shubham-das-coder commited on
Commit
1b7792f
·
verified ·
1 Parent(s): 52fab94

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +4 -0
  2. README.md +63 -0
  3. all_results.json +25 -0
  4. checkpoint-20000/config.json +34 -0
  5. checkpoint-20000/generation_config.json +10 -0
  6. checkpoint-20000/model.safetensors +3 -0
  7. checkpoint-20000/optimizer.pt +3 -0
  8. checkpoint-20000/rng_state.pth +3 -0
  9. checkpoint-20000/scheduler.pt +3 -0
  10. checkpoint-20000/sentencepiece.bpe.model +3 -0
  11. checkpoint-20000/special_tokens_map.json +255 -0
  12. checkpoint-20000/tokenizer.json +3 -0
  13. checkpoint-20000/tokenizer_config.json +1879 -0
  14. checkpoint-20000/trainer_state.json +314 -0
  15. checkpoint-20000/training_args.bin +3 -0
  16. checkpoint-30000/config.json +34 -0
  17. checkpoint-30000/generation_config.json +10 -0
  18. checkpoint-30000/model.safetensors +3 -0
  19. checkpoint-30000/rng_state.pth +3 -0
  20. checkpoint-30000/scheduler.pt +3 -0
  21. checkpoint-30000/sentencepiece.bpe.model +3 -0
  22. checkpoint-30000/special_tokens_map.json +255 -0
  23. checkpoint-30000/tokenizer.json +3 -0
  24. checkpoint-30000/tokenizer_config.json +1879 -0
  25. checkpoint-30000/trainer_state.json +454 -0
  26. checkpoint-30000/training_args.bin +3 -0
  27. checkpoint-37460/config.json +34 -0
  28. checkpoint-37460/generation_config.json +10 -0
  29. checkpoint-37460/model.safetensors +3 -0
  30. checkpoint-37460/optimizer.pt +3 -0
  31. checkpoint-37460/rng_state.pth +3 -0
  32. checkpoint-37460/scheduler.pt +3 -0
  33. checkpoint-37460/sentencepiece.bpe.model +3 -0
  34. checkpoint-37460/special_tokens_map.json +255 -0
  35. checkpoint-37460/tokenizer.json +3 -0
  36. checkpoint-37460/tokenizer_config.json +1879 -0
  37. checkpoint-37460/trainer_state.json +552 -0
  38. checkpoint-37460/training_args.bin +3 -0
  39. config.json +34 -0
  40. eval_results.json +11 -0
  41. generated_predictions.txt +0 -0
  42. generation_config.json +10 -0
  43. model.safetensors +3 -0
  44. predict_results.json +10 -0
  45. sentencepiece.bpe.model +3 -0
  46. special_tokens_map.json +255 -0
  47. tokenizer.json +3 -0
  48. tokenizer_config.json +1879 -0
  49. train_results.json +9 -0
  50. trainer_state.json +561 -0
.gitattributes CHANGED
@@ -33,3 +33,7 @@ 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
+ checkpoint-20000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-37460/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ checkpoint-30000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
39
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language_bcp47:
4
+ - kan_Knda
5
+ - hin_Deva
6
+ license: cc-by-nc-4.0
7
+ base_model: facebook/nllb-200-distilled-600M
8
+ tags:
9
+ - generated_from_trainer
10
+ metrics:
11
+ - bleu
12
+ model-index:
13
+ - name: output
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # output
21
+
22
+ This model is a fine-tuned version of [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 1.1433
25
+ - Bleu: 43.1563
26
+ - Chrf: 71.5797
27
+ - Gen Len: 24.5884
28
+
29
+ ## Model description
30
+
31
+ More information needed
32
+
33
+ ## Intended uses & limitations
34
+
35
+ More information needed
36
+
37
+ ## Training and evaluation data
38
+
39
+ More information needed
40
+
41
+ ## Training procedure
42
+
43
+ ### Training hyperparameters
44
+
45
+ The following hyperparameters were used during training:
46
+ - learning_rate: 5e-05
47
+ - train_batch_size: 4
48
+ - eval_batch_size: 4
49
+ - seed: 42
50
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 10.0
53
+
54
+ ### Training results
55
+
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.54.0.dev0
61
+ - Pytorch 2.7.1+cu126
62
+ - Datasets 4.0.0
63
+ - Tokenizers 0.21.2
all_results.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_bleu": 43.1563,
4
+ "eval_chrf": 71.5797,
5
+ "eval_gen_len": 24.5884,
6
+ "eval_loss": 1.1433292627334595,
7
+ "eval_runtime": 357.9909,
8
+ "eval_samples": 1873,
9
+ "eval_samples_per_second": 5.232,
10
+ "eval_steps_per_second": 1.31,
11
+ "predict_bleu": 42.4892,
12
+ "predict_chrf": 71.0352,
13
+ "predict_gen_len": 24.7318,
14
+ "predict_loss": 1.173148274421692,
15
+ "predict_runtime": 367.2146,
16
+ "predict_samples": 1872,
17
+ "predict_samples_per_second": 5.098,
18
+ "predict_steps_per_second": 1.274,
19
+ "total_flos": 1.5022851621224448e+16,
20
+ "train_loss": 0.5662414055868578,
21
+ "train_runtime": 9241.9444,
22
+ "train_samples": 14984,
23
+ "train_samples_per_second": 16.213,
24
+ "train_steps_per_second": 4.053
25
+ }
checkpoint-20000/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "M2M100ForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 0,
9
+ "d_model": 1024,
10
+ "decoder_attention_heads": 16,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0,
13
+ "decoder_layers": 12,
14
+ "decoder_start_token_id": 2,
15
+ "dropout": 0.1,
16
+ "encoder_attention_heads": 16,
17
+ "encoder_ffn_dim": 4096,
18
+ "encoder_layerdrop": 0,
19
+ "encoder_layers": 12,
20
+ "eos_token_id": 2,
21
+ "init_std": 0.02,
22
+ "is_encoder_decoder": true,
23
+ "max_length": null,
24
+ "max_position_embeddings": 1024,
25
+ "model_type": "m2m_100",
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 1,
28
+ "scale_embedding": true,
29
+ "tokenizer_class": "NllbTokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.54.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 256206
34
+ }
checkpoint-20000/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 256068,
7
+ "max_length": 200,
8
+ "pad_token_id": 1,
9
+ "transformers_version": "4.54.0.dev0"
10
+ }
checkpoint-20000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ceeadbadfa58e8ef22ce8883250420273e30e588a9da3e7e9eb4a9cd47a160
3
+ size 2460354912
checkpoint-20000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:193dff2ae7a08391e11f7de2d56a19817e42753124588eed98b0458029f1578e
3
+ size 4921030362
checkpoint-20000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b54c8b879822d61214a4f6fc7daf64792d1b3cf0823472318569728f91d240db
3
+ size 14645
checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:185bd87e09a60f85f553eb90e4e28428955994fb174b2657233bd2274e11d977
3
+ size 1465
checkpoint-20000/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
checkpoint-20000/special_tokens_map.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ace_Arab",
4
+ "ace_Latn",
5
+ "acm_Arab",
6
+ "acq_Arab",
7
+ "aeb_Arab",
8
+ "afr_Latn",
9
+ "ajp_Arab",
10
+ "aka_Latn",
11
+ "amh_Ethi",
12
+ "apc_Arab",
13
+ "arb_Arab",
14
+ "ars_Arab",
15
+ "ary_Arab",
16
+ "arz_Arab",
17
+ "asm_Beng",
18
+ "ast_Latn",
19
+ "awa_Deva",
20
+ "ayr_Latn",
21
+ "azb_Arab",
22
+ "azj_Latn",
23
+ "bak_Cyrl",
24
+ "bam_Latn",
25
+ "ban_Latn",
26
+ "bel_Cyrl",
27
+ "bem_Latn",
28
+ "ben_Beng",
29
+ "bho_Deva",
30
+ "bjn_Arab",
31
+ "bjn_Latn",
32
+ "bod_Tibt",
33
+ "bos_Latn",
34
+ "bug_Latn",
35
+ "bul_Cyrl",
36
+ "cat_Latn",
37
+ "ceb_Latn",
38
+ "ces_Latn",
39
+ "cjk_Latn",
40
+ "ckb_Arab",
41
+ "crh_Latn",
42
+ "cym_Latn",
43
+ "dan_Latn",
44
+ "deu_Latn",
45
+ "dik_Latn",
46
+ "dyu_Latn",
47
+ "dzo_Tibt",
48
+ "ell_Grek",
49
+ "eng_Latn",
50
+ "epo_Latn",
51
+ "est_Latn",
52
+ "eus_Latn",
53
+ "ewe_Latn",
54
+ "fao_Latn",
55
+ "pes_Arab",
56
+ "fij_Latn",
57
+ "fin_Latn",
58
+ "fon_Latn",
59
+ "fra_Latn",
60
+ "fur_Latn",
61
+ "fuv_Latn",
62
+ "gla_Latn",
63
+ "gle_Latn",
64
+ "glg_Latn",
65
+ "grn_Latn",
66
+ "guj_Gujr",
67
+ "hat_Latn",
68
+ "hau_Latn",
69
+ "heb_Hebr",
70
+ "hin_Deva",
71
+ "hne_Deva",
72
+ "hrv_Latn",
73
+ "hun_Latn",
74
+ "hye_Armn",
75
+ "ibo_Latn",
76
+ "ilo_Latn",
77
+ "ind_Latn",
78
+ "isl_Latn",
79
+ "ita_Latn",
80
+ "jav_Latn",
81
+ "jpn_Jpan",
82
+ "kab_Latn",
83
+ "kac_Latn",
84
+ "kam_Latn",
85
+ "kan_Knda",
86
+ "kas_Arab",
87
+ "kas_Deva",
88
+ "kat_Geor",
89
+ "knc_Arab",
90
+ "knc_Latn",
91
+ "kaz_Cyrl",
92
+ "kbp_Latn",
93
+ "kea_Latn",
94
+ "khm_Khmr",
95
+ "kik_Latn",
96
+ "kin_Latn",
97
+ "kir_Cyrl",
98
+ "kmb_Latn",
99
+ "kon_Latn",
100
+ "kor_Hang",
101
+ "kmr_Latn",
102
+ "lao_Laoo",
103
+ "lvs_Latn",
104
+ "lij_Latn",
105
+ "lim_Latn",
106
+ "lin_Latn",
107
+ "lit_Latn",
108
+ "lmo_Latn",
109
+ "ltg_Latn",
110
+ "ltz_Latn",
111
+ "lua_Latn",
112
+ "lug_Latn",
113
+ "luo_Latn",
114
+ "lus_Latn",
115
+ "mag_Deva",
116
+ "mai_Deva",
117
+ "mal_Mlym",
118
+ "mar_Deva",
119
+ "min_Latn",
120
+ "mkd_Cyrl",
121
+ "plt_Latn",
122
+ "mlt_Latn",
123
+ "mni_Beng",
124
+ "khk_Cyrl",
125
+ "mos_Latn",
126
+ "mri_Latn",
127
+ "zsm_Latn",
128
+ "mya_Mymr",
129
+ "nld_Latn",
130
+ "nno_Latn",
131
+ "nob_Latn",
132
+ "npi_Deva",
133
+ "nso_Latn",
134
+ "nus_Latn",
135
+ "nya_Latn",
136
+ "oci_Latn",
137
+ "gaz_Latn",
138
+ "ory_Orya",
139
+ "pag_Latn",
140
+ "pan_Guru",
141
+ "pap_Latn",
142
+ "pol_Latn",
143
+ "por_Latn",
144
+ "prs_Arab",
145
+ "pbt_Arab",
146
+ "quy_Latn",
147
+ "ron_Latn",
148
+ "run_Latn",
149
+ "rus_Cyrl",
150
+ "sag_Latn",
151
+ "san_Deva",
152
+ "sat_Beng",
153
+ "scn_Latn",
154
+ "shn_Mymr",
155
+ "sin_Sinh",
156
+ "slk_Latn",
157
+ "slv_Latn",
158
+ "smo_Latn",
159
+ "sna_Latn",
160
+ "snd_Arab",
161
+ "som_Latn",
162
+ "sot_Latn",
163
+ "spa_Latn",
164
+ "als_Latn",
165
+ "srd_Latn",
166
+ "srp_Cyrl",
167
+ "ssw_Latn",
168
+ "sun_Latn",
169
+ "swe_Latn",
170
+ "swh_Latn",
171
+ "szl_Latn",
172
+ "tam_Taml",
173
+ "tat_Cyrl",
174
+ "tel_Telu",
175
+ "tgk_Cyrl",
176
+ "tgl_Latn",
177
+ "tha_Thai",
178
+ "tir_Ethi",
179
+ "taq_Latn",
180
+ "taq_Tfng",
181
+ "tpi_Latn",
182
+ "tsn_Latn",
183
+ "tso_Latn",
184
+ "tuk_Latn",
185
+ "tum_Latn",
186
+ "tur_Latn",
187
+ "twi_Latn",
188
+ "tzm_Tfng",
189
+ "uig_Arab",
190
+ "ukr_Cyrl",
191
+ "umb_Latn",
192
+ "urd_Arab",
193
+ "uzn_Latn",
194
+ "vec_Latn",
195
+ "vie_Latn",
196
+ "war_Latn",
197
+ "wol_Latn",
198
+ "xho_Latn",
199
+ "ydd_Hebr",
200
+ "yor_Latn",
201
+ "yue_Hant",
202
+ "zho_Hans",
203
+ "zho_Hant",
204
+ "zul_Latn"
205
+ ],
206
+ "bos_token": {
207
+ "content": "<s>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ "cls_token": {
214
+ "content": "<s>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ "eos_token": {
221
+ "content": "</s>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ "mask_token": {
228
+ "content": "<mask>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ "pad_token": {
235
+ "content": "<pad>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ "sep_token": {
242
+ "content": "</s>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ "unk_token": {
249
+ "content": "<unk>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ }
255
+ }
checkpoint-20000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd897f6e1b43d40640d698f1ed736005d47a08ed8e8e2e389d4b5d60d7892212
3
+ size 32240214
checkpoint-20000/tokenizer_config.json ADDED
@@ -0,0 +1,1879 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "256001": {
36
+ "content": "ace_Arab",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "256002": {
44
+ "content": "ace_Latn",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "256003": {
52
+ "content": "acm_Arab",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "256004": {
60
+ "content": "acq_Arab",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "256005": {
68
+ "content": "aeb_Arab",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "256006": {
76
+ "content": "afr_Latn",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "256007": {
84
+ "content": "ajp_Arab",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "256008": {
92
+ "content": "aka_Latn",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "256009": {
100
+ "content": "amh_Ethi",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "256010": {
108
+ "content": "apc_Arab",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "256011": {
116
+ "content": "arb_Arab",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "256012": {
124
+ "content": "ars_Arab",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "256013": {
132
+ "content": "ary_Arab",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "256014": {
140
+ "content": "arz_Arab",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "256015": {
148
+ "content": "asm_Beng",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "256016": {
156
+ "content": "ast_Latn",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "256017": {
164
+ "content": "awa_Deva",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "256018": {
172
+ "content": "ayr_Latn",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "256019": {
180
+ "content": "azb_Arab",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "256020": {
188
+ "content": "azj_Latn",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "256021": {
196
+ "content": "bak_Cyrl",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "256022": {
204
+ "content": "bam_Latn",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "256023": {
212
+ "content": "ban_Latn",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "256024": {
220
+ "content": "bel_Cyrl",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "256025": {
228
+ "content": "bem_Latn",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "256026": {
236
+ "content": "ben_Beng",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "256027": {
244
+ "content": "bho_Deva",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "256028": {
252
+ "content": "bjn_Arab",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "256029": {
260
+ "content": "bjn_Latn",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "256030": {
268
+ "content": "bod_Tibt",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "256031": {
276
+ "content": "bos_Latn",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "256032": {
284
+ "content": "bug_Latn",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "256033": {
292
+ "content": "bul_Cyrl",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "256034": {
300
+ "content": "cat_Latn",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "256035": {
308
+ "content": "ceb_Latn",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "256036": {
316
+ "content": "ces_Latn",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "256037": {
324
+ "content": "cjk_Latn",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "256038": {
332
+ "content": "ckb_Arab",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "256039": {
340
+ "content": "crh_Latn",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "256040": {
348
+ "content": "cym_Latn",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "256041": {
356
+ "content": "dan_Latn",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "256042": {
364
+ "content": "deu_Latn",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "256043": {
372
+ "content": "dik_Latn",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "256044": {
380
+ "content": "dyu_Latn",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "256045": {
388
+ "content": "dzo_Tibt",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "256046": {
396
+ "content": "ell_Grek",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "256047": {
404
+ "content": "eng_Latn",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "256048": {
412
+ "content": "epo_Latn",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "256049": {
420
+ "content": "est_Latn",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "256050": {
428
+ "content": "eus_Latn",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "256051": {
436
+ "content": "ewe_Latn",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "256052": {
444
+ "content": "fao_Latn",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "256053": {
452
+ "content": "pes_Arab",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "256054": {
460
+ "content": "fij_Latn",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "256055": {
468
+ "content": "fin_Latn",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "256056": {
476
+ "content": "fon_Latn",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "256057": {
484
+ "content": "fra_Latn",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "256058": {
492
+ "content": "fur_Latn",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "256059": {
500
+ "content": "fuv_Latn",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "256060": {
508
+ "content": "gla_Latn",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "256061": {
516
+ "content": "gle_Latn",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "256062": {
524
+ "content": "glg_Latn",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "256063": {
532
+ "content": "grn_Latn",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "256064": {
540
+ "content": "guj_Gujr",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "256065": {
548
+ "content": "hat_Latn",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "256066": {
556
+ "content": "hau_Latn",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "256067": {
564
+ "content": "heb_Hebr",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "256068": {
572
+ "content": "hin_Deva",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "256069": {
580
+ "content": "hne_Deva",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "256070": {
588
+ "content": "hrv_Latn",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "256071": {
596
+ "content": "hun_Latn",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "256072": {
604
+ "content": "hye_Armn",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "256073": {
612
+ "content": "ibo_Latn",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "256074": {
620
+ "content": "ilo_Latn",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "256075": {
628
+ "content": "ind_Latn",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "256076": {
636
+ "content": "isl_Latn",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "256077": {
644
+ "content": "ita_Latn",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "256078": {
652
+ "content": "jav_Latn",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "256079": {
660
+ "content": "jpn_Jpan",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "256080": {
668
+ "content": "kab_Latn",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "256081": {
676
+ "content": "kac_Latn",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "256082": {
684
+ "content": "kam_Latn",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "256083": {
692
+ "content": "kan_Knda",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "256084": {
700
+ "content": "kas_Arab",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "256085": {
708
+ "content": "kas_Deva",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "256086": {
716
+ "content": "kat_Geor",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "256087": {
724
+ "content": "knc_Arab",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "256088": {
732
+ "content": "knc_Latn",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "256089": {
740
+ "content": "kaz_Cyrl",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "256090": {
748
+ "content": "kbp_Latn",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "256091": {
756
+ "content": "kea_Latn",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "256092": {
764
+ "content": "khm_Khmr",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "256093": {
772
+ "content": "kik_Latn",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "256094": {
780
+ "content": "kin_Latn",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "256095": {
788
+ "content": "kir_Cyrl",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "256096": {
796
+ "content": "kmb_Latn",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "256097": {
804
+ "content": "kon_Latn",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "256098": {
812
+ "content": "kor_Hang",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "256099": {
820
+ "content": "kmr_Latn",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "256100": {
828
+ "content": "lao_Laoo",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "256101": {
836
+ "content": "lvs_Latn",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "256102": {
844
+ "content": "lij_Latn",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "256103": {
852
+ "content": "lim_Latn",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "256104": {
860
+ "content": "lin_Latn",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "256105": {
868
+ "content": "lit_Latn",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "256106": {
876
+ "content": "lmo_Latn",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "256107": {
884
+ "content": "ltg_Latn",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "256108": {
892
+ "content": "ltz_Latn",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "256109": {
900
+ "content": "lua_Latn",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "256110": {
908
+ "content": "lug_Latn",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "256111": {
916
+ "content": "luo_Latn",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "256112": {
924
+ "content": "lus_Latn",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "256113": {
932
+ "content": "mag_Deva",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "256114": {
940
+ "content": "mai_Deva",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "256115": {
948
+ "content": "mal_Mlym",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "256116": {
956
+ "content": "mar_Deva",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "256117": {
964
+ "content": "min_Latn",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "256118": {
972
+ "content": "mkd_Cyrl",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "256119": {
980
+ "content": "plt_Latn",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "256120": {
988
+ "content": "mlt_Latn",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "256121": {
996
+ "content": "mni_Beng",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "256122": {
1004
+ "content": "khk_Cyrl",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "256123": {
1012
+ "content": "mos_Latn",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "256124": {
1020
+ "content": "mri_Latn",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "256125": {
1028
+ "content": "zsm_Latn",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "256126": {
1036
+ "content": "mya_Mymr",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "256127": {
1044
+ "content": "nld_Latn",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "256128": {
1052
+ "content": "nno_Latn",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "256129": {
1060
+ "content": "nob_Latn",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "256130": {
1068
+ "content": "npi_Deva",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "256131": {
1076
+ "content": "nso_Latn",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "256132": {
1084
+ "content": "nus_Latn",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "256133": {
1092
+ "content": "nya_Latn",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "256134": {
1100
+ "content": "oci_Latn",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "256135": {
1108
+ "content": "gaz_Latn",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "256136": {
1116
+ "content": "ory_Orya",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "256137": {
1124
+ "content": "pag_Latn",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "256138": {
1132
+ "content": "pan_Guru",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "256139": {
1140
+ "content": "pap_Latn",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "256140": {
1148
+ "content": "pol_Latn",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "256141": {
1156
+ "content": "por_Latn",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "256142": {
1164
+ "content": "prs_Arab",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "256143": {
1172
+ "content": "pbt_Arab",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "256144": {
1180
+ "content": "quy_Latn",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "256145": {
1188
+ "content": "ron_Latn",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "256146": {
1196
+ "content": "run_Latn",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "256147": {
1204
+ "content": "rus_Cyrl",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "256148": {
1212
+ "content": "sag_Latn",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "256149": {
1220
+ "content": "san_Deva",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "256150": {
1228
+ "content": "sat_Beng",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "256151": {
1236
+ "content": "scn_Latn",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "256152": {
1244
+ "content": "shn_Mymr",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "256153": {
1252
+ "content": "sin_Sinh",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "256154": {
1260
+ "content": "slk_Latn",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "256155": {
1268
+ "content": "slv_Latn",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "256156": {
1276
+ "content": "smo_Latn",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "256157": {
1284
+ "content": "sna_Latn",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "256158": {
1292
+ "content": "snd_Arab",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "256159": {
1300
+ "content": "som_Latn",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "256160": {
1308
+ "content": "sot_Latn",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "256161": {
1316
+ "content": "spa_Latn",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "256162": {
1324
+ "content": "als_Latn",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "256163": {
1332
+ "content": "srd_Latn",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "256164": {
1340
+ "content": "srp_Cyrl",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "256165": {
1348
+ "content": "ssw_Latn",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "256166": {
1356
+ "content": "sun_Latn",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "256167": {
1364
+ "content": "swe_Latn",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "256168": {
1372
+ "content": "swh_Latn",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "256169": {
1380
+ "content": "szl_Latn",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "256170": {
1388
+ "content": "tam_Taml",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "256171": {
1396
+ "content": "tat_Cyrl",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "256172": {
1404
+ "content": "tel_Telu",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "256173": {
1412
+ "content": "tgk_Cyrl",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "256174": {
1420
+ "content": "tgl_Latn",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "256175": {
1428
+ "content": "tha_Thai",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "256176": {
1436
+ "content": "tir_Ethi",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "256177": {
1444
+ "content": "taq_Latn",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "256178": {
1452
+ "content": "taq_Tfng",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "256179": {
1460
+ "content": "tpi_Latn",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "256180": {
1468
+ "content": "tsn_Latn",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "256181": {
1476
+ "content": "tso_Latn",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "256182": {
1484
+ "content": "tuk_Latn",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "256183": {
1492
+ "content": "tum_Latn",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "256184": {
1500
+ "content": "tur_Latn",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "256185": {
1508
+ "content": "twi_Latn",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "256186": {
1516
+ "content": "tzm_Tfng",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "256187": {
1524
+ "content": "uig_Arab",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "256188": {
1532
+ "content": "ukr_Cyrl",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "256189": {
1540
+ "content": "umb_Latn",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "256190": {
1548
+ "content": "urd_Arab",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "256191": {
1556
+ "content": "uzn_Latn",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "256192": {
1564
+ "content": "vec_Latn",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "256193": {
1572
+ "content": "vie_Latn",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "256194": {
1580
+ "content": "war_Latn",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "256195": {
1588
+ "content": "wol_Latn",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "256196": {
1596
+ "content": "xho_Latn",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "256197": {
1604
+ "content": "ydd_Hebr",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "256198": {
1612
+ "content": "yor_Latn",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "256199": {
1620
+ "content": "yue_Hant",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "256200": {
1628
+ "content": "zho_Hans",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "256201": {
1636
+ "content": "zho_Hant",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "256202": {
1644
+ "content": "zul_Latn",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "256203": {
1652
+ "content": "<mask>",
1653
+ "lstrip": true,
1654
+ "normalized": true,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ }
1659
+ },
1660
+ "additional_special_tokens": [
1661
+ "ace_Arab",
1662
+ "ace_Latn",
1663
+ "acm_Arab",
1664
+ "acq_Arab",
1665
+ "aeb_Arab",
1666
+ "afr_Latn",
1667
+ "ajp_Arab",
1668
+ "aka_Latn",
1669
+ "amh_Ethi",
1670
+ "apc_Arab",
1671
+ "arb_Arab",
1672
+ "ars_Arab",
1673
+ "ary_Arab",
1674
+ "arz_Arab",
1675
+ "asm_Beng",
1676
+ "ast_Latn",
1677
+ "awa_Deva",
1678
+ "ayr_Latn",
1679
+ "azb_Arab",
1680
+ "azj_Latn",
1681
+ "bak_Cyrl",
1682
+ "bam_Latn",
1683
+ "ban_Latn",
1684
+ "bel_Cyrl",
1685
+ "bem_Latn",
1686
+ "ben_Beng",
1687
+ "bho_Deva",
1688
+ "bjn_Arab",
1689
+ "bjn_Latn",
1690
+ "bod_Tibt",
1691
+ "bos_Latn",
1692
+ "bug_Latn",
1693
+ "bul_Cyrl",
1694
+ "cat_Latn",
1695
+ "ceb_Latn",
1696
+ "ces_Latn",
1697
+ "cjk_Latn",
1698
+ "ckb_Arab",
1699
+ "crh_Latn",
1700
+ "cym_Latn",
1701
+ "dan_Latn",
1702
+ "deu_Latn",
1703
+ "dik_Latn",
1704
+ "dyu_Latn",
1705
+ "dzo_Tibt",
1706
+ "ell_Grek",
1707
+ "eng_Latn",
1708
+ "epo_Latn",
1709
+ "est_Latn",
1710
+ "eus_Latn",
1711
+ "ewe_Latn",
1712
+ "fao_Latn",
1713
+ "pes_Arab",
1714
+ "fij_Latn",
1715
+ "fin_Latn",
1716
+ "fon_Latn",
1717
+ "fra_Latn",
1718
+ "fur_Latn",
1719
+ "fuv_Latn",
1720
+ "gla_Latn",
1721
+ "gle_Latn",
1722
+ "glg_Latn",
1723
+ "grn_Latn",
1724
+ "guj_Gujr",
1725
+ "hat_Latn",
1726
+ "hau_Latn",
1727
+ "heb_Hebr",
1728
+ "hin_Deva",
1729
+ "hne_Deva",
1730
+ "hrv_Latn",
1731
+ "hun_Latn",
1732
+ "hye_Armn",
1733
+ "ibo_Latn",
1734
+ "ilo_Latn",
1735
+ "ind_Latn",
1736
+ "isl_Latn",
1737
+ "ita_Latn",
1738
+ "jav_Latn",
1739
+ "jpn_Jpan",
1740
+ "kab_Latn",
1741
+ "kac_Latn",
1742
+ "kam_Latn",
1743
+ "kan_Knda",
1744
+ "kas_Arab",
1745
+ "kas_Deva",
1746
+ "kat_Geor",
1747
+ "knc_Arab",
1748
+ "knc_Latn",
1749
+ "kaz_Cyrl",
1750
+ "kbp_Latn",
1751
+ "kea_Latn",
1752
+ "khm_Khmr",
1753
+ "kik_Latn",
1754
+ "kin_Latn",
1755
+ "kir_Cyrl",
1756
+ "kmb_Latn",
1757
+ "kon_Latn",
1758
+ "kor_Hang",
1759
+ "kmr_Latn",
1760
+ "lao_Laoo",
1761
+ "lvs_Latn",
1762
+ "lij_Latn",
1763
+ "lim_Latn",
1764
+ "lin_Latn",
1765
+ "lit_Latn",
1766
+ "lmo_Latn",
1767
+ "ltg_Latn",
1768
+ "ltz_Latn",
1769
+ "lua_Latn",
1770
+ "lug_Latn",
1771
+ "luo_Latn",
1772
+ "lus_Latn",
1773
+ "mag_Deva",
1774
+ "mai_Deva",
1775
+ "mal_Mlym",
1776
+ "mar_Deva",
1777
+ "min_Latn",
1778
+ "mkd_Cyrl",
1779
+ "plt_Latn",
1780
+ "mlt_Latn",
1781
+ "mni_Beng",
1782
+ "khk_Cyrl",
1783
+ "mos_Latn",
1784
+ "mri_Latn",
1785
+ "zsm_Latn",
1786
+ "mya_Mymr",
1787
+ "nld_Latn",
1788
+ "nno_Latn",
1789
+ "nob_Latn",
1790
+ "npi_Deva",
1791
+ "nso_Latn",
1792
+ "nus_Latn",
1793
+ "nya_Latn",
1794
+ "oci_Latn",
1795
+ "gaz_Latn",
1796
+ "ory_Orya",
1797
+ "pag_Latn",
1798
+ "pan_Guru",
1799
+ "pap_Latn",
1800
+ "pol_Latn",
1801
+ "por_Latn",
1802
+ "prs_Arab",
1803
+ "pbt_Arab",
1804
+ "quy_Latn",
1805
+ "ron_Latn",
1806
+ "run_Latn",
1807
+ "rus_Cyrl",
1808
+ "sag_Latn",
1809
+ "san_Deva",
1810
+ "sat_Beng",
1811
+ "scn_Latn",
1812
+ "shn_Mymr",
1813
+ "sin_Sinh",
1814
+ "slk_Latn",
1815
+ "slv_Latn",
1816
+ "smo_Latn",
1817
+ "sna_Latn",
1818
+ "snd_Arab",
1819
+ "som_Latn",
1820
+ "sot_Latn",
1821
+ "spa_Latn",
1822
+ "als_Latn",
1823
+ "srd_Latn",
1824
+ "srp_Cyrl",
1825
+ "ssw_Latn",
1826
+ "sun_Latn",
1827
+ "swe_Latn",
1828
+ "swh_Latn",
1829
+ "szl_Latn",
1830
+ "tam_Taml",
1831
+ "tat_Cyrl",
1832
+ "tel_Telu",
1833
+ "tgk_Cyrl",
1834
+ "tgl_Latn",
1835
+ "tha_Thai",
1836
+ "tir_Ethi",
1837
+ "taq_Latn",
1838
+ "taq_Tfng",
1839
+ "tpi_Latn",
1840
+ "tsn_Latn",
1841
+ "tso_Latn",
1842
+ "tuk_Latn",
1843
+ "tum_Latn",
1844
+ "tur_Latn",
1845
+ "twi_Latn",
1846
+ "tzm_Tfng",
1847
+ "uig_Arab",
1848
+ "ukr_Cyrl",
1849
+ "umb_Latn",
1850
+ "urd_Arab",
1851
+ "uzn_Latn",
1852
+ "vec_Latn",
1853
+ "vie_Latn",
1854
+ "war_Latn",
1855
+ "wol_Latn",
1856
+ "xho_Latn",
1857
+ "ydd_Hebr",
1858
+ "yor_Latn",
1859
+ "yue_Hant",
1860
+ "zho_Hans",
1861
+ "zho_Hant",
1862
+ "zul_Latn"
1863
+ ],
1864
+ "bos_token": "<s>",
1865
+ "clean_up_tokenization_spaces": false,
1866
+ "cls_token": "<s>",
1867
+ "eos_token": "</s>",
1868
+ "extra_special_tokens": {},
1869
+ "legacy_behaviour": false,
1870
+ "mask_token": "<mask>",
1871
+ "model_max_length": 1024,
1872
+ "pad_token": "<pad>",
1873
+ "sep_token": "</s>",
1874
+ "sp_model_kwargs": {},
1875
+ "src_lang": "kan_Deva",
1876
+ "tgt_lang": "hin_Deva",
1877
+ "tokenizer_class": "NllbTokenizer",
1878
+ "unk_token": "<unk>"
1879
+ }
checkpoint-20000/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": 5.339028296849973,
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": 0.13347570742124934,
14
+ "grad_norm": 3.1176345348358154,
15
+ "learning_rate": 4.933395621996797e-05,
16
+ "loss": 1.6549,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.2669514148424987,
21
+ "grad_norm": 2.8823812007904053,
22
+ "learning_rate": 4.866657768286172e-05,
23
+ "loss": 1.3869,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.400427122263748,
28
+ "grad_norm": 3.436349630355835,
29
+ "learning_rate": 4.7999199145755475e-05,
30
+ "loss": 1.31,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.5339028296849974,
35
+ "grad_norm": 2.7581417560577393,
36
+ "learning_rate": 4.733182060864923e-05,
37
+ "loss": 1.2632,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.6673785371062466,
42
+ "grad_norm": 3.0282974243164062,
43
+ "learning_rate": 4.666444207154298e-05,
44
+ "loss": 1.2197,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.800854244527496,
49
+ "grad_norm": 2.7351794242858887,
50
+ "learning_rate": 4.599706353443674e-05,
51
+ "loss": 1.1942,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.9343299519487454,
56
+ "grad_norm": 2.228116035461426,
57
+ "learning_rate": 4.532968499733049e-05,
58
+ "loss": 1.1273,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.0678056593699947,
63
+ "grad_norm": 3.064039707183838,
64
+ "learning_rate": 4.466230646022424e-05,
65
+ "loss": 1.0261,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.201281366791244,
70
+ "grad_norm": 2.9547019004821777,
71
+ "learning_rate": 4.3994927923117995e-05,
72
+ "loss": 0.9262,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.3347570742124932,
77
+ "grad_norm": 2.8099584579467773,
78
+ "learning_rate": 4.332754938601175e-05,
79
+ "loss": 0.9193,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.4682327816337426,
84
+ "grad_norm": 2.4523322582244873,
85
+ "learning_rate": 4.26601708489055e-05,
86
+ "loss": 0.939,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.601708489054992,
91
+ "grad_norm": 2.4100770950317383,
92
+ "learning_rate": 4.199279231179926e-05,
93
+ "loss": 0.9084,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.7351841964762413,
98
+ "grad_norm": 2.4628851413726807,
99
+ "learning_rate": 4.1325413774693004e-05,
100
+ "loss": 0.9303,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 1.8686599038974907,
105
+ "grad_norm": 2.522763967514038,
106
+ "learning_rate": 4.0658035237586763e-05,
107
+ "loss": 0.8988,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 2.00213561131874,
112
+ "grad_norm": 1.8565527200698853,
113
+ "learning_rate": 3.9990656700480516e-05,
114
+ "loss": 0.9408,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 2.1356113187399894,
119
+ "grad_norm": 3.084707498550415,
120
+ "learning_rate": 3.932327816337427e-05,
121
+ "loss": 0.7548,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 2.269087026161239,
126
+ "grad_norm": 1.836754322052002,
127
+ "learning_rate": 3.865589962626802e-05,
128
+ "loss": 0.7447,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 2.402562733582488,
133
+ "grad_norm": 2.452847719192505,
134
+ "learning_rate": 3.798852108916178e-05,
135
+ "loss": 0.7293,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 2.536038441003737,
140
+ "grad_norm": 3.363875150680542,
141
+ "learning_rate": 3.7321142552055525e-05,
142
+ "loss": 0.7437,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 2.6695141484249865,
147
+ "grad_norm": 2.087559700012207,
148
+ "learning_rate": 3.6653764014949284e-05,
149
+ "loss": 0.7217,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 2.802989855846236,
154
+ "grad_norm": 2.1554408073425293,
155
+ "learning_rate": 3.598638547784303e-05,
156
+ "loss": 0.7459,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 2.936465563267485,
161
+ "grad_norm": 1.8922470808029175,
162
+ "learning_rate": 3.531900694073679e-05,
163
+ "loss": 0.7586,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 3.0699412706887346,
168
+ "grad_norm": 2.0937387943267822,
169
+ "learning_rate": 3.465162840363054e-05,
170
+ "loss": 0.6552,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 3.203416978109984,
175
+ "grad_norm": 2.954742908477783,
176
+ "learning_rate": 3.398424986652429e-05,
177
+ "loss": 0.6012,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 3.3368926855312333,
182
+ "grad_norm": 2.8236591815948486,
183
+ "learning_rate": 3.3316871329418045e-05,
184
+ "loss": 0.607,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 3.4703683929524827,
189
+ "grad_norm": 2.4959943294525146,
190
+ "learning_rate": 3.2649492792311804e-05,
191
+ "loss": 0.6181,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 3.603844100373732,
196
+ "grad_norm": 3.4247825145721436,
197
+ "learning_rate": 3.198211425520555e-05,
198
+ "loss": 0.6029,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 3.7373198077949814,
203
+ "grad_norm": 2.6698663234710693,
204
+ "learning_rate": 3.131473571809931e-05,
205
+ "loss": 0.6032,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 3.8707955152162308,
210
+ "grad_norm": 1.9999539852142334,
211
+ "learning_rate": 3.064735718099306e-05,
212
+ "loss": 0.6241,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 4.00427122263748,
217
+ "grad_norm": 2.449364185333252,
218
+ "learning_rate": 2.9979978643886814e-05,
219
+ "loss": 0.6183,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 4.1377469300587295,
224
+ "grad_norm": 4.328239917755127,
225
+ "learning_rate": 2.931260010678057e-05,
226
+ "loss": 0.4832,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 4.271222637479979,
231
+ "grad_norm": 1.9375187158584595,
232
+ "learning_rate": 2.8645221569674318e-05,
233
+ "loss": 0.4963,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 4.404698344901228,
238
+ "grad_norm": 2.9625084400177,
239
+ "learning_rate": 2.7977843032568074e-05,
240
+ "loss": 0.5162,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 4.538174052322478,
245
+ "grad_norm": 3.514462947845459,
246
+ "learning_rate": 2.731046449546183e-05,
247
+ "loss": 0.4913,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 4.671649759743727,
252
+ "grad_norm": 2.035665988922119,
253
+ "learning_rate": 2.664308595835558e-05,
254
+ "loss": 0.5062,
255
+ "step": 17500
256
+ },
257
+ {
258
+ "epoch": 4.805125467164976,
259
+ "grad_norm": 3.025426149368286,
260
+ "learning_rate": 2.5975707421249334e-05,
261
+ "loss": 0.5167,
262
+ "step": 18000
263
+ },
264
+ {
265
+ "epoch": 4.938601174586225,
266
+ "grad_norm": 3.0361483097076416,
267
+ "learning_rate": 2.530832888414309e-05,
268
+ "loss": 0.4961,
269
+ "step": 18500
270
+ },
271
+ {
272
+ "epoch": 5.072076882007474,
273
+ "grad_norm": 2.769930124282837,
274
+ "learning_rate": 2.464095034703684e-05,
275
+ "loss": 0.4582,
276
+ "step": 19000
277
+ },
278
+ {
279
+ "epoch": 5.205552589428724,
280
+ "grad_norm": 2.209397077560425,
281
+ "learning_rate": 2.3973571809930594e-05,
282
+ "loss": 0.3926,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 5.339028296849973,
287
+ "grad_norm": 2.680094003677368,
288
+ "learning_rate": 2.3306193272824347e-05,
289
+ "loss": 0.4187,
290
+ "step": 20000
291
+ }
292
+ ],
293
+ "logging_steps": 500,
294
+ "max_steps": 37460,
295
+ "num_input_tokens_seen": 0,
296
+ "num_train_epochs": 10,
297
+ "save_steps": 10000,
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": 8016585512091648.0,
311
+ "train_batch_size": 4,
312
+ "trial_name": null,
313
+ "trial_params": null
314
+ }
checkpoint-20000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a28c287e6a8ecc8bf8b81de0d0de1e07fac49ed361faad102304759b8b3544
3
+ size 5905
checkpoint-30000/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "M2M100ForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 0,
9
+ "d_model": 1024,
10
+ "decoder_attention_heads": 16,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0,
13
+ "decoder_layers": 12,
14
+ "decoder_start_token_id": 2,
15
+ "dropout": 0.1,
16
+ "encoder_attention_heads": 16,
17
+ "encoder_ffn_dim": 4096,
18
+ "encoder_layerdrop": 0,
19
+ "encoder_layers": 12,
20
+ "eos_token_id": 2,
21
+ "init_std": 0.02,
22
+ "is_encoder_decoder": true,
23
+ "max_length": null,
24
+ "max_position_embeddings": 1024,
25
+ "model_type": "m2m_100",
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 1,
28
+ "scale_embedding": true,
29
+ "tokenizer_class": "NllbTokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.54.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 256206
34
+ }
checkpoint-30000/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 256068,
7
+ "max_length": 200,
8
+ "pad_token_id": 1,
9
+ "transformers_version": "4.54.0.dev0"
10
+ }
checkpoint-30000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95fc62d9d2f78908b0e09df2d4ffa8d9a48aa02c2263781079c01bf32c67aa17
3
+ size 2460354912
checkpoint-30000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:206d388ac5350c8ead06ded9adceb859ae289813a3b82460705f8dca3e800336
3
+ size 14645
checkpoint-30000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e445e6dacacf56492f01dcfb953fe87b3e5d0c39ed62ed19dceae77b80a76f
3
+ size 1465
checkpoint-30000/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
checkpoint-30000/special_tokens_map.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ace_Arab",
4
+ "ace_Latn",
5
+ "acm_Arab",
6
+ "acq_Arab",
7
+ "aeb_Arab",
8
+ "afr_Latn",
9
+ "ajp_Arab",
10
+ "aka_Latn",
11
+ "amh_Ethi",
12
+ "apc_Arab",
13
+ "arb_Arab",
14
+ "ars_Arab",
15
+ "ary_Arab",
16
+ "arz_Arab",
17
+ "asm_Beng",
18
+ "ast_Latn",
19
+ "awa_Deva",
20
+ "ayr_Latn",
21
+ "azb_Arab",
22
+ "azj_Latn",
23
+ "bak_Cyrl",
24
+ "bam_Latn",
25
+ "ban_Latn",
26
+ "bel_Cyrl",
27
+ "bem_Latn",
28
+ "ben_Beng",
29
+ "bho_Deva",
30
+ "bjn_Arab",
31
+ "bjn_Latn",
32
+ "bod_Tibt",
33
+ "bos_Latn",
34
+ "bug_Latn",
35
+ "bul_Cyrl",
36
+ "cat_Latn",
37
+ "ceb_Latn",
38
+ "ces_Latn",
39
+ "cjk_Latn",
40
+ "ckb_Arab",
41
+ "crh_Latn",
42
+ "cym_Latn",
43
+ "dan_Latn",
44
+ "deu_Latn",
45
+ "dik_Latn",
46
+ "dyu_Latn",
47
+ "dzo_Tibt",
48
+ "ell_Grek",
49
+ "eng_Latn",
50
+ "epo_Latn",
51
+ "est_Latn",
52
+ "eus_Latn",
53
+ "ewe_Latn",
54
+ "fao_Latn",
55
+ "pes_Arab",
56
+ "fij_Latn",
57
+ "fin_Latn",
58
+ "fon_Latn",
59
+ "fra_Latn",
60
+ "fur_Latn",
61
+ "fuv_Latn",
62
+ "gla_Latn",
63
+ "gle_Latn",
64
+ "glg_Latn",
65
+ "grn_Latn",
66
+ "guj_Gujr",
67
+ "hat_Latn",
68
+ "hau_Latn",
69
+ "heb_Hebr",
70
+ "hin_Deva",
71
+ "hne_Deva",
72
+ "hrv_Latn",
73
+ "hun_Latn",
74
+ "hye_Armn",
75
+ "ibo_Latn",
76
+ "ilo_Latn",
77
+ "ind_Latn",
78
+ "isl_Latn",
79
+ "ita_Latn",
80
+ "jav_Latn",
81
+ "jpn_Jpan",
82
+ "kab_Latn",
83
+ "kac_Latn",
84
+ "kam_Latn",
85
+ "kan_Knda",
86
+ "kas_Arab",
87
+ "kas_Deva",
88
+ "kat_Geor",
89
+ "knc_Arab",
90
+ "knc_Latn",
91
+ "kaz_Cyrl",
92
+ "kbp_Latn",
93
+ "kea_Latn",
94
+ "khm_Khmr",
95
+ "kik_Latn",
96
+ "kin_Latn",
97
+ "kir_Cyrl",
98
+ "kmb_Latn",
99
+ "kon_Latn",
100
+ "kor_Hang",
101
+ "kmr_Latn",
102
+ "lao_Laoo",
103
+ "lvs_Latn",
104
+ "lij_Latn",
105
+ "lim_Latn",
106
+ "lin_Latn",
107
+ "lit_Latn",
108
+ "lmo_Latn",
109
+ "ltg_Latn",
110
+ "ltz_Latn",
111
+ "lua_Latn",
112
+ "lug_Latn",
113
+ "luo_Latn",
114
+ "lus_Latn",
115
+ "mag_Deva",
116
+ "mai_Deva",
117
+ "mal_Mlym",
118
+ "mar_Deva",
119
+ "min_Latn",
120
+ "mkd_Cyrl",
121
+ "plt_Latn",
122
+ "mlt_Latn",
123
+ "mni_Beng",
124
+ "khk_Cyrl",
125
+ "mos_Latn",
126
+ "mri_Latn",
127
+ "zsm_Latn",
128
+ "mya_Mymr",
129
+ "nld_Latn",
130
+ "nno_Latn",
131
+ "nob_Latn",
132
+ "npi_Deva",
133
+ "nso_Latn",
134
+ "nus_Latn",
135
+ "nya_Latn",
136
+ "oci_Latn",
137
+ "gaz_Latn",
138
+ "ory_Orya",
139
+ "pag_Latn",
140
+ "pan_Guru",
141
+ "pap_Latn",
142
+ "pol_Latn",
143
+ "por_Latn",
144
+ "prs_Arab",
145
+ "pbt_Arab",
146
+ "quy_Latn",
147
+ "ron_Latn",
148
+ "run_Latn",
149
+ "rus_Cyrl",
150
+ "sag_Latn",
151
+ "san_Deva",
152
+ "sat_Beng",
153
+ "scn_Latn",
154
+ "shn_Mymr",
155
+ "sin_Sinh",
156
+ "slk_Latn",
157
+ "slv_Latn",
158
+ "smo_Latn",
159
+ "sna_Latn",
160
+ "snd_Arab",
161
+ "som_Latn",
162
+ "sot_Latn",
163
+ "spa_Latn",
164
+ "als_Latn",
165
+ "srd_Latn",
166
+ "srp_Cyrl",
167
+ "ssw_Latn",
168
+ "sun_Latn",
169
+ "swe_Latn",
170
+ "swh_Latn",
171
+ "szl_Latn",
172
+ "tam_Taml",
173
+ "tat_Cyrl",
174
+ "tel_Telu",
175
+ "tgk_Cyrl",
176
+ "tgl_Latn",
177
+ "tha_Thai",
178
+ "tir_Ethi",
179
+ "taq_Latn",
180
+ "taq_Tfng",
181
+ "tpi_Latn",
182
+ "tsn_Latn",
183
+ "tso_Latn",
184
+ "tuk_Latn",
185
+ "tum_Latn",
186
+ "tur_Latn",
187
+ "twi_Latn",
188
+ "tzm_Tfng",
189
+ "uig_Arab",
190
+ "ukr_Cyrl",
191
+ "umb_Latn",
192
+ "urd_Arab",
193
+ "uzn_Latn",
194
+ "vec_Latn",
195
+ "vie_Latn",
196
+ "war_Latn",
197
+ "wol_Latn",
198
+ "xho_Latn",
199
+ "ydd_Hebr",
200
+ "yor_Latn",
201
+ "yue_Hant",
202
+ "zho_Hans",
203
+ "zho_Hant",
204
+ "zul_Latn"
205
+ ],
206
+ "bos_token": {
207
+ "content": "<s>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ "cls_token": {
214
+ "content": "<s>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ "eos_token": {
221
+ "content": "</s>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ "mask_token": {
228
+ "content": "<mask>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ "pad_token": {
235
+ "content": "<pad>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ "sep_token": {
242
+ "content": "</s>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ "unk_token": {
249
+ "content": "<unk>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ }
255
+ }
checkpoint-30000/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd897f6e1b43d40640d698f1ed736005d47a08ed8e8e2e389d4b5d60d7892212
3
+ size 32240214
checkpoint-30000/tokenizer_config.json ADDED
@@ -0,0 +1,1879 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "256001": {
36
+ "content": "ace_Arab",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "256002": {
44
+ "content": "ace_Latn",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "256003": {
52
+ "content": "acm_Arab",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "256004": {
60
+ "content": "acq_Arab",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "256005": {
68
+ "content": "aeb_Arab",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "256006": {
76
+ "content": "afr_Latn",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "256007": {
84
+ "content": "ajp_Arab",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "256008": {
92
+ "content": "aka_Latn",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "256009": {
100
+ "content": "amh_Ethi",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "256010": {
108
+ "content": "apc_Arab",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "256011": {
116
+ "content": "arb_Arab",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "256012": {
124
+ "content": "ars_Arab",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "256013": {
132
+ "content": "ary_Arab",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "256014": {
140
+ "content": "arz_Arab",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "256015": {
148
+ "content": "asm_Beng",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "256016": {
156
+ "content": "ast_Latn",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "256017": {
164
+ "content": "awa_Deva",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "256018": {
172
+ "content": "ayr_Latn",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "256019": {
180
+ "content": "azb_Arab",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "256020": {
188
+ "content": "azj_Latn",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "256021": {
196
+ "content": "bak_Cyrl",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "256022": {
204
+ "content": "bam_Latn",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "256023": {
212
+ "content": "ban_Latn",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "256024": {
220
+ "content": "bel_Cyrl",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "256025": {
228
+ "content": "bem_Latn",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "256026": {
236
+ "content": "ben_Beng",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "256027": {
244
+ "content": "bho_Deva",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "256028": {
252
+ "content": "bjn_Arab",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "256029": {
260
+ "content": "bjn_Latn",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "256030": {
268
+ "content": "bod_Tibt",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "256031": {
276
+ "content": "bos_Latn",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "256032": {
284
+ "content": "bug_Latn",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "256033": {
292
+ "content": "bul_Cyrl",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "256034": {
300
+ "content": "cat_Latn",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "256035": {
308
+ "content": "ceb_Latn",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "256036": {
316
+ "content": "ces_Latn",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "256037": {
324
+ "content": "cjk_Latn",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "256038": {
332
+ "content": "ckb_Arab",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "256039": {
340
+ "content": "crh_Latn",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "256040": {
348
+ "content": "cym_Latn",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "256041": {
356
+ "content": "dan_Latn",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "256042": {
364
+ "content": "deu_Latn",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "256043": {
372
+ "content": "dik_Latn",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "256044": {
380
+ "content": "dyu_Latn",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "256045": {
388
+ "content": "dzo_Tibt",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "256046": {
396
+ "content": "ell_Grek",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "256047": {
404
+ "content": "eng_Latn",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "256048": {
412
+ "content": "epo_Latn",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "256049": {
420
+ "content": "est_Latn",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "256050": {
428
+ "content": "eus_Latn",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "256051": {
436
+ "content": "ewe_Latn",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "256052": {
444
+ "content": "fao_Latn",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "256053": {
452
+ "content": "pes_Arab",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "256054": {
460
+ "content": "fij_Latn",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "256055": {
468
+ "content": "fin_Latn",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "256056": {
476
+ "content": "fon_Latn",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "256057": {
484
+ "content": "fra_Latn",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "256058": {
492
+ "content": "fur_Latn",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "256059": {
500
+ "content": "fuv_Latn",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "256060": {
508
+ "content": "gla_Latn",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "256061": {
516
+ "content": "gle_Latn",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "256062": {
524
+ "content": "glg_Latn",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "256063": {
532
+ "content": "grn_Latn",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "256064": {
540
+ "content": "guj_Gujr",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "256065": {
548
+ "content": "hat_Latn",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "256066": {
556
+ "content": "hau_Latn",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "256067": {
564
+ "content": "heb_Hebr",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "256068": {
572
+ "content": "hin_Deva",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "256069": {
580
+ "content": "hne_Deva",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "256070": {
588
+ "content": "hrv_Latn",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "256071": {
596
+ "content": "hun_Latn",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "256072": {
604
+ "content": "hye_Armn",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "256073": {
612
+ "content": "ibo_Latn",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "256074": {
620
+ "content": "ilo_Latn",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "256075": {
628
+ "content": "ind_Latn",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "256076": {
636
+ "content": "isl_Latn",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "256077": {
644
+ "content": "ita_Latn",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "256078": {
652
+ "content": "jav_Latn",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "256079": {
660
+ "content": "jpn_Jpan",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "256080": {
668
+ "content": "kab_Latn",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "256081": {
676
+ "content": "kac_Latn",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "256082": {
684
+ "content": "kam_Latn",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "256083": {
692
+ "content": "kan_Knda",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "256084": {
700
+ "content": "kas_Arab",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "256085": {
708
+ "content": "kas_Deva",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "256086": {
716
+ "content": "kat_Geor",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "256087": {
724
+ "content": "knc_Arab",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "256088": {
732
+ "content": "knc_Latn",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "256089": {
740
+ "content": "kaz_Cyrl",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "256090": {
748
+ "content": "kbp_Latn",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "256091": {
756
+ "content": "kea_Latn",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "256092": {
764
+ "content": "khm_Khmr",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "256093": {
772
+ "content": "kik_Latn",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "256094": {
780
+ "content": "kin_Latn",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "256095": {
788
+ "content": "kir_Cyrl",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "256096": {
796
+ "content": "kmb_Latn",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "256097": {
804
+ "content": "kon_Latn",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "256098": {
812
+ "content": "kor_Hang",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "256099": {
820
+ "content": "kmr_Latn",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "256100": {
828
+ "content": "lao_Laoo",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "256101": {
836
+ "content": "lvs_Latn",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "256102": {
844
+ "content": "lij_Latn",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "256103": {
852
+ "content": "lim_Latn",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "256104": {
860
+ "content": "lin_Latn",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "256105": {
868
+ "content": "lit_Latn",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "256106": {
876
+ "content": "lmo_Latn",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "256107": {
884
+ "content": "ltg_Latn",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "256108": {
892
+ "content": "ltz_Latn",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "256109": {
900
+ "content": "lua_Latn",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "256110": {
908
+ "content": "lug_Latn",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "256111": {
916
+ "content": "luo_Latn",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "256112": {
924
+ "content": "lus_Latn",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "256113": {
932
+ "content": "mag_Deva",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "256114": {
940
+ "content": "mai_Deva",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "256115": {
948
+ "content": "mal_Mlym",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "256116": {
956
+ "content": "mar_Deva",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "256117": {
964
+ "content": "min_Latn",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "256118": {
972
+ "content": "mkd_Cyrl",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "256119": {
980
+ "content": "plt_Latn",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "256120": {
988
+ "content": "mlt_Latn",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "256121": {
996
+ "content": "mni_Beng",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "256122": {
1004
+ "content": "khk_Cyrl",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "256123": {
1012
+ "content": "mos_Latn",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "256124": {
1020
+ "content": "mri_Latn",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "256125": {
1028
+ "content": "zsm_Latn",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "256126": {
1036
+ "content": "mya_Mymr",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "256127": {
1044
+ "content": "nld_Latn",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "256128": {
1052
+ "content": "nno_Latn",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "256129": {
1060
+ "content": "nob_Latn",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "256130": {
1068
+ "content": "npi_Deva",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "256131": {
1076
+ "content": "nso_Latn",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "256132": {
1084
+ "content": "nus_Latn",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "256133": {
1092
+ "content": "nya_Latn",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "256134": {
1100
+ "content": "oci_Latn",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "256135": {
1108
+ "content": "gaz_Latn",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "256136": {
1116
+ "content": "ory_Orya",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "256137": {
1124
+ "content": "pag_Latn",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "256138": {
1132
+ "content": "pan_Guru",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "256139": {
1140
+ "content": "pap_Latn",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "256140": {
1148
+ "content": "pol_Latn",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "256141": {
1156
+ "content": "por_Latn",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "256142": {
1164
+ "content": "prs_Arab",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "256143": {
1172
+ "content": "pbt_Arab",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "256144": {
1180
+ "content": "quy_Latn",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "256145": {
1188
+ "content": "ron_Latn",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "256146": {
1196
+ "content": "run_Latn",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "256147": {
1204
+ "content": "rus_Cyrl",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "256148": {
1212
+ "content": "sag_Latn",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "256149": {
1220
+ "content": "san_Deva",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "256150": {
1228
+ "content": "sat_Beng",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "256151": {
1236
+ "content": "scn_Latn",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "256152": {
1244
+ "content": "shn_Mymr",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "256153": {
1252
+ "content": "sin_Sinh",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "256154": {
1260
+ "content": "slk_Latn",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "256155": {
1268
+ "content": "slv_Latn",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "256156": {
1276
+ "content": "smo_Latn",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "256157": {
1284
+ "content": "sna_Latn",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "256158": {
1292
+ "content": "snd_Arab",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "256159": {
1300
+ "content": "som_Latn",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "256160": {
1308
+ "content": "sot_Latn",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "256161": {
1316
+ "content": "spa_Latn",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "256162": {
1324
+ "content": "als_Latn",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "256163": {
1332
+ "content": "srd_Latn",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "256164": {
1340
+ "content": "srp_Cyrl",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "256165": {
1348
+ "content": "ssw_Latn",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "256166": {
1356
+ "content": "sun_Latn",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "256167": {
1364
+ "content": "swe_Latn",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "256168": {
1372
+ "content": "swh_Latn",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "256169": {
1380
+ "content": "szl_Latn",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "256170": {
1388
+ "content": "tam_Taml",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "256171": {
1396
+ "content": "tat_Cyrl",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "256172": {
1404
+ "content": "tel_Telu",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "256173": {
1412
+ "content": "tgk_Cyrl",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "256174": {
1420
+ "content": "tgl_Latn",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "256175": {
1428
+ "content": "tha_Thai",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "256176": {
1436
+ "content": "tir_Ethi",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "256177": {
1444
+ "content": "taq_Latn",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "256178": {
1452
+ "content": "taq_Tfng",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "256179": {
1460
+ "content": "tpi_Latn",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "256180": {
1468
+ "content": "tsn_Latn",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "256181": {
1476
+ "content": "tso_Latn",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "256182": {
1484
+ "content": "tuk_Latn",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "256183": {
1492
+ "content": "tum_Latn",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "256184": {
1500
+ "content": "tur_Latn",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "256185": {
1508
+ "content": "twi_Latn",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "256186": {
1516
+ "content": "tzm_Tfng",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "256187": {
1524
+ "content": "uig_Arab",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "256188": {
1532
+ "content": "ukr_Cyrl",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "256189": {
1540
+ "content": "umb_Latn",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "256190": {
1548
+ "content": "urd_Arab",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "256191": {
1556
+ "content": "uzn_Latn",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "256192": {
1564
+ "content": "vec_Latn",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "256193": {
1572
+ "content": "vie_Latn",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "256194": {
1580
+ "content": "war_Latn",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "256195": {
1588
+ "content": "wol_Latn",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "256196": {
1596
+ "content": "xho_Latn",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "256197": {
1604
+ "content": "ydd_Hebr",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "256198": {
1612
+ "content": "yor_Latn",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "256199": {
1620
+ "content": "yue_Hant",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "256200": {
1628
+ "content": "zho_Hans",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "256201": {
1636
+ "content": "zho_Hant",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "256202": {
1644
+ "content": "zul_Latn",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "256203": {
1652
+ "content": "<mask>",
1653
+ "lstrip": true,
1654
+ "normalized": true,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ }
1659
+ },
1660
+ "additional_special_tokens": [
1661
+ "ace_Arab",
1662
+ "ace_Latn",
1663
+ "acm_Arab",
1664
+ "acq_Arab",
1665
+ "aeb_Arab",
1666
+ "afr_Latn",
1667
+ "ajp_Arab",
1668
+ "aka_Latn",
1669
+ "amh_Ethi",
1670
+ "apc_Arab",
1671
+ "arb_Arab",
1672
+ "ars_Arab",
1673
+ "ary_Arab",
1674
+ "arz_Arab",
1675
+ "asm_Beng",
1676
+ "ast_Latn",
1677
+ "awa_Deva",
1678
+ "ayr_Latn",
1679
+ "azb_Arab",
1680
+ "azj_Latn",
1681
+ "bak_Cyrl",
1682
+ "bam_Latn",
1683
+ "ban_Latn",
1684
+ "bel_Cyrl",
1685
+ "bem_Latn",
1686
+ "ben_Beng",
1687
+ "bho_Deva",
1688
+ "bjn_Arab",
1689
+ "bjn_Latn",
1690
+ "bod_Tibt",
1691
+ "bos_Latn",
1692
+ "bug_Latn",
1693
+ "bul_Cyrl",
1694
+ "cat_Latn",
1695
+ "ceb_Latn",
1696
+ "ces_Latn",
1697
+ "cjk_Latn",
1698
+ "ckb_Arab",
1699
+ "crh_Latn",
1700
+ "cym_Latn",
1701
+ "dan_Latn",
1702
+ "deu_Latn",
1703
+ "dik_Latn",
1704
+ "dyu_Latn",
1705
+ "dzo_Tibt",
1706
+ "ell_Grek",
1707
+ "eng_Latn",
1708
+ "epo_Latn",
1709
+ "est_Latn",
1710
+ "eus_Latn",
1711
+ "ewe_Latn",
1712
+ "fao_Latn",
1713
+ "pes_Arab",
1714
+ "fij_Latn",
1715
+ "fin_Latn",
1716
+ "fon_Latn",
1717
+ "fra_Latn",
1718
+ "fur_Latn",
1719
+ "fuv_Latn",
1720
+ "gla_Latn",
1721
+ "gle_Latn",
1722
+ "glg_Latn",
1723
+ "grn_Latn",
1724
+ "guj_Gujr",
1725
+ "hat_Latn",
1726
+ "hau_Latn",
1727
+ "heb_Hebr",
1728
+ "hin_Deva",
1729
+ "hne_Deva",
1730
+ "hrv_Latn",
1731
+ "hun_Latn",
1732
+ "hye_Armn",
1733
+ "ibo_Latn",
1734
+ "ilo_Latn",
1735
+ "ind_Latn",
1736
+ "isl_Latn",
1737
+ "ita_Latn",
1738
+ "jav_Latn",
1739
+ "jpn_Jpan",
1740
+ "kab_Latn",
1741
+ "kac_Latn",
1742
+ "kam_Latn",
1743
+ "kan_Knda",
1744
+ "kas_Arab",
1745
+ "kas_Deva",
1746
+ "kat_Geor",
1747
+ "knc_Arab",
1748
+ "knc_Latn",
1749
+ "kaz_Cyrl",
1750
+ "kbp_Latn",
1751
+ "kea_Latn",
1752
+ "khm_Khmr",
1753
+ "kik_Latn",
1754
+ "kin_Latn",
1755
+ "kir_Cyrl",
1756
+ "kmb_Latn",
1757
+ "kon_Latn",
1758
+ "kor_Hang",
1759
+ "kmr_Latn",
1760
+ "lao_Laoo",
1761
+ "lvs_Latn",
1762
+ "lij_Latn",
1763
+ "lim_Latn",
1764
+ "lin_Latn",
1765
+ "lit_Latn",
1766
+ "lmo_Latn",
1767
+ "ltg_Latn",
1768
+ "ltz_Latn",
1769
+ "lua_Latn",
1770
+ "lug_Latn",
1771
+ "luo_Latn",
1772
+ "lus_Latn",
1773
+ "mag_Deva",
1774
+ "mai_Deva",
1775
+ "mal_Mlym",
1776
+ "mar_Deva",
1777
+ "min_Latn",
1778
+ "mkd_Cyrl",
1779
+ "plt_Latn",
1780
+ "mlt_Latn",
1781
+ "mni_Beng",
1782
+ "khk_Cyrl",
1783
+ "mos_Latn",
1784
+ "mri_Latn",
1785
+ "zsm_Latn",
1786
+ "mya_Mymr",
1787
+ "nld_Latn",
1788
+ "nno_Latn",
1789
+ "nob_Latn",
1790
+ "npi_Deva",
1791
+ "nso_Latn",
1792
+ "nus_Latn",
1793
+ "nya_Latn",
1794
+ "oci_Latn",
1795
+ "gaz_Latn",
1796
+ "ory_Orya",
1797
+ "pag_Latn",
1798
+ "pan_Guru",
1799
+ "pap_Latn",
1800
+ "pol_Latn",
1801
+ "por_Latn",
1802
+ "prs_Arab",
1803
+ "pbt_Arab",
1804
+ "quy_Latn",
1805
+ "ron_Latn",
1806
+ "run_Latn",
1807
+ "rus_Cyrl",
1808
+ "sag_Latn",
1809
+ "san_Deva",
1810
+ "sat_Beng",
1811
+ "scn_Latn",
1812
+ "shn_Mymr",
1813
+ "sin_Sinh",
1814
+ "slk_Latn",
1815
+ "slv_Latn",
1816
+ "smo_Latn",
1817
+ "sna_Latn",
1818
+ "snd_Arab",
1819
+ "som_Latn",
1820
+ "sot_Latn",
1821
+ "spa_Latn",
1822
+ "als_Latn",
1823
+ "srd_Latn",
1824
+ "srp_Cyrl",
1825
+ "ssw_Latn",
1826
+ "sun_Latn",
1827
+ "swe_Latn",
1828
+ "swh_Latn",
1829
+ "szl_Latn",
1830
+ "tam_Taml",
1831
+ "tat_Cyrl",
1832
+ "tel_Telu",
1833
+ "tgk_Cyrl",
1834
+ "tgl_Latn",
1835
+ "tha_Thai",
1836
+ "tir_Ethi",
1837
+ "taq_Latn",
1838
+ "taq_Tfng",
1839
+ "tpi_Latn",
1840
+ "tsn_Latn",
1841
+ "tso_Latn",
1842
+ "tuk_Latn",
1843
+ "tum_Latn",
1844
+ "tur_Latn",
1845
+ "twi_Latn",
1846
+ "tzm_Tfng",
1847
+ "uig_Arab",
1848
+ "ukr_Cyrl",
1849
+ "umb_Latn",
1850
+ "urd_Arab",
1851
+ "uzn_Latn",
1852
+ "vec_Latn",
1853
+ "vie_Latn",
1854
+ "war_Latn",
1855
+ "wol_Latn",
1856
+ "xho_Latn",
1857
+ "ydd_Hebr",
1858
+ "yor_Latn",
1859
+ "yue_Hant",
1860
+ "zho_Hans",
1861
+ "zho_Hant",
1862
+ "zul_Latn"
1863
+ ],
1864
+ "bos_token": "<s>",
1865
+ "clean_up_tokenization_spaces": false,
1866
+ "cls_token": "<s>",
1867
+ "eos_token": "</s>",
1868
+ "extra_special_tokens": {},
1869
+ "legacy_behaviour": false,
1870
+ "mask_token": "<mask>",
1871
+ "model_max_length": 1024,
1872
+ "pad_token": "<pad>",
1873
+ "sep_token": "</s>",
1874
+ "sp_model_kwargs": {},
1875
+ "src_lang": "kan_Deva",
1876
+ "tgt_lang": "hin_Deva",
1877
+ "tokenizer_class": "NllbTokenizer",
1878
+ "unk_token": "<unk>"
1879
+ }
checkpoint-30000/trainer_state.json ADDED
@@ -0,0 +1,454 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 8.00854244527496,
6
+ "eval_steps": 500,
7
+ "global_step": 30000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13347570742124934,
14
+ "grad_norm": 3.1176345348358154,
15
+ "learning_rate": 4.933395621996797e-05,
16
+ "loss": 1.6549,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.2669514148424987,
21
+ "grad_norm": 2.8823812007904053,
22
+ "learning_rate": 4.866657768286172e-05,
23
+ "loss": 1.3869,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.400427122263748,
28
+ "grad_norm": 3.436349630355835,
29
+ "learning_rate": 4.7999199145755475e-05,
30
+ "loss": 1.31,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.5339028296849974,
35
+ "grad_norm": 2.7581417560577393,
36
+ "learning_rate": 4.733182060864923e-05,
37
+ "loss": 1.2632,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.6673785371062466,
42
+ "grad_norm": 3.0282974243164062,
43
+ "learning_rate": 4.666444207154298e-05,
44
+ "loss": 1.2197,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.800854244527496,
49
+ "grad_norm": 2.7351794242858887,
50
+ "learning_rate": 4.599706353443674e-05,
51
+ "loss": 1.1942,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.9343299519487454,
56
+ "grad_norm": 2.228116035461426,
57
+ "learning_rate": 4.532968499733049e-05,
58
+ "loss": 1.1273,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.0678056593699947,
63
+ "grad_norm": 3.064039707183838,
64
+ "learning_rate": 4.466230646022424e-05,
65
+ "loss": 1.0261,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.201281366791244,
70
+ "grad_norm": 2.9547019004821777,
71
+ "learning_rate": 4.3994927923117995e-05,
72
+ "loss": 0.9262,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.3347570742124932,
77
+ "grad_norm": 2.8099584579467773,
78
+ "learning_rate": 4.332754938601175e-05,
79
+ "loss": 0.9193,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.4682327816337426,
84
+ "grad_norm": 2.4523322582244873,
85
+ "learning_rate": 4.26601708489055e-05,
86
+ "loss": 0.939,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.601708489054992,
91
+ "grad_norm": 2.4100770950317383,
92
+ "learning_rate": 4.199279231179926e-05,
93
+ "loss": 0.9084,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.7351841964762413,
98
+ "grad_norm": 2.4628851413726807,
99
+ "learning_rate": 4.1325413774693004e-05,
100
+ "loss": 0.9303,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 1.8686599038974907,
105
+ "grad_norm": 2.522763967514038,
106
+ "learning_rate": 4.0658035237586763e-05,
107
+ "loss": 0.8988,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 2.00213561131874,
112
+ "grad_norm": 1.8565527200698853,
113
+ "learning_rate": 3.9990656700480516e-05,
114
+ "loss": 0.9408,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 2.1356113187399894,
119
+ "grad_norm": 3.084707498550415,
120
+ "learning_rate": 3.932327816337427e-05,
121
+ "loss": 0.7548,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 2.269087026161239,
126
+ "grad_norm": 1.836754322052002,
127
+ "learning_rate": 3.865589962626802e-05,
128
+ "loss": 0.7447,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 2.402562733582488,
133
+ "grad_norm": 2.452847719192505,
134
+ "learning_rate": 3.798852108916178e-05,
135
+ "loss": 0.7293,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 2.536038441003737,
140
+ "grad_norm": 3.363875150680542,
141
+ "learning_rate": 3.7321142552055525e-05,
142
+ "loss": 0.7437,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 2.6695141484249865,
147
+ "grad_norm": 2.087559700012207,
148
+ "learning_rate": 3.6653764014949284e-05,
149
+ "loss": 0.7217,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 2.802989855846236,
154
+ "grad_norm": 2.1554408073425293,
155
+ "learning_rate": 3.598638547784303e-05,
156
+ "loss": 0.7459,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 2.936465563267485,
161
+ "grad_norm": 1.8922470808029175,
162
+ "learning_rate": 3.531900694073679e-05,
163
+ "loss": 0.7586,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 3.0699412706887346,
168
+ "grad_norm": 2.0937387943267822,
169
+ "learning_rate": 3.465162840363054e-05,
170
+ "loss": 0.6552,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 3.203416978109984,
175
+ "grad_norm": 2.954742908477783,
176
+ "learning_rate": 3.398424986652429e-05,
177
+ "loss": 0.6012,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 3.3368926855312333,
182
+ "grad_norm": 2.8236591815948486,
183
+ "learning_rate": 3.3316871329418045e-05,
184
+ "loss": 0.607,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 3.4703683929524827,
189
+ "grad_norm": 2.4959943294525146,
190
+ "learning_rate": 3.2649492792311804e-05,
191
+ "loss": 0.6181,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 3.603844100373732,
196
+ "grad_norm": 3.4247825145721436,
197
+ "learning_rate": 3.198211425520555e-05,
198
+ "loss": 0.6029,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 3.7373198077949814,
203
+ "grad_norm": 2.6698663234710693,
204
+ "learning_rate": 3.131473571809931e-05,
205
+ "loss": 0.6032,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 3.8707955152162308,
210
+ "grad_norm": 1.9999539852142334,
211
+ "learning_rate": 3.064735718099306e-05,
212
+ "loss": 0.6241,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 4.00427122263748,
217
+ "grad_norm": 2.449364185333252,
218
+ "learning_rate": 2.9979978643886814e-05,
219
+ "loss": 0.6183,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 4.1377469300587295,
224
+ "grad_norm": 4.328239917755127,
225
+ "learning_rate": 2.931260010678057e-05,
226
+ "loss": 0.4832,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 4.271222637479979,
231
+ "grad_norm": 1.9375187158584595,
232
+ "learning_rate": 2.8645221569674318e-05,
233
+ "loss": 0.4963,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 4.404698344901228,
238
+ "grad_norm": 2.9625084400177,
239
+ "learning_rate": 2.7977843032568074e-05,
240
+ "loss": 0.5162,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 4.538174052322478,
245
+ "grad_norm": 3.514462947845459,
246
+ "learning_rate": 2.731046449546183e-05,
247
+ "loss": 0.4913,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 4.671649759743727,
252
+ "grad_norm": 2.035665988922119,
253
+ "learning_rate": 2.664308595835558e-05,
254
+ "loss": 0.5062,
255
+ "step": 17500
256
+ },
257
+ {
258
+ "epoch": 4.805125467164976,
259
+ "grad_norm": 3.025426149368286,
260
+ "learning_rate": 2.5975707421249334e-05,
261
+ "loss": 0.5167,
262
+ "step": 18000
263
+ },
264
+ {
265
+ "epoch": 4.938601174586225,
266
+ "grad_norm": 3.0361483097076416,
267
+ "learning_rate": 2.530832888414309e-05,
268
+ "loss": 0.4961,
269
+ "step": 18500
270
+ },
271
+ {
272
+ "epoch": 5.072076882007474,
273
+ "grad_norm": 2.769930124282837,
274
+ "learning_rate": 2.464095034703684e-05,
275
+ "loss": 0.4582,
276
+ "step": 19000
277
+ },
278
+ {
279
+ "epoch": 5.205552589428724,
280
+ "grad_norm": 2.209397077560425,
281
+ "learning_rate": 2.3973571809930594e-05,
282
+ "loss": 0.3926,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 5.339028296849973,
287
+ "grad_norm": 2.680094003677368,
288
+ "learning_rate": 2.3306193272824347e-05,
289
+ "loss": 0.4187,
290
+ "step": 20000
291
+ },
292
+ {
293
+ "epoch": 5.472504004271222,
294
+ "grad_norm": 2.425154447555542,
295
+ "learning_rate": 2.26388147357181e-05,
296
+ "loss": 0.4182,
297
+ "step": 20500
298
+ },
299
+ {
300
+ "epoch": 5.605979711692472,
301
+ "grad_norm": 4.719789505004883,
302
+ "learning_rate": 2.197143619861185e-05,
303
+ "loss": 0.4257,
304
+ "step": 21000
305
+ },
306
+ {
307
+ "epoch": 5.739455419113721,
308
+ "grad_norm": 1.3763984441757202,
309
+ "learning_rate": 2.1304057661505607e-05,
310
+ "loss": 0.4222,
311
+ "step": 21500
312
+ },
313
+ {
314
+ "epoch": 5.87293112653497,
315
+ "grad_norm": 2.8332626819610596,
316
+ "learning_rate": 2.063667912439936e-05,
317
+ "loss": 0.4247,
318
+ "step": 22000
319
+ },
320
+ {
321
+ "epoch": 6.00640683395622,
322
+ "grad_norm": 1.990326166152954,
323
+ "learning_rate": 1.996930058729311e-05,
324
+ "loss": 0.4149,
325
+ "step": 22500
326
+ },
327
+ {
328
+ "epoch": 6.139882541377469,
329
+ "grad_norm": 1.9501370191574097,
330
+ "learning_rate": 1.9301922050186867e-05,
331
+ "loss": 0.3451,
332
+ "step": 23000
333
+ },
334
+ {
335
+ "epoch": 6.2733582487987185,
336
+ "grad_norm": 2.518463611602783,
337
+ "learning_rate": 1.863454351308062e-05,
338
+ "loss": 0.3338,
339
+ "step": 23500
340
+ },
341
+ {
342
+ "epoch": 6.406833956219968,
343
+ "grad_norm": 2.567760705947876,
344
+ "learning_rate": 1.7967164975974375e-05,
345
+ "loss": 0.3537,
346
+ "step": 24000
347
+ },
348
+ {
349
+ "epoch": 6.540309663641217,
350
+ "grad_norm": 3.4953105449676514,
351
+ "learning_rate": 1.7299786438868128e-05,
352
+ "loss": 0.3463,
353
+ "step": 24500
354
+ },
355
+ {
356
+ "epoch": 6.673785371062467,
357
+ "grad_norm": 4.280869007110596,
358
+ "learning_rate": 1.663240790176188e-05,
359
+ "loss": 0.3794,
360
+ "step": 25000
361
+ },
362
+ {
363
+ "epoch": 6.807261078483716,
364
+ "grad_norm": 1.3708416223526,
365
+ "learning_rate": 1.5965029364655636e-05,
366
+ "loss": 0.3595,
367
+ "step": 25500
368
+ },
369
+ {
370
+ "epoch": 6.940736785904965,
371
+ "grad_norm": 1.9402921199798584,
372
+ "learning_rate": 1.5297650827549388e-05,
373
+ "loss": 0.3567,
374
+ "step": 26000
375
+ },
376
+ {
377
+ "epoch": 7.074212493326215,
378
+ "grad_norm": 3.4459097385406494,
379
+ "learning_rate": 1.463027229044314e-05,
380
+ "loss": 0.3271,
381
+ "step": 26500
382
+ },
383
+ {
384
+ "epoch": 7.207688200747464,
385
+ "grad_norm": 3.0598597526550293,
386
+ "learning_rate": 1.3962893753336892e-05,
387
+ "loss": 0.3053,
388
+ "step": 27000
389
+ },
390
+ {
391
+ "epoch": 7.3411639081687134,
392
+ "grad_norm": 1.887160062789917,
393
+ "learning_rate": 1.3295515216230648e-05,
394
+ "loss": 0.2941,
395
+ "step": 27500
396
+ },
397
+ {
398
+ "epoch": 7.474639615589963,
399
+ "grad_norm": 2.143535852432251,
400
+ "learning_rate": 1.26281366791244e-05,
401
+ "loss": 0.2981,
402
+ "step": 28000
403
+ },
404
+ {
405
+ "epoch": 7.608115323011212,
406
+ "grad_norm": 4.371819019317627,
407
+ "learning_rate": 1.1960758142018154e-05,
408
+ "loss": 0.2986,
409
+ "step": 28500
410
+ },
411
+ {
412
+ "epoch": 7.7415910304324616,
413
+ "grad_norm": 3.378239631652832,
414
+ "learning_rate": 1.1293379604911907e-05,
415
+ "loss": 0.305,
416
+ "step": 29000
417
+ },
418
+ {
419
+ "epoch": 7.875066737853711,
420
+ "grad_norm": 2.8271336555480957,
421
+ "learning_rate": 1.062600106780566e-05,
422
+ "loss": 0.3193,
423
+ "step": 29500
424
+ },
425
+ {
426
+ "epoch": 8.00854244527496,
427
+ "grad_norm": 2.825468063354492,
428
+ "learning_rate": 9.958622530699413e-06,
429
+ "loss": 0.3004,
430
+ "step": 30000
431
+ }
432
+ ],
433
+ "logging_steps": 500,
434
+ "max_steps": 37460,
435
+ "num_input_tokens_seen": 0,
436
+ "num_train_epochs": 10,
437
+ "save_steps": 10000,
438
+ "stateful_callbacks": {
439
+ "TrainerControl": {
440
+ "args": {
441
+ "should_epoch_stop": false,
442
+ "should_evaluate": false,
443
+ "should_log": false,
444
+ "should_save": true,
445
+ "should_training_stop": false
446
+ },
447
+ "attributes": {}
448
+ }
449
+ },
450
+ "total_flos": 1.2035066199343104e+16,
451
+ "train_batch_size": 4,
452
+ "trial_name": null,
453
+ "trial_params": null
454
+ }
checkpoint-30000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a28c287e6a8ecc8bf8b81de0d0de1e07fac49ed361faad102304759b8b3544
3
+ size 5905
checkpoint-37460/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "M2M100ForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 0,
9
+ "d_model": 1024,
10
+ "decoder_attention_heads": 16,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0,
13
+ "decoder_layers": 12,
14
+ "decoder_start_token_id": 2,
15
+ "dropout": 0.1,
16
+ "encoder_attention_heads": 16,
17
+ "encoder_ffn_dim": 4096,
18
+ "encoder_layerdrop": 0,
19
+ "encoder_layers": 12,
20
+ "eos_token_id": 2,
21
+ "init_std": 0.02,
22
+ "is_encoder_decoder": true,
23
+ "max_length": null,
24
+ "max_position_embeddings": 1024,
25
+ "model_type": "m2m_100",
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 1,
28
+ "scale_embedding": true,
29
+ "tokenizer_class": "NllbTokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.54.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 256206
34
+ }
checkpoint-37460/generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 256068,
7
+ "max_length": 200,
8
+ "pad_token_id": 1,
9
+ "transformers_version": "4.54.0.dev0"
10
+ }
checkpoint-37460/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85637fa1e094799e84b5acec70617c4215a8e1119c8f43992c8070541d0e3112
3
+ size 2460354912
checkpoint-37460/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d71723f7c9020f1778fd514da18d4f1bcfe0c9e4eae02b6c76f919d0b62ccd
3
+ size 4921030362
checkpoint-37460/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a495a51b0212825f5fbe433eeb5f101f66e80d4f0952ed512b3d7abeeba2a26
3
+ size 14645
checkpoint-37460/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a8f9fb64339c057ba30c43356f8903958a3fe018434ac1be3fc980fe6802a8
3
+ size 1465
checkpoint-37460/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
checkpoint-37460/special_tokens_map.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ace_Arab",
4
+ "ace_Latn",
5
+ "acm_Arab",
6
+ "acq_Arab",
7
+ "aeb_Arab",
8
+ "afr_Latn",
9
+ "ajp_Arab",
10
+ "aka_Latn",
11
+ "amh_Ethi",
12
+ "apc_Arab",
13
+ "arb_Arab",
14
+ "ars_Arab",
15
+ "ary_Arab",
16
+ "arz_Arab",
17
+ "asm_Beng",
18
+ "ast_Latn",
19
+ "awa_Deva",
20
+ "ayr_Latn",
21
+ "azb_Arab",
22
+ "azj_Latn",
23
+ "bak_Cyrl",
24
+ "bam_Latn",
25
+ "ban_Latn",
26
+ "bel_Cyrl",
27
+ "bem_Latn",
28
+ "ben_Beng",
29
+ "bho_Deva",
30
+ "bjn_Arab",
31
+ "bjn_Latn",
32
+ "bod_Tibt",
33
+ "bos_Latn",
34
+ "bug_Latn",
35
+ "bul_Cyrl",
36
+ "cat_Latn",
37
+ "ceb_Latn",
38
+ "ces_Latn",
39
+ "cjk_Latn",
40
+ "ckb_Arab",
41
+ "crh_Latn",
42
+ "cym_Latn",
43
+ "dan_Latn",
44
+ "deu_Latn",
45
+ "dik_Latn",
46
+ "dyu_Latn",
47
+ "dzo_Tibt",
48
+ "ell_Grek",
49
+ "eng_Latn",
50
+ "epo_Latn",
51
+ "est_Latn",
52
+ "eus_Latn",
53
+ "ewe_Latn",
54
+ "fao_Latn",
55
+ "pes_Arab",
56
+ "fij_Latn",
57
+ "fin_Latn",
58
+ "fon_Latn",
59
+ "fra_Latn",
60
+ "fur_Latn",
61
+ "fuv_Latn",
62
+ "gla_Latn",
63
+ "gle_Latn",
64
+ "glg_Latn",
65
+ "grn_Latn",
66
+ "guj_Gujr",
67
+ "hat_Latn",
68
+ "hau_Latn",
69
+ "heb_Hebr",
70
+ "hin_Deva",
71
+ "hne_Deva",
72
+ "hrv_Latn",
73
+ "hun_Latn",
74
+ "hye_Armn",
75
+ "ibo_Latn",
76
+ "ilo_Latn",
77
+ "ind_Latn",
78
+ "isl_Latn",
79
+ "ita_Latn",
80
+ "jav_Latn",
81
+ "jpn_Jpan",
82
+ "kab_Latn",
83
+ "kac_Latn",
84
+ "kam_Latn",
85
+ "kan_Knda",
86
+ "kas_Arab",
87
+ "kas_Deva",
88
+ "kat_Geor",
89
+ "knc_Arab",
90
+ "knc_Latn",
91
+ "kaz_Cyrl",
92
+ "kbp_Latn",
93
+ "kea_Latn",
94
+ "khm_Khmr",
95
+ "kik_Latn",
96
+ "kin_Latn",
97
+ "kir_Cyrl",
98
+ "kmb_Latn",
99
+ "kon_Latn",
100
+ "kor_Hang",
101
+ "kmr_Latn",
102
+ "lao_Laoo",
103
+ "lvs_Latn",
104
+ "lij_Latn",
105
+ "lim_Latn",
106
+ "lin_Latn",
107
+ "lit_Latn",
108
+ "lmo_Latn",
109
+ "ltg_Latn",
110
+ "ltz_Latn",
111
+ "lua_Latn",
112
+ "lug_Latn",
113
+ "luo_Latn",
114
+ "lus_Latn",
115
+ "mag_Deva",
116
+ "mai_Deva",
117
+ "mal_Mlym",
118
+ "mar_Deva",
119
+ "min_Latn",
120
+ "mkd_Cyrl",
121
+ "plt_Latn",
122
+ "mlt_Latn",
123
+ "mni_Beng",
124
+ "khk_Cyrl",
125
+ "mos_Latn",
126
+ "mri_Latn",
127
+ "zsm_Latn",
128
+ "mya_Mymr",
129
+ "nld_Latn",
130
+ "nno_Latn",
131
+ "nob_Latn",
132
+ "npi_Deva",
133
+ "nso_Latn",
134
+ "nus_Latn",
135
+ "nya_Latn",
136
+ "oci_Latn",
137
+ "gaz_Latn",
138
+ "ory_Orya",
139
+ "pag_Latn",
140
+ "pan_Guru",
141
+ "pap_Latn",
142
+ "pol_Latn",
143
+ "por_Latn",
144
+ "prs_Arab",
145
+ "pbt_Arab",
146
+ "quy_Latn",
147
+ "ron_Latn",
148
+ "run_Latn",
149
+ "rus_Cyrl",
150
+ "sag_Latn",
151
+ "san_Deva",
152
+ "sat_Beng",
153
+ "scn_Latn",
154
+ "shn_Mymr",
155
+ "sin_Sinh",
156
+ "slk_Latn",
157
+ "slv_Latn",
158
+ "smo_Latn",
159
+ "sna_Latn",
160
+ "snd_Arab",
161
+ "som_Latn",
162
+ "sot_Latn",
163
+ "spa_Latn",
164
+ "als_Latn",
165
+ "srd_Latn",
166
+ "srp_Cyrl",
167
+ "ssw_Latn",
168
+ "sun_Latn",
169
+ "swe_Latn",
170
+ "swh_Latn",
171
+ "szl_Latn",
172
+ "tam_Taml",
173
+ "tat_Cyrl",
174
+ "tel_Telu",
175
+ "tgk_Cyrl",
176
+ "tgl_Latn",
177
+ "tha_Thai",
178
+ "tir_Ethi",
179
+ "taq_Latn",
180
+ "taq_Tfng",
181
+ "tpi_Latn",
182
+ "tsn_Latn",
183
+ "tso_Latn",
184
+ "tuk_Latn",
185
+ "tum_Latn",
186
+ "tur_Latn",
187
+ "twi_Latn",
188
+ "tzm_Tfng",
189
+ "uig_Arab",
190
+ "ukr_Cyrl",
191
+ "umb_Latn",
192
+ "urd_Arab",
193
+ "uzn_Latn",
194
+ "vec_Latn",
195
+ "vie_Latn",
196
+ "war_Latn",
197
+ "wol_Latn",
198
+ "xho_Latn",
199
+ "ydd_Hebr",
200
+ "yor_Latn",
201
+ "yue_Hant",
202
+ "zho_Hans",
203
+ "zho_Hant",
204
+ "zul_Latn"
205
+ ],
206
+ "bos_token": {
207
+ "content": "<s>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ "cls_token": {
214
+ "content": "<s>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ "eos_token": {
221
+ "content": "</s>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ "mask_token": {
228
+ "content": "<mask>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ "pad_token": {
235
+ "content": "<pad>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ "sep_token": {
242
+ "content": "</s>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ "unk_token": {
249
+ "content": "<unk>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ }
255
+ }
checkpoint-37460/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd897f6e1b43d40640d698f1ed736005d47a08ed8e8e2e389d4b5d60d7892212
3
+ size 32240214
checkpoint-37460/tokenizer_config.json ADDED
@@ -0,0 +1,1879 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "256001": {
36
+ "content": "ace_Arab",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "256002": {
44
+ "content": "ace_Latn",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "256003": {
52
+ "content": "acm_Arab",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "256004": {
60
+ "content": "acq_Arab",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "256005": {
68
+ "content": "aeb_Arab",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "256006": {
76
+ "content": "afr_Latn",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "256007": {
84
+ "content": "ajp_Arab",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "256008": {
92
+ "content": "aka_Latn",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "256009": {
100
+ "content": "amh_Ethi",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "256010": {
108
+ "content": "apc_Arab",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "256011": {
116
+ "content": "arb_Arab",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "256012": {
124
+ "content": "ars_Arab",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "256013": {
132
+ "content": "ary_Arab",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "256014": {
140
+ "content": "arz_Arab",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "256015": {
148
+ "content": "asm_Beng",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "256016": {
156
+ "content": "ast_Latn",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "256017": {
164
+ "content": "awa_Deva",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "256018": {
172
+ "content": "ayr_Latn",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "256019": {
180
+ "content": "azb_Arab",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "256020": {
188
+ "content": "azj_Latn",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "256021": {
196
+ "content": "bak_Cyrl",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "256022": {
204
+ "content": "bam_Latn",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "256023": {
212
+ "content": "ban_Latn",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "256024": {
220
+ "content": "bel_Cyrl",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "256025": {
228
+ "content": "bem_Latn",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "256026": {
236
+ "content": "ben_Beng",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "256027": {
244
+ "content": "bho_Deva",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "256028": {
252
+ "content": "bjn_Arab",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "256029": {
260
+ "content": "bjn_Latn",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "256030": {
268
+ "content": "bod_Tibt",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "256031": {
276
+ "content": "bos_Latn",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "256032": {
284
+ "content": "bug_Latn",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "256033": {
292
+ "content": "bul_Cyrl",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "256034": {
300
+ "content": "cat_Latn",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "256035": {
308
+ "content": "ceb_Latn",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "256036": {
316
+ "content": "ces_Latn",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "256037": {
324
+ "content": "cjk_Latn",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "256038": {
332
+ "content": "ckb_Arab",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "256039": {
340
+ "content": "crh_Latn",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "256040": {
348
+ "content": "cym_Latn",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "256041": {
356
+ "content": "dan_Latn",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "256042": {
364
+ "content": "deu_Latn",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "256043": {
372
+ "content": "dik_Latn",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "256044": {
380
+ "content": "dyu_Latn",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "256045": {
388
+ "content": "dzo_Tibt",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "256046": {
396
+ "content": "ell_Grek",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "256047": {
404
+ "content": "eng_Latn",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "256048": {
412
+ "content": "epo_Latn",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "256049": {
420
+ "content": "est_Latn",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "256050": {
428
+ "content": "eus_Latn",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "256051": {
436
+ "content": "ewe_Latn",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "256052": {
444
+ "content": "fao_Latn",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "256053": {
452
+ "content": "pes_Arab",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "256054": {
460
+ "content": "fij_Latn",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "256055": {
468
+ "content": "fin_Latn",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "256056": {
476
+ "content": "fon_Latn",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "256057": {
484
+ "content": "fra_Latn",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "256058": {
492
+ "content": "fur_Latn",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "256059": {
500
+ "content": "fuv_Latn",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "256060": {
508
+ "content": "gla_Latn",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "256061": {
516
+ "content": "gle_Latn",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "256062": {
524
+ "content": "glg_Latn",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "256063": {
532
+ "content": "grn_Latn",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "256064": {
540
+ "content": "guj_Gujr",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "256065": {
548
+ "content": "hat_Latn",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "256066": {
556
+ "content": "hau_Latn",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "256067": {
564
+ "content": "heb_Hebr",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "256068": {
572
+ "content": "hin_Deva",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "256069": {
580
+ "content": "hne_Deva",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "256070": {
588
+ "content": "hrv_Latn",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "256071": {
596
+ "content": "hun_Latn",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "256072": {
604
+ "content": "hye_Armn",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "256073": {
612
+ "content": "ibo_Latn",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "256074": {
620
+ "content": "ilo_Latn",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "256075": {
628
+ "content": "ind_Latn",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "256076": {
636
+ "content": "isl_Latn",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "256077": {
644
+ "content": "ita_Latn",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "256078": {
652
+ "content": "jav_Latn",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "256079": {
660
+ "content": "jpn_Jpan",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "256080": {
668
+ "content": "kab_Latn",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "256081": {
676
+ "content": "kac_Latn",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "256082": {
684
+ "content": "kam_Latn",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "256083": {
692
+ "content": "kan_Knda",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "256084": {
700
+ "content": "kas_Arab",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "256085": {
708
+ "content": "kas_Deva",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "256086": {
716
+ "content": "kat_Geor",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "256087": {
724
+ "content": "knc_Arab",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "256088": {
732
+ "content": "knc_Latn",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "256089": {
740
+ "content": "kaz_Cyrl",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "256090": {
748
+ "content": "kbp_Latn",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "256091": {
756
+ "content": "kea_Latn",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "256092": {
764
+ "content": "khm_Khmr",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "256093": {
772
+ "content": "kik_Latn",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "256094": {
780
+ "content": "kin_Latn",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "256095": {
788
+ "content": "kir_Cyrl",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "256096": {
796
+ "content": "kmb_Latn",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "256097": {
804
+ "content": "kon_Latn",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "256098": {
812
+ "content": "kor_Hang",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "256099": {
820
+ "content": "kmr_Latn",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "256100": {
828
+ "content": "lao_Laoo",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "256101": {
836
+ "content": "lvs_Latn",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "256102": {
844
+ "content": "lij_Latn",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "256103": {
852
+ "content": "lim_Latn",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "256104": {
860
+ "content": "lin_Latn",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "256105": {
868
+ "content": "lit_Latn",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "256106": {
876
+ "content": "lmo_Latn",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "256107": {
884
+ "content": "ltg_Latn",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "256108": {
892
+ "content": "ltz_Latn",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "256109": {
900
+ "content": "lua_Latn",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "256110": {
908
+ "content": "lug_Latn",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "256111": {
916
+ "content": "luo_Latn",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "256112": {
924
+ "content": "lus_Latn",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "256113": {
932
+ "content": "mag_Deva",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "256114": {
940
+ "content": "mai_Deva",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "256115": {
948
+ "content": "mal_Mlym",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "256116": {
956
+ "content": "mar_Deva",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "256117": {
964
+ "content": "min_Latn",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "256118": {
972
+ "content": "mkd_Cyrl",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "256119": {
980
+ "content": "plt_Latn",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "256120": {
988
+ "content": "mlt_Latn",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "256121": {
996
+ "content": "mni_Beng",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "256122": {
1004
+ "content": "khk_Cyrl",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "256123": {
1012
+ "content": "mos_Latn",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "256124": {
1020
+ "content": "mri_Latn",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "256125": {
1028
+ "content": "zsm_Latn",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "256126": {
1036
+ "content": "mya_Mymr",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "256127": {
1044
+ "content": "nld_Latn",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "256128": {
1052
+ "content": "nno_Latn",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "256129": {
1060
+ "content": "nob_Latn",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "256130": {
1068
+ "content": "npi_Deva",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "256131": {
1076
+ "content": "nso_Latn",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "256132": {
1084
+ "content": "nus_Latn",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "256133": {
1092
+ "content": "nya_Latn",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "256134": {
1100
+ "content": "oci_Latn",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "256135": {
1108
+ "content": "gaz_Latn",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "256136": {
1116
+ "content": "ory_Orya",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "256137": {
1124
+ "content": "pag_Latn",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "256138": {
1132
+ "content": "pan_Guru",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "256139": {
1140
+ "content": "pap_Latn",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "256140": {
1148
+ "content": "pol_Latn",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "256141": {
1156
+ "content": "por_Latn",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "256142": {
1164
+ "content": "prs_Arab",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "256143": {
1172
+ "content": "pbt_Arab",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "256144": {
1180
+ "content": "quy_Latn",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "256145": {
1188
+ "content": "ron_Latn",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "256146": {
1196
+ "content": "run_Latn",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "256147": {
1204
+ "content": "rus_Cyrl",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "256148": {
1212
+ "content": "sag_Latn",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "256149": {
1220
+ "content": "san_Deva",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "256150": {
1228
+ "content": "sat_Beng",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "256151": {
1236
+ "content": "scn_Latn",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "256152": {
1244
+ "content": "shn_Mymr",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "256153": {
1252
+ "content": "sin_Sinh",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "256154": {
1260
+ "content": "slk_Latn",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "256155": {
1268
+ "content": "slv_Latn",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "256156": {
1276
+ "content": "smo_Latn",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "256157": {
1284
+ "content": "sna_Latn",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "256158": {
1292
+ "content": "snd_Arab",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "256159": {
1300
+ "content": "som_Latn",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "256160": {
1308
+ "content": "sot_Latn",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "256161": {
1316
+ "content": "spa_Latn",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "256162": {
1324
+ "content": "als_Latn",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "256163": {
1332
+ "content": "srd_Latn",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "256164": {
1340
+ "content": "srp_Cyrl",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "256165": {
1348
+ "content": "ssw_Latn",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "256166": {
1356
+ "content": "sun_Latn",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "256167": {
1364
+ "content": "swe_Latn",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "256168": {
1372
+ "content": "swh_Latn",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "256169": {
1380
+ "content": "szl_Latn",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "256170": {
1388
+ "content": "tam_Taml",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "256171": {
1396
+ "content": "tat_Cyrl",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "256172": {
1404
+ "content": "tel_Telu",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "256173": {
1412
+ "content": "tgk_Cyrl",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "256174": {
1420
+ "content": "tgl_Latn",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "256175": {
1428
+ "content": "tha_Thai",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "256176": {
1436
+ "content": "tir_Ethi",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "256177": {
1444
+ "content": "taq_Latn",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "256178": {
1452
+ "content": "taq_Tfng",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "256179": {
1460
+ "content": "tpi_Latn",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "256180": {
1468
+ "content": "tsn_Latn",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "256181": {
1476
+ "content": "tso_Latn",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "256182": {
1484
+ "content": "tuk_Latn",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "256183": {
1492
+ "content": "tum_Latn",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "256184": {
1500
+ "content": "tur_Latn",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "256185": {
1508
+ "content": "twi_Latn",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "256186": {
1516
+ "content": "tzm_Tfng",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "256187": {
1524
+ "content": "uig_Arab",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "256188": {
1532
+ "content": "ukr_Cyrl",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "256189": {
1540
+ "content": "umb_Latn",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "256190": {
1548
+ "content": "urd_Arab",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "256191": {
1556
+ "content": "uzn_Latn",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "256192": {
1564
+ "content": "vec_Latn",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "256193": {
1572
+ "content": "vie_Latn",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "256194": {
1580
+ "content": "war_Latn",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "256195": {
1588
+ "content": "wol_Latn",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "256196": {
1596
+ "content": "xho_Latn",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "256197": {
1604
+ "content": "ydd_Hebr",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "256198": {
1612
+ "content": "yor_Latn",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "256199": {
1620
+ "content": "yue_Hant",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "256200": {
1628
+ "content": "zho_Hans",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "256201": {
1636
+ "content": "zho_Hant",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "256202": {
1644
+ "content": "zul_Latn",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "256203": {
1652
+ "content": "<mask>",
1653
+ "lstrip": true,
1654
+ "normalized": true,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ }
1659
+ },
1660
+ "additional_special_tokens": [
1661
+ "ace_Arab",
1662
+ "ace_Latn",
1663
+ "acm_Arab",
1664
+ "acq_Arab",
1665
+ "aeb_Arab",
1666
+ "afr_Latn",
1667
+ "ajp_Arab",
1668
+ "aka_Latn",
1669
+ "amh_Ethi",
1670
+ "apc_Arab",
1671
+ "arb_Arab",
1672
+ "ars_Arab",
1673
+ "ary_Arab",
1674
+ "arz_Arab",
1675
+ "asm_Beng",
1676
+ "ast_Latn",
1677
+ "awa_Deva",
1678
+ "ayr_Latn",
1679
+ "azb_Arab",
1680
+ "azj_Latn",
1681
+ "bak_Cyrl",
1682
+ "bam_Latn",
1683
+ "ban_Latn",
1684
+ "bel_Cyrl",
1685
+ "bem_Latn",
1686
+ "ben_Beng",
1687
+ "bho_Deva",
1688
+ "bjn_Arab",
1689
+ "bjn_Latn",
1690
+ "bod_Tibt",
1691
+ "bos_Latn",
1692
+ "bug_Latn",
1693
+ "bul_Cyrl",
1694
+ "cat_Latn",
1695
+ "ceb_Latn",
1696
+ "ces_Latn",
1697
+ "cjk_Latn",
1698
+ "ckb_Arab",
1699
+ "crh_Latn",
1700
+ "cym_Latn",
1701
+ "dan_Latn",
1702
+ "deu_Latn",
1703
+ "dik_Latn",
1704
+ "dyu_Latn",
1705
+ "dzo_Tibt",
1706
+ "ell_Grek",
1707
+ "eng_Latn",
1708
+ "epo_Latn",
1709
+ "est_Latn",
1710
+ "eus_Latn",
1711
+ "ewe_Latn",
1712
+ "fao_Latn",
1713
+ "pes_Arab",
1714
+ "fij_Latn",
1715
+ "fin_Latn",
1716
+ "fon_Latn",
1717
+ "fra_Latn",
1718
+ "fur_Latn",
1719
+ "fuv_Latn",
1720
+ "gla_Latn",
1721
+ "gle_Latn",
1722
+ "glg_Latn",
1723
+ "grn_Latn",
1724
+ "guj_Gujr",
1725
+ "hat_Latn",
1726
+ "hau_Latn",
1727
+ "heb_Hebr",
1728
+ "hin_Deva",
1729
+ "hne_Deva",
1730
+ "hrv_Latn",
1731
+ "hun_Latn",
1732
+ "hye_Armn",
1733
+ "ibo_Latn",
1734
+ "ilo_Latn",
1735
+ "ind_Latn",
1736
+ "isl_Latn",
1737
+ "ita_Latn",
1738
+ "jav_Latn",
1739
+ "jpn_Jpan",
1740
+ "kab_Latn",
1741
+ "kac_Latn",
1742
+ "kam_Latn",
1743
+ "kan_Knda",
1744
+ "kas_Arab",
1745
+ "kas_Deva",
1746
+ "kat_Geor",
1747
+ "knc_Arab",
1748
+ "knc_Latn",
1749
+ "kaz_Cyrl",
1750
+ "kbp_Latn",
1751
+ "kea_Latn",
1752
+ "khm_Khmr",
1753
+ "kik_Latn",
1754
+ "kin_Latn",
1755
+ "kir_Cyrl",
1756
+ "kmb_Latn",
1757
+ "kon_Latn",
1758
+ "kor_Hang",
1759
+ "kmr_Latn",
1760
+ "lao_Laoo",
1761
+ "lvs_Latn",
1762
+ "lij_Latn",
1763
+ "lim_Latn",
1764
+ "lin_Latn",
1765
+ "lit_Latn",
1766
+ "lmo_Latn",
1767
+ "ltg_Latn",
1768
+ "ltz_Latn",
1769
+ "lua_Latn",
1770
+ "lug_Latn",
1771
+ "luo_Latn",
1772
+ "lus_Latn",
1773
+ "mag_Deva",
1774
+ "mai_Deva",
1775
+ "mal_Mlym",
1776
+ "mar_Deva",
1777
+ "min_Latn",
1778
+ "mkd_Cyrl",
1779
+ "plt_Latn",
1780
+ "mlt_Latn",
1781
+ "mni_Beng",
1782
+ "khk_Cyrl",
1783
+ "mos_Latn",
1784
+ "mri_Latn",
1785
+ "zsm_Latn",
1786
+ "mya_Mymr",
1787
+ "nld_Latn",
1788
+ "nno_Latn",
1789
+ "nob_Latn",
1790
+ "npi_Deva",
1791
+ "nso_Latn",
1792
+ "nus_Latn",
1793
+ "nya_Latn",
1794
+ "oci_Latn",
1795
+ "gaz_Latn",
1796
+ "ory_Orya",
1797
+ "pag_Latn",
1798
+ "pan_Guru",
1799
+ "pap_Latn",
1800
+ "pol_Latn",
1801
+ "por_Latn",
1802
+ "prs_Arab",
1803
+ "pbt_Arab",
1804
+ "quy_Latn",
1805
+ "ron_Latn",
1806
+ "run_Latn",
1807
+ "rus_Cyrl",
1808
+ "sag_Latn",
1809
+ "san_Deva",
1810
+ "sat_Beng",
1811
+ "scn_Latn",
1812
+ "shn_Mymr",
1813
+ "sin_Sinh",
1814
+ "slk_Latn",
1815
+ "slv_Latn",
1816
+ "smo_Latn",
1817
+ "sna_Latn",
1818
+ "snd_Arab",
1819
+ "som_Latn",
1820
+ "sot_Latn",
1821
+ "spa_Latn",
1822
+ "als_Latn",
1823
+ "srd_Latn",
1824
+ "srp_Cyrl",
1825
+ "ssw_Latn",
1826
+ "sun_Latn",
1827
+ "swe_Latn",
1828
+ "swh_Latn",
1829
+ "szl_Latn",
1830
+ "tam_Taml",
1831
+ "tat_Cyrl",
1832
+ "tel_Telu",
1833
+ "tgk_Cyrl",
1834
+ "tgl_Latn",
1835
+ "tha_Thai",
1836
+ "tir_Ethi",
1837
+ "taq_Latn",
1838
+ "taq_Tfng",
1839
+ "tpi_Latn",
1840
+ "tsn_Latn",
1841
+ "tso_Latn",
1842
+ "tuk_Latn",
1843
+ "tum_Latn",
1844
+ "tur_Latn",
1845
+ "twi_Latn",
1846
+ "tzm_Tfng",
1847
+ "uig_Arab",
1848
+ "ukr_Cyrl",
1849
+ "umb_Latn",
1850
+ "urd_Arab",
1851
+ "uzn_Latn",
1852
+ "vec_Latn",
1853
+ "vie_Latn",
1854
+ "war_Latn",
1855
+ "wol_Latn",
1856
+ "xho_Latn",
1857
+ "ydd_Hebr",
1858
+ "yor_Latn",
1859
+ "yue_Hant",
1860
+ "zho_Hans",
1861
+ "zho_Hant",
1862
+ "zul_Latn"
1863
+ ],
1864
+ "bos_token": "<s>",
1865
+ "clean_up_tokenization_spaces": false,
1866
+ "cls_token": "<s>",
1867
+ "eos_token": "</s>",
1868
+ "extra_special_tokens": {},
1869
+ "legacy_behaviour": false,
1870
+ "mask_token": "<mask>",
1871
+ "model_max_length": 1024,
1872
+ "pad_token": "<pad>",
1873
+ "sep_token": "</s>",
1874
+ "sp_model_kwargs": {},
1875
+ "src_lang": "kan_Deva",
1876
+ "tgt_lang": "hin_Deva",
1877
+ "tokenizer_class": "NllbTokenizer",
1878
+ "unk_token": "<unk>"
1879
+ }
checkpoint-37460/trainer_state.json ADDED
@@ -0,0 +1,552 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 37460,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13347570742124934,
14
+ "grad_norm": 3.1176345348358154,
15
+ "learning_rate": 4.933395621996797e-05,
16
+ "loss": 1.6549,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.2669514148424987,
21
+ "grad_norm": 2.8823812007904053,
22
+ "learning_rate": 4.866657768286172e-05,
23
+ "loss": 1.3869,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.400427122263748,
28
+ "grad_norm": 3.436349630355835,
29
+ "learning_rate": 4.7999199145755475e-05,
30
+ "loss": 1.31,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.5339028296849974,
35
+ "grad_norm": 2.7581417560577393,
36
+ "learning_rate": 4.733182060864923e-05,
37
+ "loss": 1.2632,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.6673785371062466,
42
+ "grad_norm": 3.0282974243164062,
43
+ "learning_rate": 4.666444207154298e-05,
44
+ "loss": 1.2197,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.800854244527496,
49
+ "grad_norm": 2.7351794242858887,
50
+ "learning_rate": 4.599706353443674e-05,
51
+ "loss": 1.1942,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.9343299519487454,
56
+ "grad_norm": 2.228116035461426,
57
+ "learning_rate": 4.532968499733049e-05,
58
+ "loss": 1.1273,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.0678056593699947,
63
+ "grad_norm": 3.064039707183838,
64
+ "learning_rate": 4.466230646022424e-05,
65
+ "loss": 1.0261,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.201281366791244,
70
+ "grad_norm": 2.9547019004821777,
71
+ "learning_rate": 4.3994927923117995e-05,
72
+ "loss": 0.9262,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.3347570742124932,
77
+ "grad_norm": 2.8099584579467773,
78
+ "learning_rate": 4.332754938601175e-05,
79
+ "loss": 0.9193,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.4682327816337426,
84
+ "grad_norm": 2.4523322582244873,
85
+ "learning_rate": 4.26601708489055e-05,
86
+ "loss": 0.939,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.601708489054992,
91
+ "grad_norm": 2.4100770950317383,
92
+ "learning_rate": 4.199279231179926e-05,
93
+ "loss": 0.9084,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.7351841964762413,
98
+ "grad_norm": 2.4628851413726807,
99
+ "learning_rate": 4.1325413774693004e-05,
100
+ "loss": 0.9303,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 1.8686599038974907,
105
+ "grad_norm": 2.522763967514038,
106
+ "learning_rate": 4.0658035237586763e-05,
107
+ "loss": 0.8988,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 2.00213561131874,
112
+ "grad_norm": 1.8565527200698853,
113
+ "learning_rate": 3.9990656700480516e-05,
114
+ "loss": 0.9408,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 2.1356113187399894,
119
+ "grad_norm": 3.084707498550415,
120
+ "learning_rate": 3.932327816337427e-05,
121
+ "loss": 0.7548,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 2.269087026161239,
126
+ "grad_norm": 1.836754322052002,
127
+ "learning_rate": 3.865589962626802e-05,
128
+ "loss": 0.7447,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 2.402562733582488,
133
+ "grad_norm": 2.452847719192505,
134
+ "learning_rate": 3.798852108916178e-05,
135
+ "loss": 0.7293,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 2.536038441003737,
140
+ "grad_norm": 3.363875150680542,
141
+ "learning_rate": 3.7321142552055525e-05,
142
+ "loss": 0.7437,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 2.6695141484249865,
147
+ "grad_norm": 2.087559700012207,
148
+ "learning_rate": 3.6653764014949284e-05,
149
+ "loss": 0.7217,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 2.802989855846236,
154
+ "grad_norm": 2.1554408073425293,
155
+ "learning_rate": 3.598638547784303e-05,
156
+ "loss": 0.7459,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 2.936465563267485,
161
+ "grad_norm": 1.8922470808029175,
162
+ "learning_rate": 3.531900694073679e-05,
163
+ "loss": 0.7586,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 3.0699412706887346,
168
+ "grad_norm": 2.0937387943267822,
169
+ "learning_rate": 3.465162840363054e-05,
170
+ "loss": 0.6552,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 3.203416978109984,
175
+ "grad_norm": 2.954742908477783,
176
+ "learning_rate": 3.398424986652429e-05,
177
+ "loss": 0.6012,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 3.3368926855312333,
182
+ "grad_norm": 2.8236591815948486,
183
+ "learning_rate": 3.3316871329418045e-05,
184
+ "loss": 0.607,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 3.4703683929524827,
189
+ "grad_norm": 2.4959943294525146,
190
+ "learning_rate": 3.2649492792311804e-05,
191
+ "loss": 0.6181,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 3.603844100373732,
196
+ "grad_norm": 3.4247825145721436,
197
+ "learning_rate": 3.198211425520555e-05,
198
+ "loss": 0.6029,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 3.7373198077949814,
203
+ "grad_norm": 2.6698663234710693,
204
+ "learning_rate": 3.131473571809931e-05,
205
+ "loss": 0.6032,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 3.8707955152162308,
210
+ "grad_norm": 1.9999539852142334,
211
+ "learning_rate": 3.064735718099306e-05,
212
+ "loss": 0.6241,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 4.00427122263748,
217
+ "grad_norm": 2.449364185333252,
218
+ "learning_rate": 2.9979978643886814e-05,
219
+ "loss": 0.6183,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 4.1377469300587295,
224
+ "grad_norm": 4.328239917755127,
225
+ "learning_rate": 2.931260010678057e-05,
226
+ "loss": 0.4832,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 4.271222637479979,
231
+ "grad_norm": 1.9375187158584595,
232
+ "learning_rate": 2.8645221569674318e-05,
233
+ "loss": 0.4963,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 4.404698344901228,
238
+ "grad_norm": 2.9625084400177,
239
+ "learning_rate": 2.7977843032568074e-05,
240
+ "loss": 0.5162,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 4.538174052322478,
245
+ "grad_norm": 3.514462947845459,
246
+ "learning_rate": 2.731046449546183e-05,
247
+ "loss": 0.4913,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 4.671649759743727,
252
+ "grad_norm": 2.035665988922119,
253
+ "learning_rate": 2.664308595835558e-05,
254
+ "loss": 0.5062,
255
+ "step": 17500
256
+ },
257
+ {
258
+ "epoch": 4.805125467164976,
259
+ "grad_norm": 3.025426149368286,
260
+ "learning_rate": 2.5975707421249334e-05,
261
+ "loss": 0.5167,
262
+ "step": 18000
263
+ },
264
+ {
265
+ "epoch": 4.938601174586225,
266
+ "grad_norm": 3.0361483097076416,
267
+ "learning_rate": 2.530832888414309e-05,
268
+ "loss": 0.4961,
269
+ "step": 18500
270
+ },
271
+ {
272
+ "epoch": 5.072076882007474,
273
+ "grad_norm": 2.769930124282837,
274
+ "learning_rate": 2.464095034703684e-05,
275
+ "loss": 0.4582,
276
+ "step": 19000
277
+ },
278
+ {
279
+ "epoch": 5.205552589428724,
280
+ "grad_norm": 2.209397077560425,
281
+ "learning_rate": 2.3973571809930594e-05,
282
+ "loss": 0.3926,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 5.339028296849973,
287
+ "grad_norm": 2.680094003677368,
288
+ "learning_rate": 2.3306193272824347e-05,
289
+ "loss": 0.4187,
290
+ "step": 20000
291
+ },
292
+ {
293
+ "epoch": 5.472504004271222,
294
+ "grad_norm": 2.425154447555542,
295
+ "learning_rate": 2.26388147357181e-05,
296
+ "loss": 0.4182,
297
+ "step": 20500
298
+ },
299
+ {
300
+ "epoch": 5.605979711692472,
301
+ "grad_norm": 4.719789505004883,
302
+ "learning_rate": 2.197143619861185e-05,
303
+ "loss": 0.4257,
304
+ "step": 21000
305
+ },
306
+ {
307
+ "epoch": 5.739455419113721,
308
+ "grad_norm": 1.3763984441757202,
309
+ "learning_rate": 2.1304057661505607e-05,
310
+ "loss": 0.4222,
311
+ "step": 21500
312
+ },
313
+ {
314
+ "epoch": 5.87293112653497,
315
+ "grad_norm": 2.8332626819610596,
316
+ "learning_rate": 2.063667912439936e-05,
317
+ "loss": 0.4247,
318
+ "step": 22000
319
+ },
320
+ {
321
+ "epoch": 6.00640683395622,
322
+ "grad_norm": 1.990326166152954,
323
+ "learning_rate": 1.996930058729311e-05,
324
+ "loss": 0.4149,
325
+ "step": 22500
326
+ },
327
+ {
328
+ "epoch": 6.139882541377469,
329
+ "grad_norm": 1.9501370191574097,
330
+ "learning_rate": 1.9301922050186867e-05,
331
+ "loss": 0.3451,
332
+ "step": 23000
333
+ },
334
+ {
335
+ "epoch": 6.2733582487987185,
336
+ "grad_norm": 2.518463611602783,
337
+ "learning_rate": 1.863454351308062e-05,
338
+ "loss": 0.3338,
339
+ "step": 23500
340
+ },
341
+ {
342
+ "epoch": 6.406833956219968,
343
+ "grad_norm": 2.567760705947876,
344
+ "learning_rate": 1.7967164975974375e-05,
345
+ "loss": 0.3537,
346
+ "step": 24000
347
+ },
348
+ {
349
+ "epoch": 6.540309663641217,
350
+ "grad_norm": 3.4953105449676514,
351
+ "learning_rate": 1.7299786438868128e-05,
352
+ "loss": 0.3463,
353
+ "step": 24500
354
+ },
355
+ {
356
+ "epoch": 6.673785371062467,
357
+ "grad_norm": 4.280869007110596,
358
+ "learning_rate": 1.663240790176188e-05,
359
+ "loss": 0.3794,
360
+ "step": 25000
361
+ },
362
+ {
363
+ "epoch": 6.807261078483716,
364
+ "grad_norm": 1.3708416223526,
365
+ "learning_rate": 1.5965029364655636e-05,
366
+ "loss": 0.3595,
367
+ "step": 25500
368
+ },
369
+ {
370
+ "epoch": 6.940736785904965,
371
+ "grad_norm": 1.9402921199798584,
372
+ "learning_rate": 1.5297650827549388e-05,
373
+ "loss": 0.3567,
374
+ "step": 26000
375
+ },
376
+ {
377
+ "epoch": 7.074212493326215,
378
+ "grad_norm": 3.4459097385406494,
379
+ "learning_rate": 1.463027229044314e-05,
380
+ "loss": 0.3271,
381
+ "step": 26500
382
+ },
383
+ {
384
+ "epoch": 7.207688200747464,
385
+ "grad_norm": 3.0598597526550293,
386
+ "learning_rate": 1.3962893753336892e-05,
387
+ "loss": 0.3053,
388
+ "step": 27000
389
+ },
390
+ {
391
+ "epoch": 7.3411639081687134,
392
+ "grad_norm": 1.887160062789917,
393
+ "learning_rate": 1.3295515216230648e-05,
394
+ "loss": 0.2941,
395
+ "step": 27500
396
+ },
397
+ {
398
+ "epoch": 7.474639615589963,
399
+ "grad_norm": 2.143535852432251,
400
+ "learning_rate": 1.26281366791244e-05,
401
+ "loss": 0.2981,
402
+ "step": 28000
403
+ },
404
+ {
405
+ "epoch": 7.608115323011212,
406
+ "grad_norm": 4.371819019317627,
407
+ "learning_rate": 1.1960758142018154e-05,
408
+ "loss": 0.2986,
409
+ "step": 28500
410
+ },
411
+ {
412
+ "epoch": 7.7415910304324616,
413
+ "grad_norm": 3.378239631652832,
414
+ "learning_rate": 1.1293379604911907e-05,
415
+ "loss": 0.305,
416
+ "step": 29000
417
+ },
418
+ {
419
+ "epoch": 7.875066737853711,
420
+ "grad_norm": 2.8271336555480957,
421
+ "learning_rate": 1.062600106780566e-05,
422
+ "loss": 0.3193,
423
+ "step": 29500
424
+ },
425
+ {
426
+ "epoch": 8.00854244527496,
427
+ "grad_norm": 2.825468063354492,
428
+ "learning_rate": 9.958622530699413e-06,
429
+ "loss": 0.3004,
430
+ "step": 30000
431
+ },
432
+ {
433
+ "epoch": 8.14201815269621,
434
+ "grad_norm": 2.4525914192199707,
435
+ "learning_rate": 9.291243993593167e-06,
436
+ "loss": 0.2669,
437
+ "step": 30500
438
+ },
439
+ {
440
+ "epoch": 8.275493860117459,
441
+ "grad_norm": 4.695706844329834,
442
+ "learning_rate": 8.62386545648692e-06,
443
+ "loss": 0.2737,
444
+ "step": 31000
445
+ },
446
+ {
447
+ "epoch": 8.408969567538708,
448
+ "grad_norm": 3.336611270904541,
449
+ "learning_rate": 7.956486919380673e-06,
450
+ "loss": 0.2697,
451
+ "step": 31500
452
+ },
453
+ {
454
+ "epoch": 8.542445274959958,
455
+ "grad_norm": 3.6071436405181885,
456
+ "learning_rate": 7.289108382274426e-06,
457
+ "loss": 0.2644,
458
+ "step": 32000
459
+ },
460
+ {
461
+ "epoch": 8.675920982381207,
462
+ "grad_norm": 3.1964738368988037,
463
+ "learning_rate": 6.62172984516818e-06,
464
+ "loss": 0.2669,
465
+ "step": 32500
466
+ },
467
+ {
468
+ "epoch": 8.809396689802456,
469
+ "grad_norm": 2.115790843963623,
470
+ "learning_rate": 5.9543513080619334e-06,
471
+ "loss": 0.2638,
472
+ "step": 33000
473
+ },
474
+ {
475
+ "epoch": 8.942872397223706,
476
+ "grad_norm": 1.7221794128417969,
477
+ "learning_rate": 5.286972770955687e-06,
478
+ "loss": 0.282,
479
+ "step": 33500
480
+ },
481
+ {
482
+ "epoch": 9.076348104644955,
483
+ "grad_norm": 2.4076969623565674,
484
+ "learning_rate": 4.61959423384944e-06,
485
+ "loss": 0.2601,
486
+ "step": 34000
487
+ },
488
+ {
489
+ "epoch": 9.209823812066205,
490
+ "grad_norm": 1.874233603477478,
491
+ "learning_rate": 3.952215696743193e-06,
492
+ "loss": 0.2474,
493
+ "step": 34500
494
+ },
495
+ {
496
+ "epoch": 9.343299519487454,
497
+ "grad_norm": 2.8450875282287598,
498
+ "learning_rate": 3.2848371596369464e-06,
499
+ "loss": 0.2405,
500
+ "step": 35000
501
+ },
502
+ {
503
+ "epoch": 9.476775226908703,
504
+ "grad_norm": 2.4307425022125244,
505
+ "learning_rate": 2.6174586225306996e-06,
506
+ "loss": 0.244,
507
+ "step": 35500
508
+ },
509
+ {
510
+ "epoch": 9.610250934329953,
511
+ "grad_norm": 1.2817405462265015,
512
+ "learning_rate": 1.9500800854244527e-06,
513
+ "loss": 0.2457,
514
+ "step": 36000
515
+ },
516
+ {
517
+ "epoch": 9.743726641751202,
518
+ "grad_norm": 2.613475799560547,
519
+ "learning_rate": 1.282701548318206e-06,
520
+ "loss": 0.2446,
521
+ "step": 36500
522
+ },
523
+ {
524
+ "epoch": 9.877202349172451,
525
+ "grad_norm": 1.7706152200698853,
526
+ "learning_rate": 6.153230112119594e-07,
527
+ "loss": 0.2464,
528
+ "step": 37000
529
+ }
530
+ ],
531
+ "logging_steps": 500,
532
+ "max_steps": 37460,
533
+ "num_input_tokens_seen": 0,
534
+ "num_train_epochs": 10,
535
+ "save_steps": 10000,
536
+ "stateful_callbacks": {
537
+ "TrainerControl": {
538
+ "args": {
539
+ "should_epoch_stop": false,
540
+ "should_evaluate": false,
541
+ "should_log": false,
542
+ "should_save": true,
543
+ "should_training_stop": true
544
+ },
545
+ "attributes": {}
546
+ }
547
+ },
548
+ "total_flos": 1.5022851621224448e+16,
549
+ "train_batch_size": 4,
550
+ "trial_name": null,
551
+ "trial_params": null
552
+ }
checkpoint-37460/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a28c287e6a8ecc8bf8b81de0d0de1e07fac49ed361faad102304759b8b3544
3
+ size 5905
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "relu",
4
+ "architectures": [
5
+ "M2M100ForConditionalGeneration"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 0,
9
+ "d_model": 1024,
10
+ "decoder_attention_heads": 16,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0,
13
+ "decoder_layers": 12,
14
+ "decoder_start_token_id": 2,
15
+ "dropout": 0.1,
16
+ "encoder_attention_heads": 16,
17
+ "encoder_ffn_dim": 4096,
18
+ "encoder_layerdrop": 0,
19
+ "encoder_layers": 12,
20
+ "eos_token_id": 2,
21
+ "init_std": 0.02,
22
+ "is_encoder_decoder": true,
23
+ "max_length": null,
24
+ "max_position_embeddings": 1024,
25
+ "model_type": "m2m_100",
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 1,
28
+ "scale_embedding": true,
29
+ "tokenizer_class": "NllbTokenizer",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.54.0.dev0",
32
+ "use_cache": true,
33
+ "vocab_size": 256206
34
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_bleu": 43.1563,
4
+ "eval_chrf": 71.5797,
5
+ "eval_gen_len": 24.5884,
6
+ "eval_loss": 1.1433292627334595,
7
+ "eval_runtime": 357.9909,
8
+ "eval_samples": 1873,
9
+ "eval_samples_per_second": 5.232,
10
+ "eval_steps_per_second": 1.31
11
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
generation_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "forced_bos_token_id": 256068,
7
+ "max_length": 200,
8
+ "pad_token_id": 1,
9
+ "transformers_version": "4.54.0.dev0"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85637fa1e094799e84b5acec70617c4215a8e1119c8f43992c8070541d0e3112
3
+ size 2460354912
predict_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 42.4892,
3
+ "predict_chrf": 71.0352,
4
+ "predict_gen_len": 24.7318,
5
+ "predict_loss": 1.173148274421692,
6
+ "predict_runtime": 367.2146,
7
+ "predict_samples": 1872,
8
+ "predict_samples_per_second": 5.098,
9
+ "predict_steps_per_second": 1.274
10
+ }
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14bb8dfb35c0ffdea7bc01e56cea38b9e3d5efcdcb9c251d6b40538e1aab555a
3
+ size 4852054
special_tokens_map.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ace_Arab",
4
+ "ace_Latn",
5
+ "acm_Arab",
6
+ "acq_Arab",
7
+ "aeb_Arab",
8
+ "afr_Latn",
9
+ "ajp_Arab",
10
+ "aka_Latn",
11
+ "amh_Ethi",
12
+ "apc_Arab",
13
+ "arb_Arab",
14
+ "ars_Arab",
15
+ "ary_Arab",
16
+ "arz_Arab",
17
+ "asm_Beng",
18
+ "ast_Latn",
19
+ "awa_Deva",
20
+ "ayr_Latn",
21
+ "azb_Arab",
22
+ "azj_Latn",
23
+ "bak_Cyrl",
24
+ "bam_Latn",
25
+ "ban_Latn",
26
+ "bel_Cyrl",
27
+ "bem_Latn",
28
+ "ben_Beng",
29
+ "bho_Deva",
30
+ "bjn_Arab",
31
+ "bjn_Latn",
32
+ "bod_Tibt",
33
+ "bos_Latn",
34
+ "bug_Latn",
35
+ "bul_Cyrl",
36
+ "cat_Latn",
37
+ "ceb_Latn",
38
+ "ces_Latn",
39
+ "cjk_Latn",
40
+ "ckb_Arab",
41
+ "crh_Latn",
42
+ "cym_Latn",
43
+ "dan_Latn",
44
+ "deu_Latn",
45
+ "dik_Latn",
46
+ "dyu_Latn",
47
+ "dzo_Tibt",
48
+ "ell_Grek",
49
+ "eng_Latn",
50
+ "epo_Latn",
51
+ "est_Latn",
52
+ "eus_Latn",
53
+ "ewe_Latn",
54
+ "fao_Latn",
55
+ "pes_Arab",
56
+ "fij_Latn",
57
+ "fin_Latn",
58
+ "fon_Latn",
59
+ "fra_Latn",
60
+ "fur_Latn",
61
+ "fuv_Latn",
62
+ "gla_Latn",
63
+ "gle_Latn",
64
+ "glg_Latn",
65
+ "grn_Latn",
66
+ "guj_Gujr",
67
+ "hat_Latn",
68
+ "hau_Latn",
69
+ "heb_Hebr",
70
+ "hin_Deva",
71
+ "hne_Deva",
72
+ "hrv_Latn",
73
+ "hun_Latn",
74
+ "hye_Armn",
75
+ "ibo_Latn",
76
+ "ilo_Latn",
77
+ "ind_Latn",
78
+ "isl_Latn",
79
+ "ita_Latn",
80
+ "jav_Latn",
81
+ "jpn_Jpan",
82
+ "kab_Latn",
83
+ "kac_Latn",
84
+ "kam_Latn",
85
+ "kan_Knda",
86
+ "kas_Arab",
87
+ "kas_Deva",
88
+ "kat_Geor",
89
+ "knc_Arab",
90
+ "knc_Latn",
91
+ "kaz_Cyrl",
92
+ "kbp_Latn",
93
+ "kea_Latn",
94
+ "khm_Khmr",
95
+ "kik_Latn",
96
+ "kin_Latn",
97
+ "kir_Cyrl",
98
+ "kmb_Latn",
99
+ "kon_Latn",
100
+ "kor_Hang",
101
+ "kmr_Latn",
102
+ "lao_Laoo",
103
+ "lvs_Latn",
104
+ "lij_Latn",
105
+ "lim_Latn",
106
+ "lin_Latn",
107
+ "lit_Latn",
108
+ "lmo_Latn",
109
+ "ltg_Latn",
110
+ "ltz_Latn",
111
+ "lua_Latn",
112
+ "lug_Latn",
113
+ "luo_Latn",
114
+ "lus_Latn",
115
+ "mag_Deva",
116
+ "mai_Deva",
117
+ "mal_Mlym",
118
+ "mar_Deva",
119
+ "min_Latn",
120
+ "mkd_Cyrl",
121
+ "plt_Latn",
122
+ "mlt_Latn",
123
+ "mni_Beng",
124
+ "khk_Cyrl",
125
+ "mos_Latn",
126
+ "mri_Latn",
127
+ "zsm_Latn",
128
+ "mya_Mymr",
129
+ "nld_Latn",
130
+ "nno_Latn",
131
+ "nob_Latn",
132
+ "npi_Deva",
133
+ "nso_Latn",
134
+ "nus_Latn",
135
+ "nya_Latn",
136
+ "oci_Latn",
137
+ "gaz_Latn",
138
+ "ory_Orya",
139
+ "pag_Latn",
140
+ "pan_Guru",
141
+ "pap_Latn",
142
+ "pol_Latn",
143
+ "por_Latn",
144
+ "prs_Arab",
145
+ "pbt_Arab",
146
+ "quy_Latn",
147
+ "ron_Latn",
148
+ "run_Latn",
149
+ "rus_Cyrl",
150
+ "sag_Latn",
151
+ "san_Deva",
152
+ "sat_Beng",
153
+ "scn_Latn",
154
+ "shn_Mymr",
155
+ "sin_Sinh",
156
+ "slk_Latn",
157
+ "slv_Latn",
158
+ "smo_Latn",
159
+ "sna_Latn",
160
+ "snd_Arab",
161
+ "som_Latn",
162
+ "sot_Latn",
163
+ "spa_Latn",
164
+ "als_Latn",
165
+ "srd_Latn",
166
+ "srp_Cyrl",
167
+ "ssw_Latn",
168
+ "sun_Latn",
169
+ "swe_Latn",
170
+ "swh_Latn",
171
+ "szl_Latn",
172
+ "tam_Taml",
173
+ "tat_Cyrl",
174
+ "tel_Telu",
175
+ "tgk_Cyrl",
176
+ "tgl_Latn",
177
+ "tha_Thai",
178
+ "tir_Ethi",
179
+ "taq_Latn",
180
+ "taq_Tfng",
181
+ "tpi_Latn",
182
+ "tsn_Latn",
183
+ "tso_Latn",
184
+ "tuk_Latn",
185
+ "tum_Latn",
186
+ "tur_Latn",
187
+ "twi_Latn",
188
+ "tzm_Tfng",
189
+ "uig_Arab",
190
+ "ukr_Cyrl",
191
+ "umb_Latn",
192
+ "urd_Arab",
193
+ "uzn_Latn",
194
+ "vec_Latn",
195
+ "vie_Latn",
196
+ "war_Latn",
197
+ "wol_Latn",
198
+ "xho_Latn",
199
+ "ydd_Hebr",
200
+ "yor_Latn",
201
+ "yue_Hant",
202
+ "zho_Hans",
203
+ "zho_Hant",
204
+ "zul_Latn"
205
+ ],
206
+ "bos_token": {
207
+ "content": "<s>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ "cls_token": {
214
+ "content": "<s>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ "eos_token": {
221
+ "content": "</s>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ "mask_token": {
228
+ "content": "<mask>",
229
+ "lstrip": true,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ "pad_token": {
235
+ "content": "<pad>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ "sep_token": {
242
+ "content": "</s>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ "unk_token": {
249
+ "content": "<unk>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ }
255
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd897f6e1b43d40640d698f1ed736005d47a08ed8e8e2e389d4b5d60d7892212
3
+ size 32240214
tokenizer_config.json ADDED
@@ -0,0 +1,1879 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "256001": {
36
+ "content": "ace_Arab",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "256002": {
44
+ "content": "ace_Latn",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "256003": {
52
+ "content": "acm_Arab",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "256004": {
60
+ "content": "acq_Arab",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "256005": {
68
+ "content": "aeb_Arab",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "256006": {
76
+ "content": "afr_Latn",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "256007": {
84
+ "content": "ajp_Arab",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "256008": {
92
+ "content": "aka_Latn",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "256009": {
100
+ "content": "amh_Ethi",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "256010": {
108
+ "content": "apc_Arab",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "256011": {
116
+ "content": "arb_Arab",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "256012": {
124
+ "content": "ars_Arab",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "256013": {
132
+ "content": "ary_Arab",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "256014": {
140
+ "content": "arz_Arab",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "256015": {
148
+ "content": "asm_Beng",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "256016": {
156
+ "content": "ast_Latn",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "256017": {
164
+ "content": "awa_Deva",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "256018": {
172
+ "content": "ayr_Latn",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "256019": {
180
+ "content": "azb_Arab",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "256020": {
188
+ "content": "azj_Latn",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "256021": {
196
+ "content": "bak_Cyrl",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "256022": {
204
+ "content": "bam_Latn",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "256023": {
212
+ "content": "ban_Latn",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "256024": {
220
+ "content": "bel_Cyrl",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "256025": {
228
+ "content": "bem_Latn",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "256026": {
236
+ "content": "ben_Beng",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "256027": {
244
+ "content": "bho_Deva",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "256028": {
252
+ "content": "bjn_Arab",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "256029": {
260
+ "content": "bjn_Latn",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "256030": {
268
+ "content": "bod_Tibt",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "256031": {
276
+ "content": "bos_Latn",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "256032": {
284
+ "content": "bug_Latn",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "256033": {
292
+ "content": "bul_Cyrl",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "256034": {
300
+ "content": "cat_Latn",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "256035": {
308
+ "content": "ceb_Latn",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "256036": {
316
+ "content": "ces_Latn",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "256037": {
324
+ "content": "cjk_Latn",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "256038": {
332
+ "content": "ckb_Arab",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "256039": {
340
+ "content": "crh_Latn",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "256040": {
348
+ "content": "cym_Latn",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "256041": {
356
+ "content": "dan_Latn",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "256042": {
364
+ "content": "deu_Latn",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "256043": {
372
+ "content": "dik_Latn",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "256044": {
380
+ "content": "dyu_Latn",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "256045": {
388
+ "content": "dzo_Tibt",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "256046": {
396
+ "content": "ell_Grek",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "256047": {
404
+ "content": "eng_Latn",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "256048": {
412
+ "content": "epo_Latn",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "256049": {
420
+ "content": "est_Latn",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "256050": {
428
+ "content": "eus_Latn",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "256051": {
436
+ "content": "ewe_Latn",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "256052": {
444
+ "content": "fao_Latn",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "256053": {
452
+ "content": "pes_Arab",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "256054": {
460
+ "content": "fij_Latn",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "256055": {
468
+ "content": "fin_Latn",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "256056": {
476
+ "content": "fon_Latn",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "256057": {
484
+ "content": "fra_Latn",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "256058": {
492
+ "content": "fur_Latn",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "256059": {
500
+ "content": "fuv_Latn",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "256060": {
508
+ "content": "gla_Latn",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "256061": {
516
+ "content": "gle_Latn",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "256062": {
524
+ "content": "glg_Latn",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "256063": {
532
+ "content": "grn_Latn",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "256064": {
540
+ "content": "guj_Gujr",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "256065": {
548
+ "content": "hat_Latn",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "256066": {
556
+ "content": "hau_Latn",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "256067": {
564
+ "content": "heb_Hebr",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "256068": {
572
+ "content": "hin_Deva",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "256069": {
580
+ "content": "hne_Deva",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "256070": {
588
+ "content": "hrv_Latn",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "256071": {
596
+ "content": "hun_Latn",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "256072": {
604
+ "content": "hye_Armn",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "256073": {
612
+ "content": "ibo_Latn",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "256074": {
620
+ "content": "ilo_Latn",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "256075": {
628
+ "content": "ind_Latn",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "256076": {
636
+ "content": "isl_Latn",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "256077": {
644
+ "content": "ita_Latn",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "256078": {
652
+ "content": "jav_Latn",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "256079": {
660
+ "content": "jpn_Jpan",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "256080": {
668
+ "content": "kab_Latn",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "256081": {
676
+ "content": "kac_Latn",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "256082": {
684
+ "content": "kam_Latn",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "256083": {
692
+ "content": "kan_Knda",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "256084": {
700
+ "content": "kas_Arab",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "256085": {
708
+ "content": "kas_Deva",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "256086": {
716
+ "content": "kat_Geor",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "256087": {
724
+ "content": "knc_Arab",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "256088": {
732
+ "content": "knc_Latn",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "256089": {
740
+ "content": "kaz_Cyrl",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "256090": {
748
+ "content": "kbp_Latn",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "256091": {
756
+ "content": "kea_Latn",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "256092": {
764
+ "content": "khm_Khmr",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "256093": {
772
+ "content": "kik_Latn",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "256094": {
780
+ "content": "kin_Latn",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "256095": {
788
+ "content": "kir_Cyrl",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "256096": {
796
+ "content": "kmb_Latn",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "256097": {
804
+ "content": "kon_Latn",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "256098": {
812
+ "content": "kor_Hang",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "256099": {
820
+ "content": "kmr_Latn",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "256100": {
828
+ "content": "lao_Laoo",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "256101": {
836
+ "content": "lvs_Latn",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "256102": {
844
+ "content": "lij_Latn",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "256103": {
852
+ "content": "lim_Latn",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "256104": {
860
+ "content": "lin_Latn",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "256105": {
868
+ "content": "lit_Latn",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "256106": {
876
+ "content": "lmo_Latn",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "256107": {
884
+ "content": "ltg_Latn",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "256108": {
892
+ "content": "ltz_Latn",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "256109": {
900
+ "content": "lua_Latn",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "256110": {
908
+ "content": "lug_Latn",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "256111": {
916
+ "content": "luo_Latn",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "256112": {
924
+ "content": "lus_Latn",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "256113": {
932
+ "content": "mag_Deva",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "256114": {
940
+ "content": "mai_Deva",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "256115": {
948
+ "content": "mal_Mlym",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "256116": {
956
+ "content": "mar_Deva",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "256117": {
964
+ "content": "min_Latn",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "256118": {
972
+ "content": "mkd_Cyrl",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "256119": {
980
+ "content": "plt_Latn",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "256120": {
988
+ "content": "mlt_Latn",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "256121": {
996
+ "content": "mni_Beng",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "256122": {
1004
+ "content": "khk_Cyrl",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "256123": {
1012
+ "content": "mos_Latn",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "256124": {
1020
+ "content": "mri_Latn",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "256125": {
1028
+ "content": "zsm_Latn",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "256126": {
1036
+ "content": "mya_Mymr",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "256127": {
1044
+ "content": "nld_Latn",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "256128": {
1052
+ "content": "nno_Latn",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "256129": {
1060
+ "content": "nob_Latn",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "256130": {
1068
+ "content": "npi_Deva",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "256131": {
1076
+ "content": "nso_Latn",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "256132": {
1084
+ "content": "nus_Latn",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "256133": {
1092
+ "content": "nya_Latn",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "256134": {
1100
+ "content": "oci_Latn",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "256135": {
1108
+ "content": "gaz_Latn",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "256136": {
1116
+ "content": "ory_Orya",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "256137": {
1124
+ "content": "pag_Latn",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "256138": {
1132
+ "content": "pan_Guru",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "256139": {
1140
+ "content": "pap_Latn",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "256140": {
1148
+ "content": "pol_Latn",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "256141": {
1156
+ "content": "por_Latn",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "256142": {
1164
+ "content": "prs_Arab",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "256143": {
1172
+ "content": "pbt_Arab",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "256144": {
1180
+ "content": "quy_Latn",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "256145": {
1188
+ "content": "ron_Latn",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "256146": {
1196
+ "content": "run_Latn",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "256147": {
1204
+ "content": "rus_Cyrl",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "256148": {
1212
+ "content": "sag_Latn",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "256149": {
1220
+ "content": "san_Deva",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "256150": {
1228
+ "content": "sat_Beng",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "256151": {
1236
+ "content": "scn_Latn",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "256152": {
1244
+ "content": "shn_Mymr",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "256153": {
1252
+ "content": "sin_Sinh",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "256154": {
1260
+ "content": "slk_Latn",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "256155": {
1268
+ "content": "slv_Latn",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "256156": {
1276
+ "content": "smo_Latn",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "256157": {
1284
+ "content": "sna_Latn",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "256158": {
1292
+ "content": "snd_Arab",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "256159": {
1300
+ "content": "som_Latn",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "256160": {
1308
+ "content": "sot_Latn",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "256161": {
1316
+ "content": "spa_Latn",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "256162": {
1324
+ "content": "als_Latn",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "256163": {
1332
+ "content": "srd_Latn",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "256164": {
1340
+ "content": "srp_Cyrl",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "256165": {
1348
+ "content": "ssw_Latn",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "256166": {
1356
+ "content": "sun_Latn",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "256167": {
1364
+ "content": "swe_Latn",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "256168": {
1372
+ "content": "swh_Latn",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "256169": {
1380
+ "content": "szl_Latn",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "256170": {
1388
+ "content": "tam_Taml",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "256171": {
1396
+ "content": "tat_Cyrl",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "256172": {
1404
+ "content": "tel_Telu",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "256173": {
1412
+ "content": "tgk_Cyrl",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "256174": {
1420
+ "content": "tgl_Latn",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "256175": {
1428
+ "content": "tha_Thai",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "256176": {
1436
+ "content": "tir_Ethi",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "256177": {
1444
+ "content": "taq_Latn",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "256178": {
1452
+ "content": "taq_Tfng",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "256179": {
1460
+ "content": "tpi_Latn",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "256180": {
1468
+ "content": "tsn_Latn",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "256181": {
1476
+ "content": "tso_Latn",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "256182": {
1484
+ "content": "tuk_Latn",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "256183": {
1492
+ "content": "tum_Latn",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "256184": {
1500
+ "content": "tur_Latn",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "256185": {
1508
+ "content": "twi_Latn",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "256186": {
1516
+ "content": "tzm_Tfng",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "256187": {
1524
+ "content": "uig_Arab",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "256188": {
1532
+ "content": "ukr_Cyrl",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "256189": {
1540
+ "content": "umb_Latn",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "256190": {
1548
+ "content": "urd_Arab",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "256191": {
1556
+ "content": "uzn_Latn",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "256192": {
1564
+ "content": "vec_Latn",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "256193": {
1572
+ "content": "vie_Latn",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "256194": {
1580
+ "content": "war_Latn",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "256195": {
1588
+ "content": "wol_Latn",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "256196": {
1596
+ "content": "xho_Latn",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "256197": {
1604
+ "content": "ydd_Hebr",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "256198": {
1612
+ "content": "yor_Latn",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "256199": {
1620
+ "content": "yue_Hant",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "256200": {
1628
+ "content": "zho_Hans",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "256201": {
1636
+ "content": "zho_Hant",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "256202": {
1644
+ "content": "zul_Latn",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "256203": {
1652
+ "content": "<mask>",
1653
+ "lstrip": true,
1654
+ "normalized": true,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ }
1659
+ },
1660
+ "additional_special_tokens": [
1661
+ "ace_Arab",
1662
+ "ace_Latn",
1663
+ "acm_Arab",
1664
+ "acq_Arab",
1665
+ "aeb_Arab",
1666
+ "afr_Latn",
1667
+ "ajp_Arab",
1668
+ "aka_Latn",
1669
+ "amh_Ethi",
1670
+ "apc_Arab",
1671
+ "arb_Arab",
1672
+ "ars_Arab",
1673
+ "ary_Arab",
1674
+ "arz_Arab",
1675
+ "asm_Beng",
1676
+ "ast_Latn",
1677
+ "awa_Deva",
1678
+ "ayr_Latn",
1679
+ "azb_Arab",
1680
+ "azj_Latn",
1681
+ "bak_Cyrl",
1682
+ "bam_Latn",
1683
+ "ban_Latn",
1684
+ "bel_Cyrl",
1685
+ "bem_Latn",
1686
+ "ben_Beng",
1687
+ "bho_Deva",
1688
+ "bjn_Arab",
1689
+ "bjn_Latn",
1690
+ "bod_Tibt",
1691
+ "bos_Latn",
1692
+ "bug_Latn",
1693
+ "bul_Cyrl",
1694
+ "cat_Latn",
1695
+ "ceb_Latn",
1696
+ "ces_Latn",
1697
+ "cjk_Latn",
1698
+ "ckb_Arab",
1699
+ "crh_Latn",
1700
+ "cym_Latn",
1701
+ "dan_Latn",
1702
+ "deu_Latn",
1703
+ "dik_Latn",
1704
+ "dyu_Latn",
1705
+ "dzo_Tibt",
1706
+ "ell_Grek",
1707
+ "eng_Latn",
1708
+ "epo_Latn",
1709
+ "est_Latn",
1710
+ "eus_Latn",
1711
+ "ewe_Latn",
1712
+ "fao_Latn",
1713
+ "pes_Arab",
1714
+ "fij_Latn",
1715
+ "fin_Latn",
1716
+ "fon_Latn",
1717
+ "fra_Latn",
1718
+ "fur_Latn",
1719
+ "fuv_Latn",
1720
+ "gla_Latn",
1721
+ "gle_Latn",
1722
+ "glg_Latn",
1723
+ "grn_Latn",
1724
+ "guj_Gujr",
1725
+ "hat_Latn",
1726
+ "hau_Latn",
1727
+ "heb_Hebr",
1728
+ "hin_Deva",
1729
+ "hne_Deva",
1730
+ "hrv_Latn",
1731
+ "hun_Latn",
1732
+ "hye_Armn",
1733
+ "ibo_Latn",
1734
+ "ilo_Latn",
1735
+ "ind_Latn",
1736
+ "isl_Latn",
1737
+ "ita_Latn",
1738
+ "jav_Latn",
1739
+ "jpn_Jpan",
1740
+ "kab_Latn",
1741
+ "kac_Latn",
1742
+ "kam_Latn",
1743
+ "kan_Knda",
1744
+ "kas_Arab",
1745
+ "kas_Deva",
1746
+ "kat_Geor",
1747
+ "knc_Arab",
1748
+ "knc_Latn",
1749
+ "kaz_Cyrl",
1750
+ "kbp_Latn",
1751
+ "kea_Latn",
1752
+ "khm_Khmr",
1753
+ "kik_Latn",
1754
+ "kin_Latn",
1755
+ "kir_Cyrl",
1756
+ "kmb_Latn",
1757
+ "kon_Latn",
1758
+ "kor_Hang",
1759
+ "kmr_Latn",
1760
+ "lao_Laoo",
1761
+ "lvs_Latn",
1762
+ "lij_Latn",
1763
+ "lim_Latn",
1764
+ "lin_Latn",
1765
+ "lit_Latn",
1766
+ "lmo_Latn",
1767
+ "ltg_Latn",
1768
+ "ltz_Latn",
1769
+ "lua_Latn",
1770
+ "lug_Latn",
1771
+ "luo_Latn",
1772
+ "lus_Latn",
1773
+ "mag_Deva",
1774
+ "mai_Deva",
1775
+ "mal_Mlym",
1776
+ "mar_Deva",
1777
+ "min_Latn",
1778
+ "mkd_Cyrl",
1779
+ "plt_Latn",
1780
+ "mlt_Latn",
1781
+ "mni_Beng",
1782
+ "khk_Cyrl",
1783
+ "mos_Latn",
1784
+ "mri_Latn",
1785
+ "zsm_Latn",
1786
+ "mya_Mymr",
1787
+ "nld_Latn",
1788
+ "nno_Latn",
1789
+ "nob_Latn",
1790
+ "npi_Deva",
1791
+ "nso_Latn",
1792
+ "nus_Latn",
1793
+ "nya_Latn",
1794
+ "oci_Latn",
1795
+ "gaz_Latn",
1796
+ "ory_Orya",
1797
+ "pag_Latn",
1798
+ "pan_Guru",
1799
+ "pap_Latn",
1800
+ "pol_Latn",
1801
+ "por_Latn",
1802
+ "prs_Arab",
1803
+ "pbt_Arab",
1804
+ "quy_Latn",
1805
+ "ron_Latn",
1806
+ "run_Latn",
1807
+ "rus_Cyrl",
1808
+ "sag_Latn",
1809
+ "san_Deva",
1810
+ "sat_Beng",
1811
+ "scn_Latn",
1812
+ "shn_Mymr",
1813
+ "sin_Sinh",
1814
+ "slk_Latn",
1815
+ "slv_Latn",
1816
+ "smo_Latn",
1817
+ "sna_Latn",
1818
+ "snd_Arab",
1819
+ "som_Latn",
1820
+ "sot_Latn",
1821
+ "spa_Latn",
1822
+ "als_Latn",
1823
+ "srd_Latn",
1824
+ "srp_Cyrl",
1825
+ "ssw_Latn",
1826
+ "sun_Latn",
1827
+ "swe_Latn",
1828
+ "swh_Latn",
1829
+ "szl_Latn",
1830
+ "tam_Taml",
1831
+ "tat_Cyrl",
1832
+ "tel_Telu",
1833
+ "tgk_Cyrl",
1834
+ "tgl_Latn",
1835
+ "tha_Thai",
1836
+ "tir_Ethi",
1837
+ "taq_Latn",
1838
+ "taq_Tfng",
1839
+ "tpi_Latn",
1840
+ "tsn_Latn",
1841
+ "tso_Latn",
1842
+ "tuk_Latn",
1843
+ "tum_Latn",
1844
+ "tur_Latn",
1845
+ "twi_Latn",
1846
+ "tzm_Tfng",
1847
+ "uig_Arab",
1848
+ "ukr_Cyrl",
1849
+ "umb_Latn",
1850
+ "urd_Arab",
1851
+ "uzn_Latn",
1852
+ "vec_Latn",
1853
+ "vie_Latn",
1854
+ "war_Latn",
1855
+ "wol_Latn",
1856
+ "xho_Latn",
1857
+ "ydd_Hebr",
1858
+ "yor_Latn",
1859
+ "yue_Hant",
1860
+ "zho_Hans",
1861
+ "zho_Hant",
1862
+ "zul_Latn"
1863
+ ],
1864
+ "bos_token": "<s>",
1865
+ "clean_up_tokenization_spaces": false,
1866
+ "cls_token": "<s>",
1867
+ "eos_token": "</s>",
1868
+ "extra_special_tokens": {},
1869
+ "legacy_behaviour": false,
1870
+ "mask_token": "<mask>",
1871
+ "model_max_length": 1024,
1872
+ "pad_token": "<pad>",
1873
+ "sep_token": "</s>",
1874
+ "sp_model_kwargs": {},
1875
+ "src_lang": "kan_Deva",
1876
+ "tgt_lang": "hin_Deva",
1877
+ "tokenizer_class": "NllbTokenizer",
1878
+ "unk_token": "<unk>"
1879
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "total_flos": 1.5022851621224448e+16,
4
+ "train_loss": 0.5662414055868578,
5
+ "train_runtime": 9241.9444,
6
+ "train_samples": 14984,
7
+ "train_samples_per_second": 16.213,
8
+ "train_steps_per_second": 4.053
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,561 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 10.0,
6
+ "eval_steps": 500,
7
+ "global_step": 37460,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.13347570742124934,
14
+ "grad_norm": 3.1176345348358154,
15
+ "learning_rate": 4.933395621996797e-05,
16
+ "loss": 1.6549,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.2669514148424987,
21
+ "grad_norm": 2.8823812007904053,
22
+ "learning_rate": 4.866657768286172e-05,
23
+ "loss": 1.3869,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.400427122263748,
28
+ "grad_norm": 3.436349630355835,
29
+ "learning_rate": 4.7999199145755475e-05,
30
+ "loss": 1.31,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.5339028296849974,
35
+ "grad_norm": 2.7581417560577393,
36
+ "learning_rate": 4.733182060864923e-05,
37
+ "loss": 1.2632,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.6673785371062466,
42
+ "grad_norm": 3.0282974243164062,
43
+ "learning_rate": 4.666444207154298e-05,
44
+ "loss": 1.2197,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.800854244527496,
49
+ "grad_norm": 2.7351794242858887,
50
+ "learning_rate": 4.599706353443674e-05,
51
+ "loss": 1.1942,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.9343299519487454,
56
+ "grad_norm": 2.228116035461426,
57
+ "learning_rate": 4.532968499733049e-05,
58
+ "loss": 1.1273,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.0678056593699947,
63
+ "grad_norm": 3.064039707183838,
64
+ "learning_rate": 4.466230646022424e-05,
65
+ "loss": 1.0261,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.201281366791244,
70
+ "grad_norm": 2.9547019004821777,
71
+ "learning_rate": 4.3994927923117995e-05,
72
+ "loss": 0.9262,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.3347570742124932,
77
+ "grad_norm": 2.8099584579467773,
78
+ "learning_rate": 4.332754938601175e-05,
79
+ "loss": 0.9193,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.4682327816337426,
84
+ "grad_norm": 2.4523322582244873,
85
+ "learning_rate": 4.26601708489055e-05,
86
+ "loss": 0.939,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.601708489054992,
91
+ "grad_norm": 2.4100770950317383,
92
+ "learning_rate": 4.199279231179926e-05,
93
+ "loss": 0.9084,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.7351841964762413,
98
+ "grad_norm": 2.4628851413726807,
99
+ "learning_rate": 4.1325413774693004e-05,
100
+ "loss": 0.9303,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 1.8686599038974907,
105
+ "grad_norm": 2.522763967514038,
106
+ "learning_rate": 4.0658035237586763e-05,
107
+ "loss": 0.8988,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 2.00213561131874,
112
+ "grad_norm": 1.8565527200698853,
113
+ "learning_rate": 3.9990656700480516e-05,
114
+ "loss": 0.9408,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 2.1356113187399894,
119
+ "grad_norm": 3.084707498550415,
120
+ "learning_rate": 3.932327816337427e-05,
121
+ "loss": 0.7548,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 2.269087026161239,
126
+ "grad_norm": 1.836754322052002,
127
+ "learning_rate": 3.865589962626802e-05,
128
+ "loss": 0.7447,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 2.402562733582488,
133
+ "grad_norm": 2.452847719192505,
134
+ "learning_rate": 3.798852108916178e-05,
135
+ "loss": 0.7293,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 2.536038441003737,
140
+ "grad_norm": 3.363875150680542,
141
+ "learning_rate": 3.7321142552055525e-05,
142
+ "loss": 0.7437,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 2.6695141484249865,
147
+ "grad_norm": 2.087559700012207,
148
+ "learning_rate": 3.6653764014949284e-05,
149
+ "loss": 0.7217,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 2.802989855846236,
154
+ "grad_norm": 2.1554408073425293,
155
+ "learning_rate": 3.598638547784303e-05,
156
+ "loss": 0.7459,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 2.936465563267485,
161
+ "grad_norm": 1.8922470808029175,
162
+ "learning_rate": 3.531900694073679e-05,
163
+ "loss": 0.7586,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 3.0699412706887346,
168
+ "grad_norm": 2.0937387943267822,
169
+ "learning_rate": 3.465162840363054e-05,
170
+ "loss": 0.6552,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 3.203416978109984,
175
+ "grad_norm": 2.954742908477783,
176
+ "learning_rate": 3.398424986652429e-05,
177
+ "loss": 0.6012,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 3.3368926855312333,
182
+ "grad_norm": 2.8236591815948486,
183
+ "learning_rate": 3.3316871329418045e-05,
184
+ "loss": 0.607,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 3.4703683929524827,
189
+ "grad_norm": 2.4959943294525146,
190
+ "learning_rate": 3.2649492792311804e-05,
191
+ "loss": 0.6181,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 3.603844100373732,
196
+ "grad_norm": 3.4247825145721436,
197
+ "learning_rate": 3.198211425520555e-05,
198
+ "loss": 0.6029,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 3.7373198077949814,
203
+ "grad_norm": 2.6698663234710693,
204
+ "learning_rate": 3.131473571809931e-05,
205
+ "loss": 0.6032,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 3.8707955152162308,
210
+ "grad_norm": 1.9999539852142334,
211
+ "learning_rate": 3.064735718099306e-05,
212
+ "loss": 0.6241,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 4.00427122263748,
217
+ "grad_norm": 2.449364185333252,
218
+ "learning_rate": 2.9979978643886814e-05,
219
+ "loss": 0.6183,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 4.1377469300587295,
224
+ "grad_norm": 4.328239917755127,
225
+ "learning_rate": 2.931260010678057e-05,
226
+ "loss": 0.4832,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 4.271222637479979,
231
+ "grad_norm": 1.9375187158584595,
232
+ "learning_rate": 2.8645221569674318e-05,
233
+ "loss": 0.4963,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 4.404698344901228,
238
+ "grad_norm": 2.9625084400177,
239
+ "learning_rate": 2.7977843032568074e-05,
240
+ "loss": 0.5162,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 4.538174052322478,
245
+ "grad_norm": 3.514462947845459,
246
+ "learning_rate": 2.731046449546183e-05,
247
+ "loss": 0.4913,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 4.671649759743727,
252
+ "grad_norm": 2.035665988922119,
253
+ "learning_rate": 2.664308595835558e-05,
254
+ "loss": 0.5062,
255
+ "step": 17500
256
+ },
257
+ {
258
+ "epoch": 4.805125467164976,
259
+ "grad_norm": 3.025426149368286,
260
+ "learning_rate": 2.5975707421249334e-05,
261
+ "loss": 0.5167,
262
+ "step": 18000
263
+ },
264
+ {
265
+ "epoch": 4.938601174586225,
266
+ "grad_norm": 3.0361483097076416,
267
+ "learning_rate": 2.530832888414309e-05,
268
+ "loss": 0.4961,
269
+ "step": 18500
270
+ },
271
+ {
272
+ "epoch": 5.072076882007474,
273
+ "grad_norm": 2.769930124282837,
274
+ "learning_rate": 2.464095034703684e-05,
275
+ "loss": 0.4582,
276
+ "step": 19000
277
+ },
278
+ {
279
+ "epoch": 5.205552589428724,
280
+ "grad_norm": 2.209397077560425,
281
+ "learning_rate": 2.3973571809930594e-05,
282
+ "loss": 0.3926,
283
+ "step": 19500
284
+ },
285
+ {
286
+ "epoch": 5.339028296849973,
287
+ "grad_norm": 2.680094003677368,
288
+ "learning_rate": 2.3306193272824347e-05,
289
+ "loss": 0.4187,
290
+ "step": 20000
291
+ },
292
+ {
293
+ "epoch": 5.472504004271222,
294
+ "grad_norm": 2.425154447555542,
295
+ "learning_rate": 2.26388147357181e-05,
296
+ "loss": 0.4182,
297
+ "step": 20500
298
+ },
299
+ {
300
+ "epoch": 5.605979711692472,
301
+ "grad_norm": 4.719789505004883,
302
+ "learning_rate": 2.197143619861185e-05,
303
+ "loss": 0.4257,
304
+ "step": 21000
305
+ },
306
+ {
307
+ "epoch": 5.739455419113721,
308
+ "grad_norm": 1.3763984441757202,
309
+ "learning_rate": 2.1304057661505607e-05,
310
+ "loss": 0.4222,
311
+ "step": 21500
312
+ },
313
+ {
314
+ "epoch": 5.87293112653497,
315
+ "grad_norm": 2.8332626819610596,
316
+ "learning_rate": 2.063667912439936e-05,
317
+ "loss": 0.4247,
318
+ "step": 22000
319
+ },
320
+ {
321
+ "epoch": 6.00640683395622,
322
+ "grad_norm": 1.990326166152954,
323
+ "learning_rate": 1.996930058729311e-05,
324
+ "loss": 0.4149,
325
+ "step": 22500
326
+ },
327
+ {
328
+ "epoch": 6.139882541377469,
329
+ "grad_norm": 1.9501370191574097,
330
+ "learning_rate": 1.9301922050186867e-05,
331
+ "loss": 0.3451,
332
+ "step": 23000
333
+ },
334
+ {
335
+ "epoch": 6.2733582487987185,
336
+ "grad_norm": 2.518463611602783,
337
+ "learning_rate": 1.863454351308062e-05,
338
+ "loss": 0.3338,
339
+ "step": 23500
340
+ },
341
+ {
342
+ "epoch": 6.406833956219968,
343
+ "grad_norm": 2.567760705947876,
344
+ "learning_rate": 1.7967164975974375e-05,
345
+ "loss": 0.3537,
346
+ "step": 24000
347
+ },
348
+ {
349
+ "epoch": 6.540309663641217,
350
+ "grad_norm": 3.4953105449676514,
351
+ "learning_rate": 1.7299786438868128e-05,
352
+ "loss": 0.3463,
353
+ "step": 24500
354
+ },
355
+ {
356
+ "epoch": 6.673785371062467,
357
+ "grad_norm": 4.280869007110596,
358
+ "learning_rate": 1.663240790176188e-05,
359
+ "loss": 0.3794,
360
+ "step": 25000
361
+ },
362
+ {
363
+ "epoch": 6.807261078483716,
364
+ "grad_norm": 1.3708416223526,
365
+ "learning_rate": 1.5965029364655636e-05,
366
+ "loss": 0.3595,
367
+ "step": 25500
368
+ },
369
+ {
370
+ "epoch": 6.940736785904965,
371
+ "grad_norm": 1.9402921199798584,
372
+ "learning_rate": 1.5297650827549388e-05,
373
+ "loss": 0.3567,
374
+ "step": 26000
375
+ },
376
+ {
377
+ "epoch": 7.074212493326215,
378
+ "grad_norm": 3.4459097385406494,
379
+ "learning_rate": 1.463027229044314e-05,
380
+ "loss": 0.3271,
381
+ "step": 26500
382
+ },
383
+ {
384
+ "epoch": 7.207688200747464,
385
+ "grad_norm": 3.0598597526550293,
386
+ "learning_rate": 1.3962893753336892e-05,
387
+ "loss": 0.3053,
388
+ "step": 27000
389
+ },
390
+ {
391
+ "epoch": 7.3411639081687134,
392
+ "grad_norm": 1.887160062789917,
393
+ "learning_rate": 1.3295515216230648e-05,
394
+ "loss": 0.2941,
395
+ "step": 27500
396
+ },
397
+ {
398
+ "epoch": 7.474639615589963,
399
+ "grad_norm": 2.143535852432251,
400
+ "learning_rate": 1.26281366791244e-05,
401
+ "loss": 0.2981,
402
+ "step": 28000
403
+ },
404
+ {
405
+ "epoch": 7.608115323011212,
406
+ "grad_norm": 4.371819019317627,
407
+ "learning_rate": 1.1960758142018154e-05,
408
+ "loss": 0.2986,
409
+ "step": 28500
410
+ },
411
+ {
412
+ "epoch": 7.7415910304324616,
413
+ "grad_norm": 3.378239631652832,
414
+ "learning_rate": 1.1293379604911907e-05,
415
+ "loss": 0.305,
416
+ "step": 29000
417
+ },
418
+ {
419
+ "epoch": 7.875066737853711,
420
+ "grad_norm": 2.8271336555480957,
421
+ "learning_rate": 1.062600106780566e-05,
422
+ "loss": 0.3193,
423
+ "step": 29500
424
+ },
425
+ {
426
+ "epoch": 8.00854244527496,
427
+ "grad_norm": 2.825468063354492,
428
+ "learning_rate": 9.958622530699413e-06,
429
+ "loss": 0.3004,
430
+ "step": 30000
431
+ },
432
+ {
433
+ "epoch": 8.14201815269621,
434
+ "grad_norm": 2.4525914192199707,
435
+ "learning_rate": 9.291243993593167e-06,
436
+ "loss": 0.2669,
437
+ "step": 30500
438
+ },
439
+ {
440
+ "epoch": 8.275493860117459,
441
+ "grad_norm": 4.695706844329834,
442
+ "learning_rate": 8.62386545648692e-06,
443
+ "loss": 0.2737,
444
+ "step": 31000
445
+ },
446
+ {
447
+ "epoch": 8.408969567538708,
448
+ "grad_norm": 3.336611270904541,
449
+ "learning_rate": 7.956486919380673e-06,
450
+ "loss": 0.2697,
451
+ "step": 31500
452
+ },
453
+ {
454
+ "epoch": 8.542445274959958,
455
+ "grad_norm": 3.6071436405181885,
456
+ "learning_rate": 7.289108382274426e-06,
457
+ "loss": 0.2644,
458
+ "step": 32000
459
+ },
460
+ {
461
+ "epoch": 8.675920982381207,
462
+ "grad_norm": 3.1964738368988037,
463
+ "learning_rate": 6.62172984516818e-06,
464
+ "loss": 0.2669,
465
+ "step": 32500
466
+ },
467
+ {
468
+ "epoch": 8.809396689802456,
469
+ "grad_norm": 2.115790843963623,
470
+ "learning_rate": 5.9543513080619334e-06,
471
+ "loss": 0.2638,
472
+ "step": 33000
473
+ },
474
+ {
475
+ "epoch": 8.942872397223706,
476
+ "grad_norm": 1.7221794128417969,
477
+ "learning_rate": 5.286972770955687e-06,
478
+ "loss": 0.282,
479
+ "step": 33500
480
+ },
481
+ {
482
+ "epoch": 9.076348104644955,
483
+ "grad_norm": 2.4076969623565674,
484
+ "learning_rate": 4.61959423384944e-06,
485
+ "loss": 0.2601,
486
+ "step": 34000
487
+ },
488
+ {
489
+ "epoch": 9.209823812066205,
490
+ "grad_norm": 1.874233603477478,
491
+ "learning_rate": 3.952215696743193e-06,
492
+ "loss": 0.2474,
493
+ "step": 34500
494
+ },
495
+ {
496
+ "epoch": 9.343299519487454,
497
+ "grad_norm": 2.8450875282287598,
498
+ "learning_rate": 3.2848371596369464e-06,
499
+ "loss": 0.2405,
500
+ "step": 35000
501
+ },
502
+ {
503
+ "epoch": 9.476775226908703,
504
+ "grad_norm": 2.4307425022125244,
505
+ "learning_rate": 2.6174586225306996e-06,
506
+ "loss": 0.244,
507
+ "step": 35500
508
+ },
509
+ {
510
+ "epoch": 9.610250934329953,
511
+ "grad_norm": 1.2817405462265015,
512
+ "learning_rate": 1.9500800854244527e-06,
513
+ "loss": 0.2457,
514
+ "step": 36000
515
+ },
516
+ {
517
+ "epoch": 9.743726641751202,
518
+ "grad_norm": 2.613475799560547,
519
+ "learning_rate": 1.282701548318206e-06,
520
+ "loss": 0.2446,
521
+ "step": 36500
522
+ },
523
+ {
524
+ "epoch": 9.877202349172451,
525
+ "grad_norm": 1.7706152200698853,
526
+ "learning_rate": 6.153230112119594e-07,
527
+ "loss": 0.2464,
528
+ "step": 37000
529
+ },
530
+ {
531
+ "epoch": 10.0,
532
+ "step": 37460,
533
+ "total_flos": 1.5022851621224448e+16,
534
+ "train_loss": 0.5662414055868578,
535
+ "train_runtime": 9241.9444,
536
+ "train_samples_per_second": 16.213,
537
+ "train_steps_per_second": 4.053
538
+ }
539
+ ],
540
+ "logging_steps": 500,
541
+ "max_steps": 37460,
542
+ "num_input_tokens_seen": 0,
543
+ "num_train_epochs": 10,
544
+ "save_steps": 10000,
545
+ "stateful_callbacks": {
546
+ "TrainerControl": {
547
+ "args": {
548
+ "should_epoch_stop": false,
549
+ "should_evaluate": false,
550
+ "should_log": false,
551
+ "should_save": true,
552
+ "should_training_stop": true
553
+ },
554
+ "attributes": {}
555
+ }
556
+ },
557
+ "total_flos": 1.5022851621224448e+16,
558
+ "train_batch_size": 4,
559
+ "trial_name": null,
560
+ "trial_params": null
561
+ }