BERT-crime-analysis
Browse files- README.md +92 -0
- config.json +99 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: google-bert/bert-base-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: results
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# results
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on the None dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.1241
|
21 |
+
- Macro f1: 0.8944
|
22 |
+
- Weighted f1: 0.9315
|
23 |
+
- Accuracy: 0.9380
|
24 |
+
- Balanced accuracy: 0.9042
|
25 |
+
|
26 |
+
## Model description
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Intended uses & limitations
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training and evaluation data
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training procedure
|
39 |
+
|
40 |
+
### Training hyperparameters
|
41 |
+
|
42 |
+
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 5e-05
|
44 |
+
- train_batch_size: 32
|
45 |
+
- eval_batch_size: 32
|
46 |
+
- seed: 42
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 30
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Macro f1 | Weighted f1 | Accuracy | Balanced accuracy |
|
54 |
+
|:-------------:|:-----:|:------:|:---------------:|:--------:|:-----------:|:--------:|:-----------------:|
|
55 |
+
| 0.1859 | 1.0 | 5538 | 0.1297 | 0.8561 | 0.9249 | 0.9366 | 0.8571 |
|
56 |
+
| 0.1281 | 2.0 | 11076 | 0.1260 | 0.8702 | 0.9248 | 0.9369 | 0.8740 |
|
57 |
+
| 0.1279 | 3.0 | 16614 | 0.1251 | 0.8728 | 0.9314 | 0.9380 | 0.8749 |
|
58 |
+
| 0.1272 | 4.0 | 22152 | 0.1276 | 0.8652 | 0.9247 | 0.9367 | 0.8655 |
|
59 |
+
| 0.1266 | 5.0 | 27690 | 0.1256 | 0.8685 | 0.9252 | 0.9345 | 0.8724 |
|
60 |
+
| 0.1284 | 6.0 | 33228 | 0.1264 | 0.8668 | 0.9252 | 0.9345 | 0.8724 |
|
61 |
+
| 0.1272 | 7.0 | 38766 | 0.1247 | 0.8739 | 0.9313 | 0.9379 | 0.8748 |
|
62 |
+
| 0.1262 | 8.0 | 44304 | 0.1258 | 0.8892 | 0.9246 | 0.9366 | 0.9024 |
|
63 |
+
| 0.1263 | 9.0 | 49842 | 0.1251 | 0.9038 | 0.9310 | 0.9378 | 0.9041 |
|
64 |
+
| 0.1267 | 10.0 | 55380 | 0.1244 | 0.8897 | 0.9253 | 0.9345 | 0.9018 |
|
65 |
+
| 0.1271 | 11.0 | 60918 | 0.1251 | 0.8951 | 0.9325 | 0.9371 | 0.9036 |
|
66 |
+
| 0.1268 | 12.0 | 66456 | 0.1248 | 0.8944 | 0.9315 | 0.9380 | 0.9042 |
|
67 |
+
| 0.1254 | 13.0 | 71994 | 0.1247 | 0.9038 | 0.9314 | 0.9381 | 0.9043 |
|
68 |
+
| 0.126 | 14.0 | 77532 | 0.1263 | 0.8944 | 0.9314 | 0.9379 | 0.9042 |
|
69 |
+
| 0.1261 | 15.0 | 83070 | 0.1274 | 0.8891 | 0.9250 | 0.9348 | 0.9020 |
|
70 |
+
| 0.1253 | 16.0 | 88608 | 0.1241 | 0.8944 | 0.9315 | 0.9380 | 0.9042 |
|
71 |
+
| 0.1251 | 17.0 | 94146 | 0.1244 | 0.9042 | 0.9314 | 0.9380 | 0.9042 |
|
72 |
+
| 0.125 | 18.0 | 99684 | 0.1249 | 0.9041 | 0.9314 | 0.9380 | 0.9043 |
|
73 |
+
| 0.125 | 19.0 | 105222 | 0.1245 | 0.8942 | 0.9312 | 0.9380 | 0.9042 |
|
74 |
+
| 0.1257 | 20.0 | 110760 | 0.1248 | 0.9041 | 0.9313 | 0.9379 | 0.9042 |
|
75 |
+
| 0.125 | 21.0 | 116298 | 0.1248 | 0.9000 | 0.9254 | 0.9344 | 0.9018 |
|
76 |
+
| 0.1248 | 22.0 | 121836 | 0.1244 | 0.9041 | 0.9313 | 0.9379 | 0.9042 |
|
77 |
+
| 0.1246 | 23.0 | 127374 | 0.1245 | 0.9042 | 0.9315 | 0.9380 | 0.9042 |
|
78 |
+
| 0.1247 | 24.0 | 132912 | 0.1242 | 0.8943 | 0.9314 | 0.9380 | 0.9043 |
|
79 |
+
| 0.1245 | 25.0 | 138450 | 0.1242 | 0.9042 | 0.9315 | 0.9380 | 0.9042 |
|
80 |
+
| 0.1245 | 26.0 | 143988 | 0.1245 | 0.9042 | 0.9314 | 0.9381 | 0.9043 |
|
81 |
+
| 0.1245 | 27.0 | 149526 | 0.1242 | 0.8944 | 0.9314 | 0.9381 | 0.9043 |
|
82 |
+
| 0.1244 | 28.0 | 155064 | 0.1242 | 0.9336 | 0.9315 | 0.9381 | 0.9337 |
|
83 |
+
| 0.1243 | 29.0 | 160602 | 0.1243 | 0.8944 | 0.9314 | 0.9381 | 0.9043 |
|
84 |
+
| 0.1243 | 30.0 | 166140 | 0.1243 | 0.8944 | 0.9314 | 0.9381 | 0.9043 |
|
85 |
+
|
86 |
+
|
87 |
+
### Framework versions
|
88 |
+
|
89 |
+
- Transformers 4.39.3
|
90 |
+
- Pytorch 2.2.2
|
91 |
+
- Datasets 2.18.0
|
92 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "ARSON",
|
14 |
+
"1": "ASSAULT",
|
15 |
+
"2": "BATTERY",
|
16 |
+
"3": "BURGLARY",
|
17 |
+
"4": "CONCEALED CARRY LICENSE VIOLATION",
|
18 |
+
"5": "CRIM SEXUAL ASSAULT",
|
19 |
+
"6": "CRIMINAL DAMAGE",
|
20 |
+
"7": "CRIMINAL TRESPASS",
|
21 |
+
"8": "DECEPTIVE PRACTICE",
|
22 |
+
"9": "DOMESTIC VIOLENCE",
|
23 |
+
"10": "GAMBLING",
|
24 |
+
"11": "HOMICIDE",
|
25 |
+
"12": "HUMAN TRAFFICKING",
|
26 |
+
"13": "INTERFERENCE WITH PUBLIC OFFICER",
|
27 |
+
"14": "INTIMIDATION",
|
28 |
+
"15": "KIDNAPPING",
|
29 |
+
"16": "LIQUOR LAW VIOLATION",
|
30 |
+
"17": "MOTOR VEHICLE THEFT",
|
31 |
+
"18": "NARCOTICS",
|
32 |
+
"19": "NON-CRIMINAL",
|
33 |
+
"20": "NON-CRIMINAL (SUBJECT SPECIFIED)",
|
34 |
+
"21": "OBSCENITY",
|
35 |
+
"22": "OFFENSE INVOLVING CHILDREN",
|
36 |
+
"23": "OTHER NARCOTIC VIOLATION",
|
37 |
+
"24": "OTHER OFFENSE",
|
38 |
+
"25": "PROSTITUTION",
|
39 |
+
"26": "PUBLIC INDECENCY",
|
40 |
+
"27": "PUBLIC PEACE VIOLATION",
|
41 |
+
"28": "RITUALISM",
|
42 |
+
"29": "ROBBERY",
|
43 |
+
"30": "SEX OFFENSE",
|
44 |
+
"31": "STALKING",
|
45 |
+
"32": "THEFT",
|
46 |
+
"33": "WEAPONS VIOLATION"
|
47 |
+
},
|
48 |
+
"initializer_range": 0.02,
|
49 |
+
"intermediate_size": 3072,
|
50 |
+
"label2id": {
|
51 |
+
"ARSON": 0,
|
52 |
+
"ASSAULT": 1,
|
53 |
+
"BATTERY": 2,
|
54 |
+
"BURGLARY": 3,
|
55 |
+
"CONCEALED CARRY LICENSE VIOLATION": 4,
|
56 |
+
"CRIM SEXUAL ASSAULT": 5,
|
57 |
+
"CRIMINAL DAMAGE": 6,
|
58 |
+
"CRIMINAL TRESPASS": 7,
|
59 |
+
"DECEPTIVE PRACTICE": 8,
|
60 |
+
"DOMESTIC VIOLENCE": 9,
|
61 |
+
"GAMBLING": 10,
|
62 |
+
"HOMICIDE": 11,
|
63 |
+
"HUMAN TRAFFICKING": 12,
|
64 |
+
"INTERFERENCE WITH PUBLIC OFFICER": 13,
|
65 |
+
"INTIMIDATION": 14,
|
66 |
+
"KIDNAPPING": 15,
|
67 |
+
"LIQUOR LAW VIOLATION": 16,
|
68 |
+
"MOTOR VEHICLE THEFT": 17,
|
69 |
+
"NARCOTICS": 18,
|
70 |
+
"NON-CRIMINAL": 19,
|
71 |
+
"NON-CRIMINAL (SUBJECT SPECIFIED)": 20,
|
72 |
+
"OBSCENITY": 21,
|
73 |
+
"OFFENSE INVOLVING CHILDREN": 22,
|
74 |
+
"OTHER NARCOTIC VIOLATION": 23,
|
75 |
+
"OTHER OFFENSE": 24,
|
76 |
+
"PROSTITUTION": 25,
|
77 |
+
"PUBLIC INDECENCY": 26,
|
78 |
+
"PUBLIC PEACE VIOLATION": 27,
|
79 |
+
"RITUALISM": 28,
|
80 |
+
"ROBBERY": 29,
|
81 |
+
"SEX OFFENSE": 30,
|
82 |
+
"STALKING": 31,
|
83 |
+
"THEFT": 32,
|
84 |
+
"WEAPONS VIOLATION": 33
|
85 |
+
},
|
86 |
+
"layer_norm_eps": 1e-12,
|
87 |
+
"max_position_embeddings": 512,
|
88 |
+
"model_type": "bert",
|
89 |
+
"num_attention_heads": 12,
|
90 |
+
"num_hidden_layers": 12,
|
91 |
+
"pad_token_id": 0,
|
92 |
+
"position_embedding_type": "absolute",
|
93 |
+
"problem_type": "single_label_classification",
|
94 |
+
"torch_dtype": "float32",
|
95 |
+
"transformers_version": "4.39.3",
|
96 |
+
"type_vocab_size": 2,
|
97 |
+
"use_cache": true,
|
98 |
+
"vocab_size": 30522
|
99 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4cf01dcebeb8260213d2648b5fc532c77bd5ad74689da1280c43cebc06c838c
|
3 |
+
size 438057080
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
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:f55db632f996074ad22675fe3d18994b78d082ad14e33de18dbe17da52c452a4
|
3 |
+
size 4856
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|