Commit
·
6c2afd3
1
Parent(s):
1a092d4
Upload eval_log.json
Browse files- eval_log.json +635 -0
eval_log.json
ADDED
@@ -0,0 +1,635 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
2 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
3 |
+
INFO:root:Generate setting:
|
4 |
+
use true_prev_bspn=False
|
5 |
+
use true_prev_aspn=False
|
6 |
+
use true_db_pointer=False
|
7 |
+
use true_prev_resp=False
|
8 |
+
use true_curr_bspn=False
|
9 |
+
use true_curr_aspn=False
|
10 |
+
use_all_previous_context=True
|
11 |
+
INFO:root:***** Running Evaluation *****
|
12 |
+
INFO:root: Num Turns = 7372
|
13 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
14 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
15 |
+
INFO:root:Generate setting:
|
16 |
+
use true_prev_bspn=False
|
17 |
+
use true_prev_aspn=False
|
18 |
+
use true_db_pointer=False
|
19 |
+
use true_prev_resp=False
|
20 |
+
use true_curr_bspn=False
|
21 |
+
use true_curr_aspn=False
|
22 |
+
use_all_previous_context=True
|
23 |
+
INFO:root:***** Running Evaluation *****
|
24 |
+
INFO:root: Num Turns = 7372
|
25 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
26 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
27 |
+
INFO:root:Generate setting:
|
28 |
+
use true_prev_bspn=False
|
29 |
+
use true_prev_aspn=False
|
30 |
+
use true_db_pointer=False
|
31 |
+
use true_prev_resp=False
|
32 |
+
use true_curr_bspn=False
|
33 |
+
use true_curr_aspn=False
|
34 |
+
use_all_previous_context=True
|
35 |
+
INFO:root:***** Running Evaluation *****
|
36 |
+
INFO:root: Num Turns = 7372
|
37 |
+
INFO:root:inference time: 2.18 min
|
38 |
+
INFO:root:Scoring time: 0.02 min
|
39 |
+
INFO:root:validation [CTR] match: 93.00 success: 81.00 bleu: 14.31 score: 101.31
|
40 |
+
INFO:root:update eval results to logs_test/home-all_test.json
|
41 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
42 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
43 |
+
INFO:root:Generate setting:
|
44 |
+
use true_prev_bspn=False
|
45 |
+
use true_prev_aspn=False
|
46 |
+
use true_db_pointer=False
|
47 |
+
use true_prev_resp=False
|
48 |
+
use true_curr_bspn=False
|
49 |
+
use true_curr_aspn=False
|
50 |
+
use_all_previous_context=True
|
51 |
+
INFO:root:***** Running Evaluation *****
|
52 |
+
INFO:root: Num Turns = 7372
|
53 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
54 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
55 |
+
INFO:root:Generate setting:
|
56 |
+
use true_prev_bspn=False
|
57 |
+
use true_prev_aspn=False
|
58 |
+
use true_db_pointer=False
|
59 |
+
use true_prev_resp=False
|
60 |
+
use true_curr_bspn=False
|
61 |
+
use true_curr_aspn=False
|
62 |
+
use_all_previous_context=True
|
63 |
+
INFO:root:***** Running Evaluation *****
|
64 |
+
INFO:root: Num Turns = 7372
|
65 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
66 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
67 |
+
INFO:root:Generate setting:
|
68 |
+
use true_prev_bspn=False
|
69 |
+
use true_prev_aspn=False
|
70 |
+
use true_db_pointer=False
|
71 |
+
use true_prev_resp=False
|
72 |
+
use true_curr_bspn=False
|
73 |
+
use true_curr_aspn=False
|
74 |
+
use_all_previous_context=True
|
75 |
+
INFO:root:***** Running Evaluation *****
|
76 |
+
INFO:root: Num Turns = 7372
|
77 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
78 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
79 |
+
INFO:root:Generate setting:
|
80 |
+
use true_prev_bspn=False
|
81 |
+
use true_prev_aspn=False
|
82 |
+
use true_db_pointer=False
|
83 |
+
use true_prev_resp=False
|
84 |
+
use true_curr_bspn=False
|
85 |
+
use true_curr_aspn=False
|
86 |
+
use_all_previous_context=True
|
87 |
+
INFO:root:***** Running Evaluation *****
|
88 |
+
INFO:root: Num Turns = 7372
|
89 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
90 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
91 |
+
INFO:root:Generate setting:
|
92 |
+
use true_prev_bspn=False
|
93 |
+
use true_prev_aspn=False
|
94 |
+
use true_db_pointer=False
|
95 |
+
use true_prev_resp=False
|
96 |
+
use true_curr_bspn=False
|
97 |
+
use true_curr_aspn=False
|
98 |
+
use_all_previous_context=True
|
99 |
+
INFO:root:***** Running Evaluation *****
|
100 |
+
INFO:root: Num Turns = 7372
|
101 |
+
INFO:root:inference time: 0.62 min
|
102 |
+
INFO:root:Scoring time: 0.00 min
|
103 |
+
INFO:root:validation [CTR] match: 100.00 success: 100.00 bleu: 18.49 score: 118.49
|
104 |
+
INFO:root:update eval results to logs_test/experiments-all_test.json
|
105 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
106 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
107 |
+
INFO:root:Generate setting:
|
108 |
+
use true_prev_bspn=False
|
109 |
+
use true_prev_aspn=False
|
110 |
+
use true_db_pointer=False
|
111 |
+
use true_prev_resp=False
|
112 |
+
use true_curr_bspn=False
|
113 |
+
use true_curr_aspn=False
|
114 |
+
use_all_previous_context=True
|
115 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
116 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
117 |
+
INFO:root:Generate setting:
|
118 |
+
use true_prev_bspn=False
|
119 |
+
use true_prev_aspn=False
|
120 |
+
use true_db_pointer=False
|
121 |
+
use true_prev_resp=False
|
122 |
+
use true_curr_bspn=False
|
123 |
+
use true_curr_aspn=False
|
124 |
+
use_all_previous_context=True
|
125 |
+
INFO:root:***** Running Evaluation *****
|
126 |
+
INFO:root: Num Turns = 7372
|
127 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
128 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
129 |
+
INFO:root:Generate setting:
|
130 |
+
use true_prev_bspn=False
|
131 |
+
use true_prev_aspn=False
|
132 |
+
use true_db_pointer=False
|
133 |
+
use true_prev_resp=False
|
134 |
+
use true_curr_bspn=False
|
135 |
+
use true_curr_aspn=False
|
136 |
+
use_all_previous_context=True
|
137 |
+
INFO:root:***** Running Evaluation *****
|
138 |
+
INFO:root: Num Turns = 7372
|
139 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
140 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
141 |
+
INFO:root:Generate setting:
|
142 |
+
use true_prev_bspn=False
|
143 |
+
use true_prev_aspn=False
|
144 |
+
use true_db_pointer=False
|
145 |
+
use true_prev_resp=False
|
146 |
+
use true_curr_bspn=False
|
147 |
+
use true_curr_aspn=False
|
148 |
+
use_all_previous_context=True
|
149 |
+
INFO:root:***** Running Evaluation *****
|
150 |
+
INFO:root: Num Turns = 7372
|
151 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
152 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
153 |
+
INFO:root:Generate setting:
|
154 |
+
use true_prev_bspn=False
|
155 |
+
use true_prev_aspn=False
|
156 |
+
use true_db_pointer=False
|
157 |
+
use true_prev_resp=False
|
158 |
+
use true_curr_bspn=False
|
159 |
+
use true_curr_aspn=False
|
160 |
+
use_all_previous_context=True
|
161 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
162 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
163 |
+
INFO:root:Generate setting:
|
164 |
+
use true_prev_bspn=False
|
165 |
+
use true_prev_aspn=False
|
166 |
+
use true_db_pointer=False
|
167 |
+
use true_prev_resp=False
|
168 |
+
use true_curr_bspn=False
|
169 |
+
use true_curr_aspn=False
|
170 |
+
use_all_previous_context=True
|
171 |
+
INFO:root:***** Running Evaluation *****
|
172 |
+
INFO:root: Num Turns = 7372
|
173 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
174 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
175 |
+
INFO:root:Generate setting:
|
176 |
+
use true_prev_bspn=False
|
177 |
+
use true_prev_aspn=False
|
178 |
+
use true_db_pointer=False
|
179 |
+
use true_prev_resp=False
|
180 |
+
use true_curr_bspn=False
|
181 |
+
use true_curr_aspn=False
|
182 |
+
use_all_previous_context=True
|
183 |
+
INFO:root:***** Running Evaluation *****
|
184 |
+
INFO:root: Num Turns = 7372
|
185 |
+
INFO:root:inference time: 0.70 min
|
186 |
+
INFO:root:Scoring time: 0.01 min
|
187 |
+
INFO:root:validation [CTR] match: 100.00 success: 100.00 bleu: 18.49 score: 118.49
|
188 |
+
INFO:root:update eval results to logs_test/experiments-all_test.json
|
189 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
190 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
191 |
+
INFO:root:Generate setting:
|
192 |
+
use true_prev_bspn=False
|
193 |
+
use true_prev_aspn=False
|
194 |
+
use true_db_pointer=False
|
195 |
+
use true_prev_resp=False
|
196 |
+
use true_curr_bspn=False
|
197 |
+
use true_curr_aspn=False
|
198 |
+
use_all_previous_context=True
|
199 |
+
INFO:root:***** Running Evaluation *****
|
200 |
+
INFO:root: Num Turns = 7372
|
201 |
+
INFO:root:inference time: 4.61 min
|
202 |
+
INFO:root:Scoring time: 0.01 min
|
203 |
+
INFO:root:validation [CTR] match: 100.00 success: 90.00 bleu: 12.60 score: 107.60
|
204 |
+
INFO:root:update eval results to logs_test/experiments-all_test.json
|
205 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
206 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
207 |
+
INFO:root:Generate setting:
|
208 |
+
use true_prev_bspn=False
|
209 |
+
use true_prev_aspn=False
|
210 |
+
use true_db_pointer=False
|
211 |
+
use true_prev_resp=False
|
212 |
+
use true_curr_bspn=False
|
213 |
+
use true_curr_aspn=False
|
214 |
+
use_all_previous_context=True
|
215 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
216 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
217 |
+
INFO:root:Generate setting:
|
218 |
+
use true_prev_bspn=False
|
219 |
+
use true_prev_aspn=False
|
220 |
+
use true_db_pointer=False
|
221 |
+
use true_prev_resp=False
|
222 |
+
use true_curr_bspn=False
|
223 |
+
use true_curr_aspn=False
|
224 |
+
use_all_previous_context=True
|
225 |
+
INFO:root:Running eval on test
|
226 |
+
INFO:root:***** Running Evaluation *****
|
227 |
+
INFO:root: Num Turns = 7372
|
228 |
+
INFO:root:inference time: 21.91 min
|
229 |
+
INFO:root:Scoring time: 0.17 min
|
230 |
+
INFO:root:validation [CTR] match: 87.90 success: 76.60 bleu: 15.30 score: 97.55
|
231 |
+
INFO:root:update eval results to logs_test/home-all_test.json
|
232 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
233 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
234 |
+
INFO:root:Generate setting:
|
235 |
+
use true_prev_bspn=False
|
236 |
+
use true_prev_aspn=False
|
237 |
+
use true_db_pointer=False
|
238 |
+
use true_prev_resp=False
|
239 |
+
use true_curr_bspn=False
|
240 |
+
use true_curr_aspn=False
|
241 |
+
use_all_previous_context=True
|
242 |
+
INFO:root:Running eval on test
|
243 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
244 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
245 |
+
INFO:root:Generate setting:
|
246 |
+
use true_prev_bspn=False
|
247 |
+
use true_prev_aspn=False
|
248 |
+
use true_db_pointer=False
|
249 |
+
use true_prev_resp=False
|
250 |
+
use true_curr_bspn=False
|
251 |
+
use true_curr_aspn=False
|
252 |
+
use_all_previous_context=True
|
253 |
+
INFO:root:Running eval on test
|
254 |
+
INFO:root:***** Running Evaluation *****
|
255 |
+
INFO:root: Num Turns = 7372
|
256 |
+
INFO:root:Reading encoded data from ./data/preprocessed/multi-woz-processed/new_db_se_blank_encoded.data.json
|
257 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
258 |
+
INFO:root:Generate setting:
|
259 |
+
use true_prev_bspn=False
|
260 |
+
use true_prev_aspn=False
|
261 |
+
use true_db_pointer=False
|
262 |
+
use true_prev_resp=False
|
263 |
+
use true_curr_bspn=False
|
264 |
+
use true_curr_aspn=False
|
265 |
+
use_all_previous_context=True
|
266 |
+
INFO:root:Running eval on test
|
267 |
+
INFO:root:***** Running Evaluation *****
|
268 |
+
INFO:root: Num Turns = 7372
|
269 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
270 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
271 |
+
INFO:root:Generate setting:
|
272 |
+
use true_prev_bspn=False
|
273 |
+
use true_prev_aspn=False
|
274 |
+
use true_db_pointer=False
|
275 |
+
use true_prev_resp=False
|
276 |
+
use true_curr_bspn=False
|
277 |
+
use true_curr_aspn=False
|
278 |
+
use_all_previous_context=True
|
279 |
+
INFO:root:Running eval on test
|
280 |
+
INFO:root:***** Running Evaluation *****
|
281 |
+
INFO:root: Num Turns = 7372
|
282 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
283 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
284 |
+
INFO:root:Generate setting:
|
285 |
+
use true_prev_bspn=False
|
286 |
+
use true_prev_aspn=False
|
287 |
+
use true_db_pointer=False
|
288 |
+
use true_prev_resp=False
|
289 |
+
use true_curr_bspn=False
|
290 |
+
use true_curr_aspn=False
|
291 |
+
use_all_previous_context=True
|
292 |
+
INFO:root:Running eval on test
|
293 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
294 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
295 |
+
INFO:root:Generate setting:
|
296 |
+
use true_prev_bspn=False
|
297 |
+
use true_prev_aspn=False
|
298 |
+
use true_db_pointer=False
|
299 |
+
use true_prev_resp=False
|
300 |
+
use true_curr_bspn=False
|
301 |
+
use true_curr_aspn=False
|
302 |
+
use_all_previous_context=True
|
303 |
+
INFO:root:Running eval on test
|
304 |
+
INFO:root:***** Running Evaluation *****
|
305 |
+
INFO:root: Num Turns = 7372
|
306 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
307 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
308 |
+
INFO:root:Generate setting:
|
309 |
+
use true_prev_bspn=False
|
310 |
+
use true_prev_aspn=False
|
311 |
+
use true_db_pointer=False
|
312 |
+
use true_prev_resp=False
|
313 |
+
use true_curr_bspn=False
|
314 |
+
use true_curr_aspn=False
|
315 |
+
use_all_previous_context=True
|
316 |
+
INFO:root:Running eval on test
|
317 |
+
INFO:root:***** Running Evaluation *****
|
318 |
+
INFO:root: Num Turns = 7372
|
319 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
320 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
321 |
+
INFO:root:Generate setting:
|
322 |
+
use true_prev_bspn=False
|
323 |
+
use true_prev_aspn=False
|
324 |
+
use true_db_pointer=False
|
325 |
+
use true_prev_resp=False
|
326 |
+
use true_curr_bspn=False
|
327 |
+
use true_curr_aspn=False
|
328 |
+
use_all_previous_context=True
|
329 |
+
INFO:root:Running eval on test
|
330 |
+
INFO:root:***** Running Evaluation *****
|
331 |
+
INFO:root: Num Turns = 7372
|
332 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
333 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
334 |
+
INFO:root:Generate setting:
|
335 |
+
use true_prev_bspn=False
|
336 |
+
use true_prev_aspn=False
|
337 |
+
use true_db_pointer=False
|
338 |
+
use true_prev_resp=False
|
339 |
+
use true_curr_bspn=False
|
340 |
+
use true_curr_aspn=False
|
341 |
+
use_all_previous_context=True
|
342 |
+
INFO:root:Running eval on test
|
343 |
+
INFO:root:***** Running Evaluation *****
|
344 |
+
INFO:root: Num Turns = 7372
|
345 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
346 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
347 |
+
INFO:root:Generate setting:
|
348 |
+
use true_prev_bspn=False
|
349 |
+
use true_prev_aspn=False
|
350 |
+
use true_db_pointer=False
|
351 |
+
use true_prev_resp=False
|
352 |
+
use true_curr_bspn=False
|
353 |
+
use true_curr_aspn=False
|
354 |
+
use_all_previous_context=True
|
355 |
+
INFO:root:Running eval on test
|
356 |
+
INFO:root:***** Running Evaluation *****
|
357 |
+
INFO:root: Num Turns = 7372
|
358 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
359 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
360 |
+
INFO:root:Generate setting:
|
361 |
+
use true_prev_bspn=False
|
362 |
+
use true_prev_aspn=False
|
363 |
+
use true_db_pointer=False
|
364 |
+
use true_prev_resp=False
|
365 |
+
use true_curr_bspn=False
|
366 |
+
use true_curr_aspn=False
|
367 |
+
use_all_previous_context=True
|
368 |
+
INFO:root:Running eval on test
|
369 |
+
INFO:root:***** Running Evaluation *****
|
370 |
+
INFO:root: Num Turns = 7372
|
371 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
372 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
373 |
+
INFO:root:Generate setting:
|
374 |
+
use true_prev_bspn=False
|
375 |
+
use true_prev_aspn=False
|
376 |
+
use true_db_pointer=False
|
377 |
+
use true_prev_resp=False
|
378 |
+
use true_curr_bspn=False
|
379 |
+
use true_curr_aspn=False
|
380 |
+
use_all_previous_context=True
|
381 |
+
INFO:root:Running eval on test
|
382 |
+
INFO:root:***** Running Evaluation *****
|
383 |
+
INFO:root: Num Turns = 7372
|
384 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
385 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
386 |
+
INFO:root:Generate setting:
|
387 |
+
use true_prev_bspn=False
|
388 |
+
use true_prev_aspn=False
|
389 |
+
use true_db_pointer=False
|
390 |
+
use true_prev_resp=False
|
391 |
+
use true_curr_bspn=False
|
392 |
+
use true_curr_aspn=False
|
393 |
+
use_all_previous_context=True
|
394 |
+
INFO:root:Running eval on test
|
395 |
+
INFO:root:***** Running Evaluation *****
|
396 |
+
INFO:root: Num Turns = 7372
|
397 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
398 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
399 |
+
INFO:root:Generate setting:
|
400 |
+
use true_prev_bspn=False
|
401 |
+
use true_prev_aspn=False
|
402 |
+
use true_db_pointer=False
|
403 |
+
use true_prev_resp=False
|
404 |
+
use true_curr_bspn=False
|
405 |
+
use true_curr_aspn=False
|
406 |
+
use_all_previous_context=True
|
407 |
+
INFO:root:Running eval on test
|
408 |
+
INFO:root:***** Running Evaluation *****
|
409 |
+
INFO:root: Num Turns = 7372
|
410 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
411 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
412 |
+
INFO:root:Generate setting:
|
413 |
+
use true_prev_bspn=False
|
414 |
+
use true_prev_aspn=False
|
415 |
+
use true_db_pointer=False
|
416 |
+
use true_prev_resp=False
|
417 |
+
use true_curr_bspn=False
|
418 |
+
use true_curr_aspn=False
|
419 |
+
use_all_previous_context=True
|
420 |
+
INFO:root:Running eval on test
|
421 |
+
INFO:root:***** Running Evaluation *****
|
422 |
+
INFO:root: Num Turns = 7372
|
423 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
424 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
425 |
+
INFO:root:Generate setting:
|
426 |
+
use true_prev_bspn=False
|
427 |
+
use true_prev_aspn=False
|
428 |
+
use true_db_pointer=False
|
429 |
+
use true_prev_resp=False
|
430 |
+
use true_curr_bspn=False
|
431 |
+
use true_curr_aspn=False
|
432 |
+
use_all_previous_context=True
|
433 |
+
INFO:root:Running eval on test
|
434 |
+
INFO:root:***** Running Evaluation *****
|
435 |
+
INFO:root: Num Turns = 7372
|
436 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
437 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
438 |
+
INFO:root:Generate setting:
|
439 |
+
use true_prev_bspn=False
|
440 |
+
use true_prev_aspn=False
|
441 |
+
use true_db_pointer=False
|
442 |
+
use true_prev_resp=False
|
443 |
+
use true_curr_bspn=False
|
444 |
+
use true_curr_aspn=False
|
445 |
+
use_all_previous_context=True
|
446 |
+
INFO:root:Running eval on test
|
447 |
+
INFO:root:***** Running Evaluation *****
|
448 |
+
INFO:root: Num Turns = 7372
|
449 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
450 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
451 |
+
INFO:root:Generate setting:
|
452 |
+
use true_prev_bspn=False
|
453 |
+
use true_prev_aspn=False
|
454 |
+
use true_db_pointer=False
|
455 |
+
use true_prev_resp=False
|
456 |
+
use true_curr_bspn=False
|
457 |
+
use true_curr_aspn=False
|
458 |
+
use_all_previous_context=True
|
459 |
+
INFO:root:Running eval on test
|
460 |
+
INFO:root:***** Running Evaluation *****
|
461 |
+
INFO:root: Num Turns = 7372
|
462 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
463 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
464 |
+
INFO:root:Generate setting:
|
465 |
+
use true_prev_bspn=False
|
466 |
+
use true_prev_aspn=False
|
467 |
+
use true_db_pointer=False
|
468 |
+
use true_prev_resp=False
|
469 |
+
use true_curr_bspn=False
|
470 |
+
use true_curr_aspn=False
|
471 |
+
use_all_previous_context=True
|
472 |
+
INFO:root:Running eval on test
|
473 |
+
INFO:root:***** Running Evaluation *****
|
474 |
+
INFO:root: Num Turns = 7372
|
475 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
476 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
477 |
+
INFO:root:Generate setting:
|
478 |
+
use true_prev_bspn=False
|
479 |
+
use true_prev_aspn=False
|
480 |
+
use true_db_pointer=False
|
481 |
+
use true_prev_resp=False
|
482 |
+
use true_curr_bspn=False
|
483 |
+
use true_curr_aspn=False
|
484 |
+
use_all_previous_context=True
|
485 |
+
INFO:root:Running eval on test
|
486 |
+
INFO:root:***** Running Evaluation *****
|
487 |
+
INFO:root: Num Turns = 7372
|
488 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
489 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
490 |
+
INFO:root:Generate setting:
|
491 |
+
use true_prev_bspn=False
|
492 |
+
use true_prev_aspn=False
|
493 |
+
use true_db_pointer=False
|
494 |
+
use true_prev_resp=False
|
495 |
+
use true_curr_bspn=False
|
496 |
+
use true_curr_aspn=False
|
497 |
+
use_all_previous_context=True
|
498 |
+
INFO:root:Running eval on test
|
499 |
+
INFO:root:***** Running Evaluation *****
|
500 |
+
INFO:root: Num Turns = 7372
|
501 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
502 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
503 |
+
INFO:root:Generate setting:
|
504 |
+
use true_prev_bspn=False
|
505 |
+
use true_prev_aspn=False
|
506 |
+
use true_db_pointer=False
|
507 |
+
use true_prev_resp=False
|
508 |
+
use true_curr_bspn=False
|
509 |
+
use true_curr_aspn=False
|
510 |
+
use_all_previous_context=True
|
511 |
+
INFO:root:Running eval on test
|
512 |
+
INFO:root:***** Running Evaluation *****
|
513 |
+
INFO:root: Num Turns = 7372
|
514 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
515 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
516 |
+
INFO:root:Generate setting:
|
517 |
+
use true_prev_bspn=False
|
518 |
+
use true_prev_aspn=False
|
519 |
+
use true_db_pointer=False
|
520 |
+
use true_prev_resp=False
|
521 |
+
use true_curr_bspn=False
|
522 |
+
use true_curr_aspn=False
|
523 |
+
use_all_previous_context=True
|
524 |
+
INFO:root:Running eval on test
|
525 |
+
INFO:root:***** Running Evaluation *****
|
526 |
+
INFO:root: Num Turns = 7372
|
527 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
528 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
529 |
+
INFO:root:Generate setting:
|
530 |
+
use true_prev_bspn=False
|
531 |
+
use true_prev_aspn=False
|
532 |
+
use true_db_pointer=False
|
533 |
+
use true_prev_resp=False
|
534 |
+
use true_curr_bspn=False
|
535 |
+
use true_curr_aspn=False
|
536 |
+
use_all_previous_context=True
|
537 |
+
INFO:root:Running eval on test
|
538 |
+
INFO:root:***** Running Evaluation *****
|
539 |
+
INFO:root: Num Turns = 7372
|
540 |
+
INFO:root:Reading encoded data from ./data/preprocessed/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
541 |
+
INFO:root:train size:8434, dev size:999, test size:1000
|
542 |
+
INFO:root:Generate setting:
|
543 |
+
use true_prev_bspn=False
|
544 |
+
use true_prev_aspn=False
|
545 |
+
use true_db_pointer=False
|
546 |
+
use true_prev_resp=False
|
547 |
+
use true_curr_bspn=False
|
548 |
+
use true_curr_aspn=False
|
549 |
+
use_all_previous_context=True
|
550 |
+
INFO:root:Running eval on test
|
551 |
+
INFO:root:***** Running Evaluation *****
|
552 |
+
INFO:root: Num Turns = 7372
|
553 |
+
INFO:root:Reading encoded data from ./data/preprocessed_gen_usr_utts/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
554 |
+
INFO:root:train size:14969, dev size:999, test size:1000
|
555 |
+
INFO:root:Generate setting:
|
556 |
+
use true_prev_bspn=False
|
557 |
+
use true_prev_aspn=False
|
558 |
+
use true_db_pointer=False
|
559 |
+
use true_prev_resp=False
|
560 |
+
use true_curr_bspn=False
|
561 |
+
use true_curr_aspn=False
|
562 |
+
use_all_previous_context=True
|
563 |
+
INFO:root:Running eval on test
|
564 |
+
INFO:root:***** Running Evaluation *****
|
565 |
+
INFO:root: Num Turns = 7372
|
566 |
+
INFO:root:Reading encoded data from ./data/preprocessed_gen_usr_utts/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
567 |
+
INFO:root:train size:14969, dev size:999, test size:1000
|
568 |
+
INFO:root:Generate setting:
|
569 |
+
use true_prev_bspn=False
|
570 |
+
use true_prev_aspn=False
|
571 |
+
use true_db_pointer=False
|
572 |
+
use true_prev_resp=False
|
573 |
+
use true_curr_bspn=False
|
574 |
+
use true_curr_aspn=False
|
575 |
+
use_all_previous_context=True
|
576 |
+
INFO:root:Running eval on test
|
577 |
+
INFO:root:Reading encoded data from ./data/preprocessed_gen_usr_utts/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
578 |
+
INFO:root:train size:14969, dev size:999, test size:1000
|
579 |
+
INFO:root:Generate setting:
|
580 |
+
use true_prev_bspn=False
|
581 |
+
use true_prev_aspn=False
|
582 |
+
use true_db_pointer=False
|
583 |
+
use true_prev_resp=False
|
584 |
+
use true_curr_bspn=False
|
585 |
+
use true_curr_aspn=False
|
586 |
+
use_all_previous_context=True
|
587 |
+
INFO:root:Running eval on test
|
588 |
+
INFO:root:***** Running Evaluation *****
|
589 |
+
INFO:root: Num Turns = 7372
|
590 |
+
INFO:root:Reading encoded data from ./data/preprocessed_gen_usr_utts/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
591 |
+
INFO:root:train size:14969, dev size:999, test size:1000
|
592 |
+
INFO:root:Generate setting:
|
593 |
+
use true_prev_bspn=False
|
594 |
+
use true_prev_aspn=False
|
595 |
+
use true_db_pointer=False
|
596 |
+
use true_prev_resp=False
|
597 |
+
use true_curr_bspn=False
|
598 |
+
use true_curr_aspn=False
|
599 |
+
use_all_previous_context=True
|
600 |
+
INFO:root:Running eval on test
|
601 |
+
INFO:root:***** Running Evaluation *****
|
602 |
+
INFO:root: Num Turns = 7372
|
603 |
+
INFO:root:inference time: 0.71 min
|
604 |
+
INFO:root:Reading encoded data from ./data/preprocessed_gen_usr_utts/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
605 |
+
INFO:root:train size:14969, dev size:999, test size:1000
|
606 |
+
INFO:root:Generate setting:
|
607 |
+
use true_prev_bspn=False
|
608 |
+
use true_prev_aspn=False
|
609 |
+
use true_db_pointer=False
|
610 |
+
use true_prev_resp=False
|
611 |
+
use true_curr_bspn=False
|
612 |
+
use true_curr_aspn=False
|
613 |
+
use_all_previous_context=True
|
614 |
+
INFO:root:Running eval on test
|
615 |
+
INFO:root:***** Running Evaluation *****
|
616 |
+
INFO:root: Num Turns = 7372
|
617 |
+
INFO:root:inference time: 0.89 min
|
618 |
+
INFO:root:Reading encoded data from ./data/preprocessed_gen_usr_utts/UBAR/multi-woz-processed/new_db_se_blank_encoded.data.json
|
619 |
+
INFO:root:train size:14969, dev size:999, test size:1000
|
620 |
+
INFO:root:Generate setting:
|
621 |
+
use true_prev_bspn=False
|
622 |
+
use true_prev_aspn=False
|
623 |
+
use true_db_pointer=False
|
624 |
+
use true_prev_resp=False
|
625 |
+
use true_curr_bspn=False
|
626 |
+
use true_curr_aspn=False
|
627 |
+
use_all_previous_context=True
|
628 |
+
INFO:root:Running eval on test
|
629 |
+
INFO:root:***** Running Evaluation *****
|
630 |
+
INFO:root: Num Turns = 7372
|
631 |
+
INFO:root:inference time: 0.10 min
|
632 |
+
INFO:root:Scoring time: 1.08 min
|
633 |
+
INFO:root:validation [CTR] match: 100.00 success: 100.00 bleu: 20.28 score: 120.28
|
634 |
+
INFO:root:update eval results to logs_test/UBAR-all_test.json
|
635 |
+
INFO:root:Evaluation finished
|