Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.8222368421052632
+      value: 0.8123684210526316
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [isakbos/Q8BERT_COLA_L_512](https://huggingface.co/isakbos/Q8BERT_COLA_L_512) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.8222
+- accuracy: 0.8124
 
 ## Model description
 
@@ -65,10 +65,10 @@ The following hyperparameters were used during training:
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
 | 0.25     | None       | 0     |
-| 0.7509   | 0.9367     | 0     |
-| 0.8039   | 0.6569     | 1     |
-| 0.8137   | 0.5825     | 2     |
-| 0.8222   | 0.5487     | 3     |
+| 0.6913   | 0.9180     | 0     |
+| 0.7762   | 0.7005     | 1     |
+| 0.8071   | 0.6103     | 2     |
+| 0.8124   | 0.5700     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e6b6cc5f423cefc28d9c7ebacbc5fd64995c80cab08056d2eb913f7580d04e4
+oid sha256:df8deddcdffe8a53dc2d71a55b6fcc403c9773cf48a0911d7f2ce70be22c8f3a
 size 166552