Training complete

README.md

@@ -2,8 +2,6 @@
 base_model: mor40/BulBERT-chitanka-model
 tags:
 - generated_from_trainer
-datasets:
-- bgglue
 model-index:
 - name: BulBERT-exams-5epochs
   results: []
@@ -14,10 +12,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # BulBERT-exams-5epochs
 
-This model is a fine-tuned version of [mor40/BulBERT-chitanka-model](https://huggingface.co/mor40/BulBERT-chitanka-model) on the bgglue dataset.
+This model is a fine-tuned version of [mor40/BulBERT-chitanka-model](https://huggingface.co/mor40/BulBERT-chitanka-model) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9622
-- Acc: 0.2946
+- Loss: 0.7671
+- Acc: 0.7498
 
 ## Model description
 
@@ -44,21 +42,22 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.06
 - num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Acc    |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|
-| 1.0207        | 1.0   | 2538  | 1.9309          | 0.3004 |
-| 0.9505        | 2.0   | 5076  | 2.7472          | 0.2750 |
-| 0.9552        | 3.0   | 7614  | 2.7331          | 0.2913 |
-| 0.9126        | 4.0   | 10152 | 2.8254          | 0.2798 |
-| 0.8957        | 5.0   | 12690 | 2.9622          | 0.2946 |
+| 0.7342        | 1.0   | 4309  | 0.7328          | 0.7498 |
+| 0.6805        | 2.0   | 8618  | 0.7723          | 0.7498 |
+| 0.6844        | 3.0   | 12927 | 0.7731          | 0.7498 |
+| 0.6748        | 4.0   | 17236 | 0.7608          | 0.7498 |
+| 0.6809        | 5.0   | 21545 | 0.7671          | 0.7498 |
 
 
 ### Framework versions
 
-- Transformers 4.35.0
+- Transformers 4.35.2
 - Pytorch 2.1.0+cu118
-- Datasets 2.14.6
-- Tokenizers 0.14.1
+- Datasets 2.15.0
+- Tokenizers 0.15.0