readme updated

README.md

@@ -11,23 +11,27 @@ probably proofread and complete it, then remove this comment. -->
 
 # dpr-ctx_encoder_bert_uncased_L-12_H-128_A-2
 
-This model was trained from scratch on an unknown dataset.
+This model(google/bert_uncased_L-12_H-128_A-2) was trained from scratch on training data: data.retriever.nq-adv-hn-train(facebookresearch/DPR).
 It achieves the following results on the evaluation set:
 
 
-## Model description
+## Evaluation data
 
-More information needed
+evaluation dataset: facebook-dpr-dev-dataset from official DPR github
 
-## Intended uses & limitations
+|model_name|data_name|num of queries|num of passages|R@10|R@20|R@50|R@100|R@100|
+|---|---|---|---|---|---|---|---|---|
+|nlpconnect/dpr-ctx_encoder_bert_uncased_L-12_H-128_A-2(our)|nq-dev dataset|6445|199795|60.53%|68.28%|76.07%|80.98%|91.45%|
+|*facebook/dpr-ctx_encoder-single-nq-base(hf/fb)|nq-dev dataset|6445|199795|40.94%|49.27%|59.05%|66.00%|82.00%|
 
-More information needed
+evaluation dataset: UKPLab/beir test data but we have used first 2lac passage only. 
 
-## Training and evaluation data
+|model_name|data_name|num of queries|num of passages|R@10|R@20|R@50|R@100|R@100|
+|---|---|---|---|---|---|---|---|---|
+|nlpconnect/dpr-ctx_encoder_bert_uncased_L-12_H-128_A-2(our)|nq-test dataset|3452|200001|49.68%|59.06%|69.40%|75.75%|89.28%|
+|*facebook/dpr-ctx_encoder-single-nq-base(hf/fb)|nq-test dataset|3452|200001|32.93%|43.74%|56.95%|66.30%|83.92%|
 
-More information needed
-
-## Training procedure
+Note: * means we have evaluated on same eval dataset.
 
 ### Training hyperparameters
 
@@ -35,10 +39,6 @@ The following hyperparameters were used during training:
 - optimizer: None
 - training_precision: float32
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.15.0