chosenone80 commited on
Commit
e7bbcda
1 Parent(s): 3a4538a

End of training

Browse files
Files changed (7) hide show
  1. README.md +60 -0
  2. config.json +71 -0
  3. special_tokens_map.json +7 -0
  4. tf_model.h5 +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +58 -0
  7. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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/model_save
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/model_save
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: 0.0906
19
+ - Validation Loss: 0.1264
20
+ - Train Precision: 0.9146
21
+ - Train Recall: 0.9154
22
+ - Train F1: 0.9150
23
+ - Train Accuracy: 0.9657
24
+ - Epoch: 2
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
+ - optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 48420, '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}
44
+ - training_precision: float32
45
+
46
+ ### Training results
47
+
48
+ | Train Loss | Validation Loss | Train Precision | Train Recall | Train F1 | Train Accuracy | Epoch |
49
+ |:----------:|:---------------:|:---------------:|:------------:|:--------:|:--------------:|:-----:|
50
+ | 0.1373 | 0.1417 | 0.9105 | 0.9060 | 0.9083 | 0.9628 | 0 |
51
+ | 0.1023 | 0.1244 | 0.9116 | 0.9136 | 0.9126 | 0.9643 | 1 |
52
+ | 0.0906 | 0.1264 | 0.9146 | 0.9154 | 0.9150 | 0.9657 | 2 |
53
+
54
+
55
+ ### Framework versions
56
+
57
+ - Transformers 4.35.2
58
+ - TensorFlow 2.15.0
59
+ - Datasets 2.16.1
60
+ - Tokenizers 0.15.0
config.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "Allah",
14
+ "1": "Book",
15
+ "2": "Clan",
16
+ "3": "Crime",
17
+ "4": "Date",
18
+ "5": "Day",
19
+ "6": "Hell",
20
+ "7": "Loc",
21
+ "8": "Meas",
22
+ "9": "Mon",
23
+ "10": "Month",
24
+ "11": "NatOb",
25
+ "12": "Number",
26
+ "13": "O",
27
+ "14": "Org",
28
+ "15": "Para",
29
+ "16": "Pers",
30
+ "17": "Prophet",
31
+ "18": "Rlig",
32
+ "19": "Sect",
33
+ "20": "Time"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "Allah": 0,
39
+ "Book": 1,
40
+ "Clan": 2,
41
+ "Crime": 3,
42
+ "Date": 4,
43
+ "Day": 5,
44
+ "Hell": 6,
45
+ "Loc": 7,
46
+ "Meas": 8,
47
+ "Mon": 9,
48
+ "Month": 10,
49
+ "NatOb": 11,
50
+ "Number": 12,
51
+ "O": 13,
52
+ "Org": 14,
53
+ "Para": 15,
54
+ "Pers": 16,
55
+ "Prophet": 17,
56
+ "Rlig": 18,
57
+ "Sect": 19,
58
+ "Time": 20
59
+ },
60
+ "layer_norm_eps": 1e-12,
61
+ "max_position_embeddings": 512,
62
+ "model_type": "bert",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "position_embedding_type": "absolute",
67
+ "transformers_version": "4.35.2",
68
+ "type_vocab_size": 2,
69
+ "use_cache": true,
70
+ "vocab_size": 30000
71
+ }
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 sha256:823503901da329ca9699e31349514faee95271163a3e785911c3c812fd8572fe
3
+ size 434313244
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