Hugging Face's logo

aryaumesh
/
english-to-telugu

Safetensors
mbart
Model card Files Community
aryaumesh commited on
Commit
5bfb3bc
•
1 Parent(s): 22c4d45

Upload 10 files

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. config.json +58 -0
  3. generation_config.json +12 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. sentencepiece.bpe.model +3 -0
  7. special_tokens_map.json +69 -0
  8. tokenizer.json +3 -0
  9. tokenizer_config.json +528 -0
  10. trainer_state.json +341 -0
  11. training_args.bin +3 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/mbart-large-50-many-to-many-mmt",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": true,
8
+ "architectures": [
9
+ "MBartForConditionalGeneration"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 1024,
16
+ "decoder_attention_heads": 16,
17
+ "decoder_ffn_dim": 4096,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 2,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 12,
27
+ "eos_token_id": 2,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_length": 200,
43
+ "max_position_embeddings": 1024,
44
+ "model_type": "mbart",
45
+ "normalize_before": true,
46
+ "normalize_embedding": true,
47
+ "num_beams": 5,
48
+ "num_hidden_layers": 12,
49
+ "output_past": true,
50
+ "pad_token_id": 1,
51
+ "scale_embedding": true,
52
+ "static_position_embeddings": false,
53
+ "tokenizer_class": "MBart50Tokenizer",
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.44.0",
56
+ "use_cache": true,
57
+ "vocab_size": 250054
58
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "max_length": 200,
9
+ "num_beams": 5,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.44.0"
12
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac48f08a08b80cd4ecc943df090b2582e16b2be647e290130dde11528e9a77a
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118d836fc80130da8ef6c6cd82de5ab7ffc2fe572bca21dbaabfe17c9c3acb7b
3
+ size 1064
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
special_tokens_map.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "ar_AR",
4
+ "cs_CZ",
5
+ "de_DE",
6
+ "en_XX",
7
+ "es_XX",
8
+ "et_EE",
9
+ "fi_FI",
10
+ "fr_XX",
11
+ "gu_IN",
12
+ "hi_IN",
13
+ "it_IT",
14
+ "ja_XX",
15
+ "kk_KZ",
16
+ "ko_KR",
17
+ "lt_LT",
18
+ "lv_LV",
19
+ "my_MM",
20
+ "ne_NP",
21
+ "nl_XX",
22
+ "ro_RO",
23
+ "ru_RU",
24
+ "si_LK",
25
+ "tr_TR",
26
+ "vi_VN",
27
+ "zh_CN",
28
+ "af_ZA",
29
+ "az_AZ",
30
+ "bn_IN",
31
+ "fa_IR",
32
+ "he_IL",
33
+ "hr_HR",
34
+ "id_ID",
35
+ "ka_GE",
36
+ "km_KH",
37
+ "mk_MK",
38
+ "ml_IN",
39
+ "mn_MN",
40
+ "mr_IN",
41
+ "pl_PL",
42
+ "ps_AF",
43
+ "pt_XX",
44
+ "sv_SE",
45
+ "sw_KE",
46
+ "ta_IN",
47
+ "te_IN",
48
+ "th_TH",
49
+ "tl_XX",
50
+ "uk_UA",
51
+ "ur_PK",
52
+ "xh_ZA",
53
+ "gl_ES",
54
+ "sl_SI"
55
+ ],
56
+ "bos_token": "<s>",
57
+ "cls_token": "<s>",
58
+ "eos_token": "</s>",
59
+ "mask_token": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "pad_token": "<pad>",
67
+ "sep_token": "</s>",
68
+ "unk_token": "<unk>"
69
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef126060ddcab67250020d3e4fff2150e3946ba9e7cea24b2a18dd969e0469da
3
+ size 17110019
tokenizer_config.json ADDED
@@ -0,0 +1,528 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "ar_AR",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "250002": {
44
+ "content": "cs_CZ",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "250003": {
52
+ "content": "de_DE",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "250004": {
60
+ "content": "en_XX",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "250005": {
68
+ "content": "es_XX",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "250006": {
76
+ "content": "et_EE",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "250007": {
84
+ "content": "fi_FI",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "250008": {
92
+ "content": "fr_XX",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "250009": {
100
+ "content": "gu_IN",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "250010": {
108
+ "content": "hi_IN",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "250011": {
116
+ "content": "it_IT",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "250012": {
124
+ "content": "ja_XX",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "250013": {
132
+ "content": "kk_KZ",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "250014": {
140
+ "content": "ko_KR",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "250015": {
148
+ "content": "lt_LT",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "250016": {
156
+ "content": "lv_LV",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "250017": {
164
+ "content": "my_MM",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "250018": {
172
+ "content": "ne_NP",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "250019": {
180
+ "content": "nl_XX",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "250020": {
188
+ "content": "ro_RO",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "250021": {
196
+ "content": "ru_RU",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "250022": {
204
+ "content": "si_LK",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "250023": {
212
+ "content": "tr_TR",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "250024": {
220
+ "content": "vi_VN",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "250025": {
228
+ "content": "zh_CN",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "250026": {
236
+ "content": "af_ZA",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "250027": {
244
+ "content": "az_AZ",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "250028": {
252
+ "content": "bn_IN",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "250029": {
260
+ "content": "fa_IR",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "250030": {
268
+ "content": "he_IL",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "250031": {
276
+ "content": "hr_HR",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "250032": {
284
+ "content": "id_ID",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "250033": {
292
+ "content": "ka_GE",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "250034": {
300
+ "content": "km_KH",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "250035": {
308
+ "content": "mk_MK",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "250036": {
316
+ "content": "ml_IN",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "250037": {
324
+ "content": "mn_MN",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "250038": {
332
+ "content": "mr_IN",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "250039": {
340
+ "content": "pl_PL",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "250040": {
348
+ "content": "ps_AF",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "250041": {
356
+ "content": "pt_XX",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "250042": {
364
+ "content": "sv_SE",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "250043": {
372
+ "content": "sw_KE",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "250044": {
380
+ "content": "ta_IN",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "250045": {
388
+ "content": "te_IN",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "250046": {
396
+ "content": "th_TH",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "250047": {
404
+ "content": "tl_XX",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "250048": {
412
+ "content": "uk_UA",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "250049": {
420
+ "content": "ur_PK",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "250050": {
428
+ "content": "xh_ZA",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "250051": {
436
+ "content": "gl_ES",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "250052": {
444
+ "content": "sl_SI",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "250053": {
452
+ "content": "<mask>",
453
+ "lstrip": true,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ }
459
+ },
460
+ "additional_special_tokens": [
461
+ "ar_AR",
462
+ "cs_CZ",
463
+ "de_DE",
464
+ "en_XX",
465
+ "es_XX",
466
+ "et_EE",
467
+ "fi_FI",
468
+ "fr_XX",
469
+ "gu_IN",
470
+ "hi_IN",
471
+ "it_IT",
472
+ "ja_XX",
473
+ "kk_KZ",
474
+ "ko_KR",
475
+ "lt_LT",
476
+ "lv_LV",
477
+ "my_MM",
478
+ "ne_NP",
479
+ "nl_XX",
480
+ "ro_RO",
481
+ "ru_RU",
482
+ "si_LK",
483
+ "tr_TR",
484
+ "vi_VN",
485
+ "zh_CN",
486
+ "af_ZA",
487
+ "az_AZ",
488
+ "bn_IN",
489
+ "fa_IR",
490
+ "he_IL",
491
+ "hr_HR",
492
+ "id_ID",
493
+ "ka_GE",
494
+ "km_KH",
495
+ "mk_MK",
496
+ "ml_IN",
497
+ "mn_MN",
498
+ "mr_IN",
499
+ "pl_PL",
500
+ "ps_AF",
501
+ "pt_XX",
502
+ "sv_SE",
503
+ "sw_KE",
504
+ "ta_IN",
505
+ "te_IN",
506
+ "th_TH",
507
+ "tl_XX",
508
+ "uk_UA",
509
+ "ur_PK",
510
+ "xh_ZA",
511
+ "gl_ES",
512
+ "sl_SI"
513
+ ],
514
+ "bos_token": "<s>",
515
+ "clean_up_tokenization_spaces": true,
516
+ "cls_token": "<s>",
517
+ "eos_token": "</s>",
518
+ "language_codes": "ML50",
519
+ "mask_token": "<mask>",
520
+ "model_max_length": 1000000000000000019884624838656,
521
+ "pad_token": "<pad>",
522
+ "sep_token": "</s>",
523
+ "sp_model_kwargs": {},
524
+ "src_lang": "en_XX",
525
+ "tgt_lang": null,
526
+ "tokenizer_class": "MBart50Tokenizer",
527
+ "unk_token": "<unk>"
528
+ }
trainer_state.json ADDED
@@ -0,0 +1,341 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 22079,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.022645953168168847,
13
+ "grad_norm": 6.0433220863342285,
14
+ "learning_rate": 1.9547080936636626e-05,
15
+ "loss": 1.9021,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.045291906336337694,
20
+ "grad_norm": 5.967625617980957,
21
+ "learning_rate": 1.9094161873273246e-05,
22
+ "loss": 1.312,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 0.06793785950450655,
27
+ "grad_norm": 6.04085636138916,
28
+ "learning_rate": 1.864124280990987e-05,
29
+ "loss": 1.079,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 0.09058381267267539,
34
+ "grad_norm": 4.7192912101745605,
35
+ "learning_rate": 1.8188323746546494e-05,
36
+ "loss": 0.919,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 0.11322976584084424,
41
+ "grad_norm": 5.109660625457764,
42
+ "learning_rate": 1.7735404683183118e-05,
43
+ "loss": 0.8596,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 0.1358757190090131,
48
+ "grad_norm": 4.687028884887695,
49
+ "learning_rate": 1.728248561981974e-05,
50
+ "loss": 0.7987,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.15852167217718194,
55
+ "grad_norm": 3.7766010761260986,
56
+ "learning_rate": 1.6829566556456363e-05,
57
+ "loss": 0.7281,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 0.18116762534535077,
62
+ "grad_norm": 4.304531574249268,
63
+ "learning_rate": 1.6376647493092987e-05,
64
+ "loss": 0.6821,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 0.20381357851351964,
69
+ "grad_norm": 5.7325968742370605,
70
+ "learning_rate": 1.5923728429729607e-05,
71
+ "loss": 0.6425,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 0.22645953168168848,
76
+ "grad_norm": 5.178163051605225,
77
+ "learning_rate": 1.547080936636623e-05,
78
+ "loss": 0.6295,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 0.24910548484985734,
83
+ "grad_norm": 3.056478500366211,
84
+ "learning_rate": 1.5017890303002855e-05,
85
+ "loss": 0.6005,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 0.2717514380180262,
90
+ "grad_norm": 4.0474467277526855,
91
+ "learning_rate": 1.4564971239639478e-05,
92
+ "loss": 0.5868,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.294397391186195,
97
+ "grad_norm": 3.2683613300323486,
98
+ "learning_rate": 1.4112052176276102e-05,
99
+ "loss": 0.5647,
100
+ "step": 6500
101
+ },
102
+ {
103
+ "epoch": 0.3170433443543639,
104
+ "grad_norm": 3.586979627609253,
105
+ "learning_rate": 1.3659133112912724e-05,
106
+ "loss": 0.5415,
107
+ "step": 7000
108
+ },
109
+ {
110
+ "epoch": 0.33968929752253274,
111
+ "grad_norm": 4.297875881195068,
112
+ "learning_rate": 1.3206214049549346e-05,
113
+ "loss": 0.5294,
114
+ "step": 7500
115
+ },
116
+ {
117
+ "epoch": 0.36233525069070155,
118
+ "grad_norm": 3.461622714996338,
119
+ "learning_rate": 1.2753294986185968e-05,
120
+ "loss": 0.5211,
121
+ "step": 8000
122
+ },
123
+ {
124
+ "epoch": 0.3849812038588704,
125
+ "grad_norm": 3.42155385017395,
126
+ "learning_rate": 1.2300375922822592e-05,
127
+ "loss": 0.505,
128
+ "step": 8500
129
+ },
130
+ {
131
+ "epoch": 0.4076271570270393,
132
+ "grad_norm": 3.385619878768921,
133
+ "learning_rate": 1.1847456859459216e-05,
134
+ "loss": 0.4997,
135
+ "step": 9000
136
+ },
137
+ {
138
+ "epoch": 0.43027311019520814,
139
+ "grad_norm": 3.422764778137207,
140
+ "learning_rate": 1.1394537796095839e-05,
141
+ "loss": 0.484,
142
+ "step": 9500
143
+ },
144
+ {
145
+ "epoch": 0.45291906336337695,
146
+ "grad_norm": 2.883808135986328,
147
+ "learning_rate": 1.0941618732732463e-05,
148
+ "loss": 0.4775,
149
+ "step": 10000
150
+ },
151
+ {
152
+ "epoch": 0.4755650165315458,
153
+ "grad_norm": 3.6908833980560303,
154
+ "learning_rate": 1.0488699669369085e-05,
155
+ "loss": 0.4739,
156
+ "step": 10500
157
+ },
158
+ {
159
+ "epoch": 0.4982109696997147,
160
+ "grad_norm": 3.540358066558838,
161
+ "learning_rate": 1.0035780606005707e-05,
162
+ "loss": 0.4584,
163
+ "step": 11000
164
+ },
165
+ {
166
+ "epoch": 0.5208569228678835,
167
+ "grad_norm": 3.336552858352661,
168
+ "learning_rate": 9.582861542642331e-06,
169
+ "loss": 0.4445,
170
+ "step": 11500
171
+ },
172
+ {
173
+ "epoch": 0.5435028760360524,
174
+ "grad_norm": 2.803347110748291,
175
+ "learning_rate": 9.129942479278953e-06,
176
+ "loss": 0.4435,
177
+ "step": 12000
178
+ },
179
+ {
180
+ "epoch": 0.5661488292042212,
181
+ "grad_norm": 3.0676352977752686,
182
+ "learning_rate": 8.677023415915576e-06,
183
+ "loss": 0.4312,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.58879478237239,
188
+ "grad_norm": 3.1657562255859375,
189
+ "learning_rate": 8.2241043525522e-06,
190
+ "loss": 0.4349,
191
+ "step": 13000
192
+ },
193
+ {
194
+ "epoch": 0.6114407355405589,
195
+ "grad_norm": 3.551663398742676,
196
+ "learning_rate": 7.771185289188824e-06,
197
+ "loss": 0.4255,
198
+ "step": 13500
199
+ },
200
+ {
201
+ "epoch": 0.6340866887087278,
202
+ "grad_norm": 2.3778510093688965,
203
+ "learning_rate": 7.318266225825446e-06,
204
+ "loss": 0.4148,
205
+ "step": 14000
206
+ },
207
+ {
208
+ "epoch": 0.6567326418768966,
209
+ "grad_norm": 3.684070587158203,
210
+ "learning_rate": 6.865347162462068e-06,
211
+ "loss": 0.4151,
212
+ "step": 14500
213
+ },
214
+ {
215
+ "epoch": 0.6793785950450655,
216
+ "grad_norm": 3.859379529953003,
217
+ "learning_rate": 6.412428099098692e-06,
218
+ "loss": 0.4113,
219
+ "step": 15000
220
+ },
221
+ {
222
+ "epoch": 0.7020245482132343,
223
+ "grad_norm": 3.526158094406128,
224
+ "learning_rate": 5.9595090357353145e-06,
225
+ "loss": 0.4124,
226
+ "step": 15500
227
+ },
228
+ {
229
+ "epoch": 0.7246705013814031,
230
+ "grad_norm": 3.6779990196228027,
231
+ "learning_rate": 5.506589972371938e-06,
232
+ "loss": 0.4032,
233
+ "step": 16000
234
+ },
235
+ {
236
+ "epoch": 0.747316454549572,
237
+ "grad_norm": 6.240302085876465,
238
+ "learning_rate": 5.05367090900856e-06,
239
+ "loss": 0.4019,
240
+ "step": 16500
241
+ },
242
+ {
243
+ "epoch": 0.7699624077177408,
244
+ "grad_norm": 3.5423877239227295,
245
+ "learning_rate": 4.600751845645184e-06,
246
+ "loss": 0.3845,
247
+ "step": 17000
248
+ },
249
+ {
250
+ "epoch": 0.7926083608859097,
251
+ "grad_norm": 3.668982982635498,
252
+ "learning_rate": 4.147832782281806e-06,
253
+ "loss": 0.3948,
254
+ "step": 17500
255
+ },
256
+ {
257
+ "epoch": 0.8152543140540786,
258
+ "grad_norm": 4.242081642150879,
259
+ "learning_rate": 3.6949137189184298e-06,
260
+ "loss": 0.3826,
261
+ "step": 18000
262
+ },
263
+ {
264
+ "epoch": 0.8379002672222474,
265
+ "grad_norm": 3.223057270050049,
266
+ "learning_rate": 3.2419946555550525e-06,
267
+ "loss": 0.3867,
268
+ "step": 18500
269
+ },
270
+ {
271
+ "epoch": 0.8605462203904163,
272
+ "grad_norm": 2.9004533290863037,
273
+ "learning_rate": 2.7890755921916756e-06,
274
+ "loss": 0.3894,
275
+ "step": 19000
276
+ },
277
+ {
278
+ "epoch": 0.883192173558585,
279
+ "grad_norm": 3.2891807556152344,
280
+ "learning_rate": 2.3361565288282987e-06,
281
+ "loss": 0.3793,
282
+ "step": 19500
283
+ },
284
+ {
285
+ "epoch": 0.9058381267267539,
286
+ "grad_norm": 2.6867599487304688,
287
+ "learning_rate": 1.8832374654649217e-06,
288
+ "loss": 0.3732,
289
+ "step": 20000
290
+ },
291
+ {
292
+ "epoch": 0.9284840798949228,
293
+ "grad_norm": 2.811148166656494,
294
+ "learning_rate": 1.4303184021015446e-06,
295
+ "loss": 0.3794,
296
+ "step": 20500
297
+ },
298
+ {
299
+ "epoch": 0.9511300330630916,
300
+ "grad_norm": 3.6918985843658447,
301
+ "learning_rate": 9.773993387381675e-07,
302
+ "loss": 0.3767,
303
+ "step": 21000
304
+ },
305
+ {
306
+ "epoch": 0.9737759862312605,
307
+ "grad_norm": 2.762467622756958,
308
+ "learning_rate": 5.244802753747906e-07,
309
+ "loss": 0.3741,
310
+ "step": 21500
311
+ },
312
+ {
313
+ "epoch": 0.9964219393994294,
314
+ "grad_norm": 2.7618136405944824,
315
+ "learning_rate": 7.156121201141356e-08,
316
+ "loss": 0.3751,
317
+ "step": 22000
318
+ }
319
+ ],
320
+ "logging_steps": 500,
321
+ "max_steps": 22079,
322
+ "num_input_tokens_seen": 0,
323
+ "num_train_epochs": 1,
324
+ "save_steps": 500,
325
+ "stateful_callbacks": {
326
+ "TrainerControl": {
327
+ "args": {
328
+ "should_epoch_stop": false,
329
+ "should_evaluate": false,
330
+ "should_log": false,
331
+ "should_save": true,
332
+ "should_training_stop": true
333
+ },
334
+ "attributes": {}
335
+ }
336
+ },
337
+ "total_flos": 6.147503784984576e+16,
338
+ "train_batch_size": 16,
339
+ "trial_name": null,
340
+ "trial_params": null
341
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c28896d438af0865607906065912ec16b4dccddfa1255fbd7c4418c34c81ee05
3
+ size 5368