Training in progress, epoch 1
Browse files- added_tokens.json +3 -0
- pytorch_model.bin +1 -1
- special_tokens_map.json +7 -49
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -62
- training_args.bin +1 -1
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[MASK]": 128000
|
3 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 737774905
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16c8136f4f3998707d14b302883685c9f3e9eb39ad8c8da0f8a78ac6ef27affd
|
3 |
size 737774905
|
special_tokens_map.json
CHANGED
@@ -1,51 +1,9 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"cls_token": {
|
10 |
-
"content": "[CLS]",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
-
"eos_token": {
|
17 |
-
"content": "[SEP]",
|
18 |
-
"lstrip": false,
|
19 |
-
"normalized": true,
|
20 |
-
"rstrip": false,
|
21 |
-
"single_word": false
|
22 |
-
},
|
23 |
-
"mask_token": {
|
24 |
-
"content": "[MASK]",
|
25 |
-
"lstrip": true,
|
26 |
-
"normalized": true,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
},
|
30 |
-
"pad_token": {
|
31 |
-
"content": "[PAD]",
|
32 |
-
"lstrip": false,
|
33 |
-
"normalized": true,
|
34 |
-
"rstrip": false,
|
35 |
-
"single_word": false
|
36 |
-
},
|
37 |
-
"sep_token": {
|
38 |
-
"content": "[SEP]",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": true,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false
|
43 |
-
},
|
44 |
-
"unk_token": {
|
45 |
-
"content": "[UNK]",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": true,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false
|
50 |
-
}
|
51 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
3 |
+
"cls_token": "[CLS]",
|
4 |
+
"eos_token": "[SEP]",
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"pad_token": "[PAD]",
|
7 |
+
"sep_token": "[SEP]",
|
8 |
+
"unk_token": "[UNK]"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
|
3 |
+
size 2464616
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,66 +1,16 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"add_prefix_space": false,
|
4 |
-
"bos_token": {
|
5 |
-
"__type": "AddedToken",
|
6 |
-
"content": "[CLS]",
|
7 |
-
"lstrip": false,
|
8 |
-
"normalized": true,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
"clean_up_tokenization_spaces": true,
|
13 |
-
"cls_token":
|
14 |
-
"__type": "AddedToken",
|
15 |
-
"content": "[CLS]",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": true,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
"do_lower_case": false,
|
22 |
-
"eos_token":
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"__type": "AddedToken",
|
33 |
-
"content": "[MASK]",
|
34 |
-
"lstrip": true,
|
35 |
-
"normalized": true,
|
36 |
-
"rstrip": false,
|
37 |
-
"single_word": false
|
38 |
-
},
|
39 |
-
"model_max_length": 512,
|
40 |
-
"pad_token": {
|
41 |
-
"__type": "AddedToken",
|
42 |
-
"content": "[PAD]",
|
43 |
-
"lstrip": false,
|
44 |
-
"normalized": true,
|
45 |
-
"rstrip": false,
|
46 |
-
"single_word": false
|
47 |
-
},
|
48 |
-
"sep_token": {
|
49 |
-
"__type": "AddedToken",
|
50 |
-
"content": "[SEP]",
|
51 |
-
"lstrip": false,
|
52 |
-
"normalized": true,
|
53 |
-
"rstrip": false,
|
54 |
-
"single_word": false
|
55 |
-
},
|
56 |
-
"tokenizer_class": "DebertaTokenizer",
|
57 |
-
"unk_token": {
|
58 |
-
"__type": "AddedToken",
|
59 |
-
"content": "[UNK]",
|
60 |
-
"lstrip": false,
|
61 |
-
"normalized": true,
|
62 |
-
"rstrip": false,
|
63 |
-
"single_word": false
|
64 |
-
},
|
65 |
-
"vocab_type": "gpt2"
|
66 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "[CLS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "[CLS]",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"do_lower_case": false,
|
6 |
+
"eos_token": "[SEP]",
|
7 |
+
"mask_token": "[MASK]",
|
8 |
+
"model_max_length": 1000000000000000019884624838656,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"sp_model_kwargs": {},
|
12 |
+
"split_by_punct": false,
|
13 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
14 |
+
"unk_token": "[UNK]",
|
15 |
+
"vocab_type": "spm"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01a49c1378dd92cb0430b621718d5a24464dcf9bc11f8301032f85cb87ef589a
|
3 |
size 3963
|