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: 0.0166
-- F1 Macro: 0.9972
-- F1: 0.9981
-- F1 Neg: 0.9964
-- Acc: 0.9975
+- Loss: 0.0183
+- F1 Macro: 0.9959
+- F1: 0.9971
+- F1 Neg: 0.9946
+- Acc: 0.9962
 - Prec: 1.0
-- Recall: 0.9962
-- Mcc: 0.9945
+- Recall: 0.9943
+- Mcc: 0.9917
 
 ## Model description
 
@@ -56,16 +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  | 0.0222          | 0.9945   | 0.9962 | 0.9928 | 0.995  | 0.9981 | 0.9943 | 0.9890 |
-| 0.0924        | 2.0   | 800  | 0.0128          | 0.9972   | 0.9981 | 0.9964 | 0.9975 | 0.9981 | 0.9981 | 0.9945 |
-| 0.0377        | 3.0   | 1200 | 0.0166          | 0.9972   | 0.9981 | 0.9964 | 0.9975 | 1.0    | 0.9962 | 0.9945 |
 
 
 ### Framework versions
 
-- Transformers 4.37.2
-- Pytorch 2.2.0+cu121
-- Datasets 2.16.1
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
 - Tokenizers 0.15.2