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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0978
-- Precision: 0.8382
-- Recall: 0.8906
-- F1: 0.8636
-- Accuracy: 0.9743
+- Loss: 0.1008
+- Precision: 0.8322
+- Recall: 0.8872
+- F1: 0.8588
+- Accuracy: 0.9729
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 176  | 0.1604          | 0.75      | 0.7865 | 0.7678 | 0.9554   |
-| No log        | 2.0   | 352  | 0.1005          | 0.8293    | 0.8854 | 0.8564 | 0.9720   |
-| 0.2323        | 3.0   | 528  | 0.0978          | 0.8382    | 0.8906 | 0.8636 | 0.9743   |
+| No log        | 1.0   | 176  | 0.1623          | 0.7443    | 0.7986 | 0.7705 | 0.9561   |
+| No log        | 2.0   | 352  | 0.1076          | 0.8138    | 0.8802 | 0.8457 | 0.9698   |
+| 0.2353        | 3.0   | 528  | 0.1008          | 0.8322    | 0.8872 | 0.8588 | 0.9729   |
 
 
 ### Framework versions