Hugging Face's logo

msperka
/
HeRo-finetuned-ner

Token Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
msperka commited on
Commit
2046c10
•
1 Parent(s): 038ffe9

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. config.json +107 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/Dec25_11-24-45_soc-5CG223442L/events.out.tfevents.1703496286.soc-5CG223442L +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +58 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HeNLP/HeRo",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "device_map": "dik",
10
+ "eos_token_id": 2,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "S-ANG",
16
+ "1": "B-ANG",
17
+ "2": "I-ANG",
18
+ "3": "E-ANG",
19
+ "4": "S-DUC",
20
+ "5": "B-DUC",
21
+ "6": "I-DUC",
22
+ "7": "E-DUC",
23
+ "8": "B-EVE",
24
+ "9": "E-EVE",
25
+ "10": "S-EVE",
26
+ "11": "I-EVE",
27
+ "12": "S-FAC",
28
+ "13": "B-FAC",
29
+ "14": "E-FAC",
30
+ "15": "I-FAC",
31
+ "16": "S-GPE",
32
+ "17": "B-GPE",
33
+ "18": "E-GPE",
34
+ "19": "I-GPE",
35
+ "20": "S-LOC",
36
+ "21": "B-LOC",
37
+ "22": "E-LOC",
38
+ "23": "I-LOC",
39
+ "24": "O",
40
+ "25": "S-ORG",
41
+ "26": "B-ORG",
42
+ "27": "E-ORG",
43
+ "28": "I-ORG",
44
+ "29": "B-PER",
45
+ "30": "I-PER",
46
+ "31": "E-PER",
47
+ "32": "S-PER",
48
+ "33": "B-WOA",
49
+ "34": "E-WOA",
50
+ "35": "I-WOA",
51
+ "36": "S-WOA"
52
+ },
53
+ "initializer_range": 0.02,
54
+ "intermediate_size": 3072,
55
+ "label2id": {
56
+ "B-ANG": 1,
57
+ "B-DUC": 5,
58
+ "B-EVE": 8,
59
+ "B-FAC": 13,
60
+ "B-GPE": 17,
61
+ "B-LOC": 21,
62
+ "B-ORG": 26,
63
+ "B-PER": 29,
64
+ "B-WOA": 33,
65
+ "E-ANG": 3,
66
+ "E-DUC": 7,
67
+ "E-EVE": 9,
68
+ "E-FAC": 14,
69
+ "E-GPE": 18,
70
+ "E-LOC": 22,
71
+ "E-ORG": 27,
72
+ "E-PER": 31,
73
+ "E-WOA": 34,
74
+ "I-ANG": 2,
75
+ "I-DUC": 6,
76
+ "I-EVE": 11,
77
+ "I-FAC": 15,
78
+ "I-GPE": 19,
79
+ "I-LOC": 23,
80
+ "I-ORG": 28,
81
+ "I-PER": 30,
82
+ "I-WOA": 35,
83
+ "O": 24,
84
+ "S-ANG": 0,
85
+ "S-DUC": 4,
86
+ "S-EVE": 10,
87
+ "S-FAC": 12,
88
+ "S-GPE": 16,
89
+ "S-LOC": 20,
90
+ "S-ORG": 25,
91
+ "S-PER": 32,
92
+ "S-WOA": 36
93
+ },
94
+ "layer_norm_eps": 1e-05,
95
+ "max_position_embeddings": 514,
96
+ "model_type": "roberta",
97
+ "num_attention_heads": 12,
98
+ "num_hidden_layers": 12,
99
+ "offload_folder": "os.path.join(path.parent.parent.absolute(), 'results/RoBERTa/model_and_tokenizer')",
100
+ "pad_token_id": 1,
101
+ "position_embedding_type": "absolute",
102
+ "torch_dtype": "float32",
103
+ "transformers_version": "4.35.2",
104
+ "type_vocab_size": 1,
105
+ "use_cache": true,
106
+ "vocab_size": 50265
107
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62db64ee07b6fedf25e82f680f038a5e5840015270274a2ae46f77b9945cd29b
3
+ size 496357908
runs/Dec25_11-24-45_soc-5CG223442L/events.out.tfevents.1703496286.soc-5CG223442L ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8d9ff7c1d15b5fad51ff7c782401c4556d41fc2ed06c6393f8e20cb8b0dc0b1
3
+ size 6323
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
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
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "max_len": 512,
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e77a41f52d773a1d8d379f266b454886710f631c04e10af0fa2ed85a7c7dee4
3
+ size 4155
vocab.json ADDED
The diff for this file is too large to render. See raw diff