Training in progress, epoch 1
Browse files- added_tokens.json +10 -0
- config.json +1 -1
- pytorch_model.bin +1 -1
- special_tokens_map.json +1 -7
- tokenizer.json +8 -7
- tokenizer_config.json +67 -8
- training_args.bin +2 -2
added_tokens.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 6,
|
3 |
+
"</s>NOTUSED": 2,
|
4 |
+
"<_>": 8,
|
5 |
+
"<mask>": 25004,
|
6 |
+
"<pad>": 1,
|
7 |
+
"<s>": 5,
|
8 |
+
"<s>NOTUSED": 0,
|
9 |
+
"<unk>": 3
|
10 |
+
}
|
config.json
CHANGED
@@ -59,7 +59,7 @@
|
|
59 |
"position_embedding_type": "absolute",
|
60 |
"problem_type": "single_label_classification",
|
61 |
"torch_dtype": "float32",
|
62 |
-
"transformers_version": "4.
|
63 |
"type_vocab_size": 1,
|
64 |
"use_cache": true,
|
65 |
"vocab_size": 25005
|
|
|
59 |
"position_embedding_type": "absolute",
|
60 |
"problem_type": "single_label_classification",
|
61 |
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.34.0",
|
63 |
"type_vocab_size": 1,
|
64 |
"use_cache": true,
|
65 |
"vocab_size": 25005
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 421095857
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a312472e17e06b775ee146316b4933caca2f5bbdd2f3b031fbde3250f85544e0
|
3 |
size 421095857
|
special_tokens_map.json
CHANGED
@@ -7,13 +7,7 @@
|
|
7 |
"bos_token": "<s>",
|
8 |
"cls_token": "<s>",
|
9 |
"eos_token": "</s>",
|
10 |
-
"mask_token":
|
11 |
-
"content": "<mask>",
|
12 |
-
"lstrip": true,
|
13 |
-
"normalized": true,
|
14 |
-
"rstrip": false,
|
15 |
-
"single_word": false
|
16 |
-
},
|
17 |
"pad_token": "<pad>",
|
18 |
"sep_token": "</s>",
|
19 |
"unk_token": "<unk>"
|
|
|
7 |
"bos_token": "<s>",
|
8 |
"cls_token": "<s>",
|
9 |
"eos_token": "</s>",
|
10 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"pad_token": "<pad>",
|
12 |
"sep_token": "</s>",
|
13 |
"unk_token": "<unk>"
|
tokenizer.json
CHANGED
@@ -19,8 +19,8 @@
|
|
19 |
"id": 0,
|
20 |
"content": "<s>NOTUSED",
|
21 |
"single_word": false,
|
22 |
-
"lstrip":
|
23 |
-
"rstrip":
|
24 |
"normalized": false,
|
25 |
"special": true
|
26 |
},
|
@@ -37,8 +37,8 @@
|
|
37 |
"id": 2,
|
38 |
"content": "</s>NOTUSED",
|
39 |
"single_word": false,
|
40 |
-
"lstrip":
|
41 |
-
"rstrip":
|
42 |
"normalized": false,
|
43 |
"special": true
|
44 |
},
|
@@ -73,8 +73,8 @@
|
|
73 |
"id": 8,
|
74 |
"content": "<_>",
|
75 |
"single_word": false,
|
76 |
-
"lstrip":
|
77 |
-
"rstrip":
|
78 |
"normalized": false,
|
79 |
"special": true
|
80 |
},
|
@@ -100219,6 +100219,7 @@
|
|
100219 |
"<mask>",
|
100220 |
0.0
|
100221 |
]
|
100222 |
-
]
|
|
|
100223 |
}
|
100224 |
}
|
|
|
19 |
"id": 0,
|
20 |
"content": "<s>NOTUSED",
|
21 |
"single_word": false,
|
22 |
+
"lstrip": true,
|
23 |
+
"rstrip": true,
|
24 |
"normalized": false,
|
25 |
"special": true
|
26 |
},
|
|
|
37 |
"id": 2,
|
38 |
"content": "</s>NOTUSED",
|
39 |
"single_word": false,
|
40 |
+
"lstrip": true,
|
41 |
+
"rstrip": true,
|
42 |
"normalized": false,
|
43 |
"special": true
|
44 |
},
|
|
|
73 |
"id": 8,
|
74 |
"content": "<_>",
|
75 |
"single_word": false,
|
76 |
+
"lstrip": true,
|
77 |
+
"rstrip": true,
|
78 |
"normalized": false,
|
79 |
"special": true
|
80 |
},
|
|
|
100219 |
"<mask>",
|
100220 |
0.0
|
100221 |
]
|
100222 |
+
],
|
100223 |
+
"byte_fallback": false
|
100224 |
}
|
100225 |
}
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,70 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"additional_special_tokens": [
|
3 |
"<s>NOTUSED",
|
4 |
"</s>NOTUSED",
|
@@ -8,14 +74,7 @@
|
|
8 |
"clean_up_tokenization_spaces": true,
|
9 |
"cls_token": "<s>",
|
10 |
"eos_token": "</s>",
|
11 |
-
"mask_token":
|
12 |
-
"__type": "AddedToken",
|
13 |
-
"content": "<mask>",
|
14 |
-
"lstrip": true,
|
15 |
-
"normalized": true,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false
|
18 |
-
},
|
19 |
"model_max_length": 1000000000000000019884624838656,
|
20 |
"pad_token": "<pad>",
|
21 |
"sep_token": "</s>",
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>NOTUSED",
|
5 |
+
"lstrip": true,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
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>NOTUSED",
|
21 |
+
"lstrip": true,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": true,
|
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 |
+
"5": {
|
36 |
+
"content": "<s>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"6": {
|
44 |
+
"content": "</s>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"8": {
|
52 |
+
"content": "<_>",
|
53 |
+
"lstrip": true,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": true,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"25004": {
|
60 |
+
"content": "<mask>",
|
61 |
+
"lstrip": true,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
}
|
67 |
+
},
|
68 |
"additional_special_tokens": [
|
69 |
"<s>NOTUSED",
|
70 |
"</s>NOTUSED",
|
|
|
74 |
"clean_up_tokenization_spaces": true,
|
75 |
"cls_token": "<s>",
|
76 |
"eos_token": "</s>",
|
77 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
"model_max_length": 1000000000000000019884624838656,
|
79 |
"pad_token": "<pad>",
|
80 |
"sep_token": "</s>",
|
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 sha256:146399dc469808ca75a807867388344222c46999cecc85567d637ca13ee4ba5b
|
3 |
+
size 4091
|