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: 0.8456
-- Matthews Correlation: 0.5426
+- Loss: 0.5073
+- Matthews Correlation: 0.5102
 
 ## Model description
 
@@ -37,23 +37,20 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 3.6339690156551746e-05
 - train_batch_size: 16
 - eval_batch_size: 16
-- seed: 42
+- seed: 29
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5198        | 1.0   | 535  | 0.4563          | 0.4421               |
-| 0.3424        | 2.0   | 1070 | 0.4654          | 0.5243               |
-| 0.2381        | 3.0   | 1605 | 0.6751          | 0.4990               |
-| 0.162         | 4.0   | 2140 | 0.7639          | 0.5382               |
-| 0.1213        | 5.0   | 2675 | 0.8456          | 0.5426               |
+| 0.5221        | 1.0   | 535  | 0.5117          | 0.4060               |
+| 0.3027        | 2.0   | 1070 | 0.5073          | 0.5102               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e612ff7c5a498c05d6b9f8303d5d46a5f810412c1871d7d2ceb0241c9cce62b8
+oid sha256:d33ace7df4f97944cfbaf8facfaff81799d629080bf493f06048d414a9a42915
 size 267832560