Completed Extreme Recall Training

README.md

@@ -19,11 +19,11 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9888
-- F1 At 10 Thresh: 0.7506
-- Recall: 0.9771
-- Precision: 0.6094
-- Trash Caught: 0.1692
+- Loss: 2.5903
+- F1 At 10 Thresh: 0.7458
+- Recall: 0.9755
+- Precision: 0.6037
+- Trash Caught: 0.1505
 
 ## Model description
 
@@ -42,7 +42,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 32
 - seed: 42
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | F1 At 10 Thresh | Recall | Precision | Trash Caught |
 |:-------------:|:-----:|:----:|:---------------:|:---------------:|:------:|:---------:|:------------:|
-| 0.0689        | 1.0   | 1569 | 2.2385          | 0.7263          | 1.0    | 0.5702    | 0.0          |
-| 0.0442        | 2.0   | 3138 | 2.5268          | 0.7449          | 0.9815 | 0.6002    | 0.1327       |
-| 0.0331        | 3.0   | 4707 | 2.9888          | 0.7506          | 0.9771 | 0.6094    | 0.1692       |
+| 0.1278        | 1.0   | 1569 | 1.9497          | 0.7399          | 0.9799 | 0.5943    | 0.1127       |
+| 0.088         | 2.0   | 3138 | 2.0562          | 0.7431          | 0.9655 | 0.6039    | 0.1601       |
+| 0.0619        | 3.0   | 4707 | 2.5903          | 0.7458          | 0.9755 | 0.6037    | 0.1505       |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4e797974e78b9a35a1967b13e807bec86090087e750eca54b04c5efbd0adae1
+oid sha256:e46cd9f47159ff85e682614856526d089cf27e7bb8a452d21bf15ec473d4a1f2
 size 567300568