End of training

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2816
-- Accuracy: 0.9196
-- F1: 0.9437
+- Loss: 0.3200
+- Accuracy: 0.8906
+- F1: 0.9212
 
 ## Model description
 
@@ -51,11 +51,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.4227        | 1.0   | 574  | 0.2411          | 0.9108   | 0.9390 |
-| 0.2574        | 2.0   | 1148 | 0.2203          | 0.9196   | 0.9434 |
-| 0.2273        | 3.0   | 1722 | 0.2734          | 0.9098   | 0.9358 |
-| 0.2048        | 4.0   | 2296 | 0.2758          | 0.9186   | 0.9431 |
-| 0.1746        | 5.0   | 2870 | 0.2816          | 0.9196   | 0.9437 |
+| No log        | 1.0   | 160  | 0.3912          | 0.8609   | 0.9046 |
+| No log        | 2.0   | 320  | 0.3005          | 0.8875   | 0.9167 |
+| No log        | 3.0   | 480  | 0.3223          | 0.8891   | 0.9175 |
+| 0.3952        | 4.0   | 640  | 0.3336          | 0.8859   | 0.9140 |
+| 0.3952        | 5.0   | 800  | 0.3200          | 0.8906   | 0.9212 |
 
 
 ### Framework versions

runs/Jul24_18-10-42_b5d7431e8508/events.out.tfevents.1721844695.b5d7431e8508.5520.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ee54e1ef11509143c44424fec3137a9adf4d19385c673a35a6e9e4f5e0d4bb4
-size 6633
+oid sha256:f2663882bd4b6aa3970c1c5f8e644dc04e0fa4ce9fb8e9a690df5dd252704339
+size 7356