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: 0.8553
-- Matthews Correlation: 0.5332
+- Loss: 0.5544
+- Matthews Correlation: 0.5009
 
 ## 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: 1.546889870762945e-05
+- train_batch_size: 32
 - eval_batch_size: 16
-- seed: 42
+- seed: 6
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5175        | 1.0   | 535  | 0.4515          | 0.4511               |
-| 0.3429        | 2.0   | 1070 | 0.4648          | 0.5162               |
-| 0.2373        | 3.0   | 1605 | 0.6564          | 0.5173               |
-| 0.1631        | 4.0   | 2140 | 0.7276          | 0.5265               |
-| 0.122         | 5.0   | 2675 | 0.8553          | 0.5332               |
+| No log        | 1.0   | 268  | 0.4784          | 0.4982               |
+| 0.4708        | 2.0   | 536  | 0.4544          | 0.5011               |
+| 0.4708        | 3.0   | 804  | 0.5128          | 0.5070               |
+| 0.2823        | 4.0   | 1072 | 0.5544          | 0.5009               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adf4873f03711bcd1e5aac7f2cccc8c1e3507a2ce13e9346f72877865b9aa266
+oid sha256:0d5c9dcbc1532d98a0abe41b3daecfdc5c404d0fe4e084e3e5fbc14cb188fbed
 size 267832560