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: 0.6374
-- Accuracy: 0.9178
-- F1: 0.9452
+- Loss: 0.7806
+- Accuracy: 0.9044
+- F1: 0.9363
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.0           | 1.0   | 254  | 0.5560          | 0.9022   | 0.9364 |
-| 0.0001        | 2.0   | 508  | 0.6414          | 0.9067   | 0.9375 |
-| 0.0021        | 3.0   | 762  | 0.6436          | 0.9156   | 0.9441 |
-| 0.0558        | 4.0   | 1016 | 0.6374          | 0.9178   | 0.9452 |
+| 0.0           | 1.0   | 254  | 0.6212          | 0.9      | 0.9349 |
+| 0.0249        | 2.0   | 508  | 0.6941          | 0.9133   | 0.9427 |
+| 0.0           | 3.0   | 762  | 0.6842          | 0.9156   | 0.9436 |
+| 0.0113        | 4.0   | 1016 | 0.7806          | 0.9044   | 0.9363 |
 
 
 ### Framework versions

runs/Jun17_04-43-36_a749722ad388/events.out.tfevents.1718600039.a749722ad388.519.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f9a97ead83a9a0b5ec038f7f65af82c16254001ae538b1ec245e5ff49df461
+size 457