ZodiUOA commited on
Commit
a4a18cf
1 Parent(s): a28f5d7

Upload 8 files

Browse files
Files changed (8) hide show
  1. README.md +57 -3
  2. config.json +12 -6
  3. gitattributes +35 -0
  4. special_tokens_map.json +7 -0
  5. tf_model.h5 +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +13 -0
  8. vocab.txt +0 -0
README.md CHANGED
@@ -1,4 +1,58 @@
1
  ---
2
- metrics:
3
- - bertscore
4
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_keras_callback
5
+ model-index:
6
+ - name: Valent2809/news_classifier_covid19
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information Keras had access to. You should
11
+ probably proofread and complete it, then remove this comment. -->
12
+
13
+ # Valent2809/news_classifier_covid19
14
+
15
+ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Train Loss: 0.0080
18
+ - Validation Loss: 0.1031
19
+ - Train Accuracy: 0.9771
20
+ - Epoch: 4
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2830, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
40
+ - training_precision: float32
41
+
42
+ ### Training results
43
+
44
+ | Train Loss | Validation Loss | Train Accuracy | Epoch |
45
+ |:----------:|:---------------:|:--------------:|:-----:|
46
+ | 0.0317 | 0.0990 | 0.9736 | 0 |
47
+ | 0.0239 | 0.1048 | 0.9762 | 1 |
48
+ | 0.0161 | 0.1136 | 0.9762 | 2 |
49
+ | 0.0106 | 0.1010 | 0.9789 | 3 |
50
+ | 0.0080 | 0.1031 | 0.9771 | 4 |
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.30.2
56
+ - TensorFlow 2.12.0
57
+ - Datasets 2.13.1
58
+ - Tokenizers 0.13.3
config.json CHANGED
@@ -1,25 +1,31 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "activation": "gelu",
4
  "architectures": [
5
- "BertForSequenceClassification"
6
  ],
7
  "attention_dropout": 0.1,
8
  "dim": 768,
9
  "dropout": 0.1,
10
  "hidden_dim": 3072,
 
 
 
 
11
  "initializer_range": 0.02,
 
 
 
 
12
  "max_position_embeddings": 512,
13
- "model_type": "bert",
14
  "n_heads": 12,
15
  "n_layers": 6,
16
  "pad_token_id": 0,
17
- "problem_type": "single_label_classification",
18
  "qa_dropout": 0.1,
19
  "seq_classif_dropout": 0.2,
20
  "sinusoidal_pos_embds": false,
21
  "tie_weights_": true,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.28.0",
24
  "vocab_size": 30522
25
  }
 
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": "Not Covid-19",
13
+ "1": "Covid-19"
14
+ },
15
  "initializer_range": 0.02,
16
+ "label2id": {
17
+ "Covid-19": 1,
18
+ "Not Covid-19": 0
19
+ },
20
  "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
  "n_heads": 12,
23
  "n_layers": 6,
24
  "pad_token_id": 0,
 
25
  "qa_dropout": 0.1,
26
  "seq_classif_dropout": 0.2,
27
  "sinusoidal_pos_embds": false,
28
  "tie_weights_": true,
29
+ "transformers_version": "4.30.2",
 
30
  "vocab_size": 30522
31
  }
gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a70d3dd8ef3e8231a73b895327e97e1406248aac9a36b713232ebbddbecd223
3
+ size 267956392
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "DistilBertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff