Hugging Face's logo

jayantapaul888
/
twitter-data-microsoft-deberta-base-mnli-sentiment-finetuned-memes

Text Classification
Transformers
PyTorch
TensorBoard
deberta
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
1
jayantapaul888 commited on
Commit
a5f4978
•
1 Parent(s): 3eaafc4

Training in progress, epoch 1

Browse files
Files changed (8) hide show
  1. config.json +23 -18
  2. pytorch_model.bin +2 -2
  3. runs/Nov03_01-58-13_teesta/1667420903.5132928/events.out.tfevents.1667420903.teesta.9225.3 +3 -0
  4. runs/Nov03_01-58-13_teesta/events.out.tfevents.1667420903.teesta.9225.2 +3 -0
  5. special_tokens_map.json +49 -5
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +63 -12
  8. training_args.bin +1 -1
config.json CHANGED
@@ -1,37 +1,42 @@
1
  {
2
- "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
- "activation": "gelu",
4
  "architectures": [
5
- "DistilBertForSequenceClassification"
6
  ],
7
- "attention_dropout": 0.1,
8
- "dim": 768,
9
- "dropout": 0.1,
10
- "finetuning_task": "sst-2",
11
- "hidden_dim": 3072,
12
  "id2label": {
13
  "0": "0",
14
  "1": "1",
15
  "2": "2"
16
  },
17
  "initializer_range": 0.02,
 
18
  "label2id": {
19
  "0": "0",
20
  "1": "1",
21
  "2": "2"
22
  },
 
23
  "max_position_embeddings": 512,
24
- "model_type": "distilbert",
25
- "n_heads": 12,
26
- "n_layers": 6,
27
- "output_past": true,
28
  "pad_token_id": 0,
29
- "problem_type": "single_label_classification",
30
- "qa_dropout": 0.1,
31
- "seq_classif_dropout": 0.2,
32
- "sinusoidal_pos_embds": false,
33
- "tie_weights_": true,
 
 
 
 
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.24.0.dev0",
36
- "vocab_size": 30522
 
37
  }
 
1
  {
2
+ "_name_or_path": "microsoft/deberta-base-mnli",
 
3
  "architectures": [
4
+ "DebertaForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
 
10
  "id2label": {
11
  "0": "0",
12
  "1": "1",
13
  "2": "2"
14
  },
15
  "initializer_range": 0.02,
16
+ "intermediate_size": 3072,
17
  "label2id": {
18
  "0": "0",
19
  "1": "1",
20
  "2": "2"
21
  },
22
+ "layer_norm_eps": 1e-07,
23
  "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
  "pad_token_id": 0,
29
+ "pooler_dropout": 0,
30
+ "pooler_hidden_act": "gelu",
31
+ "pooler_hidden_size": 768,
32
+ "pos_att_type": [
33
+ "c2p",
34
+ "p2c"
35
+ ],
36
+ "position_biased_input": false,
37
+ "relative_attention": true,
38
  "torch_dtype": "float32",
39
  "transformers_version": "4.24.0.dev0",
40
+ "type_vocab_size": 0,
41
+ "vocab_size": 50265
42
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5aa4a5acb9493bb425024467b1f365e2c0cc4faac454c471f61c44035c0ad6d5
3
- size 267857393
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c86ca1a69c3da9a934ed8766e8d2dd825afc6e63b3f26cd5fc1f68efbc8457c
3
+ size 556849903
runs/Nov03_01-58-13_teesta/1667420903.5132928/events.out.tfevents.1667420903.teesta.9225.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50305912711f2d2060990bb50207a94c2c6f4228a05c41163720bba05487ee10
3
+ size 5613
runs/Nov03_01-58-13_teesta/events.out.tfevents.1667420903.teesta.9225.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f922ae3fd6eed8f7f94e85656e0b2d39b5c35c49bd81cab39c820d474348e8eb
3
+ size 5040
special_tokens_map.json CHANGED
@@ -1,7 +1,51 @@
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": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,16 +1,67 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "do_basic_tokenize": true,
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "model_max_length": 512,
7
- "name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
8
- "never_split": null,
9
- "pad_token": "[PAD]",
10
- "sep_token": "[SEP]",
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  "special_tokens_map_file": null,
12
- "strip_accents": null,
13
- "tokenize_chinese_chars": true,
14
- "tokenizer_class": "DistilBertTokenizer",
15
- "unk_token": "[UNK]"
 
 
 
 
 
 
16
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "[CLS]",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "do_lower_case": false,
21
+ "eos_token": {
22
+ "__type": "AddedToken",
23
+ "content": "[SEP]",
24
+ "lstrip": false,
25
+ "normalized": true,
26
+ "rstrip": false,
27
+ "single_word": false
28
+ },
29
+ "errors": "replace",
30
+ "mask_token": {
31
+ "__type": "AddedToken",
32
+ "content": "[MASK]",
33
+ "lstrip": true,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
  "model_max_length": 512,
39
+ "name_or_path": "microsoft/deberta-base-mnli",
40
+ "pad_token": {
41
+ "__type": "AddedToken",
42
+ "content": "[PAD]",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "sep_token": {
49
+ "__type": "AddedToken",
50
+ "content": "[SEP]",
51
+ "lstrip": false,
52
+ "normalized": true,
53
+ "rstrip": false,
54
+ "single_word": false
55
+ },
56
  "special_tokens_map_file": null,
57
+ "tokenizer_class": "DebertaTokenizer",
58
+ "unk_token": {
59
+ "__type": "AddedToken",
60
+ "content": "[UNK]",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ "vocab_type": "gpt2"
67
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5412c88094dd66ea9bfb397c283a770ba81c5da922feece917f0b4368f5a6a71
3
  size 3503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdcc8a04c4eec578639c369cea2bfd3534b21b5dd2d0a7dd00a570a14b2174be
3
  size 3503