sujeongh commited on
Commit
4fb9716
·
1 Parent(s): 3a2f773

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sujeongh/biobert-v1.1-BC2GM-IOBES",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "I-protein",
14
+ "1": "B-cell_line",
15
+ "2": "S-DNA",
16
+ "3": "I-RNA",
17
+ "4": "E-DNA",
18
+ "5": "I-cell_line",
19
+ "6": "B-DNA",
20
+ "7": "S-cell_line",
21
+ "8": "S-protein",
22
+ "9": "S-cell_type",
23
+ "10": "E-cell_line",
24
+ "11": "E-cell_type",
25
+ "12": "B-RNA",
26
+ "13": "S-RNA",
27
+ "14": "B-protein",
28
+ "15": "E-protein",
29
+ "16": "B-cell_type",
30
+ "17": "I-DNA",
31
+ "18": "I-cell_type",
32
+ "19": "E-RNA",
33
+ "20": "O"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "B-DNA": 6,
39
+ "B-RNA": 12,
40
+ "B-cell_line": 1,
41
+ "B-cell_type": 16,
42
+ "B-protein": 14,
43
+ "E-DNA": 4,
44
+ "E-RNA": 19,
45
+ "E-cell_line": 10,
46
+ "E-cell_type": 11,
47
+ "E-protein": 15,
48
+ "I-DNA": 17,
49
+ "I-RNA": 3,
50
+ "I-cell_line": 5,
51
+ "I-cell_type": 18,
52
+ "I-protein": 0,
53
+ "O": 20,
54
+ "S-DNA": 2,
55
+ "S-RNA": 13,
56
+ "S-cell_line": 7,
57
+ "S-cell_type": 9,
58
+ "S-protein": 8
59
+ },
60
+ "layer_norm_eps": 1e-12,
61
+ "max_position_embeddings": 512,
62
+ "model_type": "bert",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "position_embedding_type": "absolute",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.28.1",
69
+ "type_vocab_size": 2,
70
+ "use_cache": true,
71
+ "vocab_size": 28996
72
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3933642f91e98599a56523048ad178aadcbb453eb74f139dbceb96d480d3f2
3
+ size 431015914
runs/Sep01_16-18-12_andlab-server/1725207497.1969185/events.out.tfevents.1725207497.andlab-server.3438106.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a15e98e9cf6e4bafb523a9847f702c1df3fee378b1cffa6eae6cb137bcd0c533
3
+ size 5913
runs/Sep01_16-18-12_andlab-server/events.out.tfevents.1725207497.andlab-server.3438106.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0462aa2934262020436c2e1689f9cbcd863375feffefa5234f63322f440d7731
3
+ size 5244
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 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_basic_tokenize": true,
5
+ "do_lower_case": false,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "never_split": null,
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_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c74234b64a97069369c79de4bea5aba238606c6f1ac3d6f0c6df61c936aeced8
3
+ size 4088
vocab.txt ADDED
The diff for this file is too large to render. See raw diff