I0410 01:57:47.088214 27877 upgrade_proto.cpp:1082] Attempting to upgrade input file specified using deprecated 'solver_type' field (enum)': /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210409-221117-2dbc/solver.prototxt
I0410 01:57:47.088503 27877 upgrade_proto.cpp:1089] Successfully upgraded file specified using deprecated 'solver_type' field (enum) to 'type' field (string).
W0410 01:57:47.088516 27877 upgrade_proto.cpp:1091] Note that future Caffe releases will only support 'type' field (string) for a solver's type.
I0410 01:57:47.088642 27877 caffe.cpp:218] Using GPUs 0
I0410 01:57:47.146837 27877 caffe.cpp:223] GPU 0: GeForce GTX 1080 Ti
I0410 01:57:47.464715 27877 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: 0
net: "train_val.prototxt"
train_state {
level: 0
stage: ""
}
type: "SGD"
I0410 01:57:47.553656 27877 solver.cpp:87] Creating training net from net file: train_val.prototxt
I0410 01:57:47.618111 27877 net.cpp:294] The NetState phase (0) differed from the phase (1) specified by a rule in layer val-data
I0410 01:57:47.618155 27877 net.cpp:294] The NetState phase (0) differed from the phase (1) specified by a rule in layer accuracy
I0410 01:57:47.618561 27877 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: 256
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: "pool5"
type: "Pooling"
bottom: "conv5"
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: 1024
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: 1024
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: "fc7.5"
type: "InnerProduct"
bottom: "fc7"
top: "fc7.5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1024
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7.5"
type: "ReLU"
bottom: "fc7.5"
top: "fc7.5"
}
layer {
name: "drop7.5"
type: "Dropout"
bottom: "fc7.5"
top: "fc7.5"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7.6"
type: "InnerProduct"
bottom: "fc7.5"
top: "fc7.6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1024
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7.6"
type: "ReLU"
bottom: "fc7.6"
top: "fc7.6"
}
layer {
name: "drop7.6"
type: "Dropout"
bottom: "fc7.6"
top: "fc7.6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7.6"
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"
}
I0410 01:57:47.618765 27877 layer_factory.hpp:77] Creating layer train-data
I0410 01:57:47.849860 27877 db_lmdb.cpp:35] Opened lmdb /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/train_db
I0410 01:57:47.850440 27877 net.cpp:84] Creating Layer train-data
I0410 01:57:47.850466 27877 net.cpp:380] train-data -> data
I0410 01:57:47.850503 27877 net.cpp:380] train-data -> label
I0410 01:57:47.850524 27877 data_transformer.cpp:25] Loading mean file from: /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/mean.binaryproto
I0410 01:57:47.916616 27877 data_layer.cpp:45] output data size: 128,3,227,227
I0410 01:57:48.087420 27877 net.cpp:122] Setting up train-data
I0410 01:57:48.087445 27877 net.cpp:129] Top shape: 128 3 227 227 (19787136)
I0410 01:57:48.087452 27877 net.cpp:129] Top shape: 128 (128)
I0410 01:57:48.087456 27877 net.cpp:137] Memory required for data: 79149056
I0410 01:57:48.087487 27877 layer_factory.hpp:77] Creating layer conv1
I0410 01:57:48.087512 27877 net.cpp:84] Creating Layer conv1
I0410 01:57:48.087518 27877 net.cpp:406] conv1 <- data
I0410 01:57:48.087532 27877 net.cpp:380] conv1 -> conv1
I0410 01:57:48.668146 27877 net.cpp:122] Setting up conv1
I0410 01:57:48.668169 27877 net.cpp:129] Top shape: 128 96 55 55 (37171200)
I0410 01:57:48.668174 27877 net.cpp:137] Memory required for data: 227833856
I0410 01:57:48.668195 27877 layer_factory.hpp:77] Creating layer relu1
I0410 01:57:48.668205 27877 net.cpp:84] Creating Layer relu1
I0410 01:57:48.668210 27877 net.cpp:406] relu1 <- conv1
I0410 01:57:48.668216 27877 net.cpp:367] relu1 -> conv1 (in-place)
I0410 01:57:48.668534 27877 net.cpp:122] Setting up relu1
I0410 01:57:48.668543 27877 net.cpp:129] Top shape: 128 96 55 55 (37171200)
I0410 01:57:48.668546 27877 net.cpp:137] Memory required for data: 376518656
I0410 01:57:48.668551 27877 layer_factory.hpp:77] Creating layer norm1
I0410 01:57:48.668560 27877 net.cpp:84] Creating Layer norm1
I0410 01:57:48.668565 27877 net.cpp:406] norm1 <- conv1
I0410 01:57:48.668571 27877 net.cpp:380] norm1 -> norm1
I0410 01:57:48.669049 27877 net.cpp:122] Setting up norm1
I0410 01:57:48.669060 27877 net.cpp:129] Top shape: 128 96 55 55 (37171200)
I0410 01:57:48.669064 27877 net.cpp:137] Memory required for data: 525203456
I0410 01:57:48.669068 27877 layer_factory.hpp:77] Creating layer pool1
I0410 01:57:48.669076 27877 net.cpp:84] Creating Layer pool1
I0410 01:57:48.669080 27877 net.cpp:406] pool1 <- norm1
I0410 01:57:48.669087 27877 net.cpp:380] pool1 -> pool1
I0410 01:57:48.669126 27877 net.cpp:122] Setting up pool1
I0410 01:57:48.669132 27877 net.cpp:129] Top shape: 128 96 27 27 (8957952)
I0410 01:57:48.669137 27877 net.cpp:137] Memory required for data: 561035264
I0410 01:57:48.669139 27877 layer_factory.hpp:77] Creating layer conv2
I0410 01:57:48.669149 27877 net.cpp:84] Creating Layer conv2
I0410 01:57:48.669153 27877 net.cpp:406] conv2 <- pool1
I0410 01:57:48.669159 27877 net.cpp:380] conv2 -> conv2
I0410 01:57:48.676323 27877 net.cpp:122] Setting up conv2
I0410 01:57:48.676339 27877 net.cpp:129] Top shape: 128 256 27 27 (23887872)
I0410 01:57:48.676343 27877 net.cpp:137] Memory required for data: 656586752
I0410 01:57:48.676354 27877 layer_factory.hpp:77] Creating layer relu2
I0410 01:57:48.676362 27877 net.cpp:84] Creating Layer relu2
I0410 01:57:48.676365 27877 net.cpp:406] relu2 <- conv2
I0410 01:57:48.676371 27877 net.cpp:367] relu2 -> conv2 (in-place)
I0410 01:57:48.676820 27877 net.cpp:122] Setting up relu2
I0410 01:57:48.676831 27877 net.cpp:129] Top shape: 128 256 27 27 (23887872)
I0410 01:57:48.676834 27877 net.cpp:137] Memory required for data: 752138240
I0410 01:57:48.676838 27877 layer_factory.hpp:77] Creating layer norm2
I0410 01:57:48.676847 27877 net.cpp:84] Creating Layer norm2
I0410 01:57:48.676851 27877 net.cpp:406] norm2 <- conv2
I0410 01:57:48.676857 27877 net.cpp:380] norm2 -> norm2
I0410 01:57:48.677171 27877 net.cpp:122] Setting up norm2
I0410 01:57:48.677181 27877 net.cpp:129] Top shape: 128 256 27 27 (23887872)
I0410 01:57:48.677184 27877 net.cpp:137] Memory required for data: 847689728
I0410 01:57:48.677188 27877 layer_factory.hpp:77] Creating layer pool2
I0410 01:57:48.677196 27877 net.cpp:84] Creating Layer pool2
I0410 01:57:48.677201 27877 net.cpp:406] pool2 <- norm2
I0410 01:57:48.677206 27877 net.cpp:380] pool2 -> pool2
I0410 01:57:48.677234 27877 net.cpp:122] Setting up pool2
I0410 01:57:48.677242 27877 net.cpp:129] Top shape: 128 256 13 13 (5537792)
I0410 01:57:48.677244 27877 net.cpp:137] Memory required for data: 869840896
I0410 01:57:48.677248 27877 layer_factory.hpp:77] Creating layer conv3
I0410 01:57:48.677256 27877 net.cpp:84] Creating Layer conv3
I0410 01:57:48.677261 27877 net.cpp:406] conv3 <- pool2
I0410 01:57:48.677268 27877 net.cpp:380] conv3 -> conv3
I0410 01:57:48.687913 27877 net.cpp:122] Setting up conv3
I0410 01:57:48.687927 27877 net.cpp:129] Top shape: 128 384 13 13 (8306688)
I0410 01:57:48.687930 27877 net.cpp:137] Memory required for data: 903067648
I0410 01:57:48.687959 27877 layer_factory.hpp:77] Creating layer relu3
I0410 01:57:48.687968 27877 net.cpp:84] Creating Layer relu3
I0410 01:57:48.687971 27877 net.cpp:406] relu3 <- conv3
I0410 01:57:48.687976 27877 net.cpp:367] relu3 -> conv3 (in-place)
I0410 01:57:48.688421 27877 net.cpp:122] Setting up relu3
I0410 01:57:48.688431 27877 net.cpp:129] Top shape: 128 384 13 13 (8306688)
I0410 01:57:48.688434 27877 net.cpp:137] Memory required for data: 936294400
I0410 01:57:48.688438 27877 layer_factory.hpp:77] Creating layer conv4
I0410 01:57:48.688448 27877 net.cpp:84] Creating Layer conv4
I0410 01:57:48.688452 27877 net.cpp:406] conv4 <- conv3
I0410 01:57:48.688458 27877 net.cpp:380] conv4 -> conv4
I0410 01:57:48.699209 27877 net.cpp:122] Setting up conv4
I0410 01:57:48.699223 27877 net.cpp:129] Top shape: 128 384 13 13 (8306688)
I0410 01:57:48.699229 27877 net.cpp:137] Memory required for data: 969521152
I0410 01:57:48.699237 27877 layer_factory.hpp:77] Creating layer relu4
I0410 01:57:48.699245 27877 net.cpp:84] Creating Layer relu4
I0410 01:57:48.699250 27877 net.cpp:406] relu4 <- conv4
I0410 01:57:48.699259 27877 net.cpp:367] relu4 -> conv4 (in-place)
I0410 01:57:48.699555 27877 net.cpp:122] Setting up relu4
I0410 01:57:48.699564 27877 net.cpp:129] Top shape: 128 384 13 13 (8306688)
I0410 01:57:48.699569 27877 net.cpp:137] Memory required for data: 1002747904
I0410 01:57:48.699573 27877 layer_factory.hpp:77] Creating layer conv5
I0410 01:57:48.699582 27877 net.cpp:84] Creating Layer conv5
I0410 01:57:48.699587 27877 net.cpp:406] conv5 <- conv4
I0410 01:57:48.699592 27877 net.cpp:380] conv5 -> conv5
I0410 01:57:48.708103 27877 net.cpp:122] Setting up conv5
I0410 01:57:48.708117 27877 net.cpp:129] Top shape: 128 256 13 13 (5537792)
I0410 01:57:48.708122 27877 net.cpp:137] Memory required for data: 1024899072
I0410 01:57:48.708133 27877 layer_factory.hpp:77] Creating layer relu5
I0410 01:57:48.708140 27877 net.cpp:84] Creating Layer relu5
I0410 01:57:48.708144 27877 net.cpp:406] relu5 <- conv5
I0410 01:57:48.708149 27877 net.cpp:367] relu5 -> conv5 (in-place)
I0410 01:57:48.708598 27877 net.cpp:122] Setting up relu5
I0410 01:57:48.708608 27877 net.cpp:129] Top shape: 128 256 13 13 (5537792)
I0410 01:57:48.708611 27877 net.cpp:137] Memory required for data: 1047050240
I0410 01:57:48.708616 27877 layer_factory.hpp:77] Creating layer pool5
I0410 01:57:48.708623 27877 net.cpp:84] Creating Layer pool5
I0410 01:57:48.708628 27877 net.cpp:406] pool5 <- conv5
I0410 01:57:48.708636 27877 net.cpp:380] pool5 -> pool5
I0410 01:57:48.708673 27877 net.cpp:122] Setting up pool5
I0410 01:57:48.708678 27877 net.cpp:129] Top shape: 128 256 6 6 (1179648)
I0410 01:57:48.708683 27877 net.cpp:137] Memory required for data: 1051768832
I0410 01:57:48.708685 27877 layer_factory.hpp:77] Creating layer fc6
I0410 01:57:48.708695 27877 net.cpp:84] Creating Layer fc6
I0410 01:57:48.708699 27877 net.cpp:406] fc6 <- pool5
I0410 01:57:48.708704 27877 net.cpp:380] fc6 -> fc6
I0410 01:57:48.805836 27877 net.cpp:122] Setting up fc6
I0410 01:57:48.805860 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.805863 27877 net.cpp:137] Memory required for data: 1052293120
I0410 01:57:48.805873 27877 layer_factory.hpp:77] Creating layer relu6
I0410 01:57:48.805882 27877 net.cpp:84] Creating Layer relu6
I0410 01:57:48.805887 27877 net.cpp:406] relu6 <- fc6
I0410 01:57:48.805896 27877 net.cpp:367] relu6 -> fc6 (in-place)
I0410 01:57:48.806505 27877 net.cpp:122] Setting up relu6
I0410 01:57:48.806515 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.806519 27877 net.cpp:137] Memory required for data: 1052817408
I0410 01:57:48.806524 27877 layer_factory.hpp:77] Creating layer drop6
I0410 01:57:48.806530 27877 net.cpp:84] Creating Layer drop6
I0410 01:57:48.806535 27877 net.cpp:406] drop6 <- fc6
I0410 01:57:48.806540 27877 net.cpp:367] drop6 -> fc6 (in-place)
I0410 01:57:48.806566 27877 net.cpp:122] Setting up drop6
I0410 01:57:48.806572 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.806597 27877 net.cpp:137] Memory required for data: 1053341696
I0410 01:57:48.806602 27877 layer_factory.hpp:77] Creating layer fc7
I0410 01:57:48.806608 27877 net.cpp:84] Creating Layer fc7
I0410 01:57:48.806612 27877 net.cpp:406] fc7 <- fc6
I0410 01:57:48.806618 27877 net.cpp:380] fc7 -> fc7
I0410 01:57:48.817447 27877 net.cpp:122] Setting up fc7
I0410 01:57:48.817462 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.817466 27877 net.cpp:137] Memory required for data: 1053865984
I0410 01:57:48.817473 27877 layer_factory.hpp:77] Creating layer relu7
I0410 01:57:48.817481 27877 net.cpp:84] Creating Layer relu7
I0410 01:57:48.817485 27877 net.cpp:406] relu7 <- fc7
I0410 01:57:48.817492 27877 net.cpp:367] relu7 -> fc7 (in-place)
I0410 01:57:48.818004 27877 net.cpp:122] Setting up relu7
I0410 01:57:48.818014 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.818018 27877 net.cpp:137] Memory required for data: 1054390272
I0410 01:57:48.818022 27877 layer_factory.hpp:77] Creating layer drop7
I0410 01:57:48.818028 27877 net.cpp:84] Creating Layer drop7
I0410 01:57:48.818032 27877 net.cpp:406] drop7 <- fc7
I0410 01:57:48.818037 27877 net.cpp:367] drop7 -> fc7 (in-place)
I0410 01:57:48.818063 27877 net.cpp:122] Setting up drop7
I0410 01:57:48.818068 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.818071 27877 net.cpp:137] Memory required for data: 1054914560
I0410 01:57:48.818074 27877 layer_factory.hpp:77] Creating layer fc7.5
I0410 01:57:48.818081 27877 net.cpp:84] Creating Layer fc7.5
I0410 01:57:48.818085 27877 net.cpp:406] fc7.5 <- fc7
I0410 01:57:48.818090 27877 net.cpp:380] fc7.5 -> fc7.5
I0410 01:57:48.828912 27877 net.cpp:122] Setting up fc7.5
I0410 01:57:48.828928 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.828931 27877 net.cpp:137] Memory required for data: 1055438848
I0410 01:57:48.828939 27877 layer_factory.hpp:77] Creating layer relu7.5
I0410 01:57:48.828946 27877 net.cpp:84] Creating Layer relu7.5
I0410 01:57:48.828951 27877 net.cpp:406] relu7.5 <- fc7.5
I0410 01:57:48.828958 27877 net.cpp:367] relu7.5 -> fc7.5 (in-place)
I0410 01:57:48.829473 27877 net.cpp:122] Setting up relu7.5
I0410 01:57:48.829483 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.829486 27877 net.cpp:137] Memory required for data: 1055963136
I0410 01:57:48.829489 27877 layer_factory.hpp:77] Creating layer drop7.5
I0410 01:57:48.829496 27877 net.cpp:84] Creating Layer drop7.5
I0410 01:57:48.829500 27877 net.cpp:406] drop7.5 <- fc7.5
I0410 01:57:48.829505 27877 net.cpp:367] drop7.5 -> fc7.5 (in-place)
I0410 01:57:48.829530 27877 net.cpp:122] Setting up drop7.5
I0410 01:57:48.829535 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.829540 27877 net.cpp:137] Memory required for data: 1056487424
I0410 01:57:48.829542 27877 layer_factory.hpp:77] Creating layer fc7.6
I0410 01:57:48.829550 27877 net.cpp:84] Creating Layer fc7.6
I0410 01:57:48.829552 27877 net.cpp:406] fc7.6 <- fc7.5
I0410 01:57:48.829558 27877 net.cpp:380] fc7.6 -> fc7.6
I0410 01:57:48.840397 27877 net.cpp:122] Setting up fc7.6
I0410 01:57:48.840412 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.840416 27877 net.cpp:137] Memory required for data: 1057011712
I0410 01:57:48.840428 27877 layer_factory.hpp:77] Creating layer relu7.6
I0410 01:57:48.840436 27877 net.cpp:84] Creating Layer relu7.6
I0410 01:57:48.840440 27877 net.cpp:406] relu7.6 <- fc7.6
I0410 01:57:48.840447 27877 net.cpp:367] relu7.6 -> fc7.6 (in-place)
I0410 01:57:48.840947 27877 net.cpp:122] Setting up relu7.6
I0410 01:57:48.840958 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.840961 27877 net.cpp:137] Memory required for data: 1057536000
I0410 01:57:48.840965 27877 layer_factory.hpp:77] Creating layer drop7.6
I0410 01:57:48.840972 27877 net.cpp:84] Creating Layer drop7.6
I0410 01:57:48.840976 27877 net.cpp:406] drop7.6 <- fc7.6
I0410 01:57:48.840981 27877 net.cpp:367] drop7.6 -> fc7.6 (in-place)
I0410 01:57:48.841006 27877 net.cpp:122] Setting up drop7.6
I0410 01:57:48.841010 27877 net.cpp:129] Top shape: 128 1024 (131072)
I0410 01:57:48.841034 27877 net.cpp:137] Memory required for data: 1058060288
I0410 01:57:48.841038 27877 layer_factory.hpp:77] Creating layer fc8
I0410 01:57:48.841045 27877 net.cpp:84] Creating Layer fc8
I0410 01:57:48.841048 27877 net.cpp:406] fc8 <- fc7.6
I0410 01:57:48.841054 27877 net.cpp:380] fc8 -> fc8
I0410 01:57:48.843029 27877 net.cpp:122] Setting up fc8
I0410 01:57:48.843036 27877 net.cpp:129] Top shape: 128 196 (25088)
I0410 01:57:48.843040 27877 net.cpp:137] Memory required for data: 1058160640
I0410 01:57:48.843046 27877 layer_factory.hpp:77] Creating layer loss
I0410 01:57:48.843052 27877 net.cpp:84] Creating Layer loss
I0410 01:57:48.843056 27877 net.cpp:406] loss <- fc8
I0410 01:57:48.843060 27877 net.cpp:406] loss <- label
I0410 01:57:48.843067 27877 net.cpp:380] loss -> loss
I0410 01:57:48.843076 27877 layer_factory.hpp:77] Creating layer loss
I0410 01:57:48.846568 27877 net.cpp:122] Setting up loss
I0410 01:57:48.846578 27877 net.cpp:129] Top shape: (1)
I0410 01:57:48.846581 27877 net.cpp:132]     with loss weight 1
I0410 01:57:48.846601 27877 net.cpp:137] Memory required for data: 1058160644
I0410 01:57:48.846604 27877 net.cpp:198] loss needs backward computation.
I0410 01:57:48.846612 27877 net.cpp:198] fc8 needs backward computation.
I0410 01:57:48.846616 27877 net.cpp:198] drop7.6 needs backward computation.
I0410 01:57:48.846621 27877 net.cpp:198] relu7.6 needs backward computation.
I0410 01:57:48.846624 27877 net.cpp:198] fc7.6 needs backward computation.
I0410 01:57:48.846627 27877 net.cpp:198] drop7.5 needs backward computation.
I0410 01:57:48.846632 27877 net.cpp:198] relu7.5 needs backward computation.
I0410 01:57:48.846634 27877 net.cpp:198] fc7.5 needs backward computation.
I0410 01:57:48.846639 27877 net.cpp:198] drop7 needs backward computation.
I0410 01:57:48.846643 27877 net.cpp:198] relu7 needs backward computation.
I0410 01:57:48.846647 27877 net.cpp:198] fc7 needs backward computation.
I0410 01:57:48.846650 27877 net.cpp:198] drop6 needs backward computation.
I0410 01:57:48.846654 27877 net.cpp:198] relu6 needs backward computation.
I0410 01:57:48.846658 27877 net.cpp:198] fc6 needs backward computation.
I0410 01:57:48.846662 27877 net.cpp:198] pool5 needs backward computation.
I0410 01:57:48.846665 27877 net.cpp:198] relu5 needs backward computation.
I0410 01:57:48.846669 27877 net.cpp:198] conv5 needs backward computation.
I0410 01:57:48.846673 27877 net.cpp:198] relu4 needs backward computation.
I0410 01:57:48.846676 27877 net.cpp:198] conv4 needs backward computation.
I0410 01:57:48.846680 27877 net.cpp:198] relu3 needs backward computation.
I0410 01:57:48.846684 27877 net.cpp:198] conv3 needs backward computation.
I0410 01:57:48.846688 27877 net.cpp:198] pool2 needs backward computation.
I0410 01:57:48.846693 27877 net.cpp:198] norm2 needs backward computation.
I0410 01:57:48.846698 27877 net.cpp:198] relu2 needs backward computation.
I0410 01:57:48.846700 27877 net.cpp:198] conv2 needs backward computation.
I0410 01:57:48.846705 27877 net.cpp:198] pool1 needs backward computation.
I0410 01:57:48.846709 27877 net.cpp:198] norm1 needs backward computation.
I0410 01:57:48.846712 27877 net.cpp:198] relu1 needs backward computation.
I0410 01:57:48.846716 27877 net.cpp:198] conv1 needs backward computation.
I0410 01:57:48.846720 27877 net.cpp:200] train-data does not need backward computation.
I0410 01:57:48.846724 27877 net.cpp:242] This network produces output loss
I0410 01:57:48.846742 27877 net.cpp:255] Network initialization done.
I0410 01:57:48.898881 27877 solver.cpp:172] Creating test net (#0) specified by net file: train_val.prototxt
I0410 01:57:48.898974 27877 net.cpp:294] The NetState phase (1) differed from the phase (0) specified by a rule in layer train-data
I0410 01:57:48.899394 27877 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: 256
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: "pool5"
type: "Pooling"
bottom: "conv5"
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: 1024
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: 1024
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: "fc7.5"
type: "InnerProduct"
bottom: "fc7"
top: "fc7.5"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1024
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7.5"
type: "ReLU"
bottom: "fc7.5"
top: "fc7.5"
}
layer {
name: "drop7.5"
type: "Dropout"
bottom: "fc7.5"
top: "fc7.5"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc7.6"
type: "InnerProduct"
bottom: "fc7.5"
top: "fc7.6"
param {
lr_mult: 1
decay_mult: 1
}
param {
lr_mult: 2
decay_mult: 0
}
inner_product_param {
num_output: 1024
weight_filler {
type: "gaussian"
std: 0.005
}
bias_filler {
type: "constant"
value: 0.1
}
}
}
layer {
name: "relu7.6"
type: "ReLU"
bottom: "fc7.6"
top: "fc7.6"
}
layer {
name: "drop7.6"
type: "Dropout"
bottom: "fc7.6"
top: "fc7.6"
dropout_param {
dropout_ratio: 0.5
}
}
layer {
name: "fc8"
type: "InnerProduct"
bottom: "fc7.6"
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"
}
I0410 01:57:48.899675 27877 layer_factory.hpp:77] Creating layer val-data
I0410 01:57:49.133463 27877 db_lmdb.cpp:35] Opened lmdb /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/val_db
I0410 01:57:49.134734 27877 net.cpp:84] Creating Layer val-data
I0410 01:57:49.134752 27877 net.cpp:380] val-data -> data
I0410 01:57:49.134769 27877 net.cpp:380] val-data -> label
I0410 01:57:49.134778 27877 data_transformer.cpp:25] Loading mean file from: /mnt/bigdisk/DIGITS-MAN-2/digits/jobs/20210407-214532-d396/mean.binaryproto
I0410 01:57:49.165874 27877 data_layer.cpp:45] output data size: 32,3,227,227
I0410 01:57:49.205605 27877 net.cpp:122] Setting up val-data
I0410 01:57:49.205626 27877 net.cpp:129] Top shape: 32 3 227 227 (4946784)
I0410 01:57:49.205632 27877 net.cpp:129] Top shape: 32 (32)
I0410 01:57:49.205636 27877 net.cpp:137] Memory required for data: 19787264
I0410 01:57:49.205641 27877 layer_factory.hpp:77] Creating layer label_val-data_1_split
I0410 01:57:49.205654 27877 net.cpp:84] Creating Layer label_val-data_1_split
I0410 01:57:49.205658 27877 net.cpp:406] label_val-data_1_split <- label
I0410 01:57:49.205665 27877 net.cpp:380] label_val-data_1_split -> label_val-data_1_split_0
I0410 01:57:49.205675 27877 net.cpp:380] label_val-data_1_split -> label_val-data_1_split_1
I0410 01:57:49.205722 27877 net.cpp:122] Setting up label_val-data_1_split
I0410 01:57:49.205729 27877 net.cpp:129] Top shape: 32 (32)
I0410 01:57:49.205732 27877 net.cpp:129] Top shape: 32 (32)
I0410 01:57:49.205735 27877 net.cpp:137] Memory required for data: 19787520
I0410 01:57:49.205739 27877 layer_factory.hpp:77] Creating layer conv1
I0410 01:57:49.205750 27877 net.cpp:84] Creating Layer conv1
I0410 01:57:49.205755 27877 net.cpp:406] conv1 <- data
I0410 01:57:49.205763 27877 net.cpp:380] conv1 -> conv1
I0410 01:57:49.207854 27877 net.cpp:122] Setting up conv1
I0410 01:57:49.207865 27877 net.cpp:129] Top shape: 32 96 55 55 (9292800)
I0410 01:57:49.207870 27877 net.cpp:137] Memory required for data: 56958720
I0410 01:57:49.207880 27877 layer_factory.hpp:77] Creating layer relu1
I0410 01:57:49.207886 27877 net.cpp:84] Creating Layer relu1
I0410 01:57:49.207890 27877 net.cpp:406] relu1 <- conv1
I0410 01:57:49.207916 27877 net.cpp:367] relu1 -> conv1 (in-place)
I0410 01:57:49.209532 27877 net.cpp:122] Setting up relu1
I0410 01:57:49.209544 27877 net.cpp:129] Top shape: 32 96 55 55 (9292800)
I0410 01:57:49.209547 27877 net.cpp:137] Memory required for data: 94129920
I0410 01:57:49.209551 27877 layer_factory.hpp:77] Creating layer norm1
I0410 01:57:49.209560 27877 net.cpp:84] Creating Layer norm1
I0410 01:57:49.209564 27877 net.cpp:406] norm1 <- conv1
I0410 01:57:49.209570 27877 net.cpp:380] norm1 -> norm1
I0410 01:57:49.210100 27877 net.cpp:122] Setting up norm1
I0410 01:57:49.210110 27877 net.cpp:129] Top shape: 32 96 55 55 (9292800)
I0410 01:57:49.210114 27877 net.cpp:137] Memory required for data: 131301120
I0410 01:57:49.210119 27877 layer_factory.hpp:77] Creating layer pool1
I0410 01:57:49.210125 27877 net.cpp:84] Creating Layer pool1
I0410 01:57:49.210129 27877 net.cpp:406] pool1 <- norm1
I0410 01:57:49.210135 27877 net.cpp:380] pool1 -> pool1
I0410 01:57:49.210166 27877 net.cpp:122] Setting up pool1
I0410 01:57:49.210171 27877 net.cpp:129] Top shape: 32 96 27 27 (2239488)
I0410 01:57:49.210175 27877 net.cpp:137] Memory required for data: 140259072
I0410 01:57:49.210178 27877 layer_factory.hpp:77] Creating layer conv2
I0410 01:57:49.210188 27877 net.cpp:84] Creating Layer conv2
I0410 01:57:49.210192 27877 net.cpp:406] conv2 <- pool1
I0410 01:57:49.210197 27877 net.cpp:380] conv2 -> conv2
I0410 01:57:49.222656 27877 net.cpp:122] Setting up conv2
I0410 01:57:49.222671 27877 net.cpp:129] Top shape: 32 256 27 27 (5971968)
I0410 01:57:49.222676 27877 net.cpp:137] Memory required for data: 164146944
I0410 01:57:49.222688 27877 layer_factory.hpp:77] Creating layer relu2
I0410 01:57:49.222697 27877 net.cpp:84] Creating Layer relu2
I0410 01:57:49.222702 27877 net.cpp:406] relu2 <- conv2
I0410 01:57:49.222709 27877 net.cpp:367] relu2 -> conv2 (in-place)
I0410 01:57:49.223109 27877 net.cpp:122] Setting up relu2
I0410 01:57:49.223117 27877 net.cpp:129] Top shape: 32 256 27 27 (5971968)
I0410 01:57:49.223121 27877 net.cpp:137] Memory required for data: 188034816
I0410 01:57:49.223125 27877 layer_factory.hpp:77] Creating layer norm2
I0410 01:57:49.223136 27877 net.cpp:84] Creating Layer norm2
I0410 01:57:49.223141 27877 net.cpp:406] norm2 <- conv2
I0410 01:57:49.223147 27877 net.cpp:380] norm2 -> norm2
I0410 01:57:49.225746 27877 net.cpp:122] Setting up norm2
I0410 01:57:49.225757 27877 net.cpp:129] Top shape: 32 256 27 27 (5971968)
I0410 01:57:49.225761 27877 net.cpp:137] Memory required for data: 211922688
I0410 01:57:49.225766 27877 layer_factory.hpp:77] Creating layer pool2
I0410 01:57:49.225773 27877 net.cpp:84] Creating Layer pool2
I0410 01:57:49.225778 27877 net.cpp:406] pool2 <- norm2
I0410 01:57:49.225785 27877 net.cpp:380] pool2 -> pool2
I0410 01:57:49.225821 27877 net.cpp:122] Setting up pool2
I0410 01:57:49.225826 27877 net.cpp:129] Top shape: 32 256 13 13 (1384448)
I0410 01:57:49.225831 27877 net.cpp:137] Memory required for data: 217460480
I0410 01:57:49.225836 27877 layer_factory.hpp:77] Creating layer conv3
I0410 01:57:49.225847 27877 net.cpp:84] Creating Layer conv3
I0410 01:57:49.225852 27877 net.cpp:406] conv3 <- pool2
I0410 01:57:49.225858 27877 net.cpp:380] conv3 -> conv3
I0410 01:57:49.242326 27877 net.cpp:122] Setting up conv3
I0410 01:57:49.242345 27877 net.cpp:129] Top shape: 32 384 13 13 (2076672)
I0410 01:57:49.242349 27877 net.cpp:137] Memory required for data: 225767168
I0410 01:57:49.242363 27877 layer_factory.hpp:77] Creating layer relu3
I0410 01:57:49.242372 27877 net.cpp:84] Creating Layer relu3
I0410 01:57:49.242377 27877 net.cpp:406] relu3 <- conv3
I0410 01:57:49.242384 27877 net.cpp:367] relu3 -> conv3 (in-place)
I0410 01:57:49.242946 27877 net.cpp:122] Setting up relu3
I0410 01:57:49.242956 27877 net.cpp:129] Top shape: 32 384 13 13 (2076672)
I0410 01:57:49.242959 27877 net.cpp:137] Memory required for data: 234073856
I0410 01:57:49.242964 27877 layer_factory.hpp:77] Creating layer conv4
I0410 01:57:49.242975 27877 net.cpp:84] Creating Layer conv4
I0410 01:57:49.242980 27877 net.cpp:406] conv4 <- conv3
I0410 01:57:49.243006 27877 net.cpp:380] conv4 -> conv4
I0410 01:57:49.253609 27877 net.cpp:122] Setting up conv4
I0410 01:57:49.253629 27877 net.cpp:129] Top shape: 32 384 13 13 (2076672)
I0410 01:57:49.253634 27877 net.cpp:137] Memory required for data: 242380544
I0410 01:57:49.253644 27877 layer_factory.hpp:77] Creating layer relu4
I0410 01:57:49.253654 27877 net.cpp:84] Creating Layer relu4
I0410 01:57:49.253657 27877 net.cpp:406] relu4 <- conv4
I0410 01:57:49.253665 27877 net.cpp:367] relu4 -> conv4 (in-place)
I0410 01:57:49.255406 27877 net.cpp:122] Setting up relu4
I0410 01:57:49.255419 27877 net.cpp:129] Top shape: 32 384 13 13 (2076672)
I0410 01:57:49.255424 27877 net.cpp:137] Memory required for data: 250687232
I0410 01:57:49.255427 27877 layer_factory.hpp:77] Creating layer conv5
I0410 01:57:49.255441 27877 net.cpp:84] Creating Layer conv5
I0410 01:57:49.255446 27877 net.cpp:406] conv5 <- conv4
I0410 01:57:49.255453 27877 net.cpp:380] conv5 -> conv5
I0410 01:57:49.278676 27877 net.cpp:122] Setting up conv5
I0410 01:57:49.278707 27877 net.cpp:129] Top shape: 32 256 13 13 (1384448)
I0410 01:57:49.278713 27877 net.cpp:137] Memory required for data: 256225024
I0410 01:57:49.278740 27877 layer_factory.hpp:77] Creating layer relu5
I0410 01:57:49.278756 27877 net.cpp:84] Creating Layer relu5
I0410 01:57:49.278765 27877 net.cpp:406] relu5 <- conv5
I0410 01:57:49.278781 27877 net.cpp:367] relu5 -> conv5 (in-place)
I0410 01:57:49.279620 27877 net.cpp:122] Setting up relu5
I0410 01:57:49.279640 27877 net.cpp:129] Top shape: 32 256 13 13 (1384448)
I0410 01:57:49.279647 27877 net.cpp:137] Memory required for data: 261762816
I0410 01:57:49.279655 27877 layer_factory.hpp:77] Creating layer pool5
I0410 01:57:49.279675 27877 net.cpp:84] Creating Layer pool5
I0410 01:57:49.279682 27877 net.cpp:406] pool5 <- conv5
I0410 01:57:49.279695 27877 net.cpp:380] pool5 -> pool5
I0410 01:57:49.279783 27877 net.cpp:122] Setting up pool5
I0410 01:57:49.279795 27877 net.cpp:129] Top shape: 32 256 6 6 (294912)
I0410 01:57:49.279801 27877 net.cpp:137] Memory required for data: 262942464
I0410 01:57:49.279808 27877 layer_factory.hpp:77] Creating layer fc6
I0410 01:57:49.279824 27877 net.cpp:84] Creating Layer fc6
I0410 01:57:49.279831 27877 net.cpp:406] fc6 <- pool5
I0410 01:57:49.279844 27877 net.cpp:380] fc6 -> fc6
I0410 01:57:49.429740 27877 net.cpp:122] Setting up fc6
I0410 01:57:49.429762 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.429767 27877 net.cpp:137] Memory required for data: 263073536
I0410 01:57:49.429777 27877 layer_factory.hpp:77] Creating layer relu6
I0410 01:57:49.429790 27877 net.cpp:84] Creating Layer relu6
I0410 01:57:49.429795 27877 net.cpp:406] relu6 <- fc6
I0410 01:57:49.429802 27877 net.cpp:367] relu6 -> fc6 (in-place)
I0410 01:57:49.430583 27877 net.cpp:122] Setting up relu6
I0410 01:57:49.430593 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.430598 27877 net.cpp:137] Memory required for data: 263204608
I0410 01:57:49.430603 27877 layer_factory.hpp:77] Creating layer drop6
I0410 01:57:49.430613 27877 net.cpp:84] Creating Layer drop6
I0410 01:57:49.430616 27877 net.cpp:406] drop6 <- fc6
I0410 01:57:49.430624 27877 net.cpp:367] drop6 -> fc6 (in-place)
I0410 01:57:49.430653 27877 net.cpp:122] Setting up drop6
I0410 01:57:49.430660 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.430665 27877 net.cpp:137] Memory required for data: 263335680
I0410 01:57:49.430670 27877 layer_factory.hpp:77] Creating layer fc7
I0410 01:57:49.430680 27877 net.cpp:84] Creating Layer fc7
I0410 01:57:49.430683 27877 net.cpp:406] fc7 <- fc6
I0410 01:57:49.430691 27877 net.cpp:380] fc7 -> fc7
I0410 01:57:49.443163 27877 net.cpp:122] Setting up fc7
I0410 01:57:49.443181 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.443186 27877 net.cpp:137] Memory required for data: 263466752
I0410 01:57:49.443195 27877 layer_factory.hpp:77] Creating layer relu7
I0410 01:57:49.443205 27877 net.cpp:84] Creating Layer relu7
I0410 01:57:49.443210 27877 net.cpp:406] relu7 <- fc7
I0410 01:57:49.443238 27877 net.cpp:367] relu7 -> fc7 (in-place)
I0410 01:57:49.443923 27877 net.cpp:122] Setting up relu7
I0410 01:57:49.443935 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.443939 27877 net.cpp:137] Memory required for data: 263597824
I0410 01:57:49.443944 27877 layer_factory.hpp:77] Creating layer drop7
I0410 01:57:49.443953 27877 net.cpp:84] Creating Layer drop7
I0410 01:57:49.443956 27877 net.cpp:406] drop7 <- fc7
I0410 01:57:49.443964 27877 net.cpp:367] drop7 -> fc7 (in-place)
I0410 01:57:49.443994 27877 net.cpp:122] Setting up drop7
I0410 01:57:49.444000 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.444005 27877 net.cpp:137] Memory required for data: 263728896
I0410 01:57:49.444008 27877 layer_factory.hpp:77] Creating layer fc7.5
I0410 01:57:49.444017 27877 net.cpp:84] Creating Layer fc7.5
I0410 01:57:49.444022 27877 net.cpp:406] fc7.5 <- fc7
I0410 01:57:49.444028 27877 net.cpp:380] fc7.5 -> fc7.5
I0410 01:57:49.456027 27877 net.cpp:122] Setting up fc7.5
I0410 01:57:49.456046 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.456050 27877 net.cpp:137] Memory required for data: 263859968
I0410 01:57:49.456059 27877 layer_factory.hpp:77] Creating layer relu7.5
I0410 01:57:49.456068 27877 net.cpp:84] Creating Layer relu7.5
I0410 01:57:49.456073 27877 net.cpp:406] relu7.5 <- fc7.5
I0410 01:57:49.456082 27877 net.cpp:367] relu7.5 -> fc7.5 (in-place)
I0410 01:57:49.458046 27877 net.cpp:122] Setting up relu7.5
I0410 01:57:49.458058 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.458063 27877 net.cpp:137] Memory required for data: 263991040
I0410 01:57:49.458070 27877 layer_factory.hpp:77] Creating layer drop7.5
I0410 01:57:49.458082 27877 net.cpp:84] Creating Layer drop7.5
I0410 01:57:49.458089 27877 net.cpp:406] drop7.5 <- fc7.5
I0410 01:57:49.458098 27877 net.cpp:367] drop7.5 -> fc7.5 (in-place)
I0410 01:57:49.458129 27877 net.cpp:122] Setting up drop7.5
I0410 01:57:49.458139 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.458144 27877 net.cpp:137] Memory required for data: 264122112
I0410 01:57:49.458149 27877 layer_factory.hpp:77] Creating layer fc7.6
I0410 01:57:49.458158 27877 net.cpp:84] Creating Layer fc7.6
I0410 01:57:49.458164 27877 net.cpp:406] fc7.6 <- fc7.5
I0410 01:57:49.458173 27877 net.cpp:380] fc7.6 -> fc7.6
I0410 01:57:49.470034 27877 net.cpp:122] Setting up fc7.6
I0410 01:57:49.470052 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.470058 27877 net.cpp:137] Memory required for data: 264253184
I0410 01:57:49.470072 27877 layer_factory.hpp:77] Creating layer relu7.6
I0410 01:57:49.470082 27877 net.cpp:84] Creating Layer relu7.6
I0410 01:57:49.470090 27877 net.cpp:406] relu7.6 <- fc7.6
I0410 01:57:49.470098 27877 net.cpp:367] relu7.6 -> fc7.6 (in-place)
I0410 01:57:49.470506 27877 net.cpp:122] Setting up relu7.6
I0410 01:57:49.470515 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.470521 27877 net.cpp:137] Memory required for data: 264384256
I0410 01:57:49.470525 27877 layer_factory.hpp:77] Creating layer drop7.6
I0410 01:57:49.470536 27877 net.cpp:84] Creating Layer drop7.6
I0410 01:57:49.470543 27877 net.cpp:406] drop7.6 <- fc7.6
I0410 01:57:49.470551 27877 net.cpp:367] drop7.6 -> fc7.6 (in-place)
I0410 01:57:49.470580 27877 net.cpp:122] Setting up drop7.6
I0410 01:57:49.470588 27877 net.cpp:129] Top shape: 32 1024 (32768)
I0410 01:57:49.470593 27877 net.cpp:137] Memory required for data: 264515328
I0410 01:57:49.470597 27877 layer_factory.hpp:77] Creating layer fc8
I0410 01:57:49.470607 27877 net.cpp:84] Creating Layer fc8
I0410 01:57:49.470610 27877 net.cpp:406] fc8 <- fc7.6
I0410 01:57:49.470618 27877 net.cpp:380] fc8 -> fc8
I0410 01:57:49.472661 27877 net.cpp:122] Setting up fc8
I0410 01:57:49.472668 27877 net.cpp:129] Top shape: 32 196 (6272)
I0410 01:57:49.472672 27877 net.cpp:137] Memory required for data: 264540416
I0410 01:57:49.472679 27877 layer_factory.hpp:77] Creating layer fc8_fc8_0_split
I0410 01:57:49.472690 27877 net.cpp:84] Creating Layer fc8_fc8_0_split
I0410 01:57:49.472697 27877 net.cpp:406] fc8_fc8_0_split <- fc8
I0410 01:57:49.472720 27877 net.cpp:380] fc8_fc8_0_split -> fc8_fc8_0_split_0
I0410 01:57:49.472733 27877 net.cpp:380] fc8_fc8_0_split -> fc8_fc8_0_split_1
I0410 01:57:49.472771 27877 net.cpp:122] Setting up fc8_fc8_0_split
I0410 01:57:49.472779 27877 net.cpp:129] Top shape: 32 196 (6272)
I0410 01:57:49.472785 27877 net.cpp:129] Top shape: 32 196 (6272)
I0410 01:57:49.472790 27877 net.cpp:137] Memory required for data: 264590592
I0410 01:57:49.472795 27877 layer_factory.hpp:77] Creating layer accuracy
I0410 01:57:49.472805 27877 net.cpp:84] Creating Layer accuracy
I0410 01:57:49.472810 27877 net.cpp:406] accuracy <- fc8_fc8_0_split_0
I0410 01:57:49.472815 27877 net.cpp:406] accuracy <- label_val-data_1_split_0
I0410 01:57:49.472823 27877 net.cpp:380] accuracy -> accuracy
I0410 01:57:49.472833 27877 net.cpp:122] Setting up accuracy
I0410 01:57:49.472839 27877 net.cpp:129] Top shape: (1)
I0410 01:57:49.472844 27877 net.cpp:137] Memory required for data: 264590596
I0410 01:57:49.472851 27877 layer_factory.hpp:77] Creating layer loss
I0410 01:57:49.472864 27877 net.cpp:84] Creating Layer loss
I0410 01:57:49.472872 27877 net.cpp:406] loss <- fc8_fc8_0_split_1
I0410 01:57:49.472877 27877 net.cpp:406] loss <- label_val-data_1_split_1
I0410 01:57:49.472883 27877 net.cpp:380] loss -> loss
I0410 01:57:49.472892 27877 layer_factory.hpp:77] Creating layer loss
I0410 01:57:49.473551 27877 net.cpp:122] Setting up loss
I0410 01:57:49.473564 27877 net.cpp:129] Top shape: (1)
I0410 01:57:49.473572 27877 net.cpp:132]     with loss weight 1
I0410 01:57:49.473582 27877 net.cpp:137] Memory required for data: 264590600
I0410 01:57:49.473587 27877 net.cpp:198] loss needs backward computation.
I0410 01:57:49.473593 27877 net.cpp:200] accuracy does not need backward computation.
I0410 01:57:49.473598 27877 net.cpp:198] fc8_fc8_0_split needs backward computation.
I0410 01:57:49.473603 27877 net.cpp:198] fc8 needs backward computation.
I0410 01:57:49.473606 27877 net.cpp:198] drop7.6 needs backward computation.
I0410 01:57:49.473611 27877 net.cpp:198] relu7.6 needs backward computation.
I0410 01:57:49.473618 27877 net.cpp:198] fc7.6 needs backward computation.
I0410 01:57:49.473623 27877 net.cpp:198] drop7.5 needs backward computation.
I0410 01:57:49.473626 27877 net.cpp:198] relu7.5 needs backward computation.
I0410 01:57:49.473631 27877 net.cpp:198] fc7.5 needs backward computation.
I0410 01:57:49.473636 27877 net.cpp:198] drop7 needs backward computation.
I0410 01:57:49.473642 27877 net.cpp:198] relu7 needs backward computation.
I0410 01:57:49.473646 27877 net.cpp:198] fc7 needs backward computation.
I0410 01:57:49.473651 27877 net.cpp:198] drop6 needs backward computation.
I0410 01:57:49.473655 27877 net.cpp:198] relu6 needs backward computation.
I0410 01:57:49.473660 27877 net.cpp:198] fc6 needs backward computation.
I0410 01:57:49.473664 27877 net.cpp:198] pool5 needs backward computation.
I0410 01:57:49.473670 27877 net.cpp:198] relu5 needs backward computation.
I0410 01:57:49.473673 27877 net.cpp:198] conv5 needs backward computation.
I0410 01:57:49.473680 27877 net.cpp:198] relu4 needs backward computation.
I0410 01:57:49.473685 27877 net.cpp:198] conv4 needs backward computation.
I0410 01:57:49.473688 27877 net.cpp:198] relu3 needs backward computation.
I0410 01:57:49.473695 27877 net.cpp:198] conv3 needs backward computation.
I0410 01:57:49.473699 27877 net.cpp:198] pool2 needs backward computation.
I0410 01:57:49.473704 27877 net.cpp:198] norm2 needs backward computation.
I0410 01:57:49.473711 27877 net.cpp:198] relu2 needs backward computation.
I0410 01:57:49.473716 27877 net.cpp:198] conv2 needs backward computation.
I0410 01:57:49.473721 27877 net.cpp:198] pool1 needs backward computation.
I0410 01:57:49.473726 27877 net.cpp:198] norm1 needs backward computation.
I0410 01:57:49.473733 27877 net.cpp:198] relu1 needs backward computation.
I0410 01:57:49.473738 27877 net.cpp:198] conv1 needs backward computation.
I0410 01:57:49.473743 27877 net.cpp:200] label_val-data_1_split does not need backward computation.
I0410 01:57:49.473758 27877 net.cpp:200] val-data does not need backward computation.
I0410 01:57:49.473763 27877 net.cpp:242] This network produces output accuracy
I0410 01:57:49.473768 27877 net.cpp:242] This network produces output loss
I0410 01:57:49.473793 27877 net.cpp:255] Network initialization done.
I0410 01:57:49.473881 27877 solver.cpp:56] Solver scaffolding done.
I0410 01:57:49.474479 27877 caffe.cpp:248] Starting Optimization
I0410 01:57:49.474489 27877 solver.cpp:272] Solving
I0410 01:57:49.474494 27877 solver.cpp:273] Learning Rate Policy: exp
I0410 01:57:49.476039 27877 solver.cpp:330] Iteration 0, Testing net (#0)
I0410 01:57:49.476052 27877 net.cpp:676] Ignoring source layer train-data
I0410 01:57:49.512738 27877 blocking_queue.cpp:49] Waiting for data
I0410 01:57:54.096643 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 01:57:54.145053 27877 solver.cpp:397]     Test net output #0: accuracy = 0.0067402
I0410 01:57:54.145095 27877 solver.cpp:397]     Test net output #1: loss = 5.27848 (* 1 = 5.27848 loss)
I0410 01:57:54.238351 27877 solver.cpp:218] Iteration 0 (-5.11334e-30 iter/s, 4.7637s/12 iters), loss = 5.28033
I0410 01:57:54.238397 27877 solver.cpp:237]     Train net output #0: loss = 5.28033 (* 1 = 5.28033 loss)
I0410 01:57:54.238422 27877 sgd_solver.cpp:105] Iteration 0, lr = 0.01
I0410 01:57:58.093327 27877 solver.cpp:218] Iteration 12 (3.113 iter/s, 3.85481s/12 iters), loss = 5.2764
I0410 01:57:58.093372 27877 solver.cpp:237]     Train net output #0: loss = 5.2764 (* 1 = 5.2764 loss)
I0410 01:57:58.093382 27877 sgd_solver.cpp:105] Iteration 12, lr = 0.00997626
I0410 01:58:03.011445 27877 solver.cpp:218] Iteration 24 (2.44005 iter/s, 4.91794s/12 iters), loss = 5.27689
I0410 01:58:03.011493 27877 solver.cpp:237]     Train net output #0: loss = 5.27689 (* 1 = 5.27689 loss)
I0410 01:58:03.011504 27877 sgd_solver.cpp:105] Iteration 24, lr = 0.00995257
I0410 01:58:07.856431 27877 solver.cpp:218] Iteration 36 (2.47688 iter/s, 4.8448s/12 iters), loss = 5.27734
I0410 01:58:07.856490 27877 solver.cpp:237]     Train net output #0: loss = 5.27734 (* 1 = 5.27734 loss)
I0410 01:58:07.856503 27877 sgd_solver.cpp:105] Iteration 36, lr = 0.00992894
I0410 01:58:12.829571 27877 solver.cpp:218] Iteration 48 (2.41306 iter/s, 4.97294s/12 iters), loss = 5.27911
I0410 01:58:12.829612 27877 solver.cpp:237]     Train net output #0: loss = 5.27911 (* 1 = 5.27911 loss)
I0410 01:58:12.829620 27877 sgd_solver.cpp:105] Iteration 48, lr = 0.00990537
I0410 01:58:17.772866 27877 solver.cpp:218] Iteration 60 (2.42762 iter/s, 4.94312s/12 iters), loss = 5.28231
I0410 01:58:17.773015 27877 solver.cpp:237]     Train net output #0: loss = 5.28231 (* 1 = 5.28231 loss)
I0410 01:58:17.773025 27877 sgd_solver.cpp:105] Iteration 60, lr = 0.00988185
I0410 01:58:22.655247 27877 solver.cpp:218] Iteration 72 (2.45796 iter/s, 4.8821s/12 iters), loss = 5.27176
I0410 01:58:22.655292 27877 solver.cpp:237]     Train net output #0: loss = 5.27176 (* 1 = 5.27176 loss)
I0410 01:58:22.655301 27877 sgd_solver.cpp:105] Iteration 72, lr = 0.00985839
I0410 01:58:27.669530 27877 solver.cpp:218] Iteration 84 (2.39325 iter/s, 5.0141s/12 iters), loss = 5.28598
I0410 01:58:27.669574 27877 solver.cpp:237]     Train net output #0: loss = 5.28598 (* 1 = 5.28598 loss)
I0410 01:58:27.669584 27877 sgd_solver.cpp:105] Iteration 84, lr = 0.00983498
I0410 01:58:32.736820 27877 solver.cpp:218] Iteration 96 (2.36822 iter/s, 5.06711s/12 iters), loss = 5.29415
I0410 01:58:32.736865 27877 solver.cpp:237]     Train net output #0: loss = 5.29415 (* 1 = 5.29415 loss)
I0410 01:58:32.736873 27877 sgd_solver.cpp:105] Iteration 96, lr = 0.00981163
I0410 01:58:34.495529 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 01:58:34.804069 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_102.caffemodel
I0410 01:58:35.685444 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_102.solverstate
I0410 01:58:36.337229 27877 solver.cpp:330] Iteration 102, Testing net (#0)
I0410 01:58:36.337250 27877 net.cpp:676] Ignoring source layer train-data
I0410 01:58:40.644613 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 01:58:40.722288 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 01:58:40.722330 27877 solver.cpp:397]     Test net output #1: loss = 5.28098 (* 1 = 5.28098 loss)
I0410 01:58:42.541479 27877 solver.cpp:218] Iteration 108 (1.22395 iter/s, 9.80435s/12 iters), loss = 5.27676
I0410 01:58:42.541528 27877 solver.cpp:237]     Train net output #0: loss = 5.27676 (* 1 = 5.27676 loss)
I0410 01:58:42.541539 27877 sgd_solver.cpp:105] Iteration 108, lr = 0.00978834
I0410 01:58:47.383049 27877 solver.cpp:218] Iteration 120 (2.47863 iter/s, 4.84139s/12 iters), loss = 5.27852
I0410 01:58:47.383096 27877 solver.cpp:237]     Train net output #0: loss = 5.27852 (* 1 = 5.27852 loss)
I0410 01:58:47.383105 27877 sgd_solver.cpp:105] Iteration 120, lr = 0.0097651
I0410 01:58:52.253136 27877 solver.cpp:218] Iteration 132 (2.46411 iter/s, 4.86991s/12 iters), loss = 5.24526
I0410 01:58:52.253298 27877 solver.cpp:237]     Train net output #0: loss = 5.24526 (* 1 = 5.24526 loss)
I0410 01:58:52.253310 27877 sgd_solver.cpp:105] Iteration 132, lr = 0.00974192
I0410 01:58:57.381542 27877 solver.cpp:218] Iteration 144 (2.34004 iter/s, 5.12811s/12 iters), loss = 5.29222
I0410 01:58:57.381594 27877 solver.cpp:237]     Train net output #0: loss = 5.29222 (* 1 = 5.29222 loss)
I0410 01:58:57.381605 27877 sgd_solver.cpp:105] Iteration 144, lr = 0.00971879
I0410 01:59:02.537359 27877 solver.cpp:218] Iteration 156 (2.32755 iter/s, 5.15563s/12 iters), loss = 5.26831
I0410 01:59:02.537402 27877 solver.cpp:237]     Train net output #0: loss = 5.26831 (* 1 = 5.26831 loss)
I0410 01:59:02.537413 27877 sgd_solver.cpp:105] Iteration 156, lr = 0.00969571
I0410 01:59:07.463476 27877 solver.cpp:218] Iteration 168 (2.43608 iter/s, 4.92594s/12 iters), loss = 5.2761
I0410 01:59:07.463521 27877 solver.cpp:237]     Train net output #0: loss = 5.2761 (* 1 = 5.2761 loss)
I0410 01:59:07.463531 27877 sgd_solver.cpp:105] Iteration 168, lr = 0.00967269
I0410 01:59:12.422400 27877 solver.cpp:218] Iteration 180 (2.41997 iter/s, 4.95874s/12 iters), loss = 5.26372
I0410 01:59:12.422451 27877 solver.cpp:237]     Train net output #0: loss = 5.26372 (* 1 = 5.26372 loss)
I0410 01:59:12.422463 27877 sgd_solver.cpp:105] Iteration 180, lr = 0.00964973
I0410 01:59:17.326809 27877 solver.cpp:218] Iteration 192 (2.44687 iter/s, 4.90423s/12 iters), loss = 5.27383
I0410 01:59:17.326849 27877 solver.cpp:237]     Train net output #0: loss = 5.27383 (* 1 = 5.27383 loss)
I0410 01:59:17.326858 27877 sgd_solver.cpp:105] Iteration 192, lr = 0.00962682
I0410 01:59:21.164824 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 01:59:21.831524 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_204.caffemodel
I0410 01:59:28.906311 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_204.solverstate
I0410 01:59:30.217721 27877 solver.cpp:330] Iteration 204, Testing net (#0)
I0410 01:59:30.217751 27877 net.cpp:676] Ignoring source layer train-data
I0410 01:59:34.642570 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 01:59:34.765813 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 01:59:34.765866 27877 solver.cpp:397]     Test net output #1: loss = 5.28377 (* 1 = 5.28377 loss)
I0410 01:59:34.848592 27877 solver.cpp:218] Iteration 204 (0.684881 iter/s, 17.5213s/12 iters), loss = 5.27039
I0410 01:59:34.848649 27877 solver.cpp:237]     Train net output #0: loss = 5.27039 (* 1 = 5.27039 loss)
I0410 01:59:34.848661 27877 sgd_solver.cpp:105] Iteration 204, lr = 0.00960396
I0410 01:59:39.221269 27877 solver.cpp:218] Iteration 216 (2.74443 iter/s, 4.3725s/12 iters), loss = 5.28079
I0410 01:59:39.221321 27877 solver.cpp:237]     Train net output #0: loss = 5.28079 (* 1 = 5.28079 loss)
I0410 01:59:39.221333 27877 sgd_solver.cpp:105] Iteration 216, lr = 0.00958116
I0410 01:59:44.147189 27877 solver.cpp:218] Iteration 228 (2.43619 iter/s, 4.92573s/12 iters), loss = 5.26087
I0410 01:59:44.147246 27877 solver.cpp:237]     Train net output #0: loss = 5.26087 (* 1 = 5.26087 loss)
I0410 01:59:44.147258 27877 sgd_solver.cpp:105] Iteration 228, lr = 0.00955841
I0410 01:59:48.996383 27877 solver.cpp:218] Iteration 240 (2.47474 iter/s, 4.849s/12 iters), loss = 5.28691
I0410 01:59:48.996434 27877 solver.cpp:237]     Train net output #0: loss = 5.28691 (* 1 = 5.28691 loss)
I0410 01:59:48.996445 27877 sgd_solver.cpp:105] Iteration 240, lr = 0.00953572
I0410 01:59:53.973178 27877 solver.cpp:218] Iteration 252 (2.41128 iter/s, 4.9766s/12 iters), loss = 5.26617
I0410 01:59:53.973235 27877 solver.cpp:237]     Train net output #0: loss = 5.26617 (* 1 = 5.26617 loss)
I0410 01:59:53.973248 27877 sgd_solver.cpp:105] Iteration 252, lr = 0.00951308
I0410 01:59:58.886447 27877 solver.cpp:218] Iteration 264 (2.44246 iter/s, 4.91308s/12 iters), loss = 5.27933
I0410 01:59:58.886492 27877 solver.cpp:237]     Train net output #0: loss = 5.27933 (* 1 = 5.27933 loss)
I0410 01:59:58.886500 27877 sgd_solver.cpp:105] Iteration 264, lr = 0.00949049
I0410 02:00:03.822547 27877 solver.cpp:218] Iteration 276 (2.43116 iter/s, 4.93592s/12 iters), loss = 5.28809
I0410 02:00:03.822660 27877 solver.cpp:237]     Train net output #0: loss = 5.28809 (* 1 = 5.28809 loss)
I0410 02:00:03.822674 27877 sgd_solver.cpp:105] Iteration 276, lr = 0.00946796
I0410 02:00:08.765939 27877 solver.cpp:218] Iteration 288 (2.4276 iter/s, 4.94315s/12 iters), loss = 5.27723
I0410 02:00:08.766012 27877 solver.cpp:237]     Train net output #0: loss = 5.27723 (* 1 = 5.27723 loss)
I0410 02:00:08.766024 27877 sgd_solver.cpp:105] Iteration 288, lr = 0.00944548
I0410 02:00:13.655308 27877 solver.cpp:218] Iteration 300 (2.45441 iter/s, 4.88916s/12 iters), loss = 5.28298
I0410 02:00:13.655362 27877 solver.cpp:237]     Train net output #0: loss = 5.28298 (* 1 = 5.28298 loss)
I0410 02:00:13.655375 27877 sgd_solver.cpp:105] Iteration 300, lr = 0.00942305
I0410 02:00:14.604717 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:00:15.630204 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_306.caffemodel
I0410 02:00:16.505475 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_306.solverstate
I0410 02:00:17.124579 27877 solver.cpp:330] Iteration 306, Testing net (#0)
I0410 02:00:17.124608 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:00:21.387667 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:00:21.546487 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:00:21.546541 27877 solver.cpp:397]     Test net output #1: loss = 5.28505 (* 1 = 5.28505 loss)
I0410 02:00:23.509821 27877 solver.cpp:218] Iteration 312 (1.21776 iter/s, 9.8542s/12 iters), loss = 5.28802
I0410 02:00:23.509881 27877 solver.cpp:237]     Train net output #0: loss = 5.28802 (* 1 = 5.28802 loss)
I0410 02:00:23.509893 27877 sgd_solver.cpp:105] Iteration 312, lr = 0.00940068
I0410 02:00:28.404214 27877 solver.cpp:218] Iteration 324 (2.45188 iter/s, 4.8942s/12 iters), loss = 5.25106
I0410 02:00:28.404264 27877 solver.cpp:237]     Train net output #0: loss = 5.25106 (* 1 = 5.25106 loss)
I0410 02:00:28.404275 27877 sgd_solver.cpp:105] Iteration 324, lr = 0.00937836
I0410 02:00:33.307773 27877 solver.cpp:218] Iteration 336 (2.44729 iter/s, 4.90338s/12 iters), loss = 5.26222
I0410 02:00:33.307823 27877 solver.cpp:237]     Train net output #0: loss = 5.26222 (* 1 = 5.26222 loss)
I0410 02:00:33.307834 27877 sgd_solver.cpp:105] Iteration 336, lr = 0.0093561
I0410 02:00:38.200703 27877 solver.cpp:218] Iteration 348 (2.45261 iter/s, 4.89275s/12 iters), loss = 5.27084
I0410 02:00:38.200781 27877 solver.cpp:237]     Train net output #0: loss = 5.27084 (* 1 = 5.27084 loss)
I0410 02:00:38.200791 27877 sgd_solver.cpp:105] Iteration 348, lr = 0.00933388
I0410 02:00:43.117491 27877 solver.cpp:218] Iteration 360 (2.44072 iter/s, 4.91658s/12 iters), loss = 5.29499
I0410 02:00:43.117530 27877 solver.cpp:237]     Train net output #0: loss = 5.29499 (* 1 = 5.29499 loss)
I0410 02:00:43.117539 27877 sgd_solver.cpp:105] Iteration 360, lr = 0.00931172
I0410 02:00:48.140993 27877 solver.cpp:218] Iteration 372 (2.38886 iter/s, 5.02332s/12 iters), loss = 5.27558
I0410 02:00:48.141047 27877 solver.cpp:237]     Train net output #0: loss = 5.27558 (* 1 = 5.27558 loss)
I0410 02:00:48.141059 27877 sgd_solver.cpp:105] Iteration 372, lr = 0.00928961
I0410 02:00:53.231262 27877 solver.cpp:218] Iteration 384 (2.35753 iter/s, 5.09008s/12 iters), loss = 5.28085
I0410 02:00:53.231315 27877 solver.cpp:237]     Train net output #0: loss = 5.28085 (* 1 = 5.28085 loss)
I0410 02:00:53.231328 27877 sgd_solver.cpp:105] Iteration 384, lr = 0.00926756
I0410 02:00:58.117033 27877 solver.cpp:218] Iteration 396 (2.4562 iter/s, 4.88559s/12 iters), loss = 5.27174
I0410 02:00:58.117081 27877 solver.cpp:237]     Train net output #0: loss = 5.27174 (* 1 = 5.27174 loss)
I0410 02:00:58.117094 27877 sgd_solver.cpp:105] Iteration 396, lr = 0.00924556
I0410 02:01:01.155951 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:01:02.543947 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_408.caffemodel
I0410 02:01:04.695210 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_408.solverstate
I0410 02:01:06.579633 27877 solver.cpp:330] Iteration 408, Testing net (#0)
I0410 02:01:06.579669 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:01:10.851519 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:01:11.138069 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:01:11.138113 27877 solver.cpp:397]     Test net output #1: loss = 5.28655 (* 1 = 5.28655 loss)
I0410 02:01:11.221279 27877 solver.cpp:218] Iteration 408 (0.91576 iter/s, 13.1039s/12 iters), loss = 5.28342
I0410 02:01:11.221352 27877 solver.cpp:237]     Train net output #0: loss = 5.28342 (* 1 = 5.28342 loss)
I0410 02:01:11.221365 27877 sgd_solver.cpp:105] Iteration 408, lr = 0.00922361
I0410 02:01:15.395397 27877 solver.cpp:218] Iteration 420 (2.87498 iter/s, 4.17394s/12 iters), loss = 5.27143
I0410 02:01:15.395435 27877 solver.cpp:237]     Train net output #0: loss = 5.27143 (* 1 = 5.27143 loss)
I0410 02:01:15.395443 27877 sgd_solver.cpp:105] Iteration 420, lr = 0.00920171
I0410 02:01:20.390908 27877 solver.cpp:218] Iteration 432 (2.40225 iter/s, 4.99532s/12 iters), loss = 5.27129
I0410 02:01:20.390975 27877 solver.cpp:237]     Train net output #0: loss = 5.27129 (* 1 = 5.27129 loss)
I0410 02:01:20.390991 27877 sgd_solver.cpp:105] Iteration 432, lr = 0.00917986
I0410 02:01:25.345976 27877 solver.cpp:218] Iteration 444 (2.42187 iter/s, 4.95486s/12 iters), loss = 5.29073
I0410 02:01:25.346021 27877 solver.cpp:237]     Train net output #0: loss = 5.29073 (* 1 = 5.29073 loss)
I0410 02:01:25.346029 27877 sgd_solver.cpp:105] Iteration 444, lr = 0.00915807
I0410 02:01:30.263386 27877 solver.cpp:218] Iteration 456 (2.4404 iter/s, 4.91723s/12 iters), loss = 5.28433
I0410 02:01:30.263440 27877 solver.cpp:237]     Train net output #0: loss = 5.28433 (* 1 = 5.28433 loss)
I0410 02:01:30.263451 27877 sgd_solver.cpp:105] Iteration 456, lr = 0.00913632
I0410 02:01:35.179306 27877 solver.cpp:218] Iteration 468 (2.44114 iter/s, 4.91573s/12 iters), loss = 5.28813
I0410 02:01:35.179355 27877 solver.cpp:237]     Train net output #0: loss = 5.28813 (* 1 = 5.28813 loss)
I0410 02:01:35.179368 27877 sgd_solver.cpp:105] Iteration 468, lr = 0.00911463
I0410 02:01:40.189219 27877 solver.cpp:218] Iteration 480 (2.39534 iter/s, 5.00973s/12 iters), loss = 5.26521
I0410 02:01:40.189257 27877 solver.cpp:237]     Train net output #0: loss = 5.26521 (* 1 = 5.26521 loss)
I0410 02:01:40.189265 27877 sgd_solver.cpp:105] Iteration 480, lr = 0.00909299
I0410 02:01:45.182174 27877 solver.cpp:218] Iteration 492 (2.40347 iter/s, 4.99278s/12 iters), loss = 5.28997
I0410 02:01:45.182325 27877 solver.cpp:237]     Train net output #0: loss = 5.28997 (* 1 = 5.28997 loss)
I0410 02:01:45.182339 27877 sgd_solver.cpp:105] Iteration 492, lr = 0.0090714
I0410 02:01:50.163126 27877 solver.cpp:218] Iteration 504 (2.40932 iter/s, 4.98066s/12 iters), loss = 5.27038
I0410 02:01:50.163184 27877 solver.cpp:237]     Train net output #0: loss = 5.27038 (* 1 = 5.27038 loss)
I0410 02:01:50.163195 27877 sgd_solver.cpp:105] Iteration 504, lr = 0.00904986
I0410 02:01:50.414674 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:01:52.143883 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_510.caffemodel
I0410 02:01:53.635754 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_510.solverstate
I0410 02:01:55.042145 27877 solver.cpp:330] Iteration 510, Testing net (#0)
I0410 02:01:55.042171 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:01:59.241932 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:01:59.477886 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 02:01:59.477936 27877 solver.cpp:397]     Test net output #1: loss = 5.28606 (* 1 = 5.28606 loss)
I0410 02:02:01.387344 27877 solver.cpp:218] Iteration 516 (1.06915 iter/s, 11.2239s/12 iters), loss = 5.2767
I0410 02:02:01.387410 27877 solver.cpp:237]     Train net output #0: loss = 5.2767 (* 1 = 5.2767 loss)
I0410 02:02:01.387430 27877 sgd_solver.cpp:105] Iteration 516, lr = 0.00902838
I0410 02:02:06.249912 27877 solver.cpp:218] Iteration 528 (2.46793 iter/s, 4.86237s/12 iters), loss = 5.27277
I0410 02:02:06.249974 27877 solver.cpp:237]     Train net output #0: loss = 5.27277 (* 1 = 5.27277 loss)
I0410 02:02:06.249985 27877 sgd_solver.cpp:105] Iteration 528, lr = 0.00900694
I0410 02:02:11.210723 27877 solver.cpp:218] Iteration 540 (2.41905 iter/s, 4.96063s/12 iters), loss = 5.28053
I0410 02:02:11.210767 27877 solver.cpp:237]     Train net output #0: loss = 5.28053 (* 1 = 5.28053 loss)
I0410 02:02:11.210774 27877 sgd_solver.cpp:105] Iteration 540, lr = 0.00898556
I0410 02:02:16.167456 27877 solver.cpp:218] Iteration 552 (2.42104 iter/s, 4.95655s/12 iters), loss = 5.27208
I0410 02:02:16.167567 27877 solver.cpp:237]     Train net output #0: loss = 5.27208 (* 1 = 5.27208 loss)
I0410 02:02:16.167582 27877 sgd_solver.cpp:105] Iteration 552, lr = 0.00896423
I0410 02:02:21.037770 27877 solver.cpp:218] Iteration 564 (2.46403 iter/s, 4.87007s/12 iters), loss = 5.25805
I0410 02:02:21.037824 27877 solver.cpp:237]     Train net output #0: loss = 5.25805 (* 1 = 5.25805 loss)
I0410 02:02:21.037835 27877 sgd_solver.cpp:105] Iteration 564, lr = 0.00894294
I0410 02:02:25.952116 27877 solver.cpp:218] Iteration 576 (2.44192 iter/s, 4.91416s/12 iters), loss = 5.27966
I0410 02:02:25.952158 27877 solver.cpp:237]     Train net output #0: loss = 5.27966 (* 1 = 5.27966 loss)
I0410 02:02:25.952167 27877 sgd_solver.cpp:105] Iteration 576, lr = 0.00892171
I0410 02:02:30.840770 27877 solver.cpp:218] Iteration 588 (2.45475 iter/s, 4.88847s/12 iters), loss = 5.26678
I0410 02:02:30.840822 27877 solver.cpp:237]     Train net output #0: loss = 5.26678 (* 1 = 5.26678 loss)
I0410 02:02:30.840833 27877 sgd_solver.cpp:105] Iteration 588, lr = 0.00890053
I0410 02:02:35.937692 27877 solver.cpp:218] Iteration 600 (2.35445 iter/s, 5.09673s/12 iters), loss = 5.26235
I0410 02:02:35.937741 27877 solver.cpp:237]     Train net output #0: loss = 5.26235 (* 1 = 5.26235 loss)
I0410 02:02:35.937752 27877 sgd_solver.cpp:105] Iteration 600, lr = 0.0088794
I0410 02:02:38.308439 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:02:40.412102 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_612.caffemodel
I0410 02:02:42.772871 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_612.solverstate
I0410 02:02:43.882503 27877 solver.cpp:330] Iteration 612, Testing net (#0)
I0410 02:02:43.882531 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:02:47.997866 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:02:48.281288 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:02:48.281322 27877 solver.cpp:397]     Test net output #1: loss = 5.28593 (* 1 = 5.28593 loss)
I0410 02:02:48.363803 27877 solver.cpp:218] Iteration 612 (0.965737 iter/s, 12.4257s/12 iters), loss = 5.27526
I0410 02:02:48.363850 27877 solver.cpp:237]     Train net output #0: loss = 5.27526 (* 1 = 5.27526 loss)
I0410 02:02:48.363859 27877 sgd_solver.cpp:105] Iteration 612, lr = 0.00885831
I0410 02:02:52.584987 27877 solver.cpp:218] Iteration 624 (2.84292 iter/s, 4.22102s/12 iters), loss = 5.29355
I0410 02:02:52.585034 27877 solver.cpp:237]     Train net output #0: loss = 5.29355 (* 1 = 5.29355 loss)
I0410 02:02:52.585043 27877 sgd_solver.cpp:105] Iteration 624, lr = 0.00883728
I0410 02:02:57.472993 27877 solver.cpp:218] Iteration 636 (2.45508 iter/s, 4.88783s/12 iters), loss = 5.28609
I0410 02:02:57.473042 27877 solver.cpp:237]     Train net output #0: loss = 5.28609 (* 1 = 5.28609 loss)
I0410 02:02:57.473052 27877 sgd_solver.cpp:105] Iteration 636, lr = 0.0088163
I0410 02:03:02.369751 27877 solver.cpp:218] Iteration 648 (2.45069 iter/s, 4.89657s/12 iters), loss = 5.27132
I0410 02:03:02.369804 27877 solver.cpp:237]     Train net output #0: loss = 5.27132 (* 1 = 5.27132 loss)
I0410 02:03:02.369817 27877 sgd_solver.cpp:105] Iteration 648, lr = 0.00879537
I0410 02:03:07.316442 27877 solver.cpp:218] Iteration 660 (2.42596 iter/s, 4.9465s/12 iters), loss = 5.26928
I0410 02:03:07.316499 27877 solver.cpp:237]     Train net output #0: loss = 5.26928 (* 1 = 5.26928 loss)
I0410 02:03:07.316511 27877 sgd_solver.cpp:105] Iteration 660, lr = 0.00877449
I0410 02:03:12.249990 27877 solver.cpp:218] Iteration 672 (2.43243 iter/s, 4.93335s/12 iters), loss = 5.27814
I0410 02:03:12.250043 27877 solver.cpp:237]     Train net output #0: loss = 5.27814 (* 1 = 5.27814 loss)
I0410 02:03:12.250056 27877 sgd_solver.cpp:105] Iteration 672, lr = 0.00875366
I0410 02:03:17.186671 27877 solver.cpp:218] Iteration 684 (2.43088 iter/s, 4.93647s/12 iters), loss = 5.27472
I0410 02:03:17.186738 27877 solver.cpp:237]     Train net output #0: loss = 5.27472 (* 1 = 5.27472 loss)
I0410 02:03:17.186761 27877 sgd_solver.cpp:105] Iteration 684, lr = 0.00873287
I0410 02:03:17.187065 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:03:22.105928 27877 solver.cpp:218] Iteration 696 (2.43949 iter/s, 4.91905s/12 iters), loss = 5.27356
I0410 02:03:22.106043 27877 solver.cpp:237]     Train net output #0: loss = 5.27356 (* 1 = 5.27356 loss)
I0410 02:03:22.106053 27877 sgd_solver.cpp:105] Iteration 696, lr = 0.00871214
I0410 02:03:26.587993 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:03:26.966079 27877 solver.cpp:218] Iteration 708 (2.46919 iter/s, 4.8599s/12 iters), loss = 5.25735
I0410 02:03:26.966140 27877 solver.cpp:237]     Train net output #0: loss = 5.25735 (* 1 = 5.25735 loss)
I0410 02:03:26.966152 27877 sgd_solver.cpp:105] Iteration 708, lr = 0.00869145
I0410 02:03:28.971675 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_714.caffemodel
I0410 02:03:32.534757 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_714.solverstate
I0410 02:03:33.825325 27877 solver.cpp:330] Iteration 714, Testing net (#0)
I0410 02:03:33.825353 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:03:37.976563 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:03:38.305706 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:03:38.305757 27877 solver.cpp:397]     Test net output #1: loss = 5.28685 (* 1 = 5.28685 loss)
I0410 02:03:40.205066 27877 solver.cpp:218] Iteration 720 (0.906441 iter/s, 13.2386s/12 iters), loss = 5.27288
I0410 02:03:40.205132 27877 solver.cpp:237]     Train net output #0: loss = 5.27288 (* 1 = 5.27288 loss)
I0410 02:03:40.205144 27877 sgd_solver.cpp:105] Iteration 720, lr = 0.00867082
I0410 02:03:45.157579 27877 solver.cpp:218] Iteration 732 (2.4231 iter/s, 4.95233s/12 iters), loss = 5.28176
I0410 02:03:45.157606 27877 solver.cpp:237]     Train net output #0: loss = 5.28176 (* 1 = 5.28176 loss)
I0410 02:03:45.157613 27877 sgd_solver.cpp:105] Iteration 732, lr = 0.00865023
I0410 02:03:50.085314 27877 solver.cpp:218] Iteration 744 (2.43528 iter/s, 4.92757s/12 iters), loss = 5.27848
I0410 02:03:50.085371 27877 solver.cpp:237]     Train net output #0: loss = 5.27848 (* 1 = 5.27848 loss)
I0410 02:03:50.085384 27877 sgd_solver.cpp:105] Iteration 744, lr = 0.0086297
I0410 02:03:55.004837 27877 solver.cpp:218] Iteration 756 (2.43936 iter/s, 4.91933s/12 iters), loss = 5.27495
I0410 02:03:55.004974 27877 solver.cpp:237]     Train net output #0: loss = 5.27495 (* 1 = 5.27495 loss)
I0410 02:03:55.004987 27877 sgd_solver.cpp:105] Iteration 756, lr = 0.00860921
I0410 02:03:59.976187 27877 solver.cpp:218] Iteration 768 (2.41396 iter/s, 4.97108s/12 iters), loss = 5.27854
I0410 02:03:59.976230 27877 solver.cpp:237]     Train net output #0: loss = 5.27854 (* 1 = 5.27854 loss)
I0410 02:03:59.976241 27877 sgd_solver.cpp:105] Iteration 768, lr = 0.00858877
I0410 02:04:05.021265 27877 solver.cpp:218] Iteration 780 (2.37864 iter/s, 5.04489s/12 iters), loss = 5.26707
I0410 02:04:05.021317 27877 solver.cpp:237]     Train net output #0: loss = 5.26707 (* 1 = 5.26707 loss)
I0410 02:04:05.021329 27877 sgd_solver.cpp:105] Iteration 780, lr = 0.00856838
I0410 02:04:10.009951 27877 solver.cpp:218] Iteration 792 (2.40553 iter/s, 4.9885s/12 iters), loss = 5.27263
I0410 02:04:10.010021 27877 solver.cpp:237]     Train net output #0: loss = 5.27263 (* 1 = 5.27263 loss)
I0410 02:04:10.010032 27877 sgd_solver.cpp:105] Iteration 792, lr = 0.00854803
I0410 02:04:14.904721 27877 solver.cpp:218] Iteration 804 (2.4517 iter/s, 4.89456s/12 iters), loss = 5.28907
I0410 02:04:14.904764 27877 solver.cpp:237]     Train net output #0: loss = 5.28907 (* 1 = 5.28907 loss)
I0410 02:04:14.904774 27877 sgd_solver.cpp:105] Iteration 804, lr = 0.00852774
I0410 02:04:16.615664 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:04:19.334398 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_816.caffemodel
I0410 02:04:20.165860 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_816.solverstate
I0410 02:04:20.781378 27877 solver.cpp:330] Iteration 816, Testing net (#0)
I0410 02:04:20.781404 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:04:24.897363 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:04:25.264333 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:04:25.264439 27877 solver.cpp:397]     Test net output #1: loss = 5.28677 (* 1 = 5.28677 loss)
I0410 02:04:25.347381 27877 solver.cpp:218] Iteration 816 (1.14917 iter/s, 10.4423s/12 iters), loss = 5.27523
I0410 02:04:25.347434 27877 solver.cpp:237]     Train net output #0: loss = 5.27523 (* 1 = 5.27523 loss)
I0410 02:04:25.347445 27877 sgd_solver.cpp:105] Iteration 816, lr = 0.00850749
I0410 02:04:29.675482 27877 solver.cpp:218] Iteration 828 (2.77269 iter/s, 4.32793s/12 iters), loss = 5.28577
I0410 02:04:29.675523 27877 solver.cpp:237]     Train net output #0: loss = 5.28577 (* 1 = 5.28577 loss)
I0410 02:04:29.675531 27877 sgd_solver.cpp:105] Iteration 828, lr = 0.00848729
I0410 02:04:34.553987 27877 solver.cpp:218] Iteration 840 (2.45987 iter/s, 4.87831s/12 iters), loss = 5.23135
I0410 02:04:34.554030 27877 solver.cpp:237]     Train net output #0: loss = 5.23135 (* 1 = 5.23135 loss)
I0410 02:04:34.554040 27877 sgd_solver.cpp:105] Iteration 840, lr = 0.00846714
I0410 02:04:39.541252 27877 solver.cpp:218] Iteration 852 (2.40622 iter/s, 4.98708s/12 iters), loss = 5.30437
I0410 02:04:39.541306 27877 solver.cpp:237]     Train net output #0: loss = 5.30437 (* 1 = 5.30437 loss)
I0410 02:04:39.541317 27877 sgd_solver.cpp:105] Iteration 852, lr = 0.00844704
I0410 02:04:44.431527 27877 solver.cpp:218] Iteration 864 (2.45394 iter/s, 4.89009s/12 iters), loss = 5.26519
I0410 02:04:44.431573 27877 solver.cpp:237]     Train net output #0: loss = 5.26519 (* 1 = 5.26519 loss)
I0410 02:04:44.431584 27877 sgd_solver.cpp:105] Iteration 864, lr = 0.00842698
I0410 02:04:49.345839 27877 solver.cpp:218] Iteration 876 (2.44194 iter/s, 4.91413s/12 iters), loss = 5.27462
I0410 02:04:49.345890 27877 solver.cpp:237]     Train net output #0: loss = 5.27462 (* 1 = 5.27462 loss)
I0410 02:04:49.345899 27877 sgd_solver.cpp:105] Iteration 876, lr = 0.00840698
I0410 02:04:54.282621 27877 solver.cpp:218] Iteration 888 (2.43082 iter/s, 4.9366s/12 iters), loss = 5.26905
I0410 02:04:54.282658 27877 solver.cpp:237]     Train net output #0: loss = 5.26905 (* 1 = 5.26905 loss)
I0410 02:04:54.282667 27877 sgd_solver.cpp:105] Iteration 888, lr = 0.00838702
I0410 02:04:59.163219 27877 solver.cpp:218] Iteration 900 (2.4588 iter/s, 4.88042s/12 iters), loss = 5.27708
I0410 02:04:59.163383 27877 solver.cpp:237]     Train net output #0: loss = 5.27708 (* 1 = 5.27708 loss)
I0410 02:04:59.163398 27877 sgd_solver.cpp:105] Iteration 900, lr = 0.0083671
I0410 02:05:02.952939 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:05:03.998203 27877 solver.cpp:218] Iteration 912 (2.48206 iter/s, 4.83469s/12 iters), loss = 5.2506
I0410 02:05:03.998251 27877 solver.cpp:237]     Train net output #0: loss = 5.2506 (* 1 = 5.2506 loss)
I0410 02:05:03.998262 27877 sgd_solver.cpp:105] Iteration 912, lr = 0.00834724
I0410 02:05:06.025213 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_918.caffemodel
I0410 02:05:07.646306 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_918.solverstate
I0410 02:05:08.968665 27877 solver.cpp:330] Iteration 918, Testing net (#0)
I0410 02:05:08.968694 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:05:12.988524 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:05:13.388962 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:05:13.388994 27877 solver.cpp:397]     Test net output #1: loss = 5.28663 (* 1 = 5.28663 loss)
I0410 02:05:15.111932 27877 solver.cpp:218] Iteration 924 (1.07978 iter/s, 11.1134s/12 iters), loss = 5.28471
I0410 02:05:15.111997 27877 solver.cpp:237]     Train net output #0: loss = 5.28471 (* 1 = 5.28471 loss)
I0410 02:05:15.112010 27877 sgd_solver.cpp:105] Iteration 924, lr = 0.00832742
I0410 02:05:20.028105 27877 solver.cpp:218] Iteration 936 (2.44102 iter/s, 4.91598s/12 iters), loss = 5.26055
I0410 02:05:20.028151 27877 solver.cpp:237]     Train net output #0: loss = 5.26055 (* 1 = 5.26055 loss)
I0410 02:05:20.028160 27877 sgd_solver.cpp:105] Iteration 936, lr = 0.00830765
I0410 02:05:24.936374 27877 solver.cpp:218] Iteration 948 (2.44494 iter/s, 4.90809s/12 iters), loss = 5.28635
I0410 02:05:24.936417 27877 solver.cpp:237]     Train net output #0: loss = 5.28635 (* 1 = 5.28635 loss)
I0410 02:05:24.936427 27877 sgd_solver.cpp:105] Iteration 948, lr = 0.00828793
I0410 02:05:29.865329 27877 solver.cpp:218] Iteration 960 (2.43468 iter/s, 4.92877s/12 iters), loss = 5.26277
I0410 02:05:29.865438 27877 solver.cpp:237]     Train net output #0: loss = 5.26277 (* 1 = 5.26277 loss)
I0410 02:05:29.865453 27877 sgd_solver.cpp:105] Iteration 960, lr = 0.00826825
I0410 02:05:34.795491 27877 solver.cpp:218] Iteration 972 (2.43411 iter/s, 4.92992s/12 iters), loss = 5.27318
I0410 02:05:34.795537 27877 solver.cpp:237]     Train net output #0: loss = 5.27318 (* 1 = 5.27318 loss)
I0410 02:05:34.795545 27877 sgd_solver.cpp:105] Iteration 972, lr = 0.00824862
I0410 02:05:39.727659 27877 solver.cpp:218] Iteration 984 (2.43309 iter/s, 4.93199s/12 iters), loss = 5.28798
I0410 02:05:39.727705 27877 solver.cpp:237]     Train net output #0: loss = 5.28798 (* 1 = 5.28798 loss)
I0410 02:05:39.727713 27877 sgd_solver.cpp:105] Iteration 984, lr = 0.00822903
I0410 02:05:44.606688 27877 solver.cpp:218] Iteration 996 (2.4596 iter/s, 4.87885s/12 iters), loss = 5.27865
I0410 02:05:44.606736 27877 solver.cpp:237]     Train net output #0: loss = 5.27865 (* 1 = 5.27865 loss)
I0410 02:05:44.606746 27877 sgd_solver.cpp:105] Iteration 996, lr = 0.0082095
I0410 02:05:49.512363 27877 solver.cpp:218] Iteration 1008 (2.44623 iter/s, 4.9055s/12 iters), loss = 5.28939
I0410 02:05:49.512413 27877 solver.cpp:237]     Train net output #0: loss = 5.28939 (* 1 = 5.28939 loss)
I0410 02:05:49.512425 27877 sgd_solver.cpp:105] Iteration 1008, lr = 0.00819001
I0410 02:05:50.496307 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:05:53.927796 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1020.caffemodel
I0410 02:05:56.575947 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1020.solverstate
I0410 02:06:00.395754 27877 solver.cpp:330] Iteration 1020, Testing net (#0)
I0410 02:06:00.395907 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:06:04.409693 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:06:04.839941 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:06:04.839989 27877 solver.cpp:397]     Test net output #1: loss = 5.28637 (* 1 = 5.28637 loss)
I0410 02:06:04.922938 27877 solver.cpp:218] Iteration 1020 (0.778708 iter/s, 15.4101s/12 iters), loss = 5.29096
I0410 02:06:04.922988 27877 solver.cpp:237]     Train net output #0: loss = 5.29096 (* 1 = 5.29096 loss)
I0410 02:06:04.923000 27877 sgd_solver.cpp:105] Iteration 1020, lr = 0.00817056
I0410 02:06:09.135288 27877 solver.cpp:218] Iteration 1032 (2.84888 iter/s, 4.21218s/12 iters), loss = 5.24972
I0410 02:06:09.135339 27877 solver.cpp:237]     Train net output #0: loss = 5.24972 (* 1 = 5.24972 loss)
I0410 02:06:09.135349 27877 sgd_solver.cpp:105] Iteration 1032, lr = 0.00815116
I0410 02:06:14.069633 27877 solver.cpp:218] Iteration 1044 (2.43202 iter/s, 4.93416s/12 iters), loss = 5.25581
I0410 02:06:14.069680 27877 solver.cpp:237]     Train net output #0: loss = 5.25581 (* 1 = 5.25581 loss)
I0410 02:06:14.069692 27877 sgd_solver.cpp:105] Iteration 1044, lr = 0.00813181
I0410 02:06:18.996685 27877 solver.cpp:218] Iteration 1056 (2.43562 iter/s, 4.92687s/12 iters), loss = 5.26442
I0410 02:06:18.996750 27877 solver.cpp:237]     Train net output #0: loss = 5.26442 (* 1 = 5.26442 loss)
I0410 02:06:18.996769 27877 sgd_solver.cpp:105] Iteration 1056, lr = 0.0081125
I0410 02:06:23.888887 27877 solver.cpp:218] Iteration 1068 (2.45298 iter/s, 4.89201s/12 iters), loss = 5.28826
I0410 02:06:23.888936 27877 solver.cpp:237]     Train net output #0: loss = 5.28826 (* 1 = 5.28826 loss)
I0410 02:06:23.888947 27877 sgd_solver.cpp:105] Iteration 1068, lr = 0.00809324
I0410 02:06:28.836138 27877 solver.cpp:218] Iteration 1080 (2.42568 iter/s, 4.94707s/12 iters), loss = 5.27057
I0410 02:06:28.836191 27877 solver.cpp:237]     Train net output #0: loss = 5.27057 (* 1 = 5.27057 loss)
I0410 02:06:28.836202 27877 sgd_solver.cpp:105] Iteration 1080, lr = 0.00807403
I0410 02:06:33.727488 27877 solver.cpp:218] Iteration 1092 (2.4534 iter/s, 4.89117s/12 iters), loss = 5.27936
I0410 02:06:33.727578 27877 solver.cpp:237]     Train net output #0: loss = 5.27936 (* 1 = 5.27936 loss)
I0410 02:06:33.727587 27877 sgd_solver.cpp:105] Iteration 1092, lr = 0.00805486
I0410 02:06:38.670403 27877 solver.cpp:218] Iteration 1104 (2.42783 iter/s, 4.94269s/12 iters), loss = 5.27547
I0410 02:06:38.670437 27877 solver.cpp:237]     Train net output #0: loss = 5.27547 (* 1 = 5.27547 loss)
I0410 02:06:38.670445 27877 sgd_solver.cpp:105] Iteration 1104, lr = 0.00803573
I0410 02:06:41.786204 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:06:43.624015 27877 solver.cpp:218] Iteration 1116 (2.42256 iter/s, 4.95344s/12 iters), loss = 5.27533
I0410 02:06:43.624073 27877 solver.cpp:237]     Train net output #0: loss = 5.27533 (* 1 = 5.27533 loss)
I0410 02:06:43.624085 27877 sgd_solver.cpp:105] Iteration 1116, lr = 0.00801666
I0410 02:06:45.609666 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1122.caffemodel
I0410 02:06:47.967370 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1122.solverstate
I0410 02:06:48.949538 27877 solver.cpp:330] Iteration 1122, Testing net (#0)
I0410 02:06:48.949569 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:06:52.979796 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:06:53.453657 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:06:53.453693 27877 solver.cpp:397]     Test net output #1: loss = 5.28642 (* 1 = 5.28642 loss)
I0410 02:06:55.392295 27877 solver.cpp:218] Iteration 1128 (1.01972 iter/s, 11.7679s/12 iters), loss = 5.26885
I0410 02:06:55.392345 27877 solver.cpp:237]     Train net output #0: loss = 5.26885 (* 1 = 5.26885 loss)
I0410 02:06:55.392356 27877 sgd_solver.cpp:105] Iteration 1128, lr = 0.00799762
I0410 02:07:00.399335 27877 solver.cpp:218] Iteration 1140 (2.39671 iter/s, 5.00685s/12 iters), loss = 5.26545
I0410 02:07:00.399387 27877 solver.cpp:237]     Train net output #0: loss = 5.26545 (* 1 = 5.26545 loss)
I0410 02:07:00.399399 27877 sgd_solver.cpp:105] Iteration 1140, lr = 0.00797863
I0410 02:07:05.249733 27877 solver.cpp:218] Iteration 1152 (2.47412 iter/s, 4.85022s/12 iters), loss = 5.28145
I0410 02:07:05.249891 27877 solver.cpp:237]     Train net output #0: loss = 5.28145 (* 1 = 5.28145 loss)
I0410 02:07:05.249905 27877 sgd_solver.cpp:105] Iteration 1152, lr = 0.00795969
I0410 02:07:10.205399 27877 solver.cpp:218] Iteration 1164 (2.42161 iter/s, 4.95538s/12 iters), loss = 5.27856
I0410 02:07:10.205448 27877 solver.cpp:237]     Train net output #0: loss = 5.27856 (* 1 = 5.27856 loss)
I0410 02:07:10.205458 27877 sgd_solver.cpp:105] Iteration 1164, lr = 0.00794079
I0410 02:07:15.233392 27877 solver.cpp:218] Iteration 1176 (2.38673 iter/s, 5.02781s/12 iters), loss = 5.29
I0410 02:07:15.233444 27877 solver.cpp:237]     Train net output #0: loss = 5.29 (* 1 = 5.29 loss)
I0410 02:07:15.233455 27877 sgd_solver.cpp:105] Iteration 1176, lr = 0.00792194
I0410 02:07:20.159044 27877 solver.cpp:218] Iteration 1188 (2.43632 iter/s, 4.92547s/12 iters), loss = 5.27686
I0410 02:07:20.159101 27877 solver.cpp:237]     Train net output #0: loss = 5.27686 (* 1 = 5.27686 loss)
I0410 02:07:20.159117 27877 sgd_solver.cpp:105] Iteration 1188, lr = 0.00790313
I0410 02:07:25.172639 27877 solver.cpp:218] Iteration 1200 (2.39358 iter/s, 5.0134s/12 iters), loss = 5.29298
I0410 02:07:25.172696 27877 solver.cpp:237]     Train net output #0: loss = 5.29298 (* 1 = 5.29298 loss)
I0410 02:07:25.172708 27877 sgd_solver.cpp:105] Iteration 1200, lr = 0.00788437
I0410 02:07:30.137060 27877 solver.cpp:218] Iteration 1212 (2.4173 iter/s, 4.96423s/12 iters), loss = 5.26501
I0410 02:07:30.137116 27877 solver.cpp:237]     Train net output #0: loss = 5.26501 (* 1 = 5.26501 loss)
I0410 02:07:30.137128 27877 sgd_solver.cpp:105] Iteration 1212, lr = 0.00786565
I0410 02:07:30.420003 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:07:34.586278 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1224.caffemodel
I0410 02:07:37.034106 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1224.solverstate
I0410 02:07:38.291388 27877 solver.cpp:330] Iteration 1224, Testing net (#0)
I0410 02:07:38.291414 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:07:42.224712 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:07:42.733515 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 02:07:42.733552 27877 solver.cpp:397]     Test net output #1: loss = 5.2865 (* 1 = 5.2865 loss)
I0410 02:07:42.816080 27877 solver.cpp:218] Iteration 1224 (0.946473 iter/s, 12.6786s/12 iters), loss = 5.28488
I0410 02:07:42.816123 27877 solver.cpp:237]     Train net output #0: loss = 5.28488 (* 1 = 5.28488 loss)
I0410 02:07:42.816131 27877 sgd_solver.cpp:105] Iteration 1224, lr = 0.00784697
I0410 02:07:47.090471 27877 solver.cpp:218] Iteration 1236 (2.80753 iter/s, 4.27422s/12 iters), loss = 5.27078
I0410 02:07:47.090528 27877 solver.cpp:237]     Train net output #0: loss = 5.27078 (* 1 = 5.27078 loss)
I0410 02:07:47.090538 27877 sgd_solver.cpp:105] Iteration 1236, lr = 0.00782834
I0410 02:07:52.311993 27877 solver.cpp:218] Iteration 1248 (2.29827 iter/s, 5.22132s/12 iters), loss = 5.27792
I0410 02:07:52.312050 27877 solver.cpp:237]     Train net output #0: loss = 5.27792 (* 1 = 5.27792 loss)
I0410 02:07:52.312063 27877 sgd_solver.cpp:105] Iteration 1248, lr = 0.00780976
I0410 02:07:57.350409 27877 solver.cpp:218] Iteration 1260 (2.38179 iter/s, 5.03822s/12 iters), loss = 5.27083
I0410 02:07:57.350456 27877 solver.cpp:237]     Train net output #0: loss = 5.27083 (* 1 = 5.27083 loss)
I0410 02:07:57.350466 27877 sgd_solver.cpp:105] Iteration 1260, lr = 0.00779122
I0410 02:08:02.306145 27877 solver.cpp:218] Iteration 1272 (2.42152 iter/s, 4.95556s/12 iters), loss = 5.24809
I0410 02:08:02.306185 27877 solver.cpp:237]     Train net output #0: loss = 5.24809 (* 1 = 5.24809 loss)
I0410 02:08:02.306193 27877 sgd_solver.cpp:105] Iteration 1272, lr = 0.00777272
I0410 02:08:07.366438 27877 solver.cpp:218] Iteration 1284 (2.37149 iter/s, 5.06011s/12 iters), loss = 5.28403
I0410 02:08:07.366560 27877 solver.cpp:237]     Train net output #0: loss = 5.28403 (* 1 = 5.28403 loss)
I0410 02:08:07.366570 27877 sgd_solver.cpp:105] Iteration 1284, lr = 0.00775426
I0410 02:08:12.268877 27877 solver.cpp:218] Iteration 1296 (2.44789 iter/s, 4.90219s/12 iters), loss = 5.2665
I0410 02:08:12.268918 27877 solver.cpp:237]     Train net output #0: loss = 5.2665 (* 1 = 5.2665 loss)
I0410 02:08:12.268926 27877 sgd_solver.cpp:105] Iteration 1296, lr = 0.00773585
I0410 02:08:17.244017 27877 solver.cpp:218] Iteration 1308 (2.41208 iter/s, 4.97496s/12 iters), loss = 5.25455
I0410 02:08:17.244068 27877 solver.cpp:237]     Train net output #0: loss = 5.25455 (* 1 = 5.25455 loss)
I0410 02:08:17.244081 27877 sgd_solver.cpp:105] Iteration 1308, lr = 0.00771749
I0410 02:08:19.741153 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:08:22.203066 27877 solver.cpp:218] Iteration 1320 (2.41991 iter/s, 4.95887s/12 iters), loss = 5.27874
I0410 02:08:22.203116 27877 solver.cpp:237]     Train net output #0: loss = 5.27874 (* 1 = 5.27874 loss)
I0410 02:08:22.203128 27877 sgd_solver.cpp:105] Iteration 1320, lr = 0.00769916
I0410 02:08:24.195394 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1326.caffemodel
I0410 02:08:25.071956 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1326.solverstate
I0410 02:08:25.720319 27877 solver.cpp:330] Iteration 1326, Testing net (#0)
I0410 02:08:25.720350 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:08:29.770910 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:08:30.326432 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:08:30.326480 27877 solver.cpp:397]     Test net output #1: loss = 5.28708 (* 1 = 5.28708 loss)
I0410 02:08:32.206990 27877 solver.cpp:218] Iteration 1332 (1.19957 iter/s, 10.0036s/12 iters), loss = 5.28766
I0410 02:08:32.207052 27877 solver.cpp:237]     Train net output #0: loss = 5.28766 (* 1 = 5.28766 loss)
I0410 02:08:32.207064 27877 sgd_solver.cpp:105] Iteration 1332, lr = 0.00768088
I0410 02:08:37.063854 27877 solver.cpp:218] Iteration 1344 (2.47083 iter/s, 4.85668s/12 iters), loss = 5.28419
I0410 02:08:37.063903 27877 solver.cpp:237]     Train net output #0: loss = 5.28419 (* 1 = 5.28419 loss)
I0410 02:08:37.063915 27877 sgd_solver.cpp:105] Iteration 1344, lr = 0.00766265
I0410 02:08:41.961735 27877 solver.cpp:218] Iteration 1356 (2.45013 iter/s, 4.8977s/12 iters), loss = 5.27264
I0410 02:08:41.961817 27877 solver.cpp:237]     Train net output #0: loss = 5.27264 (* 1 = 5.27264 loss)
I0410 02:08:41.961831 27877 sgd_solver.cpp:105] Iteration 1356, lr = 0.00764446
I0410 02:08:46.903311 27877 solver.cpp:218] Iteration 1368 (2.42848 iter/s, 4.94136s/12 iters), loss = 5.27192
I0410 02:08:46.903362 27877 solver.cpp:237]     Train net output #0: loss = 5.27192 (* 1 = 5.27192 loss)
I0410 02:08:46.903374 27877 sgd_solver.cpp:105] Iteration 1368, lr = 0.00762631
I0410 02:08:47.270193 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:08:51.803165 27877 solver.cpp:218] Iteration 1380 (2.44914 iter/s, 4.89968s/12 iters), loss = 5.27487
I0410 02:08:51.803202 27877 solver.cpp:237]     Train net output #0: loss = 5.27487 (* 1 = 5.27487 loss)
I0410 02:08:51.803210 27877 sgd_solver.cpp:105] Iteration 1380, lr = 0.0076082
I0410 02:08:56.733494 27877 solver.cpp:218] Iteration 1392 (2.434 iter/s, 4.93015s/12 iters), loss = 5.27602
I0410 02:08:56.733551 27877 solver.cpp:237]     Train net output #0: loss = 5.27602 (* 1 = 5.27602 loss)
I0410 02:08:56.733563 27877 sgd_solver.cpp:105] Iteration 1392, lr = 0.00759014
I0410 02:09:01.632774 27877 solver.cpp:218] Iteration 1404 (2.44943 iter/s, 4.89909s/12 iters), loss = 5.27572
I0410 02:09:01.632823 27877 solver.cpp:237]     Train net output #0: loss = 5.27572 (* 1 = 5.27572 loss)
I0410 02:09:01.632836 27877 sgd_solver.cpp:105] Iteration 1404, lr = 0.00757212
I0410 02:09:06.192708 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:09:06.541272 27877 solver.cpp:218] Iteration 1416 (2.44483 iter/s, 4.90832s/12 iters), loss = 5.25901
I0410 02:09:06.541321 27877 solver.cpp:237]     Train net output #0: loss = 5.25901 (* 1 = 5.25901 loss)
I0410 02:09:06.541329 27877 sgd_solver.cpp:105] Iteration 1416, lr = 0.00755414
I0410 02:09:11.075913 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1428.caffemodel
I0410 02:09:12.630843 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1428.solverstate
I0410 02:09:13.884327 27877 solver.cpp:330] Iteration 1428, Testing net (#0)
I0410 02:09:13.884348 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:09:17.812880 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:09:18.402066 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:09:18.402115 27877 solver.cpp:397]     Test net output #1: loss = 5.28648 (* 1 = 5.28648 loss)
I0410 02:09:18.485137 27877 solver.cpp:218] Iteration 1428 (1.00473 iter/s, 11.9435s/12 iters), loss = 5.27606
I0410 02:09:18.485189 27877 solver.cpp:237]     Train net output #0: loss = 5.27606 (* 1 = 5.27606 loss)
I0410 02:09:18.485200 27877 sgd_solver.cpp:105] Iteration 1428, lr = 0.0075362
I0410 02:09:22.762293 27877 solver.cpp:218] Iteration 1440 (2.80571 iter/s, 4.27699s/12 iters), loss = 5.28354
I0410 02:09:22.762338 27877 solver.cpp:237]     Train net output #0: loss = 5.28354 (* 1 = 5.28354 loss)
I0410 02:09:22.762347 27877 sgd_solver.cpp:105] Iteration 1440, lr = 0.00751831
I0410 02:09:27.783008 27877 solver.cpp:218] Iteration 1452 (2.3902 iter/s, 5.02051s/12 iters), loss = 5.28197
I0410 02:09:27.783084 27877 solver.cpp:237]     Train net output #0: loss = 5.28197 (* 1 = 5.28197 loss)
I0410 02:09:27.783104 27877 sgd_solver.cpp:105] Iteration 1452, lr = 0.00750046
I0410 02:09:33.037587 27877 solver.cpp:218] Iteration 1464 (2.28382 iter/s, 5.25436s/12 iters), loss = 5.27653
I0410 02:09:33.037645 27877 solver.cpp:237]     Train net output #0: loss = 5.27653 (* 1 = 5.27653 loss)
I0410 02:09:33.037657 27877 sgd_solver.cpp:105] Iteration 1464, lr = 0.00748265
I0410 02:09:38.030287 27877 solver.cpp:218] Iteration 1476 (2.4036 iter/s, 4.9925s/12 iters), loss = 5.28113
I0410 02:09:38.030339 27877 solver.cpp:237]     Train net output #0: loss = 5.28113 (* 1 = 5.28113 loss)
I0410 02:09:38.030350 27877 sgd_solver.cpp:105] Iteration 1476, lr = 0.00746489
I0410 02:09:43.038597 27877 solver.cpp:218] Iteration 1488 (2.39611 iter/s, 5.00812s/12 iters), loss = 5.25322
I0410 02:09:43.038717 27877 solver.cpp:237]     Train net output #0: loss = 5.25322 (* 1 = 5.25322 loss)
I0410 02:09:43.038731 27877 sgd_solver.cpp:105] Iteration 1488, lr = 0.00744716
I0410 02:09:47.908428 27877 solver.cpp:218] Iteration 1500 (2.46428 iter/s, 4.86958s/12 iters), loss = 5.26635
I0410 02:09:47.908484 27877 solver.cpp:237]     Train net output #0: loss = 5.26635 (* 1 = 5.26635 loss)
I0410 02:09:47.908495 27877 sgd_solver.cpp:105] Iteration 1500, lr = 0.00742948
I0410 02:09:52.847086 27877 solver.cpp:218] Iteration 1512 (2.4299 iter/s, 4.93847s/12 iters), loss = 5.28684
I0410 02:09:52.847126 27877 solver.cpp:237]     Train net output #0: loss = 5.28684 (* 1 = 5.28684 loss)
I0410 02:09:52.847136 27877 sgd_solver.cpp:105] Iteration 1512, lr = 0.00741184
I0410 02:09:54.573071 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:09:57.764879 27877 solver.cpp:218] Iteration 1524 (2.44021 iter/s, 4.91762s/12 iters), loss = 5.27477
I0410 02:09:57.764925 27877 solver.cpp:237]     Train net output #0: loss = 5.27477 (* 1 = 5.27477 loss)
I0410 02:09:57.764933 27877 sgd_solver.cpp:105] Iteration 1524, lr = 0.00739425
I0410 02:09:59.738824 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1530.caffemodel
I0410 02:10:00.573307 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1530.solverstate
I0410 02:10:01.251174 27877 solver.cpp:330] Iteration 1530, Testing net (#0)
I0410 02:10:01.251200 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:10:05.208037 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:10:05.842538 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:10:05.842574 27877 solver.cpp:397]     Test net output #1: loss = 5.28623 (* 1 = 5.28623 loss)
I0410 02:10:07.616277 27877 solver.cpp:218] Iteration 1536 (1.21814 iter/s, 9.8511s/12 iters), loss = 5.27624
I0410 02:10:07.616334 27877 solver.cpp:237]     Train net output #0: loss = 5.27624 (* 1 = 5.27624 loss)
I0410 02:10:07.616348 27877 sgd_solver.cpp:105] Iteration 1536, lr = 0.00737669
I0410 02:10:12.618436 27877 solver.cpp:218] Iteration 1548 (2.39906 iter/s, 5.00196s/12 iters), loss = 5.23583
I0410 02:10:12.618515 27877 solver.cpp:237]     Train net output #0: loss = 5.23583 (* 1 = 5.23583 loss)
I0410 02:10:12.618532 27877 sgd_solver.cpp:105] Iteration 1548, lr = 0.00735918
I0410 02:10:17.548300 27877 solver.cpp:218] Iteration 1560 (2.43425 iter/s, 4.92966s/12 iters), loss = 5.2924
I0410 02:10:17.548427 27877 solver.cpp:237]     Train net output #0: loss = 5.2924 (* 1 = 5.2924 loss)
I0410 02:10:17.548439 27877 sgd_solver.cpp:105] Iteration 1560, lr = 0.00734171
I0410 02:10:22.551295 27877 solver.cpp:218] Iteration 1572 (2.39869 iter/s, 5.00274s/12 iters), loss = 5.26115
I0410 02:10:22.551343 27877 solver.cpp:237]     Train net output #0: loss = 5.26115 (* 1 = 5.26115 loss)
I0410 02:10:22.551355 27877 sgd_solver.cpp:105] Iteration 1572, lr = 0.00732427
I0410 02:10:27.445084 27877 solver.cpp:218] Iteration 1584 (2.45218 iter/s, 4.8936s/12 iters), loss = 5.26616
I0410 02:10:27.445142 27877 solver.cpp:237]     Train net output #0: loss = 5.26616 (* 1 = 5.26616 loss)
I0410 02:10:27.445153 27877 sgd_solver.cpp:105] Iteration 1584, lr = 0.00730688
I0410 02:10:32.426759 27877 solver.cpp:218] Iteration 1596 (2.40892 iter/s, 4.98148s/12 iters), loss = 5.26942
I0410 02:10:32.426822 27877 solver.cpp:237]     Train net output #0: loss = 5.26942 (* 1 = 5.26942 loss)
I0410 02:10:32.426834 27877 sgd_solver.cpp:105] Iteration 1596, lr = 0.00728954
I0410 02:10:37.384613 27877 solver.cpp:218] Iteration 1608 (2.4205 iter/s, 4.95766s/12 iters), loss = 5.26921
I0410 02:10:37.384655 27877 solver.cpp:237]     Train net output #0: loss = 5.26921 (* 1 = 5.26921 loss)
I0410 02:10:37.384665 27877 sgd_solver.cpp:105] Iteration 1608, lr = 0.00727223
I0410 02:10:41.284178 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:10:42.358570 27877 solver.cpp:218] Iteration 1620 (2.41265 iter/s, 4.97378s/12 iters), loss = 5.25244
I0410 02:10:42.358616 27877 solver.cpp:237]     Train net output #0: loss = 5.25244 (* 1 = 5.25244 loss)
I0410 02:10:42.358624 27877 sgd_solver.cpp:105] Iteration 1620, lr = 0.00725496
I0410 02:10:46.878737 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1632.caffemodel
I0410 02:10:49.504041 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1632.solverstate
I0410 02:10:51.442584 27877 solver.cpp:330] Iteration 1632, Testing net (#0)
I0410 02:10:51.442612 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:10:55.226920 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:10:55.895411 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:10:55.895460 27877 solver.cpp:397]     Test net output #1: loss = 5.28631 (* 1 = 5.28631 loss)
I0410 02:10:55.978407 27877 solver.cpp:218] Iteration 1632 (0.881093 iter/s, 13.6194s/12 iters), loss = 5.28936
I0410 02:10:55.978461 27877 solver.cpp:237]     Train net output #0: loss = 5.28936 (* 1 = 5.28936 loss)
I0410 02:10:55.978471 27877 sgd_solver.cpp:105] Iteration 1632, lr = 0.00723774
I0410 02:11:00.234658 27877 solver.cpp:218] Iteration 1644 (2.8195 iter/s, 4.25608s/12 iters), loss = 5.25561
I0410 02:11:00.234715 27877 solver.cpp:237]     Train net output #0: loss = 5.25561 (* 1 = 5.25561 loss)
I0410 02:11:00.234726 27877 sgd_solver.cpp:105] Iteration 1644, lr = 0.00722056
I0410 02:11:05.130822 27877 solver.cpp:218] Iteration 1656 (2.45099 iter/s, 4.89598s/12 iters), loss = 5.29286
I0410 02:11:05.130861 27877 solver.cpp:237]     Train net output #0: loss = 5.29286 (* 1 = 5.29286 loss)
I0410 02:11:05.130869 27877 sgd_solver.cpp:105] Iteration 1656, lr = 0.00720341
I0410 02:11:10.029485 27877 solver.cpp:218] Iteration 1668 (2.44974 iter/s, 4.89849s/12 iters), loss = 5.26323
I0410 02:11:10.029538 27877 solver.cpp:237]     Train net output #0: loss = 5.26323 (* 1 = 5.26323 loss)
I0410 02:11:10.029549 27877 sgd_solver.cpp:105] Iteration 1668, lr = 0.00718631
I0410 02:11:14.992133 27877 solver.cpp:218] Iteration 1680 (2.41816 iter/s, 4.96246s/12 iters), loss = 5.27514
I0410 02:11:14.992184 27877 solver.cpp:237]     Train net output #0: loss = 5.27514 (* 1 = 5.27514 loss)
I0410 02:11:14.992194 27877 sgd_solver.cpp:105] Iteration 1680, lr = 0.00716925
I0410 02:11:20.013095 27877 solver.cpp:218] Iteration 1692 (2.39007 iter/s, 5.02078s/12 iters), loss = 5.2941
I0410 02:11:20.013221 27877 solver.cpp:237]     Train net output #0: loss = 5.2941 (* 1 = 5.2941 loss)
I0410 02:11:20.013231 27877 sgd_solver.cpp:105] Iteration 1692, lr = 0.00715223
I0410 02:11:24.975033 27877 solver.cpp:218] Iteration 1704 (2.41854 iter/s, 4.96167s/12 iters), loss = 5.27155
I0410 02:11:24.975085 27877 solver.cpp:237]     Train net output #0: loss = 5.27155 (* 1 = 5.27155 loss)
I0410 02:11:24.975098 27877 sgd_solver.cpp:105] Iteration 1704, lr = 0.00713525
I0410 02:11:29.925297 27877 solver.cpp:218] Iteration 1716 (2.42421 iter/s, 4.95007s/12 iters), loss = 5.28148
I0410 02:11:29.925354 27877 solver.cpp:237]     Train net output #0: loss = 5.28148 (* 1 = 5.28148 loss)
I0410 02:11:29.925366 27877 sgd_solver.cpp:105] Iteration 1716, lr = 0.00711831
I0410 02:11:30.959158 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:11:34.840030 27877 solver.cpp:218] Iteration 1728 (2.44173 iter/s, 4.91455s/12 iters), loss = 5.28709
I0410 02:11:34.840070 27877 solver.cpp:237]     Train net output #0: loss = 5.28709 (* 1 = 5.28709 loss)
I0410 02:11:34.840078 27877 sgd_solver.cpp:105] Iteration 1728, lr = 0.00710141
I0410 02:11:36.822716 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1734.caffemodel
I0410 02:11:40.515969 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1734.solverstate
I0410 02:11:42.714773 27877 solver.cpp:330] Iteration 1734, Testing net (#0)
I0410 02:11:42.714799 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:11:46.460083 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:11:47.162384 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:11:47.162420 27877 solver.cpp:397]     Test net output #1: loss = 5.28665 (* 1 = 5.28665 loss)
I0410 02:11:49.010839 27877 solver.cpp:218] Iteration 1740 (0.846835 iter/s, 14.1704s/12 iters), loss = 5.25697
I0410 02:11:49.010892 27877 solver.cpp:237]     Train net output #0: loss = 5.25697 (* 1 = 5.25697 loss)
I0410 02:11:49.010905 27877 sgd_solver.cpp:105] Iteration 1740, lr = 0.00708455
I0410 02:11:53.864291 27877 solver.cpp:218] Iteration 1752 (2.47256 iter/s, 4.85327s/12 iters), loss = 5.26723
I0410 02:11:53.864439 27877 solver.cpp:237]     Train net output #0: loss = 5.26723 (* 1 = 5.26723 loss)
I0410 02:11:53.864452 27877 sgd_solver.cpp:105] Iteration 1752, lr = 0.00706773
I0410 02:11:58.804605 27877 solver.cpp:218] Iteration 1764 (2.42913 iter/s, 4.94003s/12 iters), loss = 5.26454
I0410 02:11:58.804661 27877 solver.cpp:237]     Train net output #0: loss = 5.26454 (* 1 = 5.26454 loss)
I0410 02:11:58.804673 27877 sgd_solver.cpp:105] Iteration 1764, lr = 0.00705094
I0410 02:12:03.823510 27877 solver.cpp:218] Iteration 1776 (2.39105 iter/s, 5.01871s/12 iters), loss = 5.2791
I0410 02:12:03.823563 27877 solver.cpp:237]     Train net output #0: loss = 5.2791 (* 1 = 5.2791 loss)
I0410 02:12:03.823575 27877 sgd_solver.cpp:105] Iteration 1776, lr = 0.0070342
I0410 02:12:08.791728 27877 solver.cpp:218] Iteration 1788 (2.41544 iter/s, 4.96803s/12 iters), loss = 5.26935
I0410 02:12:08.791771 27877 solver.cpp:237]     Train net output #0: loss = 5.26935 (* 1 = 5.26935 loss)
I0410 02:12:08.791781 27877 sgd_solver.cpp:105] Iteration 1788, lr = 0.0070175
I0410 02:12:13.742776 27877 solver.cpp:218] Iteration 1800 (2.42382 iter/s, 4.95086s/12 iters), loss = 5.28016
I0410 02:12:13.742830 27877 solver.cpp:237]     Train net output #0: loss = 5.28016 (* 1 = 5.28016 loss)
I0410 02:12:13.742839 27877 sgd_solver.cpp:105] Iteration 1800, lr = 0.00700084
I0410 02:12:18.647428 27877 solver.cpp:218] Iteration 1812 (2.44675 iter/s, 4.90447s/12 iters), loss = 5.26722
I0410 02:12:18.647470 27877 solver.cpp:237]     Train net output #0: loss = 5.26722 (* 1 = 5.26722 loss)
I0410 02:12:18.647480 27877 sgd_solver.cpp:105] Iteration 1812, lr = 0.00698422
I0410 02:12:21.743185 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:12:23.520260 27877 solver.cpp:218] Iteration 1824 (2.46273 iter/s, 4.87265s/12 iters), loss = 5.27491
I0410 02:12:23.520321 27877 solver.cpp:237]     Train net output #0: loss = 5.27491 (* 1 = 5.27491 loss)
I0410 02:12:23.520334 27877 sgd_solver.cpp:105] Iteration 1824, lr = 0.00696764
I0410 02:12:27.974050 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1836.caffemodel
I0410 02:12:28.771723 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1836.solverstate
I0410 02:12:29.390698 27877 solver.cpp:330] Iteration 1836, Testing net (#0)
I0410 02:12:29.390728 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:12:33.045179 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:12:33.792968 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:12:33.793015 27877 solver.cpp:397]     Test net output #1: loss = 5.28611 (* 1 = 5.28611 loss)
I0410 02:12:33.875914 27877 solver.cpp:218] Iteration 1836 (1.15882 iter/s, 10.3553s/12 iters), loss = 5.27477
I0410 02:12:33.875968 27877 solver.cpp:237]     Train net output #0: loss = 5.27477 (* 1 = 5.27477 loss)
I0410 02:12:33.875979 27877 sgd_solver.cpp:105] Iteration 1836, lr = 0.0069511
I0410 02:12:38.016084 27877 solver.cpp:218] Iteration 1848 (2.89855 iter/s, 4.14s/12 iters), loss = 5.27407
I0410 02:12:38.016130 27877 solver.cpp:237]     Train net output #0: loss = 5.27407 (* 1 = 5.27407 loss)
I0410 02:12:38.016139 27877 sgd_solver.cpp:105] Iteration 1848, lr = 0.00693459
I0410 02:12:42.984599 27877 solver.cpp:218] Iteration 1860 (2.41529 iter/s, 4.96834s/12 iters), loss = 5.27923
I0410 02:12:42.984637 27877 solver.cpp:237]     Train net output #0: loss = 5.27923 (* 1 = 5.27923 loss)
I0410 02:12:42.984645 27877 sgd_solver.cpp:105] Iteration 1860, lr = 0.00691813
I0410 02:12:47.971062 27877 solver.cpp:218] Iteration 1872 (2.4066 iter/s, 4.98629s/12 iters), loss = 5.27097
I0410 02:12:47.971107 27877 solver.cpp:237]     Train net output #0: loss = 5.27097 (* 1 = 5.27097 loss)
I0410 02:12:47.971117 27877 sgd_solver.cpp:105] Iteration 1872, lr = 0.0069017
I0410 02:12:52.855831 27877 solver.cpp:218] Iteration 1884 (2.45671 iter/s, 4.88459s/12 iters), loss = 5.28713
I0410 02:12:52.855881 27877 solver.cpp:237]     Train net output #0: loss = 5.28713 (* 1 = 5.28713 loss)
I0410 02:12:52.855893 27877 sgd_solver.cpp:105] Iteration 1884, lr = 0.00688532
I0410 02:12:57.762900 27877 solver.cpp:218] Iteration 1896 (2.44554 iter/s, 4.90689s/12 iters), loss = 5.2651
I0410 02:12:57.762938 27877 solver.cpp:237]     Train net output #0: loss = 5.2651 (* 1 = 5.2651 loss)
I0410 02:12:57.762946 27877 sgd_solver.cpp:105] Iteration 1896, lr = 0.00686897
I0410 02:13:02.741026 27877 solver.cpp:218] Iteration 1908 (2.41063 iter/s, 4.97795s/12 iters), loss = 5.2846
I0410 02:13:02.741154 27877 solver.cpp:237]     Train net output #0: loss = 5.2846 (* 1 = 5.2846 loss)
I0410 02:13:02.741164 27877 sgd_solver.cpp:105] Iteration 1908, lr = 0.00685266
I0410 02:13:07.726169 27877 solver.cpp:218] Iteration 1920 (2.40728 iter/s, 4.98489s/12 iters), loss = 5.27691
I0410 02:13:07.726217 27877 solver.cpp:237]     Train net output #0: loss = 5.27691 (* 1 = 5.27691 loss)
I0410 02:13:07.726225 27877 sgd_solver.cpp:105] Iteration 1920, lr = 0.00683639
I0410 02:13:08.037144 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:13:12.748394 27877 solver.cpp:218] Iteration 1932 (2.38946 iter/s, 5.02205s/12 iters), loss = 5.28446
I0410 02:13:12.748436 27877 solver.cpp:237]     Train net output #0: loss = 5.28446 (* 1 = 5.28446 loss)
I0410 02:13:12.748445 27877 sgd_solver.cpp:105] Iteration 1932, lr = 0.00682016
I0410 02:13:14.793220 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_1938.caffemodel
I0410 02:13:16.279193 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_1938.solverstate
I0410 02:13:17.563751 27877 solver.cpp:330] Iteration 1938, Testing net (#0)
I0410 02:13:17.563781 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:13:21.363245 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:13:22.160264 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:13:22.160315 27877 solver.cpp:397]     Test net output #1: loss = 5.28655 (* 1 = 5.28655 loss)
I0410 02:13:24.055052 27877 solver.cpp:218] Iteration 1944 (1.06135 iter/s, 11.3063s/12 iters), loss = 5.27497
I0410 02:13:24.055102 27877 solver.cpp:237]     Train net output #0: loss = 5.27497 (* 1 = 5.27497 loss)
I0410 02:13:24.055112 27877 sgd_solver.cpp:105] Iteration 1944, lr = 0.00680397
I0410 02:13:29.011564 27877 solver.cpp:218] Iteration 1956 (2.42115 iter/s, 4.95633s/12 iters), loss = 5.28104
I0410 02:13:29.011606 27877 solver.cpp:237]     Train net output #0: loss = 5.28104 (* 1 = 5.28104 loss)
I0410 02:13:29.011615 27877 sgd_solver.cpp:105] Iteration 1956, lr = 0.00678782
I0410 02:13:34.033032 27877 solver.cpp:218] Iteration 1968 (2.38983 iter/s, 5.02129s/12 iters), loss = 5.27361
I0410 02:13:34.033107 27877 solver.cpp:237]     Train net output #0: loss = 5.27361 (* 1 = 5.27361 loss)
I0410 02:13:34.033118 27877 sgd_solver.cpp:105] Iteration 1968, lr = 0.0067717
I0410 02:13:38.971660 27877 solver.cpp:218] Iteration 1980 (2.42993 iter/s, 4.93842s/12 iters), loss = 5.25362
I0410 02:13:38.971706 27877 solver.cpp:237]     Train net output #0: loss = 5.25362 (* 1 = 5.25362 loss)
I0410 02:13:38.971717 27877 sgd_solver.cpp:105] Iteration 1980, lr = 0.00675562
I0410 02:13:43.869676 27877 solver.cpp:218] Iteration 1992 (2.45006 iter/s, 4.89784s/12 iters), loss = 5.28035
I0410 02:13:43.869716 27877 solver.cpp:237]     Train net output #0: loss = 5.28035 (* 1 = 5.28035 loss)
I0410 02:13:43.869725 27877 sgd_solver.cpp:105] Iteration 1992, lr = 0.00673958
I0410 02:13:48.842969 27877 solver.cpp:218] Iteration 2004 (2.41297 iter/s, 4.97312s/12 iters), loss = 5.27663
I0410 02:13:48.843015 27877 solver.cpp:237]     Train net output #0: loss = 5.27663 (* 1 = 5.27663 loss)
I0410 02:13:48.843026 27877 sgd_solver.cpp:105] Iteration 2004, lr = 0.00672358
I0410 02:13:53.790238 27877 solver.cpp:218] Iteration 2016 (2.42567 iter/s, 4.94709s/12 iters), loss = 5.25737
I0410 02:13:53.790292 27877 solver.cpp:237]     Train net output #0: loss = 5.25737 (* 1 = 5.25737 loss)
I0410 02:13:53.790303 27877 sgd_solver.cpp:105] Iteration 2016, lr = 0.00670762
I0410 02:13:56.332615 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:13:58.753983 27877 solver.cpp:218] Iteration 2028 (2.41763 iter/s, 4.96353s/12 iters), loss = 5.27752
I0410 02:13:58.754037 27877 solver.cpp:237]     Train net output #0: loss = 5.27752 (* 1 = 5.27752 loss)
I0410 02:13:58.754050 27877 sgd_solver.cpp:105] Iteration 2028, lr = 0.00669169
I0410 02:14:03.317657 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2040.caffemodel
I0410 02:14:04.121562 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2040.solverstate
I0410 02:14:04.736923 27877 solver.cpp:330] Iteration 2040, Testing net (#0)
I0410 02:14:04.736948 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:14:08.362669 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:14:09.188546 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 02:14:09.188575 27877 solver.cpp:397]     Test net output #1: loss = 5.28633 (* 1 = 5.28633 loss)
I0410 02:14:09.271200 27877 solver.cpp:218] Iteration 2040 (1.14102 iter/s, 10.5169s/12 iters), loss = 5.28339
I0410 02:14:09.271243 27877 solver.cpp:237]     Train net output #0: loss = 5.28339 (* 1 = 5.28339 loss)
I0410 02:14:09.271251 27877 sgd_solver.cpp:105] Iteration 2040, lr = 0.00667581
I0410 02:14:13.482125 27877 solver.cpp:218] Iteration 2052 (2.84985 iter/s, 4.21075s/12 iters), loss = 5.28554
I0410 02:14:13.482175 27877 solver.cpp:237]     Train net output #0: loss = 5.28554 (* 1 = 5.28554 loss)
I0410 02:14:13.482187 27877 sgd_solver.cpp:105] Iteration 2052, lr = 0.00665996
I0410 02:14:14.254509 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:14:18.529055 27877 solver.cpp:218] Iteration 2064 (2.37777 iter/s, 5.04674s/12 iters), loss = 5.278
I0410 02:14:18.529106 27877 solver.cpp:237]     Train net output #0: loss = 5.278 (* 1 = 5.278 loss)
I0410 02:14:18.529117 27877 sgd_solver.cpp:105] Iteration 2064, lr = 0.00664414
I0410 02:14:23.557317 27877 solver.cpp:218] Iteration 2076 (2.3866 iter/s, 5.02807s/12 iters), loss = 5.27743
I0410 02:14:23.557364 27877 solver.cpp:237]     Train net output #0: loss = 5.27743 (* 1 = 5.27743 loss)
I0410 02:14:23.557374 27877 sgd_solver.cpp:105] Iteration 2076, lr = 0.00662837
I0410 02:14:28.499541 27877 solver.cpp:218] Iteration 2088 (2.42815 iter/s, 4.94204s/12 iters), loss = 5.27495
I0410 02:14:28.499594 27877 solver.cpp:237]     Train net output #0: loss = 5.27495 (* 1 = 5.27495 loss)
I0410 02:14:28.499605 27877 sgd_solver.cpp:105] Iteration 2088, lr = 0.00661263
I0410 02:14:33.417619 27877 solver.cpp:218] Iteration 2100 (2.44007 iter/s, 4.91789s/12 iters), loss = 5.2687
I0410 02:14:33.417678 27877 solver.cpp:237]     Train net output #0: loss = 5.2687 (* 1 = 5.2687 loss)
I0410 02:14:33.417690 27877 sgd_solver.cpp:105] Iteration 2100, lr = 0.00659693
I0410 02:14:38.322748 27877 solver.cpp:218] Iteration 2112 (2.44651 iter/s, 4.90494s/12 iters), loss = 5.27478
I0410 02:14:38.322829 27877 solver.cpp:237]     Train net output #0: loss = 5.27478 (* 1 = 5.27478 loss)
I0410 02:14:38.322839 27877 sgd_solver.cpp:105] Iteration 2112, lr = 0.00658127
I0410 02:14:43.182293 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:14:43.496183 27877 solver.cpp:218] Iteration 2124 (2.31964 iter/s, 5.17321s/12 iters), loss = 5.26087
I0410 02:14:43.496228 27877 solver.cpp:237]     Train net output #0: loss = 5.26087 (* 1 = 5.26087 loss)
I0410 02:14:43.496238 27877 sgd_solver.cpp:105] Iteration 2124, lr = 0.00656564
I0410 02:14:48.386560 27877 solver.cpp:218] Iteration 2136 (2.45389 iter/s, 4.8902s/12 iters), loss = 5.27377
I0410 02:14:48.386603 27877 solver.cpp:237]     Train net output #0: loss = 5.27377 (* 1 = 5.27377 loss)
I0410 02:14:48.386612 27877 sgd_solver.cpp:105] Iteration 2136, lr = 0.00655006
I0410 02:14:50.431999 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2142.caffemodel
I0410 02:14:52.584472 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2142.solverstate
I0410 02:14:53.981302 27877 solver.cpp:330] Iteration 2142, Testing net (#0)
I0410 02:14:53.981326 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:14:57.585505 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:14:58.552110 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:14:58.552160 27877 solver.cpp:397]     Test net output #1: loss = 5.28655 (* 1 = 5.28655 loss)
I0410 02:15:00.343389 27877 solver.cpp:218] Iteration 2148 (1.00364 iter/s, 11.9565s/12 iters), loss = 5.28042
I0410 02:15:00.343448 27877 solver.cpp:237]     Train net output #0: loss = 5.28042 (* 1 = 5.28042 loss)
I0410 02:15:00.343459 27877 sgd_solver.cpp:105] Iteration 2148, lr = 0.00653451
I0410 02:15:05.205368 27877 solver.cpp:218] Iteration 2160 (2.46822 iter/s, 4.86179s/12 iters), loss = 5.28847
I0410 02:15:05.205413 27877 solver.cpp:237]     Train net output #0: loss = 5.28847 (* 1 = 5.28847 loss)
I0410 02:15:05.205427 27877 sgd_solver.cpp:105] Iteration 2160, lr = 0.00651899
I0410 02:15:10.295554 27877 solver.cpp:218] Iteration 2172 (2.35756 iter/s, 5.09s/12 iters), loss = 5.27848
I0410 02:15:10.295683 27877 solver.cpp:237]     Train net output #0: loss = 5.27848 (* 1 = 5.27848 loss)
I0410 02:15:10.295696 27877 sgd_solver.cpp:105] Iteration 2172, lr = 0.00650351
I0410 02:15:15.185838 27877 solver.cpp:218] Iteration 2184 (2.45398 iter/s, 4.89002s/12 iters), loss = 5.27167
I0410 02:15:15.185887 27877 solver.cpp:237]     Train net output #0: loss = 5.27167 (* 1 = 5.27167 loss)
I0410 02:15:15.185897 27877 sgd_solver.cpp:105] Iteration 2184, lr = 0.00648807
I0410 02:15:20.183986 27877 solver.cpp:218] Iteration 2196 (2.40098 iter/s, 4.99796s/12 iters), loss = 5.25415
I0410 02:15:20.184038 27877 solver.cpp:237]     Train net output #0: loss = 5.25415 (* 1 = 5.25415 loss)
I0410 02:15:20.184051 27877 sgd_solver.cpp:105] Iteration 2196, lr = 0.00647267
I0410 02:15:25.135479 27877 solver.cpp:218] Iteration 2208 (2.4236 iter/s, 4.95131s/12 iters), loss = 5.2728
I0410 02:15:25.135533 27877 solver.cpp:237]     Train net output #0: loss = 5.2728 (* 1 = 5.2728 loss)
I0410 02:15:25.135545 27877 sgd_solver.cpp:105] Iteration 2208, lr = 0.0064573
I0410 02:15:30.425132 27877 solver.cpp:218] Iteration 2220 (2.26866 iter/s, 5.28946s/12 iters), loss = 5.2865
I0410 02:15:30.425179 27877 solver.cpp:237]     Train net output #0: loss = 5.2865 (* 1 = 5.2865 loss)
I0410 02:15:30.425190 27877 sgd_solver.cpp:105] Iteration 2220, lr = 0.00644197
I0410 02:15:32.357247 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:15:35.499366 27877 solver.cpp:218] Iteration 2232 (2.36497 iter/s, 5.07406s/12 iters), loss = 5.28398
I0410 02:15:35.499403 27877 solver.cpp:237]     Train net output #0: loss = 5.28398 (* 1 = 5.28398 loss)
I0410 02:15:35.499411 27877 sgd_solver.cpp:105] Iteration 2232, lr = 0.00642668
I0410 02:15:39.939522 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2244.caffemodel
I0410 02:15:42.270784 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2244.solverstate
I0410 02:15:44.115672 27877 solver.cpp:330] Iteration 2244, Testing net (#0)
I0410 02:15:44.115700 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:15:47.657346 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:15:48.583346 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:15:48.583393 27877 solver.cpp:397]     Test net output #1: loss = 5.28645 (* 1 = 5.28645 loss)
I0410 02:15:48.666682 27877 solver.cpp:218] Iteration 2244 (0.911373 iter/s, 13.1669s/12 iters), loss = 5.28038
I0410 02:15:48.666728 27877 solver.cpp:237]     Train net output #0: loss = 5.28038 (* 1 = 5.28038 loss)
I0410 02:15:48.666738 27877 sgd_solver.cpp:105] Iteration 2244, lr = 0.00641142
I0410 02:15:52.908437 27877 solver.cpp:218] Iteration 2256 (2.82914 iter/s, 4.24157s/12 iters), loss = 5.24504
I0410 02:15:52.908501 27877 solver.cpp:237]     Train net output #0: loss = 5.24504 (* 1 = 5.24504 loss)
I0410 02:15:52.908514 27877 sgd_solver.cpp:105] Iteration 2256, lr = 0.0063962
I0410 02:15:57.788713 27877 solver.cpp:218] Iteration 2268 (2.45897 iter/s, 4.88009s/12 iters), loss = 5.28745
I0410 02:15:57.788760 27877 solver.cpp:237]     Train net output #0: loss = 5.28745 (* 1 = 5.28745 loss)
I0410 02:15:57.788772 27877 sgd_solver.cpp:105] Iteration 2268, lr = 0.00638101
I0410 02:16:02.690590 27877 solver.cpp:218] Iteration 2280 (2.44813 iter/s, 4.9017s/12 iters), loss = 5.25296
I0410 02:16:02.690639 27877 solver.cpp:237]     Train net output #0: loss = 5.25296 (* 1 = 5.25296 loss)
I0410 02:16:02.690650 27877 sgd_solver.cpp:105] Iteration 2280, lr = 0.00636586
I0410 02:16:07.605279 27877 solver.cpp:218] Iteration 2292 (2.44175 iter/s, 4.91451s/12 iters), loss = 5.27544
I0410 02:16:07.605329 27877 solver.cpp:237]     Train net output #0: loss = 5.27544 (* 1 = 5.27544 loss)
I0410 02:16:07.605341 27877 sgd_solver.cpp:105] Iteration 2292, lr = 0.00635075
I0410 02:16:12.508656 27877 solver.cpp:218] Iteration 2304 (2.44738 iter/s, 4.90319s/12 iters), loss = 5.26901
I0410 02:16:12.508790 27877 solver.cpp:237]     Train net output #0: loss = 5.26901 (* 1 = 5.26901 loss)
I0410 02:16:12.508805 27877 sgd_solver.cpp:105] Iteration 2304, lr = 0.00633567
I0410 02:16:17.421707 27877 solver.cpp:218] Iteration 2316 (2.4426 iter/s, 4.91279s/12 iters), loss = 5.26694
I0410 02:16:17.421762 27877 solver.cpp:237]     Train net output #0: loss = 5.26694 (* 1 = 5.26694 loss)
I0410 02:16:17.421774 27877 sgd_solver.cpp:105] Iteration 2316, lr = 0.00632063
I0410 02:16:21.405441 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:16:22.435746 27877 solver.cpp:218] Iteration 2328 (2.39337 iter/s, 5.01385s/12 iters), loss = 5.26567
I0410 02:16:22.435797 27877 solver.cpp:237]     Train net output #0: loss = 5.26567 (* 1 = 5.26567 loss)
I0410 02:16:22.435807 27877 sgd_solver.cpp:105] Iteration 2328, lr = 0.00630562
I0410 02:16:27.287817 27877 solver.cpp:218] Iteration 2340 (2.47326 iter/s, 4.85189s/12 iters), loss = 5.29579
I0410 02:16:27.287856 27877 solver.cpp:237]     Train net output #0: loss = 5.29579 (* 1 = 5.29579 loss)
I0410 02:16:27.287866 27877 sgd_solver.cpp:105] Iteration 2340, lr = 0.00629065
I0410 02:16:29.318143 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2346.caffemodel
I0410 02:16:30.124737 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2346.solverstate
I0410 02:16:30.735178 27877 solver.cpp:330] Iteration 2346, Testing net (#0)
I0410 02:16:30.735209 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:16:34.403039 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:16:35.340581 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:16:35.340617 27877 solver.cpp:397]     Test net output #1: loss = 5.28671 (* 1 = 5.28671 loss)
I0410 02:16:37.299607 27877 solver.cpp:218] Iteration 2352 (1.19862 iter/s, 10.0115s/12 iters), loss = 5.26092
I0410 02:16:37.299664 27877 solver.cpp:237]     Train net output #0: loss = 5.26092 (* 1 = 5.26092 loss)
I0410 02:16:37.299675 27877 sgd_solver.cpp:105] Iteration 2352, lr = 0.00627571
I0410 02:16:42.226847 27877 solver.cpp:218] Iteration 2364 (2.43554 iter/s, 4.92705s/12 iters), loss = 5.30597
I0410 02:16:42.226897 27877 solver.cpp:237]     Train net output #0: loss = 5.30597 (* 1 = 5.30597 loss)
I0410 02:16:42.226905 27877 sgd_solver.cpp:105] Iteration 2364, lr = 0.00626081
I0410 02:16:47.167587 27877 solver.cpp:218] Iteration 2376 (2.42888 iter/s, 4.94056s/12 iters), loss = 5.25978
I0410 02:16:47.167670 27877 solver.cpp:237]     Train net output #0: loss = 5.25978 (* 1 = 5.25978 loss)
I0410 02:16:47.167682 27877 sgd_solver.cpp:105] Iteration 2376, lr = 0.00624595
I0410 02:16:52.187716 27877 solver.cpp:218] Iteration 2388 (2.39048 iter/s, 5.01991s/12 iters), loss = 5.27356
I0410 02:16:52.187762 27877 solver.cpp:237]     Train net output #0: loss = 5.27356 (* 1 = 5.27356 loss)
I0410 02:16:52.187770 27877 sgd_solver.cpp:105] Iteration 2388, lr = 0.00623112
I0410 02:16:57.141429 27877 solver.cpp:218] Iteration 2400 (2.42251 iter/s, 4.95353s/12 iters), loss = 5.27812
I0410 02:16:57.141475 27877 solver.cpp:237]     Train net output #0: loss = 5.27812 (* 1 = 5.27812 loss)
I0410 02:16:57.141486 27877 sgd_solver.cpp:105] Iteration 2400, lr = 0.00621633
I0410 02:17:02.084122 27877 solver.cpp:218] Iteration 2412 (2.42791 iter/s, 4.94252s/12 iters), loss = 5.27115
I0410 02:17:02.084167 27877 solver.cpp:237]     Train net output #0: loss = 5.27115 (* 1 = 5.27115 loss)
I0410 02:17:02.084175 27877 sgd_solver.cpp:105] Iteration 2412, lr = 0.00620157
I0410 02:17:07.000422 27877 solver.cpp:218] Iteration 2424 (2.44095 iter/s, 4.91612s/12 iters), loss = 5.28057
I0410 02:17:07.000473 27877 solver.cpp:237]     Train net output #0: loss = 5.28057 (* 1 = 5.28057 loss)
I0410 02:17:07.000484 27877 sgd_solver.cpp:105] Iteration 2424, lr = 0.00618684
I0410 02:17:08.050488 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:17:11.946039 27877 solver.cpp:218] Iteration 2436 (2.42648 iter/s, 4.94544s/12 iters), loss = 5.27878
I0410 02:17:11.946082 27877 solver.cpp:237]     Train net output #0: loss = 5.27878 (* 1 = 5.27878 loss)
I0410 02:17:11.946092 27877 sgd_solver.cpp:105] Iteration 2436, lr = 0.00617215
I0410 02:17:16.368475 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2448.caffemodel
I0410 02:17:19.319615 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2448.solverstate
I0410 02:17:21.605547 27877 solver.cpp:330] Iteration 2448, Testing net (#0)
I0410 02:17:21.605581 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:17:25.268577 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:17:26.241768 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:17:26.241798 27877 solver.cpp:397]     Test net output #1: loss = 5.28646 (* 1 = 5.28646 loss)
I0410 02:17:26.324496 27877 solver.cpp:218] Iteration 2448 (0.834605 iter/s, 14.3781s/12 iters), loss = 5.25889
I0410 02:17:26.324546 27877 solver.cpp:237]     Train net output #0: loss = 5.25889 (* 1 = 5.25889 loss)
I0410 02:17:26.324558 27877 sgd_solver.cpp:105] Iteration 2448, lr = 0.0061575
I0410 02:17:30.504155 27877 solver.cpp:218] Iteration 2460 (2.87116 iter/s, 4.17949s/12 iters), loss = 5.26405
I0410 02:17:30.504207 27877 solver.cpp:237]     Train net output #0: loss = 5.26405 (* 1 = 5.26405 loss)
I0410 02:17:30.504220 27877 sgd_solver.cpp:105] Iteration 2460, lr = 0.00614288
I0410 02:17:35.449051 27877 solver.cpp:218] Iteration 2472 (2.42684 iter/s, 4.94471s/12 iters), loss = 5.27081
I0410 02:17:35.449098 27877 solver.cpp:237]     Train net output #0: loss = 5.27081 (* 1 = 5.27081 loss)
I0410 02:17:35.449108 27877 sgd_solver.cpp:105] Iteration 2472, lr = 0.0061283
I0410 02:17:40.371821 27877 solver.cpp:218] Iteration 2484 (2.43775 iter/s, 4.92258s/12 iters), loss = 5.27564
I0410 02:17:40.371874 27877 solver.cpp:237]     Train net output #0: loss = 5.27564 (* 1 = 5.27564 loss)
I0410 02:17:40.371886 27877 sgd_solver.cpp:105] Iteration 2484, lr = 0.00611375
I0410 02:17:45.311313 27877 solver.cpp:218] Iteration 2496 (2.42949 iter/s, 4.9393s/12 iters), loss = 5.27177
I0410 02:17:45.311365 27877 solver.cpp:237]     Train net output #0: loss = 5.27177 (* 1 = 5.27177 loss)
I0410 02:17:45.311376 27877 sgd_solver.cpp:105] Iteration 2496, lr = 0.00609923
I0410 02:17:50.241942 27877 solver.cpp:218] Iteration 2508 (2.43386 iter/s, 4.93044s/12 iters), loss = 5.29206
I0410 02:17:50.242053 27877 solver.cpp:237]     Train net output #0: loss = 5.29206 (* 1 = 5.29206 loss)
I0410 02:17:50.242063 27877 sgd_solver.cpp:105] Iteration 2508, lr = 0.00608475
I0410 02:17:55.306394 27877 solver.cpp:218] Iteration 2520 (2.36957 iter/s, 5.06421s/12 iters), loss = 5.2732
I0410 02:17:55.306452 27877 solver.cpp:237]     Train net output #0: loss = 5.2732 (* 1 = 5.2732 loss)
I0410 02:17:55.306463 27877 sgd_solver.cpp:105] Iteration 2520, lr = 0.0060703
I0410 02:17:58.441444 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:18:00.189154 27877 solver.cpp:218] Iteration 2532 (2.45772 iter/s, 4.88257s/12 iters), loss = 5.28305
I0410 02:18:00.189216 27877 solver.cpp:237]     Train net output #0: loss = 5.28305 (* 1 = 5.28305 loss)
I0410 02:18:00.189229 27877 sgd_solver.cpp:105] Iteration 2532, lr = 0.00605589
I0410 02:18:05.079885 27877 solver.cpp:218] Iteration 2544 (2.45372 iter/s, 4.89053s/12 iters), loss = 5.27228
I0410 02:18:05.079952 27877 solver.cpp:237]     Train net output #0: loss = 5.27228 (* 1 = 5.27228 loss)
I0410 02:18:05.079964 27877 sgd_solver.cpp:105] Iteration 2544, lr = 0.00604151
I0410 02:18:07.057126 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2550.caffemodel
I0410 02:18:08.545562 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2550.solverstate
I0410 02:18:09.486330 27877 solver.cpp:330] Iteration 2550, Testing net (#0)
I0410 02:18:09.486356 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:18:12.890646 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:18:13.913225 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:18:13.913257 27877 solver.cpp:397]     Test net output #1: loss = 5.28645 (* 1 = 5.28645 loss)
I0410 02:18:15.851812 27877 solver.cpp:218] Iteration 2556 (1.11404 iter/s, 10.7716s/12 iters), loss = 5.27671
I0410 02:18:15.851852 27877 solver.cpp:237]     Train net output #0: loss = 5.27671 (* 1 = 5.27671 loss)
I0410 02:18:15.851861 27877 sgd_solver.cpp:105] Iteration 2556, lr = 0.00602717
I0410 02:18:20.866176 27877 solver.cpp:218] Iteration 2568 (2.39321 iter/s, 5.01418s/12 iters), loss = 5.28793
I0410 02:18:20.866317 27877 solver.cpp:237]     Train net output #0: loss = 5.28793 (* 1 = 5.28793 loss)
I0410 02:18:20.866335 27877 sgd_solver.cpp:105] Iteration 2568, lr = 0.00601286
I0410 02:18:25.813802 27877 solver.cpp:218] Iteration 2580 (2.42554 iter/s, 4.94735s/12 iters), loss = 5.26943
I0410 02:18:25.813850 27877 solver.cpp:237]     Train net output #0: loss = 5.26943 (* 1 = 5.26943 loss)
I0410 02:18:25.813859 27877 sgd_solver.cpp:105] Iteration 2580, lr = 0.00599858
I0410 02:18:30.782531 27877 solver.cpp:218] Iteration 2592 (2.41519 iter/s, 4.96855s/12 iters), loss = 5.28657
I0410 02:18:30.782573 27877 solver.cpp:237]     Train net output #0: loss = 5.28657 (* 1 = 5.28657 loss)
I0410 02:18:30.782582 27877 sgd_solver.cpp:105] Iteration 2592, lr = 0.00598434
I0410 02:18:35.675737 27877 solver.cpp:218] Iteration 2604 (2.45247 iter/s, 4.89303s/12 iters), loss = 5.26192
I0410 02:18:35.675794 27877 solver.cpp:237]     Train net output #0: loss = 5.26192 (* 1 = 5.26192 loss)
I0410 02:18:35.675807 27877 sgd_solver.cpp:105] Iteration 2604, lr = 0.00597013
I0410 02:18:40.606801 27877 solver.cpp:218] Iteration 2616 (2.43365 iter/s, 4.93087s/12 iters), loss = 5.27962
I0410 02:18:40.606856 27877 solver.cpp:237]     Train net output #0: loss = 5.27962 (* 1 = 5.27962 loss)
I0410 02:18:40.606868 27877 sgd_solver.cpp:105] Iteration 2616, lr = 0.00595596
I0410 02:18:45.545354 27877 solver.cpp:218] Iteration 2628 (2.42995 iter/s, 4.93837s/12 iters), loss = 5.27561
I0410 02:18:45.545398 27877 solver.cpp:237]     Train net output #0: loss = 5.27561 (* 1 = 5.27561 loss)
I0410 02:18:45.545408 27877 sgd_solver.cpp:105] Iteration 2628, lr = 0.00594182
I0410 02:18:45.961903 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:18:50.395254 27877 solver.cpp:218] Iteration 2640 (2.47437 iter/s, 4.84972s/12 iters), loss = 5.2799
I0410 02:18:50.395303 27877 solver.cpp:237]     Train net output #0: loss = 5.2799 (* 1 = 5.2799 loss)
I0410 02:18:50.395313 27877 sgd_solver.cpp:105] Iteration 2640, lr = 0.00592771
I0410 02:18:54.870373 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2652.caffemodel
I0410 02:18:55.720360 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2652.solverstate
I0410 02:18:56.788101 27877 solver.cpp:330] Iteration 2652, Testing net (#0)
I0410 02:18:56.788130 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:19:00.335913 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:19:01.423338 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:19:01.423391 27877 solver.cpp:397]     Test net output #1: loss = 5.28673 (* 1 = 5.28673 loss)
I0410 02:19:01.506374 27877 solver.cpp:218] Iteration 2652 (1.08003 iter/s, 11.1108s/12 iters), loss = 5.27141
I0410 02:19:01.506428 27877 solver.cpp:237]     Train net output #0: loss = 5.27141 (* 1 = 5.27141 loss)
I0410 02:19:01.506440 27877 sgd_solver.cpp:105] Iteration 2652, lr = 0.00591364
I0410 02:19:05.864715 27877 solver.cpp:218] Iteration 2664 (2.75345 iter/s, 4.35816s/12 iters), loss = 5.27883
I0410 02:19:05.864758 27877 solver.cpp:237]     Train net output #0: loss = 5.27883 (* 1 = 5.27883 loss)
I0410 02:19:05.864768 27877 sgd_solver.cpp:105] Iteration 2664, lr = 0.0058996
I0410 02:19:10.713989 27877 solver.cpp:218] Iteration 2676 (2.47469 iter/s, 4.84908s/12 iters), loss = 5.27116
I0410 02:19:10.714036 27877 solver.cpp:237]     Train net output #0: loss = 5.27116 (* 1 = 5.27116 loss)
I0410 02:19:10.714046 27877 sgd_solver.cpp:105] Iteration 2676, lr = 0.00588559
I0410 02:19:15.602524 27877 solver.cpp:218] Iteration 2688 (2.45481 iter/s, 4.88835s/12 iters), loss = 5.26043
I0410 02:19:15.602572 27877 solver.cpp:237]     Train net output #0: loss = 5.26043 (* 1 = 5.26043 loss)
I0410 02:19:15.602582 27877 sgd_solver.cpp:105] Iteration 2688, lr = 0.00587162
I0410 02:19:20.535748 27877 solver.cpp:218] Iteration 2700 (2.43258 iter/s, 4.93304s/12 iters), loss = 5.2792
I0410 02:19:20.535790 27877 solver.cpp:237]     Train net output #0: loss = 5.2792 (* 1 = 5.2792 loss)
I0410 02:19:20.535799 27877 sgd_solver.cpp:105] Iteration 2700, lr = 0.00585768
I0410 02:19:25.470544 27877 solver.cpp:218] Iteration 2712 (2.4318 iter/s, 4.93462s/12 iters), loss = 5.28629
I0410 02:19:25.470691 27877 solver.cpp:237]     Train net output #0: loss = 5.28629 (* 1 = 5.28629 loss)
I0410 02:19:25.470705 27877 sgd_solver.cpp:105] Iteration 2712, lr = 0.00584377
I0410 02:19:30.416702 27877 solver.cpp:218] Iteration 2724 (2.42626 iter/s, 4.94588s/12 iters), loss = 5.25896
I0410 02:19:30.416747 27877 solver.cpp:237]     Train net output #0: loss = 5.25896 (* 1 = 5.25896 loss)
I0410 02:19:30.416755 27877 sgd_solver.cpp:105] Iteration 2724, lr = 0.0058299
I0410 02:19:33.066512 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:19:35.703119 27877 solver.cpp:218] Iteration 2736 (2.27005 iter/s, 5.28622s/12 iters), loss = 5.28273
I0410 02:19:35.703167 27877 solver.cpp:237]     Train net output #0: loss = 5.28273 (* 1 = 5.28273 loss)
I0410 02:19:35.703179 27877 sgd_solver.cpp:105] Iteration 2736, lr = 0.00581605
I0410 02:19:41.023224 27877 solver.cpp:218] Iteration 2748 (2.25568 iter/s, 5.31991s/12 iters), loss = 5.27701
I0410 02:19:41.023270 27877 solver.cpp:237]     Train net output #0: loss = 5.27701 (* 1 = 5.27701 loss)
I0410 02:19:41.023279 27877 sgd_solver.cpp:105] Iteration 2748, lr = 0.00580225
I0410 02:19:42.995193 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2754.caffemodel
I0410 02:19:46.886972 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2754.solverstate
I0410 02:19:49.651433 27877 solver.cpp:330] Iteration 2754, Testing net (#0)
I0410 02:19:49.651458 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:19:52.580070 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:19:53.019960 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:19:54.143013 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 02:19:54.143064 27877 solver.cpp:397]     Test net output #1: loss = 5.28649 (* 1 = 5.28649 loss)
I0410 02:19:55.924609 27877 solver.cpp:218] Iteration 2760 (0.805317 iter/s, 14.901s/12 iters), loss = 5.27601
I0410 02:19:55.924700 27877 solver.cpp:237]     Train net output #0: loss = 5.27601 (* 1 = 5.27601 loss)
I0410 02:19:55.924711 27877 sgd_solver.cpp:105] Iteration 2760, lr = 0.00578847
I0410 02:20:00.891434 27877 solver.cpp:218] Iteration 2772 (2.41614 iter/s, 4.9666s/12 iters), loss = 5.27621
I0410 02:20:00.891486 27877 solver.cpp:237]     Train net output #0: loss = 5.27621 (* 1 = 5.27621 loss)
I0410 02:20:00.891497 27877 sgd_solver.cpp:105] Iteration 2772, lr = 0.00577473
I0410 02:20:05.852866 27877 solver.cpp:218] Iteration 2784 (2.41875 iter/s, 4.96124s/12 iters), loss = 5.28055
I0410 02:20:05.852917 27877 solver.cpp:237]     Train net output #0: loss = 5.28055 (* 1 = 5.28055 loss)
I0410 02:20:05.852929 27877 sgd_solver.cpp:105] Iteration 2784, lr = 0.00576102
I0410 02:20:10.849164 27877 solver.cpp:218] Iteration 2796 (2.40187 iter/s, 4.99611s/12 iters), loss = 5.26885
I0410 02:20:10.849205 27877 solver.cpp:237]     Train net output #0: loss = 5.26885 (* 1 = 5.26885 loss)
I0410 02:20:10.849213 27877 sgd_solver.cpp:105] Iteration 2796, lr = 0.00574734
I0410 02:20:15.875983 27877 solver.cpp:218] Iteration 2808 (2.38728 iter/s, 5.02664s/12 iters), loss = 5.26082
I0410 02:20:15.876032 27877 solver.cpp:237]     Train net output #0: loss = 5.26082 (* 1 = 5.26082 loss)
I0410 02:20:15.876040 27877 sgd_solver.cpp:105] Iteration 2808, lr = 0.00573369
I0410 02:20:20.785219 27877 solver.cpp:218] Iteration 2820 (2.44446 iter/s, 4.90905s/12 iters), loss = 5.27914
I0410 02:20:20.785269 27877 solver.cpp:237]     Train net output #0: loss = 5.27914 (* 1 = 5.27914 loss)
I0410 02:20:20.785281 27877 sgd_solver.cpp:105] Iteration 2820, lr = 0.00572008
I0410 02:20:25.418751 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:20:25.704203 27877 solver.cpp:218] Iteration 2832 (2.43962 iter/s, 4.9188s/12 iters), loss = 5.26068
I0410 02:20:25.704248 27877 solver.cpp:237]     Train net output #0: loss = 5.26068 (* 1 = 5.26068 loss)
I0410 02:20:25.704257 27877 sgd_solver.cpp:105] Iteration 2832, lr = 0.0057065
I0410 02:20:30.668053 27877 solver.cpp:218] Iteration 2844 (2.41757 iter/s, 4.96367s/12 iters), loss = 5.26688
I0410 02:20:30.672075 27877 solver.cpp:237]     Train net output #0: loss = 5.26688 (* 1 = 5.26688 loss)
I0410 02:20:30.672088 27877 sgd_solver.cpp:105] Iteration 2844, lr = 0.00569295
I0410 02:20:35.093770 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2856.caffemodel
I0410 02:20:35.944959 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2856.solverstate
I0410 02:20:36.575531 27877 solver.cpp:330] Iteration 2856, Testing net (#0)
I0410 02:20:36.575562 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:20:39.922727 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:20:41.092068 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:20:41.092111 27877 solver.cpp:397]     Test net output #1: loss = 5.28676 (* 1 = 5.28676 loss)
I0410 02:20:41.174834 27877 solver.cpp:218] Iteration 2856 (1.14259 iter/s, 10.5025s/12 iters), loss = 5.29257
I0410 02:20:41.174885 27877 solver.cpp:237]     Train net output #0: loss = 5.29257 (* 1 = 5.29257 loss)
I0410 02:20:41.174896 27877 sgd_solver.cpp:105] Iteration 2856, lr = 0.00567944
I0410 02:20:45.373915 27877 solver.cpp:218] Iteration 2868 (2.85788 iter/s, 4.19891s/12 iters), loss = 5.28418
I0410 02:20:45.373984 27877 solver.cpp:237]     Train net output #0: loss = 5.28418 (* 1 = 5.28418 loss)
I0410 02:20:45.373996 27877 sgd_solver.cpp:105] Iteration 2868, lr = 0.00566595
I0410 02:20:50.286324 27877 solver.cpp:218] Iteration 2880 (2.44289 iter/s, 4.91221s/12 iters), loss = 5.28051
I0410 02:20:50.286367 27877 solver.cpp:237]     Train net output #0: loss = 5.28051 (* 1 = 5.28051 loss)
I0410 02:20:50.286376 27877 sgd_solver.cpp:105] Iteration 2880, lr = 0.0056525
I0410 02:20:55.208575 27877 solver.cpp:218] Iteration 2892 (2.438 iter/s, 4.92207s/12 iters), loss = 5.27251
I0410 02:20:55.208619 27877 solver.cpp:237]     Train net output #0: loss = 5.27251 (* 1 = 5.27251 loss)
I0410 02:20:55.208628 27877 sgd_solver.cpp:105] Iteration 2892, lr = 0.00563908
I0410 02:21:00.107364 27877 solver.cpp:218] Iteration 2904 (2.44967 iter/s, 4.89861s/12 iters), loss = 5.25663
I0410 02:21:00.107419 27877 solver.cpp:237]     Train net output #0: loss = 5.25663 (* 1 = 5.25663 loss)
I0410 02:21:00.107430 27877 sgd_solver.cpp:105] Iteration 2904, lr = 0.00562569
I0410 02:21:05.022313 27877 solver.cpp:218] Iteration 2916 (2.44162 iter/s, 4.91476s/12 iters), loss = 5.2718
I0410 02:21:05.022492 27877 solver.cpp:237]     Train net output #0: loss = 5.2718 (* 1 = 5.2718 loss)
I0410 02:21:05.022505 27877 sgd_solver.cpp:105] Iteration 2916, lr = 0.00561233
I0410 02:21:09.873005 27877 solver.cpp:218] Iteration 2928 (2.47403 iter/s, 4.85038s/12 iters), loss = 5.2805
I0410 02:21:09.873066 27877 solver.cpp:237]     Train net output #0: loss = 5.2805 (* 1 = 5.2805 loss)
I0410 02:21:09.873080 27877 sgd_solver.cpp:105] Iteration 2928, lr = 0.00559901
I0410 02:21:11.668093 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:21:14.758121 27877 solver.cpp:218] Iteration 2940 (2.45654 iter/s, 4.88492s/12 iters), loss = 5.28206
I0410 02:21:14.758179 27877 solver.cpp:237]     Train net output #0: loss = 5.28206 (* 1 = 5.28206 loss)
I0410 02:21:14.758190 27877 sgd_solver.cpp:105] Iteration 2940, lr = 0.00558572
I0410 02:21:19.649103 27877 solver.cpp:218] Iteration 2952 (2.45359 iter/s, 4.89079s/12 iters), loss = 5.28269
I0410 02:21:19.649160 27877 solver.cpp:237]     Train net output #0: loss = 5.28269 (* 1 = 5.28269 loss)
I0410 02:21:19.649171 27877 sgd_solver.cpp:105] Iteration 2952, lr = 0.00557245
I0410 02:21:21.621845 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_2958.caffemodel
I0410 02:21:23.934451 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_2958.solverstate
I0410 02:21:24.545308 27877 solver.cpp:330] Iteration 2958, Testing net (#0)
I0410 02:21:24.545333 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:21:27.771414 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:21:28.978540 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:21:28.978590 27877 solver.cpp:397]     Test net output #1: loss = 5.28643 (* 1 = 5.28643 loss)
I0410 02:21:30.809865 27877 solver.cpp:218] Iteration 2964 (1.07523 iter/s, 11.1604s/12 iters), loss = 5.2447
I0410 02:21:30.809914 27877 solver.cpp:237]     Train net output #0: loss = 5.2447 (* 1 = 5.2447 loss)
I0410 02:21:30.809923 27877 sgd_solver.cpp:105] Iteration 2964, lr = 0.00555922
I0410 02:21:35.769281 27877 solver.cpp:218] Iteration 2976 (2.41973 iter/s, 4.95923s/12 iters), loss = 5.2826
I0410 02:21:35.769381 27877 solver.cpp:237]     Train net output #0: loss = 5.2826 (* 1 = 5.2826 loss)
I0410 02:21:35.769390 27877 sgd_solver.cpp:105] Iteration 2976, lr = 0.00554603
I0410 02:21:40.679607 27877 solver.cpp:218] Iteration 2988 (2.44395 iter/s, 4.91009s/12 iters), loss = 5.26513
I0410 02:21:40.679657 27877 solver.cpp:237]     Train net output #0: loss = 5.26513 (* 1 = 5.26513 loss)
I0410 02:21:40.679667 27877 sgd_solver.cpp:105] Iteration 2988, lr = 0.00553286
I0410 02:21:45.546226 27877 solver.cpp:218] Iteration 3000 (2.46587 iter/s, 4.86644s/12 iters), loss = 5.27197
I0410 02:21:45.546273 27877 solver.cpp:237]     Train net output #0: loss = 5.27197 (* 1 = 5.27197 loss)
I0410 02:21:45.546284 27877 sgd_solver.cpp:105] Iteration 3000, lr = 0.00551972
I0410 02:21:50.509816 27877 solver.cpp:218] Iteration 3012 (2.41769 iter/s, 4.96341s/12 iters), loss = 5.27187
I0410 02:21:50.509867 27877 solver.cpp:237]     Train net output #0: loss = 5.27187 (* 1 = 5.27187 loss)
I0410 02:21:50.509879 27877 sgd_solver.cpp:105] Iteration 3012, lr = 0.00550662
I0410 02:21:55.601846 27877 solver.cpp:218] Iteration 3024 (2.35671 iter/s, 5.09184s/12 iters), loss = 5.26245
I0410 02:21:55.601894 27877 solver.cpp:237]     Train net output #0: loss = 5.26245 (* 1 = 5.26245 loss)
I0410 02:21:55.601903 27877 sgd_solver.cpp:105] Iteration 3024, lr = 0.00549354
I0410 02:21:59.606164 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:22:00.614097 27877 solver.cpp:218] Iteration 3036 (2.39422 iter/s, 5.01206s/12 iters), loss = 5.25772
I0410 02:22:00.614156 27877 solver.cpp:237]     Train net output #0: loss = 5.25772 (* 1 = 5.25772 loss)
I0410 02:22:00.614167 27877 sgd_solver.cpp:105] Iteration 3036, lr = 0.0054805
I0410 02:22:05.579443 27877 solver.cpp:218] Iteration 3048 (2.41684 iter/s, 4.96516s/12 iters), loss = 5.28997
I0410 02:22:05.579493 27877 solver.cpp:237]     Train net output #0: loss = 5.28997 (* 1 = 5.28997 loss)
I0410 02:22:05.579504 27877 sgd_solver.cpp:105] Iteration 3048, lr = 0.00546749
I0410 02:22:10.049150 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3060.caffemodel
I0410 02:22:11.597223 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3060.solverstate
I0410 02:22:12.913187 27877 solver.cpp:330] Iteration 3060, Testing net (#0)
I0410 02:22:12.913216 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:22:16.216043 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:22:17.563325 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 02:22:17.563376 27877 solver.cpp:397]     Test net output #1: loss = 5.28616 (* 1 = 5.28616 loss)
I0410 02:22:17.646324 27877 solver.cpp:218] Iteration 3060 (0.994487 iter/s, 12.0665s/12 iters), loss = 5.25754
I0410 02:22:17.646382 27877 solver.cpp:237]     Train net output #0: loss = 5.25754 (* 1 = 5.25754 loss)
I0410 02:22:17.646394 27877 sgd_solver.cpp:105] Iteration 3060, lr = 0.00545451
I0410 02:22:21.826874 27877 solver.cpp:218] Iteration 3072 (2.87055 iter/s, 4.18038s/12 iters), loss = 5.30422
I0410 02:22:21.826920 27877 solver.cpp:237]     Train net output #0: loss = 5.30422 (* 1 = 5.30422 loss)
I0410 02:22:21.826930 27877 sgd_solver.cpp:105] Iteration 3072, lr = 0.00544156
I0410 02:22:26.716696 27877 solver.cpp:218] Iteration 3084 (2.45417 iter/s, 4.88965s/12 iters), loss = 5.27447
I0410 02:22:26.716742 27877 solver.cpp:237]     Train net output #0: loss = 5.27447 (* 1 = 5.27447 loss)
I0410 02:22:26.716751 27877 sgd_solver.cpp:105] Iteration 3084, lr = 0.00542864
I0410 02:22:31.599475 27877 solver.cpp:218] Iteration 3096 (2.45771 iter/s, 4.8826s/12 iters), loss = 5.27376
I0410 02:22:31.599529 27877 solver.cpp:237]     Train net output #0: loss = 5.27376 (* 1 = 5.27376 loss)
I0410 02:22:31.599540 27877 sgd_solver.cpp:105] Iteration 3096, lr = 0.00541575
I0410 02:22:36.513048 27877 solver.cpp:218] Iteration 3108 (2.44231 iter/s, 4.91338s/12 iters), loss = 5.28411
I0410 02:22:36.513098 27877 solver.cpp:237]     Train net output #0: loss = 5.28411 (* 1 = 5.28411 loss)
I0410 02:22:36.513110 27877 sgd_solver.cpp:105] Iteration 3108, lr = 0.00540289
I0410 02:22:41.478821 27877 solver.cpp:218] Iteration 3120 (2.41663 iter/s, 4.96558s/12 iters), loss = 5.26448
I0410 02:22:41.478935 27877 solver.cpp:237]     Train net output #0: loss = 5.26448 (* 1 = 5.26448 loss)
I0410 02:22:41.478948 27877 sgd_solver.cpp:105] Iteration 3120, lr = 0.00539006
I0410 02:22:46.424650 27877 solver.cpp:218] Iteration 3132 (2.42641 iter/s, 4.94558s/12 iters), loss = 5.27545
I0410 02:22:46.424696 27877 solver.cpp:237]     Train net output #0: loss = 5.27545 (* 1 = 5.27545 loss)
I0410 02:22:46.424705 27877 sgd_solver.cpp:105] Iteration 3132, lr = 0.00537727
I0410 02:22:47.553838 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:22:51.506568 27877 solver.cpp:218] Iteration 3144 (2.3614 iter/s, 5.08173s/12 iters), loss = 5.28068
I0410 02:22:51.506608 27877 solver.cpp:237]     Train net output #0: loss = 5.28068 (* 1 = 5.28068 loss)
I0410 02:22:51.506618 27877 sgd_solver.cpp:105] Iteration 3144, lr = 0.0053645
I0410 02:22:56.422142 27877 solver.cpp:218] Iteration 3156 (2.44131 iter/s, 4.9154s/12 iters), loss = 5.2518
I0410 02:22:56.422194 27877 solver.cpp:237]     Train net output #0: loss = 5.2518 (* 1 = 5.2518 loss)
I0410 02:22:56.422207 27877 sgd_solver.cpp:105] Iteration 3156, lr = 0.00535176
I0410 02:22:58.383359 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3162.caffemodel
I0410 02:22:59.260974 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3162.solverstate
I0410 02:22:59.886487 27877 solver.cpp:330] Iteration 3162, Testing net (#0)
I0410 02:22:59.886515 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:23:03.076297 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:23:04.365252 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:23:04.365306 27877 solver.cpp:397]     Test net output #1: loss = 5.28626 (* 1 = 5.28626 loss)
I0410 02:23:06.313514 27877 solver.cpp:218] Iteration 3168 (1.21322 iter/s, 9.89107s/12 iters), loss = 5.26662
I0410 02:23:06.313565 27877 solver.cpp:237]     Train net output #0: loss = 5.26662 (* 1 = 5.26662 loss)
I0410 02:23:06.313575 27877 sgd_solver.cpp:105] Iteration 3168, lr = 0.00533906
I0410 02:23:11.135154 27877 solver.cpp:218] Iteration 3180 (2.48887 iter/s, 4.82146s/12 iters), loss = 5.27033
I0410 02:23:11.135210 27877 solver.cpp:237]     Train net output #0: loss = 5.27033 (* 1 = 5.27033 loss)
I0410 02:23:11.135221 27877 sgd_solver.cpp:105] Iteration 3180, lr = 0.00532638
I0410 02:23:16.050621 27877 solver.cpp:218] Iteration 3192 (2.44137 iter/s, 4.91528s/12 iters), loss = 5.27849
I0410 02:23:16.050752 27877 solver.cpp:237]     Train net output #0: loss = 5.27849 (* 1 = 5.27849 loss)
I0410 02:23:16.050762 27877 sgd_solver.cpp:105] Iteration 3192, lr = 0.00531374
I0410 02:23:21.104722 27877 solver.cpp:218] Iteration 3204 (2.37443 iter/s, 5.05383s/12 iters), loss = 5.26502
I0410 02:23:21.104773 27877 solver.cpp:237]     Train net output #0: loss = 5.26502 (* 1 = 5.26502 loss)
I0410 02:23:21.104784 27877 sgd_solver.cpp:105] Iteration 3204, lr = 0.00530112
I0410 02:23:25.970543 27877 solver.cpp:218] Iteration 3216 (2.46627 iter/s, 4.86564s/12 iters), loss = 5.28745
I0410 02:23:25.970602 27877 solver.cpp:237]     Train net output #0: loss = 5.28745 (* 1 = 5.28745 loss)
I0410 02:23:25.970613 27877 sgd_solver.cpp:105] Iteration 3216, lr = 0.00528853
I0410 02:23:30.807746 27877 solver.cpp:218] Iteration 3228 (2.48087 iter/s, 4.83701s/12 iters), loss = 5.27736
I0410 02:23:30.807808 27877 solver.cpp:237]     Train net output #0: loss = 5.27736 (* 1 = 5.27736 loss)
I0410 02:23:30.807819 27877 sgd_solver.cpp:105] Iteration 3228, lr = 0.00527598
I0410 02:23:33.955090 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:23:35.679383 27877 solver.cpp:218] Iteration 3240 (2.46334 iter/s, 4.87143s/12 iters), loss = 5.28344
I0410 02:23:35.679440 27877 solver.cpp:237]     Train net output #0: loss = 5.28344 (* 1 = 5.28344 loss)
I0410 02:23:35.679452 27877 sgd_solver.cpp:105] Iteration 3240, lr = 0.00526345
I0410 02:23:40.695466 27877 solver.cpp:218] Iteration 3252 (2.39239 iter/s, 5.01589s/12 iters), loss = 5.27051
I0410 02:23:40.695508 27877 solver.cpp:237]     Train net output #0: loss = 5.27051 (* 1 = 5.27051 loss)
I0410 02:23:40.695516 27877 sgd_solver.cpp:105] Iteration 3252, lr = 0.00525095
I0410 02:23:45.172601 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3264.caffemodel
I0410 02:23:49.051095 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3264.solverstate
I0410 02:23:51.270067 27877 solver.cpp:330] Iteration 3264, Testing net (#0)
I0410 02:23:51.270097 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:23:54.430227 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:23:55.747660 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:23:55.747697 27877 solver.cpp:397]     Test net output #1: loss = 5.28685 (* 1 = 5.28685 loss)
I0410 02:23:55.830569 27877 solver.cpp:218] Iteration 3264 (0.792881 iter/s, 15.1347s/12 iters), loss = 5.27592
I0410 02:23:55.830615 27877 solver.cpp:237]     Train net output #0: loss = 5.27592 (* 1 = 5.27592 loss)
I0410 02:23:55.830623 27877 sgd_solver.cpp:105] Iteration 3264, lr = 0.00523849
I0410 02:24:00.159199 27877 solver.cpp:218] Iteration 3276 (2.77235 iter/s, 4.32846s/12 iters), loss = 5.29053
I0410 02:24:00.159246 27877 solver.cpp:237]     Train net output #0: loss = 5.29053 (* 1 = 5.29053 loss)
I0410 02:24:00.159255 27877 sgd_solver.cpp:105] Iteration 3276, lr = 0.00522605
I0410 02:24:05.404848 27877 solver.cpp:218] Iteration 3288 (2.28769 iter/s, 5.24546s/12 iters), loss = 5.26337
I0410 02:24:05.404886 27877 solver.cpp:237]     Train net output #0: loss = 5.26337 (* 1 = 5.26337 loss)
I0410 02:24:05.404894 27877 sgd_solver.cpp:105] Iteration 3288, lr = 0.00521364
I0410 02:24:10.382728 27877 solver.cpp:218] Iteration 3300 (2.41075 iter/s, 4.9777s/12 iters), loss = 5.27969
I0410 02:24:10.382781 27877 solver.cpp:237]     Train net output #0: loss = 5.27969 (* 1 = 5.27969 loss)
I0410 02:24:10.382792 27877 sgd_solver.cpp:105] Iteration 3300, lr = 0.00520126
I0410 02:24:15.276012 27877 solver.cpp:218] Iteration 3312 (2.45244 iter/s, 4.8931s/12 iters), loss = 5.25638
I0410 02:24:15.276060 27877 solver.cpp:237]     Train net output #0: loss = 5.25638 (* 1 = 5.25638 loss)
I0410 02:24:15.276069 27877 sgd_solver.cpp:105] Iteration 3312, lr = 0.00518892
I0410 02:24:20.207717 27877 solver.cpp:218] Iteration 3324 (2.43332 iter/s, 4.93153s/12 iters), loss = 5.28545
I0410 02:24:20.207864 27877 solver.cpp:237]     Train net output #0: loss = 5.28545 (* 1 = 5.28545 loss)
I0410 02:24:20.207877 27877 sgd_solver.cpp:105] Iteration 3324, lr = 0.0051766
I0410 02:24:25.126051 27877 solver.cpp:218] Iteration 3336 (2.43999 iter/s, 4.91806s/12 iters), loss = 5.27541
I0410 02:24:25.126091 27877 solver.cpp:237]     Train net output #0: loss = 5.27541 (* 1 = 5.27541 loss)
I0410 02:24:25.126101 27877 sgd_solver.cpp:105] Iteration 3336, lr = 0.00516431
I0410 02:24:25.606380 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:24:30.068750 27877 solver.cpp:218] Iteration 3348 (2.42791 iter/s, 4.94253s/12 iters), loss = 5.27708
I0410 02:24:30.068790 27877 solver.cpp:237]     Train net output #0: loss = 5.27708 (* 1 = 5.27708 loss)
I0410 02:24:30.068799 27877 sgd_solver.cpp:105] Iteration 3348, lr = 0.00515204
I0410 02:24:34.957984 27877 solver.cpp:218] Iteration 3360 (2.45446 iter/s, 4.88905s/12 iters), loss = 5.26575
I0410 02:24:34.958024 27877 solver.cpp:237]     Train net output #0: loss = 5.26575 (* 1 = 5.26575 loss)
I0410 02:24:34.958034 27877 sgd_solver.cpp:105] Iteration 3360, lr = 0.00513981
I0410 02:24:36.930655 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3366.caffemodel
I0410 02:24:37.792824 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3366.solverstate
I0410 02:24:38.418331 27877 solver.cpp:330] Iteration 3366, Testing net (#0)
I0410 02:24:38.418357 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:24:41.451508 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:24:42.809068 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:24:42.809113 27877 solver.cpp:397]     Test net output #1: loss = 5.28652 (* 1 = 5.28652 loss)
I0410 02:24:44.598889 27877 solver.cpp:218] Iteration 3372 (1.24473 iter/s, 9.64061s/12 iters), loss = 5.28598
I0410 02:24:44.598954 27877 solver.cpp:237]     Train net output #0: loss = 5.28598 (* 1 = 5.28598 loss)
I0410 02:24:44.598966 27877 sgd_solver.cpp:105] Iteration 3372, lr = 0.00512761
I0410 02:24:49.415225 27877 solver.cpp:218] Iteration 3384 (2.49162 iter/s, 4.81614s/12 iters), loss = 5.26663
I0410 02:24:49.415279 27877 solver.cpp:237]     Train net output #0: loss = 5.26663 (* 1 = 5.26663 loss)
I0410 02:24:49.415292 27877 sgd_solver.cpp:105] Iteration 3384, lr = 0.00511544
I0410 02:24:54.297243 27877 solver.cpp:218] Iteration 3396 (2.4581 iter/s, 4.88182s/12 iters), loss = 5.26234
I0410 02:24:54.297364 27877 solver.cpp:237]     Train net output #0: loss = 5.26234 (* 1 = 5.26234 loss)
I0410 02:24:54.297379 27877 sgd_solver.cpp:105] Iteration 3396, lr = 0.00510329
I0410 02:24:59.209504 27877 solver.cpp:218] Iteration 3408 (2.44299 iter/s, 4.91202s/12 iters), loss = 5.2893
I0410 02:24:59.209550 27877 solver.cpp:237]     Train net output #0: loss = 5.2893 (* 1 = 5.2893 loss)
I0410 02:24:59.209563 27877 sgd_solver.cpp:105] Iteration 3408, lr = 0.00509117
I0410 02:25:04.247674 27877 solver.cpp:218] Iteration 3420 (2.3819 iter/s, 5.03799s/12 iters), loss = 5.28056
I0410 02:25:04.247732 27877 solver.cpp:237]     Train net output #0: loss = 5.28056 (* 1 = 5.28056 loss)
I0410 02:25:04.247745 27877 sgd_solver.cpp:105] Iteration 3420, lr = 0.00507909
I0410 02:25:09.167657 27877 solver.cpp:218] Iteration 3432 (2.43913 iter/s, 4.9198s/12 iters), loss = 5.26201
I0410 02:25:09.167707 27877 solver.cpp:237]     Train net output #0: loss = 5.26201 (* 1 = 5.26201 loss)
I0410 02:25:09.167718 27877 sgd_solver.cpp:105] Iteration 3432, lr = 0.00506703
I0410 02:25:11.688763 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:25:14.051062 27877 solver.cpp:218] Iteration 3444 (2.45739 iter/s, 4.88323s/12 iters), loss = 5.27234
I0410 02:25:14.051110 27877 solver.cpp:237]     Train net output #0: loss = 5.27234 (* 1 = 5.27234 loss)
I0410 02:25:14.051120 27877 sgd_solver.cpp:105] Iteration 3444, lr = 0.005055
I0410 02:25:18.982024 27877 solver.cpp:218] Iteration 3456 (2.43369 iter/s, 4.93078s/12 iters), loss = 5.26868
I0410 02:25:18.982076 27877 solver.cpp:237]     Train net output #0: loss = 5.26868 (* 1 = 5.26868 loss)
I0410 02:25:18.982090 27877 sgd_solver.cpp:105] Iteration 3456, lr = 0.005043
I0410 02:25:23.463260 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3468.caffemodel
I0410 02:25:24.295634 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3468.solverstate
I0410 02:25:24.922825 27877 solver.cpp:330] Iteration 3468, Testing net (#0)
I0410 02:25:24.922924 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:25:25.149909 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:25:27.939728 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:25:29.353188 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:25:29.353217 27877 solver.cpp:397]     Test net output #1: loss = 5.28676 (* 1 = 5.28676 loss)
I0410 02:25:29.437047 27877 solver.cpp:218] Iteration 3468 (1.14781 iter/s, 10.4547s/12 iters), loss = 5.27146
I0410 02:25:29.437093 27877 solver.cpp:237]     Train net output #0: loss = 5.27146 (* 1 = 5.27146 loss)
I0410 02:25:29.437101 27877 sgd_solver.cpp:105] Iteration 3468, lr = 0.00503102
I0410 02:25:33.702162 27877 solver.cpp:218] Iteration 3480 (2.81363 iter/s, 4.26495s/12 iters), loss = 5.27719
I0410 02:25:33.702211 27877 solver.cpp:237]     Train net output #0: loss = 5.27719 (* 1 = 5.27719 loss)
I0410 02:25:33.702221 27877 sgd_solver.cpp:105] Iteration 3480, lr = 0.00501908
I0410 02:25:38.685474 27877 solver.cpp:218] Iteration 3492 (2.40813 iter/s, 4.98313s/12 iters), loss = 5.28775
I0410 02:25:38.685519 27877 solver.cpp:237]     Train net output #0: loss = 5.28775 (* 1 = 5.28775 loss)
I0410 02:25:38.685529 27877 sgd_solver.cpp:105] Iteration 3492, lr = 0.00500716
I0410 02:25:43.573345 27877 solver.cpp:218] Iteration 3504 (2.45515 iter/s, 4.88769s/12 iters), loss = 5.27255
I0410 02:25:43.573405 27877 solver.cpp:237]     Train net output #0: loss = 5.27255 (* 1 = 5.27255 loss)
I0410 02:25:43.573416 27877 sgd_solver.cpp:105] Iteration 3504, lr = 0.00499527
I0410 02:25:48.556402 27877 solver.cpp:218] Iteration 3516 (2.40825 iter/s, 4.98286s/12 iters), loss = 5.26618
I0410 02:25:48.556452 27877 solver.cpp:237]     Train net output #0: loss = 5.26618 (* 1 = 5.26618 loss)
I0410 02:25:48.556460 27877 sgd_solver.cpp:105] Iteration 3516, lr = 0.00498341
I0410 02:25:53.605206 27877 solver.cpp:218] Iteration 3528 (2.37689 iter/s, 5.04862s/12 iters), loss = 5.27253
I0410 02:25:53.605263 27877 solver.cpp:237]     Train net output #0: loss = 5.27253 (* 1 = 5.27253 loss)
I0410 02:25:53.605275 27877 sgd_solver.cpp:105] Iteration 3528, lr = 0.00497158
I0410 02:25:58.305255 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:25:58.569248 27877 solver.cpp:218] Iteration 3540 (2.41748 iter/s, 4.96385s/12 iters), loss = 5.25566
I0410 02:25:58.569301 27877 solver.cpp:237]     Train net output #0: loss = 5.25566 (* 1 = 5.25566 loss)
I0410 02:25:58.569311 27877 sgd_solver.cpp:105] Iteration 3540, lr = 0.00495978
I0410 02:26:03.402895 27877 solver.cpp:218] Iteration 3552 (2.48269 iter/s, 4.83346s/12 iters), loss = 5.26584
I0410 02:26:03.402943 27877 solver.cpp:237]     Train net output #0: loss = 5.26584 (* 1 = 5.26584 loss)
I0410 02:26:03.402952 27877 sgd_solver.cpp:105] Iteration 3552, lr = 0.004948
I0410 02:26:08.334916 27877 solver.cpp:218] Iteration 3564 (2.43317 iter/s, 4.93184s/12 iters), loss = 5.29325
I0410 02:26:08.334962 27877 solver.cpp:237]     Train net output #0: loss = 5.29325 (* 1 = 5.29325 loss)
I0410 02:26:08.334972 27877 sgd_solver.cpp:105] Iteration 3564, lr = 0.00493626
I0410 02:26:10.317018 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3570.caffemodel
I0410 02:26:11.854795 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3570.solverstate
I0410 02:26:13.211097 27877 solver.cpp:330] Iteration 3570, Testing net (#0)
I0410 02:26:13.211127 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:26:16.246428 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:26:17.656031 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:26:17.656066 27877 solver.cpp:397]     Test net output #1: loss = 5.28669 (* 1 = 5.28669 loss)
I0410 02:26:19.366794 27877 solver.cpp:218] Iteration 3576 (1.08779 iter/s, 11.0316s/12 iters), loss = 5.28011
I0410 02:26:19.366842 27877 solver.cpp:237]     Train net output #0: loss = 5.28011 (* 1 = 5.28011 loss)
I0410 02:26:19.366850 27877 sgd_solver.cpp:105] Iteration 3576, lr = 0.00492454
I0410 02:26:24.305117 27877 solver.cpp:218] Iteration 3588 (2.43006 iter/s, 4.93814s/12 iters), loss = 5.27676
I0410 02:26:24.305164 27877 solver.cpp:237]     Train net output #0: loss = 5.27676 (* 1 = 5.27676 loss)
I0410 02:26:24.305174 27877 sgd_solver.cpp:105] Iteration 3588, lr = 0.00491284
I0410 02:26:29.219722 27877 solver.cpp:218] Iteration 3600 (2.44179 iter/s, 4.91442s/12 iters), loss = 5.26609
I0410 02:26:29.219858 27877 solver.cpp:237]     Train net output #0: loss = 5.26609 (* 1 = 5.26609 loss)
I0410 02:26:29.219871 27877 sgd_solver.cpp:105] Iteration 3600, lr = 0.00490118
I0410 02:26:34.176815 27877 solver.cpp:218] Iteration 3612 (2.4209 iter/s, 4.95683s/12 iters), loss = 5.24433
I0410 02:26:34.176856 27877 solver.cpp:237]     Train net output #0: loss = 5.24433 (* 1 = 5.24433 loss)
I0410 02:26:34.176864 27877 sgd_solver.cpp:105] Iteration 3612, lr = 0.00488954
I0410 02:26:39.162904 27877 solver.cpp:218] Iteration 3624 (2.40678 iter/s, 4.98591s/12 iters), loss = 5.27759
I0410 02:26:39.162963 27877 solver.cpp:237]     Train net output #0: loss = 5.27759 (* 1 = 5.27759 loss)
I0410 02:26:39.162976 27877 sgd_solver.cpp:105] Iteration 3624, lr = 0.00487793
I0410 02:26:44.277323 27877 solver.cpp:218] Iteration 3636 (2.3464 iter/s, 5.11423s/12 iters), loss = 5.27756
I0410 02:26:44.277374 27877 solver.cpp:237]     Train net output #0: loss = 5.27756 (* 1 = 5.27756 loss)
I0410 02:26:44.277385 27877 sgd_solver.cpp:105] Iteration 3636, lr = 0.00486635
I0410 02:26:46.152705 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:26:49.272362 27877 solver.cpp:218] Iteration 3648 (2.40247 iter/s, 4.99485s/12 iters), loss = 5.28435
I0410 02:26:49.272418 27877 solver.cpp:237]     Train net output #0: loss = 5.28435 (* 1 = 5.28435 loss)
I0410 02:26:49.272430 27877 sgd_solver.cpp:105] Iteration 3648, lr = 0.0048548
I0410 02:26:54.245946 27877 solver.cpp:218] Iteration 3660 (2.41284 iter/s, 4.9734s/12 iters), loss = 5.27923
I0410 02:26:54.246008 27877 solver.cpp:237]     Train net output #0: loss = 5.27923 (* 1 = 5.27923 loss)
I0410 02:26:54.246018 27877 sgd_solver.cpp:105] Iteration 3660, lr = 0.00484327
I0410 02:26:58.771286 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3672.caffemodel
I0410 02:27:00.698758 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3672.solverstate
I0410 02:27:01.323994 27877 solver.cpp:330] Iteration 3672, Testing net (#0)
I0410 02:27:01.324026 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:27:04.461397 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:27:05.938645 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:27:05.938694 27877 solver.cpp:397]     Test net output #1: loss = 5.28603 (* 1 = 5.28603 loss)
I0410 02:27:06.021782 27877 solver.cpp:218] Iteration 3672 (1.01907 iter/s, 11.7755s/12 iters), loss = 5.254
I0410 02:27:06.021834 27877 solver.cpp:237]     Train net output #0: loss = 5.254 (* 1 = 5.254 loss)
I0410 02:27:06.021845 27877 sgd_solver.cpp:105] Iteration 3672, lr = 0.00483177
I0410 02:27:10.338472 27877 solver.cpp:218] Iteration 3684 (2.78001 iter/s, 4.31652s/12 iters), loss = 5.27205
I0410 02:27:10.338522 27877 solver.cpp:237]     Train net output #0: loss = 5.27205 (* 1 = 5.27205 loss)
I0410 02:27:10.338534 27877 sgd_solver.cpp:105] Iteration 3684, lr = 0.0048203
I0410 02:27:15.272812 27877 solver.cpp:218] Iteration 3696 (2.43203 iter/s, 4.93415s/12 iters), loss = 5.26313
I0410 02:27:15.272864 27877 solver.cpp:237]     Train net output #0: loss = 5.26313 (* 1 = 5.26313 loss)
I0410 02:27:15.272876 27877 sgd_solver.cpp:105] Iteration 3696, lr = 0.00480886
I0410 02:27:20.366816 27877 solver.cpp:218] Iteration 3708 (2.3558 iter/s, 5.09381s/12 iters), loss = 5.26942
I0410 02:27:20.366873 27877 solver.cpp:237]     Train net output #0: loss = 5.26942 (* 1 = 5.26942 loss)
I0410 02:27:20.366884 27877 sgd_solver.cpp:105] Iteration 3708, lr = 0.00479744
I0410 02:27:25.324671 27877 solver.cpp:218] Iteration 3720 (2.42049 iter/s, 4.95766s/12 iters), loss = 5.26949
I0410 02:27:25.324719 27877 solver.cpp:237]     Train net output #0: loss = 5.26949 (* 1 = 5.26949 loss)
I0410 02:27:25.324728 27877 sgd_solver.cpp:105] Iteration 3720, lr = 0.00478605
I0410 02:27:30.259680 27877 solver.cpp:218] Iteration 3732 (2.4317 iter/s, 4.93482s/12 iters), loss = 5.25591
I0410 02:27:30.259732 27877 solver.cpp:237]     Train net output #0: loss = 5.25591 (* 1 = 5.25591 loss)
I0410 02:27:30.259743 27877 sgd_solver.cpp:105] Iteration 3732, lr = 0.00477469
I0410 02:27:34.173357 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:27:35.145299 27877 solver.cpp:218] Iteration 3744 (2.45628 iter/s, 4.88544s/12 iters), loss = 5.25655
I0410 02:27:35.145345 27877 solver.cpp:237]     Train net output #0: loss = 5.25655 (* 1 = 5.25655 loss)
I0410 02:27:35.145354 27877 sgd_solver.cpp:105] Iteration 3744, lr = 0.00476335
I0410 02:27:40.079516 27877 solver.cpp:218] Iteration 3756 (2.43209 iter/s, 4.93404s/12 iters), loss = 5.28249
I0410 02:27:40.079563 27877 solver.cpp:237]     Train net output #0: loss = 5.28249 (* 1 = 5.28249 loss)
I0410 02:27:40.079576 27877 sgd_solver.cpp:105] Iteration 3756, lr = 0.00475204
I0410 02:27:44.971014 27877 solver.cpp:218] Iteration 3768 (2.45333 iter/s, 4.89131s/12 iters), loss = 5.25794
I0410 02:27:44.971066 27877 solver.cpp:237]     Train net output #0: loss = 5.25794 (* 1 = 5.25794 loss)
I0410 02:27:44.971077 27877 sgd_solver.cpp:105] Iteration 3768, lr = 0.00474076
I0410 02:27:46.944902 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3774.caffemodel
I0410 02:27:48.496778 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3774.solverstate
I0410 02:27:49.546746 27877 solver.cpp:330] Iteration 3774, Testing net (#0)
I0410 02:27:49.546766 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:27:52.481593 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:27:53.982400 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:27:53.982450 27877 solver.cpp:397]     Test net output #1: loss = 5.28697 (* 1 = 5.28697 loss)
I0410 02:27:55.873081 27877 solver.cpp:218] Iteration 3780 (1.10074 iter/s, 10.9017s/12 iters), loss = 5.30564
I0410 02:27:55.873128 27877 solver.cpp:237]     Train net output #0: loss = 5.30564 (* 1 = 5.30564 loss)
I0410 02:27:55.873137 27877 sgd_solver.cpp:105] Iteration 3780, lr = 0.00472951
I0410 02:28:00.769071 27877 solver.cpp:218] Iteration 3792 (2.45108 iter/s, 4.89581s/12 iters), loss = 5.27815
I0410 02:28:00.769122 27877 solver.cpp:237]     Train net output #0: loss = 5.27815 (* 1 = 5.27815 loss)
I0410 02:28:00.769131 27877 sgd_solver.cpp:105] Iteration 3792, lr = 0.00471828
I0410 02:28:05.725764 27877 solver.cpp:218] Iteration 3804 (2.42106 iter/s, 4.95651s/12 iters), loss = 5.27015
I0410 02:28:05.725885 27877 solver.cpp:237]     Train net output #0: loss = 5.27015 (* 1 = 5.27015 loss)
I0410 02:28:05.725896 27877 sgd_solver.cpp:105] Iteration 3804, lr = 0.00470707
I0410 02:28:10.705423 27877 solver.cpp:218] Iteration 3816 (2.40993 iter/s, 4.9794s/12 iters), loss = 5.27148
I0410 02:28:10.705467 27877 solver.cpp:237]     Train net output #0: loss = 5.27148 (* 1 = 5.27148 loss)
I0410 02:28:10.705476 27877 sgd_solver.cpp:105] Iteration 3816, lr = 0.0046959
I0410 02:28:15.935175 27877 solver.cpp:218] Iteration 3828 (2.29464 iter/s, 5.22957s/12 iters), loss = 5.26494
I0410 02:28:15.935220 27877 solver.cpp:237]     Train net output #0: loss = 5.26494 (* 1 = 5.26494 loss)
I0410 02:28:15.935227 27877 sgd_solver.cpp:105] Iteration 3828, lr = 0.00468475
I0410 02:28:20.974783 27877 solver.cpp:218] Iteration 3840 (2.38123 iter/s, 5.03942s/12 iters), loss = 5.27087
I0410 02:28:20.974825 27877 solver.cpp:237]     Train net output #0: loss = 5.27087 (* 1 = 5.27087 loss)
I0410 02:28:20.974834 27877 sgd_solver.cpp:105] Iteration 3840, lr = 0.00467363
I0410 02:28:22.126927 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:28:25.918987 27877 solver.cpp:218] Iteration 3852 (2.42717 iter/s, 4.94403s/12 iters), loss = 5.27617
I0410 02:28:25.919034 27877 solver.cpp:237]     Train net output #0: loss = 5.27617 (* 1 = 5.27617 loss)
I0410 02:28:25.919044 27877 sgd_solver.cpp:105] Iteration 3852, lr = 0.00466253
I0410 02:28:30.900359 27877 solver.cpp:218] Iteration 3864 (2.40906 iter/s, 4.98119s/12 iters), loss = 5.25205
I0410 02:28:30.900408 27877 solver.cpp:237]     Train net output #0: loss = 5.25205 (* 1 = 5.25205 loss)
I0410 02:28:30.900418 27877 sgd_solver.cpp:105] Iteration 3864, lr = 0.00465146
I0410 02:28:35.373862 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3876.caffemodel
I0410 02:28:36.199604 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3876.solverstate
I0410 02:28:36.838311 27877 solver.cpp:330] Iteration 3876, Testing net (#0)
I0410 02:28:36.838338 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:28:39.655830 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:28:41.198662 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:28:41.198696 27877 solver.cpp:397]     Test net output #1: loss = 5.28646 (* 1 = 5.28646 loss)
I0410 02:28:41.280742 27877 solver.cpp:218] Iteration 3876 (1.15606 iter/s, 10.3801s/12 iters), loss = 5.27227
I0410 02:28:41.280795 27877 solver.cpp:237]     Train net output #0: loss = 5.27227 (* 1 = 5.27227 loss)
I0410 02:28:41.280807 27877 sgd_solver.cpp:105] Iteration 3876, lr = 0.00464042
I0410 02:28:45.533043 27877 solver.cpp:218] Iteration 3888 (2.82211 iter/s, 4.25213s/12 iters), loss = 5.26871
I0410 02:28:45.533092 27877 solver.cpp:237]     Train net output #0: loss = 5.26871 (* 1 = 5.26871 loss)
I0410 02:28:45.533104 27877 sgd_solver.cpp:105] Iteration 3888, lr = 0.0046294
I0410 02:28:50.765141 27877 solver.cpp:218] Iteration 3900 (2.29362 iter/s, 5.23191s/12 iters), loss = 5.27171
I0410 02:28:50.765192 27877 solver.cpp:237]     Train net output #0: loss = 5.27171 (* 1 = 5.27171 loss)
I0410 02:28:50.765204 27877 sgd_solver.cpp:105] Iteration 3900, lr = 0.00461841
I0410 02:28:55.869083 27877 solver.cpp:218] Iteration 3912 (2.35121 iter/s, 5.10375s/12 iters), loss = 5.26003
I0410 02:28:55.869134 27877 solver.cpp:237]     Train net output #0: loss = 5.26003 (* 1 = 5.26003 loss)
I0410 02:28:55.869143 27877 sgd_solver.cpp:105] Iteration 3912, lr = 0.00460744
I0410 02:29:01.157147 27877 solver.cpp:218] Iteration 3924 (2.26934 iter/s, 5.28787s/12 iters), loss = 5.29161
I0410 02:29:01.157199 27877 solver.cpp:237]     Train net output #0: loss = 5.29161 (* 1 = 5.29161 loss)
I0410 02:29:01.157212 27877 sgd_solver.cpp:105] Iteration 3924, lr = 0.0045965
I0410 02:29:06.082237 27877 solver.cpp:218] Iteration 3936 (2.43659 iter/s, 4.92491s/12 iters), loss = 5.27294
I0410 02:29:06.082298 27877 solver.cpp:237]     Train net output #0: loss = 5.27294 (* 1 = 5.27294 loss)
I0410 02:29:06.082310 27877 sgd_solver.cpp:105] Iteration 3936, lr = 0.00458559
I0410 02:29:09.516079 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:29:11.150117 27877 solver.cpp:218] Iteration 3948 (2.36794 iter/s, 5.06769s/12 iters), loss = 5.28603
I0410 02:29:11.150171 27877 solver.cpp:237]     Train net output #0: loss = 5.28603 (* 1 = 5.28603 loss)
I0410 02:29:11.150182 27877 sgd_solver.cpp:105] Iteration 3948, lr = 0.0045747
I0410 02:29:16.104219 27877 solver.cpp:218] Iteration 3960 (2.42233 iter/s, 4.95392s/12 iters), loss = 5.26956
I0410 02:29:16.104264 27877 solver.cpp:237]     Train net output #0: loss = 5.26956 (* 1 = 5.26956 loss)
I0410 02:29:16.104271 27877 sgd_solver.cpp:105] Iteration 3960, lr = 0.00456384
I0410 02:29:21.023916 27877 solver.cpp:218] Iteration 3972 (2.43926 iter/s, 4.91952s/12 iters), loss = 5.27797
I0410 02:29:21.023972 27877 solver.cpp:237]     Train net output #0: loss = 5.27797 (* 1 = 5.27797 loss)
I0410 02:29:21.023983 27877 sgd_solver.cpp:105] Iteration 3972, lr = 0.00455301
I0410 02:29:23.032388 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_3978.caffemodel
I0410 02:29:23.897286 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_3978.solverstate
I0410 02:29:24.523967 27877 solver.cpp:330] Iteration 3978, Testing net (#0)
I0410 02:29:24.523994 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:29:27.442296 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:29:29.064121 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:29:29.064157 27877 solver.cpp:397]     Test net output #1: loss = 5.28632 (* 1 = 5.28632 loss)
I0410 02:29:30.850767 27877 solver.cpp:218] Iteration 3984 (1.22118 iter/s, 9.82654s/12 iters), loss = 5.27969
I0410 02:29:30.850823 27877 solver.cpp:237]     Train net output #0: loss = 5.27969 (* 1 = 5.27969 loss)
I0410 02:29:30.850838 27877 sgd_solver.cpp:105] Iteration 3984, lr = 0.0045422
I0410 02:29:35.794693 27877 solver.cpp:218] Iteration 3996 (2.42731 iter/s, 4.94374s/12 iters), loss = 5.26401
I0410 02:29:35.794732 27877 solver.cpp:237]     Train net output #0: loss = 5.26401 (* 1 = 5.26401 loss)
I0410 02:29:35.794740 27877 sgd_solver.cpp:105] Iteration 3996, lr = 0.00453141
I0410 02:29:40.836163 27877 solver.cpp:218] Iteration 4008 (2.38034 iter/s, 5.04129s/12 iters), loss = 5.28771
I0410 02:29:40.836259 27877 solver.cpp:237]     Train net output #0: loss = 5.28771 (* 1 = 5.28771 loss)
I0410 02:29:40.836268 27877 sgd_solver.cpp:105] Iteration 4008, lr = 0.00452066
I0410 02:29:45.849859 27877 solver.cpp:218] Iteration 4020 (2.39356 iter/s, 5.01346s/12 iters), loss = 5.25687
I0410 02:29:45.849900 27877 solver.cpp:237]     Train net output #0: loss = 5.25687 (* 1 = 5.25687 loss)
I0410 02:29:45.849908 27877 sgd_solver.cpp:105] Iteration 4020, lr = 0.00450992
I0410 02:29:50.800761 27877 solver.cpp:218] Iteration 4032 (2.42389 iter/s, 4.95073s/12 iters), loss = 5.27161
I0410 02:29:50.800809 27877 solver.cpp:237]     Train net output #0: loss = 5.27161 (* 1 = 5.27161 loss)
I0410 02:29:50.800818 27877 sgd_solver.cpp:105] Iteration 4032, lr = 0.00449921
I0410 02:29:55.810432 27877 solver.cpp:218] Iteration 4044 (2.39546 iter/s, 5.00948s/12 iters), loss = 5.27324
I0410 02:29:55.810484 27877 solver.cpp:237]     Train net output #0: loss = 5.27324 (* 1 = 5.27324 loss)
I0410 02:29:55.810495 27877 sgd_solver.cpp:105] Iteration 4044, lr = 0.00448853
I0410 02:29:56.315907 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:30:00.790263 27877 solver.cpp:218] Iteration 4056 (2.40981 iter/s, 4.97965s/12 iters), loss = 5.27505
I0410 02:30:00.790309 27877 solver.cpp:237]     Train net output #0: loss = 5.27505 (* 1 = 5.27505 loss)
I0410 02:30:00.790321 27877 sgd_solver.cpp:105] Iteration 4056, lr = 0.00447788
I0410 02:30:05.851121 27877 solver.cpp:218] Iteration 4068 (2.37122 iter/s, 5.06068s/12 iters), loss = 5.27389
I0410 02:30:05.851171 27877 solver.cpp:237]     Train net output #0: loss = 5.27389 (* 1 = 5.27389 loss)
I0410 02:30:05.851182 27877 sgd_solver.cpp:105] Iteration 4068, lr = 0.00446724
I0410 02:30:10.325642 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4080.caffemodel
I0410 02:30:11.950088 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4080.solverstate
I0410 02:30:13.244912 27877 solver.cpp:330] Iteration 4080, Testing net (#0)
I0410 02:30:13.244940 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:30:16.095484 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:30:17.760030 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:30:17.760082 27877 solver.cpp:397]     Test net output #1: loss = 5.28684 (* 1 = 5.28684 loss)
I0410 02:30:17.843187 27877 solver.cpp:218] Iteration 4080 (1.00069 iter/s, 11.9917s/12 iters), loss = 5.2874
I0410 02:30:17.843238 27877 solver.cpp:237]     Train net output #0: loss = 5.2874 (* 1 = 5.2874 loss)
I0410 02:30:17.843250 27877 sgd_solver.cpp:105] Iteration 4080, lr = 0.00445664
I0410 02:30:21.887953 27877 solver.cpp:218] Iteration 4092 (2.96692 iter/s, 4.0446s/12 iters), loss = 5.26585
I0410 02:30:21.887991 27877 solver.cpp:237]     Train net output #0: loss = 5.26585 (* 1 = 5.26585 loss)
I0410 02:30:21.888000 27877 sgd_solver.cpp:105] Iteration 4092, lr = 0.00444606
I0410 02:30:26.783991 27877 solver.cpp:218] Iteration 4104 (2.45105 iter/s, 4.89586s/12 iters), loss = 5.2622
I0410 02:30:26.784037 27877 solver.cpp:237]     Train net output #0: loss = 5.2622 (* 1 = 5.2622 loss)
I0410 02:30:26.784046 27877 sgd_solver.cpp:105] Iteration 4104, lr = 0.0044355
I0410 02:30:31.701041 27877 solver.cpp:218] Iteration 4116 (2.44058 iter/s, 4.91687s/12 iters), loss = 5.29478
I0410 02:30:31.701087 27877 solver.cpp:237]     Train net output #0: loss = 5.29478 (* 1 = 5.29478 loss)
I0410 02:30:31.701097 27877 sgd_solver.cpp:105] Iteration 4116, lr = 0.00442497
I0410 02:30:36.634021 27877 solver.cpp:218] Iteration 4128 (2.4327 iter/s, 4.93279s/12 iters), loss = 5.26784
I0410 02:30:36.634073 27877 solver.cpp:237]     Train net output #0: loss = 5.26784 (* 1 = 5.26784 loss)
I0410 02:30:36.634085 27877 sgd_solver.cpp:105] Iteration 4128, lr = 0.00441447
I0410 02:30:41.568444 27877 solver.cpp:218] Iteration 4140 (2.43199 iter/s, 4.93424s/12 iters), loss = 5.26324
I0410 02:30:41.568495 27877 solver.cpp:237]     Train net output #0: loss = 5.26324 (* 1 = 5.26324 loss)
I0410 02:30:41.568504 27877 sgd_solver.cpp:105] Iteration 4140, lr = 0.00440398
I0410 02:30:44.131462 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:30:46.450901 27877 solver.cpp:218] Iteration 4152 (2.45787 iter/s, 4.88228s/12 iters), loss = 5.272
I0410 02:30:46.450949 27877 solver.cpp:237]     Train net output #0: loss = 5.272 (* 1 = 5.272 loss)
I0410 02:30:46.450960 27877 sgd_solver.cpp:105] Iteration 4152, lr = 0.00439353
I0410 02:30:47.226306 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:30:51.402645 27877 solver.cpp:218] Iteration 4164 (2.42348 iter/s, 4.95156s/12 iters), loss = 5.26597
I0410 02:30:51.402701 27877 solver.cpp:237]     Train net output #0: loss = 5.26597 (* 1 = 5.26597 loss)
I0410 02:30:51.402712 27877 sgd_solver.cpp:105] Iteration 4164, lr = 0.0043831
I0410 02:30:56.299175 27877 solver.cpp:218] Iteration 4176 (2.45081 iter/s, 4.89634s/12 iters), loss = 5.26603
I0410 02:30:56.299224 27877 solver.cpp:237]     Train net output #0: loss = 5.26603 (* 1 = 5.26603 loss)
I0410 02:30:56.299235 27877 sgd_solver.cpp:105] Iteration 4176, lr = 0.00437269
I0410 02:30:58.357252 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4182.caffemodel
I0410 02:30:59.673977 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4182.solverstate
I0410 02:31:00.784866 27877 solver.cpp:330] Iteration 4182, Testing net (#0)
I0410 02:31:00.784888 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:31:03.567055 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:31:05.265975 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 02:31:05.266036 27877 solver.cpp:397]     Test net output #1: loss = 5.28643 (* 1 = 5.28643 loss)
I0410 02:31:07.117894 27877 solver.cpp:218] Iteration 4188 (1.10922 iter/s, 10.8184s/12 iters), loss = 5.26873
I0410 02:31:07.117949 27877 solver.cpp:237]     Train net output #0: loss = 5.26873 (* 1 = 5.26873 loss)
I0410 02:31:07.117981 27877 sgd_solver.cpp:105] Iteration 4188, lr = 0.00436231
I0410 02:31:12.062652 27877 solver.cpp:218] Iteration 4200 (2.4269 iter/s, 4.94457s/12 iters), loss = 5.28386
I0410 02:31:12.062700 27877 solver.cpp:237]     Train net output #0: loss = 5.28386 (* 1 = 5.28386 loss)
I0410 02:31:12.062708 27877 sgd_solver.cpp:105] Iteration 4200, lr = 0.00435195
I0410 02:31:16.950767 27877 solver.cpp:218] Iteration 4212 (2.45503 iter/s, 4.88793s/12 iters), loss = 5.27501
I0410 02:31:16.950932 27877 solver.cpp:237]     Train net output #0: loss = 5.27501 (* 1 = 5.27501 loss)
I0410 02:31:16.950949 27877 sgd_solver.cpp:105] Iteration 4212, lr = 0.00434162
I0410 02:31:22.050912 27877 solver.cpp:218] Iteration 4224 (2.35301 iter/s, 5.09985s/12 iters), loss = 5.26223
I0410 02:31:22.050968 27877 solver.cpp:237]     Train net output #0: loss = 5.26223 (* 1 = 5.26223 loss)
I0410 02:31:22.050981 27877 sgd_solver.cpp:105] Iteration 4224, lr = 0.00433131
I0410 02:31:26.979279 27877 solver.cpp:218] Iteration 4236 (2.43498 iter/s, 4.92818s/12 iters), loss = 5.27038
I0410 02:31:26.979326 27877 solver.cpp:237]     Train net output #0: loss = 5.27038 (* 1 = 5.27038 loss)
I0410 02:31:26.979336 27877 sgd_solver.cpp:105] Iteration 4236, lr = 0.00432103
I0410 02:31:31.687734 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:31:31.915119 27877 solver.cpp:218] Iteration 4248 (2.43129 iter/s, 4.93565s/12 iters), loss = 5.24493
I0410 02:31:31.915175 27877 solver.cpp:237]     Train net output #0: loss = 5.24493 (* 1 = 5.24493 loss)
I0410 02:31:31.915187 27877 sgd_solver.cpp:105] Iteration 4248, lr = 0.00431077
I0410 02:31:36.835675 27877 solver.cpp:218] Iteration 4260 (2.43884 iter/s, 4.92037s/12 iters), loss = 5.26718
I0410 02:31:36.835722 27877 solver.cpp:237]     Train net output #0: loss = 5.26718 (* 1 = 5.26718 loss)
I0410 02:31:36.835733 27877 sgd_solver.cpp:105] Iteration 4260, lr = 0.00430053
I0410 02:31:41.744186 27877 solver.cpp:218] Iteration 4272 (2.44483 iter/s, 4.90833s/12 iters), loss = 5.29295
I0410 02:31:41.744235 27877 solver.cpp:237]     Train net output #0: loss = 5.29295 (* 1 = 5.29295 loss)
I0410 02:31:41.744246 27877 sgd_solver.cpp:105] Iteration 4272, lr = 0.00429032
I0410 02:31:46.192931 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4284.caffemodel
I0410 02:31:48.133579 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4284.solverstate
I0410 02:31:49.443540 27877 solver.cpp:330] Iteration 4284, Testing net (#0)
I0410 02:31:49.443572 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:31:52.245061 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:31:53.957892 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:31:53.957942 27877 solver.cpp:397]     Test net output #1: loss = 5.28658 (* 1 = 5.28658 loss)
I0410 02:31:54.040859 27877 solver.cpp:218] Iteration 4284 (0.975903 iter/s, 12.2963s/12 iters), loss = 5.27684
I0410 02:31:54.040910 27877 solver.cpp:237]     Train net output #0: loss = 5.27684 (* 1 = 5.27684 loss)
I0410 02:31:54.040921 27877 sgd_solver.cpp:105] Iteration 4284, lr = 0.00428014
I0410 02:31:58.367647 27877 solver.cpp:218] Iteration 4296 (2.77353 iter/s, 4.32662s/12 iters), loss = 5.2765
I0410 02:31:58.367689 27877 solver.cpp:237]     Train net output #0: loss = 5.2765 (* 1 = 5.2765 loss)
I0410 02:31:58.367697 27877 sgd_solver.cpp:105] Iteration 4296, lr = 0.00426998
I0410 02:32:03.274960 27877 solver.cpp:218] Iteration 4308 (2.44542 iter/s, 4.90714s/12 iters), loss = 5.26556
I0410 02:32:03.275002 27877 solver.cpp:237]     Train net output #0: loss = 5.26556 (* 1 = 5.26556 loss)
I0410 02:32:03.275010 27877 sgd_solver.cpp:105] Iteration 4308, lr = 0.00425984
I0410 02:32:08.141450 27877 solver.cpp:218] Iteration 4320 (2.46593 iter/s, 4.86631s/12 iters), loss = 5.24886
I0410 02:32:08.141502 27877 solver.cpp:237]     Train net output #0: loss = 5.24886 (* 1 = 5.24886 loss)
I0410 02:32:08.141515 27877 sgd_solver.cpp:105] Iteration 4320, lr = 0.00424972
I0410 02:32:13.038761 27877 solver.cpp:218] Iteration 4332 (2.45042 iter/s, 4.89713s/12 iters), loss = 5.27569
I0410 02:32:13.038810 27877 solver.cpp:237]     Train net output #0: loss = 5.27569 (* 1 = 5.27569 loss)
I0410 02:32:13.038820 27877 sgd_solver.cpp:105] Iteration 4332, lr = 0.00423964
I0410 02:32:17.981763 27877 solver.cpp:218] Iteration 4344 (2.42777 iter/s, 4.94281s/12 iters), loss = 5.28133
I0410 02:32:17.981819 27877 solver.cpp:237]     Train net output #0: loss = 5.28133 (* 1 = 5.28133 loss)
I0410 02:32:17.981830 27877 sgd_solver.cpp:105] Iteration 4344, lr = 0.00422957
I0410 02:32:19.847002 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:32:22.906098 27877 solver.cpp:218] Iteration 4356 (2.43697 iter/s, 4.92415s/12 iters), loss = 5.28807
I0410 02:32:22.906145 27877 solver.cpp:237]     Train net output #0: loss = 5.28807 (* 1 = 5.28807 loss)
I0410 02:32:22.906155 27877 sgd_solver.cpp:105] Iteration 4356, lr = 0.00421953
I0410 02:32:27.846743 27877 solver.cpp:218] Iteration 4368 (2.42892 iter/s, 4.94046s/12 iters), loss = 5.27859
I0410 02:32:27.846788 27877 solver.cpp:237]     Train net output #0: loss = 5.27859 (* 1 = 5.27859 loss)
I0410 02:32:27.846797 27877 sgd_solver.cpp:105] Iteration 4368, lr = 0.00420951
I0410 02:32:32.731534 27877 solver.cpp:218] Iteration 4380 (2.4567 iter/s, 4.88461s/12 iters), loss = 5.26119
I0410 02:32:32.731582 27877 solver.cpp:237]     Train net output #0: loss = 5.26119 (* 1 = 5.26119 loss)
I0410 02:32:32.731590 27877 sgd_solver.cpp:105] Iteration 4380, lr = 0.00419952
I0410 02:32:34.730731 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4386.caffemodel
I0410 02:32:36.301676 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4386.solverstate
I0410 02:32:37.878438 27877 solver.cpp:330] Iteration 4386, Testing net (#0)
I0410 02:32:37.878464 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:32:40.747326 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:32:42.477587 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:32:42.477633 27877 solver.cpp:397]     Test net output #1: loss = 5.28656 (* 1 = 5.28656 loss)
I0410 02:32:44.358433 27877 solver.cpp:218] Iteration 4392 (1.03212 iter/s, 11.6266s/12 iters), loss = 5.26852
I0410 02:32:44.358500 27877 solver.cpp:237]     Train net output #0: loss = 5.26852 (* 1 = 5.26852 loss)
I0410 02:32:44.358510 27877 sgd_solver.cpp:105] Iteration 4392, lr = 0.00418954
I0410 02:32:49.334347 27877 solver.cpp:218] Iteration 4404 (2.41171 iter/s, 4.97571s/12 iters), loss = 5.26348
I0410 02:32:49.334391 27877 solver.cpp:237]     Train net output #0: loss = 5.26348 (* 1 = 5.26348 loss)
I0410 02:32:49.334400 27877 sgd_solver.cpp:105] Iteration 4404, lr = 0.0041796
I0410 02:32:54.248986 27877 solver.cpp:218] Iteration 4416 (2.44178 iter/s, 4.91445s/12 iters), loss = 5.26404
I0410 02:32:54.249076 27877 solver.cpp:237]     Train net output #0: loss = 5.26404 (* 1 = 5.26404 loss)
I0410 02:32:54.249089 27877 sgd_solver.cpp:105] Iteration 4416, lr = 0.00416967
I0410 02:32:59.164392 27877 solver.cpp:218] Iteration 4428 (2.44142 iter/s, 4.91518s/12 iters), loss = 5.2708
I0410 02:32:59.164438 27877 solver.cpp:237]     Train net output #0: loss = 5.2708 (* 1 = 5.2708 loss)
I0410 02:32:59.164446 27877 sgd_solver.cpp:105] Iteration 4428, lr = 0.00415977
I0410 02:33:04.095708 27877 solver.cpp:218] Iteration 4440 (2.43352 iter/s, 4.93114s/12 iters), loss = 5.26446
I0410 02:33:04.095746 27877 solver.cpp:237]     Train net output #0: loss = 5.26446 (* 1 = 5.26446 loss)
I0410 02:33:04.095754 27877 sgd_solver.cpp:105] Iteration 4440, lr = 0.0041499
I0410 02:33:08.173161 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:33:09.131986 27877 solver.cpp:218] Iteration 4452 (2.3828 iter/s, 5.0361s/12 iters), loss = 5.25845
I0410 02:33:09.132036 27877 solver.cpp:237]     Train net output #0: loss = 5.25845 (* 1 = 5.25845 loss)
I0410 02:33:09.132045 27877 sgd_solver.cpp:105] Iteration 4452, lr = 0.00414005
I0410 02:33:14.095623 27877 solver.cpp:218] Iteration 4464 (2.41767 iter/s, 4.96345s/12 iters), loss = 5.28121
I0410 02:33:14.095671 27877 solver.cpp:237]     Train net output #0: loss = 5.28121 (* 1 = 5.28121 loss)
I0410 02:33:14.095680 27877 sgd_solver.cpp:105] Iteration 4464, lr = 0.00413022
I0410 02:33:19.034281 27877 solver.cpp:218] Iteration 4476 (2.4299 iter/s, 4.93848s/12 iters), loss = 5.25825
I0410 02:33:19.034322 27877 solver.cpp:237]     Train net output #0: loss = 5.25825 (* 1 = 5.25825 loss)
I0410 02:33:19.034330 27877 sgd_solver.cpp:105] Iteration 4476, lr = 0.00412041
I0410 02:33:23.493611 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4488.caffemodel
I0410 02:33:24.333314 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4488.solverstate
I0410 02:33:24.954362 27877 solver.cpp:330] Iteration 4488, Testing net (#0)
I0410 02:33:24.954391 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:33:27.631131 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:33:29.759728 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 02:33:29.759781 27877 solver.cpp:397]     Test net output #1: loss = 5.28638 (* 1 = 5.28638 loss)
I0410 02:33:29.842367 27877 solver.cpp:218] Iteration 4488 (1.11031 iter/s, 10.8078s/12 iters), loss = 5.30774
I0410 02:33:29.842419 27877 solver.cpp:237]     Train net output #0: loss = 5.30774 (* 1 = 5.30774 loss)
I0410 02:33:29.842430 27877 sgd_solver.cpp:105] Iteration 4488, lr = 0.00411063
I0410 02:33:34.133493 27877 solver.cpp:218] Iteration 4500 (2.79658 iter/s, 4.29096s/12 iters), loss = 5.27116
I0410 02:33:34.133531 27877 solver.cpp:237]     Train net output #0: loss = 5.27116 (* 1 = 5.27116 loss)
I0410 02:33:34.133539 27877 sgd_solver.cpp:105] Iteration 4500, lr = 0.00410087
I0410 02:33:39.349669 27877 solver.cpp:218] Iteration 4512 (2.30062 iter/s, 5.21599s/12 iters), loss = 5.27185
I0410 02:33:39.349730 27877 solver.cpp:237]     Train net output #0: loss = 5.27185 (* 1 = 5.27185 loss)
I0410 02:33:39.349741 27877 sgd_solver.cpp:105] Iteration 4512, lr = 0.00409113
I0410 02:33:44.221642 27877 solver.cpp:218] Iteration 4524 (2.46317 iter/s, 4.87178s/12 iters), loss = 5.27731
I0410 02:33:44.221688 27877 solver.cpp:237]     Train net output #0: loss = 5.27731 (* 1 = 5.27731 loss)
I0410 02:33:44.221698 27877 sgd_solver.cpp:105] Iteration 4524, lr = 0.00408142
I0410 02:33:49.113337 27877 solver.cpp:218] Iteration 4536 (2.45323 iter/s, 4.89151s/12 iters), loss = 5.26756
I0410 02:33:49.113377 27877 solver.cpp:237]     Train net output #0: loss = 5.26756 (* 1 = 5.26756 loss)
I0410 02:33:49.113385 27877 sgd_solver.cpp:105] Iteration 4536, lr = 0.00407173
I0410 02:33:54.074331 27877 solver.cpp:218] Iteration 4548 (2.41896 iter/s, 4.96081s/12 iters), loss = 5.27128
I0410 02:33:54.074388 27877 solver.cpp:237]     Train net output #0: loss = 5.27128 (* 1 = 5.27128 loss)
I0410 02:33:54.074400 27877 sgd_solver.cpp:105] Iteration 4548, lr = 0.00406206
I0410 02:33:55.309798 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:33:58.961652 27877 solver.cpp:218] Iteration 4560 (2.45543 iter/s, 4.88713s/12 iters), loss = 5.27483
I0410 02:33:58.961702 27877 solver.cpp:237]     Train net output #0: loss = 5.27483 (* 1 = 5.27483 loss)
I0410 02:33:58.961714 27877 sgd_solver.cpp:105] Iteration 4560, lr = 0.00405242
I0410 02:34:03.892299 27877 solver.cpp:218] Iteration 4572 (2.43385 iter/s, 4.93047s/12 iters), loss = 5.26637
I0410 02:34:03.892345 27877 solver.cpp:237]     Train net output #0: loss = 5.26637 (* 1 = 5.26637 loss)
I0410 02:34:03.892355 27877 sgd_solver.cpp:105] Iteration 4572, lr = 0.0040428
I0410 02:34:08.795500 27877 solver.cpp:218] Iteration 4584 (2.44747 iter/s, 4.90302s/12 iters), loss = 5.27436
I0410 02:34:08.795559 27877 solver.cpp:237]     Train net output #0: loss = 5.27436 (* 1 = 5.27436 loss)
I0410 02:34:08.795572 27877 sgd_solver.cpp:105] Iteration 4584, lr = 0.0040332
I0410 02:34:10.771381 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4590.caffemodel
I0410 02:34:12.295887 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4590.solverstate
I0410 02:34:13.670456 27877 solver.cpp:330] Iteration 4590, Testing net (#0)
I0410 02:34:13.670487 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:34:16.355836 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:34:18.169179 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:34:18.169215 27877 solver.cpp:397]     Test net output #1: loss = 5.2864 (* 1 = 5.2864 loss)
I0410 02:34:20.005941 27877 solver.cpp:218] Iteration 4596 (1.07046 iter/s, 11.2101s/12 iters), loss = 5.27394
I0410 02:34:20.006031 27877 solver.cpp:237]     Train net output #0: loss = 5.27394 (* 1 = 5.27394 loss)
I0410 02:34:20.006043 27877 sgd_solver.cpp:105] Iteration 4596, lr = 0.00402362
I0410 02:34:24.943157 27877 solver.cpp:218] Iteration 4608 (2.43063 iter/s, 4.93699s/12 iters), loss = 5.27296
I0410 02:34:24.943212 27877 solver.cpp:237]     Train net output #0: loss = 5.27296 (* 1 = 5.27296 loss)
I0410 02:34:24.943223 27877 sgd_solver.cpp:105] Iteration 4608, lr = 0.00401407
I0410 02:34:29.888702 27877 solver.cpp:218] Iteration 4620 (2.42652 iter/s, 4.94536s/12 iters), loss = 5.26419
I0410 02:34:29.888847 27877 solver.cpp:237]     Train net output #0: loss = 5.26419 (* 1 = 5.26419 loss)
I0410 02:34:29.888861 27877 sgd_solver.cpp:105] Iteration 4620, lr = 0.00400454
I0410 02:34:34.825907 27877 solver.cpp:218] Iteration 4632 (2.43066 iter/s, 4.93693s/12 iters), loss = 5.28947
I0410 02:34:34.825951 27877 solver.cpp:237]     Train net output #0: loss = 5.28947 (* 1 = 5.28947 loss)
I0410 02:34:34.825973 27877 sgd_solver.cpp:105] Iteration 4632, lr = 0.00399503
I0410 02:34:39.738407 27877 solver.cpp:218] Iteration 4644 (2.44283 iter/s, 4.91233s/12 iters), loss = 5.27143
I0410 02:34:39.738447 27877 solver.cpp:237]     Train net output #0: loss = 5.27143 (* 1 = 5.27143 loss)
I0410 02:34:39.738456 27877 sgd_solver.cpp:105] Iteration 4644, lr = 0.00398555
I0410 02:34:43.105144 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:34:44.700520 27877 solver.cpp:218] Iteration 4656 (2.41841 iter/s, 4.96194s/12 iters), loss = 5.28066
I0410 02:34:44.700563 27877 solver.cpp:237]     Train net output #0: loss = 5.28066 (* 1 = 5.28066 loss)
I0410 02:34:44.700572 27877 sgd_solver.cpp:105] Iteration 4656, lr = 0.00397608
I0410 02:34:49.699412 27877 solver.cpp:218] Iteration 4668 (2.40062 iter/s, 4.99871s/12 iters), loss = 5.26738
I0410 02:34:49.699465 27877 solver.cpp:237]     Train net output #0: loss = 5.26738 (* 1 = 5.26738 loss)
I0410 02:34:49.699476 27877 sgd_solver.cpp:105] Iteration 4668, lr = 0.00396664
I0410 02:34:54.697099 27877 solver.cpp:218] Iteration 4680 (2.4012 iter/s, 4.9975s/12 iters), loss = 5.27837
I0410 02:34:54.697151 27877 solver.cpp:237]     Train net output #0: loss = 5.27837 (* 1 = 5.27837 loss)
I0410 02:34:54.697161 27877 sgd_solver.cpp:105] Iteration 4680, lr = 0.00395723
I0410 02:34:59.202584 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4692.caffemodel
I0410 02:35:00.029196 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4692.solverstate
I0410 02:35:00.649904 27877 solver.cpp:330] Iteration 4692, Testing net (#0)
I0410 02:35:00.649930 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:35:03.271116 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:35:05.121086 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:35:05.121124 27877 solver.cpp:397]     Test net output #1: loss = 5.28667 (* 1 = 5.28667 loss)
I0410 02:35:05.203771 27877 solver.cpp:218] Iteration 4692 (1.14217 iter/s, 10.5064s/12 iters), loss = 5.27245
I0410 02:35:05.203815 27877 solver.cpp:237]     Train net output #0: loss = 5.27245 (* 1 = 5.27245 loss)
I0410 02:35:05.203824 27877 sgd_solver.cpp:105] Iteration 4692, lr = 0.00394783
I0410 02:35:09.450513 27877 solver.cpp:218] Iteration 4704 (2.82581 iter/s, 4.24657s/12 iters), loss = 5.26417
I0410 02:35:09.450563 27877 solver.cpp:237]     Train net output #0: loss = 5.26417 (* 1 = 5.26417 loss)
I0410 02:35:09.450572 27877 sgd_solver.cpp:105] Iteration 4704, lr = 0.00393846
I0410 02:35:14.476130 27877 solver.cpp:218] Iteration 4716 (2.38786 iter/s, 5.02543s/12 iters), loss = 5.28109
I0410 02:35:14.476178 27877 solver.cpp:237]     Train net output #0: loss = 5.28109 (* 1 = 5.28109 loss)
I0410 02:35:14.476191 27877 sgd_solver.cpp:105] Iteration 4716, lr = 0.00392911
I0410 02:35:19.533542 27877 solver.cpp:218] Iteration 4728 (2.37285 iter/s, 5.05722s/12 iters), loss = 5.26526
I0410 02:35:19.533602 27877 solver.cpp:237]     Train net output #0: loss = 5.26526 (* 1 = 5.26526 loss)
I0410 02:35:19.533614 27877 sgd_solver.cpp:105] Iteration 4728, lr = 0.00391978
I0410 02:35:24.592000 27877 solver.cpp:218] Iteration 4740 (2.37236 iter/s, 5.05826s/12 iters), loss = 5.27755
I0410 02:35:24.592056 27877 solver.cpp:237]     Train net output #0: loss = 5.27755 (* 1 = 5.27755 loss)
I0410 02:35:24.592068 27877 sgd_solver.cpp:105] Iteration 4740, lr = 0.00391047
I0410 02:35:29.495324 27877 solver.cpp:218] Iteration 4752 (2.44742 iter/s, 4.90313s/12 iters), loss = 5.28204
I0410 02:35:29.495390 27877 solver.cpp:237]     Train net output #0: loss = 5.28204 (* 1 = 5.28204 loss)
I0410 02:35:29.495409 27877 sgd_solver.cpp:105] Iteration 4752, lr = 0.00390119
I0410 02:35:30.024402 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:35:34.393335 27877 solver.cpp:218] Iteration 4764 (2.45008 iter/s, 4.89781s/12 iters), loss = 5.28264
I0410 02:35:34.393456 27877 solver.cpp:237]     Train net output #0: loss = 5.28264 (* 1 = 5.28264 loss)
I0410 02:35:34.393466 27877 sgd_solver.cpp:105] Iteration 4764, lr = 0.00389193
I0410 02:35:39.292858 27877 solver.cpp:218] Iteration 4776 (2.44935 iter/s, 4.89927s/12 iters), loss = 5.26481
I0410 02:35:39.292904 27877 solver.cpp:237]     Train net output #0: loss = 5.26481 (* 1 = 5.26481 loss)
I0410 02:35:39.292912 27877 sgd_solver.cpp:105] Iteration 4776, lr = 0.00388269
I0410 02:35:44.216070 27877 solver.cpp:218] Iteration 4788 (2.43752 iter/s, 4.92303s/12 iters), loss = 5.2907
I0410 02:35:44.216115 27877 solver.cpp:237]     Train net output #0: loss = 5.2907 (* 1 = 5.2907 loss)
I0410 02:35:44.216123 27877 sgd_solver.cpp:105] Iteration 4788, lr = 0.00387347
I0410 02:35:46.185144 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4794.caffemodel
I0410 02:35:47.059706 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4794.solverstate
I0410 02:35:47.691993 27877 solver.cpp:330] Iteration 4794, Testing net (#0)
I0410 02:35:47.692021 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:35:50.212108 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:35:52.106235 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 02:35:52.106271 27877 solver.cpp:397]     Test net output #1: loss = 5.28601 (* 1 = 5.28601 loss)
I0410 02:35:54.035203 27877 solver.cpp:218] Iteration 4800 (1.22214 iter/s, 9.81884s/12 iters), loss = 5.27169
I0410 02:35:54.035254 27877 solver.cpp:237]     Train net output #0: loss = 5.27169 (* 1 = 5.27169 loss)
I0410 02:35:54.035265 27877 sgd_solver.cpp:105] Iteration 4800, lr = 0.00386427
I0410 02:35:59.153088 27877 solver.cpp:218] Iteration 4812 (2.3448 iter/s, 5.1177s/12 iters), loss = 5.26623
I0410 02:35:59.153131 27877 solver.cpp:237]     Train net output #0: loss = 5.26623 (* 1 = 5.26623 loss)
I0410 02:35:59.153141 27877 sgd_solver.cpp:105] Iteration 4812, lr = 0.0038551
I0410 02:36:04.171902 27877 solver.cpp:218] Iteration 4824 (2.39109 iter/s, 5.01864s/12 iters), loss = 5.28727
I0410 02:36:04.171943 27877 solver.cpp:237]     Train net output #0: loss = 5.28727 (* 1 = 5.28727 loss)
I0410 02:36:04.171953 27877 sgd_solver.cpp:105] Iteration 4824, lr = 0.00384594
I0410 02:36:09.489089 27877 solver.cpp:218] Iteration 4836 (2.25691 iter/s, 5.317s/12 iters), loss = 5.26716
I0410 02:36:09.489215 27877 solver.cpp:237]     Train net output #0: loss = 5.26716 (* 1 = 5.26716 loss)
I0410 02:36:09.489224 27877 sgd_solver.cpp:105] Iteration 4836, lr = 0.00383681
I0410 02:36:10.771596 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:36:14.760109 27877 solver.cpp:218] Iteration 4848 (2.27672 iter/s, 5.27075s/12 iters), loss = 5.26842
I0410 02:36:14.760162 27877 solver.cpp:237]     Train net output #0: loss = 5.26842 (* 1 = 5.26842 loss)
I0410 02:36:14.760174 27877 sgd_solver.cpp:105] Iteration 4848, lr = 0.0038277
I0410 02:36:17.436760 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:36:19.733323 27877 solver.cpp:218] Iteration 4860 (2.41302 iter/s, 4.97303s/12 iters), loss = 5.26796
I0410 02:36:19.733366 27877 solver.cpp:237]     Train net output #0: loss = 5.26796 (* 1 = 5.26796 loss)
I0410 02:36:19.733376 27877 sgd_solver.cpp:105] Iteration 4860, lr = 0.00381862
I0410 02:36:24.643087 27877 solver.cpp:218] Iteration 4872 (2.4442 iter/s, 4.90958s/12 iters), loss = 5.26595
I0410 02:36:24.643146 27877 solver.cpp:237]     Train net output #0: loss = 5.26595 (* 1 = 5.26595 loss)
I0410 02:36:24.643158 27877 sgd_solver.cpp:105] Iteration 4872, lr = 0.00380955
I0410 02:36:29.487342 27877 solver.cpp:218] Iteration 4884 (2.47726 iter/s, 4.84406s/12 iters), loss = 5.26649
I0410 02:36:29.487390 27877 solver.cpp:237]     Train net output #0: loss = 5.26649 (* 1 = 5.26649 loss)
I0410 02:36:29.487398 27877 sgd_solver.cpp:105] Iteration 4884, lr = 0.0038005
I0410 02:36:34.201402 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4896.caffemodel
I0410 02:36:35.678901 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4896.solverstate
I0410 02:36:36.939239 27877 solver.cpp:330] Iteration 4896, Testing net (#0)
I0410 02:36:36.939265 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:36:39.599795 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:36:41.525830 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:36:41.525867 27877 solver.cpp:397]     Test net output #1: loss = 5.2868 (* 1 = 5.2868 loss)
I0410 02:36:41.608776 27877 solver.cpp:218] Iteration 4896 (0.990011 iter/s, 12.1211s/12 iters), loss = 5.27001
I0410 02:36:41.608816 27877 solver.cpp:237]     Train net output #0: loss = 5.27001 (* 1 = 5.27001 loss)
I0410 02:36:41.608825 27877 sgd_solver.cpp:105] Iteration 4896, lr = 0.00379148
I0410 02:36:45.958752 27877 solver.cpp:218] Iteration 4908 (2.75874 iter/s, 4.34981s/12 iters), loss = 5.29358
I0410 02:36:45.958796 27877 solver.cpp:237]     Train net output #0: loss = 5.29358 (* 1 = 5.29358 loss)
I0410 02:36:45.958803 27877 sgd_solver.cpp:105] Iteration 4908, lr = 0.00378248
I0410 02:36:51.017246 27877 solver.cpp:218] Iteration 4920 (2.37233 iter/s, 5.05831s/12 iters), loss = 5.27041
I0410 02:36:51.017295 27877 solver.cpp:237]     Train net output #0: loss = 5.27041 (* 1 = 5.27041 loss)
I0410 02:36:51.017307 27877 sgd_solver.cpp:105] Iteration 4920, lr = 0.0037735
I0410 02:36:55.906708 27877 solver.cpp:218] Iteration 4932 (2.45435 iter/s, 4.88928s/12 iters), loss = 5.26461
I0410 02:36:55.906751 27877 solver.cpp:237]     Train net output #0: loss = 5.26461 (* 1 = 5.26461 loss)
I0410 02:36:55.906760 27877 sgd_solver.cpp:105] Iteration 4932, lr = 0.00376454
I0410 02:37:00.768085 27877 solver.cpp:218] Iteration 4944 (2.46853 iter/s, 4.8612s/12 iters), loss = 5.26793
I0410 02:37:00.768136 27877 solver.cpp:237]     Train net output #0: loss = 5.26793 (* 1 = 5.26793 loss)
I0410 02:37:00.768147 27877 sgd_solver.cpp:105] Iteration 4944, lr = 0.0037556
I0410 02:37:05.758536 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:37:05.951130 27877 solver.cpp:218] Iteration 4956 (2.31533 iter/s, 5.18285s/12 iters), loss = 5.25173
I0410 02:37:05.951176 27877 solver.cpp:237]     Train net output #0: loss = 5.25173 (* 1 = 5.25173 loss)
I0410 02:37:05.951184 27877 sgd_solver.cpp:105] Iteration 4956, lr = 0.00374669
I0410 02:37:10.847944 27877 solver.cpp:218] Iteration 4968 (2.45066 iter/s, 4.89664s/12 iters), loss = 5.26309
I0410 02:37:10.848063 27877 solver.cpp:237]     Train net output #0: loss = 5.26309 (* 1 = 5.26309 loss)
I0410 02:37:10.848073 27877 sgd_solver.cpp:105] Iteration 4968, lr = 0.00373779
I0410 02:37:15.749827 27877 solver.cpp:218] Iteration 4980 (2.44816 iter/s, 4.90163s/12 iters), loss = 5.29145
I0410 02:37:15.749873 27877 solver.cpp:237]     Train net output #0: loss = 5.29145 (* 1 = 5.29145 loss)
I0410 02:37:15.749882 27877 sgd_solver.cpp:105] Iteration 4980, lr = 0.00372892
I0410 02:37:20.660163 27877 solver.cpp:218] Iteration 4992 (2.44392 iter/s, 4.91015s/12 iters), loss = 5.28404
I0410 02:37:20.660218 27877 solver.cpp:237]     Train net output #0: loss = 5.28404 (* 1 = 5.28404 loss)
I0410 02:37:20.660229 27877 sgd_solver.cpp:105] Iteration 4992, lr = 0.00372006
I0410 02:37:22.662015 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_4998.caffemodel
I0410 02:37:23.513566 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_4998.solverstate
I0410 02:37:24.140089 27877 solver.cpp:330] Iteration 4998, Testing net (#0)
I0410 02:37:24.140116 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:37:26.620411 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:37:28.696100 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:37:28.696138 27877 solver.cpp:397]     Test net output #1: loss = 5.28656 (* 1 = 5.28656 loss)
I0410 02:37:30.488250 27877 solver.cpp:218] Iteration 5004 (1.22103 iter/s, 9.82778s/12 iters), loss = 5.28259
I0410 02:37:30.488307 27877 solver.cpp:237]     Train net output #0: loss = 5.28259 (* 1 = 5.28259 loss)
I0410 02:37:30.488318 27877 sgd_solver.cpp:105] Iteration 5004, lr = 0.00371123
I0410 02:37:35.510100 27877 solver.cpp:218] Iteration 5016 (2.38965 iter/s, 5.02166s/12 iters), loss = 5.26495
I0410 02:37:35.510145 27877 solver.cpp:237]     Train net output #0: loss = 5.26495 (* 1 = 5.26495 loss)
I0410 02:37:35.510154 27877 sgd_solver.cpp:105] Iteration 5016, lr = 0.00370242
I0410 02:37:40.558558 27877 solver.cpp:218] Iteration 5028 (2.37705 iter/s, 5.04827s/12 iters), loss = 5.24869
I0410 02:37:40.558609 27877 solver.cpp:237]     Train net output #0: loss = 5.24869 (* 1 = 5.24869 loss)
I0410 02:37:40.558620 27877 sgd_solver.cpp:105] Iteration 5028, lr = 0.00369363
I0410 02:37:45.656154 27877 solver.cpp:218] Iteration 5040 (2.35414 iter/s, 5.0974s/12 iters), loss = 5.28401
I0410 02:37:45.656250 27877 solver.cpp:237]     Train net output #0: loss = 5.28401 (* 1 = 5.28401 loss)
I0410 02:37:45.656258 27877 sgd_solver.cpp:105] Iteration 5040, lr = 0.00368486
I0410 02:37:50.924118 27877 solver.cpp:218] Iteration 5052 (2.27803 iter/s, 5.26772s/12 iters), loss = 5.27366
I0410 02:37:50.924175 27877 solver.cpp:237]     Train net output #0: loss = 5.27366 (* 1 = 5.27366 loss)
I0410 02:37:50.924186 27877 sgd_solver.cpp:105] Iteration 5052, lr = 0.00367611
I0410 02:37:52.845759 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:37:55.885736 27877 solver.cpp:218] Iteration 5064 (2.41866 iter/s, 4.96143s/12 iters), loss = 5.289
I0410 02:37:55.885777 27877 solver.cpp:237]     Train net output #0: loss = 5.289 (* 1 = 5.289 loss)
I0410 02:37:55.885785 27877 sgd_solver.cpp:105] Iteration 5064, lr = 0.00366738
I0410 02:38:00.800555 27877 solver.cpp:218] Iteration 5076 (2.44168 iter/s, 4.91465s/12 iters), loss = 5.27306
I0410 02:38:00.800592 27877 solver.cpp:237]     Train net output #0: loss = 5.27306 (* 1 = 5.27306 loss)
I0410 02:38:00.800601 27877 sgd_solver.cpp:105] Iteration 5076, lr = 0.00365868
I0410 02:38:05.734437 27877 solver.cpp:218] Iteration 5088 (2.43225 iter/s, 4.93371s/12 iters), loss = 5.26429
I0410 02:38:05.734491 27877 solver.cpp:237]     Train net output #0: loss = 5.26429 (* 1 = 5.26429 loss)
I0410 02:38:05.734503 27877 sgd_solver.cpp:105] Iteration 5088, lr = 0.00364999
I0410 02:38:10.324034 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5100.caffemodel
I0410 02:38:12.855607 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5100.solverstate
I0410 02:38:15.195282 27877 solver.cpp:330] Iteration 5100, Testing net (#0)
I0410 02:38:15.195302 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:38:17.774940 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:38:20.003126 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:38:20.003170 27877 solver.cpp:397]     Test net output #1: loss = 5.28629 (* 1 = 5.28629 loss)
I0410 02:38:20.085794 27877 solver.cpp:218] Iteration 5100 (0.836182 iter/s, 14.3509s/12 iters), loss = 5.26903
I0410 02:38:20.085846 27877 solver.cpp:237]     Train net output #0: loss = 5.26903 (* 1 = 5.26903 loss)
I0410 02:38:20.085857 27877 sgd_solver.cpp:105] Iteration 5100, lr = 0.00364132
I0410 02:38:24.265837 27877 solver.cpp:218] Iteration 5112 (2.8709 iter/s, 4.17987s/12 iters), loss = 5.26089
I0410 02:38:24.265897 27877 solver.cpp:237]     Train net output #0: loss = 5.26089 (* 1 = 5.26089 loss)
I0410 02:38:24.265908 27877 sgd_solver.cpp:105] Iteration 5112, lr = 0.00363268
I0410 02:38:29.250430 27877 solver.cpp:218] Iteration 5124 (2.40751 iter/s, 4.9844s/12 iters), loss = 5.27809
I0410 02:38:29.250470 27877 solver.cpp:237]     Train net output #0: loss = 5.27809 (* 1 = 5.27809 loss)
I0410 02:38:29.250478 27877 sgd_solver.cpp:105] Iteration 5124, lr = 0.00362405
I0410 02:38:34.235409 27877 solver.cpp:218] Iteration 5136 (2.40732 iter/s, 4.9848s/12 iters), loss = 5.26756
I0410 02:38:34.235460 27877 solver.cpp:237]     Train net output #0: loss = 5.26756 (* 1 = 5.26756 loss)
I0410 02:38:34.235471 27877 sgd_solver.cpp:105] Iteration 5136, lr = 0.00361545
I0410 02:38:39.174607 27877 solver.cpp:218] Iteration 5148 (2.42964 iter/s, 4.93901s/12 iters), loss = 5.26246
I0410 02:38:39.174661 27877 solver.cpp:237]     Train net output #0: loss = 5.26246 (* 1 = 5.26246 loss)
I0410 02:38:39.174674 27877 sgd_solver.cpp:105] Iteration 5148, lr = 0.00360687
I0410 02:38:43.175154 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:38:44.081292 27877 solver.cpp:218] Iteration 5160 (2.44574 iter/s, 4.90649s/12 iters), loss = 5.25989
I0410 02:38:44.081352 27877 solver.cpp:237]     Train net output #0: loss = 5.25989 (* 1 = 5.25989 loss)
I0410 02:38:44.081365 27877 sgd_solver.cpp:105] Iteration 5160, lr = 0.0035983
I0410 02:38:49.278892 27877 solver.cpp:218] Iteration 5172 (2.30885 iter/s, 5.19739s/12 iters), loss = 5.27428
I0410 02:38:49.279016 27877 solver.cpp:237]     Train net output #0: loss = 5.27428 (* 1 = 5.27428 loss)
I0410 02:38:49.279029 27877 sgd_solver.cpp:105] Iteration 5172, lr = 0.00358976
I0410 02:38:54.277452 27877 solver.cpp:218] Iteration 5184 (2.40081 iter/s, 4.9983s/12 iters), loss = 5.2721
I0410 02:38:54.277493 27877 solver.cpp:237]     Train net output #0: loss = 5.2721 (* 1 = 5.2721 loss)
I0410 02:38:54.277500 27877 sgd_solver.cpp:105] Iteration 5184, lr = 0.00358124
I0410 02:38:59.171144 27877 solver.cpp:218] Iteration 5196 (2.45222 iter/s, 4.89352s/12 iters), loss = 5.30495
I0410 02:38:59.171187 27877 solver.cpp:237]     Train net output #0: loss = 5.30495 (* 1 = 5.30495 loss)
I0410 02:38:59.171197 27877 sgd_solver.cpp:105] Iteration 5196, lr = 0.00357273
I0410 02:39:01.188298 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5202.caffemodel
I0410 02:39:02.034610 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5202.solverstate
I0410 02:39:02.645093 27877 solver.cpp:330] Iteration 5202, Testing net (#0)
I0410 02:39:02.645112 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:39:04.958118 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:39:07.047791 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:39:07.047819 27877 solver.cpp:397]     Test net output #1: loss = 5.28647 (* 1 = 5.28647 loss)
I0410 02:39:08.924425 27877 solver.cpp:218] Iteration 5208 (1.23039 iter/s, 9.75298s/12 iters), loss = 5.27302
I0410 02:39:08.924476 27877 solver.cpp:237]     Train net output #0: loss = 5.27302 (* 1 = 5.27302 loss)
I0410 02:39:08.924490 27877 sgd_solver.cpp:105] Iteration 5208, lr = 0.00356425
I0410 02:39:14.121742 27877 solver.cpp:218] Iteration 5220 (2.30897 iter/s, 5.19712s/12 iters), loss = 5.27349
I0410 02:39:14.121800 27877 solver.cpp:237]     Train net output #0: loss = 5.27349 (* 1 = 5.27349 loss)
I0410 02:39:14.121812 27877 sgd_solver.cpp:105] Iteration 5220, lr = 0.00355579
I0410 02:39:19.074231 27877 solver.cpp:218] Iteration 5232 (2.42312 iter/s, 4.9523s/12 iters), loss = 5.27725
I0410 02:39:19.074275 27877 solver.cpp:237]     Train net output #0: loss = 5.27725 (* 1 = 5.27725 loss)
I0410 02:39:19.074285 27877 sgd_solver.cpp:105] Iteration 5232, lr = 0.00354735
I0410 02:39:23.994784 27877 solver.cpp:218] Iteration 5244 (2.43884 iter/s, 4.92037s/12 iters), loss = 5.27262
I0410 02:39:23.994882 27877 solver.cpp:237]     Train net output #0: loss = 5.27262 (* 1 = 5.27262 loss)
I0410 02:39:23.994891 27877 sgd_solver.cpp:105] Iteration 5244, lr = 0.00353892
I0410 02:39:28.896456 27877 solver.cpp:218] Iteration 5256 (2.44826 iter/s, 4.90144s/12 iters), loss = 5.26287
I0410 02:39:28.896502 27877 solver.cpp:237]     Train net output #0: loss = 5.26287 (* 1 = 5.26287 loss)
I0410 02:39:28.896512 27877 sgd_solver.cpp:105] Iteration 5256, lr = 0.00353052
I0410 02:39:30.164069 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:39:33.826237 27877 solver.cpp:218] Iteration 5268 (2.43427 iter/s, 4.9296s/12 iters), loss = 5.27533
I0410 02:39:33.826293 27877 solver.cpp:237]     Train net output #0: loss = 5.27533 (* 1 = 5.27533 loss)
I0410 02:39:33.826305 27877 sgd_solver.cpp:105] Iteration 5268, lr = 0.00352214
I0410 02:39:38.733585 27877 solver.cpp:218] Iteration 5280 (2.44541 iter/s, 4.90715s/12 iters), loss = 5.26934
I0410 02:39:38.733640 27877 solver.cpp:237]     Train net output #0: loss = 5.26934 (* 1 = 5.26934 loss)
I0410 02:39:38.733651 27877 sgd_solver.cpp:105] Iteration 5280, lr = 0.00351378
I0410 02:39:43.650499 27877 solver.cpp:218] Iteration 5292 (2.44065 iter/s, 4.91672s/12 iters), loss = 5.28014
I0410 02:39:43.650553 27877 solver.cpp:237]     Train net output #0: loss = 5.28014 (* 1 = 5.28014 loss)
I0410 02:39:43.650565 27877 sgd_solver.cpp:105] Iteration 5292, lr = 0.00350544
I0410 02:39:48.083667 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5304.caffemodel
I0410 02:39:49.174103 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5304.solverstate
I0410 02:39:50.120918 27877 solver.cpp:330] Iteration 5304, Testing net (#0)
I0410 02:39:50.120945 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:39:52.504993 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:39:54.644656 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:39:54.644729 27877 solver.cpp:397]     Test net output #1: loss = 5.2863 (* 1 = 5.2863 loss)
I0410 02:39:54.727178 27877 solver.cpp:218] Iteration 5304 (1.08339 iter/s, 11.0763s/12 iters), loss = 5.27115
I0410 02:39:54.727236 27877 solver.cpp:237]     Train net output #0: loss = 5.27115 (* 1 = 5.27115 loss)
I0410 02:39:54.727248 27877 sgd_solver.cpp:105] Iteration 5304, lr = 0.00349711
I0410 02:39:58.801630 27877 solver.cpp:218] Iteration 5316 (2.94531 iter/s, 4.07427s/12 iters), loss = 5.26892
I0410 02:39:58.801692 27877 solver.cpp:237]     Train net output #0: loss = 5.26892 (* 1 = 5.26892 loss)
I0410 02:39:58.801703 27877 sgd_solver.cpp:105] Iteration 5316, lr = 0.00348881
I0410 02:40:03.724959 27877 solver.cpp:218] Iteration 5328 (2.43747 iter/s, 4.92313s/12 iters), loss = 5.25984
I0410 02:40:03.725018 27877 solver.cpp:237]     Train net output #0: loss = 5.25984 (* 1 = 5.25984 loss)
I0410 02:40:03.725029 27877 sgd_solver.cpp:105] Iteration 5328, lr = 0.00348053
I0410 02:40:08.652997 27877 solver.cpp:218] Iteration 5340 (2.43514 iter/s, 4.92785s/12 iters), loss = 5.29744
I0410 02:40:08.653040 27877 solver.cpp:237]     Train net output #0: loss = 5.29744 (* 1 = 5.29744 loss)
I0410 02:40:08.653050 27877 sgd_solver.cpp:105] Iteration 5340, lr = 0.00347226
I0410 02:40:13.576508 27877 solver.cpp:218] Iteration 5352 (2.43738 iter/s, 4.92333s/12 iters), loss = 5.27662
I0410 02:40:13.576563 27877 solver.cpp:237]     Train net output #0: loss = 5.27662 (* 1 = 5.27662 loss)
I0410 02:40:13.576575 27877 sgd_solver.cpp:105] Iteration 5352, lr = 0.00346402
I0410 02:40:16.931185 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:40:18.457890 27877 solver.cpp:218] Iteration 5364 (2.45842 iter/s, 4.88119s/12 iters), loss = 5.27529
I0410 02:40:18.457945 27877 solver.cpp:237]     Train net output #0: loss = 5.27529 (* 1 = 5.27529 loss)
I0410 02:40:18.457973 27877 sgd_solver.cpp:105] Iteration 5364, lr = 0.0034558
I0410 02:40:23.397544 27877 solver.cpp:218] Iteration 5376 (2.42941 iter/s, 4.93947s/12 iters), loss = 5.26767
I0410 02:40:23.397594 27877 solver.cpp:237]     Train net output #0: loss = 5.26767 (* 1 = 5.26767 loss)
I0410 02:40:23.397605 27877 sgd_solver.cpp:105] Iteration 5376, lr = 0.00344759
I0410 02:40:28.299540 27877 solver.cpp:218] Iteration 5388 (2.44808 iter/s, 4.90181s/12 iters), loss = 5.26507
I0410 02:40:28.299670 27877 solver.cpp:237]     Train net output #0: loss = 5.26507 (* 1 = 5.26507 loss)
I0410 02:40:28.299682 27877 sgd_solver.cpp:105] Iteration 5388, lr = 0.00343941
I0410 02:40:33.163142 27877 solver.cpp:218] Iteration 5400 (2.46744 iter/s, 4.86335s/12 iters), loss = 5.26855
I0410 02:40:33.163197 27877 solver.cpp:237]     Train net output #0: loss = 5.26855 (* 1 = 5.26855 loss)
I0410 02:40:33.163210 27877 sgd_solver.cpp:105] Iteration 5400, lr = 0.00343124
I0410 02:40:35.157894 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5406.caffemodel
I0410 02:40:36.726914 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5406.solverstate
I0410 02:40:38.329857 27877 solver.cpp:330] Iteration 5406, Testing net (#0)
I0410 02:40:38.329885 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:40:40.659508 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:40:42.786116 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:40:42.786165 27877 solver.cpp:397]     Test net output #1: loss = 5.2864 (* 1 = 5.2864 loss)
I0410 02:40:44.557153 27877 solver.cpp:218] Iteration 5412 (1.05322 iter/s, 11.3937s/12 iters), loss = 5.26508
I0410 02:40:44.557204 27877 solver.cpp:237]     Train net output #0: loss = 5.26508 (* 1 = 5.26508 loss)
I0410 02:40:44.557214 27877 sgd_solver.cpp:105] Iteration 5412, lr = 0.00342309
I0410 02:40:49.625876 27877 solver.cpp:218] Iteration 5424 (2.36755 iter/s, 5.06854s/12 iters), loss = 5.27907
I0410 02:40:49.625931 27877 solver.cpp:237]     Train net output #0: loss = 5.27907 (* 1 = 5.27907 loss)
I0410 02:40:49.625942 27877 sgd_solver.cpp:105] Iteration 5424, lr = 0.00341497
I0410 02:40:54.478031 27877 solver.cpp:218] Iteration 5436 (2.47323 iter/s, 4.85196s/12 iters), loss = 5.2652
I0410 02:40:54.478091 27877 solver.cpp:237]     Train net output #0: loss = 5.2652 (* 1 = 5.2652 loss)
I0410 02:40:54.478101 27877 sgd_solver.cpp:105] Iteration 5436, lr = 0.00340686
I0410 02:40:59.394975 27877 solver.cpp:218] Iteration 5448 (2.44063 iter/s, 4.91675s/12 iters), loss = 5.27876
I0410 02:40:59.395085 27877 solver.cpp:237]     Train net output #0: loss = 5.27876 (* 1 = 5.27876 loss)
I0410 02:40:59.395097 27877 sgd_solver.cpp:105] Iteration 5448, lr = 0.00339877
I0410 02:41:04.391261 27877 solver.cpp:218] Iteration 5460 (2.4019 iter/s, 4.99604s/12 iters), loss = 5.27885
I0410 02:41:04.391302 27877 solver.cpp:237]     Train net output #0: loss = 5.27885 (* 1 = 5.27885 loss)
I0410 02:41:04.391310 27877 sgd_solver.cpp:105] Iteration 5460, lr = 0.0033907
I0410 02:41:04.928987 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:41:09.355873 27877 solver.cpp:218] Iteration 5472 (2.4172 iter/s, 4.96442s/12 iters), loss = 5.27704
I0410 02:41:09.355932 27877 solver.cpp:237]     Train net output #0: loss = 5.27704 (* 1 = 5.27704 loss)
I0410 02:41:09.355945 27877 sgd_solver.cpp:105] Iteration 5472, lr = 0.00338265
I0410 02:41:14.376114 27877 solver.cpp:218] Iteration 5484 (2.39042 iter/s, 5.02004s/12 iters), loss = 5.26945
I0410 02:41:14.376157 27877 solver.cpp:237]     Train net output #0: loss = 5.26945 (* 1 = 5.26945 loss)
I0410 02:41:14.376164 27877 sgd_solver.cpp:105] Iteration 5484, lr = 0.00337462
I0410 02:41:19.306126 27877 solver.cpp:218] Iteration 5496 (2.43416 iter/s, 4.92983s/12 iters), loss = 5.28908
I0410 02:41:19.306188 27877 solver.cpp:237]     Train net output #0: loss = 5.28908 (* 1 = 5.28908 loss)
I0410 02:41:19.306205 27877 sgd_solver.cpp:105] Iteration 5496, lr = 0.00336661
I0410 02:41:23.900892 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5508.caffemodel
I0410 02:41:24.741712 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5508.solverstate
I0410 02:41:25.351752 27877 solver.cpp:330] Iteration 5508, Testing net (#0)
I0410 02:41:25.351783 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:41:27.738364 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:41:30.273855 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:41:30.282047 27877 solver.cpp:397]     Test net output #1: loss = 5.28734 (* 1 = 5.28734 loss)
I0410 02:41:30.364413 27877 solver.cpp:218] Iteration 5508 (1.08519 iter/s, 11.0579s/12 iters), loss = 5.27866
I0410 02:41:30.364455 27877 solver.cpp:237]     Train net output #0: loss = 5.27866 (* 1 = 5.27866 loss)
I0410 02:41:30.364464 27877 sgd_solver.cpp:105] Iteration 5508, lr = 0.00335861
I0410 02:41:34.464274 27877 solver.cpp:218] Iteration 5520 (2.92704 iter/s, 4.0997s/12 iters), loss = 5.27691
I0410 02:41:34.464318 27877 solver.cpp:237]     Train net output #0: loss = 5.27691 (* 1 = 5.27691 loss)
I0410 02:41:34.464326 27877 sgd_solver.cpp:105] Iteration 5520, lr = 0.00335064
I0410 02:41:36.027477 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:41:39.360008 27877 solver.cpp:218] Iteration 5532 (2.4512 iter/s, 4.89555s/12 iters), loss = 5.28502
I0410 02:41:39.360051 27877 solver.cpp:237]     Train net output #0: loss = 5.28502 (* 1 = 5.28502 loss)
I0410 02:41:39.360060 27877 sgd_solver.cpp:105] Iteration 5532, lr = 0.00334268
I0410 02:41:44.284384 27877 solver.cpp:218] Iteration 5544 (2.43695 iter/s, 4.92419s/12 iters), loss = 5.25894
I0410 02:41:44.284440 27877 solver.cpp:237]     Train net output #0: loss = 5.25894 (* 1 = 5.25894 loss)
I0410 02:41:44.284451 27877 sgd_solver.cpp:105] Iteration 5544, lr = 0.00333475
I0410 02:41:49.204540 27877 solver.cpp:218] Iteration 5556 (2.43904 iter/s, 4.91996s/12 iters), loss = 5.27065
I0410 02:41:49.204596 27877 solver.cpp:237]     Train net output #0: loss = 5.27065 (* 1 = 5.27065 loss)
I0410 02:41:49.204608 27877 sgd_solver.cpp:105] Iteration 5556, lr = 0.00332683
I0410 02:41:51.862049 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:41:54.100615 27877 solver.cpp:218] Iteration 5568 (2.45104 iter/s, 4.89589s/12 iters), loss = 5.27818
I0410 02:41:54.100669 27877 solver.cpp:237]     Train net output #0: loss = 5.27818 (* 1 = 5.27818 loss)
I0410 02:41:54.100682 27877 sgd_solver.cpp:105] Iteration 5568, lr = 0.00331893
I0410 02:41:59.045181 27877 solver.cpp:218] Iteration 5580 (2.427 iter/s, 4.94438s/12 iters), loss = 5.26067
I0410 02:41:59.045224 27877 solver.cpp:237]     Train net output #0: loss = 5.26067 (* 1 = 5.26067 loss)
I0410 02:41:59.045233 27877 sgd_solver.cpp:105] Iteration 5580, lr = 0.00331105
I0410 02:42:03.913919 27877 solver.cpp:218] Iteration 5592 (2.4648 iter/s, 4.86856s/12 iters), loss = 5.2716
I0410 02:42:03.914055 27877 solver.cpp:237]     Train net output #0: loss = 5.2716 (* 1 = 5.2716 loss)
I0410 02:42:03.914068 27877 sgd_solver.cpp:105] Iteration 5592, lr = 0.00330319
I0410 02:42:08.837987 27877 solver.cpp:218] Iteration 5604 (2.43715 iter/s, 4.92379s/12 iters), loss = 5.26602
I0410 02:42:08.838038 27877 solver.cpp:237]     Train net output #0: loss = 5.26602 (* 1 = 5.26602 loss)
I0410 02:42:08.838049 27877 sgd_solver.cpp:105] Iteration 5604, lr = 0.00329535
I0410 02:42:10.856472 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5610.caffemodel
I0410 02:42:14.921299 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5610.solverstate
I0410 02:42:18.731106 27877 solver.cpp:330] Iteration 5610, Testing net (#0)
I0410 02:42:18.731133 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:42:20.984134 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:42:23.213418 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:42:23.213451 27877 solver.cpp:397]     Test net output #1: loss = 5.28674 (* 1 = 5.28674 loss)
I0410 02:42:25.039038 27877 solver.cpp:218] Iteration 5616 (0.740714 iter/s, 16.2006s/12 iters), loss = 5.2922
I0410 02:42:25.039084 27877 solver.cpp:237]     Train net output #0: loss = 5.2922 (* 1 = 5.2922 loss)
I0410 02:42:25.039093 27877 sgd_solver.cpp:105] Iteration 5616, lr = 0.00328752
I0410 02:42:29.983031 27877 solver.cpp:218] Iteration 5628 (2.42728 iter/s, 4.94381s/12 iters), loss = 5.27403
I0410 02:42:29.983075 27877 solver.cpp:237]     Train net output #0: loss = 5.27403 (* 1 = 5.27403 loss)
I0410 02:42:29.983084 27877 sgd_solver.cpp:105] Iteration 5628, lr = 0.00327972
I0410 02:42:34.841893 27877 solver.cpp:218] Iteration 5640 (2.4698 iter/s, 4.85869s/12 iters), loss = 5.26386
I0410 02:42:34.842016 27877 solver.cpp:237]     Train net output #0: loss = 5.26386 (* 1 = 5.26386 loss)
I0410 02:42:34.842026 27877 sgd_solver.cpp:105] Iteration 5640, lr = 0.00327193
I0410 02:42:39.789026 27877 solver.cpp:218] Iteration 5652 (2.42578 iter/s, 4.94687s/12 iters), loss = 5.27113
I0410 02:42:39.789070 27877 solver.cpp:237]     Train net output #0: loss = 5.27113 (* 1 = 5.27113 loss)
I0410 02:42:39.789080 27877 sgd_solver.cpp:105] Iteration 5652, lr = 0.00326416
I0410 02:42:44.530225 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:42:44.692288 27877 solver.cpp:218] Iteration 5664 (2.44744 iter/s, 4.90308s/12 iters), loss = 5.25234
I0410 02:42:44.692342 27877 solver.cpp:237]     Train net output #0: loss = 5.25234 (* 1 = 5.25234 loss)
I0410 02:42:44.692351 27877 sgd_solver.cpp:105] Iteration 5664, lr = 0.00325641
I0410 02:42:49.633888 27877 solver.cpp:218] Iteration 5676 (2.42846 iter/s, 4.94141s/12 iters), loss = 5.26692
I0410 02:42:49.633951 27877 solver.cpp:237]     Train net output #0: loss = 5.26692 (* 1 = 5.26692 loss)
I0410 02:42:49.633980 27877 sgd_solver.cpp:105] Iteration 5676, lr = 0.00324868
I0410 02:42:54.716503 27877 solver.cpp:218] Iteration 5688 (2.36108 iter/s, 5.08241s/12 iters), loss = 5.29575
I0410 02:42:54.716554 27877 solver.cpp:237]     Train net output #0: loss = 5.29575 (* 1 = 5.29575 loss)
I0410 02:42:54.716567 27877 sgd_solver.cpp:105] Iteration 5688, lr = 0.00324097
I0410 02:42:59.603997 27877 solver.cpp:218] Iteration 5700 (2.45534 iter/s, 4.88731s/12 iters), loss = 5.28717
I0410 02:42:59.604049 27877 solver.cpp:237]     Train net output #0: loss = 5.28717 (* 1 = 5.28717 loss)
I0410 02:42:59.604061 27877 sgd_solver.cpp:105] Iteration 5700, lr = 0.00323328
I0410 02:43:04.043794 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5712.caffemodel
I0410 02:43:04.879225 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5712.solverstate
I0410 02:43:05.608443 27877 solver.cpp:330] Iteration 5712, Testing net (#0)
I0410 02:43:05.608462 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:43:07.784615 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:43:10.025113 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:43:10.025169 27877 solver.cpp:397]     Test net output #1: loss = 5.28669 (* 1 = 5.28669 loss)
I0410 02:43:10.108083 27877 solver.cpp:218] Iteration 5712 (1.14245 iter/s, 10.5038s/12 iters), loss = 5.28004
I0410 02:43:10.108144 27877 solver.cpp:237]     Train net output #0: loss = 5.28004 (* 1 = 5.28004 loss)
I0410 02:43:10.108155 27877 sgd_solver.cpp:105] Iteration 5712, lr = 0.0032256
I0410 02:43:14.318222 27877 solver.cpp:218] Iteration 5724 (2.85038 iter/s, 4.20996s/12 iters), loss = 5.2711
I0410 02:43:14.318265 27877 solver.cpp:237]     Train net output #0: loss = 5.2711 (* 1 = 5.2711 loss)
I0410 02:43:14.318274 27877 sgd_solver.cpp:105] Iteration 5724, lr = 0.00321794
I0410 02:43:19.244341 27877 solver.cpp:218] Iteration 5736 (2.43608 iter/s, 4.92595s/12 iters), loss = 5.24522
I0410 02:43:19.244380 27877 solver.cpp:237]     Train net output #0: loss = 5.24522 (* 1 = 5.24522 loss)
I0410 02:43:19.244390 27877 sgd_solver.cpp:105] Iteration 5736, lr = 0.0032103
I0410 02:43:24.197336 27877 solver.cpp:218] Iteration 5748 (2.42286 iter/s, 4.95282s/12 iters), loss = 5.27626
I0410 02:43:24.197391 27877 solver.cpp:237]     Train net output #0: loss = 5.27626 (* 1 = 5.27626 loss)
I0410 02:43:24.197402 27877 sgd_solver.cpp:105] Iteration 5748, lr = 0.00320268
I0410 02:43:29.143894 27877 solver.cpp:218] Iteration 5760 (2.42602 iter/s, 4.94637s/12 iters), loss = 5.26471
I0410 02:43:29.143939 27877 solver.cpp:237]     Train net output #0: loss = 5.26471 (* 1 = 5.26471 loss)
I0410 02:43:29.143947 27877 sgd_solver.cpp:105] Iteration 5760, lr = 0.00319508
I0410 02:43:31.040880 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:43:34.068650 27877 solver.cpp:218] Iteration 5772 (2.43676 iter/s, 4.92458s/12 iters), loss = 5.29262
I0410 02:43:34.068691 27877 solver.cpp:237]     Train net output #0: loss = 5.29262 (* 1 = 5.29262 loss)
I0410 02:43:34.068698 27877 sgd_solver.cpp:105] Iteration 5772, lr = 0.00318749
I0410 02:43:39.031240 27877 solver.cpp:218] Iteration 5784 (2.41818 iter/s, 4.96241s/12 iters), loss = 5.27212
I0410 02:43:39.031376 27877 solver.cpp:237]     Train net output #0: loss = 5.27212 (* 1 = 5.27212 loss)
I0410 02:43:39.031388 27877 sgd_solver.cpp:105] Iteration 5784, lr = 0.00317992
I0410 02:43:43.908942 27877 solver.cpp:218] Iteration 5796 (2.46031 iter/s, 4.87744s/12 iters), loss = 5.26996
I0410 02:43:43.908995 27877 solver.cpp:237]     Train net output #0: loss = 5.26996 (* 1 = 5.26996 loss)
I0410 02:43:43.909008 27877 sgd_solver.cpp:105] Iteration 5796, lr = 0.00317237
I0410 02:43:48.834307 27877 solver.cpp:218] Iteration 5808 (2.43646 iter/s, 4.92518s/12 iters), loss = 5.26276
I0410 02:43:48.834352 27877 solver.cpp:237]     Train net output #0: loss = 5.26276 (* 1 = 5.26276 loss)
I0410 02:43:48.834362 27877 sgd_solver.cpp:105] Iteration 5808, lr = 0.00316484
I0410 02:43:50.830725 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5814.caffemodel
I0410 02:43:51.701157 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5814.solverstate
I0410 02:43:52.332386 27877 solver.cpp:330] Iteration 5814, Testing net (#0)
I0410 02:43:52.332414 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:43:54.505152 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:43:56.859304 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:43:56.859352 27877 solver.cpp:397]     Test net output #1: loss = 5.28652 (* 1 = 5.28652 loss)
I0410 02:43:58.728250 27877 solver.cpp:218] Iteration 5820 (1.2129 iter/s, 9.89364s/12 iters), loss = 5.27178
I0410 02:43:58.728302 27877 solver.cpp:237]     Train net output #0: loss = 5.27178 (* 1 = 5.27178 loss)
I0410 02:43:58.728312 27877 sgd_solver.cpp:105] Iteration 5820, lr = 0.00315733
I0410 02:44:03.676201 27877 solver.cpp:218] Iteration 5832 (2.42534 iter/s, 4.94776s/12 iters), loss = 5.27144
I0410 02:44:03.676263 27877 solver.cpp:237]     Train net output #0: loss = 5.27144 (* 1 = 5.27144 loss)
I0410 02:44:03.676278 27877 sgd_solver.cpp:105] Iteration 5832, lr = 0.00314983
I0410 02:44:08.657816 27877 solver.cpp:218] Iteration 5844 (2.40895 iter/s, 4.98142s/12 iters), loss = 5.26107
I0410 02:44:08.657878 27877 solver.cpp:237]     Train net output #0: loss = 5.26107 (* 1 = 5.26107 loss)
I0410 02:44:08.657891 27877 sgd_solver.cpp:105] Iteration 5844, lr = 0.00314235
I0410 02:44:13.582377 27877 solver.cpp:218] Iteration 5856 (2.43686 iter/s, 4.92437s/12 iters), loss = 5.26415
I0410 02:44:13.582499 27877 solver.cpp:237]     Train net output #0: loss = 5.26415 (* 1 = 5.26415 loss)
I0410 02:44:13.582510 27877 sgd_solver.cpp:105] Iteration 5856, lr = 0.00313489
I0410 02:44:17.668072 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:44:18.484359 27877 solver.cpp:218] Iteration 5868 (2.44812 iter/s, 4.90173s/12 iters), loss = 5.25229
I0410 02:44:18.484416 27877 solver.cpp:237]     Train net output #0: loss = 5.25229 (* 1 = 5.25229 loss)
I0410 02:44:18.484426 27877 sgd_solver.cpp:105] Iteration 5868, lr = 0.00312745
I0410 02:44:23.411108 27877 solver.cpp:218] Iteration 5880 (2.43578 iter/s, 4.92656s/12 iters), loss = 5.276
I0410 02:44:23.411164 27877 solver.cpp:237]     Train net output #0: loss = 5.276 (* 1 = 5.276 loss)
I0410 02:44:23.411176 27877 sgd_solver.cpp:105] Iteration 5880, lr = 0.00312002
I0410 02:44:28.341997 27877 solver.cpp:218] Iteration 5892 (2.43373 iter/s, 4.9307s/12 iters), loss = 5.26979
I0410 02:44:28.342043 27877 solver.cpp:237]     Train net output #0: loss = 5.26979 (* 1 = 5.26979 loss)
I0410 02:44:28.342053 27877 sgd_solver.cpp:105] Iteration 5892, lr = 0.00311262
I0410 02:44:33.194487 27877 solver.cpp:218] Iteration 5904 (2.47305 iter/s, 4.85231s/12 iters), loss = 5.30664
I0410 02:44:33.194537 27877 solver.cpp:237]     Train net output #0: loss = 5.30664 (* 1 = 5.30664 loss)
I0410 02:44:33.194550 27877 sgd_solver.cpp:105] Iteration 5904, lr = 0.00310523
I0410 02:44:37.733906 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_5916.caffemodel
I0410 02:44:38.858987 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_5916.solverstate
I0410 02:44:39.478971 27877 solver.cpp:330] Iteration 5916, Testing net (#0)
I0410 02:44:39.479001 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:44:41.789288 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:44:44.147212 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:44:44.147291 27877 solver.cpp:397]     Test net output #1: loss = 5.28659 (* 1 = 5.28659 loss)
I0410 02:44:44.229898 27877 solver.cpp:218] Iteration 5916 (1.08744 iter/s, 11.0351s/12 iters), loss = 5.2708
I0410 02:44:44.229952 27877 solver.cpp:237]     Train net output #0: loss = 5.2708 (* 1 = 5.2708 loss)
I0410 02:44:44.229995 27877 sgd_solver.cpp:105] Iteration 5916, lr = 0.00309785
I0410 02:44:48.374837 27877 solver.cpp:218] Iteration 5928 (2.89522 iter/s, 4.14477s/12 iters), loss = 5.26718
I0410 02:44:48.374897 27877 solver.cpp:237]     Train net output #0: loss = 5.26718 (* 1 = 5.26718 loss)
I0410 02:44:48.374907 27877 sgd_solver.cpp:105] Iteration 5928, lr = 0.0030905
I0410 02:44:53.287111 27877 solver.cpp:218] Iteration 5940 (2.44296 iter/s, 4.91208s/12 iters), loss = 5.28198
I0410 02:44:53.287178 27877 solver.cpp:237]     Train net output #0: loss = 5.28198 (* 1 = 5.28198 loss)
I0410 02:44:53.287194 27877 sgd_solver.cpp:105] Iteration 5940, lr = 0.00308316
I0410 02:44:58.332363 27877 solver.cpp:218] Iteration 5952 (2.37857 iter/s, 5.04505s/12 iters), loss = 5.27403
I0410 02:44:58.332406 27877 solver.cpp:237]     Train net output #0: loss = 5.27403 (* 1 = 5.27403 loss)
I0410 02:44:58.332415 27877 sgd_solver.cpp:105] Iteration 5952, lr = 0.00307584
I0410 02:45:03.359006 27877 solver.cpp:218] Iteration 5964 (2.38737 iter/s, 5.02646s/12 iters), loss = 5.2586
I0410 02:45:03.359058 27877 solver.cpp:237]     Train net output #0: loss = 5.2586 (* 1 = 5.2586 loss)
I0410 02:45:03.359069 27877 sgd_solver.cpp:105] Iteration 5964, lr = 0.00306854
I0410 02:45:04.641527 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:45:08.352713 27877 solver.cpp:218] Iteration 5976 (2.40312 iter/s, 4.99351s/12 iters), loss = 5.27786
I0410 02:45:08.352775 27877 solver.cpp:237]     Train net output #0: loss = 5.27786 (* 1 = 5.27786 loss)
I0410 02:45:08.352787 27877 sgd_solver.cpp:105] Iteration 5976, lr = 0.00306125
I0410 02:45:13.309612 27877 solver.cpp:218] Iteration 5988 (2.42096 iter/s, 4.95671s/12 iters), loss = 5.26671
I0410 02:45:13.309659 27877 solver.cpp:237]     Train net output #0: loss = 5.26671 (* 1 = 5.26671 loss)
I0410 02:45:13.309669 27877 sgd_solver.cpp:105] Iteration 5988, lr = 0.00305398
I0410 02:45:18.265698 27877 solver.cpp:218] Iteration 6000 (2.42136 iter/s, 4.9559s/12 iters), loss = 5.27835
I0410 02:45:18.265846 27877 solver.cpp:237]     Train net output #0: loss = 5.27835 (* 1 = 5.27835 loss)
I0410 02:45:18.265857 27877 sgd_solver.cpp:105] Iteration 6000, lr = 0.00304673
I0410 02:45:23.280433 27877 solver.cpp:218] Iteration 6012 (2.39308 iter/s, 5.01445s/12 iters), loss = 5.27096
I0410 02:45:23.280488 27877 solver.cpp:237]     Train net output #0: loss = 5.27096 (* 1 = 5.27096 loss)
I0410 02:45:23.280499 27877 sgd_solver.cpp:105] Iteration 6012, lr = 0.0030395
I0410 02:45:25.326433 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6018.caffemodel
I0410 02:45:26.182595 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6018.solverstate
I0410 02:45:26.801467 27877 solver.cpp:330] Iteration 6018, Testing net (#0)
I0410 02:45:26.801497 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:45:28.853612 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:45:31.310813 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:45:31.310858 27877 solver.cpp:397]     Test net output #1: loss = 5.28656 (* 1 = 5.28656 loss)
I0410 02:45:33.283882 27877 solver.cpp:218] Iteration 6024 (1.19962 iter/s, 10.0031s/12 iters), loss = 5.26388
I0410 02:45:33.283938 27877 solver.cpp:237]     Train net output #0: loss = 5.26388 (* 1 = 5.26388 loss)
I0410 02:45:33.283951 27877 sgd_solver.cpp:105] Iteration 6024, lr = 0.00303228
I0410 02:45:38.378526 27877 solver.cpp:218] Iteration 6036 (2.3555 iter/s, 5.09445s/12 iters), loss = 5.26464
I0410 02:45:38.378572 27877 solver.cpp:237]     Train net output #0: loss = 5.26464 (* 1 = 5.26464 loss)
I0410 02:45:38.378583 27877 sgd_solver.cpp:105] Iteration 6036, lr = 0.00302508
I0410 02:45:43.293404 27877 solver.cpp:218] Iteration 6048 (2.44166 iter/s, 4.9147s/12 iters), loss = 5.30376
I0410 02:45:43.293454 27877 solver.cpp:237]     Train net output #0: loss = 5.30376 (* 1 = 5.30376 loss)
I0410 02:45:43.293467 27877 sgd_solver.cpp:105] Iteration 6048, lr = 0.0030179
I0410 02:45:48.236292 27877 solver.cpp:218] Iteration 6060 (2.42782 iter/s, 4.9427s/12 iters), loss = 5.27696
I0410 02:45:48.236346 27877 solver.cpp:237]     Train net output #0: loss = 5.27696 (* 1 = 5.27696 loss)
I0410 02:45:48.236358 27877 sgd_solver.cpp:105] Iteration 6060, lr = 0.00301074
I0410 02:45:51.575294 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:45:53.096799 27877 solver.cpp:218] Iteration 6072 (2.46897 iter/s, 4.86032s/12 iters), loss = 5.2748
I0410 02:45:53.096853 27877 solver.cpp:237]     Train net output #0: loss = 5.2748 (* 1 = 5.2748 loss)
I0410 02:45:53.096864 27877 sgd_solver.cpp:105] Iteration 6072, lr = 0.00300359
I0410 02:45:58.168958 27877 solver.cpp:218] Iteration 6084 (2.36595 iter/s, 5.07196s/12 iters), loss = 5.26111
I0410 02:45:58.169016 27877 solver.cpp:237]     Train net output #0: loss = 5.26111 (* 1 = 5.26111 loss)
I0410 02:45:58.169028 27877 sgd_solver.cpp:105] Iteration 6084, lr = 0.00299646
I0410 02:46:03.129083 27877 solver.cpp:218] Iteration 6096 (2.41939 iter/s, 4.95993s/12 iters), loss = 5.26438
I0410 02:46:03.129133 27877 solver.cpp:237]     Train net output #0: loss = 5.26438 (* 1 = 5.26438 loss)
I0410 02:46:03.129144 27877 sgd_solver.cpp:105] Iteration 6096, lr = 0.00298934
I0410 02:46:08.102772 27877 solver.cpp:218] Iteration 6108 (2.41278 iter/s, 4.97351s/12 iters), loss = 5.27424
I0410 02:46:08.102816 27877 solver.cpp:237]     Train net output #0: loss = 5.27424 (* 1 = 5.27424 loss)
I0410 02:46:08.102828 27877 sgd_solver.cpp:105] Iteration 6108, lr = 0.00298225
I0410 02:46:12.559087 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6120.caffemodel
I0410 02:46:14.183543 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6120.solverstate
I0410 02:46:14.822240 27877 solver.cpp:330] Iteration 6120, Testing net (#0)
I0410 02:46:14.822269 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:46:16.786738 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:46:19.341265 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:46:19.341310 27877 solver.cpp:397]     Test net output #1: loss = 5.28647 (* 1 = 5.28647 loss)
I0410 02:46:19.423943 27877 solver.cpp:218] Iteration 6120 (1.05999 iter/s, 11.3208s/12 iters), loss = 5.26672
I0410 02:46:19.423985 27877 solver.cpp:237]     Train net output #0: loss = 5.26672 (* 1 = 5.26672 loss)
I0410 02:46:19.423995 27877 sgd_solver.cpp:105] Iteration 6120, lr = 0.00297517
I0410 02:46:23.893765 27877 solver.cpp:218] Iteration 6132 (2.68477 iter/s, 4.46965s/12 iters), loss = 5.27441
I0410 02:46:23.893894 27877 solver.cpp:237]     Train net output #0: loss = 5.27441 (* 1 = 5.27441 loss)
I0410 02:46:23.893908 27877 sgd_solver.cpp:105] Iteration 6132, lr = 0.0029681
I0410 02:46:28.916981 27877 solver.cpp:218] Iteration 6144 (2.38903 iter/s, 5.02296s/12 iters), loss = 5.26908
I0410 02:46:28.917024 27877 solver.cpp:237]     Train net output #0: loss = 5.26908 (* 1 = 5.26908 loss)
I0410 02:46:28.917034 27877 sgd_solver.cpp:105] Iteration 6144, lr = 0.00296105
I0410 02:46:33.907614 27877 solver.cpp:218] Iteration 6156 (2.40459 iter/s, 4.99045s/12 iters), loss = 5.2763
I0410 02:46:33.907661 27877 solver.cpp:237]     Train net output #0: loss = 5.2763 (* 1 = 5.2763 loss)
I0410 02:46:33.907670 27877 sgd_solver.cpp:105] Iteration 6156, lr = 0.00295402
I0410 02:46:38.959659 27877 solver.cpp:218] Iteration 6168 (2.37537 iter/s, 5.05185s/12 iters), loss = 5.28885
I0410 02:46:38.959715 27877 solver.cpp:237]     Train net output #0: loss = 5.28885 (* 1 = 5.28885 loss)
I0410 02:46:38.959726 27877 sgd_solver.cpp:105] Iteration 6168, lr = 0.00294701
I0410 02:46:39.555327 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:46:43.939040 27877 solver.cpp:218] Iteration 6180 (2.41003 iter/s, 4.97919s/12 iters), loss = 5.28072
I0410 02:46:43.939080 27877 solver.cpp:237]     Train net output #0: loss = 5.28072 (* 1 = 5.28072 loss)
I0410 02:46:43.939088 27877 sgd_solver.cpp:105] Iteration 6180, lr = 0.00294001
I0410 02:46:48.864683 27877 solver.cpp:218] Iteration 6192 (2.43632 iter/s, 4.92547s/12 iters), loss = 5.26731
I0410 02:46:48.864739 27877 solver.cpp:237]     Train net output #0: loss = 5.26731 (* 1 = 5.26731 loss)
I0410 02:46:48.864750 27877 sgd_solver.cpp:105] Iteration 6192, lr = 0.00293303
I0410 02:46:53.819905 27877 solver.cpp:218] Iteration 6204 (2.42178 iter/s, 4.95503s/12 iters), loss = 5.28699
I0410 02:46:53.819962 27877 solver.cpp:237]     Train net output #0: loss = 5.28699 (* 1 = 5.28699 loss)
I0410 02:46:53.819974 27877 sgd_solver.cpp:105] Iteration 6204, lr = 0.00292607
I0410 02:46:58.880549 27877 solver.cpp:218] Iteration 6216 (2.37133 iter/s, 5.06045s/12 iters), loss = 5.27953
I0410 02:46:58.880661 27877 solver.cpp:237]     Train net output #0: loss = 5.27953 (* 1 = 5.27953 loss)
I0410 02:46:58.880674 27877 sgd_solver.cpp:105] Iteration 6216, lr = 0.00291912
I0410 02:47:00.887989 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6222.caffemodel
I0410 02:47:02.448941 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6222.solverstate
I0410 02:47:03.710614 27877 solver.cpp:330] Iteration 6222, Testing net (#0)
I0410 02:47:03.710644 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:47:05.757292 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:47:06.861738 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:47:08.234323 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:47:08.234369 27877 solver.cpp:397]     Test net output #1: loss = 5.28629 (* 1 = 5.28629 loss)
I0410 02:47:10.087536 27877 solver.cpp:218] Iteration 6228 (1.0708 iter/s, 11.2066s/12 iters), loss = 5.27968
I0410 02:47:10.087595 27877 solver.cpp:237]     Train net output #0: loss = 5.27968 (* 1 = 5.27968 loss)
I0410 02:47:10.087606 27877 sgd_solver.cpp:105] Iteration 6228, lr = 0.00291219
I0410 02:47:15.017290 27877 solver.cpp:218] Iteration 6240 (2.43429 iter/s, 4.92956s/12 iters), loss = 5.28173
I0410 02:47:15.017346 27877 solver.cpp:237]     Train net output #0: loss = 5.28173 (* 1 = 5.28173 loss)
I0410 02:47:15.017359 27877 sgd_solver.cpp:105] Iteration 6240, lr = 0.00290528
I0410 02:47:19.964972 27877 solver.cpp:218] Iteration 6252 (2.42547 iter/s, 4.94749s/12 iters), loss = 5.26
I0410 02:47:19.965019 27877 solver.cpp:237]     Train net output #0: loss = 5.26 (* 1 = 5.26 loss)
I0410 02:47:19.965031 27877 sgd_solver.cpp:105] Iteration 6252, lr = 0.00289838
I0410 02:47:24.879438 27877 solver.cpp:218] Iteration 6264 (2.44186 iter/s, 4.91429s/12 iters), loss = 5.26747
I0410 02:47:24.879485 27877 solver.cpp:237]     Train net output #0: loss = 5.26747 (* 1 = 5.26747 loss)
I0410 02:47:24.879498 27877 sgd_solver.cpp:105] Iteration 6264, lr = 0.0028915
I0410 02:47:27.559072 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:47:29.822216 27877 solver.cpp:218] Iteration 6276 (2.42787 iter/s, 4.9426s/12 iters), loss = 5.27809
I0410 02:47:29.822324 27877 solver.cpp:237]     Train net output #0: loss = 5.27809 (* 1 = 5.27809 loss)
I0410 02:47:29.822335 27877 sgd_solver.cpp:105] Iteration 6276, lr = 0.00288463
I0410 02:47:34.718545 27877 solver.cpp:218] Iteration 6288 (2.45093 iter/s, 4.89609s/12 iters), loss = 5.26191
I0410 02:47:34.718587 27877 solver.cpp:237]     Train net output #0: loss = 5.26191 (* 1 = 5.26191 loss)
I0410 02:47:34.718596 27877 sgd_solver.cpp:105] Iteration 6288, lr = 0.00287779
I0410 02:47:39.674067 27877 solver.cpp:218] Iteration 6300 (2.42163 iter/s, 4.95534s/12 iters), loss = 5.27059
I0410 02:47:39.674119 27877 solver.cpp:237]     Train net output #0: loss = 5.27059 (* 1 = 5.27059 loss)
I0410 02:47:39.674131 27877 sgd_solver.cpp:105] Iteration 6300, lr = 0.00287095
I0410 02:47:44.542312 27877 solver.cpp:218] Iteration 6312 (2.46505 iter/s, 4.86806s/12 iters), loss = 5.26257
I0410 02:47:44.542368 27877 solver.cpp:237]     Train net output #0: loss = 5.26257 (* 1 = 5.26257 loss)
I0410 02:47:44.542380 27877 sgd_solver.cpp:105] Iteration 6312, lr = 0.00286414
I0410 02:47:49.305193 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6324.caffemodel
I0410 02:47:50.192864 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6324.solverstate
I0410 02:47:50.816556 27877 solver.cpp:330] Iteration 6324, Testing net (#0)
I0410 02:47:50.816587 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:47:53.058328 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:47:55.533726 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:47:55.533774 27877 solver.cpp:397]     Test net output #1: loss = 5.28644 (* 1 = 5.28644 loss)
I0410 02:47:55.616348 27877 solver.cpp:218] Iteration 6324 (1.08365 iter/s, 11.0737s/12 iters), loss = 5.3003
I0410 02:47:55.616400 27877 solver.cpp:237]     Train net output #0: loss = 5.3003 (* 1 = 5.3003 loss)
I0410 02:47:55.616410 27877 sgd_solver.cpp:105] Iteration 6324, lr = 0.00285734
I0410 02:47:59.712831 27877 solver.cpp:218] Iteration 6336 (2.92946 iter/s, 4.09631s/12 iters), loss = 5.26822
I0410 02:47:59.712888 27877 solver.cpp:237]     Train net output #0: loss = 5.26822 (* 1 = 5.26822 loss)
I0410 02:47:59.712899 27877 sgd_solver.cpp:105] Iteration 6336, lr = 0.00285055
I0410 02:48:04.599815 27877 solver.cpp:218] Iteration 6348 (2.4556 iter/s, 4.8868s/12 iters), loss = 5.26513
I0410 02:48:04.599949 27877 solver.cpp:237]     Train net output #0: loss = 5.26513 (* 1 = 5.26513 loss)
I0410 02:48:04.599959 27877 sgd_solver.cpp:105] Iteration 6348, lr = 0.00284379
I0410 02:48:09.483170 27877 solver.cpp:218] Iteration 6360 (2.45746 iter/s, 4.88309s/12 iters), loss = 5.26987
I0410 02:48:09.483211 27877 solver.cpp:237]     Train net output #0: loss = 5.26987 (* 1 = 5.26987 loss)
I0410 02:48:09.483218 27877 sgd_solver.cpp:105] Iteration 6360, lr = 0.00283703
I0410 02:48:14.316619 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:48:14.459709 27877 solver.cpp:218] Iteration 6372 (2.4114 iter/s, 4.97636s/12 iters), loss = 5.2524
I0410 02:48:14.459753 27877 solver.cpp:237]     Train net output #0: loss = 5.2524 (* 1 = 5.2524 loss)
I0410 02:48:14.459762 27877 sgd_solver.cpp:105] Iteration 6372, lr = 0.0028303
I0410 02:48:19.500349 27877 solver.cpp:218] Iteration 6384 (2.38074 iter/s, 5.04046s/12 iters), loss = 5.26881
I0410 02:48:19.500401 27877 solver.cpp:237]     Train net output #0: loss = 5.26881 (* 1 = 5.26881 loss)
I0410 02:48:19.500413 27877 sgd_solver.cpp:105] Iteration 6384, lr = 0.00282358
I0410 02:48:24.434082 27877 solver.cpp:218] Iteration 6396 (2.43233 iter/s, 4.93355s/12 iters), loss = 5.29695
I0410 02:48:24.434139 27877 solver.cpp:237]     Train net output #0: loss = 5.29695 (* 1 = 5.29695 loss)
I0410 02:48:24.434151 27877 sgd_solver.cpp:105] Iteration 6396, lr = 0.00281687
I0410 02:48:29.319094 27877 solver.cpp:218] Iteration 6408 (2.45659 iter/s, 4.88482s/12 iters), loss = 5.28273
I0410 02:48:29.319154 27877 solver.cpp:237]     Train net output #0: loss = 5.28273 (* 1 = 5.28273 loss)
I0410 02:48:29.319165 27877 sgd_solver.cpp:105] Iteration 6408, lr = 0.00281019
I0410 02:48:34.204217 27877 solver.cpp:218] Iteration 6420 (2.45653 iter/s, 4.88493s/12 iters), loss = 5.28142
I0410 02:48:34.204277 27877 solver.cpp:237]     Train net output #0: loss = 5.28142 (* 1 = 5.28142 loss)
I0410 02:48:34.204291 27877 sgd_solver.cpp:105] Iteration 6420, lr = 0.00280351
I0410 02:48:36.198406 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6426.caffemodel
I0410 02:48:38.401186 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6426.solverstate
I0410 02:48:40.104179 27877 solver.cpp:330] Iteration 6426, Testing net (#0)
I0410 02:48:40.104209 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:48:42.048507 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:48:44.576602 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:48:44.576648 27877 solver.cpp:397]     Test net output #1: loss = 5.28635 (* 1 = 5.28635 loss)
I0410 02:48:46.404732 27877 solver.cpp:218] Iteration 6432 (0.983594 iter/s, 12.2001s/12 iters), loss = 5.26921
I0410 02:48:46.404778 27877 solver.cpp:237]     Train net output #0: loss = 5.26921 (* 1 = 5.26921 loss)
I0410 02:48:46.404788 27877 sgd_solver.cpp:105] Iteration 6432, lr = 0.00279686
I0410 02:48:51.302415 27877 solver.cpp:218] Iteration 6444 (2.45023 iter/s, 4.8975s/12 iters), loss = 5.2441
I0410 02:48:51.302456 27877 solver.cpp:237]     Train net output #0: loss = 5.2441 (* 1 = 5.2441 loss)
I0410 02:48:51.302466 27877 sgd_solver.cpp:105] Iteration 6444, lr = 0.00279022
I0410 02:48:56.195458 27877 solver.cpp:218] Iteration 6456 (2.45255 iter/s, 4.89287s/12 iters), loss = 5.2729
I0410 02:48:56.195511 27877 solver.cpp:237]     Train net output #0: loss = 5.2729 (* 1 = 5.2729 loss)
I0410 02:48:56.195523 27877 sgd_solver.cpp:105] Iteration 6456, lr = 0.00278359
I0410 02:49:01.171744 27877 solver.cpp:218] Iteration 6468 (2.41153 iter/s, 4.9761s/12 iters), loss = 5.26698
I0410 02:49:01.171787 27877 solver.cpp:237]     Train net output #0: loss = 5.26698 (* 1 = 5.26698 loss)
I0410 02:49:01.171795 27877 sgd_solver.cpp:105] Iteration 6468, lr = 0.00277698
I0410 02:49:03.118654 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:49:06.037560 27877 solver.cpp:218] Iteration 6480 (2.46627 iter/s, 4.86564s/12 iters), loss = 5.29146
I0410 02:49:06.037606 27877 solver.cpp:237]     Train net output #0: loss = 5.29146 (* 1 = 5.29146 loss)
I0410 02:49:06.037614 27877 sgd_solver.cpp:105] Iteration 6480, lr = 0.00277039
I0410 02:49:10.944878 27877 solver.cpp:218] Iteration 6492 (2.44542 iter/s, 4.90714s/12 iters), loss = 5.26688
I0410 02:49:10.945003 27877 solver.cpp:237]     Train net output #0: loss = 5.26688 (* 1 = 5.26688 loss)
I0410 02:49:10.945012 27877 sgd_solver.cpp:105] Iteration 6492, lr = 0.00276381
I0410 02:49:15.792915 27877 solver.cpp:218] Iteration 6504 (2.47536 iter/s, 4.84778s/12 iters), loss = 5.27441
I0410 02:49:15.792963 27877 solver.cpp:237]     Train net output #0: loss = 5.27441 (* 1 = 5.27441 loss)
I0410 02:49:15.792971 27877 sgd_solver.cpp:105] Iteration 6504, lr = 0.00275725
I0410 02:49:20.763274 27877 solver.cpp:218] Iteration 6516 (2.4144 iter/s, 4.97018s/12 iters), loss = 5.26619
I0410 02:49:20.763317 27877 solver.cpp:237]     Train net output #0: loss = 5.26619 (* 1 = 5.26619 loss)
I0410 02:49:20.763326 27877 sgd_solver.cpp:105] Iteration 6516, lr = 0.00275071
I0410 02:49:25.248570 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6528.caffemodel
I0410 02:49:26.288609 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6528.solverstate
I0410 02:49:26.890738 27877 solver.cpp:330] Iteration 6528, Testing net (#0)
I0410 02:49:26.890758 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:49:28.759138 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:49:31.361886 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:49:31.361933 27877 solver.cpp:397]     Test net output #1: loss = 5.28646 (* 1 = 5.28646 loss)
I0410 02:49:31.444478 27877 solver.cpp:218] Iteration 6528 (1.1235 iter/s, 10.6809s/12 iters), loss = 5.27468
I0410 02:49:31.444530 27877 solver.cpp:237]     Train net output #0: loss = 5.27468 (* 1 = 5.27468 loss)
I0410 02:49:31.444541 27877 sgd_solver.cpp:105] Iteration 6528, lr = 0.00274418
I0410 02:49:35.599958 27877 solver.cpp:218] Iteration 6540 (2.88787 iter/s, 4.15531s/12 iters), loss = 5.27181
I0410 02:49:35.600018 27877 solver.cpp:237]     Train net output #0: loss = 5.27181 (* 1 = 5.27181 loss)
I0410 02:49:35.600031 27877 sgd_solver.cpp:105] Iteration 6540, lr = 0.00273766
I0410 02:49:40.447839 27877 solver.cpp:218] Iteration 6552 (2.47541 iter/s, 4.84768s/12 iters), loss = 5.2695
I0410 02:49:40.447888 27877 solver.cpp:237]     Train net output #0: loss = 5.2695 (* 1 = 5.2695 loss)
I0410 02:49:40.447899 27877 sgd_solver.cpp:105] Iteration 6552, lr = 0.00273116
I0410 02:49:45.398866 27877 solver.cpp:218] Iteration 6564 (2.42383 iter/s, 4.95084s/12 iters), loss = 5.25963
I0410 02:49:45.398978 27877 solver.cpp:237]     Train net output #0: loss = 5.25963 (* 1 = 5.25963 loss)
I0410 02:49:45.398993 27877 sgd_solver.cpp:105] Iteration 6564, lr = 0.00272468
I0410 02:49:49.488402 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:49:50.248359 27877 solver.cpp:218] Iteration 6576 (2.47461 iter/s, 4.84925s/12 iters), loss = 5.25331
I0410 02:49:50.248411 27877 solver.cpp:237]     Train net output #0: loss = 5.25331 (* 1 = 5.25331 loss)
I0410 02:49:50.248423 27877 sgd_solver.cpp:105] Iteration 6576, lr = 0.00271821
I0410 02:49:55.149366 27877 solver.cpp:218] Iteration 6588 (2.44857 iter/s, 4.90082s/12 iters), loss = 5.2786
I0410 02:49:55.149416 27877 solver.cpp:237]     Train net output #0: loss = 5.2786 (* 1 = 5.2786 loss)
I0410 02:49:55.149426 27877 sgd_solver.cpp:105] Iteration 6588, lr = 0.00271175
I0410 02:50:00.176203 27877 solver.cpp:218] Iteration 6600 (2.38727 iter/s, 5.02665s/12 iters), loss = 5.27264
I0410 02:50:00.176251 27877 solver.cpp:237]     Train net output #0: loss = 5.27264 (* 1 = 5.27264 loss)
I0410 02:50:00.176263 27877 sgd_solver.cpp:105] Iteration 6600, lr = 0.00270532
I0410 02:50:05.012146 27877 solver.cpp:218] Iteration 6612 (2.48151 iter/s, 4.83576s/12 iters), loss = 5.29988
I0410 02:50:05.012199 27877 solver.cpp:237]     Train net output #0: loss = 5.29988 (* 1 = 5.29988 loss)
I0410 02:50:05.012212 27877 sgd_solver.cpp:105] Iteration 6612, lr = 0.00269889
I0410 02:50:09.963318 27877 solver.cpp:218] Iteration 6624 (2.42376 iter/s, 4.95099s/12 iters), loss = 5.27248
I0410 02:50:09.963356 27877 solver.cpp:237]     Train net output #0: loss = 5.27248 (* 1 = 5.27248 loss)
I0410 02:50:09.963366 27877 sgd_solver.cpp:105] Iteration 6624, lr = 0.00269248
I0410 02:50:11.971382 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6630.caffemodel
I0410 02:50:14.073426 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6630.solverstate
I0410 02:50:15.205821 27877 solver.cpp:330] Iteration 6630, Testing net (#0)
I0410 02:50:15.205853 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:50:17.069358 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:50:19.825119 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:50:19.825170 27877 solver.cpp:397]     Test net output #1: loss = 5.28659 (* 1 = 5.28659 loss)
I0410 02:50:21.664527 27877 solver.cpp:218] Iteration 6636 (1.02556 iter/s, 11.7009s/12 iters), loss = 5.27428
I0410 02:50:21.664578 27877 solver.cpp:237]     Train net output #0: loss = 5.27428 (* 1 = 5.27428 loss)
I0410 02:50:21.664589 27877 sgd_solver.cpp:105] Iteration 6636, lr = 0.00268609
I0410 02:50:26.514503 27877 solver.cpp:218] Iteration 6648 (2.47434 iter/s, 4.84978s/12 iters), loss = 5.27808
I0410 02:50:26.514561 27877 solver.cpp:237]     Train net output #0: loss = 5.27808 (* 1 = 5.27808 loss)
I0410 02:50:26.514572 27877 sgd_solver.cpp:105] Iteration 6648, lr = 0.00267971
I0410 02:50:31.489152 27877 solver.cpp:218] Iteration 6660 (2.41232 iter/s, 4.97446s/12 iters), loss = 5.28232
I0410 02:50:31.489193 27877 solver.cpp:237]     Train net output #0: loss = 5.28232 (* 1 = 5.28232 loss)
I0410 02:50:31.489202 27877 sgd_solver.cpp:105] Iteration 6660, lr = 0.00267335
I0410 02:50:36.468787 27877 solver.cpp:218] Iteration 6672 (2.4099 iter/s, 4.97946s/12 iters), loss = 5.26581
I0410 02:50:36.468837 27877 solver.cpp:237]     Train net output #0: loss = 5.26581 (* 1 = 5.26581 loss)
I0410 02:50:36.468845 27877 sgd_solver.cpp:105] Iteration 6672, lr = 0.00266701
I0410 02:50:37.828398 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:50:41.494840 27877 solver.cpp:218] Iteration 6684 (2.38765 iter/s, 5.02587s/12 iters), loss = 5.2754
I0410 02:50:41.494881 27877 solver.cpp:237]     Train net output #0: loss = 5.2754 (* 1 = 5.2754 loss)
I0410 02:50:41.494889 27877 sgd_solver.cpp:105] Iteration 6684, lr = 0.00266067
I0410 02:50:46.485559 27877 solver.cpp:218] Iteration 6696 (2.40455 iter/s, 4.99054s/12 iters), loss = 5.26859
I0410 02:50:46.485605 27877 solver.cpp:237]     Train net output #0: loss = 5.26859 (* 1 = 5.26859 loss)
I0410 02:50:46.485616 27877 sgd_solver.cpp:105] Iteration 6696, lr = 0.00265436
I0410 02:50:51.590180 27877 solver.cpp:218] Iteration 6708 (2.3509 iter/s, 5.10443s/12 iters), loss = 5.2771
I0410 02:50:51.590335 27877 solver.cpp:237]     Train net output #0: loss = 5.2771 (* 1 = 5.2771 loss)
I0410 02:50:51.590358 27877 sgd_solver.cpp:105] Iteration 6708, lr = 0.00264805
I0410 02:50:56.705583 27877 solver.cpp:218] Iteration 6720 (2.34598 iter/s, 5.11513s/12 iters), loss = 5.26946
I0410 02:50:56.705633 27877 solver.cpp:237]     Train net output #0: loss = 5.26946 (* 1 = 5.26946 loss)
I0410 02:50:56.705644 27877 sgd_solver.cpp:105] Iteration 6720, lr = 0.00264177
I0410 02:51:01.427615 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6732.caffemodel
I0410 02:51:02.990245 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6732.solverstate
I0410 02:51:04.340312 27877 solver.cpp:330] Iteration 6732, Testing net (#0)
I0410 02:51:04.340340 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:51:06.038117 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:51:08.669951 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:51:08.670017 27877 solver.cpp:397]     Test net output #1: loss = 5.28634 (* 1 = 5.28634 loss)
I0410 02:51:08.752784 27877 solver.cpp:218] Iteration 6732 (0.996112 iter/s, 12.0468s/12 iters), loss = 5.26769
I0410 02:51:08.752846 27877 solver.cpp:237]     Train net output #0: loss = 5.26769 (* 1 = 5.26769 loss)
I0410 02:51:08.752859 27877 sgd_solver.cpp:105] Iteration 6732, lr = 0.0026355
I0410 02:51:13.059842 27877 solver.cpp:218] Iteration 6744 (2.78624 iter/s, 4.30689s/12 iters), loss = 5.26235
I0410 02:51:13.059888 27877 solver.cpp:237]     Train net output #0: loss = 5.26235 (* 1 = 5.26235 loss)
I0410 02:51:13.059900 27877 sgd_solver.cpp:105] Iteration 6744, lr = 0.00262924
I0410 02:51:18.043645 27877 solver.cpp:218] Iteration 6756 (2.40789 iter/s, 4.98362s/12 iters), loss = 5.29133
I0410 02:51:18.043697 27877 solver.cpp:237]     Train net output #0: loss = 5.29133 (* 1 = 5.29133 loss)
I0410 02:51:18.043709 27877 sgd_solver.cpp:105] Iteration 6756, lr = 0.002623
I0410 02:51:23.032812 27877 solver.cpp:218] Iteration 6768 (2.4053 iter/s, 4.98898s/12 iters), loss = 5.27123
I0410 02:51:23.032963 27877 solver.cpp:237]     Train net output #0: loss = 5.27123 (* 1 = 5.27123 loss)
I0410 02:51:23.032977 27877 sgd_solver.cpp:105] Iteration 6768, lr = 0.00261677
I0410 02:51:26.510931 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:51:28.003819 27877 solver.cpp:218] Iteration 6780 (2.41413 iter/s, 4.97073s/12 iters), loss = 5.27731
I0410 02:51:28.003872 27877 solver.cpp:237]     Train net output #0: loss = 5.27731 (* 1 = 5.27731 loss)
I0410 02:51:28.003885 27877 sgd_solver.cpp:105] Iteration 6780, lr = 0.00261056
I0410 02:51:32.923030 27877 solver.cpp:218] Iteration 6792 (2.43951 iter/s, 4.91902s/12 iters), loss = 5.25968
I0410 02:51:32.923082 27877 solver.cpp:237]     Train net output #0: loss = 5.25968 (* 1 = 5.25968 loss)
I0410 02:51:32.923094 27877 sgd_solver.cpp:105] Iteration 6792, lr = 0.00260436
I0410 02:51:37.833074 27877 solver.cpp:218] Iteration 6804 (2.44406 iter/s, 4.90986s/12 iters), loss = 5.26585
I0410 02:51:37.833123 27877 solver.cpp:237]     Train net output #0: loss = 5.26585 (* 1 = 5.26585 loss)
I0410 02:51:37.833134 27877 sgd_solver.cpp:105] Iteration 6804, lr = 0.00259817
I0410 02:51:42.728466 27877 solver.cpp:218] Iteration 6816 (2.45138 iter/s, 4.8952s/12 iters), loss = 5.27671
I0410 02:51:42.728525 27877 solver.cpp:237]     Train net output #0: loss = 5.27671 (* 1 = 5.27671 loss)
I0410 02:51:42.728538 27877 sgd_solver.cpp:105] Iteration 6816, lr = 0.00259201
I0410 02:51:47.706248 27877 solver.cpp:218] Iteration 6828 (2.4108 iter/s, 4.97759s/12 iters), loss = 5.26925
I0410 02:51:47.706292 27877 solver.cpp:237]     Train net output #0: loss = 5.26925 (* 1 = 5.26925 loss)
I0410 02:51:47.706303 27877 sgd_solver.cpp:105] Iteration 6828, lr = 0.00258585
I0410 02:51:49.767992 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6834.caffemodel
I0410 02:51:50.620998 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6834.solverstate
I0410 02:51:51.241514 27877 solver.cpp:330] Iteration 6834, Testing net (#0)
I0410 02:51:51.241537 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:51:53.023252 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:51:55.769024 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:51:55.769130 27877 solver.cpp:397]     Test net output #1: loss = 5.28711 (* 1 = 5.28711 loss)
I0410 02:51:57.598351 27877 solver.cpp:218] Iteration 6840 (1.21313 iter/s, 9.89181s/12 iters), loss = 5.27258
I0410 02:51:57.598395 27877 solver.cpp:237]     Train net output #0: loss = 5.27258 (* 1 = 5.27258 loss)
I0410 02:51:57.598407 27877 sgd_solver.cpp:105] Iteration 6840, lr = 0.00257971
I0410 02:52:02.755383 27877 solver.cpp:218] Iteration 6852 (2.32701 iter/s, 5.15684s/12 iters), loss = 5.27619
I0410 02:52:02.755439 27877 solver.cpp:237]     Train net output #0: loss = 5.27619 (* 1 = 5.27619 loss)
I0410 02:52:02.755451 27877 sgd_solver.cpp:105] Iteration 6852, lr = 0.00257359
I0410 02:52:07.711596 27877 solver.cpp:218] Iteration 6864 (2.42129 iter/s, 4.95603s/12 iters), loss = 5.27905
I0410 02:52:07.711637 27877 solver.cpp:237]     Train net output #0: loss = 5.27905 (* 1 = 5.27905 loss)
I0410 02:52:07.711647 27877 sgd_solver.cpp:105] Iteration 6864, lr = 0.00256748
I0410 02:52:12.626814 27877 solver.cpp:218] Iteration 6876 (2.44149 iter/s, 4.91504s/12 iters), loss = 5.2825
I0410 02:52:12.626873 27877 solver.cpp:237]     Train net output #0: loss = 5.2825 (* 1 = 5.2825 loss)
I0410 02:52:12.626883 27877 sgd_solver.cpp:105] Iteration 6876, lr = 0.00256138
I0410 02:52:13.228621 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:52:17.557541 27877 solver.cpp:218] Iteration 6888 (2.43381 iter/s, 4.93054s/12 iters), loss = 5.27994
I0410 02:52:17.557595 27877 solver.cpp:237]     Train net output #0: loss = 5.27994 (* 1 = 5.27994 loss)
I0410 02:52:17.557605 27877 sgd_solver.cpp:105] Iteration 6888, lr = 0.0025553
I0410 02:52:22.435303 27877 solver.cpp:218] Iteration 6900 (2.46024 iter/s, 4.87757s/12 iters), loss = 5.26591
I0410 02:52:22.435356 27877 solver.cpp:237]     Train net output #0: loss = 5.26591 (* 1 = 5.26591 loss)
I0410 02:52:22.435367 27877 sgd_solver.cpp:105] Iteration 6900, lr = 0.00254923
I0410 02:52:27.392556 27877 solver.cpp:218] Iteration 6912 (2.42079 iter/s, 4.95707s/12 iters), loss = 5.28589
I0410 02:52:27.392685 27877 solver.cpp:237]     Train net output #0: loss = 5.28589 (* 1 = 5.28589 loss)
I0410 02:52:27.392697 27877 sgd_solver.cpp:105] Iteration 6912, lr = 0.00254318
I0410 02:52:32.264370 27877 solver.cpp:218] Iteration 6924 (2.46328 iter/s, 4.87155s/12 iters), loss = 5.27976
I0410 02:52:32.264436 27877 solver.cpp:237]     Train net output #0: loss = 5.27976 (* 1 = 5.27976 loss)
I0410 02:52:32.264448 27877 sgd_solver.cpp:105] Iteration 6924, lr = 0.00253714
I0410 02:52:36.758482 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_6936.caffemodel
I0410 02:52:38.684234 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_6936.solverstate
I0410 02:52:40.070940 27877 solver.cpp:330] Iteration 6936, Testing net (#0)
I0410 02:52:40.070962 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:52:40.536742 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:52:41.806103 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:52:44.518072 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:52:44.518121 27877 solver.cpp:397]     Test net output #1: loss = 5.28677 (* 1 = 5.28677 loss)
I0410 02:52:44.600878 27877 solver.cpp:218] Iteration 6936 (0.972752 iter/s, 12.3361s/12 iters), loss = 5.28198
I0410 02:52:44.600929 27877 solver.cpp:237]     Train net output #0: loss = 5.28198 (* 1 = 5.28198 loss)
I0410 02:52:44.600939 27877 sgd_solver.cpp:105] Iteration 6936, lr = 0.00253112
I0410 02:52:48.782846 27877 solver.cpp:218] Iteration 6948 (2.86958 iter/s, 4.1818s/12 iters), loss = 5.27758
I0410 02:52:48.782900 27877 solver.cpp:237]     Train net output #0: loss = 5.27758 (* 1 = 5.27758 loss)
I0410 02:52:48.782910 27877 sgd_solver.cpp:105] Iteration 6948, lr = 0.00252511
I0410 02:52:53.728688 27877 solver.cpp:218] Iteration 6960 (2.42637 iter/s, 4.94565s/12 iters), loss = 5.26486
I0410 02:52:53.728735 27877 solver.cpp:237]     Train net output #0: loss = 5.26486 (* 1 = 5.26486 loss)
I0410 02:52:53.728747 27877 sgd_solver.cpp:105] Iteration 6960, lr = 0.00251911
I0410 02:52:58.685155 27877 solver.cpp:218] Iteration 6972 (2.42117 iter/s, 4.95628s/12 iters), loss = 5.27077
I0410 02:52:58.685289 27877 solver.cpp:237]     Train net output #0: loss = 5.27077 (* 1 = 5.27077 loss)
I0410 02:52:58.685303 27877 sgd_solver.cpp:105] Iteration 6972, lr = 0.00251313
I0410 02:53:01.363040 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:53:03.589571 27877 solver.cpp:218] Iteration 6984 (2.44691 iter/s, 4.90415s/12 iters), loss = 5.27574
I0410 02:53:03.589615 27877 solver.cpp:237]     Train net output #0: loss = 5.27574 (* 1 = 5.27574 loss)
I0410 02:53:03.589624 27877 sgd_solver.cpp:105] Iteration 6984, lr = 0.00250717
I0410 02:53:08.717855 27877 solver.cpp:218] Iteration 6996 (2.34005 iter/s, 5.1281s/12 iters), loss = 5.25881
I0410 02:53:08.717911 27877 solver.cpp:237]     Train net output #0: loss = 5.25881 (* 1 = 5.25881 loss)
I0410 02:53:08.717923 27877 sgd_solver.cpp:105] Iteration 6996, lr = 0.00250121
I0410 02:53:13.813922 27877 solver.cpp:218] Iteration 7008 (2.35485 iter/s, 5.09587s/12 iters), loss = 5.2578
I0410 02:53:13.814011 27877 solver.cpp:237]     Train net output #0: loss = 5.2578 (* 1 = 5.2578 loss)
I0410 02:53:13.814025 27877 sgd_solver.cpp:105] Iteration 7008, lr = 0.00249528
I0410 02:53:18.783471 27877 solver.cpp:218] Iteration 7020 (2.41482 iter/s, 4.96932s/12 iters), loss = 5.25839
I0410 02:53:18.783541 27877 solver.cpp:237]     Train net output #0: loss = 5.25839 (* 1 = 5.25839 loss)
I0410 02:53:18.783556 27877 sgd_solver.cpp:105] Iteration 7020, lr = 0.00248935
I0410 02:53:23.893687 27877 solver.cpp:218] Iteration 7032 (2.34833 iter/s, 5.11001s/12 iters), loss = 5.30215
I0410 02:53:23.893725 27877 solver.cpp:237]     Train net output #0: loss = 5.30215 (* 1 = 5.30215 loss)
I0410 02:53:23.893734 27877 sgd_solver.cpp:105] Iteration 7032, lr = 0.00248344
I0410 02:53:25.866880 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7038.caffemodel
I0410 02:53:27.750049 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7038.solverstate
I0410 02:53:28.719087 27877 solver.cpp:330] Iteration 7038, Testing net (#0)
I0410 02:53:28.719206 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:53:30.435995 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:53:33.561107 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:53:33.561161 27877 solver.cpp:397]     Test net output #1: loss = 5.28648 (* 1 = 5.28648 loss)
I0410 02:53:35.509557 27877 solver.cpp:218] Iteration 7044 (1.0331 iter/s, 11.6155s/12 iters), loss = 5.27182
I0410 02:53:35.509613 27877 solver.cpp:237]     Train net output #0: loss = 5.27182 (* 1 = 5.27182 loss)
I0410 02:53:35.509625 27877 sgd_solver.cpp:105] Iteration 7044, lr = 0.00247755
I0410 02:53:40.630954 27877 solver.cpp:218] Iteration 7056 (2.3432 iter/s, 5.1212s/12 iters), loss = 5.27214
I0410 02:53:40.631001 27877 solver.cpp:237]     Train net output #0: loss = 5.27214 (* 1 = 5.27214 loss)
I0410 02:53:40.631012 27877 sgd_solver.cpp:105] Iteration 7056, lr = 0.00247166
I0410 02:53:45.582227 27877 solver.cpp:218] Iteration 7068 (2.42371 iter/s, 4.95109s/12 iters), loss = 5.26737
I0410 02:53:45.582288 27877 solver.cpp:237]     Train net output #0: loss = 5.26737 (* 1 = 5.26737 loss)
I0410 02:53:45.582299 27877 sgd_solver.cpp:105] Iteration 7068, lr = 0.0024658
I0410 02:53:50.398315 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:53:50.512569 27877 solver.cpp:218] Iteration 7080 (2.434 iter/s, 4.93015s/12 iters), loss = 5.24394
I0410 02:53:50.512620 27877 solver.cpp:237]     Train net output #0: loss = 5.24394 (* 1 = 5.24394 loss)
I0410 02:53:50.512632 27877 sgd_solver.cpp:105] Iteration 7080, lr = 0.00245994
I0410 02:53:55.439131 27877 solver.cpp:218] Iteration 7092 (2.43587 iter/s, 4.92638s/12 iters), loss = 5.2665
I0410 02:53:55.439178 27877 solver.cpp:237]     Train net output #0: loss = 5.2665 (* 1 = 5.2665 loss)
I0410 02:53:55.439189 27877 sgd_solver.cpp:105] Iteration 7092, lr = 0.0024541
I0410 02:54:00.475287 27877 solver.cpp:218] Iteration 7104 (2.38286 iter/s, 5.03598s/12 iters), loss = 5.29676
I0410 02:54:00.484825 27877 solver.cpp:237]     Train net output #0: loss = 5.29676 (* 1 = 5.29676 loss)
I0410 02:54:00.484840 27877 sgd_solver.cpp:105] Iteration 7104, lr = 0.00244827
I0410 02:54:05.440920 27877 solver.cpp:218] Iteration 7116 (2.42132 iter/s, 4.95597s/12 iters), loss = 5.27707
I0410 02:54:05.440966 27877 solver.cpp:237]     Train net output #0: loss = 5.27707 (* 1 = 5.27707 loss)
I0410 02:54:05.440975 27877 sgd_solver.cpp:105] Iteration 7116, lr = 0.00244246
I0410 02:54:10.516911 27877 solver.cpp:218] Iteration 7128 (2.36416 iter/s, 5.0758s/12 iters), loss = 5.27428
I0410 02:54:10.516964 27877 solver.cpp:237]     Train net output #0: loss = 5.27428 (* 1 = 5.27428 loss)
I0410 02:54:10.516975 27877 sgd_solver.cpp:105] Iteration 7128, lr = 0.00243666
I0410 02:54:15.178231 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7140.caffemodel
I0410 02:54:16.538718 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7140.solverstate
I0410 02:54:17.591646 27877 solver.cpp:330] Iteration 7140, Testing net (#0)
I0410 02:54:17.591676 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:54:19.300161 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:54:22.089526 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:54:22.089579 27877 solver.cpp:397]     Test net output #1: loss = 5.28664 (* 1 = 5.28664 loss)
I0410 02:54:22.172569 27877 solver.cpp:218] Iteration 7140 (1.02957 iter/s, 11.6553s/12 iters), loss = 5.26664
I0410 02:54:22.172647 27877 solver.cpp:237]     Train net output #0: loss = 5.26664 (* 1 = 5.26664 loss)
I0410 02:54:22.172664 27877 sgd_solver.cpp:105] Iteration 7140, lr = 0.00243088
I0410 02:54:26.378793 27877 solver.cpp:218] Iteration 7152 (2.85304 iter/s, 4.20604s/12 iters), loss = 5.24748
I0410 02:54:26.378842 27877 solver.cpp:237]     Train net output #0: loss = 5.24748 (* 1 = 5.24748 loss)
I0410 02:54:26.378851 27877 sgd_solver.cpp:105] Iteration 7152, lr = 0.00242511
I0410 02:54:31.392989 27877 solver.cpp:218] Iteration 7164 (2.39329 iter/s, 5.01401s/12 iters), loss = 5.27135
I0410 02:54:31.393127 27877 solver.cpp:237]     Train net output #0: loss = 5.27135 (* 1 = 5.27135 loss)
I0410 02:54:31.393137 27877 sgd_solver.cpp:105] Iteration 7164, lr = 0.00241935
I0410 02:54:36.423952 27877 solver.cpp:218] Iteration 7176 (2.38536 iter/s, 5.03068s/12 iters), loss = 5.2581
I0410 02:54:36.424005 27877 solver.cpp:237]     Train net output #0: loss = 5.2581 (* 1 = 5.2581 loss)
I0410 02:54:36.424016 27877 sgd_solver.cpp:105] Iteration 7176, lr = 0.0024136
I0410 02:54:38.481050 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:54:41.308614 27877 solver.cpp:218] Iteration 7188 (2.45676 iter/s, 4.88447s/12 iters), loss = 5.27524
I0410 02:54:41.308668 27877 solver.cpp:237]     Train net output #0: loss = 5.27524 (* 1 = 5.27524 loss)
I0410 02:54:41.308679 27877 sgd_solver.cpp:105] Iteration 7188, lr = 0.00240787
I0410 02:54:46.242533 27877 solver.cpp:218] Iteration 7200 (2.43224 iter/s, 4.93373s/12 iters), loss = 5.27366
I0410 02:54:46.242588 27877 solver.cpp:237]     Train net output #0: loss = 5.27366 (* 1 = 5.27366 loss)
I0410 02:54:46.242599 27877 sgd_solver.cpp:105] Iteration 7200, lr = 0.00240216
I0410 02:54:51.177070 27877 solver.cpp:218] Iteration 7212 (2.43193 iter/s, 4.93435s/12 iters), loss = 5.28202
I0410 02:54:51.177120 27877 solver.cpp:237]     Train net output #0: loss = 5.28202 (* 1 = 5.28202 loss)
I0410 02:54:51.177131 27877 sgd_solver.cpp:105] Iteration 7212, lr = 0.00239645
I0410 02:54:56.045701 27877 solver.cpp:218] Iteration 7224 (2.46485 iter/s, 4.86844s/12 iters), loss = 5.26226
I0410 02:54:56.045768 27877 solver.cpp:237]     Train net output #0: loss = 5.26226 (* 1 = 5.26226 loss)
I0410 02:54:56.045780 27877 sgd_solver.cpp:105] Iteration 7224, lr = 0.00239076
I0410 02:55:00.928392 27877 solver.cpp:218] Iteration 7236 (2.45776 iter/s, 4.8825s/12 iters), loss = 5.27398
I0410 02:55:00.928445 27877 solver.cpp:237]     Train net output #0: loss = 5.27398 (* 1 = 5.27398 loss)
I0410 02:55:00.928457 27877 sgd_solver.cpp:105] Iteration 7236, lr = 0.00238509
I0410 02:55:02.913120 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7242.caffemodel
I0410 02:55:04.408738 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7242.solverstate
I0410 02:55:05.895395 27877 solver.cpp:330] Iteration 7242, Testing net (#0)
I0410 02:55:05.895424 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:55:07.391805 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:55:10.214704 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:55:10.214740 27877 solver.cpp:397]     Test net output #1: loss = 5.2863 (* 1 = 5.2863 loss)
I0410 02:55:12.162461 27877 solver.cpp:218] Iteration 7248 (1.06821 iter/s, 11.2337s/12 iters), loss = 5.27541
I0410 02:55:12.162506 27877 solver.cpp:237]     Train net output #0: loss = 5.27541 (* 1 = 5.27541 loss)
I0410 02:55:12.162515 27877 sgd_solver.cpp:105] Iteration 7248, lr = 0.00237942
I0410 02:55:17.167346 27877 solver.cpp:218] Iteration 7260 (2.39775 iter/s, 5.0047s/12 iters), loss = 5.27432
I0410 02:55:17.167398 27877 solver.cpp:237]     Train net output #0: loss = 5.27432 (* 1 = 5.27432 loss)
I0410 02:55:17.167410 27877 sgd_solver.cpp:105] Iteration 7260, lr = 0.00237378
I0410 02:55:22.137136 27877 solver.cpp:218] Iteration 7272 (2.41468 iter/s, 4.9696s/12 iters), loss = 5.25384
I0410 02:55:22.137188 27877 solver.cpp:237]     Train net output #0: loss = 5.25384 (* 1 = 5.25384 loss)
I0410 02:55:22.137199 27877 sgd_solver.cpp:105] Iteration 7272, lr = 0.00236814
I0410 02:55:26.306178 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:55:27.041663 27877 solver.cpp:218] Iteration 7284 (2.44681 iter/s, 4.90434s/12 iters), loss = 5.25534
I0410 02:55:27.041719 27877 solver.cpp:237]     Train net output #0: loss = 5.25534 (* 1 = 5.25534 loss)
I0410 02:55:27.041730 27877 sgd_solver.cpp:105] Iteration 7284, lr = 0.00236252
I0410 02:55:32.021308 27877 solver.cpp:218] Iteration 7296 (2.4099 iter/s, 4.97945s/12 iters), loss = 5.27748
I0410 02:55:32.021356 27877 solver.cpp:237]     Train net output #0: loss = 5.27748 (* 1 = 5.27748 loss)
I0410 02:55:32.021366 27877 sgd_solver.cpp:105] Iteration 7296, lr = 0.00235691
I0410 02:55:37.021986 27877 solver.cpp:218] Iteration 7308 (2.39976 iter/s, 5.0005s/12 iters), loss = 5.28372
I0410 02:55:37.022138 27877 solver.cpp:237]     Train net output #0: loss = 5.28372 (* 1 = 5.28372 loss)
I0410 02:55:37.022148 27877 sgd_solver.cpp:105] Iteration 7308, lr = 0.00235131
I0410 02:55:41.966766 27877 solver.cpp:218] Iteration 7320 (2.42694 iter/s, 4.9445s/12 iters), loss = 5.29285
I0410 02:55:41.966825 27877 solver.cpp:237]     Train net output #0: loss = 5.29285 (* 1 = 5.29285 loss)
I0410 02:55:41.966837 27877 sgd_solver.cpp:105] Iteration 7320, lr = 0.00234573
I0410 02:55:46.934206 27877 solver.cpp:218] Iteration 7332 (2.41583 iter/s, 4.96725s/12 iters), loss = 5.26827
I0410 02:55:46.934259 27877 solver.cpp:237]     Train net output #0: loss = 5.26827 (* 1 = 5.26827 loss)
I0410 02:55:46.934271 27877 sgd_solver.cpp:105] Iteration 7332, lr = 0.00234016
I0410 02:55:51.492565 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7344.caffemodel
I0410 02:55:52.367233 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7344.solverstate
I0410 02:55:52.994398 27877 solver.cpp:330] Iteration 7344, Testing net (#0)
I0410 02:55:52.994431 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:55:54.728045 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:55:57.617714 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:55:57.617760 27877 solver.cpp:397]     Test net output #1: loss = 5.28712 (* 1 = 5.28712 loss)
I0410 02:55:57.700376 27877 solver.cpp:218] Iteration 7344 (1.11464 iter/s, 10.7658s/12 iters), loss = 5.27607
I0410 02:55:57.700436 27877 solver.cpp:237]     Train net output #0: loss = 5.27607 (* 1 = 5.27607 loss)
I0410 02:55:57.700448 27877 sgd_solver.cpp:105] Iteration 7344, lr = 0.0023346
I0410 02:56:02.226667 27877 solver.cpp:218] Iteration 7356 (2.65128 iter/s, 4.52611s/12 iters), loss = 5.28253
I0410 02:56:02.226713 27877 solver.cpp:237]     Train net output #0: loss = 5.28253 (* 1 = 5.28253 loss)
I0410 02:56:02.226725 27877 sgd_solver.cpp:105] Iteration 7356, lr = 0.00232906
I0410 02:56:07.236536 27877 solver.cpp:218] Iteration 7368 (2.39536 iter/s, 5.00969s/12 iters), loss = 5.28034
I0410 02:56:07.236704 27877 solver.cpp:237]     Train net output #0: loss = 5.28034 (* 1 = 5.28034 loss)
I0410 02:56:07.236719 27877 sgd_solver.cpp:105] Iteration 7368, lr = 0.00232353
I0410 02:56:12.264528 27877 solver.cpp:218] Iteration 7380 (2.38678 iter/s, 5.02769s/12 iters), loss = 5.26328
I0410 02:56:12.264575 27877 solver.cpp:237]     Train net output #0: loss = 5.26328 (* 1 = 5.26328 loss)
I0410 02:56:12.264585 27877 sgd_solver.cpp:105] Iteration 7380, lr = 0.00231802
I0410 02:56:13.621986 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:56:17.173492 27877 solver.cpp:218] Iteration 7392 (2.4446 iter/s, 4.90878s/12 iters), loss = 5.2739
I0410 02:56:17.173544 27877 solver.cpp:237]     Train net output #0: loss = 5.2739 (* 1 = 5.2739 loss)
I0410 02:56:17.173555 27877 sgd_solver.cpp:105] Iteration 7392, lr = 0.00231251
I0410 02:56:22.100168 27877 solver.cpp:218] Iteration 7404 (2.43581 iter/s, 4.92649s/12 iters), loss = 5.26842
I0410 02:56:22.100217 27877 solver.cpp:237]     Train net output #0: loss = 5.26842 (* 1 = 5.26842 loss)
I0410 02:56:22.100229 27877 sgd_solver.cpp:105] Iteration 7404, lr = 0.00230702
I0410 02:56:27.019383 27877 solver.cpp:218] Iteration 7416 (2.43951 iter/s, 4.91903s/12 iters), loss = 5.26673
I0410 02:56:27.019436 27877 solver.cpp:237]     Train net output #0: loss = 5.26673 (* 1 = 5.26673 loss)
I0410 02:56:27.019448 27877 sgd_solver.cpp:105] Iteration 7416, lr = 0.00230154
I0410 02:56:31.927000 27877 solver.cpp:218] Iteration 7428 (2.44527 iter/s, 4.90743s/12 iters), loss = 5.28002
I0410 02:56:31.927040 27877 solver.cpp:237]     Train net output #0: loss = 5.28002 (* 1 = 5.28002 loss)
I0410 02:56:31.927049 27877 sgd_solver.cpp:105] Iteration 7428, lr = 0.00229608
I0410 02:56:36.794472 27877 solver.cpp:218] Iteration 7440 (2.46543 iter/s, 4.8673s/12 iters), loss = 5.25849
I0410 02:56:36.794514 27877 solver.cpp:237]     Train net output #0: loss = 5.25849 (* 1 = 5.25849 loss)
I0410 02:56:36.794523 27877 sgd_solver.cpp:105] Iteration 7440, lr = 0.00229063
I0410 02:56:38.761921 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7446.caffemodel
I0410 02:56:40.150390 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7446.solverstate
I0410 02:56:41.327383 27877 solver.cpp:330] Iteration 7446, Testing net (#0)
I0410 02:56:41.327405 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:56:42.731904 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:56:45.677724 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:56:45.677775 27877 solver.cpp:397]     Test net output #1: loss = 5.28648 (* 1 = 5.28648 loss)
I0410 02:56:47.552629 27877 solver.cpp:218] Iteration 7452 (1.11547 iter/s, 10.7578s/12 iters), loss = 5.26701
I0410 02:56:47.552685 27877 solver.cpp:237]     Train net output #0: loss = 5.26701 (* 1 = 5.26701 loss)
I0410 02:56:47.552696 27877 sgd_solver.cpp:105] Iteration 7452, lr = 0.00228519
I0410 02:56:52.376358 27877 solver.cpp:218] Iteration 7464 (2.4878 iter/s, 4.82355s/12 iters), loss = 5.28627
I0410 02:56:52.376400 27877 solver.cpp:237]     Train net output #0: loss = 5.28627 (* 1 = 5.28627 loss)
I0410 02:56:52.376408 27877 sgd_solver.cpp:105] Iteration 7464, lr = 0.00227976
I0410 02:56:57.292131 27877 solver.cpp:218] Iteration 7476 (2.44121 iter/s, 4.9156s/12 iters), loss = 5.27735
I0410 02:56:57.292177 27877 solver.cpp:237]     Train net output #0: loss = 5.27735 (* 1 = 5.27735 loss)
I0410 02:56:57.292188 27877 sgd_solver.cpp:105] Iteration 7476, lr = 0.00227435
I0410 02:57:00.736260 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:57:02.217000 27877 solver.cpp:218] Iteration 7488 (2.43671 iter/s, 4.92468s/12 iters), loss = 5.27044
I0410 02:57:02.217057 27877 solver.cpp:237]     Train net output #0: loss = 5.27044 (* 1 = 5.27044 loss)
I0410 02:57:02.217069 27877 sgd_solver.cpp:105] Iteration 7488, lr = 0.00226895
I0410 02:57:07.108842 27877 solver.cpp:218] Iteration 7500 (2.45316 iter/s, 4.89165s/12 iters), loss = 5.25925
I0410 02:57:07.108894 27877 solver.cpp:237]     Train net output #0: loss = 5.25925 (* 1 = 5.25925 loss)
I0410 02:57:07.108904 27877 sgd_solver.cpp:105] Iteration 7500, lr = 0.00226357
I0410 02:57:12.017143 27877 solver.cpp:218] Iteration 7512 (2.44493 iter/s, 4.90811s/12 iters), loss = 5.26382
I0410 02:57:12.017275 27877 solver.cpp:237]     Train net output #0: loss = 5.26382 (* 1 = 5.26382 loss)
I0410 02:57:12.017288 27877 sgd_solver.cpp:105] Iteration 7512, lr = 0.00225819
I0410 02:57:16.938886 27877 solver.cpp:218] Iteration 7524 (2.43829 iter/s, 4.92148s/12 iters), loss = 5.26863
I0410 02:57:16.938938 27877 solver.cpp:237]     Train net output #0: loss = 5.26863 (* 1 = 5.26863 loss)
I0410 02:57:16.938951 27877 sgd_solver.cpp:105] Iteration 7524, lr = 0.00225283
I0410 02:57:21.855486 27877 solver.cpp:218] Iteration 7536 (2.4408 iter/s, 4.91642s/12 iters), loss = 5.25933
I0410 02:57:21.855533 27877 solver.cpp:237]     Train net output #0: loss = 5.25933 (* 1 = 5.25933 loss)
I0410 02:57:21.855541 27877 sgd_solver.cpp:105] Iteration 7536, lr = 0.00224748
I0410 02:57:26.297631 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7548.caffemodel
I0410 02:57:28.929261 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7548.solverstate
I0410 02:57:33.617347 27877 solver.cpp:330] Iteration 7548, Testing net (#0)
I0410 02:57:33.617377 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:57:35.112068 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:57:38.063124 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:57:38.063166 27877 solver.cpp:397]     Test net output #1: loss = 5.2866 (* 1 = 5.2866 loss)
I0410 02:57:38.145792 27877 solver.cpp:218] Iteration 7548 (0.736655 iter/s, 16.2899s/12 iters), loss = 5.28291
I0410 02:57:38.145838 27877 solver.cpp:237]     Train net output #0: loss = 5.28291 (* 1 = 5.28291 loss)
I0410 02:57:38.145848 27877 sgd_solver.cpp:105] Iteration 7548, lr = 0.00224215
I0410 02:57:42.355902 27877 solver.cpp:218] Iteration 7560 (2.85039 iter/s, 4.20995s/12 iters), loss = 5.26805
I0410 02:57:42.355979 27877 solver.cpp:237]     Train net output #0: loss = 5.26805 (* 1 = 5.26805 loss)
I0410 02:57:42.355990 27877 sgd_solver.cpp:105] Iteration 7560, lr = 0.00223682
I0410 02:57:47.262594 27877 solver.cpp:218] Iteration 7572 (2.44574 iter/s, 4.90649s/12 iters), loss = 5.28097
I0410 02:57:47.262630 27877 solver.cpp:237]     Train net output #0: loss = 5.28097 (* 1 = 5.28097 loss)
I0410 02:57:47.262639 27877 sgd_solver.cpp:105] Iteration 7572, lr = 0.00223151
I0410 02:57:52.271080 27877 solver.cpp:218] Iteration 7584 (2.39602 iter/s, 5.00831s/12 iters), loss = 5.288
I0410 02:57:52.271121 27877 solver.cpp:237]     Train net output #0: loss = 5.288 (* 1 = 5.288 loss)
I0410 02:57:52.271131 27877 sgd_solver.cpp:105] Iteration 7584, lr = 0.00222621
I0410 02:57:52.917641 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:57:57.249619 27877 solver.cpp:218] Iteration 7596 (2.41043 iter/s, 4.97836s/12 iters), loss = 5.27864
I0410 02:57:57.249673 27877 solver.cpp:237]     Train net output #0: loss = 5.27864 (* 1 = 5.27864 loss)
I0410 02:57:57.249687 27877 sgd_solver.cpp:105] Iteration 7596, lr = 0.00222093
I0410 02:58:02.177742 27877 solver.cpp:218] Iteration 7608 (2.4351 iter/s, 4.92793s/12 iters), loss = 5.26205
I0410 02:58:02.177805 27877 solver.cpp:237]     Train net output #0: loss = 5.26205 (* 1 = 5.26205 loss)
I0410 02:58:02.177821 27877 sgd_solver.cpp:105] Iteration 7608, lr = 0.00221565
I0410 02:58:07.111562 27877 solver.cpp:218] Iteration 7620 (2.43229 iter/s, 4.93362s/12 iters), loss = 5.28082
I0410 02:58:07.111613 27877 solver.cpp:237]     Train net output #0: loss = 5.28082 (* 1 = 5.28082 loss)
I0410 02:58:07.111624 27877 sgd_solver.cpp:105] Iteration 7620, lr = 0.00221039
I0410 02:58:08.710713 27877 blocking_queue.cpp:49] Waiting for data
I0410 02:58:12.037536 27877 solver.cpp:218] Iteration 7632 (2.43616 iter/s, 4.92579s/12 iters), loss = 5.27692
I0410 02:58:12.037585 27877 solver.cpp:237]     Train net output #0: loss = 5.27692 (* 1 = 5.27692 loss)
I0410 02:58:12.037595 27877 sgd_solver.cpp:105] Iteration 7632, lr = 0.00220515
I0410 02:58:16.952950 27877 solver.cpp:218] Iteration 7644 (2.44139 iter/s, 4.91523s/12 iters), loss = 5.28596
I0410 02:58:16.953110 27877 solver.cpp:237]     Train net output #0: loss = 5.28596 (* 1 = 5.28596 loss)
I0410 02:58:16.953125 27877 sgd_solver.cpp:105] Iteration 7644, lr = 0.00219991
I0410 02:58:18.958770 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7650.caffemodel
I0410 02:58:20.068197 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7650.solverstate
I0410 02:58:20.827600 27877 solver.cpp:330] Iteration 7650, Testing net (#0)
I0410 02:58:20.827625 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:58:22.390992 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:58:25.383256 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:58:25.383296 27877 solver.cpp:397]     Test net output #1: loss = 5.28674 (* 1 = 5.28674 loss)
I0410 02:58:27.316172 27877 solver.cpp:218] Iteration 7656 (1.15799 iter/s, 10.3628s/12 iters), loss = 5.27676
I0410 02:58:27.316233 27877 solver.cpp:237]     Train net output #0: loss = 5.27676 (* 1 = 5.27676 loss)
I0410 02:58:27.316244 27877 sgd_solver.cpp:105] Iteration 7656, lr = 0.00219469
I0410 02:58:32.278247 27877 solver.cpp:218] Iteration 7668 (2.41844 iter/s, 4.96187s/12 iters), loss = 5.27022
I0410 02:58:32.278297 27877 solver.cpp:237]     Train net output #0: loss = 5.27022 (* 1 = 5.27022 loss)
I0410 02:58:32.278306 27877 sgd_solver.cpp:105] Iteration 7668, lr = 0.00218948
I0410 02:58:37.217945 27877 solver.cpp:218] Iteration 7680 (2.42939 iter/s, 4.93951s/12 iters), loss = 5.26267
I0410 02:58:37.218012 27877 solver.cpp:237]     Train net output #0: loss = 5.26267 (* 1 = 5.26267 loss)
I0410 02:58:37.218024 27877 sgd_solver.cpp:105] Iteration 7680, lr = 0.00218428
I0410 02:58:39.976753 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:58:42.182026 27877 solver.cpp:218] Iteration 7692 (2.41746 iter/s, 4.96389s/12 iters), loss = 5.27055
I0410 02:58:42.182071 27877 solver.cpp:237]     Train net output #0: loss = 5.27055 (* 1 = 5.27055 loss)
I0410 02:58:42.182082 27877 sgd_solver.cpp:105] Iteration 7692, lr = 0.00217909
I0410 02:58:47.092592 27877 solver.cpp:218] Iteration 7704 (2.4438 iter/s, 4.91039s/12 iters), loss = 5.25404
I0410 02:58:47.092676 27877 solver.cpp:237]     Train net output #0: loss = 5.25404 (* 1 = 5.25404 loss)
I0410 02:58:47.092689 27877 sgd_solver.cpp:105] Iteration 7704, lr = 0.00217392
I0410 02:58:52.013132 27877 solver.cpp:218] Iteration 7716 (2.43886 iter/s, 4.92033s/12 iters), loss = 5.25392
I0410 02:58:52.013172 27877 solver.cpp:237]     Train net output #0: loss = 5.25392 (* 1 = 5.25392 loss)
I0410 02:58:52.013182 27877 sgd_solver.cpp:105] Iteration 7716, lr = 0.00216876
I0410 02:58:56.883035 27877 solver.cpp:218] Iteration 7728 (2.4642 iter/s, 4.86973s/12 iters), loss = 5.25858
I0410 02:58:56.883090 27877 solver.cpp:237]     Train net output #0: loss = 5.25858 (* 1 = 5.25858 loss)
I0410 02:58:56.883102 27877 sgd_solver.cpp:105] Iteration 7728, lr = 0.00216361
I0410 02:59:01.827476 27877 solver.cpp:218] Iteration 7740 (2.42706 iter/s, 4.94425s/12 iters), loss = 5.29933
I0410 02:59:01.827533 27877 solver.cpp:237]     Train net output #0: loss = 5.29933 (* 1 = 5.29933 loss)
I0410 02:59:01.827546 27877 sgd_solver.cpp:105] Iteration 7740, lr = 0.00215847
I0410 02:59:06.277551 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7752.caffemodel
I0410 02:59:08.146477 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7752.solverstate
I0410 02:59:08.938767 27877 solver.cpp:330] Iteration 7752, Testing net (#0)
I0410 02:59:08.938792 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:59:10.366003 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:59:13.388314 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 02:59:13.388365 27877 solver.cpp:397]     Test net output #1: loss = 5.28641 (* 1 = 5.28641 loss)
I0410 02:59:13.471524 27877 solver.cpp:218] Iteration 7752 (1.0306 iter/s, 11.6437s/12 iters), loss = 5.26795
I0410 02:59:13.471575 27877 solver.cpp:237]     Train net output #0: loss = 5.26795 (* 1 = 5.26795 loss)
I0410 02:59:13.471585 27877 sgd_solver.cpp:105] Iteration 7752, lr = 0.00215335
I0410 02:59:17.735003 27877 solver.cpp:218] Iteration 7764 (2.81471 iter/s, 4.26331s/12 iters), loss = 5.27805
I0410 02:59:17.735217 27877 solver.cpp:237]     Train net output #0: loss = 5.27805 (* 1 = 5.27805 loss)
I0410 02:59:17.735227 27877 sgd_solver.cpp:105] Iteration 7764, lr = 0.00214823
I0410 02:59:22.752138 27877 solver.cpp:218] Iteration 7776 (2.39197 iter/s, 5.01679s/12 iters), loss = 5.26926
I0410 02:59:22.752194 27877 solver.cpp:237]     Train net output #0: loss = 5.26926 (* 1 = 5.26926 loss)
I0410 02:59:22.752207 27877 sgd_solver.cpp:105] Iteration 7776, lr = 0.00214313
I0410 02:59:27.632908 27877 solver.cpp:218] Iteration 7788 (2.45872 iter/s, 4.88058s/12 iters), loss = 5.24455
I0410 02:59:27.632962 27877 solver.cpp:237]     Train net output #0: loss = 5.24455 (* 1 = 5.24455 loss)
I0410 02:59:27.632977 27877 sgd_solver.cpp:105] Iteration 7788, lr = 0.00213805
I0410 02:59:27.641053 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 02:59:32.514412 27877 solver.cpp:218] Iteration 7800 (2.45835 iter/s, 4.88132s/12 iters), loss = 5.27025
I0410 02:59:32.514465 27877 solver.cpp:237]     Train net output #0: loss = 5.27025 (* 1 = 5.27025 loss)
I0410 02:59:32.514487 27877 sgd_solver.cpp:105] Iteration 7800, lr = 0.00213297
I0410 02:59:37.454018 27877 solver.cpp:218] Iteration 7812 (2.42944 iter/s, 4.93942s/12 iters), loss = 5.29382
I0410 02:59:37.454071 27877 solver.cpp:237]     Train net output #0: loss = 5.29382 (* 1 = 5.29382 loss)
I0410 02:59:37.454080 27877 sgd_solver.cpp:105] Iteration 7812, lr = 0.00212791
I0410 02:59:42.368834 27877 solver.cpp:218] Iteration 7824 (2.44169 iter/s, 4.91463s/12 iters), loss = 5.27434
I0410 02:59:42.368873 27877 solver.cpp:237]     Train net output #0: loss = 5.27434 (* 1 = 5.27434 loss)
I0410 02:59:42.368882 27877 sgd_solver.cpp:105] Iteration 7824, lr = 0.00212285
I0410 02:59:47.303751 27877 solver.cpp:218] Iteration 7836 (2.43174 iter/s, 4.93474s/12 iters), loss = 5.27545
I0410 02:59:47.303807 27877 solver.cpp:237]     Train net output #0: loss = 5.27545 (* 1 = 5.27545 loss)
I0410 02:59:47.303819 27877 sgd_solver.cpp:105] Iteration 7836, lr = 0.00211781
I0410 02:59:52.231211 27877 solver.cpp:218] Iteration 7848 (2.43543 iter/s, 4.92727s/12 iters), loss = 5.26164
I0410 02:59:52.231321 27877 solver.cpp:237]     Train net output #0: loss = 5.26164 (* 1 = 5.26164 loss)
I0410 02:59:52.231333 27877 sgd_solver.cpp:105] Iteration 7848, lr = 0.00211279
I0410 02:59:54.345903 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7854.caffemodel
I0410 02:59:55.142716 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7854.solverstate
I0410 02:59:55.748318 27877 solver.cpp:330] Iteration 7854, Testing net (#0)
I0410 02:59:55.748345 27877 net.cpp:676] Ignoring source layer train-data
I0410 02:59:57.104336 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:00:00.173607 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:00:00.173658 27877 solver.cpp:397]     Test net output #1: loss = 5.28623 (* 1 = 5.28623 loss)
I0410 03:00:02.045619 27877 solver.cpp:218] Iteration 7860 (1.22274 iter/s, 9.81404s/12 iters), loss = 5.24389
I0410 03:00:02.045679 27877 solver.cpp:237]     Train net output #0: loss = 5.24389 (* 1 = 5.24389 loss)
I0410 03:00:02.045691 27877 sgd_solver.cpp:105] Iteration 7860, lr = 0.00210777
I0410 03:00:06.926226 27877 solver.cpp:218] Iteration 7872 (2.45881 iter/s, 4.88041s/12 iters), loss = 5.26664
I0410 03:00:06.926275 27877 solver.cpp:237]     Train net output #0: loss = 5.26664 (* 1 = 5.26664 loss)
I0410 03:00:06.926283 27877 sgd_solver.cpp:105] Iteration 7872, lr = 0.00210277
I0410 03:00:11.816671 27877 solver.cpp:218] Iteration 7884 (2.45386 iter/s, 4.89026s/12 iters), loss = 5.25952
I0410 03:00:11.816730 27877 solver.cpp:237]     Train net output #0: loss = 5.25952 (* 1 = 5.25952 loss)
I0410 03:00:11.816743 27877 sgd_solver.cpp:105] Iteration 7884, lr = 0.00209777
I0410 03:00:14.070375 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:00:16.858918 27877 solver.cpp:218] Iteration 7896 (2.37998 iter/s, 5.04205s/12 iters), loss = 5.27667
I0410 03:00:16.858973 27877 solver.cpp:237]     Train net output #0: loss = 5.27667 (* 1 = 5.27667 loss)
I0410 03:00:16.858984 27877 sgd_solver.cpp:105] Iteration 7896, lr = 0.00209279
I0410 03:00:21.797291 27877 solver.cpp:218] Iteration 7908 (2.43004 iter/s, 4.93819s/12 iters), loss = 5.27064
I0410 03:00:21.797331 27877 solver.cpp:237]     Train net output #0: loss = 5.27064 (* 1 = 5.27064 loss)
I0410 03:00:21.797339 27877 sgd_solver.cpp:105] Iteration 7908, lr = 0.00208782
I0410 03:00:26.882293 27877 solver.cpp:218] Iteration 7920 (2.35996 iter/s, 5.08483s/12 iters), loss = 5.28448
I0410 03:00:26.882437 27877 solver.cpp:237]     Train net output #0: loss = 5.28448 (* 1 = 5.28448 loss)
I0410 03:00:26.882448 27877 sgd_solver.cpp:105] Iteration 7920, lr = 0.00208287
I0410 03:00:31.762284 27877 solver.cpp:218] Iteration 7932 (2.45916 iter/s, 4.87972s/12 iters), loss = 5.26131
I0410 03:00:31.762324 27877 solver.cpp:237]     Train net output #0: loss = 5.26131 (* 1 = 5.26131 loss)
I0410 03:00:31.762332 27877 sgd_solver.cpp:105] Iteration 7932, lr = 0.00207792
I0410 03:00:36.677165 27877 solver.cpp:218] Iteration 7944 (2.44165 iter/s, 4.91471s/12 iters), loss = 5.26747
I0410 03:00:36.677204 27877 solver.cpp:237]     Train net output #0: loss = 5.26747 (* 1 = 5.26747 loss)
I0410 03:00:36.677212 27877 sgd_solver.cpp:105] Iteration 7944, lr = 0.00207299
I0410 03:00:41.048310 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_7956.caffemodel
I0410 03:00:41.868381 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_7956.solverstate
I0410 03:00:42.487164 27877 solver.cpp:330] Iteration 7956, Testing net (#0)
I0410 03:00:42.487191 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:00:43.821534 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:00:47.381296 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:00:47.381345 27877 solver.cpp:397]     Test net output #1: loss = 5.28677 (* 1 = 5.28677 loss)
I0410 03:00:47.464251 27877 solver.cpp:218] Iteration 7956 (1.11247 iter/s, 10.7868s/12 iters), loss = 5.27531
I0410 03:00:47.464300 27877 solver.cpp:237]     Train net output #0: loss = 5.27531 (* 1 = 5.27531 loss)
I0410 03:00:47.464313 27877 sgd_solver.cpp:105] Iteration 7956, lr = 0.00206807
I0410 03:00:51.742208 27877 solver.cpp:218] Iteration 7968 (2.80519 iter/s, 4.27779s/12 iters), loss = 5.27527
I0410 03:00:51.742266 27877 solver.cpp:237]     Train net output #0: loss = 5.27527 (* 1 = 5.27527 loss)
I0410 03:00:51.742277 27877 sgd_solver.cpp:105] Iteration 7968, lr = 0.00206316
I0410 03:00:56.734658 27877 solver.cpp:218] Iteration 7980 (2.40372 iter/s, 4.99226s/12 iters), loss = 5.25421
I0410 03:00:56.734714 27877 solver.cpp:237]     Train net output #0: loss = 5.25421 (* 1 = 5.25421 loss)
I0410 03:00:56.734726 27877 sgd_solver.cpp:105] Iteration 7980, lr = 0.00205826
I0410 03:01:01.080796 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:01:01.786168 27877 solver.cpp:218] Iteration 7992 (2.37562 iter/s, 5.05132s/12 iters), loss = 5.25916
I0410 03:01:01.786224 27877 solver.cpp:237]     Train net output #0: loss = 5.25916 (* 1 = 5.25916 loss)
I0410 03:01:01.786237 27877 sgd_solver.cpp:105] Iteration 7992, lr = 0.00205337
I0410 03:01:06.749078 27877 solver.cpp:218] Iteration 8004 (2.41803 iter/s, 4.96271s/12 iters), loss = 5.27936
I0410 03:01:06.749128 27877 solver.cpp:237]     Train net output #0: loss = 5.27936 (* 1 = 5.27936 loss)
I0410 03:01:06.749138 27877 sgd_solver.cpp:105] Iteration 8004, lr = 0.0020485
I0410 03:01:11.653481 27877 solver.cpp:218] Iteration 8016 (2.44687 iter/s, 4.90422s/12 iters), loss = 5.27724
I0410 03:01:11.653528 27877 solver.cpp:237]     Train net output #0: loss = 5.27724 (* 1 = 5.27724 loss)
I0410 03:01:11.653539 27877 sgd_solver.cpp:105] Iteration 8016, lr = 0.00204363
I0410 03:01:16.632686 27877 solver.cpp:218] Iteration 8028 (2.41011 iter/s, 4.97902s/12 iters), loss = 5.29742
I0410 03:01:16.632741 27877 solver.cpp:237]     Train net output #0: loss = 5.29742 (* 1 = 5.29742 loss)
I0410 03:01:16.632753 27877 sgd_solver.cpp:105] Iteration 8028, lr = 0.00203878
I0410 03:01:21.492954 27877 solver.cpp:218] Iteration 8040 (2.46909 iter/s, 4.86008s/12 iters), loss = 5.26718
I0410 03:01:21.493000 27877 solver.cpp:237]     Train net output #0: loss = 5.26718 (* 1 = 5.26718 loss)
I0410 03:01:21.493008 27877 sgd_solver.cpp:105] Iteration 8040, lr = 0.00203394
I0410 03:01:26.411578 27877 solver.cpp:218] Iteration 8052 (2.4398 iter/s, 4.91844s/12 iters), loss = 5.27769
I0410 03:01:26.411633 27877 solver.cpp:237]     Train net output #0: loss = 5.27769 (* 1 = 5.27769 loss)
I0410 03:01:26.411644 27877 sgd_solver.cpp:105] Iteration 8052, lr = 0.00202911
I0410 03:01:28.445178 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8058.caffemodel
I0410 03:01:30.465265 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8058.solverstate
I0410 03:01:33.003274 27877 solver.cpp:330] Iteration 8058, Testing net (#0)
I0410 03:01:33.003365 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:01:34.295293 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:01:37.476912 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:01:37.476944 27877 solver.cpp:397]     Test net output #1: loss = 5.28671 (* 1 = 5.28671 loss)
I0410 03:01:39.372318 27877 solver.cpp:218] Iteration 8064 (0.925901 iter/s, 12.9604s/12 iters), loss = 5.2777
I0410 03:01:39.372380 27877 solver.cpp:237]     Train net output #0: loss = 5.2777 (* 1 = 5.2777 loss)
I0410 03:01:39.372392 27877 sgd_solver.cpp:105] Iteration 8064, lr = 0.00202429
I0410 03:01:44.437611 27877 solver.cpp:218] Iteration 8076 (2.36916 iter/s, 5.06509s/12 iters), loss = 5.2779
I0410 03:01:44.437656 27877 solver.cpp:237]     Train net output #0: loss = 5.2779 (* 1 = 5.2779 loss)
I0410 03:01:44.437665 27877 sgd_solver.cpp:105] Iteration 8076, lr = 0.00201949
I0410 03:01:49.401762 27877 solver.cpp:218] Iteration 8088 (2.41742 iter/s, 4.96397s/12 iters), loss = 5.26304
I0410 03:01:49.401808 27877 solver.cpp:237]     Train net output #0: loss = 5.26304 (* 1 = 5.26304 loss)
I0410 03:01:49.401818 27877 sgd_solver.cpp:105] Iteration 8088, lr = 0.00201469
I0410 03:01:50.812444 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:01:54.336356 27877 solver.cpp:218] Iteration 8100 (2.4319 iter/s, 4.93441s/12 iters), loss = 5.26
I0410 03:01:54.336414 27877 solver.cpp:237]     Train net output #0: loss = 5.26 (* 1 = 5.26 loss)
I0410 03:01:54.336426 27877 sgd_solver.cpp:105] Iteration 8100, lr = 0.00200991
I0410 03:01:59.369571 27877 solver.cpp:218] Iteration 8112 (2.38426 iter/s, 5.03302s/12 iters), loss = 5.26707
I0410 03:01:59.369629 27877 solver.cpp:237]     Train net output #0: loss = 5.26707 (* 1 = 5.26707 loss)
I0410 03:01:59.369642 27877 sgd_solver.cpp:105] Iteration 8112, lr = 0.00200514
I0410 03:02:04.422574 27877 solver.cpp:218] Iteration 8124 (2.37492 iter/s, 5.05281s/12 iters), loss = 5.269
I0410 03:02:04.422674 27877 solver.cpp:237]     Train net output #0: loss = 5.269 (* 1 = 5.269 loss)
I0410 03:02:04.422684 27877 sgd_solver.cpp:105] Iteration 8124, lr = 0.00200038
I0410 03:02:09.366223 27877 solver.cpp:218] Iteration 8136 (2.42747 iter/s, 4.94342s/12 iters), loss = 5.28379
I0410 03:02:09.366267 27877 solver.cpp:237]     Train net output #0: loss = 5.28379 (* 1 = 5.28379 loss)
I0410 03:02:09.366276 27877 sgd_solver.cpp:105] Iteration 8136, lr = 0.00199563
I0410 03:02:14.686444 27877 solver.cpp:218] Iteration 8148 (2.25562 iter/s, 5.32003s/12 iters), loss = 5.24957
I0410 03:02:14.686491 27877 solver.cpp:237]     Train net output #0: loss = 5.24957 (* 1 = 5.24957 loss)
I0410 03:02:14.686501 27877 sgd_solver.cpp:105] Iteration 8148, lr = 0.00199089
I0410 03:02:19.177397 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8160.caffemodel
I0410 03:02:20.052004 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8160.solverstate
I0410 03:02:20.658376 27877 solver.cpp:330] Iteration 8160, Testing net (#0)
I0410 03:02:20.658396 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:02:21.879004 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:02:25.194380 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:02:25.194430 27877 solver.cpp:397]     Test net output #1: loss = 5.28642 (* 1 = 5.28642 loss)
I0410 03:02:25.277006 27877 solver.cpp:218] Iteration 8160 (1.13312 iter/s, 10.5902s/12 iters), loss = 5.26286
I0410 03:02:25.277055 27877 solver.cpp:237]     Train net output #0: loss = 5.26286 (* 1 = 5.26286 loss)
I0410 03:02:25.277066 27877 sgd_solver.cpp:105] Iteration 8160, lr = 0.00198616
I0410 03:02:29.473140 27877 solver.cpp:218] Iteration 8172 (2.85989 iter/s, 4.19597s/12 iters), loss = 5.28671
I0410 03:02:29.473186 27877 solver.cpp:237]     Train net output #0: loss = 5.28671 (* 1 = 5.28671 loss)
I0410 03:02:29.473196 27877 sgd_solver.cpp:105] Iteration 8172, lr = 0.00198145
I0410 03:02:34.333195 27877 solver.cpp:218] Iteration 8184 (2.4692 iter/s, 4.85988s/12 iters), loss = 5.27361
I0410 03:02:34.333250 27877 solver.cpp:237]     Train net output #0: loss = 5.27361 (* 1 = 5.27361 loss)
I0410 03:02:34.333261 27877 sgd_solver.cpp:105] Iteration 8184, lr = 0.00197674
I0410 03:02:37.854338 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:02:39.289799 27877 solver.cpp:218] Iteration 8196 (2.4211 iter/s, 4.95642s/12 iters), loss = 5.27231
I0410 03:02:39.289842 27877 solver.cpp:237]     Train net output #0: loss = 5.27231 (* 1 = 5.27231 loss)
I0410 03:02:39.289851 27877 sgd_solver.cpp:105] Iteration 8196, lr = 0.00197205
I0410 03:02:44.292992 27877 solver.cpp:218] Iteration 8208 (2.39855 iter/s, 5.00301s/12 iters), loss = 5.25811
I0410 03:02:44.293040 27877 solver.cpp:237]     Train net output #0: loss = 5.25811 (* 1 = 5.25811 loss)
I0410 03:02:44.293048 27877 sgd_solver.cpp:105] Iteration 8208, lr = 0.00196737
I0410 03:02:49.221242 27877 solver.cpp:218] Iteration 8220 (2.43503 iter/s, 4.92807s/12 iters), loss = 5.26227
I0410 03:02:49.221278 27877 solver.cpp:237]     Train net output #0: loss = 5.26227 (* 1 = 5.26227 loss)
I0410 03:02:49.221287 27877 sgd_solver.cpp:105] Iteration 8220, lr = 0.0019627
I0410 03:02:54.233343 27877 solver.cpp:218] Iteration 8232 (2.39429 iter/s, 5.01193s/12 iters), loss = 5.2702
I0410 03:02:54.233382 27877 solver.cpp:237]     Train net output #0: loss = 5.2702 (* 1 = 5.2702 loss)
I0410 03:02:54.233390 27877 sgd_solver.cpp:105] Iteration 8232, lr = 0.00195804
I0410 03:02:59.246191 27877 solver.cpp:218] Iteration 8244 (2.39393 iter/s, 5.01267s/12 iters), loss = 5.25379
I0410 03:02:59.246234 27877 solver.cpp:237]     Train net output #0: loss = 5.25379 (* 1 = 5.25379 loss)
I0410 03:02:59.246244 27877 sgd_solver.cpp:105] Iteration 8244, lr = 0.00195339
I0410 03:03:04.467875 27877 solver.cpp:218] Iteration 8256 (2.29819 iter/s, 5.2215s/12 iters), loss = 5.27273
I0410 03:03:04.467926 27877 solver.cpp:237]     Train net output #0: loss = 5.27273 (* 1 = 5.27273 loss)
I0410 03:03:04.467937 27877 sgd_solver.cpp:105] Iteration 8256, lr = 0.00194875
I0410 03:03:06.484084 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8262.caffemodel
I0410 03:03:07.382032 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8262.solverstate
I0410 03:03:08.007588 27877 solver.cpp:330] Iteration 8262, Testing net (#0)
I0410 03:03:08.007679 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:03:09.186236 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:03:12.487028 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00612745
I0410 03:03:12.487064 27877 solver.cpp:397]     Test net output #1: loss = 5.28648 (* 1 = 5.28648 loss)
I0410 03:03:14.387601 27877 solver.cpp:218] Iteration 8268 (1.20975 iter/s, 9.91943s/12 iters), loss = 5.27703
I0410 03:03:14.387645 27877 solver.cpp:237]     Train net output #0: loss = 5.27703 (* 1 = 5.27703 loss)
I0410 03:03:14.387653 27877 sgd_solver.cpp:105] Iteration 8268, lr = 0.00194412
I0410 03:03:19.362344 27877 solver.cpp:218] Iteration 8280 (2.41227 iter/s, 4.97456s/12 iters), loss = 5.28374
I0410 03:03:19.362403 27877 solver.cpp:237]     Train net output #0: loss = 5.28374 (* 1 = 5.28374 loss)
I0410 03:03:19.362416 27877 sgd_solver.cpp:105] Iteration 8280, lr = 0.00193951
I0410 03:03:24.362686 27877 solver.cpp:218] Iteration 8292 (2.39993 iter/s, 5.00015s/12 iters), loss = 5.29046
I0410 03:03:24.362747 27877 solver.cpp:237]     Train net output #0: loss = 5.29046 (* 1 = 5.29046 loss)
I0410 03:03:24.362762 27877 sgd_solver.cpp:105] Iteration 8292, lr = 0.0019349
I0410 03:03:25.031443 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:03:29.334137 27877 solver.cpp:218] Iteration 8304 (2.41388 iter/s, 4.97125s/12 iters), loss = 5.27832
I0410 03:03:29.334201 27877 solver.cpp:237]     Train net output #0: loss = 5.27832 (* 1 = 5.27832 loss)
I0410 03:03:29.334214 27877 sgd_solver.cpp:105] Iteration 8304, lr = 0.00193031
I0410 03:03:31.369745 27877 blocking_queue.cpp:49] Waiting for data
I0410 03:03:34.330554 27877 solver.cpp:218] Iteration 8316 (2.40181 iter/s, 4.99622s/12 iters), loss = 5.2716
I0410 03:03:34.330606 27877 solver.cpp:237]     Train net output #0: loss = 5.2716 (* 1 = 5.2716 loss)
I0410 03:03:34.330621 27877 sgd_solver.cpp:105] Iteration 8316, lr = 0.00192573
I0410 03:03:39.301793 27877 solver.cpp:218] Iteration 8328 (2.41398 iter/s, 4.97105s/12 iters), loss = 5.28063
I0410 03:03:39.301975 27877 solver.cpp:237]     Train net output #0: loss = 5.28063 (* 1 = 5.28063 loss)
I0410 03:03:39.301990 27877 sgd_solver.cpp:105] Iteration 8328, lr = 0.00192115
I0410 03:03:44.233197 27877 solver.cpp:218] Iteration 8340 (2.43353 iter/s, 4.93111s/12 iters), loss = 5.27305
I0410 03:03:44.233242 27877 solver.cpp:237]     Train net output #0: loss = 5.27305 (* 1 = 5.27305 loss)
I0410 03:03:44.233249 27877 sgd_solver.cpp:105] Iteration 8340, lr = 0.00191659
I0410 03:03:49.149827 27877 solver.cpp:218] Iteration 8352 (2.44078 iter/s, 4.91646s/12 iters), loss = 5.29104
I0410 03:03:49.149876 27877 solver.cpp:237]     Train net output #0: loss = 5.29104 (* 1 = 5.29104 loss)
I0410 03:03:49.149889 27877 sgd_solver.cpp:105] Iteration 8352, lr = 0.00191204
I0410 03:03:53.633268 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8364.caffemodel
I0410 03:03:57.592850 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8364.solverstate
I0410 03:03:58.864537 27877 solver.cpp:330] Iteration 8364, Testing net (#0)
I0410 03:03:58.864567 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:04:00.061558 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:04:03.385495 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:04:03.385545 27877 solver.cpp:397]     Test net output #1: loss = 5.2862 (* 1 = 5.2862 loss)
I0410 03:04:03.468222 27877 solver.cpp:218] Iteration 8364 (0.838107 iter/s, 14.318s/12 iters), loss = 5.26418
I0410 03:04:03.468277 27877 solver.cpp:237]     Train net output #0: loss = 5.26418 (* 1 = 5.26418 loss)
I0410 03:04:03.468289 27877 sgd_solver.cpp:105] Iteration 8364, lr = 0.0019075
I0410 03:04:07.605381 27877 solver.cpp:218] Iteration 8376 (2.90066 iter/s, 4.13699s/12 iters), loss = 5.26537
I0410 03:04:07.605437 27877 solver.cpp:237]     Train net output #0: loss = 5.26537 (* 1 = 5.26537 loss)
I0410 03:04:07.605450 27877 sgd_solver.cpp:105] Iteration 8376, lr = 0.00190297
I0410 03:04:12.781751 27877 solver.cpp:218] Iteration 8388 (2.31831 iter/s, 5.17618s/12 iters), loss = 5.2614
I0410 03:04:12.781883 27877 solver.cpp:237]     Train net output #0: loss = 5.2614 (* 1 = 5.2614 loss)
I0410 03:04:12.781895 27877 sgd_solver.cpp:105] Iteration 8388, lr = 0.00189846
I0410 03:04:15.547623 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:04:17.645617 27877 solver.cpp:218] Iteration 8400 (2.46731 iter/s, 4.8636s/12 iters), loss = 5.26493
I0410 03:04:17.645681 27877 solver.cpp:237]     Train net output #0: loss = 5.26493 (* 1 = 5.26493 loss)
I0410 03:04:17.645694 27877 sgd_solver.cpp:105] Iteration 8400, lr = 0.00189395
I0410 03:04:22.502341 27877 solver.cpp:218] Iteration 8412 (2.4709 iter/s, 4.85653s/12 iters), loss = 5.24989
I0410 03:04:22.502401 27877 solver.cpp:237]     Train net output #0: loss = 5.24989 (* 1 = 5.24989 loss)
I0410 03:04:22.502413 27877 sgd_solver.cpp:105] Iteration 8412, lr = 0.00188945
I0410 03:04:27.390728 27877 solver.cpp:218] Iteration 8424 (2.45489 iter/s, 4.88819s/12 iters), loss = 5.25554
I0410 03:04:27.390792 27877 solver.cpp:237]     Train net output #0: loss = 5.25554 (* 1 = 5.25554 loss)
I0410 03:04:27.390805 27877 sgd_solver.cpp:105] Iteration 8424, lr = 0.00188497
I0410 03:04:32.251381 27877 solver.cpp:218] Iteration 8436 (2.4689 iter/s, 4.86046s/12 iters), loss = 5.25517
I0410 03:04:32.251447 27877 solver.cpp:237]     Train net output #0: loss = 5.25517 (* 1 = 5.25517 loss)
I0410 03:04:32.251461 27877 sgd_solver.cpp:105] Iteration 8436, lr = 0.00188049
I0410 03:04:37.063716 27877 solver.cpp:218] Iteration 8448 (2.49369 iter/s, 4.81214s/12 iters), loss = 5.29436
I0410 03:04:37.063781 27877 solver.cpp:237]     Train net output #0: loss = 5.29436 (* 1 = 5.29436 loss)
I0410 03:04:37.063792 27877 sgd_solver.cpp:105] Iteration 8448, lr = 0.00187603
I0410 03:04:41.926375 27877 solver.cpp:218] Iteration 8460 (2.46788 iter/s, 4.86247s/12 iters), loss = 5.27352
I0410 03:04:41.926430 27877 solver.cpp:237]     Train net output #0: loss = 5.27352 (* 1 = 5.27352 loss)
I0410 03:04:41.926441 27877 sgd_solver.cpp:105] Iteration 8460, lr = 0.00187157
I0410 03:04:43.906953 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8466.caffemodel
I0410 03:04:46.246147 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8466.solverstate
I0410 03:04:47.014118 27877 solver.cpp:330] Iteration 8466, Testing net (#0)
I0410 03:04:47.014143 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:04:48.069070 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:04:51.438799 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:04:51.438850 27877 solver.cpp:397]     Test net output #1: loss = 5.28625 (* 1 = 5.28625 loss)
I0410 03:04:53.245085 27877 solver.cpp:218] Iteration 8472 (1.06022 iter/s, 11.3184s/12 iters), loss = 5.27132
I0410 03:04:53.245128 27877 solver.cpp:237]     Train net output #0: loss = 5.27132 (* 1 = 5.27132 loss)
I0410 03:04:53.245137 27877 sgd_solver.cpp:105] Iteration 8472, lr = 0.00186713
I0410 03:04:58.134402 27877 solver.cpp:218] Iteration 8484 (2.45442 iter/s, 4.88914s/12 iters), loss = 5.26885
I0410 03:04:58.134454 27877 solver.cpp:237]     Train net output #0: loss = 5.26885 (* 1 = 5.26885 loss)
I0410 03:04:58.134466 27877 sgd_solver.cpp:105] Iteration 8484, lr = 0.0018627
I0410 03:05:03.078385 27877 solver.cpp:218] Iteration 8496 (2.42728 iter/s, 4.9438s/12 iters), loss = 5.25723
I0410 03:05:03.078444 27877 solver.cpp:237]     Train net output #0: loss = 5.25723 (* 1 = 5.25723 loss)
I0410 03:05:03.078456 27877 sgd_solver.cpp:105] Iteration 8496, lr = 0.00185827
I0410 03:05:03.127669 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:05:08.024065 27877 solver.cpp:218] Iteration 8508 (2.42646 iter/s, 4.94548s/12 iters), loss = 5.27641
I0410 03:05:08.024123 27877 solver.cpp:237]     Train net output #0: loss = 5.27641 (* 1 = 5.27641 loss)
I0410 03:05:08.024135 27877 sgd_solver.cpp:105] Iteration 8508, lr = 0.00185386
I0410 03:05:12.894618 27877 solver.cpp:218] Iteration 8520 (2.46388 iter/s, 4.87036s/12 iters), loss = 5.29612
I0410 03:05:12.894670 27877 solver.cpp:237]     Train net output #0: loss = 5.29612 (* 1 = 5.29612 loss)
I0410 03:05:12.894681 27877 sgd_solver.cpp:105] Iteration 8520, lr = 0.00184946
I0410 03:05:17.831521 27877 solver.cpp:218] Iteration 8532 (2.43077 iter/s, 4.93671s/12 iters), loss = 5.2706
I0410 03:05:17.831681 27877 solver.cpp:237]     Train net output #0: loss = 5.2706 (* 1 = 5.2706 loss)
I0410 03:05:17.831692 27877 sgd_solver.cpp:105] Iteration 8532, lr = 0.00184507
I0410 03:05:22.819172 27877 solver.cpp:218] Iteration 8544 (2.40608 iter/s, 4.98736s/12 iters), loss = 5.27333
I0410 03:05:22.819221 27877 solver.cpp:237]     Train net output #0: loss = 5.27333 (* 1 = 5.27333 loss)
I0410 03:05:22.819233 27877 sgd_solver.cpp:105] Iteration 8544, lr = 0.00184069
I0410 03:05:27.878417 27877 solver.cpp:218] Iteration 8556 (2.37198 iter/s, 5.05906s/12 iters), loss = 5.25655
I0410 03:05:27.878461 27877 solver.cpp:237]     Train net output #0: loss = 5.25655 (* 1 = 5.25655 loss)
I0410 03:05:27.878471 27877 sgd_solver.cpp:105] Iteration 8556, lr = 0.00183632
I0410 03:05:32.307420 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8568.caffemodel
I0410 03:05:33.616462 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8568.solverstate
I0410 03:05:34.243376 27877 solver.cpp:330] Iteration 8568, Testing net (#0)
I0410 03:05:34.243404 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:05:35.271481 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:05:38.614380 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:05:38.614413 27877 solver.cpp:397]     Test net output #1: loss = 5.28636 (* 1 = 5.28636 loss)
I0410 03:05:38.696849 27877 solver.cpp:218] Iteration 8568 (1.10925 iter/s, 10.8181s/12 iters), loss = 5.24719
I0410 03:05:38.696897 27877 solver.cpp:237]     Train net output #0: loss = 5.24719 (* 1 = 5.24719 loss)
I0410 03:05:38.696905 27877 sgd_solver.cpp:105] Iteration 8568, lr = 0.00183196
I0410 03:05:42.941992 27877 solver.cpp:218] Iteration 8580 (2.82687 iter/s, 4.24498s/12 iters), loss = 5.26216
I0410 03:05:42.942034 27877 solver.cpp:237]     Train net output #0: loss = 5.26216 (* 1 = 5.26216 loss)
I0410 03:05:42.942042 27877 sgd_solver.cpp:105] Iteration 8580, lr = 0.00182761
I0410 03:05:47.920341 27877 solver.cpp:218] Iteration 8592 (2.41053 iter/s, 4.97817s/12 iters), loss = 5.25239
I0410 03:05:47.920439 27877 solver.cpp:237]     Train net output #0: loss = 5.25239 (* 1 = 5.25239 loss)
I0410 03:05:47.920455 27877 sgd_solver.cpp:105] Iteration 8592, lr = 0.00182327
I0410 03:05:50.107614 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:05:52.886478 27877 solver.cpp:218] Iteration 8604 (2.41648 iter/s, 4.96591s/12 iters), loss = 5.26785
I0410 03:05:52.886521 27877 solver.cpp:237]     Train net output #0: loss = 5.26785 (* 1 = 5.26785 loss)
I0410 03:05:52.886529 27877 sgd_solver.cpp:105] Iteration 8604, lr = 0.00181894
I0410 03:05:57.775712 27877 solver.cpp:218] Iteration 8616 (2.45446 iter/s, 4.88905s/12 iters), loss = 5.26539
I0410 03:05:57.775772 27877 solver.cpp:237]     Train net output #0: loss = 5.26539 (* 1 = 5.26539 loss)
I0410 03:05:57.775785 27877 sgd_solver.cpp:105] Iteration 8616, lr = 0.00181462
I0410 03:06:02.708390 27877 solver.cpp:218] Iteration 8628 (2.43285 iter/s, 4.93248s/12 iters), loss = 5.2858
I0410 03:06:02.708451 27877 solver.cpp:237]     Train net output #0: loss = 5.2858 (* 1 = 5.2858 loss)
I0410 03:06:02.708463 27877 sgd_solver.cpp:105] Iteration 8628, lr = 0.00181031
I0410 03:06:07.572111 27877 solver.cpp:218] Iteration 8640 (2.46734 iter/s, 4.86353s/12 iters), loss = 5.26416
I0410 03:06:07.572154 27877 solver.cpp:237]     Train net output #0: loss = 5.26416 (* 1 = 5.26416 loss)
I0410 03:06:07.572162 27877 sgd_solver.cpp:105] Iteration 8640, lr = 0.00180602
I0410 03:06:12.553879 27877 solver.cpp:218] Iteration 8652 (2.40887 iter/s, 4.98159s/12 iters), loss = 5.267
I0410 03:06:12.553938 27877 solver.cpp:237]     Train net output #0: loss = 5.267 (* 1 = 5.267 loss)
I0410 03:06:12.553951 27877 sgd_solver.cpp:105] Iteration 8652, lr = 0.00180173
I0410 03:06:17.463224 27877 solver.cpp:218] Iteration 8664 (2.44441 iter/s, 4.90915s/12 iters), loss = 5.2726
I0410 03:06:17.463282 27877 solver.cpp:237]     Train net output #0: loss = 5.2726 (* 1 = 5.2726 loss)
I0410 03:06:17.463295 27877 sgd_solver.cpp:105] Iteration 8664, lr = 0.00179745
I0410 03:06:19.467269 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8670.caffemodel
I0410 03:06:21.151103 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8670.solverstate
I0410 03:06:22.986562 27877 solver.cpp:330] Iteration 8670, Testing net (#0)
I0410 03:06:22.986589 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:06:24.071233 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:06:27.447633 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:06:27.447680 27877 solver.cpp:397]     Test net output #1: loss = 5.28666 (* 1 = 5.28666 loss)
I0410 03:06:29.307757 27877 solver.cpp:218] Iteration 8676 (1.01316 iter/s, 11.8442s/12 iters), loss = 5.27521
I0410 03:06:29.307799 27877 solver.cpp:237]     Train net output #0: loss = 5.27521 (* 1 = 5.27521 loss)
I0410 03:06:29.307807 27877 sgd_solver.cpp:105] Iteration 8676, lr = 0.00179318
I0410 03:06:34.262753 27877 solver.cpp:218] Iteration 8688 (2.42189 iter/s, 4.95481s/12 iters), loss = 5.26172
I0410 03:06:34.262809 27877 solver.cpp:237]     Train net output #0: loss = 5.26172 (* 1 = 5.26172 loss)
I0410 03:06:34.262820 27877 sgd_solver.cpp:105] Iteration 8688, lr = 0.00178893
I0410 03:06:38.470425 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:06:39.143760 27877 solver.cpp:218] Iteration 8700 (2.4586 iter/s, 4.88082s/12 iters), loss = 5.26458
I0410 03:06:39.143801 27877 solver.cpp:237]     Train net output #0: loss = 5.26458 (* 1 = 5.26458 loss)
I0410 03:06:39.143810 27877 sgd_solver.cpp:105] Iteration 8700, lr = 0.00178468
I0410 03:06:44.106339 27877 solver.cpp:218] Iteration 8712 (2.41818 iter/s, 4.9624s/12 iters), loss = 5.27981
I0410 03:06:44.106395 27877 solver.cpp:237]     Train net output #0: loss = 5.27981 (* 1 = 5.27981 loss)
I0410 03:06:44.106407 27877 sgd_solver.cpp:105] Iteration 8712, lr = 0.00178044
I0410 03:06:49.096730 27877 solver.cpp:218] Iteration 8724 (2.40471 iter/s, 4.9902s/12 iters), loss = 5.27989
I0410 03:06:49.096781 27877 solver.cpp:237]     Train net output #0: loss = 5.27989 (* 1 = 5.27989 loss)
I0410 03:06:49.096791 27877 sgd_solver.cpp:105] Iteration 8724, lr = 0.00177621
I0410 03:06:54.061115 27877 solver.cpp:218] Iteration 8736 (2.41731 iter/s, 4.9642s/12 iters), loss = 5.29484
I0410 03:06:54.062134 27877 solver.cpp:237]     Train net output #0: loss = 5.29484 (* 1 = 5.29484 loss)
I0410 03:06:54.062142 27877 sgd_solver.cpp:105] Iteration 8736, lr = 0.001772
I0410 03:06:58.970768 27877 solver.cpp:218] Iteration 8748 (2.44474 iter/s, 4.9085s/12 iters), loss = 5.27199
I0410 03:06:58.970827 27877 solver.cpp:237]     Train net output #0: loss = 5.27199 (* 1 = 5.27199 loss)
I0410 03:06:58.970839 27877 sgd_solver.cpp:105] Iteration 8748, lr = 0.00176779
I0410 03:07:04.088321 27877 solver.cpp:218] Iteration 8760 (2.34496 iter/s, 5.11735s/12 iters), loss = 5.27897
I0410 03:07:04.088372 27877 solver.cpp:237]     Train net output #0: loss = 5.27897 (* 1 = 5.27897 loss)
I0410 03:07:04.088384 27877 sgd_solver.cpp:105] Iteration 8760, lr = 0.00176359
I0410 03:07:08.759986 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8772.caffemodel
I0410 03:07:09.605326 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8772.solverstate
I0410 03:07:10.229074 27877 solver.cpp:330] Iteration 8772, Testing net (#0)
I0410 03:07:10.229102 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:07:11.348917 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:07:14.898329 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:07:14.898373 27877 solver.cpp:397]     Test net output #1: loss = 5.2867 (* 1 = 5.2867 loss)
I0410 03:07:14.981439 27877 solver.cpp:218] Iteration 8772 (1.10165 iter/s, 10.8928s/12 iters), loss = 5.27721
I0410 03:07:14.981510 27877 solver.cpp:237]     Train net output #0: loss = 5.27721 (* 1 = 5.27721 loss)
I0410 03:07:14.981524 27877 sgd_solver.cpp:105] Iteration 8772, lr = 0.00175941
I0410 03:07:19.081250 27877 solver.cpp:218] Iteration 8784 (2.92709 iter/s, 4.09963s/12 iters), loss = 5.27718
I0410 03:07:19.081305 27877 solver.cpp:237]     Train net output #0: loss = 5.27718 (* 1 = 5.27718 loss)
I0410 03:07:19.081317 27877 sgd_solver.cpp:105] Iteration 8784, lr = 0.00175523
I0410 03:07:23.963153 27877 solver.cpp:218] Iteration 8796 (2.45815 iter/s, 4.88172s/12 iters), loss = 5.25832
I0410 03:07:23.963197 27877 solver.cpp:237]     Train net output #0: loss = 5.25832 (* 1 = 5.25832 loss)
I0410 03:07:23.963207 27877 sgd_solver.cpp:105] Iteration 8796, lr = 0.00175106
I0410 03:07:25.398383 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:07:28.914253 27877 solver.cpp:218] Iteration 8808 (2.42379 iter/s, 4.95092s/12 iters), loss = 5.26107
I0410 03:07:28.914317 27877 solver.cpp:237]     Train net output #0: loss = 5.26107 (* 1 = 5.26107 loss)
I0410 03:07:28.914330 27877 sgd_solver.cpp:105] Iteration 8808, lr = 0.0017469
I0410 03:07:33.848949 27877 solver.cpp:218] Iteration 8820 (2.43186 iter/s, 4.9345s/12 iters), loss = 5.26593
I0410 03:07:33.848999 27877 solver.cpp:237]     Train net output #0: loss = 5.26593 (* 1 = 5.26593 loss)
I0410 03:07:33.849009 27877 sgd_solver.cpp:105] Iteration 8820, lr = 0.00174276
I0410 03:07:38.741021 27877 solver.cpp:218] Iteration 8832 (2.45304 iter/s, 4.89189s/12 iters), loss = 5.26567
I0410 03:07:38.741065 27877 solver.cpp:237]     Train net output #0: loss = 5.26567 (* 1 = 5.26567 loss)
I0410 03:07:38.741073 27877 sgd_solver.cpp:105] Iteration 8832, lr = 0.00173862
I0410 03:07:43.716336 27877 solver.cpp:218] Iteration 8844 (2.41199 iter/s, 4.97514s/12 iters), loss = 5.2958
I0410 03:07:43.716372 27877 solver.cpp:237]     Train net output #0: loss = 5.2958 (* 1 = 5.2958 loss)
I0410 03:07:43.716379 27877 sgd_solver.cpp:105] Iteration 8844, lr = 0.00173449
I0410 03:07:48.612174 27877 solver.cpp:218] Iteration 8856 (2.45115 iter/s, 4.89566s/12 iters), loss = 5.25759
I0410 03:07:48.612236 27877 solver.cpp:237]     Train net output #0: loss = 5.25759 (* 1 = 5.25759 loss)
I0410 03:07:48.612249 27877 sgd_solver.cpp:105] Iteration 8856, lr = 0.00173037
I0410 03:07:53.498106 27877 solver.cpp:218] Iteration 8868 (2.45613 iter/s, 4.88574s/12 iters), loss = 5.25776
I0410 03:07:53.498162 27877 solver.cpp:237]     Train net output #0: loss = 5.25776 (* 1 = 5.25776 loss)
I0410 03:07:53.498173 27877 sgd_solver.cpp:105] Iteration 8868, lr = 0.00172626
I0410 03:07:55.518146 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8874.caffemodel
I0410 03:07:57.715413 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8874.solverstate
I0410 03:08:00.652521 27877 solver.cpp:330] Iteration 8874, Testing net (#0)
I0410 03:08:00.652552 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:08:01.699120 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:08:05.212255 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:08:05.212299 27877 solver.cpp:397]     Test net output #1: loss = 5.28643 (* 1 = 5.28643 loss)
I0410 03:08:07.108431 27877 solver.cpp:218] Iteration 8880 (0.881709 iter/s, 13.6099s/12 iters), loss = 5.27938
I0410 03:08:07.108479 27877 solver.cpp:237]     Train net output #0: loss = 5.27938 (* 1 = 5.27938 loss)
I0410 03:08:07.108489 27877 sgd_solver.cpp:105] Iteration 8880, lr = 0.00172217
I0410 03:08:12.105479 27877 solver.cpp:218] Iteration 8892 (2.40151 iter/s, 4.99686s/12 iters), loss = 5.2803
I0410 03:08:12.105533 27877 solver.cpp:237]     Train net output #0: loss = 5.2803 (* 1 = 5.2803 loss)
I0410 03:08:12.105545 27877 sgd_solver.cpp:105] Iteration 8892, lr = 0.00171808
I0410 03:08:15.653565 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:08:17.063344 27877 solver.cpp:218] Iteration 8904 (2.42049 iter/s, 4.95767s/12 iters), loss = 5.27528
I0410 03:08:17.063390 27877 solver.cpp:237]     Train net output #0: loss = 5.27528 (* 1 = 5.27528 loss)
I0410 03:08:17.063400 27877 sgd_solver.cpp:105] Iteration 8904, lr = 0.001714
I0410 03:08:21.947686 27877 solver.cpp:218] Iteration 8916 (2.45692 iter/s, 4.88416s/12 iters), loss = 5.26651
I0410 03:08:21.947743 27877 solver.cpp:237]     Train net output #0: loss = 5.26651 (* 1 = 5.26651 loss)
I0410 03:08:21.947755 27877 sgd_solver.cpp:105] Iteration 8916, lr = 0.00170993
I0410 03:08:26.882532 27877 solver.cpp:218] Iteration 8928 (2.43178 iter/s, 4.93466s/12 iters), loss = 5.26122
I0410 03:08:26.882647 27877 solver.cpp:237]     Train net output #0: loss = 5.26122 (* 1 = 5.26122 loss)
I0410 03:08:26.882655 27877 sgd_solver.cpp:105] Iteration 8928, lr = 0.00170587
I0410 03:08:31.814934 27877 solver.cpp:218] Iteration 8940 (2.43301 iter/s, 4.93216s/12 iters), loss = 5.2663
I0410 03:08:31.814972 27877 solver.cpp:237]     Train net output #0: loss = 5.2663 (* 1 = 5.2663 loss)
I0410 03:08:31.814981 27877 sgd_solver.cpp:105] Iteration 8940, lr = 0.00170182
I0410 03:08:36.715801 27877 solver.cpp:218] Iteration 8952 (2.44863 iter/s, 4.90069s/12 iters), loss = 5.25523
I0410 03:08:36.715845 27877 solver.cpp:237]     Train net output #0: loss = 5.25523 (* 1 = 5.25523 loss)
I0410 03:08:36.715853 27877 sgd_solver.cpp:105] Iteration 8952, lr = 0.00169778
I0410 03:08:41.591867 27877 solver.cpp:218] Iteration 8964 (2.46109 iter/s, 4.87589s/12 iters), loss = 5.27704
I0410 03:08:41.591928 27877 solver.cpp:237]     Train net output #0: loss = 5.27704 (* 1 = 5.27704 loss)
I0410 03:08:41.591939 27877 sgd_solver.cpp:105] Iteration 8964, lr = 0.00169375
I0410 03:08:46.099037 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_8976.caffemodel
I0410 03:08:46.963593 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_8976.solverstate
I0410 03:08:47.591600 27877 solver.cpp:330] Iteration 8976, Testing net (#0)
I0410 03:08:47.591624 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:08:48.430806 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:08:51.941463 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:08:51.941512 27877 solver.cpp:397]     Test net output #1: loss = 5.28647 (* 1 = 5.28647 loss)
I0410 03:08:52.024255 27877 solver.cpp:218] Iteration 8976 (1.1503 iter/s, 10.4321s/12 iters), loss = 5.27796
I0410 03:08:52.024303 27877 solver.cpp:237]     Train net output #0: loss = 5.27796 (* 1 = 5.27796 loss)
I0410 03:08:52.024313 27877 sgd_solver.cpp:105] Iteration 8976, lr = 0.00168973
I0410 03:08:56.165447 27877 solver.cpp:218] Iteration 8988 (2.89783 iter/s, 4.14103s/12 iters), loss = 5.28351
I0410 03:08:56.165495 27877 solver.cpp:237]     Train net output #0: loss = 5.28351 (* 1 = 5.28351 loss)
I0410 03:08:56.165504 27877 sgd_solver.cpp:105] Iteration 8988, lr = 0.00168571
I0410 03:08:58.630355 27877 blocking_queue.cpp:49] Waiting for data
I0410 03:09:01.179029 27877 solver.cpp:218] Iteration 9000 (2.39359 iter/s, 5.0134s/12 iters), loss = 5.28546
I0410 03:09:01.179066 27877 solver.cpp:237]     Train net output #0: loss = 5.28546 (* 1 = 5.28546 loss)
I0410 03:09:01.179075 27877 sgd_solver.cpp:105] Iteration 9000, lr = 0.00168171
I0410 03:09:01.872278 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:09:06.040436 27877 solver.cpp:218] Iteration 9012 (2.46851 iter/s, 4.86124s/12 iters), loss = 5.28481
I0410 03:09:06.040472 27877 solver.cpp:237]     Train net output #0: loss = 5.28481 (* 1 = 5.28481 loss)
I0410 03:09:06.040480 27877 sgd_solver.cpp:105] Iteration 9012, lr = 0.00167772
I0410 03:09:10.932173 27877 solver.cpp:218] Iteration 9024 (2.45321 iter/s, 4.89156s/12 iters), loss = 5.26475
I0410 03:09:10.932226 27877 solver.cpp:237]     Train net output #0: loss = 5.26475 (* 1 = 5.26475 loss)
I0410 03:09:10.932235 27877 sgd_solver.cpp:105] Iteration 9024, lr = 0.00167374
I0410 03:09:15.838996 27877 solver.cpp:218] Iteration 9036 (2.44567 iter/s, 4.90664s/12 iters), loss = 5.27473
I0410 03:09:15.839036 27877 solver.cpp:237]     Train net output #0: loss = 5.27473 (* 1 = 5.27473 loss)
I0410 03:09:15.839046 27877 sgd_solver.cpp:105] Iteration 9036, lr = 0.00166976
I0410 03:09:20.742018 27877 solver.cpp:218] Iteration 9048 (2.44756 iter/s, 4.90285s/12 iters), loss = 5.27449
I0410 03:09:20.742059 27877 solver.cpp:237]     Train net output #0: loss = 5.27449 (* 1 = 5.27449 loss)
I0410 03:09:20.742069 27877 sgd_solver.cpp:105] Iteration 9048, lr = 0.0016658
I0410 03:09:25.661980 27877 solver.cpp:218] Iteration 9060 (2.43914 iter/s, 4.91977s/12 iters), loss = 5.29029
I0410 03:09:25.662027 27877 solver.cpp:237]     Train net output #0: loss = 5.29029 (* 1 = 5.29029 loss)
I0410 03:09:25.662039 27877 sgd_solver.cpp:105] Iteration 9060, lr = 0.00166184
I0410 03:09:30.581282 27877 solver.cpp:218] Iteration 9072 (2.43946 iter/s, 4.91912s/12 iters), loss = 5.2683
I0410 03:09:30.581431 27877 solver.cpp:237]     Train net output #0: loss = 5.2683 (* 1 = 5.2683 loss)
I0410 03:09:30.581444 27877 sgd_solver.cpp:105] Iteration 9072, lr = 0.0016579
I0410 03:09:32.602169 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9078.caffemodel
I0410 03:09:33.430999 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9078.solverstate
I0410 03:09:34.059479 27877 solver.cpp:330] Iteration 9078, Testing net (#0)
I0410 03:09:34.059509 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:09:34.941879 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:09:38.493211 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:09:38.493257 27877 solver.cpp:397]     Test net output #1: loss = 5.28663 (* 1 = 5.28663 loss)
I0410 03:09:40.408545 27877 solver.cpp:218] Iteration 9084 (1.22114 iter/s, 9.82686s/12 iters), loss = 5.2583
I0410 03:09:40.408593 27877 solver.cpp:237]     Train net output #0: loss = 5.2583 (* 1 = 5.2583 loss)
I0410 03:09:40.408602 27877 sgd_solver.cpp:105] Iteration 9084, lr = 0.00165396
I0410 03:09:45.329613 27877 solver.cpp:218] Iteration 9096 (2.43858 iter/s, 4.92089s/12 iters), loss = 5.26781
I0410 03:09:45.329664 27877 solver.cpp:237]     Train net output #0: loss = 5.26781 (* 1 = 5.26781 loss)
I0410 03:09:45.329676 27877 sgd_solver.cpp:105] Iteration 9096, lr = 0.00165003
I0410 03:09:48.221415 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:09:50.246006 27877 solver.cpp:218] Iteration 9108 (2.44091 iter/s, 4.91621s/12 iters), loss = 5.26331
I0410 03:09:50.246063 27877 solver.cpp:237]     Train net output #0: loss = 5.26331 (* 1 = 5.26331 loss)
I0410 03:09:50.246074 27877 sgd_solver.cpp:105] Iteration 9108, lr = 0.00164612
I0410 03:09:55.132279 27877 solver.cpp:218] Iteration 9120 (2.45595 iter/s, 4.88609s/12 iters), loss = 5.25326
I0410 03:09:55.132326 27877 solver.cpp:237]     Train net output #0: loss = 5.25326 (* 1 = 5.25326 loss)
I0410 03:09:55.132335 27877 sgd_solver.cpp:105] Iteration 9120, lr = 0.00164221
I0410 03:10:00.019306 27877 solver.cpp:218] Iteration 9132 (2.45557 iter/s, 4.88685s/12 iters), loss = 5.25059
I0410 03:10:00.019351 27877 solver.cpp:237]     Train net output #0: loss = 5.25059 (* 1 = 5.25059 loss)
I0410 03:10:00.019361 27877 sgd_solver.cpp:105] Iteration 9132, lr = 0.00163831
I0410 03:10:04.950613 27877 solver.cpp:218] Iteration 9144 (2.43352 iter/s, 4.93112s/12 iters), loss = 5.25722
I0410 03:10:04.950731 27877 solver.cpp:237]     Train net output #0: loss = 5.25722 (* 1 = 5.25722 loss)
I0410 03:10:04.950744 27877 sgd_solver.cpp:105] Iteration 9144, lr = 0.00163442
I0410 03:10:10.208098 27877 solver.cpp:218] Iteration 9156 (2.28257 iter/s, 5.25723s/12 iters), loss = 5.28471
I0410 03:10:10.208145 27877 solver.cpp:237]     Train net output #0: loss = 5.28471 (* 1 = 5.28471 loss)
I0410 03:10:10.208154 27877 sgd_solver.cpp:105] Iteration 9156, lr = 0.00163054
I0410 03:10:15.052579 27877 solver.cpp:218] Iteration 9168 (2.47713 iter/s, 4.84431s/12 iters), loss = 5.27161
I0410 03:10:15.052615 27877 solver.cpp:237]     Train net output #0: loss = 5.27161 (* 1 = 5.27161 loss)
I0410 03:10:15.052624 27877 sgd_solver.cpp:105] Iteration 9168, lr = 0.00162667
I0410 03:10:19.473716 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9180.caffemodel
I0410 03:10:21.023208 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9180.solverstate
I0410 03:10:22.336747 27877 solver.cpp:330] Iteration 9180, Testing net (#0)
I0410 03:10:22.336777 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:10:23.206480 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:10:26.785593 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:10:26.785638 27877 solver.cpp:397]     Test net output #1: loss = 5.28691 (* 1 = 5.28691 loss)
I0410 03:10:26.868433 27877 solver.cpp:218] Iteration 9180 (1.01561 iter/s, 11.8155s/12 iters), loss = 5.27355
I0410 03:10:26.868487 27877 solver.cpp:237]     Train net output #0: loss = 5.27355 (* 1 = 5.27355 loss)
I0410 03:10:26.868499 27877 sgd_solver.cpp:105] Iteration 9180, lr = 0.00162281
I0410 03:10:30.956602 27877 solver.cpp:218] Iteration 9192 (2.93542 iter/s, 4.08801s/12 iters), loss = 5.27607
I0410 03:10:30.956646 27877 solver.cpp:237]     Train net output #0: loss = 5.27607 (* 1 = 5.27607 loss)
I0410 03:10:30.956656 27877 sgd_solver.cpp:105] Iteration 9192, lr = 0.00161895
I0410 03:10:36.063853 27877 solver.cpp:218] Iteration 9204 (2.34968 iter/s, 5.10707s/12 iters), loss = 5.26529
I0410 03:10:36.063987 27877 solver.cpp:237]     Train net output #0: loss = 5.26529 (* 1 = 5.26529 loss)
I0410 03:10:36.063999 27877 sgd_solver.cpp:105] Iteration 9204, lr = 0.00161511
I0410 03:10:36.145597 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:10:41.240330 27877 solver.cpp:218] Iteration 9216 (2.3183 iter/s, 5.17621s/12 iters), loss = 5.2778
I0410 03:10:41.240386 27877 solver.cpp:237]     Train net output #0: loss = 5.2778 (* 1 = 5.2778 loss)
I0410 03:10:41.240398 27877 sgd_solver.cpp:105] Iteration 9216, lr = 0.00161128
I0410 03:10:46.108950 27877 solver.cpp:218] Iteration 9228 (2.46486 iter/s, 4.86843s/12 iters), loss = 5.28703
I0410 03:10:46.108999 27877 solver.cpp:237]     Train net output #0: loss = 5.28703 (* 1 = 5.28703 loss)
I0410 03:10:46.109009 27877 sgd_solver.cpp:105] Iteration 9228, lr = 0.00160745
I0410 03:10:51.061208 27877 solver.cpp:218] Iteration 9240 (2.42323 iter/s, 4.95207s/12 iters), loss = 5.26096
I0410 03:10:51.061244 27877 solver.cpp:237]     Train net output #0: loss = 5.26096 (* 1 = 5.26096 loss)
I0410 03:10:51.061252 27877 sgd_solver.cpp:105] Iteration 9240, lr = 0.00160363
I0410 03:10:56.015863 27877 solver.cpp:218] Iteration 9252 (2.42205 iter/s, 4.95449s/12 iters), loss = 5.27642
I0410 03:10:56.015899 27877 solver.cpp:237]     Train net output #0: loss = 5.27642 (* 1 = 5.27642 loss)
I0410 03:10:56.015908 27877 sgd_solver.cpp:105] Iteration 9252, lr = 0.00159983
I0410 03:11:01.022536 27877 solver.cpp:218] Iteration 9264 (2.39688 iter/s, 5.0065s/12 iters), loss = 5.26184
I0410 03:11:01.022585 27877 solver.cpp:237]     Train net output #0: loss = 5.26184 (* 1 = 5.26184 loss)
I0410 03:11:01.022596 27877 sgd_solver.cpp:105] Iteration 9264, lr = 0.00159603
I0410 03:11:06.016696 27877 solver.cpp:218] Iteration 9276 (2.40289 iter/s, 4.99398s/12 iters), loss = 5.2505
I0410 03:11:06.016737 27877 solver.cpp:237]     Train net output #0: loss = 5.2505 (* 1 = 5.2505 loss)
I0410 03:11:06.016746 27877 sgd_solver.cpp:105] Iteration 9276, lr = 0.00159224
I0410 03:11:08.020300 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9282.caffemodel
I0410 03:11:08.865921 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9282.solverstate
I0410 03:11:09.494155 27877 solver.cpp:330] Iteration 9282, Testing net (#0)
I0410 03:11:09.494189 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:11:10.302059 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:11:13.922351 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:11:13.922391 27877 solver.cpp:397]     Test net output #1: loss = 5.28644 (* 1 = 5.28644 loss)
I0410 03:11:15.842844 27877 solver.cpp:218] Iteration 9288 (1.22127 iter/s, 9.82585s/12 iters), loss = 5.26569
I0410 03:11:15.842887 27877 solver.cpp:237]     Train net output #0: loss = 5.26569 (* 1 = 5.26569 loss)
I0410 03:11:15.842895 27877 sgd_solver.cpp:105] Iteration 9288, lr = 0.00158846
I0410 03:11:20.716594 27877 solver.cpp:218] Iteration 9300 (2.46226 iter/s, 4.87358s/12 iters), loss = 5.2527
I0410 03:11:20.716634 27877 solver.cpp:237]     Train net output #0: loss = 5.2527 (* 1 = 5.2527 loss)
I0410 03:11:20.716640 27877 sgd_solver.cpp:105] Iteration 9300, lr = 0.00158469
I0410 03:11:22.914461 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:11:25.650573 27877 solver.cpp:218] Iteration 9312 (2.4322 iter/s, 4.9338s/12 iters), loss = 5.27391
I0410 03:11:25.650626 27877 solver.cpp:237]     Train net output #0: loss = 5.27391 (* 1 = 5.27391 loss)
I0410 03:11:25.650637 27877 sgd_solver.cpp:105] Iteration 9312, lr = 0.00158092
I0410 03:11:30.695255 27877 solver.cpp:218] Iteration 9324 (2.37883 iter/s, 5.04449s/12 iters), loss = 5.28087
I0410 03:11:30.695305 27877 solver.cpp:237]     Train net output #0: loss = 5.28087 (* 1 = 5.28087 loss)
I0410 03:11:30.695318 27877 sgd_solver.cpp:105] Iteration 9324, lr = 0.00157717
I0410 03:11:35.702086 27877 solver.cpp:218] Iteration 9336 (2.39681 iter/s, 5.00665s/12 iters), loss = 5.28531
I0410 03:11:35.702136 27877 solver.cpp:237]     Train net output #0: loss = 5.28531 (* 1 = 5.28531 loss)
I0410 03:11:35.702157 27877 sgd_solver.cpp:105] Iteration 9336, lr = 0.00157343
I0410 03:11:40.632364 27877 solver.cpp:218] Iteration 9348 (2.43403 iter/s, 4.93009s/12 iters), loss = 5.27175
I0410 03:11:40.632479 27877 solver.cpp:237]     Train net output #0: loss = 5.27175 (* 1 = 5.27175 loss)
I0410 03:11:40.632488 27877 sgd_solver.cpp:105] Iteration 9348, lr = 0.00156969
I0410 03:11:45.486244 27877 solver.cpp:218] Iteration 9360 (2.47238 iter/s, 4.85363s/12 iters), loss = 5.27082
I0410 03:11:45.486295 27877 solver.cpp:237]     Train net output #0: loss = 5.27082 (* 1 = 5.27082 loss)
I0410 03:11:45.486307 27877 sgd_solver.cpp:105] Iteration 9360, lr = 0.00156596
I0410 03:11:50.458564 27877 solver.cpp:218] Iteration 9372 (2.41345 iter/s, 4.97213s/12 iters), loss = 5.27432
I0410 03:11:50.458613 27877 solver.cpp:237]     Train net output #0: loss = 5.27432 (* 1 = 5.27432 loss)
I0410 03:11:50.458626 27877 sgd_solver.cpp:105] Iteration 9372, lr = 0.00156225
I0410 03:11:54.878650 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9384.caffemodel
I0410 03:11:56.059975 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9384.solverstate
I0410 03:11:56.802618 27877 solver.cpp:330] Iteration 9384, Testing net (#0)
I0410 03:11:56.802646 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:11:57.506027 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:12:01.269743 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:12:01.269794 27877 solver.cpp:397]     Test net output #1: loss = 5.2865 (* 1 = 5.2865 loss)
I0410 03:12:01.352372 27877 solver.cpp:218] Iteration 9384 (1.10158 iter/s, 10.8935s/12 iters), loss = 5.27542
I0410 03:12:01.352416 27877 solver.cpp:237]     Train net output #0: loss = 5.27542 (* 1 = 5.27542 loss)
I0410 03:12:01.352427 27877 sgd_solver.cpp:105] Iteration 9384, lr = 0.00155854
I0410 03:12:05.634116 27877 solver.cpp:218] Iteration 9396 (2.8027 iter/s, 4.28158s/12 iters), loss = 5.2692
I0410 03:12:05.634157 27877 solver.cpp:237]     Train net output #0: loss = 5.2692 (* 1 = 5.2692 loss)
I0410 03:12:05.634166 27877 sgd_solver.cpp:105] Iteration 9396, lr = 0.00155484
I0410 03:12:09.842401 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:12:10.491578 27877 solver.cpp:218] Iteration 9408 (2.47052 iter/s, 4.85728s/12 iters), loss = 5.26642
I0410 03:12:10.491631 27877 solver.cpp:237]     Train net output #0: loss = 5.26642 (* 1 = 5.26642 loss)
I0410 03:12:10.491643 27877 sgd_solver.cpp:105] Iteration 9408, lr = 0.00155114
I0410 03:12:15.394012 27877 solver.cpp:218] Iteration 9420 (2.44786 iter/s, 4.90225s/12 iters), loss = 5.27512
I0410 03:12:15.394179 27877 solver.cpp:237]     Train net output #0: loss = 5.27512 (* 1 = 5.27512 loss)
I0410 03:12:15.394192 27877 sgd_solver.cpp:105] Iteration 9420, lr = 0.00154746
I0410 03:12:20.258299 27877 solver.cpp:218] Iteration 9432 (2.46711 iter/s, 4.86399s/12 iters), loss = 5.28473
I0410 03:12:20.258337 27877 solver.cpp:237]     Train net output #0: loss = 5.28473 (* 1 = 5.28473 loss)
I0410 03:12:20.258347 27877 sgd_solver.cpp:105] Iteration 9432, lr = 0.00154379
I0410 03:12:25.126089 27877 solver.cpp:218] Iteration 9444 (2.46527 iter/s, 4.86761s/12 iters), loss = 5.28609
I0410 03:12:25.126142 27877 solver.cpp:237]     Train net output #0: loss = 5.28609 (* 1 = 5.28609 loss)
I0410 03:12:25.126152 27877 sgd_solver.cpp:105] Iteration 9444, lr = 0.00154012
I0410 03:12:29.961402 27877 solver.cpp:218] Iteration 9456 (2.48184 iter/s, 4.83512s/12 iters), loss = 5.26558
I0410 03:12:29.961444 27877 solver.cpp:237]     Train net output #0: loss = 5.26558 (* 1 = 5.26558 loss)
I0410 03:12:29.961452 27877 sgd_solver.cpp:105] Iteration 9456, lr = 0.00153647
I0410 03:12:34.842936 27877 solver.cpp:218] Iteration 9468 (2.45833 iter/s, 4.88135s/12 iters), loss = 5.27805
I0410 03:12:34.842983 27877 solver.cpp:237]     Train net output #0: loss = 5.27805 (* 1 = 5.27805 loss)
I0410 03:12:34.842993 27877 sgd_solver.cpp:105] Iteration 9468, lr = 0.00153282
I0410 03:12:39.765475 27877 solver.cpp:218] Iteration 9480 (2.43786 iter/s, 4.92235s/12 iters), loss = 5.27874
I0410 03:12:39.765523 27877 solver.cpp:237]     Train net output #0: loss = 5.27874 (* 1 = 5.27874 loss)
I0410 03:12:39.765533 27877 sgd_solver.cpp:105] Iteration 9480, lr = 0.00152918
I0410 03:12:41.733001 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9486.caffemodel
I0410 03:12:42.597677 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9486.solverstate
I0410 03:12:43.250798 27877 solver.cpp:330] Iteration 9486, Testing net (#0)
I0410 03:12:43.250818 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:12:43.953810 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:12:47.653574 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:12:47.653697 27877 solver.cpp:397]     Test net output #1: loss = 5.28597 (* 1 = 5.28597 loss)
I0410 03:12:49.558352 27877 solver.cpp:218] Iteration 9492 (1.22542 iter/s, 9.79258s/12 iters), loss = 5.26827
I0410 03:12:49.558389 27877 solver.cpp:237]     Train net output #0: loss = 5.26827 (* 1 = 5.26827 loss)
I0410 03:12:49.558398 27877 sgd_solver.cpp:105] Iteration 9492, lr = 0.00152555
I0410 03:12:54.409221 27877 solver.cpp:218] Iteration 9504 (2.47387 iter/s, 4.8507s/12 iters), loss = 5.25701
I0410 03:12:54.409258 27877 solver.cpp:237]     Train net output #0: loss = 5.25701 (* 1 = 5.25701 loss)
I0410 03:12:54.409266 27877 sgd_solver.cpp:105] Iteration 9504, lr = 0.00152193
I0410 03:12:55.832741 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:12:59.216008 27877 solver.cpp:218] Iteration 9516 (2.49656 iter/s, 4.80661s/12 iters), loss = 5.26217
I0410 03:12:59.216061 27877 solver.cpp:237]     Train net output #0: loss = 5.26217 (* 1 = 5.26217 loss)
I0410 03:12:59.216073 27877 sgd_solver.cpp:105] Iteration 9516, lr = 0.00151831
I0410 03:13:04.266479 27877 solver.cpp:218] Iteration 9528 (2.37611 iter/s, 5.05028s/12 iters), loss = 5.2627
I0410 03:13:04.266531 27877 solver.cpp:237]     Train net output #0: loss = 5.2627 (* 1 = 5.2627 loss)
I0410 03:13:04.266544 27877 sgd_solver.cpp:105] Iteration 9528, lr = 0.00151471
I0410 03:13:09.092922 27877 solver.cpp:218] Iteration 9540 (2.4864 iter/s, 4.82626s/12 iters), loss = 5.24775
I0410 03:13:09.092959 27877 solver.cpp:237]     Train net output #0: loss = 5.24775 (* 1 = 5.24775 loss)
I0410 03:13:09.092967 27877 sgd_solver.cpp:105] Iteration 9540, lr = 0.00151111
I0410 03:13:13.937875 27877 solver.cpp:218] Iteration 9552 (2.4769 iter/s, 4.84477s/12 iters), loss = 5.30258
I0410 03:13:13.937929 27877 solver.cpp:237]     Train net output #0: loss = 5.30258 (* 1 = 5.30258 loss)
I0410 03:13:13.937942 27877 sgd_solver.cpp:105] Iteration 9552, lr = 0.00150752
I0410 03:13:18.808338 27877 solver.cpp:218] Iteration 9564 (2.46393 iter/s, 4.87028s/12 iters), loss = 5.25739
I0410 03:13:18.809862 27877 solver.cpp:237]     Train net output #0: loss = 5.25739 (* 1 = 5.25739 loss)
I0410 03:13:18.809870 27877 sgd_solver.cpp:105] Iteration 9564, lr = 0.00150395
I0410 03:13:23.617372 27877 solver.cpp:218] Iteration 9576 (2.49617 iter/s, 4.80737s/12 iters), loss = 5.26231
I0410 03:13:23.617430 27877 solver.cpp:237]     Train net output #0: loss = 5.26231 (* 1 = 5.26231 loss)
I0410 03:13:23.617444 27877 sgd_solver.cpp:105] Iteration 9576, lr = 0.00150037
I0410 03:13:28.059118 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9588.caffemodel
I0410 03:13:28.930392 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9588.solverstate
I0410 03:13:29.560230 27877 solver.cpp:330] Iteration 9588, Testing net (#0)
I0410 03:13:29.560261 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:13:30.245762 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:13:33.994719 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:13:33.994756 27877 solver.cpp:397]     Test net output #1: loss = 5.28626 (* 1 = 5.28626 loss)
I0410 03:13:34.077320 27877 solver.cpp:218] Iteration 9588 (1.14727 iter/s, 10.4596s/12 iters), loss = 5.27697
I0410 03:13:34.077368 27877 solver.cpp:237]     Train net output #0: loss = 5.27697 (* 1 = 5.27697 loss)
I0410 03:13:34.077376 27877 sgd_solver.cpp:105] Iteration 9588, lr = 0.00149681
I0410 03:13:38.280730 27877 solver.cpp:218] Iteration 9600 (2.85494 iter/s, 4.20324s/12 iters), loss = 5.27708
I0410 03:13:38.280777 27877 solver.cpp:237]     Train net output #0: loss = 5.27708 (* 1 = 5.27708 loss)
I0410 03:13:38.280787 27877 sgd_solver.cpp:105] Iteration 9600, lr = 0.00149326
I0410 03:13:41.773105 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:13:43.119702 27877 solver.cpp:218] Iteration 9612 (2.47996 iter/s, 4.83879s/12 iters), loss = 5.27141
I0410 03:13:43.119760 27877 solver.cpp:237]     Train net output #0: loss = 5.27141 (* 1 = 5.27141 loss)
I0410 03:13:43.119773 27877 sgd_solver.cpp:105] Iteration 9612, lr = 0.00148971
I0410 03:13:47.985044 27877 solver.cpp:218] Iteration 9624 (2.46653 iter/s, 4.86514s/12 iters), loss = 5.26842
I0410 03:13:47.985100 27877 solver.cpp:237]     Train net output #0: loss = 5.26842 (* 1 = 5.26842 loss)
I0410 03:13:47.985112 27877 sgd_solver.cpp:105] Iteration 9624, lr = 0.00148618
I0410 03:13:52.855660 27877 solver.cpp:218] Iteration 9636 (2.46385 iter/s, 4.87042s/12 iters), loss = 5.25918
I0410 03:13:52.855775 27877 solver.cpp:237]     Train net output #0: loss = 5.25918 (* 1 = 5.25918 loss)
I0410 03:13:52.855789 27877 sgd_solver.cpp:105] Iteration 9636, lr = 0.00148265
I0410 03:13:57.762938 27877 solver.cpp:218] Iteration 9648 (2.44547 iter/s, 4.90702s/12 iters), loss = 5.26475
I0410 03:13:57.762995 27877 solver.cpp:237]     Train net output #0: loss = 5.26475 (* 1 = 5.26475 loss)
I0410 03:13:57.763007 27877 sgd_solver.cpp:105] Iteration 9648, lr = 0.00147913
I0410 03:14:02.656071 27877 solver.cpp:218] Iteration 9660 (2.45251 iter/s, 4.89294s/12 iters), loss = 5.25431
I0410 03:14:02.656121 27877 solver.cpp:237]     Train net output #0: loss = 5.25431 (* 1 = 5.25431 loss)
I0410 03:14:02.656132 27877 sgd_solver.cpp:105] Iteration 9660, lr = 0.00147562
I0410 03:14:07.548372 27877 solver.cpp:218] Iteration 9672 (2.45293 iter/s, 4.89212s/12 iters), loss = 5.27107
I0410 03:14:07.548422 27877 solver.cpp:237]     Train net output #0: loss = 5.27107 (* 1 = 5.27107 loss)
I0410 03:14:07.548434 27877 sgd_solver.cpp:105] Iteration 9672, lr = 0.00147211
I0410 03:14:12.465306 27877 solver.cpp:218] Iteration 9684 (2.44064 iter/s, 4.91675s/12 iters), loss = 5.28776
I0410 03:14:12.465348 27877 solver.cpp:237]     Train net output #0: loss = 5.28776 (* 1 = 5.28776 loss)
I0410 03:14:12.465356 27877 sgd_solver.cpp:105] Iteration 9684, lr = 0.00146862
I0410 03:14:14.432261 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9690.caffemodel
I0410 03:14:15.281925 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9690.solverstate
I0410 03:14:15.909354 27877 solver.cpp:330] Iteration 9690, Testing net (#0)
I0410 03:14:15.909385 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:14:16.476536 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:14:19.161617 27877 blocking_queue.cpp:49] Waiting for data
I0410 03:14:20.333636 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:14:20.333684 27877 solver.cpp:397]     Test net output #1: loss = 5.28645 (* 1 = 5.28645 loss)
I0410 03:14:22.226603 27877 solver.cpp:218] Iteration 9696 (1.22938 iter/s, 9.76099s/12 iters), loss = 5.2868
I0410 03:14:22.226647 27877 solver.cpp:237]     Train net output #0: loss = 5.2868 (* 1 = 5.2868 loss)
I0410 03:14:22.226658 27877 sgd_solver.cpp:105] Iteration 9696, lr = 0.00146513
I0410 03:14:27.124825 27877 solver.cpp:218] Iteration 9708 (2.44996 iter/s, 4.89804s/12 iters), loss = 5.28832
I0410 03:14:27.124941 27877 solver.cpp:237]     Train net output #0: loss = 5.28832 (* 1 = 5.28832 loss)
I0410 03:14:27.124954 27877 sgd_solver.cpp:105] Iteration 9708, lr = 0.00146165
I0410 03:14:27.863790 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:14:32.025004 27877 solver.cpp:218] Iteration 9720 (2.44902 iter/s, 4.89992s/12 iters), loss = 5.28925
I0410 03:14:32.025063 27877 solver.cpp:237]     Train net output #0: loss = 5.28925 (* 1 = 5.28925 loss)
I0410 03:14:32.025076 27877 sgd_solver.cpp:105] Iteration 9720, lr = 0.00145818
I0410 03:14:36.918854 27877 solver.cpp:218] Iteration 9732 (2.45215 iter/s, 4.89365s/12 iters), loss = 5.26306
I0410 03:14:36.918907 27877 solver.cpp:237]     Train net output #0: loss = 5.26306 (* 1 = 5.26306 loss)
I0410 03:14:36.918918 27877 sgd_solver.cpp:105] Iteration 9732, lr = 0.00145472
I0410 03:14:41.751127 27877 solver.cpp:218] Iteration 9744 (2.4834 iter/s, 4.83209s/12 iters), loss = 5.26807
I0410 03:14:41.751173 27877 solver.cpp:237]     Train net output #0: loss = 5.26807 (* 1 = 5.26807 loss)
I0410 03:14:41.751180 27877 sgd_solver.cpp:105] Iteration 9744, lr = 0.00145127
I0410 03:14:46.554838 27877 solver.cpp:218] Iteration 9756 (2.49816 iter/s, 4.80353s/12 iters), loss = 5.27476
I0410 03:14:46.554895 27877 solver.cpp:237]     Train net output #0: loss = 5.27476 (* 1 = 5.27476 loss)
I0410 03:14:46.554910 27877 sgd_solver.cpp:105] Iteration 9756, lr = 0.00144782
I0410 03:14:51.427568 27877 solver.cpp:218] Iteration 9768 (2.46278 iter/s, 4.87253s/12 iters), loss = 5.28749
I0410 03:14:51.427625 27877 solver.cpp:237]     Train net output #0: loss = 5.28749 (* 1 = 5.28749 loss)
I0410 03:14:51.427639 27877 sgd_solver.cpp:105] Iteration 9768, lr = 0.00144438
I0410 03:14:56.311290 27877 solver.cpp:218] Iteration 9780 (2.45724 iter/s, 4.88353s/12 iters), loss = 5.27022
I0410 03:14:56.311343 27877 solver.cpp:237]     Train net output #0: loss = 5.27022 (* 1 = 5.27022 loss)
I0410 03:14:56.311355 27877 sgd_solver.cpp:105] Iteration 9780, lr = 0.00144095
I0410 03:15:00.722570 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9792.caffemodel
I0410 03:15:01.844221 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9792.solverstate
I0410 03:15:02.837565 27877 solver.cpp:330] Iteration 9792, Testing net (#0)
I0410 03:15:02.837592 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:15:03.359760 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:15:07.148942 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:15:07.148993 27877 solver.cpp:397]     Test net output #1: loss = 5.2862 (* 1 = 5.2862 loss)
I0410 03:15:07.231681 27877 solver.cpp:218] Iteration 9792 (1.0989 iter/s, 10.92s/12 iters), loss = 5.25577
I0410 03:15:07.231734 27877 solver.cpp:237]     Train net output #0: loss = 5.25577 (* 1 = 5.25577 loss)
I0410 03:15:07.231746 27877 sgd_solver.cpp:105] Iteration 9792, lr = 0.00143753
I0410 03:15:11.331357 27877 solver.cpp:218] Iteration 9804 (2.92718 iter/s, 4.09951s/12 iters), loss = 5.27304
I0410 03:15:11.331393 27877 solver.cpp:237]     Train net output #0: loss = 5.27304 (* 1 = 5.27304 loss)
I0410 03:15:11.331401 27877 sgd_solver.cpp:105] Iteration 9804, lr = 0.00143412
I0410 03:15:14.202196 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:15:16.156273 27877 solver.cpp:218] Iteration 9816 (2.48718 iter/s, 4.82474s/12 iters), loss = 5.26351
I0410 03:15:16.156320 27877 solver.cpp:237]     Train net output #0: loss = 5.26351 (* 1 = 5.26351 loss)
I0410 03:15:16.156329 27877 sgd_solver.cpp:105] Iteration 9816, lr = 0.00143072
I0410 03:15:20.991952 27877 solver.cpp:218] Iteration 9828 (2.48165 iter/s, 4.8355s/12 iters), loss = 5.25506
I0410 03:15:20.992000 27877 solver.cpp:237]     Train net output #0: loss = 5.25506 (* 1 = 5.25506 loss)
I0410 03:15:20.992012 27877 sgd_solver.cpp:105] Iteration 9828, lr = 0.00142732
I0410 03:15:25.855763 27877 solver.cpp:218] Iteration 9840 (2.46729 iter/s, 4.86363s/12 iters), loss = 5.24946
I0410 03:15:25.855800 27877 solver.cpp:237]     Train net output #0: loss = 5.24946 (* 1 = 5.24946 loss)
I0410 03:15:25.855808 27877 sgd_solver.cpp:105] Iteration 9840, lr = 0.00142393
I0410 03:15:30.708436 27877 solver.cpp:218] Iteration 9852 (2.47296 iter/s, 4.85249s/12 iters), loss = 5.26749
I0410 03:15:30.708496 27877 solver.cpp:237]     Train net output #0: loss = 5.26749 (* 1 = 5.26749 loss)
I0410 03:15:30.708508 27877 sgd_solver.cpp:105] Iteration 9852, lr = 0.00142055
I0410 03:15:35.551573 27877 solver.cpp:218] Iteration 9864 (2.47783 iter/s, 4.84295s/12 iters), loss = 5.28808
I0410 03:15:35.551698 27877 solver.cpp:237]     Train net output #0: loss = 5.28808 (* 1 = 5.28808 loss)
I0410 03:15:35.551708 27877 sgd_solver.cpp:105] Iteration 9864, lr = 0.00141718
I0410 03:15:40.397976 27877 solver.cpp:218] Iteration 9876 (2.4762 iter/s, 4.84614s/12 iters), loss = 5.26758
I0410 03:15:40.398015 27877 solver.cpp:237]     Train net output #0: loss = 5.26758 (* 1 = 5.26758 loss)
I0410 03:15:40.398022 27877 sgd_solver.cpp:105] Iteration 9876, lr = 0.00141381
I0410 03:15:45.307019 27877 solver.cpp:218] Iteration 9888 (2.44456 iter/s, 4.90887s/12 iters), loss = 5.27764
I0410 03:15:45.307060 27877 solver.cpp:237]     Train net output #0: loss = 5.27764 (* 1 = 5.27764 loss)
I0410 03:15:45.307070 27877 sgd_solver.cpp:105] Iteration 9888, lr = 0.00141045
I0410 03:15:47.302631 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9894.caffemodel
I0410 03:15:48.128396 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9894.solverstate
I0410 03:15:48.740661 27877 solver.cpp:330] Iteration 9894, Testing net (#0)
I0410 03:15:48.740679 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:15:49.283882 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:15:53.297839 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:15:53.297888 27877 solver.cpp:397]     Test net output #1: loss = 5.28656 (* 1 = 5.28656 loss)
I0410 03:15:55.084554 27877 solver.cpp:218] Iteration 9900 (1.22734 iter/s, 9.77723s/12 iters), loss = 5.27336
I0410 03:15:55.084615 27877 solver.cpp:237]     Train net output #0: loss = 5.27336 (* 1 = 5.27336 loss)
I0410 03:15:55.084626 27877 sgd_solver.cpp:105] Iteration 9900, lr = 0.00140711
I0410 03:15:59.872921 27877 solver.cpp:218] Iteration 9912 (2.50618 iter/s, 4.78817s/12 iters), loss = 5.2576
I0410 03:15:59.872985 27877 solver.cpp:237]     Train net output #0: loss = 5.2576 (* 1 = 5.2576 loss)
I0410 03:15:59.872997 27877 sgd_solver.cpp:105] Iteration 9912, lr = 0.00140377
I0410 03:15:59.971177 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:16:04.767791 27877 solver.cpp:218] Iteration 9924 (2.45165 iter/s, 4.89467s/12 iters), loss = 5.27126
I0410 03:16:04.767841 27877 solver.cpp:237]     Train net output #0: loss = 5.27126 (* 1 = 5.27126 loss)
I0410 03:16:04.767853 27877 sgd_solver.cpp:105] Iteration 9924, lr = 0.00140043
I0410 03:16:09.607715 27877 solver.cpp:218] Iteration 9936 (2.47948 iter/s, 4.83973s/12 iters), loss = 5.28862
I0410 03:16:09.607831 27877 solver.cpp:237]     Train net output #0: loss = 5.28862 (* 1 = 5.28862 loss)
I0410 03:16:09.607841 27877 sgd_solver.cpp:105] Iteration 9936, lr = 0.00139711
I0410 03:16:14.454241 27877 solver.cpp:218] Iteration 9948 (2.47613 iter/s, 4.84628s/12 iters), loss = 5.26035
I0410 03:16:14.454286 27877 solver.cpp:237]     Train net output #0: loss = 5.26035 (* 1 = 5.26035 loss)
I0410 03:16:14.454296 27877 sgd_solver.cpp:105] Iteration 9948, lr = 0.00139379
I0410 03:16:19.298203 27877 solver.cpp:218] Iteration 9960 (2.47741 iter/s, 4.84378s/12 iters), loss = 5.27075
I0410 03:16:19.298256 27877 solver.cpp:237]     Train net output #0: loss = 5.27075 (* 1 = 5.27075 loss)
I0410 03:16:19.298266 27877 sgd_solver.cpp:105] Iteration 9960, lr = 0.00139048
I0410 03:16:24.183789 27877 solver.cpp:218] Iteration 9972 (2.4563 iter/s, 4.8854s/12 iters), loss = 5.26233
I0410 03:16:24.183835 27877 solver.cpp:237]     Train net output #0: loss = 5.26233 (* 1 = 5.26233 loss)
I0410 03:16:24.183845 27877 sgd_solver.cpp:105] Iteration 9972, lr = 0.00138718
I0410 03:16:29.038589 27877 solver.cpp:218] Iteration 9984 (2.47188 iter/s, 4.85461s/12 iters), loss = 5.2473
I0410 03:16:29.038648 27877 solver.cpp:237]     Train net output #0: loss = 5.2473 (* 1 = 5.2473 loss)
I0410 03:16:29.038661 27877 sgd_solver.cpp:105] Iteration 9984, lr = 0.00138389
I0410 03:16:33.411886 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_9996.caffemodel
I0410 03:16:34.926170 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_9996.solverstate
I0410 03:16:36.215795 27877 solver.cpp:330] Iteration 9996, Testing net (#0)
I0410 03:16:36.215821 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:16:36.733191 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:16:40.761206 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:16:40.761279 27877 solver.cpp:397]     Test net output #1: loss = 5.28701 (* 1 = 5.28701 loss)
I0410 03:16:40.842155 27877 solver.cpp:218] Iteration 9996 (1.01667 iter/s, 11.8032s/12 iters), loss = 5.26977
I0410 03:16:40.842206 27877 solver.cpp:237]     Train net output #0: loss = 5.26977 (* 1 = 5.26977 loss)
I0410 03:16:40.842217 27877 sgd_solver.cpp:105] Iteration 9996, lr = 0.0013806
I0410 03:16:44.952227 27877 solver.cpp:218] Iteration 10008 (2.91978 iter/s, 4.1099s/12 iters), loss = 5.24361
I0410 03:16:44.952271 27877 solver.cpp:237]     Train net output #0: loss = 5.24361 (* 1 = 5.24361 loss)
I0410 03:16:44.952280 27877 sgd_solver.cpp:105] Iteration 10008, lr = 0.00137732
I0410 03:16:47.115851 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:16:49.792780 27877 solver.cpp:218] Iteration 10020 (2.47915 iter/s, 4.84037s/12 iters), loss = 5.26938
I0410 03:16:49.792827 27877 solver.cpp:237]     Train net output #0: loss = 5.26938 (* 1 = 5.26938 loss)
I0410 03:16:49.792837 27877 sgd_solver.cpp:105] Iteration 10020, lr = 0.00137405
I0410 03:16:54.611307 27877 solver.cpp:218] Iteration 10032 (2.49048 iter/s, 4.81834s/12 iters), loss = 5.27372
I0410 03:16:54.611353 27877 solver.cpp:237]     Train net output #0: loss = 5.27372 (* 1 = 5.27372 loss)
I0410 03:16:54.611361 27877 sgd_solver.cpp:105] Iteration 10032, lr = 0.00137079
I0410 03:16:59.442839 27877 solver.cpp:218] Iteration 10044 (2.48378 iter/s, 4.83135s/12 iters), loss = 5.28322
I0410 03:16:59.442883 27877 solver.cpp:237]     Train net output #0: loss = 5.28322 (* 1 = 5.28322 loss)
I0410 03:16:59.442894 27877 sgd_solver.cpp:105] Iteration 10044, lr = 0.00136754
I0410 03:17:04.311853 27877 solver.cpp:218] Iteration 10056 (2.46466 iter/s, 4.86883s/12 iters), loss = 5.27752
I0410 03:17:04.311901 27877 solver.cpp:237]     Train net output #0: loss = 5.27752 (* 1 = 5.27752 loss)
I0410 03:17:04.311913 27877 sgd_solver.cpp:105] Iteration 10056, lr = 0.00136429
I0410 03:17:09.161558 27877 solver.cpp:218] Iteration 10068 (2.47447 iter/s, 4.84953s/12 iters), loss = 5.27419
I0410 03:17:09.161594 27877 solver.cpp:237]     Train net output #0: loss = 5.27419 (* 1 = 5.27419 loss)
I0410 03:17:09.161602 27877 sgd_solver.cpp:105] Iteration 10068, lr = 0.00136105
I0410 03:17:14.092187 27877 solver.cpp:218] Iteration 10080 (2.43386 iter/s, 4.93045s/12 iters), loss = 5.26083
I0410 03:17:14.092281 27877 solver.cpp:237]     Train net output #0: loss = 5.26083 (* 1 = 5.26083 loss)
I0410 03:17:14.092290 27877 sgd_solver.cpp:105] Iteration 10080, lr = 0.00135782
I0410 03:17:18.988375 27877 solver.cpp:218] Iteration 10092 (2.451 iter/s, 4.89596s/12 iters), loss = 5.27657
I0410 03:17:18.988420 27877 solver.cpp:237]     Train net output #0: loss = 5.27657 (* 1 = 5.27657 loss)
I0410 03:17:18.988430 27877 sgd_solver.cpp:105] Iteration 10092, lr = 0.0013546
I0410 03:17:20.973450 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_10098.caffemodel
I0410 03:17:21.779122 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_10098.solverstate
I0410 03:17:22.389799 27877 solver.cpp:330] Iteration 10098, Testing net (#0)
I0410 03:17:22.389824 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:17:22.793068 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:17:26.846554 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:17:26.846590 27877 solver.cpp:397]     Test net output #1: loss = 5.28667 (* 1 = 5.28667 loss)
I0410 03:17:28.601586 27877 solver.cpp:218] Iteration 10104 (1.24832 iter/s, 9.61291s/12 iters), loss = 5.272
I0410 03:17:28.601640 27877 solver.cpp:237]     Train net output #0: loss = 5.272 (* 1 = 5.272 loss)
I0410 03:17:28.601652 27877 sgd_solver.cpp:105] Iteration 10104, lr = 0.00135138
I0410 03:17:32.800730 27931 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:17:33.405323 27877 solver.cpp:218] Iteration 10116 (2.49815 iter/s, 4.80355s/12 iters), loss = 5.25745
I0410 03:17:33.405375 27877 solver.cpp:237]     Train net output #0: loss = 5.25745 (* 1 = 5.25745 loss)
I0410 03:17:33.405386 27877 sgd_solver.cpp:105] Iteration 10116, lr = 0.00134817
I0410 03:17:38.210988 27877 solver.cpp:218] Iteration 10128 (2.49715 iter/s, 4.80547s/12 iters), loss = 5.27476
I0410 03:17:38.211045 27877 solver.cpp:237]     Train net output #0: loss = 5.27476 (* 1 = 5.27476 loss)
I0410 03:17:38.211057 27877 sgd_solver.cpp:105] Iteration 10128, lr = 0.00134497
I0410 03:17:43.132613 27877 solver.cpp:218] Iteration 10140 (2.43832 iter/s, 4.92142s/12 iters), loss = 5.28084
I0410 03:17:43.132663 27877 solver.cpp:237]     Train net output #0: loss = 5.28084 (* 1 = 5.28084 loss)
I0410 03:17:43.132671 27877 sgd_solver.cpp:105] Iteration 10140, lr = 0.00134178
I0410 03:17:48.196719 27877 solver.cpp:218] Iteration 10152 (2.36971 iter/s, 5.06392s/12 iters), loss = 5.2754
I0410 03:17:48.196802 27877 solver.cpp:237]     Train net output #0: loss = 5.2754 (* 1 = 5.2754 loss)
I0410 03:17:48.196811 27877 sgd_solver.cpp:105] Iteration 10152, lr = 0.00133859
I0410 03:17:53.070116 27877 solver.cpp:218] Iteration 10164 (2.46246 iter/s, 4.87318s/12 iters), loss = 5.26522
I0410 03:17:53.070152 27877 solver.cpp:237]     Train net output #0: loss = 5.26522 (* 1 = 5.26522 loss)
I0410 03:17:53.070159 27877 sgd_solver.cpp:105] Iteration 10164, lr = 0.00133541
I0410 03:17:57.888725 27877 solver.cpp:218] Iteration 10176 (2.49043 iter/s, 4.81844s/12 iters), loss = 5.2751
I0410 03:17:57.888765 27877 solver.cpp:237]     Train net output #0: loss = 5.2751 (* 1 = 5.2751 loss)
I0410 03:17:57.888774 27877 sgd_solver.cpp:105] Iteration 10176, lr = 0.00133224
I0410 03:18:02.758548 27877 solver.cpp:218] Iteration 10188 (2.46424 iter/s, 4.86965s/12 iters), loss = 5.27909
I0410 03:18:02.758585 27877 solver.cpp:237]     Train net output #0: loss = 5.27909 (* 1 = 5.27909 loss)
I0410 03:18:02.758594 27877 sgd_solver.cpp:105] Iteration 10188, lr = 0.00132908
I0410 03:18:07.332080 27877 solver.cpp:447] Snapshotting to binary proto file snapshot_iter_10200.caffemodel
I0410 03:18:10.085716 27877 sgd_solver.cpp:273] Snapshotting solver state to binary proto file snapshot_iter_10200.solverstate
I0410 03:18:14.346279 27877 solver.cpp:310] Iteration 10200, loss = 5.26368
I0410 03:18:14.346308 27877 solver.cpp:330] Iteration 10200, Testing net (#0)
I0410 03:18:14.346314 27877 net.cpp:676] Ignoring source layer train-data
I0410 03:18:14.768409 27932 data_layer.cpp:73] Restarting data prefetching from start.
I0410 03:18:18.772419 27877 solver.cpp:397]     Test net output #0: accuracy = 0.00551471
I0410 03:18:18.772547 27877 solver.cpp:397]     Test net output #1: loss = 5.28602 (* 1 = 5.28602 loss)
I0410 03:18:18.772555 27877 solver.cpp:315] Optimization Done.
I0410 03:18:18.772560 27877 caffe.cpp:259] Optimization Done.