Commit
•
ab11e11
1
Parent(s):
ed34502
Training in progress, epoch 1
Browse files- .gitignore +1 -0
- runs/Jul05_00-55-18_e7d1b58f91de/1688518529.1055994/events.out.tfevents.1688518529.e7d1b58f91de.3129.1 +3 -0
- runs/Jul05_00-55-18_e7d1b58f91de/events.out.tfevents.1688518529.e7d1b58f91de.3129.0 +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/Jul05_00-55-18_e7d1b58f91de/1688518529.1055994/events.out.tfevents.1688518529.e7d1b58f91de.3129.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:958ddb99f77f80e5e68b1e8ed882bcfce1373d2716e3bd09ad76a0266baafb77
|
3 |
+
size 5861
|
runs/Jul05_00-55-18_e7d1b58f91de/events.out.tfevents.1688518529.e7d1b58f91de.3129.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ae4969eafc2dafb8d981c856b7fb082dc3e40d2d25dc4d037e868cba6c633f7
|
3 |
+
size 7631
|
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:acaa5dba96c0a49920ace076e0672ad1e4ed09cc11a0fe635c39650be54fc731
|
3 |
+
size 3579
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|