Training complete

README.md

@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-base-case-ner
 
-Este es un modelo de finetuning sobre  [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) sobre el dataset anotado  conll2002.
-El entrenamiento de este modelo base de BERT logra los siguientes resultados:
-- Loss: 0.1488
-- Precision: 0.7247
-- Recall: 0.7808
-- F1: 0.7517
-- Accuracy: 0.9651
+This model is a fine-tuned version of [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1733
+- Precision: 0.7598
+- Recall: 0.8054
+- F1: 0.7819
+- Accuracy: 0.9670
 
 ## Model description
 
@@ -49,15 +49,17 @@ 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: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.1039        | 1.0   | 1041 | 0.1555          | 0.7053    | 0.7502 | 0.7271 | 0.9586   |
-| 0.068         | 2.0   | 2082 | 0.1389          | 0.7195    | 0.7868 | 0.7516 | 0.9638   |
-| 0.0429        | 3.0   | 3123 | 0.1488          | 0.7247    | 0.7808 | 0.7517 | 0.9651   |
+| 0.1049        | 1.0   | 1041 | 0.1568          | 0.7038    | 0.7383 | 0.7206 | 0.9582   |
+| 0.069         | 2.0   | 2082 | 0.1487          | 0.6969    | 0.7714 | 0.7322 | 0.9623   |
+| 0.0426        | 3.0   | 3123 | 0.1424          | 0.7563    | 0.8008 | 0.7779 | 0.9676   |
+| 0.0271        | 4.0   | 4164 | 0.1594          | 0.7604    | 0.7948 | 0.7772 | 0.9666   |
+| 0.022         | 5.0   | 5205 | 0.1733          | 0.7598    | 0.8054 | 0.7819 | 0.9670   |
 
 
 ### Framework versions