bogdanraduta commited on
Commit
d37eaca
·
verified ·
1 Parent(s): 159ad22

Upload eval/groundedness_eval.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. eval/groundedness_eval.json +330 -0
eval/groundedness_eval.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "task": "groundedness",
3
+ "threshold": 0.5,
4
+ "per_language": {
5
+ "az": {
6
+ "support": 0,
7
+ "precision": 0.0,
8
+ "recall": 0.0,
9
+ "f1": 0.0,
10
+ "fpr": 0.0,
11
+ "accuracy": 0.9125,
12
+ "n": 80
13
+ },
14
+ "bg": {
15
+ "support": 0,
16
+ "precision": 0.0,
17
+ "recall": 0.0,
18
+ "f1": 0.0,
19
+ "fpr": 0.0,
20
+ "accuracy": 0.975,
21
+ "n": 80
22
+ },
23
+ "cs": {
24
+ "support": 0,
25
+ "precision": 0.0,
26
+ "recall": 0.0,
27
+ "f1": 0.0,
28
+ "fpr": 0.0,
29
+ "accuracy": 0.9615,
30
+ "n": 78
31
+ },
32
+ "da": {
33
+ "support": 0,
34
+ "precision": 0.0,
35
+ "recall": 0.0,
36
+ "f1": 0.0,
37
+ "fpr": 0.0,
38
+ "accuracy": 0.9625,
39
+ "n": 80
40
+ },
41
+ "de": {
42
+ "support": 0,
43
+ "precision": 0.0,
44
+ "recall": 0.0,
45
+ "f1": 0.0,
46
+ "fpr": 0.0,
47
+ "accuracy": 0.9359,
48
+ "n": 78
49
+ },
50
+ "el": {
51
+ "support": 0,
52
+ "precision": 0.0,
53
+ "recall": 0.0,
54
+ "f1": 0.0,
55
+ "fpr": 0.0,
56
+ "accuracy": 0.95,
57
+ "n": 80
58
+ },
59
+ "en": {
60
+ "support": 0,
61
+ "precision": 0.0,
62
+ "recall": 0.0,
63
+ "f1": 0.0,
64
+ "fpr": 0.0,
65
+ "accuracy": 0.8974,
66
+ "n": 78
67
+ },
68
+ "es": {
69
+ "support": 0,
70
+ "precision": 0.0,
71
+ "recall": 0.0,
72
+ "f1": 0.0,
73
+ "fpr": 0.0,
74
+ "accuracy": 0.95,
75
+ "n": 80
76
+ },
77
+ "et": {
78
+ "support": 0,
79
+ "precision": 0.0,
80
+ "recall": 0.0,
81
+ "f1": 0.0,
82
+ "fpr": 0.0,
83
+ "accuracy": 0.9605,
84
+ "n": 76
85
+ },
86
+ "fi": {
87
+ "support": 0,
88
+ "precision": 0.0,
89
+ "recall": 0.0,
90
+ "f1": 0.0,
91
+ "fpr": 0.0,
92
+ "accuracy": 0.9359,
93
+ "n": 78
94
+ },
95
+ "fr": {
96
+ "support": 0,
97
+ "precision": 0.0,
98
+ "recall": 0.0,
99
+ "f1": 0.0,
100
+ "fpr": 0.0,
101
+ "accuracy": 0.9375,
102
+ "n": 80
103
+ },
104
+ "ga": {
105
+ "support": 0,
106
+ "precision": 0.0,
107
+ "recall": 0.0,
108
+ "f1": 0.0,
109
+ "fpr": 0.0,
110
+ "accuracy": 0.9744,
111
+ "n": 78
112
+ },
113
+ "hr": {
114
+ "support": 0,
115
+ "precision": 0.0,
116
+ "recall": 0.0,
117
+ "f1": 0.0,
118
+ "fpr": 0.0,
119
+ "accuracy": 0.9231,
120
+ "n": 78
121
+ },
122
+ "hu": {
123
+ "support": 0,
124
+ "precision": 0.0,
125
+ "recall": 0.0,
126
+ "f1": 0.0,
127
+ "fpr": 0.0,
128
+ "accuracy": 0.95,
129
+ "n": 80
130
+ },
131
+ "it": {
132
+ "support": 0,
133
+ "precision": 0.0,
134
+ "recall": 0.0,
135
+ "f1": 0.0,
136
+ "fpr": 0.0,
137
+ "accuracy": 0.9875,
138
+ "n": 80
139
+ },
140
+ "lt": {
141
+ "support": 0,
142
+ "precision": 0.0,
143
+ "recall": 0.0,
144
+ "f1": 0.0,
145
+ "fpr": 0.0,
146
+ "accuracy": 0.9625,
147
+ "n": 80
148
+ },
149
+ "lv": {
150
+ "support": 0,
151
+ "precision": 0.0,
152
+ "recall": 0.0,
153
+ "f1": 0.0,
154
+ "fpr": 0.0,
155
+ "accuracy": 0.95,
156
+ "n": 80
157
+ },
158
+ "mt": {
159
+ "support": 0,
160
+ "precision": 0.0,
161
+ "recall": 0.0,
162
+ "f1": 0.0,
163
+ "fpr": 0.0,
164
+ "accuracy": 0.9375,
165
+ "n": 80
166
+ },
167
+ "nl": {
168
+ "support": 0,
169
+ "precision": 0.0,
170
+ "recall": 0.0,
171
+ "f1": 0.0,
172
+ "fpr": 0.0,
173
+ "accuracy": 0.9375,
174
+ "n": 80
175
+ },
176
+ "pl": {
177
+ "support": 0,
178
+ "precision": 0.0,
179
+ "recall": 0.0,
180
+ "f1": 0.0,
181
+ "fpr": 0.0,
182
+ "accuracy": 0.9125,
183
+ "n": 80
184
+ },
185
+ "pt": {
186
+ "support": 0,
187
+ "precision": 0.0,
188
+ "recall": 0.0,
189
+ "f1": 0.0,
190
+ "fpr": 0.0,
191
+ "accuracy": 0.9625,
192
+ "n": 80
193
+ },
194
+ "ro": {
195
+ "support": 0,
196
+ "precision": 0.0,
197
+ "recall": 0.0,
198
+ "f1": 0.0,
199
+ "fpr": 0.0,
200
+ "accuracy": 1.0,
201
+ "n": 80
202
+ },
203
+ "sk": {
204
+ "support": 0,
205
+ "precision": 0.0,
206
+ "recall": 0.0,
207
+ "f1": 0.0,
208
+ "fpr": 0.0,
209
+ "accuracy": 0.925,
210
+ "n": 80
211
+ },
212
+ "sl": {
213
+ "support": 0,
214
+ "precision": 0.0,
215
+ "recall": 0.0,
216
+ "f1": 0.0,
217
+ "fpr": 0.0,
218
+ "accuracy": 0.9625,
219
+ "n": 80
220
+ },
221
+ "sv": {
222
+ "support": 0,
223
+ "precision": 0.0,
224
+ "recall": 0.0,
225
+ "f1": 0.0,
226
+ "fpr": 0.0,
227
+ "accuracy": 0.9125,
228
+ "n": 80
229
+ },
230
+ "tr": {
231
+ "support": 0,
232
+ "precision": 0.0,
233
+ "recall": 0.0,
234
+ "f1": 0.0,
235
+ "fpr": 0.0,
236
+ "accuracy": 0.9615,
237
+ "n": 78
238
+ }
239
+ },
240
+ "per_register": {
241
+ "lexical_overlap": {
242
+ "support": 0,
243
+ "precision": 0.0,
244
+ "recall": 0.0,
245
+ "f1": 0.0,
246
+ "fpr": 0.0,
247
+ "accuracy": 0.949,
248
+ "n": 412
249
+ },
250
+ "negation_conflict": {
251
+ "support": 0,
252
+ "precision": 0.0,
253
+ "recall": 0.0,
254
+ "f1": 0.0,
255
+ "fpr": 0.0,
256
+ "accuracy": 0.9469,
257
+ "n": 414
258
+ },
259
+ "numeric_conflict": {
260
+ "support": 0,
261
+ "precision": 0.0,
262
+ "recall": 0.0,
263
+ "f1": 0.0,
264
+ "fpr": 0.0,
265
+ "accuracy": 0.9084,
266
+ "n": 404
267
+ },
268
+ "scope_conflict": {
269
+ "support": 0,
270
+ "precision": 0.0,
271
+ "recall": 0.0,
272
+ "f1": 0.0,
273
+ "fpr": 0.0,
274
+ "accuracy": 0.9663,
275
+ "n": 416
276
+ },
277
+ "unstated": {
278
+ "support": 0,
279
+ "precision": 0.0,
280
+ "recall": 0.0,
281
+ "f1": 0.0,
282
+ "fpr": 0.0,
283
+ "accuracy": 0.9663,
284
+ "n": 416
285
+ }
286
+ },
287
+ "per_label": {
288
+ "grounded": {
289
+ "support": 1031,
290
+ "precision": 0.9574,
291
+ "recall": 0.937,
292
+ "f1": 0.9471,
293
+ "fpr": 0.0417,
294
+ "accuracy": 0.0,
295
+ "n": 0
296
+ },
297
+ "not_grounded": {
298
+ "support": 1031,
299
+ "precision": 0.9383,
300
+ "recall": 0.9583,
301
+ "f1": 0.9482,
302
+ "fpr": 0.063,
303
+ "accuracy": 0.0,
304
+ "n": 0
305
+ }
306
+ },
307
+ "worst_languages": [
308
+ [
309
+ "en",
310
+ 0.8974358974358975
311
+ ],
312
+ [
313
+ "az",
314
+ 0.9125
315
+ ],
316
+ [
317
+ "pl",
318
+ 0.9125
319
+ ],
320
+ [
321
+ "sv",
322
+ 0.9125
323
+ ],
324
+ [
325
+ "hr",
326
+ 0.9230769230769231
327
+ ]
328
+ ],
329
+ "pair_accuracy": 0.8991
330
+ }