Training in progress, epoch 1
Browse files- added_tokens.json +7 -0
- config.json +96 -0
- pytorch_model.bin +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
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[CLS]": 2,
|
3 |
+
"[MASK]": 4,
|
4 |
+
"[PAD]": 0,
|
5 |
+
"[SEP]": 3,
|
6 |
+
"[UNK]": 1
|
7 |
+
}
|
config.json
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Leo97/KoELECTRA-small-v3-modu-ner",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 128,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 256,
|
12 |
+
"id2label": {
|
13 |
+
"0": "O",
|
14 |
+
"1": "B-PS",
|
15 |
+
"2": "I-PS",
|
16 |
+
"3": "B-FD",
|
17 |
+
"4": "I-FD",
|
18 |
+
"5": "B-TR",
|
19 |
+
"6": "I-TR",
|
20 |
+
"7": "B-AF",
|
21 |
+
"8": "I-AF",
|
22 |
+
"9": "B-OG",
|
23 |
+
"10": "I-OG",
|
24 |
+
"11": "B-LC",
|
25 |
+
"12": "I-LC",
|
26 |
+
"13": "B-CV",
|
27 |
+
"14": "I-CV",
|
28 |
+
"15": "B-DT",
|
29 |
+
"16": "I-DT",
|
30 |
+
"17": "B-TI",
|
31 |
+
"18": "I-TI",
|
32 |
+
"19": "B-QT",
|
33 |
+
"20": "I-QT",
|
34 |
+
"21": "B-EV",
|
35 |
+
"22": "I-EV",
|
36 |
+
"23": "B-AM",
|
37 |
+
"24": "I-AM",
|
38 |
+
"25": "B-PT",
|
39 |
+
"26": "I-PT",
|
40 |
+
"27": "B-MT",
|
41 |
+
"28": "I-MT",
|
42 |
+
"29": "B-TM",
|
43 |
+
"30": "I-TM"
|
44 |
+
},
|
45 |
+
"initializer_range": 0.02,
|
46 |
+
"intermediate_size": 1024,
|
47 |
+
"label2id": {
|
48 |
+
"B-AF": 7,
|
49 |
+
"B-AM": 23,
|
50 |
+
"B-CV": 13,
|
51 |
+
"B-DT": 15,
|
52 |
+
"B-EV": 21,
|
53 |
+
"B-FD": 3,
|
54 |
+
"B-LC": 11,
|
55 |
+
"B-MT": 27,
|
56 |
+
"B-OG": 9,
|
57 |
+
"B-PS": 1,
|
58 |
+
"B-PT": 25,
|
59 |
+
"B-QT": 19,
|
60 |
+
"B-TI": 17,
|
61 |
+
"B-TM": 29,
|
62 |
+
"B-TR": 5,
|
63 |
+
"I-AF": 8,
|
64 |
+
"I-AM": 24,
|
65 |
+
"I-CV": 14,
|
66 |
+
"I-DT": 16,
|
67 |
+
"I-EV": 22,
|
68 |
+
"I-FD": 4,
|
69 |
+
"I-LC": 12,
|
70 |
+
"I-MT": 28,
|
71 |
+
"I-OG": 10,
|
72 |
+
"I-PS": 2,
|
73 |
+
"I-PT": 26,
|
74 |
+
"I-QT": 20,
|
75 |
+
"I-TI": 18,
|
76 |
+
"I-TM": 30,
|
77 |
+
"I-TR": 6,
|
78 |
+
"O": 0
|
79 |
+
},
|
80 |
+
"layer_norm_eps": 1e-12,
|
81 |
+
"max_position_embeddings": 512,
|
82 |
+
"model_type": "electra",
|
83 |
+
"num_attention_heads": 4,
|
84 |
+
"num_hidden_layers": 12,
|
85 |
+
"pad_token_id": 0,
|
86 |
+
"position_embedding_type": "absolute",
|
87 |
+
"summary_activation": "gelu",
|
88 |
+
"summary_last_dropout": 0.1,
|
89 |
+
"summary_type": "first",
|
90 |
+
"summary_use_proj": true,
|
91 |
+
"torch_dtype": "float32",
|
92 |
+
"transformers_version": "4.34.0",
|
93 |
+
"type_vocab_size": 2,
|
94 |
+
"use_cache": true,
|
95 |
+
"vocab_size": 35000
|
96 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eccba992456f02d8f675e2f899af7e7630b8c0f24ef790c361f70bf9a9428e96
|
3 |
+
size 56322801
|
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 |
+
"additional_special_tokens": [],
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_basic_tokenize": true,
|
48 |
+
"do_lower_case": false,
|
49 |
+
"mask_token": "[MASK]",
|
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": "ElectraTokenizer",
|
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:c74d671973d5e443cd6e4b2e541bfbf90da8a5dedd3e90a736ec7a52529683d5
|
3 |
+
size 4091
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|