Training complete

README.md

@@ -20,10 +20,10 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [samrawal/bert-base-uncased_clinical-ner](https://huggingface.co/samrawal/bert-base-uncased_clinical-ner) on an unknown dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4144
-- Precision: 0.5375
-- Recall: 0.6260
-- F1: 0.5784
-- Accuracy: 0.8515
+- Precision: 0.5379
+- Recall: 0.6266
+- F1: 0.5789
+- Accuracy: 0.8522
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 188  | 0.4339          | 0.5159    | 0.5879 | 0.5495 | 0.8408   |
-| No log        | 2.0   | 376  | 0.4094          | 0.5344    | 0.6332 | 0.5796 | 0.8501   |
-| 0.4154        | 3.0   | 564  | 0.4144          | 0.5375    | 0.6260 | 0.5784 | 0.8515   |
+| No log        | 1.0   | 188  | 0.4360          | 0.5166    | 0.5835 | 0.5480 | 0.8411   |
+| No log        | 2.0   | 376  | 0.4066          | 0.5414    | 0.6322 | 0.5833 | 0.8521   |
+| 0.4136        | 3.0   | 564  | 0.4144          | 0.5379    | 0.6266 | 0.5789 | 0.8522   |
 
 
 ### Framework versions