t5 summarization t3

README.md

@@ -18,7 +18,7 @@ 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: 4.7402
+- Loss: 4.8149
 
 ## Model description
 
@@ -50,18 +50,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 8.7018        | 0.08  | 20   | 7.2227          |
-| 8.3474        | 0.16  | 40   | 6.9858          |
-| 8.064         | 0.24  | 60   | 6.6964          |
-| 7.5308        | 0.32  | 80   | 6.3757          |
-| 7.8531        | 0.4   | 100  | 6.0496          |
-| 7.3021        | 0.48  | 120  | 5.7389          |
-| 7.2218        | 0.56  | 140  | 5.4762          |
-| 6.9797        | 0.64  | 160  | 5.2385          |
-| 6.44          | 0.72  | 180  | 5.0457          |
-| 6.3871        | 0.8   | 200  | 4.8971          |
-| 6.2282        | 0.88  | 220  | 4.7975          |
-| 6.0898        | 0.96  | 240  | 4.7402          |
+| 6.1615        | 1.0   | 250  | 4.8149          |
 
 
 ### Framework versions