update model card README.md

README.md

@@ -12,7 +12,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # summarise_v7
 
-This model is a fine-tuned version of [debbiesoon/summarise](https://huggingface.co/debbiesoon/summarise) on an unknown dataset.
+This model is a fine-tuned version of [allenai/led-base-16384](https://huggingface.co/allenai/led-base-16384) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1331
+- Rouge2 Precision: 0.3023
+- Rouge2 Recall: 0.3298
+- Rouge2 Fmeasure: 0.2949
 
 ## Model description
 
@@ -32,12 +37,23 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 2
+- eval_batch_size: 2
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3.0
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure |
+|:-------------:|:-----:|:----:|:---------------:|:----------------:|:-------------:|:---------------:|
+| 1.3257        | 0.22  | 10   | 1.4084          | 0.1157           | 0.4297        | 0.1742          |
+| 1.6076        | 0.44  | 20   | 1.2212          | 0.337            | 0.3337        | 0.3005          |
+| 1.1881        | 0.67  | 30   | 1.2107          | 0.3219           | 0.3431        | 0.3095          |
+| 1.6237        | 0.89  | 40   | 1.1331          | 0.3023           | 0.3298        | 0.2949          |
+
 
 ### Framework versions