Finished training.

README.md

@@ -23,7 +23,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.9380263157894737
+      value: 0.9393421052631579
       name: accuracy
 ---
 
@@ -34,7 +34,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [Giyaseddin/distilroberta-base-finetuned-short-answer-assessment](https://huggingface.co/Giyaseddin/distilroberta-base-finetuned-short-answer-assessment) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.9380
+- accuracy: 0.9393
 
 ## Model description
 
@@ -66,10 +66,10 @@ The following hyperparameters were used during training:
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
 | 0.2353   | None       | 0     |
-| 0.9272   | 0.2719     | 0     |
-| 0.9338   | 0.2100     | 1     |
-| 0.9357   | 0.1927     | 2     |
-| 0.9380   | 0.1800     | 3     |
+| 0.9270   | 0.2729     | 0     |
+| 0.9320   | 0.2095     | 1     |
+| 0.9359   | 0.1934     | 2     |
+| 0.9393   | 0.1812     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ddb775cb729167cb624dfe11fa301b00c20e4f851709d47ce4911b5f98a36a1
+oid sha256:179a2ebfdd3d42b690e33c0d8823624a2feb2c1be66d4b7a81d7029121baf5e2
 size 2452296