update model card README.md

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 the glue dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5195
-- Matthews Correlation: 0.6069
+- Loss: 0.5776
+- Matthews Correlation: 0.6121
 
 ## Model description
 
@@ -44,8 +44,8 @@ The following hyperparameters were used during training:
 - seed: 42
 - distributed_type: IPU
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 64
-- total_eval_batch_size: 20
+- total_train_batch_size: 16
+- total_eval_batch_size: 5
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 5
@@ -55,11 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
 |:-------------:|:-----:|:----:|:---------------:|:--------------------:|
-| 0.3118        | 1.0   | 133  | 0.4163          | 0.5820               |
-| 0.2033        | 2.0   | 266  | 0.4956          | 0.5484               |
-| 0.1389        | 3.0   | 399  | 0.5327          | 0.5718               |
-| 0.1097        | 4.0   | 532  | 0.5195          | 0.6069               |
-| 0.0789        | 5.0   | 665  | 0.5508          | 0.6044               |
+| 0.5149        | 1.0   | 534  | 0.4097          | 0.5753               |
+| 0.3749        | 2.0   | 1068 | 0.4736          | 0.5927               |
+| 0.1327        | 3.0   | 1602 | 0.4639          | 0.5969               |
+| 0.2031        | 4.0   | 2136 | 0.5474          | 0.5696               |
+| 0.1133        | 5.0   | 2670 | 0.5776          | 0.6121               |
 
 
 ### Framework versions