End of training

README.md

@@ -25,16 +25,16 @@ model-index:
     metrics:
     - name: Precision
       type: precision
-      value: 0.8242280285035629
+      value: 0.8253343823760818
     - name: Recall
       type: recall
-      value: 0.8497959183673469
+      value: 0.856326530612245
     - name: F1
       type: f1
-      value: 0.8368167202572347
+      value: 0.8405448717948719
     - name: Accuracy
       type: accuracy
-      value: 0.9820508183380052
+      value: 0.9829550592277783
 ---
 
 <!-- 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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the szeged_ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0620
-- Precision: 0.8242
-- Recall: 0.8498
-- F1: 0.8368
-- Accuracy: 0.9821
+- Loss: 0.0590
+- Precision: 0.8253
+- Recall: 0.8563
+- F1: 0.8405
+- Accuracy: 0.9830
 
 ## Model description
 
@@ -79,8 +79,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.2234        | 1.0   | 511  | 0.0747          | 0.8070    | 0.8261 | 0.8165 | 0.9795   |
-| 0.087         | 2.0   | 1022 | 0.0620          | 0.8242    | 0.8498 | 0.8368 | 0.9821   |
+| 0.2068        | 1.0   | 511  | 0.0724          | 0.8008    | 0.8237 | 0.8121 | 0.9797   |
+| 0.0835        | 2.0   | 1022 | 0.0590          | 0.8253    | 0.8563 | 0.8405 | 0.9830   |
 
 
 ### Framework versions