CarmelaFinianos
commited on
Commit
•
9872289
1
Parent(s):
df16e5d
Training in progress, step 50
Browse files- model.safetensors +2 -2
- runs/Nov21_11-21-52_c9511e3807e4/events.out.tfevents.1732188635.c9511e3807e4.2001.0 +3 -0
- runs/Nov21_11-33-47_c9511e3807e4/events.out.tfevents.1732188832.c9511e3807e4.2001.1 +3 -0
- special_tokens_map.json +35 -4
- tokenizer.json +0 -0
- tokenizer_config.json +55 -14
- training_args.bin +1 -1
- vocab.txt +0 -0
model.safetensors
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 sha256:0b3987f395000343782d8bb22ed3f9f7339a761e2cd6d0bd0699137f950144e2
|
3 |
+
size 774148488
|
runs/Nov21_11-21-52_c9511e3807e4/events.out.tfevents.1732188635.c9511e3807e4.2001.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dd628489814d743f7cd384cc239d5b2ff694a1130885b0144e457519fbe434b
|
3 |
+
size 6660
|
runs/Nov21_11-33-47_c9511e3807e4/events.out.tfevents.1732188832.c9511e3807e4.2001.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4138c05fcd1fc062441f590ba2eb6f40e0649f94e474d34e6951cf075b8571f1
|
3 |
+
size 7340
|
special_tokens_map.json
CHANGED
@@ -1,6 +1,37 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
-
"content": "
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
@@ -9,7 +9,7 @@
|
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
-
"content": "
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
@@ -17,30 +17,71 @@
|
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
-
"content": "
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
-
"content": "
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|
35 |
},
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"
|
41 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
"processor_class": "SpeechT5Processor",
|
43 |
-
"
|
44 |
-
"
|
45 |
-
"
|
|
|
|
|
46 |
}
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
"lstrip": false,
|
6 |
"normalized": false,
|
7 |
"rstrip": false,
|
|
|
9 |
"special": true
|
10 |
},
|
11 |
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
15 |
"rstrip": false,
|
|
|
17 |
"special": true
|
18 |
},
|
19 |
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "[رابط]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": true,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "[بريد]",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": true,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": true,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "[مستخدم]",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": true,
|
65 |
+
"special": true
|
66 |
}
|
67 |
},
|
68 |
+
"clean_up_tokenization_spaces": false,
|
69 |
+
"cls_token": "[CLS]",
|
70 |
+
"do_basic_tokenize": true,
|
71 |
+
"do_lower_case": false,
|
72 |
+
"mask_token": "[MASK]",
|
73 |
+
"max_len": 512,
|
74 |
+
"model_max_length": 512,
|
75 |
+
"never_split": [
|
76 |
+
"[بريد]",
|
77 |
+
"[مستخدم]",
|
78 |
+
"[رابط]"
|
79 |
+
],
|
80 |
+
"pad_token": "[PAD]",
|
81 |
"processor_class": "SpeechT5Processor",
|
82 |
+
"sep_token": "[SEP]",
|
83 |
+
"strip_accents": null,
|
84 |
+
"tokenize_chinese_chars": true,
|
85 |
+
"tokenizer_class": "BertTokenizer",
|
86 |
+
"unk_token": "[UNK]"
|
87 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8fb585ec0014f97717a00ef3f3114a3056445e3b3d86314f8e1df6dd77231974
|
3 |
size 5432
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|