End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3065
+- Loss: 0.3246
 
 ## Model description
 
@@ -40,14 +40,15 @@ 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: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss |
 |:-------------:|:-----:|:-----:|:---------------:|
-| 0.3275        | 1.0   | 8496  | 0.3131          |
-| 0.2813        | 2.0   | 16992 | 0.3065          |
+| 0.3204        | 1.0   | 8354  | 0.3232          |
+| 0.2927        | 2.0   | 16708 | 0.3034          |
+| 0.2492        | 3.0   | 25062 | 0.3246          |
 
 
 ### Framework versions

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba16d06fb263ff256f4db2902c17f71e7994892106b362baff482e7905498fd9
+oid sha256:8b43c8ff782357122ef9bd112cb3d050aa2b1485122c6be9db313726726808b9
 size 263167661