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: 0.8797
-- Matthews Correlation: 0.5265
+- Loss: 1.2181
+- Matthews Correlation: 0.5074
 
 ## 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: 2.6293591491548714e-05
+- train_batch_size: 4
 - eval_batch_size: 16
-- seed: 42
+- seed: 37
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5167        | 1.0   | 535  | 0.4602          | 0.4382               |
-| 0.3459        | 2.0   | 1070 | 0.4649          | 0.5190               |
-| 0.2321        | 3.0   | 1605 | 0.6437          | 0.5076               |
-| 0.163         | 4.0   | 2140 | 0.7673          | 0.5195               |
-| 0.1205        | 5.0   | 2675 | 0.8797          | 0.5265               |
+| 0.5675        | 1.0   | 2138 | 0.6569          | 0.4227               |
+| 0.4431        | 2.0   | 4276 | 0.8104          | 0.4796               |
+| 0.2781        | 3.0   | 6414 | 1.0194          | 0.5086               |
+| 0.1883        | 4.0   | 8552 | 1.2181          | 0.5074               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792c1e28ef0895b481cbc5a84ce9da554b3b84f7fa42de1ba24c6a764bcefca1
+oid sha256:252b0645497e59d11ebf0827d3b5651082677f43cc2b34ce52b847fa8a3b37f4
 size 267832560