Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.8503947368421053
+      value: 0.8444736842105263
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dhimskyy/wiki-bert](https://huggingface.co/dhimskyy/wiki-bert) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.8504
+- accuracy: 0.8445
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2497   | None       | 0     |
-| 0.8170   | 0.7561     | 0     |
-| 0.8325   | 0.5355     | 1     |
-| 0.8457   | 0.4964     | 2     |
-| 0.8504   | 0.4762     | 3     |
+| 0.2471   | None       | 0     |
+| 0.8059   | 0.7762     | 0     |
+| 0.8304   | 0.5563     | 1     |
+| 0.8430   | 0.5109     | 2     |
+| 0.8445   | 0.4907     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab5afa5d40ad3aab1832d08861531e9b2920f9fc03db53b1a94fc798855c076e
+oid sha256:53d417831255301b179c5f42bd347d71f91a7ecbad9ea86fae258a451735bb4c
 size 89520