Training in progress, epoch 1
Browse files- config.json +2 -2
- model.safetensors +2 -2
- sentencepiece.bpe.model +2 -2
- special_tokens_map.json +1 -1
- tokenizer.json +2 -2
- tokenizer_config.json +5 -3
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"XLMRobertaForTokenClassification"
|
5 |
],
|
@@ -64,5 +64,5 @@
|
|
64 |
"transformers_version": "4.46.3",
|
65 |
"type_vocab_size": 1,
|
66 |
"use_cache": true,
|
67 |
-
"vocab_size":
|
68 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "cis-lmu/glot500-base",
|
3 |
"architectures": [
|
4 |
"XLMRobertaForTokenClassification"
|
5 |
],
|
|
|
64 |
"transformers_version": "4.46.3",
|
65 |
"type_vocab_size": 1,
|
66 |
"use_cache": true,
|
67 |
+
"vocab_size": 401145
|
68 |
}
|
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:e48c8764941328aeed3b497496b60221449f2eb88ced02f6c3a8bee48b81da4e
|
3 |
+
size 1574203208
|
sentencepiece.bpe.model
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 sha256:7a313a26470baedaede322622492f2a542aa41527ddc5d40de444e945ad3c613
|
3 |
+
size 7658320
|
special_tokens_map.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"mask_token": {
|
6 |
"content": "<mask>",
|
7 |
"lstrip": true,
|
8 |
-
"normalized":
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
|
|
5 |
"mask_token": {
|
6 |
"content": "<mask>",
|
7 |
"lstrip": true,
|
8 |
+
"normalized": true,
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
tokenizer.json
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:db2eadcc9c4d85bc62828f79f5b3cc05c409d958a1ed506f2835e1d38165e7fe
|
3 |
+
size 26910556
|
tokenizer_config.json
CHANGED
@@ -32,10 +32,10 @@
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "<mask>",
|
37 |
"lstrip": true,
|
38 |
-
"normalized":
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
@@ -49,6 +49,8 @@
|
|
49 |
"model_max_length": 512,
|
50 |
"pad_token": "<pad>",
|
51 |
"sep_token": "</s>",
|
|
|
52 |
"tokenizer_class": "XLMRobertaTokenizer",
|
53 |
-
"unk_token": "<unk>"
|
|
|
54 |
}
|
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"401144": {
|
36 |
"content": "<mask>",
|
37 |
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
"rstrip": false,
|
40 |
"single_word": false,
|
41 |
"special": true
|
|
|
49 |
"model_max_length": 512,
|
50 |
"pad_token": "<pad>",
|
51 |
"sep_token": "</s>",
|
52 |
+
"sp_model_kwargs": {},
|
53 |
"tokenizer_class": "XLMRobertaTokenizer",
|
54 |
+
"unk_token": "<unk>",
|
55 |
+
"use_fast": true
|
56 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ee2fc5ce5d1559e8f8d1e6817e3c69b75af0218415e1a7ca705ff65cd55ca36
|
3 |
size 5304
|