Training in progress, epoch 1
Browse files- config.json +62 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Feb25_23-52-22_13f323e323f5/events.out.tfevents.1708905143.13f323e323f5.34.0 +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +60 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "SKNahin/NER_Deberta5",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "O",
|
12 |
+
"1": "B-USERNAME",
|
13 |
+
"2": "B-EMAIL",
|
14 |
+
"3": "B-NAME_STUDENT",
|
15 |
+
"4": "I-NAME_STUDENT",
|
16 |
+
"5": "B-ID_NUM",
|
17 |
+
"6": "I-ID_NUM",
|
18 |
+
"7": "B-PHONE_NUM",
|
19 |
+
"8": "I-PHONE_NUM",
|
20 |
+
"9": "B-STREET_ADDRESS",
|
21 |
+
"10": "I-STREET_ADDRESS",
|
22 |
+
"11": "B-URL_PERSONAL",
|
23 |
+
"12": "I-URL_PERSONAL"
|
24 |
+
},
|
25 |
+
"initializer_range": 0.02,
|
26 |
+
"intermediate_size": 3072,
|
27 |
+
"label2id": {
|
28 |
+
"B-EMAIL": 2,
|
29 |
+
"B-ID_NUM": 5,
|
30 |
+
"B-NAME_STUDENT": 3,
|
31 |
+
"B-PHONE_NUM": 7,
|
32 |
+
"B-STREET_ADDRESS": 9,
|
33 |
+
"B-URL_PERSONAL": 11,
|
34 |
+
"B-USERNAME": 1,
|
35 |
+
"I-ID_NUM": 6,
|
36 |
+
"I-NAME_STUDENT": 4,
|
37 |
+
"I-PHONE_NUM": 8,
|
38 |
+
"I-STREET_ADDRESS": 10,
|
39 |
+
"I-URL_PERSONAL": 12,
|
40 |
+
"O": 0
|
41 |
+
},
|
42 |
+
"layer_norm_eps": 1e-07,
|
43 |
+
"max_position_embeddings": 512,
|
44 |
+
"max_relative_positions": -1,
|
45 |
+
"model_type": "deberta",
|
46 |
+
"num_attention_heads": 12,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"pad_token_id": 0,
|
49 |
+
"pooler_dropout": 0,
|
50 |
+
"pooler_hidden_act": "gelu",
|
51 |
+
"pooler_hidden_size": 768,
|
52 |
+
"pos_att_type": [
|
53 |
+
"c2p",
|
54 |
+
"p2c"
|
55 |
+
],
|
56 |
+
"position_biased_input": false,
|
57 |
+
"relative_attention": true,
|
58 |
+
"torch_dtype": "float32",
|
59 |
+
"transformers_version": "4.37.0",
|
60 |
+
"type_vocab_size": 0,
|
61 |
+
"vocab_size": 50265
|
62 |
+
}
|
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:eb87a89e5a453bc1b4b8a41bbb807829c4399fbc8620ee1202058c81eb3a9e48
|
3 |
+
size 554470860
|
runs/Feb25_23-52-22_13f323e323f5/events.out.tfevents.1708905143.13f323e323f5.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:605f221c8f3ded458c1b517f1fbf91ad49600583fd706d42ea6a5c5cb176f13a
|
3 |
+
size 7182
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "[SEP]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "[PAD]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "[UNK]",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": true,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "[PAD]",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "[CLS]",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "[SEP]",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "[UNK]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"50264": {
|
38 |
+
"content": "[MASK]",
|
39 |
+
"lstrip": true,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"additional_special_tokens": [],
|
47 |
+
"bos_token": "[CLS]",
|
48 |
+
"clean_up_tokenization_spaces": true,
|
49 |
+
"cls_token": "[CLS]",
|
50 |
+
"do_lower_case": false,
|
51 |
+
"eos_token": "[SEP]",
|
52 |
+
"errors": "replace",
|
53 |
+
"mask_token": "[MASK]",
|
54 |
+
"model_max_length": 512,
|
55 |
+
"pad_token": "[PAD]",
|
56 |
+
"sep_token": "[SEP]",
|
57 |
+
"tokenizer_class": "DebertaTokenizer",
|
58 |
+
"unk_token": "[UNK]",
|
59 |
+
"vocab_type": "gpt2"
|
60 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3b47ed2dad86686ce98b748ad67a4a7700c542748e3a11a7ae163192ad6a925
|
3 |
+
size 4728
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|