SMG0 commited on
Commit
013e668
·
1 Parent(s): c598cd1

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aubmindlab/bert-base-arabertv02-twitter",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "RH:ISLAM",
14
+ "1": "RH:Judaism",
15
+ "2": "RH:Christianity",
16
+ "3": "UD_RH",
17
+ "4": "EH:ARAB",
18
+ "5": "EH:African",
19
+ "6": "UD_EH",
20
+ "7": "NH:Iranian",
21
+ "8": "NH:Israeli",
22
+ "9": "NH:Saudi",
23
+ "10": "NH:Turkish",
24
+ "11": "NH:Qatari",
25
+ "12": "NH:American",
26
+ "13": "UD_NH",
27
+ "14": "GH:Females",
28
+ "15": "GH:Males",
29
+ "16": "UD_GH"
30
+ },
31
+ "initializer_range": 0.02,
32
+ "intermediate_size": 3072,
33
+ "label2id": {
34
+ "EH:ARAB": 4,
35
+ "EH:African": 5,
36
+ "GH:Females": 14,
37
+ "GH:Males": 15,
38
+ "NH:American": 12,
39
+ "NH:Iranian": 7,
40
+ "NH:Israeli": 8,
41
+ "NH:Qatari": 11,
42
+ "NH:Saudi": 9,
43
+ "NH:Turkish": 10,
44
+ "RH:Christianity": 2,
45
+ "RH:ISLAM": 0,
46
+ "RH:Judaism": 1,
47
+ "UD_EH": 6,
48
+ "UD_GH": 16,
49
+ "UD_NH": 13,
50
+ "UD_RH": 3
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "max_position_embeddings": 512,
54
+ "model_type": "bert",
55
+ "num_attention_heads": 12,
56
+ "num_hidden_layers": 12,
57
+ "pad_token_id": 0,
58
+ "position_embedding_type": "absolute",
59
+ "problem_type": "multi_label_classification",
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.31.0",
62
+ "type_vocab_size": 2,
63
+ "use_cache": true,
64
+ "vocab_size": 64000
65
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a788204cfcfb7e37f98591cf502e0478720bd15398304d7cde4311e40b001bea
3
+ size 540894065
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 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "max_len": 512,
8
+ "model_max_length": 512,
9
+ "never_split": [
10
+ "[بريد]",
11
+ "[مستخدم]",
12
+ "[رابط]"
13
+ ],
14
+ "pad_token": "[PAD]",
15
+ "sep_token": "[SEP]",
16
+ "strip_accents": null,
17
+ "tokenize_chinese_chars": true,
18
+ "tokenizer_class": "BertTokenizer",
19
+ "unk_token": "[UNK]",
20
+ "use_fast": true
21
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99aa69f7feabb7273e7ebf810c7c5a5aaaaceb75ffa6775c792c10ec6c9b3781
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff