Hugging Face's logo

hung200504
/
bert-covid

Question Answering
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
hung200504 commited on
Commit
b8968a7
•
1 Parent(s): e7fa7a1

bert-squad

Browse files
Files changed (8) hide show
  1. README.md +126 -0
  2. config.json +25 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +7 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +57 -0
  7. training_args.bin +3 -0
  8. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - covid_qa_deepset
8
+ model-index:
9
+ - name: bert-covid
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # bert-covid
17
+
18
+ This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the covid_qa_deepset dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.6900
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
+ - learning_rate: 3e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 3
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 5.474 | 0.04 | 5 | 4.3730 |
52
+ | 3.9933 | 0.09 | 10 | 3.2783 |
53
+ | 3.0206 | 0.13 | 15 | 2.0289 |
54
+ | 1.9741 | 0.18 | 20 | 1.3879 |
55
+ | 1.4351 | 0.22 | 25 | 1.1733 |
56
+ | 1.5916 | 0.26 | 30 | 1.1623 |
57
+ | 0.5383 | 0.31 | 35 | 1.1952 |
58
+ | 0.7776 | 0.35 | 40 | 1.1920 |
59
+ | 1.1785 | 0.39 | 45 | 1.1216 |
60
+ | 1.1334 | 0.44 | 50 | 1.0412 |
61
+ | 0.7445 | 0.48 | 55 | 1.0829 |
62
+ | 0.6512 | 0.53 | 60 | 1.0443 |
63
+ | 0.7516 | 0.57 | 65 | 1.0089 |
64
+ | 0.5953 | 0.61 | 70 | 0.9273 |
65
+ | 0.8589 | 0.66 | 75 | 0.8947 |
66
+ | 0.7561 | 0.7 | 80 | 0.9009 |
67
+ | 0.9561 | 0.75 | 85 | 0.9006 |
68
+ | 0.7731 | 0.79 | 90 | 0.8482 |
69
+ | 0.8269 | 0.83 | 95 | 0.8380 |
70
+ | 0.9884 | 0.88 | 100 | 0.8200 |
71
+ | 0.9187 | 0.92 | 105 | 0.8775 |
72
+ | 0.585 | 0.96 | 110 | 0.8499 |
73
+ | 0.6835 | 1.01 | 115 | 0.8314 |
74
+ | 0.6668 | 1.05 | 120 | 0.7491 |
75
+ | 0.5558 | 1.1 | 125 | 0.7154 |
76
+ | 0.4491 | 1.14 | 130 | 0.8212 |
77
+ | 1.0667 | 1.18 | 135 | 0.8477 |
78
+ | 0.4472 | 1.23 | 140 | 0.7636 |
79
+ | 0.6892 | 1.27 | 145 | 0.7493 |
80
+ | 0.66 | 1.32 | 150 | 0.6932 |
81
+ | 0.5044 | 1.36 | 155 | 0.7675 |
82
+ | 0.5329 | 1.4 | 160 | 0.7406 |
83
+ | 0.2223 | 1.45 | 165 | 0.8099 |
84
+ | 0.5495 | 1.49 | 170 | 0.8758 |
85
+ | 0.5534 | 1.54 | 175 | 0.8476 |
86
+ | 0.4962 | 1.58 | 180 | 0.7953 |
87
+ | 0.7477 | 1.62 | 185 | 0.7610 |
88
+ | 0.7293 | 1.67 | 190 | 0.8357 |
89
+ | 0.6205 | 1.71 | 195 | 0.7339 |
90
+ | 0.5687 | 1.75 | 200 | 0.6908 |
91
+ | 0.884 | 1.8 | 205 | 0.6706 |
92
+ | 0.5928 | 1.84 | 210 | 0.6546 |
93
+ | 0.3209 | 1.89 | 215 | 0.6505 |
94
+ | 0.7585 | 1.93 | 220 | 0.6486 |
95
+ | 0.8501 | 1.97 | 225 | 0.6272 |
96
+ | 0.1664 | 2.02 | 230 | 0.6211 |
97
+ | 0.4483 | 2.06 | 235 | 0.6550 |
98
+ | 0.3361 | 2.11 | 240 | 0.6604 |
99
+ | 0.3085 | 2.15 | 245 | 0.6520 |
100
+ | 0.2407 | 2.19 | 250 | 0.6695 |
101
+ | 0.3418 | 2.24 | 255 | 0.6687 |
102
+ | 0.3165 | 2.28 | 260 | 0.6730 |
103
+ | 0.5811 | 2.32 | 265 | 0.6546 |
104
+ | 0.3516 | 2.37 | 270 | 0.6579 |
105
+ | 0.3136 | 2.41 | 275 | 0.6688 |
106
+ | 0.2508 | 2.46 | 280 | 0.6921 |
107
+ | 0.3463 | 2.5 | 285 | 0.7124 |
108
+ | 0.3603 | 2.54 | 290 | 0.7160 |
109
+ | 0.4455 | 2.59 | 295 | 0.6995 |
110
+ | 0.5433 | 2.63 | 300 | 0.6919 |
111
+ | 0.3411 | 2.68 | 305 | 0.6898 |
112
+ | 0.6065 | 2.72 | 310 | 0.6922 |
113
+ | 0.6258 | 2.76 | 315 | 0.6955 |
114
+ | 0.283 | 2.81 | 320 | 0.7008 |
115
+ | 0.6233 | 2.85 | 325 | 0.6988 |
116
+ | 0.3899 | 2.89 | 330 | 0.6949 |
117
+ | 0.238 | 2.94 | 335 | 0.6916 |
118
+ | 0.3166 | 2.98 | 340 | 0.6900 |
119
+
120
+
121
+ ### Framework versions
122
+
123
+ - Transformers 4.34.1
124
+ - Pytorch 2.1.0+cu118
125
+ - Datasets 2.14.6
126
+ - Tokenizers 0.14.1
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext",
3
+ "architectures": [
4
+ "BertForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.34.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01b7c456ed6e1ceb335601cbd5f575f54b560e1d982941d5d9f4c7cd4dda23a4
3
+ size 435640934
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
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 1000000000000000019884624838656,
50
+ "never_split": null,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "strip_accents": null,
54
+ "tokenize_chinese_chars": true,
55
+ "tokenizer_class": "BertTokenizer",
56
+ "unk_token": "[UNK]"
57
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6244c99a691b9c4578eb815865fb210903751da0298cb70fe04801bd68c5f3f
3
+ size 4536
vocab.txt ADDED
The diff for this file is too large to render. See raw diff