ramdhanfirdaus
commited on
Commit
•
43e6ee5
1
Parent(s):
efbd576
Training in progress, step 3000
Browse files- adapter_model.bin +1 -1
- special_tokens_map.json +3 -21
- tokenizer_config.json +0 -4
- training_args.bin +1 -1
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50349441
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fca6089eabc9d760545d8f131c69babfe3c479af93d313825389b4f0617cf513
|
3 |
size 50349441
|
special_tokens_map.json
CHANGED
@@ -1,24 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"pad_token": "<|endoftext|>",
|
17 |
-
"unk_token":
|
18 |
-
"content": "<|endoftext|>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
}
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer_config.json
CHANGED
@@ -13,12 +13,8 @@
|
|
13 |
"bos_token": "<|endoftext|>",
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|
16 |
-
"max_length": 512,
|
17 |
"model_max_length": 1024,
|
18 |
"pad_token": "<|endoftext|>",
|
19 |
-
"stride": 0,
|
20 |
"tokenizer_class": "GPT2Tokenizer",
|
21 |
-
"truncation_side": "right",
|
22 |
-
"truncation_strategy": "longest_first",
|
23 |
"unk_token": "<|endoftext|>"
|
24 |
}
|
|
|
13 |
"bos_token": "<|endoftext|>",
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|
|
|
16 |
"model_max_length": 1024,
|
17 |
"pad_token": "<|endoftext|>",
|
|
|
18 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
19 |
"unk_token": "<|endoftext|>"
|
20 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4155
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:435ef416a520c327b44f1a335ae059bdb8b9a978d39dfecd5bff01684de2670c
|
3 |
size 4155
|