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 [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0771
-- Precision: 0.9366
-- Recall: 0.9525
-- F1: 0.9445
-- Accuracy: 0.9867
+- Loss: 0.0626
+- Precision: 0.9338
+- Recall: 0.9498
+- F1: 0.9418
+- Accuracy: 0.9864
 
 ## Model description
 
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0165        | 1.0   | 1756 | 0.0790          | 0.9256    | 0.9458 | 0.9356 | 0.9849   |
-| 0.0106        | 2.0   | 3512 | 0.0805          | 0.9323    | 0.9482 | 0.9402 | 0.9857   |
-| 0.0112        | 3.0   | 5268 | 0.0771          | 0.9366    | 0.9525 | 0.9445 | 0.9867   |
+| 0.0751        | 1.0   | 1756 | 0.0595          | 0.9048    | 0.9345 | 0.9194 | 0.9832   |
+| 0.0338        | 2.0   | 3512 | 0.0645          | 0.9311    | 0.9467 | 0.9388 | 0.9859   |
+| 0.0222        | 3.0   | 5268 | 0.0626          | 0.9338    | 0.9498 | 0.9418 | 0.9864   |
 
 
 ### Framework versions

tokenizer.json

@@ -1,7 +1,14 @@
 {
   "version": "1.0",
   "truncation": null,
-  "padding": null,
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,