cuongtran commited on
Commit
4339654
1 Parent(s): 698fadf

First model version

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<mask>": 64000}
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/bartpho-word",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "architectures": [
6
+ "MBartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 1024,
12
+ "decoder_attention_heads": 16,
13
+ "decoder_ffn_dim": 4096,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 12,
16
+ "decoder_start_token_id": 0,
17
+ "dropout": 0.1,
18
+ "early_stopping": true,
19
+ "encoder_attention_heads": 16,
20
+ "encoder_ffn_dim": 4096,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 12,
23
+ "eos_token_id": 2,
24
+ "forced_eos_token_id": 2,
25
+ "gradient_checkpointing": false,
26
+ "init_std": 0.02,
27
+ "is_encoder_decoder": true,
28
+ "length_penalty": 2.0,
29
+ "max_length": 64,
30
+ "max_position_embeddings": 1024,
31
+ "model_type": "mbart",
32
+ "no_repeat_ngram_size": 3,
33
+ "num_beams": 4,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 1,
36
+ "scale_embedding": false,
37
+ "tokenizer_class": "PhobertTokenizer",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.11.0",
40
+ "use_cache": true,
41
+ "vocab_size": 64001
42
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77e3c122ccc8d84e009dc709d9de7e7ece0e4f1828c11b9b33c60b3c11a583b0
3
+ size 3363189907
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3166bbe19d118f84de499c45f73cba1c7e1e9ef616f85096e84e4b8a75e0994
3
+ size 1681892729
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f05a6f87b6161e9f9d451415015d6ca7cea5d9a9cb5f0e6507c7722be3fc27
3
+ size 14439
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:879fa1c41cc8b64fc7acc7ed8a998190e14241211838727bf47dc362e4b5f769
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "vinai/bartpho-word", "tokenizer_class": "PhobertTokenizer"}
trainer_state.json ADDED
@@ -0,0 +1,472 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9789902790843525,
5
+ "global_step": 38000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.04,
12
+ "learning_rate": 4.934671265809554e-05,
13
+ "loss": 2.5519,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.08,
18
+ "learning_rate": 4.8693425316191076e-05,
19
+ "loss": 2.5343,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.12,
24
+ "learning_rate": 4.804013797428661e-05,
25
+ "loss": 2.4991,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.16,
30
+ "learning_rate": 4.738685063238215e-05,
31
+ "loss": 2.475,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.2,
36
+ "learning_rate": 4.6733563290477686e-05,
37
+ "loss": 2.4791,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.24,
42
+ "learning_rate": 4.608027594857322e-05,
43
+ "loss": 2.4725,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.27,
48
+ "learning_rate": 4.542698860666876e-05,
49
+ "loss": 2.4255,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.31,
54
+ "learning_rate": 4.4773701264764296e-05,
55
+ "loss": 2.4452,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.35,
60
+ "learning_rate": 4.412041392285983e-05,
61
+ "loss": 2.4272,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.39,
66
+ "learning_rate": 4.346712658095537e-05,
67
+ "loss": 2.435,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.43,
72
+ "learning_rate": 4.2813839239050906e-05,
73
+ "loss": 2.4164,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.47,
78
+ "learning_rate": 4.216055189714644e-05,
79
+ "loss": 2.3954,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.51,
84
+ "learning_rate": 4.150726455524198e-05,
85
+ "loss": 2.3677,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.55,
90
+ "learning_rate": 4.0853977213337515e-05,
91
+ "loss": 2.3643,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.59,
96
+ "learning_rate": 4.020068987143305e-05,
97
+ "loss": 2.3596,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.63,
102
+ "learning_rate": 3.954740252952859e-05,
103
+ "loss": 2.3601,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.67,
108
+ "learning_rate": 3.8894115187624125e-05,
109
+ "loss": 2.3391,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.71,
114
+ "learning_rate": 3.824082784571966e-05,
115
+ "loss": 2.3418,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.74,
120
+ "learning_rate": 3.75875405038152e-05,
121
+ "loss": 2.3256,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.78,
126
+ "learning_rate": 3.6934253161910735e-05,
127
+ "loss": 2.3386,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.82,
132
+ "learning_rate": 3.628096582000627e-05,
133
+ "loss": 2.3078,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.86,
138
+ "learning_rate": 3.562767847810181e-05,
139
+ "loss": 2.3059,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.9,
144
+ "learning_rate": 3.497439113619735e-05,
145
+ "loss": 2.3098,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.94,
150
+ "learning_rate": 3.432110379429289e-05,
151
+ "loss": 2.3021,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.98,
156
+ "learning_rate": 3.366781645238842e-05,
157
+ "loss": 2.2801,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 1.02,
162
+ "learning_rate": 3.3014529110483955e-05,
163
+ "loss": 2.0588,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 1.06,
168
+ "learning_rate": 3.236124176857949e-05,
169
+ "loss": 1.8245,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 1.1,
174
+ "learning_rate": 3.170795442667503e-05,
175
+ "loss": 1.8411,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.14,
180
+ "learning_rate": 3.1054667084770565e-05,
181
+ "loss": 1.8267,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.18,
186
+ "learning_rate": 3.0401379742866105e-05,
187
+ "loss": 1.8376,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 1.22,
192
+ "learning_rate": 2.9748092400961642e-05,
193
+ "loss": 1.863,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 1.25,
198
+ "learning_rate": 2.909480505905718e-05,
199
+ "loss": 1.8302,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 1.29,
204
+ "learning_rate": 2.8441517717152715e-05,
205
+ "loss": 1.8444,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 1.33,
210
+ "learning_rate": 2.7788230375248252e-05,
211
+ "loss": 1.8417,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 1.37,
216
+ "learning_rate": 2.7134943033343785e-05,
217
+ "loss": 1.8576,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 1.41,
222
+ "learning_rate": 2.648165569143932e-05,
223
+ "loss": 1.8421,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 1.45,
228
+ "learning_rate": 2.5828368349534858e-05,
229
+ "loss": 1.8459,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 1.49,
234
+ "learning_rate": 2.51750810076304e-05,
235
+ "loss": 1.8438,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 1.53,
240
+ "learning_rate": 2.4521793665725935e-05,
241
+ "loss": 1.8263,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 1.57,
246
+ "learning_rate": 2.386850632382147e-05,
247
+ "loss": 1.8451,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 1.61,
252
+ "learning_rate": 2.3215218981917008e-05,
253
+ "loss": 1.8439,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 1.65,
258
+ "learning_rate": 2.256193164001254e-05,
259
+ "loss": 1.8529,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 1.69,
264
+ "learning_rate": 2.190864429810808e-05,
265
+ "loss": 1.8184,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 1.72,
270
+ "learning_rate": 2.1255356956203618e-05,
271
+ "loss": 1.8364,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 1.76,
276
+ "learning_rate": 2.0602069614299155e-05,
277
+ "loss": 1.831,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.8,
282
+ "learning_rate": 1.994878227239469e-05,
283
+ "loss": 1.8103,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.84,
288
+ "learning_rate": 1.9295494930490228e-05,
289
+ "loss": 1.8078,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 1.88,
294
+ "learning_rate": 1.8642207588585765e-05,
295
+ "loss": 1.8047,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 1.92,
300
+ "learning_rate": 1.79889202466813e-05,
301
+ "loss": 1.8155,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.96,
306
+ "learning_rate": 1.7335632904776838e-05,
307
+ "loss": 1.8136,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 2.0,
312
+ "learning_rate": 1.6682345562872375e-05,
313
+ "loss": 1.8019,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 2.04,
318
+ "learning_rate": 1.602905822096791e-05,
319
+ "loss": 1.3885,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 2.08,
324
+ "learning_rate": 1.5375770879063448e-05,
325
+ "loss": 1.3774,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 2.12,
330
+ "learning_rate": 1.4722483537158985e-05,
331
+ "loss": 1.3693,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 2.16,
336
+ "learning_rate": 1.4069196195254521e-05,
337
+ "loss": 1.3827,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 2.2,
342
+ "learning_rate": 1.341590885335006e-05,
343
+ "loss": 1.3755,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 2.23,
348
+ "learning_rate": 1.2762621511445595e-05,
349
+ "loss": 1.3739,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 2.27,
354
+ "learning_rate": 1.2109334169541131e-05,
355
+ "loss": 1.3798,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 2.31,
360
+ "learning_rate": 1.1456046827636668e-05,
361
+ "loss": 1.3705,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 2.35,
366
+ "learning_rate": 1.0802759485732206e-05,
367
+ "loss": 1.3847,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 2.39,
372
+ "learning_rate": 1.0149472143827741e-05,
373
+ "loss": 1.371,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 2.43,
378
+ "learning_rate": 9.49618480192328e-06,
379
+ "loss": 1.3661,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 2.47,
384
+ "learning_rate": 8.842897460018814e-06,
385
+ "loss": 1.3863,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 2.51,
390
+ "learning_rate": 8.189610118114353e-06,
391
+ "loss": 1.3819,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 2.55,
396
+ "learning_rate": 7.536322776209888e-06,
397
+ "loss": 1.3762,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 2.59,
402
+ "learning_rate": 6.883035434305425e-06,
403
+ "loss": 1.3733,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 2.63,
408
+ "learning_rate": 6.229748092400962e-06,
409
+ "loss": 1.3591,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 2.67,
414
+ "learning_rate": 5.576460750496499e-06,
415
+ "loss": 1.3756,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 2.7,
420
+ "learning_rate": 4.923173408592035e-06,
421
+ "loss": 1.3447,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 2.74,
426
+ "learning_rate": 4.269886066687572e-06,
427
+ "loss": 1.3656,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 2.78,
432
+ "learning_rate": 3.616598724783109e-06,
433
+ "loss": 1.3549,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 2.82,
438
+ "learning_rate": 2.963311382878645e-06,
439
+ "loss": 1.3691,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 2.86,
444
+ "learning_rate": 2.310024040974182e-06,
445
+ "loss": 1.3534,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 2.9,
450
+ "learning_rate": 1.6567366990697188e-06,
451
+ "loss": 1.3391,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 2.94,
456
+ "learning_rate": 1.0034493571652555e-06,
457
+ "loss": 1.3589,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 2.98,
462
+ "learning_rate": 3.5016201526079235e-07,
463
+ "loss": 1.3393,
464
+ "step": 38000
465
+ }
466
+ ],
467
+ "max_steps": 38268,
468
+ "num_train_epochs": 3,
469
+ "total_flos": 1.948577863019397e+17,
470
+ "trial_name": null,
471
+ "trial_params": null
472
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8173b272f255c5a49ec9002a75bee61ed6b115b21a5db6bbe045b732d6166814
3
+ size 2927
vocab.txt ADDED
The diff for this file is too large to render. See raw diff