jonas-luehrs commited on
Commit
5d40b0a
1 Parent(s): 35178e1

Training in progress, epoch 1

Browse files
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "jiangg/chembert_cased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "O",
13
+ "1": "B-ADDITIVE",
14
+ "2": "I-ADDITIVE",
15
+ "3": "B-OLEFIN",
16
+ "4": "I-OLEFIN",
17
+ "5": "B-PRE_CATALYST",
18
+ "6": "I-PRE_CATALYST",
19
+ "7": "B-SOLVENT",
20
+ "8": "I-SOLVENT",
21
+ "9": "B-SUPPORT",
22
+ "10": "I-SUPPORT"
23
+ },
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 3072,
26
+ "label2id": {
27
+ "B-ADDITIVE": 1,
28
+ "B-OLEFIN": 3,
29
+ "B-PRE_CATALYST": 5,
30
+ "B-SOLVENT": 7,
31
+ "B-SUPPORT": 9,
32
+ "I-ADDITIVE": 2,
33
+ "I-OLEFIN": 4,
34
+ "I-PRE_CATALYST": 6,
35
+ "I-SOLVENT": 8,
36
+ "I-SUPPORT": 10,
37
+ "O": 0
38
+ },
39
+ "layer_norm_eps": 1e-12,
40
+ "max_position_embeddings": 512,
41
+ "model_type": "bert",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 12,
44
+ "pad_token_id": 0,
45
+ "position_embedding_type": "absolute",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.33.2",
48
+ "type_vocab_size": 2,
49
+ "use_cache": true,
50
+ "vocab_size": 28996
51
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9f3611195b8bf755b995d9d83e878fea559f6dfe062472f0df5376e4909ad4
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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "max_len": 512,
8
+ "model_max_length": 512,
9
+ "never_split": null,
10
+ "pad_token": "[PAD]",
11
+ "sep_token": "[SEP]",
12
+ "strip_accents": null,
13
+ "tokenize_chinese_chars": true,
14
+ "tokenizer_class": "BertTokenizer",
15
+ "unk_token": "[UNK]"
16
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7c55c2acbeb7c258d4cefbd28a251c90fc2c661612a96568af8ec80d9996db9
3
+ size 4027
vocab.txt ADDED
The diff for this file is too large to render. See raw diff