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: 0.4152
-- F1 Macro: 0.8830
-- F1: 0.9242
-- F1 Neg: 0.8417
-- Acc: 0.8975
-- Prec: 0.9191
-- Recall: 0.9294
-- Mcc: 0.7660
+- Loss: 0.3910
+- F1 Macro: 0.8945
+- F1: 0.9278
+- F1 Neg: 0.8613
+- Acc: 0.905
+- Prec: 0.9494
+- Recall: 0.9071
+- Mcc: 0.7910
 
 ## 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  | 0.4989          | 0.7731   | 0.8735 | 0.6726 | 0.8175 | 0.7850 | 0.9844 | 0.6091 |
-| 0.4265        | 2.0   | 800  | 0.3927          | 0.8817   | 0.9175 | 0.8459 | 0.8925 | 0.9019 | 0.9336 | 0.7644 |
-| 0.2452        | 3.0   | 1200 | 0.4323          | 0.8901   | 0.9231 | 0.8571 | 0.9    | 0.9091 | 0.9375 | 0.7811 |
+| No log        | 1.0   | 400  | 0.3361          | 0.8398   | 0.8967 | 0.7829 | 0.86   | 0.8497 | 0.9492 | 0.6918 |
+| 0.4176        | 2.0   | 800  | 0.3484          | 0.8845   | 0.9149 | 0.8542 | 0.8925 | 0.9277 | 0.9023 | 0.7697 |
+| 0.2332        | 3.0   | 1200 | 0.4062          | 0.9023   | 0.9297 | 0.875  | 0.91   | 0.9297 | 0.9297 | 0.8047 |
 
 
 ### Framework versions