update model card README.md

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: EquityVsDebtIssue
   results: []
@@ -14,13 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.9255
-- eval_accuracy: 0.7415
-- eval_runtime: 37.0257
-- eval_samples_per_second: 31.654
-- eval_steps_per_second: 1.999
-- epoch: 4.0
-- step: 2344
+- Loss: 0.7184
+- Accuracy: 0.7210
 
 ## Model description
 
@@ -45,7 +42,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 4
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 0.6182        | 1.0   | 586  | 0.5384          | 0.6997   |
+| 0.4979        | 2.0   | 1172 | 0.5136          | 0.7210   |
+| 0.3815        | 3.0   | 1758 | 0.6158          | 0.7218   |
+| 0.3048        | 4.0   | 2344 | 0.7184          | 0.7210   |
+
 
 ### Framework versions