Hugging Face's logo

nxaliao
/
roberta-lg-cased-ms-ner-v3-test

Token Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
nxaliao commited on
Commit
7983315
•
1 Parent(s): 19bff16

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. config.json +97 -0
  2. merges.txt +0 -0
  3. model.safetensors +3 -0
  4. runs/May15_20-24-55_standardnc24adsa100v4al/events.out.tfevents.1715804715.standardnc24adsa100v4al.4736.0 +3 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +57 -0
  8. training_args.bin +3 -0
  9. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-BOSS",
16
+ "2": "I-BOSS",
17
+ "3": "B-MOB",
18
+ "4": "I-MOB",
19
+ "5": "B-MAP",
20
+ "6": "I-MAP",
21
+ "7": "B-JOB",
22
+ "8": "I-JOB",
23
+ "9": "B-INGAME_ITEM",
24
+ "10": "I-INGAME_ITEM",
25
+ "11": "B-QUEST",
26
+ "12": "I-QUEST",
27
+ "13": "B-CHANNEL",
28
+ "14": "I-CHANNEL",
29
+ "15": "B-SALE_ITEM",
30
+ "16": "I-SALE_ITEM",
31
+ "17": "B-EVENT",
32
+ "18": "I-EVENT",
33
+ "19": "B-MECHANIC",
34
+ "20": "I-MECHANIC",
35
+ "21": "B-FEATURE",
36
+ "22": "I-FEATURE",
37
+ "23": "B-NPC",
38
+ "24": "I-NPC",
39
+ "25": "B-GAME",
40
+ "26": "I-GAME",
41
+ "27": "B-SKILL",
42
+ "28": "I-SKILL",
43
+ "29": "B-UPDATE",
44
+ "30": "I-UPDATE",
45
+ "31": "B-MISC",
46
+ "32": "I-MISC"
47
+ },
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": 4096,
50
+ "label2id": {
51
+ "B-BOSS": 1,
52
+ "B-CHANNEL": 13,
53
+ "B-EVENT": 17,
54
+ "B-FEATURE": 21,
55
+ "B-GAME": 25,
56
+ "B-INGAME_ITEM": 9,
57
+ "B-JOB": 7,
58
+ "B-MAP": 5,
59
+ "B-MECHANIC": 19,
60
+ "B-MISC": 31,
61
+ "B-MOB": 3,
62
+ "B-NPC": 23,
63
+ "B-QUEST": 11,
64
+ "B-SALE_ITEM": 15,
65
+ "B-SKILL": 27,
66
+ "B-UPDATE": 29,
67
+ "I-BOSS": 2,
68
+ "I-CHANNEL": 14,
69
+ "I-EVENT": 18,
70
+ "I-FEATURE": 22,
71
+ "I-GAME": 26,
72
+ "I-INGAME_ITEM": 10,
73
+ "I-JOB": 8,
74
+ "I-MAP": 6,
75
+ "I-MECHANIC": 20,
76
+ "I-MISC": 32,
77
+ "I-MOB": 4,
78
+ "I-NPC": 24,
79
+ "I-QUEST": 12,
80
+ "I-SALE_ITEM": 16,
81
+ "I-SKILL": 28,
82
+ "I-UPDATE": 30,
83
+ "O": 0
84
+ },
85
+ "layer_norm_eps": 1e-05,
86
+ "max_position_embeddings": 514,
87
+ "model_type": "roberta",
88
+ "num_attention_heads": 16,
89
+ "num_hidden_layers": 24,
90
+ "pad_token_id": 1,
91
+ "position_embedding_type": "absolute",
92
+ "torch_dtype": "float32",
93
+ "transformers_version": "4.39.3",
94
+ "type_vocab_size": 1,
95
+ "use_cache": true,
96
+ "vocab_size": 50265
97
+ }
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 sha256:9f5e3a0fde9f75605ae241eeab12cb4d6467d609527279cf224b26e8d57beae1
3
+ size 1417423900
runs/May15_20-24-55_standardnc24adsa100v4al/events.out.tfevents.1715804715.standardnc24adsa100v4al.4736.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:065a551f7bf3aee6721c2f300462e2dd31fa551da34e51bd23437d47ae8261a7
3
+ size 7919
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 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
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
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7285ffbde8dab74f3fbdcaf0c70b5cd58aef1a9365a603b7686ba732a02376f8
3
+ size 4527
vocab.json ADDED
The diff for this file is too large to render. See raw diff