ghadeermobasher commited on
Commit
4004533
1 Parent(s): a3066aa

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Disease",
15
+ "2": "I-Disease",
16
+ "3": "B-Chemical",
17
+ "4": "I-Chemical"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "B-Chemical": "3",
23
+ "B-Disease": "1",
24
+ "I-Chemical": "4",
25
+ "I-Disease": "2",
26
+ "O": "0"
27
+ },
28
+ "layer_norm_eps": 1e-12,
29
+ "max_length": 512,
30
+ "max_position_embeddings": 512,
31
+ "model_type": "electra",
32
+ "num_attention_heads": 12,
33
+ "num_hidden_layers": 12,
34
+ "pad_token_id": 0,
35
+ "position_embedding_type": "absolute",
36
+ "summary_activation": "gelu",
37
+ "summary_last_dropout": 0.1,
38
+ "summary_type": "first",
39
+ "summary_use_proj": true,
40
+ "torch_dtype": "float32",
41
+ "transformers_version": "4.16.0.dev0",
42
+ "type_vocab_size": 2,
43
+ "use_cache": true,
44
+ "vocab_size": 28895
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50a48e194bd9e63a71d39bf83b9ef46cc00b4b4a2dd8d36dc73e334b06c93b0d
3
+ size 430668465
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:fd8d02a5d06107271ca553aa2dc5cfff3aed16d9ab8aa3c9e840381da78dfcdc
3
+ size 3119
vocab.txt ADDED
The diff for this file is too large to render. See raw diff