Training in progress, epoch 1
Browse files- config.json +68 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
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": "environmental degradation",
|
14 |
+
"1": "human rights",
|
15 |
+
"2": "bribery & corruptions",
|
16 |
+
"3": "animal welfare or testing",
|
17 |
+
"4": "poor product safety and quality",
|
18 |
+
"5": "unsustainable practice",
|
19 |
+
"6": "poor corporate governance",
|
20 |
+
"7": "protected sites or species",
|
21 |
+
"8": "InappropriateUndesirable",
|
22 |
+
"9": "IllegalActivities",
|
23 |
+
"10": "DiscriminatoryHate",
|
24 |
+
"11": "ViolentGraphic",
|
25 |
+
"12": "PotentialAddiction",
|
26 |
+
"13": "ExtremismTerrorism",
|
27 |
+
"14": "SexualExplicit",
|
28 |
+
"15": "other"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"DiscriminatoryHate": 10,
|
34 |
+
"ExtremismTerrorism": 13,
|
35 |
+
"IllegalActivities": 9,
|
36 |
+
"InappropriateUndesirable": 8,
|
37 |
+
"PotentialAddiction": 12,
|
38 |
+
"SexualExplicit": 14,
|
39 |
+
"ViolentGraphic": 11,
|
40 |
+
"animal welfare or testing": 3,
|
41 |
+
"bribery & corruptions": 2,
|
42 |
+
"environmental degradation": 0,
|
43 |
+
"human rights": 1,
|
44 |
+
"other": 15,
|
45 |
+
"poor corporate governance": 6,
|
46 |
+
"poor product safety and quality": 4,
|
47 |
+
"protected sites or species": 7,
|
48 |
+
"unsustainable practice": 5
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-12,
|
51 |
+
"max_position_embeddings": 512,
|
52 |
+
"model_type": "bert",
|
53 |
+
"num_attention_heads": 12,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"pad_token_id": 0,
|
56 |
+
"pooler_fc_size": 768,
|
57 |
+
"pooler_num_attention_heads": 12,
|
58 |
+
"pooler_num_fc_layers": 3,
|
59 |
+
"pooler_size_per_head": 128,
|
60 |
+
"pooler_type": "first_token_transform",
|
61 |
+
"position_embedding_type": "absolute",
|
62 |
+
"problem_type": "single_label_classification",
|
63 |
+
"torch_dtype": "float32",
|
64 |
+
"transformers_version": "4.33.1",
|
65 |
+
"type_vocab_size": 2,
|
66 |
+
"use_cache": true,
|
67 |
+
"vocab_size": 119547
|
68 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a08320078a089e9a5238e20ed60a2ac2260f325dd8c8609951e51600d2998125
|
3 |
+
size 711531377
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"model_max_length": 512,
|
7 |
+
"pad_token": "[PAD]",
|
8 |
+
"sep_token": "[SEP]",
|
9 |
+
"strip_accents": null,
|
10 |
+
"tokenize_chinese_chars": true,
|
11 |
+
"tokenizer_class": "BertTokenizer",
|
12 |
+
"unk_token": "[UNK]"
|
13 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49baa61658decb5ec0f6effc3ce87e672145b4a7e0cfe84d11cb30d706473ce8
|
3 |
+
size 4091
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|