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: 0.7681
-- Matthews Correlation: 0.5426
+- Loss: 0.5112
+- Matthews Correlation: 0.5305
 
 ## 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: 2.9805771852415407e-05
+- train_batch_size: 64
 - eval_batch_size: 16
-- seed: 42
+- seed: 16
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5236        | 1.0   | 535  | 0.4654          | 0.4653               |
-| 0.3459        | 2.0   | 1070 | 0.5101          | 0.4963               |
-| 0.227         | 3.0   | 1605 | 0.5817          | 0.5216               |
-| 0.1733        | 4.0   | 2140 | 0.7681          | 0.5426               |
-| 0.1296        | 5.0   | 2675 | 0.8440          | 0.5377               |
+| No log        | 1.0   | 134  | 0.4761          | 0.4471               |
+| No log        | 2.0   | 268  | 0.4733          | 0.5052               |
+| No log        | 3.0   | 402  | 0.5112          | 0.5305               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b0270b07bfbec4109b4ddda5753849594e831c4e505a19dd158e923aaf46b8f
+oid sha256:3bdfcba1c7f038e0c72d9fff4f15b354e41b2cab9faa241913be25a5f1f1a60b
 size 267832560