lucafrost commited on
Commit
0ab8740
1 Parent(s): b8ee008

Training in progress, epoch 1

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-cased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForTokenClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "Out",
13
+ "1": "B-RightSpeaker",
14
+ "2": "I-RightSpeaker",
15
+ "3": "B-Speaker",
16
+ "4": "B-LeftSpeaker",
17
+ "5": "I-LeftSpeaker",
18
+ "6": "B-Unknown",
19
+ "7": "I-Unknown",
20
+ "8": "I-Speaker"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "label2id": {
24
+ "B-LeftSpeaker": 4,
25
+ "B-RightSpeaker": 1,
26
+ "B-Speaker": 3,
27
+ "B-Unknown": 6,
28
+ "I-LeftSpeaker": 5,
29
+ "I-RightSpeaker": 2,
30
+ "I-Speaker": 8,
31
+ "I-Unknown": 7,
32
+ "Out": 0
33
+ },
34
+ "max_position_embeddings": 512,
35
+ "model_type": "distilbert",
36
+ "n_heads": 12,
37
+ "n_layers": 6,
38
+ "output_past": true,
39
+ "pad_token_id": 0,
40
+ "qa_dropout": 0.1,
41
+ "seq_classif_dropout": 0.2,
42
+ "sinusoidal_pos_embds": false,
43
+ "tie_weights_": true,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.25.1",
46
+ "vocab_size": 28996
47
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0940d6ac2b10ca4373e63089c2f2a8814ae27c62672e0ad3d39620f31f80642b
3
+ size 260824949
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
+ "cls_token": "[CLS]",
3
+ "do_lower_case": false,
4
+ "mask_token": "[MASK]",
5
+ "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-cased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "special_tokens_map_file": null,
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 sha256:47bc64c94065845948c2f58e59377701f2852c1d04e3a2673caa986cb138ed07
3
+ size 3439
vocab.txt ADDED
The diff for this file is too large to render. See raw diff