PuxAI commited on
Commit
bcc4627
·
verified ·
1 Parent(s): f4e49b4

PuxAI/PhoBERT-lowPara-6L-Distilled

Browse files
Files changed (8) hide show
  1. README.md +70 -0
  2. added_tokens.json +3 -0
  3. bpe.codes +0 -0
  4. config.json +234 -0
  5. model.safetensors +3 -0
  6. tokenizer_config.json +55 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - precision
7
+ - recall
8
+ - f1
9
+ - accuracy
10
+ model-index:
11
+ - name: phobert-student-distilled
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # phobert-student-distilled
19
+
20
+ This model was trained from scratch on the None dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.0268
23
+ - Precision: 0.9399
24
+ - Recall: 0.9553
25
+ - F1: 0.9475
26
+ - Accuracy: 0.9914
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 3e-05
46
+ - train_batch_size: 16
47
+ - eval_batch_size: 16
48
+ - seed: 42
49
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
+ - lr_scheduler_type: linear
51
+ - num_epochs: 5
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.0486 | 1.0 | 1683 | 0.0387 | 0.8994 | 0.9339 | 0.9164 | 0.9877 |
59
+ | 0.0315 | 2.0 | 3366 | 0.0320 | 0.9277 | 0.9474 | 0.9374 | 0.9904 |
60
+ | 0.0260 | 3.0 | 5049 | 0.0294 | 0.9351 | 0.9523 | 0.9436 | 0.9905 |
61
+ | 0.0188 | 4.0 | 6732 | 0.0268 | 0.9417 | 0.9550 | 0.9483 | 0.9919 |
62
+ | 0.0186 | 5.0 | 8415 | 0.0268 | 0.9399 | 0.9553 | 0.9475 | 0.9914 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 5.3.0
68
+ - Pytorch 2.10.0+cu128
69
+ - Datasets 4.6.1
70
+ - Tokenizers 0.22.2
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,234 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-ACCOUNTNAME",
18
+ "2": "B-ACCOUNTNUMBER",
19
+ "3": "B-AGE",
20
+ "4": "B-AMOUNT",
21
+ "5": "B-BIC",
22
+ "6": "B-BITCOINADDRESS",
23
+ "7": "B-BUILDINGNUMBER",
24
+ "8": "B-CCCD",
25
+ "9": "B-CITY",
26
+ "10": "B-COMPANYNAME",
27
+ "11": "B-COUNTY",
28
+ "12": "B-CREDITCARDCVV",
29
+ "13": "B-CREDITCARDISSUER",
30
+ "14": "B-CREDITCARDNUMBER",
31
+ "15": "B-CURRENCY",
32
+ "16": "B-CURRENCYCODE",
33
+ "17": "B-CURRENCYNAME",
34
+ "18": "B-CURRENCYSYMBOL",
35
+ "19": "B-DATE",
36
+ "20": "B-DOB",
37
+ "21": "B-EMAIL",
38
+ "22": "B-ETHEREUMADDRESS",
39
+ "23": "B-EYECOLOR",
40
+ "24": "B-FIRSTNAME",
41
+ "25": "B-GENDER",
42
+ "26": "B-HEIGHT",
43
+ "27": "B-IBAN",
44
+ "28": "B-JOBAREA",
45
+ "29": "B-JOBTITLE",
46
+ "30": "B-JOBTYPE",
47
+ "31": "B-LASTNAME",
48
+ "32": "B-LITECOINADDRESS",
49
+ "33": "B-MAC",
50
+ "34": "B-MASKEDNUMBER",
51
+ "35": "B-MIDDLENAME",
52
+ "36": "B-NEARBYGPSCOORDINATE",
53
+ "37": "B-ORDINALDIRECTION",
54
+ "38": "B-PASSWORD",
55
+ "39": "B-PHONEIMEI",
56
+ "40": "B-PHONENUMBER",
57
+ "41": "B-PIN",
58
+ "42": "B-PREFIX",
59
+ "43": "B-SECONDARYADDRESS",
60
+ "44": "B-SEX",
61
+ "45": "B-STATE",
62
+ "46": "B-STREET",
63
+ "47": "B-TIME",
64
+ "48": "B-URL",
65
+ "49": "B-USERAGENT",
66
+ "50": "B-USERNAME",
67
+ "51": "B-VEHICLEVIN",
68
+ "52": "B-VEHICLEVRM",
69
+ "53": "B-ZIPCODE",
70
+ "54": "I-ACCOUNTNAME",
71
+ "55": "I-ACCOUNTNUMBER",
72
+ "56": "I-AMOUNT",
73
+ "57": "I-BIC",
74
+ "58": "I-BITCOINADDRESS",
75
+ "59": "I-BUILDINGNUMBER",
76
+ "60": "I-CCCD",
77
+ "61": "I-CITY",
78
+ "62": "I-COMPANYNAME",
79
+ "63": "I-COUNTY",
80
+ "64": "I-CREDITCARDCVV",
81
+ "65": "I-CREDITCARDISSUER",
82
+ "66": "I-CREDITCARDNUMBER",
83
+ "67": "I-CURRENCY",
84
+ "68": "I-CURRENCYCODE",
85
+ "69": "I-CURRENCYNAME",
86
+ "70": "I-DATE",
87
+ "71": "I-DOB",
88
+ "72": "I-EMAIL",
89
+ "73": "I-ETHEREUMADDRESS",
90
+ "74": "I-EYECOLOR",
91
+ "75": "I-FIRSTNAME",
92
+ "76": "I-HEIGHT",
93
+ "77": "I-IBAN",
94
+ "78": "I-JOBAREA",
95
+ "79": "I-JOBTITLE",
96
+ "80": "I-JOBTYPE",
97
+ "81": "I-LITECOINADDRESS",
98
+ "82": "I-MAC",
99
+ "83": "I-MASKEDNUMBER",
100
+ "84": "I-NEARBYGPSCOORDINATE",
101
+ "85": "I-PASSWORD",
102
+ "86": "I-PHONEIMEI",
103
+ "87": "I-PHONENUMBER",
104
+ "88": "I-PIN",
105
+ "89": "I-PREFIX",
106
+ "90": "I-SECONDARYADDRESS",
107
+ "91": "I-STATE",
108
+ "92": "I-STREET",
109
+ "93": "I-TIME",
110
+ "94": "I-URL",
111
+ "95": "I-USERAGENT",
112
+ "96": "I-USERNAME",
113
+ "97": "I-VEHICLEVIN",
114
+ "98": "I-VEHICLEVRM",
115
+ "99": "I-ZIPCODE"
116
+ },
117
+ "initializer_range": 0.02,
118
+ "intermediate_size": 3072,
119
+ "is_decoder": false,
120
+ "label2id": {
121
+ "B-ACCOUNTNAME": 1,
122
+ "B-ACCOUNTNUMBER": 2,
123
+ "B-AGE": 3,
124
+ "B-AMOUNT": 4,
125
+ "B-BIC": 5,
126
+ "B-BITCOINADDRESS": 6,
127
+ "B-BUILDINGNUMBER": 7,
128
+ "B-CCCD": 8,
129
+ "B-CITY": 9,
130
+ "B-COMPANYNAME": 10,
131
+ "B-COUNTY": 11,
132
+ "B-CREDITCARDCVV": 12,
133
+ "B-CREDITCARDISSUER": 13,
134
+ "B-CREDITCARDNUMBER": 14,
135
+ "B-CURRENCY": 15,
136
+ "B-CURRENCYCODE": 16,
137
+ "B-CURRENCYNAME": 17,
138
+ "B-CURRENCYSYMBOL": 18,
139
+ "B-DATE": 19,
140
+ "B-DOB": 20,
141
+ "B-EMAIL": 21,
142
+ "B-ETHEREUMADDRESS": 22,
143
+ "B-EYECOLOR": 23,
144
+ "B-FIRSTNAME": 24,
145
+ "B-GENDER": 25,
146
+ "B-HEIGHT": 26,
147
+ "B-IBAN": 27,
148
+ "B-JOBAREA": 28,
149
+ "B-JOBTITLE": 29,
150
+ "B-JOBTYPE": 30,
151
+ "B-LASTNAME": 31,
152
+ "B-LITECOINADDRESS": 32,
153
+ "B-MAC": 33,
154
+ "B-MASKEDNUMBER": 34,
155
+ "B-MIDDLENAME": 35,
156
+ "B-NEARBYGPSCOORDINATE": 36,
157
+ "B-ORDINALDIRECTION": 37,
158
+ "B-PASSWORD": 38,
159
+ "B-PHONEIMEI": 39,
160
+ "B-PHONENUMBER": 40,
161
+ "B-PIN": 41,
162
+ "B-PREFIX": 42,
163
+ "B-SECONDARYADDRESS": 43,
164
+ "B-SEX": 44,
165
+ "B-STATE": 45,
166
+ "B-STREET": 46,
167
+ "B-TIME": 47,
168
+ "B-URL": 48,
169
+ "B-USERAGENT": 49,
170
+ "B-USERNAME": 50,
171
+ "B-VEHICLEVIN": 51,
172
+ "B-VEHICLEVRM": 52,
173
+ "B-ZIPCODE": 53,
174
+ "I-ACCOUNTNAME": 54,
175
+ "I-ACCOUNTNUMBER": 55,
176
+ "I-AMOUNT": 56,
177
+ "I-BIC": 57,
178
+ "I-BITCOINADDRESS": 58,
179
+ "I-BUILDINGNUMBER": 59,
180
+ "I-CCCD": 60,
181
+ "I-CITY": 61,
182
+ "I-COMPANYNAME": 62,
183
+ "I-COUNTY": 63,
184
+ "I-CREDITCARDCVV": 64,
185
+ "I-CREDITCARDISSUER": 65,
186
+ "I-CREDITCARDNUMBER": 66,
187
+ "I-CURRENCY": 67,
188
+ "I-CURRENCYCODE": 68,
189
+ "I-CURRENCYNAME": 69,
190
+ "I-DATE": 70,
191
+ "I-DOB": 71,
192
+ "I-EMAIL": 72,
193
+ "I-ETHEREUMADDRESS": 73,
194
+ "I-EYECOLOR": 74,
195
+ "I-FIRSTNAME": 75,
196
+ "I-HEIGHT": 76,
197
+ "I-IBAN": 77,
198
+ "I-JOBAREA": 78,
199
+ "I-JOBTITLE": 79,
200
+ "I-JOBTYPE": 80,
201
+ "I-LITECOINADDRESS": 81,
202
+ "I-MAC": 82,
203
+ "I-MASKEDNUMBER": 83,
204
+ "I-NEARBYGPSCOORDINATE": 84,
205
+ "I-PASSWORD": 85,
206
+ "I-PHONEIMEI": 86,
207
+ "I-PHONENUMBER": 87,
208
+ "I-PIN": 88,
209
+ "I-PREFIX": 89,
210
+ "I-SECONDARYADDRESS": 90,
211
+ "I-STATE": 91,
212
+ "I-STREET": 92,
213
+ "I-TIME": 93,
214
+ "I-URL": 94,
215
+ "I-USERAGENT": 95,
216
+ "I-USERNAME": 96,
217
+ "I-VEHICLEVIN": 97,
218
+ "I-VEHICLEVRM": 98,
219
+ "I-ZIPCODE": 99,
220
+ "O": 0
221
+ },
222
+ "layer_norm_eps": 1e-05,
223
+ "max_position_embeddings": 258,
224
+ "model_type": "roberta",
225
+ "num_attention_heads": 12,
226
+ "num_hidden_layers": 6,
227
+ "pad_token_id": 1,
228
+ "tie_word_embeddings": true,
229
+ "tokenizer_class": "PhobertTokenizer",
230
+ "transformers_version": "5.3.0",
231
+ "type_vocab_size": 1,
232
+ "use_cache": false,
233
+ "vocab_size": 64001
234
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed11f54e9f2275d8620a05c5bf8165f889b2b99e9161133fbb0f75eebc103b9c
3
+ size 367841704
tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "64000": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "backend": "custom",
45
+ "bos_token": "<s>",
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "is_local": false,
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "PhobertTokenizer",
54
+ "unk_token": "<unk>"
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c8d3951eca7deeb25572b401b2f4619cd3d5d38c2f010bdfeac7427b761a72
3
+ size 5201
vocab.txt ADDED
The diff for this file is too large to render. See raw diff