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 [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9435
-- Accuracy: 0.9067
-- F1: 0.9381
+- Loss: 0.9900
+- Accuracy: 0.9022
+- F1: 0.9349
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.0445        | 1.0   | 254  | 0.9228          | 0.9044   | 0.9367 |
-| 0.0           | 2.0   | 508  | 0.9299          | 0.9022   | 0.9349 |
-| 0.0001        | 3.0   | 762  | 0.9626          | 0.9022   | 0.9349 |
-| 0.0162        | 4.0   | 1016 | 0.9435          | 0.9067   | 0.9381 |
+| 0.0           | 1.0   | 254  | 1.0037          | 0.9      | 0.9333 |
+| 0.0           | 2.0   | 508  | 1.4253          | 0.88     | 0.9177 |
+| 0.0007        | 3.0   | 762  | 1.1647          | 0.8933   | 0.9281 |
+| 0.0057        | 4.0   | 1016 | 0.9900          | 0.9022   | 0.9349 |
 
 
 ### Framework versions

runs/Jun17_05-13-46_a749722ad388/events.out.tfevents.1718601857.a749722ad388.519.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e13c05cdfd732a0b2c56d23fa21ab90da28ba97c3d753061df91d2b1b219a3f5
+size 457