End of training

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2081
-- Accuracy: 0.9346
+- Loss: 0.2104
+- Accuracy: 0.9323
 
 ## Model description
 
@@ -38,23 +38,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.00011270038884391928
-- train_batch_size: 32
+- learning_rate: 0.0001406585318528703
+- train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
-|:-------------:|:-----:|:-----:|:---------------:|:--------:|
-| 0.2357        | 1.0   | 2105  | 0.1983          | 0.9323   |
-| 0.2118        | 2.0   | 4210  | 0.2195          | 0.9278   |
-| 0.1939        | 3.0   | 6315  | 0.1972          | 0.9381   |
-| 0.1907        | 4.0   | 8420  | 0.2046          | 0.9358   |
-| 0.1856        | 5.0   | 10525 | 0.2081          | 0.9346   |
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.2255        | 1.0   | 4210 | 0.2104          | 0.9323   |
 
 
 ### Framework versions