Hugging Face's logo

ardauzunoglu
/
roberta-for-order-classification

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Model card Files
xet
Metrics Community
ardauzunoglu commited on
Commit
844a91d
·
1 Parent(s): c35f0e2

Training in progress, epoch 2

Browse files
Files changed (9) hide show
  1. merges.txt +0 -0
  2. model.safetensors +1 -1
  3. runs/Nov16_01-58-20_bd1110a4d2ba/events.out.tfevents.1700099901.bd1110a4d2ba.223.1 +2 -2
  4. runs/Nov16_02-00-20_bd1110a4d2ba/events.out.tfevents.1700100022.bd1110a4d2ba.223.2 +3 -0
  5. special_tokens_map.json +13 -5
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +25 -23
  8. training_args.bin +1 -1
  9. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15c64dcead502beb5ef3a335e633dad1721162ece52e7a29d72b60c59fcfea2e
3
  size 498612824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db7a2072508294e255b98e69f6d06f49035123079754a7870b4f68ac8776bedf
3
  size 498612824
runs/Nov16_01-58-20_bd1110a4d2ba/events.out.tfevents.1700099901.bd1110a4d2ba.223.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d487655e7756b9c0fa9b2e917da691638bf5784fbd7912e8228100a36469c296
3
- size 6610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b35dd14ba07ce214af8f7cb925e927beca475bb5161204232ebcd77ee05d6ab5
3
+ size 6764
runs/Nov16_02-00-20_bd1110a4d2ba/events.out.tfevents.1700100022.bd1110a4d2ba.223.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e07edbc2524731deeb36f0074887688f5e9e8d424efc19dc37e2f8932ae7151
3
+ size 6610
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,55 +1,57 @@
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": 512,
49
- "pad_token": "[PAD]",
50
- "sep_token": "[SEP]",
51
- "strip_accents": null,
52
- "tokenize_chinese_chars": true,
53
- "tokenizer_class": "DistilBertTokenizer",
54
- "unk_token": "[UNK]"
55
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "1": {
13
+ "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "2": {
21
+ "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
+ "3": {
29
+ "content": "<unk>",
30
  "lstrip": false,
31
+ "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
+ "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
  "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
 
57
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d18e417283e893cdf891de9596564cd29da830ece5eefc9eb3ba6532379888c7
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0525c43ccc4b8ed91df9385b4d02897bf42accff19d09a6dbd97e71f3c65f561
3
  size 4600
vocab.json ADDED
The diff for this file is too large to render. See raw diff