albrechtje
commited on
Commit
•
2068b5f
1
Parent(s):
2d3837e
gecco-bert-base-german-uncased
Browse files- README.md +77 -0
- config.json +110 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: dbmdz/bert-base-german-uncased
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
model-index:
|
10 |
+
- name: gecco-bert-base-german-uncased
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# gecco-bert-base-german-uncased
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [dbmdz/bert-base-german-uncased](https://huggingface.co/dbmdz/bert-base-german-uncased) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.2341
|
22 |
+
- Accuracy: 0.6968
|
23 |
+
- F1: 0.4493
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2e-05
|
43 |
+
- train_batch_size: 64
|
44 |
+
- eval_batch_size: 64
|
45 |
+
- seed: 42
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- num_epochs: 16
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
54 |
+
| 3.4151 | 1.0 | 20 | 3.0885 | 0.2935 | 0.0760 |
|
55 |
+
| 2.9316 | 2.0 | 40 | 2.7003 | 0.3484 | 0.1035 |
|
56 |
+
| 2.5556 | 3.0 | 60 | 2.3463 | 0.5032 | 0.2350 |
|
57 |
+
| 2.19 | 4.0 | 80 | 2.0714 | 0.5613 | 0.2841 |
|
58 |
+
| 1.904 | 5.0 | 100 | 1.8381 | 0.6 | 0.3085 |
|
59 |
+
| 1.6285 | 6.0 | 120 | 1.6712 | 0.6323 | 0.3633 |
|
60 |
+
| 1.4482 | 7.0 | 140 | 1.5518 | 0.6581 | 0.3774 |
|
61 |
+
| 1.2807 | 8.0 | 160 | 1.4796 | 0.6677 | 0.3880 |
|
62 |
+
| 1.1126 | 9.0 | 180 | 1.4207 | 0.6613 | 0.3787 |
|
63 |
+
| 1.0747 | 10.0 | 200 | 1.3461 | 0.6774 | 0.3885 |
|
64 |
+
| 0.9068 | 11.0 | 220 | 1.3097 | 0.6871 | 0.4132 |
|
65 |
+
| 0.8498 | 12.0 | 240 | 1.2893 | 0.6903 | 0.4235 |
|
66 |
+
| 0.8343 | 13.0 | 260 | 1.2549 | 0.7 | 0.4332 |
|
67 |
+
| 0.7375 | 14.0 | 280 | 1.2426 | 0.7 | 0.4497 |
|
68 |
+
| 0.7274 | 15.0 | 300 | 1.2385 | 0.7 | 0.4512 |
|
69 |
+
| 0.6916 | 16.0 | 320 | 1.2341 | 0.6968 | 0.4493 |
|
70 |
+
|
71 |
+
|
72 |
+
### Framework versions
|
73 |
+
|
74 |
+
- Transformers 4.35.1
|
75 |
+
- Pytorch 1.10.1+cu111
|
76 |
+
- Datasets 2.14.7
|
77 |
+
- Tokenizers 0.14.1
|
config.json
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbmdz/bert-base-german-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
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": "B-FA-*-*-G-*|Gespr\u00e4chser\u00f6ffnung",
|
13 |
+
"1": "B-FA-*-*-Mod-*|Moderation",
|
14 |
+
"2": "B-WF-AK-RS-FPD-*|Nachfrage nach pers\u00f6nlichen Daten",
|
15 |
+
"3": "B-WF-AK-RS-FBL-*|Nachfrage nach bisherigen L\u00f6sungsversuchen",
|
16 |
+
"4": "B-WF-AK-RS-ERx-*|Einfache Reflexion",
|
17 |
+
"5": "B-WF-AK-RS-FLL-SB|Nachfrage zur Lebenslage|soziale Beziehungen",
|
18 |
+
"6": "B-WF-AK-RS-FLL-BS|Nachfrage zur Lebenslage|berufliche Situation",
|
19 |
+
"7": "B-WF-AK-RS-FLL-EW|Nachfrage zur Lebenslage|Erwerbst\u00e4tigkeit/wirtschaftliche Situation",
|
20 |
+
"8": "B-WF-AK-RS-FLL-G|Nachfrage zur Lebenslage|Gesundheit (psychisch und physisch)",
|
21 |
+
"9": "B-WF-AK-RS-FLL-F|Nachfrage zur Lebenslage|Freizeit",
|
22 |
+
"10": "B-WF-AK-RS-FA-*|Nachfrage nach Anliegen",
|
23 |
+
"11": "B-WF-AK-RS-FPP-*|punktuelle, pr\u00e4zise Nachfrage",
|
24 |
+
"12": "B-WF-AK-RS-FVE-*|Nachfrage nach Ver\u00e4nderung und Entwicklung",
|
25 |
+
"13": "B-WF-AK-RE-FKR-*|Komplexe Reflexion",
|
26 |
+
"14": "B-WF-AK-RE-FEL-*|Nachfrage nach emotionaler Lage",
|
27 |
+
"15": "B-WF-ABZ-*-FZW-*|Nachfrage nach Zielsetzung/W\u00fcnschen",
|
28 |
+
"16": "B-WF-ABZ-*-IDZ-*|Definition der Zielsetzung der Beratung",
|
29 |
+
"17": "B-WF-Mot-*-FVW-*|Hervorrufen von Aussagen zum Ver\u00e4nderungswunsch (MI)",
|
30 |
+
"18": "B-WF-Mot-*-IAV-*|Artikulation der wahrgenommen F\u00e4higkeit zur Ver\u00e4nderung beim Klienten (MI)",
|
31 |
+
"19": "B-WF-Mot-*-IDW-*|Dank und Wertsch\u00e4tzung an Klient*in",
|
32 |
+
"20": "B-WF-Mot-*-IEM-*|Ermutigung, Motivation des*der Klient*in",
|
33 |
+
"21": "B-WF-RA-*-FU-*|Frage nach m\u00f6glichen Unterst\u00fctzungsressourcen",
|
34 |
+
"22": "B-WF-RA-*-FP-*|Nachfrage nach Problemstellung",
|
35 |
+
"23": "B-WF-RA-*-ARP-*|Anregung zur Ressourcenaktivierung auf professioneller Ebene",
|
36 |
+
"24": "B-WF-RA-*-N-ARFa|Netzwerkarbeit|Anregung zur Ressourcenaktivierung auf Familienebene",
|
37 |
+
"25": "B-WF-RA-*-N-ARFr|Netzwerkarbeit|Anregung zur Ressourcenaktivierung auf Freundesebene",
|
38 |
+
"26": "B-WF-HP-*-IFSE-*|Fachliche bzw. sachliche Erkl\u00e4rungen",
|
39 |
+
"27": "B-WF-HP-*-IFHE-*|Fachliche, f\u00f6rmliche, institutionelle Handlungsempfehlung",
|
40 |
+
"28": "B-WF-HP-*-IZ-*|Zukunftsprognose",
|
41 |
+
"29": "B-WF-HP-*-IW-*|Warnung",
|
42 |
+
"30": "B-WF-HP-*-IB-*|Beruhigung",
|
43 |
+
"31": "B-WF-HP-*-PS-IR|Pers\u00f6nliche Sichtweise|Ratschlag",
|
44 |
+
"32": "B-WF-HP-*-PS-IBD|Pers\u00f6nliche Sichtweise|Bewertung, Deutung",
|
45 |
+
"33": "B-WF-HP-*-PS-IW|Pers\u00f6nliche Sichtweise|Wunsch",
|
46 |
+
"34": "B-FZ-*-*-V-*|Verabschiedung",
|
47 |
+
"35": "B-FZ-*-*-APR-*|Angebot zur Nutzung der professionellen Ressourcen des*der Berater*in",
|
48 |
+
"36": "B-A-*-*-A-*",
|
49 |
+
"37": "B-A-*-*-UB-*|Unpassende Bemerkung",
|
50 |
+
"38": "B-A-*-*-PI-*|Pers\u00f6nliche Informationen (Steckbrief)",
|
51 |
+
"39": "B-A-*-*-ST-*|Small Talk"
|
52 |
+
},
|
53 |
+
"initializer_range": 0.02,
|
54 |
+
"intermediate_size": 3072,
|
55 |
+
"label2id": {
|
56 |
+
"B-A-*-*-A-*": 36,
|
57 |
+
"B-A-*-*-PI-*|Pers\u00f6nliche Informationen (Steckbrief)": 38,
|
58 |
+
"B-A-*-*-ST-*|Small Talk": 39,
|
59 |
+
"B-A-*-*-UB-*|Unpassende Bemerkung": 37,
|
60 |
+
"B-FA-*-*-G-*|Gespr\u00e4chser\u00f6ffnung": 0,
|
61 |
+
"B-FA-*-*-Mod-*|Moderation": 1,
|
62 |
+
"B-FZ-*-*-APR-*|Angebot zur Nutzung der professionellen Ressourcen des*der Berater*in": 35,
|
63 |
+
"B-FZ-*-*-V-*|Verabschiedung": 34,
|
64 |
+
"B-WF-ABZ-*-FZW-*|Nachfrage nach Zielsetzung/W\u00fcnschen": 15,
|
65 |
+
"B-WF-ABZ-*-IDZ-*|Definition der Zielsetzung der Beratung": 16,
|
66 |
+
"B-WF-AK-RE-FEL-*|Nachfrage nach emotionaler Lage": 14,
|
67 |
+
"B-WF-AK-RE-FKR-*|Komplexe Reflexion": 13,
|
68 |
+
"B-WF-AK-RS-ERx-*|Einfache Reflexion": 4,
|
69 |
+
"B-WF-AK-RS-FA-*|Nachfrage nach Anliegen": 10,
|
70 |
+
"B-WF-AK-RS-FBL-*|Nachfrage nach bisherigen L\u00f6sungsversuchen": 3,
|
71 |
+
"B-WF-AK-RS-FLL-BS|Nachfrage zur Lebenslage|berufliche Situation": 6,
|
72 |
+
"B-WF-AK-RS-FLL-EW|Nachfrage zur Lebenslage|Erwerbst\u00e4tigkeit/wirtschaftliche Situation": 7,
|
73 |
+
"B-WF-AK-RS-FLL-F|Nachfrage zur Lebenslage|Freizeit": 9,
|
74 |
+
"B-WF-AK-RS-FLL-G|Nachfrage zur Lebenslage|Gesundheit (psychisch und physisch)": 8,
|
75 |
+
"B-WF-AK-RS-FLL-SB|Nachfrage zur Lebenslage|soziale Beziehungen": 5,
|
76 |
+
"B-WF-AK-RS-FPD-*|Nachfrage nach pers\u00f6nlichen Daten": 2,
|
77 |
+
"B-WF-AK-RS-FPP-*|punktuelle, pr\u00e4zise Nachfrage": 11,
|
78 |
+
"B-WF-AK-RS-FVE-*|Nachfrage nach Ver\u00e4nderung und Entwicklung": 12,
|
79 |
+
"B-WF-HP-*-IB-*|Beruhigung": 30,
|
80 |
+
"B-WF-HP-*-IFHE-*|Fachliche, f\u00f6rmliche, institutionelle Handlungsempfehlung": 27,
|
81 |
+
"B-WF-HP-*-IFSE-*|Fachliche bzw. sachliche Erkl\u00e4rungen": 26,
|
82 |
+
"B-WF-HP-*-IW-*|Warnung": 29,
|
83 |
+
"B-WF-HP-*-IZ-*|Zukunftsprognose": 28,
|
84 |
+
"B-WF-HP-*-PS-IBD|Pers\u00f6nliche Sichtweise|Bewertung, Deutung": 32,
|
85 |
+
"B-WF-HP-*-PS-IR|Pers\u00f6nliche Sichtweise|Ratschlag": 31,
|
86 |
+
"B-WF-HP-*-PS-IW|Pers\u00f6nliche Sichtweise|Wunsch": 33,
|
87 |
+
"B-WF-Mot-*-FVW-*|Hervorrufen von Aussagen zum Ver\u00e4nderungswunsch (MI)": 17,
|
88 |
+
"B-WF-Mot-*-IAV-*|Artikulation der wahrgenommen F\u00e4higkeit zur Ver\u00e4nderung beim Klienten (MI)": 18,
|
89 |
+
"B-WF-Mot-*-IDW-*|Dank und Wertsch\u00e4tzung an Klient*in": 19,
|
90 |
+
"B-WF-Mot-*-IEM-*|Ermutigung, Motivation des*der Klient*in": 20,
|
91 |
+
"B-WF-RA-*-ARP-*|Anregung zur Ressourcenaktivierung auf professioneller Ebene": 23,
|
92 |
+
"B-WF-RA-*-FP-*|Nachfrage nach Problemstellung": 22,
|
93 |
+
"B-WF-RA-*-FU-*|Frage nach m\u00f6glichen Unterst\u00fctzungsressourcen": 21,
|
94 |
+
"B-WF-RA-*-N-ARFa|Netzwerkarbeit|Anregung zur Ressourcenaktivierung auf Familienebene": 24,
|
95 |
+
"B-WF-RA-*-N-ARFr|Netzwerkarbeit|Anregung zur Ressourcenaktivierung auf Freundesebene": 25
|
96 |
+
},
|
97 |
+
"layer_norm_eps": 1e-12,
|
98 |
+
"max_position_embeddings": 512,
|
99 |
+
"model_type": "bert",
|
100 |
+
"num_attention_heads": 12,
|
101 |
+
"num_hidden_layers": 12,
|
102 |
+
"pad_token_id": 0,
|
103 |
+
"position_embedding_type": "absolute",
|
104 |
+
"problem_type": "single_label_classification",
|
105 |
+
"torch_dtype": "float32",
|
106 |
+
"transformers_version": "4.35.1",
|
107 |
+
"type_vocab_size": 2,
|
108 |
+
"use_cache": true,
|
109 |
+
"vocab_size": 31102
|
110 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:161ad91d72f096004c1cf09df2cc79692e49e10b4bfce7aad83a7a77bda648d6
|
3 |
+
size 439857296
|
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 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"101": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"102": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"103": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"104": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"max_len": 512,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": null,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f1ff8f6750bce88ed064af94d2aeb59b3a00fd36fcc78362f03ef89c89529a8
|
3 |
+
size 4143
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|