Tommert25 commited on
Commit
6532674
1 Parent(s): 0ef66f7

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-multilingual-uncased",
3
+ "architectures": [
4
+ "BertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "directionality": "bidi",
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "Name",
14
+ "1": "Other (OTH)",
15
+ "2": "Dutch (NL)",
16
+ "3": "VAR",
17
+ "4": "Arabic (ARAB)",
18
+ "5": "English (EN)",
19
+ "6": "Borrow (BOR)",
20
+ "7": "Mixed",
21
+ "8": "Straattaal"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "Arabic (ARAB)": 4,
27
+ "Borrow (BOR)": 6,
28
+ "Dutch (NL)": 2,
29
+ "English (EN)": 5,
30
+ "Mixed": 7,
31
+ "Name": 0,
32
+ "Other (OTH)": 1,
33
+ "Straattaal": 8,
34
+ "VAR": 3
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
+ "pooler_fc_size": 768,
43
+ "pooler_num_attention_heads": 12,
44
+ "pooler_num_fc_layers": 3,
45
+ "pooler_size_per_head": 128,
46
+ "pooler_type": "first_token_transform",
47
+ "position_embedding_type": "absolute",
48
+ "torch_dtype": "float32",
49
+ "transformers_version": "4.30.2",
50
+ "type_vocab_size": 2,
51
+ "use_cache": true,
52
+ "vocab_size": 105879
53
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00295212a6bccb3747bd077858aec437f9cc821f197f40522e6f7bb724814afb
3
+ size 667163117
runs/Jul11_10-15-03_429a757f765f/events.out.tfevents.1689071029.429a757f765f.2317.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6aac147e2090159d5bb5870a276f7e34e8b4db9212e891b8a79fa305e3d8cd6
3
+ size 5083
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 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": true,
6
+ "mask_token": "[MASK]",
7
+ "model_max_length": 512,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "BertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00ec338e054dedc36b8328d788094a6318034fc23575613e31db1a1d6b9d7bc5
3
+ size 3963
vocab.txt ADDED
The diff for this file is too large to render. See raw diff