update model card README.md

README.md

@@ -3,7 +3,7 @@ tags:
 - summarization
 - generated_from_trainer
 datasets:
-- xlsum
+- wiki_lingua
 model-index:
 - name: AraT5-base-title-generation-finetuned-ar-xlsum
   results: []
@@ -14,14 +14,14 @@ should probably proofread and complete it, then remove this comment. -->
 
 # AraT5-base-title-generation-finetuned-ar-xlsum
 
-This model is a fine-tuned version of [UBC-NLP/AraT5-base-title-generation](https://huggingface.co/UBC-NLP/AraT5-base-title-generation) on the xlsum dataset.
+This model is a fine-tuned version of [UBC-NLP/AraT5-base-title-generation](https://huggingface.co/UBC-NLP/AraT5-base-title-generation) on the wiki_lingua dataset.
 It achieves the following results on the evaluation set:
-- Loss: 4.3263
-- Rouge-1: 32.03
-- Rouge-2: 14.67
-- Rouge-l: 28.04
-- Gen Len: 18.45
-- Bertscore: 74.09
+- Loss: 4.8120
+- Rouge-1: 23.29
+- Rouge-2: 8.44
+- Rouge-l: 20.74
+- Gen Len: 18.16
+- Bertscore: 70.88
 
 ## Model description
 
@@ -41,29 +41,27 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 6
-- eval_batch_size: 6
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 250
-- num_epochs: 10
+- num_epochs: 8
 - label_smoothing_factor: 0.1
 
 ### Training results
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge-1 | Rouge-2 | Rouge-l | Gen Len | Bertscore |
 |:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:-------:|:---------:|
-| 5.5156        | 1.0   | 6254  | 4.6874          | 27.18   | 10.66   | 23.51   | 18.72   | 72.39     |
-| 5.0589        | 2.0   | 12508 | 4.5374          | 28.93   | 11.87   | 25.02   | 18.69   | 73.11     |
-| 4.8629        | 3.0   | 18762 | 4.4512          | 29.31   | 12.22   | 25.51   | 18.79   | 73.2      |
-| 4.7327        | 4.0   | 25016 | 4.3989          | 29.8    | 12.73   | 25.95   | 18.72   | 73.42     |
-| 4.6317        | 5.0   | 31270 | 4.3729          | 30.23   | 12.9    | 26.37   | 18.71   | 73.57     |
-| 4.5557        | 6.0   | 37524 | 4.3497          | 30.46   | 13.14   | 26.57   | 18.76   | 73.6      |
-| 4.496         | 7.0   | 43778 | 4.3388          | 30.93   | 13.47   | 26.96   | 18.68   | 73.76     |
-| 4.4475        | 8.0   | 50032 | 4.3331          | 30.99   | 13.55   | 27.06   | 18.66   | 73.79     |
-| 4.4133        | 9.0   | 56286 | 4.3248          | 31.02   | 13.59   | 27.04   | 18.71   | 73.81     |
-| 4.3909        | 10.0  | 62540 | 4.3263          | 31.12   | 13.64   | 27.14   | 18.7    | 73.86     |
+| 6.1002        | 1.0   | 5111  | 5.2917          | 18.95   | 5.84    | 17.01   | 17.9    | 68.69     |
+| 5.4427        | 2.0   | 10222 | 5.0877          | 20.61   | 6.73    | 18.58   | 17.14   | 69.69     |
+| 5.1876        | 3.0   | 15333 | 4.9631          | 21.27   | 7.17    | 19.09   | 17.69   | 69.82     |
+| 5.0256        | 4.0   | 20444 | 4.8984          | 21.7    | 7.53    | 19.55   | 17.56   | 70.18     |
+| 4.9104        | 5.0   | 25555 | 4.8538          | 22.23   | 7.54    | 19.79   | 17.6    | 70.33     |
+| 4.8251        | 6.0   | 30666 | 4.8309          | 22.35   | 7.6     | 19.96   | 17.64   | 70.51     |
+| 4.7666        | 7.0   | 35777 | 4.8168          | 22.45   | 7.81    | 20.15   | 17.47   | 70.61     |
+| 4.7275        | 8.0   | 40888 | 4.8120          | 22.67   | 7.83    | 20.34   | 17.56   | 70.66     |
 
 
 ### Framework versions