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: 0.4607
-- Matthews Correlation: 0.5351
+- Loss: 0.5688
+- Matthews Correlation: 0.5215
 
 ## 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: 5.0568164357979843e-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 |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.5141        | 1.0   | 535  | 0.4610          | 0.4298               |
-| 0.3417        | 2.0   | 1070 | 0.4607          | 0.5351               |
-| 0.2359        | 3.0   | 1605 | 0.6526          | 0.5065               |
-| 0.1627        | 4.0   | 2140 | 0.7472          | 0.5339               |
-| 0.1204        | 5.0   | 2675 | 0.8497          | 0.5295               |
+| No log        | 1.0   | 134  | 0.4710          | 0.4269               |
+| No log        | 2.0   | 268  | 0.4810          | 0.5091               |
+| No log        | 3.0   | 402  | 0.5688          | 0.5215               |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d7b9569e1812a35365a6f1e06e72d9c90ab391e407fa76863959efda212512
+oid sha256:ec43caea3102f42de3e56419e34a66f4d9d3335d2798c85c1cb8ccc7053c7b17
 size 267832560