nemuwn commited on
Commit
fb31d58
1 Parent(s): 4258be0

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-multilingual-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "ner",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "O",
14
+ "1": "LOC",
15
+ "2": "MISC",
16
+ "3": "ORG",
17
+ "4": "PER"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "label2id": {
21
+ "LOC": 1,
22
+ "MISC": 2,
23
+ "O": 0,
24
+ "ORG": 3,
25
+ "PER": 4
26
+ },
27
+ "max_position_embeddings": 512,
28
+ "model_type": "distilbert",
29
+ "n_heads": 12,
30
+ "n_layers": 6,
31
+ "output_past": true,
32
+ "pad_token_id": 0,
33
+ "qa_dropout": 0.1,
34
+ "seq_classif_dropout": 0.2,
35
+ "sinusoidal_pos_embds": false,
36
+ "tie_weights_": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.28.0",
39
+ "vocab_size": 119547
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8404904a68f6652f74e2816b2d92963f28354fb4d1078d3b8452bb6f5032fffe
3
+ size 538986533
runs/May23_16-09-03_a44bfc1ec8a6/1684858159.2797372/events.out.tfevents.1684858159.a44bfc1ec8a6.274.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d52fe27875d7abea5d391fc2f006ee9f2bf5268c46beba5ae674d36f99c30eb
3
+ size 5963
runs/May23_16-09-03_a44bfc1ec8a6/events.out.tfevents.1684858159.a44bfc1ec8a6.274.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c2087c1d60f2ddf7c25c540a742c0701907987c7861cd5686d35c390047194b
3
+ size 4848
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": false,
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": "DistilBertTokenizer",
13
+ "unk_token": "[UNK]"
14
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e56e56a2fd0b1fd36cf037f11d7809c5f39d074fe3bf86a5b0b3410d23dedeb
3
+ size 3643
vocab.txt ADDED
The diff for this file is too large to render. See raw diff