update model card README.md

README.md

@@ -1,6 +1,8 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- custom_squad_v2
 model-index:
 - name: awsome_bigbird_24387490
   results: []
@@ -11,7 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # awsome_bigbird_24387490
 
-This model is a fine-tuned version of [monologg/kobigbird-bert-base](https://huggingface.co/monologg/kobigbird-bert-base) on the None dataset.
+This model is a fine-tuned version of [monologg/kobigbird-bert-base](https://huggingface.co/monologg/kobigbird-bert-base) on the custom_squad_v2 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1222
 
 ## Model description
 
@@ -34,18 +38,20 @@ The following hyperparameters were used during training:
 - train_batch_size: 32
 - eval_batch_size: 32
 - seed: 30
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 256
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 512
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 137  | 1.5316          |
+| No log        | 0.99  | 21   | 1.2008          |
+| No log        | 1.99  | 42   | 1.1138          |
+| No log        | 2.99  | 63   | 1.1222          |
 
 
 ### Framework versions