End of training

README.md

@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.5346
-- Rouge1: 0.1441
-- Rouge2: 0.0498
-- Rougel: 0.1187
-- Rougelsum: 0.1186
+- Loss: 2.5189
+- Rouge1: 0.1392
+- Rouge2: 0.0476
+- Rougel: 0.1168
+- Rougelsum: 0.1166
 - Gen Len: 20.0
 
 ## Model description
@@ -55,10 +55,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| No log        | 1.0   | 62   | 2.8204          | 0.1335 | 0.0353 | 0.1092 | 0.1093    | 20.0    |
-| No log        | 2.0   | 124  | 2.6152          | 0.1393 | 0.0447 | 0.1142 | 0.1139    | 20.0    |
-| No log        | 3.0   | 186  | 2.5523          | 0.1437 | 0.0495 | 0.1176 | 0.1174    | 20.0    |
-| No log        | 4.0   | 248  | 2.5346          | 0.1441 | 0.0498 | 0.1187 | 0.1186    | 20.0    |
+| No log        | 1.0   | 62   | 2.8045          | 0.1264 | 0.0365 | 0.107  | 0.1072    | 20.0    |
+| No log        | 2.0   | 124  | 2.5956          | 0.1344 | 0.0441 | 0.1124 | 0.1125    | 20.0    |
+| No log        | 3.0   | 186  | 2.5364          | 0.1398 | 0.0493 | 0.1169 | 0.1167    | 20.0    |
+| No log        | 4.0   | 248  | 2.5189          | 0.1392 | 0.0476 | 0.1168 | 0.1166    | 20.0    |
 
 
 ### Framework versions