End of training

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: F1
       type: f1
-      value: 0.9217078065402075
+      value: 0.9306532666842113
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the banking77 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3238
-- F1: 0.9217
+- Loss: 0.3035
+- F1: 0.9307
 
 ## Model description
 
@@ -64,9 +64,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 1.127         | 1.0   | 626  | 0.8050          | 0.8458 |
-| 0.4037        | 2.0   | 1252 | 0.3914          | 0.9121 |
-| 0.1982        | 3.0   | 1878 | 0.3238          | 0.9217 |
+| 1.1806        | 1.0   | 626  | 0.8316          | 0.8522 |
+| 0.3958        | 2.0   | 1252 | 0.3743          | 0.9190 |
+| 0.1875        | 3.0   | 1878 | 0.3035          | 0.9307 |
 
 
 ### Framework versions

logs/events.out.tfevents.1697975513.2be8100f72b4.5371.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec486782a85a05e9fc635b132a0be9968b5e4d5bcfd0967a7af02a300146f1b
-size 11615
+oid sha256:d1b809b66df2d8ae54637040410af5f27da356d50442653a1fbb6f649b70fd2b
+size 11969