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: 0.4811
+- Loss: 0.4689
 
 ## Model description
 
@@ -35,7 +35,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
+- learning_rate: 5e-05
 - train_batch_size: 4
 - eval_batch_size: 2
 - seed: 42
@@ -43,19 +43,24 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
-- training_steps: 500
+- lr_scheduler_warmup_steps: 200
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.6344        | 0.7333 | 100  | 0.5573          |
-| 0.5618        | 1.4665 | 200  | 0.5176          |
-| 0.5424        | 2.1998 | 300  | 0.4978          |
-| 0.5261        | 2.9331 | 400  | 0.4922          |
-| 0.5175        | 3.6664 | 500  | 0.4811          |
+| 0.754         | 0.7333 | 100  | 0.6016          |
+| 0.588         | 1.4665 | 200  | 0.5398          |
+| 0.557         | 2.1998 | 300  | 0.5056          |
+| 0.5447        | 2.9331 | 400  | 0.5043          |
+| 0.5307        | 3.6664 | 500  | 0.4880          |
+| 0.5185        | 4.3996 | 600  | 0.4909          |
+| 0.5221        | 5.1329 | 700  | 0.4802          |
+| 0.5043        | 5.8662 | 800  | 0.4712          |
+| 0.5034        | 6.5995 | 900  | 0.4686          |
+| 0.5023        | 7.3327 | 1000 | 0.4689          |
 
 
 ### Framework versions