Dims002 commited on
Commit
0efa299
·
verified ·
1 Parent(s): 7dd8df3

Deploy mBART Yemba translation model

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - fr
4
+ - mul
5
+ language_bcp47:
6
+ - fr
7
+ - yemba
8
+ license: apache-2.0
9
+ base_model: facebook/mbart-large-50
10
+ tags:
11
+ - translation
12
+ - mbart
13
+ - yemba
14
+ - african-languages
15
+ - low-resource-languages
16
+ pipeline_tag: translation
17
+ ---
18
+
19
+ # mBART Yemba Translation Model
20
+
21
+ Ce modèle est un fine-tuning de mBART pour la traduction entre le français et le yemba.
22
+
23
+ ## Utilisation
24
+
25
+ Voici comment utiliser le modèle:
26
+
27
+ from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
28
+
29
+ # Charger le modèle et le tokenizer
30
+ model = MBartForConditionalGeneration.from_pretrained("Dims002/mbart-yemba-translator")
31
+ tokenizer = MBart50TokenizerFast.from_pretrained("Dims002/mbart-yemba-translator")
32
+
33
+ # Exemple de traduction
34
+ def translate_text(text, src_lang="fr_XX", tgt_lang="yemba"):
35
+ tokenizer.src_lang = src_lang
36
+ encoded = tokenizer(text, return_tensors="pt")
37
+ generated_tokens = model.generate(**encoded)
38
+ return tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0]
39
+
40
+ ## Détails du modèle
41
+
42
+ - **Modèle de base**: facebook/mbart-large-50
43
+ - **Langues**: Français ↔ Yemba
44
+ - **Checkpoint**: 20000
45
+
46
+ ## Langues supportées
47
+
48
+ - **Français** (fr): Langue source principale
49
+ - **Yemba**: Langue cible (langue bantoue du Cameroun)
config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_num_labels": 3,
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 12,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": null,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_length": null,
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "mbart",
44
+ "normalize_before": true,
45
+ "normalize_embedding": true,
46
+ "num_beams": null,
47
+ "num_hidden_layers": 12,
48
+ "output_past": true,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": true,
51
+ "static_position_embeddings": false,
52
+ "tokenizer_class": "MBart50Tokenizer",
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.51.3",
55
+ "use_cache": true,
56
+ "vocab_size": 250054
57
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.51.3"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d10048899e0ebb9985c5b84af35d4b16275d57a419d5b1657a735b0bcedde5a5
3
+ size 2444578688
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03e478347f42b0b9c090cb01c428c09a22ed6f56701e7e412146a43607c156c2
3
+ size 4887473903
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dcf59ca816e53587eb4eca1649f47c957fc98c7803ee70559cc740df9ca4a0b
3
+ size 14244
scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265959433d40a86dc9b378fa56293d719e24b10778e4ed5c0f95bbb43a0a03e7
3
+ size 988
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e111882faa53a8ec61ad5f6b886695ae6756ef1d6ed3158f51fc7161a9c510c6
3
+ size 1064
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d967c5b869fb40df2df523bdc86a7e46888783e349ba81e7883b35f44a8c7ac0
3
+ size 17110186
tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
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
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": false,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "extra_special_tokens": {},
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1024,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "fr_XX",
525
+ "tgt_lang": "xh_ZA",
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
trainer_state.json ADDED
@@ -0,0 +1,314 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 9.980039920159681,
6
+ "eval_steps": 500,
7
+ "global_step": 20000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.249500998003992,
14
+ "grad_norm": 2.452378511428833,
15
+ "learning_rate": 4.876746506986028e-05,
16
+ "loss": 2.1274,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.499001996007984,
21
+ "grad_norm": 10.962518692016602,
22
+ "learning_rate": 4.751996007984032e-05,
23
+ "loss": 1.3207,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.7485029940119761,
28
+ "grad_norm": 2.4429094791412354,
29
+ "learning_rate": 4.627245508982036e-05,
30
+ "loss": 1.138,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.998003992015968,
35
+ "grad_norm": 2.2755186557769775,
36
+ "learning_rate": 4.50249500998004e-05,
37
+ "loss": 1.0141,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 1.24750499001996,
42
+ "grad_norm": 1.8802367448806763,
43
+ "learning_rate": 4.377744510978044e-05,
44
+ "loss": 0.8877,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 1.4970059880239521,
49
+ "grad_norm": 3.98767352104187,
50
+ "learning_rate": 4.252994011976048e-05,
51
+ "loss": 0.8705,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 1.746506986027944,
56
+ "grad_norm": 1.9973433017730713,
57
+ "learning_rate": 4.128243512974052e-05,
58
+ "loss": 0.826,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.996007984031936,
63
+ "grad_norm": 2.2026467323303223,
64
+ "learning_rate": 4.003493013972056e-05,
65
+ "loss": 0.8115,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 2.245508982035928,
70
+ "grad_norm": 2.212198257446289,
71
+ "learning_rate": 3.87874251497006e-05,
72
+ "loss": 0.6751,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 2.49500998003992,
77
+ "grad_norm": 1.5753542184829712,
78
+ "learning_rate": 3.754241516966068e-05,
79
+ "loss": 0.6747,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 2.744510978043912,
84
+ "grad_norm": 2.395479202270508,
85
+ "learning_rate": 3.629491017964072e-05,
86
+ "loss": 0.6646,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 2.9940119760479043,
91
+ "grad_norm": 2.577756643295288,
92
+ "learning_rate": 3.504740518962076e-05,
93
+ "loss": 0.66,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 3.243512974051896,
98
+ "grad_norm": 2.7224512100219727,
99
+ "learning_rate": 3.3799900199600795e-05,
100
+ "loss": 0.5135,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 3.493013972055888,
105
+ "grad_norm": 2.3300223350524902,
106
+ "learning_rate": 3.255239520958084e-05,
107
+ "loss": 0.5112,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 3.7425149700598803,
112
+ "grad_norm": 2.3015055656433105,
113
+ "learning_rate": 3.130489021956088e-05,
114
+ "loss": 0.5119,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 3.992015968063872,
119
+ "grad_norm": 2.4661030769348145,
120
+ "learning_rate": 3.0057385229540918e-05,
121
+ "loss": 0.5107,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 4.241516966067865,
126
+ "grad_norm": 2.5810928344726562,
127
+ "learning_rate": 2.880988023952096e-05,
128
+ "loss": 0.3741,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 4.491017964071856,
133
+ "grad_norm": 1.8933159112930298,
134
+ "learning_rate": 2.7562375249501e-05,
135
+ "loss": 0.3756,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 4.740518962075848,
140
+ "grad_norm": 2.711456775665283,
141
+ "learning_rate": 2.6314870259481038e-05,
142
+ "loss": 0.3745,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 4.99001996007984,
147
+ "grad_norm": 2.8451802730560303,
148
+ "learning_rate": 2.506736526946108e-05,
149
+ "loss": 0.3743,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 5.2395209580838324,
154
+ "grad_norm": 2.1212046146392822,
155
+ "learning_rate": 2.381986027944112e-05,
156
+ "loss": 0.2603,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 5.489021956087824,
161
+ "grad_norm": 2.1375863552093506,
162
+ "learning_rate": 2.257235528942116e-05,
163
+ "loss": 0.2567,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 5.738522954091817,
168
+ "grad_norm": 3.2050704956054688,
169
+ "learning_rate": 2.1324850299401196e-05,
170
+ "loss": 0.2596,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 5.9880239520958085,
175
+ "grad_norm": 1.9162492752075195,
176
+ "learning_rate": 2.007734530938124e-05,
177
+ "loss": 0.2692,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 6.2375249500998,
182
+ "grad_norm": 1.6697739362716675,
183
+ "learning_rate": 1.8829840319361277e-05,
184
+ "loss": 0.1711,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 6.487025948103792,
189
+ "grad_norm": 2.253767728805542,
190
+ "learning_rate": 1.758233532934132e-05,
191
+ "loss": 0.1705,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 6.736526946107785,
196
+ "grad_norm": 1.5864336490631104,
197
+ "learning_rate": 1.6337325349301397e-05,
198
+ "loss": 0.1735,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 6.986027944111776,
203
+ "grad_norm": 2.6011617183685303,
204
+ "learning_rate": 1.5089820359281437e-05,
205
+ "loss": 0.1785,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 7.235528942115769,
210
+ "grad_norm": 1.8357607126235962,
211
+ "learning_rate": 1.3842315369261476e-05,
212
+ "loss": 0.1101,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 7.485029940119761,
217
+ "grad_norm": 2.048788547515869,
218
+ "learning_rate": 1.2594810379241517e-05,
219
+ "loss": 0.1152,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 7.734530938123752,
224
+ "grad_norm": 2.7625575065612793,
225
+ "learning_rate": 1.1347305389221557e-05,
226
+ "loss": 0.1126,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 7.984031936127744,
231
+ "grad_norm": 2.9754233360290527,
232
+ "learning_rate": 1.0099800399201598e-05,
233
+ "loss": 0.1116,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 8.233532934131736,
238
+ "grad_norm": 2.279146909713745,
239
+ "learning_rate": 8.852295409181637e-06,
240
+ "loss": 0.0743,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 8.48303393213573,
245
+ "grad_norm": 2.4354634284973145,
246
+ "learning_rate": 7.604790419161677e-06,
247
+ "loss": 0.074,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 8.732534930139721,
252
+ "grad_norm": 2.9256038665771484,
253
+ "learning_rate": 6.357285429141717e-06,
254
+ "loss": 0.0722,
255
+ "step": 17500
256
+ },
257
+ {
258
+ "epoch": 8.982035928143713,
259
+ "grad_norm": 1.8734424114227295,
260
+ "learning_rate": 5.109780439121756e-06,
261
+ "loss": 0.0703,
262
+ "step": 18000
263
+ },
264
+ {
265
+ "epoch": 9.231536926147704,
266
+ "grad_norm": 2.1415419578552246,
267
+ "learning_rate": 3.862275449101797e-06,
268
+ "loss": 0.0503,
269
+ "step": 18500
270
+ },
271
+ {
272
+ "epoch": 9.481037924151696,
273
+ "grad_norm": 2.486562490463257,
274
+ "learning_rate": 2.6172654690618765e-06,
275
+ "loss": 0.0497,
276
+ "step": 19000
277
+ },
278
+ {
279
+ "epoch": 9.730538922155688,
280
+ "grad_norm": 1.6438294649124146,
281
+ "learning_rate": 1.3697604790419162e-06,
282
+ "loss": 0.0467,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 9.980039920159681,
287
+ "grad_norm": 2.3399159908294678,
288
+ "learning_rate": 1.222554890219561e-07,
289
+ "loss": 0.0457,
290
+ "step": 20000
291
+ }
292
+ ],
293
+ "logging_steps": 500,
294
+ "max_steps": 20040,
295
+ "num_input_tokens_seen": 0,
296
+ "num_train_epochs": 10,
297
+ "save_steps": 500,
298
+ "stateful_callbacks": {
299
+ "TrainerControl": {
300
+ "args": {
301
+ "should_epoch_stop": false,
302
+ "should_evaluate": false,
303
+ "should_log": false,
304
+ "should_save": true,
305
+ "should_training_stop": false
306
+ },
307
+ "attributes": {}
308
+ }
309
+ },
310
+ "total_flos": 2.167129767936e+16,
311
+ "train_batch_size": 4,
312
+ "trial_name": null,
313
+ "trial_params": null
314
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d042c9477f7b6640ea1b10bd8e98613e428dbf4d8529e16a0a9ebff454a8a876
3
+ size 5432