sickcell69
commited on
Commit
•
1fa0284
1
Parent(s):
ed89425
Training complete
Browse files- README.md +75 -85
- config.json +84 -84
- model.safetensors +1 -1
- runs/Aug01_17-09-19_DESKTOP-7EBBP1S/events.out.tfevents.1722503410.DESKTOP-7EBBP1S.24612.0 +3 -0
- runs/Aug01_17-13-58_DESKTOP-7EBBP1S/events.out.tfevents.1722503639.DESKTOP-7EBBP1S.24612.1 +3 -0
- runs/Aug01_17-13-58_DESKTOP-7EBBP1S/events.out.tfevents.1722504138.DESKTOP-7EBBP1S.24612.2 +3 -0
- special_tokens_map.json +7 -7
- tokenizer_config.json +55 -55
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,85 +1,75 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
base_model: bert-base-cased
|
4 |
-
tags:
|
5 |
-
- generated_from_trainer
|
6 |
-
metrics:
|
7 |
-
- precision
|
8 |
-
- recall
|
9 |
-
- f1
|
10 |
-
- accuracy
|
11 |
-
model-index:
|
12 |
-
- name: bert-finetuned-ner
|
13 |
-
results: []
|
14 |
-
---
|
15 |
-
|
16 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
-
should probably proofread and complete it, then remove this comment. -->
|
18 |
-
|
19 |
-
# bert-finetuned-ner
|
20 |
-
|
21 |
-
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
22 |
-
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
-
- Precision: 0.
|
25 |
-
- Recall: 0.
|
26 |
-
- F1: 0.
|
27 |
-
- Accuracy: 0.
|
28 |
-
|
29 |
-
## Model description
|
30 |
-
|
31 |
-
More information needed
|
32 |
-
|
33 |
-
## Intended uses & limitations
|
34 |
-
|
35 |
-
More information needed
|
36 |
-
|
37 |
-
## Training and evaluation data
|
38 |
-
|
39 |
-
More information needed
|
40 |
-
|
41 |
-
## Training procedure
|
42 |
-
|
43 |
-
### Training hyperparameters
|
44 |
-
|
45 |
-
The following hyperparameters were used during training:
|
46 |
-
- learning_rate: 1e-05
|
47 |
-
- train_batch_size: 8
|
48 |
-
- eval_batch_size: 8
|
49 |
-
- seed: 42
|
50 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
-
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
-
|
54 |
-
### Training results
|
55 |
-
|
56 |
-
| Training Loss | Epoch | Step
|
57 |
-
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
-
| 0.
|
67 |
-
| 0.
|
68 |
-
|
69 |
-
|
70 |
-
|
71 |
-
|
72 |
-
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
-
| 0.0142 | 19.0 | 12920 | 0.5687 | 0.8258 | 0.8753 | 0.8498 | 0.9259 |
|
77 |
-
| 0.0135 | 20.0 | 13600 | 0.5707 | 0.8258 | 0.8753 | 0.8498 | 0.9254 |
|
78 |
-
|
79 |
-
|
80 |
-
### Framework versions
|
81 |
-
|
82 |
-
- Transformers 4.42.4
|
83 |
-
- Pytorch 2.3.1+cu121
|
84 |
-
- Datasets 2.20.0
|
85 |
-
- Tokenizers 0.19.1
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: bert-base-cased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
- accuracy
|
11 |
+
model-index:
|
12 |
+
- name: bert-finetuned-ner
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# bert-finetuned-ner
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3391
|
24 |
+
- Precision: 0.8826
|
25 |
+
- Recall: 0.9138
|
26 |
+
- F1: 0.8979
|
27 |
+
- Accuracy: 0.9518
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 1e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 8
|
49 |
+
- seed: 42
|
50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
+
- lr_scheduler_type: linear
|
52 |
+
- num_epochs: 10
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
57 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
58 |
+
| 0.0318 | 1.0 | 680 | 0.4800 | 0.8075 | 0.8632 | 0.8344 | 0.9183 |
|
59 |
+
| 0.0206 | 2.0 | 1360 | 0.4822 | 0.8332 | 0.8634 | 0.8480 | 0.9233 |
|
60 |
+
| 0.0116 | 3.0 | 2040 | 0.5227 | 0.8167 | 0.8683 | 0.8417 | 0.9211 |
|
61 |
+
| 0.0093 | 4.0 | 2720 | 0.5366 | 0.8230 | 0.8749 | 0.8482 | 0.9246 |
|
62 |
+
| 0.0077 | 5.0 | 3400 | 0.5384 | 0.8370 | 0.8688 | 0.8526 | 0.9249 |
|
63 |
+
| 0.0061 | 6.0 | 4080 | 0.5450 | 0.8418 | 0.8754 | 0.8583 | 0.9275 |
|
64 |
+
| 0.0048 | 7.0 | 4760 | 0.5570 | 0.8346 | 0.8765 | 0.8550 | 0.9262 |
|
65 |
+
| 0.0084 | 8.0 | 5440 | 0.5565 | 0.8353 | 0.8765 | 0.8554 | 0.9261 |
|
66 |
+
| 0.0073 | 9.0 | 6120 | 0.5693 | 0.8353 | 0.8751 | 0.8547 | 0.9261 |
|
67 |
+
| 0.0058 | 10.0 | 6800 | 0.5688 | 0.8361 | 0.8766 | 0.8559 | 0.9265 |
|
68 |
+
|
69 |
+
|
70 |
+
### Framework versions
|
71 |
+
|
72 |
+
- Transformers 4.43.3
|
73 |
+
- Pytorch 2.4.0+cu118
|
74 |
+
- Datasets 2.20.0
|
75 |
+
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -1,84 +1,84 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "bert-base-cased",
|
3 |
-
"architectures": [
|
4 |
-
"BertForTokenClassification"
|
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": "B-Area",
|
14 |
-
"1": "B-Exp",
|
15 |
-
"2": "B-Features",
|
16 |
-
"3": "B-HackOrg",
|
17 |
-
"4": "B-Idus",
|
18 |
-
"5": "B-OffAct",
|
19 |
-
"6": "B-Org",
|
20 |
-
"7": "B-Purp",
|
21 |
-
"8": "B-SamFile",
|
22 |
-
"9": "B-SecTeam",
|
23 |
-
"10": "B-Time",
|
24 |
-
"11": "B-Tool",
|
25 |
-
"12": "B-Way",
|
26 |
-
"13": "I-Area",
|
27 |
-
"14": "I-Exp",
|
28 |
-
"15": "I-Features",
|
29 |
-
"16": "I-HackOrg",
|
30 |
-
"17": "I-Idus",
|
31 |
-
"18": "I-OffAct",
|
32 |
-
"19": "I-Org",
|
33 |
-
"20": "I-Purp",
|
34 |
-
"21": "I-SamFile",
|
35 |
-
"22": "I-SecTeam",
|
36 |
-
"23": "I-Time",
|
37 |
-
"24": "I-Tool",
|
38 |
-
"25": "I-Way",
|
39 |
-
"26": "O"
|
40 |
-
},
|
41 |
-
"initializer_range": 0.02,
|
42 |
-
"intermediate_size": 3072,
|
43 |
-
"label2id": {
|
44 |
-
"B-Area": 0,
|
45 |
-
"B-Exp": 1,
|
46 |
-
"B-Features": 2,
|
47 |
-
"B-HackOrg": 3,
|
48 |
-
"B-Idus": 4,
|
49 |
-
"B-OffAct": 5,
|
50 |
-
"B-Org": 6,
|
51 |
-
"B-Purp": 7,
|
52 |
-
"B-SamFile": 8,
|
53 |
-
"B-SecTeam": 9,
|
54 |
-
"B-Time": 10,
|
55 |
-
"B-Tool": 11,
|
56 |
-
"B-Way": 12,
|
57 |
-
"I-Area": 13,
|
58 |
-
"I-Exp": 14,
|
59 |
-
"I-Features": 15,
|
60 |
-
"I-HackOrg": 16,
|
61 |
-
"I-Idus": 17,
|
62 |
-
"I-OffAct": 18,
|
63 |
-
"I-Org": 19,
|
64 |
-
"I-Purp": 20,
|
65 |
-
"I-SamFile": 21,
|
66 |
-
"I-SecTeam": 22,
|
67 |
-
"I-Time": 23,
|
68 |
-
"I-Tool": 24,
|
69 |
-
"I-Way": 25,
|
70 |
-
"O": 26
|
71 |
-
},
|
72 |
-
"layer_norm_eps": 1e-12,
|
73 |
-
"max_position_embeddings": 512,
|
74 |
-
"model_type": "bert",
|
75 |
-
"num_attention_heads": 12,
|
76 |
-
"num_hidden_layers": 12,
|
77 |
-
"pad_token_id": 0,
|
78 |
-
"position_embedding_type": "absolute",
|
79 |
-
"torch_dtype": "float32",
|
80 |
-
"transformers_version": "4.
|
81 |
-
"type_vocab_size": 2,
|
82 |
-
"use_cache": true,
|
83 |
-
"vocab_size": 28996
|
84 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": "B-Area",
|
14 |
+
"1": "B-Exp",
|
15 |
+
"2": "B-Features",
|
16 |
+
"3": "B-HackOrg",
|
17 |
+
"4": "B-Idus",
|
18 |
+
"5": "B-OffAct",
|
19 |
+
"6": "B-Org",
|
20 |
+
"7": "B-Purp",
|
21 |
+
"8": "B-SamFile",
|
22 |
+
"9": "B-SecTeam",
|
23 |
+
"10": "B-Time",
|
24 |
+
"11": "B-Tool",
|
25 |
+
"12": "B-Way",
|
26 |
+
"13": "I-Area",
|
27 |
+
"14": "I-Exp",
|
28 |
+
"15": "I-Features",
|
29 |
+
"16": "I-HackOrg",
|
30 |
+
"17": "I-Idus",
|
31 |
+
"18": "I-OffAct",
|
32 |
+
"19": "I-Org",
|
33 |
+
"20": "I-Purp",
|
34 |
+
"21": "I-SamFile",
|
35 |
+
"22": "I-SecTeam",
|
36 |
+
"23": "I-Time",
|
37 |
+
"24": "I-Tool",
|
38 |
+
"25": "I-Way",
|
39 |
+
"26": "O"
|
40 |
+
},
|
41 |
+
"initializer_range": 0.02,
|
42 |
+
"intermediate_size": 3072,
|
43 |
+
"label2id": {
|
44 |
+
"B-Area": 0,
|
45 |
+
"B-Exp": 1,
|
46 |
+
"B-Features": 2,
|
47 |
+
"B-HackOrg": 3,
|
48 |
+
"B-Idus": 4,
|
49 |
+
"B-OffAct": 5,
|
50 |
+
"B-Org": 6,
|
51 |
+
"B-Purp": 7,
|
52 |
+
"B-SamFile": 8,
|
53 |
+
"B-SecTeam": 9,
|
54 |
+
"B-Time": 10,
|
55 |
+
"B-Tool": 11,
|
56 |
+
"B-Way": 12,
|
57 |
+
"I-Area": 13,
|
58 |
+
"I-Exp": 14,
|
59 |
+
"I-Features": 15,
|
60 |
+
"I-HackOrg": 16,
|
61 |
+
"I-Idus": 17,
|
62 |
+
"I-OffAct": 18,
|
63 |
+
"I-Org": 19,
|
64 |
+
"I-Purp": 20,
|
65 |
+
"I-SamFile": 21,
|
66 |
+
"I-SecTeam": 22,
|
67 |
+
"I-Time": 23,
|
68 |
+
"I-Tool": 24,
|
69 |
+
"I-Way": 25,
|
70 |
+
"O": 26
|
71 |
+
},
|
72 |
+
"layer_norm_eps": 1e-12,
|
73 |
+
"max_position_embeddings": 512,
|
74 |
+
"model_type": "bert",
|
75 |
+
"num_attention_heads": 12,
|
76 |
+
"num_hidden_layers": 12,
|
77 |
+
"pad_token_id": 0,
|
78 |
+
"position_embedding_type": "absolute",
|
79 |
+
"torch_dtype": "float32",
|
80 |
+
"transformers_version": "4.43.3",
|
81 |
+
"type_vocab_size": 2,
|
82 |
+
"use_cache": true,
|
83 |
+
"vocab_size": 28996
|
84 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 430985108
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dd97ab8ec87788cde7d9773d67e3f93eedd9d7fc2450016fde463fbd37c031e
|
3 |
size 430985108
|
runs/Aug01_17-09-19_DESKTOP-7EBBP1S/events.out.tfevents.1722503410.DESKTOP-7EBBP1S.24612.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9d4391a08f88c931cda1d85e29fb5fc947e2207ef1d2f03df3c9087376e1856
|
3 |
+
size 10719
|
runs/Aug01_17-13-58_DESKTOP-7EBBP1S/events.out.tfevents.1722503639.DESKTOP-7EBBP1S.24612.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9433c23c5da51e8040340068794c5f790c7658cfa81f1b66ce8265f8b329ecf5
|
3 |
+
size 13843
|
runs/Aug01_17-13-58_DESKTOP-7EBBP1S/events.out.tfevents.1722504138.DESKTOP-7EBBP1S.24612.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47c93e8d7951642cae069d68cf928f9d1821c0bbe4f16cbc5587012ab4bfab39
|
3 |
+
size 560
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
-
{
|
2 |
-
"cls_token": "[CLS]",
|
3 |
-
"mask_token": "[MASK]",
|
4 |
-
"pad_token": "[PAD]",
|
5 |
-
"sep_token": "[SEP]",
|
6 |
-
"unk_token": "[UNK]"
|
7 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1,55 +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": false,
|
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 |
-
}
|
|
|
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": false,
|
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
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6dd9199dca07e480484cc9aa2407894e31845e4c2f756f72f07b88637b42e81
|
3 |
+
size 5176
|