Finished training.

README.md

@@ -22,7 +22,7 @@ model-index:
       args: default
     metrics:
     - type: accuracy
-      value: 0.8830263157894737
+      value: 0.8855263157894737
       name: accuracy
 ---
 
@@ -33,7 +33,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [nreimers/mmarco-mMiniLMv2-L6-H384-v1](https://huggingface.co/nreimers/mmarco-mMiniLMv2-L6-H384-v1) on the ag_news dataset.
 It achieves the following results on the evaluation set:
-- accuracy: 0.8830
+- accuracy: 0.8855
 
 ## Model description
 
@@ -64,11 +64,11 @@ The following hyperparameters were used during training:
 
 | accuracy | train_loss | epoch |
 |:--------:|:----------:|:-----:|
-| 0.2730   | None       | 0     |
-| 0.8632   | 0.5627     | 0     |
-| 0.8746   | 0.3869     | 1     |
-| 0.8818   | 0.3592     | 2     |
-| 0.8830   | 0.3477     | 3     |
+| 0.1899   | None       | 0     |
+| 0.8628   | 0.5739     | 0     |
+| 0.8761   | 0.3828     | 1     |
+| 0.8841   | 0.3557     | 2     |
+| 0.8855   | 0.3432     | 3     |
 
 
 ### Framework versions

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f947fb63a4fd06b837c7eb4ed7b510351ad475fcdd25c2404b15c48d7d89407
+oid sha256:d55ab8edbfe7391592cf2f1e3f6498cad99ff572bf6fc284b069c65b17ad6939
 size 638224