OK!
Browse files- README.md +63 -0
- config.json +107 -0
- model.safetensors +3 -0
- runs/Jul11_13-10-11_085319a33dc1/events.out.tfevents.1720703492.085319a33dc1.34.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: dbmdz/bert-base-turkish-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
+
model-index:
|
9 |
+
- name: bert-base-turkish-uncased-ner
|
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 |
+
# bert-base-turkish-uncased-ner
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [dbmdz/bert-base-turkish-uncased](https://huggingface.co/dbmdz/bert-base-turkish-uncased) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2539
|
21 |
+
- F1: 0.7738
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 32
|
42 |
+
- eval_batch_size: 32
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- num_epochs: 4
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 |
|
51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
52 |
+
| No log | 1.0 | 593 | 0.2625 | 0.7593 |
|
53 |
+
| 0.3541 | 2.0 | 1186 | 0.2497 | 0.7683 |
|
54 |
+
| 0.3541 | 3.0 | 1779 | 0.2509 | 0.7660 |
|
55 |
+
| 0.1847 | 4.0 | 2372 | 0.2539 | 0.7738 |
|
56 |
+
|
57 |
+
|
58 |
+
### Framework versions
|
59 |
+
|
60 |
+
- Transformers 4.41.2
|
61 |
+
- Pytorch 2.1.2
|
62 |
+
- Datasets 2.19.2
|
63 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,107 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbmdz/bert-base-turkish-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "B-CARDINAL",
|
13 |
+
"1": "I-TITLE",
|
14 |
+
"2": "I-CARDINAL",
|
15 |
+
"3": "B-ORDINAL",
|
16 |
+
"4": "B-LOC",
|
17 |
+
"5": "I-QUANTITY",
|
18 |
+
"6": "I-MONEY",
|
19 |
+
"7": "I-GPE",
|
20 |
+
"8": "I-PERCENT",
|
21 |
+
"9": "I-LAW",
|
22 |
+
"10": "I-NORP",
|
23 |
+
"11": "I-EVENT",
|
24 |
+
"12": "I-ORDINAL",
|
25 |
+
"13": "B-EVENT",
|
26 |
+
"14": "I-DATE",
|
27 |
+
"15": "B-QUANTITY",
|
28 |
+
"16": "I-FAC",
|
29 |
+
"17": "B-PERSON",
|
30 |
+
"18": "B-FAC",
|
31 |
+
"19": "I-TIME",
|
32 |
+
"20": "B-ORG",
|
33 |
+
"21": "B-TITLE",
|
34 |
+
"22": "I-LANGUAGE",
|
35 |
+
"23": "I-PRODUCT",
|
36 |
+
"24": "I-ORG",
|
37 |
+
"25": "B-PERCENT",
|
38 |
+
"26": "B-LAW",
|
39 |
+
"27": "B-LANGUAGE",
|
40 |
+
"28": "B-GPE",
|
41 |
+
"29": "B-TIME",
|
42 |
+
"30": "B-WORK_OF_ART",
|
43 |
+
"31": "B-PRODUCT",
|
44 |
+
"32": "O",
|
45 |
+
"33": "I-WORK_OF_ART",
|
46 |
+
"34": "B-DATE",
|
47 |
+
"35": "I-PERSON",
|
48 |
+
"36": "B-MONEY",
|
49 |
+
"37": "I-LOC",
|
50 |
+
"38": "B-NORP"
|
51 |
+
},
|
52 |
+
"initializer_range": 0.02,
|
53 |
+
"intermediate_size": 3072,
|
54 |
+
"label2id": {
|
55 |
+
"B-CARDINAL": 0,
|
56 |
+
"B-DATE": 34,
|
57 |
+
"B-EVENT": 13,
|
58 |
+
"B-FAC": 18,
|
59 |
+
"B-GPE": 28,
|
60 |
+
"B-LANGUAGE": 27,
|
61 |
+
"B-LAW": 26,
|
62 |
+
"B-LOC": 4,
|
63 |
+
"B-MONEY": 36,
|
64 |
+
"B-NORP": 38,
|
65 |
+
"B-ORDINAL": 3,
|
66 |
+
"B-ORG": 20,
|
67 |
+
"B-PERCENT": 25,
|
68 |
+
"B-PERSON": 17,
|
69 |
+
"B-PRODUCT": 31,
|
70 |
+
"B-QUANTITY": 15,
|
71 |
+
"B-TIME": 29,
|
72 |
+
"B-TITLE": 21,
|
73 |
+
"B-WORK_OF_ART": 30,
|
74 |
+
"I-CARDINAL": 2,
|
75 |
+
"I-DATE": 14,
|
76 |
+
"I-EVENT": 11,
|
77 |
+
"I-FAC": 16,
|
78 |
+
"I-GPE": 7,
|
79 |
+
"I-LANGUAGE": 22,
|
80 |
+
"I-LAW": 9,
|
81 |
+
"I-LOC": 37,
|
82 |
+
"I-MONEY": 6,
|
83 |
+
"I-NORP": 10,
|
84 |
+
"I-ORDINAL": 12,
|
85 |
+
"I-ORG": 24,
|
86 |
+
"I-PERCENT": 8,
|
87 |
+
"I-PERSON": 35,
|
88 |
+
"I-PRODUCT": 23,
|
89 |
+
"I-QUANTITY": 5,
|
90 |
+
"I-TIME": 19,
|
91 |
+
"I-TITLE": 1,
|
92 |
+
"I-WORK_OF_ART": 33,
|
93 |
+
"O": 32
|
94 |
+
},
|
95 |
+
"layer_norm_eps": 1e-12,
|
96 |
+
"max_position_embeddings": 512,
|
97 |
+
"model_type": "bert",
|
98 |
+
"num_attention_heads": 12,
|
99 |
+
"num_hidden_layers": 12,
|
100 |
+
"pad_token_id": 0,
|
101 |
+
"position_embedding_type": "absolute",
|
102 |
+
"torch_dtype": "float32",
|
103 |
+
"transformers_version": "4.41.2",
|
104 |
+
"type_vocab_size": 2,
|
105 |
+
"use_cache": true,
|
106 |
+
"vocab_size": 32000
|
107 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88f370b8bc4db6928e82bd7e00385d96702f4eb6a3a70902c3d1b7f810b390cd
|
3 |
+
size 440250324
|
runs/Jul11_13-10-11_085319a33dc1/events.out.tfevents.1720703492.085319a33dc1.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:64d26c588e5516c640b58ffc71acd1fe865874620245373043b6c7fcb10c3498
|
3 |
+
size 8422
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_len": 512,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0db07c996371bd378cf2fe796e657c53e7db8dd13603f1c594e8ba6e758419ad
|
3 |
+
size 5112
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|