update model card README.md

README.md

@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3593
-- Rouge1: 0.1953
-- Rouge2: 0.1351
-- Rougel: 0.1778
-- Rougelsum: 0.178
+- Loss: 0.3321
+- Rouge1: 0.1914
+- Rouge2: 0.1314
+- Rougel: 0.1738
+- Rougelsum: 0.1738
 - Gen Len: 19.0
 
 ## Model description
@@ -42,8 +42,8 @@ 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: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -53,10 +53,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 112  | 0.5091          | 0.1983 | 0.1415 | 0.1806 | 0.1802    | 19.0    |
-| No log        | 2.0   | 224  | 0.3885          | 0.1917 | 0.1307 | 0.1739 | 0.1738    | 19.0    |
-| No log        | 3.0   | 336  | 0.3657          | 0.1956 | 0.1351 | 0.1777 | 0.1778    | 19.0    |
-| No log        | 4.0   | 448  | 0.3593          | 0.1953 | 0.1351 | 0.1778 | 0.178     | 19.0    |
+| No log        | 1.0   | 223  | 0.4008          | 0.1895 | 0.1299 | 0.1715 | 0.1716    | 19.0    |
+| No log        | 2.0   | 446  | 0.3517          | 0.1906 | 0.1311 | 0.1726 | 0.1726    | 19.0    |
+| 0.6596        | 3.0   | 669  | 0.3364          | 0.1915 | 0.1322 | 0.174  | 0.174     | 19.0    |
+| 0.6596        | 4.0   | 892  | 0.3321          | 0.1914 | 0.1314 | 0.1738 | 0.1738    | 19.0    |
 
 
 ### Framework versions