Hugging Face's logo

Sarmila
/
pubmed-bert-squad-covidqa

Question Answering
Transformers
PyTorch
English
bert
Generated from Trainer
biology
Inference Endpoints
Model card Files Community
4
Sarmila commited on
Commit
343875a
•
1 Parent(s): 66663d7

End of training

Browse files
Files changed (4) hide show
  1. README.md +8 -8
  2. config.json +1 -1
  3. pytorch_model.bin +1 -1
  4. training_args.bin +2 -2
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  license: mit
3
- base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
- - squad
8
  model-index:
9
  - name: pubmed-bert-squad-covidqa
10
  results: []
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # pubmed-bert-squad-covidqa
17
 
18
- This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract) on the squad dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.0342
21
 
22
  ## Model description
23
 
@@ -39,7 +39,7 @@ The following hyperparameters were used during training:
39
  - learning_rate: 2e-05
40
  - train_batch_size: 32
41
  - eval_batch_size: 32
42
- - seed: 0
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - num_epochs: 3
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 1.0731 | 1.0 | 2738 | 1.0432 |
52
- | 0.8584 | 2.0 | 5476 | 1.0055 |
53
- | 0.6878 | 3.0 | 8214 | 1.0342 |
54
 
55
 
56
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: Sarmila/pubmed-bert-squad-covidqa
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
+ - covid_qa_deepset
8
  model-index:
9
  - name: pubmed-bert-squad-covidqa
10
  results: []
 
15
 
16
  # pubmed-bert-squad-covidqa
17
 
18
+ This model is a fine-tuned version of [Sarmila/pubmed-bert-squad-covidqa](https://huggingface.co/Sarmila/pubmed-bert-squad-covidqa) on the covid_qa_deepset dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.4876
21
 
22
  ## Model description
23
 
 
39
  - learning_rate: 2e-05
40
  - train_batch_size: 32
41
  - eval_batch_size: 32
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
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 1.0 | 51 | 0.4001 |
52
+ | No log | 2.0 | 102 | 0.4524 |
53
+ | No log | 3.0 | 153 | 0.4876 |
54
 
55
 
56
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract",
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
 
1
  {
2
+ "_name_or_path": "Sarmila/pubmed-bert-squad-covidqa",
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab37892f8be6ad458f5cb070358ee42d00cee31023add669df8eb875cc87e4f7
3
  size 435640489
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af0faafd433075dc50861b0fb403b96aac7d4a82bc5d17d3167e6f7e4efe9fc4
3
  size 435640489
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a95eb3ce7695fce56a6e7dbe91a618faef19ee4c74886e46ecc2964b8dd9478d
3
- size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7d718ea7e3f72dd3bd810ac5214dd79e7d7ccf2b040fc5af5fb5a92466ae93
3
+ size 4027