Hugging Face's logo

katrinatan
/
xlm-roberta-base_ft_udpos213-vi

Token Classification
Transformers
PyTorch
xlm-roberta
Inference Endpoints
Model card Files Community
1
katrinatan commited on
Commit
077c0b7
·
verified ·
1 Parent(s): c6467fe

Upload 12 files

Browse files
Files changed (12) hide show
  1. all_results.json +15 -0
  2. config.json +67 -0
  3. eval_results.json +11 -0
  4. predictions/test_ft_udpos213-tl.results.json +1 -0
  5. predictions/test_ft_udpos213-tl.tsv +340 -0
  6. pytorch_model.bin +3 -0
  7. special_tokens_map.json +1 -0
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +1 -0
  10. train.args +1 -0
  11. train_results.json +7 -0
  12. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.71,
3
+ "eval_accuracy": 0.9072318630074153,
4
+ "eval_f1": 0.7754412279834796,
5
+ "eval_loss": 0.47113698720932007,
6
+ "eval_precision": 0.7710308213437561,
7
+ "eval_recall": 0.7826580556088215,
8
+ "eval_runtime": 24.8903,
9
+ "eval_samples_per_second": 45.118,
10
+ "eval_steps_per_second": 5.665,
11
+ "train_loss": 0.19868811893463134,
12
+ "train_runtime": 732.8661,
13
+ "train_samples_per_second": 10.916,
14
+ "train_steps_per_second": 1.365
15
+ }
config.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "xlm-roberta-base",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "ADJ",
16
+ "1": "ADP",
17
+ "2": "ADV",
18
+ "3": "AUX",
19
+ "4": "CCONJ",
20
+ "5": "DET",
21
+ "6": "INTJ",
22
+ "7": "NOUN",
23
+ "8": "NUM",
24
+ "9": "PART",
25
+ "10": "PRON",
26
+ "11": "PROPN",
27
+ "12": "PUNCT",
28
+ "13": "SCONJ",
29
+ "14": "SYM",
30
+ "15": "VERB",
31
+ "16": "X"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "ADJ": 0,
37
+ "ADP": 1,
38
+ "ADV": 2,
39
+ "AUX": 3,
40
+ "CCONJ": 4,
41
+ "DET": 5,
42
+ "INTJ": 6,
43
+ "NOUN": 7,
44
+ "NUM": 8,
45
+ "PART": 9,
46
+ "PRON": 10,
47
+ "PROPN": 11,
48
+ "PUNCT": 12,
49
+ "SCONJ": 13,
50
+ "SYM": 14,
51
+ "VERB": 15,
52
+ "X": 16
53
+ },
54
+ "layer_norm_eps": 1e-05,
55
+ "max_position_embeddings": 514,
56
+ "model_type": "xlm-roberta",
57
+ "num_attention_heads": 12,
58
+ "num_hidden_layers": 12,
59
+ "output_past": true,
60
+ "pad_token_id": 1,
61
+ "position_embedding_type": "absolute",
62
+ "torch_dtype": "float32",
63
+ "transformers_version": "4.10.2",
64
+ "type_vocab_size": 1,
65
+ "use_cache": true,
66
+ "vocab_size": 250002
67
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.71,
3
+ "eval_accuracy": 0.9072318630074153,
4
+ "eval_f1": 0.7754412279834796,
5
+ "eval_loss": 0.47113698720932007,
6
+ "eval_precision": 0.7710308213437561,
7
+ "eval_recall": 0.7826580556088215,
8
+ "eval_runtime": 24.8903,
9
+ "eval_samples_per_second": 45.118,
10
+ "eval_steps_per_second": 5.665
11
+ }
predictions/test_ft_udpos213-tl.results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"f1": 76.7848054220037}
predictions/test_ft_udpos213-tl.tsv ADDED
@@ -0,0 +1,340 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ PUNCT PUNCT
2
+ PROPN NOUN
3
+ ADV PART
4
+ NOUN PRON
5
+ PART PART
6
+ PUNCT PUNCT
7
+ PUNCT PUNCT
8
+ VERB VERB
9
+ PRON SCONJ
10
+ ADP ADP
11
+ NOUN NOUN
12
+ ADP SCONJ
13
+ PROPN PROPN
14
+ CCONJ CCONJ
15
+ VERB VERB
16
+ ADP ADP
17
+ NOUN NOUN
18
+ PRON PRON
19
+ PUNCT PUNCT
20
+ NOUN VERB
21
+ SCONJ PART
22
+ ADP ADP
23
+ NOUN NOUN
24
+ ADP PRON
25
+ NOUN NOUN
26
+ PRON PRON
27
+ PUNCT PUNCT
28
+ SCONJ ADP
29
+ VERB VERB
30
+ PRON PRON
31
+ ADP ADP
32
+ ADJ NOUN
33
+ PUNCT PUNCT
34
+ PRON PRON
35
+ ADP AUX
36
+ ADJ NOUN
37
+ PART ADP
38
+ NOUN NOUN
39
+ ADP ADP
40
+ NOUN NOUN
41
+ PUNCT PUNCT
42
+ ADP SCONJ
43
+ NOUN VERB
44
+ PRON PRON
45
+ PART PUNCT
46
+ ADJ NOUN
47
+ PART SCONJ
48
+ NOUN NOUN
49
+ CCONJ CCONJ
50
+ NOUN NOUN
51
+ PART SCONJ
52
+ ADV ADJ
53
+ ADJ ADJ
54
+ ADP ADP
55
+ PRON PRON
56
+ PUNCT PUNCT
57
+ ADJ ADJ
58
+ ADV ADV
59
+ ADP ADP
60
+ NOUN NOUN
61
+ PRON PRON
62
+ PUNCT PUNCT
63
+ VERB VERB
64
+ ADV ADV
65
+ PRON PRON
66
+ ADP ADP
67
+ DET DET
68
+ NOUN NOUN
69
+ PRON PRON
70
+ PUNCT PUNCT
71
+ ADV NOUN
72
+ PUNCT PUNCT
73
+ VERB VERB
74
+ PRON ADV
75
+ ADP ADP
76
+ NOUN NOUN
77
+ PUNCT PUNCT
78
+ VERB VERB
79
+ ADV ADV
80
+ ADP ADP
81
+ DET DET
82
+ NOUN NOUN
83
+ ADP ADP
84
+ NOUN PROPN
85
+ PUNCT PUNCT
86
+ VERB VERB
87
+ PRON ADV
88
+ PRON PRON
89
+ PUNCT PUNCT
90
+ ADV ADJ
91
+ ADV SCONJ
92
+ ADJ NOUN
93
+ ADP ADP
94
+ NOUN NOUN
95
+ SCONJ ADP
96
+ VERB VERB
97
+ PRON PRON
98
+ CCONJ CCONJ
99
+ VERB VERB
100
+ PUNCT PUNCT
101
+ ADV ADJ
102
+ ADV ADV
103
+ ADV PART
104
+ VERB ADV
105
+ VERB VERB
106
+ PART ADV
107
+ NOUN NOUN
108
+ ADP ADP
109
+ NOUN NOUN
110
+ PUNCT PUNCT
111
+ VERB VERB
112
+ ADP ADP
113
+ NOUN NOUN
114
+ PART ADP
115
+ NOUN PROPN
116
+ PUNCT PUNCT
117
+ CCONJ SCONJ
118
+ PART ADV
119
+ PRON PRON
120
+ VERB VERB
121
+ PUNCT PUNCT
122
+ VERB ADV
123
+ ADV PART
124
+ PRON PRON
125
+ PUNCT PUNCT
126
+ VERB VERB
127
+ PRON SCONJ
128
+ ADP SCONJ
129
+ NOUN PROPN
130
+ PART ADV
131
+ VERB VERB
132
+ ADV PART
133
+ PUNCT PUNCT
134
+ VERB VERB
135
+ ADV ADP
136
+ ADP NOUN
137
+ PROPN PROPN
138
+ ADP ADP
139
+ NOUN NOUN
140
+ PUNCT PUNCT
141
+ ADJ ADJ
142
+ ADV ADV
143
+ ADP ADP
144
+ NOUN NOUN
145
+ PART ADP
146
+ PRON PRON
147
+ PUNCT PUNCT
148
+ VERB VERB
149
+ PRON PRON
150
+ ADP ADP
151
+ DET DET
152
+ NOUN NOUN
153
+ PUNCT PUNCT
154
+ NOUN NOUN
155
+ ADP ADP
156
+ PROPN NOUN
157
+ PUNCT PUNCT
158
+ VERB VERB
159
+ PRON PRON
160
+ ADV PART
161
+ PART PART
162
+ ADP ADP
163
+ NOUN NOUN
164
+ PART ADV
165
+ VERB VERB
166
+ NOUN NOUN
167
+ ADP ADP
168
+ NOUN NOUN
169
+ PUNCT PUNCT
170
+ ADV VERB
171
+ ADP ADP
172
+ NOUN PROPN
173
+ ADP ADP
174
+ PROPN PROPN
175
+ ADP ADP
176
+ NOUN NOUN
177
+ ADP ADP
178
+ PROPN PROPN
179
+ PUNCT PUNCT
180
+ ADP ADP
181
+ NOUN NOUN
182
+ ADP ADP
183
+ NOUN NOUN
184
+ PRON PRON
185
+ PART AUX
186
+ ADP ADP
187
+ NOUN NOUN
188
+ PROPN PROPN
189
+ PUNCT PUNCT
190
+ ADJ VERB
191
+ ADV PART
192
+ PUNCT PUNCT
193
+ VERB VERB
194
+ PRON PRON
195
+ ADP ADP
196
+ NOUN NOUN
197
+ ADP VERB
198
+ ADP ADP
199
+ NOUN NOUN
200
+ PUNCT PUNCT
201
+ PART SCONJ
202
+ PRON PRON
203
+ VERB VERB
204
+ PUNCT PUNCT
205
+ NUM NUM
206
+ PART ADV
207
+ NOUN NOUN
208
+ ADP AUX
209
+ VERB VERB
210
+ PRON PRON
211
+ PUNCT PUNCT
212
+ PRON PRON
213
+ ADP PRON
214
+ PROPN PROPN
215
+ PROPN PROPN
216
+ PUNCT PUNCT
217
+ PROPN PROPN
218
+ PUNCT PUNCT
219
+ PROPN PROPN
220
+ PUNCT PUNCT
221
+ CCONJ SCONJ
222
+ PROPN PROPN
223
+ PUNCT PUNCT
224
+ VERB VERB
225
+ PRON PRON
226
+ ADV ADV
227
+ PART PART
228
+ ADP ADP
229
+ NOUN NOUN
230
+ PUNCT PUNCT
231
+ ADP ADP
232
+ PROPN PROPN
233
+ PROPN PROPN
234
+ NOUN PROPN
235
+ PART ADV
236
+ VERB VERB
237
+ ADV ADV
238
+ ADP ADP
239
+ NOUN NOUN
240
+ PART ADP
241
+ NOUN NOUN
242
+ PUNCT PUNCT
243
+ ADJ X
244
+ ADP ADP
245
+ PROPN PROPN
246
+ PROPN PROPN
247
+ NOUN PROPN
248
+ ADP ADP
249
+ PROPN PROPN
250
+ PUNCT PUNCT
251
+ VERB VERB
252
+ PRON ADV
253
+ PART PART
254
+ SCONJ SCONJ
255
+ PRON PRON
256
+ ADP ADP
257
+ NOUN NOUN
258
+ PUNCT PUNCT
259
+ PRON PRON
260
+ ADP AUX
261
+ ADJ ADJ
262
+ PART ADV
263
+ NOUN NOUN
264
+ PUNCT PUNCT
265
+ NOUN NOUN
266
+ PUNCT PUNCT
267
+ ADP VERB
268
+ ADP ADP
269
+ NOUN NOUN
270
+ ADP ADP
271
+ NOUN NOUN
272
+ ADP SCONJ
273
+ NOUN NOUN
274
+ ADP ADP
275
+ NOUN NOUN
276
+ PUNCT PUNCT
277
+ VERB VERB
278
+ DET DET
279
+ NOUN NOUN
280
+ PART SCONJ
281
+ ADJ ADJ
282
+ ADP ADP
283
+ NOUN NOUN
284
+ PUNCT PUNCT
285
+ ADJ ADJ
286
+ PRON PRON
287
+ ADP ADP
288
+ DET DET
289
+ NOUN NOUN
290
+ PART ADP
291
+ ADJ ADJ
292
+ ADP ADP
293
+ ADJ ADJ
294
+ PART ADP
295
+ NOUN NOUN
296
+ ADP ADP
297
+ NOUN NOUN
298
+ ADP ADP
299
+ NOUN NOUN
300
+ PUNCT PUNCT
301
+ VERB VERB
302
+ PRON PRON
303
+ ADJ ADJ
304
+ ADP ADP
305
+ NOUN PROPN
306
+ PROPN PROPN
307
+ PUNCT PUNCT
308
+ ADP ADP
309
+ NOUN NOUN
310
+ ADP ADP
311
+ ADJ ADJ
312
+ PART ADV
313
+ NOUN NOUN
314
+ PART ADP
315
+ PRON PRON
316
+ ADP ADP
317
+ ADP ADP
318
+ NOUN NOUN
319
+ PART AUX
320
+ VERB VERB
321
+ ADV ADV
322
+ ADP ADP
323
+ NOUN NOUN
324
+ PUNCT PUNCT
325
+ ADJ VERB
326
+ ADV PART
327
+ ADP ADP
328
+ DET DET
329
+ NOUN NOUN
330
+ PUNCT PUNCT
331
+ NOUN NOUN
332
+ ADP ADP
333
+ PROPN PROPN
334
+ PUNCT PUNCT
335
+ ADJ ADJ
336
+ ADV ADV
337
+ ADP ADP
338
+ DET DET
339
+ NUM PRON
340
+ PUNCT PUNCT
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8eec604351de150a1422e740a727998a39e746dfc82b8f53df79c82af45533
3
+ size 1109946481
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": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "add_prefix_space": true, "special_tokens_map_file": null, "name_or_path": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
train.args ADDED
@@ -0,0 +1 @@
 
 
1
+ udpos --learning_rate=5e-5 --eval_steps=1000 --per_device_batch_size=10 --max_steps=1000 --multi
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.71,
3
+ "train_loss": 0.19868811893463134,
4
+ "train_runtime": 732.8661,
5
+ "train_samples_per_second": 10.916,
6
+ "train_steps_per_second": 1.365
7
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b7a37e283a06bc402762728d3a3e2e602cc4a9080075f4940425cf67e04102
3
+ size 2735