Training in progress, epoch 0
Browse files- adapter_model.bin +1 -1
- special_tokens_map.json +3 -21
- tokenizer.json +8 -8
- tokenizer_config.json +62 -25
- training_args.bin +2 -2
adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 16822989
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:880670b686793c0866490f946f19f015869b92f7c89185e7b385b5fa0fab0ac0
|
3 |
size 16822989
|
special_tokens_map.json
CHANGED
@@ -5,26 +5,8 @@
|
|
5 |
"β<SUF>",
|
6 |
"β<EOT>"
|
7 |
],
|
8 |
-
"bos_token":
|
9 |
-
|
10 |
-
"lstrip": false,
|
11 |
-
"normalized": true,
|
12 |
-
"rstrip": false,
|
13 |
-
"single_word": false
|
14 |
-
},
|
15 |
-
"eos_token": {
|
16 |
-
"content": "</s>",
|
17 |
-
"lstrip": false,
|
18 |
-
"normalized": true,
|
19 |
-
"rstrip": false,
|
20 |
-
"single_word": false
|
21 |
-
},
|
22 |
"pad_token": "</s>",
|
23 |
-
"unk_token":
|
24 |
-
"content": "<unk>",
|
25 |
-
"lstrip": false,
|
26 |
-
"normalized": true,
|
27 |
-
"rstrip": false,
|
28 |
-
"single_word": false
|
29 |
-
}
|
30 |
}
|
|
|
5 |
"β<SUF>",
|
6 |
"β<EOT>"
|
7 |
],
|
8 |
+
"bos_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"pad_token": "</s>",
|
11 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
}
|
tokenizer.json
CHANGED
@@ -39,8 +39,8 @@
|
|
39 |
"id": 32007,
|
40 |
"content": "β<PRE>",
|
41 |
"single_word": false,
|
42 |
-
"lstrip":
|
43 |
-
"rstrip":
|
44 |
"normalized": false,
|
45 |
"special": true
|
46 |
},
|
@@ -48,8 +48,8 @@
|
|
48 |
"id": 32008,
|
49 |
"content": "β<SUF>",
|
50 |
"single_word": false,
|
51 |
-
"lstrip":
|
52 |
-
"rstrip":
|
53 |
"normalized": false,
|
54 |
"special": true
|
55 |
},
|
@@ -57,8 +57,8 @@
|
|
57 |
"id": 32009,
|
58 |
"content": "β<MID>",
|
59 |
"single_word": false,
|
60 |
-
"lstrip":
|
61 |
-
"rstrip":
|
62 |
"normalized": false,
|
63 |
"special": true
|
64 |
},
|
@@ -66,8 +66,8 @@
|
|
66 |
"id": 32010,
|
67 |
"content": "β<EOT>",
|
68 |
"single_word": false,
|
69 |
-
"lstrip":
|
70 |
-
"rstrip":
|
71 |
"normalized": false,
|
72 |
"special": true
|
73 |
}
|
|
|
39 |
"id": 32007,
|
40 |
"content": "β<PRE>",
|
41 |
"single_word": false,
|
42 |
+
"lstrip": true,
|
43 |
+
"rstrip": true,
|
44 |
"normalized": false,
|
45 |
"special": true
|
46 |
},
|
|
|
48 |
"id": 32008,
|
49 |
"content": "β<SUF>",
|
50 |
"single_word": false,
|
51 |
+
"lstrip": true,
|
52 |
+
"rstrip": true,
|
53 |
"normalized": false,
|
54 |
"special": true
|
55 |
},
|
|
|
57 |
"id": 32009,
|
58 |
"content": "β<MID>",
|
59 |
"single_word": false,
|
60 |
+
"lstrip": true,
|
61 |
+
"rstrip": true,
|
62 |
"normalized": false,
|
63 |
"special": true
|
64 |
},
|
|
|
66 |
"id": 32010,
|
67 |
"content": "β<EOT>",
|
68 |
"single_word": false,
|
69 |
+
"lstrip": true,
|
70 |
+
"rstrip": true,
|
71 |
"normalized": false,
|
72 |
"special": true
|
73 |
}
|
tokenizer_config.json
CHANGED
@@ -1,44 +1,81 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"additional_special_tokens": [
|
3 |
"β<PRE>",
|
4 |
"β<MID>",
|
5 |
"β<SUF>",
|
6 |
"β<EOT>"
|
7 |
],
|
8 |
-
"bos_token":
|
9 |
-
"__type": "AddedToken",
|
10 |
-
"content": "<s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"clean_up_tokenization_spaces": false,
|
17 |
-
"eos_token":
|
18 |
-
"__type": "AddedToken",
|
19 |
-
"content": "</s>",
|
20 |
-
"lstrip": false,
|
21 |
-
"normalized": true,
|
22 |
-
"rstrip": false,
|
23 |
-
"single_word": false
|
24 |
-
},
|
25 |
"eot_token": "β<EOT>",
|
26 |
"fill_token": "<FILL_ME>",
|
27 |
"legacy": null,
|
28 |
"middle_token": "β<MID>",
|
29 |
"model_max_length": 1000000000000000019884624838656,
|
30 |
-
"pad_token":
|
31 |
"prefix_token": "β<PRE>",
|
32 |
"sp_model_kwargs": {},
|
33 |
"suffix_token": "β<SUF>",
|
34 |
"tokenizer_class": "CodeLlamaTokenizer",
|
35 |
-
"unk_token":
|
36 |
-
"__type": "AddedToken",
|
37 |
-
"content": "<unk>",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": true,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false
|
42 |
-
},
|
43 |
"use_default_system_prompt": false
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"32007": {
|
28 |
+
"content": "β<PRE>",
|
29 |
+
"lstrip": true,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": true,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32008": {
|
36 |
+
"content": "β<SUF>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": true,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"32009": {
|
44 |
+
"content": "β<MID>",
|
45 |
+
"lstrip": true,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": true,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"32010": {
|
52 |
+
"content": "β<EOT>",
|
53 |
+
"lstrip": true,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": true,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
}
|
59 |
+
},
|
60 |
"additional_special_tokens": [
|
61 |
"β<PRE>",
|
62 |
"β<MID>",
|
63 |
"β<SUF>",
|
64 |
"β<EOT>"
|
65 |
],
|
66 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
"clean_up_tokenization_spaces": false,
|
68 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
"eot_token": "β<EOT>",
|
70 |
"fill_token": "<FILL_ME>",
|
71 |
"legacy": null,
|
72 |
"middle_token": "β<MID>",
|
73 |
"model_max_length": 1000000000000000019884624838656,
|
74 |
+
"pad_token": "</s>",
|
75 |
"prefix_token": "β<PRE>",
|
76 |
"sp_model_kwargs": {},
|
77 |
"suffix_token": "β<SUF>",
|
78 |
"tokenizer_class": "CodeLlamaTokenizer",
|
79 |
+
"unk_token": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
"use_default_system_prompt": false
|
81 |
}
|
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:a6fd5580b2b4c6ea4b60b8f8d103d15b7d6564b263f32e115238fa569ef23b84
|
3 |
+
size 4091
|