Completed Filter Training With Correct Test Set

README.md

@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.1566
-- F1: 0.0678
+- Loss: 3.7990
+- F1: 0.0622
 - Recall: 1.0
-- Precision: 0.0351
-- Trash Caught: 0.2431
+- Precision: 0.0321
+- Trash Caught: 0.1697
 
 ## Model description
 
@@ -43,7 +43,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 5e-06
 - train_batch_size: 16
 - eval_batch_size: 32
 - seed: 42
@@ -55,9 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1     | Recall | Precision | Trash Caught |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|:------------:|
-| 0.2949        | 1.0   | 665  | 3.4996          | 0.0522 | 1.0    | 0.0268    | 0.0          |
-| 0.1957        | 2.0   | 1330 | 2.6878          | 0.0602 | 0.8333 | 0.0312    | 0.2890       |
-| 0.1554        | 3.0   | 1995 | 3.1566          | 0.0678 | 1.0    | 0.0351    | 0.2431       |
+| 0.3358        | 1.0   | 665  | 4.1594          | 0.0522 | 1.0    | 0.0268    | 0.0          |
+| 0.205         | 2.0   | 1330 | 3.7498          | 0.0571 | 1.0    | 0.0294    | 0.0917       |
+| 0.1749        | 3.0   | 1995 | 3.6786          | 0.0588 | 1.0    | 0.0303    | 0.1193       |
+| 0.1446        | 4.0   | 2660 | 4.0665          | 0.0594 | 1.0    | 0.0306    | 0.1284       |
+| 0.1422        | 5.0   | 3325 | 3.7990          | 0.0622 | 1.0    | 0.0321    | 0.1697       |
 
 
 ### Framework versions