train.sh.o62106

reading text file
0/7350 (epoch 0), train_loss = 5.037, time/batch = 1.482
model saved to data/example/model.ckpt
1/7350 (epoch 0), train_loss = 4.316, time/batch = 0.229
2/7350 (epoch 0), train_loss = 3.728, time/batch = 0.363
3/7350 (epoch 0), train_loss = 3.541, time/batch = 0.369
4/7350 (epoch 0), train_loss = 3.476, time/batch = 0.367
5/7350 (epoch 0), train_loss = 3.354, time/batch = 0.369
6/7350 (epoch 0), train_loss = 3.257, time/batch = 0.359
7/7350 (epoch 0), train_loss = 3.183, time/batch = 0.366
8/7350 (epoch 0), train_loss = 3.274, time/batch = 0.354
9/7350 (epoch 0), train_loss = 3.248, time/batch = 0.354
10/7350 (epoch 0), train_loss = 3.234, time/batch = 0.355
11/7350 (epoch 0), train_loss = 3.237, time/batch = 0.357
12/7350 (epoch 0), train_loss = 3.227, time/batch = 0.355
13/7350 (epoch 0), train_loss = 3.194, time/batch = 0.367
14/7350 (epoch 0), train_loss = 3.175, time/batch = 0.363
15/7350 (epoch 0), train_loss = 3.166, time/batch = 0.359
16/7350 (epoch 0), train_loss = 3.199, time/batch = 0.370
17/7350 (epoch 0), train_loss = 3.121, time/batch = 0.372
18/7350 (epoch 0), train_loss = 3.141, time/batch = 0.371
19/7350 (epoch 0), train_loss = 3.144, time/batch = 0.360
20/7350 (epoch 0), train_loss = 3.148, time/batch = 0.350
21/7350 (epoch 0), train_loss = 3.188, time/batch = 0.359
22/7350 (epoch 0), train_loss = 3.135, time/batch = 0.358
23/7350 (epoch 0), train_loss = 3.141, time/batch = 0.357
24/7350 (epoch 0), train_loss = 3.139, time/batch = 0.363
25/7350 (epoch 0), train_loss = 3.120, time/batch = 0.363
26/7350 (epoch 0), train_loss = 3.123, time/batch = 0.367
27/7350 (epoch 0), train_loss = 3.154, time/batch = 0.353
28/7350 (epoch 0), train_loss = 3.143, time/batch = 0.363
29/7350 (epoch 0), train_loss = 3.170, time/batch = 0.354
30/7350 (epoch 0), train_loss = 3.106, time/batch = 0.377
31/7350 (epoch 0), train_loss = 3.125, time/batch = 0.355
32/7350 (epoch 0), train_loss = 3.118, time/batch = 0.350
33/7350 (epoch 0), train_loss = 3.081, time/batch = 0.352
34/7350 (epoch 0), train_loss = 3.177, time/batch = 0.368
35/7350 (epoch 0), train_loss = 3.130, time/batch = 0.365
36/7350 (epoch 0), train_loss = 3.125, time/batch = 0.359
37/7350 (epoch 0), train_loss = 3.127, time/batch = 0.358
38/7350 (epoch 0), train_loss = 3.135, time/batch = 0.361
39/7350 (epoch 0), train_loss = 3.141, time/batch = 0.365
40/7350 (epoch 0), train_loss = 3.111, time/batch = 0.359
41/7350 (epoch 0), train_loss = 3.120, time/batch = 0.361
42/7350 (epoch 0), train_loss = 3.117, time/batch = 0.359
43/7350 (epoch 0), train_loss = 3.154, time/batch = 0.354
44/7350 (epoch 0), train_loss = 3.130, time/batch = 0.362
45/7350 (epoch 0), train_loss = 3.102, time/batch = 0.363
46/7350 (epoch 0), train_loss = 3.081, time/batch = 0.363
47/7350 (epoch 0), train_loss = 3.131, time/batch = 0.353
48/7350 (epoch 0), train_loss = 3.112, time/batch = 0.362
49/7350 (epoch 0), train_loss = 3.148, time/batch = 0.357
50/7350 (epoch 0), train_loss = 3.152, time/batch = 0.361
51/7350 (epoch 0), train_loss = 3.180, time/batch = 0.372
52/7350 (epoch 0), train_loss = 3.172, time/batch = 0.353
53/7350 (epoch 0), train_loss = 3.119, time/batch = 0.366
54/7350 (epoch 0), train_loss = 3.162, time/batch = 0.366
55/7350 (epoch 0), train_loss = 3.164, time/batch = 0.354
56/7350 (epoch 0), train_loss = 3.129, time/batch = 0.360
57/7350 (epoch 0), train_loss = 3.136, time/batch = 0.354
58/7350 (epoch 0), train_loss = 3.143, time/batch = 0.362
59/7350 (epoch 0), train_loss = 3.093, time/batch = 0.345
60/7350 (epoch 0), train_loss = 3.124, time/batch = 0.366
61/7350 (epoch 0), train_loss = 3.110, time/batch = 0.348
62/7350 (epoch 0), train_loss = 3.130, time/batch = 0.347
63/7350 (epoch 0), train_loss = 3.132, time/batch = 0.358
64/7350 (epoch 0), train_loss = 3.194, time/batch = 0.362
65/7350 (epoch 0), train_loss = 3.119, time/batch = 0.359
66/7350 (epoch 0), train_loss = 3.102, time/batch = 0.344
67/7350 (epoch 0), train_loss = 3.157, time/batch = 0.359
68/7350 (epoch 0), train_loss = 3.110, time/batch = 0.363
69/7350 (epoch 0), train_loss = 3.103, time/batch = 0.364
70/7350 (epoch 0), train_loss = 3.110, time/batch = 0.354
71/7350 (epoch 0), train_loss = 3.119, time/batch = 0.366
72/7350 (epoch 0), train_loss = 3.156, time/batch = 0.361
73/7350 (epoch 0), train_loss = 3.123, time/batch = 0.361
74/7350 (epoch 0), train_loss = 3.095, time/batch = 0.365
75/7350 (epoch 0), train_loss = 3.116, time/batch = 0.367
76/7350 (epoch 0), train_loss = 3.216, time/batch = 0.357
77/7350 (epoch 0), train_loss = 3.142, time/batch = 0.351
78/7350 (epoch 0), train_loss = 3.147, time/batch = 0.357
79/7350 (epoch 0), train_loss = 3.123, time/batch = 0.363
80/7350 (epoch 0), train_loss = 3.109, time/batch = 0.369
81/7350 (epoch 0), train_loss = 3.059, time/batch = 0.353
82/7350 (epoch 0), train_loss = 3.068, time/batch = 0.363
83/7350 (epoch 0), train_loss = 3.059, time/batch = 0.352
84/7350 (epoch 0), train_loss = 3.008, time/batch = 0.360
85/7350 (epoch 0), train_loss = 3.031, time/batch = 0.358
86/7350 (epoch 0), train_loss = 2.983, time/batch = 0.362
87/7350 (epoch 0), train_loss = 2.997, time/batch = 0.358
88/7350 (epoch 0), train_loss = 2.997, time/batch = 0.352
89/7350 (epoch 0), train_loss = 3.045, time/batch = 0.371
90/7350 (epoch 0), train_loss = 2.980, time/batch = 0.364
91/7350 (epoch 0), train_loss = 2.958, time/batch = 0.358
92/7350 (epoch 0), train_loss = 2.916, time/batch = 0.358
93/7350 (epoch 0), train_loss = 2.941, time/batch = 0.353
94/7350 (epoch 0), train_loss = 2.954, time/batch = 0.365
95/7350 (epoch 0), train_loss = 2.971, time/batch = 0.364
96/7350 (epoch 0), train_loss = 2.988, time/batch = 0.364
97/7350 (epoch 0), train_loss = 2.954, time/batch = 0.364
98/7350 (epoch 0), train_loss = 3.067, time/batch = 0.347
99/7350 (epoch 0), train_loss = 2.895, time/batch = 0.355
100/7350 (epoch 0), train_loss = 2.962, time/batch = 0.352
101/7350 (epoch 0), train_loss = 2.909, time/batch = 0.346
102/7350 (epoch 0), train_loss = 2.989, time/batch = 0.362
103/7350 (epoch 0), train_loss = 2.943, time/batch = 0.358
104/7350 (epoch 0), train_loss = 2.899, time/batch = 0.361
105/7350 (epoch 0), train_loss = 2.897, time/batch = 0.358
106/7350 (epoch 0), train_loss = 2.835, time/batch = 0.369
107/7350 (epoch 0), train_loss = 2.844, time/batch = 0.360
108/7350 (epoch 0), train_loss = 2.845, time/batch = 0.354
109/7350 (epoch 0), train_loss = 2.861, time/batch = 0.361
110/7350 (epoch 0), train_loss = 2.870, time/batch = 0.352
111/7350 (epoch 0), train_loss = 2.839, time/batch = 0.364
112/7350 (epoch 0), train_loss = 2.840, time/batch = 0.353
113/7350 (epoch 0), train_loss = 2.759, time/batch = 0.366
114/7350 (epoch 0), train_loss = 2.840, time/batch = 0.363
115/7350 (epoch 0), train_loss = 2.792, time/batch = 0.364
116/7350 (epoch 0), train_loss = 2.801, time/batch = 0.362
117/7350 (epoch 0), train_loss = 2.797, time/batch = 0.353
118/7350 (epoch 0), train_loss = 2.844, time/batch = 0.363
119/7350 (epoch 0), train_loss = 2.794, time/batch = 0.363
120/7350 (epoch 0), train_loss = 2.808, time/batch = 0.367
121/7350 (epoch 0), train_loss = 2.784, time/batch = 0.347
122/7350 (epoch 0), train_loss = 2.768, time/batch = 0.373
123/7350 (epoch 0), train_loss = 2.740, time/batch = 0.355
124/7350 (epoch 0), train_loss = 2.747, time/batch = 0.351
125/7350 (epoch 0), train_loss = 2.745, time/batch = 0.360
126/7350 (epoch 0), train_loss = 2.689, time/batch = 0.354
127/7350 (epoch 0), train_loss = 2.728, time/batch = 0.355
128/7350 (epoch 0), train_loss = 2.716, time/batch = 0.360
129/7350 (epoch 0), train_loss = 2.711, time/batch = 0.358
130/7350 (epoch 0), train_loss = 2.667, time/batch = 0.355
131/7350 (epoch 0), train_loss = 2.651, time/batch = 0.372
132/7350 (epoch 0), train_loss = 2.717, time/batch = 0.356
133/7350 (epoch 0), train_loss = 2.687, time/batch = 0.356
134/7350 (epoch 0), train_loss = 2.684, time/batch = 0.359
135/7350 (epoch 0), train_loss = 2.665, time/batch = 0.358
136/7350 (epoch 0), train_loss = 2.641, time/batch = 0.364
137/7350 (epoch 0), train_loss = 2.608, time/batch = 0.363
138/7350 (epoch 0), train_loss = 2.728, time/batch = 0.357
139/7350 (epoch 0), train_loss = 2.646, time/batch = 0.360
140/7350 (epoch 0), train_loss = 2.598, time/batch = 0.362
141/7350 (epoch 0), train_loss = 2.597, time/batch = 0.350
142/7350 (epoch 0), train_loss = 2.636, time/batch = 0.360
143/7350 (epoch 0), train_loss = 2.549, time/batch = 0.349
144/7350 (epoch 0), train_loss = 2.613, time/batch = 0.363
145/7350 (epoch 0), train_loss = 2.588, time/batch = 0.366
146/7350 (epoch 0), train_loss = 2.637, time/batch = 0.356
147/7350 (epoch 1), train_loss = 2.759, time/batch = 0.362
148/7350 (epoch 1), train_loss = 2.588, time/batch = 0.367
149/7350 (epoch 1), train_loss = 2.560, time/batch = 0.352
150/7350 (epoch 1), train_loss = 2.588, time/batch = 0.372
151/7350 (epoch 1), train_loss = 2.587, time/batch = 0.355
152/7350 (epoch 1), train_loss = 2.566, time/batch = 0.354
153/7350 (epoch 1), train_loss = 2.528, time/batch = 0.351
154/7350 (epoch 1), train_loss = 2.512, time/batch = 0.343
155/7350 (epoch 1), train_loss = 2.593, time/batch = 0.357
156/7350 (epoch 1), train_loss = 2.554, time/batch = 0.362
157/7350 (epoch 1), train_loss = 2.574, time/batch = 0.374
158/7350 (epoch 1), train_loss = 2.541, time/batch = 0.349
159/7350 (epoch 1), train_loss = 2.564, time/batch = 0.354
160/7350 (epoch 1), train_loss = 2.551, time/batch = 0.355
161/7350 (epoch 1), train_loss = 2.436, time/batch = 0.364
162/7350 (epoch 1), train_loss = 2.513, time/batch = 0.358
163/7350 (epoch 1), train_loss = 2.522, time/batch = 0.367
164/7350 (epoch 1), train_loss = 2.413, time/batch = 0.376
165/7350 (epoch 1), train_loss = 2.446, time/batch = 0.362
166/7350 (epoch 1), train_loss = 2.444, time/batch = 0.356
167/7350 (epoch 1), train_loss = 2.474, time/batch = 0.357
168/7350 (epoch 1), train_loss = 2.447, time/batch = 0.356
169/7350 (epoch 1), train_loss = 2.431, time/batch = 0.366
170/7350 (epoch 1), train_loss = 2.412, time/batch = 0.360
171/7350 (epoch 1), train_loss = 2.409, time/batch = 0.357
172/7350 (epoch 1), train_loss = 2.381, time/batch = 0.349
173/7350 (epoch 1), train_loss = 2.379, time/batch = 0.352
174/7350 (epoch 1), train_loss = 2.450, time/batch = 0.369
175/7350 (epoch 1), train_loss = 2.376, time/batch = 0.362
176/7350 (epoch 1), train_loss = 2.452, time/batch = 0.356
177/7350 (epoch 1), train_loss = 2.346, time/batch = 0.365
178/7350 (epoch 1), train_loss = 2.383, time/batch = 0.354
179/7350 (epoch 1), train_loss = 2.390, time/batch = 0.365
180/7350 (epoch 1), train_loss = 2.352, time/batch = 0.360
181/7350 (epoch 1), train_loss = 2.448, time/batch = 0.351
182/7350 (epoch 1), train_loss = 2.393, time/batch = 0.362
183/7350 (epoch 1), train_loss = 2.348, time/batch = 0.358
184/7350 (epoch 1), train_loss = 2.379, time/batch = 0.359
185/7350 (epoch 1), train_loss = 2.350, time/batch = 0.359
186/7350 (epoch 1), train_loss = 2.395, time/batch = 0.360
187/7350 (epoch 1), train_loss = 2.405, time/batch = 0.352
188/7350 (epoch 1), train_loss = 2.354, time/batch = 0.358
189/7350 (epoch 1), train_loss = 2.331, time/batch = 0.358
190/7350 (epoch 1), train_loss = 2.361, time/batch = 0.358
191/7350 (epoch 1), train_loss = 2.376, time/batch = 0.347
192/7350 (epoch 1), train_loss = 2.324, time/batch = 0.356
193/7350 (epoch 1), train_loss = 2.286, time/batch = 0.358
194/7350 (epoch 1), train_loss = 2.342, time/batch = 0.366
195/7350 (epoch 1), train_loss = 2.354, time/batch = 0.364
196/7350 (epoch 1), train_loss = 2.352, time/batch = 0.356
197/7350 (epoch 1), train_loss = 2.351, time/batch = 0.363
198/7350 (epoch 1), train_loss = 2.437, time/batch = 0.357
199/7350 (epoch 1), train_loss = 2.373, time/batch = 0.359
200/7350 (epoch 1), train_loss = 2.337, time/batch = 0.371
201/7350 (epoch 1), train_loss = 2.328, time/batch = 0.360
202/7350 (epoch 1), train_loss = 2.340, time/batch = 0.355
203/7350 (epoch 1), train_loss = 2.309, time/batch = 0.352
204/7350 (epoch 1), train_loss = 2.346, time/batch = 0.355
205/7350 (epoch 1), train_loss = 2.302, time/batch = 0.349
206/7350 (epoch 1), train_loss = 2.274, time/batch = 0.365
207/7350 (epoch 1), train_loss = 2.305, time/batch = 0.377
208/7350 (epoch 1), train_loss = 2.314, time/batch = 0.357
209/7350 (epoch 1), train_loss = 2.305, time/batch = 0.354
210/7350 (epoch 1), train_loss = 2.335, time/batch = 0.356
211/7350 (epoch 1), train_loss = 2.344, time/batch = 0.363
212/7350 (epoch 1), train_loss = 2.283, time/batch = 0.361
213/7350 (epoch 1), train_loss = 2.258, time/batch = 0.367
214/7350 (epoch 1), train_loss = 2.279, time/batch = 0.356
215/7350 (epoch 1), train_loss = 2.274, time/batch = 0.348
216/7350 (epoch 1), train_loss = 2.283, time/batch = 0.357
217/7350 (epoch 1), train_loss = 2.301, time/batch = 0.363
218/7350 (epoch 1), train_loss = 2.247, time/batch = 0.348
219/7350 (epoch 1), train_loss = 2.340, time/batch = 0.361
220/7350 (epoch 1), train_loss = 2.269, time/batch = 0.357
221/7350 (epoch 1), train_loss = 2.253, time/batch = 0.356
222/7350 (epoch 1), train_loss = 2.301, time/batch = 0.358
223/7350 (epoch 1), train_loss = 2.363, time/batch = 0.356
224/7350 (epoch 1), train_loss = 2.316, time/batch = 0.355
225/7350 (epoch 1), train_loss = 2.350, time/batch = 0.348
226/7350 (epoch 1), train_loss = 2.285, time/batch = 0.351
227/7350 (epoch 1), train_loss = 2.269, time/batch = 0.362
228/7350 (epoch 1), train_loss = 2.212, time/batch = 0.345
229/7350 (epoch 1), train_loss = 2.237, time/batch = 0.368
230/7350 (epoch 1), train_loss = 2.277, time/batch = 0.356
231/7350 (epoch 1), train_loss = 2.187, time/batch = 0.361
232/7350 (epoch 1), train_loss = 2.252, time/batch = 0.362
233/7350 (epoch 1), train_loss = 2.225, time/batch = 0.356
234/7350 (epoch 1), train_loss = 2.200, time/batch = 0.350
235/7350 (epoch 1), train_loss = 2.256, time/batch = 0.355
236/7350 (epoch 1), train_loss = 2.290, time/batch = 0.355
237/7350 (epoch 1), train_loss = 2.209, time/batch = 0.370
238/7350 (epoch 1), train_loss = 2.222, time/batch = 0.362
239/7350 (epoch 1), train_loss = 2.149, time/batch = 0.359
240/7350 (epoch 1), train_loss = 2.197, time/batch = 0.364
241/7350 (epoch 1), train_loss = 2.205, time/batch = 0.355
242/7350 (epoch 1), train_loss = 2.228, time/batch = 0.363
243/7350 (epoch 1), train_loss = 2.262, time/batch = 0.356
244/7350 (epoch 1), train_loss = 2.218, time/batch = 0.356
245/7350 (epoch 1), train_loss = 2.314, time/batch = 0.354
246/7350 (epoch 1), train_loss = 2.201, time/batch = 0.355
247/7350 (epoch 1), train_loss = 2.229, time/batch = 0.363
248/7350 (epoch 1), train_loss = 2.161, time/batch = 0.352
249/7350 (epoch 1), train_loss = 2.233, time/batch = 0.363
250/7350 (epoch 1), train_loss = 2.246, time/batch = 0.366
251/7350 (epoch 1), train_loss = 2.209, time/batch = 0.345
252/7350 (epoch 1), train_loss = 2.268, time/batch = 0.365
253/7350 (epoch 1), train_loss = 2.147, time/batch = 0.361
254/7350 (epoch 1), train_loss = 2.167, time/batch = 0.357
255/7350 (epoch 1), train_loss = 2.169, time/batch = 0.356
256/7350 (epoch 1), train_loss = 2.148, time/batch = 0.350
257/7350 (epoch 1), train_loss = 2.224, time/batch = 0.359
258/7350 (epoch 1), train_loss = 2.219, time/batch = 0.352
259/7350 (epoch 1), train_loss = 2.231, time/batch = 0.354
260/7350 (epoch 1), train_loss = 2.103, time/batch = 0.354
261/7350 (epoch 1), train_loss = 2.195, time/batch = 0.347
262/7350 (epoch 1), train_loss = 2.156, time/batch = 0.348
263/7350 (epoch 1), train_loss = 2.199, time/batch = 0.371
264/7350 (epoch 1), train_loss = 2.188, time/batch = 0.359
265/7350 (epoch 1), train_loss = 2.221, time/batch = 0.356
266/7350 (epoch 1), train_loss = 2.193, time/batch = 0.354
267/7350 (epoch 1), train_loss = 2.197, time/batch = 0.358
268/7350 (epoch 1), train_loss = 2.158, time/batch = 0.358
269/7350 (epoch 1), train_loss = 2.179, time/batch = 0.365
270/7350 (epoch 1), train_loss = 2.165, time/batch = 0.357
271/7350 (epoch 1), train_loss = 2.184, time/batch = 0.345
272/7350 (epoch 1), train_loss = 2.170, time/batch = 0.364
273/7350 (epoch 1), train_loss = 2.090, time/batch = 0.352
274/7350 (epoch 1), train_loss = 2.149, time/batch = 0.358
275/7350 (epoch 1), train_loss = 2.158, time/batch = 0.369
276/7350 (epoch 1), train_loss = 2.144, time/batch = 0.372
277/7350 (epoch 1), train_loss = 2.101, time/batch = 0.355
278/7350 (epoch 1), train_loss = 2.085, time/batch = 0.361
279/7350 (epoch 1), train_loss = 2.135, time/batch = 0.358
280/7350 (epoch 1), train_loss = 2.108, time/batch = 0.354
281/7350 (epoch 1), train_loss = 2.127, time/batch = 0.361
282/7350 (epoch 1), train_loss = 2.169, time/batch = 0.363
283/7350 (epoch 1), train_loss = 2.106, time/batch = 0.357
284/7350 (epoch 1), train_loss = 2.077, time/batch = 0.353
285/7350 (epoch 1), train_loss = 2.188, time/batch = 0.353
286/7350 (epoch 1), train_loss = 2.140, time/batch = 0.355
287/7350 (epoch 1), train_loss = 2.082, time/batch = 0.353
288/7350 (epoch 1), train_loss = 2.144, time/batch = 0.361
289/7350 (epoch 1), train_loss = 2.150, time/batch = 0.358
290/7350 (epoch 1), train_loss = 2.069, time/batch = 0.354
291/7350 (epoch 1), train_loss = 2.156, time/batch = 0.363
292/7350 (epoch 1), train_loss = 2.114, time/batch = 0.363
293/7350 (epoch 1), train_loss = 2.181, time/batch = 0.352
294/7350 (epoch 2), train_loss = 2.314, time/batch = 0.362
295/7350 (epoch 2), train_loss = 2.147, time/batch = 0.356
296/7350 (epoch 2), train_loss = 2.136, time/batch = 0.364
297/7350 (epoch 2), train_loss = 2.169, time/batch = 0.362
298/7350 (epoch 2), train_loss = 2.149, time/batch = 0.352
299/7350 (epoch 2), train_loss = 2.159, time/batch = 0.363
300/7350 (epoch 2), train_loss = 2.132, time/batch = 0.361
301/7350 (epoch 2), train_loss = 2.103, time/batch = 0.354
302/7350 (epoch 2), train_loss = 2.159, time/batch = 0.349
303/7350 (epoch 2), train_loss = 2.155, time/batch = 0.368
304/7350 (epoch 2), train_loss = 2.149, time/batch = 0.368
305/7350 (epoch 2), train_loss = 2.113, time/batch = 0.360
306/7350 (epoch 2), train_loss = 2.151, time/batch = 0.359
307/7350 (epoch 2), train_loss = 2.164, time/batch = 0.349
308/7350 (epoch 2), train_loss = 2.022, time/batch = 0.357
309/7350 (epoch 2), train_loss = 2.093, time/batch = 0.361
310/7350 (epoch 2), train_loss = 2.139, time/batch = 0.359
311/7350 (epoch 2), train_loss = 2.051, time/batch = 0.366
312/7350 (epoch 2), train_loss = 2.093, time/batch = 0.361
313/7350 (epoch 2), train_loss = 2.048, time/batch = 0.355
314/7350 (epoch 2), train_loss = 2.064, time/batch = 0.366
315/7350 (epoch 2), train_loss = 2.069, time/batch = 0.354
316/7350 (epoch 2), train_loss = 2.064, time/batch = 0.339
317/7350 (epoch 2), train_loss = 2.028, time/batch = 0.368
318/7350 (epoch 2), train_loss = 2.047, time/batch = 0.353
319/7350 (epoch 2), train_loss = 2.039, time/batch = 0.366
320/7350 (epoch 2), train_loss = 1.985, time/batch = 0.364
321/7350 (epoch 2), train_loss = 2.083, time/batch = 0.355
322/7350 (epoch 2), train_loss = 2.013, time/batch = 0.359
323/7350 (epoch 2), train_loss = 2.104, time/batch = 0.354
324/7350 (epoch 2), train_loss = 2.003, time/batch = 0.354
325/7350 (epoch 2), train_loss = 2.046, time/batch = 0.366
326/7350 (epoch 2), train_loss = 2.036, time/batch = 0.351
327/7350 (epoch 2), train_loss = 2.029, time/batch = 0.357
328/7350 (epoch 2), train_loss = 2.125, time/batch = 0.372
329/7350 (epoch 2), train_loss = 2.031, time/batch = 0.359
330/7350 (epoch 2), train_loss = 2.032, time/batch = 0.369
331/7350 (epoch 2), train_loss = 2.058, time/batch = 0.370
332/7350 (epoch 2), train_loss = 2.031, time/batch = 0.365
333/7350 (epoch 2), train_loss = 2.047, time/batch = 0.361
334/7350 (epoch 2), train_loss = 2.063, time/batch = 0.350
335/7350 (epoch 2), train_loss = 2.022, time/batch = 0.354
336/7350 (epoch 2), train_loss = 2.030, time/batch = 0.357
337/7350 (epoch 2), train_loss = 2.010, time/batch = 0.353
338/7350 (epoch 2), train_loss = 2.042, time/batch = 0.360
339/7350 (epoch 2), train_loss = 2.011, time/batch = 0.365
340/7350 (epoch 2), train_loss = 1.979, time/batch = 0.359
341/7350 (epoch 2), train_loss = 2.027, time/batch = 0.359
342/7350 (epoch 2), train_loss = 2.005, time/batch = 0.360
343/7350 (epoch 2), train_loss = 2.031, time/batch = 0.357
344/7350 (epoch 2), train_loss = 2.011, time/batch = 0.351
345/7350 (epoch 2), train_loss = 2.074, time/batch = 0.362
346/7350 (epoch 2), train_loss = 1.998, time/batch = 0.361
347/7350 (epoch 2), train_loss = 2.026, time/batch = 0.360
348/7350 (epoch 2), train_loss = 1.991, time/batch = 0.350
349/7350 (epoch 2), train_loss = 2.017, time/batch = 0.358
350/7350 (epoch 2), train_loss = 1.995, time/batch = 0.356
351/7350 (epoch 2), train_loss = 2.011, time/batch = 0.367
352/7350 (epoch 2), train_loss = 1.987, time/batch = 0.354
353/7350 (epoch 2), train_loss = 1.951, time/batch = 0.370
354/7350 (epoch 2), train_loss = 1.996, time/batch = 0.357
355/7350 (epoch 2), train_loss = 2.002, time/batch = 0.363
356/7350 (epoch 2), train_loss = 1.993, time/batch = 0.358
357/7350 (epoch 2), train_loss = 2.040, time/batch = 0.353
358/7350 (epoch 2), train_loss = 2.029, time/batch = 0.367
359/7350 (epoch 2), train_loss = 1.961, time/batch = 0.357
360/7350 (epoch 2), train_loss = 1.964, time/batch = 0.354
361/7350 (epoch 2), train_loss = 1.966, time/batch = 0.368
362/7350 (epoch 2), train_loss = 1.964, time/batch = 0.363
363/7350 (epoch 2), train_loss = 1.982, time/batch = 0.355
364/7350 (epoch 2), train_loss = 2.000, time/batch = 0.352
365/7350 (epoch 2), train_loss = 1.956, time/batch = 0.346
366/7350 (epoch 2), train_loss = 2.038, time/batch = 0.361
367/7350 (epoch 2), train_loss = 1.998, time/batch = 0.362
368/7350 (epoch 2), train_loss = 1.959, time/batch = 0.356
369/7350 (epoch 2), train_loss = 2.013, time/batch = 0.348
370/7350 (epoch 2), train_loss = 2.040, time/batch = 0.368
371/7350 (epoch 2), train_loss = 2.024, time/batch = 0.351
372/7350 (epoch 2), train_loss = 2.028, time/batch = 0.343
373/7350 (epoch 2), train_loss = 2.011, time/batch = 0.350
374/7350 (epoch 2), train_loss = 1.973, time/batch = 0.364
375/7350 (epoch 2), train_loss = 1.920, time/batch = 0.355
376/7350 (epoch 2), train_loss = 1.937, time/batch = 0.360
377/7350 (epoch 2), train_loss = 1.992, time/batch = 0.353
378/7350 (epoch 2), train_loss = 1.928, time/batch = 0.350
379/7350 (epoch 2), train_loss = 1.969, time/batch = 0.354
380/7350 (epoch 2), train_loss = 1.948, time/batch = 0.354
381/7350 (epoch 2), train_loss = 1.923, time/batch = 0.353
382/7350 (epoch 2), train_loss = 1.968, time/batch = 0.351
383/7350 (epoch 2), train_loss = 2.003, time/batch = 0.376
384/7350 (epoch 2), train_loss = 1.938, time/batch = 0.365
385/7350 (epoch 2), train_loss = 1.944, time/batch = 0.362
386/7350 (epoch 2), train_loss = 1.859, time/batch = 0.353
387/7350 (epoch 2), train_loss = 1.912, time/batch = 0.364
388/7350 (epoch 2), train_loss = 1.903, time/batch = 0.360
389/7350 (epoch 2), train_loss = 1.935, time/batch = 0.355
390/7350 (epoch 2), train_loss = 1.963, time/batch = 0.366
391/7350 (epoch 2), train_loss = 1.928, time/batch = 0.366
392/7350 (epoch 2), train_loss = 2.010, time/batch = 0.354
393/7350 (epoch 2), train_loss = 1.923, time/batch = 0.372
394/7350 (epoch 2), train_loss = 1.957, time/batch = 0.353
395/7350 (epoch 2), train_loss = 1.874, time/batch = 0.369
396/7350 (epoch 2), train_loss = 1.970, time/batch = 0.358
397/7350 (epoch 2), train_loss = 1.965, time/batch = 0.365
398/7350 (epoch 2), train_loss = 1.917, time/batch = 0.371
399/7350 (epoch 2), train_loss = 1.974, time/batch = 0.354
400/7350 (epoch 2), train_loss = 1.883, time/batch = 0.365
401/7350 (epoch 2), train_loss = 1.927, time/batch = 0.366
402/7350 (epoch 2), train_loss = 1.889, time/batch = 0.359
403/7350 (epoch 2), train_loss = 1.863, time/batch = 0.353
404/7350 (epoch 2), train_loss = 1.947, time/batch = 0.351
405/7350 (epoch 2), train_loss = 1.935, time/batch = 0.355
406/7350 (epoch 2), train_loss = 1.982, time/batch = 0.365
407/7350 (epoch 2), train_loss = 1.854, time/batch = 0.357
408/7350 (epoch 2), train_loss = 1.937, time/batch = 0.357
409/7350 (epoch 2), train_loss = 1.881, time/batch = 0.356
410/7350 (epoch 2), train_loss = 1.924, time/batch = 0.367
411/7350 (epoch 2), train_loss = 1.947, time/batch = 0.362
412/7350 (epoch 2), train_loss = 1.963, time/batch = 0.365
413/7350 (epoch 2), train_loss = 1.923, time/batch = 0.358
414/7350 (epoch 2), train_loss = 1.956, time/batch = 0.357
415/7350 (epoch 2), train_loss = 1.875, time/batch = 0.355
416/7350 (epoch 2), train_loss = 1.913, time/batch = 0.345
417/7350 (epoch 2), train_loss = 1.886, time/batch = 0.346
418/7350 (epoch 2), train_loss = 1.925, time/batch = 0.353
419/7350 (epoch 2), train_loss = 1.914, time/batch = 0.366
420/7350 (epoch 2), train_loss = 1.842, time/batch = 0.373
421/7350 (epoch 2), train_loss = 1.891, time/batch = 0.373
422/7350 (epoch 2), train_loss = 1.924, time/batch = 0.359
423/7350 (epoch 2), train_loss = 1.873, time/batch = 0.368
424/7350 (epoch 2), train_loss = 1.863, time/batch = 0.361
425/7350 (epoch 2), train_loss = 1.846, time/batch = 0.368
426/7350 (epoch 2), train_loss = 1.889, time/batch = 0.353
427/7350 (epoch 2), train_loss = 1.856, time/batch = 0.363
428/7350 (epoch 2), train_loss = 1.874, time/batch = 0.355
429/7350 (epoch 2), train_loss = 1.917, time/batch = 0.356
430/7350 (epoch 2), train_loss = 1.856, time/batch = 0.351
431/7350 (epoch 2), train_loss = 1.820, time/batch = 0.348
432/7350 (epoch 2), train_loss = 1.928, time/batch = 0.345
433/7350 (epoch 2), train_loss = 1.881, time/batch = 0.363
434/7350 (epoch 2), train_loss = 1.831, time/batch = 0.355
435/7350 (epoch 2), train_loss = 1.892, time/batch = 0.360
436/7350 (epoch 2), train_loss = 1.916, time/batch = 0.363
437/7350 (epoch 2), train_loss = 1.826, time/batch = 0.351
438/7350 (epoch 2), train_loss = 1.929, time/batch = 0.352
439/7350 (epoch 2), train_loss = 1.901, time/batch = 0.368
440/7350 (epoch 2), train_loss = 1.936, time/batch = 0.360
441/7350 (epoch 3), train_loss = 2.076, time/batch = 0.364
442/7350 (epoch 3), train_loss = 1.913, time/batch = 0.355
443/7350 (epoch 3), train_loss = 1.898, time/batch = 0.366
444/7350 (epoch 3), train_loss = 1.929, time/batch = 0.350
445/7350 (epoch 3), train_loss = 1.920, time/batch = 0.364
446/7350 (epoch 3), train_loss = 1.947, time/batch = 0.356
447/7350 (epoch 3), train_loss = 1.909, time/batch = 0.365
448/7350 (epoch 3), train_loss = 1.880, time/batch = 0.351
449/7350 (epoch 3), train_loss = 1.950, time/batch = 0.353
450/7350 (epoch 3), train_loss = 1.928, time/batch = 0.347
451/7350 (epoch 3), train_loss = 1.923, time/batch = 0.361
452/7350 (epoch 3), train_loss = 1.861, time/batch = 0.357
453/7350 (epoch 3), train_loss = 1.905, time/batch = 0.362
454/7350 (epoch 3), train_loss = 1.934, time/batch = 0.362
455/7350 (epoch 3), train_loss = 1.806, time/batch = 0.359
456/7350 (epoch 3), train_loss = 1.860, time/batch = 0.360
457/7350 (epoch 3), train_loss = 1.910, time/batch = 0.357
458/7350 (epoch 3), train_loss = 1.837, time/batch = 0.357
459/7350 (epoch 3), train_loss = 1.861, time/batch = 0.358
460/7350 (epoch 3), train_loss = 1.824, time/batch = 0.368
461/7350 (epoch 3), train_loss = 1.841, time/batch = 0.351
462/7350 (epoch 3), train_loss = 1.866, time/batch = 0.355
463/7350 (epoch 3), train_loss = 1.832, time/batch = 0.360
464/7350 (epoch 3), train_loss = 1.824, time/batch = 0.352
465/7350 (epoch 3), train_loss = 1.848, time/batch = 0.372
466/7350 (epoch 3), train_loss = 1.849, time/batch = 0.358
467/7350 (epoch 3), train_loss = 1.773, time/batch = 0.347
468/7350 (epoch 3), train_loss = 1.867, time/batch = 0.358
469/7350 (epoch 3), train_loss = 1.784, time/batch = 0.355
470/7350 (epoch 3), train_loss = 1.916, time/batch = 0.355
471/7350 (epoch 3), train_loss = 1.788, time/batch = 0.367
472/7350 (epoch 3), train_loss = 1.845, time/batch = 0.363
473/7350 (epoch 3), train_loss = 1.836, time/batch = 0.354
474/7350 (epoch 3), train_loss = 1.829, time/batch = 0.355
475/7350 (epoch 3), train_loss = 1.915, time/batch = 0.380
476/7350 (epoch 3), train_loss = 1.823, time/batch = 0.353
477/7350 (epoch 3), train_loss = 1.834, time/batch = 0.360
478/7350 (epoch 3), train_loss = 1.877, time/batch = 0.356
479/7350 (epoch 3), train_loss = 1.830, time/batch = 0.362
480/7350 (epoch 3), train_loss = 1.824, time/batch = 0.359
481/7350 (epoch 3), train_loss = 1.881, time/batch = 0.367
482/7350 (epoch 3), train_loss = 1.813, time/batch = 0.353
483/7350 (epoch 3), train_loss = 1.866, time/batch = 0.351
484/7350 (epoch 3), train_loss = 1.800, time/batch = 0.373
485/7350 (epoch 3), train_loss = 1.851, time/batch = 0.360
486/7350 (epoch 3), train_loss = 1.862, time/batch = 0.360
487/7350 (epoch 3), train_loss = 1.806, time/batch = 0.361
488/7350 (epoch 3), train_loss = 1.862, time/batch = 0.364
489/7350 (epoch 3), train_loss = 1.804, time/batch = 0.357
490/7350 (epoch 3), train_loss = 1.832, time/batch = 0.366
491/7350 (epoch 3), train_loss = 1.817, time/batch = 0.366
492/7350 (epoch 3), train_loss = 1.883, time/batch = 0.343
493/7350 (epoch 3), train_loss = 1.796, time/batch = 0.359
494/7350 (epoch 3), train_loss = 1.857, time/batch = 0.347
495/7350 (epoch 3), train_loss = 1.802, time/batch = 0.358
496/7350 (epoch 3), train_loss = 1.823, time/batch = 0.357
497/7350 (epoch 3), train_loss = 1.806, time/batch = 0.350
498/7350 (epoch 3), train_loss = 1.810, time/batch = 0.347
499/7350 (epoch 3), train_loss = 1.797, time/batch = 0.358
500/7350 (epoch 3), train_loss = 1.772, time/batch = 0.363
501/7350 (epoch 3), train_loss = 1.817, time/batch = 0.363
502/7350 (epoch 3), train_loss = 1.807, time/batch = 0.351
503/7350 (epoch 3), train_loss = 1.813, time/batch = 0.356
504/7350 (epoch 3), train_loss = 1.866, time/batch = 0.362
505/7350 (epoch 3), train_loss = 1.862, time/batch = 0.353
506/7350 (epoch 3), train_loss = 1.756, time/batch = 0.342
507/7350 (epoch 3), train_loss = 1.796, time/batch = 0.362
508/7350 (epoch 3), train_loss = 1.789, time/batch = 0.356
509/7350 (epoch 3), train_loss = 1.776, time/batch = 0.356
510/7350 (epoch 3), train_loss = 1.814, time/batch = 0.367
511/7350 (epoch 3), train_loss = 1.825, time/batch = 0.361
512/7350 (epoch 3), train_loss = 1.776, time/batch = 0.348
513/7350 (epoch 3), train_loss = 1.857, time/batch = 0.357
514/7350 (epoch 3), train_loss = 1.812, time/batch = 0.358
515/7350 (epoch 3), train_loss = 1.782, time/batch = 0.349
516/7350 (epoch 3), train_loss = 1.828, time/batch = 0.368
517/7350 (epoch 3), train_loss = 1.838, time/batch = 0.351
518/7350 (epoch 3), train_loss = 1.850, time/batch = 0.352
519/7350 (epoch 3), train_loss = 1.836, time/batch = 0.367
520/7350 (epoch 3), train_loss = 1.814, time/batch = 0.358
521/7350 (epoch 3), train_loss = 1.810, time/batch = 0.351
522/7350 (epoch 3), train_loss = 1.738, time/batch = 0.358
523/7350 (epoch 3), train_loss = 1.769, time/batch = 0.367
524/7350 (epoch 3), train_loss = 1.835, time/batch = 0.350
525/7350 (epoch 3), train_loss = 1.760, time/batch = 0.351
526/7350 (epoch 3), train_loss = 1.811, time/batch = 0.356
527/7350 (epoch 3), train_loss = 1.776, time/batch = 0.359
528/7350 (epoch 3), train_loss = 1.758, time/batch = 0.355
529/7350 (epoch 3), train_loss = 1.773, time/batch = 0.355
530/7350 (epoch 3), train_loss = 1.824, time/batch = 0.357
531/7350 (epoch 3), train_loss = 1.763, time/batch = 0.370
532/7350 (epoch 3), train_loss = 1.766, time/batch = 0.361
533/7350 (epoch 3), train_loss = 1.702, time/batch = 0.357
534/7350 (epoch 3), train_loss = 1.746, time/batch = 0.357
535/7350 (epoch 3), train_loss = 1.720, time/batch = 0.353
536/7350 (epoch 3), train_loss = 1.744, time/batch = 0.358
537/7350 (epoch 3), train_loss = 1.774, time/batch = 0.371
538/7350 (epoch 3), train_loss = 1.767, time/batch = 0.359
539/7350 (epoch 3), train_loss = 1.814, time/batch = 0.352
540/7350 (epoch 3), train_loss = 1.766, time/batch = 0.352
541/7350 (epoch 3), train_loss = 1.786, time/batch = 0.366
542/7350 (epoch 3), train_loss = 1.701, time/batch = 0.353
543/7350 (epoch 3), train_loss = 1.809, time/batch = 0.359
544/7350 (epoch 3), train_loss = 1.824, time/batch = 0.354
545/7350 (epoch 3), train_loss = 1.742, time/batch = 0.361
546/7350 (epoch 3), train_loss = 1.811, time/batch = 0.355
547/7350 (epoch 3), train_loss = 1.722, time/batch = 0.358
548/7350 (epoch 3), train_loss = 1.782, time/batch = 0.366
549/7350 (epoch 3), train_loss = 1.733, time/batch = 0.352
550/7350 (epoch 3), train_loss = 1.688, time/batch = 0.361
551/7350 (epoch 3), train_loss = 1.795, time/batch = 0.368
552/7350 (epoch 3), train_loss = 1.783, time/batch = 0.358
553/7350 (epoch 3), train_loss = 1.835, time/batch = 0.355
554/7350 (epoch 3), train_loss = 1.705, time/batch = 0.350
555/7350 (epoch 3), train_loss = 1.798, time/batch = 0.364
556/7350 (epoch 3