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: 0.8329
-- Matthews Correlation: 0.5429
+- Loss: 0.7458
+- Matthews Correlation: 0.4922
 
 ## 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: 8.53919308272751e-06
+- train_batch_size: 8
 - eval_batch_size: 16
-- seed: 42
+- seed: 13
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5191        | 1.0   | 535  | 0.4584          | 0.4522               |
-| 0.3431        | 2.0   | 1070 | 0.4681          | 0.5105               |
-| 0.2368        | 3.0   | 1605 | 0.6857          | 0.5011               |
-| 0.1677        | 4.0   | 2140 | 0.7485          | 0.5333               |
-| 0.1258        | 5.0   | 2675 | 0.8329          | 0.5429               |
+| 0.5143        | 1.0   | 1069 | 0.4927          | 0.4359               |
+| 0.3963        | 2.0   | 2138 | 0.4984          | 0.4814               |
+| 0.3216        | 3.0   | 3207 | 0.6548          | 0.4980               |
+| 0.2629        | 4.0   | 4276 | 0.7458          | 0.4922               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b216a6e689ddde958a93b0b0b64a61bc49fabf02e397ed75fe3add93e0027c6a
+oid sha256:1c18f088ad3484b7949435a2e6c71218b17eabd3f720c94f95032724bf7933e2
 size 267832560