edanigoben commited on
Commit
9f0ed54
·
1 Parent(s): 69af1ac

Training in progress, step 500

Browse files
config.json CHANGED
@@ -2,43 +2,18 @@
2
  "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
  "attention_dropout": 0.1,
8
  "dim": 768,
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
11
- "id2label": {
12
- "0": "LABEL_0",
13
- "1": "LABEL_1",
14
- "2": "LABEL_2",
15
- "3": "LABEL_3",
16
- "4": "LABEL_4",
17
- "5": "LABEL_5",
18
- "6": "LABEL_6",
19
- "7": "LABEL_7",
20
- "8": "LABEL_8",
21
- "9": "LABEL_9"
22
- },
23
  "initializer_range": 0.02,
24
- "label2id": {
25
- "LABEL_0": 0,
26
- "LABEL_1": 1,
27
- "LABEL_2": 2,
28
- "LABEL_3": 3,
29
- "LABEL_4": 4,
30
- "LABEL_5": 5,
31
- "LABEL_6": 6,
32
- "LABEL_7": 7,
33
- "LABEL_8": 8,
34
- "LABEL_9": 9
35
- },
36
  "max_position_embeddings": 512,
37
  "model_type": "distilbert",
38
  "n_heads": 12,
39
  "n_layers": 6,
40
  "pad_token_id": 0,
41
- "problem_type": "single_label_classification",
42
  "qa_dropout": 0.1,
43
  "seq_classif_dropout": 0.2,
44
  "sinusoidal_pos_embds": false,
 
2
  "_name_or_path": "distilbert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForMaskedLM"
6
  ],
7
  "attention_dropout": 0.1,
8
  "dim": 768,
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
 
 
 
 
 
 
 
 
 
 
 
 
11
  "initializer_range": 0.02,
 
 
 
 
 
 
 
 
 
 
 
 
12
  "max_position_embeddings": 512,
13
  "model_type": "distilbert",
14
  "n_heads": 12,
15
  "n_layers": 6,
16
  "pad_token_id": 0,
 
17
  "qa_dropout": 0.1,
18
  "seq_classif_dropout": 0.2,
19
  "sinusoidal_pos_embds": false,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d93e97fccb70eea17ed2e7c678d171a6c546c96fc8949d93b21362bd8f93497f
3
- size 267880109
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ae77c3f2cb8f88156c84f405d51c3fbd1891dc0abb1dffe637966f018d1077
3
+ size 267978033
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e34e8badcf30593149bbb96814fab51e16b53f4ff6df9e25aed76859c66b5475
3
- size 3643
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f25344d923a64357f74ad09713ee8fbcd66313a57171044ae67f1dc4ed2438e
3
+ size 3707
vocab.txt ADDED
The diff for this file is too large to render. See raw diff