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: 0.7134
-- Matthews Correlation: 0.5605
+- Loss: 1.1265
+- Matthews Correlation: 0.5127
 
 ## Model description
 
@@ -37,23 +37,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 16
+- learning_rate: 1.7927953212557118e-05
+- train_batch_size: 4
 - eval_batch_size: 16
-- seed: 42
+- seed: 35
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5245        | 1.0   | 535  | 0.4719          | 0.4354               |
-| 0.3474        | 2.0   | 1070 | 0.4744          | 0.5279               |
-| 0.2424        | 3.0   | 1605 | 0.5412          | 0.5456               |
-| 0.1794        | 4.0   | 2140 | 0.7134          | 0.5605               |
-| 0.1178        | 5.0   | 2675 | 0.8179          | 0.5498               |
+| 0.5987        | 1.0   | 2138 | 0.5104          | 0.4477               |
+| 0.5073        | 2.0   | 4276 | 0.7684          | 0.4766               |
+| 0.3068        | 3.0   | 6414 | 0.9311          | 0.4972               |
+| 0.1824        | 4.0   | 8552 | 1.1265          | 0.5127               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c5d876c528b8b27f441d4fd9a3d5c561c4120b5e3951ff7092dc93fe18000f
+oid sha256:06bdda8a0812ab342f9708cb66dc2f30eff252432291dcb0dbecdbb37acf6bf7
 size 267832560