chosenone80
commited on
Commit
·
212b79c
1
Parent(s):
dc9b980
Training in progress epoch 0
Browse files- README.md +54 -0
- config.json +111 -0
- special_tokens_map.json +7 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: CAMeL-Lab/bert-base-arabic-camelbert-ca
|
4 |
+
tags:
|
5 |
+
- generated_from_keras_callback
|
6 |
+
model-index:
|
7 |
+
- name: chosenone80/bert-ner-test-3
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
12 |
+
probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# chosenone80/bert-ner-test-3
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [CAMeL-Lab/bert-base-arabic-camelbert-ca](https://huggingface.co/CAMeL-Lab/bert-base-arabic-camelbert-ca) on an unknown dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Train Loss: 0.2648
|
19 |
+
- Validation Loss: 0.0788
|
20 |
+
- Epoch: 0
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 565, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
|
40 |
+
- training_precision: mixed_float16
|
41 |
+
|
42 |
+
### Training results
|
43 |
+
|
44 |
+
| Train Loss | Validation Loss | Epoch |
|
45 |
+
|:----------:|:---------------:|:-----:|
|
46 |
+
| 0.2648 | 0.0788 | 0 |
|
47 |
+
|
48 |
+
|
49 |
+
### Framework versions
|
50 |
+
|
51 |
+
- Transformers 4.37.2
|
52 |
+
- TensorFlow 2.15.0
|
53 |
+
- Datasets 2.17.1
|
54 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,111 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-ca",
|
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-Allah",
|
14 |
+
"1": "I-Allah",
|
15 |
+
"2": "B-Book",
|
16 |
+
"3": "I-Book",
|
17 |
+
"4": "B-Clan",
|
18 |
+
"5": "I-Clan",
|
19 |
+
"6": "B-Crime",
|
20 |
+
"7": "I-Crime",
|
21 |
+
"8": "B-Date",
|
22 |
+
"9": "I-Date",
|
23 |
+
"10": "B-Day",
|
24 |
+
"11": "I-Day",
|
25 |
+
"12": "B-Hell",
|
26 |
+
"13": "I-Hell",
|
27 |
+
"14": "B-Loc",
|
28 |
+
"15": "I-Loc",
|
29 |
+
"16": "B-Meas",
|
30 |
+
"17": "I-Meas",
|
31 |
+
"18": "B-Mon",
|
32 |
+
"19": "I-Mon",
|
33 |
+
"20": "B-Month",
|
34 |
+
"21": "I-Month",
|
35 |
+
"22": "B-NatOb",
|
36 |
+
"23": "I-NatOb",
|
37 |
+
"24": "B-NUM",
|
38 |
+
"25": "I-NUM",
|
39 |
+
"26": "O",
|
40 |
+
"27": "B-Org",
|
41 |
+
"28": "I-Org",
|
42 |
+
"29": "B-Para",
|
43 |
+
"30": "I-Para",
|
44 |
+
"31": "B-Pers",
|
45 |
+
"32": "I-Pers",
|
46 |
+
"33": "B-Prophet",
|
47 |
+
"34": "I-Prophet",
|
48 |
+
"35": "B-Rlig",
|
49 |
+
"36": "I-Rlig",
|
50 |
+
"37": "B-Sect",
|
51 |
+
"38": "I-Sect",
|
52 |
+
"39": "B-Time",
|
53 |
+
"40": "I-Time"
|
54 |
+
},
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 3072,
|
57 |
+
"label2id": {
|
58 |
+
"B-Allah": 0,
|
59 |
+
"B-Book": 2,
|
60 |
+
"B-Clan": 4,
|
61 |
+
"B-Crime": 6,
|
62 |
+
"B-Date": 8,
|
63 |
+
"B-Day": 10,
|
64 |
+
"B-Hell": 12,
|
65 |
+
"B-Loc": 14,
|
66 |
+
"B-Meas": 16,
|
67 |
+
"B-Mon": 18,
|
68 |
+
"B-Month": 20,
|
69 |
+
"B-NUM": 24,
|
70 |
+
"B-NatOb": 22,
|
71 |
+
"B-Org": 27,
|
72 |
+
"B-Para": 29,
|
73 |
+
"B-Pers": 31,
|
74 |
+
"B-Prophet": 33,
|
75 |
+
"B-Rlig": 35,
|
76 |
+
"B-Sect": 37,
|
77 |
+
"B-Time": 39,
|
78 |
+
"I-Allah": 1,
|
79 |
+
"I-Book": 3,
|
80 |
+
"I-Clan": 5,
|
81 |
+
"I-Crime": 7,
|
82 |
+
"I-Date": 9,
|
83 |
+
"I-Day": 11,
|
84 |
+
"I-Hell": 13,
|
85 |
+
"I-Loc": 15,
|
86 |
+
"I-Meas": 17,
|
87 |
+
"I-Mon": 19,
|
88 |
+
"I-Month": 21,
|
89 |
+
"I-NUM": 25,
|
90 |
+
"I-NatOb": 23,
|
91 |
+
"I-Org": 28,
|
92 |
+
"I-Para": 30,
|
93 |
+
"I-Pers": 32,
|
94 |
+
"I-Prophet": 34,
|
95 |
+
"I-Rlig": 36,
|
96 |
+
"I-Sect": 38,
|
97 |
+
"I-Time": 40,
|
98 |
+
"O": 26
|
99 |
+
},
|
100 |
+
"layer_norm_eps": 1e-12,
|
101 |
+
"max_position_embeddings": 512,
|
102 |
+
"model_type": "bert",
|
103 |
+
"num_attention_heads": 12,
|
104 |
+
"num_hidden_layers": 12,
|
105 |
+
"pad_token_id": 0,
|
106 |
+
"position_embedding_type": "absolute",
|
107 |
+
"transformers_version": "4.37.2",
|
108 |
+
"type_vocab_size": 2,
|
109 |
+
"use_cache": true,
|
110 |
+
"vocab_size": 30000
|
111 |
+
}
|
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 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f620714de0b1c3839c93157d91e3841a7b3df6c1a9416a84677d59cec0729d94
|
3 |
+
size 434362476
|
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": false,
|
48 |
+
"full_tokenizer_file": null,
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 1000000000000000019884624838656,
|
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 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|