Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9411842105263157
+      value: 0.9397368421052632
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [crcb/isear_bert](https://huggingface.co/crcb/isear_bert) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9412
+- accuracy: 0.9397
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2117   | None       | 0     |
-| 0.9320   | 0.2509     | 0     |
-| 0.9372   | 0.1962     | 1     |
-| 0.9393   | 0.1782     | 2     |
-| 0.9412   | 0.1649     | 3     |
+| 0.2561   | None       | 0     |
+| 0.9347   | 0.2469     | 0     |
+| 0.9366   | 0.1942     | 1     |
+| 0.9391   | 0.1761     | 2     |
+| 0.9397   | 0.1637     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:590d5d2a52b9b785c582cfd8fd5e86e13ec311083c1b7655e822fecde2ec54d2
+oid sha256:bc35cbb196ca40bff9950b12fdc9c2aca56c19bc146a9e17521593fa89dfdfba
 size 2529464