Training in progress, step 500
Browse files- added_tokens.json +5 -1
- config.json +1 -1
- pytorch_model.bin +1 -1
- tokenizer_config.json +44 -0
- training_args.bin +2 -2
added_tokens.json
CHANGED
@@ -1,3 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
|
|
|
|
|
|
3 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<mask>": 64000,
|
4 |
+
"<pad>": 1,
|
5 |
+
"<s>": 0,
|
6 |
+
"<unk>": 3
|
7 |
}
|
config.json
CHANGED
@@ -22,7 +22,7 @@
|
|
22 |
"position_embedding_type": "absolute",
|
23 |
"tokenizer_class": "PhobertTokenizer",
|
24 |
"torch_dtype": "float32",
|
25 |
-
"transformers_version": "4.
|
26 |
"type_vocab_size": 1,
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 64001
|
|
|
22 |
"position_embedding_type": "absolute",
|
23 |
"tokenizer_class": "PhobertTokenizer",
|
24 |
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.34.0",
|
26 |
"type_vocab_size": 1,
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 64001
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1476792753
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5a0cc051f2f2c6b6236802df56691992d9bb7aaefa006303431397a755d2622
|
3 |
size 1476792753
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,47 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
@@ -8,5 +51,6 @@
|
|
8 |
"pad_token": "<pad>",
|
9 |
"sep_token": "</s>",
|
10 |
"tokenizer_class": "PhobertTokenizer",
|
|
|
11 |
"unk_token": "<unk>"
|
12 |
}
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"64000": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
"cls_token": "<s>",
|
|
|
51 |
"pad_token": "<pad>",
|
52 |
"sep_token": "</s>",
|
53 |
"tokenizer_class": "PhobertTokenizer",
|
54 |
+
"tokenizer_file": "/root/.cache/huggingface/hub/models--vinai--phobert-large/snapshots/9ce4eafcd8e601d798295b17c75c5f5f1b1509b9/tokenizer.json",
|
55 |
"unk_token": "<unk>"
|
56 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15ac3b45921ec710b69a186e83ca7a397b947760c3735b6e69c874ac831ee39e
|
3 |
+
size 4091
|