Hugging Face's logo

Apricity0201
/
legal-vn-field-v2

Text Classification
Transformers
PyTorch
Safetensors
roberta
Inference Endpoints
Model card Files Community
Apricity0201 commited on
Commit
01d0bdc
•
1 Parent(s): 2b1364b

Upload 11 files

Browse files
Files changed (11) hide show
  1. added_tokens.json +3 -0
  2. bpe.codes +0 -0
  3. model.safetensors +3 -0
  4. optimizer.pt +3 -0
  5. rng_state.pth +3 -0
  6. scheduler.pt +3 -0
  7. special_tokens_map.json +9 -0
  8. tokenizer_config.json +12 -0
  9. trainer_state.json +209 -0
  10. training_args.bin +3 -0
  11. vocab.txt +0 -0
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
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e88a02e0c1ca834ccb1ea64d6afbe4bd77b0a4ca3e365e9737bb14cf221dede
3
+ size 540097208
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29ae50f6b68844e208555ae314ac525da7a76d900d009b8b0ad3f2d8a1ec97b5
3
+ size 1080313733
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3309ae187fce4f3e4cb9bdc8766d1b833064b5bd94617be86e2d1cb67aed4c
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b58a7520a39398027bc553e4a51e1facbb4b2fcb590a33189dbdcab23091bbc8
3
+ size 755
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
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": "<mask>",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "<pad>",
9
+ "sep_token": "</s>",
10
+ "tokenizer_class": "PhobertTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
trainer_state.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8778576539129843,
3
+ "best_model_checkpoint": "./fields_classification/checkpoint-4610",
4
+ "epoch": 9.98916576381365,
5
+ "eval_steps": 500,
6
+ "global_step": 4610,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "learning_rate": 3e-05,
14
+ "loss": 0.1747,
15
+ "step": 461
16
+ },
17
+ {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.38636055803873764,
20
+ "eval_f1": 0.5336014591030258,
21
+ "eval_loss": 0.08355075865983963,
22
+ "eval_precision": 0.8621731902674928,
23
+ "eval_recall": 0.38636055803873764,
24
+ "eval_roc_auc": 0.6919450088040092,
25
+ "eval_runtime": 116.991,
26
+ "eval_samples_per_second": 126.215,
27
+ "eval_steps_per_second": 1.975,
28
+ "step": 461
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "learning_rate": 3e-05,
33
+ "loss": 0.0684,
34
+ "step": 923
35
+ },
36
+ {
37
+ "epoch": 2.0,
38
+ "eval_accuracy": 0.769944467018827,
39
+ "eval_f1": 0.8073713737883038,
40
+ "eval_loss": 0.05430687218904495,
41
+ "eval_precision": 0.8486228260058222,
42
+ "eval_recall": 0.769944467018827,
43
+ "eval_roc_auc": 0.8822253826357849,
44
+ "eval_runtime": 117.0652,
45
+ "eval_samples_per_second": 126.135,
46
+ "eval_steps_per_second": 1.973,
47
+ "step": 923
48
+ },
49
+ {
50
+ "epoch": 3.0,
51
+ "learning_rate": 3e-05,
52
+ "loss": 0.0498,
53
+ "step": 1384
54
+ },
55
+ {
56
+ "epoch": 3.0,
57
+ "eval_accuracy": 0.8040769334958688,
58
+ "eval_f1": 0.8276895206243033,
59
+ "eval_loss": 0.04519835114479065,
60
+ "eval_precision": 0.8522743578705697,
61
+ "eval_recall": 0.8044832723825004,
62
+ "eval_roc_auc": 0.8994527969660029,
63
+ "eval_runtime": 116.7477,
64
+ "eval_samples_per_second": 126.478,
65
+ "eval_steps_per_second": 1.979,
66
+ "step": 1384
67
+ },
68
+ {
69
+ "epoch": 4.0,
70
+ "learning_rate": 3e-05,
71
+ "loss": 0.0407,
72
+ "step": 1846
73
+ },
74
+ {
75
+ "epoch": 4.0,
76
+ "eval_accuracy": 0.8289990518759311,
77
+ "eval_f1": 0.8456551724137932,
78
+ "eval_loss": 0.039659492671489716,
79
+ "eval_precision": 0.8614584796965014,
80
+ "eval_recall": 0.8304212379791412,
81
+ "eval_roc_auc": 0.9125396180414465,
82
+ "eval_runtime": 117.5369,
83
+ "eval_samples_per_second": 125.629,
84
+ "eval_steps_per_second": 1.965,
85
+ "step": 1846
86
+ },
87
+ {
88
+ "epoch": 5.0,
89
+ "learning_rate": 3e-05,
90
+ "loss": 0.035,
91
+ "step": 2307
92
+ },
93
+ {
94
+ "epoch": 5.0,
95
+ "eval_accuracy": 0.8405119869971557,
96
+ "eval_f1": 0.8543429844097995,
97
+ "eval_loss": 0.03649652376770973,
98
+ "eval_precision": 0.8646230667868784,
99
+ "eval_recall": 0.8443044832723825,
100
+ "eval_roc_auc": 0.919508329947176,
101
+ "eval_runtime": 117.0597,
102
+ "eval_samples_per_second": 126.141,
103
+ "eval_steps_per_second": 1.973,
104
+ "step": 2307
105
+ },
106
+ {
107
+ "epoch": 6.0,
108
+ "learning_rate": 3e-05,
109
+ "loss": 0.0303,
110
+ "step": 2769
111
+ },
112
+ {
113
+ "epoch": 6.0,
114
+ "eval_accuracy": 0.8518217526750643,
115
+ "eval_f1": 0.8653773746363169,
116
+ "eval_loss": 0.0338783822953701,
117
+ "eval_precision": 0.8748702332341338,
118
+ "eval_recall": 0.8560883109846946,
119
+ "eval_roc_auc": 0.9255952864689151,
120
+ "eval_runtime": 116.7614,
121
+ "eval_samples_per_second": 126.463,
122
+ "eval_steps_per_second": 1.978,
123
+ "step": 2769
124
+ },
125
+ {
126
+ "epoch": 7.0,
127
+ "learning_rate": 3e-05,
128
+ "loss": 0.0268,
129
+ "step": 3230
130
+ },
131
+ {
132
+ "epoch": 7.0,
133
+ "eval_accuracy": 0.8566300961668698,
134
+ "eval_f1": 0.8697338868849113,
135
+ "eval_loss": 0.03237078711390495,
136
+ "eval_precision": 0.8740766073871409,
137
+ "eval_recall": 0.865434105377218,
138
+ "eval_roc_auc": 0.9302234863876474,
139
+ "eval_runtime": 117.0283,
140
+ "eval_samples_per_second": 126.175,
141
+ "eval_steps_per_second": 1.974,
142
+ "step": 3230
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "learning_rate": 3e-05,
147
+ "loss": 0.0237,
148
+ "step": 3692
149
+ },
150
+ {
151
+ "epoch": 8.0,
152
+ "eval_accuracy": 0.8580522822700799,
153
+ "eval_f1": 0.8707677634716261,
154
+ "eval_loss": 0.03161860257387161,
155
+ "eval_precision": 0.8759594298245614,
156
+ "eval_recall": 0.8656372748205337,
157
+ "eval_roc_auc": 0.9303670594609237,
158
+ "eval_runtime": 116.6155,
159
+ "eval_samples_per_second": 126.621,
160
+ "eval_steps_per_second": 1.981,
161
+ "step": 3692
162
+ },
163
+ {
164
+ "epoch": 9.0,
165
+ "learning_rate": 3e-05,
166
+ "loss": 0.0211,
167
+ "step": 4153
168
+ },
169
+ {
170
+ "epoch": 9.0,
171
+ "eval_accuracy": 0.8651632127861303,
172
+ "eval_f1": 0.8777002891648241,
173
+ "eval_loss": 0.030687741935253143,
174
+ "eval_precision": 0.8818101032196323,
175
+ "eval_recall": 0.8736286062576188,
176
+ "eval_roc_auc": 0.9344724366788568,
177
+ "eval_runtime": 116.7518,
178
+ "eval_samples_per_second": 126.473,
179
+ "eval_steps_per_second": 1.979,
180
+ "step": 4153
181
+ },
182
+ {
183
+ "epoch": 9.99,
184
+ "learning_rate": 3e-05,
185
+ "loss": 0.0188,
186
+ "step": 4610
187
+ },
188
+ {
189
+ "epoch": 9.99,
190
+ "eval_accuracy": 0.8656372748205337,
191
+ "eval_f1": 0.8778576539129843,
192
+ "eval_loss": 0.03020327538251877,
193
+ "eval_precision": 0.8833047651696949,
194
+ "eval_recall": 0.8724773127454964,
195
+ "eval_roc_auc": 0.9339333604225925,
196
+ "eval_runtime": 117.271,
197
+ "eval_samples_per_second": 125.914,
198
+ "eval_steps_per_second": 1.97,
199
+ "step": 4610
200
+ }
201
+ ],
202
+ "logging_steps": 500,
203
+ "max_steps": 4610,
204
+ "num_train_epochs": 10,
205
+ "save_steps": 500,
206
+ "total_flos": 1.5527107913529754e+17,
207
+ "trial_name": null,
208
+ "trial_params": null
209
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee87c617965c9b7d12fa1bea014a45cca1f6f9116717199152f482868ea6a08
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff