Training in progress, epoch 1
Browse files- config.json +2 -4
- model.safetensors +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +6 -8
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,6 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"_num_labels": 5,
|
4 |
"architectures": [
|
5 |
"BertForSequenceClassification"
|
6 |
],
|
@@ -27,7 +26,6 @@
|
|
27 |
"model_type": "bert",
|
28 |
"num_attention_heads": 12,
|
29 |
"num_hidden_layers": 12,
|
30 |
-
"output_past": true,
|
31 |
"pad_token_id": 0,
|
32 |
"pooler_fc_size": 768,
|
33 |
"pooler_num_attention_heads": 12,
|
@@ -40,5 +38,5 @@
|
|
40 |
"transformers_version": "4.41.2",
|
41 |
"type_vocab_size": 2,
|
42 |
"use_cache": true,
|
43 |
-
"vocab_size":
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
|
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
|
|
26 |
"model_type": "bert",
|
27 |
"num_attention_heads": 12,
|
28 |
"num_hidden_layers": 12,
|
|
|
29 |
"pad_token_id": 0,
|
30 |
"pooler_fc_size": 768,
|
31 |
"pooler_num_attention_heads": 12,
|
|
|
38 |
"transformers_version": "4.41.2",
|
39 |
"type_vocab_size": 2,
|
40 |
"use_cache": true,
|
41 |
+
"vocab_size": 119547
|
42 |
}
|
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 sha256:68e7fb9777420b3516be661eddf18ed8c05e4e005f0682e835b452a18c4c9489
|
3 |
+
size 711446532
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -8,7 +8,7 @@
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
-
"
|
12 |
"content": "[UNK]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
@@ -16,7 +16,7 @@
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
-
"
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
@@ -24,7 +24,7 @@
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
-
"
|
28 |
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
@@ -32,7 +32,7 @@
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
-
"
|
36 |
"content": "[MASK]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
@@ -43,11 +43,9 @@
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
-
"
|
47 |
-
"do_lower_case": true,
|
48 |
"mask_token": "[MASK]",
|
49 |
-
"model_max_length":
|
50 |
-
"never_split": null,
|
51 |
"pad_token": "[PAD]",
|
52 |
"sep_token": "[SEP]",
|
53 |
"strip_accents": null,
|
|
|
8 |
"single_word": false,
|
9 |
"special": true
|
10 |
},
|
11 |
+
"100": {
|
12 |
"content": "[UNK]",
|
13 |
"lstrip": false,
|
14 |
"normalized": false,
|
|
|
16 |
"single_word": false,
|
17 |
"special": true
|
18 |
},
|
19 |
+
"101": {
|
20 |
"content": "[CLS]",
|
21 |
"lstrip": false,
|
22 |
"normalized": false,
|
|
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
},
|
27 |
+
"102": {
|
28 |
"content": "[SEP]",
|
29 |
"lstrip": false,
|
30 |
"normalized": false,
|
|
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
},
|
35 |
+
"103": {
|
36 |
"content": "[MASK]",
|
37 |
"lstrip": false,
|
38 |
"normalized": false,
|
|
|
43 |
},
|
44 |
"clean_up_tokenization_spaces": true,
|
45 |
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": false,
|
|
|
47 |
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
|
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cee493daf36d1418cadd7b9aea2d4e32df8112ad54831c5e9167a02651503c8
|
3 |
size 5048
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|