Hugging Face's logo

apperry-ai
/
fact_extraction_roberta_crf

Token Classification
Transformers
PyTorch
roberta
Model card Files
xet
Community
3

Upload folder using huggingface_hub

#1
by animaai - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+151970
-0
Files changed (10) hide show
  1. config.json +423 -0
  2. eval/metric.json +1 -0
  3. eval/prediction.validation.json +0 -0
  4. merges.txt +0 -0
  5. pytorch_model.bin +3 -0
  6. special_tokens_map.json +15 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +16 -0
  9. trainer_config.json +1 -0
  10. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,423 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./roberta_cleen_all_exist_new/model_xchxky/epoch_1",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "crf_state_dict": {
10
+ "_constraint_mask": [
11
+ [
12
+ 1.0,
13
+ 1.0,
14
+ 1.0,
15
+ 1.0,
16
+ 1.0,
17
+ 1.0,
18
+ 0.0,
19
+ 0.0,
20
+ 0.0,
21
+ 0.0,
22
+ 1.0,
23
+ 0.0,
24
+ 1.0
25
+ ],
26
+ [
27
+ 1.0,
28
+ 1.0,
29
+ 1.0,
30
+ 1.0,
31
+ 1.0,
32
+ 0.0,
33
+ 1.0,
34
+ 0.0,
35
+ 0.0,
36
+ 0.0,
37
+ 1.0,
38
+ 0.0,
39
+ 1.0
40
+ ],
41
+ [
42
+ 1.0,
43
+ 1.0,
44
+ 1.0,
45
+ 1.0,
46
+ 1.0,
47
+ 0.0,
48
+ 0.0,
49
+ 1.0,
50
+ 0.0,
51
+ 0.0,
52
+ 1.0,
53
+ 0.0,
54
+ 1.0
55
+ ],
56
+ [
57
+ 1.0,
58
+ 1.0,
59
+ 1.0,
60
+ 1.0,
61
+ 1.0,
62
+ 0.0,
63
+ 0.0,
64
+ 0.0,
65
+ 1.0,
66
+ 0.0,
67
+ 1.0,
68
+ 0.0,
69
+ 1.0
70
+ ],
71
+ [
72
+ 1.0,
73
+ 1.0,
74
+ 1.0,
75
+ 1.0,
76
+ 1.0,
77
+ 0.0,
78
+ 0.0,
79
+ 0.0,
80
+ 0.0,
81
+ 1.0,
82
+ 1.0,
83
+ 0.0,
84
+ 1.0
85
+ ],
86
+ [
87
+ 1.0,
88
+ 1.0,
89
+ 1.0,
90
+ 1.0,
91
+ 1.0,
92
+ 1.0,
93
+ 0.0,
94
+ 0.0,
95
+ 0.0,
96
+ 0.0,
97
+ 1.0,
98
+ 0.0,
99
+ 1.0
100
+ ],
101
+ [
102
+ 1.0,
103
+ 1.0,
104
+ 1.0,
105
+ 1.0,
106
+ 1.0,
107
+ 0.0,
108
+ 1.0,
109
+ 0.0,
110
+ 0.0,
111
+ 0.0,
112
+ 1.0,
113
+ 0.0,
114
+ 1.0
115
+ ],
116
+ [
117
+ 1.0,
118
+ 1.0,
119
+ 1.0,
120
+ 1.0,
121
+ 1.0,
122
+ 0.0,
123
+ 0.0,
124
+ 1.0,
125
+ 0.0,
126
+ 0.0,
127
+ 1.0,
128
+ 0.0,
129
+ 1.0
130
+ ],
131
+ [
132
+ 1.0,
133
+ 1.0,
134
+ 1.0,
135
+ 1.0,
136
+ 1.0,
137
+ 0.0,
138
+ 0.0,
139
+ 0.0,
140
+ 1.0,
141
+ 0.0,
142
+ 1.0,
143
+ 0.0,
144
+ 1.0
145
+ ],
146
+ [
147
+ 1.0,
148
+ 1.0,
149
+ 1.0,
150
+ 1.0,
151
+ 1.0,
152
+ 0.0,
153
+ 0.0,
154
+ 0.0,
155
+ 0.0,
156
+ 1.0,
157
+ 1.0,
158
+ 0.0,
159
+ 1.0
160
+ ],
161
+ [
162
+ 1.0,
163
+ 1.0,
164
+ 1.0,
165
+ 1.0,
166
+ 1.0,
167
+ 0.0,
168
+ 0.0,
169
+ 0.0,
170
+ 0.0,
171
+ 0.0,
172
+ 1.0,
173
+ 0.0,
174
+ 1.0
175
+ ],
176
+ [
177
+ 1.0,
178
+ 1.0,
179
+ 1.0,
180
+ 1.0,
181
+ 1.0,
182
+ 0.0,
183
+ 0.0,
184
+ 0.0,
185
+ 0.0,
186
+ 0.0,
187
+ 1.0,
188
+ 0.0,
189
+ 0.0
190
+ ],
191
+ [
192
+ 0.0,
193
+ 0.0,
194
+ 0.0,
195
+ 0.0,
196
+ 0.0,
197
+ 0.0,
198
+ 0.0,
199
+ 0.0,
200
+ 0.0,
201
+ 0.0,
202
+ 0.0,
203
+ 0.0,
204
+ 0.0
205
+ ]
206
+ ],
207
+ "end_transitions": [
208
+ 0.21687424182891846,
209
+ 1.5857642889022827,
210
+ 0.758258581161499,
211
+ 0.37032732367515564,
212
+ -1.329129695892334,
213
+ 2.4964492321014404,
214
+ 0.8586344718933105,
215
+ -1.4632924795150757,
216
+ 1.2904568910598755,
217
+ 0.8706234693527222,
218
+ -0.1880217045545578
219
+ ],
220
+ "start_transitions": [
221
+ 0.9229826927185059,
222
+ 0.28560739755630493,
223
+ 0.14332018792629242,
224
+ -1.4447805881500244,
225
+ 1.4846503734588623,
226
+ -1.5904203653335571,
227
+ -0.7379185557365417,
228
+ -1.8030710220336914,
229
+ -1.0581018924713135,
230
+ 0.6242042779922485,
231
+ 0.5164673328399658
232
+ ],
233
+ "transitions": [
234
+ [
235
+ 0.3673975467681885,
236
+ 0.18701963126659393,
237
+ -0.43712371587753296,
238
+ -0.1407420039176941,
239
+ -0.10534486174583435,
240
+ 0.24474096298217773,
241
+ 0.7354440093040466,
242
+ 0.34748244285583496,
243
+ 0.17631690204143524,
244
+ -0.23136325180530548,
245
+ -0.025033308193087578
246
+ ],
247
+ [
248
+ -0.007745583541691303,
249
+ -0.09301131218671799,
250
+ -0.31596821546554565,
251
+ -0.26407039165496826,
252
+ -0.06394483149051666,
253
+ 0.13408444821834564,
254
+ -0.4474257230758667,
255
+ -0.2721427083015442,
256
+ -0.12181078642606735,
257
+ -0.12198833376169205,
258
+ 0.5588247179985046
259
+ ],
260
+ [
261
+ -0.19631847739219666,
262
+ 0.008313635364174843,
263
+ 0.15113116800785065,
264
+ 0.04224454239010811,
265
+ -0.236379936337471,
266
+ -0.22627614438533783,
267
+ -0.04470784589648247,
268
+ -0.06738904118537903,
269
+ -0.2742701470851898,
270
+ 0.5238128900527954,
271
+ -0.19441142678260803
272
+ ],
273
+ [
274
+ 0.25509530305862427,
275
+ 0.0956823006272316,
276
+ 0.32445773482322693,
277
+ -0.3041941523551941,
278
+ -0.24632413685321808,
279
+ -0.06011788919568062,
280
+ 0.05390192195773125,
281
+ -0.45170074701309204,
282
+ 0.14786915481090546,
283
+ -0.31270110607147217,
284
+ 0.12534676492214203
285
+ ],
286
+ [
287
+ -0.33268553018569946,
288
+ -0.27061566710472107,
289
+ 0.4702346622943878,
290
+ -0.374167263507843,
291
+ -0.0938689336180687,
292
+ -0.4018147885799408,
293
+ 0.24715960025787354,
294
+ 0.09559278190135956,
295
+ 0.04130111634731293,
296
+ 0.15933264791965485,
297
+ 0.5198276042938232
298
+ ],
299
+ [
300
+ -0.08424585312604904,
301
+ 0.41698721051216125,
302
+ 0.01722242869436741,
303
+ -0.317511647939682,
304
+ 0.15484148263931274,
305
+ -0.02030128985643387,
306
+ 0.1650458425283432,
307
+ 0.2202066034078598,
308
+ 0.24747343361377716,
309
+ 0.2225068062543869,
310
+ -0.07041354477405548
311
+ ],
312
+ [
313
+ 0.17406269907951355,
314
+ -0.49445095658302307,
315
+ 0.1372549682855606,
316
+ 0.5307994484901428,
317
+ 0.2616923451423645,
318
+ 0.08446840941905975,
319
+ -0.03838552534580231,
320
+ -0.39147865772247314,
321
+ 0.10781766474246979,
322
+ 0.5030436515808105,
323
+ -0.2691557705402374
324
+ ],
325
+ [
326
+ 0.3631405830383301,
327
+ 0.5819560885429382,
328
+ 0.43440482020378113,
329
+ -0.08992395550012589,
330
+ 0.12068815529346466,
331
+ -0.18815878033638,
332
+ 0.31527331471443176,
333
+ 0.03760548308491707,
334
+ 0.6801357865333557,
335
+ 0.29773885011672974,
336
+ -0.04291761294007301
337
+ ],
338
+ [
339
+ 0.17793186008930206,
340
+ 0.21460671722888947,
341
+ 0.17269837856292725,
342
+ 0.4337525963783264,
343
+ -0.3202753961086273,
344
+ 0.2475089281797409,
345
+ -0.24713143706321716,
346
+ -0.2365410327911377,
347
+ -0.2708987891674042,
348
+ -0.04050455614924431,
349
+ -0.12179888039827347
350
+ ],
351
+ [
352
+ -0.09372731298208237,
353
+ -0.03050650842487812,
354
+ -0.35732266306877136,
355
+ -0.03869544342160225,
356
+ 0.15174028277397156,
357
+ -0.2674034535884857,
358
+ -0.07940886914730072,
359
+ -0.4257971942424774,
360
+ 0.2486799657344818,
361
+ -0.12294259667396545,
362
+ 0.2491007000207901
363
+ ],
364
+ [
365
+ 0.1782885640859604,
366
+ -0.471216082572937,
367
+ -0.08392570912837982,
368
+ -0.47434109449386597,
369
+ 0.6260464787483215,
370
+ 0.23181001842021942,
371
+ -0.1574145406484604,
372
+ -0.047237854450941086,
373
+ -0.1693454533815384,
374
+ -0.4191673696041107,
375
+ 0.21925123035907745
376
+ ]
377
+ ]
378
+ },
379
+ "eos_token_id": 2,
380
+ "hidden_act": "gelu",
381
+ "hidden_dropout_prob": 0.1,
382
+ "hidden_size": 768,
383
+ "id2label": {
384
+ "0": "B-Dislikes",
385
+ "1": "B-Family",
386
+ "2": "B-Job",
387
+ "3": "B-Likes",
388
+ "4": "B-Pet",
389
+ "5": "I-Dislikes",
390
+ "6": "I-Family",
391
+ "7": "I-Job",
392
+ "8": "I-Likes",
393
+ "9": "I-Pet",
394
+ "10": "O"
395
+ },
396
+ "initializer_range": 0.02,
397
+ "intermediate_size": 3072,
398
+ "label2id": {
399
+ "B-Dislikes": 0,
400
+ "B-Family": 1,
401
+ "B-Job": 2,
402
+ "B-Likes": 3,
403
+ "B-Pet": 4,
404
+ "I-Dislikes": 5,
405
+ "I-Family": 6,
406
+ "I-Job": 7,
407
+ "I-Likes": 8,
408
+ "I-Pet": 9,
409
+ "O": 10
410
+ },
411
+ "layer_norm_eps": 1e-05,
412
+ "max_position_embeddings": 514,
413
+ "model_type": "roberta",
414
+ "num_attention_heads": 12,
415
+ "num_hidden_layers": 12,
416
+ "pad_token_id": 1,
417
+ "position_embedding_type": "absolute",
418
+ "torch_dtype": "float32",
419
+ "transformers_version": "4.20.1",
420
+ "type_vocab_size": 1,
421
+ "use_cache": true,
422
+ "vocab_size": 50265
423
+ }
eval/metric.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"validation": {"micro/f1": 0.5396109388215393, "micro/f1_ci": {}, "micro/recall": 0.44040497008743673, "micro/precision": 0.6965065502183406, "macro/f1": 0.48520536086324473, "macro/f1_ci": {}, "macro/recall": 0.38434102466203635, "macro/precision": 0.6674699394144376, "per_entity_metric": {"Dislikes": {"f1": 0.19607843137254902, "f1_ci": {}, "precision": 0.3333333333333333, "recall": 0.1388888888888889}, "Family": {"f1": 0.49343832020997375, "f1_ci": {}, "precision": 0.7580645161290323, "recall": 0.3657587548638132}, "Job": {"f1": 0.6233766233766235, "f1_ci": {}, "precision": 0.8275862068965517, "recall": 0.5}, "Likes": {"f1": 0.541704857928506, "f1_ci": {}, "precision": 0.6670428893905191, "recall": 0.45601851851851855}, "Pet": {"f1": 0.5714285714285714, "f1_ci": {}, "precision": 0.7513227513227513, "recall": 0.461038961038961}}}}
eval/prediction.validation.json ADDED
The diff for this file is too large to render. See raw diff
 
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0eb020a93f438cc8555ec21ad25051706c8af465193f2aed8af72eb3057e66
3
+ size 496326701
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "./roberta_cleen_all_exist_new/model_xchxky/epoch_1",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
trainer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"dataset": null, "dataset_split": "train", "dataset_name": null, "local_dataset": {"train": "/home/komleva/fact_extraction/prepared_data/train_.txt", "validation": "/home/komleva/fact_extraction/prepared_data/test_.txt", "test": "/home/komleva/fact_extraction/prepared_data/test_.txt"}, "model": "roberta-base", "crf": true, "max_length": 128, "epoch": 30, "batch_size": 400, "lr": 0.0001, "random_seed": 42, "gradient_accumulation_steps": 1, "weight_decay": 1e-05, "lr_warmup_step_ratio": 0.1, "max_grad_norm": 1.0}
vocab.json ADDED
The diff for this file is too large to render. See raw diff