End of training

README.md

@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/bigbird-roberta-base](https://huggingface.co/google/bigbird-roberta-base) on the race dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3863
-- Accuracy: 0.2639
+- Loss: 1.0178
+- Accuracy: 0.5884
 
 ## Model description
 
@@ -40,20 +40,21 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 2
-- eval_batch_size: 2
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 2
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.3883        | 1.0   | 3177 | 1.3863          | 0.2639   |
+| 1.313         | 1.0   | 1589 | 1.2015          | 0.4896   |
+| 1.0197        | 2.0   | 3178 | 1.0178          | 0.5884   |
 
 
 ### Framework versions