Training in progress, step 100
Browse files- .gitignore +1 -0
- config.json +58 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-uncased",
|
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": "1.1 threats of harm",
|
14 |
+
"1": "1.2 incitement and encouragement of harm",
|
15 |
+
"2": "2.1 descriptive attacks",
|
16 |
+
"3": "2.2 aggressive and emotive attacks",
|
17 |
+
"4": "2.3 dehumanising attacks & overt sexual objectification",
|
18 |
+
"5": "3.1 casual use of gendered slurs, profanities, and insults",
|
19 |
+
"6": "3.2 immutable gender differences and gender stereotypes",
|
20 |
+
"7": "3.3 backhanded gendered compliments",
|
21 |
+
"8": "3.4 condescending explanations or unwelcome advice",
|
22 |
+
"9": "4.1 supporting mistreatment of individual women",
|
23 |
+
"10": "4.2 supporting systemic discrimination against women as a group"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"1.1 threats of harm": 0,
|
29 |
+
"1.2 incitement and encouragement of harm": 1,
|
30 |
+
"2.1 descriptive attacks": 2,
|
31 |
+
"2.2 aggressive and emotive attacks": 3,
|
32 |
+
"2.3 dehumanising attacks & overt sexual objectification": 4,
|
33 |
+
"3.1 casual use of gendered slurs, profanities, and insults": 5,
|
34 |
+
"3.2 immutable gender differences and gender stereotypes": 6,
|
35 |
+
"3.3 backhanded gendered compliments": 7,
|
36 |
+
"3.4 condescending explanations or unwelcome advice": 8,
|
37 |
+
"4.1 supporting mistreatment of individual women": 9,
|
38 |
+
"4.2 supporting systemic discrimination against women as a group": 10
|
39 |
+
},
|
40 |
+
"layer_norm_eps": 1e-12,
|
41 |
+
"max_position_embeddings": 512,
|
42 |
+
"model_type": "bert",
|
43 |
+
"num_attention_heads": 12,
|
44 |
+
"num_hidden_layers": 12,
|
45 |
+
"pad_token_id": 0,
|
46 |
+
"pooler_fc_size": 768,
|
47 |
+
"pooler_num_attention_heads": 12,
|
48 |
+
"pooler_num_fc_layers": 3,
|
49 |
+
"pooler_size_per_head": 128,
|
50 |
+
"pooler_type": "first_token_transform",
|
51 |
+
"position_embedding_type": "absolute",
|
52 |
+
"problem_type": "single_label_classification",
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.24.0",
|
55 |
+
"type_vocab_size": 2,
|
56 |
+
"use_cache": true,
|
57 |
+
"vocab_size": 105879
|
58 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d210ae43c50eb9b61962d636d2ea5fdf0e2acdce1ad7f956a444f53944286077
|
3 |
+
size 669530477
|
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 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_lower_case": true,
|
4 |
+
"mask_token": "[MASK]",
|
5 |
+
"model_max_length": 512,
|
6 |
+
"name_or_path": "bert-base-multilingual-uncased",
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"strip_accents": null,
|
11 |
+
"tokenize_chinese_chars": true,
|
12 |
+
"tokenizer_class": "BertTokenizer",
|
13 |
+
"unk_token": "[UNK]"
|
14 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:204a65bee075758c5face97dfde3b735b23d1e1739d0abf26e5dbc9ebe674840
|
3 |
+
size 3631
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|