update model card README.md

README.md

@@ -14,8 +14,8 @@ 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: 0.6147
-- Rmse: 0.6327
+- Loss: 0.5618
+- Rmse: 0.6118
 
 ## Model description
 
@@ -34,12 +34,12 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- learning_rate: 2e-05
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 64
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
@@ -50,8 +50,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rmse   |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 0.6405        | 4.0   | 500  | 0.6147          | 0.6327 |
-| 0.2214        | 8.0   | 1000 | 0.8795          | 0.6251 |
+| 0.7273        | 2.0   | 500  | 0.5618          | 0.6118 |
+| 0.4294        | 4.0   | 1000 | 0.5821          | 0.5906 |
+| 0.2278        | 6.0   | 1500 | 0.8019          | 0.6235 |
+| 0.1246        | 8.0   | 2000 | 0.9412          | 0.5961 |
+| 0.083         | 10.0  | 2500 | 1.1040          | 0.5978 |
 
 
 ### Framework versions