ghadeermobasher commited on
Commit
4c670cb
1 Parent(s): ba79e7a

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sultan/BioM-ELECTRA-Base-Discriminator",
3
+ "architectures": [
4
+ "ElectraForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "embedding_size": 768,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "B-GENE",
15
+ "2": "I-GENE"
16
+ },
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 3072,
19
+ "label2id": {
20
+ "B-GENE": "1",
21
+ "I-GENE": "2",
22
+ "O": "0"
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "max_length": 512,
26
+ "max_position_embeddings": 512,
27
+ "model_type": "electra",
28
+ "num_attention_heads": 12,
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 0,
31
+ "position_embedding_type": "absolute",
32
+ "summary_activation": "gelu",
33
+ "summary_last_dropout": 0.1,
34
+ "summary_type": "first",
35
+ "summary_use_proj": true,
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.16.0.dev0",
38
+ "type_vocab_size": 2,
39
+ "use_cache": true,
40
+ "vocab_size": 28895
41
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a171d13b47bcfed84f6092cbe049097e1e1ab25cf0bfcf6b11d57e1ad823ed
3
+ size 430662321
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "problem_type": "multi_label_classification", "max_length": 512, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "sultan/BioM-ELECTRA-Base-Discriminator", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "ElectraTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92f7c15e9cf7d6d64ffc14baada78b313db23e5bb0843af0e3459ac470c9b2ad
3
+ size 3119
vocab.txt ADDED
The diff for this file is too large to render. See raw diff