Hugging Face's logo

richpsharp
/
wwf-seaweed-headline-sentiment

Text Classification
Transformers
PyTorch
electra
Generated from Trainer
Inference Endpoints
Model card Files Community
richpsharp commited on
Commit
900b19d
•
1 Parent(s): 8f9e0f5

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +16 -14
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +13 -5
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +61 -10
  6. training_args.bin +1 -1
config.json CHANGED
@@ -1,37 +1,39 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
 
8
  "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "id2label": {
13
- "0": "LABEL_0",
14
- "1": "LABEL_1",
15
- "2": "LABEL_2"
16
  },
17
  "initializer_range": 0.02,
18
  "intermediate_size": 3072,
19
  "label2id": {
20
- "LABEL_0": 0,
21
- "LABEL_1": 1,
22
- "LABEL_2": 2
23
  },
24
- "layer_norm_eps": 1e-12,
25
- "max_position_embeddings": 512,
26
- "model_type": "bert",
27
  "num_attention_heads": 12,
28
  "num_hidden_layers": 12,
29
- "pad_token_id": 0,
30
  "position_embedding_type": "absolute",
31
  "problem_type": "single_label_classification",
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.33.3",
34
- "type_vocab_size": 2,
35
  "use_cache": true,
36
- "vocab_size": 30522
37
  }
 
1
  {
2
+ "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
  "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
  "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
13
  "hidden_size": 768,
14
  "id2label": {
15
+ "0": "negative",
16
+ "1": "neutral",
17
+ "2": "positive"
18
  },
19
  "initializer_range": 0.02,
20
  "intermediate_size": 3072,
21
  "label2id": {
22
+ "negative": 0,
23
+ "neutral": 1,
24
+ "positive": 2
25
  },
26
+ "layer_norm_eps": 1e-05,
27
+ "max_position_embeddings": 514,
28
+ "model_type": "roberta",
29
  "num_attention_heads": 12,
30
  "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
  "position_embedding_type": "absolute",
33
  "problem_type": "single_label_classification",
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.33.3",
36
+ "type_vocab_size": 1,
37
  "use_cache": true,
38
+ "vocab_size": 50265
39
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5a5f7bf42555c876e8e8b4eacf756b6260bb43ce5329fb2888b56e08eecaa33
3
- size 438007022
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9c6763f92e503b57a2c34255cc27fc302deca6e863c820cb25035449abec0d2
3
+ size 498661166
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
@@ -1,13 +1,64 @@
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": "BertTokenizer",
12
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
  "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "model_max_length": 1000000000000000019884624838656,
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4ddf7c34a87a336edb0fb0c8749a945cfc4ca6bc7ea1183c2ec3f5923c0ff2f
3
  size 4472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6c30c8248bb361b31a5c7636767d891007ad9d576579ff6ef07f5a598098761
3
  size 4472