Training complete

README.md

@@ -21,7 +21,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.6226880394574599
+      value: 0.5844636251541308
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mor40/BulBERT-chitanka-model](https://huggingface.co/mor40/BulBERT-chitanka-model) on the bgglue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1742
-- Accuracy: 0.6227
+- Loss: 1.5157
+- Accuracy: 0.5845
 
 ## Model description
 
@@ -51,7 +51,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
+- learning_rate: 4e-05
 - train_batch_size: 128
 - eval_batch_size: 128
 - seed: 42
@@ -63,11 +63,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 64   | 1.2730          | 0.5931   |
-| No log        | 2.0   | 128  | 1.1778          | 0.6042   |
-| No log        | 3.0   | 192  | 1.1730          | 0.6313   |
-| No log        | 4.0   | 256  | 1.1722          | 0.6227   |
-| No log        | 5.0   | 320  | 1.1742          | 0.6227   |
+| No log        | 1.0   | 64   | 1.3080          | 0.5956   |
+| No log        | 2.0   | 128  | 1.4107          | 0.5709   |
+| No log        | 3.0   | 192  | 1.4825          | 0.5968   |
+| No log        | 4.0   | 256  | 1.5070          | 0.5882   |
+| No log        | 5.0   | 320  | 1.5157          | 0.5845   |
 
 
 ### Framework versions