SMG0 commited on
Commit
3c0a770
·
1 Parent(s): 7597465

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aubmindlab/bert-large-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": 1024,
12
+ "id2label": {
13
+ "0": "RH",
14
+ "1": "EH",
15
+ "2": "NH",
16
+ "3": "GH",
17
+ "4": "UDH",
18
+ "5": "CL"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 4096,
22
+ "label2id": {
23
+ "CL": 5,
24
+ "EH": 1,
25
+ "GH": 3,
26
+ "NH": 2,
27
+ "RH": 0,
28
+ "UDH": 4
29
+ },
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 512,
32
+ "model_type": "bert",
33
+ "num_attention_heads": 16,
34
+ "num_hidden_layers": 24,
35
+ "pad_token_id": 0,
36
+ "position_embedding_type": "absolute",
37
+ "problem_type": "multi_label_classification",
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.31.0",
40
+ "type_vocab_size": 2,
41
+ "use_cache": true,
42
+ "vocab_size": 64000
43
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f6a4bdbfe48a3a64d6de6010906c2e29b507ea3ec1ef324d004cdb2fb4658f
3
+ size 1477852465
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 sha256:15236396e9aec1c1b1ff441ff094a5a2a6cc3bc64140aa248db15a653793c3e9
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff