Hugging Face's logo

Kudod
/
my_awesome_model_IMDB

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Kudod commited on
Commit
b5b017e
•
1 Parent(s): 4caa2d9

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. added_tokens.json +1 -5
  2. bpe.codes +0 -0
  3. model.safetensors +2 -2
  4. runs/Feb12_16-06-01_729d5ad56f1a/events.out.tfevents.1707753962.729d5ad56f1a.1153.0 +3 -0
  5. special_tokens_map.json +7 -5
  6. tokenizer_config.json +19 -19
  7. training_args.bin +1 -1
  8. vocab.txt +0 -0
added_tokens.json CHANGED
@@ -1,7 +1,3 @@
1
  {
2
- "[CLS]": 101,
3
- "[MASK]": 103,
4
- "[PAD]": 0,
5
- "[SEP]": 102,
6
- "[UNK]": 100
7
  }
 
1
  {
2
+ "<mask>": 64000
 
 
 
 
3
  }
bpe.codes 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 sha256:9a80117baee4496b2b817aae5a86e125e6978b004a4634fa348597c3f421c344
3
- size 270302536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:236bc6bf7090fd8f534c2b54b98c4e20517670b13bc0434970f0d9f5f2685319
3
+ size 544376136
runs/Feb12_16-06-01_729d5ad56f1a/events.out.tfevents.1707753962.729d5ad56f1a.1153.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25b4f9dcb4ec3a008c70f0c42577282c24b50f2d878baf802428783501fa3ac9
3
+ size 5355
special_tokens_map.json CHANGED
@@ -1,7 +1,9 @@
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": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "</s>",
8
+ "unk_token": "<unk>"
9
  }
tokenizer_config.json CHANGED
@@ -1,39 +1,39 @@
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,
@@ -41,15 +41,15 @@
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
  "added_tokens_decoder": {
3
  "0": {
4
+ "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "</s>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "3": {
28
+ "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "64000": {
36
+ "content": "<mask>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 128,
50
+ "normalization": false,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "tokenizer_class": "BertweetTokenizer",
54
+ "unk_token": "<unk>"
 
55
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6f72df9b06568feaa84177d127dd084bb430302f6aeb9760717e14e213ec375
3
  size 4600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f31cc0c25785040c95b3b51f6c29f6b9e0c23f9f71bf420819f02266f19cf0
3
  size 4600
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff