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: 0.5576
-- Matthews Correlation: 0.6094
+- Loss: 0.4434
+- Matthews Correlation: 0.5974
 
 ## Model description
 
@@ -43,6 +43,7 @@ The following hyperparameters were used during training:
 - eval_batch_size: 1
 - seed: 42
 - distributed_type: IPU
+- gradient_accumulation_steps: 16
 - total_train_batch_size: 64
 - total_eval_batch_size: 20
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
@@ -52,6 +53,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Matthews Correlation |
+|:-------------:|:-----:|:----:|:---------------:|:--------------------:|
+| 0.4624        | 1.0   | 133  | 0.4446          | 0.5198               |
+| 0.2621        | 2.0   | 266  | 0.4395          | 0.5670               |
+| 0.2044        | 3.0   | 399  | 0.4434          | 0.5974               |
+| 0.1493        | 4.0   | 532  | 0.4919          | 0.5886               |
+| 0.1317        | 5.0   | 665  | 0.5820          | 0.5843               |
 
 
 ### Framework versions