vladeachka commited on
Commit
9a9c9da
·
verified ·
1 Parent(s): 88236aa

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,251 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cointegrated/rubert-tiny2",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "emb_size": 312,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 312,
13
+ "id2label": {
14
+ "0": "B-change_amount",
15
+ "1": "B-music_descriptor",
16
+ "2": "B-relation",
17
+ "3": "I-food_type",
18
+ "4": "I-time",
19
+ "5": "I-transport_name",
20
+ "6": "I-song_name",
21
+ "7": "I-ingredient",
22
+ "8": "I-podcast_descriptor",
23
+ "9": "B-transport_agency",
24
+ "10": "I-game_name",
25
+ "11": "B-time_zone",
26
+ "12": "B-event_name",
27
+ "13": "B-general_frequency",
28
+ "14": "I-person",
29
+ "15": "B-email_folder",
30
+ "16": "B-personal_info",
31
+ "17": "I-audiobook_author",
32
+ "18": "I-date",
33
+ "19": "B-list_name",
34
+ "20": "I-movie_type",
35
+ "21": "B-color_type",
36
+ "22": "I-drink_type",
37
+ "23": "I-artist_name",
38
+ "24": "B-news_topic",
39
+ "25": "B-date",
40
+ "26": "B-cooking_type",
41
+ "27": "B-transport_name",
42
+ "28": "I-weather_descriptor",
43
+ "29": "I-business_name",
44
+ "30": "B-joke_type",
45
+ "31": "I-house_place",
46
+ "32": "I-list_name",
47
+ "33": "I-playlist_name",
48
+ "34": "I-radio_name",
49
+ "35": "I-email_address",
50
+ "36": "I-meal_type",
51
+ "37": "I-time_zone",
52
+ "38": "B-business_name",
53
+ "39": "B-time",
54
+ "40": "I-relation",
55
+ "41": "I-business_type",
56
+ "42": "I-music_descriptor",
57
+ "43": "B-sport_type",
58
+ "44": "B-transport_descriptor",
59
+ "45": "B-definition_word",
60
+ "46": "O",
61
+ "47": "B-music_album",
62
+ "48": "B-coffee_type",
63
+ "49": "B-game_name",
64
+ "50": "I-joke_type",
65
+ "51": "I-sport_type",
66
+ "52": "B-audiobook_name",
67
+ "53": "I-cooking_type",
68
+ "54": "B-podcast_name",
69
+ "55": "I-personal_info",
70
+ "56": "B-artist_name",
71
+ "57": "I-transport_type",
72
+ "58": "B-business_type",
73
+ "59": "B-app_name",
74
+ "60": "B-currency_name",
75
+ "61": "I-music_album",
76
+ "62": "I-definition_word",
77
+ "63": "I-transport_agency",
78
+ "64": "I-place_name",
79
+ "65": "B-house_place",
80
+ "66": "B-music_genre",
81
+ "67": "B-playlist_name",
82
+ "68": "I-coffee_type",
83
+ "69": "B-meal_type",
84
+ "70": "B-movie_name",
85
+ "71": "B-weather_descriptor",
86
+ "72": "B-device_type",
87
+ "73": "I-podcast_name",
88
+ "74": "B-drink_type",
89
+ "75": "B-transport_type",
90
+ "76": "B-person",
91
+ "77": "I-device_type",
92
+ "78": "B-player_setting",
93
+ "79": "I-currency_name",
94
+ "80": "I-alarm_type",
95
+ "81": "B-place_name",
96
+ "82": "B-movie_type",
97
+ "83": "B-timeofday",
98
+ "84": "B-podcast_descriptor",
99
+ "85": "B-audiobook_author",
100
+ "86": "I-order_type",
101
+ "87": "B-game_type",
102
+ "88": "I-email_folder",
103
+ "89": "B-order_type",
104
+ "90": "B-media_type",
105
+ "91": "B-food_type",
106
+ "92": "I-event_name",
107
+ "93": "I-color_type",
108
+ "94": "B-alarm_type",
109
+ "95": "I-media_type",
110
+ "96": "I-player_setting",
111
+ "97": "B-song_name",
112
+ "98": "B-radio_name",
113
+ "99": "I-general_frequency",
114
+ "100": "I-news_topic",
115
+ "101": "B-ingredient",
116
+ "102": "I-timeofday",
117
+ "103": "I-app_name",
118
+ "104": "I-music_genre",
119
+ "105": "I-movie_name",
120
+ "106": "I-audiobook_name",
121
+ "107": "I-transport_descriptor",
122
+ "108": "B-email_address",
123
+ "109": "I-change_amount"
124
+ },
125
+ "initializer_range": 0.02,
126
+ "intermediate_size": 600,
127
+ "label2id": {
128
+ "B-alarm_type": 94,
129
+ "B-app_name": 59,
130
+ "B-artist_name": 56,
131
+ "B-audiobook_author": 85,
132
+ "B-audiobook_name": 52,
133
+ "B-business_name": 38,
134
+ "B-business_type": 58,
135
+ "B-change_amount": 0,
136
+ "B-coffee_type": 48,
137
+ "B-color_type": 21,
138
+ "B-cooking_type": 26,
139
+ "B-currency_name": 60,
140
+ "B-date": 25,
141
+ "B-definition_word": 45,
142
+ "B-device_type": 72,
143
+ "B-drink_type": 74,
144
+ "B-email_address": 108,
145
+ "B-email_folder": 15,
146
+ "B-event_name": 12,
147
+ "B-food_type": 91,
148
+ "B-game_name": 49,
149
+ "B-game_type": 87,
150
+ "B-general_frequency": 13,
151
+ "B-house_place": 65,
152
+ "B-ingredient": 101,
153
+ "B-joke_type": 30,
154
+ "B-list_name": 19,
155
+ "B-meal_type": 69,
156
+ "B-media_type": 90,
157
+ "B-movie_name": 70,
158
+ "B-movie_type": 82,
159
+ "B-music_album": 47,
160
+ "B-music_descriptor": 1,
161
+ "B-music_genre": 66,
162
+ "B-news_topic": 24,
163
+ "B-order_type": 89,
164
+ "B-person": 76,
165
+ "B-personal_info": 16,
166
+ "B-place_name": 81,
167
+ "B-player_setting": 78,
168
+ "B-playlist_name": 67,
169
+ "B-podcast_descriptor": 84,
170
+ "B-podcast_name": 54,
171
+ "B-radio_name": 98,
172
+ "B-relation": 2,
173
+ "B-song_name": 97,
174
+ "B-sport_type": 43,
175
+ "B-time": 39,
176
+ "B-time_zone": 11,
177
+ "B-timeofday": 83,
178
+ "B-transport_agency": 9,
179
+ "B-transport_descriptor": 44,
180
+ "B-transport_name": 27,
181
+ "B-transport_type": 75,
182
+ "B-weather_descriptor": 71,
183
+ "I-alarm_type": 80,
184
+ "I-app_name": 103,
185
+ "I-artist_name": 23,
186
+ "I-audiobook_author": 17,
187
+ "I-audiobook_name": 106,
188
+ "I-business_name": 29,
189
+ "I-business_type": 41,
190
+ "I-change_amount": 109,
191
+ "I-coffee_type": 68,
192
+ "I-color_type": 93,
193
+ "I-cooking_type": 53,
194
+ "I-currency_name": 79,
195
+ "I-date": 18,
196
+ "I-definition_word": 62,
197
+ "I-device_type": 77,
198
+ "I-drink_type": 22,
199
+ "I-email_address": 35,
200
+ "I-email_folder": 88,
201
+ "I-event_name": 92,
202
+ "I-food_type": 3,
203
+ "I-game_name": 10,
204
+ "I-general_frequency": 99,
205
+ "I-house_place": 31,
206
+ "I-ingredient": 7,
207
+ "I-joke_type": 50,
208
+ "I-list_name": 32,
209
+ "I-meal_type": 36,
210
+ "I-media_type": 95,
211
+ "I-movie_name": 105,
212
+ "I-movie_type": 20,
213
+ "I-music_album": 61,
214
+ "I-music_descriptor": 42,
215
+ "I-music_genre": 104,
216
+ "I-news_topic": 100,
217
+ "I-order_type": 86,
218
+ "I-person": 14,
219
+ "I-personal_info": 55,
220
+ "I-place_name": 64,
221
+ "I-player_setting": 96,
222
+ "I-playlist_name": 33,
223
+ "I-podcast_descriptor": 8,
224
+ "I-podcast_name": 73,
225
+ "I-radio_name": 34,
226
+ "I-relation": 40,
227
+ "I-song_name": 6,
228
+ "I-sport_type": 51,
229
+ "I-time": 4,
230
+ "I-time_zone": 37,
231
+ "I-timeofday": 102,
232
+ "I-transport_agency": 63,
233
+ "I-transport_descriptor": 107,
234
+ "I-transport_name": 5,
235
+ "I-transport_type": 57,
236
+ "I-weather_descriptor": 28,
237
+ "O": 46
238
+ },
239
+ "layer_norm_eps": 1e-12,
240
+ "max_position_embeddings": 2048,
241
+ "model_type": "bert",
242
+ "num_attention_heads": 12,
243
+ "num_hidden_layers": 3,
244
+ "pad_token_id": 0,
245
+ "position_embedding_type": "absolute",
246
+ "torch_dtype": "float32",
247
+ "transformers_version": "4.47.1",
248
+ "type_vocab_size": 2,
249
+ "use_cache": true,
250
+ "vocab_size": 83828
251
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0996134d8292f640c89b4acf88d4e118d2f1387ff53e6205d6019ee28e9b70
3
+ size 116528544
runs/Dec26_20-42-16_2d2756491a0b/events.out.tfevents.1735245737.2d2756491a0b.578.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b753a2a3f3fe1393205113ec11e90aa08f2911f4a293d42e1d05ff2fcc7680
3
+ size 11647
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "max_length": 512,
51
+ "model_max_length": 2048,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bc52eb9fce28609a7ffdf940f2598bbffef284d3ec73a69784456086865606d
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff