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: 0.3233
+- Loss: 0.2985
 
 ## Model description
 
@@ -44,18 +44,23 @@ 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: 100
-- training_steps: 500
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.5184        | 0.4545 | 100  | 0.4569          |
-| 0.419         | 0.9091 | 200  | 0.3698          |
-| 0.3798        | 1.3636 | 300  | 0.3444          |
-| 0.3573        | 1.8182 | 400  | 0.3349          |
-| 0.3484        | 2.2727 | 500  | 0.3233          |
+| 0.5079        | 0.4545 | 100  | 0.4190          |
+| 0.4305        | 0.9091 | 200  | 0.3653          |
+| 0.3847        | 1.3636 | 300  | 0.3456          |
+| 0.3575        | 1.8182 | 400  | 0.3453          |
+| 0.3482        | 2.2727 | 500  | 0.3231          |
+| 0.3414        | 2.7273 | 600  | 0.3151          |
+| 0.333         | 3.1818 | 700  | 0.3079          |
+| 0.3254        | 3.6364 | 800  | 0.3021          |
+| 0.3203        | 4.0909 | 900  | 0.2989          |
+| 0.3174        | 4.5455 | 1000 | 0.2985          |
 
 
 ### Framework versions