terzimert commited on
Commit
3a5750e
·
1 Parent(s): 1c746ac

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-mix-ner",
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-LOC",
14
+ "1": "B-MISC",
15
+ "2": "B-ORG",
16
+ "3": "B-PERS",
17
+ "4": "I-LOC",
18
+ "5": "I-MISC",
19
+ "6": "I-ORG",
20
+ "7": "I-PERS",
21
+ "8": "O"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "B-LOC": 0,
27
+ "B-MISC": 1,
28
+ "B-ORG": 2,
29
+ "B-PERS": 3,
30
+ "I-LOC": 4,
31
+ "I-MISC": 5,
32
+ "I-ORG": 6,
33
+ "I-PERS": 7,
34
+ "O": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.28.1",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30000
48
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bce34f0f972bfd95e26c6ed30278d8f80a97048a4367d2fe5b64de3c3d949c
3
+ size 434062829
runs/Apr24_06-05-47_f10d85602007/1682316358.9175115/events.out.tfevents.1682316358.f10d85602007.292.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c83c75df22d4c4bf2f06cf1961561c836c99294658eb08d9d9381f41c5e9f76
3
+ size 5879
runs/Apr24_06-05-47_f10d85602007/events.out.tfevents.1682316358.f10d85602007.292.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dacfaab01f5fbd7e6e5a7016db5eb416318d38d29b389c406d4e4b7177b17a2f
3
+ size 7047
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "full_tokenizer_file": null,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb9d13a0de59162999c7529022b1f83f2724776e388b8698839c1e6035a9ee97
3
+ size 3579
vocab.txt ADDED
The diff for this file is too large to render. See raw diff