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: 0.3476
-- F1 Macro: 0.8986
-- F1: 0.9326
-- F1 Neg: 0.8647
-- Acc: 0.91
-- Prec: 0.9396
-- Recall: 0.9257
-- Mcc: 0.7975
+- Loss: 0.4187
+- F1 Macro: 0.8891
+- F1: 0.9276
+- F1 Neg: 0.8506
+- Acc: 0.9025
+- Prec: 0.9259
+- Recall: 0.9294
+- Mcc: 0.7782
 
 ## Model description
 
@@ -58,9 +58,9 @@ The following hyperparameters were used during training:
 
 | 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 |
+| No log        | 1.0   | 400  | 0.3327          | 0.8398   | 0.8967 | 0.7829 | 0.86   | 0.8497 | 0.9492 | 0.6918 |
+| 0.4224        | 2.0   | 800  | 0.3854          | 0.8875   | 0.9210 | 0.8541 | 0.8975 | 0.9087 | 0.9336 | 0.7757 |
+| 0.2483        | 3.0   | 1200 | 0.4423          | 0.8956   | 0.9269 | 0.8643 | 0.905  | 0.9129 | 0.9414 | 0.7921 |
 
 
 ### Framework versions