update model card README.md

README.md

@@ -19,10 +19,10 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0004
-- Accuracy: 0.7739
-- F1: 0.8408
-- Precision: 0.7254
+- Loss: 0.0002
+- Accuracy: 0.8923
+- F1: 0.9167
+- Precision: 0.8462
 - Recall: 1.0
 
 ## Model description
@@ -49,13 +49,15 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
-| 0.0013        | 1.0   | 1956 | 0.0004          | 0.7739   | 0.8408 | 0.7254    | 1.0    |
+| 0.0026        | 1.0   | 1956 | 0.0003          | 0.9552   | 0.9636 | 0.9298    | 1.0    |
+| 0.0015        | 2.0   | 3912 | 0.0003          | 0.6688   | 0.7815 | 0.6416    | 0.9996 |
+| 0.0011        | 3.0   | 5868 | 0.0002          | 0.8923   | 0.9167 | 0.8462    | 1.0    |
 
 
 ### Framework versions