Model save

README.md

@@ -15,10 +15,10 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5716
-- Icm: 0.1185
-- Icmnorm: 0.5602
-- Fmeasure: 0.7096
+- Loss: 0.7353
+- Icm: 0.1069
+- Icmnorm: 0.5542
+- Fmeasure: 0.7011
 
 ## Model description
 
@@ -51,9 +51,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Icm     | Icmnorm | Fmeasure |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:--------:|
-| No log        | 1.0   | 193  | 0.6638          | -0.4059 | 0.2938  | 0.3647   |
-| No log        | 2.0   | 386  | 0.5637          | -0.0203 | 0.4897  | 0.6511   |
-| 0.6281        | 3.0   | 579  | 0.5716          | 0.1185  | 0.5602  | 0.7096   |
+| No log        | 1.0   | 193  | 0.5957          | -0.1844 | 0.4065  | 0.5965   |
+| No log        | 2.0   | 386  | 0.6312          | -0.0556 | 0.4718  | 0.6305   |
+| 0.5023        | 3.0   | 579  | 0.7353          | 0.1069  | 0.5542  | 0.7011   |
 
 
 ### Framework versions