Hugging Face's logo

zluvolyote
/
DEREXP

Text Classification
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Model card Files
xet
Metrics Community
1
zluvolyote commited on
Commit
b680c4d
·
1 Parent(s): 798de4f

Training in progress, step 500

Browse files
Files changed (9) hide show
  1. config.json +15 -23
  2. pytorch_model.bin +2 -2
  3. runs/Jul20_15-50-39_13a322e3f7f6/events.out.tfevents.1658332243.13a322e3f7f6.80.2 +2 -2
  4. runs/Jul20_16-09-53_13a322e3f7f6/1658333397.3432662/events.out.tfevents.1658333397.13a322e3f7f6.80.5 +3 -0
  5. runs/Jul20_16-09-53_13a322e3f7f6/events.out.tfevents.1658333397.13a322e3f7f6.80.4 +3 -0
  6. special_tokens_map.json +5 -49
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +10 -63
  9. training_args.bin +1 -1
config.json CHANGED
@@ -1,38 +1,30 @@
1
  {
2
- "_name_or_path": "microsoft/deberta-base",
 
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": "LABEL_0"
12
  },
13
  "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
  "label2id": {
16
  "LABEL_0": 0
17
  },
18
- "layer_norm_eps": 1e-07,
19
  "max_position_embeddings": 512,
20
- "max_relative_positions": -1,
21
- "model_type": "deberta",
22
- "num_attention_heads": 12,
23
- "num_hidden_layers": 12,
24
  "pad_token_id": 0,
25
- "pooler_dropout": 0,
26
- "pooler_hidden_act": "gelu",
27
- "pooler_hidden_size": 768,
28
- "pos_att_type": [
29
- "c2p",
30
- "p2c"
31
- ],
32
- "position_biased_input": false,
33
- "relative_attention": true,
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.20.1",
36
- "type_vocab_size": 0,
37
- "vocab_size": 50265
38
  }
 
1
  {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
  "architectures": [
5
+ "DistilBertForSequenceClassification"
6
  ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
  "id2label": {
12
  "0": "LABEL_0"
13
  },
14
  "initializer_range": 0.02,
 
15
  "label2id": {
16
  "LABEL_0": 0
17
  },
 
18
  "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
 
22
  "pad_token_id": 0,
23
+ "qa_dropout": 0.1,
24
+ "seq_classif_dropout": 0.2,
25
+ "sinusoidal_pos_embds": false,
26
+ "tie_weights_": true,
 
 
 
 
 
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.20.1",
29
+ "vocab_size": 30522
 
30
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dd41efbc575dd0687d31ce9ee305cc891349538fb6b6dfab1357de8b958cbd8
3
- size 556843759
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7d4146a8d687bbd7aec9e919b0246b4d2a34518295b38f3471a24962d542df8
3
+ size 267851249
runs/Jul20_15-50-39_13a322e3f7f6/events.out.tfevents.1658332243.13a322e3f7f6.80.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b00214a3c3652502a1f506a4aa55f72843c8f3cc0b449cf961fb638b346f97f9
3
- size 4350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca696bc8ff1bbb56e2b15061deb0f5b2ffc785ecfb36022dd59bd5d1a148cc9b
3
+ size 6830
runs/Jul20_16-09-53_13a322e3f7f6/1658333397.3432662/events.out.tfevents.1658333397.13a322e3f7f6.80.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace1e7f32ef98bfa49336404e7ee93a1aad224a96fb2b67e295f01ba45f1a070
3
+ size 5327
runs/Jul20_16-09-53_13a322e3f7f6/events.out.tfevents.1658333397.13a322e3f7f6.80.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7788227df55752a525009f7911b3fcf5390fb59c8b61eefbb2c8b2351edc065
3
+ size 4180
special_tokens_map.json CHANGED
@@ -1,51 +1,7 @@
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
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,67 +1,14 @@
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",
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
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "model_max_length": 512,
6
+ "name_or_path": "distilbert-base-uncased",
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  "special_tokens_map_file": null,
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "DistilBertTokenizer",
13
+ "unk_token": "[UNK]"
 
 
 
 
 
 
14
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebff1b2578d1a609fbff8f596d5266adde7240d5506f8aa5559e22b3db7fa4c5
3
  size 3247
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8af8eb6f8b1d61a5dd1ebd13f6717fd7112feb2a903f24c3b202ec356fcd37ed
3
  size 3247