Model save

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: 0.2099
-- Precision: 0.3678
-- Recall: 0.4479
-- F1: 0.4039
-- Accuracy: 0.9307
+- Loss: 0.2268
+- Precision: 0.3501
+- Recall: 0.4031
+- F1: 0.3747
+- Accuracy: 0.9263
 
 ## 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   | 100  | 0.2407          | 0.2507    | 0.2982 | 0.2724 | 0.9194   |
-| No log        | 2.0   | 200  | 0.2142          | 0.3712    | 0.4199 | 0.3941 | 0.9299   |
-| No log        | 3.0   | 300  | 0.2099          | 0.3678    | 0.4479 | 0.4039 | 0.9307   |
+| No log        | 1.0   | 88   | 0.2544          | 0.2549    | 0.2954 | 0.2737 | 0.9184   |
+| No log        | 2.0   | 176  | 0.2342          | 0.3342    | 0.3992 | 0.3638 | 0.9235   |
+| No log        | 3.0   | 264  | 0.2268          | 0.3501    | 0.4031 | 0.3747 | 0.9263   |
 
 
 ### Framework versions