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: 0.4680
+- Loss: 0.4791
 
 ## Model description
 
@@ -36,11 +36,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0001
-- train_batch_size: 4
-- eval_batch_size: 2
+- train_batch_size: 2
+- eval_batch_size: 1
 - seed: 42
 - gradient_accumulation_steps: 8
-- total_train_batch_size: 32
+- total_train_batch_size: 16
 - 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
@@ -51,11 +51,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 5.0756        | 0.0994 | 100  | 0.5540          |
-| 4.6645        | 0.1987 | 200  | 0.5558          |
-| 4.3179        | 0.2981 | 300  | 0.4871          |
-| 4.1836        | 0.3975 | 400  | 0.4769          |
-| 4.1409        | 0.4968 | 500  | 0.4680          |
+| 5.2111        | 0.0497 | 100  | 0.5662          |
+| 4.7315        | 0.0994 | 200  | 0.5253          |
+| 4.3949        | 0.1491 | 300  | 0.5158          |
+| 4.2589        | 0.1987 | 400  | 0.4926          |
+| 4.1795        | 0.2484 | 500  | 0.4791          |
 
 
 ### Framework versions