End of training

README.md

@@ -18,12 +18,12 @@ 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 the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.4457
-- Rouge1: 0.1812
-- Rouge2: 0.0285
-- Rougel: 0.1447
-- Rougelsum: 0.145
-- Gen Len: 18.885
+- Loss: 3.5066
+- Rouge1: 0.1851
+- Rouge2: 0.0284
+- Rougel: 0.148
+- Rougelsum: 0.1477
+- Gen Len: 18.845
 
 ## Model description
 
@@ -42,7 +42,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 4e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -55,9 +55,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
 |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
-| 3.7616        | 1.0   | 100  | 3.4788          | 0.1877 | 0.0288 | 0.1493 | 0.1499    | 18.83   |
-| 3.5537        | 2.0   | 200  | 3.4510          | 0.1803 | 0.0283 | 0.1442 | 0.1443    | 18.81   |
-| 3.4932        | 3.0   | 300  | 3.4457          | 0.1812 | 0.0285 | 0.1447 | 0.145     | 18.885  |
+| 3.8941        | 1.0   | 100  | 3.5902          | 0.1785 | 0.0256 | 0.1421 | 0.1424    | 18.765  |
+| 3.6658        | 2.0   | 200  | 3.5176          | 0.1849 | 0.0287 | 0.1481 | 0.1477    | 18.805  |
+| 3.6187        | 3.0   | 300  | 3.5066          | 0.1851 | 0.0284 | 0.148  | 0.1477    | 18.845  |
 
 
 ### Framework versions