Jehadoumer commited on
Commit
cc88001
·
1 Parent(s): 9a79682

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aubmindlab/bert-base-arabertv2",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
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": "no-disinfo",
13
+ "1": "disinfo"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "label2id": {
18
+ "disinfo": 1,
19
+ "no-disinfo": 0
20
+ },
21
+ "layer_norm_eps": 1e-12,
22
+ "max_position_embeddings": 512,
23
+ "model_type": "bert",
24
+ "num_attention_heads": 12,
25
+ "num_hidden_layers": 12,
26
+ "pad_token_id": 0,
27
+ "position_embedding_type": "absolute",
28
+ "problem_type": "single_label_classification",
29
+ "torch_dtype": "float32",
30
+ "transformers_version": "4.31.0",
31
+ "type_vocab_size": 2,
32
+ "use_cache": true,
33
+ "vocab_size": 64000
34
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbccd23f8b062ed7c22c51b63a043c5ed9a7eb0884306dde01a2949ab5aa0bd
3
+ size 540847921
runs/Aug12_04-43-59_e45790b84fe8/events.out.tfevents.1691815445.e45790b84fe8.250.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4e886cb65415bea724995c234bb436bd315e0b7eb55e3d386487e6c6311bafc
3
+ size 4726
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 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "+ك",
11
+ "+كما",
12
+ "ك+",
13
+ "+وا",
14
+ "+ين",
15
+ "و+",
16
+ "+كن",
17
+ "+ان",
18
+ "+هم",
19
+ "+ة",
20
+ "[بريد]",
21
+ "لل+",
22
+ "+ي",
23
+ "+ت",
24
+ "+ن",
25
+ "س+",
26
+ "ل+",
27
+ "[مستخدم]",
28
+ "+كم",
29
+ "+ا",
30
+ "ب+",
31
+ "ف+",
32
+ "+نا",
33
+ "+ها",
34
+ "+ون",
35
+ "+هما",
36
+ "ال+",
37
+ "+ه",
38
+ "+هن",
39
+ "+ات",
40
+ "[رابط]"
41
+ ],
42
+ "pad_token": "[PAD]",
43
+ "sep_token": "[SEP]",
44
+ "strip_accents": null,
45
+ "tokenize_chinese_chars": true,
46
+ "tokenizer_class": "BertTokenizer",
47
+ "unk_token": "[UNK]"
48
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9b23d99b2d056b1af52cebffd272ea64a60f053c6ae68a638a6311f6a1da42
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff