Hugging Face's logo

jinbbong
/
kbert_base_esg_e3

Fill-Mask
Transformers
PyTorch
bert
Model card Files
xet
Community
1
jinbbong commited on
Commit
c60c5f4
·
1 Parent(s): d8ffa19

com1

Browse files
Files changed (8) hide show
  1. config.json +32 -0
  2. pytorch_model.bin +3 -0
  3. special_tokens_map.json +1 -0
  4. tokenizer_config.json +1 -0
  5. train_results.txt +3 -0
  6. trainer_state.json +274 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "kykim/bert-kor-base",
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "directionality": "bidi",
8
+ "embedding_size": 768,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-12,
16
+ "max_position_embeddings": 512,
17
+ "model_type": "bert",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 0,
21
+ "pooler_fc_size": 768,
22
+ "pooler_num_attention_heads": 12,
23
+ "pooler_num_fc_layers": 3,
24
+ "pooler_size_per_head": 128,
25
+ "pooler_type": "first_token_transform",
26
+ "position_embedding_type": "absolute",
27
+ "transformers_version": "4.2.2",
28
+ "type_vocab_size": 2,
29
+ "use_cache": true,
30
+ "vocab_size": 42000,
31
+ "xla_device": true
32
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b79b4f861e1c9d918aab62aeb68e0b04148c84d2a8c3f33bba20cf31d4cabe9
3
+ size 602629988
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "kykim/bert-kor-base", "do_basic_tokenize": true, "never_split": null}
train_results.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ epoch = 3.0
2
+ train_runtime = 922.3702
3
+ train_samples_per_second = 2.28
trainer_state.json ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 2103,
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": 4.88112220637185e-05,
13
+ "loss": 2.1376,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.14,
18
+ "learning_rate": 4.7622444127437e-05,
19
+ "loss": 2.0469,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.21,
24
+ "learning_rate": 4.64336661911555e-05,
25
+ "loss": 1.9498,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.29,
30
+ "learning_rate": 4.524488825487399e-05,
31
+ "loss": 1.9426,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.36,
36
+ "learning_rate": 4.405611031859249e-05,
37
+ "loss": 1.9435,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.43,
42
+ "learning_rate": 4.286733238231099e-05,
43
+ "loss": 1.9045,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.5,
48
+ "learning_rate": 4.167855444602948e-05,
49
+ "loss": 1.906,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.57,
54
+ "learning_rate": 4.048977650974798e-05,
55
+ "loss": 1.8587,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 0.64,
60
+ "learning_rate": 3.930099857346648e-05,
61
+ "loss": 1.8745,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 0.71,
66
+ "learning_rate": 3.811222063718498e-05,
67
+ "loss": 1.8128,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 0.78,
72
+ "learning_rate": 3.692344270090347e-05,
73
+ "loss": 1.8424,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 0.86,
78
+ "learning_rate": 3.573466476462197e-05,
79
+ "loss": 1.8223,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 0.93,
84
+ "learning_rate": 3.454588682834047e-05,
85
+ "loss": 1.7888,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 1.0,
90
+ "learning_rate": 3.3357108892058964e-05,
91
+ "loss": 1.9001,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 1.07,
96
+ "learning_rate": 3.216833095577747e-05,
97
+ "loss": 1.8496,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 1.14,
102
+ "learning_rate": 3.097955301949596e-05,
103
+ "loss": 1.7976,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 1.21,
108
+ "learning_rate": 2.9790775083214456e-05,
109
+ "loss": 1.8336,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 1.28,
114
+ "learning_rate": 2.8601997146932952e-05,
115
+ "loss": 1.8062,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 1.36,
120
+ "learning_rate": 2.7413219210651452e-05,
121
+ "loss": 1.7623,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 1.43,
126
+ "learning_rate": 2.6224441274369948e-05,
127
+ "loss": 1.7469,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 1.5,
132
+ "learning_rate": 2.5035663338088444e-05,
133
+ "loss": 1.7603,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 1.57,
138
+ "learning_rate": 2.3846885401806944e-05,
139
+ "loss": 1.784,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 1.64,
144
+ "learning_rate": 2.265810746552544e-05,
145
+ "loss": 1.7731,
146
+ "step": 1150
147
+ },
148
+ {
149
+ "epoch": 1.71,
150
+ "learning_rate": 2.146932952924394e-05,
151
+ "loss": 1.8078,
152
+ "step": 1200
153
+ },
154
+ {
155
+ "epoch": 1.78,
156
+ "learning_rate": 2.0280551592962436e-05,
157
+ "loss": 1.7908,
158
+ "step": 1250
159
+ },
160
+ {
161
+ "epoch": 1.85,
162
+ "learning_rate": 1.9091773656680932e-05,
163
+ "loss": 1.8231,
164
+ "step": 1300
165
+ },
166
+ {
167
+ "epoch": 1.93,
168
+ "learning_rate": 1.790299572039943e-05,
169
+ "loss": 1.7073,
170
+ "step": 1350
171
+ },
172
+ {
173
+ "epoch": 2.0,
174
+ "learning_rate": 1.6714217784117928e-05,
175
+ "loss": 1.7253,
176
+ "step": 1400
177
+ },
178
+ {
179
+ "epoch": 2.07,
180
+ "learning_rate": 1.5525439847836425e-05,
181
+ "loss": 1.688,
182
+ "step": 1450
183
+ },
184
+ {
185
+ "epoch": 2.14,
186
+ "learning_rate": 1.433666191155492e-05,
187
+ "loss": 1.7227,
188
+ "step": 1500
189
+ },
190
+ {
191
+ "epoch": 2.21,
192
+ "learning_rate": 1.314788397527342e-05,
193
+ "loss": 1.713,
194
+ "step": 1550
195
+ },
196
+ {
197
+ "epoch": 2.28,
198
+ "learning_rate": 1.1959106038991917e-05,
199
+ "loss": 1.6854,
200
+ "step": 1600
201
+ },
202
+ {
203
+ "epoch": 2.35,
204
+ "learning_rate": 1.0770328102710415e-05,
205
+ "loss": 1.6999,
206
+ "step": 1650
207
+ },
208
+ {
209
+ "epoch": 2.43,
210
+ "learning_rate": 9.581550166428911e-06,
211
+ "loss": 1.7437,
212
+ "step": 1700
213
+ },
214
+ {
215
+ "epoch": 2.5,
216
+ "learning_rate": 8.392772230147409e-06,
217
+ "loss": 1.7459,
218
+ "step": 1750
219
+ },
220
+ {
221
+ "epoch": 2.57,
222
+ "learning_rate": 7.203994293865907e-06,
223
+ "loss": 1.6915,
224
+ "step": 1800
225
+ },
226
+ {
227
+ "epoch": 2.64,
228
+ "learning_rate": 6.015216357584404e-06,
229
+ "loss": 1.7785,
230
+ "step": 1850
231
+ },
232
+ {
233
+ "epoch": 2.71,
234
+ "learning_rate": 4.826438421302901e-06,
235
+ "loss": 1.7103,
236
+ "step": 1900
237
+ },
238
+ {
239
+ "epoch": 2.78,
240
+ "learning_rate": 3.6376604850213982e-06,
241
+ "loss": 1.7363,
242
+ "step": 1950
243
+ },
244
+ {
245
+ "epoch": 2.85,
246
+ "learning_rate": 2.4488825487398953e-06,
247
+ "loss": 1.7628,
248
+ "step": 2000
249
+ },
250
+ {
251
+ "epoch": 2.92,
252
+ "learning_rate": 1.2601046124583929e-06,
253
+ "loss": 1.6434,
254
+ "step": 2050
255
+ },
256
+ {
257
+ "epoch": 3.0,
258
+ "learning_rate": 7.132667617689017e-08,
259
+ "loss": 1.6829,
260
+ "step": 2100
261
+ },
262
+ {
263
+ "epoch": 3.0,
264
+ "step": 2103,
265
+ "train_runtime": 922.3702,
266
+ "train_samples_per_second": 2.28
267
+ }
268
+ ],
269
+ "max_steps": 2103,
270
+ "num_train_epochs": 3,
271
+ "total_flos": 3889982746460160,
272
+ "trial_name": null,
273
+ "trial_params": null
274
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a07f8a55d9656704f814755ba4ffc0a6708d0e47522d4c022f5951ef34cb4031
3
+ size 1967
vocab.txt ADDED
The diff for this file is too large to render. See raw diff