ghadeermobasher
commited on
Commit
•
2e2e4f6
1
Parent(s):
cb61d2d
Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +41 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.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-CHEBI",
|
15 |
+
"2": "I-CHEBI"
|
16 |
+
},
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
+
"label2id": {
|
20 |
+
"B-CHEBI": "1",
|
21 |
+
"I-CHEBI": "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 sha256:2e509fa6a80ccbb0d3263e91eaf1033dd1852da6edf488bd1158fa734aa7dae2
|
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 sha256:2cb4f22439e7e79e8afc6a20d25438fbc04421ae5efa0e3f508fe58c4406e2b9
|
3 |
+
size 3119
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|