Hugging Face's logo

FabcanK6
/
scope-bert

bert
Model card Files
xet
 Community
FabcanK6 commited on
Commit
354b5e4
·
verified ·
1 Parent(s): 220c33f

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. config.json +30 -0
  2. scope_config.json +56 -0
  3. scope_model.pt +3 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +15 -0
  6. training_history.json +50 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": false,
3
+ "architectures": [
4
+ "BertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": null,
8
+ "classifier_dropout": null,
9
+ "dtype": "float32",
10
+ "eos_token_id": null,
11
+ "gradient_checkpointing": false,
12
+ "hidden_act": "gelu",
13
+ "hidden_dropout_prob": 0.1,
14
+ "hidden_size": 768,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
+ "is_decoder": false,
18
+ "layer_norm_eps": 1e-12,
19
+ "max_position_embeddings": 512,
20
+ "model_type": "bert",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "absolute",
25
+ "tie_word_embeddings": true,
26
+ "transformers_version": "5.17.0",
27
+ "type_vocab_size": 2,
28
+ "use_cache": true,
29
+ "vocab_size": 30522
30
+ }
scope_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "bert-base-uncased",
3
+ "risk_levels": [
4
+ "low",
5
+ "medium",
6
+ "high"
7
+ ],
8
+ "issue_codes": [
9
+ "DATA_ENTRY_BACKLOG",
10
+ "QUERY_AGING",
11
+ "SDV_BACKLOG",
12
+ "SAE_REPORTING",
13
+ "CONSENT",
14
+ "PROTOCOL_DEVIATION",
15
+ "IP_ACCOUNTABILITY",
16
+ "TEMP_EXCURSION",
17
+ "STAFF_TURNOVER",
18
+ "PI_OVERSIGHT",
19
+ "ENROLLMENT_LAG",
20
+ "REG_DOCS"
21
+ ],
22
+ "bio_labels": [
23
+ "O",
24
+ "B-VISIT_TYPE",
25
+ "I-VISIT_TYPE",
26
+ "B-VISIT_DATE",
27
+ "I-VISIT_DATE",
28
+ "B-SITE",
29
+ "I-SITE",
30
+ "B-MONITOR",
31
+ "I-MONITOR",
32
+ "B-PI",
33
+ "I-PI",
34
+ "B-SCREENED",
35
+ "I-SCREENED",
36
+ "B-ENROLLED",
37
+ "I-ENROLLED",
38
+ "B-ACTION",
39
+ "I-ACTION",
40
+ "B-OWNER",
41
+ "I-OWNER",
42
+ "B-DUE",
43
+ "I-DUE"
44
+ ],
45
+ "max_length": 512,
46
+ "dropout": 0.1,
47
+ "risk_temperature": 1.3481,
48
+ "issue_threshold": 0.5,
49
+ "val": {
50
+ "val_risk_acc": 0.995,
51
+ "val_issue_f1": 1.0,
52
+ "val_span_f1": 1.0,
53
+ "val_action_f1": 1.0
54
+ },
55
+ "epoch": 3
56
+ }
scope_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c919376e117eed6a23a4b88f15b428273e22223e67d912e05063f2b35f7c745b
3
+ size 438125041
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "is_local": false,
6
+ "local_files_only": false,
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 512,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
training_history.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "args": {
3
+ "train": "data/train.jsonl",
4
+ "val": "data/val.jsonl",
5
+ "model": "bert-base-uncased",
6
+ "out": "models/scope-bert",
7
+ "epochs": 3,
8
+ "batch_size": 16,
9
+ "lr": 5e-05,
10
+ "head_lr": 0.001,
11
+ "weight_decay": 0.01,
12
+ "warmup_ratio": 0.1,
13
+ "max_length": 512,
14
+ "dropout": 0.1,
15
+ "fp16": true,
16
+ "device": "auto",
17
+ "seed": 42,
18
+ "limit": null
19
+ },
20
+ "history": [
21
+ {
22
+ "epoch": 1,
23
+ "train_loss": 0.8659564767628908,
24
+ "val_risk_acc": 0.94,
25
+ "val_issue_f1": 0.9724158836010912,
26
+ "val_span_f1": 0.9997285032773533,
27
+ "val_action_f1": 1.0,
28
+ "seconds": 177.8
29
+ },
30
+ {
31
+ "epoch": 2,
32
+ "train_loss": 0.0714571375378097,
33
+ "val_risk_acc": 0.991,
34
+ "val_issue_f1": 0.9997001499250375,
35
+ "val_span_f1": 0.9998448770650741,
36
+ "val_action_f1": 0.9991169977924945,
37
+ "seconds": 179.7
38
+ },
39
+ {
40
+ "epoch": 3,
41
+ "train_loss": 0.011617305487083892,
42
+ "val_risk_acc": 0.995,
43
+ "val_issue_f1": 1.0,
44
+ "val_span_f1": 1.0,
45
+ "val_action_f1": 1.0,
46
+ "seconds": 180.1
47
+ }
48
+ ],
49
+ "risk_temperature": 1.348070740699768
50
+ }