Hugging Face's logo

Everlyn
/
transformer_en_de10ish

Transformers
PyTorch
mbart
text2text-generation
Model card Files
xet
 Community
1
Everlyn commited on
Commit
76c267d
·
1 Parent(s): cbded8f

model

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. config.json +36 -0
  3. generation_config.json +8 -0
  4. optimizer.pt +3 -0
  5. pytorch_model.bin +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. sentencepiece.bpe.model +3 -0
  9. special_tokens_map.json +63 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +76 -0
  12. trainer_state.json +316 -0
  13. training_args.bin +3 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Everlyn/transformer_base",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
+ "architectures": [
6
+ "MBartForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 0,
10
+ "classifier_dropout": 0.0,
11
+ "d_model": 512,
12
+ "decoder_attention_heads": 8,
13
+ "decoder_ffn_dim": 2048,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 6,
16
+ "decoder_start_token_id": 250003,
17
+ "dropout": 0.1,
18
+ "encoder_attention_heads": 8,
19
+ "encoder_ffn_dim": 2048,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 6,
22
+ "eos_token_id": 2,
23
+ "forced_bos_token_id": 250003,
24
+ "forced_eos_token_id": 2,
25
+ "init_std": 0.02,
26
+ "is_encoder_decoder": true,
27
+ "max_position_embeddings": 512,
28
+ "model_type": "mbart",
29
+ "num_hidden_layers": 6,
30
+ "pad_token_id": 1,
31
+ "scale_embedding": false,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.29.0.dev0",
34
+ "use_cache": true,
35
+ "vocab_size": 250054
36
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.29.0.dev0"
8
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc74b93a975fed23b8789251b71056d29adc3efb8c14c44ed7bf3154e2eb284e
3
+ size 1381725285
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c7cd8fa5df249705762ae1447dd8e2908f40394a27ad9108f962ca60577aced
3
+ size 691874225
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed671420c6317a9b517ee3e8d49f5873c69dfda369af00a3739d9c62b8ed9f1
3
+ size 17563
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:527efa9b9484c84224cb6dfcefb3464c8cbe71c670336a590ab3d0f0b5534fe9
3
+ size 623
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 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<mask>",
60
+ "pad_token": "<pad>",
61
+ "sep_token": "</s>",
62
+ "unk_token": "<unk>"
63
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d58a68c276b56fcc48c165c63f70e5e4d452b4182032a5f7a2d018f4aa1a889
3
+ size 17109752
tokenizer_config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
58
+ "cls_token": "<s>",
59
+ "eos_token": "</s>",
60
+ "mask_token": {
61
+ "__type": "AddedToken",
62
+ "content": "<mask>",
63
+ "lstrip": true,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ },
68
+ "model_max_length": 1024,
69
+ "pad_token": "<pad>",
70
+ "sep_token": "</s>",
71
+ "sp_model_kwargs": {},
72
+ "src_lang": null,
73
+ "tgt_lang": null,
74
+ "tokenizer_class": "MBart50Tokenizer",
75
+ "unk_token": "<unk>"
76
+ }
trainer_state.json ADDED
@@ -0,0 +1,316 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.3083005260197837,
5
+ "global_step": 25000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 4.9172842773954474e-05,
13
+ "loss": 7.5606,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.13,
18
+ "learning_rate": 4.8345685547908946e-05,
19
+ "loss": 5.6106,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.2,
24
+ "learning_rate": 4.751852832186342e-05,
25
+ "loss": 4.6836,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.26,
30
+ "learning_rate": 4.669137109581789e-05,
31
+ "loss": 4.0373,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.33,
36
+ "learning_rate": 4.586421386977237e-05,
37
+ "loss": 3.6003,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.4,
42
+ "learning_rate": 4.503705664372684e-05,
43
+ "loss": 3.2726,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.46,
48
+ "learning_rate": 4.4209899417681313e-05,
49
+ "loss": 3.0363,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.53,
54
+ "learning_rate": 4.338274219163579e-05,
55
+ "loss": 2.8696,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.6,
60
+ "learning_rate": 4.2555584965590264e-05,
61
+ "loss": 2.7368,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.66,
66
+ "learning_rate": 4.1728427739544736e-05,
67
+ "loss": 2.6329,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.73,
72
+ "learning_rate": 4.090127051349921e-05,
73
+ "loss": 2.5426,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.79,
78
+ "learning_rate": 4.007411328745368e-05,
79
+ "loss": 2.4677,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.86,
84
+ "learning_rate": 3.924695606140815e-05,
85
+ "loss": 2.4017,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.93,
90
+ "learning_rate": 3.8419798835362624e-05,
91
+ "loss": 2.3466,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.99,
96
+ "learning_rate": 3.75926416093171e-05,
97
+ "loss": 2.2957,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.06,
102
+ "learning_rate": 3.6765484383271575e-05,
103
+ "loss": 2.2443,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.12,
108
+ "learning_rate": 3.593832715722605e-05,
109
+ "loss": 2.2067,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.19,
114
+ "learning_rate": 3.511116993118052e-05,
115
+ "loss": 2.17,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 1.26,
120
+ "learning_rate": 3.428401270513499e-05,
121
+ "loss": 2.1339,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 1.32,
126
+ "learning_rate": 3.345685547908946e-05,
127
+ "loss": 2.1097,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 1.39,
132
+ "learning_rate": 3.2629698253043935e-05,
133
+ "loss": 2.0808,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 1.46,
138
+ "learning_rate": 3.1802541026998414e-05,
139
+ "loss": 2.0546,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 1.52,
144
+ "learning_rate": 3.0975383800952886e-05,
145
+ "loss": 2.0371,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 1.59,
150
+ "learning_rate": 3.014822657490736e-05,
151
+ "loss": 2.0158,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 1.65,
156
+ "learning_rate": 2.9321069348861834e-05,
157
+ "loss": 1.9924,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 1.72,
162
+ "learning_rate": 2.849391212281631e-05,
163
+ "loss": 1.9762,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 1.79,
168
+ "learning_rate": 2.766675489677078e-05,
169
+ "loss": 1.9568,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 1.85,
174
+ "learning_rate": 2.6839597670725253e-05,
175
+ "loss": 1.9439,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 1.92,
180
+ "learning_rate": 2.6012440444679725e-05,
181
+ "loss": 1.9298,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 1.98,
186
+ "learning_rate": 2.5185283218634197e-05,
187
+ "loss": 1.9172,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 2.05,
192
+ "learning_rate": 2.4358125992588673e-05,
193
+ "loss": 1.893,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 2.12,
198
+ "learning_rate": 2.3530968766543145e-05,
199
+ "loss": 1.8762,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 2.18,
204
+ "learning_rate": 2.270381154049762e-05,
205
+ "loss": 1.8717,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 2.25,
210
+ "learning_rate": 2.1876654314452092e-05,
211
+ "loss": 1.8579,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 2.32,
216
+ "learning_rate": 2.1049497088406564e-05,
217
+ "loss": 1.8454,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 2.38,
222
+ "learning_rate": 2.022233986236104e-05,
223
+ "loss": 1.8387,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 2.45,
228
+ "learning_rate": 1.939518263631551e-05,
229
+ "loss": 1.8287,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 2.51,
234
+ "learning_rate": 1.8568025410269984e-05,
235
+ "loss": 1.8253,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 2.58,
240
+ "learning_rate": 1.7740868184224456e-05,
241
+ "loss": 1.8145,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 2.65,
246
+ "learning_rate": 1.691371095817893e-05,
247
+ "loss": 1.8095,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 2.71,
252
+ "learning_rate": 1.6086553732133407e-05,
253
+ "loss": 1.8027,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 2.78,
258
+ "learning_rate": 1.525939650608788e-05,
259
+ "loss": 1.7982,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 2.85,
264
+ "learning_rate": 1.443223928004235e-05,
265
+ "loss": 1.7908,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 2.91,
270
+ "learning_rate": 1.3605082053996823e-05,
271
+ "loss": 1.7863,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 2.98,
276
+ "learning_rate": 1.2777924827951298e-05,
277
+ "loss": 1.7812,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 3.04,
282
+ "learning_rate": 1.1950767601905772e-05,
283
+ "loss": 1.7693,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 3.11,
288
+ "learning_rate": 1.1123610375860244e-05,
289
+ "loss": 1.7593,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 3.18,
294
+ "learning_rate": 1.0296453149814718e-05,
295
+ "loss": 1.757,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 3.24,
300
+ "learning_rate": 9.469295923769191e-06,
301
+ "loss": 1.7535,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 3.31,
306
+ "learning_rate": 8.642138697723663e-06,
307
+ "loss": 1.7508,
308
+ "step": 25000
309
+ }
310
+ ],
311
+ "max_steps": 30224,
312
+ "num_train_epochs": 4,
313
+ "total_flos": 7.166643794309775e+17,
314
+ "trial_name": null,
315
+ "trial_params": null
316
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b37d96fc9ec9baa99c6b7e5386ca82682e951e81c7e2f71c1c857cab5dbb17d8
3
+ size 3695