Hugging Face's logo

brao
/
innox-bert

Token Classification
Transformers
PyTorch
English
bert
Model card Files
xet
 Community
1
brao commited on
Commit
7a90dee
·
1 Parent(s): 44479bb

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +56 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. special_tokens_map.json +7 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +15 -0
  9. trainer_state.json +340 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-large-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12"
26
+ },
27
+ "initializer_range": 0.02,
28
+ "intermediate_size": 4096,
29
+ "label2id": {
30
+ "LABEL_0": 0,
31
+ "LABEL_1": 1,
32
+ "LABEL_10": 10,
33
+ "LABEL_11": 11,
34
+ "LABEL_12": 12,
35
+ "LABEL_2": 2,
36
+ "LABEL_3": 3,
37
+ "LABEL_4": 4,
38
+ "LABEL_5": 5,
39
+ "LABEL_6": 6,
40
+ "LABEL_7": 7,
41
+ "LABEL_8": 8,
42
+ "LABEL_9": 9
43
+ },
44
+ "layer_norm_eps": 1e-12,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "bert",
47
+ "num_attention_heads": 16,
48
+ "num_hidden_layers": 24,
49
+ "pad_token_id": 0,
50
+ "position_embedding_type": "absolute",
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.25.1",
53
+ "type_vocab_size": 2,
54
+ "use_cache": true,
55
+ "vocab_size": 30522
56
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e60002e133897c4024a2dc8515b343843d994db18bf2cc78965f7d9cf5511c
3
+ size 2673072357
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89867acad0de4ecc45896e74fb6aab16c2ca6b6f758df173f7e41d48b7c2b1b9
3
+ size 1336557745
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74390ceb0548fc77a41fab0d84e03929f2835125c156040f32a4081e84d195e0
3
+ size 17563
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42c2522d9deea9ff7150a1554c735edc63b6ff8849453f55081ce2d93c2b680a
3
+ size 623
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ {
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "name_or_path": "bert-large-uncased",
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
trainer_state.json ADDED
@@ -0,0 +1,340 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 25.0,
5
+ "global_step": 2125,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.8444531864673486,
13
+ "eval_f1": 0.5546590729314982,
14
+ "eval_loss": 0.5102574229240417,
15
+ "eval_precision": 0.5133235724743778,
16
+ "eval_recall": 0.6032346868547832,
17
+ "eval_runtime": 19.295,
18
+ "eval_samples_per_second": 140.451,
19
+ "eval_steps_per_second": 1.14,
20
+ "step": 85
21
+ },
22
+ {
23
+ "epoch": 2.0,
24
+ "eval_accuracy": 0.8653029110936271,
25
+ "eval_f1": 0.6414725525329859,
26
+ "eval_loss": 0.43876737356185913,
27
+ "eval_precision": 0.6090318589545314,
28
+ "eval_recall": 0.6775636613902272,
29
+ "eval_runtime": 19.3861,
30
+ "eval_samples_per_second": 139.791,
31
+ "eval_steps_per_second": 1.135,
32
+ "step": 170
33
+ },
34
+ {
35
+ "epoch": 3.0,
36
+ "eval_accuracy": 0.8793863099921322,
37
+ "eval_f1": 0.6583135794107687,
38
+ "eval_loss": 0.3875023424625397,
39
+ "eval_precision": 0.648,
40
+ "eval_recall": 0.6689607708189952,
41
+ "eval_runtime": 19.4498,
42
+ "eval_samples_per_second": 139.333,
43
+ "eval_steps_per_second": 1.131,
44
+ "step": 255
45
+ },
46
+ {
47
+ "epoch": 4.0,
48
+ "eval_accuracy": 0.8793076317859952,
49
+ "eval_f1": 0.6649093904448106,
50
+ "eval_loss": 0.42981019616127014,
51
+ "eval_precision": 0.6378002528445006,
52
+ "eval_recall": 0.6944253269098417,
53
+ "eval_runtime": 19.1858,
54
+ "eval_samples_per_second": 141.25,
55
+ "eval_steps_per_second": 1.147,
56
+ "step": 340
57
+ },
58
+ {
59
+ "epoch": 5.0,
60
+ "eval_accuracy": 0.8806845003933911,
61
+ "eval_f1": 0.6834983498349835,
62
+ "eval_loss": 0.4551577568054199,
63
+ "eval_precision": 0.6566265060240963,
64
+ "eval_recall": 0.7126634549208534,
65
+ "eval_runtime": 19.2293,
66
+ "eval_samples_per_second": 140.93,
67
+ "eval_steps_per_second": 1.144,
68
+ "step": 425
69
+ },
70
+ {
71
+ "epoch": 5.88,
72
+ "learning_rate": 2.526771764705882e-05,
73
+ "loss": 0.3534,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 6.0,
78
+ "eval_accuracy": 0.8738788355625492,
79
+ "eval_f1": 0.6940358816874092,
80
+ "eval_loss": 0.5596204996109009,
81
+ "eval_precision": 0.6543736665650717,
82
+ "eval_recall": 0.7388162422573985,
83
+ "eval_runtime": 19.5147,
84
+ "eval_samples_per_second": 138.87,
85
+ "eval_steps_per_second": 1.127,
86
+ "step": 510
87
+ },
88
+ {
89
+ "epoch": 7.0,
90
+ "eval_accuracy": 0.8817073170731707,
91
+ "eval_f1": 0.6971866156151157,
92
+ "eval_loss": 0.5754502415657043,
93
+ "eval_precision": 0.6752660432118671,
94
+ "eval_recall": 0.7205781142463867,
95
+ "eval_runtime": 19.1934,
96
+ "eval_samples_per_second": 141.194,
97
+ "eval_steps_per_second": 1.146,
98
+ "step": 595
99
+ },
100
+ {
101
+ "epoch": 8.0,
102
+ "eval_accuracy": 0.879897718332022,
103
+ "eval_f1": 0.7010550996483003,
104
+ "eval_loss": 0.6235392093658447,
105
+ "eval_precision": 0.6828711256117456,
106
+ "eval_recall": 0.7202339986235375,
107
+ "eval_runtime": 19.2793,
108
+ "eval_samples_per_second": 140.565,
109
+ "eval_steps_per_second": 1.141,
110
+ "step": 680
111
+ },
112
+ {
113
+ "epoch": 9.0,
114
+ "eval_accuracy": 0.8861132966168371,
115
+ "eval_f1": 0.7035076108537393,
116
+ "eval_loss": 0.6701436638832092,
117
+ "eval_precision": 0.6775015933715742,
118
+ "eval_recall": 0.7315898141775636,
119
+ "eval_runtime": 19.3944,
120
+ "eval_samples_per_second": 139.731,
121
+ "eval_steps_per_second": 1.134,
122
+ "step": 765
123
+ },
124
+ {
125
+ "epoch": 10.0,
126
+ "eval_accuracy": 0.8706530291109362,
127
+ "eval_f1": 0.6894660429101467,
128
+ "eval_loss": 0.7287982106208801,
129
+ "eval_precision": 0.6489523231096265,
130
+ "eval_recall": 0.7353750860289057,
131
+ "eval_runtime": 19.3186,
132
+ "eval_samples_per_second": 140.279,
133
+ "eval_steps_per_second": 1.139,
134
+ "step": 850
135
+ },
136
+ {
137
+ "epoch": 11.0,
138
+ "eval_accuracy": 0.877537372147915,
139
+ "eval_f1": 0.6930596285434995,
140
+ "eval_loss": 0.7054932713508606,
141
+ "eval_precision": 0.6581064356435643,
142
+ "eval_recall": 0.7319339298004129,
143
+ "eval_runtime": 19.2233,
144
+ "eval_samples_per_second": 140.975,
145
+ "eval_steps_per_second": 1.144,
146
+ "step": 935
147
+ },
148
+ {
149
+ "epoch": 11.76,
150
+ "learning_rate": 1.7493035294117648e-05,
151
+ "loss": 0.0425,
152
+ "step": 1000
153
+ },
154
+ {
155
+ "epoch": 12.0,
156
+ "eval_accuracy": 0.8837529504327302,
157
+ "eval_f1": 0.7010959814015278,
158
+ "eval_loss": 0.7131127119064331,
159
+ "eval_precision": 0.6774711168164314,
160
+ "eval_recall": 0.7264280798348245,
161
+ "eval_runtime": 19.4321,
162
+ "eval_samples_per_second": 139.46,
163
+ "eval_steps_per_second": 1.132,
164
+ "step": 1020
165
+ },
166
+ {
167
+ "epoch": 13.0,
168
+ "eval_accuracy": 0.8865460267505901,
169
+ "eval_f1": 0.71240632805995,
170
+ "eval_loss": 0.7414566278457642,
171
+ "eval_precision": 0.6902226524685382,
172
+ "eval_recall": 0.7360633172746043,
173
+ "eval_runtime": 19.4932,
174
+ "eval_samples_per_second": 139.023,
175
+ "eval_steps_per_second": 1.129,
176
+ "step": 1105
177
+ },
178
+ {
179
+ "epoch": 14.0,
180
+ "eval_accuracy": 0.8769079464988199,
181
+ "eval_f1": 0.7031301482701812,
182
+ "eval_loss": 0.820663332939148,
183
+ "eval_precision": 0.6744627054361567,
184
+ "eval_recall": 0.7343427391603579,
185
+ "eval_runtime": 19.2777,
186
+ "eval_samples_per_second": 140.577,
187
+ "eval_steps_per_second": 1.141,
188
+ "step": 1190
189
+ },
190
+ {
191
+ "epoch": 15.0,
192
+ "eval_accuracy": 0.8817859952793077,
193
+ "eval_f1": 0.7152581769882118,
194
+ "eval_loss": 0.8483569622039795,
195
+ "eval_precision": 0.6910490856592878,
196
+ "eval_recall": 0.7412250516173434,
197
+ "eval_runtime": 19.4808,
198
+ "eval_samples_per_second": 139.112,
199
+ "eval_steps_per_second": 1.129,
200
+ "step": 1275
201
+ },
202
+ {
203
+ "epoch": 16.0,
204
+ "eval_accuracy": 0.8836349331235248,
205
+ "eval_f1": 0.7072444591465431,
206
+ "eval_loss": 0.8380259275436401,
207
+ "eval_precision": 0.6808917197452229,
208
+ "eval_recall": 0.735719201651755,
209
+ "eval_runtime": 19.2903,
210
+ "eval_samples_per_second": 140.485,
211
+ "eval_steps_per_second": 1.14,
212
+ "step": 1360
213
+ },
214
+ {
215
+ "epoch": 17.0,
216
+ "eval_accuracy": 0.8843430369787569,
217
+ "eval_f1": 0.7132094424912104,
218
+ "eval_loss": 0.8519468307495117,
219
+ "eval_precision": 0.6944897293772416,
220
+ "eval_recall": 0.7329662766689607,
221
+ "eval_runtime": 19.2344,
222
+ "eval_samples_per_second": 140.893,
223
+ "eval_steps_per_second": 1.144,
224
+ "step": 1445
225
+ },
226
+ {
227
+ "epoch": 17.65,
228
+ "learning_rate": 9.71835294117647e-06,
229
+ "loss": 0.0084,
230
+ "step": 1500
231
+ },
232
+ {
233
+ "epoch": 18.0,
234
+ "eval_accuracy": 0.8830841856805665,
235
+ "eval_f1": 0.7116891779222945,
236
+ "eval_loss": 0.8689035773277283,
237
+ "eval_precision": 0.6903914590747331,
238
+ "eval_recall": 0.7343427391603579,
239
+ "eval_runtime": 19.4385,
240
+ "eval_samples_per_second": 139.414,
241
+ "eval_steps_per_second": 1.132,
242
+ "step": 1530
243
+ },
244
+ {
245
+ "epoch": 19.0,
246
+ "eval_accuracy": 0.8835562549173879,
247
+ "eval_f1": 0.7146202743392439,
248
+ "eval_loss": 0.8715231418609619,
249
+ "eval_precision": 0.6953125,
250
+ "eval_recall": 0.7350309704060565,
251
+ "eval_runtime": 19.2513,
252
+ "eval_samples_per_second": 140.77,
253
+ "eval_steps_per_second": 1.143,
254
+ "step": 1615
255
+ },
256
+ {
257
+ "epoch": 20.0,
258
+ "eval_accuracy": 0.885483870967742,
259
+ "eval_f1": 0.7111858704793944,
260
+ "eval_loss": 0.8707020282745361,
261
+ "eval_precision": 0.6956235603817045,
262
+ "eval_recall": 0.7274604267033723,
263
+ "eval_runtime": 19.2021,
264
+ "eval_samples_per_second": 141.13,
265
+ "eval_steps_per_second": 1.146,
266
+ "step": 1700
267
+ },
268
+ {
269
+ "epoch": 21.0,
270
+ "eval_accuracy": 0.8852478363493312,
271
+ "eval_f1": 0.7130956347884039,
272
+ "eval_loss": 0.8659564256668091,
273
+ "eval_precision": 0.6912144702842378,
274
+ "eval_recall": 0.7364074328974536,
275
+ "eval_runtime": 19.3453,
276
+ "eval_samples_per_second": 140.086,
277
+ "eval_steps_per_second": 1.137,
278
+ "step": 1785
279
+ },
280
+ {
281
+ "epoch": 22.0,
282
+ "eval_accuracy": 0.8861132966168371,
283
+ "eval_f1": 0.7195429339606789,
284
+ "eval_loss": 0.8910586833953857,
285
+ "eval_precision": 0.7031198686371101,
286
+ "eval_recall": 0.7367515485203028,
287
+ "eval_runtime": 19.253,
288
+ "eval_samples_per_second": 140.757,
289
+ "eval_steps_per_second": 1.143,
290
+ "step": 1870
291
+ },
292
+ {
293
+ "epoch": 23.0,
294
+ "eval_accuracy": 0.8848544453186468,
295
+ "eval_f1": 0.7184726176519846,
296
+ "eval_loss": 0.9158034920692444,
297
+ "eval_precision": 0.6998368678629691,
298
+ "eval_recall": 0.7381280110116999,
299
+ "eval_runtime": 19.2359,
300
+ "eval_samples_per_second": 140.882,
301
+ "eval_steps_per_second": 1.144,
302
+ "step": 1955
303
+ },
304
+ {
305
+ "epoch": 23.53,
306
+ "learning_rate": 1.943670588235294e-06,
307
+ "loss": 0.0026,
308
+ "step": 2000
309
+ },
310
+ {
311
+ "epoch": 24.0,
312
+ "eval_accuracy": 0.8862706530291109,
313
+ "eval_f1": 0.7187237615449201,
314
+ "eval_loss": 0.9025561809539795,
315
+ "eval_precision": 0.7018694653984913,
316
+ "eval_recall": 0.7364074328974536,
317
+ "eval_runtime": 19.4156,
318
+ "eval_samples_per_second": 139.578,
319
+ "eval_steps_per_second": 1.133,
320
+ "step": 2040
321
+ },
322
+ {
323
+ "epoch": 25.0,
324
+ "eval_accuracy": 0.8865066876475216,
325
+ "eval_f1": 0.718912569223024,
326
+ "eval_loss": 0.9014936089515686,
327
+ "eval_precision": 0.7016049787094661,
328
+ "eval_recall": 0.7370956641431521,
329
+ "eval_runtime": 19.2209,
330
+ "eval_samples_per_second": 140.992,
331
+ "eval_steps_per_second": 1.145,
332
+ "step": 2125
333
+ }
334
+ ],
335
+ "max_steps": 2125,
336
+ "num_train_epochs": 25,
337
+ "total_flos": 1.5762129485609082e+16,
338
+ "trial_name": null,
339
+ "trial_params": null
340
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbe7cdcd926dae7c2318f04bcf681a1ab9fa3c0d3736d6d2968248c5934cfc06
3
+ size 3375
vocab.txt ADDED
The diff for this file is too large to render. See raw diff