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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7500
-- Matthews Correlation: 0.5391
+- Loss: 1.0243
+- Matthews Correlation: 0.4896
 
 ## Model description
 
@@ -37,23 +37,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
+- learning_rate: 2.4503901752406154e-05
+- train_batch_size: 4
 - eval_batch_size: 16
-- seed: 42
+- seed: 11
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5184        | 1.0   | 535  | 0.4484          | 0.4500               |
-| 0.3421        | 2.0   | 1070 | 0.4663          | 0.5158               |
-| 0.2347        | 3.0   | 1605 | 0.6697          | 0.5126               |
-| 0.158         | 4.0   | 2140 | 0.7500          | 0.5391               |
-| 0.1219        | 5.0   | 2675 | 0.8446          | 0.5321               |
+| 0.5604        | 1.0   | 2138 | 0.5529          | 0.4471               |
+| 0.4503        | 2.0   | 4276 | 0.8003          | 0.5166               |
+| 0.2792        | 3.0   | 6414 | 1.0243          | 0.4896               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10425bd7dbfd09e13f0a50ef5d196ea0174d4383837b86a489605ae63579ade3
+oid sha256:e59a3a9959ed5c9ef756be9972e0a308d6775bc0b2d9bff9bd37c11f353874d1
 size 267832560