End of training

README.md

@@ -17,9 +17,9 @@ 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: 1.2500
-- Bleu: 1.5635
-- Gen Len: 9.05
+- Loss: 0.6219
+- Bleu: 13.8583
+- Gen Len: 7.98
 
 ## Model description
 
@@ -48,10 +48,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Bleu   | Gen Len |
-|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
-| No log        | 1.0   | 5    | 1.2965          | 1.5365 | 9.2     |
-| No log        | 2.0   | 10   | 1.2500          | 1.5635 | 9.05    |
+| Training Loss | Epoch | Step | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
+| 0.9215        | 1.0   | 500  | 0.6627          | 8.2664  | 8.0255  |
+| 0.7364        | 2.0   | 1000 | 0.6219          | 13.8583 | 7.98    |
 
 
 ### Framework versions

runs/May16_14-02-57_93922bb4881d/events.out.tfevents.1715868178.93922bb4881d.33.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86057babb14c8179e7f8545cc5be576ff05d792190d74ddbe4996738644440e2
-size 6415
+oid sha256:95c84bc659c4d5e318cec866d343474678dee7e05b5f65eefd947a97e4a7b24c
+size 7139