End of training

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6463
+- Loss: 0.3877
 
 ## Model description
 
@@ -44,18 +44,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 5000
-- training_steps: 500
+- training_steps: 9000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.1659        | 0.3556 | 100  | 0.8903          |
-| 1.0118        | 0.7111 | 200  | 0.8274          |
-| 0.9067        | 1.0667 | 300  | 0.7328          |
-| 0.831         | 1.4222 | 400  | 0.6840          |
-| 0.7502        | 1.7778 | 500  | 0.6463          |
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 0.4585        | 7.1111  | 3000 | 0.4186          |
+| 0.4252        | 14.2222 | 6000 | 0.3937          |
+| 0.4198        | 21.3333 | 9000 | 0.3877          |
 
 
 ### Framework versions