Model save

README.md

@@ -18,14 +18,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3742
-- F1 Macro: 0.8982
-- F1: 0.9328
-- F1 Neg: 0.8636
+- Loss: 0.3476
+- F1 Macro: 0.8986
+- F1: 0.9326
+- F1 Neg: 0.8647
 - Acc: 0.91
-- Prec: 0.9363
-- Recall: 0.9294
-- Mcc: 0.7965
+- Prec: 0.9396
+- Recall: 0.9257
+- Mcc: 0.7975
 
 ## Model description
 
@@ -56,11 +56,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc   | Prec   | Recall | Mcc    |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:-----:|:------:|:------:|:------:|
-| No log        | 1.0   | 400  | 0.4954          | 0.7896   | 0.8759 | 0.7034 | 0.825 | 0.8019 | 0.9648 | 0.6173 |
-| 0.4294        | 2.0   | 800  | 0.4126          | 0.8709   | 0.9135 | 0.8284 | 0.885 | 0.8804 | 0.9492 | 0.7473 |
-| 0.2622        | 3.0   | 1200 | 0.4557          | 0.8779   | 0.9163 | 0.8394 | 0.89  | 0.8926 | 0.9414 | 0.7584 |
+| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1     | F1 Neg | Acc    | Prec   | Recall | Mcc    |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:------:|:------:|:------:|:------:|
+| No log        | 1.0   | 400  | 0.6003          | 0.7473   | 0.8654 | 0.6291 | 0.8025 | 0.7674 | 0.9922 | 0.5812 |
+| 0.4396        | 2.0   | 800  | 0.3386          | 0.8839   | 0.9155 | 0.8522 | 0.8925 | 0.9209 | 0.9102 | 0.7679 |
+| 0.2546        | 3.0   | 1200 | 0.3809          | 0.8982   | 0.9290 | 0.8674 | 0.9075 | 0.9132 | 0.9453 | 0.7975 |
 
 
 ### Framework versions