NiWang2024 commited on
Commit
298f726
1 Parent(s): 3cbe119

Training in progress, step 500

Browse files
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json CHANGED
@@ -36,6 +36,6 @@
36
  "sinusoidal_pos_embds": false,
37
  "tie_weights_": true,
38
  "torch_dtype": "float32",
39
- "transformers_version": "4.40.1",
40
  "vocab_size": 30522
41
  }
 
36
  "sinusoidal_pos_embds": false,
37
  "tie_weights_": true,
38
  "torch_dtype": "float32",
39
+ "transformers_version": "4.30.2",
40
  "vocab_size": 30522
41
  }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28446b7280bd6339c814e19ee0e81e5a4c84bbac8aee54290a374f13dd870d87
3
+ size 267867821
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": {
5
  "strategy": "BatchLongest",
6
  "direction": "Right",
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": {
10
  "strategy": "BatchLongest",
11
  "direction": "Right",
tokenizer_config.json CHANGED
@@ -1,51 +1,9 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "[PAD]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "100": {
12
- "content": "[UNK]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "101": {
20
- "content": "[CLS]",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "102": {
28
- "content": "[SEP]",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "103": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- }
43
- },
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_lower_case": true,
47
  "mask_token": "[MASK]",
48
- "model_max_length": 1000000000000000019884624838656,
49
  "pad_token": "[PAD]",
50
  "sep_token": "[SEP]",
51
  "strip_accents": null,
 
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,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34cb939dfa727c45da39b0d51ad2031ee8692fb2b8c652cb48097f8d9a0820c4
3
- size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0b1e1fe0d94143c00556d5f711e612e469f9ece52eeaf236ba18281fed71b10
3
+ size 3963