Hugging Face's logo

Jehadoumer
/
task2B-preprocessed

Text Classification
Transformers
PyTorch
TensorBoard
bert
Model card Files
xet
Metrics Community
Jehadoumer commited on
Commit
d9ece77
·
1 Parent(s): 10d1476

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +2 -1
  2. pytorch_model.bin +1 -1
  3. runs/Aug13_12-25-41_24ab7b88dc52/events.out.tfevents.1691929711.24ab7b88dc52.184.1 +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +2 -29
  6. training_args.bin +1 -1
  7. vocab.txt +0 -0
config.json CHANGED
@@ -1,10 +1,11 @@
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,
 
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,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7724ec15db14f3e5d59f208296776c725a937bebb237ccfcf38abf97bf869be
3
  size 540854065
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07569c032c49f99965863f1d430bae602c950b8c76837c5514148e81b2faae20
3
  size 540854065
runs/Aug13_12-25-41_24ab7b88dc52/events.out.tfevents.1691929711.24ab7b88dc52.184.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0da3c8f8f939d17ad96b154a036b9234d083fcfb72534023f314c01980c4b3aa
3
+ size 4725
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -7,36 +7,8 @@
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]",
@@ -44,5 +16,6 @@
44
  "strip_accents": null,
45
  "tokenize_chinese_chars": true,
46
  "tokenizer_class": "BertTokenizer",
47
- "unk_token": "[UNK]"
 
48
  }
 
7
  "max_len": 512,
8
  "model_max_length": 512,
9
  "never_split": [
 
 
 
 
 
 
 
 
 
 
10
  "[بريد]",
 
 
 
 
 
 
11
  "[مستخدم]",
 
 
 
 
 
 
 
 
 
 
 
 
12
  "[رابط]"
13
  ],
14
  "pad_token": "[PAD]",
 
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9fb9ddc31ff614d55c6ef3ed8bef3430118d6c64b3d34663a13168f32def7b09
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4289cd9e78357cd6a1191dd58a278205d9ae77020bc48b204d2ae622e223a0a
3
  size 4027
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff