Update README.md

README.md

@@ -32,10 +32,10 @@ This medical named entity recognition model detects 7 types of semantic groups f
 - PROC: diagnostic and therapeutic procedures, laboratory analyses and medical research activities (e.g. *cirugía*, 'surgery')
 
 The model achieves the following results on the test set (when trained with the training and development set; results are averaged over 5 evaluation rounds):
-- Precision: 0.876 (±0.003)
-- Recall: 0.895 (±0.001)
-- F1: 0.885 (±0.001)
-- Accuracy: 0.960 (±0.001)
+- Precision: 0.878 (±0.003)
+- Recall: 0.894 (±0.003)
+- F1: 0.886 (±0.002)
+- Accuracy: 0.961 (±0.001)
 
 
 ## Model description
@@ -98,27 +98,27 @@ The following hyperparameters were used during training:
 - seed: we used different seeds for 5 evaluation rounds, and uploaded the model with the best results
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 12 
+- num_epochs: average 17 epochs (±2.83); trained with early stopping if no improvement after 5 epochs (early stopping patience: 5)
 
 
 ### Training results (test set; average and standard deviation of 5 rounds with different seeds)
 
 |   Precision    |     Recall     |       F1       |    Accuracy    |
 |:--------------:|:--------------:|:--------------:|:--------------:|
-| 0.876 (±0.003) | 0.895 (±0.001) | 0.885 (±0.001) | 0.960 (±0.001) |
+| 0.878 (±0.003) | 0.894 (±0.003) | 0.886 (±0.002) | 0.961 (±0.001) |
 
 
 **Results per class (test set; average and standard deviation of 5 rounds with different seeds)**  
 
 | Class      |   Precision    |     Recall     |       F1       |  Support  |
 |:----------:|:--------------:|:--------------:|:--------------:|:---------:|
-| ANAT       | 0.726 (±0.027) | 0.695 (±0.019) | 0.710 (±0.018) |    307    |
-| CHEM       | 0.910 (±0.009) | 0.927 (±0.006) | 0.918 (±0.003) |   2932    |
-| DEVI       | 0.647 (±0.023) | 0.810 (±0.019) | 0.719 (±0.021) |    134    |
-| DISO       | 0.891 (±0.005) | 0.898 (±0.002) | 0.894 (±0.002) |   3064    |
-| LIVB       | 0.943 (±0.004) | 0.956 (±0.006) | 0.949 (±0.002) |   1671    |
-| PHYS       | 0.779 (±0.008) | 0.760 (±0.018) | 0.769 (±0.009) |    308    |
-| PROC       | 0.841 (±0.007) | 0.874 (±0.005) | 0.857 (±0.004) |   4150    |
+| ANAT       | 0.728 (±0.030) | 0.686 (±0.030) | 0.706 (±0.025) |    308    |
+| CHEM       | 0.917 (±0.005) | 0.923 (±0.008) | 0.920 (±0.005) |   2932    |
+| DEVI       | 0.645 (±0.018) | 0.791 (±0.047) | 0.711 (±0.027) |    134    |
+| DISO       | 0.890 (±0.008) | 0.903 (±0.003) | 0.896 (±0.003) |   3065    |
+| LIVB       | 0.949 (±0.004) | 0.959 (±0.006) | 0.954 (±0.003) |   1685    |
+| PHYS       | 0.766 (±0.021) | 0.765 (±0.012) | 0.765 (±0.008) |    308    |
+| PROC       | 0.842 (±0.002) | 0.871 (±0.004) | 0.856 (±0.001) |   4154    |
 
 
 ### Framework versions