cartesinus commited on
Commit
39f4233
1 Parent(s): 30ca7f8

Training in progress, epoch 1

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,310 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "o",
15
+ "1": "b-device_name",
16
+ "10": "i-date",
17
+ "100": "i-text_es",
18
+ "101": "b-src_lang_es",
19
+ "102": "b-trg_lang_de",
20
+ "103": "b-text_it",
21
+ "104": "i-text_it",
22
+ "105": "b-src_lang_it",
23
+ "106": "b-text_fr",
24
+ "107": "i-text_fr",
25
+ "108": "b-src_lang_fr",
26
+ "109": "b-text_en",
27
+ "11": "",
28
+ "110": "b-src_lang_en",
29
+ "111": "i-text_en",
30
+ "112": "b-text_pl",
31
+ "113": "b-src_lang_pl",
32
+ "114": "i-text_pl",
33
+ "115": "b-trg_lang_general",
34
+ "116": "b-img_query",
35
+ "117": "i-img_query",
36
+ "118": "i-txt_query",
37
+ "119": "i-query",
38
+ "12": "b-location",
39
+ "120": "b-category",
40
+ "121": "i-category",
41
+ "122": "b-rating",
42
+ "123": "b-review_count",
43
+ "124": "b-channel_id",
44
+ "125": "i-channel_id",
45
+ "126": "i-pathname",
46
+ "127": "i-mesage",
47
+ "128": "i-massage",
48
+ "129": "i-filter",
49
+ "13": "i-location",
50
+ "130": "i-percent",
51
+ "131": "b-album_type_an",
52
+ "132": "b-album_type_1a",
53
+ "133": "i-album_type_1a",
54
+ "134": "i-text_esi",
55
+ "135": "i-all_lang",
56
+ "136": "i-rating",
57
+ "137": "i-review_count",
58
+ "138": "i-filename",
59
+ "14": "b-pathname",
60
+ "15": "b-from",
61
+ "16": "b-to",
62
+ "17": "b-filename",
63
+ "18": "b-txt_query",
64
+ "19": "b-query",
65
+ "2": "i-device_name",
66
+ "20": "b-name",
67
+ "21": "i-name",
68
+ "22": "b-phone_number",
69
+ "23": "i-phone_number",
70
+ "24": "b-phone_type",
71
+ "25": "b-email",
72
+ "26": "i-email",
73
+ "27": "b-sender_address",
74
+ "28": "i-to",
75
+ "29": "b-subject",
76
+ "3": "b-av_alias",
77
+ "30": "i-subject",
78
+ "31": "b-message",
79
+ "32": "i-message",
80
+ "33": "b-time",
81
+ "34": "i-time",
82
+ "35": "b-label",
83
+ "36": "i-label",
84
+ "37": "b-priority",
85
+ "38": "i-priority",
86
+ "39": "b-caption",
87
+ "4": "i-av_alias",
88
+ "40": "i-caption",
89
+ "41": "b-picture_url",
90
+ "42": "b-status",
91
+ "43": "i-status",
92
+ "44": "b-album",
93
+ "45": "i-album",
94
+ "46": "b-weight",
95
+ "47": "i-weight",
96
+ "48": "b-file_name",
97
+ "49": "i-file_name",
98
+ "5": "b-value",
99
+ "50": "b-mail",
100
+ "51": "b-file_size",
101
+ "52": "i-file_size",
102
+ "53": "b-mime_type",
103
+ "54": "b-hashtag",
104
+ "55": "b-filter",
105
+ "56": "i-hashtag",
106
+ "57": "b-date_day",
107
+ "58": "b-date_month",
108
+ "59": "b-count",
109
+ "6": "i-value",
110
+ "60": "b-portal",
111
+ "61": "b-section",
112
+ "62": "i-portal",
113
+ "63": "b-sender",
114
+ "64": "i-sender",
115
+ "65": "b-channel",
116
+ "66": "i-channel",
117
+ "67": "b-username",
118
+ "68": "i-username",
119
+ "69": "b-purpose",
120
+ "7": "b-event_name",
121
+ "70": "i-purpose",
122
+ "71": "b-topic",
123
+ "72": "i-topic",
124
+ "73": "b-percent",
125
+ "74": "b-artist",
126
+ "75": "b-power",
127
+ "76": "b-album_type",
128
+ "77": "i-album_type",
129
+ "78": "b-playlist",
130
+ "79": "i-playlist",
131
+ "8": "i-event_name",
132
+ "80": "b-song",
133
+ "81": "i-song",
134
+ "82": "b-album_name",
135
+ "83": "i-artist",
136
+ "84": "i-album_name",
137
+ "85": "b-state",
138
+ "86": "b-seek_time",
139
+ "87": "b-text_multi",
140
+ "88": "i-text_multi",
141
+ "89": "b-all_lang",
142
+ "9": "b-date",
143
+ "90": "b-text_de",
144
+ "91": "i-text_de",
145
+ "92": "b-src_lang_de",
146
+ "93": "b-trg_lang_pl",
147
+ "94": "b-translator",
148
+ "95": "b-trg_lang_es",
149
+ "96": "b-trg_lang_it",
150
+ "97": "b-trg_lang_fr",
151
+ "98": "b-trg_lang_en",
152
+ "99": "b-text_es"
153
+ },
154
+ "initializer_range": 0.02,
155
+ "intermediate_size": 3072,
156
+ "label2id": {
157
+ "": "11",
158
+ "b-album": "44",
159
+ "b-album_name": "82",
160
+ "b-album_type": "76",
161
+ "b-album_type_1a": "132",
162
+ "b-album_type_an": "131",
163
+ "b-all_lang": "89",
164
+ "b-artist": "74",
165
+ "b-av_alias": "3",
166
+ "b-caption": "39",
167
+ "b-category": "120",
168
+ "b-channel": "65",
169
+ "b-channel_id": "124",
170
+ "b-count": "59",
171
+ "b-date": "9",
172
+ "b-date_day": "57",
173
+ "b-date_month": "58",
174
+ "b-device_name": "1",
175
+ "b-email": "25",
176
+ "b-event_name": "7",
177
+ "b-file_name": "48",
178
+ "b-file_size": "51",
179
+ "b-filename": "17",
180
+ "b-filter": "55",
181
+ "b-from": "15",
182
+ "b-hashtag": "54",
183
+ "b-img_query": "116",
184
+ "b-label": "35",
185
+ "b-location": "12",
186
+ "b-mail": "50",
187
+ "b-message": "31",
188
+ "b-mime_type": "53",
189
+ "b-name": "20",
190
+ "b-pathname": "14",
191
+ "b-percent": "73",
192
+ "b-phone_number": "22",
193
+ "b-phone_type": "24",
194
+ "b-picture_url": "41",
195
+ "b-playlist": "78",
196
+ "b-portal": "60",
197
+ "b-power": "75",
198
+ "b-priority": "37",
199
+ "b-purpose": "69",
200
+ "b-query": "19",
201
+ "b-rating": "122",
202
+ "b-review_count": "123",
203
+ "b-section": "61",
204
+ "b-seek_time": "86",
205
+ "b-sender": "63",
206
+ "b-sender_address": "27",
207
+ "b-song": "80",
208
+ "b-src_lang_de": "92",
209
+ "b-src_lang_en": "110",
210
+ "b-src_lang_es": "101",
211
+ "b-src_lang_fr": "108",
212
+ "b-src_lang_it": "105",
213
+ "b-src_lang_pl": "113",
214
+ "b-state": "85",
215
+ "b-status": "42",
216
+ "b-subject": "29",
217
+ "b-text_de": "90",
218
+ "b-text_en": "109",
219
+ "b-text_es": "99",
220
+ "b-text_fr": "106",
221
+ "b-text_it": "103",
222
+ "b-text_multi": "87",
223
+ "b-text_pl": "112",
224
+ "b-time": "33",
225
+ "b-to": "16",
226
+ "b-topic": "71",
227
+ "b-translator": "94",
228
+ "b-trg_lang_de": "102",
229
+ "b-trg_lang_en": "98",
230
+ "b-trg_lang_es": "95",
231
+ "b-trg_lang_fr": "97",
232
+ "b-trg_lang_general": "115",
233
+ "b-trg_lang_it": "96",
234
+ "b-trg_lang_pl": "93",
235
+ "b-txt_query": "18",
236
+ "b-username": "67",
237
+ "b-value": "5",
238
+ "b-weight": "46",
239
+ "i-album": "45",
240
+ "i-album_name": "84",
241
+ "i-album_type": "77",
242
+ "i-album_type_1a": "133",
243
+ "i-all_lang": "135",
244
+ "i-artist": "83",
245
+ "i-av_alias": "4",
246
+ "i-caption": "40",
247
+ "i-category": "121",
248
+ "i-channel": "66",
249
+ "i-channel_id": "125",
250
+ "i-date": "10",
251
+ "i-device_name": "2",
252
+ "i-email": "26",
253
+ "i-event_name": "8",
254
+ "i-file_name": "49",
255
+ "i-file_size": "52",
256
+ "i-filename": "138",
257
+ "i-filter": "129",
258
+ "i-hashtag": "56",
259
+ "i-img_query": "117",
260
+ "i-label": "36",
261
+ "i-location": "13",
262
+ "i-massage": "128",
263
+ "i-mesage": "127",
264
+ "i-message": "32",
265
+ "i-name": "21",
266
+ "i-pathname": "126",
267
+ "i-percent": "130",
268
+ "i-phone_number": "23",
269
+ "i-playlist": "79",
270
+ "i-portal": "62",
271
+ "i-priority": "38",
272
+ "i-purpose": "70",
273
+ "i-query": "119",
274
+ "i-rating": "136",
275
+ "i-review_count": "137",
276
+ "i-sender": "64",
277
+ "i-song": "81",
278
+ "i-status": "43",
279
+ "i-subject": "30",
280
+ "i-text_de": "91",
281
+ "i-text_en": "111",
282
+ "i-text_es": "100",
283
+ "i-text_esi": "134",
284
+ "i-text_fr": "107",
285
+ "i-text_it": "104",
286
+ "i-text_multi": "88",
287
+ "i-text_pl": "114",
288
+ "i-time": "34",
289
+ "i-to": "28",
290
+ "i-topic": "72",
291
+ "i-txt_query": "118",
292
+ "i-username": "68",
293
+ "i-value": "6",
294
+ "i-weight": "47",
295
+ "o": "0"
296
+ },
297
+ "layer_norm_eps": 1e-05,
298
+ "max_position_embeddings": 514,
299
+ "model_type": "xlm-roberta",
300
+ "num_attention_heads": 12,
301
+ "num_hidden_layers": 12,
302
+ "output_past": true,
303
+ "pad_token_id": 1,
304
+ "position_embedding_type": "absolute",
305
+ "torch_dtype": "float32",
306
+ "transformers_version": "4.27.4",
307
+ "type_vocab_size": 1,
308
+ "use_cache": true,
309
+ "vocab_size": 250002
310
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063e05bb6b579773d42a47e6b01cca1096bfacdcd7eca3a764273ce2e4a2d7d6
3
+ size 1110312493
runs/Mar31_11-30-02_348414bc3e7d/1680262218.9235544/events.out.tfevents.1680262218.348414bc3e7d.589.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b95a31f5cbc797d2d92e4484dbd9e2c79013925c3ad8ee31d58049e6cb14f3
3
+ size 5856
runs/Mar31_11-30-02_348414bc3e7d/events.out.tfevents.1680262218.348414bc3e7d.589.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a153d308212003cfd04a5a540a88448ebc5efa5c1049783820a4a5cba710bbf
3
+ size 11343
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
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
+ size 17082758
tokenizer_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 512,
14
+ "pad_token": "<pad>",
15
+ "sep_token": "</s>",
16
+ "special_tokens_map_file": null,
17
+ "tokenizer_class": "XLMRobertaTokenizer",
18
+ "unk_token": "<unk>"
19
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b59cfa06ffce057546986cfac015ea86219b29cef74468b92b53f003db5cfce
3
+ size 3579