Danil
commited on
Commit
·
6321132
1
Parent(s):
318e5ec
End of training
Browse files- .gitignore +1 -0
- config.json +254 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,254 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "DeepPavlov/rubert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-alarm_type",
|
15 |
+
"2": "B-app_name",
|
16 |
+
"3": "B-artist_name",
|
17 |
+
"4": "B-audiobook_author",
|
18 |
+
"5": "B-audiobook_name",
|
19 |
+
"6": "B-business_name",
|
20 |
+
"7": "B-business_type",
|
21 |
+
"8": "B-change_amount",
|
22 |
+
"9": "B-coffee_type",
|
23 |
+
"10": "B-color_type",
|
24 |
+
"11": "B-cooking_type",
|
25 |
+
"12": "B-currency_name",
|
26 |
+
"13": "B-date",
|
27 |
+
"14": "B-definition_word",
|
28 |
+
"15": "B-device_type",
|
29 |
+
"16": "B-drink_type",
|
30 |
+
"17": "B-email_address",
|
31 |
+
"18": "B-email_folder",
|
32 |
+
"19": "B-event_name",
|
33 |
+
"20": "B-food_type",
|
34 |
+
"21": "B-game_name",
|
35 |
+
"22": "B-general_frequency",
|
36 |
+
"23": "B-house_place",
|
37 |
+
"24": "B-ingredient",
|
38 |
+
"25": "B-joke_type",
|
39 |
+
"26": "B-list_name",
|
40 |
+
"27": "B-meal_type",
|
41 |
+
"28": "B-media_type",
|
42 |
+
"29": "B-movie_name",
|
43 |
+
"30": "B-movie_type",
|
44 |
+
"31": "B-music_album",
|
45 |
+
"32": "B-music_descriptor",
|
46 |
+
"33": "B-music_genre",
|
47 |
+
"34": "B-news_topic",
|
48 |
+
"35": "B-order_type",
|
49 |
+
"36": "B-person",
|
50 |
+
"37": "B-personal_info",
|
51 |
+
"38": "B-place_name",
|
52 |
+
"39": "B-player_setting",
|
53 |
+
"40": "B-playlist_name",
|
54 |
+
"41": "B-podcast_descriptor",
|
55 |
+
"42": "B-podcast_name",
|
56 |
+
"43": "B-radio_name",
|
57 |
+
"44": "B-relation",
|
58 |
+
"45": "B-song_name",
|
59 |
+
"46": "B-sport_type",
|
60 |
+
"47": "B-time",
|
61 |
+
"48": "B-time_zone",
|
62 |
+
"49": "B-timeofday",
|
63 |
+
"50": "B-transport_agency",
|
64 |
+
"51": "B-transport_descriptor",
|
65 |
+
"52": "B-transport_name",
|
66 |
+
"53": "B-transport_type",
|
67 |
+
"54": "B-weather_descriptor",
|
68 |
+
"55": "I-alarm_type",
|
69 |
+
"56": "I-app_name",
|
70 |
+
"57": "I-artist_name",
|
71 |
+
"58": "I-audiobook_author",
|
72 |
+
"59": "I-audiobook_name",
|
73 |
+
"60": "I-business_name",
|
74 |
+
"61": "I-business_type",
|
75 |
+
"62": "I-change_amount",
|
76 |
+
"63": "I-coffee_type",
|
77 |
+
"64": "I-color_type",
|
78 |
+
"65": "I-cooking_type",
|
79 |
+
"66": "I-currency_name",
|
80 |
+
"67": "I-date",
|
81 |
+
"68": "I-definition_word",
|
82 |
+
"69": "I-device_type",
|
83 |
+
"70": "I-drink_type",
|
84 |
+
"71": "I-email_address",
|
85 |
+
"72": "I-email_folder",
|
86 |
+
"73": "I-event_name",
|
87 |
+
"74": "I-food_type",
|
88 |
+
"75": "I-game_name",
|
89 |
+
"76": "I-general_frequency",
|
90 |
+
"77": "I-house_place",
|
91 |
+
"78": "I-ingredient",
|
92 |
+
"79": "I-joke_type",
|
93 |
+
"80": "I-list_name",
|
94 |
+
"81": "I-meal_type",
|
95 |
+
"82": "I-media_type",
|
96 |
+
"83": "I-movie_name",
|
97 |
+
"84": "I-movie_type",
|
98 |
+
"85": "I-music_album",
|
99 |
+
"86": "I-music_descriptor",
|
100 |
+
"87": "I-music_genre",
|
101 |
+
"88": "I-news_topic",
|
102 |
+
"89": "I-order_type",
|
103 |
+
"90": "I-person",
|
104 |
+
"91": "I-personal_info",
|
105 |
+
"92": "I-place_name",
|
106 |
+
"93": "I-player_setting",
|
107 |
+
"94": "I-playlist_name",
|
108 |
+
"95": "I-podcast_descriptor",
|
109 |
+
"96": "I-podcast_name",
|
110 |
+
"97": "I-radio_name",
|
111 |
+
"98": "I-relation",
|
112 |
+
"99": "I-song_name",
|
113 |
+
"100": "I-sport_type",
|
114 |
+
"101": "I-time",
|
115 |
+
"102": "I-time_zone",
|
116 |
+
"103": "I-timeofday",
|
117 |
+
"104": "I-transport_agency",
|
118 |
+
"105": "I-transport_descriptor",
|
119 |
+
"106": "I-transport_name",
|
120 |
+
"107": "I-transport_type",
|
121 |
+
"108": "I-weather_descriptor"
|
122 |
+
},
|
123 |
+
"initializer_range": 0.02,
|
124 |
+
"intermediate_size": 3072,
|
125 |
+
"label2id": {
|
126 |
+
"B-alarm_type": 1,
|
127 |
+
"B-app_name": 2,
|
128 |
+
"B-artist_name": 3,
|
129 |
+
"B-audiobook_author": 4,
|
130 |
+
"B-audiobook_name": 5,
|
131 |
+
"B-business_name": 6,
|
132 |
+
"B-business_type": 7,
|
133 |
+
"B-change_amount": 8,
|
134 |
+
"B-coffee_type": 9,
|
135 |
+
"B-color_type": 10,
|
136 |
+
"B-cooking_type": 11,
|
137 |
+
"B-currency_name": 12,
|
138 |
+
"B-date": 13,
|
139 |
+
"B-definition_word": 14,
|
140 |
+
"B-device_type": 15,
|
141 |
+
"B-drink_type": 16,
|
142 |
+
"B-email_address": 17,
|
143 |
+
"B-email_folder": 18,
|
144 |
+
"B-event_name": 19,
|
145 |
+
"B-food_type": 20,
|
146 |
+
"B-game_name": 21,
|
147 |
+
"B-general_frequency": 22,
|
148 |
+
"B-house_place": 23,
|
149 |
+
"B-ingredient": 24,
|
150 |
+
"B-joke_type": 25,
|
151 |
+
"B-list_name": 26,
|
152 |
+
"B-meal_type": 27,
|
153 |
+
"B-media_type": 28,
|
154 |
+
"B-movie_name": 29,
|
155 |
+
"B-movie_type": 30,
|
156 |
+
"B-music_album": 31,
|
157 |
+
"B-music_descriptor": 32,
|
158 |
+
"B-music_genre": 33,
|
159 |
+
"B-news_topic": 34,
|
160 |
+
"B-order_type": 35,
|
161 |
+
"B-person": 36,
|
162 |
+
"B-personal_info": 37,
|
163 |
+
"B-place_name": 38,
|
164 |
+
"B-player_setting": 39,
|
165 |
+
"B-playlist_name": 40,
|
166 |
+
"B-podcast_descriptor": 41,
|
167 |
+
"B-podcast_name": 42,
|
168 |
+
"B-radio_name": 43,
|
169 |
+
"B-relation": 44,
|
170 |
+
"B-song_name": 45,
|
171 |
+
"B-sport_type": 46,
|
172 |
+
"B-time": 47,
|
173 |
+
"B-time_zone": 48,
|
174 |
+
"B-timeofday": 49,
|
175 |
+
"B-transport_agency": 50,
|
176 |
+
"B-transport_descriptor": 51,
|
177 |
+
"B-transport_name": 52,
|
178 |
+
"B-transport_type": 53,
|
179 |
+
"B-weather_descriptor": 54,
|
180 |
+
"I-alarm_type": 55,
|
181 |
+
"I-app_name": 56,
|
182 |
+
"I-artist_name": 57,
|
183 |
+
"I-audiobook_author": 58,
|
184 |
+
"I-audiobook_name": 59,
|
185 |
+
"I-business_name": 60,
|
186 |
+
"I-business_type": 61,
|
187 |
+
"I-change_amount": 62,
|
188 |
+
"I-coffee_type": 63,
|
189 |
+
"I-color_type": 64,
|
190 |
+
"I-cooking_type": 65,
|
191 |
+
"I-currency_name": 66,
|
192 |
+
"I-date": 67,
|
193 |
+
"I-definition_word": 68,
|
194 |
+
"I-device_type": 69,
|
195 |
+
"I-drink_type": 70,
|
196 |
+
"I-email_address": 71,
|
197 |
+
"I-email_folder": 72,
|
198 |
+
"I-event_name": 73,
|
199 |
+
"I-food_type": 74,
|
200 |
+
"I-game_name": 75,
|
201 |
+
"I-general_frequency": 76,
|
202 |
+
"I-house_place": 77,
|
203 |
+
"I-ingredient": 78,
|
204 |
+
"I-joke_type": 79,
|
205 |
+
"I-list_name": 80,
|
206 |
+
"I-meal_type": 81,
|
207 |
+
"I-media_type": 82,
|
208 |
+
"I-movie_name": 83,
|
209 |
+
"I-movie_type": 84,
|
210 |
+
"I-music_album": 85,
|
211 |
+
"I-music_descriptor": 86,
|
212 |
+
"I-music_genre": 87,
|
213 |
+
"I-news_topic": 88,
|
214 |
+
"I-order_type": 89,
|
215 |
+
"I-person": 90,
|
216 |
+
"I-personal_info": 91,
|
217 |
+
"I-place_name": 92,
|
218 |
+
"I-player_setting": 93,
|
219 |
+
"I-playlist_name": 94,
|
220 |
+
"I-podcast_descriptor": 95,
|
221 |
+
"I-podcast_name": 96,
|
222 |
+
"I-radio_name": 97,
|
223 |
+
"I-relation": 98,
|
224 |
+
"I-song_name": 99,
|
225 |
+
"I-sport_type": 100,
|
226 |
+
"I-time": 101,
|
227 |
+
"I-time_zone": 102,
|
228 |
+
"I-timeofday": 103,
|
229 |
+
"I-transport_agency": 104,
|
230 |
+
"I-transport_descriptor": 105,
|
231 |
+
"I-transport_name": 106,
|
232 |
+
"I-transport_type": 107,
|
233 |
+
"I-weather_descriptor": 108,
|
234 |
+
"O": 0
|
235 |
+
},
|
236 |
+
"layer_norm_eps": 1e-12,
|
237 |
+
"max_position_embeddings": 512,
|
238 |
+
"model_type": "bert",
|
239 |
+
"num_attention_heads": 12,
|
240 |
+
"num_hidden_layers": 12,
|
241 |
+
"output_past": true,
|
242 |
+
"pad_token_id": 0,
|
243 |
+
"pooler_fc_size": 768,
|
244 |
+
"pooler_num_attention_heads": 12,
|
245 |
+
"pooler_num_fc_layers": 3,
|
246 |
+
"pooler_size_per_head": 128,
|
247 |
+
"pooler_type": "first_token_transform",
|
248 |
+
"position_embedding_type": "absolute",
|
249 |
+
"torch_dtype": "float32",
|
250 |
+
"transformers_version": "4.30.2",
|
251 |
+
"type_vocab_size": 2,
|
252 |
+
"use_cache": true,
|
253 |
+
"vocab_size": 119547
|
254 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e816242fb49c29ad398d82b4e6971a6089572c66b761cc7f62a236d9e9eff9a4
|
3 |
+
size 709458797
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_basic_tokenize": true,
|
5 |
+
"do_lower_case": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"model_max_length": 1000000000000000019884624838656,
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"strip_accents": null,
|
12 |
+
"tokenize_chinese_chars": true,
|
13 |
+
"tokenizer_class": "BertTokenizer",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0856f605059e3dce0783dc5fcb2fa53a9a830c99333aa5b0ddbf87bd426c1487
|
3 |
+
size 3963
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|