1-13-am commited on
Commit
c740b68
1 Parent(s): 99c4b22

Training in progress, step 150

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/kaggle/input/pretrained-1-0-450/Pretrained 1.0 - 450",
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-NAME_STUDENT",
13
+ "2": "B-URL_PERSONAL",
14
+ "3": "B-ID_NUM",
15
+ "4": "B-STREET_ADDRESS",
16
+ "5": "B-PHONE_NUM",
17
+ "6": "B-EMAIL",
18
+ "7": "B-USERNAME",
19
+ "8": "I-NAME_STUDENT",
20
+ "9": "I-URL_PERSONAL",
21
+ "10": "I-ID_NUM",
22
+ "11": "I-STREET_ADDRESS",
23
+ "12": "I-PHONE_NUM"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "B-EMAIL": 6,
29
+ "B-ID_NUM": 3,
30
+ "B-NAME_STUDENT": 1,
31
+ "B-PHONE_NUM": 5,
32
+ "B-STREET_ADDRESS": 4,
33
+ "B-URL_PERSONAL": 2,
34
+ "B-USERNAME": 7,
35
+ "I-ID_NUM": 10,
36
+ "I-NAME_STUDENT": 8,
37
+ "I-PHONE_NUM": 12,
38
+ "I-STREET_ADDRESS": 11,
39
+ "I-URL_PERSONAL": 9,
40
+ "O": 0
41
+ },
42
+ "layer_norm_eps": 1e-07,
43
+ "max_position_embeddings": 512,
44
+ "max_relative_positions": -1,
45
+ "model_type": "deberta-v2",
46
+ "norm_rel_ebd": "layer_norm",
47
+ "num_attention_heads": 12,
48
+ "num_hidden_layers": 12,
49
+ "pad_token_id": 0,
50
+ "pooler_dropout": 0,
51
+ "pooler_hidden_act": "gelu",
52
+ "pooler_hidden_size": 768,
53
+ "pos_att_type": [
54
+ "p2c",
55
+ "c2p"
56
+ ],
57
+ "position_biased_input": false,
58
+ "position_buckets": 256,
59
+ "relative_attention": true,
60
+ "share_att_key": true,
61
+ "torch_dtype": "float32",
62
+ "transformers_version": "4.37.2",
63
+ "type_vocab_size": 0,
64
+ "vocab_size": 128100
65
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:685e2d56af7b81070a84e20e9bbafef3258c3aa0ead79c3b33cc8f6a76eec00d
3
+ size 737753016
runs/Feb16_16-04-42_52dbddf20dd6/events.out.tfevents.1708099488.52dbddf20dd6.26.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0d5d0a41ddc3437b10e25a2e174aa5bbc0acff8f6a7cacf6ab9617bb9662a1e
3
+ size 10341
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
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
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "max_length": 1024,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "stride": 0,
57
+ "tokenizer_class": "DebertaV2Tokenizer",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "[UNK]",
61
+ "vocab_type": "spm"
62
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd7bcb877b649bf06fd6f4532b488ce3e862526d68aaa00f41f4cd91216ee3c
3
+ size 4283