Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +83 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +49 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "aubmindlab/bert-base-arabert",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
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": "0",
|
14 |
+
"1": "Loaded_Language",
|
15 |
+
"10": "Conversation_Killer",
|
16 |
+
"11": "Causal_Oversimplification",
|
17 |
+
"12": "False_Dilemma-No_Choice",
|
18 |
+
"13": "Whataboutism",
|
19 |
+
"14": "Straw_Man",
|
20 |
+
"15": "Guilt_by_Association",
|
21 |
+
"16": "Obfuscation-Vagueness-Confusion",
|
22 |
+
"17": "Red_Herring",
|
23 |
+
"18": "Questioning_the_Reputation",
|
24 |
+
"19": "Appeal_to_Values",
|
25 |
+
"2": "Appeal_to_Fear-Prejudice",
|
26 |
+
"20": "Appeal_to_Hypocrisy",
|
27 |
+
"21": "Appeal_to_Popularity",
|
28 |
+
"22": "Appeal_to_Time",
|
29 |
+
"23": "Consequential_Oversimplification",
|
30 |
+
"3": "Repetition",
|
31 |
+
"4": "Exaggeration-Minimisation",
|
32 |
+
"5": "Slogans",
|
33 |
+
"6": "Name_Calling-Labeling",
|
34 |
+
"7": "Doubt",
|
35 |
+
"8": "Appeal_to_Authority",
|
36 |
+
"9": "Flag_Waving"
|
37 |
+
},
|
38 |
+
"initializer_range": 0.02,
|
39 |
+
"intermediate_size": 3072,
|
40 |
+
"label2id": {
|
41 |
+
"0": "0",
|
42 |
+
"Appeal_to_Authority": "8",
|
43 |
+
"Appeal_to_Fear-Prejudice": "2",
|
44 |
+
"Appeal_to_Hypocrisy": "20",
|
45 |
+
"Appeal_to_Popularity": "21",
|
46 |
+
"Appeal_to_Time": "22",
|
47 |
+
"Appeal_to_Values": "19",
|
48 |
+
"Causal_Oversimplification": "11",
|
49 |
+
"Consequential_Oversimplification": "23",
|
50 |
+
"Conversation_Killer": "10",
|
51 |
+
"Doubt": "7",
|
52 |
+
"Exaggeration-Minimisation": "4",
|
53 |
+
"False_Dilemma-No_Choice": "12",
|
54 |
+
"Flag_Waving": "9",
|
55 |
+
"Guilt_by_Association": "15",
|
56 |
+
"Loaded_Language": "1",
|
57 |
+
"Name_Calling-Labeling": "6",
|
58 |
+
"Obfuscation-Vagueness-Confusion": "16",
|
59 |
+
"Questioning_the_Reputation": "18",
|
60 |
+
"Red_Herring": "17",
|
61 |
+
"Repetition": "3",
|
62 |
+
"Slogans": "5",
|
63 |
+
"Straw_Man": "14",
|
64 |
+
"Whataboutism": "13"
|
65 |
+
},
|
66 |
+
"layer_norm_eps": 1e-12,
|
67 |
+
"max_position_embeddings": 512,
|
68 |
+
"model_type": "bert",
|
69 |
+
"num_attention_heads": 12,
|
70 |
+
"num_hidden_layers": 12,
|
71 |
+
"pad_token_id": 0,
|
72 |
+
"pooler_fc_size": 768,
|
73 |
+
"pooler_num_attention_heads": 12,
|
74 |
+
"pooler_num_fc_layers": 3,
|
75 |
+
"pooler_size_per_head": 128,
|
76 |
+
"pooler_type": "first_token_transform",
|
77 |
+
"position_embedding_type": "absolute",
|
78 |
+
"torch_dtype": "float32",
|
79 |
+
"transformers_version": "4.30.2",
|
80 |
+
"type_vocab_size": 2,
|
81 |
+
"use_cache": true,
|
82 |
+
"vocab_size": 64000
|
83 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59fa66f9d37b7e6a61c245fcec83b6cb3722a4cde173ab065d10ab8db19fdfd4
|
3 |
+
size 538552433
|
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 |
+
"+ูุง",
|
12 |
+
"ุณ+",
|
13 |
+
"[ู
ุณุชุฎุฏู
]",
|
14 |
+
"+ู",
|
15 |
+
"+ูู
",
|
16 |
+
"+ุฉ",
|
17 |
+
"+ู",
|
18 |
+
"ูู+",
|
19 |
+
"[ุจุฑูุฏ]",
|
20 |
+
"[ุฑุงุจุท]",
|
21 |
+
"+ู",
|
22 |
+
"+ูู",
|
23 |
+
"+ุง",
|
24 |
+
"+ุงุช",
|
25 |
+
"+ู",
|
26 |
+
"ุจ+",
|
27 |
+
"+ูุง",
|
28 |
+
"+ูู",
|
29 |
+
"+ูู
",
|
30 |
+
"ู+",
|
31 |
+
"+ูู",
|
32 |
+
"+ูู
ุง",
|
33 |
+
"ู+",
|
34 |
+
"+ูู
ุง",
|
35 |
+
"+ุงู",
|
36 |
+
"+ุช",
|
37 |
+
"+ูู",
|
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 sha256:99cedc9375cd5e8f6b8ce5530c69da252bfd3e36b015e344c3a82e6aedb4e21d
|
3 |
+
size 4015
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|