End of training

README.md

@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # newsdata-bert
 
-This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
+This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7534
-- Accuracy: 0.8531
+- Loss: 0.5569
+- Accuracy: 0.8447
 
 ## Model description
 
@@ -38,28 +38,22 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 2
+- train_batch_size: 4
 - eval_batch_size: 2
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
-|:-------------:|:------:|:-----:|:---------------:|:--------:|
-| 1.4704        | 0.0859 | 5000  | 1.4487          | 0.6858   |
-| 1.1946        | 0.1718 | 10000 | 1.2197          | 0.7417   |
-| 1.1323        | 0.2577 | 15000 | 0.9984          | 0.7733   |
-| 0.9926        | 0.3436 | 20000 | 1.0195          | 0.7901   |
-| 0.9232        | 0.4295 | 25000 | 0.9879          | 0.8089   |
-| 0.9273        | 0.5155 | 30000 | 0.8956          | 0.8224   |
-| 1.0023        | 0.6014 | 35000 | 0.8435          | 0.8277   |
-| 0.7566        | 0.6873 | 40000 | 0.8668          | 0.8331   |
-| 0.9032        | 0.7732 | 45000 | 0.8221          | 0.8408   |
-| 0.7227        | 0.8591 | 50000 | 0.7653          | 0.8456   |
-| 0.8159        | 0.9450 | 55000 | 0.7534          | 0.8531   |
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 0.8762        | 0.2749 | 2000 | 0.7835          | 0.7864   |
+| 0.6718        | 0.5498 | 4000 | 0.6341          | 0.8259   |
+| 0.5852        | 0.8247 | 6000 | 0.5569          | 0.8447   |
 
 
 ### Framework versions