V1 Training complete

README.md

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3451
-- Rouge1: 12.9978
-- Rouge2: 5.3218
-- Rougel: 12.5685
-- Rougelsum: 12.5517
+- Loss: 3.2107
+- Rouge1: 16.5873
+- Rouge2: 8.3667
+- Rougel: 16.096
+- Rougelsum: 16.0654
 
 ## Model description
 
@@ -48,13 +48,15 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 1
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2 | Rougel  | Rougelsum |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|
-| 4.4084        | 1.0   | 968  | 3.3451          | 12.9978 | 5.3218 | 12.5685 | 12.5517   |
+| 7.4326        | 1.0   | 968  | 3.3609          | 14.4654 | 5.3488 | 14.1032 | 14.1348   |
+| 4.1082        | 2.0   | 1936 | 3.2265          | 15.9058 | 7.6084 | 15.3178 | 15.3304   |
+| 3.8946        | 3.0   | 2904 | 3.2107          | 16.5873 | 8.3667 | 16.096  | 16.0654   |
 
 
 ### Framework versions