update model card README.md

README.md

@@ -16,12 +16,12 @@ model-index:
       name: crd3
       type: crd3
       config: default
-      split: train[:1]
+      split: train[:500]
       args: default
     metrics:
     - name: Rouge1
       type: rouge
-      value: 0.0
+      value: 0.16466172750612934
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,11 +31,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [allenai/PRIMERA](https://huggingface.co/allenai/PRIMERA) on the crd3 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 7.7826
-- Rouge1: 0.0
-- Rouge2: 0.0
-- Rougel: 0.0
-- Rougelsum: 0.0
+- Loss: 3.8082
+- Rouge1: 0.1647
+- Rouge2: 0.0348
+- Rougel: 0.1376
+- Rougelsum: 0.1488
 
 ## Model description
 
@@ -55,19 +55,20 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- 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: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|
-| No log        | 1.0   | 1    | 8.1025          | 0.0    | 0.0    | 0.0    | 0.0       |
-| No log        | 2.0   | 2    | 7.7826          | 0.0    | 0.0    | 0.0    | 0.0       |
+| No log        | 1.0   | 250  | 2.9780          | 0.1772 | 0.0578 | 0.1547 | 0.1617    |
+| 1.8204        | 2.0   | 500  | 3.3771          | 0.1685 | 0.0331 | 0.1404 | 0.1496    |
+| 1.8204        | 3.0   | 750  | 3.8082          | 0.1647 | 0.0348 | 0.1376 | 0.1488    |
 
 
 ### Framework versions