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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6543
-- Accuracy: 0.7228
+- Loss: 0.6560
+- Accuracy: 0.7250
 
 ## Model description
 
@@ -43,7 +43,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 7
+- num_epochs: 8
 
 ### Training results
 
@@ -55,7 +55,8 @@ The following hyperparameters were used during training:
 | 0.5696        | 4.0   | 1080 | 0.7185   | 0.6674          |
 | 0.5696        | 5.0   | 1350 | 0.7136   | 0.6607          |
 | 0.49          | 6.0   | 1620 | 0.7206   | 0.6531          |
-| 0.49          | 7.0   | 1890 | 0.6543   | 0.7228          |
+| 0.49          | 7.0   | 1890 | 0.7228   | 0.6543          |
+| 0.4287        | 8.0   | 2160 | 0.6560   | 0.7250          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aec08c9fcc700473b8a767c9244cd1740eeb65bc8d2e3888748fe3e175936ed
+oid sha256:b00f7a5c6942228b9d5d1b47c9e952b383623bf2ab6d5839c7df3a0deb262a66
 size 267835644