End of training

README.md

@@ -19,12 +19,12 @@ 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 the generator dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.4278
-- eval_runtime: 543.447
-- eval_samples_per_second: 12.349
-- eval_steps_per_second: 0.386
-- epoch: 32.6531
-- step: 16000
+- eval_loss: 0.5410
+- eval_runtime: 292.5007
+- eval_samples_per_second: 42.496
+- eval_steps_per_second: 2.656
+- epoch: 8.2736
+- step: 15000
 
 ## Model description
 
@@ -43,9 +43,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 32
-- eval_batch_size: 32
+- learning_rate: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ebddb797d7a7b2c4832084dfb3dc30cdc2fb54a28ad457e5c9decf7b46e791
+oid sha256:a170293fdc6840ed868de8cf609b91664994f3baebd984ab54f2eafc2f4a7478
 size 577859976

runs/Jul12_01-53-47_MinhTien-PC/events.out.tfevents.1720724028.MinhTien-PC.12508.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7ee84382bef5935ec5a578782c21ed200e85897c46353c264b71926f678e62c
-size 7448
+oid sha256:c4ac5a0a0ef55bd4a3bb57adf900a8c6ea6a106795bd22641c4ac6922f10a169
+size 7930