Update README.md

README.md

@@ -15,9 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [ai-forever/ruT5-base](https://huggingface.co/ai-forever/ruT5-base) on an unknown dataset.
+This model is a fine-tuned version of [ai-forever/ruT5-base](https://huggingface.co/ai-forever/ruT5-base) on an MCHS anonymized dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4056
+- Loss: 0.3848
+- ParaScore: 0.8265
 
 ## Model description
 
@@ -25,7 +26,7 @@ More information needed
 
 ## Intended uses & limitations
 
-More information needed
+Neutralization of emotional speech
 
 ## Training and evaluation data
 
@@ -44,19 +45,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 8
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.0734        | 1.0   | 786  | 0.4548          |
-| 0.5162        | 2.0   | 1572 | 0.4309          |
-| 0.4561        | 3.0   | 2358 | 0.4134          |
-| 0.4202        | 4.0   | 3144 | 0.4088          |
-| 0.3939        | 5.0   | 3930 | 0.4072          |
-| 0.3746        | 6.0   | 4716 | 0.4053          |
-| 0.3637        | 7.0   | 5502 | 0.4054          |
-| 0.3564        | 8.0   | 6288 | 0.4056          |
-
 
 ### Framework versions