Hugging Face's logo

PremalMatalia
/
electra-base-best-squad2

Question Answering Transformers PyTorch
electra Inference Endpoints
Model card Files Community
1
PremalMatalia commited on
Commit
18d6210
•
1 Parent(s): 2ed088a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -6,7 +6,7 @@ datasets:
6
  # ELECTRA-base for QA
7
 
8
  ## Overview
9
- **Language model:** deepset/electra-base-squad2 </br>
10
  **Language:** English </br>
11
  **Downstream-task:** Extractive QA </br>
12
  **Training data:** SQuAD 2.0 </br>
@@ -30,7 +30,7 @@ min_null_score=7.0
30
  batch_size=8
31
 
32
  n_epochs=2
33
- base_LM_model = "deepset/electra-base-squad2"
34
  learning_rate=1.5e-5
35
  adam_epsilon=1e-5
36
  adam_beta1=0.95
@@ -45,7 +45,7 @@ lr_scheduler="polynomial"
45
  ## Performance
46
  ```
47
  "exact": 79.331256
48
- "f1": 83.232347
49
  "total": 11873
50
  "HasAns_exact": 76.501350
51
  "HasAns_f1": 84.314719
6
  # ELECTRA-base for QA
7
 
8
  ## Overview
9
+ **Language model:** electra-base </br>
10
  **Language:** English </br>
11
  **Downstream-task:** Extractive QA </br>
12
  **Training data:** SQuAD 2.0 </br>
30
  batch_size=8
31
 
32
  n_epochs=2
33
+ base_LM_model = "google/electra-base-discriminator"
34
  learning_rate=1.5e-5
35
  adam_epsilon=1e-5
36
  adam_beta1=0.95
45
  ## Performance
46
  ```
47
  "exact": 79.331256
48
+ "f1": 83.232347\t
49
  "total": 11873
50
  "HasAns_exact": 76.501350
51
  "HasAns_f1": 84.314719