Training in progress, step 200
Browse files- added_tokens.json +2 -2
- config.json +2 -2
- model.safetensors +2 -2
- tokenizer_config.json +4 -4
- training_args.bin +2 -2
- vocab.json +37 -38
added_tokens.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
{
|
2 |
-
"</s>":
|
3 |
-
"<s>":
|
4 |
}
|
|
|
1 |
{
|
2 |
+
"</s>": 45,
|
3 |
+
"<s>": 44
|
4 |
}
|
config.json
CHANGED
@@ -77,7 +77,7 @@
|
|
77 |
"num_hidden_layers": 48,
|
78 |
"num_negatives": 100,
|
79 |
"output_hidden_size": 1280,
|
80 |
-
"pad_token_id":
|
81 |
"proj_codevector_dim": 1024,
|
82 |
"tdnn_dilation": [
|
83 |
1,
|
@@ -103,6 +103,6 @@
|
|
103 |
"torch_dtype": "float32",
|
104 |
"transformers_version": "4.46.0.dev0",
|
105 |
"use_weighted_layer_sum": false,
|
106 |
-
"vocab_size":
|
107 |
"xvector_output_dim": 512
|
108 |
}
|
|
|
77 |
"num_hidden_layers": 48,
|
78 |
"num_negatives": 100,
|
79 |
"output_hidden_size": 1280,
|
80 |
+
"pad_token_id": 43,
|
81 |
"proj_codevector_dim": 1024,
|
82 |
"tdnn_dilation": [
|
83 |
1,
|
|
|
103 |
"torch_dtype": "float32",
|
104 |
"transformers_version": "4.46.0.dev0",
|
105 |
"use_weighted_layer_sum": false,
|
106 |
+
"vocab_size": 46,
|
107 |
"xvector_output_dim": 512
|
108 |
}
|
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 sha256:789436420644d24827d936d9ceddb275261dbb26222339e591a8e617f8da203e
|
3 |
+
size 3850326704
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
-
"
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
-
"
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
1 |
{
|
2 |
"added_tokens_decoder": {
|
3 |
+
"42": {
|
4 |
"content": "[UNK]",
|
5 |
"lstrip": true,
|
6 |
"normalized": false,
|
|
|
8 |
"single_word": false,
|
9 |
"special": false
|
10 |
},
|
11 |
+
"43": {
|
12 |
"content": "[PAD]",
|
13 |
"lstrip": true,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": false
|
18 |
},
|
19 |
+
"44": {
|
20 |
"content": "<s>",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"45": {
|
28 |
"content": "</s>",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
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 sha256:5b5f873ccc8a6d04388d15316b393072b2225df3ecd6bcca4500bf02e8464718
|
3 |
+
size 5368
|
vocab.json
CHANGED
@@ -5,43 +5,42 @@
|
|
5 |
"$": 4,
|
6 |
"'": 5,
|
7 |
"(": 6,
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"[
|
15 |
-
"
|
16 |
-
"
|
17 |
-
"
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"z": 37,
|
41 |
"|": 1,
|
42 |
-
"à":
|
43 |
-
"á":
|
44 |
-
"â":
|
45 |
-
"ģ":
|
46 |
-
"’":
|
47 |
}
|
|
|
5 |
"$": 4,
|
6 |
"'": 5,
|
7 |
"(": 6,
|
8 |
+
",": 7,
|
9 |
+
"-": 8,
|
10 |
+
".": 9,
|
11 |
+
"/": 10,
|
12 |
+
"?": 11,
|
13 |
+
"[PAD]": 43,
|
14 |
+
"[UNK]": 42,
|
15 |
+
"a": 12,
|
16 |
+
"b": 13,
|
17 |
+
"c": 14,
|
18 |
+
"d": 15,
|
19 |
+
"e": 16,
|
20 |
+
"f": 17,
|
21 |
+
"g": 18,
|
22 |
+
"h": 19,
|
23 |
+
"i": 20,
|
24 |
+
"j": 21,
|
25 |
+
"k": 22,
|
26 |
+
"l": 23,
|
27 |
+
"m": 24,
|
28 |
+
"n": 25,
|
29 |
+
"o": 26,
|
30 |
+
"p": 27,
|
31 |
+
"r": 28,
|
32 |
+
"s": 29,
|
33 |
+
"t": 30,
|
34 |
+
"u": 31,
|
35 |
+
"v": 32,
|
36 |
+
"w": 33,
|
37 |
+
"x": 34,
|
38 |
+
"y": 35,
|
39 |
+
"z": 36,
|
|
|
40 |
"|": 1,
|
41 |
+
"à": 37,
|
42 |
+
"á": 38,
|
43 |
+
"â": 39,
|
44 |
+
"ģ": 40,
|
45 |
+
"’": 41
|
46 |
}
|