Commit 1

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: 0.0609
-- Precision: 0.9387
-- Recall: 0.9517
-- F1: 0.9452
-- Accuracy: 0.9869
+- Loss: 0.2040
+- Precision: 0.8009
+- Recall: 0.8341
+- F1: 0.8171
+- Accuracy: 0.9414
 
 ## Model description
 
@@ -53,11 +53,11 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0806        | 1.0   | 1756 | 0.0714          | 0.9103    | 0.9357 | 0.9228 | 0.9821   |
-| 0.0405        | 2.0   | 3512 | 0.0578          | 0.9288    | 0.9487 | 0.9386 | 0.9862   |
-| 0.0243        | 3.0   | 5268 | 0.0609          | 0.9387    | 0.9517 | 0.9452 | 0.9869   |
+| Training Loss | Epoch | Step  | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.1983        | 1.0   | 16471 | 0.1868          | 0.7919    | 0.8142 | 0.8029 | 0.9382   |
+| 0.1527        | 2.0   | 32942 | 0.1889          | 0.7951    | 0.8344 | 0.8143 | 0.9406   |
+| 0.1142        | 3.0   | 49413 | 0.2040          | 0.8009    | 0.8341 | 0.8171 | 0.9414   |
 
 
 ### Framework versions