API tools faq
paste
Guest User

Untitled

a guest
May 25th, 2016
180
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 216.06 KB | None | 0 0
raw download clone embed print report
  1. I0524 22:40:32.193439 138703 caffe.cpp:113] Use GPU with device ID 0
  2. I0524 22:40:34.494611 138703 caffe.cpp:121] Starting Optimization
  3. I0524 22:40:34.494921 138703 solver.cpp:32] Initializing solver from parameters:
  4. test_iter: 75
  5. test_interval: 100
  6. base_lr: 0.001
  7. display: 20
  8. max_iter: 50000
  9. lr_policy: "step"
  10. gamma: 0.1
  11. momentum: 0.9
  12. weight_decay: 0.005
  13. stepsize: 20000
  14. snapshot: 5000
  15. snapshot_prefix: "/home/fe/anilil/miniconda2/lisa-caffe-public/examples/LRCN_activity_recognition/singleframe_flow/snaps/10f_v1_xmlinput_"
  16. solver_mode: GPU
  17. device_id: 0
  18. random_seed: 1701
  19. net: "train_test_singleFrame_flow.prototxt"
  20. test_state {
  21. stage: "test-on-test"
  22. }
  23. I0524 22:40:34.495246 138703 solver.cpp:70] Creating training net from net file: train_test_singleFrame_flow.prototxt
  24. I0524 22:40:34.507985 138703 net.cpp:258] The NetState phase (0) differed from the phase (1) specified by a rule in layer data
  25. I0524 22:40:34.508551 138703 net.cpp:42] Initializing net from parameters:
  26. name: "singleFrame_flow"
  27. state {
  28. phase: TRAIN
  29. }
  30. layer {
  31. name: "data"
  32. type: "Data"
  33. top: "data"
  34. top: "label"
  35. include {
  36. phase: TRAIN
  37. }
  38. transform_param {
  39. mirror: true
  40. crop_size: 227
  41. mean_value: 128
  42. flow: true
  43. }
  44. data_param {
  45. source: "/home/fe/data/lmdb/xml_ucf_10_train/mylmdb"
  46. batch_size: 64
  47. backend: LMDB
  48. }
  49. }
  50. layer {
  51. name: "conv1"
  52. type: "Convolution"
  53. bottom: "data"
  54. top: "conv1"
  55. param {
  56. lr_mult: 1
  57. decay_mult: 1
  58. }
  59. param {
  60. lr_mult: 2
  61. decay_mult: 0
  62. }
  63. convolution_param {
  64. num_output: 96
  65. kernel_size: 7
  66. stride: 2
  67. weight_filler {
  68. type: "gaussian"
  69. std: 0.01
  70. }
  71. bias_filler {
  72. type: "constant"
  73. value: 0.1
  74. }
  75. }
  76. }
  77. layer {
  78. name: "relu1"
  79. type: "ReLU"
  80. bottom: "conv1"
  81. top: "conv1"
  82. }
  83. layer {
  84. name: "pool1"
  85. type: "Pooling"
  86. bottom: "conv1"
  87. top: "pool1"
  88. pooling_param {
  89. pool: MAX
  90. kernel_size: 3
  91. stride: 2
  92. }
  93. }
  94. layer {
  95. name: "norm1"
  96. type: "LRN"
  97. bottom: "pool1"
  98. top: "norm1"
  99. lrn_param {
  100. local_size: 5
  101. alpha: 0.0001
  102. beta: 0.75
  103. }
  104. }
  105. layer {
  106. name: "conv2"
  107. type: "Convolution"
  108. bottom: "norm1"
  109. top: "conv2"
  110. param {
  111. lr_mult: 1
  112. decay_mult: 1
  113. }
  114. param {
  115. lr_mult: 2
  116. decay_mult: 0
  117. }
  118. convolution_param {
  119. num_output: 384
  120. kernel_size: 5
  121. group: 2
  122. stride: 2
  123. weight_filler {
  124. type: "gaussian"
  125. std: 0.01
  126. }
  127. bias_filler {
  128. type: "constant"
  129. value: 0.1
  130. }
  131. }
  132. }
  133. layer {
  134. name: "relu2"
  135. type: "ReLU"
  136. bottom: "conv2"
  137. top: "conv2"
  138. }
  139. layer {
  140. name: "pool2"
  141. type: "Pooling"
  142. bottom: "conv2"
  143. top: "pool2"
  144. pooling_param {
  145. pool: MAX
  146. kernel_size: 3
  147. stride: 2
  148. }
  149. }
  150. layer {
  151. name: "norm2"
  152. type: "LRN"
  153. bottom: "pool2"
  154. top: "norm2"
  155. lrn_param {
  156. local_size: 5
  157. alpha: 0.0001
  158. beta: 0.75
  159. }
  160. }
  161. layer {
  162. name: "conv3"
  163. type: "Convolution"
  164. bottom: "norm2"
  165. top: "conv3"
  166. param {
  167. lr_mult: 1
  168. decay_mult: 1
  169. }
  170. param {
  171. lr_mult: 2
  172. decay_mult: 0
  173. }
  174. convolution_param {
  175. num_output: 512
  176. pad: 1
  177. kernel_size: 3
  178. weight_filler {
  179. type: "gaussian"
  180. std: 0.01
  181. }
  182. bias_filler {
  183. type: "constant"
  184. value: 0.1
  185. }
  186. }
  187. }
  188. layer {
  189. name: "relu3"
  190. type: "ReLU"
  191. bottom: "conv3"
  192. top: "conv3"
  193. }
  194. layer {
  195. name: "conv4"
  196. type: "Convolution"
  197. bottom: "conv3"
  198. top: "conv4"
  199. param {
  200. lr_mult: 1
  201. decay_mult: 1
  202. }
  203. param {
  204. lr_mult: 2
  205. decay_mult: 0
  206. }
  207. convolution_param {
  208. num_output: 512
  209. pad: 1
  210. kernel_size: 3
  211. group: 2
  212. weight_filler {
  213. type: "gaussian"
  214. std: 0.01
  215. }
  216. bias_filler {
  217. type: "constant"
  218. value: 0.1
  219. }
  220. }
  221. }
  222. layer {
  223. name: "relu4"
  224. type: "ReLU"
  225. bottom: "conv4"
  226. top: "conv4"
  227. }
  228. layer {
  229. name: "conv5"
  230. type: "Convolution"
  231. bottom: "conv4"
  232. top: "conv5"
  233. param {
  234. lr_mult: 1
  235. decay_mult: 1
  236. }
  237. param {
  238. lr_mult: 2
  239. decay_mult: 0
  240. }
  241. convolution_param {
  242. num_output: 384
  243. pad: 1
  244. kernel_size: 3
  245. group: 2
  246. weight_filler {
  247. type: "gaussian"
  248. std: 0.01
  249. }
  250. bias_filler {
  251. type: "constant"
  252. value: 0.1
  253. }
  254. }
  255. }
  256. layer {
  257. name: "relu5"
  258. type: "ReLU"
  259. bottom: "conv5"
  260. top: "conv5"
  261. }
  262. layer {
  263. name: "pool5"
  264. type: "Pooling"
  265. bottom: "conv5"
  266. top: "pool5"
  267. pooling_param {
  268. pool: MAX
  269. kernel_size: 3
  270. stride: 2
  271. }
  272. }
  273. layer {
  274. name: "fc6"
  275. type: "InnerProduct"
  276. bottom: "pool5"
  277. top: "fc6"
  278. param {
  279. lr_mult: 1
  280. decay_mult: 1
  281. }
  282. param {
  283. lr_mult: 2
  284. decay_mult: 0
  285. }
  286. inner_product_param {
  287. num_output: 4096
  288. weight_filler {
  289. type: "gaussian"
  290. std: 0.01
  291. }
  292. bias_filler {
  293. type: "constant"
  294. value: 0.1
  295. }
  296. }
  297. }
  298. layer {
  299. name: "relu6"
  300. type: "ReLU"
  301. bottom: "fc6"
  302. top: "fc6"
  303. }
  304. layer {
  305. name: "drop6"
  306. type: "Dropout"
  307. bottom: "fc6"
  308. top: "fc6"
  309. dropout_param {
  310. dropout_ratio: 0.5
  311. }
  312. }
  313. layer {
  314. name: "fc7"
  315. type: "InnerProduct"
  316. bottom: "fc6"
  317. top: "fc7"
  318. param {
  319. lr_mult: 1
  320. decay_mult: 1
  321. }
  322. param {
  323. lr_mult: 2
  324. decay_mult: 0
  325. }
  326. inner_product_param {
  327. num_output: 4096
  328. weight_filler {
  329. type: "gaussian"
  330. std: 0.01
  331. }
  332. bias_filler {
  333. type: "constant"
  334. value: 0.1
  335. }
  336. }
  337. }
  338. layer {
  339. name: "relu7"
  340. type: "ReLU"
  341. bottom: "fc7"
  342. top: "fc7"
  343. }
  344. layer {
  345. name: "drop7"
  346. type: "Dropout"
  347. bottom: "fc7"
  348. top: "fc7"
  349. dropout_param {
  350. dropout_ratio: 0.5
  351. }
  352. }
  353. layer {
  354. name: "fc8-ucf"
  355. type: "InnerProduct"
  356. bottom: "fc7"
  357. top: "fc8-ucf"
  358. param {
  359. lr_mult: 10
  360. decay_mult: 1
  361. }
  362. param {
  363. lr_mult: 20
  364. decay_mult: 0
  365. }
  366. inner_product_param {
  367. num_output: 101
  368. weight_filler {
  369. type: "gaussian"
  370. std: 0.01
  371. }
  372. bias_filler {
  373. type: "constant"
  374. value: 0
  375. }
  376. }
  377. }
  378. layer {
  379. name: "loss"
  380. type: "SoftmaxWithLoss"
  381. bottom: "fc8-ucf"
  382. bottom: "label"
  383. top: "loss"
  384. }
  385. layer {
  386. name: "accuracy"
  387. type: "Accuracy"
  388. bottom: "fc8-ucf"
  389. bottom: "label"
  390. top: "accuracy"
  391. }
  392. I0524 22:40:34.509047 138703 layer_factory.hpp:74] Creating layer data
  393. I0524 22:40:34.511577 138703 net.cpp:84] Creating Layer data
  394. I0524 22:40:34.511615 138703 net.cpp:339] data -> data
  395. I0524 22:40:34.511677 138703 net.cpp:339] data -> label
  396. I0524 22:40:34.511818 138703 net.cpp:113] Setting up data
  397. I0524 22:40:34.555011 138703 db.cpp:34] Opened lmdb /home/fe/data/lmdb/xml_ucf_10_train/mylmdb
  398. I0524 22:40:34.602366 138703 data_layer.cpp:67] output data size: 64,30,227,227
  399. I0524 22:40:36.582067 138703 net.cpp:120] Top shape: 64 30 227 227 (98935680)
  400. I0524 22:40:36.582128 138703 net.cpp:120] Top shape: 64 (64)
  401. I0524 22:40:36.582140 138703 layer_factory.hpp:74] Creating layer label_data_1_split
  402. I0524 22:40:36.582197 138703 net.cpp:84] Creating Layer label_data_1_split
  403. I0524 22:40:36.582211 138703 net.cpp:381] label_data_1_split <- label
  404. I0524 22:40:36.582236 138703 net.cpp:339] label_data_1_split -> label_data_1_split_0
  405. I0524 22:40:36.582281 138703 net.cpp:339] label_data_1_split -> label_data_1_split_1
  406. I0524 22:40:36.582295 138703 net.cpp:113] Setting up label_data_1_split
  407. I0524 22:40:36.583618 138703 net.cpp:120] Top shape: 64 (64)
  408. I0524 22:40:36.583631 138703 net.cpp:120] Top shape: 64 (64)
  409. I0524 22:40:36.583638 138703 layer_factory.hpp:74] Creating layer conv1
  410. I0524 22:40:36.583660 138703 net.cpp:84] Creating Layer conv1
  411. I0524 22:40:36.583670 138703 net.cpp:381] conv1 <- data
  412. I0524 22:40:36.583683 138703 net.cpp:339] conv1 -> conv1
  413. I0524 22:40:36.583705 138703 net.cpp:113] Setting up conv1
  414. I0524 22:40:36.588496 138703 net.cpp:120] Top shape: 64 96 111 111 (75700224)
  415. I0524 22:40:36.588522 138703 layer_factory.hpp:74] Creating layer relu1
  416. I0524 22:40:36.588556 138703 net.cpp:84] Creating Layer relu1
  417. I0524 22:40:36.588564 138703 net.cpp:381] relu1 <- conv1
  418. I0524 22:40:36.588574 138703 net.cpp:328] relu1 -> conv1 (in-place)
  419. I0524 22:40:36.588604 138703 net.cpp:113] Setting up relu1
  420. I0524 22:40:36.588636 138703 net.cpp:120] Top shape: 64 96 111 111 (75700224)
  421. I0524 22:40:36.588662 138703 layer_factory.hpp:74] Creating layer pool1
  422. I0524 22:40:36.588696 138703 net.cpp:84] Creating Layer pool1
  423. I0524 22:40:36.588724 138703 net.cpp:381] pool1 <- conv1
  424. I0524 22:40:36.588757 138703 net.cpp:339] pool1 -> pool1
  425. I0524 22:40:36.588804 138703 net.cpp:113] Setting up pool1
  426. I0524 22:40:36.589171 138703 net.cpp:120] Top shape: 64 96 55 55 (18585600)
  427. I0524 22:40:36.589182 138703 layer_factory.hpp:74] Creating layer norm1
  428. I0524 22:40:36.589196 138703 net.cpp:84] Creating Layer norm1
  429. I0524 22:40:36.589224 138703 net.cpp:381] norm1 <- pool1
  430. I0524 22:40:36.589256 138703 net.cpp:339] norm1 -> norm1
  431. I0524 22:40:36.589288 138703 net.cpp:113] Setting up norm1
  432. I0524 22:40:36.589305 138703 net.cpp:120] Top shape: 64 96 55 55 (18585600)
  433. I0524 22:40:36.589334 138703 layer_factory.hpp:74] Creating layer conv2
  434. I0524 22:40:36.589370 138703 net.cpp:84] Creating Layer conv2
  435. I0524 22:40:36.589380 138703 net.cpp:381] conv2 <- norm1
  436. I0524 22:40:36.589393 138703 net.cpp:339] conv2 -> conv2
  437. I0524 22:40:36.589426 138703 net.cpp:113] Setting up conv2
  438. I0524 22:40:36.604993 138703 net.cpp:120] Top shape: 64 384 26 26 (16613376)
  439. I0524 22:40:36.605013 138703 layer_factory.hpp:74] Creating layer relu2
  440. I0524 22:40:36.605024 138703 net.cpp:84] Creating Layer relu2
  441. I0524 22:40:36.605054 138703 net.cpp:381] relu2 <- conv2
  442. I0524 22:40:36.605085 138703 net.cpp:328] relu2 -> conv2 (in-place)
  443. I0524 22:40:36.605114 138703 net.cpp:113] Setting up relu2
  444. I0524 22:40:36.605145 138703 net.cpp:120] Top shape: 64 384 26 26 (16613376)
  445. I0524 22:40:36.605172 138703 layer_factory.hpp:74] Creating layer pool2
  446. I0524 22:40:36.605204 138703 net.cpp:84] Creating Layer pool2
  447. I0524 22:40:36.605232 138703 net.cpp:381] pool2 <- conv2
  448. I0524 22:40:36.605264 138703 net.cpp:339] pool2 -> pool2
  449. I0524 22:40:36.605299 138703 net.cpp:113] Setting up pool2
  450. I0524 22:40:36.605336 138703 net.cpp:120] Top shape: 64 384 13 13 (4153344)
  451. I0524 22:40:36.605347 138703 layer_factory.hpp:74] Creating layer norm2
  452. I0524 22:40:36.605360 138703 net.cpp:84] Creating Layer norm2
  453. I0524 22:40:36.605387 138703 net.cpp:381] norm2 <- pool2
  454. I0524 22:40:36.605417 138703 net.cpp:339] norm2 -> norm2
  455. I0524 22:40:36.605448 138703 net.cpp:113] Setting up norm2
  456. I0524 22:40:36.605465 138703 net.cpp:120] Top shape: 64 384 13 13 (4153344)
  457. I0524 22:40:36.605491 138703 layer_factory.hpp:74] Creating layer conv3
  458. I0524 22:40:36.605525 138703 net.cpp:84] Creating Layer conv3
  459. I0524 22:40:36.605535 138703 net.cpp:381] conv3 <- norm2
  460. I0524 22:40:36.605548 138703 net.cpp:339] conv3 -> conv3
  461. I0524 22:40:36.605581 138703 net.cpp:113] Setting up conv3
  462. I0524 22:40:36.685092 138703 net.cpp:120] Top shape: 64 512 13 13 (5537792)
  463. I0524 22:40:36.685137 138703 layer_factory.hpp:74] Creating layer relu3
  464. I0524 22:40:36.685153 138703 net.cpp:84] Creating Layer relu3
  465. I0524 22:40:36.685160 138703 net.cpp:381] relu3 <- conv3
  466. I0524 22:40:36.685170 138703 net.cpp:328] relu3 -> conv3 (in-place)
  467. I0524 22:40:36.685184 138703 net.cpp:113] Setting up relu3
  468. I0524 22:40:36.685220 138703 net.cpp:120] Top shape: 64 512 13 13 (5537792)
  469. I0524 22:40:36.685243 138703 layer_factory.hpp:74] Creating layer conv4
  470. I0524 22:40:36.685276 138703 net.cpp:84] Creating Layer conv4
  471. I0524 22:40:36.685300 138703 net.cpp:381] conv4 <- conv3
  472. I0524 22:40:36.685329 138703 net.cpp:339] conv4 -> conv4
  473. I0524 22:40:36.685361 138703 net.cpp:113] Setting up conv4
  474. I0524 22:40:36.735338 138703 net.cpp:120] Top shape: 64 512 13 13 (5537792)
  475. I0524 22:40:36.735365 138703 layer_factory.hpp:74] Creating layer relu4
  476. I0524 22:40:36.735379 138703 net.cpp:84] Creating Layer relu4
  477. I0524 22:40:36.735386 138703 net.cpp:381] relu4 <- conv4
  478. I0524 22:40:36.735399 138703 net.cpp:328] relu4 -> conv4 (in-place)
  479. I0524 22:40:36.735412 138703 net.cpp:113] Setting up relu4
  480. I0524 22:40:36.735424 138703 net.cpp:120] Top shape: 64 512 13 13 (5537792)
  481. I0524 22:40:36.735430 138703 layer_factory.hpp:74] Creating layer conv5
  482. I0524 22:40:36.735445 138703 net.cpp:84] Creating Layer conv5
  483. I0524 22:40:36.735451 138703 net.cpp:381] conv5 <- conv4
  484. I0524 22:40:36.735465 138703 net.cpp:339] conv5 -> conv5
  485. I0524 22:40:36.735476 138703 net.cpp:113] Setting up conv5
  486. I0524 22:40:36.776077 138703 net.cpp:120] Top shape: 64 384 13 13 (4153344)
  487. I0524 22:40:36.776108 138703 layer_factory.hpp:74] Creating layer relu5
  488. I0524 22:40:36.776120 138703 net.cpp:84] Creating Layer relu5
  489. I0524 22:40:36.776196 138703 net.cpp:381] relu5 <- conv5
  490. I0524 22:40:36.776254 138703 net.cpp:328] relu5 -> conv5 (in-place)
  491. I0524 22:40:36.776268 138703 net.cpp:113] Setting up relu5
  492. I0524 22:40:36.776317 138703 net.cpp:120] Top shape: 64 384 13 13 (4153344)
  493. I0524 22:40:36.776325 138703 layer_factory.hpp:74] Creating layer pool5
  494. I0524 22:40:36.776376 138703 net.cpp:84] Creating Layer pool5
  495. I0524 22:40:36.776384 138703 net.cpp:381] pool5 <- conv5
  496. I0524 22:40:36.776396 138703 net.cpp:339] pool5 -> pool5
  497. I0524 22:40:36.776448 138703 net.cpp:113] Setting up pool5
  498. I0524 22:40:36.776509 138703 net.cpp:120] Top shape: 64 384 6 6 (884736)
  499. I0524 22:40:36.776517 138703 layer_factory.hpp:74] Creating layer fc6
  500. I0524 22:40:36.776566 138703 net.cpp:84] Creating Layer fc6
  501. I0524 22:40:36.776576 138703 net.cpp:381] fc6 <- pool5
  502. I0524 22:40:36.776587 138703 net.cpp:339] fc6 -> fc6
  503. I0524 22:40:36.776653 138703 net.cpp:113] Setting up fc6
  504. I0524 22:40:39.856278 138703 net.cpp:120] Top shape: 64 4096 (262144)
  505. I0524 22:40:39.856325 138703 layer_factory.hpp:74] Creating layer relu6
  506. I0524 22:40:39.856343 138703 net.cpp:84] Creating Layer relu6
  507. I0524 22:40:39.856351 138703 net.cpp:381] relu6 <- fc6
  508. I0524 22:40:39.856362 138703 net.cpp:328] relu6 -> fc6 (in-place)
  509. I0524 22:40:39.856397 138703 net.cpp:113] Setting up relu6
  510. I0524 22:40:39.856438 138703 net.cpp:120] Top shape: 64 4096 (262144)
  511. I0524 22:40:39.856463 138703 layer_factory.hpp:74] Creating layer drop6
  512. I0524 22:40:39.856495 138703 net.cpp:84] Creating Layer drop6
  513. I0524 22:40:39.856520 138703 net.cpp:381] drop6 <- fc6
  514. I0524 22:40:39.856547 138703 net.cpp:328] drop6 -> fc6 (in-place)
  515. I0524 22:40:39.856588 138703 net.cpp:113] Setting up drop6
  516. I0524 22:40:39.856623 138703 net.cpp:120] Top shape: 64 4096 (262144)
  517. I0524 22:40:39.856652 138703 layer_factory.hpp:74] Creating layer fc7
  518. I0524 22:40:39.856683 138703 net.cpp:84] Creating Layer fc7
  519. I0524 22:40:39.856705 138703 net.cpp:381] fc7 <- fc6
  520. I0524 22:40:39.856737 138703 net.cpp:339] fc7 -> fc7
  521. I0524 22:40:39.856770 138703 net.cpp:113] Setting up fc7
  522. I0524 22:40:40.740289 138703 net.cpp:120] Top shape: 64 4096 (262144)
  523. I0524 22:40:40.740332 138703 layer_factory.hpp:74] Creating layer relu7
  524. I0524 22:40:40.740346 138703 net.cpp:84] Creating Layer relu7
  525. I0524 22:40:40.740352 138703 net.cpp:381] relu7 <- fc7
  526. I0524 22:40:40.740361 138703 net.cpp:328] relu7 -> fc7 (in-place)
  527. I0524 22:40:40.740370 138703 net.cpp:113] Setting up relu7
  528. I0524 22:40:40.740377 138703 net.cpp:120] Top shape: 64 4096 (262144)
  529. I0524 22:40:40.740381 138703 layer_factory.hpp:74] Creating layer drop7
  530. I0524 22:40:40.740391 138703 net.cpp:84] Creating Layer drop7
  531. I0524 22:40:40.740397 138703 net.cpp:381] drop7 <- fc7
  532. I0524 22:40:40.740403 138703 net.cpp:328] drop7 -> fc7 (in-place)
  533. I0524 22:40:40.740411 138703 net.cpp:113] Setting up drop7
  534. I0524 22:40:40.740427 138703 net.cpp:120] Top shape: 64 4096 (262144)
  535. I0524 22:40:40.740430 138703 layer_factory.hpp:74] Creating layer fc8-ucf
  536. I0524 22:40:40.740440 138703 net.cpp:84] Creating Layer fc8-ucf
  537. I0524 22:40:40.740445 138703 net.cpp:381] fc8-ucf <- fc7
  538. I0524 22:40:40.740452 138703 net.cpp:339] fc8-ucf -> fc8-ucf
  539. I0524 22:40:40.740464 138703 net.cpp:113] Setting up fc8-ucf
  540. I0524 22:40:40.754626 138703 net.cpp:120] Top shape: 64 101 (6464)
  541. I0524 22:40:40.754658 138703 layer_factory.hpp:74] Creating layer fc8-ucf_fc8-ucf_0_split
  542. I0524 22:40:40.754676 138703 net.cpp:84] Creating Layer fc8-ucf_fc8-ucf_0_split
  543. I0524 22:40:40.754685 138703 net.cpp:381] fc8-ucf_fc8-ucf_0_split <- fc8-ucf
  544. I0524 22:40:40.754698 138703 net.cpp:339] fc8-ucf_fc8-ucf_0_split -> fc8-ucf_fc8-ucf_0_split_0
  545. I0524 22:40:40.754745 138703 net.cpp:339] fc8-ucf_fc8-ucf_0_split -> fc8-ucf_fc8-ucf_0_split_1
  546. I0524 22:40:40.754781 138703 net.cpp:113] Setting up fc8-ucf_fc8-ucf_0_split
  547. I0524 22:40:40.754815 138703 net.cpp:120] Top shape: 64 101 (6464)
  548. I0524 22:40:40.754845 138703 net.cpp:120] Top shape: 64 101 (6464)
  549. I0524 22:40:40.754871 138703 layer_factory.hpp:74] Creating layer loss
  550. I0524 22:40:40.755280 138703 net.cpp:84] Creating Layer loss
  551. I0524 22:40:40.755295 138703 net.cpp:381] loss <- fc8-ucf_fc8-ucf_0_split_0
  552. I0524 22:40:40.755347 138703 net.cpp:381] loss <- label_data_1_split_0
  553. I0524 22:40:40.755384 138703 net.cpp:339] loss -> loss
  554. I0524 22:40:40.755419 138703 net.cpp:113] Setting up loss
  555. I0524 22:40:40.755462 138703 layer_factory.hpp:74] Creating layer loss
  556. I0524 22:40:40.755542 138703 net.cpp:120] Top shape: (1)
  557. I0524 22:40:40.755555 138703 net.cpp:122] with loss weight 1
  558. I0524 22:40:40.755616 138703 layer_factory.hpp:74] Creating layer accuracy
  559. I0524 22:40:40.755650 138703 net.cpp:84] Creating Layer accuracy
  560. I0524 22:40:40.755678 138703 net.cpp:381] accuracy <- fc8-ucf_fc8-ucf_0_split_1
  561. I0524 22:40:40.755708 138703 net.cpp:381] accuracy <- label_data_1_split_1
  562. I0524 22:40:40.755740 138703 net.cpp:339] accuracy -> accuracy
  563. I0524 22:40:40.755774 138703 net.cpp:113] Setting up accuracy
  564. I0524 22:40:40.755807 138703 net.cpp:120] Top shape: (1)
  565. I0524 22:40:40.755836 138703 net.cpp:169] accuracy does not need backward computation.
  566. I0524 22:40:40.755864 138703 net.cpp:167] loss needs backward computation.
  567. I0524 22:40:40.755893 138703 net.cpp:167] fc8-ucf_fc8-ucf_0_split needs backward computation.
  568. I0524 22:40:40.755919 138703 net.cpp:167] fc8-ucf needs backward computation.
  569. I0524 22:40:40.755949 138703 net.cpp:167] drop7 needs backward computation.
  570. I0524 22:40:40.755977 138703 net.cpp:167] relu7 needs backward computation.
  571. I0524 22:40:40.756002 138703 net.cpp:167] fc7 needs backward computation.
  572. I0524 22:40:40.756031 138703 net.cpp:167] drop6 needs backward computation.
  573. I0524 22:40:40.756059 138703 net.cpp:167] relu6 needs backward computation.
  574. I0524 22:40:40.756086 138703 net.cpp:167] fc6 needs backward computation.
  575. I0524 22:40:40.756114 138703 net.cpp:167] pool5 needs backward computation.
  576. I0524 22:40:40.756140 138703 net.cpp:167] relu5 needs backward computation.
  577. I0524 22:40:40.756168 138703 net.cpp:167] conv5 needs backward computation.
  578. I0524 22:40:40.756193 138703 net.cpp:167] relu4 needs backward computation.
  579. I0524 22:40:40.756220 138703 net.cpp:167] conv4 needs backward computation.
  580. I0524 22:40:40.756247 138703 net.cpp:167] relu3 needs backward computation.
  581. I0524 22:40:40.756273 138703 net.cpp:167] conv3 needs backward computation.
  582. I0524 22:40:40.756301 138703 net.cpp:167] norm2 needs backward computation.
  583. I0524 22:40:40.756330 138703 net.cpp:167] pool2 needs backward computation.
  584. I0524 22:40:40.756356 138703 net.cpp:167] relu2 needs backward computation.
  585. I0524 22:40:40.756383 138703 net.cpp:167] conv2 needs backward computation.
  586. I0524 22:40:40.756410 138703 net.cpp:167] norm1 needs backward computation.
  587. I0524 22:40:40.756448 138703 net.cpp:167] pool1 needs backward computation.
  588. I0524 22:40:40.756476 138703 net.cpp:167] relu1 needs backward computation.
  589. I0524 22:40:40.756502 138703 net.cpp:167] conv1 needs backward computation.
  590. I0524 22:40:40.756527 138703 net.cpp:169] label_data_1_split does not need backward computation.
  591. I0524 22:40:40.756562 138703 net.cpp:169] data does not need backward computation.
  592. I0524 22:40:40.756590 138703 net.cpp:205] This network produces output accuracy
  593. I0524 22:40:40.756616 138703 net.cpp:205] This network produces output loss
  594. I0524 22:40:40.756666 138703 net.cpp:446] Collecting Learning Rate and Weight Decay.
  595. I0524 22:40:40.756706 138703 net.cpp:218] Network initialization done.
  596. I0524 22:40:40.756734 138703 net.cpp:219] Memory required for data: 1447903240
  597. I0524 22:40:40.757727 138703 solver.cpp:154] Creating test net (#0) specified by net file: train_test_singleFrame_flow.prototxt
  598. I0524 22:40:40.757805 138703 net.cpp:258] The NetState phase (1) differed from the phase (0) specified by a rule in layer data
  599. I0524 22:40:40.758072 138703 net.cpp:42] Initializing net from parameters:
  600. name: "singleFrame_flow"
  601. state {
  602. phase: TEST
  603. stage: "test-on-test"
  604. }
  605. layer {
  606. name: "data"
  607. type: "Data"
  608. top: "data"
  609. top: "label"
  610. include {
  611. phase: TEST
  612. stage: "test-on-test"
  613. }
  614. transform_param {
  615. mirror: true
  616. crop_size: 227
  617. mean_value: 64
  618. flow: true
  619. }
  620. data_param {
  621. source: "/home/fe/data/lmdb/xml_ucf_10_test/mylmdb"
  622. batch_size: 64
  623. backend: LMDB
  624. }
  625. }
  626. layer {
  627. name: "conv1"
  628. type: "Convolution"
  629. bottom: "data"
  630. top: "conv1"
  631. param {
  632. lr_mult: 1
  633. decay_mult: 1
  634. }
  635. param {
  636. lr_mult: 2
  637. decay_mult: 0
  638. }
  639. convolution_param {
  640. num_output: 96
  641. kernel_size: 7
  642. stride: 2
  643. weight_filler {
  644. type: "gaussian"
  645. std: 0.01
  646. }
  647. bias_filler {
  648. type: "constant"
  649. value: 0.1
  650. }
  651. }
  652. }
  653. layer {
  654. name: "relu1"
  655. type: "ReLU"
  656. bottom: "conv1"
  657. top: "conv1"
  658. }
  659. layer {
  660. name: "pool1"
  661. type: "Pooling"
  662. bottom: "conv1"
  663. top: "pool1"
  664. pooling_param {
  665. pool: MAX
  666. kernel_size: 3
  667. stride: 2
  668. }
  669. }
  670. layer {
  671. name: "norm1"
  672. type: "LRN"
  673. bottom: "pool1"
  674. top: "norm1"
  675. lrn_param {
  676. local_size: 5
  677. alpha: 0.0001
  678. beta: 0.75
  679. }
  680. }
  681. layer {
  682. name: "conv2"
  683. type: "Convolution"
  684. bottom: "norm1"
  685. top: "conv2"
  686. param {
  687. lr_mult: 1
  688. decay_mult: 1
  689. }
  690. param {
  691. lr_mult: 2
  692. decay_mult: 0
  693. }
  694. convolution_param {
  695. num_output: 384
  696. kernel_size: 5
  697. group: 2
  698. stride: 2
  699. weight_filler {
  700. type: "gaussian"
  701. std: 0.01
  702. }
  703. bias_filler {
  704. type: "constant"
  705. value: 0.1
  706. }
  707. }
  708. }
  709. layer {
  710. name: "relu2"
  711. type: "ReLU"
  712. bottom: "conv2"
  713. top: "conv2"
  714. }
  715. layer {
  716. name: "pool2"
  717. type: "Pooling"
  718. bottom: "conv2"
  719. top: "pool2"
  720. pooling_param {
  721. pool: MAX
  722. kernel_size: 3
  723. stride: 2
  724. }
  725. }
  726. layer {
  727. name: "norm2"
  728. type: "LRN"
  729. bottom: "pool2"
  730. top: "norm2"
  731. lrn_param {
  732. local_size: 5
  733. alpha: 0.0001
  734. beta: 0.75
  735. }
  736. }
  737. layer {
  738. name: "conv3"
  739. type: "Convolution"
  740. bottom: "norm2"
  741. top: "conv3"
  742. param {
  743. lr_mult: 1
  744. decay_mult: 1
  745. }
  746. param {
  747. lr_mult: 2
  748. decay_mult: 0
  749. }
  750. convolution_param {
  751. num_output: 512
  752. pad: 1
  753. kernel_size: 3
  754. weight_filler {
  755. type: "gaussian"
  756. std: 0.01
  757. }
  758. bias_filler {
  759. type: "constant"
  760. value: 0.1
  761. }
  762. }
  763. }
  764. layer {
  765. name: "relu3"
  766. type: "ReLU"
  767. bottom: "conv3"
  768. top: "conv3"
  769. }
  770. layer {
  771. name: "conv4"
  772. type: "Convolution"
  773. bottom: "conv3"
  774. top: "conv4"
  775. param {
  776. lr_mult: 1
  777. decay_mult: 1
  778. }
  779. param {
  780. lr_mult: 2
  781. decay_mult: 0
  782. }
  783. convolution_param {
  784. num_output: 512
  785. pad: 1
  786. kernel_size: 3
  787. group: 2
  788. weight_filler {
  789. type: "gaussian"
  790. std: 0.01
  791. }
  792. bias_filler {
  793. type: "constant"
  794. value: 0.1
  795. }
  796. }
  797. }
  798. layer {
  799. name: "relu4"
  800. type: "ReLU"
  801. bottom: "conv4"
  802. top: "conv4"
  803. }
  804. layer {
  805. name: "conv5"
  806. type: "Convolution"
  807. bottom: "conv4"
  808. top: "conv5"
  809. param {
  810. lr_mult: 1
  811. decay_mult: 1
  812. }
  813. param {
  814. lr_mult: 2
  815. decay_mult: 0
  816. }
  817. convolution_param {
  818. num_output: 384
  819. pad: 1
  820. kernel_size: 3
  821. group: 2
  822. weight_filler {
  823. type: "gaussian"
  824. std: 0.01
  825. }
  826. bias_filler {
  827. type: "constant"
  828. value: 0.1
  829. }
  830. }
  831. }
  832. layer {
  833. name: "relu5"
  834. type: "ReLU"
  835. bottom: "conv5"
  836. top: "conv5"
  837. }
  838. layer {
  839. name: "pool5"
  840. type: "Pooling"
  841. bottom: "conv5"
  842. top: "pool5"
  843. pooling_param {
  844. pool: MAX
  845. kernel_size: 3
  846. stride: 2
  847. }
  848. }
  849. layer {
  850. name: "fc6"
  851. type: "InnerProduct"
  852. bottom: "pool5"
  853. top: "fc6"
  854. param {
  855. lr_mult: 1
  856. decay_mult: 1
  857. }
  858. param {
  859. lr_mult: 2
  860. decay_mult: 0
  861. }
  862. inner_product_param {
  863. num_output: 4096
  864. weight_filler {
  865. type: "gaussian"
  866. std: 0.01
  867. }
  868. bias_filler {
  869. type: "constant"
  870. value: 0.1
  871. }
  872. }
  873. }
  874. layer {
  875. name: "relu6"
  876. type: "ReLU"
  877. bottom: "fc6"
  878. top: "fc6"
  879. }
  880. layer {
  881. name: "drop6"
  882. type: "Dropout"
  883. bottom: "fc6"
  884. top: "fc6"
  885. dropout_param {
  886. dropout_ratio: 0.5
  887. }
  888. }
  889. layer {
  890. name: "fc7"
  891. type: "InnerProduct"
  892. bottom: "fc6"
  893. top: "fc7"
  894. param {
  895. lr_mult: 1
  896. decay_mult: 1
  897. }
  898. param {
  899. lr_mult: 2
  900. decay_mult: 0
  901. }
  902. inner_product_param {
  903. num_output: 4096
  904. weight_filler {
  905. type: "gaussian"
  906. std: 0.01
  907. }
  908. bias_filler {
  909. type: "constant"
  910. value: 0.1
  911. }
  912. }
  913. }
  914. layer {
  915. name: "relu7"
  916. type: "ReLU"
  917. bottom: "fc7"
  918. top: "fc7"
  919. }
  920. layer {
  921. name: "drop7"
  922. type: "Dropout"
  923. bottom: "fc7"
  924. top: "fc7"
  925. dropout_param {
  926. dropout_ratio: 0.5
  927. }
  928. }
  929. layer {
  930. name: "fc8-ucf"
  931. type: "InnerProduct"
  932. bottom: "fc7"
  933. top: "fc8-ucf"
  934. param {
  935. lr_mult: 10
  936. decay_mult: 1
  937. }
  938. param {
  939. lr_mult: 20
  940. decay_mult: 0
  941. }
  942. inner_product_param {
  943. num_output: 101
  944. weight_filler {
  945. type: "gaussian"
  946. std: 0.01
  947. }
  948. bias_filler {
  949. type: "constant"
  950. value: 0
  951. }
  952. }
  953. }
  954. layer {
  955. name: "loss"
  956. type: "SoftmaxWithLoss"
  957. bottom: "fc8-ucf"
  958. bottom: "label"
  959. top: "loss"
  960. }
  961. layer {
  962. name: "accuracy"
  963. type: "Accuracy"
  964. bottom: "fc8-ucf"
  965. bottom: "label"
  966. top: "accuracy"
  967. }
  968. I0524 22:40:40.758290 138703 layer_factory.hpp:74] Creating layer data
  969. I0524 22:40:40.758337 138703 net.cpp:84] Creating Layer data
  970. I0524 22:40:40.758368 138703 net.cpp:339] data -> data
  971. I0524 22:40:40.758404 138703 net.cpp:339] data -> label
  972. I0524 22:40:40.758438 138703 net.cpp:113] Setting up data
  973. I0524 22:40:40.776651 138703 db.cpp:34] Opened lmdb /home/fe/data/lmdb/xml_ucf_10_test/mylmdb
  974. I0524 22:40:40.833392 138703 data_layer.cpp:67] output data size: 64,30,227,227
  975. I0524 22:40:42.129523 138703 net.cpp:120] Top shape: 64 30 227 227 (98935680)
  976. I0524 22:40:42.129583 138703 net.cpp:120] Top shape: 64 (64)
  977. I0524 22:40:42.129598 138703 layer_factory.hpp:74] Creating layer label_data_1_split
  978. I0524 22:40:42.129627 138703 net.cpp:84] Creating Layer label_data_1_split
  979. I0524 22:40:42.129662 138703 net.cpp:381] label_data_1_split <- label
  980. I0524 22:40:42.129693 138703 net.cpp:339] label_data_1_split -> label_data_1_split_0
  981. I0524 22:40:42.129726 138703 net.cpp:339] label_data_1_split -> label_data_1_split_1
  982. I0524 22:40:42.129751 138703 net.cpp:113] Setting up label_data_1_split
  983. I0524 22:40:42.129778 138703 net.cpp:120] Top shape: 64 (64)
  984. I0524 22:40:42.129804 138703 net.cpp:120] Top shape: 64 (64)
  985. I0524 22:40:42.129825 138703 layer_factory.hpp:74] Creating layer conv1
  986. I0524 22:40:42.129859 138703 net.cpp:84] Creating Layer conv1
  987. I0524 22:40:42.129881 138703 net.cpp:381] conv1 <- data
  988. I0524 22:40:42.129899 138703 net.cpp:339] conv1 -> conv1
  989. I0524 22:40:42.129921 138703 net.cpp:113] Setting up conv1
  990. I0524 22:40:42.135072 138703 net.cpp:120] Top shape: 64 96 111 111 (75700224)
  991. I0524 22:40:42.135103 138703 layer_factory.hpp:74] Creating layer relu1
  992. I0524 22:40:42.135136 138703 net.cpp:84] Creating Layer relu1
  993. I0524 22:40:42.135148 138703 net.cpp:381] relu1 <- conv1
  994. I0524 22:40:42.135160 138703 net.cpp:328] relu1 -> conv1 (in-place)
  995. I0524 22:40:42.135174 138703 net.cpp:113] Setting up relu1
  996. I0524 22:40:42.135191 138703 net.cpp:120] Top shape: 64 96 111 111 (75700224)
  997. I0524 22:40:42.135203 138703 layer_factory.hpp:74] Creating layer pool1
  998. I0524 22:40:42.135220 138703 net.cpp:84] Creating Layer pool1
  999. I0524 22:40:42.135227 138703 net.cpp:381] pool1 <- conv1
  1000. I0524 22:40:42.135241 138703 net.cpp:339] pool1 -> pool1
  1001. I0524 22:40:42.135252 138703 net.cpp:113] Setting up pool1
  1002. I0524 22:40:42.135270 138703 net.cpp:120] Top shape: 64 96 55 55 (18585600)
  1003. I0524 22:40:42.135279 138703 layer_factory.hpp:74] Creating layer norm1
  1004. I0524 22:40:42.135296 138703 net.cpp:84] Creating Layer norm1
  1005. I0524 22:40:42.135304 138703 net.cpp:381] norm1 <- pool1
  1006. I0524 22:40:42.135318 138703 net.cpp:339] norm1 -> norm1
  1007. I0524 22:40:42.135334 138703 net.cpp:113] Setting up norm1
  1008. I0524 22:40:42.135350 138703 net.cpp:120] Top shape: 64 96 55 55 (18585600)
  1009. I0524 22:40:42.135361 138703 layer_factory.hpp:74] Creating layer conv2
  1010. I0524 22:40:42.135376 138703 net.cpp:84] Creating Layer conv2
  1011. I0524 22:40:42.135385 138703 net.cpp:381] conv2 <- norm1
  1012. I0524 22:40:42.135398 138703 net.cpp:339] conv2 -> conv2
  1013. I0524 22:40:42.135411 138703 net.cpp:113] Setting up conv2
  1014. I0524 22:40:42.151944 138703 net.cpp:120] Top shape: 64 384 26 26 (16613376)
  1015. I0524 22:40:42.151969 138703 layer_factory.hpp:74] Creating layer relu2
  1016. I0524 22:40:42.151983 138703 net.cpp:84] Creating Layer relu2
  1017. I0524 22:40:42.151994 138703 net.cpp:381] relu2 <- conv2
  1018. I0524 22:40:42.152006 138703 net.cpp:328] relu2 -> conv2 (in-place)
  1019. I0524 22:40:42.152017 138703 net.cpp:113] Setting up relu2
  1020. I0524 22:40:42.152029 138703 net.cpp:120] Top shape: 64 384 26 26 (16613376)
  1021. I0524 22:40:42.152063 138703 layer_factory.hpp:74] Creating layer pool2
  1022. I0524 22:40:42.152079 138703 net.cpp:84] Creating Layer pool2
  1023. I0524 22:40:42.152091 138703 net.cpp:381] pool2 <- conv2
  1024. I0524 22:40:42.152106 138703 net.cpp:339] pool2 -> pool2
  1025. I0524 22:40:42.152120 138703 net.cpp:113] Setting up pool2
  1026. I0524 22:40:42.152137 138703 net.cpp:120] Top shape: 64 384 13 13 (4153344)
  1027. I0524 22:40:42.152145 138703 layer_factory.hpp:74] Creating layer norm2
  1028. I0524 22:40:42.152159 138703 net.cpp:84] Creating Layer norm2
  1029. I0524 22:40:42.152168 138703 net.cpp:381] norm2 <- pool2
  1030. I0524 22:40:42.152179 138703 net.cpp:339] norm2 -> norm2
  1031. I0524 22:40:42.152190 138703 net.cpp:113] Setting up norm2
  1032. I0524 22:40:42.152204 138703 net.cpp:120] Top shape: 64 384 13 13 (4153344)
  1033. I0524 22:40:42.152212 138703 layer_factory.hpp:74] Creating layer conv3
  1034. I0524 22:40:42.152225 138703 net.cpp:84] Creating Layer conv3
  1035. I0524 22:40:42.152233 138703 net.cpp:381] conv3 <- norm2
  1036. I0524 22:40:42.152247 138703 net.cpp:339] conv3 -> conv3
  1037. I0524 22:40:42.152263 138703 net.cpp:113] Setting up conv3
  1038. I0524 22:40:42.215615 138703 net.cpp:120] Top shape: 64 512 13 13 (5537792)
  1039. I0524 22:40:42.215672 138703 layer_factory.hpp:74] Creating layer relu3
  1040. I0524 22:40:42.215688 138703 net.cpp:84] Creating Layer relu3
  1041. I0524 22:40:42.215697 138703 net.cpp:381] relu3 <- conv3
  1042. I0524 22:40:42.215718 138703 net.cpp:328] relu3 -> conv3 (in-place)
  1043. I0524 22:40:42.215733 138703 net.cpp:113] Setting up relu3
  1044. I0524 22:40:42.215744 138703 net.cpp:120] Top shape: 64 512 13 13 (5537792)
  1045. I0524 22:40:42.215751 138703 layer_factory.hpp:74] Creating layer conv4
  1046. I0524 22:40:42.215765 138703 net.cpp:84] Creating Layer conv4
  1047. I0524 22:40:42.215772 138703 net.cpp:381] conv4 <- conv3
  1048. I0524 22:40:42.215785 138703 net.cpp:339] conv4 -> conv4
  1049. I0524 22:40:42.215804 138703 net.cpp:113] Setting up conv4
  1050. I0524 22:40:42.257380 138703 net.cpp:120] Top shape: 64 512 13 13 (5537792)
  1051. I0524 22:40:42.257681 138703 layer_factory.hpp:74] Creating layer relu4
  1052. I0524 22:40:42.257702 138703 net.cpp:84] Creating Layer relu4
  1053. I0524 22:40:42.257714 138703 net.cpp:381] relu4 <- conv4
  1054. I0524 22:40:42.257732 138703 net.cpp:328] relu4 -> conv4 (in-place)
  1055. I0524 22:40:42.257747 138703 net.cpp:113] Setting up relu4
  1056. I0524 22:40:42.257760 138703 net.cpp:120] Top shape: 64 512 13 13 (5537792)
  1057. I0524 22:40:42.257767 138703 layer_factory.hpp:74] Creating layer conv5
  1058. I0524 22:40:42.257782 138703 net.cpp:84] Creating Layer conv5
  1059. I0524 22:40:42.257792 138703 net.cpp:381] conv5 <- conv4
  1060. I0524 22:40:42.257807 138703 net.cpp:339] conv5 -> conv5
  1061. I0524 22:40:42.257822 138703 net.cpp:113] Setting up conv5
  1062. I0524 22:40:42.292773 138703 net.cpp:120] Top shape: 64 384 13 13 (4153344)
  1063. I0524 22:40:42.292796 138703 layer_factory.hpp:74] Creating layer relu5
  1064. I0524 22:40:42.292806 138703 net.cpp:84] Creating Layer relu5
  1065. I0524 22:40:42.292811 138703 net.cpp:381] relu5 <- conv5
  1066. I0524 22:40:42.292819 138703 net.cpp:328] relu5 -> conv5 (in-place)
  1067. I0524 22:40:42.292826 138703 net.cpp:113] Setting up relu5
  1068. I0524 22:40:42.292835 138703 net.cpp:120] Top shape: 64 384 13 13 (4153344)
  1069. I0524 22:40:42.292840 138703 layer_factory.hpp:74] Creating layer pool5
  1070. I0524 22:40:42.292851 138703 net.cpp:84] Creating Layer pool5
  1071. I0524 22:40:42.292857 138703 net.cpp:381] pool5 <- conv5
  1072. I0524 22:40:42.292865 138703 net.cpp:339] pool5 -> pool5
  1073. I0524 22:40:42.292872 138703 net.cpp:113] Setting up pool5
  1074. I0524 22:40:42.292883 138703 net.cpp:120] Top shape: 64 384 6 6 (884736)
  1075. I0524 22:40:42.292889 138703 layer_factory.hpp:74] Creating layer fc6
  1076. I0524 22:40:42.292899 138703 net.cpp:84] Creating Layer fc6
  1077. I0524 22:40:42.292906 138703 net.cpp:381] fc6 <- pool5
  1078. I0524 22:40:42.292912 138703 net.cpp:339] fc6 -> fc6
  1079. I0524 22:40:42.292922 138703 net.cpp:113] Setting up fc6
  1080. I0524 22:40:44.376781 138703 net.cpp:120] Top shape: 64 4096 (262144)
  1081. I0524 22:40:44.376837 138703 layer_factory.hpp:74] Creating layer relu6
  1082. I0524 22:40:44.376857 138703 net.cpp:84] Creating Layer relu6
  1083. I0524 22:40:44.376868 138703 net.cpp:381] relu6 <- fc6
  1084. I0524 22:40:44.376930 138703 net.cpp:328] relu6 -> fc6 (in-place)
  1085. I0524 22:40:44.376965 138703 net.cpp:113] Setting up relu6
  1086. I0524 22:40:44.376992 138703 net.cpp:120] Top shape: 64 4096 (262144)
  1087. I0524 22:40:44.377015 138703 layer_factory.hpp:74] Creating layer drop6
  1088. I0524 22:40:44.377046 138703 net.cpp:84] Creating Layer drop6
  1089. I0524 22:40:44.377054 138703 net.cpp:381] drop6 <- fc6
  1090. I0524 22:40:44.377064 138703 net.cpp:328] drop6 -> fc6 (in-place)
  1091. I0524 22:40:44.377075 138703 net.cpp:113] Setting up drop6
  1092. I0524 22:40:44.377089 138703 net.cpp:120] Top shape: 64 4096 (262144)
  1093. I0524 22:40:44.377123 138703 layer_factory.hpp:74] Creating layer fc7
  1094. I0524 22:40:44.377157 138703 net.cpp:84] Creating Layer fc7
  1095. I0524 22:40:44.377180 138703 net.cpp:381] fc7 <- fc6
  1096. I0524 22:40:44.377213 138703 net.cpp:339] fc7 -> fc7
  1097. I0524 22:40:44.377245 138703 net.cpp:113] Setting up fc7
  1098. I0524 22:40:45.278657 138703 net.cpp:120] Top shape: 64 4096 (262144)
  1099. I0524 22:40:45.278717 138703 layer_factory.hpp:74] Creating layer relu7
  1100. I0524 22:40:45.278738 138703 net.cpp:84] Creating Layer relu7
  1101. I0524 22:40:45.278753 138703 net.cpp:381] relu7 <- fc7
  1102. I0524 22:40:45.278794 138703 net.cpp:328] relu7 -> fc7 (in-place)
  1103. I0524 22:40:45.278827 138703 net.cpp:113] Setting up relu7
  1104. I0524 22:40:45.278854 138703 net.cpp:120] Top shape: 64 4096 (262144)
  1105. I0524 22:40:45.278879 138703 layer_factory.hpp:74] Creating layer drop7
  1106. I0524 22:40:45.278913 138703 net.cpp:84] Creating Layer drop7
  1107. I0524 22:40:45.278939 138703 net.cpp:381] drop7 <- fc7
  1108. I0524 22:40:45.278969 138703 net.cpp:328] drop7 -> fc7 (in-place)
  1109. I0524 22:40:45.278998 138703 net.cpp:113] Setting up drop7
  1110. I0524 22:40:45.279032 138703 net.cpp:120] Top shape: 64 4096 (262144)
  1111. I0524 22:40:45.279060 138703 layer_factory.hpp:74] Creating layer fc8-ucf
  1112. I0524 22:40:45.279095 138703 net.cpp:84] Creating Layer fc8-ucf
  1113. I0524 22:40:45.279122 138703 net.cpp:381] fc8-ucf <- fc7
  1114. I0524 22:40:45.279156 138703 net.cpp:339] fc8-ucf -> fc8-ucf
  1115. I0524 22:40:45.279201 138703 net.cpp:113] Setting up fc8-ucf
  1116. I0524 22:40:45.293254 138703 net.cpp:120] Top shape: 64 101 (6464)
  1117. I0524 22:40:45.293272 138703 layer_factory.hpp:74] Creating layer fc8-ucf_fc8-ucf_0_split
  1118. I0524 22:40:45.293287 138703 net.cpp:84] Creating Layer fc8-ucf_fc8-ucf_0_split
  1119. I0524 22:40:45.293320 138703 net.cpp:381] fc8-ucf_fc8-ucf_0_split <- fc8-ucf
  1120. I0524 22:40:45.293351 138703 net.cpp:339] fc8-ucf_fc8-ucf_0_split -> fc8-ucf_fc8-ucf_0_split_0
  1121. I0524 22:40:45.293385 138703 net.cpp:339] fc8-ucf_fc8-ucf_0_split -> fc8-ucf_fc8-ucf_0_split_1
  1122. I0524 22:40:45.293417 138703 net.cpp:113] Setting up fc8-ucf_fc8-ucf_0_split
  1123. I0524 22:40:45.293453 138703 net.cpp:120] Top shape: 64 101 (6464)
  1124. I0524 22:40:45.293483 138703 net.cpp:120] Top shape: 64 101 (6464)
  1125. I0524 22:40:45.293509 138703 layer_factory.hpp:74] Creating layer loss
  1126. I0524 22:40:45.293541 138703 net.cpp:84] Creating Layer loss
  1127. I0524 22:40:45.293568 138703 net.cpp:381] loss <- fc8-ucf_fc8-ucf_0_split_0
  1128. I0524 22:40:45.293597 138703 net.cpp:381] loss <- label_data_1_split_0
  1129. I0524 22:40:45.293627 138703 net.cpp:339] loss -> loss
  1130. I0524 22:40:45.293658 138703 net.cpp:113] Setting up loss
  1131. I0524 22:40:45.293673 138703 layer_factory.hpp:74] Creating layer loss
  1132. I0524 22:40:45.293743 138703 net.cpp:120] Top shape: (1)
  1133. I0524 22:40:45.293752 138703 net.cpp:122] with loss weight 1
  1134. I0524 22:40:45.293789 138703 layer_factory.hpp:74] Creating layer accuracy
  1135. I0524 22:40:45.293820 138703 net.cpp:84] Creating Layer accuracy
  1136. I0524 22:40:45.293846 138703 net.cpp:381] accuracy <- fc8-ucf_fc8-ucf_0_split_1
  1137. I0524 22:40:45.293875 138703 net.cpp:381] accuracy <- label_data_1_split_1
  1138. I0524 22:40:45.293905 138703 net.cpp:339] accuracy -> accuracy
  1139. I0524 22:40:45.293936 138703 net.cpp:113] Setting up accuracy
  1140. I0524 22:40:45.293967 138703 net.cpp:120] Top shape: (1)
  1141. I0524 22:40:45.293978 138703 net.cpp:169] accuracy does not need backward computation.
  1142. I0524 22:40:45.293985 138703 net.cpp:167] loss needs backward computation.
  1143. I0524 22:40:45.294013 138703 net.cpp:167] fc8-ucf_fc8-ucf_0_split needs backward computation.
  1144. I0524 22:40:45.294051 138703 net.cpp:167] fc8-ucf needs backward computation.
  1145. I0524 22:40:45.294080 138703 net.cpp:167] drop7 needs backward computation.
  1146. I0524 22:40:45.294086 138703 net.cpp:167] relu7 needs backward computation.
  1147. I0524 22:40:45.294112 138703 net.cpp:167] fc7 needs backward computation.
  1148. I0524 22:40:45.294140 138703 net.cpp:167] drop6 needs backward computation.
  1149. I0524 22:40:45.294163 138703 net.cpp:167] relu6 needs backward computation.
  1150. I0524 22:40:45.294188 138703 net.cpp:167] fc6 needs backward computation.
  1151. I0524 22:40:45.294216 138703 net.cpp:167] pool5 needs backward computation.
  1152. I0524 22:40:45.294242 138703 net.cpp:167] relu5 needs backward computation.
  1153. I0524 22:40:45.294270 138703 net.cpp:167] conv5 needs backward computation.
  1154. I0524 22:40:45.294296 138703 net.cpp:167] relu4 needs backward computation.
  1155. I0524 22:40:45.294322 138703 net.cpp:167] conv4 needs backward computation.
  1156. I0524 22:40:45.294348 138703 net.cpp:167] relu3 needs backward computation.
  1157. I0524 22:40:45.294373 138703 net.cpp:167] conv3 needs backward computation.
  1158. I0524 22:40:45.294402 138703 net.cpp:167] norm2 needs backward computation.
  1159. I0524 22:40:45.294430 138703 net.cpp:167] pool2 needs backward computation.
  1160. I0524 22:40:45.294456 138703 net.cpp:167] relu2 needs backward computation.
  1161. I0524 22:40:45.294481 138703 net.cpp:167] conv2 needs backward computation.
  1162. I0524 22:40:45.294507 138703 net.cpp:167] norm1 needs backward computation.
  1163. I0524 22:40:45.294531 138703 net.cpp:167] pool1 needs backward computation.
  1164. I0524 22:40:45.294556 138703 net.cpp:167] relu1 needs backward computation.
  1165. I0524 22:40:45.294581 138703 net.cpp:167] conv1 needs backward computation.
  1166. I0524 22:40:45.294607 138703 net.cpp:169] label_data_1_split does not need backward computation.
  1167. I0524 22:40:45.294632 138703 net.cpp:169] data does not need backward computation.
  1168. I0524 22:40:45.294656 138703 net.cpp:205] This network produces output accuracy
  1169. I0524 22:40:45.294679 138703 net.cpp:205] This network produces output loss
  1170. I0524 22:40:45.294725 138703 net.cpp:446] Collecting Learning Rate and Weight Decay.
  1171. I0524 22:40:45.294740 138703 net.cpp:218] Network initialization done.
  1172. I0524 22:40:45.294765 138703 net.cpp:219] Memory required for data: 1447903240
  1173. I0524 22:40:45.294977 138703 solver.cpp:42] Solver scaffolding done.
  1174. I0524 22:40:45.295042 138703 solver.cpp:247] Solving singleFrame_flow
  1175. I0524 22:40:45.295052 138703 solver.cpp:248] Learning Rate Policy: step
  1176. I0524 22:40:45.299389 138703 solver.cpp:291] Iteration 0, Testing net (#0)
  1177. I0524 22:44:49.625109 138703 solver.cpp:340] Test net output #0: accuracy = 0.0110417
  1178. I0524 22:44:49.625236 138703 solver.cpp:340] Test net output #1: loss = 4.64081 (* 1 = 4.64081 loss)
  1179. I0524 22:44:52.939046 138703 solver.cpp:214] Iteration 0, loss = 4.70357
  1180. I0524 22:44:52.939111 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1181. I0524 22:44:52.939139 138703 solver.cpp:229] Train net output #1: loss = 4.70357 (* 1 = 4.70357 loss)
  1182. I0524 22:44:52.939190 138703 solver.cpp:489] Iteration 0, lr = 0.001
  1183. I0524 22:46:03.091089 138703 solver.cpp:214] Iteration 20, loss = 4.51372
  1184. I0524 22:46:03.091240 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1185. I0524 22:46:03.091258 138703 solver.cpp:229] Train net output #1: loss = 4.51372 (* 1 = 4.51372 loss)
  1186. I0524 22:46:03.091279 138703 solver.cpp:489] Iteration 20, lr = 0.001
  1187. I0524 22:47:14.046478 138703 solver.cpp:214] Iteration 40, loss = 4.62159
  1188. I0524 22:47:14.046618 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1189. I0524 22:47:14.046643 138703 solver.cpp:229] Train net output #1: loss = 4.62159 (* 1 = 4.62159 loss)
  1190. I0524 22:47:14.046689 138703 solver.cpp:489] Iteration 40, lr = 0.001
  1191. I0524 22:48:26.734160 138703 solver.cpp:214] Iteration 60, loss = 4.54802
  1192. I0524 22:48:26.735971 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1193. I0524 22:48:26.735991 138703 solver.cpp:229] Train net output #1: loss = 4.54802 (* 1 = 4.54802 loss)
  1194. I0524 22:48:26.736006 138703 solver.cpp:489] Iteration 60, lr = 0.001
  1195. I0524 22:49:39.820689 138703 solver.cpp:214] Iteration 80, loss = 4.65066
  1196. I0524 22:49:39.820863 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1197. I0524 22:49:39.820883 138703 solver.cpp:229] Train net output #1: loss = 4.65066 (* 1 = 4.65066 loss)
  1198. I0524 22:49:39.820901 138703 solver.cpp:489] Iteration 80, lr = 0.001
  1199. I0524 22:50:51.969734 138703 solver.cpp:291] Iteration 100, Testing net (#0)
  1200. I0524 22:53:53.926062 138703 solver.cpp:340] Test net output #0: accuracy = 0.0225
  1201. I0524 22:53:53.926208 138703 solver.cpp:340] Test net output #1: loss = 4.57388 (* 1 = 4.57388 loss)
  1202. I0524 22:53:56.376865 138703 solver.cpp:214] Iteration 100, loss = 4.48973
  1203. I0524 22:53:56.376915 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1204. I0524 22:53:56.376934 138703 solver.cpp:229] Train net output #1: loss = 4.48973 (* 1 = 4.48973 loss)
  1205. I0524 22:53:56.376953 138703 solver.cpp:489] Iteration 100, lr = 0.001
  1206. I0524 22:55:10.381433 138703 solver.cpp:214] Iteration 120, loss = 4.59416
  1207. I0524 22:55:10.381585 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1208. I0524 22:55:10.381608 138703 solver.cpp:229] Train net output #1: loss = 4.59416 (* 1 = 4.59416 loss)
  1209. I0524 22:55:10.381628 138703 solver.cpp:489] Iteration 120, lr = 0.001
  1210. I0524 22:56:22.451100 138703 solver.cpp:214] Iteration 140, loss = 4.51941
  1211. I0524 22:56:22.451338 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1212. I0524 22:56:22.451354 138703 solver.cpp:229] Train net output #1: loss = 4.51941 (* 1 = 4.51941 loss)
  1213. I0524 22:56:22.451369 138703 solver.cpp:489] Iteration 140, lr = 0.001
  1214. I0524 22:57:38.372445 138703 solver.cpp:214] Iteration 160, loss = 4.58693
  1215. I0524 22:57:38.372607 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1216. I0524 22:57:38.372624 138703 solver.cpp:229] Train net output #1: loss = 4.58693 (* 1 = 4.58693 loss)
  1217. I0524 22:57:38.372638 138703 solver.cpp:489] Iteration 160, lr = 0.001
  1218. I0524 22:58:54.504142 138703 solver.cpp:214] Iteration 180, loss = 4.42354
  1219. I0524 22:58:54.504297 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1220. I0524 22:58:54.504313 138703 solver.cpp:229] Train net output #1: loss = 4.42354 (* 1 = 4.42354 loss)
  1221. I0524 22:58:54.504326 138703 solver.cpp:489] Iteration 180, lr = 0.001
  1222. I0524 23:00:05.802309 138703 solver.cpp:291] Iteration 200, Testing net (#0)
  1223. I0524 23:03:08.973074 138703 solver.cpp:340] Test net output #0: accuracy = 0.023125
  1224. I0524 23:03:08.974046 138703 solver.cpp:340] Test net output #1: loss = 4.55702 (* 1 = 4.55702 loss)
  1225. I0524 23:03:11.432184 138703 solver.cpp:214] Iteration 200, loss = 4.59867
  1226. I0524 23:03:11.432232 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1227. I0524 23:03:11.432250 138703 solver.cpp:229] Train net output #1: loss = 4.59867 (* 1 = 4.59867 loss)
  1228. I0524 23:03:11.432268 138703 solver.cpp:489] Iteration 200, lr = 0.001
  1229. I0524 23:04:27.518496 138703 solver.cpp:214] Iteration 220, loss = 4.58314
  1230. I0524 23:04:27.518633 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1231. I0524 23:04:27.518656 138703 solver.cpp:229] Train net output #1: loss = 4.58314 (* 1 = 4.58314 loss)
  1232. I0524 23:04:27.518702 138703 solver.cpp:489] Iteration 220, lr = 0.001
  1233. I0524 23:05:43.433465 138703 solver.cpp:214] Iteration 240, loss = 4.47373
  1234. I0524 23:05:43.433617 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1235. I0524 23:05:43.433634 138703 solver.cpp:229] Train net output #1: loss = 4.47373 (* 1 = 4.47373 loss)
  1236. I0524 23:05:43.433648 138703 solver.cpp:489] Iteration 240, lr = 0.001
  1237. I0524 23:06:56.575230 138703 solver.cpp:214] Iteration 260, loss = 4.52448
  1238. I0524 23:06:56.575461 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  1239. I0524 23:06:56.575487 138703 solver.cpp:229] Train net output #1: loss = 4.52448 (* 1 = 4.52448 loss)
  1240. I0524 23:06:56.575510 138703 solver.cpp:489] Iteration 260, lr = 0.001
  1241. I0524 23:08:07.069103 138703 solver.cpp:214] Iteration 280, loss = 4.51746
  1242. I0524 23:08:07.069254 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1243. I0524 23:08:07.069270 138703 solver.cpp:229] Train net output #1: loss = 4.51746 (* 1 = 4.51746 loss)
  1244. I0524 23:08:07.069284 138703 solver.cpp:489] Iteration 280, lr = 0.001
  1245. I0524 23:09:11.868643 138703 solver.cpp:291] Iteration 300, Testing net (#0)
  1246. I0524 23:12:16.402215 138703 solver.cpp:340] Test net output #0: accuracy = 0.0147917
  1247. I0524 23:12:16.402371 138703 solver.cpp:340] Test net output #1: loss = 4.57558 (* 1 = 4.57558 loss)
  1248. I0524 23:12:18.868732 138703 solver.cpp:214] Iteration 300, loss = 4.53992
  1249. I0524 23:12:18.868782 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1250. I0524 23:12:18.868801 138703 solver.cpp:229] Train net output #1: loss = 4.53992 (* 1 = 4.53992 loss)
  1251. I0524 23:12:18.868819 138703 solver.cpp:489] Iteration 300, lr = 0.001
  1252. I0524 23:13:35.852485 138703 solver.cpp:214] Iteration 320, loss = 4.51065
  1253. I0524 23:13:35.852632 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1254. I0524 23:13:35.852650 138703 solver.cpp:229] Train net output #1: loss = 4.51065 (* 1 = 4.51065 loss)
  1255. I0524 23:13:35.852664 138703 solver.cpp:489] Iteration 320, lr = 0.001
  1256. I0524 23:14:45.226703 138703 solver.cpp:214] Iteration 340, loss = 4.52654
  1257. I0524 23:14:45.226847 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1258. I0524 23:14:45.226866 138703 solver.cpp:229] Train net output #1: loss = 4.52654 (* 1 = 4.52654 loss)
  1259. I0524 23:14:45.226878 138703 solver.cpp:489] Iteration 340, lr = 0.001
  1260. I0524 23:15:50.947469 138703 solver.cpp:214] Iteration 360, loss = 4.49887
  1261. I0524 23:15:50.947602 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1262. I0524 23:15:50.947620 138703 solver.cpp:229] Train net output #1: loss = 4.49887 (* 1 = 4.49887 loss)
  1263. I0524 23:15:50.947634 138703 solver.cpp:489] Iteration 360, lr = 0.001
  1264. I0524 23:17:01.366631 138703 solver.cpp:214] Iteration 380, loss = 4.54761
  1265. I0524 23:17:01.366761 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1266. I0524 23:17:01.366780 138703 solver.cpp:229] Train net output #1: loss = 4.54761 (* 1 = 4.54761 loss)
  1267. I0524 23:17:01.366792 138703 solver.cpp:489] Iteration 380, lr = 0.001
  1268. I0524 23:18:13.593641 138703 solver.cpp:291] Iteration 400, Testing net (#0)
  1269. I0524 23:21:22.111552 138703 solver.cpp:340] Test net output #0: accuracy = 0.0191667
  1270. I0524 23:21:22.111712 138703 solver.cpp:340] Test net output #1: loss = 4.53109 (* 1 = 4.53109 loss)
  1271. I0524 23:21:24.597728 138703 solver.cpp:214] Iteration 400, loss = 4.63498
  1272. I0524 23:21:24.597782 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1273. I0524 23:21:24.597806 138703 solver.cpp:229] Train net output #1: loss = 4.63498 (* 1 = 4.63498 loss)
  1274. I0524 23:21:24.597825 138703 solver.cpp:489] Iteration 400, lr = 0.001
  1275. I0524 23:22:33.700228 138703 solver.cpp:214] Iteration 420, loss = 4.50529
  1276. I0524 23:22:33.700366 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1277. I0524 23:22:33.700383 138703 solver.cpp:229] Train net output #1: loss = 4.50529 (* 1 = 4.50529 loss)
  1278. I0524 23:22:33.700395 138703 solver.cpp:489] Iteration 420, lr = 0.001
  1279. I0524 23:23:43.433524 138703 solver.cpp:214] Iteration 440, loss = 4.61166
  1280. I0524 23:23:43.433673 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1281. I0524 23:23:43.433701 138703 solver.cpp:229] Train net output #1: loss = 4.61166 (* 1 = 4.61166 loss)
  1282. I0524 23:23:43.433745 138703 solver.cpp:489] Iteration 440, lr = 0.001
  1283. I0524 23:24:59.636443 138703 solver.cpp:214] Iteration 460, loss = 4.45173
  1284. I0524 23:24:59.637037 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1285. I0524 23:24:59.637058 138703 solver.cpp:229] Train net output #1: loss = 4.45173 (* 1 = 4.45173 loss)
  1286. I0524 23:24:59.637073 138703 solver.cpp:489] Iteration 460, lr = 0.001
  1287. I0524 23:26:15.678037 138703 solver.cpp:214] Iteration 480, loss = 4.57064
  1288. I0524 23:26:15.678184 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1289. I0524 23:26:15.678210 138703 solver.cpp:229] Train net output #1: loss = 4.57064 (* 1 = 4.57064 loss)
  1290. I0524 23:26:15.678254 138703 solver.cpp:489] Iteration 480, lr = 0.001
  1291. I0524 23:27:28.017033 138703 solver.cpp:291] Iteration 500, Testing net (#0)
  1292. I0524 23:30:36.843104 138703 solver.cpp:340] Test net output #0: accuracy = 0.0247917
  1293. I0524 23:30:36.845855 138703 solver.cpp:340] Test net output #1: loss = 4.57009 (* 1 = 4.57009 loss)
  1294. I0524 23:30:39.312402 138703 solver.cpp:214] Iteration 500, loss = 4.51115
  1295. I0524 23:30:39.312453 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1296. I0524 23:30:39.312470 138703 solver.cpp:229] Train net output #1: loss = 4.51115 (* 1 = 4.51115 loss)
  1297. I0524 23:30:39.312484 138703 solver.cpp:489] Iteration 500, lr = 0.001
  1298. I0524 23:31:55.299831 138703 solver.cpp:214] Iteration 520, loss = 4.41992
  1299. I0524 23:31:55.300042 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1300. I0524 23:31:55.300086 138703 solver.cpp:229] Train net output #1: loss = 4.41992 (* 1 = 4.41992 loss)
  1301. I0524 23:31:55.300122 138703 solver.cpp:489] Iteration 520, lr = 0.001
  1302. I0524 23:33:11.416810 138703 solver.cpp:214] Iteration 540, loss = 4.52528
  1303. I0524 23:33:11.417045 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1304. I0524 23:33:11.417088 138703 solver.cpp:229] Train net output #1: loss = 4.52528 (* 1 = 4.52528 loss)
  1305. I0524 23:33:11.417119 138703 solver.cpp:489] Iteration 540, lr = 0.001
  1306. I0524 23:34:26.896179 138703 solver.cpp:214] Iteration 560, loss = 4.54924
  1307. I0524 23:34:26.896389 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1308. I0524 23:34:26.896445 138703 solver.cpp:229] Train net output #1: loss = 4.54924 (* 1 = 4.54924 loss)
  1309. I0524 23:34:26.896481 138703 solver.cpp:489] Iteration 560, lr = 0.001
  1310. I0524 23:35:37.662381 138703 solver.cpp:214] Iteration 580, loss = 4.54194
  1311. I0524 23:35:37.662540 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1312. I0524 23:35:37.662559 138703 solver.cpp:229] Train net output #1: loss = 4.54194 (* 1 = 4.54194 loss)
  1313. I0524 23:35:37.662572 138703 solver.cpp:489] Iteration 580, lr = 0.001
  1314. I0524 23:36:49.574558 138703 solver.cpp:291] Iteration 600, Testing net (#0)
  1315. I0524 23:39:59.557834 138703 solver.cpp:340] Test net output #0: accuracy = 0.015
  1316. I0524 23:39:59.557991 138703 solver.cpp:340] Test net output #1: loss = 4.54958 (* 1 = 4.54958 loss)
  1317. I0524 23:40:01.999552 138703 solver.cpp:214] Iteration 600, loss = 4.44046
  1318. I0524 23:40:01.999600 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1319. I0524 23:40:01.999619 138703 solver.cpp:229] Train net output #1: loss = 4.44046 (* 1 = 4.44046 loss)
  1320. I0524 23:40:01.999635 138703 solver.cpp:489] Iteration 600, lr = 0.001
  1321. I0524 23:41:17.732296 138703 solver.cpp:214] Iteration 620, loss = 4.48777
  1322. I0524 23:41:17.732483 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1323. I0524 23:41:17.732506 138703 solver.cpp:229] Train net output #1: loss = 4.48777 (* 1 = 4.48777 loss)
  1324. I0524 23:41:17.732525 138703 solver.cpp:489] Iteration 620, lr = 0.001
  1325. I0524 23:42:32.420616 138703 solver.cpp:214] Iteration 640, loss = 4.57999
  1326. I0524 23:42:32.420773 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1327. I0524 23:42:32.420799 138703 solver.cpp:229] Train net output #1: loss = 4.57999 (* 1 = 4.57999 loss)
  1328. I0524 23:42:32.420840 138703 solver.cpp:489] Iteration 640, lr = 0.001
  1329. I0524 23:43:42.462966 138703 solver.cpp:214] Iteration 660, loss = 4.56551
  1330. I0524 23:43:42.463124 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1331. I0524 23:43:42.463143 138703 solver.cpp:229] Train net output #1: loss = 4.56551 (* 1 = 4.56551 loss)
  1332. I0524 23:43:42.463157 138703 solver.cpp:489] Iteration 660, lr = 0.001
  1333. I0524 23:44:51.117818 138703 solver.cpp:214] Iteration 680, loss = 4.5298
  1334. I0524 23:44:51.117996 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1335. I0524 23:44:51.118015 138703 solver.cpp:229] Train net output #1: loss = 4.5298 (* 1 = 4.5298 loss)
  1336. I0524 23:44:51.118028 138703 solver.cpp:489] Iteration 680, lr = 0.001
  1337. I0524 23:46:03.598601 138703 solver.cpp:291] Iteration 700, Testing net (#0)
  1338. I0524 23:49:15.565232 138703 solver.cpp:340] Test net output #0: accuracy = 0.025
  1339. I0524 23:49:15.565378 138703 solver.cpp:340] Test net output #1: loss = 4.5475 (* 1 = 4.5475 loss)
  1340. I0524 23:49:18.037204 138703 solver.cpp:214] Iteration 700, loss = 4.48317
  1341. I0524 23:49:18.037250 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1342. I0524 23:49:18.037264 138703 solver.cpp:229] Train net output #1: loss = 4.48317 (* 1 = 4.48317 loss)
  1343. I0524 23:49:18.037278 138703 solver.cpp:489] Iteration 700, lr = 0.001
  1344. I0524 23:50:28.863509 138703 solver.cpp:214] Iteration 720, loss = 4.45289
  1345. I0524 23:50:28.863677 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1346. I0524 23:50:28.863699 138703 solver.cpp:229] Train net output #1: loss = 4.45289 (* 1 = 4.45289 loss)
  1347. I0524 23:50:28.863752 138703 solver.cpp:489] Iteration 720, lr = 0.001
  1348. I0524 23:51:36.669387 138703 solver.cpp:214] Iteration 740, loss = 4.47954
  1349. I0524 23:51:36.672874 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1350. I0524 23:51:36.672890 138703 solver.cpp:229] Train net output #1: loss = 4.47954 (* 1 = 4.47954 loss)
  1351. I0524 23:51:36.672905 138703 solver.cpp:489] Iteration 740, lr = 0.001
  1352. I0524 23:52:48.839931 138703 solver.cpp:214] Iteration 760, loss = 4.59684
  1353. I0524 23:52:48.840066 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1354. I0524 23:52:48.840090 138703 solver.cpp:229] Train net output #1: loss = 4.59684 (* 1 = 4.59684 loss)
  1355. I0524 23:52:48.840138 138703 solver.cpp:489] Iteration 760, lr = 0.001
  1356. I0524 23:54:04.535289 138703 solver.cpp:214] Iteration 780, loss = 4.55373
  1357. I0524 23:54:04.535518 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1358. I0524 23:54:04.535537 138703 solver.cpp:229] Train net output #1: loss = 4.55373 (* 1 = 4.55373 loss)
  1359. I0524 23:54:04.535550 138703 solver.cpp:489] Iteration 780, lr = 0.001
  1360. I0524 23:55:17.813962 138703 solver.cpp:291] Iteration 800, Testing net (#0)
  1361. I0524 23:58:33.912055 138703 solver.cpp:340] Test net output #0: accuracy = 0.0364583
  1362. I0524 23:58:33.912202 138703 solver.cpp:340] Test net output #1: loss = 4.51093 (* 1 = 4.51093 loss)
  1363. I0524 23:58:35.787883 138703 solver.cpp:214] Iteration 800, loss = 4.41901
  1364. I0524 23:58:35.787930 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1365. I0524 23:58:35.787945 138703 solver.cpp:229] Train net output #1: loss = 4.41901 (* 1 = 4.41901 loss)
  1366. I0524 23:58:35.787957 138703 solver.cpp:489] Iteration 800, lr = 0.001
  1367. I0524 23:59:49.327036 138703 solver.cpp:214] Iteration 820, loss = 4.41647
  1368. I0524 23:59:49.327185 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1369. I0524 23:59:49.327201 138703 solver.cpp:229] Train net output #1: loss = 4.41647 (* 1 = 4.41647 loss)
  1370. I0524 23:59:49.327214 138703 solver.cpp:489] Iteration 820, lr = 0.001
  1371. I0525 00:01:05.214942 138703 solver.cpp:214] Iteration 840, loss = 4.37763
  1372. I0525 00:01:05.215085 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1373. I0525 00:01:05.215108 138703 solver.cpp:229] Train net output #1: loss = 4.37763 (* 1 = 4.37763 loss)
  1374. I0525 00:01:05.215147 138703 solver.cpp:489] Iteration 840, lr = 0.001
  1375. I0525 00:02:21.901170 138703 solver.cpp:214] Iteration 860, loss = 4.5282
  1376. I0525 00:02:21.901316 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1377. I0525 00:02:21.901335 138703 solver.cpp:229] Train net output #1: loss = 4.5282 (* 1 = 4.5282 loss)
  1378. I0525 00:02:21.901347 138703 solver.cpp:489] Iteration 860, lr = 0.001
  1379. I0525 00:03:32.926962 138703 solver.cpp:214] Iteration 880, loss = 4.61298
  1380. I0525 00:03:32.927127 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1381. I0525 00:03:32.927151 138703 solver.cpp:229] Train net output #1: loss = 4.61298 (* 1 = 4.61298 loss)
  1382. I0525 00:03:32.927192 138703 solver.cpp:489] Iteration 880, lr = 0.001
  1383. I0525 00:04:37.312484 138703 solver.cpp:291] Iteration 900, Testing net (#0)
  1384. I0525 00:07:56.898192 138703 solver.cpp:340] Test net output #0: accuracy = 0.0270833
  1385. I0525 00:07:56.898389 138703 solver.cpp:340] Test net output #1: loss = 4.51743 (* 1 = 4.51743 loss)
  1386. I0525 00:07:59.331938 138703 solver.cpp:214] Iteration 900, loss = 4.42672
  1387. I0525 00:07:59.331995 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1388. I0525 00:07:59.332008 138703 solver.cpp:229] Train net output #1: loss = 4.42672 (* 1 = 4.42672 loss)
  1389. I0525 00:07:59.332023 138703 solver.cpp:489] Iteration 900, lr = 0.001
  1390. I0525 00:09:14.687733 138703 solver.cpp:214] Iteration 920, loss = 4.51494
  1391. I0525 00:09:14.687878 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1392. I0525 00:09:14.687901 138703 solver.cpp:229] Train net output #1: loss = 4.51494 (* 1 = 4.51494 loss)
  1393. I0525 00:09:14.687922 138703 solver.cpp:489] Iteration 920, lr = 0.001
  1394. I0525 00:10:27.611666 138703 solver.cpp:214] Iteration 940, loss = 4.51017
  1395. I0525 00:10:27.611806 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1396. I0525 00:10:27.611831 138703 solver.cpp:229] Train net output #1: loss = 4.51017 (* 1 = 4.51017 loss)
  1397. I0525 00:10:27.611856 138703 solver.cpp:489] Iteration 940, lr = 0.001
  1398. I0525 00:11:35.376315 138703 solver.cpp:214] Iteration 960, loss = 4.57164
  1399. I0525 00:11:35.380475 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1400. I0525 00:11:35.380494 138703 solver.cpp:229] Train net output #1: loss = 4.57164 (* 1 = 4.57164 loss)
  1401. I0525 00:11:35.380508 138703 solver.cpp:489] Iteration 960, lr = 0.001
  1402. I0525 00:12:50.412984 138703 solver.cpp:214] Iteration 980, loss = 4.37572
  1403. I0525 00:12:50.413127 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1404. I0525 00:12:50.413146 138703 solver.cpp:229] Train net output #1: loss = 4.37572 (* 1 = 4.37572 loss)
  1405. I0525 00:12:50.413161 138703 solver.cpp:489] Iteration 980, lr = 0.001
  1406. I0525 00:13:52.629767 138703 solver.cpp:291] Iteration 1000, Testing net (#0)
  1407. I0525 00:16:33.598321 138703 solver.cpp:340] Test net output #0: accuracy = 0.015625
  1408. I0525 00:16:33.598459 138703 solver.cpp:340] Test net output #1: loss = 4.55309 (* 1 = 4.55309 loss)
  1409. I0525 00:16:36.048038 138703 solver.cpp:214] Iteration 1000, loss = 4.61699
  1410. I0525 00:16:36.048086 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1411. I0525 00:16:36.048099 138703 solver.cpp:229] Train net output #1: loss = 4.61699 (* 1 = 4.61699 loss)
  1412. I0525 00:16:36.048112 138703 solver.cpp:489] Iteration 1000, lr = 0.001
  1413. I0525 00:17:47.795863 138703 solver.cpp:214] Iteration 1020, loss = 4.58036
  1414. I0525 00:17:47.795991 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1415. I0525 00:17:47.796007 138703 solver.cpp:229] Train net output #1: loss = 4.58036 (* 1 = 4.58036 loss)
  1416. I0525 00:17:47.796021 138703 solver.cpp:489] Iteration 1020, lr = 0.001
  1417. I0525 00:18:56.244459 138703 solver.cpp:214] Iteration 1040, loss = 4.46653
  1418. I0525 00:18:56.244601 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1419. I0525 00:18:56.244618 138703 solver.cpp:229] Train net output #1: loss = 4.46653 (* 1 = 4.46653 loss)
  1420. I0525 00:18:56.244632 138703 solver.cpp:489] Iteration 1040, lr = 0.001
  1421. I0525 00:20:09.922253 138703 solver.cpp:214] Iteration 1060, loss = 4.52868
  1422. I0525 00:20:09.922487 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1423. I0525 00:20:09.922504 138703 solver.cpp:229] Train net output #1: loss = 4.52868 (* 1 = 4.52868 loss)
  1424. I0525 00:20:09.922519 138703 solver.cpp:489] Iteration 1060, lr = 0.001
  1425. I0525 00:21:19.470921 138703 solver.cpp:214] Iteration 1080, loss = 4.53337
  1426. I0525 00:21:19.471060 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1427. I0525 00:21:19.471077 138703 solver.cpp:229] Train net output #1: loss = 4.53337 (* 1 = 4.53337 loss)
  1428. I0525 00:21:19.471096 138703 solver.cpp:489] Iteration 1080, lr = 0.001
  1429. I0525 00:22:31.929456 138703 solver.cpp:291] Iteration 1100, Testing net (#0)
  1430. I0525 00:25:08.712357 138703 solver.cpp:340] Test net output #0: accuracy = 0.013125
  1431. I0525 00:25:08.712505 138703 solver.cpp:340] Test net output #1: loss = 4.49535 (* 1 = 4.49535 loss)
  1432. I0525 00:25:10.571182 138703 solver.cpp:214] Iteration 1100, loss = 4.4391
  1433. I0525 00:25:10.571233 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1434. I0525 00:25:10.571254 138703 solver.cpp:229] Train net output #1: loss = 4.4391 (* 1 = 4.4391 loss)
  1435. I0525 00:25:10.571274 138703 solver.cpp:489] Iteration 1100, lr = 0.001
  1436. I0525 00:26:27.851946 138703 solver.cpp:214] Iteration 1120, loss = 4.52023
  1437. I0525 00:26:27.852105 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1438. I0525 00:26:27.852123 138703 solver.cpp:229] Train net output #1: loss = 4.52023 (* 1 = 4.52023 loss)
  1439. I0525 00:26:27.852138 138703 solver.cpp:489] Iteration 1120, lr = 0.001
  1440. I0525 00:27:36.804314 138703 solver.cpp:214] Iteration 1140, loss = 4.51916
  1441. I0525 00:27:36.804466 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1442. I0525 00:27:36.804489 138703 solver.cpp:229] Train net output #1: loss = 4.51916 (* 1 = 4.51916 loss)
  1443. I0525 00:27:36.804508 138703 solver.cpp:489] Iteration 1140, lr = 0.001
  1444. I0525 00:28:46.844386 138703 solver.cpp:214] Iteration 1160, loss = 4.34574
  1445. I0525 00:28:46.845484 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1446. I0525 00:28:46.845512 138703 solver.cpp:229] Train net output #1: loss = 4.34574 (* 1 = 4.34574 loss)
  1447. I0525 00:28:46.845535 138703 solver.cpp:489] Iteration 1160, lr = 0.001
  1448. I0525 00:30:03.469593 138703 solver.cpp:214] Iteration 1180, loss = 4.48789
  1449. I0525 00:30:03.469739 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1450. I0525 00:30:03.469765 138703 solver.cpp:229] Train net output #1: loss = 4.48789 (* 1 = 4.48789 loss)
  1451. I0525 00:30:03.469810 138703 solver.cpp:489] Iteration 1180, lr = 0.001
  1452. I0525 00:31:13.865722 138703 solver.cpp:291] Iteration 1200, Testing net (#0)
  1453. I0525 00:33:43.534761 138703 solver.cpp:340] Test net output #0: accuracy = 0.0172917
  1454. I0525 00:33:43.534917 138703 solver.cpp:340] Test net output #1: loss = 4.58847 (* 1 = 4.58847 loss)
  1455. I0525 00:33:45.966276 138703 solver.cpp:214] Iteration 1200, loss = 4.52573
  1456. I0525 00:33:45.966323 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1457. I0525 00:33:45.966338 138703 solver.cpp:229] Train net output #1: loss = 4.52573 (* 1 = 4.52573 loss)
  1458. I0525 00:33:45.966351 138703 solver.cpp:489] Iteration 1200, lr = 0.001
  1459. I0525 00:34:57.674051 138703 solver.cpp:214] Iteration 1220, loss = 4.58259
  1460. I0525 00:34:57.674221 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1461. I0525 00:34:57.674244 138703 solver.cpp:229] Train net output #1: loss = 4.58259 (* 1 = 4.58259 loss)
  1462. I0525 00:34:57.674263 138703 solver.cpp:489] Iteration 1220, lr = 0.001
  1463. I0525 00:36:08.014027 138703 solver.cpp:214] Iteration 1240, loss = 4.57311
  1464. I0525 00:36:08.014163 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1465. I0525 00:36:08.014188 138703 solver.cpp:229] Train net output #1: loss = 4.57311 (* 1 = 4.57311 loss)
  1466. I0525 00:36:08.014232 138703 solver.cpp:489] Iteration 1240, lr = 0.001
  1467. I0525 00:37:22.062667 138703 solver.cpp:214] Iteration 1260, loss = 4.65528
  1468. I0525 00:37:22.062799 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1469. I0525 00:37:22.062816 138703 solver.cpp:229] Train net output #1: loss = 4.65528 (* 1 = 4.65528 loss)
  1470. I0525 00:37:22.062829 138703 solver.cpp:489] Iteration 1260, lr = 0.001
  1471. I0525 00:38:37.726382 138703 solver.cpp:214] Iteration 1280, loss = 4.56766
  1472. I0525 00:38:37.726511 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1473. I0525 00:38:37.726527 138703 solver.cpp:229] Train net output #1: loss = 4.56766 (* 1 = 4.56766 loss)
  1474. I0525 00:38:37.726541 138703 solver.cpp:489] Iteration 1280, lr = 0.001
  1475. I0525 00:39:45.410914 138703 solver.cpp:291] Iteration 1300, Testing net (#0)
  1476. I0525 00:42:23.094606 138703 solver.cpp:340] Test net output #0: accuracy = 0.0202083
  1477. I0525 00:42:23.098400 138703 solver.cpp:340] Test net output #1: loss = 4.55479 (* 1 = 4.55479 loss)
  1478. I0525 00:42:24.970340 138703 solver.cpp:214] Iteration 1300, loss = 4.47431
  1479. I0525 00:42:24.970386 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  1480. I0525 00:42:24.970399 138703 solver.cpp:229] Train net output #1: loss = 4.47431 (* 1 = 4.47431 loss)
  1481. I0525 00:42:24.970413 138703 solver.cpp:489] Iteration 1300, lr = 0.001
  1482. I0525 00:43:35.592141 138703 solver.cpp:214] Iteration 1320, loss = 4.64956
  1483. I0525 00:43:35.594070 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1484. I0525 00:43:35.594097 138703 solver.cpp:229] Train net output #1: loss = 4.64956 (* 1 = 4.64956 loss)
  1485. I0525 00:43:35.594144 138703 solver.cpp:489] Iteration 1320, lr = 0.001
  1486. I0525 00:44:46.887776 138703 solver.cpp:214] Iteration 1340, loss = 4.65341
  1487. I0525 00:44:46.887923 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1488. I0525 00:44:46.887943 138703 solver.cpp:229] Train net output #1: loss = 4.65341 (* 1 = 4.65341 loss)
  1489. I0525 00:44:46.887961 138703 solver.cpp:489] Iteration 1340, lr = 0.001
  1490. I0525 00:46:00.767623 138703 solver.cpp:214] Iteration 1360, loss = 4.47019
  1491. I0525 00:46:00.767767 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1492. I0525 00:46:00.767786 138703 solver.cpp:229] Train net output #1: loss = 4.47019 (* 1 = 4.47019 loss)
  1493. I0525 00:46:00.767798 138703 solver.cpp:489] Iteration 1360, lr = 0.001
  1494. I0525 00:47:10.439981 138703 solver.cpp:214] Iteration 1380, loss = 4.5828
  1495. I0525 00:47:10.440099 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1496. I0525 00:47:10.440114 138703 solver.cpp:229] Train net output #1: loss = 4.5828 (* 1 = 4.5828 loss)
  1497. I0525 00:47:10.440127 138703 solver.cpp:489] Iteration 1380, lr = 0.001
  1498. I0525 00:48:22.766080 138703 solver.cpp:291] Iteration 1400, Testing net (#0)
  1499. I0525 00:50:48.162565 138703 solver.cpp:340] Test net output #0: accuracy = 0.0160417
  1500. I0525 00:50:48.162727 138703 solver.cpp:340] Test net output #1: loss = 4.63969 (* 1 = 4.63969 loss)
  1501. I0525 00:50:50.728652 138703 solver.cpp:214] Iteration 1400, loss = 4.61869
  1502. I0525 00:50:50.728711 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1503. I0525 00:50:50.728736 138703 solver.cpp:229] Train net output #1: loss = 4.61869 (* 1 = 4.61869 loss)
  1504. I0525 00:50:50.728754 138703 solver.cpp:489] Iteration 1400, lr = 0.001
  1505. I0525 00:52:03.206712 138703 solver.cpp:214] Iteration 1420, loss = 4.51125
  1506. I0525 00:52:03.206856 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1507. I0525 00:52:03.206879 138703 solver.cpp:229] Train net output #1: loss = 4.51125 (* 1 = 4.51125 loss)
  1508. I0525 00:52:03.206928 138703 solver.cpp:489] Iteration 1420, lr = 0.001
  1509. I0525 00:53:15.009591 138703 solver.cpp:214] Iteration 1440, loss = 4.52814
  1510. I0525 00:53:15.009732 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1511. I0525 00:53:15.009749 138703 solver.cpp:229] Train net output #1: loss = 4.52814 (* 1 = 4.52814 loss)
  1512. I0525 00:53:15.009763 138703 solver.cpp:489] Iteration 1440, lr = 0.001
  1513. I0525 00:54:27.070802 138703 solver.cpp:214] Iteration 1460, loss = 4.56297
  1514. I0525 00:54:27.070945 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1515. I0525 00:54:27.070961 138703 solver.cpp:229] Train net output #1: loss = 4.56297 (* 1 = 4.56297 loss)
  1516. I0525 00:54:27.070973 138703 solver.cpp:489] Iteration 1460, lr = 0.001
  1517. I0525 00:55:42.956086 138703 solver.cpp:214] Iteration 1480, loss = 4.43312
  1518. I0525 00:55:42.956223 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  1519. I0525 00:55:42.956248 138703 solver.cpp:229] Train net output #1: loss = 4.43312 (* 1 = 4.43312 loss)
  1520. I0525 00:55:42.956292 138703 solver.cpp:489] Iteration 1480, lr = 0.001
  1521. I0525 00:56:55.366313 138703 solver.cpp:291] Iteration 1500, Testing net (#0)
  1522. I0525 00:59:21.391888 138703 solver.cpp:340] Test net output #0: accuracy = 0.0195833
  1523. I0525 00:59:21.392038 138703 solver.cpp:340] Test net output #1: loss = 4.54221 (* 1 = 4.54221 loss)
  1524. I0525 00:59:23.832108 138703 solver.cpp:214] Iteration 1500, loss = 4.4653
  1525. I0525 00:59:23.832162 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1526. I0525 00:59:23.832177 138703 solver.cpp:229] Train net output #1: loss = 4.4653 (* 1 = 4.4653 loss)
  1527. I0525 00:59:23.832190 138703 solver.cpp:489] Iteration 1500, lr = 0.001
  1528. I0525 01:00:32.535977 138703 solver.cpp:214] Iteration 1520, loss = 4.38027
  1529. I0525 01:00:32.547319 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  1530. I0525 01:00:32.547348 138703 solver.cpp:229] Train net output #1: loss = 4.38027 (* 1 = 4.38027 loss)
  1531. I0525 01:00:32.547366 138703 solver.cpp:489] Iteration 1520, lr = 0.001
  1532. I0525 01:01:48.598873 138703 solver.cpp:214] Iteration 1540, loss = 4.56617
  1533. I0525 01:01:48.599025 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1534. I0525 01:01:48.599048 138703 solver.cpp:229] Train net output #1: loss = 4.56617 (* 1 = 4.56617 loss)
  1535. I0525 01:01:48.599066 138703 solver.cpp:489] Iteration 1540, lr = 0.001
  1536. I0525 01:03:04.521932 138703 solver.cpp:214] Iteration 1560, loss = 4.45605
  1537. I0525 01:03:04.522972 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1538. I0525 01:03:04.522992 138703 solver.cpp:229] Train net output #1: loss = 4.45605 (* 1 = 4.45605 loss)
  1539. I0525 01:03:04.523006 138703 solver.cpp:489] Iteration 1560, lr = 0.001
  1540. I0525 01:04:20.687165 138703 solver.cpp:214] Iteration 1580, loss = 4.56741
  1541. I0525 01:04:20.687324 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1542. I0525 01:04:20.687340 138703 solver.cpp:229] Train net output #1: loss = 4.56741 (* 1 = 4.56741 loss)
  1543. I0525 01:04:20.687355 138703 solver.cpp:489] Iteration 1580, lr = 0.001
  1544. I0525 01:05:25.001899 138703 solver.cpp:291] Iteration 1600, Testing net (#0)
  1545. I0525 01:07:48.994817 138703 solver.cpp:340] Test net output #0: accuracy = 0.0147917
  1546. I0525 01:07:48.994966 138703 solver.cpp:340] Test net output #1: loss = 4.56582 (* 1 = 4.56582 loss)
  1547. I0525 01:07:51.449589 138703 solver.cpp:214] Iteration 1600, loss = 4.51399
  1548. I0525 01:07:51.449640 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1549. I0525 01:07:51.449662 138703 solver.cpp:229] Train net output #1: loss = 4.51399 (* 1 = 4.51399 loss)
  1550. I0525 01:07:51.449679 138703 solver.cpp:489] Iteration 1600, lr = 0.001
  1551. I0525 01:09:07.355517 138703 solver.cpp:214] Iteration 1620, loss = 4.55552
  1552. I0525 01:09:07.355655 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1553. I0525 01:09:07.355675 138703 solver.cpp:229] Train net output #1: loss = 4.55552 (* 1 = 4.55552 loss)
  1554. I0525 01:09:07.355690 138703 solver.cpp:489] Iteration 1620, lr = 0.001
  1555. I0525 01:10:23.280748 138703 solver.cpp:214] Iteration 1640, loss = 4.45101
  1556. I0525 01:10:23.283078 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1557. I0525 01:10:23.283100 138703 solver.cpp:229] Train net output #1: loss = 4.45101 (* 1 = 4.45101 loss)
  1558. I0525 01:10:23.283154 138703 solver.cpp:489] Iteration 1640, lr = 0.001
  1559. I0525 01:11:38.962132 138703 solver.cpp:214] Iteration 1660, loss = 4.56799
  1560. I0525 01:11:38.962272 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1561. I0525 01:11:38.962291 138703 solver.cpp:229] Train net output #1: loss = 4.56799 (* 1 = 4.56799 loss)
  1562. I0525 01:11:38.962306 138703 solver.cpp:489] Iteration 1660, lr = 0.001
  1563. I0525 01:12:44.331730 138703 solver.cpp:214] Iteration 1680, loss = 4.50677
  1564. I0525 01:12:44.331874 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1565. I0525 01:12:44.331892 138703 solver.cpp:229] Train net output #1: loss = 4.50677 (* 1 = 4.50677 loss)
  1566. I0525 01:12:44.331905 138703 solver.cpp:489] Iteration 1680, lr = 0.001
  1567. I0525 01:13:55.904884 138703 solver.cpp:291] Iteration 1700, Testing net (#0)
  1568. I0525 01:16:31.576457 138703 solver.cpp:340] Test net output #0: accuracy = 0.0183333
  1569. I0525 01:16:31.579006 138703 solver.cpp:340] Test net output #1: loss = 4.53831 (* 1 = 4.53831 loss)
  1570. I0525 01:16:34.009817 138703 solver.cpp:214] Iteration 1700, loss = 4.53167
  1571. I0525 01:16:34.009872 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1572. I0525 01:16:34.009892 138703 solver.cpp:229] Train net output #1: loss = 4.53167 (* 1 = 4.53167 loss)
  1573. I0525 01:16:34.009910 138703 solver.cpp:489] Iteration 1700, lr = 0.001
  1574. I0525 01:17:49.910389 138703 solver.cpp:214] Iteration 1720, loss = 4.56963
  1575. I0525 01:17:49.910583 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1576. I0525 01:17:49.910600 138703 solver.cpp:229] Train net output #1: loss = 4.56963 (* 1 = 4.56963 loss)
  1577. I0525 01:17:49.910616 138703 solver.cpp:489] Iteration 1720, lr = 0.001
  1578. I0525 01:19:05.345921 138703 solver.cpp:214] Iteration 1740, loss = 4.52133
  1579. I0525 01:19:05.346078 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1580. I0525 01:19:05.346096 138703 solver.cpp:229] Train net output #1: loss = 4.52133 (* 1 = 4.52133 loss)
  1581. I0525 01:19:05.346110 138703 solver.cpp:489] Iteration 1740, lr = 0.001
  1582. I0525 01:20:05.603137 138703 solver.cpp:214] Iteration 1760, loss = 4.56245
  1583. I0525 01:20:05.603297 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1584. I0525 01:20:05.603322 138703 solver.cpp:229] Train net output #1: loss = 4.56245 (* 1 = 4.56245 loss)
  1585. I0525 01:20:05.603365 138703 solver.cpp:489] Iteration 1760, lr = 0.001
  1586. I0525 01:21:21.453423 138703 solver.cpp:214] Iteration 1780, loss = 4.51709
  1587. I0525 01:21:21.453629 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1588. I0525 01:21:21.453660 138703 solver.cpp:229] Train net output #1: loss = 4.51709 (* 1 = 4.51709 loss)
  1589. I0525 01:21:21.453686 138703 solver.cpp:489] Iteration 1780, lr = 0.001
  1590. I0525 01:22:26.379731 138703 solver.cpp:291] Iteration 1800, Testing net (#0)
  1591. I0525 01:25:38.622720 138703 solver.cpp:340] Test net output #0: accuracy = 0.0179167
  1592. I0525 01:25:38.622869 138703 solver.cpp:340] Test net output #1: loss = 4.56401 (* 1 = 4.56401 loss)
  1593. I0525 01:25:41.029026 138703 solver.cpp:214] Iteration 1800, loss = 4.57656
  1594. I0525 01:25:41.029075 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1595. I0525 01:25:41.029093 138703 solver.cpp:229] Train net output #1: loss = 4.57656 (* 1 = 4.57656 loss)
  1596. I0525 01:25:41.029112 138703 solver.cpp:489] Iteration 1800, lr = 0.001
  1597. I0525 01:26:40.902380 138703 solver.cpp:214] Iteration 1820, loss = 4.58177
  1598. I0525 01:26:40.902521 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1599. I0525 01:26:40.902539 138703 solver.cpp:229] Train net output #1: loss = 4.58177 (* 1 = 4.58177 loss)
  1600. I0525 01:26:40.902552 138703 solver.cpp:489] Iteration 1820, lr = 0.001
  1601. I0525 01:27:56.688695 138703 solver.cpp:214] Iteration 1840, loss = 4.50857
  1602. I0525 01:27:56.688863 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1603. I0525 01:27:56.688880 138703 solver.cpp:229] Train net output #1: loss = 4.50857 (* 1 = 4.50857 loss)
  1604. I0525 01:27:56.688894 138703 solver.cpp:489] Iteration 1840, lr = 0.001
  1605. I0525 01:29:04.915130 138703 solver.cpp:214] Iteration 1860, loss = 4.43603
  1606. I0525 01:29:04.915288 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1607. I0525 01:29:04.915313 138703 solver.cpp:229] Train net output #1: loss = 4.43603 (* 1 = 4.43603 loss)
  1608. I0525 01:29:04.915357 138703 solver.cpp:489] Iteration 1860, lr = 0.001
  1609. I0525 01:30:20.710374 138703 solver.cpp:214] Iteration 1880, loss = 4.56912
  1610. I0525 01:30:20.710543 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1611. I0525 01:30:20.710561 138703 solver.cpp:229] Train net output #1: loss = 4.56912 (* 1 = 4.56912 loss)
  1612. I0525 01:30:20.710574 138703 solver.cpp:489] Iteration 1880, lr = 0.001
  1613. I0525 01:31:32.922808 138703 solver.cpp:291] Iteration 1900, Testing net (#0)
  1614. I0525 01:34:46.213878 138703 solver.cpp:340] Test net output #0: accuracy = 0.0158333
  1615. I0525 01:34:46.214035 138703 solver.cpp:340] Test net output #1: loss = 4.56297 (* 1 = 4.56297 loss)
  1616. I0525 01:34:48.080605 138703 solver.cpp:214] Iteration 1900, loss = 4.57141
  1617. I0525 01:34:48.080644 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1618. I0525 01:34:48.080658 138703 solver.cpp:229] Train net output #1: loss = 4.57141 (* 1 = 4.57141 loss)
  1619. I0525 01:34:48.080672 138703 solver.cpp:489] Iteration 1900, lr = 0.001
  1620. I0525 01:36:02.826405 138703 solver.cpp:214] Iteration 1920, loss = 4.54422
  1621. I0525 01:36:02.826572 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1622. I0525 01:36:02.826592 138703 solver.cpp:229] Train net output #1: loss = 4.54422 (* 1 = 4.54422 loss)
  1623. I0525 01:36:02.826607 138703 solver.cpp:489] Iteration 1920, lr = 0.001
  1624. I0525 01:37:18.935154 138703 solver.cpp:214] Iteration 1940, loss = 4.48297
  1625. I0525 01:37:18.935348 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1626. I0525 01:37:18.935374 138703 solver.cpp:229] Train net output #1: loss = 4.48297 (* 1 = 4.48297 loss)
  1627. I0525 01:37:18.935421 138703 solver.cpp:489] Iteration 1940, lr = 0.001
  1628. I0525 01:38:35.030601 138703 solver.cpp:214] Iteration 1960, loss = 4.53258
  1629. I0525 01:38:35.030741 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1630. I0525 01:38:35.030758 138703 solver.cpp:229] Train net output #1: loss = 4.53258 (* 1 = 4.53258 loss)
  1631. I0525 01:38:35.030771 138703 solver.cpp:489] Iteration 1960, lr = 0.001
  1632. I0525 01:39:50.990685 138703 solver.cpp:214] Iteration 1980, loss = 4.42387
  1633. I0525 01:39:50.990835 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1634. I0525 01:39:50.990864 138703 solver.cpp:229] Train net output #1: loss = 4.42387 (* 1 = 4.42387 loss)
  1635. I0525 01:39:50.990882 138703 solver.cpp:489] Iteration 1980, lr = 0.001
  1636. I0525 01:41:00.481812 138703 solver.cpp:291] Iteration 2000, Testing net (#0)
  1637. I0525 01:44:15.303119 138703 solver.cpp:340] Test net output #0: accuracy = 0.0245833
  1638. I0525 01:44:15.303277 138703 solver.cpp:340] Test net output #1: loss = 4.58055 (* 1 = 4.58055 loss)
  1639. I0525 01:44:17.729007 138703 solver.cpp:214] Iteration 2000, loss = 4.47854
  1640. I0525 01:44:17.729054 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1641. I0525 01:44:17.729076 138703 solver.cpp:229] Train net output #1: loss = 4.47854 (* 1 = 4.47854 loss)
  1642. I0525 01:44:17.729094 138703 solver.cpp:489] Iteration 2000, lr = 0.001
  1643. I0525 01:45:33.603386 138703 solver.cpp:214] Iteration 2020, loss = 4.50137
  1644. I0525 01:45:33.603559 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1645. I0525 01:45:33.603585 138703 solver.cpp:229] Train net output #1: loss = 4.50137 (* 1 = 4.50137 loss)
  1646. I0525 01:45:33.603636 138703 solver.cpp:489] Iteration 2020, lr = 0.001
  1647. I0525 01:46:49.396117 138703 solver.cpp:214] Iteration 2040, loss = 4.51917
  1648. I0525 01:46:49.396273 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1649. I0525 01:46:49.396297 138703 solver.cpp:229] Train net output #1: loss = 4.51917 (* 1 = 4.51917 loss)
  1650. I0525 01:46:49.396319 138703 solver.cpp:489] Iteration 2040, lr = 0.001
  1651. I0525 01:48:01.358831 138703 solver.cpp:214] Iteration 2060, loss = 4.60905
  1652. I0525 01:48:01.358983 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1653. I0525 01:48:01.359006 138703 solver.cpp:229] Train net output #1: loss = 4.60905 (* 1 = 4.60905 loss)
  1654. I0525 01:48:01.359053 138703 solver.cpp:489] Iteration 2060, lr = 0.001
  1655. I0525 01:49:02.674679 138703 solver.cpp:214] Iteration 2080, loss = 4.58994
  1656. I0525 01:49:02.674834 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1657. I0525 01:49:02.674851 138703 solver.cpp:229] Train net output #1: loss = 4.58994 (* 1 = 4.58994 loss)
  1658. I0525 01:49:02.674866 138703 solver.cpp:489] Iteration 2080, lr = 0.001
  1659. I0525 01:50:12.610126 138703 solver.cpp:291] Iteration 2100, Testing net (#0)
  1660. I0525 01:53:27.545198 138703 solver.cpp:340] Test net output #0: accuracy = 0.0241667
  1661. I0525 01:53:27.545341 138703 solver.cpp:340] Test net output #1: loss = 4.54141 (* 1 = 4.54141 loss)
  1662. I0525 01:53:29.960755 138703 solver.cpp:214] Iteration 2100, loss = 4.52306
  1663. I0525 01:53:29.960809 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1664. I0525 01:53:29.960829 138703 solver.cpp:229] Train net output #1: loss = 4.52306 (* 1 = 4.52306 loss)
  1665. I0525 01:53:29.960846 138703 solver.cpp:489] Iteration 2100, lr = 0.001
  1666. I0525 01:54:42.363159 138703 solver.cpp:214] Iteration 2120, loss = 4.47706
  1667. I0525 01:54:42.363313 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1668. I0525 01:54:42.363337 138703 solver.cpp:229] Train net output #1: loss = 4.47706 (* 1 = 4.47706 loss)
  1669. I0525 01:54:42.363358 138703 solver.cpp:489] Iteration 2120, lr = 0.001
  1670. I0525 01:55:49.730764 138703 solver.cpp:214] Iteration 2140, loss = 4.54867
  1671. I0525 01:55:49.731006 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1672. I0525 01:55:49.731026 138703 solver.cpp:229] Train net output #1: loss = 4.54867 (* 1 = 4.54867 loss)
  1673. I0525 01:55:49.731040 138703 solver.cpp:489] Iteration 2140, lr = 0.001
  1674. I0525 01:56:58.915971 138703 solver.cpp:214] Iteration 2160, loss = 4.51479
  1675. I0525 01:56:58.916139 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1676. I0525 01:56:58.916164 138703 solver.cpp:229] Train net output #1: loss = 4.51479 (* 1 = 4.51479 loss)
  1677. I0525 01:56:58.916208 138703 solver.cpp:489] Iteration 2160, lr = 0.001
  1678. I0525 01:58:14.840296 138703 solver.cpp:214] Iteration 2180, loss = 4.49732
  1679. I0525 01:58:14.840448 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1680. I0525 01:58:14.840472 138703 solver.cpp:229] Train net output #1: loss = 4.49732 (* 1 = 4.49732 loss)
  1681. I0525 01:58:14.840515 138703 solver.cpp:489] Iteration 2180, lr = 0.001
  1682. I0525 01:59:27.283077 138703 solver.cpp:291] Iteration 2200, Testing net (#0)
  1683. I0525 02:02:45.518139 138703 solver.cpp:340] Test net output #0: accuracy = 0.0302083
  1684. I0525 02:02:45.518301 138703 solver.cpp:340] Test net output #1: loss = 4.56817 (* 1 = 4.56817 loss)
  1685. I0525 02:02:47.359557 138703 solver.cpp:214] Iteration 2200, loss = 4.52421
  1686. I0525 02:02:47.359622 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1687. I0525 02:02:47.359644 138703 solver.cpp:229] Train net output #1: loss = 4.52421 (* 1 = 4.52421 loss)
  1688. I0525 02:02:47.359664 138703 solver.cpp:489] Iteration 2200, lr = 0.001
  1689. I0525 02:03:57.754602 138703 solver.cpp:214] Iteration 2220, loss = 4.5109
  1690. I0525 02:03:57.754751 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1691. I0525 02:03:57.754770 138703 solver.cpp:229] Train net output #1: loss = 4.5109 (* 1 = 4.5109 loss)
  1692. I0525 02:03:57.754784 138703 solver.cpp:489] Iteration 2220, lr = 0.001
  1693. I0525 02:05:13.834183 138703 solver.cpp:214] Iteration 2240, loss = 4.55072
  1694. I0525 02:05:13.834321 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1695. I0525 02:05:13.834339 138703 solver.cpp:229] Train net output #1: loss = 4.55072 (* 1 = 4.55072 loss)
  1696. I0525 02:05:13.834352 138703 solver.cpp:489] Iteration 2240, lr = 0.001
  1697. I0525 02:06:29.902271 138703 solver.cpp:214] Iteration 2260, loss = 4.48998
  1698. I0525 02:06:29.902415 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1699. I0525 02:06:29.902434 138703 solver.cpp:229] Train net output #1: loss = 4.48998 (* 1 = 4.48998 loss)
  1700. I0525 02:06:29.902448 138703 solver.cpp:489] Iteration 2260, lr = 0.001
  1701. I0525 02:07:46.178768 138703 solver.cpp:214] Iteration 2280, loss = 4.57835
  1702. I0525 02:07:46.178926 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1703. I0525 02:07:46.178953 138703 solver.cpp:229] Train net output #1: loss = 4.57835 (* 1 = 4.57835 loss)
  1704. I0525 02:07:46.178966 138703 solver.cpp:489] Iteration 2280, lr = 0.001
  1705. I0525 02:08:54.371337 138703 solver.cpp:291] Iteration 2300, Testing net (#0)
  1706. I0525 02:12:14.312881 138703 solver.cpp:340] Test net output #0: accuracy = 0.0239583
  1707. I0525 02:12:14.313040 138703 solver.cpp:340] Test net output #1: loss = 4.54183 (* 1 = 4.54183 loss)
  1708. I0525 02:12:16.760776 138703 solver.cpp:214] Iteration 2300, loss = 4.4726
  1709. I0525 02:12:16.760823 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1710. I0525 02:12:16.760838 138703 solver.cpp:229] Train net output #1: loss = 4.4726 (* 1 = 4.4726 loss)
  1711. I0525 02:12:16.760853 138703 solver.cpp:489] Iteration 2300, lr = 0.001
  1712. I0525 02:13:32.706811 138703 solver.cpp:214] Iteration 2320, loss = 4.58139
  1713. I0525 02:13:32.706970 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1714. I0525 02:13:32.706995 138703 solver.cpp:229] Train net output #1: loss = 4.58139 (* 1 = 4.58139 loss)
  1715. I0525 02:13:32.707036 138703 solver.cpp:489] Iteration 2320, lr = 0.001
  1716. I0525 02:14:45.607746 138703 solver.cpp:214] Iteration 2340, loss = 4.56137
  1717. I0525 02:14:45.607892 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1718. I0525 02:14:45.607908 138703 solver.cpp:229] Train net output #1: loss = 4.56137 (* 1 = 4.56137 loss)
  1719. I0525 02:14:45.607923 138703 solver.cpp:489] Iteration 2340, lr = 0.001
  1720. I0525 02:16:00.528825 138703 solver.cpp:214] Iteration 2360, loss = 4.39018
  1721. I0525 02:16:00.529026 138703 solver.cpp:229] Train net output #0: accuracy = 0.09375
  1722. I0525 02:16:00.529045 138703 solver.cpp:229] Train net output #1: loss = 4.39018 (* 1 = 4.39018 loss)
  1723. I0525 02:16:00.529059 138703 solver.cpp:489] Iteration 2360, lr = 0.001
  1724. I0525 02:17:05.658243 138703 solver.cpp:214] Iteration 2380, loss = 4.43442
  1725. I0525 02:17:05.658423 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1726. I0525 02:17:05.658447 138703 solver.cpp:229] Train net output #1: loss = 4.43442 (* 1 = 4.43442 loss)
  1727. I0525 02:17:05.658490 138703 solver.cpp:489] Iteration 2380, lr = 0.001
  1728. I0525 02:18:18.495470 138703 solver.cpp:291] Iteration 2400, Testing net (#0)
  1729. I0525 02:21:41.732513 138703 solver.cpp:340] Test net output #0: accuracy = 0.02125
  1730. I0525 02:21:41.732666 138703 solver.cpp:340] Test net output #1: loss = 4.56155 (* 1 = 4.56155 loss)
  1731. I0525 02:21:43.602489 138703 solver.cpp:214] Iteration 2400, loss = 4.61331
  1732. I0525 02:21:43.602531 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  1733. I0525 02:21:43.602545 138703 solver.cpp:229] Train net output #1: loss = 4.61331 (* 1 = 4.61331 loss)
  1734. I0525 02:21:43.602556 138703 solver.cpp:489] Iteration 2400, lr = 0.001
  1735. I0525 02:22:57.418709 138703 solver.cpp:214] Iteration 2420, loss = 4.51178
  1736. I0525 02:22:57.418869 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1737. I0525 02:22:57.418894 138703 solver.cpp:229] Train net output #1: loss = 4.51178 (* 1 = 4.51178 loss)
  1738. I0525 02:22:57.418910 138703 solver.cpp:489] Iteration 2420, lr = 0.001
  1739. I0525 02:23:58.408485 138703 solver.cpp:214] Iteration 2440, loss = 4.45853
  1740. I0525 02:23:58.408623 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1741. I0525 02:23:58.408638 138703 solver.cpp:229] Train net output #1: loss = 4.45853 (* 1 = 4.45853 loss)
  1742. I0525 02:23:58.408649 138703 solver.cpp:489] Iteration 2440, lr = 0.001
  1743. I0525 02:25:14.334852 138703 solver.cpp:214] Iteration 2460, loss = 4.54925
  1744. I0525 02:25:14.334997 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1745. I0525 02:25:14.335013 138703 solver.cpp:229] Train net output #1: loss = 4.54925 (* 1 = 4.54925 loss)
  1746. I0525 02:25:14.335026 138703 solver.cpp:489] Iteration 2460, lr = 0.001
  1747. I0525 02:26:30.176594 138703 solver.cpp:214] Iteration 2480, loss = 4.53004
  1748. I0525 02:26:30.176753 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1749. I0525 02:26:30.176769 138703 solver.cpp:229] Train net output #1: loss = 4.53004 (* 1 = 4.53004 loss)
  1750. I0525 02:26:30.176780 138703 solver.cpp:489] Iteration 2480, lr = 0.001
  1751. I0525 02:27:42.456341 138703 solver.cpp:291] Iteration 2500, Testing net (#0)
  1752. I0525 02:31:05.929014 138703 solver.cpp:340] Test net output #0: accuracy = 0.0195833
  1753. I0525 02:31:05.929296 138703 solver.cpp:340] Test net output #1: loss = 4.56941 (* 1 = 4.56941 loss)
  1754. I0525 02:31:08.346832 138703 solver.cpp:214] Iteration 2500, loss = 4.42783
  1755. I0525 02:31:08.346870 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1756. I0525 02:31:08.346889 138703 solver.cpp:229] Train net output #1: loss = 4.42783 (* 1 = 4.42783 loss)
  1757. I0525 02:31:08.346904 138703 solver.cpp:489] Iteration 2500, lr = 0.001
  1758. I0525 02:32:24.446811 138703 solver.cpp:214] Iteration 2520, loss = 4.51118
  1759. I0525 02:32:24.446952 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1760. I0525 02:32:24.446969 138703 solver.cpp:229] Train net output #1: loss = 4.51118 (* 1 = 4.51118 loss)
  1761. I0525 02:32:24.446980 138703 solver.cpp:489] Iteration 2520, lr = 0.001
  1762. I0525 02:33:40.344774 138703 solver.cpp:214] Iteration 2540, loss = 4.42855
  1763. I0525 02:33:40.344923 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1764. I0525 02:33:40.344938 138703 solver.cpp:229] Train net output #1: loss = 4.42855 (* 1 = 4.42855 loss)
  1765. I0525 02:33:40.344950 138703 solver.cpp:489] Iteration 2540, lr = 0.001
  1766. I0525 02:34:56.443496 138703 solver.cpp:214] Iteration 2560, loss = 4.47418
  1767. I0525 02:34:56.443671 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1768. I0525 02:34:56.443687 138703 solver.cpp:229] Train net output #1: loss = 4.47418 (* 1 = 4.47418 loss)
  1769. I0525 02:34:56.443699 138703 solver.cpp:489] Iteration 2560, lr = 0.001
  1770. I0525 02:36:05.603060 138703 solver.cpp:214] Iteration 2580, loss = 4.42431
  1771. I0525 02:36:05.603262 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1772. I0525 02:36:05.603301 138703 solver.cpp:229] Train net output #1: loss = 4.42431 (* 1 = 4.42431 loss)
  1773. I0525 02:36:05.603332 138703 solver.cpp:489] Iteration 2580, lr = 0.001
  1774. I0525 02:37:18.425850 138703 solver.cpp:291] Iteration 2600, Testing net (#0)
  1775. I0525 02:40:49.678155 138703 solver.cpp:340] Test net output #0: accuracy = 0.0227083
  1776. I0525 02:40:49.678313 138703 solver.cpp:340] Test net output #1: loss = 4.56412 (* 1 = 4.56412 loss)
  1777. I0525 02:40:52.110162 138703 solver.cpp:214] Iteration 2600, loss = 4.51113
  1778. I0525 02:40:52.110203 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1779. I0525 02:40:52.110215 138703 solver.cpp:229] Train net output #1: loss = 4.51113 (* 1 = 4.51113 loss)
  1780. I0525 02:40:52.110227 138703 solver.cpp:489] Iteration 2600, lr = 0.001
  1781. I0525 02:42:02.487453 138703 solver.cpp:214] Iteration 2620, loss = 4.50094
  1782. I0525 02:42:02.487582 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1783. I0525 02:42:02.487602 138703 solver.cpp:229] Train net output #1: loss = 4.50094 (* 1 = 4.50094 loss)
  1784. I0525 02:42:02.487618 138703 solver.cpp:489] Iteration 2620, lr = 0.001
  1785. I0525 02:43:18.043352 138703 solver.cpp:214] Iteration 2640, loss = 4.50764
  1786. I0525 02:43:18.043509 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1787. I0525 02:43:18.043525 138703 solver.cpp:229] Train net output #1: loss = 4.50764 (* 1 = 4.50764 loss)
  1788. I0525 02:43:18.043537 138703 solver.cpp:489] Iteration 2640, lr = 0.001
  1789. I0525 02:44:33.220499 138703 solver.cpp:214] Iteration 2660, loss = 4.55888
  1790. I0525 02:44:33.220636 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1791. I0525 02:44:33.220652 138703 solver.cpp:229] Train net output #1: loss = 4.55888 (* 1 = 4.55888 loss)
  1792. I0525 02:44:33.220664 138703 solver.cpp:489] Iteration 2660, lr = 0.001
  1793. I0525 02:45:32.268942 138703 solver.cpp:214] Iteration 2680, loss = 4.4949
  1794. I0525 02:45:32.269089 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1795. I0525 02:45:32.269105 138703 solver.cpp:229] Train net output #1: loss = 4.4949 (* 1 = 4.4949 loss)
  1796. I0525 02:45:32.269117 138703 solver.cpp:489] Iteration 2680, lr = 0.001
  1797. I0525 02:46:44.562526 138703 solver.cpp:291] Iteration 2700, Testing net (#0)
  1798. I0525 02:50:07.295030 138703 solver.cpp:340] Test net output #0: accuracy = 0.0247917
  1799. I0525 02:50:07.298858 138703 solver.cpp:340] Test net output #1: loss = 4.61029 (* 1 = 4.61029 loss)
  1800. I0525 02:50:09.749194 138703 solver.cpp:214] Iteration 2700, loss = 4.51589
  1801. I0525 02:50:09.749240 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1802. I0525 02:50:09.749258 138703 solver.cpp:229] Train net output #1: loss = 4.51589 (* 1 = 4.51589 loss)
  1803. I0525 02:50:09.749275 138703 solver.cpp:489] Iteration 2700, lr = 0.001
  1804. I0525 02:51:23.394902 138703 solver.cpp:214] Iteration 2720, loss = 4.59409
  1805. I0525 02:51:23.395046 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1806. I0525 02:51:23.395062 138703 solver.cpp:229] Train net output #1: loss = 4.59409 (* 1 = 4.59409 loss)
  1807. I0525 02:51:23.395074 138703 solver.cpp:489] Iteration 2720, lr = 0.001
  1808. I0525 02:52:26.835819 138703 solver.cpp:214] Iteration 2740, loss = 4.48119
  1809. I0525 02:52:26.835978 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  1810. I0525 02:52:26.836000 138703 solver.cpp:229] Train net output #1: loss = 4.48119 (* 1 = 4.48119 loss)
  1811. I0525 02:52:26.836016 138703 solver.cpp:489] Iteration 2740, lr = 0.001
  1812. I0525 02:53:42.412000 138703 solver.cpp:214] Iteration 2760, loss = 4.48469
  1813. I0525 02:53:42.412220 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  1814. I0525 02:53:42.412237 138703 solver.cpp:229] Train net output #1: loss = 4.48469 (* 1 = 4.48469 loss)
  1815. I0525 02:53:42.412250 138703 solver.cpp:489] Iteration 2760, lr = 0.001
  1816. I0525 02:54:58.287477 138703 solver.cpp:214] Iteration 2780, loss = 4.48366
  1817. I0525 02:54:58.287622 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1818. I0525 02:54:58.287645 138703 solver.cpp:229] Train net output #1: loss = 4.48366 (* 1 = 4.48366 loss)
  1819. I0525 02:54:58.287662 138703 solver.cpp:489] Iteration 2780, lr = 0.001
  1820. I0525 02:56:03.830713 138703 solver.cpp:291] Iteration 2800, Testing net (#0)
  1821. I0525 02:58:27.713640 138703 solver.cpp:340] Test net output #0: accuracy = 0.0158333
  1822. I0525 02:58:27.713794 138703 solver.cpp:340] Test net output #1: loss = 4.55342 (* 1 = 4.55342 loss)
  1823. I0525 02:58:29.539355 138703 solver.cpp:214] Iteration 2800, loss = 4.4879
  1824. I0525 02:58:29.539394 138703 solver.cpp:229] Train net output #0: accuracy = 0.078125
  1825. I0525 02:58:29.539407 138703 solver.cpp:229] Train net output #1: loss = 4.4879 (* 1 = 4.4879 loss)
  1826. I0525 02:58:29.539418 138703 solver.cpp:489] Iteration 2800, lr = 0.001
  1827. I0525 02:59:33.640107 138703 solver.cpp:214] Iteration 2820, loss = 4.50896
  1828. I0525 02:59:33.640249 138703 solver.cpp:229] Train net output #0: accuracy = 0.078125
  1829. I0525 02:59:33.640264 138703 solver.cpp:229] Train net output #1: loss = 4.50896 (* 1 = 4.50896 loss)
  1830. I0525 02:59:33.640275 138703 solver.cpp:489] Iteration 2820, lr = 0.001
  1831. I0525 03:00:49.237455 138703 solver.cpp:214] Iteration 2840, loss = 4.57942
  1832. I0525 03:00:49.237598 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1833. I0525 03:00:49.237613 138703 solver.cpp:229] Train net output #1: loss = 4.57942 (* 1 = 4.57942 loss)
  1834. I0525 03:00:49.237625 138703 solver.cpp:489] Iteration 2840, lr = 0.001
  1835. I0525 03:02:04.840292 138703 solver.cpp:214] Iteration 2860, loss = 4.46162
  1836. I0525 03:02:04.840445 138703 solver.cpp:229] Train net output #0: accuracy = 0.078125
  1837. I0525 03:02:04.840459 138703 solver.cpp:229] Train net output #1: loss = 4.46162 (* 1 = 4.46162 loss)
  1838. I0525 03:02:04.840471 138703 solver.cpp:489] Iteration 2860, lr = 0.001
  1839. I0525 03:03:14.596065 138703 solver.cpp:214] Iteration 2880, loss = 4.51776
  1840. I0525 03:03:14.596205 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1841. I0525 03:03:14.596220 138703 solver.cpp:229] Train net output #1: loss = 4.51776 (* 1 = 4.51776 loss)
  1842. I0525 03:03:14.596233 138703 solver.cpp:489] Iteration 2880, lr = 0.001
  1843. I0525 03:04:24.589535 138703 solver.cpp:291] Iteration 2900, Testing net (#0)
  1844. I0525 03:06:46.176502 138703 solver.cpp:340] Test net output #0: accuracy = 0.021875
  1845. I0525 03:06:46.176645 138703 solver.cpp:340] Test net output #1: loss = 4.54854 (* 1 = 4.54854 loss)
  1846. I0525 03:06:48.588659 138703 solver.cpp:214] Iteration 2900, loss = 4.47458
  1847. I0525 03:06:48.588702 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1848. I0525 03:06:48.588721 138703 solver.cpp:229] Train net output #1: loss = 4.47458 (* 1 = 4.47458 loss)
  1849. I0525 03:06:48.588737 138703 solver.cpp:489] Iteration 2900, lr = 0.001
  1850. I0525 03:08:04.165513 138703 solver.cpp:214] Iteration 2920, loss = 4.58019
  1851. I0525 03:08:04.165652 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1852. I0525 03:08:04.165673 138703 solver.cpp:229] Train net output #1: loss = 4.58019 (* 1 = 4.58019 loss)
  1853. I0525 03:08:04.165690 138703 solver.cpp:489] Iteration 2920, lr = 0.001
  1854. I0525 03:09:19.721463 138703 solver.cpp:214] Iteration 2940, loss = 4.4391
  1855. I0525 03:09:19.721619 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1856. I0525 03:09:19.721635 138703 solver.cpp:229] Train net output #1: loss = 4.4391 (* 1 = 4.4391 loss)
  1857. I0525 03:09:19.721659 138703 solver.cpp:489] Iteration 2940, lr = 0.001
  1858. I0525 03:10:28.319609 138703 solver.cpp:214] Iteration 2960, loss = 4.39921
  1859. I0525 03:10:28.319754 138703 solver.cpp:229] Train net output #0: accuracy = 0.09375
  1860. I0525 03:10:28.319769 138703 solver.cpp:229] Train net output #1: loss = 4.39921 (* 1 = 4.39921 loss)
  1861. I0525 03:10:28.319782 138703 solver.cpp:489] Iteration 2960, lr = 0.001
  1862. I0525 03:11:43.229575 138703 solver.cpp:214] Iteration 2980, loss = 4.40929
  1863. I0525 03:11:43.231017 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1864. I0525 03:11:43.231034 138703 solver.cpp:229] Train net output #1: loss = 4.40929 (* 1 = 4.40929 loss)
  1865. I0525 03:11:43.231047 138703 solver.cpp:489] Iteration 2980, lr = 0.001
  1866. I0525 03:12:50.647435 138703 solver.cpp:291] Iteration 3000, Testing net (#0)
  1867. I0525 03:15:13.809528 138703 solver.cpp:340] Test net output #0: accuracy = 0.0252083
  1868. I0525 03:15:13.813105 138703 solver.cpp:340] Test net output #1: loss = 4.55314 (* 1 = 4.55314 loss)
  1869. I0525 03:15:16.199261 138703 solver.cpp:214] Iteration 3000, loss = 4.58575
  1870. I0525 03:15:16.199304 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1871. I0525 03:15:16.199316 138703 solver.cpp:229] Train net output #1: loss = 4.58575 (* 1 = 4.58575 loss)
  1872. I0525 03:15:16.199327 138703 solver.cpp:489] Iteration 3000, lr = 0.001
  1873. I0525 03:16:31.027652 138703 solver.cpp:214] Iteration 3020, loss = 4.52076
  1874. I0525 03:16:31.027797 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1875. I0525 03:16:31.027813 138703 solver.cpp:229] Train net output #1: loss = 4.52076 (* 1 = 4.52076 loss)
  1876. I0525 03:16:31.027825 138703 solver.cpp:489] Iteration 3020, lr = 0.001
  1877. I0525 03:17:41.238294 138703 solver.cpp:214] Iteration 3040, loss = 4.58322
  1878. I0525 03:17:41.238443 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1879. I0525 03:17:41.238463 138703 solver.cpp:229] Train net output #1: loss = 4.58322 (* 1 = 4.58322 loss)
  1880. I0525 03:17:41.238481 138703 solver.cpp:489] Iteration 3040, lr = 0.001
  1881. I0525 03:18:56.162986 138703 solver.cpp:214] Iteration 3060, loss = 4.50576
  1882. I0525 03:18:56.163122 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1883. I0525 03:18:56.163143 138703 solver.cpp:229] Train net output #1: loss = 4.50576 (* 1 = 4.50576 loss)
  1884. I0525 03:18:56.163159 138703 solver.cpp:489] Iteration 3060, lr = 0.001
  1885. I0525 03:20:05.524755 138703 solver.cpp:214] Iteration 3080, loss = 4.44586
  1886. I0525 03:20:05.524893 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1887. I0525 03:20:05.524914 138703 solver.cpp:229] Train net output #1: loss = 4.44586 (* 1 = 4.44586 loss)
  1888. I0525 03:20:05.524932 138703 solver.cpp:489] Iteration 3080, lr = 0.001
  1889. I0525 03:21:14.180287 138703 solver.cpp:291] Iteration 3100, Testing net (#0)
  1890. I0525 03:23:36.665503 138703 solver.cpp:340] Test net output #0: accuracy = 0.0229167
  1891. I0525 03:23:36.665650 138703 solver.cpp:340] Test net output #1: loss = 4.51513 (* 1 = 4.51513 loss)
  1892. I0525 03:23:39.069859 138703 solver.cpp:214] Iteration 3100, loss = 4.58609
  1893. I0525 03:23:39.069898 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1894. I0525 03:23:39.069911 138703 solver.cpp:229] Train net output #1: loss = 4.58609 (* 1 = 4.58609 loss)
  1895. I0525 03:23:39.069922 138703 solver.cpp:489] Iteration 3100, lr = 0.001
  1896. I0525 03:24:48.113682 138703 solver.cpp:214] Iteration 3120, loss = 4.47232
  1897. I0525 03:24:48.113819 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1898. I0525 03:24:48.113842 138703 solver.cpp:229] Train net output #1: loss = 4.47232 (* 1 = 4.47232 loss)
  1899. I0525 03:24:48.113860 138703 solver.cpp:489] Iteration 3120, lr = 0.001
  1900. I0525 03:26:03.129057 138703 solver.cpp:214] Iteration 3140, loss = 4.53637
  1901. I0525 03:26:03.129192 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1902. I0525 03:26:03.129215 138703 solver.cpp:229] Train net output #1: loss = 4.53637 (* 1 = 4.53637 loss)
  1903. I0525 03:26:03.129230 138703 solver.cpp:489] Iteration 3140, lr = 0.001
  1904. I0525 03:27:11.977581 138703 solver.cpp:214] Iteration 3160, loss = 4.42123
  1905. I0525 03:27:11.977747 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1906. I0525 03:27:11.977771 138703 solver.cpp:229] Train net output #1: loss = 4.42123 (* 1 = 4.42123 loss)
  1907. I0525 03:27:11.977788 138703 solver.cpp:489] Iteration 3160, lr = 0.001
  1908. I0525 03:28:25.949123 138703 solver.cpp:214] Iteration 3180, loss = 4.51332
  1909. I0525 03:28:25.949312 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1910. I0525 03:28:25.949336 138703 solver.cpp:229] Train net output #1: loss = 4.51332 (* 1 = 4.51332 loss)
  1911. I0525 03:28:25.949353 138703 solver.cpp:489] Iteration 3180, lr = 0.001
  1912. I0525 03:29:28.870803 138703 solver.cpp:291] Iteration 3200, Testing net (#0)
  1913. I0525 03:31:50.367566 138703 solver.cpp:340] Test net output #0: accuracy = 0.0195833
  1914. I0525 03:31:50.367723 138703 solver.cpp:340] Test net output #1: loss = 4.53519 (* 1 = 4.53519 loss)
  1915. I0525 03:31:52.143141 138703 solver.cpp:214] Iteration 3200, loss = 4.42615
  1916. I0525 03:31:52.143182 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1917. I0525 03:31:52.143195 138703 solver.cpp:229] Train net output #1: loss = 4.42615 (* 1 = 4.42615 loss)
  1918. I0525 03:31:52.143209 138703 solver.cpp:489] Iteration 3200, lr = 0.001
  1919. I0525 03:33:06.453732 138703 solver.cpp:214] Iteration 3220, loss = 4.47096
  1920. I0525 03:33:06.453874 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1921. I0525 03:33:06.453891 138703 solver.cpp:229] Train net output #1: loss = 4.47096 (* 1 = 4.47096 loss)
  1922. I0525 03:33:06.453902 138703 solver.cpp:489] Iteration 3220, lr = 0.001
  1923. I0525 03:34:16.458886 138703 solver.cpp:214] Iteration 3240, loss = 4.52258
  1924. I0525 03:34:16.459029 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1925. I0525 03:34:16.459045 138703 solver.cpp:229] Train net output #1: loss = 4.52258 (* 1 = 4.52258 loss)
  1926. I0525 03:34:16.459059 138703 solver.cpp:489] Iteration 3240, lr = 0.001
  1927. I0525 03:35:30.061530 138703 solver.cpp:214] Iteration 3260, loss = 4.51843
  1928. I0525 03:35:30.061664 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1929. I0525 03:35:30.061679 138703 solver.cpp:229] Train net output #1: loss = 4.51843 (* 1 = 4.51843 loss)
  1930. I0525 03:35:30.061691 138703 solver.cpp:489] Iteration 3260, lr = 0.001
  1931. I0525 03:36:32.518693 138703 solver.cpp:214] Iteration 3280, loss = 4.47318
  1932. I0525 03:36:32.518836 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1933. I0525 03:36:32.518851 138703 solver.cpp:229] Train net output #1: loss = 4.47318 (* 1 = 4.47318 loss)
  1934. I0525 03:36:32.518864 138703 solver.cpp:489] Iteration 3280, lr = 0.001
  1935. I0525 03:37:43.899104 138703 solver.cpp:291] Iteration 3300, Testing net (#0)
  1936. I0525 03:40:07.081544 138703 solver.cpp:340] Test net output #0: accuracy = 0.0322917
  1937. I0525 03:40:07.084585 138703 solver.cpp:340] Test net output #1: loss = 4.47466 (* 1 = 4.47466 loss)
  1938. I0525 03:40:09.463973 138703 solver.cpp:214] Iteration 3300, loss = 4.41874
  1939. I0525 03:40:09.464031 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1940. I0525 03:40:09.464046 138703 solver.cpp:229] Train net output #1: loss = 4.41874 (* 1 = 4.41874 loss)
  1941. I0525 03:40:09.464057 138703 solver.cpp:489] Iteration 3300, lr = 0.001
  1942. I0525 03:41:20.158682 138703 solver.cpp:214] Iteration 3320, loss = 4.37814
  1943. I0525 03:41:20.158823 138703 solver.cpp:229] Train net output #0: accuracy = 0.078125
  1944. I0525 03:41:20.158836 138703 solver.cpp:229] Train net output #1: loss = 4.37814 (* 1 = 4.37814 loss)
  1945. I0525 03:41:20.158848 138703 solver.cpp:489] Iteration 3320, lr = 0.001
  1946. I0525 03:42:34.933823 138703 solver.cpp:214] Iteration 3340, loss = 4.5966
  1947. I0525 03:42:34.933974 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1948. I0525 03:42:34.933995 138703 solver.cpp:229] Train net output #1: loss = 4.5966 (* 1 = 4.5966 loss)
  1949. I0525 03:42:34.934010 138703 solver.cpp:489] Iteration 3340, lr = 0.001
  1950. I0525 03:43:44.739619 138703 solver.cpp:214] Iteration 3360, loss = 4.57539
  1951. I0525 03:43:44.739763 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  1952. I0525 03:43:44.739778 138703 solver.cpp:229] Train net output #1: loss = 4.57539 (* 1 = 4.57539 loss)
  1953. I0525 03:43:44.739789 138703 solver.cpp:489] Iteration 3360, lr = 0.001
  1954. I0525 03:44:54.716918 138703 solver.cpp:214] Iteration 3380, loss = 4.45601
  1955. I0525 03:44:54.720036 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1956. I0525 03:44:54.720130 138703 solver.cpp:229] Train net output #1: loss = 4.45601 (* 1 = 4.45601 loss)
  1957. I0525 03:44:54.720151 138703 solver.cpp:489] Iteration 3380, lr = 0.001
  1958. I0525 03:46:06.849257 138703 solver.cpp:291] Iteration 3400, Testing net (#0)
  1959. I0525 03:48:26.733415 138703 solver.cpp:340] Test net output #0: accuracy = 0.0202083
  1960. I0525 03:48:26.735174 138703 solver.cpp:340] Test net output #1: loss = 4.5671 (* 1 = 4.5671 loss)
  1961. I0525 03:48:28.520272 138703 solver.cpp:214] Iteration 3400, loss = 4.51
  1962. I0525 03:48:28.520315 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  1963. I0525 03:48:28.520328 138703 solver.cpp:229] Train net output #1: loss = 4.51 (* 1 = 4.51 loss)
  1964. I0525 03:48:28.520339 138703 solver.cpp:489] Iteration 3400, lr = 0.001
  1965. I0525 03:49:42.410174 138703 solver.cpp:214] Iteration 3420, loss = 4.47273
  1966. I0525 03:49:42.410326 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  1967. I0525 03:49:42.410347 138703 solver.cpp:229] Train net output #1: loss = 4.47273 (* 1 = 4.47273 loss)
  1968. I0525 03:49:42.410365 138703 solver.cpp:489] Iteration 3420, lr = 0.001
  1969. I0525 03:50:55.900243 138703 solver.cpp:214] Iteration 3440, loss = 4.52467
  1970. I0525 03:50:55.900394 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1971. I0525 03:50:55.900410 138703 solver.cpp:229] Train net output #1: loss = 4.52467 (* 1 = 4.52467 loss)
  1972. I0525 03:50:55.900430 138703 solver.cpp:489] Iteration 3440, lr = 0.001
  1973. I0525 03:52:03.875403 138703 solver.cpp:214] Iteration 3460, loss = 4.61589
  1974. I0525 03:52:03.875563 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1975. I0525 03:52:03.875583 138703 solver.cpp:229] Train net output #1: loss = 4.61589 (* 1 = 4.61589 loss)
  1976. I0525 03:52:03.875600 138703 solver.cpp:489] Iteration 3460, lr = 0.001
  1977. I0525 03:53:16.853581 138703 solver.cpp:214] Iteration 3480, loss = 4.45861
  1978. I0525 03:53:16.853706 138703 solver.cpp:229] Train net output #0: accuracy = 0
  1979. I0525 03:53:16.853720 138703 solver.cpp:229] Train net output #1: loss = 4.45861 (* 1 = 4.45861 loss)
  1980. I0525 03:53:16.853731 138703 solver.cpp:489] Iteration 3480, lr = 0.001
  1981. I0525 03:54:27.779789 138703 solver.cpp:291] Iteration 3500, Testing net (#0)
  1982. I0525 03:57:19.882102 138703 solver.cpp:340] Test net output #0: accuracy = 0.019375
  1983. I0525 03:57:19.882244 138703 solver.cpp:340] Test net output #1: loss = 4.60716 (* 1 = 4.60716 loss)
  1984. I0525 03:57:22.278534 138703 solver.cpp:214] Iteration 3500, loss = 4.52455
  1985. I0525 03:57:22.278586 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1986. I0525 03:57:22.278605 138703 solver.cpp:229] Train net output #1: loss = 4.52455 (* 1 = 4.52455 loss)
  1987. I0525 03:57:22.278623 138703 solver.cpp:489] Iteration 3500, lr = 0.001
  1988. I0525 03:58:31.064730 138703 solver.cpp:214] Iteration 3520, loss = 4.54087
  1989. I0525 03:58:31.067525 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1990. I0525 03:58:31.067549 138703 solver.cpp:229] Train net output #1: loss = 4.54087 (* 1 = 4.54087 loss)
  1991. I0525 03:58:31.067566 138703 solver.cpp:489] Iteration 3520, lr = 0.001
  1992. I0525 03:59:46.518481 138703 solver.cpp:214] Iteration 3540, loss = 4.50574
  1993. I0525 03:59:46.519824 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  1994. I0525 03:59:46.519840 138703 solver.cpp:229] Train net output #1: loss = 4.50574 (* 1 = 4.50574 loss)
  1995. I0525 03:59:46.519853 138703 solver.cpp:489] Iteration 3540, lr = 0.001
  1996. I0525 04:00:57.008713 138703 solver.cpp:214] Iteration 3560, loss = 4.43564
  1997. I0525 04:00:57.008857 138703 solver.cpp:229] Train net output #0: accuracy = 0.078125
  1998. I0525 04:00:57.008872 138703 solver.cpp:229] Train net output #1: loss = 4.43564 (* 1 = 4.43564 loss)
  1999. I0525 04:00:57.008884 138703 solver.cpp:489] Iteration 3560, lr = 0.001
  2000. I0525 04:02:12.869670 138703 solver.cpp:214] Iteration 3580, loss = 4.58715
  2001. I0525 04:02:12.869822 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2002. I0525 04:02:12.869837 138703 solver.cpp:229] Train net output #1: loss = 4.58715 (* 1 = 4.58715 loss)
  2003. I0525 04:02:12.869849 138703 solver.cpp:489] Iteration 3580, lr = 0.001
  2004. I0525 04:03:16.051816 138703 solver.cpp:291] Iteration 3600, Testing net (#0)
  2005. I0525 04:06:24.565240 138703 solver.cpp:340] Test net output #0: accuracy = 0.0183333
  2006. I0525 04:06:24.565397 138703 solver.cpp:340] Test net output #1: loss = 4.57573 (* 1 = 4.57573 loss)
  2007. I0525 04:06:27.050029 138703 solver.cpp:214] Iteration 3600, loss = 4.54975
  2008. I0525 04:06:27.050073 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2009. I0525 04:06:27.050086 138703 solver.cpp:229] Train net output #1: loss = 4.54975 (* 1 = 4.54975 loss)
  2010. I0525 04:06:27.050098 138703 solver.cpp:489] Iteration 3600, lr = 0.001
  2011. I0525 04:07:36.137786 138703 solver.cpp:214] Iteration 3620, loss = 4.48728
  2012. I0525 04:07:36.137944 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2013. I0525 04:07:36.137961 138703 solver.cpp:229] Train net output #1: loss = 4.48728 (* 1 = 4.48728 loss)
  2014. I0525 04:07:36.137974 138703 solver.cpp:489] Iteration 3620, lr = 0.001
  2015. I0525 04:08:51.097123 138703 solver.cpp:214] Iteration 3640, loss = 4.46684
  2016. I0525 04:08:51.100451 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2017. I0525 04:08:51.100472 138703 solver.cpp:229] Train net output #1: loss = 4.46684 (* 1 = 4.46684 loss)
  2018. I0525 04:08:51.100488 138703 solver.cpp:489] Iteration 3640, lr = 0.001
  2019. I0525 04:10:00.442756 138703 solver.cpp:214] Iteration 3660, loss = 4.45586
  2020. I0525 04:10:00.442896 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2021. I0525 04:10:00.442910 138703 solver.cpp:229] Train net output #1: loss = 4.45586 (* 1 = 4.45586 loss)
  2022. I0525 04:10:00.442922 138703 solver.cpp:489] Iteration 3660, lr = 0.001
  2023. I0525 04:11:15.266180 138703 solver.cpp:214] Iteration 3680, loss = 4.57161
  2024. I0525 04:11:15.266453 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2025. I0525 04:11:15.266517 138703 solver.cpp:229] Train net output #1: loss = 4.57161 (* 1 = 4.57161 loss)
  2026. I0525 04:11:15.266577 138703 solver.cpp:489] Iteration 3680, lr = 0.001
  2027. I0525 04:12:26.338496 138703 solver.cpp:291] Iteration 3700, Testing net (#0)
  2028. I0525 04:15:40.982499 138703 solver.cpp:340] Test net output #0: accuracy = 0.0214583
  2029. I0525 04:15:40.982650 138703 solver.cpp:340] Test net output #1: loss = 4.53632 (* 1 = 4.53632 loss)
  2030. I0525 04:15:43.484786 138703 solver.cpp:214] Iteration 3700, loss = 4.57166
  2031. I0525 04:15:43.484833 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2032. I0525 04:15:43.484850 138703 solver.cpp:229] Train net output #1: loss = 4.57166 (* 1 = 4.57166 loss)
  2033. I0525 04:15:43.484869 138703 solver.cpp:489] Iteration 3700, lr = 0.001
  2034. I0525 04:16:48.520201 138703 solver.cpp:214] Iteration 3720, loss = 4.51213
  2035. I0525 04:16:48.520360 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2036. I0525 04:16:48.520385 138703 solver.cpp:229] Train net output #1: loss = 4.51213 (* 1 = 4.51213 loss)
  2037. I0525 04:16:48.520401 138703 solver.cpp:489] Iteration 3720, lr = 0.001
  2038. I0525 04:18:03.352926 138703 solver.cpp:214] Iteration 3740, loss = 4.51042
  2039. I0525 04:18:03.353070 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2040. I0525 04:18:03.353085 138703 solver.cpp:229] Train net output #1: loss = 4.51042 (* 1 = 4.51042 loss)
  2041. I0525 04:18:03.353097 138703 solver.cpp:489] Iteration 3740, lr = 0.001
  2042. I0525 04:19:18.017220 138703 solver.cpp:214] Iteration 3760, loss = 4.6076
  2043. I0525 04:19:18.017382 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2044. I0525 04:19:18.017405 138703 solver.cpp:229] Train net output #1: loss = 4.6076 (* 1 = 4.6076 loss)
  2045. I0525 04:19:18.017421 138703 solver.cpp:489] Iteration 3760, lr = 0.001
  2046. I0525 04:20:22.393049 138703 solver.cpp:214] Iteration 3780, loss = 4.50863
  2047. I0525 04:20:22.393292 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2048. I0525 04:20:22.393309 138703 solver.cpp:229] Train net output #1: loss = 4.50863 (* 1 = 4.50863 loss)
  2049. I0525 04:20:22.393322 138703 solver.cpp:489] Iteration 3780, lr = 0.001
  2050. I0525 04:21:28.587635 138703 solver.cpp:291] Iteration 3800, Testing net (#0)
  2051. I0525 04:24:39.098008 138703 solver.cpp:340] Test net output #0: accuracy = 0.0170833
  2052. I0525 04:24:39.098157 138703 solver.cpp:340] Test net output #1: loss = 4.55833 (* 1 = 4.55833 loss)
  2053. I0525 04:24:41.479641 138703 solver.cpp:214] Iteration 3800, loss = 4.58705
  2054. I0525 04:24:41.479687 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2055. I0525 04:24:41.479704 138703 solver.cpp:229] Train net output #1: loss = 4.58705 (* 1 = 4.58705 loss)
  2056. I0525 04:24:41.479720 138703 solver.cpp:489] Iteration 3800, lr = 0.001
  2057. I0525 04:25:56.315296 138703 solver.cpp:214] Iteration 3820, loss = 4.58583
  2058. I0525 04:25:56.315443 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2059. I0525 04:25:56.315465 138703 solver.cpp:229] Train net output #1: loss = 4.58583 (* 1 = 4.58583 loss)
  2060. I0525 04:25:56.315482 138703 solver.cpp:489] Iteration 3820, lr = 0.001
  2061. I0525 04:27:02.543288 138703 solver.cpp:214] Iteration 3840, loss = 4.5552
  2062. I0525 04:27:02.543443 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2063. I0525 04:27:02.543463 138703 solver.cpp:229] Train net output #1: loss = 4.5552 (* 1 = 4.5552 loss)
  2064. I0525 04:27:02.543480 138703 solver.cpp:489] Iteration 3840, lr = 0.001
  2065. I0525 04:28:13.292919 138703 solver.cpp:214] Iteration 3860, loss = 4.52564
  2066. I0525 04:28:13.293077 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2067. I0525 04:28:13.293098 138703 solver.cpp:229] Train net output #1: loss = 4.52564 (* 1 = 4.52564 loss)
  2068. I0525 04:28:13.293114 138703 solver.cpp:489] Iteration 3860, lr = 0.001
  2069. I0525 04:29:28.081543 138703 solver.cpp:214] Iteration 3880, loss = 4.57978
  2070. I0525 04:29:28.081691 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2071. I0525 04:29:28.081712 138703 solver.cpp:229] Train net output #1: loss = 4.57978 (* 1 = 4.57978 loss)
  2072. I0525 04:29:28.081728 138703 solver.cpp:489] Iteration 3880, lr = 0.001
  2073. I0525 04:30:37.829910 138703 solver.cpp:291] Iteration 3900, Testing net (#0)
  2074. I0525 04:33:47.980387 138703 solver.cpp:340] Test net output #0: accuracy = 0.0247917
  2075. I0525 04:33:47.980561 138703 solver.cpp:340] Test net output #1: loss = 4.52568 (* 1 = 4.52568 loss)
  2076. I0525 04:33:49.777043 138703 solver.cpp:214] Iteration 3900, loss = 4.51685
  2077. I0525 04:33:49.777086 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2078. I0525 04:33:49.777096 138703 solver.cpp:229] Train net output #1: loss = 4.51685 (* 1 = 4.51685 loss)
  2079. I0525 04:33:49.777108 138703 solver.cpp:489] Iteration 3900, lr = 0.001
  2080. I0525 04:34:55.899673 138703 solver.cpp:214] Iteration 3920, loss = 4.51627
  2081. I0525 04:34:55.899845 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2082. I0525 04:34:55.899866 138703 solver.cpp:229] Train net output #1: loss = 4.51627 (* 1 = 4.51627 loss)
  2083. I0525 04:34:55.899884 138703 solver.cpp:489] Iteration 3920, lr = 0.001
  2084. I0525 04:36:10.663266 138703 solver.cpp:214] Iteration 3940, loss = 4.62058
  2085. I0525 04:36:10.663409 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2086. I0525 04:36:10.663424 138703 solver.cpp:229] Train net output #1: loss = 4.62058 (* 1 = 4.62058 loss)
  2087. I0525 04:36:10.663436 138703 solver.cpp:489] Iteration 3940, lr = 0.001
  2088. I0525 04:37:25.544198 138703 solver.cpp:214] Iteration 3960, loss = 4.47512
  2089. I0525 04:37:25.544338 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2090. I0525 04:37:25.544353 138703 solver.cpp:229] Train net output #1: loss = 4.47512 (* 1 = 4.47512 loss)
  2091. I0525 04:37:25.544365 138703 solver.cpp:489] Iteration 3960, lr = 0.001
  2092. I0525 04:38:36.128072 138703 solver.cpp:214] Iteration 3980, loss = 4.6092
  2093. I0525 04:38:36.128250 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2094. I0525 04:38:36.128267 138703 solver.cpp:229] Train net output #1: loss = 4.6092 (* 1 = 4.6092 loss)
  2095. I0525 04:38:36.128279 138703 solver.cpp:489] Iteration 3980, lr = 0.001
  2096. I0525 04:39:47.068346 138703 solver.cpp:291] Iteration 4000, Testing net (#0)
  2097. I0525 04:43:05.922168 138703 solver.cpp:340] Test net output #0: accuracy = 0.026875
  2098. I0525 04:43:05.922336 138703 solver.cpp:340] Test net output #1: loss = 4.53817 (* 1 = 4.53817 loss)
  2099. I0525 04:43:08.329025 138703 solver.cpp:214] Iteration 4000, loss = 4.50317
  2100. I0525 04:43:08.329071 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2101. I0525 04:43:08.329083 138703 solver.cpp:229] Train net output #1: loss = 4.50317 (* 1 = 4.50317 loss)
  2102. I0525 04:43:08.329095 138703 solver.cpp:489] Iteration 4000, lr = 0.001
  2103. I0525 04:44:17.585615 138703 solver.cpp:214] Iteration 4020, loss = 4.53538
  2104. I0525 04:44:17.585834 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2105. I0525 04:44:17.585855 138703 solver.cpp:229] Train net output #1: loss = 4.53538 (* 1 = 4.53538 loss)
  2106. I0525 04:44:17.585871 138703 solver.cpp:489] Iteration 4020, lr = 0.001
  2107. I0525 04:45:32.822679 138703 solver.cpp:214] Iteration 4040, loss = 4.50244
  2108. I0525 04:45:32.822819 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2109. I0525 04:45:32.822834 138703 solver.cpp:229] Train net output #1: loss = 4.50244 (* 1 = 4.50244 loss)
  2110. I0525 04:45:32.822846 138703 solver.cpp:489] Iteration 4040, lr = 0.001
  2111. I0525 04:46:47.753130 138703 solver.cpp:214] Iteration 4060, loss = 4.53842
  2112. I0525 04:46:47.753331 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2113. I0525 04:46:47.753360 138703 solver.cpp:229] Train net output #1: loss = 4.53842 (* 1 = 4.53842 loss)
  2114. I0525 04:46:47.753384 138703 solver.cpp:489] Iteration 4060, lr = 0.001
  2115. I0525 04:48:02.803966 138703 solver.cpp:214] Iteration 4080, loss = 4.48889
  2116. I0525 04:48:02.807013 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2117. I0525 04:48:02.807032 138703 solver.cpp:229] Train net output #1: loss = 4.48889 (* 1 = 4.48889 loss)
  2118. I0525 04:48:02.807045 138703 solver.cpp:489] Iteration 4080, lr = 0.001
  2119. I0525 04:48:59.052616 138703 solver.cpp:291] Iteration 4100, Testing net (#0)
  2120. I0525 04:52:16.976050 138703 solver.cpp:340] Test net output #0: accuracy = 0.0191667
  2121. I0525 04:52:16.976200 138703 solver.cpp:340] Test net output #1: loss = 4.59167 (* 1 = 4.59167 loss)
  2122. I0525 04:52:19.387976 138703 solver.cpp:214] Iteration 4100, loss = 4.61202
  2123. I0525 04:52:19.388021 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2124. I0525 04:52:19.388034 138703 solver.cpp:229] Train net output #1: loss = 4.61202 (* 1 = 4.61202 loss)
  2125. I0525 04:52:19.388047 138703 solver.cpp:489] Iteration 4100, lr = 0.001
  2126. I0525 04:53:34.265976 138703 solver.cpp:214] Iteration 4120, loss = 4.54875
  2127. I0525 04:53:34.266108 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2128. I0525 04:53:34.266124 138703 solver.cpp:229] Train net output #1: loss = 4.54875 (* 1 = 4.54875 loss)
  2129. I0525 04:53:34.266135 138703 solver.cpp:489] Iteration 4120, lr = 0.001
  2130. I0525 04:54:49.137459 138703 solver.cpp:214] Iteration 4140, loss = 4.55185
  2131. I0525 04:54:49.137601 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2132. I0525 04:54:49.137627 138703 solver.cpp:229] Train net output #1: loss = 4.55185 (* 1 = 4.55185 loss)
  2133. I0525 04:54:49.137639 138703 solver.cpp:489] Iteration 4140, lr = 0.001
  2134. I0525 04:55:52.729590 138703 solver.cpp:214] Iteration 4160, loss = 4.52841
  2135. I0525 04:55:52.729733 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2136. I0525 04:55:52.729748 138703 solver.cpp:229] Train net output #1: loss = 4.52841 (* 1 = 4.52841 loss)
  2137. I0525 04:55:52.729761 138703 solver.cpp:489] Iteration 4160, lr = 0.001
  2138. I0525 04:57:02.618226 138703 solver.cpp:214] Iteration 4180, loss = 4.49145
  2139. I0525 04:57:02.618386 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2140. I0525 04:57:02.618402 138703 solver.cpp:229] Train net output #1: loss = 4.49145 (* 1 = 4.49145 loss)
  2141. I0525 04:57:02.618414 138703 solver.cpp:489] Iteration 4180, lr = 0.001
  2142. I0525 04:58:08.553347 138703 solver.cpp:291] Iteration 4200, Testing net (#0)
  2143. I0525 05:01:29.728931 138703 solver.cpp:340] Test net output #0: accuracy = 0.0227083
  2144. I0525 05:01:29.729079 138703 solver.cpp:340] Test net output #1: loss = 4.54165 (* 1 = 4.54165 loss)
  2145. I0525 05:01:32.128955 138703 solver.cpp:214] Iteration 4200, loss = 4.53555
  2146. I0525 05:01:32.128999 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2147. I0525 05:01:32.129012 138703 solver.cpp:229] Train net output #1: loss = 4.53555 (* 1 = 4.53555 loss)
  2148. I0525 05:01:32.129024 138703 solver.cpp:489] Iteration 4200, lr = 0.001
  2149. I0525 05:02:43.796728 138703 solver.cpp:214] Iteration 4220, loss = 4.48476
  2150. I0525 05:02:43.796907 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2151. I0525 05:02:43.796929 138703 solver.cpp:229] Train net output #1: loss = 4.48476 (* 1 = 4.48476 loss)
  2152. I0525 05:02:43.796947 138703 solver.cpp:489] Iteration 4220, lr = 0.001
  2153. I0525 05:03:44.810313 138703 solver.cpp:214] Iteration 4240, loss = 4.55997
  2154. I0525 05:03:44.810474 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2155. I0525 05:03:44.810490 138703 solver.cpp:229] Train net output #1: loss = 4.55997 (* 1 = 4.55997 loss)
  2156. I0525 05:03:44.810503 138703 solver.cpp:489] Iteration 4240, lr = 0.001
  2157. I0525 05:04:52.403220 138703 solver.cpp:214] Iteration 4260, loss = 4.61192
  2158. I0525 05:04:52.403370 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2159. I0525 05:04:52.403386 138703 solver.cpp:229] Train net output #1: loss = 4.61192 (* 1 = 4.61192 loss)
  2160. I0525 05:04:52.403398 138703 solver.cpp:489] Iteration 4260, lr = 0.001
  2161. I0525 05:06:06.912132 138703 solver.cpp:214] Iteration 4280, loss = 4.42258
  2162. I0525 05:06:06.912304 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  2163. I0525 05:06:06.912328 138703 solver.cpp:229] Train net output #1: loss = 4.42258 (* 1 = 4.42258 loss)
  2164. I0525 05:06:06.912345 138703 solver.cpp:489] Iteration 4280, lr = 0.001
  2165. I0525 05:07:18.172860 138703 solver.cpp:291] Iteration 4300, Testing net (#0)
  2166. I0525 05:10:44.624944 138703 solver.cpp:340] Test net output #0: accuracy = 0.02875
  2167. I0525 05:10:44.625097 138703 solver.cpp:340] Test net output #1: loss = 4.53246 (* 1 = 4.53246 loss)
  2168. I0525 05:10:46.431995 138703 solver.cpp:214] Iteration 4300, loss = 4.516
  2169. I0525 05:10:46.432039 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2170. I0525 05:10:46.432055 138703 solver.cpp:229] Train net output #1: loss = 4.516 (* 1 = 4.516 loss)
  2171. I0525 05:10:46.432071 138703 solver.cpp:489] Iteration 4300, lr = 0.001
  2172. I0525 05:11:53.299417 138703 solver.cpp:214] Iteration 4320, loss = 4.47689
  2173. I0525 05:11:53.299576 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2174. I0525 05:11:53.299597 138703 solver.cpp:229] Train net output #1: loss = 4.47689 (* 1 = 4.47689 loss)
  2175. I0525 05:11:53.299613 138703 solver.cpp:489] Iteration 4320, lr = 0.001
  2176. I0525 05:13:07.847439 138703 solver.cpp:214] Iteration 4340, loss = 4.37423
  2177. I0525 05:13:07.847592 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  2178. I0525 05:13:07.847615 138703 solver.cpp:229] Train net output #1: loss = 4.37423 (* 1 = 4.37423 loss)
  2179. I0525 05:13:07.847632 138703 solver.cpp:489] Iteration 4340, lr = 0.001
  2180. I0525 05:14:22.775514 138703 solver.cpp:214] Iteration 4360, loss = 4.5803
  2181. I0525 05:14:22.775686 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2182. I0525 05:14:22.775702 138703 solver.cpp:229] Train net output #1: loss = 4.5803 (* 1 = 4.5803 loss)
  2183. I0525 05:14:22.775727 138703 solver.cpp:489] Iteration 4360, lr = 0.001
  2184. I0525 05:15:37.328052 138703 solver.cpp:214] Iteration 4380, loss = 4.55184
  2185. I0525 05:15:37.328198 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2186. I0525 05:15:37.328220 138703 solver.cpp:229] Train net output #1: loss = 4.55184 (* 1 = 4.55184 loss)
  2187. I0525 05:15:37.328264 138703 solver.cpp:489] Iteration 4380, lr = 0.001
  2188. I0525 05:16:49.222071 138703 solver.cpp:291] Iteration 4400, Testing net (#0)
  2189. I0525 05:20:24.477972 138703 solver.cpp:340] Test net output #0: accuracy = 0.025
  2190. I0525 05:20:24.478123 138703 solver.cpp:340] Test net output #1: loss = 4.53503 (* 1 = 4.53503 loss)
  2191. I0525 05:20:26.862479 138703 solver.cpp:214] Iteration 4400, loss = 4.43181
  2192. I0525 05:20:26.862524 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2193. I0525 05:20:26.862535 138703 solver.cpp:229] Train net output #1: loss = 4.43181 (* 1 = 4.43181 loss)
  2194. I0525 05:20:26.862546 138703 solver.cpp:489] Iteration 4400, lr = 0.001
  2195. I0525 05:21:41.562711 138703 solver.cpp:214] Iteration 4420, loss = 4.4657
  2196. I0525 05:21:41.562877 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2197. I0525 05:21:41.562898 138703 solver.cpp:229] Train net output #1: loss = 4.4657 (* 1 = 4.4657 loss)
  2198. I0525 05:21:41.562914 138703 solver.cpp:489] Iteration 4420, lr = 0.001
  2199. I0525 05:22:56.298763 138703 solver.cpp:214] Iteration 4440, loss = 4.57491
  2200. I0525 05:22:56.298976 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2201. I0525 05:22:56.298993 138703 solver.cpp:229] Train net output #1: loss = 4.57491 (* 1 = 4.57491 loss)
  2202. I0525 05:22:56.299007 138703 solver.cpp:489] Iteration 4440, lr = 0.001
  2203. I0525 05:24:04.852658 138703 solver.cpp:214] Iteration 4460, loss = 4.52683
  2204. I0525 05:24:04.852795 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2205. I0525 05:24:04.852816 138703 solver.cpp:229] Train net output #1: loss = 4.52683 (* 1 = 4.52683 loss)
  2206. I0525 05:24:04.852833 138703 solver.cpp:489] Iteration 4460, lr = 0.001
  2207. I0525 05:25:08.025321 138703 solver.cpp:214] Iteration 4480, loss = 4.58903
  2208. I0525 05:25:08.025470 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2209. I0525 05:25:08.025490 138703 solver.cpp:229] Train net output #1: loss = 4.58903 (* 1 = 4.58903 loss)
  2210. I0525 05:25:08.025506 138703 solver.cpp:489] Iteration 4480, lr = 0.001
  2211. I0525 05:26:19.039582 138703 solver.cpp:291] Iteration 4500, Testing net (#0)
  2212. I0525 05:29:22.184532 138703 solver.cpp:340] Test net output #0: accuracy = 0.0210417
  2213. I0525 05:29:22.192479 138703 solver.cpp:340] Test net output #1: loss = 4.53654 (* 1 = 4.53654 loss)
  2214. I0525 05:29:24.591929 138703 solver.cpp:214] Iteration 4500, loss = 4.528
  2215. I0525 05:29:24.591970 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2216. I0525 05:29:24.591984 138703 solver.cpp:229] Train net output #1: loss = 4.528 (* 1 = 4.528 loss)
  2217. I0525 05:29:24.591998 138703 solver.cpp:489] Iteration 4500, lr = 0.001
  2218. I0525 05:30:38.289711 138703 solver.cpp:214] Iteration 4520, loss = 4.49417
  2219. I0525 05:30:38.289865 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2220. I0525 05:30:38.289880 138703 solver.cpp:229] Train net output #1: loss = 4.49417 (* 1 = 4.49417 loss)
  2221. I0525 05:30:38.289891 138703 solver.cpp:489] Iteration 4520, lr = 0.001
  2222. I0525 05:31:42.092741 138703 solver.cpp:214] Iteration 4540, loss = 4.5236
  2223. I0525 05:31:42.095470 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2224. I0525 05:31:42.095485 138703 solver.cpp:229] Train net output #1: loss = 4.5236 (* 1 = 4.5236 loss)
  2225. I0525 05:31:42.095499 138703 solver.cpp:489] Iteration 4540, lr = 0.001
  2226. I0525 05:32:48.047351 138703 solver.cpp:214] Iteration 4560, loss = 4.51277
  2227. I0525 05:32:48.047507 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2228. I0525 05:32:48.047521 138703 solver.cpp:229] Train net output #1: loss = 4.51277 (* 1 = 4.51277 loss)
  2229. I0525 05:32:48.047534 138703 solver.cpp:489] Iteration 4560, lr = 0.001
  2230. I0525 05:34:02.929927 138703 solver.cpp:214] Iteration 4580, loss = 4.5051
  2231. I0525 05:34:02.930100 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2232. I0525 05:34:02.930114 138703 solver.cpp:229] Train net output #1: loss = 4.5051 (* 1 = 4.5051 loss)
  2233. I0525 05:34:02.930127 138703 solver.cpp:489] Iteration 4580, lr = 0.001
  2234. I0525 05:35:14.033216 138703 solver.cpp:291] Iteration 4600, Testing net (#0)
  2235. I0525 05:37:39.678338 138703 solver.cpp:340] Test net output #0: accuracy = 0.0222917
  2236. I0525 05:37:39.679903 138703 solver.cpp:340] Test net output #1: loss = 4.57315 (* 1 = 4.57315 loss)
  2237. I0525 05:37:41.494298 138703 solver.cpp:214] Iteration 4600, loss = 4.4979
  2238. I0525 05:37:41.494344 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2239. I0525 05:37:41.494357 138703 solver.cpp:229] Train net output #1: loss = 4.4979 (* 1 = 4.4979 loss)
  2240. I0525 05:37:41.494369 138703 solver.cpp:489] Iteration 4600, lr = 0.001
  2241. I0525 05:38:47.594224 138703 solver.cpp:214] Iteration 4620, loss = 4.60662
  2242. I0525 05:38:47.594401 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2243. I0525 05:38:47.594416 138703 solver.cpp:229] Train net output #1: loss = 4.60662 (* 1 = 4.60662 loss)
  2244. I0525 05:38:47.594429 138703 solver.cpp:489] Iteration 4620, lr = 0.001
  2245. I0525 05:39:48.079504 138703 solver.cpp:214] Iteration 4640, loss = 4.5202
  2246. I0525 05:39:48.079654 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2247. I0525 05:39:48.079671 138703 solver.cpp:229] Train net output #1: loss = 4.5202 (* 1 = 4.5202 loss)
  2248. I0525 05:39:48.079684 138703 solver.cpp:489] Iteration 4640, lr = 0.001
  2249. I0525 05:41:02.917750 138703 solver.cpp:214] Iteration 4660, loss = 4.48751
  2250. I0525 05:41:02.917913 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2251. I0525 05:41:02.917938 138703 solver.cpp:229] Train net output #1: loss = 4.48751 (* 1 = 4.48751 loss)
  2252. I0525 05:41:02.917979 138703 solver.cpp:489] Iteration 4660, lr = 0.001
  2253. I0525 05:42:17.849303 138703 solver.cpp:214] Iteration 4680, loss = 4.59259
  2254. I0525 05:42:17.849447 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2255. I0525 05:42:17.849462 138703 solver.cpp:229] Train net output #1: loss = 4.59259 (* 1 = 4.59259 loss)
  2256. I0525 05:42:17.849473 138703 solver.cpp:489] Iteration 4680, lr = 0.001
  2257. I0525 05:43:29.147689 138703 solver.cpp:291] Iteration 4700, Testing net (#0)
  2258. I0525 05:45:49.275059 138703 solver.cpp:340] Test net output #0: accuracy = 0.02625
  2259. I0525 05:45:49.275221 138703 solver.cpp:340] Test net output #1: loss = 4.56343 (* 1 = 4.56343 loss)
  2260. I0525 05:45:51.727818 138703 solver.cpp:214] Iteration 4700, loss = 4.56151
  2261. I0525 05:45:51.727864 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2262. I0525 05:45:51.727876 138703 solver.cpp:229] Train net output #1: loss = 4.56151 (* 1 = 4.56151 loss)
  2263. I0525 05:45:51.727888 138703 solver.cpp:489] Iteration 4700, lr = 0.001
  2264. I0525 05:46:49.357992 138703 solver.cpp:214] Iteration 4720, loss = 4.5545
  2265. I0525 05:46:49.358213 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2266. I0525 05:46:49.358239 138703 solver.cpp:229] Train net output #1: loss = 4.5545 (* 1 = 4.5545 loss)
  2267. I0525 05:46:49.358294 138703 solver.cpp:489] Iteration 4720, lr = 0.001
  2268. I0525 05:48:04.297294 138703 solver.cpp:214] Iteration 4740, loss = 4.52848
  2269. I0525 05:48:04.297453 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2270. I0525 05:48:04.297469 138703 solver.cpp:229] Train net output #1: loss = 4.52848 (* 1 = 4.52848 loss)
  2271. I0525 05:48:04.297482 138703 solver.cpp:489] Iteration 4740, lr = 0.001
  2272. I0525 05:49:19.325837 138703 solver.cpp:214] Iteration 4760, loss = 4.50292
  2273. I0525 05:49:19.326149 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2274. I0525 05:49:19.326191 138703 solver.cpp:229] Train net output #1: loss = 4.50292 (* 1 = 4.50292 loss)
  2275. I0525 05:49:19.326237 138703 solver.cpp:489] Iteration 4760, lr = 0.001
  2276. I0525 05:50:33.882391 138703 solver.cpp:214] Iteration 4780, loss = 4.37589
  2277. I0525 05:50:33.882529 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2278. I0525 05:50:33.882550 138703 solver.cpp:229] Train net output #1: loss = 4.37589 (* 1 = 4.37589 loss)
  2279. I0525 05:50:33.882568 138703 solver.cpp:489] Iteration 4780, lr = 0.001
  2280. I0525 05:51:45.217356 138703 solver.cpp:291] Iteration 4800, Testing net (#0)
  2281. I0525 05:54:07.798854 138703 solver.cpp:340] Test net output #0: accuracy = 0.0189583
  2282. I0525 05:54:07.799013 138703 solver.cpp:340] Test net output #1: loss = 4.54384 (* 1 = 4.54384 loss)
  2283. I0525 05:54:10.168756 138703 solver.cpp:214] Iteration 4800, loss = 4.64315
  2284. I0525 05:54:10.168802 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2285. I0525 05:54:10.168820 138703 solver.cpp:229] Train net output #1: loss = 4.64315 (* 1 = 4.64315 loss)
  2286. I0525 05:54:10.168838 138703 solver.cpp:489] Iteration 4800, lr = 0.001
  2287. I0525 05:55:24.670264 138703 solver.cpp:214] Iteration 4820, loss = 4.58402
  2288. I0525 05:55:24.672119 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2289. I0525 05:55:24.672138 138703 solver.cpp:229] Train net output #1: loss = 4.58402 (* 1 = 4.58402 loss)
  2290. I0525 05:55:24.672152 138703 solver.cpp:489] Iteration 4820, lr = 0.001
  2291. I0525 05:56:39.401916 138703 solver.cpp:214] Iteration 4840, loss = 4.66694
  2292. I0525 05:56:39.402081 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2293. I0525 05:56:39.402104 138703 solver.cpp:229] Train net output #1: loss = 4.66694 (* 1 = 4.66694 loss)
  2294. I0525 05:56:39.402122 138703 solver.cpp:489] Iteration 4840, lr = 0.001
  2295. I0525 05:57:54.172251 138703 solver.cpp:214] Iteration 4860, loss = 4.54252
  2296. I0525 05:57:54.172390 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2297. I0525 05:57:54.172418 138703 solver.cpp:229] Train net output #1: loss = 4.54252 (* 1 = 4.54252 loss)
  2298. I0525 05:57:54.172437 138703 solver.cpp:489] Iteration 4860, lr = 0.001
  2299. I0525 05:59:08.903770 138703 solver.cpp:214] Iteration 4880, loss = 4.54923
  2300. I0525 05:59:08.903915 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2301. I0525 05:59:08.903931 138703 solver.cpp:229] Train net output #1: loss = 4.54923 (* 1 = 4.54923 loss)
  2302. I0525 05:59:08.903944 138703 solver.cpp:489] Iteration 4880, lr = 0.001
  2303. I0525 06:00:15.715358 138703 solver.cpp:291] Iteration 4900, Testing net (#0)
  2304. I0525 06:02:39.400554 138703 solver.cpp:340] Test net output #0: accuracy = 0.0208333
  2305. I0525 06:02:39.400704 138703 solver.cpp:340] Test net output #1: loss = 4.53714 (* 1 = 4.53714 loss)
  2306. I0525 06:02:41.817493 138703 solver.cpp:214] Iteration 4900, loss = 4.55629
  2307. I0525 06:02:41.817536 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2308. I0525 06:02:41.817550 138703 solver.cpp:229] Train net output #1: loss = 4.55629 (* 1 = 4.55629 loss)
  2309. I0525 06:02:41.817562 138703 solver.cpp:489] Iteration 4900, lr = 0.001
  2310. I0525 06:03:56.713284 138703 solver.cpp:214] Iteration 4920, loss = 4.57565
  2311. I0525 06:03:56.713663 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2312. I0525 06:03:56.713686 138703 solver.cpp:229] Train net output #1: loss = 4.57565 (* 1 = 4.57565 loss)
  2313. I0525 06:03:56.713703 138703 solver.cpp:489] Iteration 4920, lr = 0.001
  2314. I0525 06:05:11.686767 138703 solver.cpp:214] Iteration 4940, loss = 4.64876
  2315. I0525 06:05:11.686916 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2316. I0525 06:05:11.686935 138703 solver.cpp:229] Train net output #1: loss = 4.64876 (* 1 = 4.64876 loss)
  2317. I0525 06:05:11.686952 138703 solver.cpp:489] Iteration 4940, lr = 0.001
  2318. I0525 06:06:26.970468 138703 solver.cpp:214] Iteration 4960, loss = 4.47955
  2319. I0525 06:06:26.970650 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2320. I0525 06:06:26.970669 138703 solver.cpp:229] Train net output #1: loss = 4.47955 (* 1 = 4.47955 loss)
  2321. I0525 06:06:26.970684 138703 solver.cpp:489] Iteration 4960, lr = 0.001
  2322. I0525 06:07:33.843013 138703 solver.cpp:214] Iteration 4980, loss = 4.54305
  2323. I0525 06:07:33.843153 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2324. I0525 06:07:33.843168 138703 solver.cpp:229] Train net output #1: loss = 4.54305 (* 1 = 4.54305 loss)
  2325. I0525 06:07:33.843180 138703 solver.cpp:489] Iteration 4980, lr = 0.001
  2326. I0525 06:08:30.261400 138703 solver.cpp:359] Snapshotting to /home/fe/anilil/miniconda2/lisa-caffe-public/examples/LRCN_activity_recognition/singleframe_flow/snaps/10f_v1_xmlinput__iter_5000.caffemodel
  2327. I0525 06:08:35.130925 138703 solver.cpp:367] Snapshotting solver state to /home/fe/anilil/miniconda2/lisa-caffe-public/examples/LRCN_activity_recognition/singleframe_flow/snaps/10f_v1_xmlinput__iter_5000.solverstate
  2328. I0525 06:08:35.740198 138703 solver.cpp:291] Iteration 5000, Testing net (#0)
  2329. I0525 06:10:57.051283 138703 solver.cpp:340] Test net output #0: accuracy = 0.0185417
  2330. I0525 06:10:57.051434 138703 solver.cpp:340] Test net output #1: loss = 4.52787 (* 1 = 4.52787 loss)
  2331. I0525 06:10:59.431982 138703 solver.cpp:214] Iteration 5000, loss = 4.50182
  2332. I0525 06:10:59.432035 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2333. I0525 06:10:59.432054 138703 solver.cpp:229] Train net output #1: loss = 4.50182 (* 1 = 4.50182 loss)
  2334. I0525 06:10:59.432070 138703 solver.cpp:489] Iteration 5000, lr = 0.001
  2335. I0525 06:12:14.448577 138703 solver.cpp:214] Iteration 5020, loss = 4.37115
  2336. I0525 06:12:14.448781 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2337. I0525 06:12:14.448803 138703 solver.cpp:229] Train net output #1: loss = 4.37115 (* 1 = 4.37115 loss)
  2338. I0525 06:12:14.448848 138703 solver.cpp:489] Iteration 5020, lr = 0.001
  2339. I0525 06:13:29.178825 138703 solver.cpp:214] Iteration 5040, loss = 4.50959
  2340. I0525 06:13:29.178999 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2341. I0525 06:13:29.179023 138703 solver.cpp:229] Train net output #1: loss = 4.50959 (* 1 = 4.50959 loss)
  2342. I0525 06:13:29.179040 138703 solver.cpp:489] Iteration 5040, lr = 0.001
  2343. I0525 06:14:39.664991 138703 solver.cpp:214] Iteration 5060, loss = 4.51436
  2344. I0525 06:14:39.665134 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2345. I0525 06:14:39.665149 138703 solver.cpp:229] Train net output #1: loss = 4.51436 (* 1 = 4.51436 loss)
  2346. I0525 06:14:39.665161 138703 solver.cpp:489] Iteration 5060, lr = 0.001
  2347. I0525 06:15:40.516952 138703 solver.cpp:214] Iteration 5080, loss = 4.5303
  2348. I0525 06:15:40.519166 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2349. I0525 06:15:40.519184 138703 solver.cpp:229] Train net output #1: loss = 4.5303 (* 1 = 4.5303 loss)
  2350. I0525 06:15:40.519198 138703 solver.cpp:489] Iteration 5080, lr = 0.001
  2351. I0525 06:16:51.324686 138703 solver.cpp:291] Iteration 5100, Testing net (#0)
  2352. I0525 06:19:11.759816 138703 solver.cpp:340] Test net output #0: accuracy = 0.0295833
  2353. I0525 06:19:11.759963 138703 solver.cpp:340] Test net output #1: loss = 4.54885 (* 1 = 4.54885 loss)
  2354. I0525 06:19:14.149734 138703 solver.cpp:214] Iteration 5100, loss = 4.54109
  2355. I0525 06:19:14.149780 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2356. I0525 06:19:14.149797 138703 solver.cpp:229] Train net output #1: loss = 4.54109 (* 1 = 4.54109 loss)
  2357. I0525 06:19:14.149816 138703 solver.cpp:489] Iteration 5100, lr = 0.001
  2358. I0525 06:20:29.086503 138703 solver.cpp:214] Iteration 5120, loss = 4.50266
  2359. I0525 06:20:29.086647 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2360. I0525 06:20:29.086660 138703 solver.cpp:229] Train net output #1: loss = 4.50266 (* 1 = 4.50266 loss)
  2361. I0525 06:20:29.086674 138703 solver.cpp:489] Iteration 5120, lr = 0.001
  2362. I0525 06:21:36.960954 138703 solver.cpp:214] Iteration 5140, loss = 4.54662
  2363. I0525 06:21:36.961104 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2364. I0525 06:21:36.961124 138703 solver.cpp:229] Train net output #1: loss = 4.54662 (* 1 = 4.54662 loss)
  2365. I0525 06:21:36.961140 138703 solver.cpp:489] Iteration 5140, lr = 0.001
  2366. I0525 06:22:39.498365 138703 solver.cpp:214] Iteration 5160, loss = 4.52419
  2367. I0525 06:22:39.500049 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2368. I0525 06:22:39.500066 138703 solver.cpp:229] Train net output #1: loss = 4.52419 (* 1 = 4.52419 loss)
  2369. I0525 06:22:39.500080 138703 solver.cpp:489] Iteration 5160, lr = 0.001
  2370. I0525 06:23:50.703809 138703 solver.cpp:214] Iteration 5180, loss = 4.56402
  2371. I0525 06:23:50.703953 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2372. I0525 06:23:50.703968 138703 solver.cpp:229] Train net output #1: loss = 4.56402 (* 1 = 4.56402 loss)
  2373. I0525 06:23:50.703979 138703 solver.cpp:489] Iteration 5180, lr = 0.001
  2374. I0525 06:25:01.936489 138703 solver.cpp:291] Iteration 5200, Testing net (#0)
  2375. I0525 06:27:24.053227 138703 solver.cpp:340] Test net output #0: accuracy = 0.0270833
  2376. I0525 06:27:24.053380 138703 solver.cpp:340] Test net output #1: loss = 4.52687 (* 1 = 4.52687 loss)
  2377. I0525 06:27:26.431071 138703 solver.cpp:214] Iteration 5200, loss = 4.43702
  2378. I0525 06:27:26.431113 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2379. I0525 06:27:26.431126 138703 solver.cpp:229] Train net output #1: loss = 4.43702 (* 1 = 4.43702 loss)
  2380. I0525 06:27:26.431140 138703 solver.cpp:489] Iteration 5200, lr = 0.001
  2381. I0525 06:28:42.233597 138703 solver.cpp:214] Iteration 5220, loss = 4.50222
  2382. I0525 06:28:42.233788 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2383. I0525 06:28:42.233803 138703 solver.cpp:229] Train net output #1: loss = 4.50222 (* 1 = 4.50222 loss)
  2384. I0525 06:28:42.233816 138703 solver.cpp:489] Iteration 5220, lr = 0.001
  2385. I0525 06:29:41.511132 138703 solver.cpp:214] Iteration 5240, loss = 4.60892
  2386. I0525 06:29:41.511279 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2387. I0525 06:29:41.511294 138703 solver.cpp:229] Train net output #1: loss = 4.60892 (* 1 = 4.60892 loss)
  2388. I0525 06:29:41.511307 138703 solver.cpp:489] Iteration 5240, lr = 0.001
  2389. I0525 06:30:50.678798 138703 solver.cpp:214] Iteration 5260, loss = 4.65166
  2390. I0525 06:30:50.678954 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2391. I0525 06:30:50.678969 138703 solver.cpp:229] Train net output #1: loss = 4.65166 (* 1 = 4.65166 loss)
  2392. I0525 06:30:50.678982 138703 solver.cpp:489] Iteration 5260, lr = 0.001
  2393. I0525 06:32:05.479701 138703 solver.cpp:214] Iteration 5280, loss = 4.52183
  2394. I0525 06:32:05.479864 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2395. I0525 06:32:05.479884 138703 solver.cpp:229] Train net output #1: loss = 4.52183 (* 1 = 4.52183 loss)
  2396. I0525 06:32:05.479904 138703 solver.cpp:489] Iteration 5280, lr = 0.001
  2397. I0525 06:33:16.947041 138703 solver.cpp:291] Iteration 5300, Testing net (#0)
  2398. I0525 06:36:19.146414 138703 solver.cpp:340] Test net output #0: accuracy = 0.018125
  2399. I0525 06:36:19.146574 138703 solver.cpp:340] Test net output #1: loss = 4.56107 (* 1 = 4.56107 loss)
  2400. I0525 06:36:21.264744 138703 solver.cpp:214] Iteration 5300, loss = 4.50201
  2401. I0525 06:36:21.264782 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2402. I0525 06:36:21.264796 138703 solver.cpp:229] Train net output #1: loss = 4.50201 (* 1 = 4.50201 loss)
  2403. I0525 06:36:21.264808 138703 solver.cpp:489] Iteration 5300, lr = 0.001
  2404. I0525 06:37:28.710762 138703 solver.cpp:214] Iteration 5320, loss = 4.59289
  2405. I0525 06:37:28.710912 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2406. I0525 06:37:28.710927 138703 solver.cpp:229] Train net output #1: loss = 4.59289 (* 1 = 4.59289 loss)
  2407. I0525 06:37:28.710940 138703 solver.cpp:489] Iteration 5320, lr = 0.001
  2408. I0525 06:38:43.924567 138703 solver.cpp:214] Iteration 5340, loss = 4.4297
  2409. I0525 06:38:43.924718 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2410. I0525 06:38:43.924739 138703 solver.cpp:229] Train net output #1: loss = 4.4297 (* 1 = 4.4297 loss)
  2411. I0525 06:38:43.924757 138703 solver.cpp:489] Iteration 5340, lr = 0.001
  2412. I0525 06:39:59.031399 138703 solver.cpp:214] Iteration 5360, loss = 4.4589
  2413. I0525 06:39:59.031556 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2414. I0525 06:39:59.031579 138703 solver.cpp:229] Train net output #1: loss = 4.4589 (* 1 = 4.4589 loss)
  2415. I0525 06:39:59.031623 138703 solver.cpp:489] Iteration 5360, lr = 0.001
  2416. I0525 06:41:13.624346 138703 solver.cpp:214] Iteration 5380, loss = 4.47513
  2417. I0525 06:41:13.624487 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2418. I0525 06:41:13.624507 138703 solver.cpp:229] Train net output #1: loss = 4.47513 (* 1 = 4.47513 loss)
  2419. I0525 06:41:13.624526 138703 solver.cpp:489] Iteration 5380, lr = 0.001
  2420. I0525 06:42:24.811743 138703 solver.cpp:291] Iteration 5400, Testing net (#0)
  2421. I0525 06:45:36.476742 138703 solver.cpp:340] Test net output #0: accuracy = 0.0229167
  2422. I0525 06:45:36.476891 138703 solver.cpp:340] Test net output #1: loss = 4.57909 (* 1 = 4.57909 loss)
  2423. I0525 06:45:38.875957 138703 solver.cpp:214] Iteration 5400, loss = 4.56224
  2424. I0525 06:45:38.876001 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2425. I0525 06:45:38.876019 138703 solver.cpp:229] Train net output #1: loss = 4.56224 (* 1 = 4.56224 loss)
  2426. I0525 06:45:38.876036 138703 solver.cpp:489] Iteration 5400, lr = 0.001
  2427. I0525 06:46:54.058697 138703 solver.cpp:214] Iteration 5420, loss = 4.52903
  2428. I0525 06:46:54.058918 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2429. I0525 06:46:54.058943 138703 solver.cpp:229] Train net output #1: loss = 4.52903 (* 1 = 4.52903 loss)
  2430. I0525 06:46:54.058960 138703 solver.cpp:489] Iteration 5420, lr = 0.001
  2431. I0525 06:48:08.894518 138703 solver.cpp:214] Iteration 5440, loss = 4.5106
  2432. I0525 06:48:08.894686 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2433. I0525 06:48:08.894701 138703 solver.cpp:229] Train net output #1: loss = 4.5106 (* 1 = 4.5106 loss)
  2434. I0525 06:48:08.894714 138703 solver.cpp:489] Iteration 5440, lr = 0.001
  2435. I0525 06:49:23.730388 138703 solver.cpp:214] Iteration 5460, loss = 4.58083
  2436. I0525 06:49:23.730545 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2437. I0525 06:49:23.730561 138703 solver.cpp:229] Train net output #1: loss = 4.58083 (* 1 = 4.58083 loss)
  2438. I0525 06:49:23.730574 138703 solver.cpp:489] Iteration 5460, lr = 0.001
  2439. I0525 06:50:27.795828 138703 solver.cpp:214] Iteration 5480, loss = 4.50355
  2440. I0525 06:50:27.795970 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2441. I0525 06:50:27.795986 138703 solver.cpp:229] Train net output #1: loss = 4.50355 (* 1 = 4.50355 loss)
  2442. I0525 06:50:27.796006 138703 solver.cpp:489] Iteration 5480, lr = 0.001
  2443. I0525 06:51:26.050671 138703 solver.cpp:291] Iteration 5500, Testing net (#0)
  2444. I0525 06:54:33.070361 138703 solver.cpp:340] Test net output #0: accuracy = 0.0208333
  2445. I0525 06:54:33.071450 138703 solver.cpp:340] Test net output #1: loss = 4.53055 (* 1 = 4.53055 loss)
  2446. I0525 06:54:35.459981 138703 solver.cpp:214] Iteration 5500, loss = 4.55917
  2447. I0525 06:54:35.460024 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2448. I0525 06:54:35.460039 138703 solver.cpp:229] Train net output #1: loss = 4.55917 (* 1 = 4.55917 loss)
  2449. I0525 06:54:35.460052 138703 solver.cpp:489] Iteration 5500, lr = 0.001
  2450. I0525 06:55:50.632829 138703 solver.cpp:214] Iteration 5520, loss = 4.47095
  2451. I0525 06:55:50.632979 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2452. I0525 06:55:50.633000 138703 solver.cpp:229] Train net output #1: loss = 4.47095 (* 1 = 4.47095 loss)
  2453. I0525 06:55:50.633018 138703 solver.cpp:489] Iteration 5520, lr = 0.001
  2454. I0525 06:57:02.722693 138703 solver.cpp:214] Iteration 5540, loss = 4.56437
  2455. I0525 06:57:02.722841 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2456. I0525 06:57:02.722856 138703 solver.cpp:229] Train net output #1: loss = 4.56437 (* 1 = 4.56437 loss)
  2457. I0525 06:57:02.722867 138703 solver.cpp:489] Iteration 5540, lr = 0.001
  2458. I0525 06:58:03.122571 138703 solver.cpp:214] Iteration 5560, loss = 4.54946
  2459. I0525 06:58:03.122737 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  2460. I0525 06:58:03.122758 138703 solver.cpp:229] Train net output #1: loss = 4.54946 (* 1 = 4.54946 loss)
  2461. I0525 06:58:03.122776 138703 solver.cpp:489] Iteration 5560, lr = 0.001
  2462. I0525 06:59:17.875546 138703 solver.cpp:214] Iteration 5580, loss = 4.54341
  2463. I0525 06:59:17.875695 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2464. I0525 06:59:17.875717 138703 solver.cpp:229] Train net output #1: loss = 4.54341 (* 1 = 4.54341 loss)
  2465. I0525 06:59:17.875759 138703 solver.cpp:489] Iteration 5580, lr = 0.001
  2466. I0525 07:00:29.132448 138703 solver.cpp:291] Iteration 5600, Testing net (#0)
  2467. I0525 07:03:37.563722 138703 solver.cpp:340] Test net output #0: accuracy = 0.02375
  2468. I0525 07:03:37.563861 138703 solver.cpp:340] Test net output #1: loss = 4.53561 (* 1 = 4.53561 loss)
  2469. I0525 07:03:40.041558 138703 solver.cpp:214] Iteration 5600, loss = 4.40765
  2470. I0525 07:03:40.041602 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2471. I0525 07:03:40.041616 138703 solver.cpp:229] Train net output #1: loss = 4.40765 (* 1 = 4.40765 loss)
  2472. I0525 07:03:40.041628 138703 solver.cpp:489] Iteration 5600, lr = 0.001
  2473. I0525 07:04:39.709949 138703 solver.cpp:214] Iteration 5620, loss = 4.44479
  2474. I0525 07:04:39.710096 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2475. I0525 07:04:39.710111 138703 solver.cpp:229] Train net output #1: loss = 4.44479 (* 1 = 4.44479 loss)
  2476. I0525 07:04:39.710125 138703 solver.cpp:489] Iteration 5620, lr = 0.001
  2477. I0525 07:05:46.295150 138703 solver.cpp:214] Iteration 5640, loss = 4.51171
  2478. I0525 07:05:46.295380 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2479. I0525 07:05:46.295397 138703 solver.cpp:229] Train net output #1: loss = 4.51171 (* 1 = 4.51171 loss)
  2480. I0525 07:05:46.295409 138703 solver.cpp:489] Iteration 5640, lr = 0.001
  2481. I0525 07:07:01.197597 138703 solver.cpp:214] Iteration 5660, loss = 4.50632
  2482. I0525 07:07:01.197743 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2483. I0525 07:07:01.197765 138703 solver.cpp:229] Train net output #1: loss = 4.50632 (* 1 = 4.50632 loss)
  2484. I0525 07:07:01.197785 138703 solver.cpp:489] Iteration 5660, lr = 0.001
  2485. I0525 07:08:16.346174 138703 solver.cpp:214] Iteration 5680, loss = 4.46988
  2486. I0525 07:08:16.346303 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2487. I0525 07:08:16.346319 138703 solver.cpp:229] Train net output #1: loss = 4.46988 (* 1 = 4.46988 loss)
  2488. I0525 07:08:16.346333 138703 solver.cpp:489] Iteration 5680, lr = 0.001
  2489. I0525 07:09:27.565659 138703 solver.cpp:291] Iteration 5700, Testing net (#0)
  2490. I0525 07:12:42.310506 138703 solver.cpp:340] Test net output #0: accuracy = 0.0239583
  2491. I0525 07:12:42.310664 138703 solver.cpp:340] Test net output #1: loss = 4.54725 (* 1 = 4.54725 loss)
  2492. I0525 07:12:44.676211 138703 solver.cpp:214] Iteration 5700, loss = 4.527
  2493. I0525 07:12:44.676261 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2494. I0525 07:12:44.676276 138703 solver.cpp:229] Train net output #1: loss = 4.527 (* 1 = 4.527 loss)
  2495. I0525 07:12:44.676288 138703 solver.cpp:489] Iteration 5700, lr = 0.001
  2496. I0525 07:13:59.628170 138703 solver.cpp:214] Iteration 5720, loss = 4.53856
  2497. I0525 07:13:59.628327 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2498. I0525 07:13:59.628350 138703 solver.cpp:229] Train net output #1: loss = 4.53856 (* 1 = 4.53856 loss)
  2499. I0525 07:13:59.628368 138703 solver.cpp:489] Iteration 5720, lr = 0.001
  2500. I0525 07:15:14.351477 138703 solver.cpp:214] Iteration 5740, loss = 4.53609
  2501. I0525 07:15:14.351649 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2502. I0525 07:15:14.351673 138703 solver.cpp:229] Train net output #1: loss = 4.53609 (* 1 = 4.53609 loss)
  2503. I0525 07:15:14.351719 138703 solver.cpp:489] Iteration 5740, lr = 0.001
  2504. I0525 07:16:29.140153 138703 solver.cpp:214] Iteration 5760, loss = 4.59089
  2505. I0525 07:16:29.140293 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2506. I0525 07:16:29.140311 138703 solver.cpp:229] Train net output #1: loss = 4.59089 (* 1 = 4.59089 loss)
  2507. I0525 07:16:29.140322 138703 solver.cpp:489] Iteration 5760, lr = 0.001
  2508. I0525 07:17:40.792186 138703 solver.cpp:214] Iteration 5780, loss = 4.507
  2509. I0525 07:17:40.792325 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2510. I0525 07:17:40.792340 138703 solver.cpp:229] Train net output #1: loss = 4.507 (* 1 = 4.507 loss)
  2511. I0525 07:17:40.792352 138703 solver.cpp:489] Iteration 5780, lr = 0.001
  2512. I0525 07:18:46.863586 138703 solver.cpp:291] Iteration 5800, Testing net (#0)
  2513. I0525 07:22:00.484335 138703 solver.cpp:340] Test net output #0: accuracy = 0.0202083
  2514. I0525 07:22:00.484493 138703 solver.cpp:340] Test net output #1: loss = 4.5395 (* 1 = 4.5395 loss)
  2515. I0525 07:22:02.888182 138703 solver.cpp:214] Iteration 5800, loss = 4.53189
  2516. I0525 07:22:02.888226 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2517. I0525 07:22:02.888239 138703 solver.cpp:229] Train net output #1: loss = 4.53189 (* 1 = 4.53189 loss)
  2518. I0525 07:22:02.888252 138703 solver.cpp:489] Iteration 5800, lr = 0.001
  2519. I0525 07:23:17.793359 138703 solver.cpp:214] Iteration 5820, loss = 4.51769
  2520. I0525 07:23:17.793510 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2521. I0525 07:23:17.793534 138703 solver.cpp:229] Train net output #1: loss = 4.51769 (* 1 = 4.51769 loss)
  2522. I0525 07:23:17.793578 138703 solver.cpp:489] Iteration 5820, lr = 0.001
  2523. I0525 07:24:26.088575 138703 solver.cpp:214] Iteration 5840, loss = 4.52052
  2524. I0525 07:24:26.088740 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2525. I0525 07:24:26.088757 138703 solver.cpp:229] Train net output #1: loss = 4.52052 (* 1 = 4.52052 loss)
  2526. I0525 07:24:26.088770 138703 solver.cpp:489] Iteration 5840, lr = 0.001
  2527. I0525 07:25:36.774631 138703 solver.cpp:214] Iteration 5860, loss = 4.41747
  2528. I0525 07:25:36.774778 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2529. I0525 07:25:36.774794 138703 solver.cpp:229] Train net output #1: loss = 4.41747 (* 1 = 4.41747 loss)
  2530. I0525 07:25:36.774806 138703 solver.cpp:489] Iteration 5860, lr = 0.001
  2531. I0525 07:26:38.692656 138703 solver.cpp:214] Iteration 5880, loss = 4.55045
  2532. I0525 07:26:38.692975 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2533. I0525 07:26:38.692997 138703 solver.cpp:229] Train net output #1: loss = 4.55045 (* 1 = 4.55045 loss)
  2534. I0525 07:26:38.693040 138703 solver.cpp:489] Iteration 5880, lr = 0.001
  2535. I0525 07:27:49.734076 138703 solver.cpp:291] Iteration 5900, Testing net (#0)
  2536. I0525 07:31:04.956200 138703 solver.cpp:340] Test net output #0: accuracy = 0.019375
  2537. I0525 07:31:04.956347 138703 solver.cpp:340] Test net output #1: loss = 4.58777 (* 1 = 4.58777 loss)
  2538. I0525 07:31:06.740265 138703 solver.cpp:214] Iteration 5900, loss = 4.39055
  2539. I0525 07:31:06.740305 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2540. I0525 07:31:06.740317 138703 solver.cpp:229] Train net output #1: loss = 4.39055 (* 1 = 4.39055 loss)
  2541. I0525 07:31:06.740331 138703 solver.cpp:489] Iteration 5900, lr = 0.001
  2542. I0525 07:32:14.269438 138703 solver.cpp:214] Iteration 5920, loss = 4.54
  2543. I0525 07:32:14.269583 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2544. I0525 07:32:14.269598 138703 solver.cpp:229] Train net output #1: loss = 4.54 (* 1 = 4.54 loss)
  2545. I0525 07:32:14.269611 138703 solver.cpp:489] Iteration 5920, lr = 0.001
  2546. I0525 07:33:17.167070 138703 solver.cpp:214] Iteration 5940, loss = 4.53309
  2547. I0525 07:33:17.167234 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2548. I0525 07:33:17.167250 138703 solver.cpp:229] Train net output #1: loss = 4.53309 (* 1 = 4.53309 loss)
  2549. I0525 07:33:17.167263 138703 solver.cpp:489] Iteration 5940, lr = 0.001
  2550. I0525 07:34:31.760926 138703 solver.cpp:214] Iteration 5960, loss = 4.54832
  2551. I0525 07:34:31.761065 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2552. I0525 07:34:31.761080 138703 solver.cpp:229] Train net output #1: loss = 4.54832 (* 1 = 4.54832 loss)
  2553. I0525 07:34:31.761093 138703 solver.cpp:489] Iteration 5960, lr = 0.001
  2554. I0525 07:35:48.443706 138703 solver.cpp:214] Iteration 5980, loss = 4.48838
  2555. I0525 07:35:48.443856 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2556. I0525 07:35:48.443871 138703 solver.cpp:229] Train net output #1: loss = 4.48838 (* 1 = 4.48838 loss)
  2557. I0525 07:35:48.443886 138703 solver.cpp:489] Iteration 5980, lr = 0.001
  2558. I0525 07:37:00.477303 138703 solver.cpp:291] Iteration 6000, Testing net (#0)
  2559. I0525 07:40:20.701479 138703 solver.cpp:340] Test net output #0: accuracy = 0.0214583
  2560. I0525 07:40:20.701611 138703 solver.cpp:340] Test net output #1: loss = 4.56037 (* 1 = 4.56037 loss)
  2561. I0525 07:40:22.612933 138703 solver.cpp:214] Iteration 6000, loss = 4.52741
  2562. I0525 07:40:22.612973 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2563. I0525 07:40:22.612985 138703 solver.cpp:229] Train net output #1: loss = 4.52741 (* 1 = 4.52741 loss)
  2564. I0525 07:40:22.612998 138703 solver.cpp:489] Iteration 6000, lr = 0.001
  2565. I0525 07:41:37.642537 138703 solver.cpp:214] Iteration 6020, loss = 4.63039
  2566. I0525 07:41:37.642691 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2567. I0525 07:41:37.642707 138703 solver.cpp:229] Train net output #1: loss = 4.63039 (* 1 = 4.63039 loss)
  2568. I0525 07:41:37.642720 138703 solver.cpp:489] Iteration 6020, lr = 0.001
  2569. I0525 07:42:52.307714 138703 solver.cpp:214] Iteration 6040, loss = 4.59176
  2570. I0525 07:42:52.307868 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2571. I0525 07:42:52.307884 138703 solver.cpp:229] Train net output #1: loss = 4.59176 (* 1 = 4.59176 loss)
  2572. I0525 07:42:52.307898 138703 solver.cpp:489] Iteration 6040, lr = 0.001
  2573. I0525 07:44:07.147286 138703 solver.cpp:214] Iteration 6060, loss = 4.51317
  2574. I0525 07:44:07.147471 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2575. I0525 07:44:07.147493 138703 solver.cpp:229] Train net output #1: loss = 4.51317 (* 1 = 4.51317 loss)
  2576. I0525 07:44:07.147511 138703 solver.cpp:489] Iteration 6060, lr = 0.001
  2577. I0525 07:45:15.317391 138703 solver.cpp:214] Iteration 6080, loss = 4.45396
  2578. I0525 07:45:15.317548 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2579. I0525 07:45:15.317569 138703 solver.cpp:229] Train net output #1: loss = 4.45396 (* 1 = 4.45396 loss)
  2580. I0525 07:45:15.317587 138703 solver.cpp:489] Iteration 6080, lr = 0.001
  2581. I0525 07:46:26.718737 138703 solver.cpp:291] Iteration 6100, Testing net (#0)
  2582. I0525 07:49:56.352484 138703 solver.cpp:340] Test net output #0: accuracy = 0.020625
  2583. I0525 07:49:56.354601 138703 solver.cpp:340] Test net output #1: loss = 4.55405 (* 1 = 4.55405 loss)
  2584. I0525 07:49:58.733495 138703 solver.cpp:214] Iteration 6100, loss = 4.55245
  2585. I0525 07:49:58.733535 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2586. I0525 07:49:58.733547 138703 solver.cpp:229] Train net output #1: loss = 4.55245 (* 1 = 4.55245 loss)
  2587. I0525 07:49:58.733561 138703 solver.cpp:489] Iteration 6100, lr = 0.001
  2588. I0525 07:51:05.974990 138703 solver.cpp:214] Iteration 6120, loss = 4.55246
  2589. I0525 07:51:05.976471 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2590. I0525 07:51:05.976495 138703 solver.cpp:229] Train net output #1: loss = 4.55246 (* 1 = 4.55246 loss)
  2591. I0525 07:51:05.976516 138703 solver.cpp:489] Iteration 6120, lr = 0.001
  2592. I0525 07:52:18.199671 138703 solver.cpp:214] Iteration 6140, loss = 4.54496
  2593. I0525 07:52:18.199833 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2594. I0525 07:52:18.199849 138703 solver.cpp:229] Train net output #1: loss = 4.54496 (* 1 = 4.54496 loss)
  2595. I0525 07:52:18.199862 138703 solver.cpp:489] Iteration 6140, lr = 0.001
  2596. I0525 07:53:33.192783 138703 solver.cpp:214] Iteration 6160, loss = 4.48573
  2597. I0525 07:53:33.192937 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2598. I0525 07:53:33.192952 138703 solver.cpp:229] Train net output #1: loss = 4.48573 (* 1 = 4.48573 loss)
  2599. I0525 07:53:33.192965 138703 solver.cpp:489] Iteration 6160, lr = 0.001
  2600. I0525 07:54:42.174556 138703 solver.cpp:214] Iteration 6180, loss = 4.56024
  2601. I0525 07:54:42.174722 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2602. I0525 07:54:42.174743 138703 solver.cpp:229] Train net output #1: loss = 4.56024 (* 1 = 4.56024 loss)
  2603. I0525 07:54:42.174759 138703 solver.cpp:489] Iteration 6180, lr = 0.001
  2604. I0525 07:55:42.096943 138703 solver.cpp:291] Iteration 6200, Testing net (#0)
  2605. I0525 07:59:05.508088 138703 solver.cpp:340] Test net output #0: accuracy = 0.0210417
  2606. I0525 07:59:05.508227 138703 solver.cpp:340] Test net output #1: loss = 4.56484 (* 1 = 4.56484 loss)
  2607. I0525 07:59:07.855175 138703 solver.cpp:214] Iteration 6200, loss = 4.56805
  2608. I0525 07:59:07.855217 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2609. I0525 07:59:07.855234 138703 solver.cpp:229] Train net output #1: loss = 4.56805 (* 1 = 4.56805 loss)
  2610. I0525 07:59:07.855250 138703 solver.cpp:489] Iteration 6200, lr = 0.001
  2611. I0525 08:00:22.741521 138703 solver.cpp:214] Iteration 6220, loss = 4.48731
  2612. I0525 08:00:22.741811 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2613. I0525 08:00:22.741835 138703 solver.cpp:229] Train net output #1: loss = 4.48731 (* 1 = 4.48731 loss)
  2614. I0525 08:00:22.741885 138703 solver.cpp:489] Iteration 6220, lr = 0.001
  2615. I0525 08:01:33.239858 138703 solver.cpp:214] Iteration 6240, loss = 4.51805
  2616. I0525 08:01:33.240002 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2617. I0525 08:01:33.240017 138703 solver.cpp:229] Train net output #1: loss = 4.51805 (* 1 = 4.51805 loss)
  2618. I0525 08:01:33.240031 138703 solver.cpp:489] Iteration 6240, lr = 0.001
  2619. I0525 08:02:32.282172 138703 solver.cpp:214] Iteration 6260, loss = 4.4501
  2620. I0525 08:02:32.282385 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2621. I0525 08:02:32.282402 138703 solver.cpp:229] Train net output #1: loss = 4.4501 (* 1 = 4.4501 loss)
  2622. I0525 08:02:32.282415 138703 solver.cpp:489] Iteration 6260, lr = 0.001
  2623. I0525 08:03:46.728653 138703 solver.cpp:214] Iteration 6280, loss = 4.46143
  2624. I0525 08:03:46.728976 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2625. I0525 08:03:46.728993 138703 solver.cpp:229] Train net output #1: loss = 4.46143 (* 1 = 4.46143 loss)
  2626. I0525 08:03:46.729007 138703 solver.cpp:489] Iteration 6280, lr = 0.001
  2627. I0525 08:04:53.792167 138703 solver.cpp:291] Iteration 6300, Testing net (#0)
  2628. I0525 08:07:40.150962 138703 solver.cpp:340] Test net output #0: accuracy = 0.021875
  2629. I0525 08:07:40.151108 138703 solver.cpp:340] Test net output #1: loss = 4.54132 (* 1 = 4.54132 loss)
  2630. I0525 08:07:42.529520 138703 solver.cpp:214] Iteration 6300, loss = 4.49163
  2631. I0525 08:07:42.529562 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2632. I0525 08:07:42.529577 138703 solver.cpp:229] Train net output #1: loss = 4.49163 (* 1 = 4.49163 loss)
  2633. I0525 08:07:42.529588 138703 solver.cpp:489] Iteration 6300, lr = 0.001
  2634. I0525 08:08:50.660090 138703 solver.cpp:214] Iteration 6320, loss = 4.49604
  2635. I0525 08:08:50.660244 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2636. I0525 08:08:50.660259 138703 solver.cpp:229] Train net output #1: loss = 4.49604 (* 1 = 4.49604 loss)
  2637. I0525 08:08:50.660274 138703 solver.cpp:489] Iteration 6320, lr = 0.001
  2638. I0525 08:09:52.524981 138703 solver.cpp:214] Iteration 6340, loss = 4.50144
  2639. I0525 08:09:52.525128 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2640. I0525 08:09:52.525144 138703 solver.cpp:229] Train net output #1: loss = 4.50144 (* 1 = 4.50144 loss)
  2641. I0525 08:09:52.525156 138703 solver.cpp:489] Iteration 6340, lr = 0.001
  2642. I0525 08:11:07.168030 138703 solver.cpp:214] Iteration 6360, loss = 4.68453
  2643. I0525 08:11:07.168182 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2644. I0525 08:11:07.168197 138703 solver.cpp:229] Train net output #1: loss = 4.68453 (* 1 = 4.68453 loss)
  2645. I0525 08:11:07.168210 138703 solver.cpp:489] Iteration 6360, lr = 0.001
  2646. I0525 08:12:13.819001 138703 solver.cpp:214] Iteration 6380, loss = 4.5199
  2647. I0525 08:12:13.819156 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2648. I0525 08:12:13.819172 138703 solver.cpp:229] Train net output #1: loss = 4.5199 (* 1 = 4.5199 loss)
  2649. I0525 08:12:13.819187 138703 solver.cpp:489] Iteration 6380, lr = 0.001
  2650. I0525 08:13:24.973242 138703 solver.cpp:291] Iteration 6400, Testing net (#0)
  2651. I0525 08:15:50.548199 138703 solver.cpp:340] Test net output #0: accuracy = 0.023125
  2652. I0525 08:15:50.548336 138703 solver.cpp:340] Test net output #1: loss = 4.59912 (* 1 = 4.59912 loss)
  2653. I0525 08:15:52.357312 138703 solver.cpp:214] Iteration 6400, loss = 4.58196
  2654. I0525 08:15:52.357357 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2655. I0525 08:15:52.357369 138703 solver.cpp:229] Train net output #1: loss = 4.58196 (* 1 = 4.58196 loss)
  2656. I0525 08:15:52.357383 138703 solver.cpp:489] Iteration 6400, lr = 0.001
  2657. I0525 08:16:49.967721 138703 solver.cpp:214] Iteration 6420, loss = 4.46966
  2658. I0525 08:16:49.967878 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2659. I0525 08:16:49.967900 138703 solver.cpp:229] Train net output #1: loss = 4.46966 (* 1 = 4.46966 loss)
  2660. I0525 08:16:49.967946 138703 solver.cpp:489] Iteration 6420, lr = 0.001
  2661. I0525 08:18:04.687662 138703 solver.cpp:214] Iteration 6440, loss = 4.59273
  2662. I0525 08:18:04.687872 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2663. I0525 08:18:04.687896 138703 solver.cpp:229] Train net output #1: loss = 4.59273 (* 1 = 4.59273 loss)
  2664. I0525 08:18:04.687914 138703 solver.cpp:489] Iteration 6440, lr = 0.001
  2665. I0525 08:19:14.823096 138703 solver.cpp:214] Iteration 6460, loss = 4.62515
  2666. I0525 08:19:14.823263 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2667. I0525 08:19:14.823279 138703 solver.cpp:229] Train net output #1: loss = 4.62515 (* 1 = 4.62515 loss)
  2668. I0525 08:19:14.823292 138703 solver.cpp:489] Iteration 6460, lr = 0.001
  2669. I0525 08:20:29.720922 138703 solver.cpp:214] Iteration 6480, loss = 4.61983
  2670. I0525 08:20:29.721210 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2671. I0525 08:20:29.721232 138703 solver.cpp:229] Train net output #1: loss = 4.61983 (* 1 = 4.61983 loss)
  2672. I0525 08:20:29.721256 138703 solver.cpp:489] Iteration 6480, lr = 0.001
  2673. I0525 08:21:40.834945 138703 solver.cpp:291] Iteration 6500, Testing net (#0)
  2674. I0525 08:24:02.062297 138703 solver.cpp:340] Test net output #0: accuracy = 0.0258333
  2675. I0525 08:24:02.064034 138703 solver.cpp:340] Test net output #1: loss = 4.56517 (* 1 = 4.56517 loss)
  2676. I0525 08:24:04.432173 138703 solver.cpp:214] Iteration 6500, loss = 4.58719
  2677. I0525 08:24:04.432211 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2678. I0525 08:24:04.432222 138703 solver.cpp:229] Train net output #1: loss = 4.58719 (* 1 = 4.58719 loss)
  2679. I0525 08:24:04.432235 138703 solver.cpp:489] Iteration 6500, lr = 0.001
  2680. I0525 08:25:19.276633 138703 solver.cpp:214] Iteration 6520, loss = 4.54539
  2681. I0525 08:25:19.277125 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2682. I0525 08:25:19.277145 138703 solver.cpp:229] Train net output #1: loss = 4.54539 (* 1 = 4.54539 loss)
  2683. I0525 08:25:19.277163 138703 solver.cpp:489] Iteration 6520, lr = 0.001
  2684. I0525 08:26:27.962185 138703 solver.cpp:214] Iteration 6540, loss = 4.55613
  2685. I0525 08:26:27.962345 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2686. I0525 08:26:27.962370 138703 solver.cpp:229] Train net output #1: loss = 4.55613 (* 1 = 4.55613 loss)
  2687. I0525 08:26:27.962393 138703 solver.cpp:489] Iteration 6540, lr = 0.001
  2688. I0525 08:27:42.551748 138703 solver.cpp:214] Iteration 6560, loss = 4.50615
  2689. I0525 08:27:42.551946 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2690. I0525 08:27:42.551970 138703 solver.cpp:229] Train net output #1: loss = 4.50615 (* 1 = 4.50615 loss)
  2691. I0525 08:27:42.551987 138703 solver.cpp:489] Iteration 6560, lr = 0.001
  2692. I0525 08:28:57.363623 138703 solver.cpp:214] Iteration 6580, loss = 4.59254
  2693. I0525 08:28:57.363781 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2694. I0525 08:28:57.363795 138703 solver.cpp:229] Train net output #1: loss = 4.59254 (* 1 = 4.59254 loss)
  2695. I0525 08:28:57.363807 138703 solver.cpp:489] Iteration 6580, lr = 0.001
  2696. I0525 08:30:08.676350 138703 solver.cpp:291] Iteration 6600, Testing net (#0)
  2697. I0525 08:32:30.247572 138703 solver.cpp:340] Test net output #0: accuracy = 0.0185417
  2698. I0525 08:32:30.247719 138703 solver.cpp:340] Test net output #1: loss = 4.56097 (* 1 = 4.56097 loss)
  2699. I0525 08:32:32.460815 138703 solver.cpp:214] Iteration 6600, loss = 4.51654
  2700. I0525 08:32:32.460858 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2701. I0525 08:32:32.460870 138703 solver.cpp:229] Train net output #1: loss = 4.51654 (* 1 = 4.51654 loss)
  2702. I0525 08:32:32.460882 138703 solver.cpp:489] Iteration 6600, lr = 0.001
  2703. I0525 08:33:39.531919 138703 solver.cpp:214] Iteration 6620, loss = 4.53845
  2704. I0525 08:33:39.532076 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2705. I0525 08:33:39.532099 138703 solver.cpp:229] Train net output #1: loss = 4.53845 (* 1 = 4.53845 loss)
  2706. I0525 08:33:39.532145 138703 solver.cpp:489] Iteration 6620, lr = 0.001
  2707. I0525 08:34:54.481227 138703 solver.cpp:214] Iteration 6640, loss = 4.49725
  2708. I0525 08:34:54.481375 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2709. I0525 08:34:54.481390 138703 solver.cpp:229] Train net output #1: loss = 4.49725 (* 1 = 4.49725 loss)
  2710. I0525 08:34:54.481405 138703 solver.cpp:489] Iteration 6640, lr = 0.001
  2711. I0525 08:36:09.327627 138703 solver.cpp:214] Iteration 6660, loss = 4.52735
  2712. I0525 08:36:09.327778 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2713. I0525 08:36:09.327793 138703 solver.cpp:229] Train net output #1: loss = 4.52735 (* 1 = 4.52735 loss)
  2714. I0525 08:36:09.327806 138703 solver.cpp:489] Iteration 6660, lr = 0.001
  2715. I0525 08:37:24.196697 138703 solver.cpp:214] Iteration 6680, loss = 4.52168
  2716. I0525 08:37:24.196912 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2717. I0525 08:37:24.196934 138703 solver.cpp:229] Train net output #1: loss = 4.52168 (* 1 = 4.52168 loss)
  2718. I0525 08:37:24.196957 138703 solver.cpp:489] Iteration 6680, lr = 0.001
  2719. I0525 08:38:28.939613 138703 solver.cpp:291] Iteration 6700, Testing net (#0)
  2720. I0525 08:40:52.525574 138703 solver.cpp:340] Test net output #0: accuracy = 0.02
  2721. I0525 08:40:52.527467 138703 solver.cpp:340] Test net output #1: loss = 4.5302 (* 1 = 4.5302 loss)
  2722. I0525 08:40:54.926522 138703 solver.cpp:214] Iteration 6700, loss = 4.63185
  2723. I0525 08:40:54.926568 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2724. I0525 08:40:54.926584 138703 solver.cpp:229] Train net output #1: loss = 4.63185 (* 1 = 4.63185 loss)
  2725. I0525 08:40:54.926635 138703 solver.cpp:489] Iteration 6700, lr = 0.001
  2726. I0525 08:42:09.738591 138703 solver.cpp:214] Iteration 6720, loss = 4.6016
  2727. I0525 08:42:09.738754 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2728. I0525 08:42:09.738768 138703 solver.cpp:229] Train net output #1: loss = 4.6016 (* 1 = 4.6016 loss)
  2729. I0525 08:42:09.738781 138703 solver.cpp:489] Iteration 6720, lr = 0.001
  2730. I0525 08:43:24.275442 138703 solver.cpp:214] Iteration 6740, loss = 4.54718
  2731. I0525 08:43:24.279183 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2732. I0525 08:43:24.279209 138703 solver.cpp:229] Train net output #1: loss = 4.54718 (* 1 = 4.54718 loss)
  2733. I0525 08:43:24.279255 138703 solver.cpp:489] Iteration 6740, lr = 0.001
  2734. I0525 08:44:38.897323 138703 solver.cpp:214] Iteration 6760, loss = 4.44341
  2735. I0525 08:44:38.897485 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2736. I0525 08:44:38.897507 138703 solver.cpp:229] Train net output #1: loss = 4.44341 (* 1 = 4.44341 loss)
  2737. I0525 08:44:38.897524 138703 solver.cpp:489] Iteration 6760, lr = 0.001
  2738. I0525 08:45:45.369354 138703 solver.cpp:214] Iteration 6780, loss = 4.52302
  2739. I0525 08:45:45.369498 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2740. I0525 08:45:45.369513 138703 solver.cpp:229] Train net output #1: loss = 4.52302 (* 1 = 4.52302 loss)
  2741. I0525 08:45:45.369526 138703 solver.cpp:489] Iteration 6780, lr = 0.001
  2742. I0525 08:46:51.144752 138703 solver.cpp:291] Iteration 6800, Testing net (#0)
  2743. I0525 08:49:11.262115 138703 solver.cpp:340] Test net output #0: accuracy = 0.0204167
  2744. I0525 08:49:11.263193 138703 solver.cpp:340] Test net output #1: loss = 4.54314 (* 1 = 4.54314 loss)
  2745. I0525 08:49:13.656877 138703 solver.cpp:214] Iteration 6800, loss = 4.51442
  2746. I0525 08:49:13.656922 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2747. I0525 08:49:13.656940 138703 solver.cpp:229] Train net output #1: loss = 4.51442 (* 1 = 4.51442 loss)
  2748. I0525 08:49:13.656956 138703 solver.cpp:489] Iteration 6800, lr = 0.001
  2749. I0525 08:50:28.533325 138703 solver.cpp:214] Iteration 6820, loss = 4.5617
  2750. I0525 08:50:28.533478 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2751. I0525 08:50:28.533499 138703 solver.cpp:229] Train net output #1: loss = 4.5617 (* 1 = 4.5617 loss)
  2752. I0525 08:50:28.533515 138703 solver.cpp:489] Iteration 6820, lr = 0.001
  2753. I0525 08:51:43.486521 138703 solver.cpp:214] Iteration 6840, loss = 4.54072
  2754. I0525 08:51:43.486719 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  2755. I0525 08:51:43.486763 138703 solver.cpp:229] Train net output #1: loss = 4.54072 (* 1 = 4.54072 loss)
  2756. I0525 08:51:43.486800 138703 solver.cpp:489] Iteration 6840, lr = 0.001
  2757. I0525 08:52:52.369768 138703 solver.cpp:214] Iteration 6860, loss = 4.55937
  2758. I0525 08:52:52.369940 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2759. I0525 08:52:52.369961 138703 solver.cpp:229] Train net output #1: loss = 4.55937 (* 1 = 4.55937 loss)
  2760. I0525 08:52:52.369976 138703 solver.cpp:489] Iteration 6860, lr = 0.001
  2761. I0525 08:53:59.639843 138703 solver.cpp:214] Iteration 6880, loss = 4.53612
  2762. I0525 08:53:59.640012 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2763. I0525 08:53:59.640029 138703 solver.cpp:229] Train net output #1: loss = 4.53612 (* 1 = 4.53612 loss)
  2764. I0525 08:53:59.640041 138703 solver.cpp:489] Iteration 6880, lr = 0.001
  2765. I0525 08:55:05.471432 138703 solver.cpp:291] Iteration 6900, Testing net (#0)
  2766. I0525 08:57:27.111914 138703 solver.cpp:340] Test net output #0: accuracy = 0.020625
  2767. I0525 08:57:27.112056 138703 solver.cpp:340] Test net output #1: loss = 4.56007 (* 1 = 4.56007 loss)
  2768. I0525 08:57:29.502425 138703 solver.cpp:214] Iteration 6900, loss = 4.46425
  2769. I0525 08:57:29.502467 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2770. I0525 08:57:29.502478 138703 solver.cpp:229] Train net output #1: loss = 4.46425 (* 1 = 4.46425 loss)
  2771. I0525 08:57:29.502490 138703 solver.cpp:489] Iteration 6900, lr = 0.001
  2772. I0525 08:58:44.443994 138703 solver.cpp:214] Iteration 6920, loss = 4.52026
  2773. I0525 08:58:44.444155 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2774. I0525 08:58:44.444177 138703 solver.cpp:229] Train net output #1: loss = 4.52026 (* 1 = 4.52026 loss)
  2775. I0525 08:58:44.444226 138703 solver.cpp:489] Iteration 6920, lr = 0.001
  2776. I0525 08:59:53.192747 138703 solver.cpp:214] Iteration 6940, loss = 4.51868
  2777. I0525 08:59:53.193019 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  2778. I0525 08:59:53.193037 138703 solver.cpp:229] Train net output #1: loss = 4.51868 (* 1 = 4.51868 loss)
  2779. I0525 08:59:53.193050 138703 solver.cpp:489] Iteration 6940, lr = 0.001
  2780. I0525 09:01:01.065085 138703 solver.cpp:214] Iteration 6960, loss = 4.56611
  2781. I0525 09:01:01.065250 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2782. I0525 09:01:01.065268 138703 solver.cpp:229] Train net output #1: loss = 4.56611 (* 1 = 4.56611 loss)
  2783. I0525 09:01:01.065279 138703 solver.cpp:489] Iteration 6960, lr = 0.001
  2784. I0525 09:02:08.857132 138703 solver.cpp:214] Iteration 6980, loss = 4.49936
  2785. I0525 09:02:08.857277 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2786. I0525 09:02:08.857292 138703 solver.cpp:229] Train net output #1: loss = 4.49936 (* 1 = 4.49936 loss)
  2787. I0525 09:02:08.857306 138703 solver.cpp:489] Iteration 6980, lr = 0.001
  2788. I0525 09:03:20.092031 138703 solver.cpp:291] Iteration 7000, Testing net (#0)
  2789. I0525 09:05:51.906826 138703 solver.cpp:340] Test net output #0: accuracy = 0.0191667
  2790. I0525 09:05:51.907227 138703 solver.cpp:340] Test net output #1: loss = 4.53318 (* 1 = 4.53318 loss)
  2791. I0525 09:05:54.274700 138703 solver.cpp:214] Iteration 7000, loss = 4.48971
  2792. I0525 09:05:54.274745 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2793. I0525 09:05:54.274765 138703 solver.cpp:229] Train net output #1: loss = 4.48971 (* 1 = 4.48971 loss)
  2794. I0525 09:05:54.274782 138703 solver.cpp:489] Iteration 7000, lr = 0.001
  2795. I0525 09:07:04.725008 138703 solver.cpp:214] Iteration 7020, loss = 4.5633
  2796. I0525 09:07:04.725152 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2797. I0525 09:07:04.725165 138703 solver.cpp:229] Train net output #1: loss = 4.5633 (* 1 = 4.5633 loss)
  2798. I0525 09:07:04.725179 138703 solver.cpp:489] Iteration 7020, lr = 0.001
  2799. I0525 09:08:10.140406 138703 solver.cpp:214] Iteration 7040, loss = 4.55031
  2800. I0525 09:08:10.141604 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2801. I0525 09:08:10.141628 138703 solver.cpp:229] Train net output #1: loss = 4.55031 (* 1 = 4.55031 loss)
  2802. I0525 09:08:10.141645 138703 solver.cpp:489] Iteration 7040, lr = 0.001
  2803. I0525 09:09:19.406607 138703 solver.cpp:214] Iteration 7060, loss = 4.56705
  2804. I0525 09:09:19.406747 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2805. I0525 09:09:19.406762 138703 solver.cpp:229] Train net output #1: loss = 4.56705 (* 1 = 4.56705 loss)
  2806. I0525 09:09:19.406775 138703 solver.cpp:489] Iteration 7060, lr = 0.001
  2807. I0525 09:10:34.423555 138703 solver.cpp:214] Iteration 7080, loss = 4.46195
  2808. I0525 09:10:34.423737 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2809. I0525 09:10:34.423761 138703 solver.cpp:229] Train net output #1: loss = 4.46195 (* 1 = 4.46195 loss)
  2810. I0525 09:10:34.423791 138703 solver.cpp:489] Iteration 7080, lr = 0.001
  2811. I0525 09:11:45.773262 138703 solver.cpp:291] Iteration 7100, Testing net (#0)
  2812. I0525 09:14:51.330915 138703 solver.cpp:340] Test net output #0: accuracy = 0.0175
  2813. I0525 09:14:51.336521 138703 solver.cpp:340] Test net output #1: loss = 4.5599 (* 1 = 4.5599 loss)
  2814. I0525 09:14:52.932421 138703 solver.cpp:214] Iteration 7100, loss = 4.51841
  2815. I0525 09:14:52.932464 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2816. I0525 09:14:52.932482 138703 solver.cpp:229] Train net output #1: loss = 4.51841 (* 1 = 4.51841 loss)
  2817. I0525 09:14:52.932498 138703 solver.cpp:489] Iteration 7100, lr = 0.001
  2818. I0525 09:15:55.910748 138703 solver.cpp:214] Iteration 7120, loss = 4.48953
  2819. I0525 09:15:55.910931 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2820. I0525 09:15:55.910956 138703 solver.cpp:229] Train net output #1: loss = 4.48953 (* 1 = 4.48953 loss)
  2821. I0525 09:15:55.910969 138703 solver.cpp:489] Iteration 7120, lr = 0.001
  2822. I0525 09:17:11.122154 138703 solver.cpp:214] Iteration 7140, loss = 4.51152
  2823. I0525 09:17:11.122320 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2824. I0525 09:17:11.122340 138703 solver.cpp:229] Train net output #1: loss = 4.51152 (* 1 = 4.51152 loss)
  2825. I0525 09:17:11.122357 138703 solver.cpp:489] Iteration 7140, lr = 0.001
  2826. I0525 09:18:25.698143 138703 solver.cpp:214] Iteration 7160, loss = 4.56002
  2827. I0525 09:18:25.698288 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2828. I0525 09:18:25.698303 138703 solver.cpp:229] Train net output #1: loss = 4.56002 (* 1 = 4.56002 loss)
  2829. I0525 09:18:25.698315 138703 solver.cpp:489] Iteration 7160, lr = 0.001
  2830. I0525 09:19:40.532322 138703 solver.cpp:214] Iteration 7180, loss = 4.59369
  2831. I0525 09:19:40.532488 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2832. I0525 09:19:40.532505 138703 solver.cpp:229] Train net output #1: loss = 4.59369 (* 1 = 4.59369 loss)
  2833. I0525 09:19:40.532519 138703 solver.cpp:489] Iteration 7180, lr = 0.001
  2834. I0525 09:20:51.612293 138703 solver.cpp:291] Iteration 7200, Testing net (#0)
  2835. I0525 09:24:08.336370 138703 solver.cpp:340] Test net output #0: accuracy = 0.019375
  2836. I0525 09:24:08.340484 138703 solver.cpp:340] Test net output #1: loss = 4.53985 (* 1 = 4.53985 loss)
  2837. I0525 09:24:10.719687 138703 solver.cpp:214] Iteration 7200, loss = 4.53634
  2838. I0525 09:24:10.719743 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2839. I0525 09:24:10.719756 138703 solver.cpp:229] Train net output #1: loss = 4.53634 (* 1 = 4.53634 loss)
  2840. I0525 09:24:10.719770 138703 solver.cpp:489] Iteration 7200, lr = 0.001
  2841. I0525 09:25:25.749657 138703 solver.cpp:214] Iteration 7220, loss = 4.53391
  2842. I0525 09:25:25.749815 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2843. I0525 09:25:25.749837 138703 solver.cpp:229] Train net output #1: loss = 4.53391 (* 1 = 4.53391 loss)
  2844. I0525 09:25:25.749856 138703 solver.cpp:489] Iteration 7220, lr = 0.001
  2845. I0525 09:26:40.629107 138703 solver.cpp:214] Iteration 7240, loss = 4.46326
  2846. I0525 09:26:40.629248 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2847. I0525 09:26:40.629264 138703 solver.cpp:229] Train net output #1: loss = 4.46326 (* 1 = 4.46326 loss)
  2848. I0525 09:26:40.629278 138703 solver.cpp:489] Iteration 7240, lr = 0.001
  2849. I0525 09:27:55.954188 138703 solver.cpp:214] Iteration 7260, loss = 4.51052
  2850. I0525 09:27:55.954340 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2851. I0525 09:27:55.954355 138703 solver.cpp:229] Train net output #1: loss = 4.51052 (* 1 = 4.51052 loss)
  2852. I0525 09:27:55.954370 138703 solver.cpp:489] Iteration 7260, lr = 0.001
  2853. I0525 09:29:02.185744 138703 solver.cpp:214] Iteration 7280, loss = 4.58602
  2854. I0525 09:29:02.185916 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2855. I0525 09:29:02.185936 138703 solver.cpp:229] Train net output #1: loss = 4.58602 (* 1 = 4.58602 loss)
  2856. I0525 09:29:02.185956 138703 solver.cpp:489] Iteration 7280, lr = 0.001
  2857. I0525 09:29:53.757586 138703 solver.cpp:291] Iteration 7300, Testing net (#0)
  2858. I0525 09:33:04.863648 138703 solver.cpp:340] Test net output #0: accuracy = 0.02375
  2859. I0525 09:33:04.863796 138703 solver.cpp:340] Test net output #1: loss = 4.55297 (* 1 = 4.55297 loss)
  2860. I0525 09:33:07.225586 138703 solver.cpp:214] Iteration 7300, loss = 4.58117
  2861. I0525 09:33:07.225627 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2862. I0525 09:33:07.225641 138703 solver.cpp:229] Train net output #1: loss = 4.58117 (* 1 = 4.58117 loss)
  2863. I0525 09:33:07.225652 138703 solver.cpp:489] Iteration 7300, lr = 0.001
  2864. I0525 09:34:22.024327 138703 solver.cpp:214] Iteration 7320, loss = 4.44842
  2865. I0525 09:34:22.024502 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2866. I0525 09:34:22.024528 138703 solver.cpp:229] Train net output #1: loss = 4.44842 (* 1 = 4.44842 loss)
  2867. I0525 09:34:22.024549 138703 solver.cpp:489] Iteration 7320, lr = 0.001
  2868. I0525 09:35:30.856164 138703 solver.cpp:214] Iteration 7340, loss = 4.49756
  2869. I0525 09:35:30.860460 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2870. I0525 09:35:30.860486 138703 solver.cpp:229] Train net output #1: loss = 4.49756 (* 1 = 4.49756 loss)
  2871. I0525 09:35:30.860503 138703 solver.cpp:489] Iteration 7340, lr = 0.001
  2872. I0525 09:36:31.662025 138703 solver.cpp:214] Iteration 7360, loss = 4.51936
  2873. I0525 09:36:31.662189 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2874. I0525 09:36:31.662202 138703 solver.cpp:229] Train net output #1: loss = 4.51936 (* 1 = 4.51936 loss)
  2875. I0525 09:36:31.662215 138703 solver.cpp:489] Iteration 7360, lr = 0.001
  2876. I0525 09:37:46.287227 138703 solver.cpp:214] Iteration 7380, loss = 4.57078
  2877. I0525 09:37:46.287384 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2878. I0525 09:37:46.287400 138703 solver.cpp:229] Train net output #1: loss = 4.57078 (* 1 = 4.57078 loss)
  2879. I0525 09:37:46.287412 138703 solver.cpp:489] Iteration 7380, lr = 0.001
  2880. I0525 09:38:57.620784 138703 solver.cpp:291] Iteration 7400, Testing net (#0)
  2881. I0525 09:42:08.469379 138703 solver.cpp:340] Test net output #0: accuracy = 0.0247917
  2882. I0525 09:42:08.469558 138703 solver.cpp:340] Test net output #1: loss = 4.54958 (* 1 = 4.54958 loss)
  2883. I0525 09:42:10.984977 138703 solver.cpp:214] Iteration 7400, loss = 4.53342
  2884. I0525 09:42:10.985024 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2885. I0525 09:42:10.985036 138703 solver.cpp:229] Train net output #1: loss = 4.53342 (* 1 = 4.53342 loss)
  2886. I0525 09:42:10.985049 138703 solver.cpp:489] Iteration 7400, lr = 0.001
  2887. I0525 09:43:07.438917 138703 solver.cpp:214] Iteration 7420, loss = 4.50609
  2888. I0525 09:43:07.439072 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2889. I0525 09:43:07.439087 138703 solver.cpp:229] Train net output #1: loss = 4.50609 (* 1 = 4.50609 loss)
  2890. I0525 09:43:07.439101 138703 solver.cpp:489] Iteration 7420, lr = 0.001
  2891. I0525 09:44:18.253897 138703 solver.cpp:214] Iteration 7440, loss = 4.50414
  2892. I0525 09:44:18.256049 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2893. I0525 09:44:18.256064 138703 solver.cpp:229] Train net output #1: loss = 4.50414 (* 1 = 4.50414 loss)
  2894. I0525 09:44:18.256078 138703 solver.cpp:489] Iteration 7440, lr = 0.001
  2895. I0525 09:45:32.991258 138703 solver.cpp:214] Iteration 7460, loss = 4.54863
  2896. I0525 09:45:32.991390 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2897. I0525 09:45:32.991405 138703 solver.cpp:229] Train net output #1: loss = 4.54863 (* 1 = 4.54863 loss)
  2898. I0525 09:45:32.991417 138703 solver.cpp:489] Iteration 7460, lr = 0.001
  2899. I0525 09:46:47.727782 138703 solver.cpp:214] Iteration 7480, loss = 4.57717
  2900. I0525 09:46:47.727915 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2901. I0525 09:46:47.727934 138703 solver.cpp:229] Train net output #1: loss = 4.57717 (* 1 = 4.57717 loss)
  2902. I0525 09:46:47.727953 138703 solver.cpp:489] Iteration 7480, lr = 0.001
  2903. I0525 09:47:58.888638 138703 solver.cpp:291] Iteration 7500, Testing net (#0)
  2904. I0525 09:51:14.040794 138703 solver.cpp:340] Test net output #0: accuracy = 0.0179167
  2905. I0525 09:51:14.040954 138703 solver.cpp:340] Test net output #1: loss = 4.53039 (* 1 = 4.53039 loss)
  2906. I0525 09:51:16.430200 138703 solver.cpp:214] Iteration 7500, loss = 4.55844
  2907. I0525 09:51:16.430244 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2908. I0525 09:51:16.430258 138703 solver.cpp:229] Train net output #1: loss = 4.55844 (* 1 = 4.55844 loss)
  2909. I0525 09:51:16.430270 138703 solver.cpp:489] Iteration 7500, lr = 0.001
  2910. I0525 09:52:31.345827 138703 solver.cpp:214] Iteration 7520, loss = 4.52036
  2911. I0525 09:52:31.345986 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2912. I0525 09:52:31.346009 138703 solver.cpp:229] Train net output #1: loss = 4.52036 (* 1 = 4.52036 loss)
  2913. I0525 09:52:31.346026 138703 solver.cpp:489] Iteration 7520, lr = 0.001
  2914. I0525 09:53:46.171932 138703 solver.cpp:214] Iteration 7540, loss = 4.47638
  2915. I0525 09:53:46.172397 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2916. I0525 09:53:46.172457 138703 solver.cpp:229] Train net output #1: loss = 4.47638 (* 1 = 4.47638 loss)
  2917. I0525 09:53:46.172497 138703 solver.cpp:489] Iteration 7540, lr = 0.001
  2918. I0525 09:55:00.957475 138703 solver.cpp:214] Iteration 7560, loss = 4.57092
  2919. I0525 09:55:00.957613 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2920. I0525 09:55:00.957629 138703 solver.cpp:229] Train net output #1: loss = 4.57092 (* 1 = 4.57092 loss)
  2921. I0525 09:55:00.957641 138703 solver.cpp:489] Iteration 7560, lr = 0.001
  2922. I0525 09:56:15.939805 138703 solver.cpp:214] Iteration 7580, loss = 4.54881
  2923. I0525 09:56:15.939959 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2924. I0525 09:56:15.939973 138703 solver.cpp:229] Train net output #1: loss = 4.54881 (* 1 = 4.54881 loss)
  2925. I0525 09:56:15.939987 138703 solver.cpp:489] Iteration 7580, lr = 0.001
  2926. I0525 09:57:17.453333 138703 solver.cpp:291] Iteration 7600, Testing net (#0)
  2927. I0525 10:00:40.398325 138703 solver.cpp:340] Test net output #0: accuracy = 0.0204167
  2928. I0525 10:00:40.398478 138703 solver.cpp:340] Test net output #1: loss = 4.57441 (* 1 = 4.57441 loss)
  2929. I0525 10:00:42.807559 138703 solver.cpp:214] Iteration 7600, loss = 4.55221
  2930. I0525 10:00:42.807603 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2931. I0525 10:00:42.807616 138703 solver.cpp:229] Train net output #1: loss = 4.55221 (* 1 = 4.55221 loss)
  2932. I0525 10:00:42.807629 138703 solver.cpp:489] Iteration 7600, lr = 0.001
  2933. I0525 10:01:57.719916 138703 solver.cpp:214] Iteration 7620, loss = 4.63194
  2934. I0525 10:01:57.720058 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2935. I0525 10:01:57.720080 138703 solver.cpp:229] Train net output #1: loss = 4.63194 (* 1 = 4.63194 loss)
  2936. I0525 10:01:57.720098 138703 solver.cpp:489] Iteration 7620, lr = 0.001
  2937. I0525 10:03:06.788295 138703 solver.cpp:214] Iteration 7640, loss = 4.44548
  2938. I0525 10:03:06.788518 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2939. I0525 10:03:06.788560 138703 solver.cpp:229] Train net output #1: loss = 4.44548 (* 1 = 4.44548 loss)
  2940. I0525 10:03:06.788591 138703 solver.cpp:489] Iteration 7640, lr = 0.001
  2941. I0525 10:04:16.952690 138703 solver.cpp:214] Iteration 7660, loss = 4.58152
  2942. I0525 10:04:16.952854 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2943. I0525 10:04:16.952872 138703 solver.cpp:229] Train net output #1: loss = 4.58152 (* 1 = 4.58152 loss)
  2944. I0525 10:04:16.952884 138703 solver.cpp:489] Iteration 7660, lr = 0.001
  2945. I0525 10:05:21.829517 138703 solver.cpp:214] Iteration 7680, loss = 4.55046
  2946. I0525 10:05:21.829676 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2947. I0525 10:05:21.829692 138703 solver.cpp:229] Train net output #1: loss = 4.55046 (* 1 = 4.55046 loss)
  2948. I0525 10:05:21.829705 138703 solver.cpp:489] Iteration 7680, lr = 0.001
  2949. I0525 10:06:33.202658 138703 solver.cpp:291] Iteration 7700, Testing net (#0)
  2950. I0525 10:09:55.015323 138703 solver.cpp:340] Test net output #0: accuracy = 0.0233333
  2951. I0525 10:09:55.015462 138703 solver.cpp:340] Test net output #1: loss = 4.58711 (* 1 = 4.58711 loss)
  2952. I0525 10:09:56.804417 138703 solver.cpp:214] Iteration 7700, loss = 4.4776
  2953. I0525 10:09:56.804486 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  2954. I0525 10:09:56.804509 138703 solver.cpp:229] Train net output #1: loss = 4.4776 (* 1 = 4.4776 loss)
  2955. I0525 10:09:56.804534 138703 solver.cpp:489] Iteration 7700, lr = 0.001
  2956. I0525 10:11:03.214237 138703 solver.cpp:214] Iteration 7720, loss = 4.57446
  2957. I0525 10:11:03.214408 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2958. I0525 10:11:03.214423 138703 solver.cpp:229] Train net output #1: loss = 4.57446 (* 1 = 4.57446 loss)
  2959. I0525 10:11:03.214435 138703 solver.cpp:489] Iteration 7720, lr = 0.001
  2960. I0525 10:12:08.725692 138703 solver.cpp:214] Iteration 7740, loss = 4.53864
  2961. I0525 10:12:08.725834 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2962. I0525 10:12:08.725849 138703 solver.cpp:229] Train net output #1: loss = 4.53864 (* 1 = 4.53864 loss)
  2963. I0525 10:12:08.725862 138703 solver.cpp:489] Iteration 7740, lr = 0.001
  2964. I0525 10:13:23.513674 138703 solver.cpp:214] Iteration 7760, loss = 4.53121
  2965. I0525 10:13:23.513840 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2966. I0525 10:13:23.513864 138703 solver.cpp:229] Train net output #1: loss = 4.53121 (* 1 = 4.53121 loss)
  2967. I0525 10:13:23.513912 138703 solver.cpp:489] Iteration 7760, lr = 0.001
  2968. I0525 10:14:38.117343 138703 solver.cpp:214] Iteration 7780, loss = 4.519
  2969. I0525 10:14:38.117487 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2970. I0525 10:14:38.117503 138703 solver.cpp:229] Train net output #1: loss = 4.519 (* 1 = 4.519 loss)
  2971. I0525 10:14:38.117516 138703 solver.cpp:489] Iteration 7780, lr = 0.001
  2972. I0525 10:15:49.200621 138703 solver.cpp:291] Iteration 7800, Testing net (#0)
  2973. I0525 10:18:57.894863 138703 solver.cpp:340] Test net output #0: accuracy = 0.0197917
  2974. I0525 10:18:57.895015 138703 solver.cpp:340] Test net output #1: loss = 4.54503 (* 1 = 4.54503 loss)
  2975. I0525 10:19:00.262688 138703 solver.cpp:214] Iteration 7800, loss = 4.47349
  2976. I0525 10:19:00.262730 138703 solver.cpp:229] Train net output #0: accuracy = 0
  2977. I0525 10:19:00.262742 138703 solver.cpp:229] Train net output #1: loss = 4.47349 (* 1 = 4.47349 loss)
  2978. I0525 10:19:00.262754 138703 solver.cpp:489] Iteration 7800, lr = 0.001
  2979. I0525 10:20:15.109761 138703 solver.cpp:214] Iteration 7820, loss = 4.55332
  2980. I0525 10:20:15.109951 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2981. I0525 10:20:15.109974 138703 solver.cpp:229] Train net output #1: loss = 4.55332 (* 1 = 4.55332 loss)
  2982. I0525 10:20:15.109994 138703 solver.cpp:489] Iteration 7820, lr = 0.001
  2983. I0525 10:21:29.937993 138703 solver.cpp:214] Iteration 7840, loss = 4.5594
  2984. I0525 10:21:29.938133 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  2985. I0525 10:21:29.938149 138703 solver.cpp:229] Train net output #1: loss = 4.5594 (* 1 = 4.5594 loss)
  2986. I0525 10:21:29.938161 138703 solver.cpp:489] Iteration 7840, lr = 0.001
  2987. I0525 10:22:44.664849 138703 solver.cpp:214] Iteration 7860, loss = 4.53306
  2988. I0525 10:22:44.665109 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  2989. I0525 10:22:44.665163 138703 solver.cpp:229] Train net output #1: loss = 4.53306 (* 1 = 4.53306 loss)
  2990. I0525 10:22:44.665204 138703 solver.cpp:489] Iteration 7860, lr = 0.001
  2991. I0525 10:23:59.784037 138703 solver.cpp:214] Iteration 7880, loss = 4.56563
  2992. I0525 10:23:59.784195 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  2993. I0525 10:23:59.784210 138703 solver.cpp:229] Train net output #1: loss = 4.56563 (* 1 = 4.56563 loss)
  2994. I0525 10:23:59.784224 138703 solver.cpp:489] Iteration 7880, lr = 0.001
  2995. I0525 10:24:56.298733 138703 solver.cpp:291] Iteration 7900, Testing net (#0)
  2996. I0525 10:28:11.827117 138703 solver.cpp:340] Test net output #0: accuracy = 0.019375
  2997. I0525 10:28:11.827288 138703 solver.cpp:340] Test net output #1: loss = 4.53286 (* 1 = 4.53286 loss)
  2998. I0525 10:28:14.204123 138703 solver.cpp:214] Iteration 7900, loss = 4.60967
  2999. I0525 10:28:14.204174 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3000. I0525 10:28:14.204186 138703 solver.cpp:229] Train net output #1: loss = 4.60967 (* 1 = 4.60967 loss)
  3001. I0525 10:28:14.204198 138703 solver.cpp:489] Iteration 7900, lr = 0.001
  3002. I0525 10:29:29.032510 138703 solver.cpp:214] Iteration 7920, loss = 4.53373
  3003. I0525 10:29:29.034229 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3004. I0525 10:29:29.034245 138703 solver.cpp:229] Train net output #1: loss = 4.53373 (* 1 = 4.53373 loss)
  3005. I0525 10:29:29.034258 138703 solver.cpp:489] Iteration 7920, lr = 0.001
  3006. I0525 10:30:43.872056 138703 solver.cpp:214] Iteration 7940, loss = 4.4757
  3007. I0525 10:30:43.872220 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3008. I0525 10:30:43.872236 138703 solver.cpp:229] Train net output #1: loss = 4.4757 (* 1 = 4.4757 loss)
  3009. I0525 10:30:43.872248 138703 solver.cpp:489] Iteration 7940, lr = 0.001
  3010. I0525 10:31:44.106082 138703 solver.cpp:214] Iteration 7960, loss = 4.50139
  3011. I0525 10:31:44.106235 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3012. I0525 10:31:44.106248 138703 solver.cpp:229] Train net output #1: loss = 4.50139 (* 1 = 4.50139 loss)
  3013. I0525 10:31:44.106262 138703 solver.cpp:489] Iteration 7960, lr = 0.001
  3014. I0525 10:32:49.691969 138703 solver.cpp:214] Iteration 7980, loss = 4.55394
  3015. I0525 10:32:49.692117 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3016. I0525 10:32:49.692134 138703 solver.cpp:229] Train net output #1: loss = 4.55394 (* 1 = 4.55394 loss)
  3017. I0525 10:32:49.692147 138703 solver.cpp:489] Iteration 7980, lr = 0.001
  3018. I0525 10:34:00.709228 138703 solver.cpp:291] Iteration 8000, Testing net (#0)
  3019. I0525 10:37:18.981501 138703 solver.cpp:340] Test net output #0: accuracy = 0.025625
  3020. I0525 10:37:18.981662 138703 solver.cpp:340] Test net output #1: loss = 4.55121 (* 1 = 4.55121 loss)
  3021. I0525 10:37:21.365394 138703 solver.cpp:214] Iteration 8000, loss = 4.6242
  3022. I0525 10:37:21.365439 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3023. I0525 10:37:21.365453 138703 solver.cpp:229] Train net output #1: loss = 4.6242 (* 1 = 4.6242 loss)
  3024. I0525 10:37:21.365466 138703 solver.cpp:489] Iteration 8000, lr = 0.001
  3025. I0525 10:38:33.750167 138703 solver.cpp:214] Iteration 8020, loss = 4.49255
  3026. I0525 10:38:33.750427 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3027. I0525 10:38:33.750443 138703 solver.cpp:229] Train net output #1: loss = 4.49255 (* 1 = 4.49255 loss)
  3028. I0525 10:38:33.750457 138703 solver.cpp:489] Iteration 8020, lr = 0.001
  3029. I0525 10:39:30.820868 138703 solver.cpp:214] Iteration 8040, loss = 4.56548
  3030. I0525 10:39:30.821166 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3031. I0525 10:39:30.821184 138703 solver.cpp:229] Train net output #1: loss = 4.56548 (* 1 = 4.56548 loss)
  3032. I0525 10:39:30.821197 138703 solver.cpp:489] Iteration 8040, lr = 0.001
  3033. I0525 10:40:45.257498 138703 solver.cpp:214] Iteration 8060, loss = 4.52548
  3034. I0525 10:40:45.259480 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3035. I0525 10:40:45.259513 138703 solver.cpp:229] Train net output #1: loss = 4.52548 (* 1 = 4.52548 loss)
  3036. I0525 10:40:45.259534 138703 solver.cpp:489] Iteration 8060, lr = 0.001
  3037. I0525 10:42:00.133575 138703 solver.cpp:214] Iteration 8080, loss = 4.49053
  3038. I0525 10:42:00.133740 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3039. I0525 10:42:00.133755 138703 solver.cpp:229] Train net output #1: loss = 4.49053 (* 1 = 4.49053 loss)
  3040. I0525 10:42:00.133769 138703 solver.cpp:489] Iteration 8080, lr = 0.001
  3041. I0525 10:43:11.187273 138703 solver.cpp:291] Iteration 8100, Testing net (#0)
  3042. I0525 10:45:36.222182 138703 solver.cpp:340] Test net output #0: accuracy = 0.0158333
  3043. I0525 10:45:36.222359 138703 solver.cpp:340] Test net output #1: loss = 4.55359 (* 1 = 4.55359 loss)
  3044. I0525 10:45:38.526145 138703 solver.cpp:214] Iteration 8100, loss = 4.54228
  3045. I0525 10:45:38.526211 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3046. I0525 10:45:38.526231 138703 solver.cpp:229] Train net output #1: loss = 4.54228 (* 1 = 4.54228 loss)
  3047. I0525 10:45:38.526247 138703 solver.cpp:489] Iteration 8100, lr = 0.001
  3048. I0525 10:46:32.403157 138703 solver.cpp:214] Iteration 8120, loss = 4.54786
  3049. I0525 10:46:32.403332 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3050. I0525 10:46:32.403348 138703 solver.cpp:229] Train net output #1: loss = 4.54786 (* 1 = 4.54786 loss)
  3051. I0525 10:46:32.403362 138703 solver.cpp:489] Iteration 8120, lr = 0.001
  3052. I0525 10:47:46.283578 138703 solver.cpp:214] Iteration 8140, loss = 4.4229
  3053. I0525 10:47:46.283728 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3054. I0525 10:47:46.283743 138703 solver.cpp:229] Train net output #1: loss = 4.4229 (* 1 = 4.4229 loss)
  3055. I0525 10:47:46.283756 138703 solver.cpp:489] Iteration 8140, lr = 0.001
  3056. I0525 10:49:01.127540 138703 solver.cpp:214] Iteration 8160, loss = 4.61735
  3057. I0525 10:49:01.127697 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3058. I0525 10:49:01.127715 138703 solver.cpp:229] Train net output #1: loss = 4.61735 (* 1 = 4.61735 loss)
  3059. I0525 10:49:01.127728 138703 solver.cpp:489] Iteration 8160, lr = 0.001
  3060. I0525 10:50:15.953570 138703 solver.cpp:214] Iteration 8180, loss = 4.56588
  3061. I0525 10:50:15.953739 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3062. I0525 10:50:15.953760 138703 solver.cpp:229] Train net output #1: loss = 4.56588 (* 1 = 4.56588 loss)
  3063. I0525 10:50:15.953810 138703 solver.cpp:489] Iteration 8180, lr = 0.001
  3064. I0525 10:51:26.878406 138703 solver.cpp:291] Iteration 8200, Testing net (#0)
  3065. I0525 10:53:58.311961 138703 solver.cpp:340] Test net output #0: accuracy = 0.0216667
  3066. I0525 10:53:58.312119 138703 solver.cpp:340] Test net output #1: loss = 4.56948 (* 1 = 4.56948 loss)
  3067. I0525 10:54:00.662359 138703 solver.cpp:214] Iteration 8200, loss = 4.5923
  3068. I0525 10:54:00.662405 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3069. I0525 10:54:00.662418 138703 solver.cpp:229] Train net output #1: loss = 4.5923 (* 1 = 4.5923 loss)
  3070. I0525 10:54:00.662431 138703 solver.cpp:489] Iteration 8200, lr = 0.001
  3071. I0525 10:55:15.216611 138703 solver.cpp:214] Iteration 8220, loss = 4.53195
  3072. I0525 10:55:15.219805 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  3073. I0525 10:55:15.219822 138703 solver.cpp:229] Train net output #1: loss = 4.53195 (* 1 = 4.53195 loss)
  3074. I0525 10:55:15.219835 138703 solver.cpp:489] Iteration 8220, lr = 0.001
  3075. I0525 10:56:30.213524 138703 solver.cpp:214] Iteration 8240, loss = 4.57283
  3076. I0525 10:56:30.214320 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3077. I0525 10:56:30.214342 138703 solver.cpp:229] Train net output #1: loss = 4.57283 (* 1 = 4.57283 loss)
  3078. I0525 10:56:30.214387 138703 solver.cpp:489] Iteration 8240, lr = 0.001
  3079. I0525 10:57:44.968992 138703 solver.cpp:214] Iteration 8260, loss = 4.48174
  3080. I0525 10:57:44.969431 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3081. I0525 10:57:44.969457 138703 solver.cpp:229] Train net output #1: loss = 4.48174 (* 1 = 4.48174 loss)
  3082. I0525 10:57:44.969506 138703 solver.cpp:489] Iteration 8260, lr = 0.001
  3083. I0525 10:58:59.799918 138703 solver.cpp:214] Iteration 8280, loss = 4.57228
  3084. I0525 10:58:59.800081 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3085. I0525 10:58:59.800104 138703 solver.cpp:229] Train net output #1: loss = 4.57228 (* 1 = 4.57228 loss)
  3086. I0525 10:58:59.800149 138703 solver.cpp:489] Iteration 8280, lr = 0.001
  3087. I0525 11:00:06.688047 138703 solver.cpp:291] Iteration 8300, Testing net (#0)
  3088. I0525 11:02:32.556018 138703 solver.cpp:340] Test net output #0: accuracy = 0.0220833
  3089. I0525 11:02:32.556296 138703 solver.cpp:340] Test net output #1: loss = 4.54691 (* 1 = 4.54691 loss)
  3090. I0525 11:02:34.902329 138703 solver.cpp:214] Iteration 8300, loss = 4.60138
  3091. I0525 11:02:34.902374 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3092. I0525 11:02:34.902385 138703 solver.cpp:229] Train net output #1: loss = 4.60138 (* 1 = 4.60138 loss)
  3093. I0525 11:02:34.902398 138703 solver.cpp:489] Iteration 8300, lr = 0.001
  3094. I0525 11:03:49.590389 138703 solver.cpp:214] Iteration 8320, loss = 4.54913
  3095. I0525 11:03:49.590631 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3096. I0525 11:03:49.590649 138703 solver.cpp:229] Train net output #1: loss = 4.54913 (* 1 = 4.54913 loss)
  3097. I0525 11:03:49.590665 138703 solver.cpp:489] Iteration 8320, lr = 0.001
  3098. I0525 11:05:04.484665 138703 solver.cpp:214] Iteration 8340, loss = 4.66699
  3099. I0525 11:05:04.485649 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3100. I0525 11:05:04.485673 138703 solver.cpp:229] Train net output #1: loss = 4.66699 (* 1 = 4.66699 loss)
  3101. I0525 11:05:04.485720 138703 solver.cpp:489] Iteration 8340, lr = 0.001
  3102. I0525 11:06:19.434034 138703 solver.cpp:214] Iteration 8360, loss = 4.52777
  3103. I0525 11:06:19.434180 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3104. I0525 11:06:19.434195 138703 solver.cpp:229] Train net output #1: loss = 4.52777 (* 1 = 4.52777 loss)
  3105. I0525 11:06:19.434207 138703 solver.cpp:489] Iteration 8360, lr = 0.001
  3106. I0525 11:07:29.488445 138703 solver.cpp:214] Iteration 8380, loss = 4.56329
  3107. I0525 11:07:29.488590 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3108. I0525 11:07:29.488605 138703 solver.cpp:229] Train net output #1: loss = 4.56329 (* 1 = 4.56329 loss)
  3109. I0525 11:07:29.488620 138703 solver.cpp:489] Iteration 8380, lr = 0.001
  3110. I0525 11:08:30.672229 138703 solver.cpp:291] Iteration 8400, Testing net (#0)
  3111. I0525 11:10:54.408711 138703 solver.cpp:340] Test net output #0: accuracy = 0.0222917
  3112. I0525 11:10:54.408852 138703 solver.cpp:340] Test net output #1: loss = 4.53635 (* 1 = 4.53635 loss)
  3113. I0525 11:10:56.788677 138703 solver.cpp:214] Iteration 8400, loss = 4.57907
  3114. I0525 11:10:56.788722 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3115. I0525 11:10:56.788735 138703 solver.cpp:229] Train net output #1: loss = 4.57907 (* 1 = 4.57907 loss)
  3116. I0525 11:10:56.788748 138703 solver.cpp:489] Iteration 8400, lr = 0.001
  3117. I0525 11:12:11.704579 138703 solver.cpp:214] Iteration 8420, loss = 4.56789
  3118. I0525 11:12:11.704722 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3119. I0525 11:12:11.704743 138703 solver.cpp:229] Train net output #1: loss = 4.56789 (* 1 = 4.56789 loss)
  3120. I0525 11:12:11.704761 138703 solver.cpp:489] Iteration 8420, lr = 0.001
  3121. I0525 11:13:26.496986 138703 solver.cpp:214] Iteration 8440, loss = 4.60343
  3122. I0525 11:13:26.497133 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3123. I0525 11:13:26.497154 138703 solver.cpp:229] Train net output #1: loss = 4.60343 (* 1 = 4.60343 loss)
  3124. I0525 11:13:26.497171 138703 solver.cpp:489] Iteration 8440, lr = 0.001
  3125. I0525 11:14:35.153322 138703 solver.cpp:214] Iteration 8460, loss = 4.55812
  3126. I0525 11:14:35.153486 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3127. I0525 11:14:35.153501 138703 solver.cpp:229] Train net output #1: loss = 4.55812 (* 1 = 4.55812 loss)
  3128. I0525 11:14:35.153515 138703 solver.cpp:489] Iteration 8460, lr = 0.001
  3129. I0525 11:15:41.938940 138703 solver.cpp:214] Iteration 8480, loss = 4.56682
  3130. I0525 11:15:41.939086 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3131. I0525 11:15:41.939105 138703 solver.cpp:229] Train net output #1: loss = 4.56682 (* 1 = 4.56682 loss)
  3132. I0525 11:15:41.939123 138703 solver.cpp:489] Iteration 8480, lr = 0.001
  3133. I0525 11:16:44.871918 138703 solver.cpp:291] Iteration 8500, Testing net (#0)
  3134. I0525 11:19:09.160711 138703 solver.cpp:340] Test net output #0: accuracy = 0.0202083
  3135. I0525 11:19:09.160852 138703 solver.cpp:340] Test net output #1: loss = 4.56561 (* 1 = 4.56561 loss)
  3136. I0525 11:19:11.544406 138703 solver.cpp:214] Iteration 8500, loss = 4.58252
  3137. I0525 11:19:11.544456 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3138. I0525 11:19:11.544474 138703 solver.cpp:229] Train net output #1: loss = 4.58252 (* 1 = 4.58252 loss)
  3139. I0525 11:19:11.544492 138703 solver.cpp:489] Iteration 8500, lr = 0.001
  3140. I0525 11:20:26.565556 138703 solver.cpp:214] Iteration 8520, loss = 4.41587
  3141. I0525 11:20:26.565718 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3142. I0525 11:20:26.565740 138703 solver.cpp:229] Train net output #1: loss = 4.41587 (* 1 = 4.41587 loss)
  3143. I0525 11:20:26.565759 138703 solver.cpp:489] Iteration 8520, lr = 0.001
  3144. I0525 11:21:36.252554 138703 solver.cpp:214] Iteration 8540, loss = 4.516
  3145. I0525 11:21:36.252763 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3146. I0525 11:21:36.252786 138703 solver.cpp:229] Train net output #1: loss = 4.516 (* 1 = 4.516 loss)
  3147. I0525 11:21:36.252804 138703 solver.cpp:489] Iteration 8540, lr = 0.001
  3148. I0525 11:22:41.102013 138703 solver.cpp:214] Iteration 8560, loss = 4.50578
  3149. I0525 11:22:41.102169 138703 solver.cpp:229] Train net output #0: accuracy = 0.046875
  3150. I0525 11:22:41.102192 138703 solver.cpp:229] Train net output #1: loss = 4.50578 (* 1 = 4.50578 loss)
  3151. I0525 11:22:41.102231 138703 solver.cpp:489] Iteration 8560, lr = 0.001
  3152. I0525 11:23:45.146100 138703 solver.cpp:214] Iteration 8580, loss = 4.49509
  3153. I0525 11:23:45.146248 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3154. I0525 11:23:45.146265 138703 solver.cpp:229] Train net output #1: loss = 4.49509 (* 1 = 4.49509 loss)
  3155. I0525 11:23:45.146277 138703 solver.cpp:489] Iteration 8580, lr = 0.001
  3156. I0525 11:24:56.399683 138703 solver.cpp:291] Iteration 8600, Testing net (#0)
  3157. I0525 11:27:19.292968 138703 solver.cpp:340] Test net output #0: accuracy = 0.01875
  3158. I0525 11:27:19.295284 138703 solver.cpp:340] Test net output #1: loss = 4.52877 (* 1 = 4.52877 loss)
  3159. I0525 11:27:21.688118 138703 solver.cpp:214] Iteration 8600, loss = 4.52171
  3160. I0525 11:27:21.688168 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3161. I0525 11:27:21.688185 138703 solver.cpp:229] Train net output #1: loss = 4.52171 (* 1 = 4.52171 loss)
  3162. I0525 11:27:21.688204 138703 solver.cpp:489] Iteration 8600, lr = 0.001
  3163. I0525 11:28:29.719497 138703 solver.cpp:214] Iteration 8620, loss = 4.57015
  3164. I0525 11:28:29.719655 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3165. I0525 11:28:29.719673 138703 solver.cpp:229] Train net output #1: loss = 4.57015 (* 1 = 4.57015 loss)
  3166. I0525 11:28:29.719691 138703 solver.cpp:489] Iteration 8620, lr = 0.001
  3167. I0525 11:29:38.666908 138703 solver.cpp:214] Iteration 8640, loss = 4.45159
  3168. I0525 11:29:38.667049 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3169. I0525 11:29:38.667064 138703 solver.cpp:229] Train net output #1: loss = 4.45159 (* 1 = 4.45159 loss)
  3170. I0525 11:29:38.667078 138703 solver.cpp:489] Iteration 8640, lr = 0.001
  3171. I0525 11:30:46.905464 138703 solver.cpp:214] Iteration 8660, loss = 4.56944
  3172. I0525 11:30:46.905645 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3173. I0525 11:30:46.905685 138703 solver.cpp:229] Train net output #1: loss = 4.56944 (* 1 = 4.56944 loss)
  3174. I0525 11:30:46.905709 138703 solver.cpp:489] Iteration 8660, lr = 0.001
  3175. I0525 11:31:59.675557 138703 solver.cpp:214] Iteration 8680, loss = 4.51663
  3176. I0525 11:31:59.675704 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3177. I0525 11:31:59.675720 138703 solver.cpp:229] Train net output #1: loss = 4.51663 (* 1 = 4.51663 loss)
  3178. I0525 11:31:59.675734 138703 solver.cpp:489] Iteration 8680, lr = 0.001
  3179. I0525 11:33:11.022948 138703 solver.cpp:291] Iteration 8700, Testing net (#0)
  3180. I0525 11:35:38.398097 138703 solver.cpp:340] Test net output #0: accuracy = 0.02
  3181. I0525 11:35:38.398270 138703 solver.cpp:340] Test net output #1: loss = 4.54496 (* 1 = 4.54496 loss)
  3182. I0525 11:35:40.766269 138703 solver.cpp:214] Iteration 8700, loss = 4.59022
  3183. I0525 11:35:40.766316 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3184. I0525 11:35:40.766332 138703 solver.cpp:229] Train net output #1: loss = 4.59022 (* 1 = 4.59022 loss)
  3185. I0525 11:35:40.766351 138703 solver.cpp:489] Iteration 8700, lr = 0.001
  3186. I0525 11:36:50.397089 138703 solver.cpp:214] Iteration 8720, loss = 4.52055
  3187. I0525 11:36:50.397248 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3188. I0525 11:36:50.397264 138703 solver.cpp:229] Train net output #1: loss = 4.52055 (* 1 = 4.52055 loss)
  3189. I0525 11:36:50.397275 138703 solver.cpp:489] Iteration 8720, lr = 0.001
  3190. I0525 11:37:55.695863 138703 solver.cpp:214] Iteration 8740, loss = 4.52334
  3191. I0525 11:37:55.696074 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3192. I0525 11:37:55.696096 138703 solver.cpp:229] Train net output #1: loss = 4.52334 (* 1 = 4.52334 loss)
  3193. I0525 11:37:55.696113 138703 solver.cpp:489] Iteration 8740, lr = 0.001
  3194. I0525 11:39:07.503345 138703 solver.cpp:214] Iteration 8760, loss = 4.64926
  3195. I0525 11:39:07.503514 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3196. I0525 11:39:07.503535 138703 solver.cpp:229] Train net output #1: loss = 4.64926 (* 1 = 4.64926 loss)
  3197. I0525 11:39:07.503553 138703 solver.cpp:489] Iteration 8760, lr = 0.001
  3198. I0525 11:40:22.066087 138703 solver.cpp:214] Iteration 8780, loss = 4.49431
  3199. I0525 11:40:22.066241 138703 solver.cpp:229] Train net output #0: accuracy = 0.0625
  3200. I0525 11:40:22.066256 138703 solver.cpp:229] Train net output #1: loss = 4.49431 (* 1 = 4.49431 loss)
  3201. I0525 11:40:22.066268 138703 solver.cpp:489] Iteration 8780, lr = 0.001
  3202. I0525 11:41:33.129115 138703 solver.cpp:291] Iteration 8800, Testing net (#0)
  3203. I0525 11:44:43.096940 138703 solver.cpp:340] Test net output #0: accuracy = 0.0191667
  3204. I0525 11:44:43.097108 138703 solver.cpp:340] Test net output #1: loss = 4.53665 (* 1 = 4.53665 loss)
  3205. I0525 11:44:44.890193 138703 solver.cpp:214] Iteration 8800, loss = 4.51287
  3206. I0525 11:44:44.890239 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3207. I0525 11:44:44.890252 138703 solver.cpp:229] Train net output #1: loss = 4.51287 (* 1 = 4.51287 loss)
  3208. I0525 11:44:44.890265 138703 solver.cpp:489] Iteration 8800, lr = 0.001
  3209. I0525 11:45:54.171449 138703 solver.cpp:214] Iteration 8820, loss = 4.51586
  3210. I0525 11:45:54.171597 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3211. I0525 11:45:54.171613 138703 solver.cpp:229] Train net output #1: loss = 4.51586 (* 1 = 4.51586 loss)
  3212. I0525 11:45:54.171625 138703 solver.cpp:489] Iteration 8820, lr = 0.001
  3213. I0525 11:47:09.147394 138703 solver.cpp:214] Iteration 8840, loss = 4.58221
  3214. I0525 11:47:09.147536 138703 solver.cpp:229] Train net output #0: accuracy = 0
  3215. I0525 11:47:09.147550 138703 solver.cpp:229] Train net output #1: loss = 4.58221 (* 1 = 4.58221 loss)
  3216. I0525 11:47:09.147563 138703 solver.cpp:489] Iteration 8840, lr = 0.001
  3217. I0525 11:48:23.683918 138703 solver.cpp:214] Iteration 8860, loss = 4.58626
  3218. I0525 11:48:23.684118 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3219. I0525 11:48:23.684165 138703 solver.cpp:229] Train net output #1: loss = 4.58626 (* 1 = 4.58626 loss)
  3220. I0525 11:48:23.684239 138703 solver.cpp:489] Iteration 8860, lr = 0.001
  3221. I0525 11:49:35.063756 138703 solver.cpp:214] Iteration 8880, loss = 4.54849
  3222. I0525 11:49:35.063922 138703 solver.cpp:229] Train net output #0: accuracy = 0.03125
  3223. I0525 11:49:35.063937 138703 solver.cpp:229] Train net output #1: loss = 4.54849 (* 1 = 4.54849 loss)
  3224. I0525 11:49:35.063952 138703 solver.cpp:489] Iteration 8880, lr = 0.001
  3225. I0525 11:50:42.463621 138703 solver.cpp:291] Iteration 8900, Testing net (#0)
  3226. I0525 11:54:46.888116 138703 solver.cpp:340] Test net output #0: accuracy = 0.0185417
  3227. I0525 11:54:46.888274 138703 solver.cpp:340] Test net output #1: loss = 4.55445 (* 1 = 4.55445 loss)
  3228. I0525 11:54:49.255123 138703 solver.cpp:214] Iteration 8900, loss = 4.44181
  3229. I0525 11:54:49.255165 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3230. I0525 11:54:49.255182 138703 solver.cpp:229] Train net output #1: loss = 4.44181 (* 1 = 4.44181 loss)
  3231. I0525 11:54:49.255198 138703 solver.cpp:489] Iteration 8900, lr = 0.001
  3232. I0525 11:56:01.773797 138703 solver.cpp:214] Iteration 8920, loss = 4.57153
  3233. I0525 11:56:01.775621 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3234. I0525 11:56:01.775638 138703 solver.cpp:229] Train net output #1: loss = 4.57153 (* 1 = 4.57153 loss)
  3235. I0525 11:56:01.775651 138703 solver.cpp:489] Iteration 8920, lr = 0.001
  3236. I0525 11:57:13.645099 138703 solver.cpp:214] Iteration 8940, loss = 4.56247
  3237. I0525 11:57:13.645294 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3238. I0525 11:57:13.645310 138703 solver.cpp:229] Train net output #1: loss = 4.56247 (* 1 = 4.56247 loss)
  3239. I0525 11:57:13.645324 138703 solver.cpp:489] Iteration 8940, lr = 0.001
  3240. I0525 11:58:19.459451 138703 solver.cpp:214] Iteration 8960, loss = 4.48509
  3241. I0525 11:58:19.459609 138703 solver.cpp:229] Train net output #0: accuracy = 0.078125
  3242. I0525 11:58:19.459630 138703 solver.cpp:229] Train net output #1: loss = 4.48509 (* 1 = 4.48509 loss)
  3243. I0525 11:58:19.459646 138703 solver.cpp:489] Iteration 8960, lr = 0.001
  3244. I0525 11:59:24.668808 138703 solver.cpp:214] Iteration 8980, loss = 4.54418
  3245. I0525 11:59:24.671639 138703 solver.cpp:229] Train net output #0: accuracy = 0.015625
  3246. I0525 11:59:24.671663 138703 solver.cpp:229] Train net output #1: loss = 4.54418 (* 1 = 4.54418 loss)
  3247. I0525 11:59:24.671682 138703 solver.cpp:489] Iteration 8980, lr = 0.001
  3248. I0525 12:00:35.596009 138703 solver.cpp:291] Iteration 9000, Testing net (#0)
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!