Training complete

README.md

@@ -11,7 +11,7 @@ metrics:
 - f1
 - accuracy
 model-index:
-- name: bert-finetuned-ner
+- name: bert-finetuned-ner-accelerate
   results:
   - task:
       name: Token Classification
@@ -25,30 +25,30 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.9309661436829066
+      value: 0.9354304635761589
     - name: Recall
       type: recall
-      value: 0.9486704813194211
+      value: 0.9508582968697409
     - name: F1
       type: f1
-      value: 0.9397349337334334
+      value: 0.9430812885995661
     - name: Accuracy
       type: accuracy
-      value: 0.9858273974215577
+      value: 0.9866809913463237
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# bert-finetuned-ner
+# bert-finetuned-ner-accelerate
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0629
-- Precision: 0.9310
-- Recall: 0.9487
-- F1: 0.9397
-- Accuracy: 0.9858
+- Loss: 0.0797
+- Precision: 0.9354
+- Recall: 0.9509
+- F1: 0.9431
+- Accuracy: 0.9867
 
 ## Model description
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0791        | 1.0   | 1756 | 0.0877          | 0.8995    | 0.9291 | 0.9141 | 0.9777   |
-| 0.0388        | 2.0   | 3512 | 0.0570          | 0.9287    | 0.9470 | 0.9378 | 0.9856   |
-| 0.0245        | 3.0   | 5268 | 0.0629          | 0.9310    | 0.9487 | 0.9397 | 0.9858   |
+| 0.0211        | 1.0   | 1756 | 0.0741          | 0.9254    | 0.9443 | 0.9348 | 0.9851   |
+| 0.0126        | 2.0   | 3512 | 0.0741          | 0.9331    | 0.9485 | 0.9407 | 0.9862   |
+| 0.0084        | 3.0   | 5268 | 0.0797          | 0.9354    | 0.9509 | 0.9431 | 0.9867   |
 
 
 ### Framework versions