Training complete

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dslim/bert-large-NER](https://huggingface.co/dslim/bert-large-NER) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3135
-- Precision: 0.5388
-- Recall: 0.7020
-- F1: 0.6096
-- Accuracy: 0.9072
+- Loss: 0.1966
+- Precision: 0.6438
+- Recall: 0.6483
+- F1: 0.6460
+- Accuracy: 0.9478
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 429  | 0.3677          | 0.4476    | 0.6465 | 0.5289 | 0.8761   |
-| 0.5014        | 2.0   | 858  | 0.2789          | 0.5375    | 0.6515 | 0.5890 | 0.9084   |
-| 0.204         | 3.0   | 1287 | 0.3135          | 0.5388    | 0.7020 | 0.6096 | 0.9072   |
+| 0.4628        | 1.0   | 551  | 0.2481          | 0.5940    | 0.5448 | 0.5683 | 0.9326   |
+| 0.2106        | 2.0   | 1102 | 0.1833          | 0.6486    | 0.6621 | 0.6553 | 0.9433   |
+| 0.1434        | 3.0   | 1653 | 0.1966          | 0.6438    | 0.6483 | 0.6460 | 0.9478   |
 
 
 ### Framework versions