Training in progress, step 500
Browse files- .gitignore +1 -0
- config.json +48 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dbmdz/bert-base-historic-multilingual-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"finetuning_task": "ner",
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": 0,
|
14 |
+
"1": 1,
|
15 |
+
"2": 2,
|
16 |
+
"3": 3,
|
17 |
+
"4": 4,
|
18 |
+
"5": 5,
|
19 |
+
"6": 6,
|
20 |
+
"7": 7,
|
21 |
+
"8": 8
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"0": 0,
|
27 |
+
"1": 1,
|
28 |
+
"2": 2,
|
29 |
+
"3": 3,
|
30 |
+
"4": 4,
|
31 |
+
"5": 5,
|
32 |
+
"6": 6,
|
33 |
+
"7": 7,
|
34 |
+
"8": 8
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"max_position_embeddings": 512,
|
38 |
+
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"pad_token_id": 0,
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.20.1",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 32000
|
48 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cf80ff445e2d1e0f4c12220486f378faa240e7e3d18ff2bfd80a0c8d2b1f427
|
3 |
+
size 440205105
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": false,
|
5 |
+
"mask_token": "[MASK]",
|
6 |
+
"max_len": 512,
|
7 |
+
"name_or_path": "dbmdz/bert-base-historic-multilingual-cased",
|
8 |
+
"never_split": null,
|
9 |
+
"pad_token": "[PAD]",
|
10 |
+
"sep_token": "[SEP]",
|
11 |
+
"special_tokens_map_file": null,
|
12 |
+
"strip_accents": false,
|
13 |
+
"tokenize_chinese_chars": true,
|
14 |
+
"tokenizer_class": "BertTokenizer",
|
15 |
+
"unk_token": "[UNK]"
|
16 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1b71fed2f689284142bb334fb346d008b29ae77086b74513c480771ef6e3e5d
|
3 |
+
size 3247
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|