update model card README.md

README.md

@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [alexsha/t5-large-finetuned-English-to-BASH](https://huggingface.co/alexsha/t5-large-finetuned-English-to-BASH) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5974
-- Nl2bash M: 0.8941
-- Gen Len: 13.3264
+- Loss: 0.6790
+- Nl2bash M: 0.8878
+- Gen Len: 13.5207
 
 ## Model description
 
@@ -36,22 +36,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 6e-05
-- train_batch_size: 3
-- eval_batch_size: 3
+- train_batch_size: 5
+- eval_batch_size: 5
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Nl2bash M | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:-------:|
-| 0.2667        | 1.0   | 645  | 0.5067          | 0.869     | 13.0661 |
-| 0.2216        | 2.0   | 1290 | 0.5360          | 0.8747    | 13.4917 |
-| 0.1917        | 3.0   | 1935 | 0.5263          | 0.8867    | 13.6488 |
-| 0.1185        | 4.0   | 2580 | 0.5827          | 0.8931    | 13.3058 |
-| 0.0965        | 5.0   | 3225 | 0.5974          | 0.8941    | 13.3264 |
+| No log        | 1.0   | 387  | 0.6405          | 0.8927    | 13.3223 |
+| 0.0699        | 2.0   | 774  | 0.6508          | 0.8898    | 13.5207 |
+| 0.0578        | 3.0   | 1161 | 0.6790          | 0.8878    | 13.5207 |
 
 
 ### Framework versions