Update README.md

README.md

@@ -39,7 +39,7 @@ The model achieves the following results on the test set (when trained with the
 
 This model adapts the pre-trained model [bsc-bio-ehr-es](https://huggingface.co/PlanTL-GOB-ES/bsc-bio-ehr-es), presented in [Pio Carriño et al. (2022)](https://aclanthology.org/2022.bionlp-1.19/). 
 It is fine-tuned to conduct temporal named entity recognition on Spanish texts about clinical trials. 
-The model is fine-tuned on the [CT-EBM-SP corpus (Campillos-Llanos et al. 2021)](https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01395-z).
+The model is fine-tuned on the [CT-EBM-ES corpus (Campillos-Llanos et al. 2021)](https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-021-01395-z).
 
 ## Intended uses & limitations
 
@@ -67,7 +67,7 @@ It is a collection of 1200 texts about clinical trials studies and clinical tria
 - 500 abstracts from journals published under a Creative Commons license, e.g. available in PubMed or the Scientific Electronic Library Online (SciELO)
 - 700 clinical trials announcements published in the European Clinical Trials Register and Repositorio Español de Estudios Clínicos
 
-If you use the CT-EBM-SP resource, please, cite as follows:
+If you use the CT-EBM-ES resource, please, cite as follows:
 
 ```
 @article{campillosetal-midm2021,
@@ -95,25 +95,26 @@ 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: 8 
+- num_epochs: 10 
 
 
 ### Training results (test set; average and standard deviation of 5 rounds with different seeds)
 
 |   Precision    |     Recall     |       F1       |    Accuracy    |
 |:--------------:|:--------------:|:--------------:|:--------------:|
-| 0.975 (±0.001) | 0.984 (±0.001) | 0.980 (±0.001) | 0.999 (±0.001) |
+| 0.884 (±0.011) | 0.893 (±0.010) | 0.888 (±0.009) | 0.995 (±0.001) |
 
 
-**Results per class (test set; average and standard deviation of 5 rounds with different seeds)**  
+** Results per class (test set; average and standard deviation of 5 rounds with different seeds) **  
 
+|:---------:|:--------------:|:--------------:|:--------------:|:---------:|
 | Class     |   Precision    |     Recall     |       F1       |  Support  |
 |:---------:|:--------------:|:--------------:|:--------------:|:---------:|
-| Age       | 0.974 (±0.002) | 0.979 (±0.001) | 0.977 (±0.001) |    634    |
-| Date      | 0.983 (±0.006) | 0.981 (±0.003) | 0.982 (±0.003) |    647    |
-| Duration  | 0.978 (±0.002) | 0.983 (±0.001) | 0.981 (±0.001) |   1164    |
-| Frequency | 0.971 (±0.004) | 0.999 (±0.002) | 0.985 (±0.003) |    292    |
-| Time      | 0.950 (±0.009) | 0.991 (±0.005) | 0.970 (±0.006) |    228    |
+| Age       | 0.905 (±0.016) | 0.920 (±0.011) | 0.912 (±0.013) |    372    |
+| Date      | 0.931 (±0.019) | 0.891 (±0.009) | 0.910 (±0.004) |    412    |
+| Duration  | 0.895 (±0.012) | 0.890 (±0.017) | 0.893 (±0.013) |    622    |
+| Frequency | 0.725 (±0.047) | 0.879 (±0.006) | 0.794 (±0.029) |     73    |
+| Time      | 0.733 (±0.026) | 0.834 (±0.027) | 0.780 (±0.017) |    113    |
 
 
 ### Framework versions