Training complete

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4019
-- Precision: 0.7377
-- Recall: 0.7895
-- F1: 0.7627
-- Accuracy: 0.8852
+- Loss: 0.3999
+- Precision: 0.7515
+- Recall: 0.7934
+- F1: 0.7719
+- Accuracy: 0.8886
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.7616        | 1.0   | 680  | 0.4616          | 0.6658    | 0.7177 | 0.6908 | 0.8550   |
-| 0.4107        | 2.0   | 1360 | 0.4135          | 0.7202    | 0.7696 | 0.7441 | 0.8755   |
-| 0.2543        | 3.0   | 2040 | 0.4019          | 0.7377    | 0.7895 | 0.7627 | 0.8852   |
+| 0.7659        | 1.0   | 680  | 0.4549          | 0.6904    | 0.7061 | 0.6982 | 0.8620   |
+| 0.4146        | 2.0   | 1360 | 0.4111          | 0.7310    | 0.7679 | 0.7490 | 0.8788   |
+| 0.2556        | 3.0   | 2040 | 0.3999          | 0.7515    | 0.7934 | 0.7719 | 0.8886   |
 
 
 ### Framework versions

runs/Jul29_07-48-16_4e059612800c/events.out.tfevents.1722239297.4e059612800c.548.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6e08e6d0829138e6a331630be9964abf422ffc2d77ac9ff454b9ddcadae5681
-size 7701
+oid sha256:c2a04661410916859a973ccee4c7e940ba585204caaeb3dc2700f39a004e4630
+size 8527