End of training

README.md

@@ -17,8 +17,8 @@ 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: 0.3612
-- Accuracy: 0.9031
+- Loss: 0.3919
+- Accuracy: 0.9156
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 180  | 0.3510          | 0.8562   |
-| No log        | 2.0   | 360  | 0.2871          | 0.8781   |
-| 0.3882        | 3.0   | 540  | 0.2901          | 0.8969   |
-| 0.3882        | 4.0   | 720  | 0.3236          | 0.8969   |
-| 0.3882        | 5.0   | 900  | 0.3612          | 0.9031   |
+| No log        | 1.0   | 180  | 0.2849          | 0.8906   |
+| No log        | 2.0   | 360  | 0.4328          | 0.8375   |
+| 0.3096        | 3.0   | 540  | 0.2765          | 0.9156   |
+| 0.3096        | 4.0   | 720  | 0.3247          | 0.9125   |
+| 0.3096        | 5.0   | 900  | 0.3919          | 0.9156   |
 
 
 ### Framework versions

runs/Sep04_15-52-10_0ecfd9ff1619/events.out.tfevents.1725465157.0ecfd9ff1619.2927.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e61aff2940a942950f322f8f3aa2e6791dfcc4b13caa0edd1adc791a13846ed
-size 6482
+oid sha256:8abe872093c03199257fbacf3abf0a6cee3783aefab39f97f21d4c2926054820
+size 7159