Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9302631578947368
+      value: 0.930921052631579
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Jeevesh8/init_bert_ft_qqp-49](https://huggingface.co/Jeevesh8/init_bert_ft_qqp-49) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9303
+- accuracy: 0.9309
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2491   | None       | 0     |
-| 0.9161   | 0.3421     | 0     |
-| 0.9237   | 0.2393     | 1     |
-| 0.9286   | 0.2178     | 2     |
-| 0.9303   | 0.2052     | 3     |
+| 0.2393   | None       | 0     |
+| 0.9161   | 0.3364     | 0     |
+| 0.9229   | 0.2379     | 1     |
+| 0.9276   | 0.2161     | 2     |
+| 0.9309   | 0.2026     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:433ed9cb01bb37a3da92aaf2a33148f568da56a996b681cc01dac4d605ad34db
+oid sha256:b5cb09c56aa602436eeac55c2de6c00d045b064db148271da4cee8131ee63f74
 size 166552