Hugging Face's logo

schnell
/
bert-small-unidic-bpe

Fill-Mask
Transformers
PyTorch
TensorBoard
bert
Inference Endpoints
Model card Files Metrics Community
schnell commited on
Commit
f130419
•
1 Parent(s): 149a383

Training in progress, epoch 1

Browse files
Files changed (21) hide show
  1. .gitignore +1 -0
  2. config.json +24 -0
  3. last-checkpoint/config.json +24 -0
  4. last-checkpoint/generation_config.json +5 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scaler.pt +3 -0
  9. last-checkpoint/scheduler.pt +3 -0
  10. last-checkpoint/special_tokens_map.json +7 -0
  11. last-checkpoint/tokenizer.json +0 -0
  12. last-checkpoint/tokenizer_config.json +13 -0
  13. last-checkpoint/trainer_state.json +295 -0
  14. last-checkpoint/training_args.bin +3 -0
  15. pytorch_model.bin +3 -0
  16. runs/Feb20_18-27-58_ubuntu-2004/1676885321.0138385/events.out.tfevents.1676885321.ubuntu-2004.886785.1 +3 -0
  17. runs/Feb20_18-27-58_ubuntu-2004/events.out.tfevents.1676885321.ubuntu-2004.886785.0 +3 -0
  18. special_tokens_map.json +7 -0
  19. tokenizer.json +0 -0
  20. tokenizer_config.json +13 -0
  21. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 512,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2048,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 8,
16
+ "num_hidden_layers": 4,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.26.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 512,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2048,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 8,
16
+ "num_hidden_layers": 4,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.26.1",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 32000
24
+ }
last-checkpoint/generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 0,
4
+ "transformers_version": "4.26.1"
5
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20315281d2709eeaf40aef0b7cc4d196cd14608adb7bd0f2764153d10eb4b453
3
+ size 236470597
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb60d21e79b08d340917bd4193659ab665cae0e2926559f7d6fb69d778c1264
3
+ size 118243218
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b45169c2d7f760d0d63ab509780edaaef50645ee6919bb4678f28bb477deb54
3
+ size 15597
last-checkpoint/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c82be8dc5906dfab465533ffb74c437a07ef6699c0aaca81752078b7823155dc
3
+ size 557
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:546fe8726f6cfec6c57c4fbd26c11b0f2d923540abe005bb870e9a3e1931a49b
3
+ size 627
last-checkpoint/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
+ }
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 128,
5
+ "name_or_path": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/UnidicBpe",
6
+ "pad_token": "[PAD]",
7
+ "padding_side": "right",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/UnidicBpe/special_tokens_map.json",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "truncation_side": "right",
12
+ "unk_token": "[UNK]"
13
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,295 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "global_step": 22940,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 1.5566625155666254e-05,
13
+ "loss": 9.0543,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 3.113325031133251e-05,
19
+ "loss": 6.7369,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.07,
24
+ "learning_rate": 4.6699875466998756e-05,
25
+ "loss": 6.0998,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.09,
30
+ "learning_rate": 6.226650062266502e-05,
31
+ "loss": 5.4282,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.11,
36
+ "learning_rate": 7.783312577833126e-05,
37
+ "loss": 4.749,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.13,
42
+ "learning_rate": 9.339975093399751e-05,
43
+ "loss": 4.3351,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.15,
48
+ "learning_rate": 9.990941915030131e-05,
49
+ "loss": 4.0473,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.17,
54
+ "learning_rate": 9.975216073068553e-05,
55
+ "loss": 3.8251,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.2,
60
+ "learning_rate": 9.959490231106974e-05,
61
+ "loss": 3.6631,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.22,
66
+ "learning_rate": 9.943764389145395e-05,
67
+ "loss": 3.532,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.24,
72
+ "learning_rate": 9.928038547183816e-05,
73
+ "loss": 3.4285,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.26,
78
+ "learning_rate": 9.912312705222237e-05,
79
+ "loss": 3.3414,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.28,
84
+ "learning_rate": 9.89658686326066e-05,
85
+ "loss": 3.2622,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.31,
90
+ "learning_rate": 9.880861021299081e-05,
91
+ "loss": 3.2048,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.33,
96
+ "learning_rate": 9.865135179337502e-05,
97
+ "loss": 3.1463,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.35,
102
+ "learning_rate": 9.849409337375923e-05,
103
+ "loss": 3.0932,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.37,
108
+ "learning_rate": 9.833683495414345e-05,
109
+ "loss": 3.0433,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.39,
114
+ "learning_rate": 9.817957653452766e-05,
115
+ "loss": 3.0056,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.41,
120
+ "learning_rate": 9.802231811491189e-05,
121
+ "loss": 2.9611,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.44,
126
+ "learning_rate": 9.78650596952961e-05,
127
+ "loss": 2.9247,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.46,
132
+ "learning_rate": 9.77078012756803e-05,
133
+ "loss": 2.8874,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.48,
138
+ "learning_rate": 9.755054285606452e-05,
139
+ "loss": 2.8569,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.5,
144
+ "learning_rate": 9.739328443644873e-05,
145
+ "loss": 2.8276,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.52,
150
+ "learning_rate": 9.723602601683295e-05,
151
+ "loss": 2.7987,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.54,
156
+ "learning_rate": 9.70790821140564e-05,
157
+ "loss": 2.7716,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.57,
162
+ "learning_rate": 9.69218236944406e-05,
163
+ "loss": 2.745,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.59,
168
+ "learning_rate": 9.676456527482482e-05,
169
+ "loss": 2.7229,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.61,
174
+ "learning_rate": 9.660730685520904e-05,
175
+ "loss": 2.7021,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.63,
180
+ "learning_rate": 9.645036295243249e-05,
181
+ "loss": 2.679,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.65,
186
+ "learning_rate": 9.62931045328167e-05,
187
+ "loss": 2.6618,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.68,
192
+ "learning_rate": 9.61358461132009e-05,
193
+ "loss": 2.6444,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.7,
198
+ "learning_rate": 9.597858769358512e-05,
199
+ "loss": 2.6249,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.72,
204
+ "learning_rate": 9.582164379080856e-05,
205
+ "loss": 2.6169,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.74,
210
+ "learning_rate": 9.566438537119277e-05,
211
+ "loss": 2.5936,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.76,
216
+ "learning_rate": 9.5507126951577e-05,
217
+ "loss": 2.5854,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.78,
222
+ "learning_rate": 9.535018304880043e-05,
223
+ "loss": 2.5693,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.81,
228
+ "learning_rate": 9.519292462918465e-05,
229
+ "loss": 2.5525,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.83,
234
+ "learning_rate": 9.503566620956886e-05,
235
+ "loss": 2.539,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.85,
240
+ "learning_rate": 9.487840778995309e-05,
241
+ "loss": 2.5256,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.87,
246
+ "learning_rate": 9.47211493703373e-05,
247
+ "loss": 2.5207,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.89,
252
+ "learning_rate": 9.45638909507215e-05,
253
+ "loss": 2.5017,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.92,
258
+ "learning_rate": 9.440663253110572e-05,
259
+ "loss": 2.4895,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.94,
264
+ "learning_rate": 9.424968862832916e-05,
265
+ "loss": 2.4808,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.96,
270
+ "learning_rate": 9.409243020871337e-05,
271
+ "loss": 2.4713,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 0.98,
276
+ "learning_rate": 9.39351717890976e-05,
277
+ "loss": 2.4602,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.0,
282
+ "eval_accuracy": 0.5603946985569819,
283
+ "eval_loss": 2.3326776027679443,
284
+ "eval_runtime": 361.5158,
285
+ "eval_samples_per_second": 492.238,
286
+ "eval_steps_per_second": 30.765,
287
+ "step": 22940
288
+ }
289
+ ],
290
+ "max_steps": 321160,
291
+ "num_train_epochs": 14,
292
+ "total_flos": 1.7360137911435264e+17,
293
+ "trial_name": null,
294
+ "trial_params": null
295
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21dda82a5ed06968ea65861e4382100859f4eda48d2a75fee60005cb40e4082
3
+ size 3579
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb60d21e79b08d340917bd4193659ab665cae0e2926559f7d6fb69d778c1264
3
+ size 118243218
runs/Feb20_18-27-58_ubuntu-2004/1676885321.0138385/events.out.tfevents.1676885321.ubuntu-2004.886785.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44364b3babeea86e0b06e5fb0d42a07a6dfda07ef823e1f93605ad9e9adf7f32
3
+ size 5735
runs/Feb20_18-27-58_ubuntu-2004/events.out.tfevents.1676885321.ubuntu-2004.886785.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f30a6aa5e6d30d62cd28bab4145aefb7411eead1b80cf2fcedc8f1e2cf1b38c1
3
+ size 11185
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "model_max_length": 128,
5
+ "name_or_path": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/UnidicBpe",
6
+ "pad_token": "[PAD]",
7
+ "padding_side": "right",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": "/home/mdxuser/JSAI2023/train_tokenizer/pretrained_tokenizers/UnidicBpe/special_tokens_map.json",
10
+ "tokenizer_class": "PreTrainedTokenizerFast",
11
+ "truncation_side": "right",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21dda82a5ed06968ea65861e4382100859f4eda48d2a75fee60005cb40e4082
3
+ size 3579