salohnana2018
commited on
Commit
•
46a6024
1
Parent(s):
3f9e986
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- runs/Aug06_12-36-06_557fceba12b2/1691325395.6777432/events.out.tfevents.1691325395.557fceba12b2.2012.1 +3 -0
- runs/Aug06_12-36-06_557fceba12b2/events.out.tfevents.1691325395.557fceba12b2.2012.0 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
runs/Aug06_12-36-06_557fceba12b2/1691325395.6777432/events.out.tfevents.1691325395.557fceba12b2.2012.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff9c394d0199c12e65e8b10336e519e894140b5e7718b4b89fadfeb2124a85f7
|
3 |
+
size 5891
|
runs/Aug06_12-36-06_557fceba12b2/events.out.tfevents.1691325395.557fceba12b2.2012.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:150bdccd80e283c2432593d63e5b6ad665d88bff292dfe73a75a611ea9179458
|
3 |
+
size 7687
|
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 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"duplicate": 10,
|
6 |
+
"full_tokenizer_file": null,
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_length": 1000000000000000019884624838656,
|
9 |
+
"name_or_path": "CAMeL-Lab/bert-base-arabic-camelbert-msa",
|
10 |
+
"never_split": null,
|
11 |
+
"pad_token": "[PAD]",
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"special_tokens_map_file": null,
|
14 |
+
"strip_accents": null,
|
15 |
+
"tokenize_chinese_chars": true,
|
16 |
+
"tokenizer_class": "BertTokenizer",
|
17 |
+
"unk_token": "[UNK]"
|
18 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab731cf95fe45c152abe52f43ed4accd20de3267d13d01b7261e926ca24ff408
|
3 |
+
size 3643
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|