Training in progress, epoch 1
Browse files- config.json +72 -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
config.json
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "chkla/parlbert-topic-german",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "Macroeconomics",
|
13 |
+
"1": "Civil",
|
14 |
+
"2": "Health",
|
15 |
+
"3": "Agriculture",
|
16 |
+
"4": "Labor",
|
17 |
+
"5": "Education",
|
18 |
+
"6": "Environment",
|
19 |
+
"7": "Energy",
|
20 |
+
"8": "Immigration",
|
21 |
+
"9": "Transportation",
|
22 |
+
"10": "Law",
|
23 |
+
"11": "Social",
|
24 |
+
"12": "Housing",
|
25 |
+
"13": "Domestic",
|
26 |
+
"14": "Defense",
|
27 |
+
"15": "Technology",
|
28 |
+
"16": "Foreign",
|
29 |
+
"17": "International",
|
30 |
+
"18": "Government",
|
31 |
+
"19": "Public",
|
32 |
+
"20": "Culture"
|
33 |
+
},
|
34 |
+
"initializer_range": 0.02,
|
35 |
+
"intermediate_size": 3072,
|
36 |
+
"label2id": {
|
37 |
+
"Agriculture": 3,
|
38 |
+
"Civil": 1,
|
39 |
+
"Culture": 20,
|
40 |
+
"Defense": 14,
|
41 |
+
"Domestic": 13,
|
42 |
+
"Education": 5,
|
43 |
+
"Energy": 7,
|
44 |
+
"Environment": 6,
|
45 |
+
"Foreign": 16,
|
46 |
+
"Government": 18,
|
47 |
+
"Health": 2,
|
48 |
+
"Housing": 12,
|
49 |
+
"Immigration": 8,
|
50 |
+
"International": 17,
|
51 |
+
"Labor": 4,
|
52 |
+
"Law": 10,
|
53 |
+
"Macroeconomics": 0,
|
54 |
+
"Public": 19,
|
55 |
+
"Social": 11,
|
56 |
+
"Technology": 15,
|
57 |
+
"Transportation": 9
|
58 |
+
},
|
59 |
+
"layer_norm_eps": 1e-12,
|
60 |
+
"max_position_embeddings": 512,
|
61 |
+
"model_type": "bert",
|
62 |
+
"num_attention_heads": 12,
|
63 |
+
"num_hidden_layers": 12,
|
64 |
+
"pad_token_id": 0,
|
65 |
+
"position_embedding_type": "absolute",
|
66 |
+
"problem_type": "single_label_classification",
|
67 |
+
"torch_dtype": "float32",
|
68 |
+
"transformers_version": "4.32.1",
|
69 |
+
"type_vocab_size": 2,
|
70 |
+
"use_cache": true,
|
71 |
+
"vocab_size": 30000
|
72 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a2d6b48e608c7921c77c465a219f90e7b48adafede3d42807448717c6a427fd
|
3 |
+
size 436520501
|
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 |
+
"clean_up_tokenization_spaces": true,
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 128,
|
7 |
+
"model_max_length": 512,
|
8 |
+
"pad_token": "[PAD]",
|
9 |
+
"sep_token": "[SEP]",
|
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 sha256:8ea4998a7b822a726d48af9fdca81cee72313f27ad531c63b428b61055964b1d
|
3 |
+
size 4091
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|