update model card README.md

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2941
-- Precision: 0.3955
-- Recall: 0.5486
-- F1: 0.4596
-- Accuracy: 0.9323
+- Loss: 0.2976
+- Precision: 0.4183
+- Recall: 0.5546
+- F1: 0.4769
+- Accuracy: 0.9343
 
 ## Model description
 
@@ -48,15 +48,14 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 19   | 0.3101          | 0.3553    | 0.5725 | 0.4385 | 0.9236   |
-| No log        | 2.0   | 38   | 0.2725          | 0.4236    | 0.5262 | 0.4693 | 0.9370   |
-| No log        | 3.0   | 57   | 0.2941          | 0.3955    | 0.5486 | 0.4596 | 0.9323   |
+| No log        | 1.0   | 19   | 0.2900          | 0.3809    | 0.5710 | 0.4569 | 0.9285   |
+| No log        | 2.0   | 38   | 0.2976          | 0.4183    | 0.5546 | 0.4769 | 0.9343   |
 
 
 ### Framework versions