Jehadoumer commited on
Commit
314030d
ยท
1 Parent(s): d581e34

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "HS",
13
+ "1": "OFF",
14
+ "2": "SPAM",
15
+ "3": "Rumor"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "HS": 0,
21
+ "OFF": 1,
22
+ "Rumor": 3,
23
+ "SPAM": 2
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "bert",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "problem_type": "single_label_classification",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.31.0",
35
+ "type_vocab_size": 2,
36
+ "use_cache": true,
37
+ "vocab_size": 64000
38
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fd00d0a45c8b5d8a0adcc150c23408cc0e04392a9669eeddc79907ab998c24
3
+ size 540854065
runs/Aug12_10-20-43_d5e8e653435b/events.out.tfevents.1691835648.d5e8e653435b.249.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0b24a91033d28e31d235ce235dd088a5aea3347902af1a81960ce51a38c04af
3
+ size 4625
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
+ "+ูƒ",
11
+ "+ูƒู…ุง",
12
+ "ูƒ+",
13
+ "+ูˆุง",
14
+ "+ูŠู†",
15
+ "ูˆ+",
16
+ "+ูƒู†",
17
+ "+ุงู†",
18
+ "+ู‡ู…",
19
+ "+ุฉ",
20
+ "[ุจุฑูŠุฏ]",
21
+ "ู„ู„+",
22
+ "+ูŠ",
23
+ "+ุช",
24
+ "+ู†",
25
+ "ุณ+",
26
+ "ู„+",
27
+ "[ู…ุณุชุฎุฏู…]",
28
+ "+ูƒู…",
29
+ "+ุง",
30
+ "ุจ+",
31
+ "ู+",
32
+ "+ู†ุง",
33
+ "+ู‡ุง",
34
+ "+ูˆู†",
35
+ "+ู‡ู…ุง",
36
+ "ุงู„+",
37
+ "+ู‡",
38
+ "+ู‡ู†",
39
+ "+ุงุช",
40
+ "[ุฑุงุจุท]"
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:f189d405dc581718a9f2a3aba64eb52becf5e38c7861cf2951003259f2a060b5
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff