Training complete

README.md

@@ -1,5 +1,4 @@
 ---
-base_model: csebuetnlp/banglabert
 tags:
 - generated_from_trainer
 model-index:
@@ -12,9 +11,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert-finetuned-ner-bangla
 
-This model is a fine-tuned version of [csebuetnlp/banglabert](https://huggingface.co/csebuetnlp/banglabert) on an unknown dataset.
+This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1003
+- Loss: 0.1048
 
 ## Model description
 
@@ -34,21 +33,19 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 128
-- eval_batch_size: 128
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2571        | 0.23  | 500  | 0.1299          |
-| 0.1247        | 0.45  | 1000 | 0.1106          |
-| 0.112         | 0.68  | 1500 | 0.1011          |
-| 0.1059        | 0.91  | 2000 | 0.1003          |
+| 0.1194        | 0.84  | 500  | 0.1120          |
+| 0.1027        | 1.68  | 1000 | 0.1048          |
 
 
 ### Framework versions