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 [MBZUAI/speecht5_tts_clartts_ar](https://huggingface.co/MBZUAI/speecht5_tts_clartts_ar) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5440
+- Loss: 0.5164
 
 ## Model description
 
@@ -44,20 +44,18 @@ The following hyperparameters were used during training:
 - 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
 - lr_scheduler_warmup_steps: 100
-- training_steps: 700
+- training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss |
-|:-------------:|:-------:|:----:|:---------------:|
-| 0.5389        | 2.2663  | 100  | 0.6067          |
-| 0.5034        | 4.5326  | 200  | 0.5614          |
-| 0.4852        | 6.7989  | 300  | 0.5554          |
-| 0.4727        | 9.0652  | 400  | 0.5449          |
-| 0.463         | 11.3314 | 500  | 0.5422          |
-| 0.4501        | 13.5977 | 600  | 0.5429          |
-| 0.4503        | 15.8640 | 700  | 0.5440          |
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.5796        | 1.1331 | 100  | 0.5698          |
+| 0.5436        | 2.2663 | 200  | 0.5432          |
+| 0.5168        | 3.3994 | 300  | 0.5293          |
+| 0.5096        | 4.5326 | 400  | 0.5199          |
+| 0.4976        | 5.6657 | 500  | 0.5164          |
 
 
 ### Framework versions