aomar85 commited on
Commit
fc76994
·
1 Parent(s): 871b281

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "problem_type": "single_label_classification",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.21.3",
23
+ "type_vocab_size": 2,
24
+ "use_cache": true,
25
+ "vocab_size": 64000
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54bfc02778a61889698c21b93f077ee947a05e6a7aaf5748280704765b162d38
3
+ size 540850541
runs/Sep06_17-42-43_7dc6aeb90020/1662486222.3901448/events.out.tfevents.1662486222.7dc6aeb90020.89.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6a264ef8fa4b7765244e1215c4f6c0a7c2607627eedc77e9b726a044e1164d2
3
+ size 5472
runs/Sep06_17-42-43_7dc6aeb90020/events.out.tfevents.1662486222.7dc6aeb90020.89.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc307ccfbb25ec967b7c1f35794eb957175d718abedb997da4d0bf5a48a4526
3
+ size 4310
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
+ "cls_token": "[CLS]",
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "max_len": 512,
7
+ "name_or_path": "aubmindlab/bert-base-arabertv2",
8
+ "never_split": [
9
+ "+ك",
10
+ "+كما",
11
+ "ك+",
12
+ "+وا",
13
+ "+ين",
14
+ "و+",
15
+ "+كن",
16
+ "+ان",
17
+ "+هم",
18
+ "+ة",
19
+ "[بريد]",
20
+ "لل+",
21
+ "+ي",
22
+ "+ت",
23
+ "+ن",
24
+ "س+",
25
+ "ل+",
26
+ "[مستخدم]",
27
+ "+كم",
28
+ "+ا",
29
+ "ب+",
30
+ "ف+",
31
+ "+نا",
32
+ "+ها",
33
+ "+ون",
34
+ "+هما",
35
+ "ال+",
36
+ "+ه",
37
+ "+هن",
38
+ "+ات",
39
+ "[رابط]"
40
+ ],
41
+ "pad_token": "[PAD]",
42
+ "sep_token": "[SEP]",
43
+ "special_tokens_map_file": null,
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:fc0520614ccf7329f52e6b9ce45adb3257ed2fc424f73fad8e203e9f1c8ab5a3
3
+ size 3375
vocab.txt ADDED
The diff for this file is too large to render. See raw diff