End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8493006993006993
+      value: 0.8735552872175263
     - name: Recall
       type: recall
-      value: 0.8601274787535411
+      value: 0.896600566572238
     - name: F1
       type: f1
-      value: 0.854679802955665
+      value: 0.8849279161205766
     - name: Accuracy
       type: accuracy
-      value: 0.9687950899106278
+      value: 0.9755572305373102
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [dslim/distilbert-NER](https://huggingface.co/dslim/distilbert-NER) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Precision: 0.8493
-- Recall: 0.8601
-- F1: 0.8547
-- Accuracy: 0.9688
+- Loss: 0.1932
+- Precision: 0.8736
+- Recall: 0.8966
+- F1: 0.8849
+- Accuracy: 0.9756
 
 ## Model description
 
@@ -79,8 +79,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0901        | 1.0   | 3922 | nan             | 0.8591    | 0.8656 | 0.8623 | 0.9706   |
-| 0.0498        | 2.0   | 7844 | nan             | 0.8493    | 0.8601 | 0.8547 | 0.9688   |
+| 0.0567        | 1.0   | 3922 | 0.1809          | 0.8698    | 0.8904 | 0.8800 | 0.9750   |
+| 0.0245        | 2.0   | 7844 | 0.1932          | 0.8736    | 0.8966 | 0.8849 | 0.9756   |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb87394da29510f4313357e9cd9e7a478f8ef10068accfd773efdf184a4f1bd
+oid sha256:b324c73ec766fe7a16234db66602009d0c409c4065420c424440f1d1ebce49e0
 size 260825186