AMA80 ThomNP commited on
Commit
caa017e
1 Parent(s): e90c1b9

sss-ner-dp-1 (#3)

Browse files

- sss-ner-dp-1 (eda575780e5735f82e776c2a32b553aa0dd957e1)


Co-authored-by: Thomas Pedersen <ThomNP@users.noreply.huggingface.co>

.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model_weights.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/srv/alvenir/modelling/mlm/models/SAS/best_model",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-PERSON",
16
+ "2": "I-PERSON",
17
+ "3": "B-LOKATION",
18
+ "4": "I-LOKATION",
19
+ "5": "B-ADRESSE",
20
+ "6": "I-ADRESSE",
21
+ "7": "B-HELBRED",
22
+ "8": "I-HELBRED",
23
+ "9": "B-ORGANISATION",
24
+ "10": "I-ORGANISATION",
25
+ "11": "B-KOMMUNE",
26
+ "12": "I-KOMMUNE",
27
+ "13": "B-TELEFONNUMMER",
28
+ "14": "I-TELEFONNUMMER"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 3072,
32
+ "label2id": {
33
+ "B-ADRESSE": 5,
34
+ "B-HELBRED": 7,
35
+ "B-KOMMUNE": 11,
36
+ "B-LOKATION": 3,
37
+ "B-ORGANISATION": 9,
38
+ "B-PERSON": 1,
39
+ "B-TELEFONNUMMER": 13,
40
+ "I-ADRESSE": 6,
41
+ "I-HELBRED": 8,
42
+ "I-KOMMUNE": 12,
43
+ "I-LOKATION": 4,
44
+ "I-ORGANISATION": 10,
45
+ "I-PERSON": 2,
46
+ "I-TELEFONNUMMER": 14,
47
+ "O": 0
48
+ },
49
+ "layer_norm_eps": 1e-12,
50
+ "max_position_embeddings": 512,
51
+ "model_type": "bert",
52
+ "num_attention_heads": 12,
53
+ "num_hidden_layers": 12,
54
+ "pad_token_id": 0,
55
+ "pooler_fc_size": 768,
56
+ "pooler_num_attention_heads": 12,
57
+ "pooler_num_fc_layers": 3,
58
+ "pooler_size_per_head": 128,
59
+ "pooler_type": "first_token_transform",
60
+ "position_embedding_type": "absolute",
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.19.2",
63
+ "type_vocab_size": 2,
64
+ "use_cache": true,
65
+ "vocab_size": 119547
66
+ }
eval_scores.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ {"epoch": 13, "step": 40000, "loss": 0.1288171410717926, "accuracy": 0.9710784923497947, "f_1": 0.6568184738460724, "f_1_none": [{"O": 0.9864759339527619}, {"B-PERSON": 0.9363662539591132}, {"I-PERSON": 0.9103291713961407}, {"B-LOKATION": 0.6023391812865497}, {"I-LOKATION": 0.06451612903225806}, {"B-ADRESSE": 0.83}, {"I-ADRESSE": 0.867605633802817}, {"B-HELBRED": 0.3660714285714286}, {"I-HELBRED": 0.0}, {"B-ORGANISATION": 0.5065666041275798}, {"I-ORGANISATION": 0.615916955017301}, {"B-KOMMUNE": 0.837037037037037}, {"I-KOMMUNE": 0.8984375}, {"B-TELEFONNUMMER": 0.4910179640718563}, {"I-TELEFONNUMMER": 0.9395973154362416}]}
model_weights.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b311dce7d9e43fca91100eb91fb81f15eb819c9e050aff47186602bdc432b2
3
+ size 709183597
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa50443cf3a4f866fae3ac9e3eee0577cab9ae67a9d71644aa1dfe5e750d941e
3
+ size 709169709
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/srv/alvenir/modelling/mlm/models/SAS/best_model", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f325c991d1845b7b4d6011605f176d4253f9eb44104916f57b842c3414036638
3
+ size 3323
vocab.txt ADDED
The diff for this file is too large to render. See raw diff