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: 0.8360
-- Matthews Correlation: 0.5354
+- Loss: 0.5382
+- Matthews Correlation: 0.4677
 
 ## 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: 2.829056514710492e-05
+- train_batch_size: 64
 - eval_batch_size: 16
-- seed: 42
+- seed: 21
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5224        | 1.0   | 535  | 0.4521          | 0.4692               |
-| 0.3508        | 2.0   | 1070 | 0.4663          | 0.5062               |
-| 0.239         | 3.0   | 1605 | 0.6668          | 0.4982               |
-| 0.1695        | 4.0   | 2140 | 0.7490          | 0.5207               |
-| 0.131         | 5.0   | 2675 | 0.8360          | 0.5354               |
+| No log        | 1.0   | 134  | 0.5430          | 0.3489               |
+| No log        | 2.0   | 268  | 0.4852          | 0.4818               |
+| No log        | 3.0   | 402  | 0.5382          | 0.4677               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85c9db6b304cec82199c794dc856ace06a931e2bf6d224a19996ad692e9dd528
+oid sha256:37c1d3f957f29d7064ec44df127e22dff47f830ad87b4c8c5e4ee6406535f61f
 size 267832560