Hugging Face's logo

msperka
/
aleph_bert-finetuned-ner

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
msperka commited on
Commit
075b65f
·
1 Parent(s): 36c4eac

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +104 -0
  2. model.safetensors +3 -0
  3. runs/Dec14_12-50-36_soc-5CG223442L/events.out.tfevents.1702551039.soc-5CG223442L +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +58 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "onlplab/alephbert-base",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "S-ANG",
14
+ "1": "B-ANG",
15
+ "2": "I-ANG",
16
+ "3": "E-ANG",
17
+ "4": "S-DUC",
18
+ "5": "B-DUC",
19
+ "6": "I-DUC",
20
+ "7": "E-DUC",
21
+ "8": "B-EVE",
22
+ "9": "E-EVE",
23
+ "10": "S-EVE",
24
+ "11": "I-EVE",
25
+ "12": "S-FAC",
26
+ "13": "B-FAC",
27
+ "14": "E-FAC",
28
+ "15": "I-FAC",
29
+ "16": "S-GPE",
30
+ "17": "B-GPE",
31
+ "18": "E-GPE",
32
+ "19": "I-GPE",
33
+ "20": "S-LOC",
34
+ "21": "B-LOC",
35
+ "22": "E-LOC",
36
+ "23": "I-LOC",
37
+ "24": "O",
38
+ "25": "S-ORG",
39
+ "26": "B-ORG",
40
+ "27": "E-ORG",
41
+ "28": "I-ORG",
42
+ "29": "B-PER",
43
+ "30": "I-PER",
44
+ "31": "E-PER",
45
+ "32": "S-PER",
46
+ "33": "B-WOA",
47
+ "34": "E-WOA",
48
+ "35": "I-WOA",
49
+ "36": "S-WOA"
50
+ },
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 3072,
53
+ "label2id": {
54
+ "B-ANG": 1,
55
+ "B-DUC": 5,
56
+ "B-EVE": 8,
57
+ "B-FAC": 13,
58
+ "B-GPE": 17,
59
+ "B-LOC": 21,
60
+ "B-ORG": 26,
61
+ "B-PER": 29,
62
+ "B-WOA": 33,
63
+ "E-ANG": 3,
64
+ "E-DUC": 7,
65
+ "E-EVE": 9,
66
+ "E-FAC": 14,
67
+ "E-GPE": 18,
68
+ "E-LOC": 22,
69
+ "E-ORG": 27,
70
+ "E-PER": 31,
71
+ "E-WOA": 34,
72
+ "I-ANG": 2,
73
+ "I-DUC": 6,
74
+ "I-EVE": 11,
75
+ "I-FAC": 15,
76
+ "I-GPE": 19,
77
+ "I-LOC": 23,
78
+ "I-ORG": 28,
79
+ "I-PER": 30,
80
+ "I-WOA": 35,
81
+ "O": 24,
82
+ "S-ANG": 0,
83
+ "S-DUC": 4,
84
+ "S-EVE": 10,
85
+ "S-FAC": 12,
86
+ "S-GPE": 16,
87
+ "S-LOC": 20,
88
+ "S-ORG": 25,
89
+ "S-PER": 32,
90
+ "S-WOA": 36
91
+ },
92
+ "layer_norm_eps": 1e-12,
93
+ "max_position_embeddings": 512,
94
+ "model_type": "bert",
95
+ "num_attention_heads": 12,
96
+ "num_hidden_layers": 12,
97
+ "pad_token_id": 0,
98
+ "position_embedding_type": "absolute",
99
+ "torch_dtype": "float32",
100
+ "transformers_version": "4.35.2",
101
+ "type_vocab_size": 1,
102
+ "use_cache": true,
103
+ "vocab_size": 52000
104
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c3e6ec097194e5e546f9554dbca94125fcb89b1cbd4c0b840044a95409c16a
3
+ size 501681108
runs/Dec14_12-50-36_soc-5CG223442L/events.out.tfevents.1702551039.soc-5CG223442L ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9057ba3d30ebbd871c1bc00a9df3f654a5e8edfe59d2e6d9621bf502ef533e8
3
+ size 5750
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
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:df6848e55b688d5aca3e32babe164be035f31aa29f4c418c4ad8f648dc75ab95
3
+ size 4155
vocab.txt ADDED
The diff for this file is too large to render. See raw diff