saiteki-kai commited on
Commit
df4cb96
·
verified ·
1 Parent(s): 4386caf

Training in progress, step 2114

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaQADiff"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 1,
7
+ "cls_dropout": 0.3,
8
+ "dtype": "float32",
9
+ "eos_token_id": 2,
10
+ "finetuning_task": "text-classification",
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "animal_abuse",
16
+ "1": "child_abuse",
17
+ "2": "controversial_topics,politics",
18
+ "3": "discrimination,stereotype,injustice",
19
+ "4": "drug_abuse,weapons,banned_substance",
20
+ "5": "financial_crime,property_crime,theft",
21
+ "6": "hate_speech,offensive_language",
22
+ "7": "misinformation_regarding_ethics,laws_and_safety",
23
+ "8": "non_violent_unethical_behavior",
24
+ "9": "privacy_violation",
25
+ "10": "self_harm",
26
+ "11": "sexually_explicit,adult_content",
27
+ "12": "terrorism,organized_crime",
28
+ "13": "violence,aiding_and_abetting,incitement"
29
+ },
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 4096,
32
+ "label2id": {
33
+ "animal_abuse": 0,
34
+ "child_abuse": 1,
35
+ "controversial_topics,politics": 2,
36
+ "discrimination,stereotype,injustice": 3,
37
+ "drug_abuse,weapons,banned_substance": 4,
38
+ "financial_crime,property_crime,theft": 5,
39
+ "hate_speech,offensive_language": 6,
40
+ "misinformation_regarding_ethics,laws_and_safety": 7,
41
+ "non_violent_unethical_behavior": 8,
42
+ "privacy_violation": 9,
43
+ "self_harm": 10,
44
+ "sexually_explicit,adult_content": 11,
45
+ "terrorism,organized_crime": 12,
46
+ "violence,aiding_and_abetting,incitement": 13
47
+ },
48
+ "layer_norm_eps": 1e-07,
49
+ "legacy": true,
50
+ "max_position_embeddings": 512,
51
+ "max_relative_positions": -1,
52
+ "model_type": "deberta-v2",
53
+ "norm_rel_ebd": "layer_norm",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 24,
56
+ "pad_token_id": 0,
57
+ "pooler_dropout": 0,
58
+ "pooler_hidden_act": "gelu",
59
+ "pooler_hidden_size": 1024,
60
+ "pos_att_type": [
61
+ "p2c",
62
+ "c2p"
63
+ ],
64
+ "position_biased_input": false,
65
+ "position_buckets": 256,
66
+ "problem_type": "multi_label_classification",
67
+ "relative_attention": true,
68
+ "share_att_key": true,
69
+ "transformers_version": "4.57.1",
70
+ "type_vocab_size": 0,
71
+ "vocab_size": 128100
72
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d9b216d599895bcedcb2225802e416d59d5a1b9aaad1837a8b2b63e88d3462
3
+ size 1757143544
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
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 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "[PAD]",
53
+ "padding_side": "right",
54
+ "sep_token": "[SEP]",
55
+ "sp_model_kwargs": {},
56
+ "split_by_punct": false,
57
+ "tokenizer_class": "DebertaV2Tokenizer",
58
+ "unk_token": "[UNK]",
59
+ "vocab_type": "spm"
60
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c983c4693662fa612d78a6ce8c9053c5bc8c4b0dea382577bff0e468d1fd7d75
3
+ size 5905