ashabrawy commited on
Commit
65bfbd0
·
verified ·
1 Parent(s): b3bdbe0

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "MSA",
14
+ "1": "Algeria",
15
+ "2": "Bahrain",
16
+ "3": "Djibouti",
17
+ "4": "Egypt",
18
+ "5": "Iraq",
19
+ "6": "Jordan",
20
+ "7": "Kuwait",
21
+ "8": "Lebanon",
22
+ "9": "Libya",
23
+ "10": "Mauritania",
24
+ "11": "Morocco",
25
+ "12": "Oman",
26
+ "13": "Palestine",
27
+ "14": "Qatar",
28
+ "15": "Saudi_Arabia",
29
+ "16": "Somalia",
30
+ "17": "Sudan",
31
+ "18": "Syria",
32
+ "19": "Tunisia",
33
+ "20": "United_Arab_Emirates",
34
+ "21": "Yemen"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "label2id": {
39
+ "Algeria": 1,
40
+ "Bahrain": 2,
41
+ "Djibouti": 3,
42
+ "Egypt": 4,
43
+ "Iraq": 5,
44
+ "Jordan": 6,
45
+ "Kuwait": 7,
46
+ "Lebanon": 8,
47
+ "Libya": 9,
48
+ "MSA": 0,
49
+ "Mauritania": 10,
50
+ "Morocco": 11,
51
+ "Oman": 12,
52
+ "Palestine": 13,
53
+ "Qatar": 14,
54
+ "Saudi_Arabia": 15,
55
+ "Somalia": 16,
56
+ "Sudan": 17,
57
+ "Syria": 18,
58
+ "Tunisia": 19,
59
+ "United_Arab_Emirates": 20,
60
+ "Yemen": 21
61
+ },
62
+ "layer_norm_eps": 1e-12,
63
+ "max_position_embeddings": 512,
64
+ "model_type": "bert",
65
+ "num_attention_heads": 12,
66
+ "num_hidden_layers": 12,
67
+ "pad_token_id": 0,
68
+ "pooler_fc_size": 768,
69
+ "pooler_num_attention_heads": 12,
70
+ "pooler_num_fc_layers": 3,
71
+ "pooler_size_per_head": 128,
72
+ "pooler_type": "first_token_transform",
73
+ "position_embedding_type": "absolute",
74
+ "problem_type": "single_label_classification",
75
+ "torch_dtype": "float32",
76
+ "transformers_version": "4.55.2",
77
+ "type_vocab_size": 2,
78
+ "use_cache": true,
79
+ "vocab_size": 100000
80
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e23ec4c768894faee94889dc324b13e6afbfdecae5858a9c4fb9e43f449ee34
3
+ size 651456600
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c119cc25d759b2999d44d68b1f58facad023b3eb6a1fc62beb4154f2e171b46
3
+ size 5777
vocab.txt ADDED
The diff for this file is too large to render. See raw diff