update model card README.md

README.md

@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 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: 2.1609
-- Rouge1: 0.4549
-- Rouge2: 0.1557
-- Rougel: 0.2442
-- Rougelsum: 0.2442
+- Loss: 2.1666
+- Rouge1: 0.4524
+- Rouge2: 0.1553
+- Rougel: 0.2434
+- Rougelsum: 0.2434
 
 ## Model description
 
@@ -40,8 +40,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -52,11 +52,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step  | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
 |:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|
-| 2.2814        | 0.69  | 5000  | 2.2276          | 0.4490 | 0.1510 | 0.2408 | 0.2408    |
-| 2.0472        | 1.37  | 10000 | 2.1609          | 0.4549 | 0.1557 | 0.2442 | 0.2442    |
-| 1.9301        | 2.06  | 15000 | 2.1339          | 0.4536 | 0.1517 | 0.2395 | 0.2396    |
-| 1.911         | 2.75  | 20000 | 2.1154          | 0.4544 | 0.1522 | 0.2394 | 0.2395    |
-| 1.7848        | 3.43  | 25000 | 2.1048          | 0.4555 | 0.1525 | 0.2408 | 0.2410    |
+| 2.0914        | 1.37  | 5000  | 2.1666          | 0.4524 | 0.1553 | 0.2434 | 0.2434    |
+| 1.9787        | 2.75  | 10000 | 2.1174          | 0.4561 | 0.1540 | 0.2412 | 0.2412    |
 
 
 ### Framework versions