Training in progress, epoch 1
Browse files- .gitignore +1 -0
- config.json +105 -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 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "Name calling_Labeling",
|
15 |
+
"10": "Flag_waving",
|
16 |
+
"11": "Glittering generalities (Virtue)",
|
17 |
+
"12": "Repetition",
|
18 |
+
"13": "Slogans",
|
19 |
+
"14": "Whataboutism",
|
20 |
+
"15": "Reductio ad hitlerum",
|
21 |
+
"16": "Appeal_to_Fear-Prejudice",
|
22 |
+
"17": "Loaded_Language",
|
23 |
+
"18": "Name_Calling-Labeling",
|
24 |
+
"19": "Questioning_the_Reputation",
|
25 |
+
"2": "Causal Oversimplification",
|
26 |
+
"20": "Exaggeration-Minimisation",
|
27 |
+
"21": "Appeal_to_Values",
|
28 |
+
"22": "Flag_Waving",
|
29 |
+
"23": "Obfuscation-Vagueness-Confusion",
|
30 |
+
"24": "Appeal_to_Authority",
|
31 |
+
"25": "Causal_Oversimplification",
|
32 |
+
"26": "False_Dilemma-No_Choice",
|
33 |
+
"27": "Conversation_Killer",
|
34 |
+
"28": "Straw_Man",
|
35 |
+
"29": "Appeal_to_Hypocrisy",
|
36 |
+
"3": "Loaded Language",
|
37 |
+
"30": "Appeal_to_Popularity",
|
38 |
+
"31": "Guilt_by_Association",
|
39 |
+
"32": "Red_Herring",
|
40 |
+
"33": "Appeal_to_Time",
|
41 |
+
"34": "Consequential_Oversimplification",
|
42 |
+
"4": "no technique",
|
43 |
+
"5": "Appeal to authority",
|
44 |
+
"6": "Smears",
|
45 |
+
"7": "Exaggeration_Minimisation",
|
46 |
+
"8": "Appeal to fear_prejudice",
|
47 |
+
"9": "Doubt"
|
48 |
+
},
|
49 |
+
"initializer_range": 0.02,
|
50 |
+
"intermediate_size": 3072,
|
51 |
+
"label2id": {
|
52 |
+
"0": "0",
|
53 |
+
"Appeal to authority": "5",
|
54 |
+
"Appeal to fear_prejudice": "8",
|
55 |
+
"Appeal_to_Authority": "24",
|
56 |
+
"Appeal_to_Fear-Prejudice": "16",
|
57 |
+
"Appeal_to_Hypocrisy": "29",
|
58 |
+
"Appeal_to_Popularity": "30",
|
59 |
+
"Appeal_to_Time": "33",
|
60 |
+
"Appeal_to_Values": "21",
|
61 |
+
"Causal Oversimplification": "2",
|
62 |
+
"Causal_Oversimplification": "25",
|
63 |
+
"Consequential_Oversimplification": "34",
|
64 |
+
"Conversation_Killer": "27",
|
65 |
+
"Doubt": "9",
|
66 |
+
"Exaggeration-Minimisation": "20",
|
67 |
+
"Exaggeration_Minimisation": "7",
|
68 |
+
"False_Dilemma-No_Choice": "26",
|
69 |
+
"Flag_Waving": "22",
|
70 |
+
"Flag_waving": "10",
|
71 |
+
"Glittering generalities (Virtue)": "11",
|
72 |
+
"Guilt_by_Association": "31",
|
73 |
+
"Loaded Language": "3",
|
74 |
+
"Loaded_Language": "17",
|
75 |
+
"Name calling_Labeling": "1",
|
76 |
+
"Name_Calling-Labeling": "18",
|
77 |
+
"Obfuscation-Vagueness-Confusion": "23",
|
78 |
+
"Questioning_the_Reputation": "19",
|
79 |
+
"Red_Herring": "32",
|
80 |
+
"Reductio ad hitlerum": "15",
|
81 |
+
"Repetition": "12",
|
82 |
+
"Slogans": "13",
|
83 |
+
"Smears": "6",
|
84 |
+
"Straw_Man": "28",
|
85 |
+
"Whataboutism": "14",
|
86 |
+
"no technique": "4"
|
87 |
+
},
|
88 |
+
"layer_norm_eps": 1e-12,
|
89 |
+
"max_position_embeddings": 512,
|
90 |
+
"model_type": "bert",
|
91 |
+
"num_attention_heads": 12,
|
92 |
+
"num_hidden_layers": 12,
|
93 |
+
"pad_token_id": 0,
|
94 |
+
"pooler_fc_size": 768,
|
95 |
+
"pooler_num_attention_heads": 12,
|
96 |
+
"pooler_num_fc_layers": 3,
|
97 |
+
"pooler_size_per_head": 128,
|
98 |
+
"pooler_type": "first_token_transform",
|
99 |
+
"position_embedding_type": "absolute",
|
100 |
+
"torch_dtype": "float32",
|
101 |
+
"transformers_version": "4.30.2",
|
102 |
+
"type_vocab_size": 2,
|
103 |
+
"use_cache": true,
|
104 |
+
"vocab_size": 64000
|
105 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04d9847d29ef2c6c707661fb114d76d3b813e8e516b50fc303808f2336327c3e
|
3 |
+
size 538586289
|
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 sha256:8f8c6f02e4decd49c6b87bc2412526e2855721a1c6f89457a663a74b70f6f4b4
|
3 |
+
size 3951
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|