jonas-luehrs commited on
Commit
a6c697d
1 Parent(s): 86dc1f6

Training in progress, step 500

Browse files
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jonas-luehrs/bert-base-cased-MLM-chemistry",
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": "O",
14
+ "1": "B-ADDITIVE",
15
+ "2": "I-ADDITIVE",
16
+ "3": "B-OLEFIN",
17
+ "4": "I-OLEFIN",
18
+ "5": "B-PRE_CATALYST",
19
+ "6": "I-PRE_CATALYST",
20
+ "7": "B-SOLVENT",
21
+ "8": "I-SOLVENT",
22
+ "9": "B-SUPPORT",
23
+ "10": "I-SUPPORT"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "B-ADDITIVE": 1,
29
+ "B-OLEFIN": 3,
30
+ "B-PRE_CATALYST": 5,
31
+ "B-SOLVENT": 7,
32
+ "B-SUPPORT": 9,
33
+ "I-ADDITIVE": 2,
34
+ "I-OLEFIN": 4,
35
+ "I-PRE_CATALYST": 6,
36
+ "I-SOLVENT": 8,
37
+ "I-SUPPORT": 10,
38
+ "O": 0
39
+ },
40
+ "layer_norm_eps": 1e-12,
41
+ "max_position_embeddings": 512,
42
+ "model_type": "bert",
43
+ "num_attention_heads": 12,
44
+ "num_hidden_layers": 12,
45
+ "pad_token_id": 0,
46
+ "position_embedding_type": "absolute",
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.33.2",
49
+ "type_vocab_size": 2,
50
+ "use_cache": true,
51
+ "vocab_size": 28996
52
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6168352f86e86945c071a99dd19b448f9b329d9b8607b92e51b2671d1fe96c
3
+ size 430980265
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": false,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec3f85abddc957dcbac830874cb0878121c2e15519ad7f9d2b03668311e15f07
3
+ size 4091
vocab.txt ADDED
The diff for this file is too large to render. See raw diff