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-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3350
-- Accuracy: 0.9062
+- Loss: 0.5197
+- Accuracy: 0.9176
 
 ## 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  | 0.2740          | 0.8875   |
-| No log        | 2.0   | 360  | 0.2828          | 0.8875   |
-| 0.3594        | 3.0   | 540  | 0.3322          | 0.8812   |
-| 0.3594        | 4.0   | 720  | 0.3220          | 0.9031   |
-| 0.3594        | 5.0   | 900  | 0.3350          | 0.9062   |
+| 0.3419        | 1.0   | 574  | 0.2332          | 0.9157   |
+| 0.2018        | 2.0   | 1148 | 0.2548          | 0.8990   |
+| 0.1382        | 3.0   | 1722 | 0.3566          | 0.9186   |
+| 0.0986        | 4.0   | 2296 | 0.4599          | 0.9196   |
+| 0.0547        | 5.0   | 2870 | 0.5197          | 0.9176   |
 
 
 ### Framework versions

runs/Sep04_18-59-33_0ecfd9ff1619/events.out.tfevents.1725476389.0ecfd9ff1619.2927.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0e84feeb11cc2df5ee4b2734733435c624110629b034796cd604c3aead03cc
-size 7417
+oid sha256:ea329aac81c9130ee3048d475b7e525aee9d144805f66b34c0937e48a501489a
+size 8094