Hugging Face's logo

kornwtp
/
ThaiBERT-Small

Fill-Mask
Transformers
PyTorch
bert
Model card Files
xet
 Community
1
kornwtp commited on
Commit
b0ec9a0
·
1 Parent(s): 866ff69

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": 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": "4.21.2",
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 sha256:54a79ea1ea68aa9a96cb087f26281e77fd52a1daad8af21f95685ae126a0b4a6
3
+ size 230408035
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3b7868ce0da4a341c6c50409439d0fa5be8e13e778504941d576c11f0057fa4
3
+ size 115211730
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b07330660a04a3ac517d996d3fdffcd8bf643b86a94482070982b1d307004f3
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": 8.2829,
14
+ "step": 1000
15
+ },
16
+ {
17
+ "epoch": 1.09,
18
+ "eval_loss": 7.862854957580566,
19
+ "eval_runtime": 8.3401,
20
+ "eval_samples_per_second": 1057.901,
21
+ "eval_steps_per_second": 16.547,
22
+ "step": 1000
23
+ },
24
+ {
25
+ "epoch": 2.19,
26
+ "learning_rate": 4.452954048140044e-05,
27
+ "loss": 7.6392,
28
+ "step": 2000
29
+ },
30
+ {
31
+ "epoch": 2.19,
32
+ "eval_loss": 7.756640911102295,
33
+ "eval_runtime": 8.275,
34
+ "eval_samples_per_second": 1066.219,
35
+ "eval_steps_per_second": 16.677,
36
+ "step": 2000
37
+ },
38
+ {
39
+ "epoch": 3.28,
40
+ "learning_rate": 4.179431072210066e-05,
41
+ "loss": 7.4879,
42
+ "step": 3000
43
+ },
44
+ {
45
+ "epoch": 3.28,
46
+ "eval_loss": 7.715595245361328,
47
+ "eval_runtime": 8.2125,
48
+ "eval_samples_per_second": 1074.342,
49
+ "eval_steps_per_second": 16.804,
50
+ "step": 3000
51
+ },
52
+ {
53
+ "epoch": 4.38,
54
+ "learning_rate": 3.9059080962800876e-05,
55
+ "loss": 7.4085,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 4.38,
60
+ "eval_loss": 7.6904520988464355,
61
+ "eval_runtime": 8.2902,
62
+ "eval_samples_per_second": 1064.264,
63
+ "eval_steps_per_second": 16.646,
64
+ "step": 4000
65
+ },
66
+ {
67
+ "epoch": 5.47,
68
+ "learning_rate": 3.6323851203501094e-05,
69
+ "loss": 7.3528,
70
+ "step": 5000
71
+ },
72
+ {
73
+ "epoch": 5.47,
74
+ "eval_loss": 7.6683526039123535,
75
+ "eval_runtime": 8.2932,
76
+ "eval_samples_per_second": 1063.881,
77
+ "eval_steps_per_second": 16.64,
78
+ "step": 5000
79
+ },
80
+ {
81
+ "epoch": 6.56,
82
+ "learning_rate": 3.358862144420131e-05,
83
+ "loss": 7.3099,
84
+ "step": 6000
85
+ },
86
+ {
87
+ "epoch": 6.56,
88
+ "eval_loss": 7.6456756591796875,
89
+ "eval_runtime": 8.2108,
90
+ "eval_samples_per_second": 1074.565,
91
+ "eval_steps_per_second": 16.807,
92
+ "step": 6000
93
+ },
94
+ {
95
+ "epoch": 7.66,
96
+ "learning_rate": 3.085339168490153e-05,
97
+ "loss": 7.2768,
98
+ "step": 7000
99
+ },
100
+ {
101
+ "epoch": 7.66,
102
+ "eval_loss": 7.635733604431152,
103
+ "eval_runtime": 8.2718,
104
+ "eval_samples_per_second": 1066.63,
105
+ "eval_steps_per_second": 16.683,
106
+ "step": 7000
107
+ },
108
+ {
109
+ "epoch": 8.75,
110
+ "learning_rate": 2.811816192560175e-05,
111
+ "loss": 7.2502,
112
+ "step": 8000
113
+ },
114
+ {
115
+ "epoch": 8.75,
116
+ "eval_loss": 7.628890037536621,
117
+ "eval_runtime": 8.2137,
118
+ "eval_samples_per_second": 1074.176,
119
+ "eval_steps_per_second": 16.801,
120
+ "step": 8000
121
+ },
122
+ {
123
+ "epoch": 9.85,
124
+ "learning_rate": 2.538293216630197e-05,
125
+ "loss": 7.2288,
126
+ "step": 9000
127
+ },
128
+ {
129
+ "epoch": 9.85,
130
+ "eval_loss": 7.607583522796631,
131
+ "eval_runtime": 8.3598,
132
+ "eval_samples_per_second": 1055.408,
133
+ "eval_steps_per_second": 16.508,
134
+ "step": 9000
135
+ },
136
+ {
137
+ "epoch": 10.94,
138
+ "learning_rate": 2.264770240700219e-05,
139
+ "loss": 7.1375,
140
+ "step": 10000
141
+ },
142
+ {
143
+ "epoch": 10.94,
144
+ "eval_loss": 7.213150501251221,
145
+ "eval_runtime": 8.22,
146
+ "eval_samples_per_second": 1073.361,
147
+ "eval_steps_per_second": 16.788,
148
+ "step": 10000
149
+ },
150
+ {
151
+ "epoch": 12.04,
152
+ "learning_rate": 1.9912472647702408e-05,
153
+ "loss": 6.9675,
154
+ "step": 11000
155
+ },
156
+ {
157
+ "epoch": 12.04,
158
+ "eval_loss": 7.0395402908325195,
159
+ "eval_runtime": 8.2128,
160
+ "eval_samples_per_second": 1074.296,
161
+ "eval_steps_per_second": 16.803,
162
+ "step": 11000
163
+ },
164
+ {
165
+ "epoch": 13.13,
166
+ "learning_rate": 1.7177242888402626e-05,
167
+ "loss": 6.8891,
168
+ "step": 12000
169
+ },
170
+ {
171
+ "epoch": 13.13,
172
+ "eval_loss": 6.947587966918945,
173
+ "eval_runtime": 8.2276,
174
+ "eval_samples_per_second": 1072.371,
175
+ "eval_steps_per_second": 16.773,
176
+ "step": 12000
177
+ },
178
+ {
179
+ "epoch": 14.22,
180
+ "learning_rate": 1.4442013129102846e-05,
181
+ "loss": 6.8349,
182
+ "step": 13000
183
+ },
184
+ {
185
+ "epoch": 14.22,
186
+ "eval_loss": 6.882002353668213,
187
+ "eval_runtime": 8.216,
188
+ "eval_samples_per_second": 1073.882,
189
+ "eval_steps_per_second": 16.797,
190
+ "step": 13000
191
+ },
192
+ {
193
+ "epoch": 15.32,
194
+ "learning_rate": 1.1706783369803063e-05,
195
+ "loss": 6.7952,
196
+ "step": 14000
197
+ },
198
+ {
199
+ "epoch": 15.32,
200
+ "eval_loss": 6.837276458740234,
201
+ "eval_runtime": 8.2097,
202
+ "eval_samples_per_second": 1074.706,
203
+ "eval_steps_per_second": 16.809,
204
+ "step": 14000
205
+ },
206
+ {
207
+ "epoch": 16.41,
208
+ "learning_rate": 8.971553610503283e-06,
209
+ "loss": 6.7664,
210
+ "step": 15000
211
+ },
212
+ {
213
+ "epoch": 16.41,
214
+ "eval_loss": 6.805047512054443,
215
+ "eval_runtime": 8.2203,
216
+ "eval_samples_per_second": 1073.312,
217
+ "eval_steps_per_second": 16.788,
218
+ "step": 15000
219
+ },
220
+ {
221
+ "epoch": 17.51,
222
+ "learning_rate": 6.2363238512035015e-06,
223
+ "loss": 6.7444,
224
+ "step": 16000
225
+ },
226
+ {
227
+ "epoch": 17.51,
228
+ "eval_loss": 6.779191493988037,
229
+ "eval_runtime": 8.2441,
230
+ "eval_samples_per_second": 1070.226,
231
+ "eval_steps_per_second": 16.739,
232
+ "step": 16000
233
+ },
234
+ {
235
+ "epoch": 18.6,
236
+ "learning_rate": 3.50109409190372e-06,
237
+ "loss": 6.7268,
238
+ "step": 17000
239
+ },
240
+ {
241
+ "epoch": 18.6,
242
+ "eval_loss": 6.760980606079102,
243
+ "eval_runtime": 8.2098,
244
+ "eval_samples_per_second": 1074.685,
245
+ "eval_steps_per_second": 16.809,
246
+ "step": 17000
247
+ },
248
+ {
249
+ "epoch": 19.69,
250
+ "learning_rate": 7.658643326039388e-07,
251
+ "loss": 6.7164,
252
+ "step": 18000
253
+ },
254
+ {
255
+ "epoch": 19.69,
256
+ "eval_loss": 6.750948905944824,
257
+ "eval_runtime": 8.2106,
258
+ "eval_samples_per_second": 1074.59,
259
+ "eval_steps_per_second": 16.808,
260
+ "step": 18000
261
+ }
262
+ ],
263
+ "max_steps": 18280,
264
+ "num_train_epochs": 20,
265
+ "total_flos": 7.308771564796416e+17,
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 sha256:642201d6bb488ccc5c633b4952b9b216fc6c78cbcf4bfc2255f40050969ac49e
3
+ size 3311
vocab.txt ADDED
The diff for this file is too large to render. See raw diff