judithrosell commited on
Commit
e569be0
1 Parent(s): 8e7964c

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "medicalai/ClinicalBERT",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "B-DNA",
13
+ "1": "B-RNA",
14
+ "2": "B-cell_line",
15
+ "3": "B-cell_type",
16
+ "4": "B-protein",
17
+ "5": "I-DNA",
18
+ "6": "I-RNA",
19
+ "7": "I-cell_line",
20
+ "8": "I-cell_type",
21
+ "9": "I-protein",
22
+ "10": "O"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "label2id": {
26
+ "B-DNA": 0,
27
+ "B-RNA": 1,
28
+ "B-cell_line": 2,
29
+ "B-cell_type": 3,
30
+ "B-protein": 4,
31
+ "I-DNA": 5,
32
+ "I-RNA": 6,
33
+ "I-cell_line": 7,
34
+ "I-cell_type": 8,
35
+ "I-protein": 9,
36
+ "O": 10
37
+ },
38
+ "max_position_embeddings": 512,
39
+ "model_type": "distilbert",
40
+ "n_heads": 12,
41
+ "n_layers": 6,
42
+ "output_past": true,
43
+ "pad_token_id": 0,
44
+ "qa_dropout": 0.1,
45
+ "seq_classif_dropout": 0.2,
46
+ "sinusoidal_pos_embds": false,
47
+ "tie_weights_": true,
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.35.2",
50
+ "vocab_size": 119547
51
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8556305fecbb23761ab9437d59ccb27c404cd85931792a958de24a67bbdcd581
3
+ size 538982508
runs/Dec18_15-02-02_82808077908c/events.out.tfevents.1702911723.82808077908c.1690.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dfa5f432b8dbe50e79667a0ad3afe08461f8c1b0fcf7d06127ce904b642465c
3
+ size 5037
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "full_tokenizer_file": null,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7777e13dbed38348848b78e8c87df3b99c6e8d2b68cf65688b70bf225772cc49
3
+ size 4600
vocab.txt ADDED
The diff for this file is too large to render. See raw diff