Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9307894736842105
+      value: 0.9323684210526316
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Capreolus/bert-base-msmarco](https://huggingface.co/Capreolus/bert-base-msmarco) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9308
+- accuracy: 0.9324
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2496   | None       | 0     |
-| 0.9187   | 0.3048     | 0     |
-| 0.9267   | 0.2229     | 1     |
-| 0.9289   | 0.2036     | 2     |
-| 0.9308   | 0.1938     | 3     |
+| 0.2472   | None       | 0     |
+| 0.9203   | 0.3173     | 0     |
+| 0.9238   | 0.2280     | 1     |
+| 0.9301   | 0.2069     | 2     |
+| 0.9324   | 0.1954     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a23c8925bc5951740f85ca578213a19c2c66ce4f5dcb67a1f47e5ca3703486d
+oid sha256:e1f4bafed67d8e5b557679bdfe396e008e8a711e15177a3923d8e8b5228dce2b
 size 166552