ai-forever commited on
Commit
8067e3e
·
verified ·
1 Parent(s): c04507d

Init results file.

Browse files
Files changed (1) hide show
  1. results.json +7 -533
results.json CHANGED
@@ -1,533 +1,7 @@
1
- {
2
- "items": {
3
- "1.24.1": {
4
- "7bfbc0c372f54d82af0569242d9ef432": {
5
- "model_name": "Gemma-3 4B",
6
- "timestamp": "2025-05-21T06:59:16",
7
- "config": {
8
- "embedding_model": "sentence-transformers/distiluse-base-multilingual-cased",
9
- "retriever_type": "mmr",
10
- "retrieval_config": {
11
- "top_k": 5,
12
- "chunk_size": 1000,
13
- "chunk_overlap": 100
14
- }
15
- },
16
- "metrics": {
17
- "cond": {
18
- "retrieval": {
19
- "hit_rate": 0.0,
20
- "mrr": 0.0,
21
- "precision": 0.0
22
- },
23
- "generation": {
24
- "rouge1": 0.007746031746031746,
25
- "rougeL": 0.007746031746031746
26
- }
27
- },
28
- "set": {
29
- "retrieval": {
30
- "hit_rate": 0.0,
31
- "mrr": 0.0,
32
- "precision": 0.0
33
- },
34
- "generation": {
35
- "rouge1": 0.05579228423808982,
36
- "rougeL": 0.05280572991285028
37
- }
38
- },
39
- "mh": {
40
- "retrieval": {
41
- "hit_rate": 0.006666666666666667,
42
- "mrr": 0.006666666666666667,
43
- "precision": 0.0013333333333333335
44
- },
45
- "generation": {
46
- "rouge1": 0.006774903840121232,
47
- "rougeL": 0.006774903840121232
48
- }
49
- },
50
- "simple": {
51
- "retrieval": {
52
- "hit_rate": 0.0,
53
- "mrr": 0.0,
54
- "precision": 0.0
55
- },
56
- "generation": {
57
- "rouge1": 0.013215695323413091,
58
- "rougeL": 0.012039224735177797
59
- }
60
- },
61
- "overall": {
62
- "retrieval": {
63
- "hit_rate": 0.001658374792703151,
64
- "mrr": 0.001658374792703151,
65
- "precision": 0.0003316749585406302
66
- },
67
- "generation": {
68
- "rouge1": 0.020844086829384115,
69
- "rougeL": 0.01980265540519518
70
- }
71
- }
72
- },
73
- "metadata": {
74
- "n_questions": 603,
75
- "submit_timestamp": ""
76
- }
77
- }
78
- },
79
- "1.26.1": {
80
- "7bfbc0c372f54d82af0569242d9ef432": {
81
- "model_name": "Gemma-3 4B",
82
- "timestamp": "2025-05-21T07:35:57",
83
- "config": {
84
- "embedding_model": "sentence-transformers/distiluse-base-multilingual-cased",
85
- "retriever_type": "mmr",
86
- "retrieval_config": {
87
- "top_k": 5,
88
- "chunk_size": 1000,
89
- "chunk_overlap": 100
90
- }
91
- },
92
- "metrics": {
93
- "cond": {
94
- "retrieval": {
95
- "hit_rate": 0.9333333333333333,
96
- "mrr": 0.8,
97
- "precision": 0.30666666666666675
98
- },
99
- "generation": {
100
- "rouge1": 0.08025308025308027,
101
- "rougeL": 0.08025308025308027
102
- }
103
- },
104
- "mh": {
105
- "retrieval": {
106
- "hit_rate": 0.6,
107
- "mrr": 0.55,
108
- "precision": 0.16
109
- },
110
- "generation": {
111
- "rouge1": 0.048484848484848485,
112
- "rougeL": 0.048484848484848485
113
- }
114
- },
115
- "set": {
116
- "retrieval": {
117
- "hit_rate": 1.0,
118
- "mrr": 0.8074074074074074,
119
- "precision": 0.3111111111111111
120
- },
121
- "generation": {
122
- "rouge1": 0.12864011633361477,
123
- "rougeL": 0.12864011633361477
124
- }
125
- },
126
- "simple": {
127
- "retrieval": {
128
- "hit_rate": 0.75,
129
- "mrr": 0.5625,
130
- "precision": 0.25
131
- },
132
- "generation": {
133
- "rouge1": 0.2142857142857143,
134
- "rougeL": 0.2142857142857143
135
- }
136
- },
137
- "overall": {
138
- "retrieval": {
139
- "hit_rate": 0.8723404255319149,
140
- "mrr": 0.7294326241134753,
141
- "precision": 0.2723404255319149
142
- },
143
- "generation": {
144
- "rouge1": 0.1034321199955875,
145
- "rougeL": 0.1034321199955875
146
- }
147
- }
148
- },
149
- "metadata": {
150
- "n_questions": 47,
151
- "submit_timestamp": ""
152
- }
153
- }
154
- },
155
- "1.32.1": {
156
- "0733a3f98fc046deb0bfe1b7cc110547": {
157
- "model_name": "Gemma-3 1B",
158
- "timestamp": "2025-05-22T09:41:08",
159
- "config": {
160
- "embedding_model": "sentence-transformers/distiluse-base-multilingual-cased",
161
- "retriever_type": "mmr",
162
- "retrieval_config": {
163
- "top_k": 5,
164
- "chunk_size": 1000,
165
- "chunk_overlap": 100
166
- }
167
- },
168
- "metrics": {
169
- "mh": {
170
- "retrieval": {
171
- "hit_rate": 0.5862068965517241,
172
- "mrr": 0.47413793103448276,
173
- "precision": 0.11724137931034484
174
- },
175
- "generation": {
176
- "rouge1": 0.02324309735987758,
177
- "rougeL": 0.02324309735987758
178
- }
179
- },
180
- "cond": {
181
- "retrieval": {
182
- "hit_rate": 0.6956521739130435,
183
- "mrr": 0.6956521739130435,
184
- "precision": 0.1478260869565218
185
- },
186
- "generation": {
187
- "rouge1": 0.03246378430639343,
188
- "rougeL": 0.03184707138625775
189
- }
190
- },
191
- "simple": {
192
- "retrieval": {
193
- "hit_rate": 0.6206896551724138,
194
- "mrr": 0.47701149425287354,
195
- "precision": 0.1241379310344828
196
- },
197
- "generation": {
198
- "rouge1": 0.03693659162302205,
199
- "rougeL": 0.03693659162302205
200
- }
201
- },
202
- "set": {
203
- "retrieval": {
204
- "hit_rate": 0.3333333333333333,
205
- "mrr": 0.3333333333333333,
206
- "precision": 0.06666666666666667
207
- },
208
- "generation": {
209
- "rouge1": 0.053958575300038725,
210
- "rougeL": 0.053958575300038725
211
- }
212
- },
213
- "overall": {
214
- "retrieval": {
215
- "hit_rate": 0.6190476190476191,
216
- "mrr": 0.5307539682539681,
217
- "precision": 0.12619047619047616
218
- },
219
- "generation": {
220
- "rouge1": 0.031592306493467316,
221
- "rougeL": 0.03142344462247778
222
- }
223
- }
224
- },
225
- "metadata": {
226
- "n_questions": 84,
227
- "submit_timestamp": ""
228
- }
229
- },
230
- "7bfbc0c372f54d82af0569242d9ef432": {
231
- "model_name": "Gemma-3 4B",
232
- "timestamp": "2025-05-22T09:44:39",
233
- "config": {
234
- "embedding_model": "sentence-transformers/distiluse-base-multilingual-cased",
235
- "retriever_type": "mmr",
236
- "retrieval_config": {
237
- "top_k": 5,
238
- "chunk_size": 1000,
239
- "chunk_overlap": 100
240
- }
241
- },
242
- "metrics": {
243
- "mh": {
244
- "retrieval": {
245
- "hit_rate": 0.5862068965517241,
246
- "mrr": 0.47413793103448276,
247
- "precision": 0.11724137931034484
248
- },
249
- "generation": {
250
- "rouge1": 0.17858012396806958,
251
- "rougeL": 0.17858012396806958
252
- }
253
- },
254
- "cond": {
255
- "retrieval": {
256
- "hit_rate": 0.6956521739130435,
257
- "mrr": 0.6956521739130435,
258
- "precision": 0.1478260869565218
259
- },
260
- "generation": {
261
- "rouge1": 0.14728260869565218,
262
- "rougeL": 0.14456521739130435
263
- }
264
- },
265
- "simple": {
266
- "retrieval": {
267
- "hit_rate": 0.6206896551724138,
268
- "mrr": 0.47701149425287354,
269
- "precision": 0.1241379310344828
270
- },
271
- "generation": {
272
- "rouge1": 0.1256521796705334,
273
- "rougeL": 0.1256521796705334
274
- }
275
- },
276
- "set": {
277
- "retrieval": {
278
- "hit_rate": 0.3333333333333333,
279
- "mrr": 0.3333333333333333,
280
- "precision": 0.06666666666666667
281
- },
282
- "generation": {
283
- "rouge1": 0.05676328502415459,
284
- "rougeL": 0.05676328502415459
285
- }
286
- },
287
- "overall": {
288
- "retrieval": {
289
- "hit_rate": 0.6190476190476191,
290
- "mrr": 0.5307539682539681,
291
- "precision": 0.12619047619047616
292
- },
293
- "generation": {
294
- "rouge1": 0.14738722214990416,
295
- "rougeL": 0.14664317453085654
296
- }
297
- }
298
- },
299
- "metadata": {
300
- "n_questions": 84,
301
- "submit_timestamp": ""
302
- }
303
- }
304
- },
305
- "1.33.1": {
306
- "0733a3f98fc046deb0bfe1b7cc110547": {
307
- "model_name": "Gemma-3 1B",
308
- "timestamp": "2025-05-22T10:26:07",
309
- "config": {
310
- "embedding_model": "sentence-transformers/distiluse-base-multilingual-cased",
311
- "retriever_type": "mmr",
312
- "retrieval_config": {
313
- "top_k": 5,
314
- "chunk_size": 1000,
315
- "chunk_overlap": 100
316
- }
317
- },
318
- "metrics": {
319
- "mh": {
320
- "retrieval": {
321
- "hit_rate": 0.5208333333333334,
322
- "mrr": 0.3277777777777778,
323
- "precision": 0.11666666666666668
324
- },
325
- "generation": {
326
- "rouge1": 0.027308327224987633,
327
- "rougeL": 0.027308327224987633
328
- }
329
- },
330
- "cond": {
331
- "retrieval": {
332
- "hit_rate": 0.6078431372549019,
333
- "mrr": 0.45392156862745103,
334
- "precision": 0.1725490196078431
335
- },
336
- "generation": {
337
- "rouge1": 0.019595373319985267,
338
- "rougeL": 0.019595373319985267
339
- }
340
- },
341
- "simple": {
342
- "retrieval": {
343
- "hit_rate": 0.5925925925925926,
344
- "mrr": 0.3833333333333333,
345
- "precision": 0.13703703703703707
346
- },
347
- "generation": {
348
- "rouge1": 0.06423697711511875,
349
- "rougeL": 0.06423697711511875
350
- }
351
- },
352
- "set": {
353
- "retrieval": {
354
- "hit_rate": 0.6,
355
- "mrr": 0.24,
356
- "precision": 0.16
357
- },
358
- "generation": {
359
- "rouge1": 0.04461659954197268,
360
- "rougeL": 0.04461659954197268
361
- }
362
- },
363
- "overall": {
364
- "retrieval": {
365
- "hit_rate": 0.5759493670886076,
366
- "mrr": 0.384704641350211,
367
- "precision": 0.1430379746835443
368
- },
369
- "generation": {
370
- "rouge1": 0.03798761713952488,
371
- "rougeL": 0.03798761713952488
372
- }
373
- }
374
- },
375
- "metadata": {
376
- "n_questions": 158,
377
- "submit_timestamp": ""
378
- }
379
- },
380
- "7bfbc0c372f54d82af0569242d9ef432": {
381
- "model_name": "Gemma-3 4B",
382
- "timestamp": "2025-05-22T10:29:32",
383
- "config": {
384
- "embedding_model": "sentence-transformers/distiluse-base-multilingual-cased",
385
- "retriever_type": "mmr",
386
- "retrieval_config": {
387
- "top_k": 5,
388
- "chunk_size": 1000,
389
- "chunk_overlap": 100
390
- }
391
- },
392
- "metrics": {
393
- "mh": {
394
- "retrieval": {
395
- "hit_rate": 0.5208333333333334,
396
- "mrr": 0.3277777777777778,
397
- "precision": 0.11666666666666668
398
- },
399
- "generation": {
400
- "rouge1": 0.09788079222156261,
401
- "rougeL": 0.09788079222156261
402
- }
403
- },
404
- "cond": {
405
- "retrieval": {
406
- "hit_rate": 0.6078431372549019,
407
- "mrr": 0.45392156862745103,
408
- "precision": 0.1725490196078431
409
- },
410
- "generation": {
411
- "rouge1": 0.09129736523672684,
412
- "rougeL": 0.09129736523672684
413
- }
414
- },
415
- "simple": {
416
- "retrieval": {
417
- "hit_rate": 0.5925925925925926,
418
- "mrr": 0.3833333333333333,
419
- "precision": 0.13703703703703707
420
- },
421
- "generation": {
422
- "rouge1": 0.13183956817502798,
423
- "rougeL": 0.13183956817502798
424
- }
425
- },
426
- "set": {
427
- "retrieval": {
428
- "hit_rate": 0.6,
429
- "mrr": 0.24,
430
- "precision": 0.16
431
- },
432
- "generation": {
433
- "rouge1": 0.08549707602339182,
434
- "rougeL": 0.08549707602339182
435
- }
436
- },
437
- "overall": {
438
- "retrieval": {
439
- "hit_rate": 0.5759493670886076,
440
- "mrr": 0.384704641350211,
441
- "precision": 0.1430379746835443
442
- },
443
- "generation": {
444
- "rouge1": 0.10697003617263635,
445
- "rougeL": 0.10697003617263635
446
- }
447
- }
448
- },
449
- "metadata": {
450
- "n_questions": 158,
451
- "submit_timestamp": ""
452
- }
453
- },
454
- "ef91e41e46fd4351b30c5cf2e2e6f9fc": {
455
- "model_name": "Llama 4 Scout 17B",
456
- "timestamp": "2025-05-22T14:47:39",
457
- "config": {
458
- "embedding_model": "sentence-transformers/distiluse-base-multilingual-cased",
459
- "retriever_type": "mmr",
460
- "retrieval_config": {
461
- "top_k": 4,
462
- "chunk_size": 1000,
463
- "chunk_overlap": 100
464
- }
465
- },
466
- "metrics": {
467
- "mh": {
468
- "retrieval": {
469
- "hit_rate": 0.4791666666666667,
470
- "mrr": 0.328125,
471
- "precision": 0.13541666666666666
472
- },
473
- "generation": {
474
- "rouge1": 0.04071969696969697,
475
- "rougeL": 0.04071969696969697
476
- }
477
- },
478
- "cond": {
479
- "retrieval": {
480
- "hit_rate": 0.5686274509803921,
481
- "mrr": 0.43137254901960786,
482
- "precision": 0.18627450980392157
483
- },
484
- "generation": {
485
- "rouge1": 0.012118736383442266,
486
- "rougeL": 0.012118736383442266
487
- }
488
- },
489
- "simple": {
490
- "retrieval": {
491
- "hit_rate": 0.5555555555555556,
492
- "mrr": 0.39351851851851843,
493
- "precision": 0.1527777777777778
494
- },
495
- "generation": {
496
- "rouge1": 0.04487118921642731,
497
- "rougeL": 0.04487118921642731
498
- }
499
- },
500
- "set": {
501
- "retrieval": {
502
- "hit_rate": 0.6,
503
- "mrr": 0.25,
504
- "precision": 0.2
505
- },
506
- "generation": {
507
- "rouge1": 0.0,
508
- "rougeL": 0.0
509
- }
510
- },
511
- "overall": {
512
- "retrieval": {
513
- "hit_rate": 0.5379746835443038,
514
- "mrr": 0.38132911392405067,
515
- "precision": 0.15981012658227847
516
- },
517
- "generation": {
518
- "rouge1": 0.03161800777081066,
519
- "rougeL": 0.03161800777081066
520
- }
521
- }
522
- },
523
- "metadata": {
524
- "n_questions": 158,
525
- "submit_timestamp": ""
526
- }
527
- }
528
- }
529
- },
530
- "last_version": "1.33.1",
531
- "n_questions": 158,
532
- "date_title": "22 \u043c\u0430\u044f 2025"
533
- }
 
1
+ {
2
+ "items": {
3
+ },
4
+ "last_version": "1.0.0",
5
+ "n_questions": "600",
6
+ "date_title": "31 декабря 2042"
7
+ }