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: 2.5102
-- Rouge1: 0.1383
-- Rouge2: 0.0486
-- Rougel: 0.1139
-- Rougelsum: 0.1136
+- Loss: 2.5617
+- Rouge1: 0.1369
+- Rouge2: 0.0477
+- Rougel: 0.1127
+- Rougelsum: 0.1126
 - Gen Len: 19.0
 
 ## 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   | 2.8061          | 0.1294 | 0.0405 | 0.1089 | 0.1086    | 19.0    |
-| No log        | 2.0   | 124  | 2.5896          | 0.14   | 0.0514 | 0.1178 | 0.1174    | 19.0    |
-| No log        | 3.0   | 186  | 2.5273          | 0.1394 | 0.0494 | 0.1143 | 0.1141    | 19.0    |
-| No log        | 4.0   | 248  | 2.5102          | 0.1383 | 0.0486 | 0.1139 | 0.1136    | 19.0    |
+| No log        | 1.0   | 62   | 2.8520          | 0.1239 | 0.0352 | 0.1039 | 0.1038    | 19.0    |
+| No log        | 2.0   | 124  | 2.6398          | 0.1306 | 0.0433 | 0.1084 | 0.1082    | 19.0    |
+| No log        | 3.0   | 186  | 2.5787          | 0.1355 | 0.0467 | 0.1118 | 0.1117    | 19.0    |
+| No log        | 4.0   | 248  | 2.5617          | 0.1369 | 0.0477 | 0.1127 | 0.1126    | 19.0    |
 
 
 ### Framework versions