Matankl commited on
Commit
080ffcb
ยท
1 Parent(s): 4e09996

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-arabert",
3
+ "architectures": [
4
+ "BertForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "Interesting"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "Interesting": 1,
20
+ "O": 0
21
+ },
22
+ "layer_norm_eps": 1e-12,
23
+ "max_position_embeddings": 512,
24
+ "model_type": "bert",
25
+ "num_attention_heads": 12,
26
+ "num_hidden_layers": 12,
27
+ "pad_token_id": 0,
28
+ "pooler_fc_size": 768,
29
+ "pooler_num_attention_heads": 12,
30
+ "pooler_num_fc_layers": 3,
31
+ "pooler_size_per_head": 128,
32
+ "pooler_type": "first_token_transform",
33
+ "position_embedding_type": "absolute",
34
+ "problem_type": "single_label_classification",
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.30.2",
37
+ "type_vocab_size": 2,
38
+ "use_cache": true,
39
+ "vocab_size": 64000
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8f03abc840acfb32efd1be0c49534960ca5a2b987582f686d570f9004da24bc
3
+ size 540849970
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "full_tokenizer_file": null,
7
+ "mask_token": "[MASK]",
8
+ "max_len": 512,
9
+ "model_max_length": 512,
10
+ "never_split": [
11
+ "+ูˆุง",
12
+ "ุณ+",
13
+ "[ู…ุณุชุฎุฏู…]",
14
+ "+ูƒ",
15
+ "+ู‡ู…",
16
+ "+ุฉ",
17
+ "+ู†",
18
+ "ู„ู„+",
19
+ "[ุจุฑูŠุฏ]",
20
+ "[ุฑุงุจุท]",
21
+ "+ู‡",
22
+ "+ูƒู†",
23
+ "+ุง",
24
+ "+ุงุช",
25
+ "+ูŠ",
26
+ "ุจ+",
27
+ "+ู†ุง",
28
+ "+ู‡ู†",
29
+ "+ูƒู…",
30
+ "ูƒ+",
31
+ "+ูŠู†",
32
+ "+ู‡ู…ุง",
33
+ "ูˆ+",
34
+ "+ูƒู…ุง",
35
+ "+ุงู†",
36
+ "+ุช",
37
+ "+ูˆู†",
38
+ "ู„+",
39
+ "+ู‡ุง",
40
+ "ุงู„+",
41
+ "ู+"
42
+ ],
43
+ "pad_token": "[PAD]",
44
+ "sep_token": "[SEP]",
45
+ "strip_accents": null,
46
+ "tokenize_chinese_chars": true,
47
+ "tokenizer_class": "BertTokenizer",
48
+ "unk_token": "[UNK]"
49
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f4da2e2d3a7d086fcc319b85a60fc58358ffaf62dc9264468b7c0ce0b65403a
3
+ size 4408
vocab.txt ADDED
The diff for this file is too large to render. See raw diff