Hugging Face's logo

phuongsuga
/
PBL6_AI_Model_Text_Image

TensorBoard
Safetensors
roberta
Model card Files
xet
 Metrics Community
phuongsuga commited on
Commit
ed416d1
·
verified ·
1 Parent(s): 6f0ecbb

Upload 9 files

Browse files
Files changed (9) hide show
  1. text_model/added_tokens.json +3 -0
  2. text_model/bpe.codes +0 -0
  3. text_model/classification_report.txt +10 -0
  4. text_model/config.json +40 -0
  5. text_model/label2id.json +6 -0
  6. text_model/log_history.json +243 -0
  7. text_model/per_class_metrics.json +26 -0
  8. text_model/runs/Sep21_01-15-07_2e74df84add7/events.out.tfevents.1758417314.2e74df84add7.475.0 +3 -0
  9. text_model/special_tokens_map.json +9 -0
text_model/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<mask>": 64000
3
+ }
text_model/bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
text_model/classification_report.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ precision recall f1-score support
2
+
3
+ an_toan 0.86 0.85 0.85 947
4
+ khieu_dam_doi_truy 0.92 0.98 0.95 500
5
+ ngon_tu_thu_ghet 0.84 0.76 0.80 761
6
+ nhay_cam_chinh_tri 0.82 0.92 0.87 500
7
+
8
+ accuracy 0.86 2708
9
+ macro avg 0.86 0.88 0.87 2708
10
+ weighted avg 0.86 0.86 0.86 2708
text_model/config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "LABEL_0": 0,
23
+ "LABEL_1": 1,
24
+ "LABEL_2": 2,
25
+ "LABEL_3": 3
26
+ },
27
+ "layer_norm_eps": 1e-05,
28
+ "max_position_embeddings": 258,
29
+ "model_type": "roberta",
30
+ "num_attention_heads": 12,
31
+ "num_hidden_layers": 12,
32
+ "pad_token_id": 1,
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "tokenizer_class": "PhobertTokenizer",
36
+ "transformers_version": "4.56.1",
37
+ "type_vocab_size": 1,
38
+ "use_cache": true,
39
+ "vocab_size": 64001
40
+ }
text_model/label2id.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "an_toan": 0,
3
+ "khieu_dam_doi_truy": 1,
4
+ "ngon_tu_thu_ghet": 2,
5
+ "nhay_cam_chinh_tri": 3
6
+ }
text_model/log_history.json ADDED
@@ -0,0 +1,243 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "loss": 1.0146,
4
+ "grad_norm": 8.066655158996582,
5
+ "learning_rate": 1.88259587020649e-05,
6
+ "epoch": 0.5908419497784343,
7
+ "step": 200
8
+ },
9
+ {
10
+ "eval_loss": 0.6535171866416931,
11
+ "eval_accuracy": 0.7455686853766618,
12
+ "eval_precision": 0.7438951273666146,
13
+ "eval_recall": 0.7635212365766714,
14
+ "eval_f1": 0.7480569004890223,
15
+ "eval_runtime": 4.1402,
16
+ "eval_samples_per_second": 654.079,
17
+ "eval_steps_per_second": 10.386,
18
+ "epoch": 1.0,
19
+ "step": 339
20
+ },
21
+ {
22
+ "loss": 0.7183,
23
+ "grad_norm": 8.033791542053223,
24
+ "learning_rate": 1.7646017699115045e-05,
25
+ "epoch": 1.1802067946824224,
26
+ "step": 400
27
+ },
28
+ {
29
+ "loss": 0.5841,
30
+ "grad_norm": 7.553318500518799,
31
+ "learning_rate": 1.6466076696165194e-05,
32
+ "epoch": 1.7710487444608567,
33
+ "step": 600
34
+ },
35
+ {
36
+ "eval_loss": 0.5103763341903687,
37
+ "eval_accuracy": 0.7961595273264401,
38
+ "eval_precision": 0.7954926941267795,
39
+ "eval_recall": 0.8145635466866111,
40
+ "eval_f1": 0.8004633351993021,
41
+ "eval_runtime": 4.2164,
42
+ "eval_samples_per_second": 642.252,
43
+ "eval_steps_per_second": 10.198,
44
+ "epoch": 2.0,
45
+ "step": 678
46
+ },
47
+ {
48
+ "loss": 0.4924,
49
+ "grad_norm": 11.982539176940918,
50
+ "learning_rate": 1.528613569321534e-05,
51
+ "epoch": 2.360413589364845,
52
+ "step": 800
53
+ },
54
+ {
55
+ "loss": 0.4396,
56
+ "grad_norm": 10.420658111572266,
57
+ "learning_rate": 1.410619469026549e-05,
58
+ "epoch": 2.951255539143279,
59
+ "step": 1000
60
+ },
61
+ {
62
+ "eval_loss": 0.43686869740486145,
63
+ "eval_accuracy": 0.8319793205317577,
64
+ "eval_precision": 0.8322550154197035,
65
+ "eval_recall": 0.8486163782995474,
66
+ "eval_f1": 0.839237623407653,
67
+ "eval_runtime": 4.2136,
68
+ "eval_samples_per_second": 642.679,
69
+ "eval_steps_per_second": 10.205,
70
+ "epoch": 3.0,
71
+ "step": 1017
72
+ },
73
+ {
74
+ "loss": 0.3559,
75
+ "grad_norm": 13.99537181854248,
76
+ "learning_rate": 1.2926253687315635e-05,
77
+ "epoch": 3.5406203840472674,
78
+ "step": 1200
79
+ },
80
+ {
81
+ "eval_loss": 0.40422186255455017,
82
+ "eval_accuracy": 0.8545051698670606,
83
+ "eval_precision": 0.8628044809228071,
84
+ "eval_recall": 0.8634142412515072,
85
+ "eval_f1": 0.8630242724646225,
86
+ "eval_runtime": 4.206,
87
+ "eval_samples_per_second": 643.836,
88
+ "eval_steps_per_second": 10.223,
89
+ "epoch": 4.0,
90
+ "step": 1356
91
+ },
92
+ {
93
+ "loss": 0.3394,
94
+ "grad_norm": 14.122424125671387,
95
+ "learning_rate": 1.1746312684365783e-05,
96
+ "epoch": 4.129985228951256,
97
+ "step": 1400
98
+ },
99
+ {
100
+ "loss": 0.2889,
101
+ "grad_norm": 10.866605758666992,
102
+ "learning_rate": 1.056637168141593e-05,
103
+ "epoch": 4.72082717872969,
104
+ "step": 1600
105
+ },
106
+ {
107
+ "eval_loss": 0.4265260100364685,
108
+ "eval_accuracy": 0.8441654357459379,
109
+ "eval_precision": 0.8441186724361562,
110
+ "eval_recall": 0.8647582579749038,
111
+ "eval_f1": 0.8517152790349632,
112
+ "eval_runtime": 4.1986,
113
+ "eval_samples_per_second": 644.981,
114
+ "eval_steps_per_second": 10.242,
115
+ "epoch": 5.0,
116
+ "step": 1695
117
+ },
118
+ {
119
+ "loss": 0.2514,
120
+ "grad_norm": 5.72359561920166,
121
+ "learning_rate": 9.386430678466077e-06,
122
+ "epoch": 5.310192023633678,
123
+ "step": 1800
124
+ },
125
+ {
126
+ "loss": 0.2464,
127
+ "grad_norm": 9.600533485412598,
128
+ "learning_rate": 8.206489675516224e-06,
129
+ "epoch": 5.901033973412112,
130
+ "step": 2000
131
+ },
132
+ {
133
+ "eval_loss": 0.389065682888031,
134
+ "eval_accuracy": 0.8626292466765141,
135
+ "eval_precision": 0.8652231358736173,
136
+ "eval_recall": 0.8783380417030334,
137
+ "eval_f1": 0.8702889928876043,
138
+ "eval_runtime": 4.2127,
139
+ "eval_samples_per_second": 642.817,
140
+ "eval_steps_per_second": 10.207,
141
+ "epoch": 6.0,
142
+ "step": 2034
143
+ },
144
+ {
145
+ "loss": 0.211,
146
+ "grad_norm": 17.138826370239258,
147
+ "learning_rate": 7.026548672566372e-06,
148
+ "epoch": 6.4903988183161,
149
+ "step": 2200
150
+ },
151
+ {
152
+ "eval_loss": 0.39963972568511963,
153
+ "eval_accuracy": 0.8674298375184638,
154
+ "eval_precision": 0.8702205064128979,
155
+ "eval_recall": 0.8830179653015887,
156
+ "eval_f1": 0.8754706796586051,
157
+ "eval_runtime": 4.256,
158
+ "eval_samples_per_second": 636.271,
159
+ "eval_steps_per_second": 10.103,
160
+ "epoch": 7.0,
161
+ "step": 2373
162
+ },
163
+ {
164
+ "loss": 0.1979,
165
+ "grad_norm": 6.464990615844727,
166
+ "learning_rate": 5.8466076696165195e-06,
167
+ "epoch": 7.079763663220088,
168
+ "step": 2400
169
+ },
170
+ {
171
+ "loss": 0.1781,
172
+ "grad_norm": 9.935137748718262,
173
+ "learning_rate": 4.666666666666667e-06,
174
+ "epoch": 7.670605612998523,
175
+ "step": 2600
176
+ },
177
+ {
178
+ "eval_loss": 0.4202274978160858,
179
+ "eval_accuracy": 0.8707533234859675,
180
+ "eval_precision": 0.8721032179023319,
181
+ "eval_recall": 0.8847283016982879,
182
+ "eval_f1": 0.8775633088032715,
183
+ "eval_runtime": 4.21,
184
+ "eval_samples_per_second": 643.232,
185
+ "eval_steps_per_second": 10.214,
186
+ "epoch": 8.0,
187
+ "step": 2712
188
+ },
189
+ {
190
+ "loss": 0.1651,
191
+ "grad_norm": 9.050063133239746,
192
+ "learning_rate": 3.4867256637168144e-06,
193
+ "epoch": 8.259970457902511,
194
+ "step": 2800
195
+ },
196
+ {
197
+ "loss": 0.1541,
198
+ "grad_norm": 11.100234985351562,
199
+ "learning_rate": 2.306784660766962e-06,
200
+ "epoch": 8.850812407680944,
201
+ "step": 3000
202
+ },
203
+ {
204
+ "eval_loss": 0.4208575487136841,
205
+ "eval_accuracy": 0.869645494830133,
206
+ "eval_precision": 0.8718772232277948,
207
+ "eval_recall": 0.8837444901736863,
208
+ "eval_f1": 0.877165841562759,
209
+ "eval_runtime": 4.2122,
210
+ "eval_samples_per_second": 642.888,
211
+ "eval_steps_per_second": 10.208,
212
+ "epoch": 9.0,
213
+ "step": 3051
214
+ },
215
+ {
216
+ "loss": 0.1452,
217
+ "grad_norm": 9.718356132507324,
218
+ "learning_rate": 1.1268436578171092e-06,
219
+ "epoch": 9.440177252584933,
220
+ "step": 3200
221
+ },
222
+ {
223
+ "eval_loss": 0.4245568513870239,
224
+ "eval_accuracy": 0.8670605612998523,
225
+ "eval_precision": 0.8694463928962631,
226
+ "eval_recall": 0.8819628066777028,
227
+ "eval_f1": 0.8750774553354714,
228
+ "eval_runtime": 4.2399,
229
+ "eval_samples_per_second": 638.697,
230
+ "eval_steps_per_second": 10.142,
231
+ "epoch": 10.0,
232
+ "step": 3390
233
+ },
234
+ {
235
+ "train_runtime": 1402.4702,
236
+ "train_samples_per_second": 154.442,
237
+ "train_steps_per_second": 2.417,
238
+ "total_flos": 1.42477194921984e+16,
239
+ "train_loss": 0.34887106960150344,
240
+ "epoch": 10.0,
241
+ "step": 3390
242
+ }
243
+ ]
text_model/per_class_metrics.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "an_toan": {
3
+ "precision": 0.8631465517241379,
4
+ "recall": 0.8458289334741288,
5
+ "f1": 0.8544,
6
+ "support": 947
7
+ },
8
+ "khieu_dam_doi_truy": {
9
+ "precision": 0.9213483146067416,
10
+ "recall": 0.984,
11
+ "f1": 0.9516441005802708,
12
+ "support": 500
13
+ },
14
+ "ngon_tu_thu_ghet": {
15
+ "precision": 0.8411078717201166,
16
+ "recall": 0.7582128777923784,
17
+ "f1": 0.7975120939875605,
18
+ "support": 761
19
+ },
20
+ "nhay_cam_chinh_tri": {
21
+ "precision": 0.8214285714285714,
22
+ "recall": 0.92,
23
+ "f1": 0.8679245283018868,
24
+ "support": 500
25
+ }
26
+ }
text_model/runs/Sep21_01-15-07_2e74df84add7/events.out.tfevents.1758417314.2e74df84add7.475.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92058c88aa0152ab33d1d7fab0e390e9c1edac705fcf8189519251eadeaf0653
3
+ size 10603
text_model/special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
+ }