Alias64 commited on
Commit
d86c7e3
·
verified ·
1 Parent(s): e45c437

End of training

Browse files
README.md ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: flaubert/flaubert_base_cased
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: bert-base-banking77-pt2
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # bert-base-banking77-pt2
15
+
16
+ This model is a fine-tuned version of [flaubert/flaubert_base_cased](https://huggingface.co/flaubert/flaubert_base_cased) on the None dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 1024
37
+ - eval_batch_size: 32
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 1
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.41.2
50
+ - Pytorch 2.3.1+cu121
51
+ - Datasets 2.19.2
52
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,325 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "flaubert/flaubert_base_cased",
3
+ "amp": 1,
4
+ "architectures": [
5
+ "FlaubertForSequenceClassification"
6
+ ],
7
+ "asm": false,
8
+ "attention_dropout": 0.1,
9
+ "bos_index": 0,
10
+ "bos_token_id": 0,
11
+ "bptt": 512,
12
+ "causal": false,
13
+ "clip_grad_norm": 5,
14
+ "dropout": 0.1,
15
+ "emb_dim": 768,
16
+ "embed_init_std": 0.02209708691207961,
17
+ "encoder_only": true,
18
+ "end_n_top": 5,
19
+ "eos_index": 1,
20
+ "fp16": true,
21
+ "gelu_activation": true,
22
+ "group_by_size": true,
23
+ "id2label": {
24
+ "0": "Taxes",
25
+ "1": "Esth\u00e9tique",
26
+ "2": "Ch\u00e8ques",
27
+ "3": "Baby-sitters & Cr\u00e8ches",
28
+ "4": "Entretien",
29
+ "5": "Frais juridique",
30
+ "6": "Internet",
31
+ "7": "Billets de train",
32
+ "8": "Sport",
33
+ "9": "H\u00f4tels",
34
+ "10": "Transports en commun",
35
+ "11": "Assurance habitation",
36
+ "12": "TVA",
37
+ "13": "Alimentation - Autres",
38
+ "14": "Carburant",
39
+ "15": "Frais bancaires",
40
+ "16": "D\u00e9p\u00f4t d'argent",
41
+ "17": "D\u00e9bit mensuel carte",
42
+ "18": "Sant\u00e9 - Autres",
43
+ "19": "Publicit\u00e9",
44
+ "20": "Stationnement",
45
+ "21": "Pr\u00e9voyance",
46
+ "22": "Spa & Massage",
47
+ "23": "Extra",
48
+ "24": "T\u00e9l\u00e9phonie mobile",
49
+ "25": "Articles de sport",
50
+ "26": "Musique",
51
+ "27": "Loyer",
52
+ "28": "Salaires",
53
+ "29": "Livres",
54
+ "30": "C\u00e2ble / Satellite",
55
+ "31": "Divertissements",
56
+ "32": "Billets d'avion",
57
+ "33": "Virements internes",
58
+ "34": "Entretien v\u00e9hicule",
59
+ "35": "P\u00e9age",
60
+ "36": "Remboursements",
61
+ "37": "Hypoth\u00e8que",
62
+ "38": "Cadeaux",
63
+ "39": "Conseils",
64
+ "40": "V\u00eatements/Chaussures",
65
+ "41": "Remboursement emprunt",
66
+ "42": "Auto & Transports - Autres",
67
+ "43": "Marketing",
68
+ "44": "Esth\u00e9tique & Soins - Autres",
69
+ "45": "Sortie au restaurant",
70
+ "46": "Subventions",
71
+ "47": "Pressing",
72
+ "48": "Sports d'hiver",
73
+ "49": "R\u00e9mun\u00e9rations dirigeants",
74
+ "50": "Cosm\u00e9tique",
75
+ "51": "Charges diverses",
76
+ "52": "Retraite",
77
+ "53": "Autres rentr\u00e9es",
78
+ "54": "Allocations et pensions",
79
+ "55": "Dons",
80
+ "56": "Economies",
81
+ "57": "Comptabilit\u00e9",
82
+ "58": "Frais d'impressions",
83
+ "59": "Jouets",
84
+ "60": "Taxe d'apprentissage",
85
+ "61": "Imp\u00f4ts & Taxes - Autres",
86
+ "62": "Fast foods",
87
+ "63": "Tabac",
88
+ "64": "Licences",
89
+ "65": "Supermarch\u00e9 / Epicerie",
90
+ "66": "M\u00e9decin",
91
+ "67": "Frais d'exp\u00e9ditions",
92
+ "68": "Ecole",
93
+ "69": "Films & DVDs",
94
+ "70": "Emprunt",
95
+ "71": "Pharmacie",
96
+ "72": "Incidents de paiement",
97
+ "73": "Autres d\u00e9penses",
98
+ "74": "Sorties culturelles",
99
+ "75": "Voyages / Vacances",
100
+ "76": "Logement \u00e9tudiant",
101
+ "77": "Frais Animaux",
102
+ "78": "Mutuelle",
103
+ "79": "Electricit\u00e9",
104
+ "80": "Ext\u00e9rieur et jardin",
105
+ "81": "Assurance",
106
+ "82": "Opticien / Ophtalmo.",
107
+ "83": "D\u00e9penses pro - Autres",
108
+ "84": "Amendes",
109
+ "85": "Epargne",
110
+ "86": "Abonnements - Autres",
111
+ "87": "Bars / Clubs",
112
+ "88": "Dentiste",
113
+ "89": "Retraits",
114
+ "90": "Fournitures de bureau",
115
+ "91": "Loisirs & Sorties - Autres",
116
+ "92": "Coiffeur",
117
+ "93": "Banque - Autres",
118
+ "94": "Eau",
119
+ "95": "Sous-traitance",
120
+ "96": "D\u00e9coration",
121
+ "97": "Logement - Autres",
122
+ "98": "Gaz",
123
+ "99": "Location de v\u00e9hicule",
124
+ "100": "Imp\u00f4ts fonciers",
125
+ "101": "Services Bancaires",
126
+ "102": "Hobbies",
127
+ "103": "Virements",
128
+ "104": "Ventes",
129
+ "105": "Loyers re\u00e7us",
130
+ "106": "A cat\u00e9goriser",
131
+ "107": "Services",
132
+ "108": "Services en ligne",
133
+ "109": "Maintenance bureaux",
134
+ "110": "Notes de frais",
135
+ "111": "Achats & Shopping - Autres",
136
+ "112": "Pensions",
137
+ "113": "Fournitures scolaires",
138
+ "114": "High Tech",
139
+ "115": "Assurance v\u00e9hicule",
140
+ "116": "Restaurants",
141
+ "117": "Int\u00e9r\u00eats",
142
+ "118": "Scolarit\u00e9 & Enfants - Autres",
143
+ "119": "Caf\u00e9"
144
+ },
145
+ "id2lang": {
146
+ "0": "fr"
147
+ },
148
+ "init_std": 0.02,
149
+ "is_encoder": true,
150
+ "label2id": {
151
+ "A cat\u00e9goriser": 106,
152
+ "Abonnements - Autres": 86,
153
+ "Achats & Shopping - Autres": 111,
154
+ "Alimentation - Autres": 13,
155
+ "Allocations et pensions": 54,
156
+ "Amendes": 84,
157
+ "Articles de sport": 25,
158
+ "Assurance": 81,
159
+ "Assurance habitation": 11,
160
+ "Assurance v\u00e9hicule": 115,
161
+ "Auto & Transports - Autres": 42,
162
+ "Autres d\u00e9penses": 73,
163
+ "Autres rentr\u00e9es": 53,
164
+ "Baby-sitters & Cr\u00e8ches": 3,
165
+ "Banque - Autres": 93,
166
+ "Bars / Clubs": 87,
167
+ "Billets d'avion": 32,
168
+ "Billets de train": 7,
169
+ "Cadeaux": 38,
170
+ "Caf\u00e9": 119,
171
+ "Carburant": 14,
172
+ "Charges diverses": 51,
173
+ "Ch\u00e8ques": 2,
174
+ "Coiffeur": 92,
175
+ "Comptabilit\u00e9": 57,
176
+ "Conseils": 39,
177
+ "Cosm\u00e9tique": 50,
178
+ "C\u00e2ble / Satellite": 30,
179
+ "Dentiste": 88,
180
+ "Divertissements": 31,
181
+ "Dons": 55,
182
+ "D\u00e9bit mensuel carte": 17,
183
+ "D\u00e9coration": 96,
184
+ "D\u00e9penses pro - Autres": 83,
185
+ "D\u00e9p\u00f4t d'argent": 16,
186
+ "Eau": 94,
187
+ "Ecole": 68,
188
+ "Economies": 56,
189
+ "Electricit\u00e9": 79,
190
+ "Emprunt": 70,
191
+ "Entretien": 4,
192
+ "Entretien v\u00e9hicule": 34,
193
+ "Epargne": 85,
194
+ "Esth\u00e9tique": 1,
195
+ "Esth\u00e9tique & Soins - Autres": 44,
196
+ "Extra": 23,
197
+ "Ext\u00e9rieur et jardin": 80,
198
+ "Fast foods": 62,
199
+ "Films & DVDs": 69,
200
+ "Fournitures de bureau": 90,
201
+ "Fournitures scolaires": 113,
202
+ "Frais Animaux": 77,
203
+ "Frais bancaires": 15,
204
+ "Frais d'exp\u00e9ditions": 67,
205
+ "Frais d'impressions": 58,
206
+ "Frais juridique": 5,
207
+ "Gaz": 98,
208
+ "High Tech": 114,
209
+ "Hobbies": 102,
210
+ "Hypoth\u00e8que": 37,
211
+ "H\u00f4tels": 9,
212
+ "Imp\u00f4ts & Taxes - Autres": 61,
213
+ "Imp\u00f4ts fonciers": 100,
214
+ "Incidents de paiement": 72,
215
+ "Internet": 6,
216
+ "Int\u00e9r\u00eats": 117,
217
+ "Jouets": 59,
218
+ "Licences": 64,
219
+ "Livres": 29,
220
+ "Location de v\u00e9hicule": 99,
221
+ "Logement - Autres": 97,
222
+ "Logement \u00e9tudiant": 76,
223
+ "Loisirs & Sorties - Autres": 91,
224
+ "Loyer": 27,
225
+ "Loyers re\u00e7us": 105,
226
+ "Maintenance bureaux": 109,
227
+ "Marketing": 43,
228
+ "Musique": 26,
229
+ "Mutuelle": 78,
230
+ "M\u00e9decin": 66,
231
+ "Notes de frais": 110,
232
+ "Opticien / Ophtalmo.": 82,
233
+ "Pensions": 112,
234
+ "Pharmacie": 71,
235
+ "Pressing": 47,
236
+ "Pr\u00e9voyance": 21,
237
+ "Publicit\u00e9": 19,
238
+ "P\u00e9age": 35,
239
+ "Remboursement emprunt": 41,
240
+ "Remboursements": 36,
241
+ "Restaurants": 116,
242
+ "Retraite": 52,
243
+ "Retraits": 89,
244
+ "R\u00e9mun\u00e9rations dirigeants": 49,
245
+ "Salaires": 28,
246
+ "Sant\u00e9 - Autres": 18,
247
+ "Scolarit\u00e9 & Enfants - Autres": 118,
248
+ "Services": 107,
249
+ "Services Bancaires": 101,
250
+ "Services en ligne": 108,
251
+ "Sortie au restaurant": 45,
252
+ "Sorties culturelles": 74,
253
+ "Sous-traitance": 95,
254
+ "Spa & Massage": 22,
255
+ "Sport": 8,
256
+ "Sports d'hiver": 48,
257
+ "Stationnement": 20,
258
+ "Subventions": 46,
259
+ "Supermarch\u00e9 / Epicerie": 65,
260
+ "TVA": 12,
261
+ "Tabac": 63,
262
+ "Taxe d'apprentissage": 60,
263
+ "Taxes": 0,
264
+ "Transports en commun": 10,
265
+ "T\u00e9l\u00e9phonie mobile": 24,
266
+ "Ventes": 104,
267
+ "Virements": 103,
268
+ "Virements internes": 33,
269
+ "Voyages / Vacances": 75,
270
+ "V\u00eatements/Chaussures": 40
271
+ },
272
+ "lang2id": {
273
+ "fr": 0
274
+ },
275
+ "lang_id": 0,
276
+ "langs": [
277
+ "fr"
278
+ ],
279
+ "layer_norm_eps": 1e-12,
280
+ "layerdrop": 0.0,
281
+ "lg_sampling_factor": -1,
282
+ "lgs": "fr",
283
+ "mask_index": 5,
284
+ "mask_token_id": 0,
285
+ "max_batch_size": 0,
286
+ "max_position_embeddings": 512,
287
+ "max_vocab": -1,
288
+ "mlm_steps": [
289
+ [
290
+ "fr",
291
+ null
292
+ ]
293
+ ],
294
+ "model_type": "flaubert",
295
+ "n_heads": 12,
296
+ "n_langs": 1,
297
+ "n_layers": 12,
298
+ "pad_index": 2,
299
+ "pad_token_id": 2,
300
+ "pre_norm": false,
301
+ "problem_type": "single_label_classification",
302
+ "sample_alpha": 0,
303
+ "share_inout_emb": true,
304
+ "sinusoidal_embeddings": false,
305
+ "start_n_top": 5,
306
+ "summary_activation": null,
307
+ "summary_first_dropout": 0.1,
308
+ "summary_proj_to_labels": true,
309
+ "summary_type": "first",
310
+ "summary_use_proj": true,
311
+ "tokens_per_batch": -1,
312
+ "torch_dtype": "float32",
313
+ "transformers_version": "4.41.2",
314
+ "unk_index": 3,
315
+ "use_lang_emb": true,
316
+ "vocab_size": 68729,
317
+ "word_blank": 0,
318
+ "word_dropout": 0,
319
+ "word_keep": 0.1,
320
+ "word_mask": 0.8,
321
+ "word_mask_keep_rand": "0.8,0.1,0.1",
322
+ "word_pred": 0.15,
323
+ "word_rand": 0.1,
324
+ "word_shuffle": 0
325
+ }
logs/events.out.tfevents.1718202403.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f37953a5b9c168e581c3d31c25f5c6b832d4759e1ba60d423df6ed2eab33d40
3
+ size 10806
logs/events.out.tfevents.1718203072.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b2842bbab6edaa5eaac39e985d4fe3d408b75b7b800c262e18aa1a3b2a48523
3
+ size 10802
logs/events.out.tfevents.1718203388.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:085c1ced60bb1efc34ae1d7a3ba8470d9c7f47f342bc57a36a8acca2118bc7a4
3
+ size 10636
logs/events.out.tfevents.1718203821.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad925c909e8337b70d4133d8159a7c3e3bc0912d472f0d13aa9a42b7273708e5
3
+ size 10470
logs/events.out.tfevents.1718204662.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eca26a587e2ec4e57ca01e7b581b0955e37b1c631a2103e21a18c1a057f168af
3
+ size 12813
logs/events.out.tfevents.1718206952.pytorch-2-0-0-gpu-p-ml-g5-12xlarge-bd6adb7f7a95188f931aa4f47fd4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caee9db9140fccb285633825a40aecb438dab496386c506039d7902d2abfd1c2
3
+ size 12813
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25bc504f7d46b0adcf3a6902664efebaac77736935464fa04230557b87523303
3
+ size 553322104
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<special0>",
4
+ "<special1>",
5
+ "<special2>",
6
+ "<special3>",
7
+ "<special4>",
8
+ "<special5>",
9
+ "<special6>",
10
+ "<special7>",
11
+ "<special8>",
12
+ "<special9>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "cls_token": "</s>",
16
+ "mask_token": "<special1>",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,140 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "</s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<special0>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<special1>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<special2>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<special3>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<special4>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<special5>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<special6>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<special7>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "12": {
100
+ "content": "<special8>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "13": {
108
+ "content": "<special9>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ }
115
+ },
116
+ "additional_special_tokens": [
117
+ "<special0>",
118
+ "<special1>",
119
+ "<special2>",
120
+ "<special3>",
121
+ "<special4>",
122
+ "<special5>",
123
+ "<special6>",
124
+ "<special7>",
125
+ "<special8>",
126
+ "<special9>"
127
+ ],
128
+ "bos_token": "<s>",
129
+ "clean_up_tokenization_spaces": true,
130
+ "cls_token": "</s>",
131
+ "do_lower_case": false,
132
+ "id2lang": null,
133
+ "lang2id": null,
134
+ "mask_token": "<special1>",
135
+ "model_max_length": 512,
136
+ "pad_token": "<pad>",
137
+ "sep_token": "</s>",
138
+ "tokenizer_class": "FlaubertTokenizer",
139
+ "unk_token": "<unk>"
140
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61f85c5a97b6db5a59ff5a06f3b7b4d9ac62ce87b819291d65fbf7027758e4b
3
+ size 5112
vocab.json ADDED
The diff for this file is too large to render. See raw diff