Hugging Face's logo

kornwtp
/
ThaiBERT-Tiny

Fill-Mask
Transformers
PyTorch
bert
Model card Files
xet
 Community
1
kornwtp commited on
Commit
e1d9668
·
1 Parent(s): c6f8471

Upload 9 files

Browse files
Files changed (9) hide show
  1. config.json +24 -0
  2. optimizer.pt +3 -0
  3. pytorch_model.bin +3 -0
  4. rng_state.pth +3 -0
  5. scheduler.pt +3 -0
  6. tokenizer_config.json +1 -0
  7. trainer_state.json +268 -0
  8. training_args.bin +3 -0
  9. vocab.txt +0 -0
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": 128,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 512,
12
+ "layer_norm_eps": 1e-12,
13
+ "max_position_embeddings": 512,
14
+ "model_type": "bert",
15
+ "num_attention_heads": 2,
16
+ "num_hidden_layers": 2,
17
+ "pad_token_id": 0,
18
+ "position_embedding_type": "absolute",
19
+ "torch_dtype": "float32",
20
+ "transformers_version": "4.21.2",
21
+ "type_vocab_size": 2,
22
+ "use_cache": true,
23
+ "vocab_size": 30522
24
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266464c1d86337b00ff13027c7b0ef22e69a7b2c0055ac54666a5e8dadc76b64
3
+ size 35359779
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2da38c00e25fc591778700d5c31d4b3ba294c43630fa36113acbe9671c4f7e1
3
+ size 17686130
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef8c46b0a525c0f9ff53a1635276e5997e740b473c4f30e2b35825973722c2f
3
+ size 14657
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5fba7cbe13253e3ed2f1e63ef62343f057badfdc91b8c0fa87518c69863a40f
3
+ size 623
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]", "model_max_length": 512, "max_len": 512}
trainer_state.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.693464588460486,
5
+ "global_step": 18000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.09,
12
+ "learning_rate": 4.726477024070022e-05,
13
+ "loss": 9.1433,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 1.09,
18
+ "eval_loss": 8.796442985534668,
19
+ "eval_runtime": 3.8329,
20
+ "eval_samples_per_second": 2301.909,
21
+ "eval_steps_per_second": 36.004,
22
+ "step": 1000
23
+ },
24
+ {
25
+ "epoch": 2.19,
26
+ "learning_rate": 4.452954048140044e-05,
27
+ "loss": 8.6087,
28
+ "step": 2000
29
+ },
30
+ {
31
+ "epoch": 2.19,
32
+ "eval_loss": 8.433659553527832,
33
+ "eval_runtime": 3.759,
34
+ "eval_samples_per_second": 2347.193,
35
+ "eval_steps_per_second": 36.712,
36
+ "step": 2000
37
+ },
38
+ {
39
+ "epoch": 3.28,
40
+ "learning_rate": 4.179431072210066e-05,
41
+ "loss": 8.279,
42
+ "step": 3000
43
+ },
44
+ {
45
+ "epoch": 3.28,
46
+ "eval_loss": 8.201327323913574,
47
+ "eval_runtime": 3.7567,
48
+ "eval_samples_per_second": 2348.629,
49
+ "eval_steps_per_second": 36.735,
50
+ "step": 3000
51
+ },
52
+ {
53
+ "epoch": 4.38,
54
+ "learning_rate": 3.9059080962800876e-05,
55
+ "loss": 8.0793,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 4.38,
60
+ "eval_loss": 8.072661399841309,
61
+ "eval_runtime": 3.7318,
62
+ "eval_samples_per_second": 2364.306,
63
+ "eval_steps_per_second": 36.98,
64
+ "step": 4000
65
+ },
66
+ {
67
+ "epoch": 5.47,
68
+ "learning_rate": 3.6323851203501094e-05,
69
+ "loss": 7.9475,
70
+ "step": 5000
71
+ },
72
+ {
73
+ "epoch": 5.47,
74
+ "eval_loss": 7.999021530151367,
75
+ "eval_runtime": 3.764,
76
+ "eval_samples_per_second": 2344.05,
77
+ "eval_steps_per_second": 36.663,
78
+ "step": 5000
79
+ },
80
+ {
81
+ "epoch": 6.56,
82
+ "learning_rate": 3.358862144420131e-05,
83
+ "loss": 7.8577,
84
+ "step": 6000
85
+ },
86
+ {
87
+ "epoch": 6.56,
88
+ "eval_loss": 7.939911365509033,
89
+ "eval_runtime": 3.6792,
90
+ "eval_samples_per_second": 2398.058,
91
+ "eval_steps_per_second": 37.508,
92
+ "step": 6000
93
+ },
94
+ {
95
+ "epoch": 7.66,
96
+ "learning_rate": 3.085339168490153e-05,
97
+ "loss": 7.7935,
98
+ "step": 7000
99
+ },
100
+ {
101
+ "epoch": 7.66,
102
+ "eval_loss": 7.911438941955566,
103
+ "eval_runtime": 3.6878,
104
+ "eval_samples_per_second": 2392.511,
105
+ "eval_steps_per_second": 37.421,
106
+ "step": 7000
107
+ },
108
+ {
109
+ "epoch": 8.75,
110
+ "learning_rate": 2.811816192560175e-05,
111
+ "loss": 7.7466,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 8.75,
116
+ "eval_loss": 7.892585277557373,
117
+ "eval_runtime": 3.7467,
118
+ "eval_samples_per_second": 2354.877,
119
+ "eval_steps_per_second": 36.832,
120
+ "step": 8000
121
+ },
122
+ {
123
+ "epoch": 9.85,
124
+ "learning_rate": 2.538293216630197e-05,
125
+ "loss": 7.7115,
126
+ "step": 9000
127
+ },
128
+ {
129
+ "epoch": 9.85,
130
+ "eval_loss": 7.864039421081543,
131
+ "eval_runtime": 3.6874,
132
+ "eval_samples_per_second": 2392.746,
133
+ "eval_steps_per_second": 37.425,
134
+ "step": 9000
135
+ },
136
+ {
137
+ "epoch": 10.94,
138
+ "learning_rate": 2.264770240700219e-05,
139
+ "loss": 7.6821,
140
+ "step": 10000
141
+ },
142
+ {
143
+ "epoch": 10.94,
144
+ "eval_loss": 7.849886417388916,
145
+ "eval_runtime": 3.6752,
146
+ "eval_samples_per_second": 2400.679,
147
+ "eval_steps_per_second": 37.549,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 12.04,
152
+ "learning_rate": 1.9912472647702408e-05,
153
+ "loss": 7.6611,
154
+ "step": 11000
155
+ },
156
+ {
157
+ "epoch": 12.04,
158
+ "eval_loss": 7.837656021118164,
159
+ "eval_runtime": 3.6572,
160
+ "eval_samples_per_second": 2412.526,
161
+ "eval_steps_per_second": 37.734,
162
+ "step": 11000
163
+ },
164
+ {
165
+ "epoch": 13.13,
166
+ "learning_rate": 1.7177242888402626e-05,
167
+ "loss": 7.64,
168
+ "step": 12000
169
+ },
170
+ {
171
+ "epoch": 13.13,
172
+ "eval_loss": 7.833044528961182,
173
+ "eval_runtime": 3.7781,
174
+ "eval_samples_per_second": 2335.296,
175
+ "eval_steps_per_second": 36.526,
176
+ "step": 12000
177
+ },
178
+ {
179
+ "epoch": 14.22,
180
+ "learning_rate": 1.4442013129102846e-05,
181
+ "loss": 7.6245,
182
+ "step": 13000
183
+ },
184
+ {
185
+ "epoch": 14.22,
186
+ "eval_loss": 7.824341297149658,
187
+ "eval_runtime": 3.6826,
188
+ "eval_samples_per_second": 2395.856,
189
+ "eval_steps_per_second": 37.473,
190
+ "step": 13000
191
+ },
192
+ {
193
+ "epoch": 15.32,
194
+ "learning_rate": 1.1706783369803063e-05,
195
+ "loss": 7.6114,
196
+ "step": 14000
197
+ },
198
+ {
199
+ "epoch": 15.32,
200
+ "eval_loss": 7.818795680999756,
201
+ "eval_runtime": 3.7376,
202
+ "eval_samples_per_second": 2360.637,
203
+ "eval_steps_per_second": 36.923,
204
+ "step": 14000
205
+ },
206
+ {
207
+ "epoch": 16.41,
208
+ "learning_rate": 8.971553610503283e-06,
209
+ "loss": 7.6037,
210
+ "step": 15000
211
+ },
212
+ {
213
+ "epoch": 16.41,
214
+ "eval_loss": 7.814483642578125,
215
+ "eval_runtime": 3.7397,
216
+ "eval_samples_per_second": 2359.276,
217
+ "eval_steps_per_second": 36.901,
218
+ "step": 15000
219
+ },
220
+ {
221
+ "epoch": 17.51,
222
+ "learning_rate": 6.2363238512035015e-06,
223
+ "loss": 7.5976,
224
+ "step": 16000
225
+ },
226
+ {
227
+ "epoch": 17.51,
228
+ "eval_loss": 7.810541152954102,
229
+ "eval_runtime": 3.6527,
230
+ "eval_samples_per_second": 2415.442,
231
+ "eval_steps_per_second": 37.78,
232
+ "step": 16000
233
+ },
234
+ {
235
+ "epoch": 18.6,
236
+ "learning_rate": 3.50109409190372e-06,
237
+ "loss": 7.5917,
238
+ "step": 17000
239
+ },
240
+ {
241
+ "epoch": 18.6,
242
+ "eval_loss": 7.808047771453857,
243
+ "eval_runtime": 3.6988,
244
+ "eval_samples_per_second": 2385.398,
245
+ "eval_steps_per_second": 37.31,
246
+ "step": 17000
247
+ },
248
+ {
249
+ "epoch": 19.69,
250
+ "learning_rate": 7.658643326039388e-07,
251
+ "loss": 7.589,
252
+ "step": 18000
253
+ },
254
+ {
255
+ "epoch": 19.69,
256
+ "eval_loss": 7.805490493774414,
257
+ "eval_runtime": 3.6528,
258
+ "eval_samples_per_second": 2415.393,
259
+ "eval_steps_per_second": 37.779,
260
+ "step": 18000
261
+ }
262
+ ],
263
+ "max_steps": 18280,
264
+ "num_train_epochs": 20,
265
+ "total_flos": 2.5151586400512e+16,
266
+ "trial_name": null,
267
+ "trial_params": null
268
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2046832228598c3dd9abfba9642edc658ca4f7e3307550516b283d0d1005d45
3
+ size 3311
vocab.txt ADDED
The diff for this file is too large to render. See raw diff