Model save

README.md

@@ -17,9 +17,9 @@ 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: 1.9476
-- Bleu: 18.8732
-- Gen Len: 28.2253
+- Loss: 1.9203
+- Bleu: 19.1114
+- Gen Len: 28.331
 
 ## Model description
 
@@ -46,13 +46,13 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- training_steps: 5000
+- training_steps: 10000
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Bleu    | Gen Len |
-|:-------------:|:------:|:----:|:---------------:|:-------:|:-------:|
-| 2.4878        | 0.0177 | 5000 | 1.9476          | 18.8732 | 28.2253 |
+| Training Loss | Epoch  | Step  | Validation Loss | Bleu    | Gen Len |
+|:-------------:|:------:|:-----:|:---------------:|:-------:|:-------:|
+| 1.9517        | 0.2778 | 10000 | 1.9203          | 19.1114 | 28.331  |
 
 
 ### Framework versions