Training complete

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3022
-- Precision: 0.5119
-- Recall: 0.6335
-- F1: 0.5663
-- Accuracy: 0.9109
+- Loss: 0.3032
+- Precision: 0.4930
+- Recall: 0.5856
+- F1: 0.5354
+- Accuracy: 0.9049
 
 ## Model description
 
@@ -53,9 +53,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 18   | 0.3172          | 0.5214    | 0.6722 | 0.5873 | 0.9119   |
-| No log        | 2.0   | 36   | 0.2945          | 0.5099    | 0.6169 | 0.5583 | 0.9102   |
-| No log        | 3.0   | 54   | 0.3022          | 0.5119    | 0.6335 | 0.5663 | 0.9109   |
+| No log        | 1.0   | 18   | 0.4004          | 0.4339    | 0.4475 | 0.4406 | 0.8762   |
+| No log        | 2.0   | 36   | 0.3122          | 0.4649    | 0.5120 | 0.4873 | 0.9009   |
+| No log        | 3.0   | 54   | 0.3032          | 0.4930    | 0.5856 | 0.5354 | 0.9049   |
 
 
 ### Framework versions