895 net.cpp:380] conv4 -> conv4
I0412 12:48:32.865684  6895 net.cpp:122] Setting up conv4
I0412 12:48:32.865697  6895 net.cpp:129] Top shape: 32 384 13 13 (2076672)
I0412 12:48:32.865700  6895 net.cpp:137] Memory required for data: 242380544
I0412 12:48:32.865707  6895 layer_factory.hpp:77] Creating layer relu4
I0412 12:48:32.865715  6895 net.cpp:84] Creating Layer relu4
I0412 12:48:32.865720  6895 net.cpp:406] relu4 <- conv4
I0412 12:48:32.865725  6895 net.cpp:367] relu4 -> conv4 (in-place)
I0412 12:48:32.866235  6895 net.cpp:122] Setting up relu4
I0412 12:48:32.866245  6895 net.cpp:129] Top shape: 32 384 13 13 (2076672)
I0412 12:48:32.866247  6895 net.cpp:137] Memory required for data: 250687232
I0412 12:48:32.866251  6895 layer_factory.hpp:77] Creating layer conv5
I0412 12:48:32.866261  6895 net.cpp:84] Creating Layer conv5
I0412 12:48:32.866264  6895 net.cpp:406] conv5 <- conv4
I0412 12:48:32.866272  6895 net.cpp:380] conv5 -> conv5
I0412 12:48:32.871418  6895 net.cpp:122] Setting up conv5
I0412 12:48:32.871430  6895 net.cpp:129] Top shape: 32 64 13 13 (346112)
I0412 12:48:32.871433  6895 net.cpp:137] Memory required for data: 252071680
I0412 12:48:32.871445  6895 layer_factory.hpp:77] Creating layer relu5
I0412 12:48:32.871451  6895 net.cpp:84] Creating Layer relu5
I0412 12:48:32.871456  6895 net.cpp:406] relu5 <- conv5
I0412 12:48:32.871462  6895 net.cpp:367] relu5 -> conv5 (in-place)
I0412 12:48:32.871973  6895 net.cpp:122] Setting up relu5
I0412 12:48:32.871982  6895 net.cpp:129] Top shape: 32 64 13 13 (346112)
I0412 12:48:32.871985  6895 net.cpp:137] Memory required for data: 253456128
I0412 12:48:32.871989  6895 layer_factory.hpp:77] Creating layer conv5.2
I0412 12:48:32.872004  6895 net.cpp:84] Creating Layer conv5.2
I0412 12:48:32.872006  6895 net.cpp:406] conv5.2 <- conv5
I0412 12:48:32.872012  6895 net.cpp:380] conv5.2 -> conv5.2
I0412 12:48:32.876181  6895 net.cpp:122] Setting up conv5.2
I0412 12:48:32.876192  6895 net.cpp:129] Top shape: 32 64 13 13 (346112)
I0412 12:48:32.876196  6895 net.cpp:137] Memory required for data: 254840576
I0412 12:48:32.876204  6895 layer_factory.hpp:77] Creating layer relu5.2
I0412 12:48:32.876211  6895 net.cpp:84] Creating Layer relu5.2
I0412 12:48:32.876215  6895 net.cpp:406] relu5.2 <- conv5.2
I0412 12:48:32.876221  6895 net.cpp:367] relu5.2 -> conv5.2 (in-place)
I0412 12:48:32.876565  6895 net.cpp:122] Setting up relu5.2
I0412 12:48:32.876574  6895 net.cpp:129] Top shape: 32 64 13 13 (346112)
I0412 12:48:32.876578  6895 net.cpp:137] Memory required for data: 256225024
I0412 12:48:32.876581  6895 layer_factory.hpp:77] Creating layer conv5.3
I0412 12:48:32.876591  6895 net.cpp:84] Creating Layer conv5.3
I0412 12:48:32.876595  6895 net.cpp:406] conv5.3 <- conv5.2
I0412 12:48:32.876600  6895 net.cpp:380] conv5.3 -> conv5.3
I0412 12:48:32.881510  6895 net.cpp:122] Setting up conv5.3
I0412 12:48:32.881520  6895 net.cpp:129] Top shape: 32 64 13 13 (346112)
I0412 12:48:32.881523  6895 net.cpp:137] Memory required for data: 257609472
I0412 12:48:32.881531  6895 layer_factory.hpp:77] Creating layer relu5.3
I0412 12:48:32.881536  6895 net.cpp:84] Creating Layer relu5.3
I0412 12:48:32.881539  6895 net.cpp:406] relu5.3 <- conv5.3
I0412 12:48:32.881546  6895 net.cpp:367] relu5.3 -> conv5.3 (in-place)
I0412 12:48:32.883091  6895 net.cpp:122] Setting up relu5.3
I0412 12:48:32.883117  6895 net.cpp:129] Top shape: 32 64 13 13 (346112)
I0412 12:48:32.883121  6895 net.cpp:137] Memory required for data: 258993920
I0412 12:48:32.883124  6895 layer_factory.hpp:77] Creating layer conv5.4
I0412 12:48:32.883136  6895 net.cpp:84] Creating Layer conv5.4
I0412 12:48:32.883141  6895 net.cpp:406] conv5.4 <- conv5.3
I0412 12:48:32.883147  6895 net.cpp:380] conv5.4 -> conv5.4
I0412 12:48:32.886323  6895 net.cpp:122] Setting up conv5.4
I0412 12:48:32.886333  6895 net.cpp:129] Top shape: 32 64 13 13 (346112)
I0412 12:48:32.886337  6895 net.cpp:137] Memory required for data: 260378368
I0412 12:48:32.886343  6895 layer_factory.hpp:77] Creating layer relu5.4
I0412 12:48:32.886349  6895 net.cpp:84] Creating Layer relu5.4
I0412 12:48:32.886353  6895 net.cpp:406] relu5.4 <- conv5.4
I0412 12:48:32.886359  6895 net.cpp:367] relu5.4 -> conv5.4 (in-place)
I0412 12:48:32.886857  6895 net.cpp:122] Setting up relu5.4
I0412 12:48:32.886868  6895 net.cpp:129] Top shape: 32 64 13 13 (346112)
I0412 12:48:32.886870  6895 net.cpp:137] Memory required for data: 261762816
I0412 12:48:32.886874  6895 layer_factory.hpp:77] Creating layer pool5
I0412 12:48:32.886880  6895 net.cpp:84] Creating Layer pool5
I0412 12:48:32.886884  6895 net.cpp:406] pool5 <- conv5.4
I0412 12:48:32.886890  6895 net.cpp:380] pool5 -> pool5
I0412 12:48:32.886932  6895 net.cpp:122] Setting up pool5
I0412 12:48:32.886938  6895 net.cpp:129] Top shape: 32 64 6 6 (73728)
I0412 12:48:32.886941  6895 net.cpp:137] Memory required for data: 262057728
I0412 12:48:32.886945  6895 layer_factory.hpp:77] Creating layer fc6
I0412 12:48:32.886951  6895 net.cpp:84] Creating Layer fc6
I0412 12:48:32.886955  6895 net.cpp:406] fc6 <- pool5
I0412 12:48:32.886960  6895 net.cpp:380] fc6 -> fc6
I0412 12:48:32.976459  6895 net.cpp:122] Setting up fc6
I0412 12:48:32.976480  6895 net.cpp:129] Top shape: 32 4096 (131072)
I0412 12:48:32.976483  6895 net.cpp:137] Memory required for data: 262582016
I0412 12:48:32.976495  6895 layer_factory.hpp:77] Creating layer relu6
I0412 12:48:32.976505  6895 net.cpp:84] Creating Layer relu6
I0412 12:48:32.976511  6895 net.cpp:406] relu6 <- fc6
I0412 12:48:32.976516  6895 net.cpp:367] relu6 -> fc6 (in-place)
I0412 12:48:32.976923  6895 net.cpp:122] Setting up relu6
I0412 12:48:32.976931  6895 net.cpp:129] Top shape: 32 4096 (131072)
I0412 12:48:32.976934  6895 net.cpp:137] Memory required for data: 263106304
I0412 12:48:32.976938  6895 layer_factory.hpp:77] Creating layer drop6
I0412 12:48:32.976944  6895 net.cpp:84] Creating Layer drop6
I0412 12:48:32.976948  6895 net.cpp:406] drop6 <- fc6
I0412 12:48:32.976953  6895 net.cpp:367] drop6 -> fc6 (in-place)
I0412 12:48:32.976977  6895 net.cpp:122] Setting up drop6
I0412 12:48:32.976982  6895 net.cpp:129] Top shape: 32 4096 (131072)
I0412 12:48:32.976985  6895 net.cpp:137] Memory required for data: 263630592
I0412 12:48:32.976989  6895 layer_factory.hpp:77] Creating layer fc7
I0412 12:48:32.976996  6895 net.cpp:84] Creating Layer fc7
I0412 12:48:32.976999  6895 net.cpp:406] fc7 <- fc6
I0412 12:48:32.977005  6895 net.cpp:380] fc7 -> fc7
I0412 12:48:33.135601  6895 net.cpp:122] Setting up fc7
I0412 12:48:33.135623  6895 net.cpp:129] Top shape: 32 4096 (131072)
I0412 12:48:33.135627  6895 net.cpp:137] Memory required for data: 264154880
I0412 12:48:33.135637  6895 layer_factory.hpp:77] Creating layer relu7
I0412 12:48:33.135644  6895 net.cpp:84] Creating Layer relu7
I0412 12:48:33.135648  6895 net.cpp:406] relu7 <- fc7
I0412 12:48:33.135655  6895 net.cpp:367] relu7 -> fc7 (in-place)
I0412 12:48:33.136323  6895 net.cpp:122] Setting up relu7
I0412 12:48:33.136333  6895 net.cpp:129] Top shape: 32 4096 (131072)
I0412 12:48:33.136337  6895 net.cpp:137] Memory required for data: 264679168
I0412 12:48:33.136340  6895 layer_factory.hpp:77] Creating layer drop7
I0412 12:48:33.136346  6895 net.cpp:84] Creating Layer drop7
I0412 12:48:33.136350  6895 net.cpp:406] drop7 <- fc7
I0412 12:48:33.136356  6895 net.cpp:367] drop7 -> fc7 (in-place)
I0412 12:48:33.136381  6895 net.cpp:122] Setting up drop7
I0412 12:48:33.136405  6895 net.cpp:129] Top shape: 32 4096 (131072)
I0412 12:48:33.136409  6895 net.cpp:137] Memory required for data: 265203456
I0412 12:48:33.136412  6895 layer_factory.hpp:77] Creating layer fc8
I0412 12:48:33.136420  6895 net.cpp:84] Creating Layer fc8
I0412 12:48:33.136423  6895 net.cpp:406] fc8 <- fc7
I0412 12:48:33.136430  6895 net.cpp:380] fc8 -> fc8
I0412 12:48:33.144217  6895 net.cpp:122] Setting up fc8
I0412 12:48:33.144228  6895 net.cpp:129] Top shape: 32 196 (6272)
I0412 12:48:33.144232  6895 net.cpp:137] Memory required for data: 265228544
I0412 12:48:33.144238  6895 layer_factory.hpp:77] Creating layer fc8_fc8_0_split
I0412 12:48:33.144246  6895 net.cpp:84] Creating Layer fc8_fc8_0_split
I0412 12:48:33.144250  6895 net.cpp:406] fc8_fc8_0_split <- fc8
I0412 12:48:33.144255  6895 net.cpp:380] fc8_fc8_0_split -> fc8_fc8_0_split_0
I0412 12:48:33.144263  6895 net.cpp:380] fc8_fc8_0_split -> fc8_fc8_0_split_1
I0412 12:48:33.144297  6895 net.cpp:122] Setting up fc8_fc8_0_split
I0412 12:48:33.144301  6895 net.cpp:129] Top shape: 32 196 (6272)
I0412 12:48:33.144305  6895 net.cpp:129] Top shape: 32 196 (6272)
I0412 12:48:33.144309  6895 net.cpp:137] Memory required for data: 265278720
I0412 12:48:33.144311  6895 layer_factory.hpp:77] Creating layer accuracy
I0412 12:48:33.144317  6895 net.cpp:84] Creating Layer accuracy
I0412 12:48:33.144321  6895 net.cpp:406] accuracy <- fc8_fc8_0_split_0
I0412 12:48:33.144325  6895 net.cpp:406] accuracy <- label_val-data_1_split_0
I0412 12:48:33.144331  6895 net.cpp:380] accuracy -> accuracy
I0412 12:48:33.144337  6895 net.cpp:122] Setting up accuracy
I0412 12:48:33.144341  6895 net.cpp:129] Top shape: (1)
I0412 12:48:33.144345  6895 net.cpp:137] Memory required for data: 265278724
I0412 12:48:33.144347  6895 layer_factory.hpp:77] Creating layer loss
I0412 12:48:33.144357  6895 net.cpp:84] Creating Layer loss
I0412 12:48:33.144361  6895 net.cpp:406] loss <- fc8_fc8_0_split_1
I0412 12:48:33.144366  6895 net.cpp:406] loss <- label_val-data_1_split_1
I0412 12:48:33.144369  6895 net.cpp:380] loss -> loss
I0412 12:48:33.144376  6895 layer_factory.hpp:77] Creating layer loss
I0412 12:48:33.146119  6895 net.cpp:122] Setting up loss
I0412 12:48:33.146129  6895 net.cpp:129] Top shape: (1)
I0412 12:48:33.146133  6895 net.cpp:132]     with loss weight 1
I0412 12:48:33.146143  6895 net.cpp:137] Memory required for data: 265278728
I0412 12:48:33.146147  6895 net.cpp:198] loss needs backward computation.
I0412 12:48:33.146152  6895 net.cpp:200] accuracy does not need backward computation.
I0412 12:48:33.146155  6895 net.cpp:198] fc8_fc8_0_split needs backward computation.
I0412 12:48:33.146158  6895 net.cpp:198] fc8 needs backward computation.
I0412 12:48:33.146162  6895 net.cpp:198] drop7 needs backward computation.
I0412 12:48:33.146165  6895 net.cpp:198] relu7 needs backward computation.
I0412 12:48:33.146168  6895 net.cpp:198] fc7 needs backward computation.
I0412 12:48:33.146171  6895 net.cpp:198] drop6 needs backward computation.
I0412 12:48:33.146175  6895 net.cpp:198] relu6 needs backward computation.
I0412 12:48:33.146178  6895 net.cpp:198] fc6 needs backward computation.
I0412 12:48:33.146183  6895 net.cpp:198] pool5 needs backward computation.
I0412 12:48:33.146185  6895 net.cpp:198] relu5.4 needs backward computation.
I0412 12:48:33.146189  6895 net.cpp:198] conv5.4 needs backward computation.
I0412 12:48:33.146193  6895 net.cpp:198] relu5.3 needs backward computation.
I0412 12:48:33.146198  6895 net.cpp:198] conv5.3 needs backward computation.
I0412 12:48:33.146200  6895 net.cpp:198] relu5.2 needs backward computation.
I0412 12:48:33.146203  6895 net.cpp:198] conv5.2 needs backward computation.
I0412 12:48:33.146207  6895 net.cpp:198] relu5 needs backward computation.
I0412 12:48:33.146210  6895 net.cpp:198] conv5 needs backward computation.
I0412 12:48:33.146214  6895 net.cpp:198] relu4 needs backward computation.
I0412 12:48:33.146217  6895 net.cpp:198] conv4 needs backward computation.
I0412 12:48:33.146221  6895 net.cpp:198] relu3 needs backward computation.
I0412 12:48:33.146239  6895 net.cpp:198] conv3 needs backward computation.
I0412 12:48:33.146242  6895 net.cpp:198] pool2 needs backward computation.
I0412 12:48:33.146246  6895 net.cpp:198] norm2 needs backward computation.
I0412 12:48:33.146250  6895 net.cpp:198] relu2 needs backward computation.
I0412 12:48:33.146253  6895 net.cpp:198] conv2 needs backward computation.
I0412 12:48:33.146256  6895 net.cpp:198] pool1 needs backward computation.
I0412 12:48:33.146260  6895 net.cpp:198] norm1 needs backward computation.
I0412 12:48:33.146263  6895 net.cpp:198] relu1 needs backward computation.
I0412 12:48:33.146266  6895 net.cpp:198] conv1 needs backward computation.
I0412 12:48:33.146270  6895 net.cpp:200] label_val-data_1_split does not need backward computation.
I0412 12:48:33.146275  6895 net.cpp:200] val-data does not need backward computation.
I0412 12:48:33.146277  6895 net.cpp:242] This network produces output accuracy
I0412 12:48:33.146281  6895 net.cpp:242] This network produces output loss
I0412 12:48:33.146299  6895 net.cpp:255] Network initialization done.
I0412 12:48:33.146386  6895 solver.cpp:56] Solver scaffolding done.
I0412 12:48:33.146981  6895 caffe.cpp:248] Starting Optimization
I0412 12:48:33.146989  6895 solver.cpp:272] Solving
I0412 12:48:33.146992  6895 solver.cpp:273] Learning Rate Policy: exp
I0412 12:48:33.148236  6895 solver.cpp:330] Iteration 0, Testing net (#0)
I0412 12:48:33.148245  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:48:33.201103  6895 blocking_queue.cpp:49] Waiting for data
I0412 12:48:37.690565  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:48:37.734858  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00428922
I0412 12:48:37.734910  6895 solver.cpp:397]     Test net output #1: loss = 5.27973 (* 1 = 5.27973 loss)
I0412 12:48:37.823364  6895 solver.cpp:218] Iteration 0 (1.13746e+37 iter/s, 4.67619s/12 iters), loss = 5.28104
I0412 12:48:37.824892  6895 solver.cpp:237]     Train net output #0: loss = 5.28104 (* 1 = 5.28104 loss)
I0412 12:48:37.824911  6895 sgd_solver.cpp:105] Iteration 0, lr = 0.01
I0412 12:48:41.401437  6895 solver.cpp:218] Iteration 12 (3.35533 iter/s, 3.5764s/12 iters), loss = 5.29723
I0412 12:48:41.401489  6895 solver.cpp:237]     Train net output #0: loss = 5.29723 (* 1 = 5.29723 loss)
I0412 12:48:41.401502  6895 sgd_solver.cpp:105] Iteration 12, lr = 0.00997626
I0412 12:48:45.981995  6895 solver.cpp:218] Iteration 24 (2.6199 iter/s, 4.58033s/12 iters), loss = 5.27704
I0412 12:48:45.982048  6895 solver.cpp:237]     Train net output #0: loss = 5.27704 (* 1 = 5.27704 loss)
I0412 12:48:45.982059  6895 sgd_solver.cpp:105] Iteration 24, lr = 0.00995257
I0412 12:48:50.384068  6895 solver.cpp:218] Iteration 36 (2.72612 iter/s, 4.40186s/12 iters), loss = 5.28652
I0412 12:48:50.384121  6895 solver.cpp:237]     Train net output #0: loss = 5.28652 (* 1 = 5.28652 loss)
I0412 12:48:50.384135  6895 sgd_solver.cpp:105] Iteration 36, lr = 0.00992894
I0412 12:48:54.910501  6895 solver.cpp:218] Iteration 48 (2.65122 iter/s, 4.52621s/12 iters), loss = 5.31176
I0412 12:48:54.910557  6895 solver.cpp:237]     Train net output #0: loss = 5.31176 (* 1 = 5.31176 loss)
I0412 12:48:54.910569  6895 sgd_solver.cpp:105] Iteration 48, lr = 0.00990537
I0412 12:48:59.402689  6895 solver.cpp:218] Iteration 60 (2.67144 iter/s, 4.49196s/12 iters), loss = 5.30572
I0412 12:48:59.402738  6895 solver.cpp:237]     Train net output #0: loss = 5.30572 (* 1 = 5.30572 loss)
I0412 12:48:59.402750  6895 sgd_solver.cpp:105] Iteration 60, lr = 0.00988185
I0412 12:49:03.949535  6895 solver.cpp:218] Iteration 72 (2.63932 iter/s, 4.54662s/12 iters), loss = 5.29702
I0412 12:49:03.949668  6895 solver.cpp:237]     Train net output #0: loss = 5.29702 (* 1 = 5.29702 loss)
I0412 12:49:03.949687  6895 sgd_solver.cpp:105] Iteration 72, lr = 0.00985839
I0412 12:49:08.529842  6895 solver.cpp:218] Iteration 84 (2.62008 iter/s, 4.58001s/12 iters), loss = 5.30138
I0412 12:49:08.529896  6895 solver.cpp:237]     Train net output #0: loss = 5.30138 (* 1 = 5.30138 loss)
I0412 12:49:08.529908  6895 sgd_solver.cpp:105] Iteration 84, lr = 0.00983498
I0412 12:49:13.166011  6895 solver.cpp:218] Iteration 96 (2.58847 iter/s, 4.63595s/12 iters), loss = 5.31484
I0412 12:49:13.166050  6895 solver.cpp:237]     Train net output #0: loss = 5.31484 (* 1 = 5.31484 loss)
I0412 12:49:13.166059  6895 sgd_solver.cpp:105] Iteration 96, lr = 0.00981163
I0412 12:49:14.703181  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:49:15.008548  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_102.caffemodel
I0412 12:49:16.639775  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_102.solverstate
I0412 12:49:17.816581  6895 solver.cpp:330] Iteration 102, Testing net (#0)
I0412 12:49:17.816609  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:49:22.178182  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:49:22.254534  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:49:22.254573  6895 solver.cpp:397]     Test net output #1: loss = 5.29122 (* 1 = 5.29122 loss)
I0412 12:49:24.053894  6895 solver.cpp:218] Iteration 108 (1.10219 iter/s, 10.8875s/12 iters), loss = 5.31404
I0412 12:49:24.053934  6895 solver.cpp:237]     Train net output #0: loss = 5.31404 (* 1 = 5.31404 loss)
I0412 12:49:24.053943  6895 sgd_solver.cpp:105] Iteration 108, lr = 0.00978834
I0412 12:49:28.793980  6895 solver.cpp:218] Iteration 120 (2.53172 iter/s, 4.73986s/12 iters), loss = 5.28525
I0412 12:49:28.794023  6895 solver.cpp:237]     Train net output #0: loss = 5.28525 (* 1 = 5.28525 loss)
I0412 12:49:28.794034  6895 sgd_solver.cpp:105] Iteration 120, lr = 0.0097651
I0412 12:49:33.403769  6895 solver.cpp:218] Iteration 132 (2.60328 iter/s, 4.60958s/12 iters), loss = 5.25532
I0412 12:49:33.403818  6895 solver.cpp:237]     Train net output #0: loss = 5.25532 (* 1 = 5.25532 loss)
I0412 12:49:33.403831  6895 sgd_solver.cpp:105] Iteration 132, lr = 0.00974192
I0412 12:49:37.988653  6895 solver.cpp:218] Iteration 144 (2.61742 iter/s, 4.58467s/12 iters), loss = 5.3164
I0412 12:49:37.988819  6895 solver.cpp:237]     Train net output #0: loss = 5.3164 (* 1 = 5.3164 loss)
I0412 12:49:37.988832  6895 sgd_solver.cpp:105] Iteration 144, lr = 0.00971879
I0412 12:49:42.592864  6895 solver.cpp:218] Iteration 156 (2.60649 iter/s, 4.60388s/12 iters), loss = 5.25733
I0412 12:49:42.592902  6895 solver.cpp:237]     Train net output #0: loss = 5.25733 (* 1 = 5.25733 loss)
I0412 12:49:42.592911  6895 sgd_solver.cpp:105] Iteration 156, lr = 0.00969571
I0412 12:49:47.170789  6895 solver.cpp:218] Iteration 168 (2.6214 iter/s, 4.57771s/12 iters), loss = 5.28043
I0412 12:49:47.170838  6895 solver.cpp:237]     Train net output #0: loss = 5.28043 (* 1 = 5.28043 loss)
I0412 12:49:47.170850  6895 sgd_solver.cpp:105] Iteration 168, lr = 0.00967269
I0412 12:49:51.682124  6895 solver.cpp:218] Iteration 180 (2.66009 iter/s, 4.51112s/12 iters), loss = 5.27176
I0412 12:49:51.682179  6895 solver.cpp:237]     Train net output #0: loss = 5.27176 (* 1 = 5.27176 loss)
I0412 12:49:51.682193  6895 sgd_solver.cpp:105] Iteration 180, lr = 0.00964973
I0412 12:49:56.591210  6895 solver.cpp:218] Iteration 192 (2.44456 iter/s, 4.90885s/12 iters), loss = 5.28863
I0412 12:49:56.591261  6895 solver.cpp:237]     Train net output #0: loss = 5.28863 (* 1 = 5.28863 loss)
I0412 12:49:56.591274  6895 sgd_solver.cpp:105] Iteration 192, lr = 0.00962682
I0412 12:50:00.089115  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:50:00.755875  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_204.caffemodel
I0412 12:50:02.302210  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_204.solverstate
I0412 12:50:03.480113  6895 solver.cpp:330] Iteration 204, Testing net (#0)
I0412 12:50:03.480139  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:50:07.794843  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:50:07.916316  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:50:07.916363  6895 solver.cpp:397]     Test net output #1: loss = 5.28899 (* 1 = 5.28899 loss)
I0412 12:50:07.999385  6895 solver.cpp:218] Iteration 204 (1.05192 iter/s, 11.4077s/12 iters), loss = 5.27954
I0412 12:50:08.050048  6895 solver.cpp:237]     Train net output #0: loss = 5.27954 (* 1 = 5.27954 loss)
I0412 12:50:08.050066  6895 sgd_solver.cpp:105] Iteration 204, lr = 0.00960396
I0412 12:50:12.236886  6895 solver.cpp:218] Iteration 216 (2.86623 iter/s, 4.18668s/12 iters), loss = 5.28881
I0412 12:50:12.236938  6895 solver.cpp:237]     Train net output #0: loss = 5.28881 (* 1 = 5.28881 loss)
I0412 12:50:12.236951  6895 sgd_solver.cpp:105] Iteration 216, lr = 0.00958116
I0412 12:50:16.969936  6895 solver.cpp:218] Iteration 228 (2.53549 iter/s, 4.73281s/12 iters), loss = 5.27958
I0412 12:50:16.970008  6895 solver.cpp:237]     Train net output #0: loss = 5.27958 (* 1 = 5.27958 loss)
I0412 12:50:16.970021  6895 sgd_solver.cpp:105] Iteration 228, lr = 0.00955841
I0412 12:50:21.572053  6895 solver.cpp:218] Iteration 240 (2.60764 iter/s, 4.60187s/12 iters), loss = 5.30905
I0412 12:50:21.572103  6895 solver.cpp:237]     Train net output #0: loss = 5.30905 (* 1 = 5.30905 loss)
I0412 12:50:21.572114  6895 sgd_solver.cpp:105] Iteration 240, lr = 0.00953572
I0412 12:50:26.272096  6895 solver.cpp:218] Iteration 252 (2.55329 iter/s, 4.69982s/12 iters), loss = 5.28255
I0412 12:50:26.272145  6895 solver.cpp:237]     Train net output #0: loss = 5.28255 (* 1 = 5.28255 loss)
I0412 12:50:26.272157  6895 sgd_solver.cpp:105] Iteration 252, lr = 0.00951308
I0412 12:50:31.026850  6895 solver.cpp:218] Iteration 264 (2.52391 iter/s, 4.75452s/12 iters), loss = 5.28733
I0412 12:50:31.026901  6895 solver.cpp:237]     Train net output #0: loss = 5.28733 (* 1 = 5.28733 loss)
I0412 12:50:31.026913  6895 sgd_solver.cpp:105] Iteration 264, lr = 0.00949049
I0412 12:50:35.834257  6895 solver.cpp:218] Iteration 276 (2.49627 iter/s, 4.80717s/12 iters), loss = 5.30319
I0412 12:50:35.834313  6895 solver.cpp:237]     Train net output #0: loss = 5.30319 (* 1 = 5.30319 loss)
I0412 12:50:35.834326  6895 sgd_solver.cpp:105] Iteration 276, lr = 0.00946796
I0412 12:50:40.620882  6895 solver.cpp:218] Iteration 288 (2.50711 iter/s, 4.78639s/12 iters), loss = 5.28544
I0412 12:50:40.622267  6895 solver.cpp:237]     Train net output #0: loss = 5.28544 (* 1 = 5.28544 loss)
I0412 12:50:40.622277  6895 sgd_solver.cpp:105] Iteration 288, lr = 0.00944548
I0412 12:50:45.366179  6895 solver.cpp:218] Iteration 300 (2.52965 iter/s, 4.74373s/12 iters), loss = 5.30741
I0412 12:50:45.366227  6895 solver.cpp:237]     Train net output #0: loss = 5.30741 (* 1 = 5.30741 loss)
I0412 12:50:45.366240  6895 sgd_solver.cpp:105] Iteration 300, lr = 0.00942305
I0412 12:50:46.247294  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:50:47.246747  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_306.caffemodel
I0412 12:50:48.803447  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_306.solverstate
I0412 12:50:49.984553  6895 solver.cpp:330] Iteration 306, Testing net (#0)
I0412 12:50:49.984583  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:50:54.253332  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:50:54.409705  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:50:54.409750  6895 solver.cpp:397]     Test net output #1: loss = 5.28761 (* 1 = 5.28761 loss)
I0412 12:50:56.209753  6895 solver.cpp:218] Iteration 312 (1.10669 iter/s, 10.8431s/12 iters), loss = 5.28592
I0412 12:50:56.209810  6895 solver.cpp:237]     Train net output #0: loss = 5.28592 (* 1 = 5.28592 loss)
I0412 12:50:56.209821  6895 sgd_solver.cpp:105] Iteration 312, lr = 0.00940068
I0412 12:51:00.560437  6895 solver.cpp:218] Iteration 324 (2.75833 iter/s, 4.35045s/12 iters), loss = 5.24838
I0412 12:51:00.560492  6895 solver.cpp:237]     Train net output #0: loss = 5.24838 (* 1 = 5.24838 loss)
I0412 12:51:00.560504  6895 sgd_solver.cpp:105] Iteration 324, lr = 0.00937836
I0412 12:51:05.171787  6895 solver.cpp:218] Iteration 336 (2.60241 iter/s, 4.61112s/12 iters), loss = 5.27058
I0412 12:51:05.171834  6895 solver.cpp:237]     Train net output #0: loss = 5.27058 (* 1 = 5.27058 loss)
I0412 12:51:05.171845  6895 sgd_solver.cpp:105] Iteration 336, lr = 0.0093561
I0412 12:51:09.878695  6895 solver.cpp:218] Iteration 348 (2.54956 iter/s, 4.70669s/12 iters), loss = 5.27802
I0412 12:51:09.878732  6895 solver.cpp:237]     Train net output #0: loss = 5.27802 (* 1 = 5.27802 loss)
I0412 12:51:09.878741  6895 sgd_solver.cpp:105] Iteration 348, lr = 0.00933388
I0412 12:51:14.531731  6895 solver.cpp:218] Iteration 360 (2.57908 iter/s, 4.65282s/12 iters), loss = 5.29873
I0412 12:51:14.531859  6895 solver.cpp:237]     Train net output #0: loss = 5.29873 (* 1 = 5.29873 loss)
I0412 12:51:14.531868  6895 sgd_solver.cpp:105] Iteration 360, lr = 0.00931172
I0412 12:51:19.278115  6895 solver.cpp:218] Iteration 372 (2.5284 iter/s, 4.74608s/12 iters), loss = 5.27862
I0412 12:51:19.278152  6895 solver.cpp:237]     Train net output #0: loss = 5.27862 (* 1 = 5.27862 loss)
I0412 12:51:19.278162  6895 sgd_solver.cpp:105] Iteration 372, lr = 0.00928961
I0412 12:51:24.060083  6895 solver.cpp:218] Iteration 384 (2.50955 iter/s, 4.78174s/12 iters), loss = 5.28298
I0412 12:51:24.060142  6895 solver.cpp:237]     Train net output #0: loss = 5.28298 (* 1 = 5.28298 loss)
I0412 12:51:24.060158  6895 sgd_solver.cpp:105] Iteration 384, lr = 0.00926756
I0412 12:51:28.681586  6895 solver.cpp:218] Iteration 396 (2.59669 iter/s, 4.62127s/12 iters), loss = 5.281
I0412 12:51:28.681635  6895 solver.cpp:237]     Train net output #0: loss = 5.281 (* 1 = 5.281 loss)
I0412 12:51:28.681648  6895 sgd_solver.cpp:105] Iteration 396, lr = 0.00924556
I0412 12:51:31.540634  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:51:32.813357  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_408.caffemodel
I0412 12:51:34.361600  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_408.solverstate
I0412 12:51:35.680192  6895 solver.cpp:330] Iteration 408, Testing net (#0)
I0412 12:51:35.680219  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:51:39.899422  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:51:40.101161  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:51:40.101210  6895 solver.cpp:397]     Test net output #1: loss = 5.28786 (* 1 = 5.28786 loss)
I0412 12:51:40.183200  6895 solver.cpp:218] Iteration 408 (1.04338 iter/s, 11.5011s/12 iters), loss = 5.28961
I0412 12:51:40.183245  6895 solver.cpp:237]     Train net output #0: loss = 5.28961 (* 1 = 5.28961 loss)
I0412 12:51:40.183257  6895 sgd_solver.cpp:105] Iteration 408, lr = 0.00922361
I0412 12:51:44.088420  6895 solver.cpp:218] Iteration 420 (3.07297 iter/s, 3.90502s/12 iters), loss = 5.27667
I0412 12:51:44.088472  6895 solver.cpp:237]     Train net output #0: loss = 5.27667 (* 1 = 5.27667 loss)
I0412 12:51:44.088486  6895 sgd_solver.cpp:105] Iteration 420, lr = 0.00920171
I0412 12:51:48.619386  6895 solver.cpp:218] Iteration 432 (2.64857 iter/s, 4.53074s/12 iters), loss = 5.27791
I0412 12:51:48.619503  6895 solver.cpp:237]     Train net output #0: loss = 5.27791 (* 1 = 5.27791 loss)
I0412 12:51:48.619516  6895 sgd_solver.cpp:105] Iteration 432, lr = 0.00917986
I0412 12:51:53.199671  6895 solver.cpp:218] Iteration 444 (2.62009 iter/s, 4.57999s/12 iters), loss = 5.29805
I0412 12:51:53.199710  6895 solver.cpp:237]     Train net output #0: loss = 5.29805 (* 1 = 5.29805 loss)
I0412 12:51:53.199719  6895 sgd_solver.cpp:105] Iteration 444, lr = 0.00915807
I0412 12:51:57.840859  6895 solver.cpp:218] Iteration 456 (2.58567 iter/s, 4.64097s/12 iters), loss = 5.2865
I0412 12:51:57.840907  6895 solver.cpp:237]     Train net output #0: loss = 5.2865 (* 1 = 5.2865 loss)
I0412 12:51:57.840919  6895 sgd_solver.cpp:105] Iteration 456, lr = 0.00913632
I0412 12:52:02.675797  6895 solver.cpp:218] Iteration 468 (2.48206 iter/s, 4.8347s/12 iters), loss = 5.29359
I0412 12:52:02.675840  6895 solver.cpp:237]     Train net output #0: loss = 5.29359 (* 1 = 5.29359 loss)
I0412 12:52:02.675849  6895 sgd_solver.cpp:105] Iteration 468, lr = 0.00911463
I0412 12:52:07.532490  6895 solver.cpp:218] Iteration 480 (2.47094 iter/s, 4.85646s/12 iters), loss = 5.2713
I0412 12:52:07.532547  6895 solver.cpp:237]     Train net output #0: loss = 5.2713 (* 1 = 5.2713 loss)
I0412 12:52:07.532562  6895 sgd_solver.cpp:105] Iteration 480, lr = 0.00909299
I0412 12:52:12.278789  6895 solver.cpp:218] Iteration 492 (2.52842 iter/s, 4.74606s/12 iters), loss = 5.29781
I0412 12:52:12.278836  6895 solver.cpp:237]     Train net output #0: loss = 5.29781 (* 1 = 5.29781 loss)
I0412 12:52:12.278847  6895 sgd_solver.cpp:105] Iteration 492, lr = 0.0090714
I0412 12:52:16.832526  6895 solver.cpp:218] Iteration 504 (2.63533 iter/s, 4.55351s/12 iters), loss = 5.27753
I0412 12:52:16.832583  6895 solver.cpp:237]     Train net output #0: loss = 5.27753 (* 1 = 5.27753 loss)
I0412 12:52:16.832595  6895 sgd_solver.cpp:105] Iteration 504, lr = 0.00904986
I0412 12:52:17.037868  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:52:18.631309  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_510.caffemodel
I0412 12:52:20.855567  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_510.solverstate
I0412 12:52:22.052778  6895 solver.cpp:330] Iteration 510, Testing net (#0)
I0412 12:52:22.052805  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:52:26.250666  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:52:26.486325  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 12:52:26.486367  6895 solver.cpp:397]     Test net output #1: loss = 5.28671 (* 1 = 5.28671 loss)
I0412 12:52:28.289288  6895 solver.cpp:218] Iteration 516 (1.04746 iter/s, 11.4563s/12 iters), loss = 5.29619
I0412 12:52:28.289338  6895 solver.cpp:237]     Train net output #0: loss = 5.29619 (* 1 = 5.29619 loss)
I0412 12:52:28.289351  6895 sgd_solver.cpp:105] Iteration 516, lr = 0.00902838
I0412 12:52:32.755352  6895 solver.cpp:218] Iteration 528 (2.68706 iter/s, 4.46584s/12 iters), loss = 5.28695
I0412 12:52:32.755388  6895 solver.cpp:237]     Train net output #0: loss = 5.28695 (* 1 = 5.28695 loss)
I0412 12:52:32.755398  6895 sgd_solver.cpp:105] Iteration 528, lr = 0.00900694
I0412 12:52:37.464805  6895 solver.cpp:218] Iteration 540 (2.54819 iter/s, 4.70923s/12 iters), loss = 5.28201
I0412 12:52:37.464864  6895 solver.cpp:237]     Train net output #0: loss = 5.28201 (* 1 = 5.28201 loss)
I0412 12:52:37.464880  6895 sgd_solver.cpp:105] Iteration 540, lr = 0.00898556
I0412 12:52:42.191092  6895 solver.cpp:218] Iteration 552 (2.53912 iter/s, 4.72604s/12 iters), loss = 5.27329
I0412 12:52:42.191143  6895 solver.cpp:237]     Train net output #0: loss = 5.27329 (* 1 = 5.27329 loss)
I0412 12:52:42.191155  6895 sgd_solver.cpp:105] Iteration 552, lr = 0.00896423
I0412 12:52:46.806666  6895 solver.cpp:218] Iteration 564 (2.60002 iter/s, 4.61534s/12 iters), loss = 5.26979
I0412 12:52:46.806707  6895 solver.cpp:237]     Train net output #0: loss = 5.26979 (* 1 = 5.26979 loss)
I0412 12:52:46.806715  6895 sgd_solver.cpp:105] Iteration 564, lr = 0.00894294
I0412 12:52:51.581661  6895 solver.cpp:218] Iteration 576 (2.51321 iter/s, 4.77477s/12 iters), loss = 5.28361
I0412 12:52:51.581725  6895 solver.cpp:237]     Train net output #0: loss = 5.28361 (* 1 = 5.28361 loss)
I0412 12:52:51.581734  6895 sgd_solver.cpp:105] Iteration 576, lr = 0.00892171
I0412 12:52:56.172927  6895 solver.cpp:218] Iteration 588 (2.6138 iter/s, 4.59102s/12 iters), loss = 5.27288
I0412 12:52:56.172966  6895 solver.cpp:237]     Train net output #0: loss = 5.27288 (* 1 = 5.27288 loss)
I0412 12:52:56.172973  6895 sgd_solver.cpp:105] Iteration 588, lr = 0.00890053
I0412 12:53:00.999977  6895 solver.cpp:218] Iteration 600 (2.48611 iter/s, 4.82682s/12 iters), loss = 5.2641
I0412 12:53:01.000028  6895 solver.cpp:237]     Train net output #0: loss = 5.2641 (* 1 = 5.2641 loss)
I0412 12:53:01.000041  6895 sgd_solver.cpp:105] Iteration 600, lr = 0.0088794
I0412 12:53:03.141002  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:53:05.184850  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_612.caffemodel
I0412 12:53:07.540866  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_612.solverstate
I0412 12:53:09.785488  6895 solver.cpp:330] Iteration 612, Testing net (#0)
I0412 12:53:09.785522  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:53:13.942217  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:53:14.224691  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:53:14.224753  6895 solver.cpp:397]     Test net output #1: loss = 5.28638 (* 1 = 5.28638 loss)
I0412 12:53:14.306268  6895 solver.cpp:218] Iteration 612 (0.901866 iter/s, 13.3057s/12 iters), loss = 5.28776
I0412 12:53:14.306329  6895 solver.cpp:237]     Train net output #0: loss = 5.28776 (* 1 = 5.28776 loss)
I0412 12:53:14.306344  6895 sgd_solver.cpp:105] Iteration 612, lr = 0.00885831
I0412 12:53:18.449738  6895 solver.cpp:218] Iteration 624 (2.89628 iter/s, 4.14325s/12 iters), loss = 5.30074
I0412 12:53:18.449776  6895 solver.cpp:237]     Train net output #0: loss = 5.30074 (* 1 = 5.30074 loss)
I0412 12:53:18.449784  6895 sgd_solver.cpp:105] Iteration 624, lr = 0.00883728
I0412 12:53:23.182945  6895 solver.cpp:218] Iteration 636 (2.5354 iter/s, 4.73299s/12 iters), loss = 5.29173
I0412 12:53:23.183084  6895 solver.cpp:237]     Train net output #0: loss = 5.29173 (* 1 = 5.29173 loss)
I0412 12:53:23.183094  6895 sgd_solver.cpp:105] Iteration 636, lr = 0.0088163
I0412 12:53:27.704612  6895 solver.cpp:218] Iteration 648 (2.65408 iter/s, 4.52135s/12 iters), loss = 5.26638
I0412 12:53:27.704670  6895 solver.cpp:237]     Train net output #0: loss = 5.26638 (* 1 = 5.26638 loss)
I0412 12:53:27.704684  6895 sgd_solver.cpp:105] Iteration 648, lr = 0.00879537
I0412 12:53:32.248598  6895 solver.cpp:218] Iteration 660 (2.64099 iter/s, 4.54375s/12 iters), loss = 5.2741
I0412 12:53:32.248649  6895 solver.cpp:237]     Train net output #0: loss = 5.2741 (* 1 = 5.2741 loss)
I0412 12:53:32.248662  6895 sgd_solver.cpp:105] Iteration 660, lr = 0.00877449
I0412 12:53:36.756805  6895 solver.cpp:218] Iteration 672 (2.66195 iter/s, 4.50797s/12 iters), loss = 5.28561
I0412 12:53:36.756863  6895 solver.cpp:237]     Train net output #0: loss = 5.28561 (* 1 = 5.28561 loss)
I0412 12:53:36.756875  6895 sgd_solver.cpp:105] Iteration 672, lr = 0.00875366
I0412 12:53:41.426079  6895 solver.cpp:218] Iteration 684 (2.57013 iter/s, 4.66903s/12 iters), loss = 5.28071
I0412 12:53:41.426139  6895 solver.cpp:237]     Train net output #0: loss = 5.28071 (* 1 = 5.28071 loss)
I0412 12:53:41.426152  6895 sgd_solver.cpp:105] Iteration 684, lr = 0.00873287
I0412 12:53:41.748548  6895 blocking_queue.cpp:49] Waiting for data
I0412 12:53:45.988903  6895 solver.cpp:218] Iteration 696 (2.63008 iter/s, 4.56259s/12 iters), loss = 5.27411
I0412 12:53:45.988942  6895 solver.cpp:237]     Train net output #0: loss = 5.27411 (* 1 = 5.27411 loss)
I0412 12:53:45.988950  6895 sgd_solver.cpp:105] Iteration 696, lr = 0.00871214
I0412 12:53:50.404037  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:53:50.774830  6895 solver.cpp:218] Iteration 708 (2.50747 iter/s, 4.7857s/12 iters), loss = 5.25915
I0412 12:53:50.774883  6895 solver.cpp:237]     Train net output #0: loss = 5.25915 (* 1 = 5.25915 loss)
I0412 12:53:50.774895  6895 sgd_solver.cpp:105] Iteration 708, lr = 0.00869145
I0412 12:53:52.723212  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_714.caffemodel
I0412 12:53:54.271729  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_714.solverstate
I0412 12:53:55.670935  6895 solver.cpp:330] Iteration 714, Testing net (#0)
I0412 12:53:55.670959  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:53:59.767300  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:54:00.084301  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:54:00.084350  6895 solver.cpp:397]     Test net output #1: loss = 5.28711 (* 1 = 5.28711 loss)
I0412 12:54:01.848992  6895 solver.cpp:218] Iteration 720 (1.08365 iter/s, 11.0737s/12 iters), loss = 5.28074
I0412 12:54:01.849050  6895 solver.cpp:237]     Train net output #0: loss = 5.28074 (* 1 = 5.28074 loss)
I0412 12:54:01.849061  6895 sgd_solver.cpp:105] Iteration 720, lr = 0.00867082
I0412 12:54:06.393859  6895 solver.cpp:218] Iteration 732 (2.64048 iter/s, 4.54463s/12 iters), loss = 5.27636
I0412 12:54:06.393906  6895 solver.cpp:237]     Train net output #0: loss = 5.27636 (* 1 = 5.27636 loss)
I0412 12:54:06.393918  6895 sgd_solver.cpp:105] Iteration 732, lr = 0.00865023
I0412 12:54:10.987524  6895 solver.cpp:218] Iteration 744 (2.61242 iter/s, 4.59344s/12 iters), loss = 5.28484
I0412 12:54:10.987571  6895 solver.cpp:237]     Train net output #0: loss = 5.28484 (* 1 = 5.28484 loss)
I0412 12:54:10.987583  6895 sgd_solver.cpp:105] Iteration 744, lr = 0.0086297
I0412 12:54:15.580893  6895 solver.cpp:218] Iteration 756 (2.61259 iter/s, 4.59314s/12 iters), loss = 5.28823
I0412 12:54:15.580946  6895 solver.cpp:237]     Train net output #0: loss = 5.28823 (* 1 = 5.28823 loss)
I0412 12:54:15.580958  6895 sgd_solver.cpp:105] Iteration 756, lr = 0.00860921
I0412 12:54:20.089118  6895 solver.cpp:218] Iteration 768 (2.66194 iter/s, 4.508s/12 iters), loss = 5.28312
I0412 12:54:20.089169  6895 solver.cpp:237]     Train net output #0: loss = 5.28312 (* 1 = 5.28312 loss)
I0412 12:54:20.089182  6895 sgd_solver.cpp:105] Iteration 768, lr = 0.00858877
I0412 12:54:24.562855  6895 solver.cpp:218] Iteration 780 (2.68246 iter/s, 4.4735s/12 iters), loss = 5.26528
I0412 12:54:24.563001  6895 solver.cpp:237]     Train net output #0: loss = 5.26528 (* 1 = 5.26528 loss)
I0412 12:54:24.563016  6895 sgd_solver.cpp:105] Iteration 780, lr = 0.00856838
I0412 12:54:29.118896  6895 solver.cpp:218] Iteration 792 (2.63405 iter/s, 4.55572s/12 iters), loss = 5.26999
I0412 12:54:29.118933  6895 solver.cpp:237]     Train net output #0: loss = 5.26999 (* 1 = 5.26999 loss)
I0412 12:54:29.118942  6895 sgd_solver.cpp:105] Iteration 792, lr = 0.00854803
I0412 12:54:33.872632  6895 solver.cpp:218] Iteration 804 (2.52445 iter/s, 4.75351s/12 iters), loss = 5.29654
I0412 12:54:33.872684  6895 solver.cpp:237]     Train net output #0: loss = 5.29654 (* 1 = 5.29654 loss)
I0412 12:54:33.872696  6895 sgd_solver.cpp:105] Iteration 804, lr = 0.00852774
I0412 12:54:35.461997  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:54:38.008719  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_816.caffemodel
I0412 12:54:39.511540  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_816.solverstate
I0412 12:54:40.683897  6895 solver.cpp:330] Iteration 816, Testing net (#0)
I0412 12:54:40.683920  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:54:44.849347  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:54:45.201333  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:54:45.201375  6895 solver.cpp:397]     Test net output #1: loss = 5.28677 (* 1 = 5.28677 loss)
I0412 12:54:45.283259  6895 solver.cpp:218] Iteration 816 (1.0517 iter/s, 11.4101s/12 iters), loss = 5.28559
I0412 12:54:45.283298  6895 solver.cpp:237]     Train net output #0: loss = 5.28559 (* 1 = 5.28559 loss)
I0412 12:54:45.283308  6895 sgd_solver.cpp:105] Iteration 816, lr = 0.00850749
I0412 12:54:49.369395  6895 solver.cpp:218] Iteration 828 (2.93691 iter/s, 4.08593s/12 iters), loss = 5.28282
I0412 12:54:49.369452  6895 solver.cpp:237]     Train net output #0: loss = 5.28282 (* 1 = 5.28282 loss)
I0412 12:54:49.369467  6895 sgd_solver.cpp:105] Iteration 828, lr = 0.00848729
I0412 12:54:53.994318  6895 solver.cpp:218] Iteration 840 (2.59477 iter/s, 4.62469s/12 iters), loss = 5.24052
I0412 12:54:53.994359  6895 solver.cpp:237]     Train net output #0: loss = 5.24052 (* 1 = 5.24052 loss)
I0412 12:54:53.994367  6895 sgd_solver.cpp:105] Iteration 840, lr = 0.00846714
I0412 12:54:58.765026  6895 solver.cpp:218] Iteration 852 (2.51547 iter/s, 4.77048s/12 iters), loss = 5.30545
I0412 12:54:58.765199  6895 solver.cpp:237]     Train net output #0: loss = 5.30545 (* 1 = 5.30545 loss)
I0412 12:54:58.765215  6895 sgd_solver.cpp:105] Iteration 852, lr = 0.00844704
I0412 12:55:03.197095  6895 solver.cpp:218] Iteration 864 (2.70775 iter/s, 4.43172s/12 iters), loss = 5.26045
I0412 12:55:03.197150  6895 solver.cpp:237]     Train net output #0: loss = 5.26045 (* 1 = 5.26045 loss)
I0412 12:55:03.197165  6895 sgd_solver.cpp:105] Iteration 864, lr = 0.00842698
I0412 12:55:07.620424  6895 solver.cpp:218] Iteration 876 (2.71303 iter/s, 4.4231s/12 iters), loss = 5.27754
I0412 12:55:07.620478  6895 solver.cpp:237]     Train net output #0: loss = 5.27754 (* 1 = 5.27754 loss)
I0412 12:55:07.620491  6895 sgd_solver.cpp:105] Iteration 876, lr = 0.00840698
I0412 12:55:12.070470  6895 solver.cpp:218] Iteration 888 (2.69674 iter/s, 4.44982s/12 iters), loss = 5.27424
I0412 12:55:12.070518  6895 solver.cpp:237]     Train net output #0: loss = 5.27424 (* 1 = 5.27424 loss)
I0412 12:55:12.070529  6895 sgd_solver.cpp:105] Iteration 888, lr = 0.00838702
I0412 12:55:16.656962  6895 solver.cpp:218] Iteration 900 (2.61651 iter/s, 4.58626s/12 iters), loss = 5.28302
I0412 12:55:16.657019  6895 solver.cpp:237]     Train net output #0: loss = 5.28302 (* 1 = 5.28302 loss)
I0412 12:55:16.657032  6895 sgd_solver.cpp:105] Iteration 900, lr = 0.0083671
I0412 12:55:20.253166  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:55:21.293089  6895 solver.cpp:218] Iteration 912 (2.58851 iter/s, 4.63588s/12 iters), loss = 5.26479
I0412 12:55:21.293140  6895 solver.cpp:237]     Train net output #0: loss = 5.26479 (* 1 = 5.26479 loss)
I0412 12:55:21.293152  6895 sgd_solver.cpp:105] Iteration 912, lr = 0.00834724
I0412 12:55:23.102921  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_918.caffemodel
I0412 12:55:24.672719  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_918.solverstate
I0412 12:55:25.863783  6895 solver.cpp:330] Iteration 918, Testing net (#0)
I0412 12:55:25.863812  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:55:29.872663  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:55:30.275331  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:55:30.275380  6895 solver.cpp:397]     Test net output #1: loss = 5.28641 (* 1 = 5.28641 loss)
I0412 12:55:31.993129  6895 solver.cpp:218] Iteration 924 (1.12154 iter/s, 10.6996s/12 iters), loss = 5.28492
I0412 12:55:31.993182  6895 solver.cpp:237]     Train net output #0: loss = 5.28492 (* 1 = 5.28492 loss)
I0412 12:55:31.993196  6895 sgd_solver.cpp:105] Iteration 924, lr = 0.00832742
I0412 12:55:36.426291  6895 solver.cpp:218] Iteration 936 (2.70701 iter/s, 4.43294s/12 iters), loss = 5.26647
I0412 12:55:36.426338  6895 solver.cpp:237]     Train net output #0: loss = 5.26647 (* 1 = 5.26647 loss)
I0412 12:55:36.426349  6895 sgd_solver.cpp:105] Iteration 936, lr = 0.00830765
I0412 12:55:40.979606  6895 solver.cpp:218] Iteration 948 (2.63557 iter/s, 4.55309s/12 iters), loss = 5.29206
I0412 12:55:40.979648  6895 solver.cpp:237]     Train net output #0: loss = 5.29206 (* 1 = 5.29206 loss)
I0412 12:55:40.979660  6895 sgd_solver.cpp:105] Iteration 948, lr = 0.00828793
I0412 12:55:45.527746  6895 solver.cpp:218] Iteration 960 (2.63857 iter/s, 4.54792s/12 iters), loss = 5.25876
I0412 12:55:45.527782  6895 solver.cpp:237]     Train net output #0: loss = 5.25876 (* 1 = 5.25876 loss)
I0412 12:55:45.527789  6895 sgd_solver.cpp:105] Iteration 960, lr = 0.00826825
I0412 12:55:50.149525  6895 solver.cpp:218] Iteration 972 (2.59653 iter/s, 4.62156s/12 iters), loss = 5.27607
I0412 12:55:50.149566  6895 solver.cpp:237]     Train net output #0: loss = 5.27607 (* 1 = 5.27607 loss)
I0412 12:55:50.149576  6895 sgd_solver.cpp:105] Iteration 972, lr = 0.00824862
I0412 12:55:54.631160  6895 solver.cpp:218] Iteration 984 (2.67773 iter/s, 4.48141s/12 iters), loss = 5.29292
I0412 12:55:54.631214  6895 solver.cpp:237]     Train net output #0: loss = 5.29292 (* 1 = 5.29292 loss)
I0412 12:55:54.631227  6895 sgd_solver.cpp:105] Iteration 984, lr = 0.00822903
I0412 12:55:59.252925  6895 solver.cpp:218] Iteration 996 (2.59654 iter/s, 4.62153s/12 iters), loss = 5.28055
I0412 12:55:59.252972  6895 solver.cpp:237]     Train net output #0: loss = 5.28055 (* 1 = 5.28055 loss)
I0412 12:55:59.252985  6895 sgd_solver.cpp:105] Iteration 996, lr = 0.0082095
I0412 12:56:03.757944  6895 solver.cpp:218] Iteration 1008 (2.66383 iter/s, 4.5048s/12 iters), loss = 5.29522
I0412 12:56:03.758114  6895 solver.cpp:237]     Train net output #0: loss = 5.29522 (* 1 = 5.29522 loss)
I0412 12:56:03.758126  6895 sgd_solver.cpp:105] Iteration 1008, lr = 0.00819001
I0412 12:56:04.668505  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:56:08.043040  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1020.caffemodel
I0412 12:56:09.585644  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1020.solverstate
I0412 12:56:10.804677  6895 solver.cpp:330] Iteration 1020, Testing net (#0)
I0412 12:56:10.804708  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:56:14.867442  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:56:15.295719  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:56:15.295768  6895 solver.cpp:397]     Test net output #1: loss = 5.28621 (* 1 = 5.28621 loss)
I0412 12:56:15.378868  6895 solver.cpp:218] Iteration 1020 (1.03267 iter/s, 11.6203s/12 iters), loss = 5.30033
I0412 12:56:15.378926  6895 solver.cpp:237]     Train net output #0: loss = 5.30033 (* 1 = 5.30033 loss)
I0412 12:56:15.378937  6895 sgd_solver.cpp:105] Iteration 1020, lr = 0.00817056
I0412 12:56:19.189785  6895 solver.cpp:218] Iteration 1032 (3.14902 iter/s, 3.81071s/12 iters), loss = 5.25487
I0412 12:56:19.189826  6895 solver.cpp:237]     Train net output #0: loss = 5.25487 (* 1 = 5.25487 loss)
I0412 12:56:19.189834  6895 sgd_solver.cpp:105] Iteration 1032, lr = 0.00815116
I0412 12:56:24.024960  6895 solver.cpp:218] Iteration 1044 (2.48193 iter/s, 4.83494s/12 iters), loss = 5.26782
I0412 12:56:24.025004  6895 solver.cpp:237]     Train net output #0: loss = 5.26782 (* 1 = 5.26782 loss)
I0412 12:56:24.025014  6895 sgd_solver.cpp:105] Iteration 1044, lr = 0.00813181
I0412 12:56:28.767381  6895 solver.cpp:218] Iteration 1056 (2.53048 iter/s, 4.74219s/12 iters), loss = 5.27006
I0412 12:56:28.767437  6895 solver.cpp:237]     Train net output #0: loss = 5.27006 (* 1 = 5.27006 loss)
I0412 12:56:28.767450  6895 sgd_solver.cpp:105] Iteration 1056, lr = 0.0081125
I0412 12:56:33.271030  6895 solver.cpp:218] Iteration 1068 (2.66464 iter/s, 4.50342s/12 iters), loss = 5.29013
I0412 12:56:33.271085  6895 solver.cpp:237]     Train net output #0: loss = 5.29013 (* 1 = 5.29013 loss)
I0412 12:56:33.271097  6895 sgd_solver.cpp:105] Iteration 1068, lr = 0.00809324
I0412 12:56:37.976837  6895 solver.cpp:218] Iteration 1080 (2.55017 iter/s, 4.70556s/12 iters), loss = 5.27946
I0412 12:56:37.976931  6895 solver.cpp:237]     Train net output #0: loss = 5.27946 (* 1 = 5.27946 loss)
I0412 12:56:37.976945  6895 sgd_solver.cpp:105] Iteration 1080, lr = 0.00807403
I0412 12:56:42.519913  6895 solver.cpp:218] Iteration 1092 (2.64154 iter/s, 4.54281s/12 iters), loss = 5.28525
I0412 12:56:42.519963  6895 solver.cpp:237]     Train net output #0: loss = 5.28525 (* 1 = 5.28525 loss)
I0412 12:56:42.519973  6895 sgd_solver.cpp:105] Iteration 1092, lr = 0.00805486
I0412 12:56:47.203883  6895 solver.cpp:218] Iteration 1104 (2.56206 iter/s, 4.68373s/12 iters), loss = 5.27253
I0412 12:56:47.203940  6895 solver.cpp:237]     Train net output #0: loss = 5.27253 (* 1 = 5.27253 loss)
I0412 12:56:47.203953  6895 sgd_solver.cpp:105] Iteration 1104, lr = 0.00803573
I0412 12:56:50.142125  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:56:51.852430  6895 solver.cpp:218] Iteration 1116 (2.58159 iter/s, 4.6483s/12 iters), loss = 5.27505
I0412 12:56:51.852488  6895 solver.cpp:237]     Train net output #0: loss = 5.27505 (* 1 = 5.27505 loss)
I0412 12:56:51.852501  6895 sgd_solver.cpp:105] Iteration 1116, lr = 0.00801666
I0412 12:56:53.620857  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1122.caffemodel
I0412 12:56:56.294914  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1122.solverstate
I0412 12:56:58.316812  6895 solver.cpp:330] Iteration 1122, Testing net (#0)
I0412 12:56:58.316840  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:57:02.285226  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:57:02.758239  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:57:02.758287  6895 solver.cpp:397]     Test net output #1: loss = 5.28677 (* 1 = 5.28677 loss)
I0412 12:57:04.608191  6895 solver.cpp:218] Iteration 1128 (0.940791 iter/s, 12.7552s/12 iters), loss = 5.2711
I0412 12:57:04.608249  6895 solver.cpp:237]     Train net output #0: loss = 5.2711 (* 1 = 5.2711 loss)
I0412 12:57:04.608263  6895 sgd_solver.cpp:105] Iteration 1128, lr = 0.00799762
I0412 12:57:09.250834  6895 solver.cpp:218] Iteration 1140 (2.58487 iter/s, 4.6424s/12 iters), loss = 5.26928
I0412 12:57:09.250967  6895 solver.cpp:237]     Train net output #0: loss = 5.26928 (* 1 = 5.26928 loss)
I0412 12:57:09.250979  6895 sgd_solver.cpp:105] Iteration 1140, lr = 0.00797863
I0412 12:57:13.797328  6895 solver.cpp:218] Iteration 1152 (2.63958 iter/s, 4.54618s/12 iters), loss = 5.28318
I0412 12:57:13.797370  6895 solver.cpp:237]     Train net output #0: loss = 5.28318 (* 1 = 5.28318 loss)
I0412 12:57:13.797381  6895 sgd_solver.cpp:105] Iteration 1152, lr = 0.00795969
I0412 12:57:18.394642  6895 solver.cpp:218] Iteration 1164 (2.61035 iter/s, 4.59709s/12 iters), loss = 5.27217
I0412 12:57:18.394681  6895 solver.cpp:237]     Train net output #0: loss = 5.27217 (* 1 = 5.27217 loss)
I0412 12:57:18.394690  6895 sgd_solver.cpp:105] Iteration 1164, lr = 0.00794079
I0412 12:57:22.984671  6895 solver.cpp:218] Iteration 1176 (2.61449 iter/s, 4.5898s/12 iters), loss = 5.2896
I0412 12:57:22.984724  6895 solver.cpp:237]     Train net output #0: loss = 5.2896 (* 1 = 5.2896 loss)
I0412 12:57:22.984735  6895 sgd_solver.cpp:105] Iteration 1176, lr = 0.00792194
I0412 12:57:27.766736  6895 solver.cpp:218] Iteration 1188 (2.5095 iter/s, 4.78182s/12 iters), loss = 5.27718
I0412 12:57:27.766785  6895 solver.cpp:237]     Train net output #0: loss = 5.27718 (* 1 = 5.27718 loss)
I0412 12:57:27.766795  6895 sgd_solver.cpp:105] Iteration 1188, lr = 0.00790313
I0412 12:57:32.525148  6895 solver.cpp:218] Iteration 1200 (2.52197 iter/s, 4.75818s/12 iters), loss = 5.28826
I0412 12:57:32.525195  6895 solver.cpp:237]     Train net output #0: loss = 5.28826 (* 1 = 5.28826 loss)
I0412 12:57:32.525204  6895 sgd_solver.cpp:105] Iteration 1200, lr = 0.00788437
I0412 12:57:37.399842  6895 solver.cpp:218] Iteration 1212 (2.46182 iter/s, 4.87445s/12 iters), loss = 5.27032
I0412 12:57:37.399904  6895 solver.cpp:237]     Train net output #0: loss = 5.27032 (* 1 = 5.27032 loss)
I0412 12:57:37.399919  6895 sgd_solver.cpp:105] Iteration 1212, lr = 0.00786565
I0412 12:57:37.656977  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:57:41.892423  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1224.caffemodel
I0412 12:57:44.887754  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1224.solverstate
I0412 12:57:46.616103  6895 solver.cpp:330] Iteration 1224, Testing net (#0)
I0412 12:57:46.616135  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:57:50.638041  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:57:51.146347  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 12:57:51.146394  6895 solver.cpp:397]     Test net output #1: loss = 5.28622 (* 1 = 5.28622 loss)
I0412 12:57:51.229600  6895 solver.cpp:218] Iteration 1224 (0.867731 iter/s, 13.8292s/12 iters), loss = 5.28931
I0412 12:57:51.229655  6895 solver.cpp:237]     Train net output #0: loss = 5.28931 (* 1 = 5.28931 loss)
I0412 12:57:51.229666  6895 sgd_solver.cpp:105] Iteration 1224, lr = 0.00784697
I0412 12:57:55.350536  6895 solver.cpp:218] Iteration 1236 (2.91211 iter/s, 4.12072s/12 iters), loss = 5.27456
I0412 12:57:55.350589  6895 solver.cpp:237]     Train net output #0: loss = 5.27456 (* 1 = 5.27456 loss)
I0412 12:57:55.350602  6895 sgd_solver.cpp:105] Iteration 1236, lr = 0.00782834
I0412 12:58:00.028194  6895 solver.cpp:218] Iteration 1248 (2.56552 iter/s, 4.67742s/12 iters), loss = 5.28282
I0412 12:58:00.028242  6895 solver.cpp:237]     Train net output #0: loss = 5.28282 (* 1 = 5.28282 loss)
I0412 12:58:00.028254  6895 sgd_solver.cpp:105] Iteration 1248, lr = 0.00780976
I0412 12:58:05.031042  6895 solver.cpp:218] Iteration 1260 (2.39875 iter/s, 5.00261s/12 iters), loss = 5.2748
I0412 12:58:05.031100  6895 solver.cpp:237]     Train net output #0: loss = 5.2748 (* 1 = 5.2748 loss)
I0412 12:58:05.031114  6895 sgd_solver.cpp:105] Iteration 1260, lr = 0.00779122
I0412 12:58:09.500113  6895 solver.cpp:218] Iteration 1272 (2.68526 iter/s, 4.46884s/12 iters), loss = 5.244
I0412 12:58:09.500149  6895 solver.cpp:237]     Train net output #0: loss = 5.244 (* 1 = 5.244 loss)
I0412 12:58:09.500157  6895 sgd_solver.cpp:105] Iteration 1272, lr = 0.00777272
I0412 12:58:14.567026  6895 solver.cpp:218] Iteration 1284 (2.36842 iter/s, 5.06667s/12 iters), loss = 5.28712
I0412 12:58:14.567262  6895 solver.cpp:237]     Train net output #0: loss = 5.28712 (* 1 = 5.28712 loss)
I0412 12:58:14.567272  6895 sgd_solver.cpp:105] Iteration 1284, lr = 0.00775426
I0412 12:58:19.415709  6895 solver.cpp:218] Iteration 1296 (2.47512 iter/s, 4.84826s/12 iters), loss = 5.26481
I0412 12:58:19.415761  6895 solver.cpp:237]     Train net output #0: loss = 5.26481 (* 1 = 5.26481 loss)
I0412 12:58:19.415772  6895 sgd_solver.cpp:105] Iteration 1296, lr = 0.00773585
I0412 12:58:24.266186  6895 solver.cpp:218] Iteration 1308 (2.47411 iter/s, 4.85024s/12 iters), loss = 5.25368
I0412 12:58:24.266243  6895 solver.cpp:237]     Train net output #0: loss = 5.25368 (* 1 = 5.25368 loss)
I0412 12:58:24.266258  6895 sgd_solver.cpp:105] Iteration 1308, lr = 0.00771749
I0412 12:58:26.705137  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:58:29.063206  6895 solver.cpp:218] Iteration 1320 (2.50168 iter/s, 4.79677s/12 iters), loss = 5.28209
I0412 12:58:29.063252  6895 solver.cpp:237]     Train net output #0: loss = 5.28209 (* 1 = 5.28209 loss)
I0412 12:58:29.063261  6895 sgd_solver.cpp:105] Iteration 1320, lr = 0.00769916
I0412 12:58:30.919299  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1326.caffemodel
I0412 12:58:32.462154  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1326.solverstate
I0412 12:58:33.642817  6895 solver.cpp:330] Iteration 1326, Testing net (#0)
I0412 12:58:33.642846  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:58:37.696472  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:58:38.253684  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:58:38.253731  6895 solver.cpp:397]     Test net output #1: loss = 5.28702 (* 1 = 5.28702 loss)
I0412 12:58:40.083053  6895 solver.cpp:218] Iteration 1332 (1.08899 iter/s, 11.0194s/12 iters), loss = 5.29007
I0412 12:58:40.083097  6895 solver.cpp:237]     Train net output #0: loss = 5.29007 (* 1 = 5.29007 loss)
I0412 12:58:40.083106  6895 sgd_solver.cpp:105] Iteration 1332, lr = 0.00768088
I0412 12:58:44.800455  6895 solver.cpp:218] Iteration 1344 (2.5439 iter/s, 4.71717s/12 iters), loss = 5.2876
I0412 12:58:44.800592  6895 solver.cpp:237]     Train net output #0: loss = 5.2876 (* 1 = 5.2876 loss)
I0412 12:58:44.800602  6895 sgd_solver.cpp:105] Iteration 1344, lr = 0.00766265
I0412 12:58:49.638500  6895 solver.cpp:218] Iteration 1356 (2.48051 iter/s, 4.83772s/12 iters), loss = 5.27717
I0412 12:58:49.638543  6895 solver.cpp:237]     Train net output #0: loss = 5.27717 (* 1 = 5.27717 loss)
I0412 12:58:49.638556  6895 sgd_solver.cpp:105] Iteration 1356, lr = 0.00764446
I0412 12:58:54.529489  6895 solver.cpp:218] Iteration 1368 (2.45361 iter/s, 4.89075s/12 iters), loss = 5.27491
I0412 12:58:54.529539  6895 solver.cpp:237]     Train net output #0: loss = 5.27491 (* 1 = 5.27491 loss)
I0412 12:58:54.529551  6895 sgd_solver.cpp:105] Iteration 1368, lr = 0.00762631
I0412 12:58:55.260325  6895 blocking_queue.cpp:49] Waiting for data
I0412 12:58:59.074154  6895 solver.cpp:218] Iteration 1380 (2.64059 iter/s, 4.54443s/12 iters), loss = 5.2762
I0412 12:58:59.074210  6895 solver.cpp:237]     Train net output #0: loss = 5.2762 (* 1 = 5.2762 loss)
I0412 12:58:59.074223  6895 sgd_solver.cpp:105] Iteration 1380, lr = 0.0076082
I0412 12:59:03.830839  6895 solver.cpp:218] Iteration 1392 (2.52289 iter/s, 4.75645s/12 iters), loss = 5.26885
I0412 12:59:03.830878  6895 solver.cpp:237]     Train net output #0: loss = 5.26885 (* 1 = 5.26885 loss)
I0412 12:59:03.830888  6895 sgd_solver.cpp:105] Iteration 1392, lr = 0.00759014
I0412 12:59:08.777796  6895 solver.cpp:218] Iteration 1404 (2.42585 iter/s, 4.94672s/12 iters), loss = 5.28153
I0412 12:59:08.777846  6895 solver.cpp:237]     Train net output #0: loss = 5.28153 (* 1 = 5.28153 loss)
I0412 12:59:08.777858  6895 sgd_solver.cpp:105] Iteration 1404, lr = 0.00757212
I0412 12:59:12.981858  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:59:13.323226  6895 solver.cpp:218] Iteration 1416 (2.64015 iter/s, 4.5452s/12 iters), loss = 5.26331
I0412 12:59:13.323290  6895 solver.cpp:237]     Train net output #0: loss = 5.26331 (* 1 = 5.26331 loss)
I0412 12:59:13.323308  6895 sgd_solver.cpp:105] Iteration 1416, lr = 0.00755414
I0412 12:59:17.715131  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1428.caffemodel
I0412 12:59:19.200783  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1428.solverstate
I0412 12:59:20.984850  6895 solver.cpp:330] Iteration 1428, Testing net (#0)
I0412 12:59:20.984877  6895 net.cpp:676] Ignoring source layer train-data
I0412 12:59:25.185369  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 12:59:25.776583  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 12:59:25.776631  6895 solver.cpp:397]     Test net output #1: loss = 5.2862 (* 1 = 5.2862 loss)
I0412 12:59:25.859921  6895 solver.cpp:218] Iteration 1428 (0.957231 iter/s, 12.5362s/12 iters), loss = 5.27563
I0412 12:59:25.859964  6895 solver.cpp:237]     Train net output #0: loss = 5.27563 (* 1 = 5.27563 loss)
I0412 12:59:25.859974  6895 sgd_solver.cpp:105] Iteration 1428, lr = 0.0075362
I0412 12:59:29.925839  6895 solver.cpp:218] Iteration 1440 (2.95152 iter/s, 4.06571s/12 iters), loss = 5.28669
I0412 12:59:29.925892  6895 solver.cpp:237]     Train net output #0: loss = 5.28669 (* 1 = 5.28669 loss)
I0412 12:59:29.925904  6895 sgd_solver.cpp:105] Iteration 1440, lr = 0.00751831
I0412 12:59:35.027884  6895 solver.cpp:218] Iteration 1452 (2.35212 iter/s, 5.10179s/12 iters), loss = 5.28321
I0412 12:59:35.027937  6895 solver.cpp:237]     Train net output #0: loss = 5.28321 (* 1 = 5.28321 loss)
I0412 12:59:35.027948  6895 sgd_solver.cpp:105] Iteration 1452, lr = 0.00750046
I0412 12:59:39.581465  6895 solver.cpp:218] Iteration 1464 (2.63542 iter/s, 4.55335s/12 iters), loss = 5.28135
I0412 12:59:39.581507  6895 solver.cpp:237]     Train net output #0: loss = 5.28135 (* 1 = 5.28135 loss)
I0412 12:59:39.581516  6895 sgd_solver.cpp:105] Iteration 1464, lr = 0.00748265
I0412 12:59:44.365751  6895 solver.cpp:218] Iteration 1476 (2.50833 iter/s, 4.78406s/12 iters), loss = 5.27557
I0412 12:59:44.365794  6895 solver.cpp:237]     Train net output #0: loss = 5.27557 (* 1 = 5.27557 loss)
I0412 12:59:44.365805  6895 sgd_solver.cpp:105] Iteration 1476, lr = 0.00746489
I0412 12:59:49.136624  6895 solver.cpp:218] Iteration 1488 (2.51538 iter/s, 4.77064s/12 iters), loss = 5.25007
I0412 12:59:49.136775  6895 solver.cpp:237]     Train net output #0: loss = 5.25007 (* 1 = 5.25007 loss)
I0412 12:59:49.136788  6895 sgd_solver.cpp:105] Iteration 1488, lr = 0.00744716
I0412 12:59:53.869357  6895 solver.cpp:218] Iteration 1500 (2.53571 iter/s, 4.7324s/12 iters), loss = 5.27066
I0412 12:59:53.869406  6895 solver.cpp:237]     Train net output #0: loss = 5.27066 (* 1 = 5.27066 loss)
I0412 12:59:53.869416  6895 sgd_solver.cpp:105] Iteration 1500, lr = 0.00742948
I0412 12:59:58.679227  6895 solver.cpp:218] Iteration 1512 (2.495 iter/s, 4.80963s/12 iters), loss = 5.29204
I0412 12:59:58.679280  6895 solver.cpp:237]     Train net output #0: loss = 5.29204 (* 1 = 5.29204 loss)
I0412 12:59:58.679289  6895 sgd_solver.cpp:105] Iteration 1512, lr = 0.00741184
I0412 13:00:00.289821  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:00:03.426920  6895 solver.cpp:218] Iteration 1524 (2.52767 iter/s, 4.74745s/12 iters), loss = 5.27713
I0412 13:00:03.426972  6895 solver.cpp:237]     Train net output #0: loss = 5.27713 (* 1 = 5.27713 loss)
I0412 13:00:03.426985  6895 sgd_solver.cpp:105] Iteration 1524, lr = 0.00739425
I0412 13:00:05.344749  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1530.caffemodel
I0412 13:00:06.896195  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1530.solverstate
I0412 13:00:08.066613  6895 solver.cpp:330] Iteration 1530, Testing net (#0)
I0412 13:00:08.066635  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:00:11.857064  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:00:12.503051  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:00:12.503096  6895 solver.cpp:397]     Test net output #1: loss = 5.28588 (* 1 = 5.28588 loss)
I0412 13:00:14.288653  6895 solver.cpp:218] Iteration 1536 (1.10484 iter/s, 10.8613s/12 iters), loss = 5.28564
I0412 13:00:14.288698  6895 solver.cpp:237]     Train net output #0: loss = 5.28564 (* 1 = 5.28564 loss)
I0412 13:00:14.288707  6895 sgd_solver.cpp:105] Iteration 1536, lr = 0.00737669
I0412 13:00:18.918908  6895 solver.cpp:218] Iteration 1548 (2.59178 iter/s, 4.63002s/12 iters), loss = 5.2372
I0412 13:00:18.918965  6895 solver.cpp:237]     Train net output #0: loss = 5.2372 (* 1 = 5.2372 loss)
I0412 13:00:18.918978  6895 sgd_solver.cpp:105] Iteration 1548, lr = 0.00735918
I0412 13:00:23.602453  6895 solver.cpp:218] Iteration 1560 (2.56229 iter/s, 4.6833s/12 iters), loss = 5.29264
I0412 13:00:23.602560  6895 solver.cpp:237]     Train net output #0: loss = 5.29264 (* 1 = 5.29264 loss)
I0412 13:00:23.602576  6895 sgd_solver.cpp:105] Iteration 1560, lr = 0.00734171
I0412 13:00:28.319772  6895 solver.cpp:218] Iteration 1572 (2.54397 iter/s, 4.71703s/12 iters), loss = 5.25925
I0412 13:00:28.319819  6895 solver.cpp:237]     Train net output #0: loss = 5.25925 (* 1 = 5.25925 loss)
I0412 13:00:28.319829  6895 sgd_solver.cpp:105] Iteration 1572, lr = 0.00732427
I0412 13:00:33.056125  6895 solver.cpp:218] Iteration 1584 (2.53372 iter/s, 4.73611s/12 iters), loss = 5.27499
I0412 13:00:33.056187  6895 solver.cpp:237]     Train net output #0: loss = 5.27499 (* 1 = 5.27499 loss)
I0412 13:00:33.056205  6895 sgd_solver.cpp:105] Iteration 1584, lr = 0.00730688
I0412 13:00:37.749620  6895 solver.cpp:218] Iteration 1596 (2.55686 iter/s, 4.69325s/12 iters), loss = 5.27181
I0412 13:00:37.749683  6895 solver.cpp:237]     Train net output #0: loss = 5.27181 (* 1 = 5.27181 loss)
I0412 13:00:37.749697  6895 sgd_solver.cpp:105] Iteration 1596, lr = 0.00728954
I0412 13:00:42.418876  6895 solver.cpp:218] Iteration 1608 (2.57014 iter/s, 4.66901s/12 iters), loss = 5.27769
I0412 13:00:42.418921  6895 solver.cpp:237]     Train net output #0: loss = 5.27769 (* 1 = 5.27769 loss)
I0412 13:00:42.418931  6895 sgd_solver.cpp:105] Iteration 1608, lr = 0.00727223
I0412 13:00:46.071380  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:00:47.077145  6895 solver.cpp:218] Iteration 1620 (2.57619 iter/s, 4.65804s/12 iters), loss = 5.26207
I0412 13:00:47.077201  6895 solver.cpp:237]     Train net output #0: loss = 5.26207 (* 1 = 5.26207 loss)
I0412 13:00:47.077214  6895 sgd_solver.cpp:105] Iteration 1620, lr = 0.00725496
I0412 13:00:51.571384  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1632.caffemodel
I0412 13:00:53.074774  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1632.solverstate
I0412 13:00:55.806603  6895 solver.cpp:330] Iteration 1632, Testing net (#0)
I0412 13:00:55.806728  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:00:59.695036  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:01:00.418051  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:01:00.418092  6895 solver.cpp:397]     Test net output #1: loss = 5.28581 (* 1 = 5.28581 loss)
I0412 13:01:00.501793  6895 solver.cpp:218] Iteration 1632 (0.893915 iter/s, 13.4241s/12 iters), loss = 5.28758
I0412 13:01:00.501844  6895 solver.cpp:237]     Train net output #0: loss = 5.28758 (* 1 = 5.28758 loss)
I0412 13:01:00.501855  6895 sgd_solver.cpp:105] Iteration 1632, lr = 0.00723774
I0412 13:01:04.550338  6895 solver.cpp:218] Iteration 1644 (2.96419 iter/s, 4.04833s/12 iters), loss = 5.25816
I0412 13:01:04.550379  6895 solver.cpp:237]     Train net output #0: loss = 5.25816 (* 1 = 5.25816 loss)
I0412 13:01:04.550388  6895 sgd_solver.cpp:105] Iteration 1644, lr = 0.00722056
I0412 13:01:09.383036  6895 solver.cpp:218] Iteration 1656 (2.48321 iter/s, 4.83246s/12 iters), loss = 5.28783
I0412 13:01:09.383095  6895 solver.cpp:237]     Train net output #0: loss = 5.28783 (* 1 = 5.28783 loss)
I0412 13:01:09.383106  6895 sgd_solver.cpp:105] Iteration 1656, lr = 0.00720341
I0412 13:01:14.052202  6895 solver.cpp:218] Iteration 1668 (2.57018 iter/s, 4.66893s/12 iters), loss = 5.26214
I0412 13:01:14.052259  6895 solver.cpp:237]     Train net output #0: loss = 5.26214 (* 1 = 5.26214 loss)
I0412 13:01:14.052271  6895 sgd_solver.cpp:105] Iteration 1668, lr = 0.00718631
I0412 13:01:18.846226  6895 solver.cpp:218] Iteration 1680 (2.50325 iter/s, 4.79378s/12 iters), loss = 5.27722
I0412 13:01:18.846276  6895 solver.cpp:237]     Train net output #0: loss = 5.27722 (* 1 = 5.27722 loss)
I0412 13:01:18.846287  6895 sgd_solver.cpp:105] Iteration 1680, lr = 0.00716925
I0412 13:01:23.657325  6895 solver.cpp:218] Iteration 1692 (2.49436 iter/s, 4.81086s/12 iters), loss = 5.29632
I0412 13:01:23.657373  6895 solver.cpp:237]     Train net output #0: loss = 5.29632 (* 1 = 5.29632 loss)
I0412 13:01:23.657383  6895 sgd_solver.cpp:105] Iteration 1692, lr = 0.00715223
I0412 13:01:28.327873  6895 solver.cpp:218] Iteration 1704 (2.56942 iter/s, 4.67031s/12 iters), loss = 5.26865
I0412 13:01:28.327975  6895 solver.cpp:237]     Train net output #0: loss = 5.26865 (* 1 = 5.26865 loss)
I0412 13:01:28.327989  6895 sgd_solver.cpp:105] Iteration 1704, lr = 0.00713525
I0412 13:01:33.055905  6895 solver.cpp:218] Iteration 1716 (2.53821 iter/s, 4.72774s/12 iters), loss = 5.28277
I0412 13:01:33.055961  6895 solver.cpp:237]     Train net output #0: loss = 5.28277 (* 1 = 5.28277 loss)
I0412 13:01:33.055974  6895 sgd_solver.cpp:105] Iteration 1716, lr = 0.00711831
I0412 13:01:34.005095  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:01:37.702775  6895 solver.cpp:218] Iteration 1728 (2.58252 iter/s, 4.64663s/12 iters), loss = 5.28648
I0412 13:01:37.702833  6895 solver.cpp:237]     Train net output #0: loss = 5.28648 (* 1 = 5.28648 loss)
I0412 13:01:37.702847  6895 sgd_solver.cpp:105] Iteration 1728, lr = 0.00710141
I0412 13:01:39.730684  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1734.caffemodel
I0412 13:01:41.276796  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1734.solverstate
I0412 13:01:42.447108  6895 solver.cpp:330] Iteration 1734, Testing net (#0)
I0412 13:01:42.447130  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:01:46.306538  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:01:47.011994  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:01:47.012043  6895 solver.cpp:397]     Test net output #1: loss = 5.28626 (* 1 = 5.28626 loss)
I0412 13:01:48.641634  6895 solver.cpp:218] Iteration 1740 (1.09705 iter/s, 10.9384s/12 iters), loss = 5.25696
I0412 13:01:48.641682  6895 solver.cpp:237]     Train net output #0: loss = 5.25696 (* 1 = 5.25696 loss)
I0412 13:01:48.641690  6895 sgd_solver.cpp:105] Iteration 1740, lr = 0.00708455
I0412 13:01:53.134516  6895 solver.cpp:218] Iteration 1752 (2.67103 iter/s, 4.49265s/12 iters), loss = 5.26981
I0412 13:01:53.134572  6895 solver.cpp:237]     Train net output #0: loss = 5.26981 (* 1 = 5.26981 loss)
I0412 13:01:53.134583  6895 sgd_solver.cpp:105] Iteration 1752, lr = 0.00706773
I0412 13:01:57.669589  6895 solver.cpp:218] Iteration 1764 (2.64618 iter/s, 4.53484s/12 iters), loss = 5.27007
I0412 13:01:57.669638  6895 solver.cpp:237]     Train net output #0: loss = 5.27007 (* 1 = 5.27007 loss)
I0412 13:01:57.669648  6895 sgd_solver.cpp:105] Iteration 1764, lr = 0.00705094
I0412 13:02:02.515455  6895 solver.cpp:218] Iteration 1776 (2.47646 iter/s, 4.84562s/12 iters), loss = 5.2801
I0412 13:02:02.515631  6895 solver.cpp:237]     Train net output #0: loss = 5.2801 (* 1 = 5.2801 loss)
I0412 13:02:02.515648  6895 sgd_solver.cpp:105] Iteration 1776, lr = 0.0070342
I0412 13:02:07.306991  6895 solver.cpp:218] Iteration 1788 (2.5046 iter/s, 4.79118s/12 iters), loss = 5.26694
I0412 13:02:07.307042  6895 solver.cpp:237]     Train net output #0: loss = 5.26694 (* 1 = 5.26694 loss)
I0412 13:02:07.307054  6895 sgd_solver.cpp:105] Iteration 1788, lr = 0.0070175
I0412 13:02:12.028062  6895 solver.cpp:218] Iteration 1800 (2.54192 iter/s, 4.72084s/12 iters), loss = 5.27943
I0412 13:02:12.028105  6895 solver.cpp:237]     Train net output #0: loss = 5.27943 (* 1 = 5.27943 loss)
I0412 13:02:12.028112  6895 sgd_solver.cpp:105] Iteration 1800, lr = 0.00700084
I0412 13:02:16.882972  6895 solver.cpp:218] Iteration 1812 (2.47184 iter/s, 4.85468s/12 iters), loss = 5.2651
I0412 13:02:16.883023  6895 solver.cpp:237]     Train net output #0: loss = 5.2651 (* 1 = 5.2651 loss)
I0412 13:02:16.883035  6895 sgd_solver.cpp:105] Iteration 1812, lr = 0.00698422
I0412 13:02:19.891167  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:02:21.533437  6895 solver.cpp:218] Iteration 1824 (2.58052 iter/s, 4.65023s/12 iters), loss = 5.27713
I0412 13:02:21.533483  6895 solver.cpp:237]     Train net output #0: loss = 5.27713 (* 1 = 5.27713 loss)
I0412 13:02:21.533493  6895 sgd_solver.cpp:105] Iteration 1824, lr = 0.00696764
I0412 13:02:25.841490  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1836.caffemodel
I0412 13:02:31.909224  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1836.solverstate
I0412 13:02:33.534070  6895 solver.cpp:330] Iteration 1836, Testing net (#0)
I0412 13:02:33.534150  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:02:37.262881  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:02:38.011471  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:02:38.011520  6895 solver.cpp:397]     Test net output #1: loss = 5.28551 (* 1 = 5.28551 loss)
I0412 13:02:38.094558  6895 solver.cpp:218] Iteration 1836 (0.724618 iter/s, 16.5605s/12 iters), loss = 5.27936
I0412 13:02:38.094611  6895 solver.cpp:237]     Train net output #0: loss = 5.27936 (* 1 = 5.27936 loss)
I0412 13:02:38.094621  6895 sgd_solver.cpp:105] Iteration 1836, lr = 0.0069511
I0412 13:02:41.970981  6895 solver.cpp:218] Iteration 1848 (3.0958 iter/s, 3.87622s/12 iters), loss = 5.27736
I0412 13:02:41.971036  6895 solver.cpp:237]     Train net output #0: loss = 5.27736 (* 1 = 5.27736 loss)
I0412 13:02:41.971048  6895 sgd_solver.cpp:105] Iteration 1848, lr = 0.00693459
I0412 13:02:46.598357  6895 solver.cpp:218] Iteration 1860 (2.59339 iter/s, 4.62715s/12 iters), loss = 5.28735
I0412 13:02:46.598402  6895 solver.cpp:237]     Train net output #0: loss = 5.28735 (* 1 = 5.28735 loss)
I0412 13:02:46.598412  6895 sgd_solver.cpp:105] Iteration 1860, lr = 0.00691813
I0412 13:02:51.269163  6895 solver.cpp:218] Iteration 1872 (2.56928 iter/s, 4.67057s/12 iters), loss = 5.27063
I0412 13:02:51.269223  6895 solver.cpp:237]     Train net output #0: loss = 5.27063 (* 1 = 5.27063 loss)
I0412 13:02:51.269237  6895 sgd_solver.cpp:105] Iteration 1872, lr = 0.0069017
I0412 13:02:55.984100  6895 solver.cpp:218] Iteration 1884 (2.54523 iter/s, 4.7147s/12 iters), loss = 5.28331
I0412 13:02:55.984143  6895 solver.cpp:237]     Train net output #0: loss = 5.28331 (* 1 = 5.28331 loss)
I0412 13:02:55.984151  6895 sgd_solver.cpp:105] Iteration 1884, lr = 0.00688532
I0412 13:03:00.861975  6895 solver.cpp:218] Iteration 1896 (2.46022 iter/s, 4.87762s/12 iters), loss = 5.26893
I0412 13:03:00.862031  6895 solver.cpp:237]     Train net output #0: loss = 5.26893 (* 1 = 5.26893 loss)
I0412 13:03:00.862044  6895 sgd_solver.cpp:105] Iteration 1896, lr = 0.00686897
I0412 13:03:05.654886  6895 solver.cpp:218] Iteration 1908 (2.50383 iter/s, 4.79266s/12 iters), loss = 5.28856
I0412 13:03:05.655015  6895 solver.cpp:237]     Train net output #0: loss = 5.28856 (* 1 = 5.28856 loss)
I0412 13:03:05.655025  6895 sgd_solver.cpp:105] Iteration 1908, lr = 0.00685266
I0412 13:03:10.404692  6895 solver.cpp:218] Iteration 1920 (2.52659 iter/s, 4.74949s/12 iters), loss = 5.27268
I0412 13:03:10.404733  6895 solver.cpp:237]     Train net output #0: loss = 5.27268 (* 1 = 5.27268 loss)
I0412 13:03:10.404742  6895 sgd_solver.cpp:105] Iteration 1920, lr = 0.00683639
I0412 13:03:10.722687  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:03:15.227334  6895 solver.cpp:218] Iteration 1932 (2.48838 iter/s, 4.82241s/12 iters), loss = 5.28533
I0412 13:03:15.227383  6895 solver.cpp:237]     Train net output #0: loss = 5.28533 (* 1 = 5.28533 loss)
I0412 13:03:15.227396  6895 sgd_solver.cpp:105] Iteration 1932, lr = 0.00682016
I0412 13:03:17.190949  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1938.caffemodel
I0412 13:03:20.602068  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1938.solverstate
I0412 13:03:21.770781  6895 solver.cpp:330] Iteration 1938, Testing net (#0)
I0412 13:03:21.770804  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:03:25.460532  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:03:26.262663  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:03:26.262710  6895 solver.cpp:397]     Test net output #1: loss = 5.28592 (* 1 = 5.28592 loss)
I0412 13:03:27.830073  6895 solver.cpp:218] Iteration 1944 (0.952213 iter/s, 12.6022s/12 iters), loss = 5.2659
I0412 13:03:27.830129  6895 solver.cpp:237]     Train net output #0: loss = 5.2659 (* 1 = 5.2659 loss)
I0412 13:03:27.830142  6895 sgd_solver.cpp:105] Iteration 1944, lr = 0.00680397
I0412 13:03:32.245981  6895 solver.cpp:218] Iteration 1956 (2.71759 iter/s, 4.41567s/12 iters), loss = 5.28476
I0412 13:03:32.246026  6895 solver.cpp:237]     Train net output #0: loss = 5.28476 (* 1 = 5.28476 loss)
I0412 13:03:32.246037  6895 sgd_solver.cpp:105] Iteration 1956, lr = 0.00678782
I0412 13:03:37.053037  6895 solver.cpp:218] Iteration 1968 (2.49645 iter/s, 4.80682s/12 iters), loss = 5.28258
I0412 13:03:37.053158  6895 solver.cpp:237]     Train net output #0: loss = 5.28258 (* 1 = 5.28258 loss)
I0412 13:03:37.053169  6895 sgd_solver.cpp:105] Iteration 1968, lr = 0.0067717
I0412 13:03:41.965757  6895 solver.cpp:218] Iteration 1980 (2.44279 iter/s, 4.91241s/12 iters), loss = 5.25556
I0412 13:03:41.965813  6895 solver.cpp:237]     Train net output #0: loss = 5.25556 (* 1 = 5.25556 loss)
I0412 13:03:41.965828  6895 sgd_solver.cpp:105] Iteration 1980, lr = 0.00675562
I0412 13:03:46.679632  6895 solver.cpp:218] Iteration 1992 (2.54581 iter/s, 4.71363s/12 iters), loss = 5.28419
I0412 13:03:46.679692  6895 solver.cpp:237]     Train net output #0: loss = 5.28419 (* 1 = 5.28419 loss)
I0412 13:03:46.679704  6895 sgd_solver.cpp:105] Iteration 1992, lr = 0.00673958
I0412 13:03:51.496825  6895 solver.cpp:218] Iteration 2004 (2.4912 iter/s, 4.81695s/12 iters), loss = 5.27435
I0412 13:03:51.496870  6895 solver.cpp:237]     Train net output #0: loss = 5.27435 (* 1 = 5.27435 loss)
I0412 13:03:51.496877  6895 sgd_solver.cpp:105] Iteration 2004, lr = 0.00672358
I0412 13:03:56.444203  6895 solver.cpp:218] Iteration 2016 (2.42565 iter/s, 4.94714s/12 iters), loss = 5.25626
I0412 13:03:56.444247  6895 solver.cpp:237]     Train net output #0: loss = 5.25626 (* 1 = 5.25626 loss)
I0412 13:03:56.444255  6895 sgd_solver.cpp:105] Iteration 2016, lr = 0.00670762
I0412 13:03:58.827412  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:04:01.244678  6895 solver.cpp:218] Iteration 2028 (2.49987 iter/s, 4.80024s/12 iters), loss = 5.27435
I0412 13:04:01.244729  6895 solver.cpp:237]     Train net output #0: loss = 5.27435 (* 1 = 5.27435 loss)
I0412 13:04:01.244740  6895 sgd_solver.cpp:105] Iteration 2028, lr = 0.00669169
I0412 13:04:05.672617  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2040.caffemodel
I0412 13:04:07.283316  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2040.solverstate
I0412 13:04:08.455230  6895 solver.cpp:330] Iteration 2040, Testing net (#0)
I0412 13:04:08.455252  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:04:12.127408  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:04:12.955099  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 13:04:12.955150  6895 solver.cpp:397]     Test net output #1: loss = 5.2858 (* 1 = 5.2858 loss)
I0412 13:04:13.037781  6895 solver.cpp:218] Iteration 2040 (1.01759 iter/s, 11.7926s/12 iters), loss = 5.27988
I0412 13:04:13.037842  6895 solver.cpp:237]     Train net output #0: loss = 5.27988 (* 1 = 5.27988 loss)
I0412 13:04:13.037854  6895 sgd_solver.cpp:105] Iteration 2040, lr = 0.00667581
I0412 13:04:17.013196  6895 solver.cpp:218] Iteration 2052 (3.01872 iter/s, 3.97519s/12 iters), loss = 5.28716
I0412 13:04:17.013262  6895 solver.cpp:237]     Train net output #0: loss = 5.28716 (* 1 = 5.28716 loss)
I0412 13:04:17.013274  6895 sgd_solver.cpp:105] Iteration 2052, lr = 0.00665996
I0412 13:04:18.196627  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:04:21.871817  6895 solver.cpp:218] Iteration 2064 (2.46996 iter/s, 4.85837s/12 iters), loss = 5.28015
I0412 13:04:21.871867  6895 solver.cpp:237]     Train net output #0: loss = 5.28015 (* 1 = 5.28015 loss)
I0412 13:04:21.871879  6895 sgd_solver.cpp:105] Iteration 2064, lr = 0.00664414
I0412 13:04:26.709221  6895 solver.cpp:218] Iteration 2076 (2.48079 iter/s, 4.83716s/12 iters), loss = 5.27821
I0412 13:04:26.709276  6895 solver.cpp:237]     Train net output #0: loss = 5.27821 (* 1 = 5.27821 loss)
I0412 13:04:26.709288  6895 sgd_solver.cpp:105] Iteration 2076, lr = 0.00662837
I0412 13:04:31.554461  6895 solver.cpp:218] Iteration 2088 (2.47678 iter/s, 4.845s/12 iters), loss = 5.27327
I0412 13:04:31.554512  6895 solver.cpp:237]     Train net output #0: loss = 5.27327 (* 1 = 5.27327 loss)
I0412 13:04:31.554524  6895 sgd_solver.cpp:105] Iteration 2088, lr = 0.00661263
I0412 13:04:36.500164  6895 solver.cpp:218] Iteration 2100 (2.42647 iter/s, 4.94546s/12 iters), loss = 5.27263
I0412 13:04:36.500221  6895 solver.cpp:237]     Train net output #0: loss = 5.27263 (* 1 = 5.27263 loss)
I0412 13:04:36.500233  6895 sgd_solver.cpp:105] Iteration 2100, lr = 0.00659693
I0412 13:04:41.345945  6895 solver.cpp:218] Iteration 2112 (2.47651 iter/s, 4.84554s/12 iters), loss = 5.27834
I0412 13:04:41.346065  6895 solver.cpp:237]     Train net output #0: loss = 5.27834 (* 1 = 5.27834 loss)
I0412 13:04:41.346078  6895 sgd_solver.cpp:105] Iteration 2112, lr = 0.00658127
I0412 13:04:45.764796  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:04:46.090046  6895 solver.cpp:218] Iteration 2124 (2.52962 iter/s, 4.7438s/12 iters), loss = 5.2596
I0412 13:04:46.090096  6895 solver.cpp:237]     Train net output #0: loss = 5.2596 (* 1 = 5.2596 loss)
I0412 13:04:46.090106  6895 sgd_solver.cpp:105] Iteration 2124, lr = 0.00656564
I0412 13:04:50.827495  6895 solver.cpp:218] Iteration 2136 (2.53313 iter/s, 4.73721s/12 iters), loss = 5.276
I0412 13:04:50.827539  6895 solver.cpp:237]     Train net output #0: loss = 5.276 (* 1 = 5.276 loss)
I0412 13:04:50.827549  6895 sgd_solver.cpp:105] Iteration 2136, lr = 0.00655006
I0412 13:04:52.850210  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2142.caffemodel
I0412 13:04:54.409541  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2142.solverstate
I0412 13:04:55.580611  6895 solver.cpp:330] Iteration 2142, Testing net (#0)
I0412 13:04:55.580636  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:04:59.068666  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:04:59.929448  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:04:59.929487  6895 solver.cpp:397]     Test net output #1: loss = 5.28569 (* 1 = 5.28569 loss)
I0412 13:05:01.721484  6895 solver.cpp:218] Iteration 2148 (1.10157 iter/s, 10.8935s/12 iters), loss = 5.28234
I0412 13:05:01.721536  6895 solver.cpp:237]     Train net output #0: loss = 5.28234 (* 1 = 5.28234 loss)
I0412 13:05:01.721547  6895 sgd_solver.cpp:105] Iteration 2148, lr = 0.00653451
I0412 13:05:06.570394  6895 solver.cpp:218] Iteration 2160 (2.47491 iter/s, 4.84867s/12 iters), loss = 5.2876
I0412 13:05:06.570446  6895 solver.cpp:237]     Train net output #0: loss = 5.2876 (* 1 = 5.2876 loss)
I0412 13:05:06.570457  6895 sgd_solver.cpp:105] Iteration 2160, lr = 0.00651899
I0412 13:05:11.641263  6895 solver.cpp:218] Iteration 2172 (2.36658 iter/s, 5.07061s/12 iters), loss = 5.27966
I0412 13:05:11.641369  6895 solver.cpp:237]     Train net output #0: loss = 5.27966 (* 1 = 5.27966 loss)
I0412 13:05:11.641379  6895 sgd_solver.cpp:105] Iteration 2172, lr = 0.00650351
I0412 13:05:16.641659  6895 solver.cpp:218] Iteration 2184 (2.39995 iter/s, 5.0001s/12 iters), loss = 5.26912
I0412 13:05:16.641710  6895 solver.cpp:237]     Train net output #0: loss = 5.26912 (* 1 = 5.26912 loss)
I0412 13:05:16.641721  6895 sgd_solver.cpp:105] Iteration 2184, lr = 0.00648807
I0412 13:05:21.473765  6895 solver.cpp:218] Iteration 2196 (2.48351 iter/s, 4.83187s/12 iters), loss = 5.25495
I0412 13:05:21.473816  6895 solver.cpp:237]     Train net output #0: loss = 5.25495 (* 1 = 5.25495 loss)
I0412 13:05:21.473829  6895 sgd_solver.cpp:105] Iteration 2196, lr = 0.00647267
I0412 13:05:26.509009  6895 solver.cpp:218] Iteration 2208 (2.38332 iter/s, 5.035s/12 iters), loss = 5.27244
I0412 13:05:26.509061  6895 solver.cpp:237]     Train net output #0: loss = 5.27244 (* 1 = 5.27244 loss)
I0412 13:05:26.509073  6895 sgd_solver.cpp:105] Iteration 2208, lr = 0.0064573
I0412 13:05:31.397472  6895 solver.cpp:218] Iteration 2220 (2.45488 iter/s, 4.88822s/12 iters), loss = 5.27864
I0412 13:05:31.397524  6895 solver.cpp:237]     Train net output #0: loss = 5.27864 (* 1 = 5.27864 loss)
I0412 13:05:31.397536  6895 sgd_solver.cpp:105] Iteration 2220, lr = 0.00644197
I0412 13:05:33.161717  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:05:36.225481  6895 solver.cpp:218] Iteration 2232 (2.48562 iter/s, 4.82777s/12 iters), loss = 5.28784
I0412 13:05:36.225533  6895 solver.cpp:237]     Train net output #0: loss = 5.28784 (* 1 = 5.28784 loss)
I0412 13:05:36.225543  6895 sgd_solver.cpp:105] Iteration 2232, lr = 0.00642668
I0412 13:05:40.629791  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2244.caffemodel
I0412 13:05:43.810258  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2244.solverstate
I0412 13:05:45.005833  6895 solver.cpp:330] Iteration 2244, Testing net (#0)
I0412 13:05:45.005862  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:05:48.656343  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:05:49.563421  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:05:49.563475  6895 solver.cpp:397]     Test net output #1: loss = 5.28564 (* 1 = 5.28564 loss)
I0412 13:05:49.646925  6895 solver.cpp:218] Iteration 2244 (0.894128 iter/s, 13.4209s/12 iters), loss = 5.28253
I0412 13:05:49.646975  6895 solver.cpp:237]     Train net output #0: loss = 5.28253 (* 1 = 5.28253 loss)
I0412 13:05:49.646986  6895 sgd_solver.cpp:105] Iteration 2244, lr = 0.00641142
I0412 13:05:53.787668  6895 solver.cpp:218] Iteration 2256 (2.89818 iter/s, 4.14053s/12 iters), loss = 5.24433
I0412 13:05:53.787714  6895 solver.cpp:237]     Train net output #0: loss = 5.24433 (* 1 = 5.24433 loss)
I0412 13:05:53.787724  6895 sgd_solver.cpp:105] Iteration 2256, lr = 0.0063962
I0412 13:05:58.592062  6895 solver.cpp:218] Iteration 2268 (2.49784 iter/s, 4.80416s/12 iters), loss = 5.28682
I0412 13:05:58.592108  6895 solver.cpp:237]     Train net output #0: loss = 5.28682 (* 1 = 5.28682 loss)
I0412 13:05:58.592115  6895 sgd_solver.cpp:105] Iteration 2268, lr = 0.00638101
I0412 13:06:03.496592  6895 solver.cpp:218] Iteration 2280 (2.44684 iter/s, 4.90429s/12 iters), loss = 5.25681
I0412 13:06:03.496641  6895 solver.cpp:237]     Train net output #0: loss = 5.25681 (* 1 = 5.25681 loss)
I0412 13:06:03.496651  6895 sgd_solver.cpp:105] Iteration 2280, lr = 0.00636586
I0412 13:06:08.211678  6895 solver.cpp:218] Iteration 2292 (2.54515 iter/s, 4.71485s/12 iters), loss = 5.27078
I0412 13:06:08.211719  6895 solver.cpp:237]     Train net output #0: loss = 5.27078 (* 1 = 5.27078 loss)
I0412 13:06:08.211728  6895 sgd_solver.cpp:105] Iteration 2292, lr = 0.00635075
I0412 13:06:13.134305  6895 solver.cpp:218] Iteration 2304 (2.43784 iter/s, 4.92239s/12 iters), loss = 5.26999
I0412 13:06:13.134364  6895 solver.cpp:237]     Train net output #0: loss = 5.26999 (* 1 = 5.26999 loss)
I0412 13:06:13.134378  6895 sgd_solver.cpp:105] Iteration 2304, lr = 0.00633567
I0412 13:06:17.931043  6895 solver.cpp:218] Iteration 2316 (2.50183 iter/s, 4.79649s/12 iters), loss = 5.26945
I0412 13:06:17.931177  6895 solver.cpp:237]     Train net output #0: loss = 5.26945 (* 1 = 5.26945 loss)
I0412 13:06:17.931190  6895 sgd_solver.cpp:105] Iteration 2316, lr = 0.00632063
I0412 13:06:21.924508  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:06:23.098049  6895 solver.cpp:218] Iteration 2328 (2.32258 iter/s, 5.16667s/12 iters), loss = 5.26007
I0412 13:06:23.098104  6895 solver.cpp:237]     Train net output #0: loss = 5.26007 (* 1 = 5.26007 loss)
I0412 13:06:23.098117  6895 sgd_solver.cpp:105] Iteration 2328, lr = 0.00630562
I0412 13:06:28.002854  6895 solver.cpp:218] Iteration 2340 (2.4467 iter/s, 4.90456s/12 iters), loss = 5.28798
I0412 13:06:28.002904  6895 solver.cpp:237]     Train net output #0: loss = 5.28798 (* 1 = 5.28798 loss)
I0412 13:06:28.002914  6895 sgd_solver.cpp:105] Iteration 2340, lr = 0.00629065
I0412 13:06:30.000631  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2346.caffemodel
I0412 13:06:32.053277  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2346.solverstate
I0412 13:06:38.345288  6895 solver.cpp:330] Iteration 2346, Testing net (#0)
I0412 13:06:38.345316  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:06:41.844035  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:06:42.798996  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:06:42.799038  6895 solver.cpp:397]     Test net output #1: loss = 5.28595 (* 1 = 5.28595 loss)
I0412 13:06:44.465377  6895 solver.cpp:218] Iteration 2352 (0.728958 iter/s, 16.4619s/12 iters), loss = 5.25958
I0412 13:06:44.465436  6895 solver.cpp:237]     Train net output #0: loss = 5.25958 (* 1 = 5.25958 loss)
I0412 13:06:44.465448  6895 sgd_solver.cpp:105] Iteration 2352, lr = 0.00627571
I0412 13:06:49.180979  6895 solver.cpp:218] Iteration 2364 (2.54488 iter/s, 4.71535s/12 iters), loss = 5.30477
I0412 13:06:49.181118  6895 solver.cpp:237]     Train net output #0: loss = 5.30477 (* 1 = 5.30477 loss)
I0412 13:06:49.181129  6895 sgd_solver.cpp:105] Iteration 2364, lr = 0.00626081
I0412 13:06:54.085124  6895 solver.cpp:218] Iteration 2376 (2.44707 iter/s, 4.90382s/12 iters), loss = 5.26193
I0412 13:06:54.085183  6895 solver.cpp:237]     Train net output #0: loss = 5.26193 (* 1 = 5.26193 loss)
I0412 13:06:54.085198  6895 sgd_solver.cpp:105] Iteration 2376, lr = 0.00624595
I0412 13:06:58.979809  6895 solver.cpp:218] Iteration 2388 (2.45176 iter/s, 4.89443s/12 iters), loss = 5.27815
I0412 13:06:58.979863  6895 solver.cpp:237]     Train net output #0: loss = 5.27815 (* 1 = 5.27815 loss)
I0412 13:06:58.979874  6895 sgd_solver.cpp:105] Iteration 2388, lr = 0.00623112
I0412 13:07:03.996178  6895 solver.cpp:218] Iteration 2400 (2.39229 iter/s, 5.01612s/12 iters), loss = 5.28382
I0412 13:07:03.996230  6895 solver.cpp:237]     Train net output #0: loss = 5.28382 (* 1 = 5.28382 loss)
I0412 13:07:03.996241  6895 sgd_solver.cpp:105] Iteration 2400, lr = 0.00621633
I0412 13:07:09.274855  6895 solver.cpp:218] Iteration 2412 (2.27341 iter/s, 5.27842s/12 iters), loss = 5.27336
I0412 13:07:09.274911  6895 solver.cpp:237]     Train net output #0: loss = 5.27336 (* 1 = 5.27336 loss)
I0412 13:07:09.274924  6895 sgd_solver.cpp:105] Iteration 2412, lr = 0.00620157
I0412 13:07:14.138849  6895 solver.cpp:218] Iteration 2424 (2.46723 iter/s, 4.86375s/12 iters), loss = 5.27805
I0412 13:07:14.138891  6895 solver.cpp:237]     Train net output #0: loss = 5.27805 (* 1 = 5.27805 loss)
I0412 13:07:14.138900  6895 sgd_solver.cpp:105] Iteration 2424, lr = 0.00618684
I0412 13:07:15.217376  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:07:19.046002  6895 solver.cpp:218] Iteration 2436 (2.44555 iter/s, 4.90688s/12 iters), loss = 5.28455
I0412 13:07:19.046046  6895 solver.cpp:237]     Train net output #0: loss = 5.28455 (* 1 = 5.28455 loss)
I0412 13:07:19.046054  6895 sgd_solver.cpp:105] Iteration 2436, lr = 0.00617215
I0412 13:07:23.482159  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2448.caffemodel
I0412 13:07:26.440433  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2448.solverstate
I0412 13:07:28.254940  6895 solver.cpp:330] Iteration 2448, Testing net (#0)
I0412 13:07:28.254971  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:07:31.846019  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:07:32.977350  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:07:32.977401  6895 solver.cpp:397]     Test net output #1: loss = 5.28538 (* 1 = 5.28538 loss)
I0412 13:07:33.060708  6895 solver.cpp:218] Iteration 2448 (0.856278 iter/s, 14.0141s/12 iters), loss = 5.26208
I0412 13:07:33.060761  6895 solver.cpp:237]     Train net output #0: loss = 5.26208 (* 1 = 5.26208 loss)
I0412 13:07:33.060772  6895 sgd_solver.cpp:105] Iteration 2448, lr = 0.0061575
I0412 13:07:37.304991  6895 solver.cpp:218] Iteration 2460 (2.82748 iter/s, 4.24406s/12 iters), loss = 5.26289
I0412 13:07:37.305040  6895 solver.cpp:237]     Train net output #0: loss = 5.26289 (* 1 = 5.26289 loss)
I0412 13:07:37.305050  6895 sgd_solver.cpp:105] Iteration 2460, lr = 0.00614288
I0412 13:07:42.038038  6895 solver.cpp:218] Iteration 2472 (2.53549 iter/s, 4.73281s/12 iters), loss = 5.27272
I0412 13:07:42.038092  6895 solver.cpp:237]     Train net output #0: loss = 5.27272 (* 1 = 5.27272 loss)
I0412 13:07:42.038105  6895 sgd_solver.cpp:105] Iteration 2472, lr = 0.0061283
I0412 13:07:46.809478  6895 solver.cpp:218] Iteration 2484 (2.51509 iter/s, 4.77119s/12 iters), loss = 5.2766
I0412 13:07:46.809536  6895 solver.cpp:237]     Train net output #0: loss = 5.2766 (* 1 = 5.2766 loss)
I0412 13:07:46.809548  6895 sgd_solver.cpp:105] Iteration 2484, lr = 0.00611375
I0412 13:07:51.666678  6895 solver.cpp:218] Iteration 2496 (2.47068 iter/s, 4.85696s/12 iters), loss = 5.27292
I0412 13:07:51.666724  6895 solver.cpp:237]     Train net output #0: loss = 5.27292 (* 1 = 5.27292 loss)
I0412 13:07:51.666733  6895 sgd_solver.cpp:105] Iteration 2496, lr = 0.00609923
I0412 13:07:56.479841  6895 solver.cpp:218] Iteration 2508 (2.49328 iter/s, 4.81293s/12 iters), loss = 5.29029
I0412 13:07:56.479974  6895 solver.cpp:237]     Train net output #0: loss = 5.29029 (* 1 = 5.29029 loss)
I0412 13:07:56.479986  6895 sgd_solver.cpp:105] Iteration 2508, lr = 0.00608475
I0412 13:08:01.358610  6895 solver.cpp:218] Iteration 2520 (2.4598 iter/s, 4.87845s/12 iters), loss = 5.27947
I0412 13:08:01.358655  6895 solver.cpp:237]     Train net output #0: loss = 5.27947 (* 1 = 5.27947 loss)
I0412 13:08:01.358665  6895 sgd_solver.cpp:105] Iteration 2520, lr = 0.0060703
I0412 13:08:04.538448  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:08:06.255251  6895 solver.cpp:218] Iteration 2532 (2.45078 iter/s, 4.8964s/12 iters), loss = 5.28117
I0412 13:08:06.255304  6895 solver.cpp:237]     Train net output #0: loss = 5.28117 (* 1 = 5.28117 loss)
I0412 13:08:06.255316  6895 sgd_solver.cpp:105] Iteration 2532, lr = 0.00605589
I0412 13:08:10.997758  6895 solver.cpp:218] Iteration 2544 (2.53044 iter/s, 4.74227s/12 iters), loss = 5.27635
I0412 13:08:10.997808  6895 solver.cpp:237]     Train net output #0: loss = 5.27635 (* 1 = 5.27635 loss)
I0412 13:08:10.997819  6895 sgd_solver.cpp:105] Iteration 2544, lr = 0.00604151
I0412 13:08:13.016981  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2550.caffemodel
I0412 13:08:19.817821  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2550.solverstate
I0412 13:08:24.844863  6895 solver.cpp:330] Iteration 2550, Testing net (#0)
I0412 13:08:24.844893  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:08:28.230868  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:08:29.246942  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:08:29.246986  6895 solver.cpp:397]     Test net output #1: loss = 5.28554 (* 1 = 5.28554 loss)
I0412 13:08:31.083899  6895 solver.cpp:218] Iteration 2556 (0.59745 iter/s, 20.0853s/12 iters), loss = 5.28406
I0412 13:08:31.083945  6895 solver.cpp:237]     Train net output #0: loss = 5.28406 (* 1 = 5.28406 loss)
I0412 13:08:31.083953  6895 sgd_solver.cpp:105] Iteration 2556, lr = 0.00602717
I0412 13:08:36.206233  6895 solver.cpp:218] Iteration 2568 (2.3428 iter/s, 5.12208s/12 iters), loss = 5.28937
I0412 13:08:36.206281  6895 solver.cpp:237]     Train net output #0: loss = 5.28937 (* 1 = 5.28937 loss)
I0412 13:08:36.206290  6895 sgd_solver.cpp:105] Iteration 2568, lr = 0.00601286
I0412 13:08:40.999626  6895 solver.cpp:218] Iteration 2580 (2.50357 iter/s, 4.79315s/12 iters), loss = 5.27495
I0412 13:08:40.999687  6895 solver.cpp:237]     Train net output #0: loss = 5.27495 (* 1 = 5.27495 loss)
I0412 13:08:40.999699  6895 sgd_solver.cpp:105] Iteration 2580, lr = 0.00599858
I0412 13:08:46.174960  6895 solver.cpp:218] Iteration 2592 (2.31881 iter/s, 5.17507s/12 iters), loss = 5.28511
I0412 13:08:46.175012  6895 solver.cpp:237]     Train net output #0: loss = 5.28511 (* 1 = 5.28511 loss)
I0412 13:08:46.175024  6895 sgd_solver.cpp:105] Iteration 2592, lr = 0.00598434
I0412 13:08:50.960772  6895 solver.cpp:218] Iteration 2604 (2.50754 iter/s, 4.78557s/12 iters), loss = 5.25661
I0412 13:08:50.960820  6895 solver.cpp:237]     Train net output #0: loss = 5.25661 (* 1 = 5.25661 loss)
I0412 13:08:50.960829  6895 sgd_solver.cpp:105] Iteration 2604, lr = 0.00597013
I0412 13:08:55.652348  6895 solver.cpp:218] Iteration 2616 (2.5579 iter/s, 4.69134s/12 iters), loss = 5.2783
I0412 13:08:55.652392  6895 solver.cpp:237]     Train net output #0: loss = 5.2783 (* 1 = 5.2783 loss)
I0412 13:08:55.652401  6895 sgd_solver.cpp:105] Iteration 2616, lr = 0.00595596
I0412 13:09:00.533974  6895 solver.cpp:218] Iteration 2628 (2.45832 iter/s, 4.88138s/12 iters), loss = 5.28085
I0412 13:09:00.534067  6895 solver.cpp:237]     Train net output #0: loss = 5.28085 (* 1 = 5.28085 loss)
I0412 13:09:00.534081  6895 sgd_solver.cpp:105] Iteration 2628, lr = 0.00594182
I0412 13:09:00.920794  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:09:05.570259  6895 solver.cpp:218] Iteration 2640 (2.38284 iter/s, 5.036s/12 iters), loss = 5.28327
I0412 13:09:05.570309  6895 solver.cpp:237]     Train net output #0: loss = 5.28327 (* 1 = 5.28327 loss)
I0412 13:09:05.570320  6895 sgd_solver.cpp:105] Iteration 2640, lr = 0.00592771
I0412 13:09:10.160691  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2652.caffemodel
I0412 13:09:11.707106  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2652.solverstate
I0412 13:09:13.964583  6895 solver.cpp:330] Iteration 2652, Testing net (#0)
I0412 13:09:13.964612  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:09:17.637143  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:09:18.688210  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:09:18.688239  6895 solver.cpp:397]     Test net output #1: loss = 5.28578 (* 1 = 5.28578 loss)
I0412 13:09:18.771143  6895 solver.cpp:218] Iteration 2652 (0.909067 iter/s, 13.2003s/12 iters), loss = 5.26996
I0412 13:09:18.771184  6895 solver.cpp:237]     Train net output #0: loss = 5.26996 (* 1 = 5.26996 loss)
I0412 13:09:18.771193  6895 sgd_solver.cpp:105] Iteration 2652, lr = 0.00591364
I0412 13:09:22.796289  6895 solver.cpp:218] Iteration 2664 (2.98141 iter/s, 4.02494s/12 iters), loss = 5.28087
I0412 13:09:22.796334  6895 solver.cpp:237]     Train net output #0: loss = 5.28087 (* 1 = 5.28087 loss)
I0412 13:09:22.796345  6895 sgd_solver.cpp:105] Iteration 2664, lr = 0.0058996
I0412 13:09:27.562111  6895 solver.cpp:218] Iteration 2676 (2.51805 iter/s, 4.76559s/12 iters), loss = 5.27199
I0412 13:09:27.562155  6895 solver.cpp:237]     Train net output #0: loss = 5.27199 (* 1 = 5.27199 loss)
I0412 13:09:27.562165  6895 sgd_solver.cpp:105] Iteration 2676, lr = 0.00588559
I0412 13:09:32.442169  6895 solver.cpp:218] Iteration 2688 (2.45911 iter/s, 4.87982s/12 iters), loss = 5.26433
I0412 13:09:32.442309  6895 solver.cpp:237]     Train net output #0: loss = 5.26433 (* 1 = 5.26433 loss)
I0412 13:09:32.442322  6895 sgd_solver.cpp:105] Iteration 2688, lr = 0.00587162
I0412 13:09:37.293555  6895 solver.cpp:218] Iteration 2700 (2.47369 iter/s, 4.85106s/12 iters), loss = 5.28082
I0412 13:09:37.293608  6895 solver.cpp:237]     Train net output #0: loss = 5.28082 (* 1 = 5.28082 loss)
I0412 13:09:37.293620  6895 sgd_solver.cpp:105] Iteration 2700, lr = 0.00585768
I0412 13:09:42.176746  6895 solver.cpp:218] Iteration 2712 (2.45753 iter/s, 4.88295s/12 iters), loss = 5.28254
I0412 13:09:42.176795  6895 solver.cpp:237]     Train net output #0: loss = 5.28254 (* 1 = 5.28254 loss)
I0412 13:09:42.176807  6895 sgd_solver.cpp:105] Iteration 2712, lr = 0.00584377
I0412 13:09:47.076584  6895 solver.cpp:218] Iteration 2724 (2.44918 iter/s, 4.8996s/12 iters), loss = 5.26058
I0412 13:09:47.076635  6895 solver.cpp:237]     Train net output #0: loss = 5.26058 (* 1 = 5.26058 loss)
I0412 13:09:47.076645  6895 sgd_solver.cpp:105] Iteration 2724, lr = 0.0058299
I0412 13:09:49.822789  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:09:52.332798  6895 solver.cpp:218] Iteration 2736 (2.28312 iter/s, 5.25596s/12 iters), loss = 5.28527
I0412 13:09:52.332846  6895 solver.cpp:237]     Train net output #0: loss = 5.28527 (* 1 = 5.28527 loss)
I0412 13:09:52.332856  6895 sgd_solver.cpp:105] Iteration 2736, lr = 0.00581605
I0412 13:09:57.108518  6895 solver.cpp:218] Iteration 2748 (2.51284 iter/s, 4.77548s/12 iters), loss = 5.27622
I0412 13:09:57.108579  6895 solver.cpp:237]     Train net output #0: loss = 5.27622 (* 1 = 5.27622 loss)
I0412 13:09:57.108592  6895 sgd_solver.cpp:105] Iteration 2748, lr = 0.00580225
I0412 13:09:59.038751  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2754.caffemodel
I0412 13:10:00.541721  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2754.solverstate
I0412 13:10:01.708606  6895 solver.cpp:330] Iteration 2754, Testing net (#0)
I0412 13:10:01.708629  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:10:04.742636  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:10:05.067154  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:10:06.169993  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 13:10:06.170043  6895 solver.cpp:397]     Test net output #1: loss = 5.28567 (* 1 = 5.28567 loss)
I0412 13:10:08.166734  6895 solver.cpp:218] Iteration 2760 (1.08521 iter/s, 11.0577s/12 iters), loss = 5.28099
I0412 13:10:08.166779  6895 solver.cpp:237]     Train net output #0: loss = 5.28099 (* 1 = 5.28099 loss)
I0412 13:10:08.166788  6895 sgd_solver.cpp:105] Iteration 2760, lr = 0.00578847
I0412 13:10:12.925983  6895 solver.cpp:218] Iteration 2772 (2.52154 iter/s, 4.759s/12 iters), loss = 5.27795
I0412 13:10:12.926036  6895 solver.cpp:237]     Train net output #0: loss = 5.27795 (* 1 = 5.27795 loss)
I0412 13:10:12.926049  6895 sgd_solver.cpp:105] Iteration 2772, lr = 0.00577473
I0412 13:10:17.727275  6895 solver.cpp:218] Iteration 2784 (2.49945 iter/s, 4.80105s/12 iters), loss = 5.28562
I0412 13:10:17.727330  6895 solver.cpp:237]     Train net output #0: loss = 5.28562 (* 1 = 5.28562 loss)
I0412 13:10:17.727344  6895 sgd_solver.cpp:105] Iteration 2784, lr = 0.00576102
I0412 13:10:22.465240  6895 solver.cpp:218] Iteration 2796 (2.53286 iter/s, 4.73772s/12 iters), loss = 5.26863
I0412 13:10:22.465296  6895 solver.cpp:237]     Train net output #0: loss = 5.26863 (* 1 = 5.26863 loss)
I0412 13:10:22.465307  6895 sgd_solver.cpp:105] Iteration 2796, lr = 0.00574734
I0412 13:10:27.313776  6895 solver.cpp:218] Iteration 2808 (2.4751 iter/s, 4.84829s/12 iters), loss = 5.26685
I0412 13:10:27.313838  6895 solver.cpp:237]     Train net output #0: loss = 5.26685 (* 1 = 5.26685 loss)
I0412 13:10:27.313853  6895 sgd_solver.cpp:105] Iteration 2808, lr = 0.00573369
I0412 13:10:31.999377  6895 solver.cpp:218] Iteration 2820 (2.56117 iter/s, 4.68535s/12 iters), loss = 5.27641
I0412 13:10:31.999433  6895 solver.cpp:237]     Train net output #0: loss = 5.27641 (* 1 = 5.27641 loss)
I0412 13:10:31.999444  6895 sgd_solver.cpp:105] Iteration 2820, lr = 0.00572008
I0412 13:10:36.552740  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:10:36.842155  6895 solver.cpp:218] Iteration 2832 (2.47804 iter/s, 4.84253s/12 iters), loss = 5.26032
I0412 13:10:36.842209  6895 solver.cpp:237]     Train net output #0: loss = 5.26032 (* 1 = 5.26032 loss)
I0412 13:10:36.842223  6895 sgd_solver.cpp:105] Iteration 2832, lr = 0.0057065
I0412 13:10:41.603636  6895 solver.cpp:218] Iteration 2844 (2.52035 iter/s, 4.76124s/12 iters), loss = 5.27054
I0412 13:10:41.603688  6895 solver.cpp:237]     Train net output #0: loss = 5.27054 (* 1 = 5.27054 loss)
I0412 13:10:41.603700  6895 sgd_solver.cpp:105] Iteration 2844, lr = 0.00569295
I0412 13:10:45.859833  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2856.caffemodel
I0412 13:10:49.115020  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2856.solverstate
I0412 13:10:51.676409  6895 solver.cpp:330] Iteration 2856, Testing net (#0)
I0412 13:10:51.676438  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:10:55.098178  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:10:56.234905  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:10:56.234961  6895 solver.cpp:397]     Test net output #1: loss = 5.28609 (* 1 = 5.28609 loss)
I0412 13:10:56.318023  6895 solver.cpp:218] Iteration 2856 (0.815562 iter/s, 14.7138s/12 iters), loss = 5.29319
I0412 13:10:56.318082  6895 solver.cpp:237]     Train net output #0: loss = 5.29319 (* 1 = 5.29319 loss)
I0412 13:10:56.318094  6895 sgd_solver.cpp:105] Iteration 2856, lr = 0.00567944
I0412 13:11:00.338742  6895 solver.cpp:218] Iteration 2868 (2.9847 iter/s, 4.0205s/12 iters), loss = 5.28292
I0412 13:11:00.338799  6895 solver.cpp:237]     Train net output #0: loss = 5.28292 (* 1 = 5.28292 loss)
I0412 13:11:00.338814  6895 sgd_solver.cpp:105] Iteration 2868, lr = 0.00566595
I0412 13:11:05.087682  6895 solver.cpp:218] Iteration 2880 (2.52701 iter/s, 4.74869s/12 iters), loss = 5.27799
I0412 13:11:05.087726  6895 solver.cpp:237]     Train net output #0: loss = 5.27799 (* 1 = 5.27799 loss)
I0412 13:11:05.087734  6895 sgd_solver.cpp:105] Iteration 2880, lr = 0.0056525
I0412 13:11:09.936295  6895 solver.cpp:218] Iteration 2892 (2.47506 iter/s, 4.84837s/12 iters), loss = 5.27522
I0412 13:11:09.936408  6895 solver.cpp:237]     Train net output #0: loss = 5.27522 (* 1 = 5.27522 loss)
I0412 13:11:09.936417  6895 sgd_solver.cpp:105] Iteration 2892, lr = 0.00563908
I0412 13:11:14.626628  6895 solver.cpp:218] Iteration 2904 (2.55862 iter/s, 4.69003s/12 iters), loss = 5.25393
I0412 13:11:14.626690  6895 solver.cpp:237]     Train net output #0: loss = 5.25393 (* 1 = 5.25393 loss)
I0412 13:11:14.626705  6895 sgd_solver.cpp:105] Iteration 2904, lr = 0.00562569
I0412 13:11:19.509881  6895 solver.cpp:218] Iteration 2916 (2.45751 iter/s, 4.883s/12 iters), loss = 5.27658
I0412 13:11:19.509932  6895 solver.cpp:237]     Train net output #0: loss = 5.27658 (* 1 = 5.27658 loss)
I0412 13:11:19.509943  6895 sgd_solver.cpp:105] Iteration 2916, lr = 0.00561233
I0412 13:11:24.473125  6895 solver.cpp:218] Iteration 2928 (2.41789 iter/s, 4.963s/12 iters), loss = 5.28563
I0412 13:11:24.473184  6895 solver.cpp:237]     Train net output #0: loss = 5.28563 (* 1 = 5.28563 loss)
I0412 13:11:24.473196  6895 sgd_solver.cpp:105] Iteration 2928, lr = 0.00559901
I0412 13:11:26.302491  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:11:29.285343  6895 solver.cpp:218] Iteration 2940 (2.49378 iter/s, 4.81197s/12 iters), loss = 5.28426
I0412 13:11:29.285392  6895 solver.cpp:237]     Train net output #0: loss = 5.28426 (* 1 = 5.28426 loss)
I0412 13:11:29.285403  6895 sgd_solver.cpp:105] Iteration 2940, lr = 0.00558572
I0412 13:11:34.299919  6895 solver.cpp:218] Iteration 2952 (2.39314 iter/s, 5.01433s/12 iters), loss = 5.28121
I0412 13:11:34.299958  6895 solver.cpp:237]     Train net output #0: loss = 5.28121 (* 1 = 5.28121 loss)
I0412 13:11:34.299968  6895 sgd_solver.cpp:105] Iteration 2952, lr = 0.00557245
I0412 13:11:36.270363  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2958.caffemodel
I0412 13:11:40.297288  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2958.solverstate
I0412 13:11:42.929410  6895 solver.cpp:330] Iteration 2958, Testing net (#0)
I0412 13:11:42.929436  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:11:46.192595  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:11:47.462484  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:11:47.462534  6895 solver.cpp:397]     Test net output #1: loss = 5.28578 (* 1 = 5.28578 loss)
I0412 13:11:49.362993  6895 solver.cpp:218] Iteration 2964 (0.796682 iter/s, 15.0625s/12 iters), loss = 5.24393
I0412 13:11:49.363042  6895 solver.cpp:237]     Train net output #0: loss = 5.24393 (* 1 = 5.24393 loss)
I0412 13:11:49.363052  6895 sgd_solver.cpp:105] Iteration 2964, lr = 0.00555922
I0412 13:11:54.168942  6895 solver.cpp:218] Iteration 2976 (2.49703 iter/s, 4.80571s/12 iters), loss = 5.28513
I0412 13:11:54.168987  6895 solver.cpp:237]     Train net output #0: loss = 5.28513 (* 1 = 5.28513 loss)
I0412 13:11:54.168994  6895 sgd_solver.cpp:105] Iteration 2976, lr = 0.00554603
I0412 13:11:58.883198  6895 solver.cpp:218] Iteration 2988 (2.5456 iter/s, 4.71402s/12 iters), loss = 5.26118
I0412 13:11:58.883263  6895 solver.cpp:237]     Train net output #0: loss = 5.26118 (* 1 = 5.26118 loss)
I0412 13:11:58.883277  6895 sgd_solver.cpp:105] Iteration 2988, lr = 0.00553286
I0412 13:12:03.543610  6895 solver.cpp:218] Iteration 3000 (2.57502 iter/s, 4.66016s/12 iters), loss = 5.27216
I0412 13:12:03.543666  6895 solver.cpp:237]     Train net output #0: loss = 5.27216 (* 1 = 5.27216 loss)
I0412 13:12:03.543678  6895 sgd_solver.cpp:105] Iteration 3000, lr = 0.00551972
I0412 13:12:08.350876  6895 solver.cpp:218] Iteration 3012 (2.49635 iter/s, 4.80703s/12 iters), loss = 5.27358
I0412 13:12:08.350924  6895 solver.cpp:237]     Train net output #0: loss = 5.27358 (* 1 = 5.27358 loss)
I0412 13:12:08.350937  6895 sgd_solver.cpp:105] Iteration 3012, lr = 0.00550662
I0412 13:12:13.285097  6895 solver.cpp:218] Iteration 3024 (2.43212 iter/s, 4.93397s/12 iters), loss = 5.26325
I0412 13:12:13.285259  6895 solver.cpp:237]     Train net output #0: loss = 5.26325 (* 1 = 5.26325 loss)
I0412 13:12:13.285274  6895 sgd_solver.cpp:105] Iteration 3024, lr = 0.00549354
I0412 13:12:17.053987  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:12:18.101215  6895 solver.cpp:218] Iteration 3036 (2.49181 iter/s, 4.81577s/12 iters), loss = 5.2603
I0412 13:12:18.101260  6895 solver.cpp:237]     Train net output #0: loss = 5.2603 (* 1 = 5.2603 loss)
I0412 13:12:18.101270  6895 sgd_solver.cpp:105] Iteration 3036, lr = 0.0054805
I0412 13:12:22.945914  6895 solver.cpp:218] Iteration 3048 (2.47706 iter/s, 4.84446s/12 iters), loss = 5.29349
I0412 13:12:22.945983  6895 solver.cpp:237]     Train net output #0: loss = 5.29349 (* 1 = 5.29349 loss)
I0412 13:12:22.945996  6895 sgd_solver.cpp:105] Iteration 3048, lr = 0.00546749
I0412 13:12:27.427120  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3060.caffemodel
I0412 13:12:31.743901  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3060.solverstate
I0412 13:12:34.616662  6895 solver.cpp:330] Iteration 3060, Testing net (#0)
I0412 13:12:34.616691  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:12:37.847096  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:12:39.058887  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 13:12:39.058938  6895 solver.cpp:397]     Test net output #1: loss = 5.28565 (* 1 = 5.28565 loss)
I0412 13:12:39.142338  6895 solver.cpp:218] Iteration 3060 (0.740935 iter/s, 16.1957s/12 iters), loss = 5.25967
I0412 13:12:39.142400  6895 solver.cpp:237]     Train net output #0: loss = 5.25967 (* 1 = 5.25967 loss)
I0412 13:12:39.142412  6895 sgd_solver.cpp:105] Iteration 3060, lr = 0.00545451
I0412 13:12:43.114531  6895 solver.cpp:218] Iteration 3072 (3.02117 iter/s, 3.97197s/12 iters), loss = 5.30707
I0412 13:12:43.114581  6895 solver.cpp:237]     Train net output #0: loss = 5.30707 (* 1 = 5.30707 loss)
I0412 13:12:43.114589  6895 sgd_solver.cpp:105] Iteration 3072, lr = 0.00544156
I0412 13:12:48.056016  6895 solver.cpp:218] Iteration 3084 (2.42855 iter/s, 4.94123s/12 iters), loss = 5.27359
I0412 13:12:48.056156  6895 solver.cpp:237]     Train net output #0: loss = 5.27359 (* 1 = 5.27359 loss)
I0412 13:12:48.056172  6895 sgd_solver.cpp:105] Iteration 3084, lr = 0.00542864
I0412 13:12:52.947224  6895 solver.cpp:218] Iteration 3096 (2.45355 iter/s, 4.89088s/12 iters), loss = 5.27309
I0412 13:12:52.947284  6895 solver.cpp:237]     Train net output #0: loss = 5.27309 (* 1 = 5.27309 loss)
I0412 13:12:52.947297  6895 sgd_solver.cpp:105] Iteration 3096, lr = 0.00541575
I0412 13:12:57.887270  6895 solver.cpp:218] Iteration 3108 (2.42925 iter/s, 4.9398s/12 iters), loss = 5.27804
I0412 13:12:57.887310  6895 solver.cpp:237]     Train net output #0: loss = 5.27804 (* 1 = 5.27804 loss)
I0412 13:12:57.887320  6895 sgd_solver.cpp:105] Iteration 3108, lr = 0.00540289
I0412 13:13:02.777675  6895 solver.cpp:218] Iteration 3120 (2.4539 iter/s, 4.89017s/12 iters), loss = 5.27157
I0412 13:13:02.777737  6895 solver.cpp:237]     Train net output #0: loss = 5.27157 (* 1 = 5.27157 loss)
I0412 13:13:02.777753  6895 sgd_solver.cpp:105] Iteration 3120, lr = 0.00539006
I0412 13:13:07.757261  6895 solver.cpp:218] Iteration 3132 (2.40996 iter/s, 4.97933s/12 iters), loss = 5.2828
I0412 13:13:07.757315  6895 solver.cpp:237]     Train net output #0: loss = 5.2828 (* 1 = 5.2828 loss)
I0412 13:13:07.757328  6895 sgd_solver.cpp:105] Iteration 3132, lr = 0.00537727
I0412 13:13:08.887809  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:13:12.735587  6895 solver.cpp:218] Iteration 3144 (2.41057 iter/s, 4.97807s/12 iters), loss = 5.28299
I0412 13:13:12.735643  6895 solver.cpp:237]     Train net output #0: loss = 5.28299 (* 1 = 5.28299 loss)
I0412 13:13:12.735656  6895 sgd_solver.cpp:105] Iteration 3144, lr = 0.0053645
I0412 13:13:17.564591  6895 solver.cpp:218] Iteration 3156 (2.48511 iter/s, 4.82875s/12 iters), loss = 5.24879
I0412 13:13:17.564646  6895 solver.cpp:237]     Train net output #0: loss = 5.24879 (* 1 = 5.24879 loss)
I0412 13:13:17.564657  6895 sgd_solver.cpp:105] Iteration 3156, lr = 0.00535176
I0412 13:13:19.521294  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3162.caffemodel
I0412 13:13:21.071678  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3162.solverstate
I0412 13:13:22.311825  6895 solver.cpp:330] Iteration 3162, Testing net (#0)
I0412 13:13:22.311846  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:13:25.540194  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:13:26.797125  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:13:26.797155  6895 solver.cpp:397]     Test net output #1: loss = 5.28574 (* 1 = 5.28574 loss)
I0412 13:13:28.575278  6895 solver.cpp:218] Iteration 3168 (1.0899 iter/s, 11.0102s/12 iters), loss = 5.27107
I0412 13:13:28.575337  6895 solver.cpp:237]     Train net output #0: loss = 5.27107 (* 1 = 5.27107 loss)
I0412 13:13:28.575349  6895 sgd_solver.cpp:105] Iteration 3168, lr = 0.00533906
I0412 13:13:33.418238  6895 solver.cpp:218] Iteration 3180 (2.47795 iter/s, 4.84271s/12 iters), loss = 5.27588
I0412 13:13:33.418293  6895 solver.cpp:237]     Train net output #0: loss = 5.27588 (* 1 = 5.27588 loss)
I0412 13:13:33.418304  6895 sgd_solver.cpp:105] Iteration 3180, lr = 0.00532638
I0412 13:13:38.210332  6895 solver.cpp:218] Iteration 3192 (2.50425 iter/s, 4.79185s/12 iters), loss = 5.27511
I0412 13:13:38.210386  6895 solver.cpp:237]     Train net output #0: loss = 5.27511 (* 1 = 5.27511 loss)
I0412 13:13:38.210397  6895 sgd_solver.cpp:105] Iteration 3192, lr = 0.00531374
I0412 13:13:43.071931  6895 solver.cpp:218] Iteration 3204 (2.46845 iter/s, 4.86136s/12 iters), loss = 5.26554
I0412 13:13:43.071979  6895 solver.cpp:237]     Train net output #0: loss = 5.26554 (* 1 = 5.26554 loss)
I0412 13:13:43.071991  6895 sgd_solver.cpp:105] Iteration 3204, lr = 0.00530112
I0412 13:13:47.996381  6895 solver.cpp:218] Iteration 3216 (2.43694 iter/s, 4.92421s/12 iters), loss = 5.28966
I0412 13:13:47.996438  6895 solver.cpp:237]     Train net output #0: loss = 5.28966 (* 1 = 5.28966 loss)
I0412 13:13:47.996449  6895 sgd_solver.cpp:105] Iteration 3216, lr = 0.00528853
I0412 13:13:52.892709  6895 solver.cpp:218] Iteration 3228 (2.45094 iter/s, 4.89608s/12 iters), loss = 5.27876
I0412 13:13:52.895576  6895 solver.cpp:237]     Train net output #0: loss = 5.27876 (* 1 = 5.27876 loss)
I0412 13:13:52.895587  6895 sgd_solver.cpp:105] Iteration 3228, lr = 0.00527598
I0412 13:13:56.054507  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:13:57.758257  6895 solver.cpp:218] Iteration 3240 (2.46787 iter/s, 4.86249s/12 iters), loss = 5.28389
I0412 13:13:57.758322  6895 solver.cpp:237]     Train net output #0: loss = 5.28389 (* 1 = 5.28389 loss)
I0412 13:13:57.758337  6895 sgd_solver.cpp:105] Iteration 3240, lr = 0.00526345
I0412 13:14:03.051517  6895 solver.cpp:218] Iteration 3252 (2.26715 iter/s, 5.29299s/12 iters), loss = 5.26997
I0412 13:14:03.051560  6895 solver.cpp:237]     Train net output #0: loss = 5.26997 (* 1 = 5.26997 loss)
I0412 13:14:03.051569  6895 sgd_solver.cpp:105] Iteration 3252, lr = 0.00525095
I0412 13:14:07.433584  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3264.caffemodel
I0412 13:14:09.024056  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3264.solverstate
I0412 13:14:10.236852  6895 solver.cpp:330] Iteration 3264, Testing net (#0)
I0412 13:14:10.236877  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:14:13.474803  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:14:14.823798  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:14:14.823854  6895 solver.cpp:397]     Test net output #1: loss = 5.2861 (* 1 = 5.2861 loss)
I0412 13:14:14.906993  6895 solver.cpp:218] Iteration 3264 (1.01223 iter/s, 11.855s/12 iters), loss = 5.27476
I0412 13:14:14.907052  6895 solver.cpp:237]     Train net output #0: loss = 5.27476 (* 1 = 5.27476 loss)
I0412 13:14:14.907064  6895 sgd_solver.cpp:105] Iteration 3264, lr = 0.00523849
I0412 13:14:18.800807  6895 solver.cpp:218] Iteration 3276 (3.08198 iter/s, 3.89361s/12 iters), loss = 5.29066
I0412 13:14:18.800853  6895 solver.cpp:237]     Train net output #0: loss = 5.29066 (* 1 = 5.29066 loss)
I0412 13:14:18.800863  6895 sgd_solver.cpp:105] Iteration 3276, lr = 0.00522605
I0412 13:14:23.900171  6895 solver.cpp:218] Iteration 3288 (2.35335 iter/s, 5.09912s/12 iters), loss = 5.26243
I0412 13:14:23.900302  6895 solver.cpp:237]     Train net output #0: loss = 5.26243 (* 1 = 5.26243 loss)
I0412 13:14:23.900312  6895 sgd_solver.cpp:105] Iteration 3288, lr = 0.00521364
I0412 13:14:28.684322  6895 solver.cpp:218] Iteration 3300 (2.50845 iter/s, 4.78383s/12 iters), loss = 5.28695
I0412 13:14:28.684366  6895 solver.cpp:237]     Train net output #0: loss = 5.28695 (* 1 = 5.28695 loss)
I0412 13:14:28.684374  6895 sgd_solver.cpp:105] Iteration 3300, lr = 0.00520126
I0412 13:14:33.763958  6895 solver.cpp:218] Iteration 3312 (2.36248 iter/s, 5.0794s/12 iters), loss = 5.26255
I0412 13:14:33.763994  6895 solver.cpp:237]     Train net output #0: loss = 5.26255 (* 1 = 5.26255 loss)
I0412 13:14:33.764003  6895 sgd_solver.cpp:105] Iteration 3312, lr = 0.00518892
I0412 13:14:38.669339  6895 solver.cpp:218] Iteration 3324 (2.44641 iter/s, 4.90515s/12 iters), loss = 5.28406
I0412 13:14:38.669381  6895 solver.cpp:237]     Train net output #0: loss = 5.28406 (* 1 = 5.28406 loss)
I0412 13:14:38.669389  6895 sgd_solver.cpp:105] Iteration 3324, lr = 0.0051766
I0412 13:14:43.354743  6895 solver.cpp:218] Iteration 3336 (2.56127 iter/s, 4.68518s/12 iters), loss = 5.27623
I0412 13:14:43.354797  6895 solver.cpp:237]     Train net output #0: loss = 5.27623 (* 1 = 5.27623 loss)
I0412 13:14:43.354810  6895 sgd_solver.cpp:105] Iteration 3336, lr = 0.00516431
I0412 13:14:43.755203  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:14:49.017786  6895 solver.cpp:218] Iteration 3348 (2.11911 iter/s, 5.66276s/12 iters), loss = 5.27772
I0412 13:14:49.017833  6895 solver.cpp:237]     Train net output #0: loss = 5.27772 (* 1 = 5.27772 loss)
I0412 13:14:49.017843  6895 sgd_solver.cpp:105] Iteration 3348, lr = 0.00515204
I0412 13:14:53.979674  6895 solver.cpp:218] Iteration 3360 (2.41855 iter/s, 4.96165s/12 iters), loss = 5.26601
I0412 13:14:53.979735  6895 solver.cpp:237]     Train net output #0: loss = 5.26601 (* 1 = 5.26601 loss)
I0412 13:14:53.979745  6895 sgd_solver.cpp:105] Iteration 3360, lr = 0.00513981
I0412 13:14:55.977129  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3366.caffemodel
I0412 13:14:57.455128  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3366.solverstate
I0412 13:14:58.617069  6895 solver.cpp:330] Iteration 3366, Testing net (#0)
I0412 13:14:58.617095  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:15:01.676635  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:15:03.059293  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:15:03.059342  6895 solver.cpp:397]     Test net output #1: loss = 5.28585 (* 1 = 5.28585 loss)
I0412 13:15:04.800329  6895 solver.cpp:218] Iteration 3372 (1.10904 iter/s, 10.8202s/12 iters), loss = 5.28264
I0412 13:15:04.800380  6895 solver.cpp:237]     Train net output #0: loss = 5.28264 (* 1 = 5.28264 loss)
I0412 13:15:04.800390  6895 sgd_solver.cpp:105] Iteration 3372, lr = 0.00512761
I0412 13:15:09.613843  6895 solver.cpp:218] Iteration 3384 (2.49311 iter/s, 4.81327s/12 iters), loss = 5.26503
I0412 13:15:09.613889  6895 solver.cpp:237]     Train net output #0: loss = 5.26503 (* 1 = 5.26503 loss)
I0412 13:15:09.613899  6895 sgd_solver.cpp:105] Iteration 3384, lr = 0.00511544
I0412 13:15:14.463673  6895 solver.cpp:218] Iteration 3396 (2.47443 iter/s, 4.84959s/12 iters), loss = 5.26331
I0412 13:15:14.463718  6895 solver.cpp:237]     Train net output #0: loss = 5.26331 (* 1 = 5.26331 loss)
I0412 13:15:14.463726  6895 sgd_solver.cpp:105] Iteration 3396, lr = 0.00510329
I0412 13:15:19.258548  6895 solver.cpp:218] Iteration 3408 (2.50279 iter/s, 4.79464s/12 iters), loss = 5.28709
I0412 13:15:19.258594  6895 solver.cpp:237]     Train net output #0: loss = 5.28709 (* 1 = 5.28709 loss)
I0412 13:15:19.258602  6895 sgd_solver.cpp:105] Iteration 3408, lr = 0.00509117
I0412 13:15:24.066746  6895 solver.cpp:218] Iteration 3420 (2.49586 iter/s, 4.80795s/12 iters), loss = 5.27561
I0412 13:15:24.066890  6895 solver.cpp:237]     Train net output #0: loss = 5.27561 (* 1 = 5.27561 loss)
I0412 13:15:24.066905  6895 sgd_solver.cpp:105] Iteration 3420, lr = 0.00507909
I0412 13:15:29.000520  6895 solver.cpp:218] Iteration 3432 (2.43238 iter/s, 4.93344s/12 iters), loss = 5.26261
I0412 13:15:29.000568  6895 solver.cpp:237]     Train net output #0: loss = 5.26261 (* 1 = 5.26261 loss)
I0412 13:15:29.000581  6895 sgd_solver.cpp:105] Iteration 3432, lr = 0.00506703
I0412 13:15:31.556972  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:15:33.786306  6895 solver.cpp:218] Iteration 3444 (2.50755 iter/s, 4.78555s/12 iters), loss = 5.27616
I0412 13:15:33.786365  6895 solver.cpp:237]     Train net output #0: loss = 5.27616 (* 1 = 5.27616 loss)
I0412 13:15:33.786375  6895 sgd_solver.cpp:105] Iteration 3444, lr = 0.005055
I0412 13:15:38.565987  6895 solver.cpp:218] Iteration 3456 (2.51077 iter/s, 4.77941s/12 iters), loss = 5.27682
I0412 13:15:38.566049  6895 solver.cpp:237]     Train net output #0: loss = 5.27682 (* 1 = 5.27682 loss)
I0412 13:15:38.566064  6895 sgd_solver.cpp:105] Iteration 3456, lr = 0.005043
I0412 13:15:43.064008  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3468.caffemodel
I0412 13:15:44.611219  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3468.solverstate
I0412 13:15:45.917811  6895 solver.cpp:330] Iteration 3468, Testing net (#0)
I0412 13:15:45.917836  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:15:46.276623  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:15:48.985970  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:15:50.367861  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:15:50.367897  6895 solver.cpp:397]     Test net output #1: loss = 5.28618 (* 1 = 5.28618 loss)
I0412 13:15:50.450904  6895 solver.cpp:218] Iteration 3468 (1.00973 iter/s, 11.8844s/12 iters), loss = 5.27477
I0412 13:15:50.450958  6895 solver.cpp:237]     Train net output #0: loss = 5.27477 (* 1 = 5.27477 loss)
I0412 13:15:50.450969  6895 sgd_solver.cpp:105] Iteration 3468, lr = 0.00503102
I0412 13:15:54.406059  6895 solver.cpp:218] Iteration 3480 (3.03418 iter/s, 3.95495s/12 iters), loss = 5.27944
I0412 13:15:54.406185  6895 solver.cpp:237]     Train net output #0: loss = 5.27944 (* 1 = 5.27944 loss)
I0412 13:15:54.406200  6895 sgd_solver.cpp:105] Iteration 3480, lr = 0.00501908
I0412 13:15:59.054965  6895 solver.cpp:218] Iteration 3492 (2.58143 iter/s, 4.64859s/12 iters), loss = 5.28781
I0412 13:15:59.055011  6895 solver.cpp:237]     Train net output #0: loss = 5.28781 (* 1 = 5.28781 loss)
I0412 13:15:59.055020  6895 sgd_solver.cpp:105] Iteration 3492, lr = 0.00500716
I0412 13:16:03.932713  6895 solver.cpp:218] Iteration 3504 (2.46027 iter/s, 4.87751s/12 iters), loss = 5.27615
I0412 13:16:03.932771  6895 solver.cpp:237]     Train net output #0: loss = 5.27615 (* 1 = 5.27615 loss)
I0412 13:16:03.932782  6895 sgd_solver.cpp:105] Iteration 3504, lr = 0.00499527
I0412 13:16:08.958537  6895 solver.cpp:218] Iteration 3516 (2.38779 iter/s, 5.02557s/12 iters), loss = 5.26704
I0412 13:16:08.958580  6895 solver.cpp:237]     Train net output #0: loss = 5.26704 (* 1 = 5.26704 loss)
I0412 13:16:08.958590  6895 sgd_solver.cpp:105] Iteration 3516, lr = 0.00498341
I0412 13:16:13.853204  6895 solver.cpp:218] Iteration 3528 (2.45177 iter/s, 4.89443s/12 iters), loss = 5.27221
I0412 13:16:13.853241  6895 solver.cpp:237]     Train net output #0: loss = 5.27221 (* 1 = 5.27221 loss)
I0412 13:16:13.853250  6895 sgd_solver.cpp:105] Iteration 3528, lr = 0.00497158
I0412 13:16:18.353801  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:16:18.610193  6895 solver.cpp:218] Iteration 3540 (2.52273 iter/s, 4.75676s/12 iters), loss = 5.26285
I0412 13:16:18.610236  6895 solver.cpp:237]     Train net output #0: loss = 5.26285 (* 1 = 5.26285 loss)
I0412 13:16:18.610245  6895 sgd_solver.cpp:105] Iteration 3540, lr = 0.00495978
I0412 13:16:23.473377  6895 solver.cpp:218] Iteration 3552 (2.46764 iter/s, 4.86294s/12 iters), loss = 5.26738
I0412 13:16:23.473433  6895 solver.cpp:237]     Train net output #0: loss = 5.26738 (* 1 = 5.26738 loss)
I0412 13:16:23.473445  6895 sgd_solver.cpp:105] Iteration 3552, lr = 0.004948
I0412 13:16:28.325546  6895 solver.cpp:218] Iteration 3564 (2.47325 iter/s, 4.85192s/12 iters), loss = 5.29174
I0412 13:16:28.325690  6895 solver.cpp:237]     Train net output #0: loss = 5.29174 (* 1 = 5.29174 loss)
I0412 13:16:28.325704  6895 sgd_solver.cpp:105] Iteration 3564, lr = 0.00493626
I0412 13:16:30.237408  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3570.caffemodel
I0412 13:16:34.219467  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3570.solverstate
I0412 13:16:38.470937  6895 solver.cpp:330] Iteration 3570, Testing net (#0)
I0412 13:16:38.470959  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:16:41.493223  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:16:42.900251  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:16:42.900298  6895 solver.cpp:397]     Test net output #1: loss = 5.28592 (* 1 = 5.28592 loss)
I0412 13:16:44.607614  6895 solver.cpp:218] Iteration 3576 (0.737041 iter/s, 16.2813s/12 iters), loss = 5.28697
I0412 13:16:44.607666  6895 solver.cpp:237]     Train net output #0: loss = 5.28697 (* 1 = 5.28697 loss)
I0412 13:16:44.607677  6895 sgd_solver.cpp:105] Iteration 3576, lr = 0.00492454
I0412 13:16:49.463354  6895 solver.cpp:218] Iteration 3588 (2.47143 iter/s, 4.85549s/12 iters), loss = 5.27697
I0412 13:16:49.463404  6895 solver.cpp:237]     Train net output #0: loss = 5.27697 (* 1 = 5.27697 loss)
I0412 13:16:49.463416  6895 sgd_solver.cpp:105] Iteration 3588, lr = 0.00491284
I0412 13:16:54.387217  6895 solver.cpp:218] Iteration 3600 (2.43724 iter/s, 4.92361s/12 iters), loss = 5.26214
I0412 13:16:54.387271  6895 solver.cpp:237]     Train net output #0: loss = 5.26214 (* 1 = 5.26214 loss)
I0412 13:16:54.387284  6895 sgd_solver.cpp:105] Iteration 3600, lr = 0.00490118
I0412 13:16:59.304930  6895 solver.cpp:218] Iteration 3612 (2.44028 iter/s, 4.91746s/12 iters), loss = 5.24481
I0412 13:16:59.305030  6895 solver.cpp:237]     Train net output #0: loss = 5.24481 (* 1 = 5.24481 loss)
I0412 13:16:59.305042  6895 sgd_solver.cpp:105] Iteration 3612, lr = 0.00488954
I0412 13:17:04.158345  6895 solver.cpp:218] Iteration 3624 (2.47264 iter/s, 4.85312s/12 iters), loss = 5.27834
I0412 13:17:04.158404  6895 solver.cpp:237]     Train net output #0: loss = 5.27834 (* 1 = 5.27834 loss)
I0412 13:17:04.158417  6895 sgd_solver.cpp:105] Iteration 3624, lr = 0.00487793
I0412 13:17:09.102005  6895 solver.cpp:218] Iteration 3636 (2.42749 iter/s, 4.94338s/12 iters), loss = 5.28357
I0412 13:17:09.102052  6895 solver.cpp:237]     Train net output #0: loss = 5.28357 (* 1 = 5.28357 loss)
I0412 13:17:09.102062  6895 sgd_solver.cpp:105] Iteration 3636, lr = 0.00486635
I0412 13:17:11.018281  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:17:14.237493  6895 solver.cpp:218] Iteration 3648 (2.3368 iter/s, 5.13524s/12 iters), loss = 5.28739
I0412 13:17:14.237557  6895 solver.cpp:237]     Train net output #0: loss = 5.28739 (* 1 = 5.28739 loss)
I0412 13:17:14.237573  6895 sgd_solver.cpp:105] Iteration 3648, lr = 0.0048548
I0412 13:17:19.153625  6895 solver.cpp:218] Iteration 3660 (2.44107 iter/s, 4.91588s/12 iters), loss = 5.2794
I0412 13:17:19.153676  6895 solver.cpp:237]     Train net output #0: loss = 5.2794 (* 1 = 5.2794 loss)
I0412 13:17:19.153688  6895 sgd_solver.cpp:105] Iteration 3660, lr = 0.00484327
I0412 13:17:23.474191  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3672.caffemodel
I0412 13:17:24.951632  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3672.solverstate
I0412 13:17:26.125222  6895 solver.cpp:330] Iteration 3672, Testing net (#0)
I0412 13:17:26.125247  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:17:28.998697  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:17:30.451414  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:17:30.451509  6895 solver.cpp:397]     Test net output #1: loss = 5.28534 (* 1 = 5.28534 loss)
I0412 13:17:30.534404  6895 solver.cpp:218] Iteration 3672 (1.05445 iter/s, 11.3803s/12 iters), loss = 5.25554
I0412 13:17:30.534448  6895 solver.cpp:237]     Train net output #0: loss = 5.25554 (* 1 = 5.25554 loss)
I0412 13:17:30.534456  6895 sgd_solver.cpp:105] Iteration 3672, lr = 0.00483177
I0412 13:17:34.718633  6895 solver.cpp:218] Iteration 3684 (2.86806 iter/s, 4.18402s/12 iters), loss = 5.27058
I0412 13:17:34.718677  6895 solver.cpp:237]     Train net output #0: loss = 5.27058 (* 1 = 5.27058 loss)
I0412 13:17:34.718684  6895 sgd_solver.cpp:105] Iteration 3684, lr = 0.0048203
I0412 13:17:39.586563  6895 solver.cpp:218] Iteration 3696 (2.46523 iter/s, 4.86769s/12 iters), loss = 5.26182
I0412 13:17:39.586613  6895 solver.cpp:237]     Train net output #0: loss = 5.26182 (* 1 = 5.26182 loss)
I0412 13:17:39.586624  6895 sgd_solver.cpp:105] Iteration 3696, lr = 0.00480886
I0412 13:17:44.333391  6895 solver.cpp:218] Iteration 3708 (2.52813 iter/s, 4.74659s/12 iters), loss = 5.26838
I0412 13:17:44.333431  6895 solver.cpp:237]     Train net output #0: loss = 5.26838 (* 1 = 5.26838 loss)
I0412 13:17:44.333439  6895 sgd_solver.cpp:105] Iteration 3708, lr = 0.00479744
I0412 13:17:49.146088  6895 solver.cpp:218] Iteration 3720 (2.49353 iter/s, 4.81246s/12 iters), loss = 5.27118
I0412 13:17:49.146144  6895 solver.cpp:237]     Train net output #0: loss = 5.27118 (* 1 = 5.27118 loss)
I0412 13:17:49.146157  6895 sgd_solver.cpp:105] Iteration 3720, lr = 0.00478605
I0412 13:17:53.995321  6895 solver.cpp:218] Iteration 3732 (2.47474 iter/s, 4.84899s/12 iters), loss = 5.25685
I0412 13:17:53.995365  6895 solver.cpp:237]     Train net output #0: loss = 5.25685 (* 1 = 5.25685 loss)
I0412 13:17:53.995374  6895 sgd_solver.cpp:105] Iteration 3732, lr = 0.00477469
I0412 13:17:57.922346  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:17:58.814941  6895 solver.cpp:218] Iteration 3744 (2.48995 iter/s, 4.81938s/12 iters), loss = 5.25813
I0412 13:17:58.814994  6895 solver.cpp:237]     Train net output #0: loss = 5.25813 (* 1 = 5.25813 loss)
I0412 13:17:58.815006  6895 sgd_solver.cpp:105] Iteration 3744, lr = 0.00476335
I0412 13:18:03.690762  6895 solver.cpp:218] Iteration 3756 (2.46125 iter/s, 4.87557s/12 iters), loss = 5.28385
I0412 13:18:03.690867  6895 solver.cpp:237]     Train net output #0: loss = 5.28385 (* 1 = 5.28385 loss)
I0412 13:18:03.690878  6895 sgd_solver.cpp:105] Iteration 3756, lr = 0.00475204
I0412 13:18:08.554922  6895 solver.cpp:218] Iteration 3768 (2.46717 iter/s, 4.86386s/12 iters), loss = 5.26175
I0412 13:18:08.554968  6895 solver.cpp:237]     Train net output #0: loss = 5.26175 (* 1 = 5.26175 loss)
I0412 13:18:08.554978  6895 sgd_solver.cpp:105] Iteration 3768, lr = 0.00474076
I0412 13:18:10.534263  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3774.caffemodel
I0412 13:18:13.264951  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3774.solverstate
I0412 13:18:15.248209  6895 solver.cpp:330] Iteration 3774, Testing net (#0)
I0412 13:18:15.248240  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:18:18.316488  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:18:19.812193  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:18:19.812247  6895 solver.cpp:397]     Test net output #1: loss = 5.28642 (* 1 = 5.28642 loss)
I0412 13:18:21.632341  6895 solver.cpp:218] Iteration 3780 (0.91765 iter/s, 13.0769s/12 iters), loss = 5.30766
I0412 13:18:21.632393  6895 solver.cpp:237]     Train net output #0: loss = 5.30766 (* 1 = 5.30766 loss)
I0412 13:18:21.632405  6895 sgd_solver.cpp:105] Iteration 3780, lr = 0.00472951
I0412 13:18:26.502928  6895 solver.cpp:218] Iteration 3792 (2.46389 iter/s, 4.87034s/12 iters), loss = 5.2754
I0412 13:18:26.502985  6895 solver.cpp:237]     Train net output #0: loss = 5.2754 (* 1 = 5.2754 loss)
I0412 13:18:26.503000  6895 sgd_solver.cpp:105] Iteration 3792, lr = 0.00471828
I0412 13:18:31.144430  6895 solver.cpp:218] Iteration 3804 (2.5855 iter/s, 4.64127s/12 iters), loss = 5.27207
I0412 13:18:31.144462  6895 solver.cpp:237]     Train net output #0: loss = 5.27207 (* 1 = 5.27207 loss)
I0412 13:18:31.144469  6895 sgd_solver.cpp:105] Iteration 3804, lr = 0.00470707
I0412 13:18:35.734680  6895 solver.cpp:218] Iteration 3816 (2.61436 iter/s, 4.59003s/12 iters), loss = 5.27416
I0412 13:18:35.734825  6895 solver.cpp:237]     Train net output #0: loss = 5.27416 (* 1 = 5.27416 loss)
I0412 13:18:35.734838  6895 sgd_solver.cpp:105] Iteration 3816, lr = 0.0046959
I0412 13:18:40.395188  6895 solver.cpp:218] Iteration 3828 (2.57501 iter/s, 4.66018s/12 iters), loss = 5.26478
I0412 13:18:40.395249  6895 solver.cpp:237]     Train net output #0: loss = 5.26478 (* 1 = 5.26478 loss)
I0412 13:18:40.395262  6895 sgd_solver.cpp:105] Iteration 3828, lr = 0.00468475
I0412 13:18:45.328946  6895 solver.cpp:218] Iteration 3840 (2.43235 iter/s, 4.9335s/12 iters), loss = 5.26765
I0412 13:18:45.329000  6895 solver.cpp:237]     Train net output #0: loss = 5.26765 (* 1 = 5.26765 loss)
I0412 13:18:45.329012  6895 sgd_solver.cpp:105] Iteration 3840, lr = 0.00467363
I0412 13:18:46.450835  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:18:50.337586  6895 solver.cpp:218] Iteration 3852 (2.39598 iter/s, 5.00838s/12 iters), loss = 5.27657
I0412 13:18:50.337641  6895 solver.cpp:237]     Train net output #0: loss = 5.27657 (* 1 = 5.27657 loss)
I0412 13:18:50.337652  6895 sgd_solver.cpp:105] Iteration 3852, lr = 0.00466253
I0412 13:18:55.141979  6895 solver.cpp:218] Iteration 3864 (2.49785 iter/s, 4.80412s/12 iters), loss = 5.25491
I0412 13:18:55.142032  6895 solver.cpp:237]     Train net output #0: loss = 5.25491 (* 1 = 5.25491 loss)
I0412 13:18:55.142043  6895 sgd_solver.cpp:105] Iteration 3864, lr = 0.00465146
I0412 13:18:59.551434  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3876.caffemodel
I0412 13:19:02.578861  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3876.solverstate
I0412 13:19:07.311666  6895 solver.cpp:330] Iteration 3876, Testing net (#0)
I0412 13:19:07.311766  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:19:10.234333  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:19:11.767804  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:19:11.767846  6895 solver.cpp:397]     Test net output #1: loss = 5.28592 (* 1 = 5.28592 loss)
I0412 13:19:11.850867  6895 solver.cpp:218] Iteration 3876 (0.71821 iter/s, 16.7082s/12 iters), loss = 5.27111
I0412 13:19:11.850919  6895 solver.cpp:237]     Train net output #0: loss = 5.27111 (* 1 = 5.27111 loss)
I0412 13:19:11.850930  6895 sgd_solver.cpp:105] Iteration 3876, lr = 0.00464042
I0412 13:19:15.937903  6895 solver.cpp:218] Iteration 3888 (2.93627 iter/s, 4.08682s/12 iters), loss = 5.27429
I0412 13:19:15.937980  6895 solver.cpp:237]     Train net output #0: loss = 5.27429 (* 1 = 5.27429 loss)
I0412 13:19:15.937994  6895 sgd_solver.cpp:105] Iteration 3888, lr = 0.0046294
I0412 13:19:20.629320  6895 solver.cpp:218] Iteration 3900 (2.55799 iter/s, 4.69118s/12 iters), loss = 5.27472
I0412 13:19:20.629369  6895 solver.cpp:237]     Train net output #0: loss = 5.27472 (* 1 = 5.27472 loss)
I0412 13:19:20.629379  6895 sgd_solver.cpp:105] Iteration 3900, lr = 0.00461841
I0412 13:19:25.432273  6895 solver.cpp:218] Iteration 3912 (2.49859 iter/s, 4.80271s/12 iters), loss = 5.26442
I0412 13:19:25.432332  6895 solver.cpp:237]     Train net output #0: loss = 5.26442 (* 1 = 5.26442 loss)
I0412 13:19:25.432344  6895 sgd_solver.cpp:105] Iteration 3912, lr = 0.00460744
I0412 13:19:30.207511  6895 solver.cpp:218] Iteration 3924 (2.51309 iter/s, 4.77499s/12 iters), loss = 5.29634
I0412 13:19:30.207564  6895 solver.cpp:237]     Train net output #0: loss = 5.29634 (* 1 = 5.29634 loss)
I0412 13:19:30.207576  6895 sgd_solver.cpp:105] Iteration 3924, lr = 0.0045965
I0412 13:19:35.057703  6895 solver.cpp:218] Iteration 3936 (2.47425 iter/s, 4.84995s/12 iters), loss = 5.2759
I0412 13:19:35.057755  6895 solver.cpp:237]     Train net output #0: loss = 5.2759 (* 1 = 5.2759 loss)
I0412 13:19:35.057767  6895 sgd_solver.cpp:105] Iteration 3936, lr = 0.00458559
I0412 13:19:38.521010  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:19:40.193691  6895 solver.cpp:218] Iteration 3948 (2.33657 iter/s, 5.13574s/12 iters), loss = 5.28469
I0412 13:19:40.193734  6895 solver.cpp:237]     Train net output #0: loss = 5.28469 (* 1 = 5.28469 loss)
I0412 13:19:40.193743  6895 sgd_solver.cpp:105] Iteration 3948, lr = 0.0045747
I0412 13:19:44.945840  6895 solver.cpp:218] Iteration 3960 (2.5253 iter/s, 4.75191s/12 iters), loss = 5.26908
I0412 13:19:44.945894  6895 solver.cpp:237]     Train net output #0: loss = 5.26908 (* 1 = 5.26908 loss)
I0412 13:19:44.945905  6895 sgd_solver.cpp:105] Iteration 3960, lr = 0.00456384
I0412 13:19:49.708230  6895 solver.cpp:218] Iteration 3972 (2.51987 iter/s, 4.76215s/12 iters), loss = 5.2791
I0412 13:19:49.708276  6895 solver.cpp:237]     Train net output #0: loss = 5.2791 (* 1 = 5.2791 loss)
I0412 13:19:49.708285  6895 sgd_solver.cpp:105] Iteration 3972, lr = 0.00455301
I0412 13:19:51.688884  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3978.caffemodel
I0412 13:19:55.541966  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3978.solverstate
I0412 13:19:58.654150  6895 solver.cpp:330] Iteration 3978, Testing net (#0)
I0412 13:19:58.654181  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:20:01.529953  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:20:03.102485  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:20:03.102531  6895 solver.cpp:397]     Test net output #1: loss = 5.28569 (* 1 = 5.28569 loss)
I0412 13:20:05.100129  6895 solver.cpp:218] Iteration 3984 (0.779663 iter/s, 15.3913s/12 iters), loss = 5.27958
I0412 13:20:05.100189  6895 solver.cpp:237]     Train net output #0: loss = 5.27958 (* 1 = 5.27958 loss)
I0412 13:20:05.100201  6895 sgd_solver.cpp:105] Iteration 3984, lr = 0.0045422
I0412 13:20:09.928046  6895 solver.cpp:218] Iteration 3996 (2.48567 iter/s, 4.82767s/12 iters), loss = 5.26898
I0412 13:20:09.928144  6895 solver.cpp:237]     Train net output #0: loss = 5.26898 (* 1 = 5.26898 loss)
I0412 13:20:09.928156  6895 sgd_solver.cpp:105] Iteration 3996, lr = 0.00453141
I0412 13:20:14.567852  6895 solver.cpp:218] Iteration 4008 (2.58647 iter/s, 4.63952s/12 iters), loss = 5.28718
I0412 13:20:14.567893  6895 solver.cpp:237]     Train net output #0: loss = 5.28718 (* 1 = 5.28718 loss)
I0412 13:20:14.567901  6895 sgd_solver.cpp:105] Iteration 4008, lr = 0.00452066
I0412 13:20:19.323130  6895 solver.cpp:218] Iteration 4020 (2.52364 iter/s, 4.75504s/12 iters), loss = 5.25735
I0412 13:20:19.323185  6895 solver.cpp:237]     Train net output #0: loss = 5.25735 (* 1 = 5.25735 loss)
I0412 13:20:19.323199  6895 sgd_solver.cpp:105] Iteration 4020, lr = 0.00450992
I0412 13:20:24.077589  6895 solver.cpp:218] Iteration 4032 (2.52408 iter/s, 4.75421s/12 iters), loss = 5.27288
I0412 13:20:24.077648  6895 solver.cpp:237]     Train net output #0: loss = 5.27288 (* 1 = 5.27288 loss)
I0412 13:20:24.077662  6895 sgd_solver.cpp:105] Iteration 4032, lr = 0.00449921
I0412 13:20:28.927996  6895 solver.cpp:218] Iteration 4044 (2.47414 iter/s, 4.85016s/12 iters), loss = 5.27578
I0412 13:20:28.928043  6895 solver.cpp:237]     Train net output #0: loss = 5.27578 (* 1 = 5.27578 loss)
I0412 13:20:28.928053  6895 sgd_solver.cpp:105] Iteration 4044, lr = 0.00448853
I0412 13:20:29.434877  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:20:33.937762  6895 solver.cpp:218] Iteration 4056 (2.39544 iter/s, 5.00953s/12 iters), loss = 5.27817
I0412 13:20:33.937800  6895 solver.cpp:237]     Train net output #0: loss = 5.27817 (* 1 = 5.27817 loss)
I0412 13:20:33.937809  6895 sgd_solver.cpp:105] Iteration 4056, lr = 0.00447788
I0412 13:20:38.767114  6895 solver.cpp:218] Iteration 4068 (2.48492 iter/s, 4.82912s/12 iters), loss = 5.27277
I0412 13:20:38.767160  6895 solver.cpp:237]     Train net output #0: loss = 5.27277 (* 1 = 5.27277 loss)
I0412 13:20:38.767169  6895 sgd_solver.cpp:105] Iteration 4068, lr = 0.00446724
I0412 13:20:43.231393  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4080.caffemodel
I0412 13:20:44.897080  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4080.solverstate
I0412 13:20:46.065677  6895 solver.cpp:330] Iteration 4080, Testing net (#0)
I0412 13:20:46.065697  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:20:48.903893  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:20:50.507411  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:20:50.507462  6895 solver.cpp:397]     Test net output #1: loss = 5.28616 (* 1 = 5.28616 loss)
I0412 13:20:50.590210  6895 solver.cpp:218] Iteration 4080 (1.015 iter/s, 11.8226s/12 iters), loss = 5.28854
I0412 13:20:50.590265  6895 solver.cpp:237]     Train net output #0: loss = 5.28854 (* 1 = 5.28854 loss)
I0412 13:20:50.590287  6895 sgd_solver.cpp:105] Iteration 4080, lr = 0.00445664
I0412 13:20:54.674896  6895 solver.cpp:218] Iteration 4092 (2.93796 iter/s, 4.08447s/12 iters), loss = 5.26624
I0412 13:20:54.674945  6895 solver.cpp:237]     Train net output #0: loss = 5.26624 (* 1 = 5.26624 loss)
I0412 13:20:54.674957  6895 sgd_solver.cpp:105] Iteration 4092, lr = 0.00444606
I0412 13:20:59.509855  6895 solver.cpp:218] Iteration 4104 (2.48205 iter/s, 4.83471s/12 iters), loss = 5.2631
I0412 13:20:59.509912  6895 solver.cpp:237]     Train net output #0: loss = 5.2631 (* 1 = 5.2631 loss)
I0412 13:20:59.509923  6895 sgd_solver.cpp:105] Iteration 4104, lr = 0.0044355
I0412 13:21:04.654007  6895 solver.cpp:218] Iteration 4116 (2.33287 iter/s, 5.14389s/12 iters), loss = 5.29664
I0412 13:21:04.654059  6895 solver.cpp:237]     Train net output #0: loss = 5.29664 (* 1 = 5.29664 loss)
I0412 13:21:04.654070  6895 sgd_solver.cpp:105] Iteration 4116, lr = 0.00442497
I0412 13:21:09.613395  6895 solver.cpp:218] Iteration 4128 (2.41977 iter/s, 4.95914s/12 iters), loss = 5.26592
I0412 13:21:09.613447  6895 solver.cpp:237]     Train net output #0: loss = 5.26592 (* 1 = 5.26592 loss)
I0412 13:21:09.613459  6895 sgd_solver.cpp:105] Iteration 4128, lr = 0.00441447
I0412 13:21:14.509474  6895 solver.cpp:218] Iteration 4140 (2.45106 iter/s, 4.89584s/12 iters), loss = 5.2593
I0412 13:21:14.509583  6895 solver.cpp:237]     Train net output #0: loss = 5.2593 (* 1 = 5.2593 loss)
I0412 13:21:14.509595  6895 sgd_solver.cpp:105] Iteration 4140, lr = 0.00440398
I0412 13:21:17.236364  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:21:19.694061  6895 solver.cpp:218] Iteration 4152 (2.31469 iter/s, 5.18427s/12 iters), loss = 5.27085
I0412 13:21:19.694116  6895 solver.cpp:237]     Train net output #0: loss = 5.27085 (* 1 = 5.27085 loss)
I0412 13:21:19.694128  6895 sgd_solver.cpp:105] Iteration 4152, lr = 0.00439353
I0412 13:21:21.055307  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:21:24.688349  6895 solver.cpp:218] Iteration 4164 (2.40287 iter/s, 4.99404s/12 iters), loss = 5.26466
I0412 13:21:24.688400  6895 solver.cpp:237]     Train net output #0: loss = 5.26466 (* 1 = 5.26466 loss)
I0412 13:21:24.688411  6895 sgd_solver.cpp:105] Iteration 4164, lr = 0.0043831
I0412 13:21:29.633071  6895 solver.cpp:218] Iteration 4176 (2.42695 iter/s, 4.94447s/12 iters), loss = 5.27147
I0412 13:21:29.633124  6895 solver.cpp:237]     Train net output #0: loss = 5.27147 (* 1 = 5.27147 loss)
I0412 13:21:29.633136  6895 sgd_solver.cpp:105] Iteration 4176, lr = 0.00437269
I0412 13:21:31.749567  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4182.caffemodel
I0412 13:21:35.018097  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4182.solverstate
I0412 13:21:36.190912  6895 solver.cpp:330] Iteration 4182, Testing net (#0)
I0412 13:21:36.190937  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:21:39.141322  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:21:40.795081  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 13:21:40.795128  6895 solver.cpp:397]     Test net output #1: loss = 5.28585 (* 1 = 5.28585 loss)
I0412 13:21:42.660559  6895 solver.cpp:218] Iteration 4188 (0.921168 iter/s, 13.0269s/12 iters), loss = 5.27243
I0412 13:21:42.660616  6895 solver.cpp:237]     Train net output #0: loss = 5.27243 (* 1 = 5.27243 loss)
I0412 13:21:42.660629  6895 sgd_solver.cpp:105] Iteration 4188, lr = 0.00436231
I0412 13:21:47.474228  6895 solver.cpp:218] Iteration 4200 (2.49303 iter/s, 4.81343s/12 iters), loss = 5.28447
I0412 13:21:47.474352  6895 solver.cpp:237]     Train net output #0: loss = 5.28447 (* 1 = 5.28447 loss)
I0412 13:21:47.474362  6895 sgd_solver.cpp:105] Iteration 4200, lr = 0.00435195
I0412 13:21:52.190378  6895 solver.cpp:218] Iteration 4212 (2.54462 iter/s, 4.71584s/12 iters), loss = 5.27363
I0412 13:21:52.190424  6895 solver.cpp:237]     Train net output #0: loss = 5.27363 (* 1 = 5.27363 loss)
I0412 13:21:52.190436  6895 sgd_solver.cpp:105] Iteration 4212, lr = 0.00434162
I0412 13:21:57.040654  6895 solver.cpp:218] Iteration 4224 (2.47421 iter/s, 4.85003s/12 iters), loss = 5.26101
I0412 13:21:57.040711  6895 solver.cpp:237]     Train net output #0: loss = 5.26101 (* 1 = 5.26101 loss)
I0412 13:21:57.040724  6895 sgd_solver.cpp:105] Iteration 4224, lr = 0.00433131
I0412 13:22:02.019362  6895 solver.cpp:218] Iteration 4236 (2.41039 iter/s, 4.97845s/12 iters), loss = 5.26748
I0412 13:22:02.019412  6895 solver.cpp:237]     Train net output #0: loss = 5.26748 (* 1 = 5.26748 loss)
I0412 13:22:02.019424  6895 sgd_solver.cpp:105] Iteration 4236, lr = 0.00432103
I0412 13:22:06.679572  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:22:06.908071  6895 solver.cpp:218] Iteration 4248 (2.45476 iter/s, 4.88846s/12 iters), loss = 5.24243
I0412 13:22:06.908124  6895 solver.cpp:237]     Train net output #0: loss = 5.24243 (* 1 = 5.24243 loss)
I0412 13:22:06.908136  6895 sgd_solver.cpp:105] Iteration 4248, lr = 0.00431077
I0412 13:22:12.018250  6895 solver.cpp:218] Iteration 4260 (2.34837 iter/s, 5.10992s/12 iters), loss = 5.26584
I0412 13:22:12.018299  6895 solver.cpp:237]     Train net output #0: loss = 5.26584 (* 1 = 5.26584 loss)
I0412 13:22:12.018311  6895 sgd_solver.cpp:105] Iteration 4260, lr = 0.00430053
I0412 13:22:16.878319  6895 solver.cpp:218] Iteration 4272 (2.46922 iter/s, 4.85983s/12 iters), loss = 5.29066
I0412 13:22:16.878376  6895 solver.cpp:237]     Train net output #0: loss = 5.29066 (* 1 = 5.29066 loss)
I0412 13:22:16.878388  6895 sgd_solver.cpp:105] Iteration 4272, lr = 0.00429032
I0412 13:22:21.025892  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4284.caffemodel
I0412 13:22:25.313843  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4284.solverstate
I0412 13:22:30.348309  6895 solver.cpp:330] Iteration 4284, Testing net (#0)
I0412 13:22:30.348330  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:22:33.166591  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:22:34.867034  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:22:34.867084  6895 solver.cpp:397]     Test net output #1: loss = 5.28598 (* 1 = 5.28598 loss)
I0412 13:22:34.950229  6895 solver.cpp:218] Iteration 4284 (0.664041 iter/s, 18.0712s/12 iters), loss = 5.27973
I0412 13:22:34.950289  6895 solver.cpp:237]     Train net output #0: loss = 5.27973 (* 1 = 5.27973 loss)
I0412 13:22:34.950299  6895 sgd_solver.cpp:105] Iteration 4284, lr = 0.00428014
I0412 13:22:39.194996  6895 solver.cpp:218] Iteration 4296 (2.82717 iter/s, 4.24453s/12 iters), loss = 5.27544
I0412 13:22:39.195060  6895 solver.cpp:237]     Train net output #0: loss = 5.27544 (* 1 = 5.27544 loss)
I0412 13:22:39.195075  6895 sgd_solver.cpp:105] Iteration 4296, lr = 0.00426998
I0412 13:22:44.485215  6895 solver.cpp:218] Iteration 4308 (2.26845 iter/s, 5.28995s/12 iters), loss = 5.26007
I0412 13:22:44.485258  6895 solver.cpp:237]     Train net output #0: loss = 5.26007 (* 1 = 5.26007 loss)
I0412 13:22:44.485267  6895 sgd_solver.cpp:105] Iteration 4308, lr = 0.00425984
I0412 13:22:49.255385  6895 solver.cpp:218] Iteration 4320 (2.51575 iter/s, 4.76994s/12 iters), loss = 5.25049
I0412 13:22:49.255429  6895 solver.cpp:237]     Train net output #0: loss = 5.25049 (* 1 = 5.25049 loss)
I0412 13:22:49.255440  6895 sgd_solver.cpp:105] Iteration 4320, lr = 0.00424972
I0412 13:22:53.956204  6895 solver.cpp:218] Iteration 4332 (2.55287 iter/s, 4.70059s/12 iters), loss = 5.27902
I0412 13:22:53.956346  6895 solver.cpp:237]     Train net output #0: loss = 5.27902 (* 1 = 5.27902 loss)
I0412 13:22:53.956357  6895 sgd_solver.cpp:105] Iteration 4332, lr = 0.00423964
I0412 13:22:58.742681  6895 solver.cpp:218] Iteration 4344 (2.50723 iter/s, 4.78615s/12 iters), loss = 5.28001
I0412 13:22:58.742728  6895 solver.cpp:237]     Train net output #0: loss = 5.28001 (* 1 = 5.28001 loss)
I0412 13:22:58.742740  6895 sgd_solver.cpp:105] Iteration 4344, lr = 0.00422957
I0412 13:23:00.540511  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:23:03.498234  6895 solver.cpp:218] Iteration 4356 (2.52349 iter/s, 4.75531s/12 iters), loss = 5.29127
I0412 13:23:03.498288  6895 solver.cpp:237]     Train net output #0: loss = 5.29127 (* 1 = 5.29127 loss)
I0412 13:23:03.498301  6895 sgd_solver.cpp:105] Iteration 4356, lr = 0.00421953
I0412 13:23:08.318409  6895 solver.cpp:218] Iteration 4368 (2.48966 iter/s, 4.81993s/12 iters), loss = 5.2794
I0412 13:23:08.318465  6895 solver.cpp:237]     Train net output #0: loss = 5.2794 (* 1 = 5.2794 loss)
I0412 13:23:08.318476  6895 sgd_solver.cpp:105] Iteration 4368, lr = 0.00420951
I0412 13:23:12.982007  6895 solver.cpp:218] Iteration 4380 (2.57325 iter/s, 4.66336s/12 iters), loss = 5.26511
I0412 13:23:12.982053  6895 solver.cpp:237]     Train net output #0: loss = 5.26511 (* 1 = 5.26511 loss)
I0412 13:23:12.982062  6895 sgd_solver.cpp:105] Iteration 4380, lr = 0.00419952
I0412 13:23:14.993594  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4386.caffemodel
I0412 13:23:16.536265  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4386.solverstate
I0412 13:23:19.293231  6895 solver.cpp:330] Iteration 4386, Testing net (#0)
I0412 13:23:19.293254  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:23:22.056309  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:23:23.830955  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:23:23.830996  6895 solver.cpp:397]     Test net output #1: loss = 5.28581 (* 1 = 5.28581 loss)
I0412 13:23:25.534014  6895 solver.cpp:218] Iteration 4392 (0.956062 iter/s, 12.5515s/12 iters), loss = 5.26923
I0412 13:23:25.534124  6895 solver.cpp:237]     Train net output #0: loss = 5.26923 (* 1 = 5.26923 loss)
I0412 13:23:25.534134  6895 sgd_solver.cpp:105] Iteration 4392, lr = 0.00418954
I0412 13:23:30.666673  6895 solver.cpp:218] Iteration 4404 (2.33811 iter/s, 5.13234s/12 iters), loss = 5.26404
I0412 13:23:30.666725  6895 solver.cpp:237]     Train net output #0: loss = 5.26404 (* 1 = 5.26404 loss)
I0412 13:23:30.666736  6895 sgd_solver.cpp:105] Iteration 4404, lr = 0.0041796
I0412 13:23:35.334080  6895 solver.cpp:218] Iteration 4416 (2.57115 iter/s, 4.66717s/12 iters), loss = 5.2677
I0412 13:23:35.334131  6895 solver.cpp:237]     Train net output #0: loss = 5.2677 (* 1 = 5.2677 loss)
I0412 13:23:35.334143  6895 sgd_solver.cpp:105] Iteration 4416, lr = 0.00416967
I0412 13:23:40.123404  6895 solver.cpp:218] Iteration 4428 (2.5057 iter/s, 4.78908s/12 iters), loss = 5.26619
I0412 13:23:40.123456  6895 solver.cpp:237]     Train net output #0: loss = 5.26619 (* 1 = 5.26619 loss)
I0412 13:23:40.123468  6895 sgd_solver.cpp:105] Iteration 4428, lr = 0.00415977
I0412 13:23:45.012666  6895 solver.cpp:218] Iteration 4440 (2.45448 iter/s, 4.88901s/12 iters), loss = 5.26618
I0412 13:23:45.012725  6895 solver.cpp:237]     Train net output #0: loss = 5.26618 (* 1 = 5.26618 loss)
I0412 13:23:45.012738  6895 sgd_solver.cpp:105] Iteration 4440, lr = 0.0041499
I0412 13:23:48.998669  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:23:49.997675  6895 solver.cpp:218] Iteration 4452 (2.40734 iter/s, 4.98475s/12 iters), loss = 5.25524
I0412 13:23:49.997728  6895 solver.cpp:237]     Train net output #0: loss = 5.25524 (* 1 = 5.25524 loss)
I0412 13:23:49.997738  6895 sgd_solver.cpp:105] Iteration 4452, lr = 0.00414005
I0412 13:23:54.794782  6895 solver.cpp:218] Iteration 4464 (2.50164 iter/s, 4.79686s/12 iters), loss = 5.28031
I0412 13:23:54.794840  6895 solver.cpp:237]     Train net output #0: loss = 5.28031 (* 1 = 5.28031 loss)
I0412 13:23:54.794852  6895 sgd_solver.cpp:105] Iteration 4464, lr = 0.00413022
I0412 13:23:59.735515  6895 solver.cpp:218] Iteration 4476 (2.42891 iter/s, 4.94048s/12 iters), loss = 5.26179
I0412 13:23:59.735638  6895 solver.cpp:237]     Train net output #0: loss = 5.26179 (* 1 = 5.26179 loss)
I0412 13:23:59.735649  6895 sgd_solver.cpp:105] Iteration 4476, lr = 0.00412041
I0412 13:24:04.164814  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4488.caffemodel
I0412 13:24:07.050361  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4488.solverstate
I0412 13:24:12.943588  6895 solver.cpp:330] Iteration 4488, Testing net (#0)
I0412 13:24:12.943619  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:24:15.627960  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:24:17.399153  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 13:24:17.399199  6895 solver.cpp:397]     Test net output #1: loss = 5.2857 (* 1 = 5.2857 loss)
I0412 13:24:17.482266  6895 solver.cpp:218] Iteration 4488 (0.67621 iter/s, 17.746s/12 iters), loss = 5.31
I0412 13:24:17.482321  6895 solver.cpp:237]     Train net output #0: loss = 5.31 (* 1 = 5.31 loss)
I0412 13:24:17.482331  6895 sgd_solver.cpp:105] Iteration 4488, lr = 0.00411063
I0412 13:24:21.963855  6895 solver.cpp:218] Iteration 4500 (2.67776 iter/s, 4.48136s/12 iters), loss = 5.26826
I0412 13:24:21.963912  6895 solver.cpp:237]     Train net output #0: loss = 5.26826 (* 1 = 5.26826 loss)
I0412 13:24:21.963923  6895 sgd_solver.cpp:105] Iteration 4500, lr = 0.00410087
I0412 13:24:26.843437  6895 solver.cpp:218] Iteration 4512 (2.45935 iter/s, 4.87933s/12 iters), loss = 5.26776
I0412 13:24:26.843493  6895 solver.cpp:237]     Train net output #0: loss = 5.26776 (* 1 = 5.26776 loss)
I0412 13:24:26.843508  6895 sgd_solver.cpp:105] Iteration 4512, lr = 0.00409113
I0412 13:24:31.771311  6895 solver.cpp:218] Iteration 4524 (2.43525 iter/s, 4.92762s/12 iters), loss = 5.27692
I0412 13:24:31.771394  6895 solver.cpp:237]     Train net output #0: loss = 5.27692 (* 1 = 5.27692 loss)
I0412 13:24:31.771405  6895 sgd_solver.cpp:105] Iteration 4524, lr = 0.00408142
I0412 13:24:36.591789  6895 solver.cpp:218] Iteration 4536 (2.48952 iter/s, 4.82021s/12 iters), loss = 5.27064
I0412 13:24:36.591841  6895 solver.cpp:237]     Train net output #0: loss = 5.27064 (* 1 = 5.27064 loss)
I0412 13:24:36.591854  6895 sgd_solver.cpp:105] Iteration 4536, lr = 0.00407173
I0412 13:24:41.318117  6895 solver.cpp:218] Iteration 4548 (2.5391 iter/s, 4.72609s/12 iters), loss = 5.26399
I0412 13:24:41.318157  6895 solver.cpp:237]     Train net output #0: loss = 5.26399 (* 1 = 5.26399 loss)
I0412 13:24:41.318167  6895 sgd_solver.cpp:105] Iteration 4548, lr = 0.00406206
I0412 13:24:42.533082  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:24:46.044920  6895 solver.cpp:218] Iteration 4560 (2.53884 iter/s, 4.72657s/12 iters), loss = 5.27572
I0412 13:24:46.044970  6895 solver.cpp:237]     Train net output #0: loss = 5.27572 (* 1 = 5.27572 loss)
I0412 13:24:46.044981  6895 sgd_solver.cpp:105] Iteration 4560, lr = 0.00405242
I0412 13:24:50.617708  6895 solver.cpp:218] Iteration 4572 (2.62435 iter/s, 4.57256s/12 iters), loss = 5.26485
I0412 13:24:50.617753  6895 solver.cpp:237]     Train net output #0: loss = 5.26485 (* 1 = 5.26485 loss)
I0412 13:24:50.617765  6895 sgd_solver.cpp:105] Iteration 4572, lr = 0.0040428
I0412 13:24:55.636379  6895 solver.cpp:218] Iteration 4584 (2.39119 iter/s, 5.01843s/12 iters), loss = 5.27758
I0412 13:24:55.636420  6895 solver.cpp:237]     Train net output #0: loss = 5.27758 (* 1 = 5.27758 loss)
I0412 13:24:55.636428  6895 sgd_solver.cpp:105] Iteration 4584, lr = 0.0040332
I0412 13:24:57.625308  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4590.caffemodel
I0412 13:25:01.004762  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4590.solverstate
I0412 13:25:03.309437  6895 solver.cpp:330] Iteration 4590, Testing net (#0)
I0412 13:25:03.309538  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:25:05.974253  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:25:07.790355  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:25:07.790398  6895 solver.cpp:397]     Test net output #1: loss = 5.28567 (* 1 = 5.28567 loss)
I0412 13:25:09.641537  6895 solver.cpp:218] Iteration 4596 (0.856862 iter/s, 14.0046s/12 iters), loss = 5.26722
I0412 13:25:09.641589  6895 solver.cpp:237]     Train net output #0: loss = 5.26722 (* 1 = 5.26722 loss)
I0412 13:25:09.641602  6895 sgd_solver.cpp:105] Iteration 4596, lr = 0.00402362
I0412 13:25:14.322221  6895 solver.cpp:218] Iteration 4608 (2.56386 iter/s, 4.68045s/12 iters), loss = 5.27354
I0412 13:25:14.322260  6895 solver.cpp:237]     Train net output #0: loss = 5.27354 (* 1 = 5.27354 loss)
I0412 13:25:14.322269  6895 sgd_solver.cpp:105] Iteration 4608, lr = 0.00401407
I0412 13:25:19.246989  6895 solver.cpp:218] Iteration 4620 (2.43678 iter/s, 4.92453s/12 iters), loss = 5.26268
I0412 13:25:19.247037  6895 solver.cpp:237]     Train net output #0: loss = 5.26268 (* 1 = 5.26268 loss)
I0412 13:25:19.247049  6895 sgd_solver.cpp:105] Iteration 4620, lr = 0.00400454
I0412 13:25:24.127919  6895 solver.cpp:218] Iteration 4632 (2.45867 iter/s, 4.88069s/12 iters), loss = 5.29171
I0412 13:25:24.127961  6895 solver.cpp:237]     Train net output #0: loss = 5.29171 (* 1 = 5.29171 loss)
I0412 13:25:24.127969  6895 sgd_solver.cpp:105] Iteration 4632, lr = 0.00399503
I0412 13:25:28.853765  6895 solver.cpp:218] Iteration 4644 (2.53936 iter/s, 4.72561s/12 iters), loss = 5.27098
I0412 13:25:28.853827  6895 solver.cpp:237]     Train net output #0: loss = 5.27098 (* 1 = 5.27098 loss)
I0412 13:25:28.853842  6895 sgd_solver.cpp:105] Iteration 4644, lr = 0.00398555
I0412 13:25:32.178685  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:25:33.754063  6895 solver.cpp:218] Iteration 4656 (2.44896 iter/s, 4.90004s/12 iters), loss = 5.27993
I0412 13:25:33.754206  6895 solver.cpp:237]     Train net output #0: loss = 5.27993 (* 1 = 5.27993 loss)
I0412 13:25:33.754218  6895 sgd_solver.cpp:105] Iteration 4656, lr = 0.00397608
I0412 13:25:38.633952  6895 solver.cpp:218] Iteration 4668 (2.45924 iter/s, 4.87955s/12 iters), loss = 5.2648
I0412 13:25:38.634025  6895 solver.cpp:237]     Train net output #0: loss = 5.2648 (* 1 = 5.2648 loss)
I0412 13:25:38.634037  6895 sgd_solver.cpp:105] Iteration 4668, lr = 0.00396664
I0412 13:25:43.316612  6895 solver.cpp:218] Iteration 4680 (2.56279 iter/s, 4.6824s/12 iters), loss = 5.28033
I0412 13:25:43.316673  6895 solver.cpp:237]     Train net output #0: loss = 5.28033 (* 1 = 5.28033 loss)
I0412 13:25:43.316686  6895 sgd_solver.cpp:105] Iteration 4680, lr = 0.00395723
I0412 13:25:47.640110  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4692.caffemodel
I0412 13:25:53.636649  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4692.solverstate
I0412 13:25:58.753464  6895 solver.cpp:330] Iteration 4692, Testing net (#0)
I0412 13:25:58.753494  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:26:01.344980  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:26:03.195657  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:26:03.195708  6895 solver.cpp:397]     Test net output #1: loss = 5.28606 (* 1 = 5.28606 loss)
I0412 13:26:03.279309  6895 solver.cpp:218] Iteration 4692 (0.601146 iter/s, 19.9619s/12 iters), loss = 5.27232
I0412 13:26:03.279363  6895 solver.cpp:237]     Train net output #0: loss = 5.27232 (* 1 = 5.27232 loss)
I0412 13:26:03.279376  6895 sgd_solver.cpp:105] Iteration 4692, lr = 0.00394783
I0412 13:26:07.379492  6895 solver.cpp:218] Iteration 4704 (2.92686 iter/s, 4.09996s/12 iters), loss = 5.26765
I0412 13:26:07.379637  6895 solver.cpp:237]     Train net output #0: loss = 5.26765 (* 1 = 5.26765 loss)
I0412 13:26:07.379649  6895 sgd_solver.cpp:105] Iteration 4704, lr = 0.00393846
I0412 13:26:12.262779  6895 solver.cpp:218] Iteration 4716 (2.45753 iter/s, 4.88295s/12 iters), loss = 5.27852
I0412 13:26:12.262830  6895 solver.cpp:237]     Train net output #0: loss = 5.27852 (* 1 = 5.27852 loss)
I0412 13:26:12.262842  6895 sgd_solver.cpp:105] Iteration 4716, lr = 0.00392911
I0412 13:26:17.080142  6895 solver.cpp:218] Iteration 4728 (2.49111 iter/s, 4.81712s/12 iters), loss = 5.26629
I0412 13:26:17.080204  6895 solver.cpp:237]     Train net output #0: loss = 5.26629 (* 1 = 5.26629 loss)
I0412 13:26:17.080217  6895 sgd_solver.cpp:105] Iteration 4728, lr = 0.00391978
I0412 13:26:21.904048  6895 solver.cpp:218] Iteration 4740 (2.48774 iter/s, 4.82365s/12 iters), loss = 5.27973
I0412 13:26:21.904100  6895 solver.cpp:237]     Train net output #0: loss = 5.27973 (* 1 = 5.27973 loss)
I0412 13:26:21.904110  6895 sgd_solver.cpp:105] Iteration 4740, lr = 0.00391047
I0412 13:26:26.782694  6895 solver.cpp:218] Iteration 4752 (2.45982 iter/s, 4.8784s/12 iters), loss = 5.28606
I0412 13:26:26.782744  6895 solver.cpp:237]     Train net output #0: loss = 5.28606 (* 1 = 5.28606 loss)
I0412 13:26:26.782755  6895 sgd_solver.cpp:105] Iteration 4752, lr = 0.00390119
I0412 13:26:27.312146  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:26:31.504258  6895 solver.cpp:218] Iteration 4764 (2.54166 iter/s, 4.72133s/12 iters), loss = 5.28174
I0412 13:26:31.504313  6895 solver.cpp:237]     Train net output #0: loss = 5.28174 (* 1 = 5.28174 loss)
I0412 13:26:31.504328  6895 sgd_solver.cpp:105] Iteration 4764, lr = 0.00389193
I0412 13:26:36.444794  6895 solver.cpp:218] Iteration 4776 (2.42901 iter/s, 4.94029s/12 iters), loss = 5.26723
I0412 13:26:36.444849  6895 solver.cpp:237]     Train net output #0: loss = 5.26723 (* 1 = 5.26723 loss)
I0412 13:26:36.444860  6895 sgd_solver.cpp:105] Iteration 4776, lr = 0.00388269
I0412 13:26:41.291435  6895 solver.cpp:218] Iteration 4788 (2.47607 iter/s, 4.84639s/12 iters), loss = 5.29397
I0412 13:26:41.291551  6895 solver.cpp:237]     Train net output #0: loss = 5.29397 (* 1 = 5.29397 loss)
I0412 13:26:41.291566  6895 sgd_solver.cpp:105] Iteration 4788, lr = 0.00387347
I0412 13:26:43.237164  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4794.caffemodel
I0412 13:26:45.045081  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4794.solverstate
I0412 13:26:46.235934  6895 solver.cpp:330] Iteration 4794, Testing net (#0)
I0412 13:26:46.235957  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:26:48.786618  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:26:50.686043  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 13:26:50.686091  6895 solver.cpp:397]     Test net output #1: loss = 5.28536 (* 1 = 5.28536 loss)
I0412 13:26:52.524749  6895 solver.cpp:218] Iteration 4800 (1.0683 iter/s, 11.2328s/12 iters), loss = 5.27577
I0412 13:26:52.524806  6895 solver.cpp:237]     Train net output #0: loss = 5.27577 (* 1 = 5.27577 loss)
I0412 13:26:52.524819  6895 sgd_solver.cpp:105] Iteration 4800, lr = 0.00386427
I0412 13:26:57.381206  6895 solver.cpp:218] Iteration 4812 (2.47106 iter/s, 4.85621s/12 iters), loss = 5.26323
I0412 13:26:57.381245  6895 solver.cpp:237]     Train net output #0: loss = 5.26323 (* 1 = 5.26323 loss)
I0412 13:26:57.381256  6895 sgd_solver.cpp:105] Iteration 4812, lr = 0.0038551
I0412 13:27:02.310317  6895 solver.cpp:218] Iteration 4824 (2.43463 iter/s, 4.92887s/12 iters), loss = 5.29073
I0412 13:27:02.310369  6895 solver.cpp:237]     Train net output #0: loss = 5.29073 (* 1 = 5.29073 loss)
I0412 13:27:02.310379  6895 sgd_solver.cpp:105] Iteration 4824, lr = 0.00384594
I0412 13:27:07.216940  6895 solver.cpp:218] Iteration 4836 (2.4458 iter/s, 4.90638s/12 iters), loss = 5.26393
I0412 13:27:07.216996  6895 solver.cpp:237]     Train net output #0: loss = 5.26393 (* 1 = 5.26393 loss)
I0412 13:27:07.217010  6895 sgd_solver.cpp:105] Iteration 4836, lr = 0.00383681
I0412 13:27:08.780073  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:27:12.172859  6895 solver.cpp:218] Iteration 4848 (2.42147 iter/s, 4.95566s/12 iters), loss = 5.26941
I0412 13:27:12.172991  6895 solver.cpp:237]     Train net output #0: loss = 5.26941 (* 1 = 5.26941 loss)
I0412 13:27:12.173000  6895 sgd_solver.cpp:105] Iteration 4848, lr = 0.0038277
I0412 13:27:14.703773  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:27:17.049242  6895 solver.cpp:218] Iteration 4860 (2.461 iter/s, 4.87606s/12 iters), loss = 5.26891
I0412 13:27:17.049289  6895 solver.cpp:237]     Train net output #0: loss = 5.26891 (* 1 = 5.26891 loss)
I0412 13:27:17.049299  6895 sgd_solver.cpp:105] Iteration 4860, lr = 0.00381862
I0412 13:27:21.832018  6895 solver.cpp:218] Iteration 4872 (2.50913 iter/s, 4.78254s/12 iters), loss = 5.26481
I0412 13:27:21.832074  6895 solver.cpp:237]     Train net output #0: loss = 5.26481 (* 1 = 5.26481 loss)
I0412 13:27:21.832087  6895 sgd_solver.cpp:105] Iteration 4872, lr = 0.00380955
I0412 13:27:26.753307  6895 solver.cpp:218] Iteration 4884 (2.43851 iter/s, 4.92104s/12 iters), loss = 5.26865
I0412 13:27:26.753361  6895 solver.cpp:237]     Train net output #0: loss = 5.26865 (* 1 = 5.26865 loss)
I0412 13:27:26.753373  6895 sgd_solver.cpp:105] Iteration 4884, lr = 0.0038005
I0412 13:27:31.073465  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4896.caffemodel
I0412 13:27:33.112591  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4896.solverstate
I0412 13:27:34.294682  6895 solver.cpp:330] Iteration 4896, Testing net (#0)
I0412 13:27:34.294713  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:27:36.908679  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:27:38.881693  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:27:38.881744  6895 solver.cpp:397]     Test net output #1: loss = 5.2863 (* 1 = 5.2863 loss)
I0412 13:27:38.964546  6895 solver.cpp:218] Iteration 4896 (0.982743 iter/s, 12.2107s/12 iters), loss = 5.26911
I0412 13:27:38.964599  6895 solver.cpp:237]     Train net output #0: loss = 5.26911 (* 1 = 5.26911 loss)
I0412 13:27:38.964612  6895 sgd_solver.cpp:105] Iteration 4896, lr = 0.00379148
I0412 13:27:43.051664  6895 solver.cpp:218] Iteration 4908 (2.93621 iter/s, 4.08689s/12 iters), loss = 5.29148
I0412 13:27:43.051782  6895 solver.cpp:237]     Train net output #0: loss = 5.29148 (* 1 = 5.29148 loss)
I0412 13:27:43.051795  6895 sgd_solver.cpp:105] Iteration 4908, lr = 0.00378248
I0412 13:27:48.000706  6895 solver.cpp:218] Iteration 4920 (2.42486 iter/s, 4.94873s/12 iters), loss = 5.26906
I0412 13:27:48.000749  6895 solver.cpp:237]     Train net output #0: loss = 5.26906 (* 1 = 5.26906 loss)
I0412 13:27:48.000759  6895 sgd_solver.cpp:105] Iteration 4920, lr = 0.0037735
I0412 13:27:52.911413  6895 solver.cpp:218] Iteration 4932 (2.44376 iter/s, 4.91047s/12 iters), loss = 5.2652
I0412 13:27:52.911468  6895 solver.cpp:237]     Train net output #0: loss = 5.2652 (* 1 = 5.2652 loss)
I0412 13:27:52.911478  6895 sgd_solver.cpp:105] Iteration 4932, lr = 0.00376454
I0412 13:27:57.786660  6895 solver.cpp:218] Iteration 4944 (2.46154 iter/s, 4.875s/12 iters), loss = 5.26649
I0412 13:27:57.786705  6895 solver.cpp:237]     Train net output #0: loss = 5.26649 (* 1 = 5.26649 loss)
I0412 13:27:57.786712  6895 sgd_solver.cpp:105] Iteration 4944, lr = 0.0037556
I0412 13:28:02.798759  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:28:02.990717  6895 solver.cpp:218] Iteration 4956 (2.30601 iter/s, 5.2038s/12 iters), loss = 5.24959
I0412 13:28:02.990780  6895 solver.cpp:237]     Train net output #0: loss = 5.24959 (* 1 = 5.24959 loss)
I0412 13:28:02.990797  6895 sgd_solver.cpp:105] Iteration 4956, lr = 0.00374669
I0412 13:28:07.854180  6895 solver.cpp:218] Iteration 4968 (2.46751 iter/s, 4.86321s/12 iters), loss = 5.26735
I0412 13:28:07.854244  6895 solver.cpp:237]     Train net output #0: loss = 5.26735 (* 1 = 5.26735 loss)
I0412 13:28:07.854260  6895 sgd_solver.cpp:105] Iteration 4968, lr = 0.00373779
I0412 13:28:12.531075  6895 solver.cpp:218] Iteration 4980 (2.56594 iter/s, 4.67664s/12 iters), loss = 5.29236
I0412 13:28:12.531134  6895 solver.cpp:237]     Train net output #0: loss = 5.29236 (* 1 = 5.29236 loss)
I0412 13:28:12.531148  6895 sgd_solver.cpp:105] Iteration 4980, lr = 0.00372892
I0412 13:28:17.468652  6895 solver.cpp:218] Iteration 4992 (2.43047 iter/s, 4.93732s/12 iters), loss = 5.28742
I0412 13:28:17.468811  6895 solver.cpp:237]     Train net output #0: loss = 5.28742 (* 1 = 5.28742 loss)
I0412 13:28:17.468824  6895 sgd_solver.cpp:105] Iteration 4992, lr = 0.00372006
I0412 13:28:19.410356  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4998.caffemodel
I0412 13:28:24.889210  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4998.solverstate
I0412 13:28:26.075443  6895 solver.cpp:330] Iteration 4998, Testing net (#0)
I0412 13:28:26.075465  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:28:28.460722  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:28:30.489130  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:28:30.489174  6895 solver.cpp:397]     Test net output #1: loss = 5.2862 (* 1 = 5.2862 loss)
I0412 13:28:32.319520  6895 solver.cpp:218] Iteration 5004 (0.808072 iter/s, 14.8502s/12 iters), loss = 5.28023
I0412 13:28:32.319569  6895 solver.cpp:237]     Train net output #0: loss = 5.28023 (* 1 = 5.28023 loss)
I0412 13:28:32.319579  6895 sgd_solver.cpp:105] Iteration 5004, lr = 0.00371123
I0412 13:28:37.024952  6895 solver.cpp:218] Iteration 5016 (2.55037 iter/s, 4.70519s/12 iters), loss = 5.267
I0412 13:28:37.025009  6895 solver.cpp:237]     Train net output #0: loss = 5.267 (* 1 = 5.267 loss)
I0412 13:28:37.025022  6895 sgd_solver.cpp:105] Iteration 5016, lr = 0.00370242
I0412 13:28:41.821082  6895 solver.cpp:218] Iteration 5028 (2.50215 iter/s, 4.79588s/12 iters), loss = 5.24806
I0412 13:28:41.821127  6895 solver.cpp:237]     Train net output #0: loss = 5.24806 (* 1 = 5.24806 loss)
I0412 13:28:41.821135  6895 sgd_solver.cpp:105] Iteration 5028, lr = 0.00369363
I0412 13:28:46.701275  6895 solver.cpp:218] Iteration 5040 (2.45904 iter/s, 4.87995s/12 iters), loss = 5.28829
I0412 13:28:46.701325  6895 solver.cpp:237]     Train net output #0: loss = 5.28829 (* 1 = 5.28829 loss)
I0412 13:28:46.701336  6895 sgd_solver.cpp:105] Iteration 5040, lr = 0.00368486
I0412 13:28:51.489184  6895 solver.cpp:218] Iteration 5052 (2.50644 iter/s, 4.78767s/12 iters), loss = 5.27062
I0412 13:28:51.489338  6895 solver.cpp:237]     Train net output #0: loss = 5.27062 (* 1 = 5.27062 loss)
I0412 13:28:51.489352  6895 sgd_solver.cpp:105] Iteration 5052, lr = 0.00367611
I0412 13:28:53.385823  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:28:56.364923  6895 solver.cpp:218] Iteration 5064 (2.46134 iter/s, 4.87539s/12 iters), loss = 5.29132
I0412 13:28:56.364974  6895 solver.cpp:237]     Train net output #0: loss = 5.29132 (* 1 = 5.29132 loss)
I0412 13:28:56.364986  6895 sgd_solver.cpp:105] Iteration 5064, lr = 0.00366738
I0412 13:29:01.191480  6895 solver.cpp:218] Iteration 5076 (2.48637 iter/s, 4.82632s/12 iters), loss = 5.27018
I0412 13:29:01.191522  6895 solver.cpp:237]     Train net output #0: loss = 5.27018 (* 1 = 5.27018 loss)
I0412 13:29:01.191530  6895 sgd_solver.cpp:105] Iteration 5076, lr = 0.00365868
I0412 13:29:06.228837  6895 solver.cpp:218] Iteration 5088 (2.38232 iter/s, 5.03711s/12 iters), loss = 5.26159
I0412 13:29:06.228879  6895 solver.cpp:237]     Train net output #0: loss = 5.26159 (* 1 = 5.26159 loss)
I0412 13:29:06.228888  6895 sgd_solver.cpp:105] Iteration 5088, lr = 0.00364999
I0412 13:29:10.632246  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5100.caffemodel
I0412 13:29:15.025849  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5100.solverstate
I0412 13:29:19.099771  6895 solver.cpp:330] Iteration 5100, Testing net (#0)
I0412 13:29:19.099795  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:29:21.437418  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:29:23.451236  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:29:23.454355  6895 solver.cpp:397]     Test net output #1: loss = 5.28592 (* 1 = 5.28592 loss)
I0412 13:29:23.538441  6895 solver.cpp:218] Iteration 5100 (0.693284 iter/s, 17.3089s/12 iters), loss = 5.26542
I0412 13:29:23.540064  6895 solver.cpp:237]     Train net output #0: loss = 5.26542 (* 1 = 5.26542 loss)
I0412 13:29:23.540078  6895 sgd_solver.cpp:105] Iteration 5100, lr = 0.00364132
I0412 13:29:27.733309  6895 solver.cpp:218] Iteration 5112 (2.86187 iter/s, 4.19307s/12 iters), loss = 5.26208
I0412 13:29:27.733353  6895 solver.cpp:237]     Train net output #0: loss = 5.26208 (* 1 = 5.26208 loss)
I0412 13:29:27.733362  6895 sgd_solver.cpp:105] Iteration 5112, lr = 0.00363268
I0412 13:29:32.674446  6895 solver.cpp:218] Iteration 5124 (2.42871 iter/s, 4.94089s/12 iters), loss = 5.27586
I0412 13:29:32.674506  6895 solver.cpp:237]     Train net output #0: loss = 5.27586 (* 1 = 5.27586 loss)
I0412 13:29:32.674520  6895 sgd_solver.cpp:105] Iteration 5124, lr = 0.00362405
I0412 13:29:37.450372  6895 solver.cpp:218] Iteration 5136 (2.51273 iter/s, 4.77567s/12 iters), loss = 5.26526
I0412 13:29:37.450430  6895 solver.cpp:237]     Train net output #0: loss = 5.26526 (* 1 = 5.26526 loss)
I0412 13:29:37.450444  6895 sgd_solver.cpp:105] Iteration 5136, lr = 0.00361545
I0412 13:29:41.988744  6895 solver.cpp:218] Iteration 5148 (2.64426 iter/s, 4.53814s/12 iters), loss = 5.2626
I0412 13:29:41.988796  6895 solver.cpp:237]     Train net output #0: loss = 5.2626 (* 1 = 5.2626 loss)
I0412 13:29:41.988809  6895 sgd_solver.cpp:105] Iteration 5148, lr = 0.00360687
I0412 13:29:45.849578  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:29:46.719682  6895 solver.cpp:218] Iteration 5160 (2.53662 iter/s, 4.7307s/12 iters), loss = 5.26358
I0412 13:29:46.719736  6895 solver.cpp:237]     Train net output #0: loss = 5.26358 (* 1 = 5.26358 loss)
I0412 13:29:46.719748  6895 sgd_solver.cpp:105] Iteration 5160, lr = 0.0035983
I0412 13:29:51.591949  6895 solver.cpp:218] Iteration 5172 (2.46304 iter/s, 4.87202s/12 iters), loss = 5.27612
I0412 13:29:51.591998  6895 solver.cpp:237]     Train net output #0: loss = 5.27612 (* 1 = 5.27612 loss)
I0412 13:29:51.592012  6895 sgd_solver.cpp:105] Iteration 5172, lr = 0.00358976
I0412 13:29:56.539909  6895 solver.cpp:218] Iteration 5184 (2.42536 iter/s, 4.94772s/12 iters), loss = 5.27239
I0412 13:29:56.540047  6895 solver.cpp:237]     Train net output #0: loss = 5.27239 (* 1 = 5.27239 loss)
I0412 13:29:56.540058  6895 sgd_solver.cpp:105] Iteration 5184, lr = 0.00358124
I0412 13:30:01.487882  6895 solver.cpp:218] Iteration 5196 (2.4254 iter/s, 4.94763s/12 iters), loss = 5.31076
I0412 13:30:01.487938  6895 solver.cpp:237]     Train net output #0: loss = 5.31076 (* 1 = 5.31076 loss)
I0412 13:30:01.487951  6895 sgd_solver.cpp:105] Iteration 5196, lr = 0.00357273
I0412 13:30:03.369400  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5202.caffemodel
I0412 13:30:04.877647  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5202.solverstate
I0412 13:30:06.062213  6895 solver.cpp:330] Iteration 5202, Testing net (#0)
I0412 13:30:06.062239  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:30:08.506736  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:30:10.561075  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:30:10.561127  6895 solver.cpp:397]     Test net output #1: loss = 5.28609 (* 1 = 5.28609 loss)
I0412 13:30:12.257408  6895 solver.cpp:218] Iteration 5208 (1.1143 iter/s, 10.7691s/12 iters), loss = 5.27321
I0412 13:30:12.257474  6895 solver.cpp:237]     Train net output #0: loss = 5.27321 (* 1 = 5.27321 loss)
I0412 13:30:12.257489  6895 sgd_solver.cpp:105] Iteration 5208, lr = 0.00356425
I0412 13:30:16.994241  6895 solver.cpp:218] Iteration 5220 (2.53347 iter/s, 4.73658s/12 iters), loss = 5.27401
I0412 13:30:16.994294  6895 solver.cpp:237]     Train net output #0: loss = 5.27401 (* 1 = 5.27401 loss)
I0412 13:30:16.994305  6895 sgd_solver.cpp:105] Iteration 5220, lr = 0.00355579
I0412 13:30:22.011768  6895 solver.cpp:218] Iteration 5232 (2.39174 iter/s, 5.01728s/12 iters), loss = 5.27431
I0412 13:30:22.011811  6895 solver.cpp:237]     Train net output #0: loss = 5.27431 (* 1 = 5.27431 loss)
I0412 13:30:22.011821  6895 sgd_solver.cpp:105] Iteration 5232, lr = 0.00354735
I0412 13:30:26.883630  6895 solver.cpp:218] Iteration 5244 (2.46325 iter/s, 4.87162s/12 iters), loss = 5.27078
I0412 13:30:26.883750  6895 solver.cpp:237]     Train net output #0: loss = 5.27078 (* 1 = 5.27078 loss)
I0412 13:30:26.883760  6895 sgd_solver.cpp:105] Iteration 5244, lr = 0.00353892
I0412 13:30:31.721587  6895 solver.cpp:218] Iteration 5256 (2.48055 iter/s, 4.83765s/12 iters), loss = 5.26164
I0412 13:30:31.721630  6895 solver.cpp:237]     Train net output #0: loss = 5.26164 (* 1 = 5.26164 loss)
I0412 13:30:31.721639  6895 sgd_solver.cpp:105] Iteration 5256, lr = 0.00353052
I0412 13:30:32.992293  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:30:36.752290  6895 solver.cpp:218] Iteration 5268 (2.38547 iter/s, 5.03046s/12 iters), loss = 5.27825
I0412 13:30:36.752332  6895 solver.cpp:237]     Train net output #0: loss = 5.27825 (* 1 = 5.27825 loss)
I0412 13:30:36.752341  6895 sgd_solver.cpp:105] Iteration 5268, lr = 0.00352214
I0412 13:30:41.837050  6895 solver.cpp:218] Iteration 5280 (2.36011 iter/s, 5.08452s/12 iters), loss = 5.26596
I0412 13:30:41.837095  6895 solver.cpp:237]     Train net output #0: loss = 5.26596 (* 1 = 5.26596 loss)
I0412 13:30:41.837105  6895 sgd_solver.cpp:105] Iteration 5280, lr = 0.00351378
I0412 13:30:46.809747  6895 solver.cpp:218] Iteration 5292 (2.4133 iter/s, 4.97245s/12 iters), loss = 5.27896
I0412 13:30:46.809790  6895 solver.cpp:237]     Train net output #0: loss = 5.27896 (* 1 = 5.27896 loss)
I0412 13:30:46.809799  6895 sgd_solver.cpp:105] Iteration 5292, lr = 0.00350544
I0412 13:30:51.340171  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5304.caffemodel
I0412 13:30:53.155306  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5304.solverstate
I0412 13:30:54.694319  6895 solver.cpp:330] Iteration 5304, Testing net (#0)
I0412 13:30:54.694339  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:30:57.065486  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:30:59.307193  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:30:59.307237  6895 solver.cpp:397]     Test net output #1: loss = 5.2861 (* 1 = 5.2861 loss)
I0412 13:30:59.391321  6895 solver.cpp:218] Iteration 5304 (0.953815 iter/s, 12.5811s/12 iters), loss = 5.27339
I0412 13:30:59.391368  6895 solver.cpp:237]     Train net output #0: loss = 5.27339 (* 1 = 5.27339 loss)
I0412 13:30:59.391377  6895 sgd_solver.cpp:105] Iteration 5304, lr = 0.00349711
I0412 13:31:03.586249  6895 solver.cpp:218] Iteration 5316 (2.86074 iter/s, 4.19471s/12 iters), loss = 5.26959
I0412 13:31:03.586311  6895 solver.cpp:237]     Train net output #0: loss = 5.26959 (* 1 = 5.26959 loss)
I0412 13:31:03.586326  6895 sgd_solver.cpp:105] Iteration 5316, lr = 0.00348881
I0412 13:31:08.298398  6895 solver.cpp:218] Iteration 5328 (2.54674 iter/s, 4.7119s/12 iters), loss = 5.26215
I0412 13:31:08.298442  6895 solver.cpp:237]     Train net output #0: loss = 5.26215 (* 1 = 5.26215 loss)
I0412 13:31:08.298453  6895 sgd_solver.cpp:105] Iteration 5328, lr = 0.00348053
I0412 13:31:13.213304  6895 solver.cpp:218] Iteration 5340 (2.44167 iter/s, 4.91466s/12 iters), loss = 5.29815
I0412 13:31:13.213358  6895 solver.cpp:237]     Train net output #0: loss = 5.29815 (* 1 = 5.29815 loss)
I0412 13:31:13.213371  6895 sgd_solver.cpp:105] Iteration 5340, lr = 0.00347226
I0412 13:31:18.098623  6895 solver.cpp:218] Iteration 5352 (2.45646 iter/s, 4.88507s/12 iters), loss = 5.27234
I0412 13:31:18.098680  6895 solver.cpp:237]     Train net output #0: loss = 5.27234 (* 1 = 5.27234 loss)
I0412 13:31:18.098696  6895 sgd_solver.cpp:105] Iteration 5352, lr = 0.00346402
I0412 13:31:21.384258  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:31:22.844938  6895 solver.cpp:218] Iteration 5364 (2.52841 iter/s, 4.74607s/12 iters), loss = 5.27619
I0412 13:31:22.844990  6895 solver.cpp:237]     Train net output #0: loss = 5.27619 (* 1 = 5.27619 loss)
I0412 13:31:22.845002  6895 sgd_solver.cpp:105] Iteration 5364, lr = 0.0034558
I0412 13:31:27.657567  6895 solver.cpp:218] Iteration 5376 (2.49356 iter/s, 4.81239s/12 iters), loss = 5.26675
I0412 13:31:27.657696  6895 solver.cpp:237]     Train net output #0: loss = 5.26675 (* 1 = 5.26675 loss)
I0412 13:31:27.657704  6895 sgd_solver.cpp:105] Iteration 5376, lr = 0.00344759
I0412 13:31:32.499547  6895 solver.cpp:218] Iteration 5388 (2.47849 iter/s, 4.84166s/12 iters), loss = 5.2706
I0412 13:31:32.499596  6895 solver.cpp:237]     Train net output #0: loss = 5.2706 (* 1 = 5.2706 loss)
I0412 13:31:32.499606  6895 sgd_solver.cpp:105] Iteration 5388, lr = 0.00343941
I0412 13:31:37.362105  6895 solver.cpp:218] Iteration 5400 (2.46796 iter/s, 4.86232s/12 iters), loss = 5.2685
I0412 13:31:37.362160  6895 solver.cpp:237]     Train net output #0: loss = 5.2685 (* 1 = 5.2685 loss)
I0412 13:31:37.362172  6895 sgd_solver.cpp:105] Iteration 5400, lr = 0.00343124
I0412 13:31:39.290308  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5406.caffemodel
I0412 13:31:40.842424  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5406.solverstate
I0412 13:31:42.901129  6895 solver.cpp:330] Iteration 5406, Testing net (#0)
I0412 13:31:42.901160  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:31:45.288918  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:31:47.420193  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:31:47.420239  6895 solver.cpp:397]     Test net output #1: loss = 5.28594 (* 1 = 5.28594 loss)
I0412 13:31:49.203783  6895 solver.cpp:218] Iteration 5412 (1.01341 iter/s, 11.8412s/12 iters), loss = 5.26411
I0412 13:31:49.203840  6895 solver.cpp:237]     Train net output #0: loss = 5.26411 (* 1 = 5.26411 loss)
I0412 13:31:49.203851  6895 sgd_solver.cpp:105] Iteration 5412, lr = 0.00342309
I0412 13:31:54.113148  6895 solver.cpp:218] Iteration 5424 (2.44443 iter/s, 4.90911s/12 iters), loss = 5.27823
I0412 13:31:54.113209  6895 solver.cpp:237]     Train net output #0: loss = 5.27823 (* 1 = 5.27823 loss)
I0412 13:31:54.113224  6895 sgd_solver.cpp:105] Iteration 5424, lr = 0.00341497
I0412 13:31:59.236507  6895 solver.cpp:218] Iteration 5436 (2.34233 iter/s, 5.1231s/12 iters), loss = 5.26819
I0412 13:31:59.236634  6895 solver.cpp:237]     Train net output #0: loss = 5.26819 (* 1 = 5.26819 loss)
I0412 13:31:59.236645  6895 sgd_solver.cpp:105] Iteration 5436, lr = 0.00340686
I0412 13:32:03.949060  6895 solver.cpp:218] Iteration 5448 (2.54656 iter/s, 4.71224s/12 iters), loss = 5.2775
I0412 13:32:03.949115  6895 solver.cpp:237]     Train net output #0: loss = 5.2775 (* 1 = 5.2775 loss)
I0412 13:32:03.949126  6895 sgd_solver.cpp:105] Iteration 5448, lr = 0.00339877
I0412 13:32:08.749527  6895 solver.cpp:218] Iteration 5460 (2.49988 iter/s, 4.80022s/12 iters), loss = 5.28175
I0412 13:32:08.749577  6895 solver.cpp:237]     Train net output #0: loss = 5.28175 (* 1 = 5.28175 loss)
I0412 13:32:08.749586  6895 sgd_solver.cpp:105] Iteration 5460, lr = 0.0033907
I0412 13:32:09.300616  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:32:13.670817  6895 solver.cpp:218] Iteration 5472 (2.43851 iter/s, 4.92104s/12 iters), loss = 5.2792
I0412 13:32:13.670871  6895 solver.cpp:237]     Train net output #0: loss = 5.2792 (* 1 = 5.2792 loss)
I0412 13:32:13.670882  6895 sgd_solver.cpp:105] Iteration 5472, lr = 0.00338265
I0412 13:32:18.676992  6895 solver.cpp:218] Iteration 5484 (2.39716 iter/s, 5.00592s/12 iters), loss = 5.2735
I0412 13:32:18.677038  6895 solver.cpp:237]     Train net output #0: loss = 5.2735 (* 1 = 5.2735 loss)
I0412 13:32:18.677048  6895 sgd_solver.cpp:105] Iteration 5484, lr = 0.00337462
I0412 13:32:23.344159  6895 solver.cpp:218] Iteration 5496 (2.57128 iter/s, 4.66694s/12 iters), loss = 5.28901
I0412 13:32:23.344208  6895 solver.cpp:237]     Train net output #0: loss = 5.28901 (* 1 = 5.28901 loss)
I0412 13:32:23.344219  6895 sgd_solver.cpp:105] Iteration 5496, lr = 0.00336661
I0412 13:32:28.096690  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5508.caffemodel
I0412 13:32:29.547169  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5508.solverstate
I0412 13:32:30.908538  6895 solver.cpp:330] Iteration 5508, Testing net (#0)
I0412 13:32:30.908565  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:32:33.061473  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:32:35.511104  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:32:35.511163  6895 solver.cpp:397]     Test net output #1: loss = 5.28674 (* 1 = 5.28674 loss)
I0412 13:32:35.595427  6895 solver.cpp:218] Iteration 5508 (0.979532 iter/s, 12.2507s/12 iters), loss = 5.27773
I0412 13:32:35.595491  6895 solver.cpp:237]     Train net output #0: loss = 5.27773 (* 1 = 5.27773 loss)
I0412 13:32:35.595505  6895 sgd_solver.cpp:105] Iteration 5508, lr = 0.00335861
I0412 13:32:39.855979  6895 solver.cpp:218] Iteration 5520 (2.81669 iter/s, 4.26032s/12 iters), loss = 5.27574
I0412 13:32:39.856019  6895 solver.cpp:237]     Train net output #0: loss = 5.27574 (* 1 = 5.27574 loss)
I0412 13:32:39.856029  6895 sgd_solver.cpp:105] Iteration 5520, lr = 0.00335064
I0412 13:32:41.897534  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:32:44.672097  6895 solver.cpp:218] Iteration 5532 (2.49176 iter/s, 4.81588s/12 iters), loss = 5.28641
I0412 13:32:44.672154  6895 solver.cpp:237]     Train net output #0: loss = 5.28641 (* 1 = 5.28641 loss)
I0412 13:32:44.672168  6895 sgd_solver.cpp:105] Iteration 5532, lr = 0.00334268
I0412 13:32:49.616969  6895 solver.cpp:218] Iteration 5544 (2.42688 iter/s, 4.94461s/12 iters), loss = 5.25794
I0412 13:32:49.617030  6895 solver.cpp:237]     Train net output #0: loss = 5.25794 (* 1 = 5.25794 loss)
I0412 13:32:49.617043  6895 sgd_solver.cpp:105] Iteration 5544, lr = 0.00333475
I0412 13:32:54.545686  6895 solver.cpp:218] Iteration 5556 (2.43483 iter/s, 4.92847s/12 iters), loss = 5.27411
I0412 13:32:54.545730  6895 solver.cpp:237]     Train net output #0: loss = 5.27411 (* 1 = 5.27411 loss)
I0412 13:32:54.545738  6895 sgd_solver.cpp:105] Iteration 5556, lr = 0.00332683
I0412 13:32:57.285672  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:32:59.598093  6895 solver.cpp:218] Iteration 5568 (2.37522 iter/s, 5.05216s/12 iters), loss = 5.28006
I0412 13:32:59.598246  6895 solver.cpp:237]     Train net output #0: loss = 5.28006 (* 1 = 5.28006 loss)
I0412 13:32:59.598261  6895 sgd_solver.cpp:105] Iteration 5568, lr = 0.00331893
I0412 13:33:04.264154  6895 solver.cpp:218] Iteration 5580 (2.57195 iter/s, 4.66573s/12 iters), loss = 5.2664
I0412 13:33:04.264211  6895 solver.cpp:237]     Train net output #0: loss = 5.2664 (* 1 = 5.2664 loss)
I0412 13:33:04.264222  6895 sgd_solver.cpp:105] Iteration 5580, lr = 0.00331105
I0412 13:33:09.098276  6895 solver.cpp:218] Iteration 5592 (2.48248 iter/s, 4.83388s/12 iters), loss = 5.27848
I0412 13:33:09.098315  6895 solver.cpp:237]     Train net output #0: loss = 5.27848 (* 1 = 5.27848 loss)
I0412 13:33:09.098325  6895 sgd_solver.cpp:105] Iteration 5592, lr = 0.00330319
I0412 13:33:13.899395  6895 solver.cpp:218] Iteration 5604 (2.49954 iter/s, 4.80089s/12 iters), loss = 5.26953
I0412 13:33:13.899451  6895 solver.cpp:237]     Train net output #0: loss = 5.26953 (* 1 = 5.26953 loss)
I0412 13:33:13.899463  6895 sgd_solver.cpp:105] Iteration 5604, lr = 0.00329535
I0412 13:33:15.765151  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5610.caffemodel
I0412 13:33:23.090137  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5610.solverstate
I0412 13:33:27.909102  6895 solver.cpp:330] Iteration 5610, Testing net (#0)
I0412 13:33:27.909130  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:33:30.069555  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:33:32.359493  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:33:32.359529  6895 solver.cpp:397]     Test net output #1: loss = 5.28603 (* 1 = 5.28603 loss)
I0412 13:33:34.131011  6895 solver.cpp:218] Iteration 5616 (0.593155 iter/s, 20.2308s/12 iters), loss = 5.29231
I0412 13:33:34.131059  6895 solver.cpp:237]     Train net output #0: loss = 5.29231 (* 1 = 5.29231 loss)
I0412 13:33:34.131069  6895 sgd_solver.cpp:105] Iteration 5616, lr = 0.00328752
I0412 13:33:39.085407  6895 solver.cpp:218] Iteration 5628 (2.42221 iter/s, 4.95415s/12 iters), loss = 5.27287
I0412 13:33:39.085449  6895 solver.cpp:237]     Train net output #0: loss = 5.27287 (* 1 = 5.27287 loss)
I0412 13:33:39.085459  6895 sgd_solver.cpp:105] Iteration 5628, lr = 0.00327972
I0412 13:33:44.116813  6895 solver.cpp:218] Iteration 5640 (2.38514 iter/s, 5.03116s/12 iters), loss = 5.26448
I0412 13:33:44.116875  6895 solver.cpp:237]     Train net output #0: loss = 5.26448 (* 1 = 5.26448 loss)
I0412 13:33:44.116890  6895 sgd_solver.cpp:105] Iteration 5640, lr = 0.00327193
I0412 13:33:48.798763  6895 solver.cpp:218] Iteration 5652 (2.56317 iter/s, 4.6817s/12 iters), loss = 5.26716
I0412 13:33:48.798820  6895 solver.cpp:237]     Train net output #0: loss = 5.26716 (* 1 = 5.26716 loss)
I0412 13:33:48.798831  6895 sgd_solver.cpp:105] Iteration 5652, lr = 0.00326416
I0412 13:33:53.709518  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:33:53.869341  6895 solver.cpp:218] Iteration 5664 (2.36672 iter/s, 5.07032s/12 iters), loss = 5.25295
I0412 13:33:53.869397  6895 solver.cpp:237]     Train net output #0: loss = 5.25295 (* 1 = 5.25295 loss)
I0412 13:33:53.869410  6895 sgd_solver.cpp:105] Iteration 5664, lr = 0.00325641
I0412 13:33:58.888731  6895 solver.cpp:218] Iteration 5676 (2.39085 iter/s, 5.01914s/12 iters), loss = 5.26501
I0412 13:33:58.888774  6895 solver.cpp:237]     Train net output #0: loss = 5.26501 (* 1 = 5.26501 loss)
I0412 13:33:58.888783  6895 sgd_solver.cpp:105] Iteration 5676, lr = 0.00324868
I0412 13:34:03.737795  6895 solver.cpp:218] Iteration 5688 (2.47482 iter/s, 4.84883s/12 iters), loss = 5.29441
I0412 13:34:03.737895  6895 solver.cpp:237]     Train net output #0: loss = 5.29441 (* 1 = 5.29441 loss)
I0412 13:34:03.737905  6895 sgd_solver.cpp:105] Iteration 5688, lr = 0.00324097
I0412 13:34:08.787060  6895 solver.cpp:218] Iteration 5700 (2.37672 iter/s, 5.04897s/12 iters), loss = 5.28538
I0412 13:34:08.787101  6895 solver.cpp:237]     Train net output #0: loss = 5.28538 (* 1 = 5.28538 loss)
I0412 13:34:08.787109  6895 sgd_solver.cpp:105] Iteration 5700, lr = 0.00323328
I0412 13:34:13.291131  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5712.caffemodel
I0412 13:34:15.288964  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5712.solverstate
I0412 13:34:16.459830  6895 solver.cpp:330] Iteration 5712, Testing net (#0)
I0412 13:34:16.459858  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:34:18.741084  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:34:21.086102  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:34:21.086148  6895 solver.cpp:397]     Test net output #1: loss = 5.28594 (* 1 = 5.28594 loss)
I0412 13:34:21.170094  6895 solver.cpp:218] Iteration 5712 (0.969108 iter/s, 12.3825s/12 iters), loss = 5.27795
I0412 13:34:21.170172  6895 solver.cpp:237]     Train net output #0: loss = 5.27795 (* 1 = 5.27795 loss)
I0412 13:34:21.170189  6895 sgd_solver.cpp:105] Iteration 5712, lr = 0.0032256
I0412 13:34:25.293248  6895 solver.cpp:218] Iteration 5724 (2.91056 iter/s, 4.12291s/12 iters), loss = 5.26504
I0412 13:34:25.293305  6895 solver.cpp:237]     Train net output #0: loss = 5.26504 (* 1 = 5.26504 loss)
I0412 13:34:25.293318  6895 sgd_solver.cpp:105] Iteration 5724, lr = 0.00321794
I0412 13:34:30.150950  6895 solver.cpp:218] Iteration 5736 (2.47043 iter/s, 4.85745s/12 iters), loss = 5.24704
I0412 13:34:30.151005  6895 solver.cpp:237]     Train net output #0: loss = 5.24704 (* 1 = 5.24704 loss)
I0412 13:34:30.151018  6895 sgd_solver.cpp:105] Iteration 5736, lr = 0.0032103
I0412 13:34:35.091636  6895 solver.cpp:218] Iteration 5748 (2.42894 iter/s, 4.94043s/12 iters), loss = 5.27886
I0412 13:34:35.091795  6895 solver.cpp:237]     Train net output #0: loss = 5.27886 (* 1 = 5.27886 loss)
I0412 13:34:35.091809  6895 sgd_solver.cpp:105] Iteration 5748, lr = 0.00320268
I0412 13:34:39.995301  6895 solver.cpp:218] Iteration 5760 (2.44732 iter/s, 4.90332s/12 iters), loss = 5.26752
I0412 13:34:39.995344  6895 solver.cpp:237]     Train net output #0: loss = 5.26752 (* 1 = 5.26752 loss)
I0412 13:34:39.995352  6895 sgd_solver.cpp:105] Iteration 5760, lr = 0.00319508
I0412 13:34:41.852262  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:34:44.691138  6895 solver.cpp:218] Iteration 5772 (2.55558 iter/s, 4.69561s/12 iters), loss = 5.29442
I0412 13:34:44.691182  6895 solver.cpp:237]     Train net output #0: loss = 5.29442 (* 1 = 5.29442 loss)
I0412 13:34:44.691191  6895 sgd_solver.cpp:105] Iteration 5772, lr = 0.00318749
I0412 13:34:49.639968  6895 solver.cpp:218] Iteration 5784 (2.42494 iter/s, 4.94858s/12 iters), loss = 5.27442
I0412 13:34:49.640020  6895 solver.cpp:237]     Train net output #0: loss = 5.27442 (* 1 = 5.27442 loss)
I0412 13:34:49.640031  6895 sgd_solver.cpp:105] Iteration 5784, lr = 0.00317992
I0412 13:34:54.584456  6895 solver.cpp:218] Iteration 5796 (2.42707 iter/s, 4.94424s/12 iters), loss = 5.26901
I0412 13:34:54.584497  6895 solver.cpp:237]     Train net output #0: loss = 5.26901 (* 1 = 5.26901 loss)
I0412 13:34:54.584506  6895 sgd_solver.cpp:105] Iteration 5796, lr = 0.00317237
I0412 13:34:59.503800  6895 solver.cpp:218] Iteration 5808 (2.43946 iter/s, 4.91911s/12 iters), loss = 5.26413
I0412 13:34:59.503840  6895 solver.cpp:237]     Train net output #0: loss = 5.26413 (* 1 = 5.26413 loss)
I0412 13:34:59.503851  6895 sgd_solver.cpp:105] Iteration 5808, lr = 0.00316484
I0412 13:35:01.366984  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5814.caffemodel
I0412 13:35:02.924129  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5814.solverstate
I0412 13:35:04.093140  6895 solver.cpp:330] Iteration 5814, Testing net (#0)
I0412 13:35:04.093163  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:35:06.308863  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:35:08.602072  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:35:08.602116  6895 solver.cpp:397]     Test net output #1: loss = 5.28578 (* 1 = 5.28578 loss)
I0412 13:35:10.547230  6895 solver.cpp:218] Iteration 5820 (1.08666 iter/s, 11.043s/12 iters), loss = 5.27483
I0412 13:35:10.547273  6895 solver.cpp:237]     Train net output #0: loss = 5.27483 (* 1 = 5.27483 loss)
I0412 13:35:10.547281  6895 sgd_solver.cpp:105] Iteration 5820, lr = 0.00315733
I0412 13:35:15.480343  6895 solver.cpp:218] Iteration 5832 (2.43266 iter/s, 4.93287s/12 iters), loss = 5.27814
I0412 13:35:15.480396  6895 solver.cpp:237]     Train net output #0: loss = 5.27814 (* 1 = 5.27814 loss)
I0412 13:35:15.480407  6895 sgd_solver.cpp:105] Iteration 5832, lr = 0.00314983
I0412 13:35:20.353061  6895 solver.cpp:218] Iteration 5844 (2.46282 iter/s, 4.87247s/12 iters), loss = 5.25762
I0412 13:35:20.353101  6895 solver.cpp:237]     Train net output #0: loss = 5.25762 (* 1 = 5.25762 loss)
I0412 13:35:20.353109  6895 sgd_solver.cpp:105] Iteration 5844, lr = 0.00314235
I0412 13:35:25.217301  6895 solver.cpp:218] Iteration 5856 (2.4671 iter/s, 4.86401s/12 iters), loss = 5.26121
I0412 13:35:25.217350  6895 solver.cpp:237]     Train net output #0: loss = 5.26121 (* 1 = 5.26121 loss)
I0412 13:35:25.217360  6895 sgd_solver.cpp:105] Iteration 5856, lr = 0.00313489
I0412 13:35:29.536834  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:35:30.363936  6895 solver.cpp:218] Iteration 5868 (2.33173 iter/s, 5.14639s/12 iters), loss = 5.25673
I0412 13:35:30.363982  6895 solver.cpp:237]     Train net output #0: loss = 5.25673 (* 1 = 5.25673 loss)
I0412 13:35:30.363992  6895 sgd_solver.cpp:105] Iteration 5868, lr = 0.00312745
I0412 13:35:35.025573  6895 solver.cpp:218] Iteration 5880 (2.57433 iter/s, 4.66141s/12 iters), loss = 5.2781
I0412 13:35:35.025614  6895 solver.cpp:237]     Train net output #0: loss = 5.2781 (* 1 = 5.2781 loss)
I0412 13:35:35.025624  6895 sgd_solver.cpp:105] Iteration 5880, lr = 0.00312002
I0412 13:35:39.740078  6895 solver.cpp:218] Iteration 5892 (2.54546 iter/s, 4.71428s/12 iters), loss = 5.27066
I0412 13:35:39.740151  6895 solver.cpp:237]     Train net output #0: loss = 5.27066 (* 1 = 5.27066 loss)
I0412 13:35:39.740161  6895 sgd_solver.cpp:105] Iteration 5892, lr = 0.00311262
I0412 13:35:44.875800  6895 solver.cpp:218] Iteration 5904 (2.3367 iter/s, 5.13545s/12 iters), loss = 5.30557
I0412 13:35:44.875852  6895 solver.cpp:237]     Train net output #0: loss = 5.30557 (* 1 = 5.30557 loss)
I0412 13:35:44.875864  6895 sgd_solver.cpp:105] Iteration 5904, lr = 0.00310523
I0412 13:35:49.253363  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5916.caffemodel
I0412 13:35:50.808861  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5916.solverstate
I0412 13:35:51.998718  6895 solver.cpp:330] Iteration 5916, Testing net (#0)
I0412 13:35:51.998746  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:35:54.067404  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:35:56.405057  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:35:56.405095  6895 solver.cpp:397]     Test net output #1: loss = 5.28582 (* 1 = 5.28582 loss)
I0412 13:35:56.488471  6895 solver.cpp:218] Iteration 5916 (1.0334 iter/s, 11.6122s/12 iters), loss = 5.27096
I0412 13:35:56.488517  6895 solver.cpp:237]     Train net output #0: loss = 5.27096 (* 1 = 5.27096 loss)
I0412 13:35:56.488525  6895 sgd_solver.cpp:105] Iteration 5916, lr = 0.00309785
I0412 13:36:00.603008  6895 solver.cpp:218] Iteration 5928 (2.91664 iter/s, 4.11432s/12 iters), loss = 5.2726
I0412 13:36:00.603057  6895 solver.cpp:237]     Train net output #0: loss = 5.2726 (* 1 = 5.2726 loss)
I0412 13:36:00.603070  6895 sgd_solver.cpp:105] Iteration 5928, lr = 0.0030905
I0412 13:36:05.331310  6895 solver.cpp:218] Iteration 5940 (2.53804 iter/s, 4.72806s/12 iters), loss = 5.28109
I0412 13:36:05.331360  6895 solver.cpp:237]     Train net output #0: loss = 5.28109 (* 1 = 5.28109 loss)
I0412 13:36:05.331370  6895 sgd_solver.cpp:105] Iteration 5940, lr = 0.00308316
I0412 13:36:10.252862  6895 solver.cpp:218] Iteration 5952 (2.43838 iter/s, 4.92131s/12 iters), loss = 5.27157
I0412 13:36:10.252965  6895 solver.cpp:237]     Train net output #0: loss = 5.27157 (* 1 = 5.27157 loss)
I0412 13:36:10.252977  6895 sgd_solver.cpp:105] Iteration 5952, lr = 0.00307584
I0412 13:36:15.078356  6895 solver.cpp:218] Iteration 5964 (2.48694 iter/s, 4.8252s/12 iters), loss = 5.25963
I0412 13:36:15.078409  6895 solver.cpp:237]     Train net output #0: loss = 5.25963 (* 1 = 5.25963 loss)
I0412 13:36:15.078420  6895 sgd_solver.cpp:105] Iteration 5964, lr = 0.00306854
I0412 13:36:16.354018  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:36:19.953085  6895 solver.cpp:218] Iteration 5976 (2.4618 iter/s, 4.87449s/12 iters), loss = 5.27747
I0412 13:36:19.953123  6895 solver.cpp:237]     Train net output #0: loss = 5.27747 (* 1 = 5.27747 loss)
I0412 13:36:19.953131  6895 sgd_solver.cpp:105] Iteration 5976, lr = 0.00306125
I0412 13:36:24.880209  6895 solver.cpp:218] Iteration 5988 (2.43561 iter/s, 4.92689s/12 iters), loss = 5.26505
I0412 13:36:24.880256  6895 solver.cpp:237]     Train net output #0: loss = 5.26505 (* 1 = 5.26505 loss)
I0412 13:36:24.880266  6895 sgd_solver.cpp:105] Iteration 5988, lr = 0.00305398
I0412 13:36:29.811265  6895 solver.cpp:218] Iteration 6000 (2.43368 iter/s, 4.93081s/12 iters), loss = 5.27855
I0412 13:36:29.811319  6895 solver.cpp:237]     Train net output #0: loss = 5.27855 (* 1 = 5.27855 loss)
I0412 13:36:29.811331  6895 sgd_solver.cpp:105] Iteration 6000, lr = 0.00304673
I0412 13:36:34.715776  6895 solver.cpp:218] Iteration 6012 (2.44685 iter/s, 4.90427s/12 iters), loss = 5.27079
I0412 13:36:34.715818  6895 solver.cpp:237]     Train net output #0: loss = 5.27079 (* 1 = 5.27079 loss)
I0412 13:36:34.715827  6895 sgd_solver.cpp:105] Iteration 6012, lr = 0.0030395
I0412 13:36:36.597273  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6018.caffemodel
I0412 13:36:38.269855  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6018.solverstate
I0412 13:36:39.443819  6895 solver.cpp:330] Iteration 6018, Testing net (#0)
I0412 13:36:39.443846  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:36:41.531219  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:36:43.988647  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:36:43.988678  6895 solver.cpp:397]     Test net output #1: loss = 5.28588 (* 1 = 5.28588 loss)
I0412 13:36:45.709084  6895 solver.cpp:218] Iteration 6024 (1.09162 iter/s, 10.9929s/12 iters), loss = 5.2652
I0412 13:36:45.709128  6895 solver.cpp:237]     Train net output #0: loss = 5.2652 (* 1 = 5.2652 loss)
I0412 13:36:45.709136  6895 sgd_solver.cpp:105] Iteration 6024, lr = 0.00303228
I0412 13:36:50.712137  6895 solver.cpp:218] Iteration 6036 (2.39865 iter/s, 5.00281s/12 iters), loss = 5.25859
I0412 13:36:50.712183  6895 solver.cpp:237]     Train net output #0: loss = 5.25859 (* 1 = 5.25859 loss)
I0412 13:36:50.712193  6895 sgd_solver.cpp:105] Iteration 6036, lr = 0.00302508
I0412 13:36:55.364884  6895 solver.cpp:218] Iteration 6048 (2.57925 iter/s, 4.65252s/12 iters), loss = 5.3033
I0412 13:36:55.364928  6895 solver.cpp:237]     Train net output #0: loss = 5.3033 (* 1 = 5.3033 loss)
I0412 13:36:55.364935  6895 sgd_solver.cpp:105] Iteration 6048, lr = 0.0030179
I0412 13:37:00.223402  6895 solver.cpp:218] Iteration 6060 (2.47001 iter/s, 4.85828s/12 iters), loss = 5.28307
I0412 13:37:00.223451  6895 solver.cpp:237]     Train net output #0: loss = 5.28307 (* 1 = 5.28307 loss)
I0412 13:37:00.223462  6895 sgd_solver.cpp:105] Iteration 6060, lr = 0.00301074
I0412 13:37:03.673185  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:37:05.094075  6895 solver.cpp:218] Iteration 6072 (2.46385 iter/s, 4.87043s/12 iters), loss = 5.27539
I0412 13:37:05.094117  6895 solver.cpp:237]     Train net output #0: loss = 5.27539 (* 1 = 5.27539 loss)
I0412 13:37:05.094126  6895 sgd_solver.cpp:105] Iteration 6072, lr = 0.00300359
I0412 13:37:09.896251  6895 solver.cpp:218] Iteration 6084 (2.49899 iter/s, 4.80194s/12 iters), loss = 5.262
I0412 13:37:09.896302  6895 solver.cpp:237]     Train net output #0: loss = 5.262 (* 1 = 5.262 loss)
I0412 13:37:09.896315  6895 sgd_solver.cpp:105] Iteration 6084, lr = 0.00299646
I0412 13:37:14.604882  6895 solver.cpp:218] Iteration 6096 (2.54864 iter/s, 4.7084s/12 iters), loss = 5.26215
I0412 13:37:14.605000  6895 solver.cpp:237]     Train net output #0: loss = 5.26215 (* 1 = 5.26215 loss)
I0412 13:37:14.605007  6895 sgd_solver.cpp:105] Iteration 6096, lr = 0.00298934
I0412 13:37:19.391943  6895 solver.cpp:218] Iteration 6108 (2.50692 iter/s, 4.78675s/12 iters), loss = 5.27467
I0412 13:37:19.392005  6895 solver.cpp:237]     Train net output #0: loss = 5.27467 (* 1 = 5.27467 loss)
I0412 13:37:19.392022  6895 sgd_solver.cpp:105] Iteration 6108, lr = 0.00298225
I0412 13:37:23.638770  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6120.caffemodel
I0412 13:37:27.979641  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6120.solverstate
I0412 13:37:33.614960  6895 solver.cpp:330] Iteration 6120, Testing net (#0)
I0412 13:37:33.614980  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:37:35.786346  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:37:38.245625  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:37:38.245676  6895 solver.cpp:397]     Test net output #1: loss = 5.28579 (* 1 = 5.28579 loss)
I0412 13:37:38.329437  6895 solver.cpp:218] Iteration 6120 (0.633689 iter/s, 18.9367s/12 iters), loss = 5.26519
I0412 13:37:38.329494  6895 solver.cpp:237]     Train net output #0: loss = 5.26519 (* 1 = 5.26519 loss)
I0412 13:37:38.329507  6895 sgd_solver.cpp:105] Iteration 6120, lr = 0.00297517
I0412 13:37:42.446154  6895 solver.cpp:218] Iteration 6132 (2.9151 iter/s, 4.1165s/12 iters), loss = 5.27403
I0412 13:37:42.446195  6895 solver.cpp:237]     Train net output #0: loss = 5.27403 (* 1 = 5.27403 loss)
I0412 13:37:42.446204  6895 sgd_solver.cpp:105] Iteration 6132, lr = 0.0029681
I0412 13:37:47.281020  6895 solver.cpp:218] Iteration 6144 (2.48209 iter/s, 4.83463s/12 iters), loss = 5.27006
I0412 13:37:47.281127  6895 solver.cpp:237]     Train net output #0: loss = 5.27006 (* 1 = 5.27006 loss)
I0412 13:37:47.281139  6895 sgd_solver.cpp:105] Iteration 6144, lr = 0.00296105
I0412 13:37:52.203467  6895 solver.cpp:218] Iteration 6156 (2.43796 iter/s, 4.92215s/12 iters), loss = 5.27707
I0412 13:37:52.203526  6895 solver.cpp:237]     Train net output #0: loss = 5.27707 (* 1 = 5.27707 loss)
I0412 13:37:52.203539  6895 sgd_solver.cpp:105] Iteration 6156, lr = 0.00295402
I0412 13:37:57.125712  6895 solver.cpp:218] Iteration 6168 (2.43804 iter/s, 4.92199s/12 iters), loss = 5.28815
I0412 13:37:57.125758  6895 solver.cpp:237]     Train net output #0: loss = 5.28815 (* 1 = 5.28815 loss)
I0412 13:37:57.125768  6895 sgd_solver.cpp:105] Iteration 6168, lr = 0.00294701
I0412 13:37:57.775821  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:38:02.209620  6895 solver.cpp:218] Iteration 6180 (2.36051 iter/s, 5.08364s/12 iters), loss = 5.28324
I0412 13:38:02.209672  6895 solver.cpp:237]     Train net output #0: loss = 5.28324 (* 1 = 5.28324 loss)
I0412 13:38:02.209683  6895 sgd_solver.cpp:105] Iteration 6180, lr = 0.00294001
I0412 13:38:07.026821  6895 solver.cpp:218] Iteration 6192 (2.4912 iter/s, 4.81696s/12 iters), loss = 5.26979
I0412 13:38:07.026860  6895 solver.cpp:237]     Train net output #0: loss = 5.26979 (* 1 = 5.26979 loss)
I0412 13:38:07.026868  6895 sgd_solver.cpp:105] Iteration 6192, lr = 0.00293303
I0412 13:38:11.785288  6895 solver.cpp:218] Iteration 6204 (2.52194 iter/s, 4.75823s/12 iters), loss = 5.28823
I0412 13:38:11.785347  6895 solver.cpp:237]     Train net output #0: loss = 5.28823 (* 1 = 5.28823 loss)
I0412 13:38:11.785358  6895 sgd_solver.cpp:105] Iteration 6204, lr = 0.00292607
I0412 13:38:16.648268  6895 solver.cpp:218] Iteration 6216 (2.46775 iter/s, 4.86274s/12 iters), loss = 5.27945
I0412 13:38:16.648325  6895 solver.cpp:237]     Train net output #0: loss = 5.27945 (* 1 = 5.27945 loss)
I0412 13:38:16.648336  6895 sgd_solver.cpp:105] Iteration 6216, lr = 0.00291912
I0412 13:38:18.712692  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6222.caffemodel
I0412 13:38:20.569451  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6222.solverstate
I0412 13:38:21.745668  6895 solver.cpp:330] Iteration 6222, Testing net (#0)
I0412 13:38:21.745695  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:38:23.746981  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:38:25.070951  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:38:26.446919  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:38:26.446950  6895 solver.cpp:397]     Test net output #1: loss = 5.28567 (* 1 = 5.28567 loss)
I0412 13:38:28.332185  6895 solver.cpp:218] Iteration 6228 (1.0271 iter/s, 11.6834s/12 iters), loss = 5.27916
I0412 13:38:28.332229  6895 solver.cpp:237]     Train net output #0: loss = 5.27916 (* 1 = 5.27916 loss)
I0412 13:38:28.332237  6895 sgd_solver.cpp:105] Iteration 6228, lr = 0.00291219
I0412 13:38:33.147109  6895 solver.cpp:218] Iteration 6240 (2.49237 iter/s, 4.8147s/12 iters), loss = 5.2813
I0412 13:38:33.147153  6895 solver.cpp:237]     Train net output #0: loss = 5.2813 (* 1 = 5.2813 loss)
I0412 13:38:33.147163  6895 sgd_solver.cpp:105] Iteration 6240, lr = 0.00290528
I0412 13:38:37.937649  6895 solver.cpp:218] Iteration 6252 (2.50506 iter/s, 4.79031s/12 iters), loss = 5.26073
I0412 13:38:37.937705  6895 solver.cpp:237]     Train net output #0: loss = 5.26073 (* 1 = 5.26073 loss)
I0412 13:38:37.937716  6895 sgd_solver.cpp:105] Iteration 6252, lr = 0.00289838
I0412 13:38:42.782619  6895 solver.cpp:218] Iteration 6264 (2.47692 iter/s, 4.84473s/12 iters), loss = 5.26628
I0412 13:38:42.782658  6895 solver.cpp:237]     Train net output #0: loss = 5.26628 (* 1 = 5.26628 loss)
I0412 13:38:42.782667  6895 sgd_solver.cpp:105] Iteration 6264, lr = 0.0028915
I0412 13:38:45.373041  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:38:47.556684  6895 solver.cpp:218] Iteration 6276 (2.5137 iter/s, 4.77384s/12 iters), loss = 5.27611
I0412 13:38:47.556732  6895 solver.cpp:237]     Train net output #0: loss = 5.27611 (* 1 = 5.27611 loss)
I0412 13:38:47.556744  6895 sgd_solver.cpp:105] Iteration 6276, lr = 0.00288463
I0412 13:38:52.217998  6895 solver.cpp:218] Iteration 6288 (2.5745 iter/s, 4.66109s/12 iters), loss = 5.25624
I0412 13:38:52.218116  6895 solver.cpp:237]     Train net output #0: loss = 5.25624 (* 1 = 5.25624 loss)
I0412 13:38:52.218127  6895 sgd_solver.cpp:105] Iteration 6288, lr = 0.00287779
I0412 13:38:57.235524  6895 solver.cpp:218] Iteration 6300 (2.39176 iter/s, 5.01722s/12 iters), loss = 5.26939
I0412 13:38:57.235571  6895 solver.cpp:237]     Train net output #0: loss = 5.26939 (* 1 = 5.26939 loss)
I0412 13:38:57.235582  6895 sgd_solver.cpp:105] Iteration 6300, lr = 0.00287095
I0412 13:39:01.924994  6895 solver.cpp:218] Iteration 6312 (2.55904 iter/s, 4.68925s/12 iters), loss = 5.26096
I0412 13:39:01.925031  6895 solver.cpp:237]     Train net output #0: loss = 5.26096 (* 1 = 5.26096 loss)
I0412 13:39:01.925040  6895 sgd_solver.cpp:105] Iteration 6312, lr = 0.00286414
I0412 13:39:06.225122  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6324.caffemodel
I0412 13:39:08.836993  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6324.solverstate
I0412 13:39:10.736963  6895 solver.cpp:330] Iteration 6324, Testing net (#0)
I0412 13:39:10.736989  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:39:12.624555  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:39:15.165362  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:39:15.165407  6895 solver.cpp:397]     Test net output #1: loss = 5.28571 (* 1 = 5.28571 loss)
I0412 13:39:15.248889  6895 solver.cpp:218] Iteration 6324 (0.900673 iter/s, 13.3234s/12 iters), loss = 5.29699
I0412 13:39:15.248936  6895 solver.cpp:237]     Train net output #0: loss = 5.29699 (* 1 = 5.29699 loss)
I0412 13:39:15.248946  6895 sgd_solver.cpp:105] Iteration 6324, lr = 0.00285734
I0412 13:39:19.292387  6895 solver.cpp:218] Iteration 6336 (2.96788 iter/s, 4.04329s/12 iters), loss = 5.27112
I0412 13:39:19.292431  6895 solver.cpp:237]     Train net output #0: loss = 5.27112 (* 1 = 5.27112 loss)
I0412 13:39:19.292439  6895 sgd_solver.cpp:105] Iteration 6336, lr = 0.00285055
I0412 13:39:24.400156  6895 solver.cpp:218] Iteration 6348 (2.34947 iter/s, 5.10753s/12 iters), loss = 5.26746
I0412 13:39:24.400290  6895 solver.cpp:237]     Train net output #0: loss = 5.26746 (* 1 = 5.26746 loss)
I0412 13:39:24.400301  6895 sgd_solver.cpp:105] Iteration 6348, lr = 0.00284379
I0412 13:39:29.251276  6895 solver.cpp:218] Iteration 6360 (2.47382 iter/s, 4.8508s/12 iters), loss = 5.26716
I0412 13:39:29.251323  6895 solver.cpp:237]     Train net output #0: loss = 5.26716 (* 1 = 5.26716 loss)
I0412 13:39:29.251334  6895 sgd_solver.cpp:105] Iteration 6360, lr = 0.00283703
I0412 13:39:33.927532  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:39:34.067306  6895 solver.cpp:218] Iteration 6372 (2.4918 iter/s, 4.8158s/12 iters), loss = 5.25294
I0412 13:39:34.067355  6895 solver.cpp:237]     Train net output #0: loss = 5.25294 (* 1 = 5.25294 loss)
I0412 13:39:34.067366  6895 sgd_solver.cpp:105] Iteration 6372, lr = 0.0028303
I0412 13:39:38.845906  6895 solver.cpp:218] Iteration 6384 (2.51132 iter/s, 4.77836s/12 iters), loss = 5.2709
I0412 13:39:38.845973  6895 solver.cpp:237]     Train net output #0: loss = 5.2709 (* 1 = 5.2709 loss)
I0412 13:39:38.845988  6895 sgd_solver.cpp:105] Iteration 6384, lr = 0.00282358
I0412 13:39:43.540444  6895 solver.cpp:218] Iteration 6396 (2.55629 iter/s, 4.6943s/12 iters), loss = 5.29306
I0412 13:39:43.540510  6895 solver.cpp:237]     Train net output #0: loss = 5.29306 (* 1 = 5.29306 loss)
I0412 13:39:43.540529  6895 sgd_solver.cpp:105] Iteration 6396, lr = 0.00281687
I0412 13:39:48.356088  6895 solver.cpp:218] Iteration 6408 (2.492 iter/s, 4.8154s/12 iters), loss = 5.28434
I0412 13:39:48.356135  6895 solver.cpp:237]     Train net output #0: loss = 5.28434 (* 1 = 5.28434 loss)
I0412 13:39:48.356146  6895 sgd_solver.cpp:105] Iteration 6408, lr = 0.00281019
I0412 13:39:52.998720  6895 solver.cpp:218] Iteration 6420 (2.58486 iter/s, 4.64241s/12 iters), loss = 5.28096
I0412 13:39:52.998761  6895 solver.cpp:237]     Train net output #0: loss = 5.28096 (* 1 = 5.28096 loss)
I0412 13:39:52.998771  6895 sgd_solver.cpp:105] Iteration 6420, lr = 0.00280351
I0412 13:39:54.867812  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6426.caffemodel
I0412 13:40:07.479441  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6426.solverstate
I0412 13:40:14.540212  6895 solver.cpp:330] Iteration 6426, Testing net (#0)
I0412 13:40:14.540232  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:40:16.499617  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:40:19.091274  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:40:19.091325  6895 solver.cpp:397]     Test net output #1: loss = 5.28574 (* 1 = 5.28574 loss)
I0412 13:40:20.897730  6895 solver.cpp:218] Iteration 6432 (0.430139 iter/s, 27.898s/12 iters), loss = 5.2658
I0412 13:40:20.897789  6895 solver.cpp:237]     Train net output #0: loss = 5.2658 (* 1 = 5.2658 loss)
I0412 13:40:20.897800  6895 sgd_solver.cpp:105] Iteration 6432, lr = 0.00279686
I0412 13:40:25.632529  6895 solver.cpp:218] Iteration 6444 (2.53456 iter/s, 4.73456s/12 iters), loss = 5.24549
I0412 13:40:25.632633  6895 solver.cpp:237]     Train net output #0: loss = 5.24549 (* 1 = 5.24549 loss)
I0412 13:40:25.632645  6895 sgd_solver.cpp:105] Iteration 6444, lr = 0.00279022
I0412 13:40:30.617074  6895 solver.cpp:218] Iteration 6456 (2.40758 iter/s, 4.98425s/12 iters), loss = 5.27469
I0412 13:40:30.617120  6895 solver.cpp:237]     Train net output #0: loss = 5.27469 (* 1 = 5.27469 loss)
I0412 13:40:30.617130  6895 sgd_solver.cpp:105] Iteration 6456, lr = 0.00278359
I0412 13:40:35.324959  6895 solver.cpp:218] Iteration 6468 (2.54904 iter/s, 4.70765s/12 iters), loss = 5.2664
I0412 13:40:35.325011  6895 solver.cpp:237]     Train net output #0: loss = 5.2664 (* 1 = 5.2664 loss)
I0412 13:40:35.325021  6895 sgd_solver.cpp:105] Iteration 6468, lr = 0.00277698
I0412 13:40:37.255079  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:40:40.101574  6895 solver.cpp:218] Iteration 6480 (2.51236 iter/s, 4.77638s/12 iters), loss = 5.28705
I0412 13:40:40.101619  6895 solver.cpp:237]     Train net output #0: loss = 5.28705 (* 1 = 5.28705 loss)
I0412 13:40:40.101629  6895 sgd_solver.cpp:105] Iteration 6480, lr = 0.00277039
I0412 13:40:44.987815  6895 solver.cpp:218] Iteration 6492 (2.45599 iter/s, 4.88601s/12 iters), loss = 5.27077
I0412 13:40:44.987855  6895 solver.cpp:237]     Train net output #0: loss = 5.27077 (* 1 = 5.27077 loss)
I0412 13:40:44.987864  6895 sgd_solver.cpp:105] Iteration 6492, lr = 0.00276381
I0412 13:40:49.838234  6895 solver.cpp:218] Iteration 6504 (2.47413 iter/s, 4.85019s/12 iters), loss = 5.27175
I0412 13:40:49.838276  6895 solver.cpp:237]     Train net output #0: loss = 5.27175 (* 1 = 5.27175 loss)
I0412 13:40:49.838286  6895 sgd_solver.cpp:105] Iteration 6504, lr = 0.00275725
I0412 13:40:54.426518  6895 solver.cpp:218] Iteration 6516 (2.61548 iter/s, 4.58806s/12 iters), loss = 5.26234
I0412 13:40:54.426563  6895 solver.cpp:237]     Train net output #0: loss = 5.26234 (* 1 = 5.26234 loss)
I0412 13:40:54.426573  6895 sgd_solver.cpp:105] Iteration 6516, lr = 0.00275071
I0412 13:40:59.143615  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6528.caffemodel
I0412 13:41:02.391491  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6528.solverstate
I0412 13:41:03.978857  6895 solver.cpp:330] Iteration 6528, Testing net (#0)
I0412 13:41:03.978878  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:41:05.774297  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:41:08.335192  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:41:08.335243  6895 solver.cpp:397]     Test net output #1: loss = 5.28563 (* 1 = 5.28563 loss)
I0412 13:41:08.418989  6895 solver.cpp:218] Iteration 6528 (0.857638 iter/s, 13.9919s/12 iters), loss = 5.26976
I0412 13:41:08.419044  6895 solver.cpp:237]     Train net output #0: loss = 5.26976 (* 1 = 5.26976 loss)
I0412 13:41:08.419055  6895 sgd_solver.cpp:105] Iteration 6528, lr = 0.00274418
I0412 13:41:12.809306  6895 solver.cpp:218] Iteration 6540 (2.73343 iter/s, 4.39009s/12 iters), loss = 5.27528
I0412 13:41:12.809352  6895 solver.cpp:237]     Train net output #0: loss = 5.27528 (* 1 = 5.27528 loss)
I0412 13:41:12.809361  6895 sgd_solver.cpp:105] Iteration 6540, lr = 0.00273766
I0412 13:41:17.412652  6895 solver.cpp:218] Iteration 6552 (2.60693 iter/s, 4.60312s/12 iters), loss = 5.27352
I0412 13:41:17.412706  6895 solver.cpp:237]     Train net output #0: loss = 5.27352 (* 1 = 5.27352 loss)
I0412 13:41:17.412717  6895 sgd_solver.cpp:105] Iteration 6552, lr = 0.00273116
I0412 13:41:22.226444  6895 solver.cpp:218] Iteration 6564 (2.49296 iter/s, 4.81356s/12 iters), loss = 5.26062
I0412 13:41:22.226485  6895 solver.cpp:237]     Train net output #0: loss = 5.26062 (* 1 = 5.26062 loss)
I0412 13:41:22.226493  6895 sgd_solver.cpp:105] Iteration 6564, lr = 0.00272468
I0412 13:41:26.489658  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:41:27.266633  6895 solver.cpp:218] Iteration 6576 (2.38098 iter/s, 5.03995s/12 iters), loss = 5.25579
I0412 13:41:27.266700  6895 solver.cpp:237]     Train net output #0: loss = 5.25579 (* 1 = 5.25579 loss)
I0412 13:41:27.266714  6895 sgd_solver.cpp:105] Iteration 6576, lr = 0.00271821
I0412 13:41:32.065791  6895 solver.cpp:218] Iteration 6588 (2.50057 iter/s, 4.79891s/12 iters), loss = 5.27942
I0412 13:41:32.065992  6895 solver.cpp:237]     Train net output #0: loss = 5.27942 (* 1 = 5.27942 loss)
I0412 13:41:32.066009  6895 sgd_solver.cpp:105] Iteration 6588, lr = 0.00271175
I0412 13:41:36.781731  6895 solver.cpp:218] Iteration 6600 (2.54475 iter/s, 4.71559s/12 iters), loss = 5.27305
I0412 13:41:36.781778  6895 solver.cpp:237]     Train net output #0: loss = 5.27305 (* 1 = 5.27305 loss)
I0412 13:41:36.781788  6895 sgd_solver.cpp:105] Iteration 6600, lr = 0.00270532
I0412 13:41:41.554836  6895 solver.cpp:218] Iteration 6612 (2.51421 iter/s, 4.77287s/12 iters), loss = 5.30424
I0412 13:41:41.554894  6895 solver.cpp:237]     Train net output #0: loss = 5.30424 (* 1 = 5.30424 loss)
I0412 13:41:41.554906  6895 sgd_solver.cpp:105] Iteration 6612, lr = 0.00269889
I0412 13:41:46.538542  6895 solver.cpp:218] Iteration 6624 (2.40796 iter/s, 4.98346s/12 iters), loss = 5.27384
I0412 13:41:46.538583  6895 solver.cpp:237]     Train net output #0: loss = 5.27384 (* 1 = 5.27384 loss)
I0412 13:41:46.538592  6895 sgd_solver.cpp:105] Iteration 6624, lr = 0.00269248
I0412 13:41:48.435918  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6630.caffemodel
I0412 13:41:49.999883  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6630.solverstate
I0412 13:41:51.860654  6895 solver.cpp:330] Iteration 6630, Testing net (#0)
I0412 13:41:51.860683  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:41:53.694648  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:41:56.289105  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:41:56.289149  6895 solver.cpp:397]     Test net output #1: loss = 5.28575 (* 1 = 5.28575 loss)
I0412 13:41:57.918473  6895 solver.cpp:218] Iteration 6636 (1.05453 iter/s, 11.3795s/12 iters), loss = 5.2755
I0412 13:41:57.918534  6895 solver.cpp:237]     Train net output #0: loss = 5.2755 (* 1 = 5.2755 loss)
I0412 13:41:57.918547  6895 sgd_solver.cpp:105] Iteration 6636, lr = 0.00268609
I0412 13:42:02.629113  6895 solver.cpp:218] Iteration 6648 (2.54756 iter/s, 4.71039s/12 iters), loss = 5.27744
I0412 13:42:02.629246  6895 solver.cpp:237]     Train net output #0: loss = 5.27744 (* 1 = 5.27744 loss)
I0412 13:42:02.629261  6895 sgd_solver.cpp:105] Iteration 6648, lr = 0.00267971
I0412 13:42:07.576968  6895 solver.cpp:218] Iteration 6660 (2.42545 iter/s, 4.94753s/12 iters), loss = 5.28235
I0412 13:42:07.577023  6895 solver.cpp:237]     Train net output #0: loss = 5.28235 (* 1 = 5.28235 loss)
I0412 13:42:07.577035  6895 sgd_solver.cpp:105] Iteration 6660, lr = 0.00267335
I0412 13:42:12.715864  6895 solver.cpp:218] Iteration 6672 (2.33524 iter/s, 5.13865s/12 iters), loss = 5.26567
I0412 13:42:12.715906  6895 solver.cpp:237]     Train net output #0: loss = 5.26567 (* 1 = 5.26567 loss)
I0412 13:42:12.715915  6895 sgd_solver.cpp:105] Iteration 6672, lr = 0.00266701
I0412 13:42:13.990293  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:42:17.533439  6895 solver.cpp:218] Iteration 6684 (2.491 iter/s, 4.81735s/12 iters), loss = 5.27392
I0412 13:42:17.533486  6895 solver.cpp:237]     Train net output #0: loss = 5.27392 (* 1 = 5.27392 loss)
I0412 13:42:17.533497  6895 sgd_solver.cpp:105] Iteration 6684, lr = 0.00266067
I0412 13:42:22.343248  6895 solver.cpp:218] Iteration 6696 (2.49502 iter/s, 4.80958s/12 iters), loss = 5.26904
I0412 13:42:22.343299  6895 solver.cpp:237]     Train net output #0: loss = 5.26904 (* 1 = 5.26904 loss)
I0412 13:42:22.343310  6895 sgd_solver.cpp:105] Iteration 6696, lr = 0.00265436
I0412 13:42:26.995040  6895 solver.cpp:218] Iteration 6708 (2.57978 iter/s, 4.65156s/12 iters), loss = 5.27427
I0412 13:42:26.995096  6895 solver.cpp:237]     Train net output #0: loss = 5.27427 (* 1 = 5.27427 loss)
I0412 13:42:26.995110  6895 sgd_solver.cpp:105] Iteration 6708, lr = 0.00264805
I0412 13:42:31.706368  6895 solver.cpp:218] Iteration 6720 (2.54718 iter/s, 4.7111s/12 iters), loss = 5.27207
I0412 13:42:31.706411  6895 solver.cpp:237]     Train net output #0: loss = 5.27207 (* 1 = 5.27207 loss)
I0412 13:42:31.706420  6895 sgd_solver.cpp:105] Iteration 6720, lr = 0.00264177
I0412 13:42:36.309515  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6732.caffemodel
I0412 13:42:39.940249  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6732.solverstate
I0412 13:42:43.281832  6895 solver.cpp:330] Iteration 6732, Testing net (#0)
I0412 13:42:43.281862  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:42:45.080494  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:42:47.720335  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:42:47.720364  6895 solver.cpp:397]     Test net output #1: loss = 5.28555 (* 1 = 5.28555 loss)
I0412 13:42:47.801769  6895 solver.cpp:218] Iteration 6732 (0.745584 iter/s, 16.0948s/12 iters), loss = 5.26823
I0412 13:42:47.801810  6895 solver.cpp:237]     Train net output #0: loss = 5.26823 (* 1 = 5.26823 loss)
I0412 13:42:47.801820  6895 sgd_solver.cpp:105] Iteration 6732, lr = 0.0026355
I0412 13:42:51.859930  6895 solver.cpp:218] Iteration 6744 (2.95715 iter/s, 4.05796s/12 iters), loss = 5.26029
I0412 13:42:51.859992  6895 solver.cpp:237]     Train net output #0: loss = 5.26029 (* 1 = 5.26029 loss)
I0412 13:42:51.860006  6895 sgd_solver.cpp:105] Iteration 6744, lr = 0.00262924
I0412 13:42:56.664258  6895 solver.cpp:218] Iteration 6756 (2.49788 iter/s, 4.80407s/12 iters), loss = 5.29343
I0412 13:42:56.664330  6895 solver.cpp:237]     Train net output #0: loss = 5.29343 (* 1 = 5.29343 loss)
I0412 13:42:56.664348  6895 sgd_solver.cpp:105] Iteration 6756, lr = 0.002623
I0412 13:43:01.420029  6895 solver.cpp:218] Iteration 6768 (2.52338 iter/s, 4.75552s/12 iters), loss = 5.27273
I0412 13:43:01.420080  6895 solver.cpp:237]     Train net output #0: loss = 5.27273 (* 1 = 5.27273 loss)
I0412 13:43:01.420090  6895 sgd_solver.cpp:105] Iteration 6768, lr = 0.00261677
I0412 13:43:04.823473  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:43:06.310125  6895 solver.cpp:218] Iteration 6780 (2.45406 iter/s, 4.88986s/12 iters), loss = 5.27718
I0412 13:43:06.310235  6895 solver.cpp:237]     Train net output #0: loss = 5.27718 (* 1 = 5.27718 loss)
I0412 13:43:06.310246  6895 sgd_solver.cpp:105] Iteration 6780, lr = 0.00261056
I0412 13:43:11.184474  6895 solver.cpp:218] Iteration 6792 (2.46202 iter/s, 4.87405s/12 iters), loss = 5.26161
I0412 13:43:11.184526  6895 solver.cpp:237]     Train net output #0: loss = 5.26161 (* 1 = 5.26161 loss)
I0412 13:43:11.184538  6895 sgd_solver.cpp:105] Iteration 6792, lr = 0.00260436
I0412 13:43:15.996765  6895 solver.cpp:218] Iteration 6804 (2.49374 iter/s, 4.81205s/12 iters), loss = 5.26957
I0412 13:43:15.996819  6895 solver.cpp:237]     Train net output #0: loss = 5.26957 (* 1 = 5.26957 loss)
I0412 13:43:15.996831  6895 sgd_solver.cpp:105] Iteration 6804, lr = 0.00259817
I0412 13:43:20.616869  6895 solver.cpp:218] Iteration 6816 (2.59748 iter/s, 4.61987s/12 iters), loss = 5.28215
I0412 13:43:20.616925  6895 solver.cpp:237]     Train net output #0: loss = 5.28215 (* 1 = 5.28215 loss)
I0412 13:43:20.616940  6895 sgd_solver.cpp:105] Iteration 6816, lr = 0.00259201
I0412 13:43:25.517310  6895 solver.cpp:218] Iteration 6828 (2.44888 iter/s, 4.9002s/12 iters), loss = 5.26794
I0412 13:43:25.517362  6895 solver.cpp:237]     Train net output #0: loss = 5.26794 (* 1 = 5.26794 loss)
I0412 13:43:25.517374  6895 sgd_solver.cpp:105] Iteration 6828, lr = 0.00258585
I0412 13:43:27.463867  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6834.caffemodel
I0412 13:43:30.380203  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6834.solverstate
I0412 13:43:33.506369  6895 solver.cpp:330] Iteration 6834, Testing net (#0)
I0412 13:43:33.506386  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:43:35.157727  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:43:38.002612  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:43:38.002787  6895 solver.cpp:397]     Test net output #1: loss = 5.28628 (* 1 = 5.28628 loss)
I0412 13:43:40.008605  6895 solver.cpp:218] Iteration 6840 (0.828117 iter/s, 14.4907s/12 iters), loss = 5.27755
I0412 13:43:40.008656  6895 solver.cpp:237]     Train net output #0: loss = 5.27755 (* 1 = 5.27755 loss)
I0412 13:43:40.008666  6895 sgd_solver.cpp:105] Iteration 6840, lr = 0.00257971
I0412 13:43:45.035717  6895 solver.cpp:218] Iteration 6852 (2.38717 iter/s, 5.02687s/12 iters), loss = 5.27518
I0412 13:43:45.035771  6895 solver.cpp:237]     Train net output #0: loss = 5.27518 (* 1 = 5.27518 loss)
I0412 13:43:45.035784  6895 sgd_solver.cpp:105] Iteration 6852, lr = 0.00257359
I0412 13:43:49.680347  6895 solver.cpp:218] Iteration 6864 (2.58376 iter/s, 4.64439s/12 iters), loss = 5.2752
I0412 13:43:49.680404  6895 solver.cpp:237]     Train net output #0: loss = 5.2752 (* 1 = 5.2752 loss)
I0412 13:43:49.680415  6895 sgd_solver.cpp:105] Iteration 6864, lr = 0.00256748
I0412 13:43:54.547785  6895 solver.cpp:218] Iteration 6876 (2.46548 iter/s, 4.8672s/12 iters), loss = 5.28706
I0412 13:43:54.547824  6895 solver.cpp:237]     Train net output #0: loss = 5.28706 (* 1 = 5.28706 loss)
I0412 13:43:54.547834  6895 sgd_solver.cpp:105] Iteration 6876, lr = 0.00256138
I0412 13:43:55.132810  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:43:59.364207  6895 solver.cpp:218] Iteration 6888 (2.49159 iter/s, 4.81619s/12 iters), loss = 5.28294
I0412 13:43:59.364259  6895 solver.cpp:237]     Train net output #0: loss = 5.28294 (* 1 = 5.28294 loss)
I0412 13:43:59.364271  6895 sgd_solver.cpp:105] Iteration 6888, lr = 0.0025553
I0412 13:44:04.263530  6895 solver.cpp:218] Iteration 6900 (2.44944 iter/s, 4.89908s/12 iters), loss = 5.2698
I0412 13:44:04.263583  6895 solver.cpp:237]     Train net output #0: loss = 5.2698 (* 1 = 5.2698 loss)
I0412 13:44:04.263599  6895 sgd_solver.cpp:105] Iteration 6900, lr = 0.00254923
I0412 13:44:09.116158  6895 solver.cpp:218] Iteration 6912 (2.47301 iter/s, 4.85239s/12 iters), loss = 5.28973
I0412 13:44:09.116271  6895 solver.cpp:237]     Train net output #0: loss = 5.28973 (* 1 = 5.28973 loss)
I0412 13:44:09.116284  6895 sgd_solver.cpp:105] Iteration 6912, lr = 0.00254318
I0412 13:44:13.977562  6895 solver.cpp:218] Iteration 6924 (2.46857 iter/s, 4.86111s/12 iters), loss = 5.28445
I0412 13:44:13.977617  6895 solver.cpp:237]     Train net output #0: loss = 5.28445 (* 1 = 5.28445 loss)
I0412 13:44:13.977629  6895 sgd_solver.cpp:105] Iteration 6924, lr = 0.00253714
I0412 13:44:18.693773  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6936.caffemodel
I0412 13:44:21.970728  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6936.solverstate
I0412 13:44:24.203423  6895 solver.cpp:330] Iteration 6936, Testing net (#0)
I0412 13:44:24.203450  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:44:24.806660  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:44:26.115306  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:44:28.866317  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:44:28.866364  6895 solver.cpp:397]     Test net output #1: loss = 5.28602 (* 1 = 5.28602 loss)
I0412 13:44:28.949666  6895 solver.cpp:218] Iteration 6936 (0.801523 iter/s, 14.9715s/12 iters), loss = 5.28441
I0412 13:44:28.949710  6895 solver.cpp:237]     Train net output #0: loss = 5.28441 (* 1 = 5.28441 loss)
I0412 13:44:28.949721  6895 sgd_solver.cpp:105] Iteration 6936, lr = 0.00253112
I0412 13:44:32.958045  6895 solver.cpp:218] Iteration 6948 (2.99388 iter/s, 4.00818s/12 iters), loss = 5.27363
I0412 13:44:32.958096  6895 solver.cpp:237]     Train net output #0: loss = 5.27363 (* 1 = 5.27363 loss)
I0412 13:44:32.958108  6895 sgd_solver.cpp:105] Iteration 6948, lr = 0.00252511
I0412 13:44:37.808761  6895 solver.cpp:218] Iteration 6960 (2.47398 iter/s, 4.85047s/12 iters), loss = 5.26304
I0412 13:44:37.808828  6895 solver.cpp:237]     Train net output #0: loss = 5.26304 (* 1 = 5.26304 loss)
I0412 13:44:37.808843  6895 sgd_solver.cpp:105] Iteration 6960, lr = 0.00251911
I0412 13:44:42.692117  6895 solver.cpp:218] Iteration 6972 (2.45746 iter/s, 4.8831s/12 iters), loss = 5.26772
I0412 13:44:42.692260  6895 solver.cpp:237]     Train net output #0: loss = 5.26772 (* 1 = 5.26772 loss)
I0412 13:44:42.692274  6895 sgd_solver.cpp:105] Iteration 6972, lr = 0.00251313
I0412 13:44:45.395277  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:44:47.572077  6895 solver.cpp:218] Iteration 6984 (2.4592 iter/s, 4.87964s/12 iters), loss = 5.27758
I0412 13:44:47.572126  6895 solver.cpp:237]     Train net output #0: loss = 5.27758 (* 1 = 5.27758 loss)
I0412 13:44:47.572137  6895 sgd_solver.cpp:105] Iteration 6984, lr = 0.00250717
I0412 13:44:52.570802  6895 solver.cpp:218] Iteration 6996 (2.40073 iter/s, 4.99849s/12 iters), loss = 5.25957
I0412 13:44:52.570852  6895 solver.cpp:237]     Train net output #0: loss = 5.25957 (* 1 = 5.25957 loss)
I0412 13:44:52.570864  6895 sgd_solver.cpp:105] Iteration 6996, lr = 0.00250121
I0412 13:44:57.547106  6895 solver.cpp:218] Iteration 7008 (2.41155 iter/s, 4.97606s/12 iters), loss = 5.25857
I0412 13:44:57.547153  6895 solver.cpp:237]     Train net output #0: loss = 5.25857 (* 1 = 5.25857 loss)
I0412 13:44:57.547163  6895 sgd_solver.cpp:105] Iteration 7008, lr = 0.00249528
I0412 13:45:02.396675  6895 solver.cpp:218] Iteration 7020 (2.47457 iter/s, 4.84933s/12 iters), loss = 5.26369
I0412 13:45:02.396721  6895 solver.cpp:237]     Train net output #0: loss = 5.26369 (* 1 = 5.26369 loss)
I0412 13:45:02.396731  6895 sgd_solver.cpp:105] Iteration 7020, lr = 0.00248935
I0412 13:45:07.197185  6895 solver.cpp:218] Iteration 7032 (2.49986 iter/s, 4.80027s/12 iters), loss = 5.30196
I0412 13:45:07.197242  6895 solver.cpp:237]     Train net output #0: loss = 5.30196 (* 1 = 5.30196 loss)
I0412 13:45:07.197254  6895 sgd_solver.cpp:105] Iteration 7032, lr = 0.00248344
I0412 13:45:09.187597  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7038.caffemodel
I0412 13:45:11.801023  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7038.solverstate
I0412 13:45:16.303122  6895 solver.cpp:330] Iteration 7038, Testing net (#0)
I0412 13:45:16.303182  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:45:18.124492  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:45:21.245050  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:45:21.245081  6895 solver.cpp:397]     Test net output #1: loss = 5.28583 (* 1 = 5.28583 loss)
I0412 13:45:23.066139  6895 solver.cpp:218] Iteration 7044 (0.756224 iter/s, 15.8683s/12 iters), loss = 5.27244
I0412 13:45:23.066195  6895 solver.cpp:237]     Train net output #0: loss = 5.27244 (* 1 = 5.27244 loss)
I0412 13:45:23.066207  6895 sgd_solver.cpp:105] Iteration 7044, lr = 0.00247755
I0412 13:45:28.039779  6895 solver.cpp:218] Iteration 7056 (2.41284 iter/s, 4.97339s/12 iters), loss = 5.27173
I0412 13:45:28.039827  6895 solver.cpp:237]     Train net output #0: loss = 5.27173 (* 1 = 5.27173 loss)
I0412 13:45:28.039839  6895 sgd_solver.cpp:105] Iteration 7056, lr = 0.00247166
I0412 13:45:32.890240  6895 solver.cpp:218] Iteration 7068 (2.47411 iter/s, 4.85022s/12 iters), loss = 5.26719
I0412 13:45:32.890292  6895 solver.cpp:237]     Train net output #0: loss = 5.26719 (* 1 = 5.26719 loss)
I0412 13:45:32.890303  6895 sgd_solver.cpp:105] Iteration 7068, lr = 0.0024658
I0412 13:45:37.773720  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:45:37.886708  6895 solver.cpp:218] Iteration 7080 (2.40182 iter/s, 4.99621s/12 iters), loss = 5.24708
I0412 13:45:37.886772  6895 solver.cpp:237]     Train net output #0: loss = 5.24708 (* 1 = 5.24708 loss)
I0412 13:45:37.886786  6895 sgd_solver.cpp:105] Iteration 7080, lr = 0.00245994
I0412 13:45:42.794708  6895 solver.cpp:218] Iteration 7092 (2.44511 iter/s, 4.90775s/12 iters), loss = 5.2718
I0412 13:45:42.794765  6895 solver.cpp:237]     Train net output #0: loss = 5.2718 (* 1 = 5.2718 loss)
I0412 13:45:42.794777  6895 sgd_solver.cpp:105] Iteration 7092, lr = 0.0024541
I0412 13:45:47.575938  6895 solver.cpp:218] Iteration 7104 (2.50994 iter/s, 4.78099s/12 iters), loss = 5.29432
I0412 13:45:47.576054  6895 solver.cpp:237]     Train net output #0: loss = 5.29432 (* 1 = 5.29432 loss)
I0412 13:45:47.576067  6895 sgd_solver.cpp:105] Iteration 7104, lr = 0.00244827
I0412 13:45:52.397755  6895 solver.cpp:218] Iteration 7116 (2.48885 iter/s, 4.82151s/12 iters), loss = 5.2757
I0412 13:45:52.397809  6895 solver.cpp:237]     Train net output #0: loss = 5.2757 (* 1 = 5.2757 loss)
I0412 13:45:52.397819  6895 sgd_solver.cpp:105] Iteration 7116, lr = 0.00244246
I0412 13:45:57.266101  6895 solver.cpp:218] Iteration 7128 (2.46503 iter/s, 4.8681s/12 iters), loss = 5.2744
I0412 13:45:57.266160  6895 solver.cpp:237]     Train net output #0: loss = 5.2744 (* 1 = 5.2744 loss)
I0412 13:45:57.266173  6895 sgd_solver.cpp:105] Iteration 7128, lr = 0.00243666
I0412 13:46:01.742245  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7140.caffemodel
I0412 13:46:03.394018  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7140.solverstate
I0412 13:46:04.577915  6895 solver.cpp:330] Iteration 7140, Testing net (#0)
I0412 13:46:04.577945  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:46:06.220700  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:46:09.034777  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:46:09.034824  6895 solver.cpp:397]     Test net output #1: loss = 5.28601 (* 1 = 5.28601 loss)
I0412 13:46:09.118556  6895 solver.cpp:218] Iteration 7140 (1.01249 iter/s, 11.852s/12 iters), loss = 5.26295
I0412 13:46:09.118607  6895 solver.cpp:237]     Train net output #0: loss = 5.26295 (* 1 = 5.26295 loss)
I0412 13:46:09.118618  6895 sgd_solver.cpp:105] Iteration 7140, lr = 0.00243088
I0412 13:46:13.317937  6895 solver.cpp:218] Iteration 7152 (2.85771 iter/s, 4.19916s/12 iters), loss = 5.24562
I0412 13:46:13.318008  6895 solver.cpp:237]     Train net output #0: loss = 5.24562 (* 1 = 5.24562 loss)
I0412 13:46:13.318020  6895 sgd_solver.cpp:105] Iteration 7152, lr = 0.00242511
I0412 13:46:18.558890  6895 solver.cpp:218] Iteration 7164 (2.28978 iter/s, 5.24068s/12 iters), loss = 5.27473
I0412 13:46:18.558982  6895 solver.cpp:237]     Train net output #0: loss = 5.27473 (* 1 = 5.27473 loss)
I0412 13:46:18.558992  6895 sgd_solver.cpp:105] Iteration 7164, lr = 0.00241935
I0412 13:46:23.470068  6895 solver.cpp:218] Iteration 7176 (2.44355 iter/s, 4.9109s/12 iters), loss = 5.25762
I0412 13:46:23.470122  6895 solver.cpp:237]     Train net output #0: loss = 5.25762 (* 1 = 5.25762 loss)
I0412 13:46:23.470135  6895 sgd_solver.cpp:105] Iteration 7176, lr = 0.0024136
I0412 13:46:25.416138  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:46:28.219134  6895 solver.cpp:218] Iteration 7188 (2.52694 iter/s, 4.74883s/12 iters), loss = 5.27708
I0412 13:46:28.219195  6895 solver.cpp:237]     Train net output #0: loss = 5.27708 (* 1 = 5.27708 loss)
I0412 13:46:28.219210  6895 sgd_solver.cpp:105] Iteration 7188, lr = 0.00240787
I0412 13:46:32.974514  6895 solver.cpp:218] Iteration 7200 (2.52359 iter/s, 4.75514s/12 iters), loss = 5.26986
I0412 13:46:32.974560  6895 solver.cpp:237]     Train net output #0: loss = 5.26986 (* 1 = 5.26986 loss)
I0412 13:46:32.974570  6895 sgd_solver.cpp:105] Iteration 7200, lr = 0.00240216
I0412 13:46:37.668282  6895 solver.cpp:218] Iteration 7212 (2.55671 iter/s, 4.69354s/12 iters), loss = 5.28129
I0412 13:46:37.668339  6895 solver.cpp:237]     Train net output #0: loss = 5.28129 (* 1 = 5.28129 loss)
I0412 13:46:37.668351  6895 sgd_solver.cpp:105] Iteration 7212, lr = 0.00239645
I0412 13:46:42.574501  6895 solver.cpp:218] Iteration 7224 (2.446 iter/s, 4.90596s/12 iters), loss = 5.26338
I0412 13:46:42.574555  6895 solver.cpp:237]     Train net output #0: loss = 5.26338 (* 1 = 5.26338 loss)
I0412 13:46:42.574568  6895 sgd_solver.cpp:105] Iteration 7224, lr = 0.00239076
I0412 13:46:47.579756  6895 solver.cpp:218] Iteration 7236 (2.3976 iter/s, 5.00501s/12 iters), loss = 5.27396
I0412 13:46:47.579823  6895 solver.cpp:237]     Train net output #0: loss = 5.27396 (* 1 = 5.27396 loss)
I0412 13:46:47.579838  6895 sgd_solver.cpp:105] Iteration 7236, lr = 0.00238509
I0412 13:46:49.503324  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7242.caffemodel
I0412 13:46:51.354133  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7242.solverstate
I0412 13:46:53.141826  6895 solver.cpp:330] Iteration 7242, Testing net (#0)
I0412 13:46:53.141855  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:46:54.801981  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:46:57.677028  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:46:57.677079  6895 solver.cpp:397]     Test net output #1: loss = 5.28578 (* 1 = 5.28578 loss)
I0412 13:46:59.513290  6895 solver.cpp:218] Iteration 7248 (1.00561 iter/s, 11.933s/12 iters), loss = 5.27335
I0412 13:46:59.513351  6895 solver.cpp:237]     Train net output #0: loss = 5.27335 (* 1 = 5.27335 loss)
I0412 13:46:59.513366  6895 sgd_solver.cpp:105] Iteration 7248, lr = 0.00237942
I0412 13:47:04.443645  6895 solver.cpp:218] Iteration 7260 (2.43403 iter/s, 4.9301s/12 iters), loss = 5.27501
I0412 13:47:04.443693  6895 solver.cpp:237]     Train net output #0: loss = 5.27501 (* 1 = 5.27501 loss)
I0412 13:47:04.443704  6895 sgd_solver.cpp:105] Iteration 7260, lr = 0.00237378
I0412 13:47:09.516691  6895 solver.cpp:218] Iteration 7272 (2.36556 iter/s, 5.0728s/12 iters), loss = 5.253
I0412 13:47:09.516736  6895 solver.cpp:237]     Train net output #0: loss = 5.253 (* 1 = 5.253 loss)
I0412 13:47:09.516743  6895 sgd_solver.cpp:105] Iteration 7272, lr = 0.00236814
I0412 13:47:13.579887  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:47:14.375769  6895 solver.cpp:218] Iteration 7284 (2.46972 iter/s, 4.85884s/12 iters), loss = 5.25803
I0412 13:47:14.375815  6895 solver.cpp:237]     Train net output #0: loss = 5.25803 (* 1 = 5.25803 loss)
I0412 13:47:14.375825  6895 sgd_solver.cpp:105] Iteration 7284, lr = 0.00236252
I0412 13:47:19.226809  6895 solver.cpp:218] Iteration 7296 (2.47382 iter/s, 4.85081s/12 iters), loss = 5.28207
I0412 13:47:19.226864  6895 solver.cpp:237]     Train net output #0: loss = 5.28207 (* 1 = 5.28207 loss)
I0412 13:47:19.226876  6895 sgd_solver.cpp:105] Iteration 7296, lr = 0.00235691
I0412 13:47:23.940492  6895 solver.cpp:218] Iteration 7308 (2.54591 iter/s, 4.71344s/12 iters), loss = 5.28026
I0412 13:47:23.940623  6895 solver.cpp:237]     Train net output #0: loss = 5.28026 (* 1 = 5.28026 loss)
I0412 13:47:23.940635  6895 sgd_solver.cpp:105] Iteration 7308, lr = 0.00235131
I0412 13:47:28.823060  6895 solver.cpp:218] Iteration 7320 (2.45788 iter/s, 4.88225s/12 iters), loss = 5.29223
I0412 13:47:28.823108  6895 solver.cpp:237]     Train net output #0: loss = 5.29223 (* 1 = 5.29223 loss)
I0412 13:47:28.823117  6895 sgd_solver.cpp:105] Iteration 7320, lr = 0.00234573
I0412 13:47:33.720101  6895 solver.cpp:218] Iteration 7332 (2.45058 iter/s, 4.8968s/12 iters), loss = 5.26847
I0412 13:47:33.720160  6895 solver.cpp:237]     Train net output #0: loss = 5.26847 (* 1 = 5.26847 loss)
I0412 13:47:33.720175  6895 sgd_solver.cpp:105] Iteration 7332, lr = 0.00234016
I0412 13:47:38.076009  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7344.caffemodel
I0412 13:47:42.023764  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7344.solverstate
I0412 13:47:47.565821  6895 solver.cpp:330] Iteration 7344, Testing net (#0)
I0412 13:47:47.565852  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:47:49.143286  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:47:52.304919  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:47:52.304958  6895 solver.cpp:397]     Test net output #1: loss = 5.28667 (* 1 = 5.28667 loss)
I0412 13:47:52.388525  6895 solver.cpp:218] Iteration 7344 (0.642822 iter/s, 18.6677s/12 iters), loss = 5.28007
I0412 13:47:52.388583  6895 solver.cpp:237]     Train net output #0: loss = 5.28007 (* 1 = 5.28007 loss)
I0412 13:47:52.388597  6895 sgd_solver.cpp:105] Iteration 7344, lr = 0.0023346
I0412 13:47:56.689085  6895 solver.cpp:218] Iteration 7356 (2.79048 iter/s, 4.30033s/12 iters), loss = 5.27919
I0412 13:47:56.689230  6895 solver.cpp:237]     Train net output #0: loss = 5.27919 (* 1 = 5.27919 loss)
I0412 13:47:56.689242  6895 sgd_solver.cpp:105] Iteration 7356, lr = 0.00232906
I0412 13:48:01.514361  6895 solver.cpp:218] Iteration 7368 (2.48708 iter/s, 4.82494s/12 iters), loss = 5.27634
I0412 13:48:01.514418  6895 solver.cpp:237]     Train net output #0: loss = 5.27634 (* 1 = 5.27634 loss)
I0412 13:48:01.514430  6895 sgd_solver.cpp:105] Iteration 7368, lr = 0.00232353
I0412 13:48:06.327016  6895 solver.cpp:218] Iteration 7380 (2.49355 iter/s, 4.81241s/12 iters), loss = 5.26414
I0412 13:48:06.327064  6895 solver.cpp:237]     Train net output #0: loss = 5.26414 (* 1 = 5.26414 loss)
I0412 13:48:06.327077  6895 sgd_solver.cpp:105] Iteration 7380, lr = 0.00231802
I0412 13:48:07.666481  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:48:11.122071  6895 solver.cpp:218] Iteration 7392 (2.5027 iter/s, 4.79482s/12 iters), loss = 5.27584
I0412 13:48:11.122117  6895 solver.cpp:237]     Train net output #0: loss = 5.27584 (* 1 = 5.27584 loss)
I0412 13:48:11.122126  6895 sgd_solver.cpp:105] Iteration 7392, lr = 0.00231251
I0412 13:48:15.948315  6895 solver.cpp:218] Iteration 7404 (2.48653 iter/s, 4.82601s/12 iters), loss = 5.2663
I0412 13:48:15.948365  6895 solver.cpp:237]     Train net output #0: loss = 5.2663 (* 1 = 5.2663 loss)
I0412 13:48:15.948376  6895 sgd_solver.cpp:105] Iteration 7404, lr = 0.00230702
I0412 13:48:20.835816  6895 solver.cpp:218] Iteration 7416 (2.45536 iter/s, 4.88726s/12 iters), loss = 5.26561
I0412 13:48:20.835861  6895 solver.cpp:237]     Train net output #0: loss = 5.26561 (* 1 = 5.26561 loss)
I0412 13:48:20.835870  6895 sgd_solver.cpp:105] Iteration 7416, lr = 0.00230154
I0412 13:48:25.656749  6895 solver.cpp:218] Iteration 7428 (2.48926 iter/s, 4.8207s/12 iters), loss = 5.27881
I0412 13:48:25.656788  6895 solver.cpp:237]     Train net output #0: loss = 5.27881 (* 1 = 5.27881 loss)
I0412 13:48:25.656798  6895 sgd_solver.cpp:105] Iteration 7428, lr = 0.00229608
I0412 13:48:30.519243  6895 solver.cpp:218] Iteration 7440 (2.46799 iter/s, 4.86227s/12 iters), loss = 5.25924
I0412 13:48:30.520064  6895 solver.cpp:237]     Train net output #0: loss = 5.25924 (* 1 = 5.25924 loss)
I0412 13:48:30.520076  6895 sgd_solver.cpp:105] Iteration 7440, lr = 0.00229063
I0412 13:48:32.468983  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7446.caffemodel
I0412 13:48:34.702786  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7446.solverstate
I0412 13:48:36.798013  6895 solver.cpp:330] Iteration 7446, Testing net (#0)
I0412 13:48:36.798041  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:48:38.348562  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:48:41.346982  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:48:41.347031  6895 solver.cpp:397]     Test net output #1: loss = 5.28593 (* 1 = 5.28593 loss)
I0412 13:48:43.228009  6895 solver.cpp:218] Iteration 7452 (0.944326 iter/s, 12.7075s/12 iters), loss = 5.26598
I0412 13:48:43.228063  6895 solver.cpp:237]     Train net output #0: loss = 5.26598 (* 1 = 5.26598 loss)
I0412 13:48:43.228076  6895 sgd_solver.cpp:105] Iteration 7452, lr = 0.00228519
I0412 13:48:48.183297  6895 solver.cpp:218] Iteration 7464 (2.42178 iter/s, 4.95504s/12 iters), loss = 5.28774
I0412 13:48:48.183341  6895 solver.cpp:237]     Train net output #0: loss = 5.28774 (* 1 = 5.28774 loss)
I0412 13:48:48.183351  6895 sgd_solver.cpp:105] Iteration 7464, lr = 0.00227976
I0412 13:48:52.994237  6895 solver.cpp:218] Iteration 7476 (2.49443 iter/s, 4.81071s/12 iters), loss = 5.27543
I0412 13:48:52.994282  6895 solver.cpp:237]     Train net output #0: loss = 5.27543 (* 1 = 5.27543 loss)
I0412 13:48:52.994289  6895 sgd_solver.cpp:105] Iteration 7476, lr = 0.00227435
I0412 13:48:56.296856  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:48:57.760563  6895 solver.cpp:218] Iteration 7488 (2.51778 iter/s, 4.7661s/12 iters), loss = 5.2688
I0412 13:48:57.760613  6895 solver.cpp:237]     Train net output #0: loss = 5.2688 (* 1 = 5.2688 loss)
I0412 13:48:57.760627  6895 sgd_solver.cpp:105] Iteration 7488, lr = 0.00226895
I0412 13:49:02.460621  6895 solver.cpp:218] Iteration 7500 (2.55329 iter/s, 4.69983s/12 iters), loss = 5.26266
I0412 13:49:02.460778  6895 solver.cpp:237]     Train net output #0: loss = 5.26266 (* 1 = 5.26266 loss)
I0412 13:49:02.460793  6895 sgd_solver.cpp:105] Iteration 7500, lr = 0.00226357
I0412 13:49:07.582257  6895 solver.cpp:218] Iteration 7512 (2.34316 iter/s, 5.12129s/12 iters), loss = 5.26313
I0412 13:49:07.582307  6895 solver.cpp:237]     Train net output #0: loss = 5.26313 (* 1 = 5.26313 loss)
I0412 13:49:07.582319  6895 sgd_solver.cpp:105] Iteration 7512, lr = 0.00225819
I0412 13:49:12.456634  6895 solver.cpp:218] Iteration 7524 (2.46197 iter/s, 4.87414s/12 iters), loss = 5.26963
I0412 13:49:12.456687  6895 solver.cpp:237]     Train net output #0: loss = 5.26963 (* 1 = 5.26963 loss)
I0412 13:49:12.456699  6895 sgd_solver.cpp:105] Iteration 7524, lr = 0.00225283
I0412 13:49:17.575781  6895 solver.cpp:218] Iteration 7536 (2.34425 iter/s, 5.1189s/12 iters), loss = 5.26416
I0412 13:49:17.575826  6895 solver.cpp:237]     Train net output #0: loss = 5.26416 (* 1 = 5.26416 loss)
I0412 13:49:17.575836  6895 sgd_solver.cpp:105] Iteration 7536, lr = 0.00224748
I0412 13:49:22.155987  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7548.caffemodel
I0412 13:49:24.116559  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7548.solverstate
I0412 13:49:25.323973  6895 solver.cpp:330] Iteration 7548, Testing net (#0)
I0412 13:49:25.323999  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:49:26.869134  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:49:29.874447  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:49:29.874486  6895 solver.cpp:397]     Test net output #1: loss = 5.28607 (* 1 = 5.28607 loss)
I0412 13:49:29.957892  6895 solver.cpp:218] Iteration 7548 (0.96918 iter/s, 12.3816s/12 iters), loss = 5.27968
I0412 13:49:29.957949  6895 solver.cpp:237]     Train net output #0: loss = 5.27968 (* 1 = 5.27968 loss)
I0412 13:49:29.957984  6895 sgd_solver.cpp:105] Iteration 7548, lr = 0.00224215
I0412 13:49:34.491776  6895 solver.cpp:218] Iteration 7560 (2.64687 iter/s, 4.53365s/12 iters), loss = 5.269
I0412 13:49:34.491869  6895 solver.cpp:237]     Train net output #0: loss = 5.269 (* 1 = 5.269 loss)
I0412 13:49:34.491879  6895 sgd_solver.cpp:105] Iteration 7560, lr = 0.00223682
I0412 13:49:39.607399  6895 solver.cpp:218] Iteration 7572 (2.34589 iter/s, 5.11533s/12 iters), loss = 5.28169
I0412 13:49:39.607462  6895 solver.cpp:237]     Train net output #0: loss = 5.28169 (* 1 = 5.28169 loss)
I0412 13:49:39.607477  6895 sgd_solver.cpp:105] Iteration 7572, lr = 0.00223151
I0412 13:49:44.334208  6895 solver.cpp:218] Iteration 7584 (2.53884 iter/s, 4.72656s/12 iters), loss = 5.2913
I0412 13:49:44.334259  6895 solver.cpp:237]     Train net output #0: loss = 5.2913 (* 1 = 5.2913 loss)
I0412 13:49:44.334270  6895 sgd_solver.cpp:105] Iteration 7584, lr = 0.00222621
I0412 13:49:44.986033  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:49:49.369832  6895 solver.cpp:218] Iteration 7596 (2.38314 iter/s, 5.03538s/12 iters), loss = 5.2791
I0412 13:49:49.369879  6895 solver.cpp:237]     Train net output #0: loss = 5.2791 (* 1 = 5.2791 loss)
I0412 13:49:49.369887  6895 sgd_solver.cpp:105] Iteration 7596, lr = 0.00222093
I0412 13:49:54.390898  6895 solver.cpp:218] Iteration 7608 (2.39005 iter/s, 5.02082s/12 iters), loss = 5.2647
I0412 13:49:54.390955  6895 solver.cpp:237]     Train net output #0: loss = 5.2647 (* 1 = 5.2647 loss)
I0412 13:49:54.390966  6895 sgd_solver.cpp:105] Iteration 7608, lr = 0.00221565
I0412 13:49:59.158041  6895 solver.cpp:218] Iteration 7620 (2.51736 iter/s, 4.7669s/12 iters), loss = 5.28114
I0412 13:49:59.158097  6895 solver.cpp:237]     Train net output #0: loss = 5.28114 (* 1 = 5.28114 loss)
I0412 13:49:59.158110  6895 sgd_solver.cpp:105] Iteration 7620, lr = 0.00221039
I0412 13:50:01.039858  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:50:03.881630  6895 solver.cpp:218] Iteration 7632 (2.54057 iter/s, 4.72336s/12 iters), loss = 5.28041
I0412 13:50:03.881671  6895 solver.cpp:237]     Train net output #0: loss = 5.28041 (* 1 = 5.28041 loss)
I0412 13:50:03.881680  6895 sgd_solver.cpp:105] Iteration 7632, lr = 0.00220515
I0412 13:50:08.739374  6895 solver.cpp:218] Iteration 7644 (2.4704 iter/s, 4.85751s/12 iters), loss = 5.28373
I0412 13:50:08.740674  6895 solver.cpp:237]     Train net output #0: loss = 5.28373 (* 1 = 5.28373 loss)
I0412 13:50:08.740684  6895 sgd_solver.cpp:105] Iteration 7644, lr = 0.00219991
I0412 13:50:10.724889  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7650.caffemodel
I0412 13:50:12.690685  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7650.solverstate
I0412 13:50:13.864956  6895 solver.cpp:330] Iteration 7650, Testing net (#0)
I0412 13:50:13.864979  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:50:15.358454  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:50:18.442598  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:50:18.442642  6895 solver.cpp:397]     Test net output #1: loss = 5.28616 (* 1 = 5.28616 loss)
I0412 13:50:20.242432  6895 solver.cpp:218] Iteration 7656 (1.04336 iter/s, 11.5013s/12 iters), loss = 5.26982
I0412 13:50:20.242478  6895 solver.cpp:237]     Train net output #0: loss = 5.26982 (* 1 = 5.26982 loss)
I0412 13:50:20.242487  6895 sgd_solver.cpp:105] Iteration 7656, lr = 0.00219469
I0412 13:50:25.240496  6895 solver.cpp:218] Iteration 7668 (2.40104 iter/s, 4.99782s/12 iters), loss = 5.26882
I0412 13:50:25.240548  6895 solver.cpp:237]     Train net output #0: loss = 5.26882 (* 1 = 5.26882 loss)
I0412 13:50:25.240561  6895 sgd_solver.cpp:105] Iteration 7668, lr = 0.00218948
I0412 13:50:30.271891  6895 solver.cpp:218] Iteration 7680 (2.38514 iter/s, 5.03115s/12 iters), loss = 5.26135
I0412 13:50:30.271935  6895 solver.cpp:237]     Train net output #0: loss = 5.26135 (* 1 = 5.26135 loss)
I0412 13:50:30.271945  6895 sgd_solver.cpp:105] Iteration 7680, lr = 0.00218428
I0412 13:50:33.042707  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:50:35.083130  6895 solver.cpp:218] Iteration 7692 (2.49428 iter/s, 4.811s/12 iters), loss = 5.26901
I0412 13:50:35.083181  6895 solver.cpp:237]     Train net output #0: loss = 5.26901 (* 1 = 5.26901 loss)
I0412 13:50:35.083190  6895 sgd_solver.cpp:105] Iteration 7692, lr = 0.00217909
I0412 13:50:39.969347  6895 solver.cpp:218] Iteration 7704 (2.45601 iter/s, 4.88597s/12 iters), loss = 5.25554
I0412 13:50:39.969449  6895 solver.cpp:237]     Train net output #0: loss = 5.25554 (* 1 = 5.25554 loss)
I0412 13:50:39.969458  6895 sgd_solver.cpp:105] Iteration 7704, lr = 0.00217392
I0412 13:50:44.869741  6895 solver.cpp:218] Iteration 7716 (2.44893 iter/s, 4.9001s/12 iters), loss = 5.25456
I0412 13:50:44.869783  6895 solver.cpp:237]     Train net output #0: loss = 5.25456 (* 1 = 5.25456 loss)
I0412 13:50:44.869791  6895 sgd_solver.cpp:105] Iteration 7716, lr = 0.00216876
I0412 13:50:49.902920  6895 solver.cpp:218] Iteration 7728 (2.3843 iter/s, 5.03293s/12 iters), loss = 5.2559
I0412 13:50:49.902974  6895 solver.cpp:237]     Train net output #0: loss = 5.2559 (* 1 = 5.2559 loss)
I0412 13:50:49.902987  6895 sgd_solver.cpp:105] Iteration 7728, lr = 0.00216361
I0412 13:50:54.645223  6895 solver.cpp:218] Iteration 7740 (2.53054 iter/s, 4.74206s/12 iters), loss = 5.29742
I0412 13:50:54.645272  6895 solver.cpp:237]     Train net output #0: loss = 5.29742 (* 1 = 5.29742 loss)
I0412 13:50:54.645280  6895 sgd_solver.cpp:105] Iteration 7740, lr = 0.00215847
I0412 13:50:59.173408  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7752.caffemodel
I0412 13:51:03.488209  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7752.solverstate
I0412 13:51:11.722757  6895 solver.cpp:330] Iteration 7752, Testing net (#0)
I0412 13:51:11.722909  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:51:13.137830  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:51:16.169492  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:51:16.169541  6895 solver.cpp:397]     Test net output #1: loss = 5.28578 (* 1 = 5.28578 loss)
I0412 13:51:16.253087  6895 solver.cpp:218] Iteration 7752 (0.555375 iter/s, 21.607s/12 iters), loss = 5.2692
I0412 13:51:16.253135  6895 solver.cpp:237]     Train net output #0: loss = 5.2692 (* 1 = 5.2692 loss)
I0412 13:51:16.253146  6895 sgd_solver.cpp:105] Iteration 7752, lr = 0.00215335
I0412 13:51:20.297562  6895 solver.cpp:218] Iteration 7764 (2.96716 iter/s, 4.04427s/12 iters), loss = 5.2748
I0412 13:51:20.297600  6895 solver.cpp:237]     Train net output #0: loss = 5.2748 (* 1 = 5.2748 loss)
I0412 13:51:20.297607  6895 sgd_solver.cpp:105] Iteration 7764, lr = 0.00214823
I0412 13:51:25.069334  6895 solver.cpp:218] Iteration 7776 (2.51491 iter/s, 4.77155s/12 iters), loss = 5.27194
I0412 13:51:25.069386  6895 solver.cpp:237]     Train net output #0: loss = 5.27194 (* 1 = 5.27194 loss)
I0412 13:51:25.069396  6895 sgd_solver.cpp:105] Iteration 7776, lr = 0.00214313
I0412 13:51:29.815487  6895 solver.cpp:218] Iteration 7788 (2.52849 iter/s, 4.74592s/12 iters), loss = 5.25146
I0412 13:51:29.815541  6895 solver.cpp:237]     Train net output #0: loss = 5.25146 (* 1 = 5.25146 loss)
I0412 13:51:29.815551  6895 sgd_solver.cpp:105] Iteration 7788, lr = 0.00213805
I0412 13:51:29.830240  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:51:34.803009  6895 solver.cpp:218] Iteration 7800 (2.40612 iter/s, 4.98728s/12 iters), loss = 5.27061
I0412 13:51:34.803048  6895 solver.cpp:237]     Train net output #0: loss = 5.27061 (* 1 = 5.27061 loss)
I0412 13:51:34.803056  6895 sgd_solver.cpp:105] Iteration 7800, lr = 0.00213297
I0412 13:51:39.543275  6895 solver.cpp:218] Iteration 7812 (2.53162 iter/s, 4.74004s/12 iters), loss = 5.29486
I0412 13:51:39.543327  6895 solver.cpp:237]     Train net output #0: loss = 5.29486 (* 1 = 5.29486 loss)
I0412 13:51:39.543339  6895 sgd_solver.cpp:105] Iteration 7812, lr = 0.00212791
I0412 13:51:44.193210  6895 solver.cpp:218] Iteration 7824 (2.58081 iter/s, 4.6497s/12 iters), loss = 5.27482
I0412 13:51:44.193322  6895 solver.cpp:237]     Train net output #0: loss = 5.27482 (* 1 = 5.27482 loss)
I0412 13:51:44.193334  6895 sgd_solver.cpp:105] Iteration 7824, lr = 0.00212285
I0412 13:51:49.167780  6895 solver.cpp:218] Iteration 7836 (2.41242 iter/s, 4.97426s/12 iters), loss = 5.2734
I0412 13:51:49.167819  6895 solver.cpp:237]     Train net output #0: loss = 5.2734 (* 1 = 5.2734 loss)
I0412 13:51:49.167829  6895 sgd_solver.cpp:105] Iteration 7836, lr = 0.00211781
I0412 13:51:54.074474  6895 solver.cpp:218] Iteration 7848 (2.44576 iter/s, 4.90646s/12 iters), loss = 5.25774
I0412 13:51:54.074524  6895 solver.cpp:237]     Train net output #0: loss = 5.25774 (* 1 = 5.25774 loss)
I0412 13:51:54.074535  6895 sgd_solver.cpp:105] Iteration 7848, lr = 0.00211279
I0412 13:51:56.049593  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7854.caffemodel
I0412 13:51:57.640872  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7854.solverstate
I0412 13:52:00.966084  6895 solver.cpp:330] Iteration 7854, Testing net (#0)
I0412 13:52:00.966114  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:52:02.348839  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:52:05.584295  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:52:05.584345  6895 solver.cpp:397]     Test net output #1: loss = 5.2857 (* 1 = 5.2857 loss)
I0412 13:52:07.384863  6895 solver.cpp:218] Iteration 7860 (0.901589 iter/s, 13.3098s/12 iters), loss = 5.24252
I0412 13:52:07.384928  6895 solver.cpp:237]     Train net output #0: loss = 5.24252 (* 1 = 5.24252 loss)
I0412 13:52:07.384941  6895 sgd_solver.cpp:105] Iteration 7860, lr = 0.00210777
I0412 13:52:11.890730  6895 solver.cpp:218] Iteration 7872 (2.66334 iter/s, 4.50563s/12 iters), loss = 5.26246
I0412 13:52:11.890784  6895 solver.cpp:237]     Train net output #0: loss = 5.26246 (* 1 = 5.26246 loss)
I0412 13:52:11.890797  6895 sgd_solver.cpp:105] Iteration 7872, lr = 0.00210277
I0412 13:52:16.661075  6895 solver.cpp:218] Iteration 7884 (2.51567 iter/s, 4.7701s/12 iters), loss = 5.25943
I0412 13:52:16.666049  6895 solver.cpp:237]     Train net output #0: loss = 5.25943 (* 1 = 5.25943 loss)
I0412 13:52:16.666066  6895 sgd_solver.cpp:105] Iteration 7884, lr = 0.00209777
I0412 13:52:18.643133  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:52:21.446820  6895 solver.cpp:218] Iteration 7896 (2.51015 iter/s, 4.78059s/12 iters), loss = 5.27795
I0412 13:52:21.446877  6895 solver.cpp:237]     Train net output #0: loss = 5.27795 (* 1 = 5.27795 loss)
I0412 13:52:21.446890  6895 sgd_solver.cpp:105] Iteration 7896, lr = 0.00209279
I0412 13:52:26.455686  6895 solver.cpp:218] Iteration 7908 (2.39587 iter/s, 5.00862s/12 iters), loss = 5.26905
I0412 13:52:26.455731  6895 solver.cpp:237]     Train net output #0: loss = 5.26905 (* 1 = 5.26905 loss)
I0412 13:52:26.455740  6895 sgd_solver.cpp:105] Iteration 7908, lr = 0.00208782
I0412 13:52:31.236488  6895 solver.cpp:218] Iteration 7920 (2.51017 iter/s, 4.78056s/12 iters), loss = 5.284
I0412 13:52:31.236544  6895 solver.cpp:237]     Train net output #0: loss = 5.284 (* 1 = 5.284 loss)
I0412 13:52:31.236558  6895 sgd_solver.cpp:105] Iteration 7920, lr = 0.00208287
I0412 13:52:36.033643  6895 solver.cpp:218] Iteration 7932 (2.50161 iter/s, 4.79692s/12 iters), loss = 5.2661
I0412 13:52:36.033702  6895 solver.cpp:237]     Train net output #0: loss = 5.2661 (* 1 = 5.2661 loss)
I0412 13:52:36.033715  6895 sgd_solver.cpp:105] Iteration 7932, lr = 0.00207792
I0412 13:52:40.822343  6895 solver.cpp:218] Iteration 7944 (2.50603 iter/s, 4.78846s/12 iters), loss = 5.26427
I0412 13:52:40.822391  6895 solver.cpp:237]     Train net output #0: loss = 5.26427 (* 1 = 5.26427 loss)
I0412 13:52:40.822399  6895 sgd_solver.cpp:105] Iteration 7944, lr = 0.00207299
I0412 13:52:45.220860  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7956.caffemodel
I0412 13:52:46.711261  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7956.solverstate
I0412 13:52:47.913400  6895 solver.cpp:330] Iteration 7956, Testing net (#0)
I0412 13:52:47.913429  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:52:49.187041  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:52:52.542606  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:52:52.542644  6895 solver.cpp:397]     Test net output #1: loss = 5.2863 (* 1 = 5.2863 loss)
I0412 13:52:52.625980  6895 solver.cpp:218] Iteration 7956 (1.01668 iter/s, 11.8031s/12 iters), loss = 5.2776
I0412 13:52:52.626029  6895 solver.cpp:237]     Train net output #0: loss = 5.2776 (* 1 = 5.2776 loss)
I0412 13:52:52.626039  6895 sgd_solver.cpp:105] Iteration 7956, lr = 0.00206807
I0412 13:52:56.772485  6895 solver.cpp:218] Iteration 7968 (2.89415 iter/s, 4.14629s/12 iters), loss = 5.27333
I0412 13:52:56.772537  6895 solver.cpp:237]     Train net output #0: loss = 5.27333 (* 1 = 5.27333 loss)
I0412 13:52:56.772549  6895 sgd_solver.cpp:105] Iteration 7968, lr = 0.00206316
I0412 13:53:01.630728  6895 solver.cpp:218] Iteration 7980 (2.47015 iter/s, 4.858s/12 iters), loss = 5.25501
I0412 13:53:01.630774  6895 solver.cpp:237]     Train net output #0: loss = 5.25501 (* 1 = 5.25501 loss)
I0412 13:53:01.630785  6895 sgd_solver.cpp:105] Iteration 7980, lr = 0.00205826
I0412 13:53:05.784674  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:53:06.497023  6895 solver.cpp:218] Iteration 7992 (2.46606 iter/s, 4.86606s/12 iters), loss = 5.26038
I0412 13:53:06.497077  6895 solver.cpp:237]     Train net output #0: loss = 5.26038 (* 1 = 5.26038 loss)
I0412 13:53:06.497088  6895 sgd_solver.cpp:105] Iteration 7992, lr = 0.00205337
I0412 13:53:11.517572  6895 solver.cpp:218] Iteration 8004 (2.39029 iter/s, 5.0203s/12 iters), loss = 5.27624
I0412 13:53:11.517616  6895 solver.cpp:237]     Train net output #0: loss = 5.27624 (* 1 = 5.27624 loss)
I0412 13:53:11.517625  6895 sgd_solver.cpp:105] Iteration 8004, lr = 0.0020485
I0412 13:53:16.223840  6895 solver.cpp:218] Iteration 8016 (2.54992 iter/s, 4.70604s/12 iters), loss = 5.27876
I0412 13:53:16.223883  6895 solver.cpp:237]     Train net output #0: loss = 5.27876 (* 1 = 5.27876 loss)
I0412 13:53:16.223892  6895 sgd_solver.cpp:105] Iteration 8016, lr = 0.00204363
I0412 13:53:21.104040  6895 solver.cpp:218] Iteration 8028 (2.45903 iter/s, 4.87996s/12 iters), loss = 5.29329
I0412 13:53:21.104163  6895 solver.cpp:237]     Train net output #0: loss = 5.29329 (* 1 = 5.29329 loss)
I0412 13:53:21.104173  6895 sgd_solver.cpp:105] Iteration 8028, lr = 0.00203878
I0412 13:53:26.086529  6895 solver.cpp:218] Iteration 8040 (2.40859 iter/s, 4.98217s/12 iters), loss = 5.26177
I0412 13:53:26.086585  6895 solver.cpp:237]     Train net output #0: loss = 5.26177 (* 1 = 5.26177 loss)
I0412 13:53:26.086597  6895 sgd_solver.cpp:105] Iteration 8040, lr = 0.00203394
I0412 13:53:31.231204  6895 solver.cpp:218] Iteration 8052 (2.33263 iter/s, 5.14441s/12 iters), loss = 5.28011
I0412 13:53:31.231256  6895 solver.cpp:237]     Train net output #0: loss = 5.28011 (* 1 = 5.28011 loss)
I0412 13:53:31.231267  6895 sgd_solver.cpp:105] Iteration 8052, lr = 0.00202911
I0412 13:53:33.294613  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8058.caffemodel
I0412 13:53:34.873067  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8058.solverstate
I0412 13:53:36.041915  6895 solver.cpp:330] Iteration 8058, Testing net (#0)
I0412 13:53:36.041937  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:53:37.518946  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:53:40.738130  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:53:40.738178  6895 solver.cpp:397]     Test net output #1: loss = 5.28633 (* 1 = 5.28633 loss)
I0412 13:53:42.346940  6895 solver.cpp:218] Iteration 8064 (1.0796 iter/s, 11.1153s/12 iters), loss = 5.28074
I0412 13:53:42.346992  6895 solver.cpp:237]     Train net output #0: loss = 5.28074 (* 1 = 5.28074 loss)
I0412 13:53:42.347003  6895 sgd_solver.cpp:105] Iteration 8064, lr = 0.00202429
I0412 13:53:47.258992  6895 solver.cpp:218] Iteration 8076 (2.44309 iter/s, 4.9118s/12 iters), loss = 5.27681
I0412 13:53:47.259047  6895 solver.cpp:237]     Train net output #0: loss = 5.27681 (* 1 = 5.27681 loss)
I0412 13:53:47.259060  6895 sgd_solver.cpp:105] Iteration 8076, lr = 0.00201949
I0412 13:53:52.139669  6895 solver.cpp:218] Iteration 8088 (2.4588 iter/s, 4.88043s/12 iters), loss = 5.26327
I0412 13:53:52.139763  6895 solver.cpp:237]     Train net output #0: loss = 5.26327 (* 1 = 5.26327 loss)
I0412 13:53:52.139775  6895 sgd_solver.cpp:105] Iteration 8088, lr = 0.00201469
I0412 13:53:53.517424  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:53:57.009359  6895 solver.cpp:218] Iteration 8100 (2.46436 iter/s, 4.86941s/12 iters), loss = 5.2624
I0412 13:53:57.009407  6895 solver.cpp:237]     Train net output #0: loss = 5.2624 (* 1 = 5.2624 loss)
I0412 13:53:57.009418  6895 sgd_solver.cpp:105] Iteration 8100, lr = 0.00200991
I0412 13:54:01.877969  6895 solver.cpp:218] Iteration 8112 (2.4649 iter/s, 4.86835s/12 iters), loss = 5.26618
I0412 13:54:01.878021  6895 solver.cpp:237]     Train net output #0: loss = 5.26618 (* 1 = 5.26618 loss)
I0412 13:54:01.878031  6895 sgd_solver.cpp:105] Iteration 8112, lr = 0.00200514
I0412 13:54:06.809301  6895 solver.cpp:218] Iteration 8124 (2.43354 iter/s, 4.93109s/12 iters), loss = 5.27239
I0412 13:54:06.809355  6895 solver.cpp:237]     Train net output #0: loss = 5.27239 (* 1 = 5.27239 loss)
I0412 13:54:06.809366  6895 sgd_solver.cpp:105] Iteration 8124, lr = 0.00200038
I0412 13:54:11.889226  6895 solver.cpp:218] Iteration 8136 (2.36236 iter/s, 5.07967s/12 iters), loss = 5.28654
I0412 13:54:11.889283  6895 solver.cpp:237]     Train net output #0: loss = 5.28654 (* 1 = 5.28654 loss)
I0412 13:54:11.889297  6895 sgd_solver.cpp:105] Iteration 8136, lr = 0.00199563
I0412 13:54:16.829643  6895 solver.cpp:218] Iteration 8148 (2.42907 iter/s, 4.94017s/12 iters), loss = 5.2531
I0412 13:54:16.829703  6895 solver.cpp:237]     Train net output #0: loss = 5.2531 (* 1 = 5.2531 loss)
I0412 13:54:16.829720  6895 sgd_solver.cpp:105] Iteration 8148, lr = 0.00199089
I0412 13:54:21.241431  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8160.caffemodel
I0412 13:54:22.832423  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8160.solverstate
I0412 13:54:24.001875  6895 solver.cpp:330] Iteration 8160, Testing net (#0)
I0412 13:54:24.001902  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:54:25.196887  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:54:28.391182  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:54:28.391238  6895 solver.cpp:397]     Test net output #1: loss = 5.28607 (* 1 = 5.28607 loss)
I0412 13:54:28.474520  6895 solver.cpp:218] Iteration 8160 (1.03054 iter/s, 11.6444s/12 iters), loss = 5.26173
I0412 13:54:28.474578  6895 solver.cpp:237]     Train net output #0: loss = 5.26173 (* 1 = 5.26173 loss)
I0412 13:54:28.474591  6895 sgd_solver.cpp:105] Iteration 8160, lr = 0.00198616
I0412 13:54:32.645289  6895 solver.cpp:218] Iteration 8172 (2.87732 iter/s, 4.17055s/12 iters), loss = 5.28225
I0412 13:54:32.645339  6895 solver.cpp:237]     Train net output #0: loss = 5.28225 (* 1 = 5.28225 loss)
I0412 13:54:32.645349  6895 sgd_solver.cpp:105] Iteration 8172, lr = 0.00198145
I0412 13:54:37.586998  6895 solver.cpp:218] Iteration 8184 (2.42843 iter/s, 4.94146s/12 iters), loss = 5.27621
I0412 13:54:37.587052  6895 solver.cpp:237]     Train net output #0: loss = 5.27621 (* 1 = 5.27621 loss)
I0412 13:54:37.587064  6895 sgd_solver.cpp:105] Iteration 8184, lr = 0.00197674
I0412 13:54:40.856401  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:54:42.195384  6895 solver.cpp:218] Iteration 8196 (2.60408 iter/s, 4.60815s/12 iters), loss = 5.27519
I0412 13:54:42.195441  6895 solver.cpp:237]     Train net output #0: loss = 5.27519 (* 1 = 5.27519 loss)
I0412 13:54:42.195456  6895 sgd_solver.cpp:105] Iteration 8196, lr = 0.00197205
I0412 13:54:46.929869  6895 solver.cpp:218] Iteration 8208 (2.53472 iter/s, 4.73424s/12 iters), loss = 5.26049
I0412 13:54:46.929924  6895 solver.cpp:237]     Train net output #0: loss = 5.26049 (* 1 = 5.26049 loss)
I0412 13:54:46.929936  6895 sgd_solver.cpp:105] Iteration 8208, lr = 0.00196737
I0412 13:54:51.645166  6895 solver.cpp:218] Iteration 8220 (2.54504 iter/s, 4.71506s/12 iters), loss = 5.26297
I0412 13:54:51.645211  6895 solver.cpp:237]     Train net output #0: loss = 5.26297 (* 1 = 5.26297 loss)
I0412 13:54:51.645221  6895 sgd_solver.cpp:105] Iteration 8220, lr = 0.0019627
I0412 13:54:56.527123  6895 solver.cpp:218] Iteration 8232 (2.45815 iter/s, 4.88172s/12 iters), loss = 5.27041
I0412 13:54:56.527225  6895 solver.cpp:237]     Train net output #0: loss = 5.27041 (* 1 = 5.27041 loss)
I0412 13:54:56.527235  6895 sgd_solver.cpp:105] Iteration 8232, lr = 0.00195804
I0412 13:55:01.407006  6895 solver.cpp:218] Iteration 8244 (2.45922 iter/s, 4.87959s/12 iters), loss = 5.25487
I0412 13:55:01.407045  6895 solver.cpp:237]     Train net output #0: loss = 5.25487 (* 1 = 5.25487 loss)
I0412 13:55:01.407054  6895 sgd_solver.cpp:105] Iteration 8244, lr = 0.00195339
I0412 13:55:06.152940  6895 solver.cpp:218] Iteration 8256 (2.5286 iter/s, 4.74571s/12 iters), loss = 5.272
I0412 13:55:06.152981  6895 solver.cpp:237]     Train net output #0: loss = 5.272 (* 1 = 5.272 loss)
I0412 13:55:06.152988  6895 sgd_solver.cpp:105] Iteration 8256, lr = 0.00194875
I0412 13:55:08.392889  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8262.caffemodel
I0412 13:55:10.754648  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8262.solverstate
I0412 13:55:11.930734  6895 solver.cpp:330] Iteration 8262, Testing net (#0)
I0412 13:55:11.930764  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:55:13.229131  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:55:16.451663  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0412 13:55:16.451715  6895 solver.cpp:397]     Test net output #1: loss = 5.28614 (* 1 = 5.28614 loss)
I0412 13:55:18.192137  6895 solver.cpp:218] Iteration 8268 (0.996785 iter/s, 12.0387s/12 iters), loss = 5.27749
I0412 13:55:18.192193  6895 solver.cpp:237]     Train net output #0: loss = 5.27749 (* 1 = 5.27749 loss)
I0412 13:55:18.192204  6895 sgd_solver.cpp:105] Iteration 8268, lr = 0.00194412
I0412 13:55:23.057708  6895 solver.cpp:218] Iteration 8280 (2.46643 iter/s, 4.86533s/12 iters), loss = 5.28437
I0412 13:55:23.057767  6895 solver.cpp:237]     Train net output #0: loss = 5.28437 (* 1 = 5.28437 loss)
I0412 13:55:23.057781  6895 sgd_solver.cpp:105] Iteration 8280, lr = 0.00193951
I0412 13:55:28.108237  6895 solver.cpp:218] Iteration 8292 (2.37611 iter/s, 5.05028s/12 iters), loss = 5.28943
I0412 13:55:28.108377  6895 solver.cpp:237]     Train net output #0: loss = 5.28943 (* 1 = 5.28943 loss)
I0412 13:55:28.108390  6895 sgd_solver.cpp:105] Iteration 8292, lr = 0.0019349
I0412 13:55:28.759721  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:55:33.011799  6895 solver.cpp:218] Iteration 8304 (2.44737 iter/s, 4.90323s/12 iters), loss = 5.28139
I0412 13:55:33.011863  6895 solver.cpp:237]     Train net output #0: loss = 5.28139 (* 1 = 5.28139 loss)
I0412 13:55:33.011875  6895 sgd_solver.cpp:105] Iteration 8304, lr = 0.00193031
I0412 13:55:35.429648  6895 blocking_queue.cpp:49] Waiting for data
I0412 13:55:37.923743  6895 solver.cpp:218] Iteration 8316 (2.44315 iter/s, 4.91169s/12 iters), loss = 5.26961
I0412 13:55:37.923789  6895 solver.cpp:237]     Train net output #0: loss = 5.26961 (* 1 = 5.26961 loss)
I0412 13:55:37.923799  6895 sgd_solver.cpp:105] Iteration 8316, lr = 0.00192573
I0412 13:55:42.838413  6895 solver.cpp:218] Iteration 8328 (2.44179 iter/s, 4.91443s/12 iters), loss = 5.28417
I0412 13:55:42.838470  6895 solver.cpp:237]     Train net output #0: loss = 5.28417 (* 1 = 5.28417 loss)
I0412 13:55:42.838483  6895 sgd_solver.cpp:105] Iteration 8328, lr = 0.00192115
I0412 13:55:47.743691  6895 solver.cpp:218] Iteration 8340 (2.44647 iter/s, 4.90503s/12 iters), loss = 5.27314
I0412 13:55:47.743747  6895 solver.cpp:237]     Train net output #0: loss = 5.27314 (* 1 = 5.27314 loss)
I0412 13:55:47.743758  6895 sgd_solver.cpp:105] Iteration 8340, lr = 0.00191659
I0412 13:55:52.672011  6895 solver.cpp:218] Iteration 8352 (2.43503 iter/s, 4.92807s/12 iters), loss = 5.29015
I0412 13:55:52.672070  6895 solver.cpp:237]     Train net output #0: loss = 5.29015 (* 1 = 5.29015 loss)
I0412 13:55:52.672083  6895 sgd_solver.cpp:105] Iteration 8352, lr = 0.00191204
I0412 13:55:57.193881  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8364.caffemodel
I0412 13:56:02.021500  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8364.solverstate
I0412 13:56:05.930052  6895 solver.cpp:330] Iteration 8364, Testing net (#0)
I0412 13:56:05.930076  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:56:07.119941  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:56:10.421284  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:56:10.421348  6895 solver.cpp:397]     Test net output #1: loss = 5.28592 (* 1 = 5.28592 loss)
I0412 13:56:10.505388  6895 solver.cpp:218] Iteration 8364 (0.672923 iter/s, 17.8327s/12 iters), loss = 5.26528
I0412 13:56:10.505456  6895 solver.cpp:237]     Train net output #0: loss = 5.26528 (* 1 = 5.26528 loss)
I0412 13:56:10.505471  6895 sgd_solver.cpp:105] Iteration 8364, lr = 0.0019075
I0412 13:56:14.530707  6895 solver.cpp:218] Iteration 8376 (2.98129 iter/s, 4.0251s/12 iters), loss = 5.26562
I0412 13:56:14.530746  6895 solver.cpp:237]     Train net output #0: loss = 5.26562 (* 1 = 5.26562 loss)
I0412 13:56:14.530755  6895 sgd_solver.cpp:105] Iteration 8376, lr = 0.00190297
I0412 13:56:19.424808  6895 solver.cpp:218] Iteration 8388 (2.45205 iter/s, 4.89387s/12 iters), loss = 5.25957
I0412 13:56:19.424856  6895 solver.cpp:237]     Train net output #0: loss = 5.25957 (* 1 = 5.25957 loss)
I0412 13:56:19.424867  6895 sgd_solver.cpp:105] Iteration 8388, lr = 0.00189846
I0412 13:56:22.235360  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:56:24.285811  6895 solver.cpp:218] Iteration 8400 (2.46875 iter/s, 4.86076s/12 iters), loss = 5.26424
I0412 13:56:24.285857  6895 solver.cpp:237]     Train net output #0: loss = 5.26424 (* 1 = 5.26424 loss)
I0412 13:56:24.285866  6895 sgd_solver.cpp:105] Iteration 8400, lr = 0.00189395
I0412 13:56:29.182428  6895 solver.cpp:218] Iteration 8412 (2.45079 iter/s, 4.89638s/12 iters), loss = 5.2519
I0412 13:56:29.182478  6895 solver.cpp:237]     Train net output #0: loss = 5.2519 (* 1 = 5.2519 loss)
I0412 13:56:29.182492  6895 sgd_solver.cpp:105] Iteration 8412, lr = 0.00188945
I0412 13:56:33.804435  6895 solver.cpp:218] Iteration 8424 (2.59641 iter/s, 4.62177s/12 iters), loss = 5.2571
I0412 13:56:33.804556  6895 solver.cpp:237]     Train net output #0: loss = 5.2571 (* 1 = 5.2571 loss)
I0412 13:56:33.804566  6895 sgd_solver.cpp:105] Iteration 8424, lr = 0.00188497
I0412 13:56:38.511951  6895 solver.cpp:218] Iteration 8436 (2.54928 iter/s, 4.70721s/12 iters), loss = 5.25287
I0412 13:56:38.512006  6895 solver.cpp:237]     Train net output #0: loss = 5.25287 (* 1 = 5.25287 loss)
I0412 13:56:38.512018  6895 sgd_solver.cpp:105] Iteration 8436, lr = 0.00188049
I0412 13:56:43.213505  6895 solver.cpp:218] Iteration 8448 (2.55248 iter/s, 4.70132s/12 iters), loss = 5.29485
I0412 13:56:43.213553  6895 solver.cpp:237]     Train net output #0: loss = 5.29485 (* 1 = 5.29485 loss)
I0412 13:56:43.213564  6895 sgd_solver.cpp:105] Iteration 8448, lr = 0.00187603
I0412 13:56:47.959874  6895 solver.cpp:218] Iteration 8460 (2.52838 iter/s, 4.74613s/12 iters), loss = 5.27038
I0412 13:56:47.959931  6895 solver.cpp:237]     Train net output #0: loss = 5.27038 (* 1 = 5.27038 loss)
I0412 13:56:47.959945  6895 sgd_solver.cpp:105] Iteration 8460, lr = 0.00187157
I0412 13:56:49.957319  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8466.caffemodel
I0412 13:56:51.545280  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8466.solverstate
I0412 13:56:52.866905  6895 solver.cpp:330] Iteration 8466, Testing net (#0)
I0412 13:56:52.866927  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:56:54.018832  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:56:57.647240  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:56:57.647290  6895 solver.cpp:397]     Test net output #1: loss = 5.2859 (* 1 = 5.2859 loss)
I0412 13:56:59.398983  6895 solver.cpp:218] Iteration 8472 (1.04908 iter/s, 11.4386s/12 iters), loss = 5.27302
I0412 13:56:59.399034  6895 solver.cpp:237]     Train net output #0: loss = 5.27302 (* 1 = 5.27302 loss)
I0412 13:56:59.399047  6895 sgd_solver.cpp:105] Iteration 8472, lr = 0.00186713
I0412 13:57:04.232232  6895 solver.cpp:218] Iteration 8484 (2.48293 iter/s, 4.83301s/12 iters), loss = 5.27292
I0412 13:57:04.232314  6895 solver.cpp:237]     Train net output #0: loss = 5.27292 (* 1 = 5.27292 loss)
I0412 13:57:04.232326  6895 sgd_solver.cpp:105] Iteration 8484, lr = 0.0018627
I0412 13:57:08.794899  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:57:08.800038  6895 solver.cpp:218] Iteration 8496 (2.62723 iter/s, 4.56755s/12 iters), loss = 5.25399
I0412 13:57:08.800088  6895 solver.cpp:237]     Train net output #0: loss = 5.25399 (* 1 = 5.25399 loss)
I0412 13:57:08.800101  6895 sgd_solver.cpp:105] Iteration 8496, lr = 0.00185827
I0412 13:57:13.585752  6895 solver.cpp:218] Iteration 8508 (2.50758 iter/s, 4.78548s/12 iters), loss = 5.2783
I0412 13:57:13.585796  6895 solver.cpp:237]     Train net output #0: loss = 5.2783 (* 1 = 5.2783 loss)
I0412 13:57:13.585806  6895 sgd_solver.cpp:105] Iteration 8508, lr = 0.00185386
I0412 13:57:18.436664  6895 solver.cpp:218] Iteration 8520 (2.47388 iter/s, 4.85067s/12 iters), loss = 5.29403
I0412 13:57:18.436714  6895 solver.cpp:237]     Train net output #0: loss = 5.29403 (* 1 = 5.29403 loss)
I0412 13:57:18.436726  6895 sgd_solver.cpp:105] Iteration 8520, lr = 0.00184946
I0412 13:57:23.328593  6895 solver.cpp:218] Iteration 8532 (2.45314 iter/s, 4.89168s/12 iters), loss = 5.27193
I0412 13:57:23.328647  6895 solver.cpp:237]     Train net output #0: loss = 5.27193 (* 1 = 5.27193 loss)
I0412 13:57:23.328660  6895 sgd_solver.cpp:105] Iteration 8532, lr = 0.00184507
I0412 13:57:28.197592  6895 solver.cpp:218] Iteration 8544 (2.4647 iter/s, 4.86875s/12 iters), loss = 5.27025
I0412 13:57:28.197650  6895 solver.cpp:237]     Train net output #0: loss = 5.27025 (* 1 = 5.27025 loss)
I0412 13:57:28.197661  6895 sgd_solver.cpp:105] Iteration 8544, lr = 0.00184069
I0412 13:57:33.047590  6895 solver.cpp:218] Iteration 8556 (2.47436 iter/s, 4.84975s/12 iters), loss = 5.25946
I0412 13:57:33.047648  6895 solver.cpp:237]     Train net output #0: loss = 5.25946 (* 1 = 5.25946 loss)
I0412 13:57:33.047662  6895 sgd_solver.cpp:105] Iteration 8556, lr = 0.00183632
I0412 13:57:37.457422  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8568.caffemodel
I0412 13:57:39.069005  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8568.solverstate
I0412 13:57:41.246692  6895 solver.cpp:330] Iteration 8568, Testing net (#0)
I0412 13:57:41.246726  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:57:42.380555  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:57:45.982030  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:57:45.982067  6895 solver.cpp:397]     Test net output #1: loss = 5.28607 (* 1 = 5.28607 loss)
I0412 13:57:46.065095  6895 solver.cpp:218] Iteration 8568 (0.921874 iter/s, 13.017s/12 iters), loss = 5.24846
I0412 13:57:46.065148  6895 solver.cpp:237]     Train net output #0: loss = 5.24846 (* 1 = 5.24846 loss)
I0412 13:57:46.065160  6895 sgd_solver.cpp:105] Iteration 8568, lr = 0.00183196
I0412 13:57:50.141383  6895 solver.cpp:218] Iteration 8580 (2.94401 iter/s, 4.07607s/12 iters), loss = 5.26334
I0412 13:57:50.141439  6895 solver.cpp:237]     Train net output #0: loss = 5.26334 (* 1 = 5.26334 loss)
I0412 13:57:50.141453  6895 sgd_solver.cpp:105] Iteration 8580, lr = 0.00182761
I0412 13:57:54.903246  6895 solver.cpp:218] Iteration 8592 (2.52015 iter/s, 4.76162s/12 iters), loss = 5.25269
I0412 13:57:54.903295  6895 solver.cpp:237]     Train net output #0: loss = 5.25269 (* 1 = 5.25269 loss)
I0412 13:57:54.903308  6895 sgd_solver.cpp:105] Iteration 8592, lr = 0.00182327
I0412 13:57:57.052623  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:57:59.915854  6895 solver.cpp:218] Iteration 8604 (2.39408 iter/s, 5.01236s/12 iters), loss = 5.27001
I0412 13:57:59.915899  6895 solver.cpp:237]     Train net output #0: loss = 5.27001 (* 1 = 5.27001 loss)
I0412 13:57:59.915907  6895 sgd_solver.cpp:105] Iteration 8604, lr = 0.00181894
I0412 13:58:04.871568  6895 solver.cpp:218] Iteration 8616 (2.42156 iter/s, 4.95548s/12 iters), loss = 5.26689
I0412 13:58:04.871620  6895 solver.cpp:237]     Train net output #0: loss = 5.26689 (* 1 = 5.26689 loss)
I0412 13:58:04.871631  6895 sgd_solver.cpp:105] Iteration 8616, lr = 0.00181462
I0412 13:58:09.666465  6895 solver.cpp:218] Iteration 8628 (2.50278 iter/s, 4.79466s/12 iters), loss = 5.28315
I0412 13:58:09.666607  6895 solver.cpp:237]     Train net output #0: loss = 5.28315 (* 1 = 5.28315 loss)
I0412 13:58:09.666618  6895 sgd_solver.cpp:105] Iteration 8628, lr = 0.00181031
I0412 13:58:14.614894  6895 solver.cpp:218] Iteration 8640 (2.42517 iter/s, 4.9481s/12 iters), loss = 5.26307
I0412 13:58:14.614940  6895 solver.cpp:237]     Train net output #0: loss = 5.26307 (* 1 = 5.26307 loss)
I0412 13:58:14.614949  6895 sgd_solver.cpp:105] Iteration 8640, lr = 0.00180602
I0412 13:58:19.455391  6895 solver.cpp:218] Iteration 8652 (2.47921 iter/s, 4.84026s/12 iters), loss = 5.26726
I0412 13:58:19.455447  6895 solver.cpp:237]     Train net output #0: loss = 5.26726 (* 1 = 5.26726 loss)
I0412 13:58:19.455462  6895 sgd_solver.cpp:105] Iteration 8652, lr = 0.00180173
I0412 13:58:24.273077  6895 solver.cpp:218] Iteration 8664 (2.49095 iter/s, 4.81745s/12 iters), loss = 5.27197
I0412 13:58:24.273116  6895 solver.cpp:237]     Train net output #0: loss = 5.27197 (* 1 = 5.27197 loss)
I0412 13:58:24.273125  6895 sgd_solver.cpp:105] Iteration 8664, lr = 0.00179745
I0412 13:58:26.289510  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8670.caffemodel
I0412 13:58:27.842685  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8670.solverstate
I0412 13:58:29.027827  6895 solver.cpp:330] Iteration 8670, Testing net (#0)
I0412 13:58:29.027858  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:58:30.036929  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:58:33.492323  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:58:33.492372  6895 solver.cpp:397]     Test net output #1: loss = 5.28628 (* 1 = 5.28628 loss)
I0412 13:58:35.369246  6895 solver.cpp:218] Iteration 8676 (1.0815 iter/s, 11.0957s/12 iters), loss = 5.2779
I0412 13:58:35.369292  6895 solver.cpp:237]     Train net output #0: loss = 5.2779 (* 1 = 5.2779 loss)
I0412 13:58:35.369302  6895 sgd_solver.cpp:105] Iteration 8676, lr = 0.00179318
I0412 13:58:40.305694  6895 solver.cpp:218] Iteration 8688 (2.43102 iter/s, 4.9362s/12 iters), loss = 5.25972
I0412 13:58:40.305809  6895 solver.cpp:237]     Train net output #0: loss = 5.25972 (* 1 = 5.25972 loss)
I0412 13:58:40.305824  6895 sgd_solver.cpp:105] Iteration 8688, lr = 0.00178893
I0412 13:58:44.401408  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:58:45.089488  6895 solver.cpp:218] Iteration 8700 (2.50863 iter/s, 4.78349s/12 iters), loss = 5.26437
I0412 13:58:45.089531  6895 solver.cpp:237]     Train net output #0: loss = 5.26437 (* 1 = 5.26437 loss)
I0412 13:58:45.089540  6895 sgd_solver.cpp:105] Iteration 8700, lr = 0.00178468
I0412 13:58:49.905366  6895 solver.cpp:218] Iteration 8712 (2.49188 iter/s, 4.81564s/12 iters), loss = 5.27965
I0412 13:58:49.905421  6895 solver.cpp:237]     Train net output #0: loss = 5.27965 (* 1 = 5.27965 loss)
I0412 13:58:49.905432  6895 sgd_solver.cpp:105] Iteration 8712, lr = 0.00178044
I0412 13:58:54.742022  6895 solver.cpp:218] Iteration 8724 (2.48118 iter/s, 4.8364s/12 iters), loss = 5.2812
I0412 13:58:54.742081  6895 solver.cpp:237]     Train net output #0: loss = 5.2812 (* 1 = 5.2812 loss)
I0412 13:58:54.742094  6895 sgd_solver.cpp:105] Iteration 8724, lr = 0.00177621
I0412 13:58:59.729355  6895 solver.cpp:218] Iteration 8736 (2.40622 iter/s, 4.98708s/12 iters), loss = 5.296
I0412 13:58:59.729409  6895 solver.cpp:237]     Train net output #0: loss = 5.296 (* 1 = 5.296 loss)
I0412 13:58:59.729423  6895 sgd_solver.cpp:105] Iteration 8736, lr = 0.001772
I0412 13:59:04.742345  6895 solver.cpp:218] Iteration 8748 (2.3939 iter/s, 5.01275s/12 iters), loss = 5.271
I0412 13:59:04.742384  6895 solver.cpp:237]     Train net output #0: loss = 5.271 (* 1 = 5.271 loss)
I0412 13:59:04.742393  6895 sgd_solver.cpp:105] Iteration 8748, lr = 0.00176779
I0412 13:59:09.652722  6895 solver.cpp:218] Iteration 8760 (2.44392 iter/s, 4.91014s/12 iters), loss = 5.27809
I0412 13:59:09.652781  6895 solver.cpp:237]     Train net output #0: loss = 5.27809 (* 1 = 5.27809 loss)
I0412 13:59:09.652792  6895 sgd_solver.cpp:105] Iteration 8760, lr = 0.00176359
I0412 13:59:14.129209  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8772.caffemodel
I0412 13:59:15.763473  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8772.solverstate
I0412 13:59:16.929361  6895 solver.cpp:330] Iteration 8772, Testing net (#0)
I0412 13:59:16.929383  6895 net.cpp:676] Ignoring source layer train-data
I0412 13:59:17.828729  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:59:21.295648  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 13:59:21.295684  6895 solver.cpp:397]     Test net output #1: loss = 5.28627 (* 1 = 5.28627 loss)
I0412 13:59:21.379056  6895 solver.cpp:218] Iteration 8772 (1.02338 iter/s, 11.7258s/12 iters), loss = 5.27986
I0412 13:59:21.379102  6895 solver.cpp:237]     Train net output #0: loss = 5.27986 (* 1 = 5.27986 loss)
I0412 13:59:21.379112  6895 sgd_solver.cpp:105] Iteration 8772, lr = 0.00175941
I0412 13:59:25.250411  6895 solver.cpp:218] Iteration 8784 (3.09985 iter/s, 3.87115s/12 iters), loss = 5.27674
I0412 13:59:25.250471  6895 solver.cpp:237]     Train net output #0: loss = 5.27674 (* 1 = 5.27674 loss)
I0412 13:59:25.250488  6895 sgd_solver.cpp:105] Iteration 8784, lr = 0.00175523
I0412 13:59:30.346683  6895 solver.cpp:218] Iteration 8796 (2.35478 iter/s, 5.09602s/12 iters), loss = 5.25927
I0412 13:59:30.346733  6895 solver.cpp:237]     Train net output #0: loss = 5.25927 (* 1 = 5.25927 loss)
I0412 13:59:30.346746  6895 sgd_solver.cpp:105] Iteration 8796, lr = 0.00175106
I0412 13:59:31.686198  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 13:59:34.951014  6895 solver.cpp:218] Iteration 8808 (2.60637 iter/s, 4.6041s/12 iters), loss = 5.26355
I0412 13:59:34.951072  6895 solver.cpp:237]     Train net output #0: loss = 5.26355 (* 1 = 5.26355 loss)
I0412 13:59:34.951086  6895 sgd_solver.cpp:105] Iteration 8808, lr = 0.0017469
I0412 13:59:39.673128  6895 solver.cpp:218] Iteration 8820 (2.54137 iter/s, 4.72187s/12 iters), loss = 5.2636
I0412 13:59:39.673182  6895 solver.cpp:237]     Train net output #0: loss = 5.2636 (* 1 = 5.2636 loss)
I0412 13:59:39.673192  6895 sgd_solver.cpp:105] Iteration 8820, lr = 0.00174276
I0412 13:59:44.581624  6895 solver.cpp:218] Iteration 8832 (2.44486 iter/s, 4.90825s/12 iters), loss = 5.26716
I0412 13:59:44.581739  6895 solver.cpp:237]     Train net output #0: loss = 5.26716 (* 1 = 5.26716 loss)
I0412 13:59:44.581751  6895 sgd_solver.cpp:105] Iteration 8832, lr = 0.00173862
I0412 13:59:49.661067  6895 solver.cpp:218] Iteration 8844 (2.36261 iter/s, 5.07912s/12 iters), loss = 5.29651
I0412 13:59:49.661123  6895 solver.cpp:237]     Train net output #0: loss = 5.29651 (* 1 = 5.29651 loss)
I0412 13:59:49.661135  6895 sgd_solver.cpp:105] Iteration 8844, lr = 0.00173449
I0412 13:59:54.617926  6895 solver.cpp:218] Iteration 8856 (2.42101 iter/s, 4.95661s/12 iters), loss = 5.25659
I0412 13:59:54.617975  6895 solver.cpp:237]     Train net output #0: loss = 5.25659 (* 1 = 5.25659 loss)
I0412 13:59:54.617985  6895 sgd_solver.cpp:105] Iteration 8856, lr = 0.00173037
I0412 13:59:59.408306  6895 solver.cpp:218] Iteration 8868 (2.50515 iter/s, 4.79014s/12 iters), loss = 5.25871
I0412 13:59:59.408358  6895 solver.cpp:237]     Train net output #0: loss = 5.25871 (* 1 = 5.25871 loss)
I0412 13:59:59.408370  6895 sgd_solver.cpp:105] Iteration 8868, lr = 0.00172626
I0412 14:00:01.264096  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8874.caffemodel
I0412 14:00:02.781251  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8874.solverstate
I0412 14:00:03.947259  6895 solver.cpp:330] Iteration 8874, Testing net (#0)
I0412 14:00:03.947284  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:00:04.912485  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:00:08.472772  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:00:08.472812  6895 solver.cpp:397]     Test net output #1: loss = 5.28609 (* 1 = 5.28609 loss)
I0412 14:00:10.333828  6895 solver.cpp:218] Iteration 8880 (1.09839 iter/s, 10.9251s/12 iters), loss = 5.28247
I0412 14:00:10.333882  6895 solver.cpp:237]     Train net output #0: loss = 5.28247 (* 1 = 5.28247 loss)
I0412 14:00:10.333894  6895 sgd_solver.cpp:105] Iteration 8880, lr = 0.00172217
I0412 14:00:14.968832  6895 solver.cpp:218] Iteration 8892 (2.58913 iter/s, 4.63476s/12 iters), loss = 5.27922
I0412 14:00:14.971603  6895 solver.cpp:237]     Train net output #0: loss = 5.27922 (* 1 = 5.27922 loss)
I0412 14:00:14.971619  6895 sgd_solver.cpp:105] Iteration 8892, lr = 0.00171808
I0412 14:00:18.454833  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:00:19.858413  6895 solver.cpp:218] Iteration 8904 (2.45568 iter/s, 4.88662s/12 iters), loss = 5.27618
I0412 14:00:19.858464  6895 solver.cpp:237]     Train net output #0: loss = 5.27618 (* 1 = 5.27618 loss)
I0412 14:00:19.858476  6895 sgd_solver.cpp:105] Iteration 8904, lr = 0.001714
I0412 14:00:24.895975  6895 solver.cpp:218] Iteration 8916 (2.38222 iter/s, 5.03731s/12 iters), loss = 5.26606
I0412 14:00:24.896029  6895 solver.cpp:237]     Train net output #0: loss = 5.26606 (* 1 = 5.26606 loss)
I0412 14:00:24.896041  6895 sgd_solver.cpp:105] Iteration 8916, lr = 0.00170993
I0412 14:00:29.402613  6895 solver.cpp:218] Iteration 8928 (2.66288 iter/s, 4.50641s/12 iters), loss = 5.2653
I0412 14:00:29.402667  6895 solver.cpp:237]     Train net output #0: loss = 5.2653 (* 1 = 5.2653 loss)
I0412 14:00:29.402678  6895 sgd_solver.cpp:105] Iteration 8928, lr = 0.00170587
I0412 14:00:33.906747  6895 solver.cpp:218] Iteration 8940 (2.66436 iter/s, 4.5039s/12 iters), loss = 5.26472
I0412 14:00:33.906800  6895 solver.cpp:237]     Train net output #0: loss = 5.26472 (* 1 = 5.26472 loss)
I0412 14:00:33.906812  6895 sgd_solver.cpp:105] Iteration 8940, lr = 0.00170182
I0412 14:00:38.721276  6895 solver.cpp:218] Iteration 8952 (2.49258 iter/s, 4.81429s/12 iters), loss = 5.25802
I0412 14:00:38.721328  6895 solver.cpp:237]     Train net output #0: loss = 5.25802 (* 1 = 5.25802 loss)
I0412 14:00:38.721341  6895 sgd_solver.cpp:105] Iteration 8952, lr = 0.00169778
I0412 14:00:43.568697  6895 solver.cpp:218] Iteration 8964 (2.47567 iter/s, 4.84718s/12 iters), loss = 5.27838
I0412 14:00:43.568754  6895 solver.cpp:237]     Train net output #0: loss = 5.27838 (* 1 = 5.27838 loss)
I0412 14:00:43.568768  6895 sgd_solver.cpp:105] Iteration 8964, lr = 0.00169375
I0412 14:00:47.945242  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8976.caffemodel
I0412 14:00:49.443064  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8976.solverstate
I0412 14:00:50.629087  6895 solver.cpp:330] Iteration 8976, Testing net (#0)
I0412 14:00:50.629117  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:00:51.581163  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:00:55.185050  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:00:55.185081  6895 solver.cpp:397]     Test net output #1: loss = 5.28611 (* 1 = 5.28611 loss)
I0412 14:00:55.268640  6895 solver.cpp:218] Iteration 8976 (1.02569 iter/s, 11.6994s/12 iters), loss = 5.27515
I0412 14:00:55.268705  6895 solver.cpp:237]     Train net output #0: loss = 5.27515 (* 1 = 5.27515 loss)
I0412 14:00:55.268720  6895 sgd_solver.cpp:105] Iteration 8976, lr = 0.00168973
I0412 14:00:59.312255  6895 solver.cpp:218] Iteration 8988 (2.9678 iter/s, 4.0434s/12 iters), loss = 5.28493
I0412 14:00:59.312297  6895 solver.cpp:237]     Train net output #0: loss = 5.28493 (* 1 = 5.28493 loss)
I0412 14:00:59.312305  6895 sgd_solver.cpp:105] Iteration 8988, lr = 0.00168571
I0412 14:01:02.161823  6895 blocking_queue.cpp:49] Waiting for data
I0412 14:01:04.254540  6895 solver.cpp:218] Iteration 9000 (2.42814 iter/s, 4.94204s/12 iters), loss = 5.28722
I0412 14:01:04.254585  6895 solver.cpp:237]     Train net output #0: loss = 5.28722 (* 1 = 5.28722 loss)
I0412 14:01:04.254595  6895 sgd_solver.cpp:105] Iteration 9000, lr = 0.00168171
I0412 14:01:04.869381  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:01:08.976487  6895 solver.cpp:218] Iteration 9012 (2.54145 iter/s, 4.72171s/12 iters), loss = 5.2816
I0412 14:01:08.976537  6895 solver.cpp:237]     Train net output #0: loss = 5.2816 (* 1 = 5.2816 loss)
I0412 14:01:08.976549  6895 sgd_solver.cpp:105] Iteration 9012, lr = 0.00167772
I0412 14:01:14.082024  6895 solver.cpp:218] Iteration 9024 (2.3505 iter/s, 5.10529s/12 iters), loss = 5.2658
I0412 14:01:14.082074  6895 solver.cpp:237]     Train net output #0: loss = 5.2658 (* 1 = 5.2658 loss)
I0412 14:01:14.082087  6895 sgd_solver.cpp:105] Iteration 9024, lr = 0.00167374
I0412 14:01:18.761260  6895 solver.cpp:218] Iteration 9036 (2.56465 iter/s, 4.679s/12 iters), loss = 5.2695
I0412 14:01:18.761358  6895 solver.cpp:237]     Train net output #0: loss = 5.2695 (* 1 = 5.2695 loss)
I0412 14:01:18.761368  6895 sgd_solver.cpp:105] Iteration 9036, lr = 0.00166976
I0412 14:01:23.602421  6895 solver.cpp:218] Iteration 9048 (2.47889 iter/s, 4.84088s/12 iters), loss = 5.27734
I0412 14:01:23.602476  6895 solver.cpp:237]     Train net output #0: loss = 5.27734 (* 1 = 5.27734 loss)
I0412 14:01:23.602490  6895 sgd_solver.cpp:105] Iteration 9048, lr = 0.0016658
I0412 14:01:28.492296  6895 solver.cpp:218] Iteration 9060 (2.45418 iter/s, 4.88962s/12 iters), loss = 5.28905
I0412 14:01:28.492359  6895 solver.cpp:237]     Train net output #0: loss = 5.28905 (* 1 = 5.28905 loss)
I0412 14:01:28.492373  6895 sgd_solver.cpp:105] Iteration 9060, lr = 0.00166184
I0412 14:01:33.316336  6895 solver.cpp:218] Iteration 9072 (2.48767 iter/s, 4.8238s/12 iters), loss = 5.27064
I0412 14:01:33.316378  6895 solver.cpp:237]     Train net output #0: loss = 5.27064 (* 1 = 5.27064 loss)
I0412 14:01:33.316387  6895 sgd_solver.cpp:105] Iteration 9072, lr = 0.0016579
I0412 14:01:35.351325  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9078.caffemodel
I0412 14:01:37.235088  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9078.solverstate
I0412 14:01:38.941272  6895 solver.cpp:330] Iteration 9078, Testing net (#0)
I0412 14:01:38.941303  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:01:39.831404  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:01:43.525174  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:01:43.525211  6895 solver.cpp:397]     Test net output #1: loss = 5.28632 (* 1 = 5.28632 loss)
I0412 14:01:45.362283  6895 solver.cpp:218] Iteration 9084 (0.996226 iter/s, 12.0455s/12 iters), loss = 5.26161
I0412 14:01:45.362330  6895 solver.cpp:237]     Train net output #0: loss = 5.26161 (* 1 = 5.26161 loss)
I0412 14:01:45.362339  6895 sgd_solver.cpp:105] Iteration 9084, lr = 0.00165396
I0412 14:01:50.592792  6895 solver.cpp:218] Iteration 9096 (2.29434 iter/s, 5.23026s/12 iters), loss = 5.2651
I0412 14:01:50.592881  6895 solver.cpp:237]     Train net output #0: loss = 5.2651 (* 1 = 5.2651 loss)
I0412 14:01:50.592891  6895 sgd_solver.cpp:105] Iteration 9096, lr = 0.00165003
I0412 14:01:53.683817  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:01:55.690172  6895 solver.cpp:218] Iteration 9108 (2.35428 iter/s, 5.0971s/12 iters), loss = 5.26439
I0412 14:01:55.690208  6895 solver.cpp:237]     Train net output #0: loss = 5.26439 (* 1 = 5.26439 loss)
I0412 14:01:55.690217  6895 sgd_solver.cpp:105] Iteration 9108, lr = 0.00164612
I0412 14:02:00.559689  6895 solver.cpp:218] Iteration 9120 (2.46442 iter/s, 4.86929s/12 iters), loss = 5.2516
I0412 14:02:00.559741  6895 solver.cpp:237]     Train net output #0: loss = 5.2516 (* 1 = 5.2516 loss)
I0412 14:02:00.559751  6895 sgd_solver.cpp:105] Iteration 9120, lr = 0.00164221
I0412 14:02:05.328681  6895 solver.cpp:218] Iteration 9132 (2.51638 iter/s, 4.76875s/12 iters), loss = 5.25046
I0412 14:02:05.328734  6895 solver.cpp:237]     Train net output #0: loss = 5.25046 (* 1 = 5.25046 loss)
I0412 14:02:05.328747  6895 sgd_solver.cpp:105] Iteration 9132, lr = 0.00163831
I0412 14:02:10.285162  6895 solver.cpp:218] Iteration 9144 (2.42119 iter/s, 4.95623s/12 iters), loss = 5.25657
I0412 14:02:10.285207  6895 solver.cpp:237]     Train net output #0: loss = 5.25657 (* 1 = 5.25657 loss)
I0412 14:02:10.285215  6895 sgd_solver.cpp:105] Iteration 9144, lr = 0.00163442
I0412 14:02:15.425302  6895 solver.cpp:218] Iteration 9156 (2.33468 iter/s, 5.13989s/12 iters), loss = 5.28946
I0412 14:02:15.425352  6895 solver.cpp:237]     Train net output #0: loss = 5.28946 (* 1 = 5.28946 loss)
I0412 14:02:15.425364  6895 sgd_solver.cpp:105] Iteration 9156, lr = 0.00163054
I0412 14:02:20.562469  6895 solver.cpp:218] Iteration 9168 (2.33603 iter/s, 5.13692s/12 iters), loss = 5.27259
I0412 14:02:20.562510  6895 solver.cpp:237]     Train net output #0: loss = 5.27259 (* 1 = 5.27259 loss)
I0412 14:02:20.562517  6895 sgd_solver.cpp:105] Iteration 9168, lr = 0.00162667
I0412 14:02:25.107215  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9180.caffemodel
I0412 14:02:26.686632  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9180.solverstate
I0412 14:02:27.855561  6895 solver.cpp:330] Iteration 9180, Testing net (#0)
I0412 14:02:27.855588  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:02:28.714917  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:02:32.766023  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:02:32.766070  6895 solver.cpp:397]     Test net output #1: loss = 5.28658 (* 1 = 5.28658 loss)
I0412 14:02:32.849570  6895 solver.cpp:218] Iteration 9180 (0.976674 iter/s, 12.2866s/12 iters), loss = 5.27561
I0412 14:02:32.849620  6895 solver.cpp:237]     Train net output #0: loss = 5.27561 (* 1 = 5.27561 loss)
I0412 14:02:32.849632  6895 sgd_solver.cpp:105] Iteration 9180, lr = 0.00162281
I0412 14:02:37.216248  6895 solver.cpp:218] Iteration 9192 (2.74823 iter/s, 4.36645s/12 iters), loss = 5.27095
I0412 14:02:37.216295  6895 solver.cpp:237]     Train net output #0: loss = 5.27095 (* 1 = 5.27095 loss)
I0412 14:02:37.216307  6895 sgd_solver.cpp:105] Iteration 9192, lr = 0.00161895
I0412 14:02:42.047582  6895 solver.cpp:218] Iteration 9204 (2.48391 iter/s, 4.8311s/12 iters), loss = 5.26625
I0412 14:02:42.047628  6895 solver.cpp:237]     Train net output #0: loss = 5.26625 (* 1 = 5.26625 loss)
I0412 14:02:42.047637  6895 sgd_solver.cpp:105] Iteration 9204, lr = 0.00161511
I0412 14:02:42.115339  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:02:46.784288  6895 solver.cpp:218] Iteration 9216 (2.53353 iter/s, 4.73647s/12 iters), loss = 5.2825
I0412 14:02:46.784341  6895 solver.cpp:237]     Train net output #0: loss = 5.2825 (* 1 = 5.2825 loss)
I0412 14:02:46.784354  6895 sgd_solver.cpp:105] Iteration 9216, lr = 0.00161128
I0412 14:02:51.551497  6895 solver.cpp:218] Iteration 9228 (2.51732 iter/s, 4.76697s/12 iters), loss = 5.28485
I0412 14:02:51.551542  6895 solver.cpp:237]     Train net output #0: loss = 5.28485 (* 1 = 5.28485 loss)
I0412 14:02:51.551551  6895 sgd_solver.cpp:105] Iteration 9228, lr = 0.00160745
I0412 14:02:56.309630  6895 solver.cpp:218] Iteration 9240 (2.52212 iter/s, 4.7579s/12 iters), loss = 5.26234
I0412 14:02:56.310108  6895 solver.cpp:237]     Train net output #0: loss = 5.26234 (* 1 = 5.26234 loss)
I0412 14:02:56.310123  6895 sgd_solver.cpp:105] Iteration 9240, lr = 0.00160363
I0412 14:03:01.097316  6895 solver.cpp:218] Iteration 9252 (2.50678 iter/s, 4.78702s/12 iters), loss = 5.27441
I0412 14:03:01.097378  6895 solver.cpp:237]     Train net output #0: loss = 5.27441 (* 1 = 5.27441 loss)
I0412 14:03:01.097389  6895 sgd_solver.cpp:105] Iteration 9252, lr = 0.00159983
I0412 14:03:05.839190  6895 solver.cpp:218] Iteration 9264 (2.53078 iter/s, 4.74163s/12 iters), loss = 5.26444
I0412 14:03:05.839238  6895 solver.cpp:237]     Train net output #0: loss = 5.26444 (* 1 = 5.26444 loss)
I0412 14:03:05.839247  6895 sgd_solver.cpp:105] Iteration 9264, lr = 0.00159603
I0412 14:03:10.539399  6895 solver.cpp:218] Iteration 9276 (2.5532 iter/s, 4.69998s/12 iters), loss = 5.25081
I0412 14:03:10.539449  6895 solver.cpp:237]     Train net output #0: loss = 5.25081 (* 1 = 5.25081 loss)
I0412 14:03:10.539461  6895 sgd_solver.cpp:105] Iteration 9276, lr = 0.00159224
I0412 14:03:12.524883  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9282.caffemodel
I0412 14:03:14.058107  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9282.solverstate
I0412 14:03:15.226205  6895 solver.cpp:330] Iteration 9282, Testing net (#0)
I0412 14:03:15.226231  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:03:16.054260  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:03:19.685003  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:03:19.685055  6895 solver.cpp:397]     Test net output #1: loss = 5.28614 (* 1 = 5.28614 loss)
I0412 14:03:21.457249  6895 solver.cpp:218] Iteration 9288 (1.09916 iter/s, 10.9174s/12 iters), loss = 5.26794
I0412 14:03:21.457305  6895 solver.cpp:237]     Train net output #0: loss = 5.26794 (* 1 = 5.26794 loss)
I0412 14:03:21.457316  6895 sgd_solver.cpp:105] Iteration 9288, lr = 0.00158846
I0412 14:03:26.289068  6895 solver.cpp:218] Iteration 9300 (2.48366 iter/s, 4.83157s/12 iters), loss = 5.25084
I0412 14:03:26.289119  6895 solver.cpp:237]     Train net output #0: loss = 5.25084 (* 1 = 5.25084 loss)
I0412 14:03:26.289129  6895 sgd_solver.cpp:105] Iteration 9300, lr = 0.00158469
I0412 14:03:28.352903  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:03:31.027040  6895 solver.cpp:218] Iteration 9312 (2.53286 iter/s, 4.73774s/12 iters), loss = 5.27142
I0412 14:03:31.027096  6895 solver.cpp:237]     Train net output #0: loss = 5.27142 (* 1 = 5.27142 loss)
I0412 14:03:31.027112  6895 sgd_solver.cpp:105] Iteration 9312, lr = 0.00158092
I0412 14:03:35.686501  6895 solver.cpp:218] Iteration 9324 (2.57554 iter/s, 4.65922s/12 iters), loss = 5.27779
I0412 14:03:35.686553  6895 solver.cpp:237]     Train net output #0: loss = 5.27779 (* 1 = 5.27779 loss)
I0412 14:03:35.686564  6895 sgd_solver.cpp:105] Iteration 9324, lr = 0.00157717
I0412 14:03:40.421555  6895 solver.cpp:218] Iteration 9336 (2.53442 iter/s, 4.73481s/12 iters), loss = 5.28474
I0412 14:03:40.421610  6895 solver.cpp:237]     Train net output #0: loss = 5.28474 (* 1 = 5.28474 loss)
I0412 14:03:40.421622  6895 sgd_solver.cpp:105] Iteration 9336, lr = 0.00157343
I0412 14:03:45.073496  6895 solver.cpp:218] Iteration 9348 (2.5797 iter/s, 4.6517s/12 iters), loss = 5.27016
I0412 14:03:45.073550  6895 solver.cpp:237]     Train net output #0: loss = 5.27016 (* 1 = 5.27016 loss)
I0412 14:03:45.073562  6895 sgd_solver.cpp:105] Iteration 9348, lr = 0.00156969
I0412 14:03:49.863976  6895 solver.cpp:218] Iteration 9360 (2.5051 iter/s, 4.79024s/12 iters), loss = 5.27044
I0412 14:03:49.864032  6895 solver.cpp:237]     Train net output #0: loss = 5.27044 (* 1 = 5.27044 loss)
I0412 14:03:49.864045  6895 sgd_solver.cpp:105] Iteration 9360, lr = 0.00156596
I0412 14:03:54.590582  6895 solver.cpp:218] Iteration 9372 (2.53895 iter/s, 4.72637s/12 iters), loss = 5.27196
I0412 14:03:54.590627  6895 solver.cpp:237]     Train net output #0: loss = 5.27196 (* 1 = 5.27196 loss)
I0412 14:03:54.590636  6895 sgd_solver.cpp:105] Iteration 9372, lr = 0.00156225
I0412 14:03:59.208885  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9384.caffemodel
I0412 14:04:02.628093  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9384.solverstate
I0412 14:04:05.268959  6895 solver.cpp:330] Iteration 9384, Testing net (#0)
I0412 14:04:05.268988  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:04:06.050433  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:04:09.731938  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:04:09.731984  6895 solver.cpp:397]     Test net output #1: loss = 5.2862 (* 1 = 5.2862 loss)
I0412 14:04:09.816174  6895 solver.cpp:218] Iteration 9384 (0.788178 iter/s, 15.225s/12 iters), loss = 5.27892
I0412 14:04:09.816221  6895 solver.cpp:237]     Train net output #0: loss = 5.27892 (* 1 = 5.27892 loss)
I0412 14:04:09.816232  6895 sgd_solver.cpp:105] Iteration 9384, lr = 0.00155854
I0412 14:04:13.912302  6895 solver.cpp:218] Iteration 9396 (2.92975 iter/s, 4.09591s/12 iters), loss = 5.27065
I0412 14:04:13.912353  6895 solver.cpp:237]     Train net output #0: loss = 5.27065 (* 1 = 5.27065 loss)
I0412 14:04:13.912364  6895 sgd_solver.cpp:105] Iteration 9396, lr = 0.00155484
I0412 14:04:18.055383  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:04:18.660358  6895 solver.cpp:218] Iteration 9408 (2.52748 iter/s, 4.74782s/12 iters), loss = 5.27024
I0412 14:04:18.660410  6895 solver.cpp:237]     Train net output #0: loss = 5.27024 (* 1 = 5.27024 loss)
I0412 14:04:18.660424  6895 sgd_solver.cpp:105] Iteration 9408, lr = 0.00155114
I0412 14:04:23.428915  6895 solver.cpp:218] Iteration 9420 (2.51661 iter/s, 4.76832s/12 iters), loss = 5.2792
I0412 14:04:23.428968  6895 solver.cpp:237]     Train net output #0: loss = 5.2792 (* 1 = 5.2792 loss)
I0412 14:04:23.428980  6895 sgd_solver.cpp:105] Iteration 9420, lr = 0.00154746
I0412 14:04:28.318486  6895 solver.cpp:218] Iteration 9432 (2.45432 iter/s, 4.88933s/12 iters), loss = 5.28252
I0412 14:04:28.318518  6895 solver.cpp:237]     Train net output #0: loss = 5.28252 (* 1 = 5.28252 loss)
I0412 14:04:28.318526  6895 sgd_solver.cpp:105] Iteration 9432, lr = 0.00154379
I0412 14:04:33.225458  6895 solver.cpp:218] Iteration 9444 (2.44562 iter/s, 4.90674s/12 iters), loss = 5.28256
I0412 14:04:33.225601  6895 solver.cpp:237]     Train net output #0: loss = 5.28256 (* 1 = 5.28256 loss)
I0412 14:04:33.225615  6895 sgd_solver.cpp:105] Iteration 9444, lr = 0.00154012
I0412 14:04:38.208076  6895 solver.cpp:218] Iteration 9456 (2.40854 iter/s, 4.98228s/12 iters), loss = 5.26837
I0412 14:04:38.208129  6895 solver.cpp:237]     Train net output #0: loss = 5.26837 (* 1 = 5.26837 loss)
I0412 14:04:38.208142  6895 sgd_solver.cpp:105] Iteration 9456, lr = 0.00153647
I0412 14:04:42.980568  6895 solver.cpp:218] Iteration 9468 (2.51454 iter/s, 4.77225s/12 iters), loss = 5.27849
I0412 14:04:42.980620  6895 solver.cpp:237]     Train net output #0: loss = 5.27849 (* 1 = 5.27849 loss)
I0412 14:04:42.980631  6895 sgd_solver.cpp:105] Iteration 9468, lr = 0.00153282
I0412 14:04:47.892031  6895 solver.cpp:218] Iteration 9480 (2.44339 iter/s, 4.91122s/12 iters), loss = 5.27857
I0412 14:04:47.892076  6895 solver.cpp:237]     Train net output #0: loss = 5.27857 (* 1 = 5.27857 loss)
I0412 14:04:47.892084  6895 sgd_solver.cpp:105] Iteration 9480, lr = 0.00152918
I0412 14:04:49.955716  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9486.caffemodel
I0412 14:04:52.115504  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9486.solverstate
I0412 14:04:53.881454  6895 solver.cpp:330] Iteration 9486, Testing net (#0)
I0412 14:04:53.881481  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:04:54.605304  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:04:58.639210  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:04:58.639254  6895 solver.cpp:397]     Test net output #1: loss = 5.28576 (* 1 = 5.28576 loss)
I0412 14:05:00.541237  6895 solver.cpp:218] Iteration 9492 (0.948716 iter/s, 12.6487s/12 iters), loss = 5.27409
I0412 14:05:00.541299  6895 solver.cpp:237]     Train net output #0: loss = 5.27409 (* 1 = 5.27409 loss)
I0412 14:05:00.541311  6895 sgd_solver.cpp:105] Iteration 9492, lr = 0.00152555
I0412 14:05:05.306069  6895 solver.cpp:218] Iteration 9504 (2.51858 iter/s, 4.76458s/12 iters), loss = 5.26169
I0412 14:05:05.306171  6895 solver.cpp:237]     Train net output #0: loss = 5.26169 (* 1 = 5.26169 loss)
I0412 14:05:05.306182  6895 sgd_solver.cpp:105] Iteration 9504, lr = 0.00152193
I0412 14:05:06.725997  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:05:10.182499  6895 solver.cpp:218] Iteration 9516 (2.46097 iter/s, 4.87613s/12 iters), loss = 5.2585
I0412 14:05:10.182554  6895 solver.cpp:237]     Train net output #0: loss = 5.2585 (* 1 = 5.2585 loss)
I0412 14:05:10.182566  6895 sgd_solver.cpp:105] Iteration 9516, lr = 0.00151831
I0412 14:05:15.252249  6895 solver.cpp:218] Iteration 9528 (2.3671 iter/s, 5.0695s/12 iters), loss = 5.26417
I0412 14:05:15.252298  6895 solver.cpp:237]     Train net output #0: loss = 5.26417 (* 1 = 5.26417 loss)
I0412 14:05:15.252310  6895 sgd_solver.cpp:105] Iteration 9528, lr = 0.00151471
I0412 14:05:20.050700  6895 solver.cpp:218] Iteration 9540 (2.50093 iter/s, 4.79821s/12 iters), loss = 5.24573
I0412 14:05:20.050746  6895 solver.cpp:237]     Train net output #0: loss = 5.24573 (* 1 = 5.24573 loss)
I0412 14:05:20.050755  6895 sgd_solver.cpp:105] Iteration 9540, lr = 0.00151111
I0412 14:05:24.895658  6895 solver.cpp:218] Iteration 9552 (2.47692 iter/s, 4.84472s/12 iters), loss = 5.30126
I0412 14:05:24.895714  6895 solver.cpp:237]     Train net output #0: loss = 5.30126 (* 1 = 5.30126 loss)
I0412 14:05:24.895726  6895 sgd_solver.cpp:105] Iteration 9552, lr = 0.00150752
I0412 14:05:29.568173  6895 solver.cpp:218] Iteration 9564 (2.56834 iter/s, 4.67228s/12 iters), loss = 5.25637
I0412 14:05:29.568224  6895 solver.cpp:237]     Train net output #0: loss = 5.25637 (* 1 = 5.25637 loss)
I0412 14:05:29.568235  6895 sgd_solver.cpp:105] Iteration 9564, lr = 0.00150395
I0412 14:05:34.494477  6895 solver.cpp:218] Iteration 9576 (2.43603 iter/s, 4.92605s/12 iters), loss = 5.26477
I0412 14:05:34.494524  6895 solver.cpp:237]     Train net output #0: loss = 5.26477 (* 1 = 5.26477 loss)
I0412 14:05:34.494531  6895 sgd_solver.cpp:105] Iteration 9576, lr = 0.00150037
I0412 14:05:38.829020  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9588.caffemodel
I0412 14:05:40.364568  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9588.solverstate
I0412 14:05:41.548887  6895 solver.cpp:330] Iteration 9588, Testing net (#0)
I0412 14:05:41.548907  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:05:42.234930  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:05:45.999662  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:05:45.999699  6895 solver.cpp:397]     Test net output #1: loss = 5.28599 (* 1 = 5.28599 loss)
I0412 14:05:46.083097  6895 solver.cpp:218] Iteration 9588 (1.03554 iter/s, 11.5881s/12 iters), loss = 5.27283
I0412 14:05:46.083151  6895 solver.cpp:237]     Train net output #0: loss = 5.27283 (* 1 = 5.27283 loss)
I0412 14:05:46.083163  6895 sgd_solver.cpp:105] Iteration 9588, lr = 0.00149681
I0412 14:05:50.222406  6895 solver.cpp:218] Iteration 9600 (2.89922 iter/s, 4.13905s/12 iters), loss = 5.27258
I0412 14:05:50.222468  6895 solver.cpp:237]     Train net output #0: loss = 5.27258 (* 1 = 5.27258 loss)
I0412 14:05:50.222483  6895 sgd_solver.cpp:105] Iteration 9600, lr = 0.00149326
I0412 14:05:53.760013  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:05:55.041533  6895 solver.cpp:218] Iteration 9612 (2.49021 iter/s, 4.81888s/12 iters), loss = 5.27352
I0412 14:05:55.041589  6895 solver.cpp:237]     Train net output #0: loss = 5.27352 (* 1 = 5.27352 loss)
I0412 14:05:55.041604  6895 sgd_solver.cpp:105] Iteration 9612, lr = 0.00148971
I0412 14:05:59.844254  6895 solver.cpp:218] Iteration 9624 (2.49871 iter/s, 4.80248s/12 iters), loss = 5.27061
I0412 14:05:59.844298  6895 solver.cpp:237]     Train net output #0: loss = 5.27061 (* 1 = 5.27061 loss)
I0412 14:05:59.844307  6895 sgd_solver.cpp:105] Iteration 9624, lr = 0.00148618
I0412 14:06:04.711362  6895 solver.cpp:218] Iteration 9636 (2.46565 iter/s, 4.86687s/12 iters), loss = 5.25582
I0412 14:06:04.711405  6895 solver.cpp:237]     Train net output #0: loss = 5.25582 (* 1 = 5.25582 loss)
I0412 14:06:04.711413  6895 sgd_solver.cpp:105] Iteration 9636, lr = 0.00148265
I0412 14:06:09.467833  6895 solver.cpp:218] Iteration 9648 (2.523 iter/s, 4.75624s/12 iters), loss = 5.26755
I0412 14:06:09.467991  6895 solver.cpp:237]     Train net output #0: loss = 5.26755 (* 1 = 5.26755 loss)
I0412 14:06:09.468003  6895 sgd_solver.cpp:105] Iteration 9648, lr = 0.00147913
I0412 14:06:14.240170  6895 solver.cpp:218] Iteration 9660 (2.51467 iter/s, 4.77199s/12 iters), loss = 5.25292
I0412 14:06:14.240226  6895 solver.cpp:237]     Train net output #0: loss = 5.25292 (* 1 = 5.25292 loss)
I0412 14:06:14.240237  6895 sgd_solver.cpp:105] Iteration 9660, lr = 0.00147562
I0412 14:06:19.206460  6895 solver.cpp:218] Iteration 9672 (2.41641 iter/s, 4.96604s/12 iters), loss = 5.27516
I0412 14:06:19.206514  6895 solver.cpp:237]     Train net output #0: loss = 5.27516 (* 1 = 5.27516 loss)
I0412 14:06:19.206526  6895 sgd_solver.cpp:105] Iteration 9672, lr = 0.00147211
I0412 14:06:23.832448  6895 solver.cpp:218] Iteration 9684 (2.59417 iter/s, 4.62575s/12 iters), loss = 5.29085
I0412 14:06:23.832500  6895 solver.cpp:237]     Train net output #0: loss = 5.29085 (* 1 = 5.29085 loss)
I0412 14:06:23.832511  6895 sgd_solver.cpp:105] Iteration 9684, lr = 0.00146862
I0412 14:06:25.804827  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9690.caffemodel
I0412 14:06:27.360313  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9690.solverstate
I0412 14:06:30.524413  6895 solver.cpp:330] Iteration 9690, Testing net (#0)
I0412 14:06:30.524437  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:06:31.146186  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:06:33.942443  6895 blocking_queue.cpp:49] Waiting for data
I0412 14:06:35.035110  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:06:35.035156  6895 solver.cpp:397]     Test net output #1: loss = 5.28617 (* 1 = 5.28617 loss)
I0412 14:06:36.974064  6895 solver.cpp:218] Iteration 9696 (0.913167 iter/s, 13.1411s/12 iters), loss = 5.28591
I0412 14:06:36.974109  6895 solver.cpp:237]     Train net output #0: loss = 5.28591 (* 1 = 5.28591 loss)
I0412 14:06:36.974118  6895 sgd_solver.cpp:105] Iteration 9696, lr = 0.00146513
I0412 14:06:41.672984  6895 solver.cpp:218] Iteration 9708 (2.5539 iter/s, 4.69869s/12 iters), loss = 5.28653
I0412 14:06:41.673100  6895 solver.cpp:237]     Train net output #0: loss = 5.28653 (* 1 = 5.28653 loss)
I0412 14:06:41.673115  6895 sgd_solver.cpp:105] Iteration 9708, lr = 0.00146165
I0412 14:06:42.423601  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:06:46.765426  6895 solver.cpp:218] Iteration 9720 (2.35658 iter/s, 5.09213s/12 iters), loss = 5.28855
I0412 14:06:46.765478  6895 solver.cpp:237]     Train net output #0: loss = 5.28855 (* 1 = 5.28855 loss)
I0412 14:06:46.765489  6895 sgd_solver.cpp:105] Iteration 9720, lr = 0.00145818
I0412 14:06:51.795089  6895 solver.cpp:218] Iteration 9732 (2.38596 iter/s, 5.02942s/12 iters), loss = 5.26073
I0412 14:06:51.795135  6895 solver.cpp:237]     Train net output #0: loss = 5.26073 (* 1 = 5.26073 loss)
I0412 14:06:51.795145  6895 sgd_solver.cpp:105] Iteration 9732, lr = 0.00145472
I0412 14:06:56.717200  6895 solver.cpp:218] Iteration 9744 (2.4381 iter/s, 4.92186s/12 iters), loss = 5.26712
I0412 14:06:56.717260  6895 solver.cpp:237]     Train net output #0: loss = 5.26712 (* 1 = 5.26712 loss)
I0412 14:06:56.717274  6895 sgd_solver.cpp:105] Iteration 9744, lr = 0.00145127
I0412 14:07:01.815263  6895 solver.cpp:218] Iteration 9756 (2.35395 iter/s, 5.09781s/12 iters), loss = 5.27444
I0412 14:07:01.815306  6895 solver.cpp:237]     Train net output #0: loss = 5.27444 (* 1 = 5.27444 loss)
I0412 14:07:01.815315  6895 sgd_solver.cpp:105] Iteration 9756, lr = 0.00144782
I0412 14:07:06.720201  6895 solver.cpp:218] Iteration 9768 (2.44663 iter/s, 4.9047s/12 iters), loss = 5.28765
I0412 14:07:06.720257  6895 solver.cpp:237]     Train net output #0: loss = 5.28765 (* 1 = 5.28765 loss)
I0412 14:07:06.720270  6895 sgd_solver.cpp:105] Iteration 9768, lr = 0.00144438
I0412 14:07:11.657441  6895 solver.cpp:218] Iteration 9780 (2.43063 iter/s, 4.93699s/12 iters), loss = 5.27152
I0412 14:07:11.657490  6895 solver.cpp:237]     Train net output #0: loss = 5.27152 (* 1 = 5.27152 loss)
I0412 14:07:11.657501  6895 sgd_solver.cpp:105] Iteration 9780, lr = 0.00144095
I0412 14:07:16.567344  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9792.caffemodel
I0412 14:07:18.141345  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9792.solverstate
I0412 14:07:19.324884  6895 solver.cpp:330] Iteration 9792, Testing net (#0)
I0412 14:07:19.324910  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:07:19.926959  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:07:23.905114  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:07:23.905164  6895 solver.cpp:397]     Test net output #1: loss = 5.28591 (* 1 = 5.28591 loss)
I0412 14:07:23.988752  6895 solver.cpp:218] Iteration 9792 (0.973173 iter/s, 12.3308s/12 iters), loss = 5.25703
I0412 14:07:23.988802  6895 solver.cpp:237]     Train net output #0: loss = 5.25703 (* 1 = 5.25703 loss)
I0412 14:07:23.988814  6895 sgd_solver.cpp:105] Iteration 9792, lr = 0.00143753
I0412 14:07:27.965528  6895 solver.cpp:218] Iteration 9804 (3.01768 iter/s, 3.97656s/12 iters), loss = 5.27349
I0412 14:07:27.965574  6895 solver.cpp:237]     Train net output #0: loss = 5.27349 (* 1 = 5.27349 loss)
I0412 14:07:27.965584  6895 sgd_solver.cpp:105] Iteration 9804, lr = 0.00143412
I0412 14:07:30.901583  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:07:32.761798  6895 solver.cpp:218] Iteration 9816 (2.50207 iter/s, 4.79604s/12 iters), loss = 5.26231
I0412 14:07:32.761844  6895 solver.cpp:237]     Train net output #0: loss = 5.26231 (* 1 = 5.26231 loss)
I0412 14:07:32.761854  6895 sgd_solver.cpp:105] Iteration 9816, lr = 0.00143072
I0412 14:07:37.433879  6895 solver.cpp:218] Iteration 9828 (2.56858 iter/s, 4.67185s/12 iters), loss = 5.25568
I0412 14:07:37.433928  6895 solver.cpp:237]     Train net output #0: loss = 5.25568 (* 1 = 5.25568 loss)
I0412 14:07:37.433938  6895 sgd_solver.cpp:105] Iteration 9828, lr = 0.00142732
I0412 14:07:42.276036  6895 solver.cpp:218] Iteration 9840 (2.47836 iter/s, 4.84192s/12 iters), loss = 5.2522
I0412 14:07:42.276085  6895 solver.cpp:237]     Train net output #0: loss = 5.2522 (* 1 = 5.2522 loss)
I0412 14:07:42.276098  6895 sgd_solver.cpp:105] Iteration 9840, lr = 0.00142393
I0412 14:07:47.061462  6895 solver.cpp:218] Iteration 9852 (2.50774 iter/s, 4.78519s/12 iters), loss = 5.26635
I0412 14:07:47.061578  6895 solver.cpp:237]     Train net output #0: loss = 5.26635 (* 1 = 5.26635 loss)
I0412 14:07:47.061591  6895 sgd_solver.cpp:105] Iteration 9852, lr = 0.00142055
I0412 14:07:51.819720  6895 solver.cpp:218] Iteration 9864 (2.52209 iter/s, 4.75796s/12 iters), loss = 5.28957
I0412 14:07:51.819774  6895 solver.cpp:237]     Train net output #0: loss = 5.28957 (* 1 = 5.28957 loss)
I0412 14:07:51.819787  6895 sgd_solver.cpp:105] Iteration 9864, lr = 0.00141718
I0412 14:07:56.449129  6895 solver.cpp:218] Iteration 9876 (2.59226 iter/s, 4.62917s/12 iters), loss = 5.27225
I0412 14:07:56.449187  6895 solver.cpp:237]     Train net output #0: loss = 5.27225 (* 1 = 5.27225 loss)
I0412 14:07:56.449199  6895 sgd_solver.cpp:105] Iteration 9876, lr = 0.00141381
I0412 14:08:01.277518  6895 solver.cpp:218] Iteration 9888 (2.48543 iter/s, 4.82814s/12 iters), loss = 5.27776
I0412 14:08:01.277561  6895 solver.cpp:237]     Train net output #0: loss = 5.27776 (* 1 = 5.27776 loss)
I0412 14:08:01.277570  6895 sgd_solver.cpp:105] Iteration 9888, lr = 0.00141045
I0412 14:08:03.245429  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9894.caffemodel
I0412 14:08:04.788544  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9894.solverstate
I0412 14:08:05.970425  6895 solver.cpp:330] Iteration 9894, Testing net (#0)
I0412 14:08:05.970453  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:08:06.486641  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:08:10.339149  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:08:10.339190  6895 solver.cpp:397]     Test net output #1: loss = 5.2863 (* 1 = 5.2863 loss)
I0412 14:08:12.163872  6895 solver.cpp:218] Iteration 9900 (1.10234 iter/s, 10.8859s/12 iters), loss = 5.27487
I0412 14:08:12.163921  6895 solver.cpp:237]     Train net output #0: loss = 5.27487 (* 1 = 5.27487 loss)
I0412 14:08:12.163933  6895 sgd_solver.cpp:105] Iteration 9900, lr = 0.00140711
I0412 14:08:17.054008  6895 solver.cpp:218] Iteration 9912 (2.45404 iter/s, 4.88989s/12 iters), loss = 5.25538
I0412 14:08:17.054056  6895 solver.cpp:237]     Train net output #0: loss = 5.25538 (* 1 = 5.25538 loss)
I0412 14:08:17.054067  6895 sgd_solver.cpp:105] Iteration 9912, lr = 0.00140377
I0412 14:08:17.167474  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:08:21.887282  6895 solver.cpp:218] Iteration 9924 (2.48291 iter/s, 4.83304s/12 iters), loss = 5.27403
I0412 14:08:21.887326  6895 solver.cpp:237]     Train net output #0: loss = 5.27403 (* 1 = 5.27403 loss)
I0412 14:08:21.887336  6895 sgd_solver.cpp:105] Iteration 9924, lr = 0.00140043
I0412 14:08:26.785801  6895 solver.cpp:218] Iteration 9936 (2.44984 iter/s, 4.89828s/12 iters), loss = 5.28879
I0412 14:08:26.785845  6895 solver.cpp:237]     Train net output #0: loss = 5.28879 (* 1 = 5.28879 loss)
I0412 14:08:26.785853  6895 sgd_solver.cpp:105] Iteration 9936, lr = 0.00139711
I0412 14:08:31.860167  6895 solver.cpp:218] Iteration 9948 (2.36494 iter/s, 5.07412s/12 iters), loss = 5.26243
I0412 14:08:31.860220  6895 solver.cpp:237]     Train net output #0: loss = 5.26243 (* 1 = 5.26243 loss)
I0412 14:08:31.860232  6895 sgd_solver.cpp:105] Iteration 9948, lr = 0.00139379
I0412 14:08:36.763972  6895 solver.cpp:218] Iteration 9960 (2.4472 iter/s, 4.90356s/12 iters), loss = 5.2702
I0412 14:08:36.764024  6895 solver.cpp:237]     Train net output #0: loss = 5.2702 (* 1 = 5.2702 loss)
I0412 14:08:36.764034  6895 sgd_solver.cpp:105] Iteration 9960, lr = 0.00139048
I0412 14:08:41.565717  6895 solver.cpp:218] Iteration 9972 (2.49922 iter/s, 4.8015s/12 iters), loss = 5.26456
I0412 14:08:41.565773  6895 solver.cpp:237]     Train net output #0: loss = 5.26456 (* 1 = 5.26456 loss)
I0412 14:08:41.565784  6895 sgd_solver.cpp:105] Iteration 9972, lr = 0.00138718
I0412 14:08:46.402190  6895 solver.cpp:218] Iteration 9984 (2.48127 iter/s, 4.83623s/12 iters), loss = 5.24642
I0412 14:08:46.402245  6895 solver.cpp:237]     Train net output #0: loss = 5.24642 (* 1 = 5.24642 loss)
I0412 14:08:46.402256  6895 sgd_solver.cpp:105] Iteration 9984, lr = 0.00138389
I0412 14:08:50.676620  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9996.caffemodel
I0412 14:08:52.232292  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9996.solverstate
I0412 14:08:53.821022  6895 solver.cpp:330] Iteration 9996, Testing net (#0)
I0412 14:08:53.821049  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:08:54.245645  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:08:58.255112  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:08:58.255146  6895 solver.cpp:397]     Test net output #1: loss = 5.28671 (* 1 = 5.28671 loss)
I0412 14:08:58.338891  6895 solver.cpp:218] Iteration 9996 (1.00534 iter/s, 11.9362s/12 iters), loss = 5.27174
I0412 14:08:58.338930  6895 solver.cpp:237]     Train net output #0: loss = 5.27174 (* 1 = 5.27174 loss)
I0412 14:08:58.338938  6895 sgd_solver.cpp:105] Iteration 9996, lr = 0.0013806
I0412 14:09:02.410925  6895 solver.cpp:218] Iteration 10008 (2.94708 iter/s, 4.07183s/12 iters), loss = 5.24456
I0412 14:09:02.410985  6895 solver.cpp:237]     Train net output #0: loss = 5.24456 (* 1 = 5.24456 loss)
I0412 14:09:02.410998  6895 sgd_solver.cpp:105] Iteration 10008, lr = 0.00137732
I0412 14:09:04.606178  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:09:07.333307  6895 solver.cpp:218] Iteration 10020 (2.43797 iter/s, 4.92213s/12 iters), loss = 5.27106
I0412 14:09:07.333360  6895 solver.cpp:237]     Train net output #0: loss = 5.27106 (* 1 = 5.27106 loss)
I0412 14:09:07.333372  6895 sgd_solver.cpp:105] Iteration 10020, lr = 0.00137405
I0412 14:09:12.243618  6895 solver.cpp:218] Iteration 10032 (2.44396 iter/s, 4.91006s/12 iters), loss = 5.27406
I0412 14:09:12.243665  6895 solver.cpp:237]     Train net output #0: loss = 5.27406 (* 1 = 5.27406 loss)
I0412 14:09:12.243674  6895 sgd_solver.cpp:105] Iteration 10032, lr = 0.00137079
I0412 14:09:17.076911  6895 solver.cpp:218] Iteration 10044 (2.4829 iter/s, 4.83306s/12 iters), loss = 5.2869
I0412 14:09:17.076961  6895 solver.cpp:237]     Train net output #0: loss = 5.2869 (* 1 = 5.2869 loss)
I0412 14:09:17.076970  6895 sgd_solver.cpp:105] Iteration 10044, lr = 0.00136754
I0412 14:09:21.897241  6895 solver.cpp:218] Iteration 10056 (2.48958 iter/s, 4.82009s/12 iters), loss = 5.27646
I0412 14:09:21.897403  6895 solver.cpp:237]     Train net output #0: loss = 5.27646 (* 1 = 5.27646 loss)
I0412 14:09:21.897418  6895 sgd_solver.cpp:105] Iteration 10056, lr = 0.00136429
I0412 14:09:26.749213  6895 solver.cpp:218] Iteration 10068 (2.4734 iter/s, 4.85163s/12 iters), loss = 5.27452
I0412 14:09:26.749254  6895 solver.cpp:237]     Train net output #0: loss = 5.27452 (* 1 = 5.27452 loss)
I0412 14:09:26.749265  6895 sgd_solver.cpp:105] Iteration 10068, lr = 0.00136105
I0412 14:09:31.469902  6895 solver.cpp:218] Iteration 10080 (2.54213 iter/s, 4.72046s/12 iters), loss = 5.26021
I0412 14:09:31.469949  6895 solver.cpp:237]     Train net output #0: loss = 5.26021 (* 1 = 5.26021 loss)
I0412 14:09:31.469975  6895 sgd_solver.cpp:105] Iteration 10080, lr = 0.00135782
I0412 14:09:36.479442  6895 solver.cpp:218] Iteration 10092 (2.39555 iter/s, 5.00929s/12 iters), loss = 5.28163
I0412 14:09:36.479490  6895 solver.cpp:237]     Train net output #0: loss = 5.28163 (* 1 = 5.28163 loss)
I0412 14:09:36.479498  6895 sgd_solver.cpp:105] Iteration 10092, lr = 0.0013546
I0412 14:09:38.409736  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_10098.caffemodel
I0412 14:09:39.878976  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_10098.solverstate
I0412 14:09:41.057657  6895 solver.cpp:330] Iteration 10098, Testing net (#0)
I0412 14:09:41.057684  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:09:41.522097  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:09:45.456266  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:09:45.456315  6895 solver.cpp:397]     Test net output #1: loss = 5.28635 (* 1 = 5.28635 loss)
I0412 14:09:47.385298  6895 solver.cpp:218] Iteration 10104 (1.10037 iter/s, 10.9054s/12 iters), loss = 5.27108
I0412 14:09:47.385344  6895 solver.cpp:237]     Train net output #0: loss = 5.27108 (* 1 = 5.27108 loss)
I0412 14:09:47.385354  6895 sgd_solver.cpp:105] Iteration 10104, lr = 0.00135138
I0412 14:09:51.650411  6899 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:09:52.259723  6895 solver.cpp:218] Iteration 10116 (2.46195 iter/s, 4.87418s/12 iters), loss = 5.26313
I0412 14:09:52.259865  6895 solver.cpp:237]     Train net output #0: loss = 5.26313 (* 1 = 5.26313 loss)
I0412 14:09:52.259879  6895 sgd_solver.cpp:105] Iteration 10116, lr = 0.00134817
I0412 14:09:57.200206  6895 solver.cpp:218] Iteration 10128 (2.42908 iter/s, 4.94015s/12 iters), loss = 5.27258
I0412 14:09:57.200249  6895 solver.cpp:237]     Train net output #0: loss = 5.27258 (* 1 = 5.27258 loss)
I0412 14:09:57.200258  6895 sgd_solver.cpp:105] Iteration 10128, lr = 0.00134497
I0412 14:10:02.192194  6895 solver.cpp:218] Iteration 10140 (2.40397 iter/s, 4.99174s/12 iters), loss = 5.2843
I0412 14:10:02.192246  6895 solver.cpp:237]     Train net output #0: loss = 5.2843 (* 1 = 5.2843 loss)
I0412 14:10:02.192258  6895 sgd_solver.cpp:105] Iteration 10140, lr = 0.00134178
I0412 14:10:07.054286  6895 solver.cpp:218] Iteration 10152 (2.4682 iter/s, 4.86185s/12 iters), loss = 5.27533
I0412 14:10:07.054349  6895 solver.cpp:237]     Train net output #0: loss = 5.27533 (* 1 = 5.27533 loss)
I0412 14:10:07.054363  6895 sgd_solver.cpp:105] Iteration 10152, lr = 0.00133859
I0412 14:10:12.190455  6895 solver.cpp:218] Iteration 10164 (2.33649 iter/s, 5.13592s/12 iters), loss = 5.26199
I0412 14:10:12.190511  6895 solver.cpp:237]     Train net output #0: loss = 5.26199 (* 1 = 5.26199 loss)
I0412 14:10:12.190522  6895 sgd_solver.cpp:105] Iteration 10164, lr = 0.00133541
I0412 14:10:17.162938  6895 solver.cpp:218] Iteration 10176 (2.4134 iter/s, 4.97223s/12 iters), loss = 5.27811
I0412 14:10:17.162986  6895 solver.cpp:237]     Train net output #0: loss = 5.27811 (* 1 = 5.27811 loss)
I0412 14:10:17.162999  6895 sgd_solver.cpp:105] Iteration 10176, lr = 0.00133224
I0412 14:10:21.988860  6895 solver.cpp:218] Iteration 10188 (2.48669 iter/s, 4.82568s/12 iters), loss = 5.27792
I0412 14:10:21.988901  6895 solver.cpp:237]     Train net output #0: loss = 5.27792 (* 1 = 5.27792 loss)
I0412 14:10:21.988910  6895 sgd_solver.cpp:105] Iteration 10188, lr = 0.00132908
I0412 14:10:26.571506  6895 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_10200.caffemodel
I0412 14:10:28.122284  6895 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_10200.solverstate
I0412 14:10:29.338454  6895 solver.cpp:310] Iteration 10200, loss = 5.2636
I0412 14:10:29.338490  6895 solver.cpp:330] Iteration 10200, Testing net (#0)
I0412 14:10:29.338496  6895 net.cpp:676] Ignoring source layer train-data
I0412 14:10:29.761833  6900 data_layer.cpp:73] Restarting data prefetching from start.
I0412 14:10:33.839372  6895 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0412 14:10:33.839423  6895 solver.cpp:397]     Test net output #1: loss = 5.28572 (* 1 = 5.28572 loss)
I0412 14:10:33.839433  6895 solver.cpp:315] Optimization Done.
I0412 14:10:33.839440  6895 caffe.cpp:259] Optimization Done.