End of training

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # malay_norm_checkpoint
 
 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: 0.5154
 
 ## Model description
 
@@ -32,7 +34,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-10
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 3
 - seed: 42
@@ -42,6 +44,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.6406        | 0.45  | 500  | 0.5370          |
+| 0.6336        | 0.9   | 1000 | 0.5275          |
+| 0.6197        | 1.35  | 1500 | 0.5259          |
+| 0.6089        | 1.8   | 2000 | 0.5254          |
+| 0.6024        | 2.25  | 2500 | 0.5141          |
+| 0.6022        | 2.7   | 3000 | 0.5154          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eddf9c38f4e557a79a54c72fa333db8ef6c284c36f063db8a75b65bfef7b8e7e
+oid sha256:db58d0abf0549cd94fe906efc72928cf7f1756474d3ac40a9dbc70207c92a257
 size 577789320

runs/Apr04_10-55-20_ab33e364ce2f/events.out.tfevents.1712228120.ab33e364ce2f.1299.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00ce267f8fa283d5286244a8349c058ef9f8e5f42718a298eb48a25fbcf55ce7
-size 9246
+oid sha256:e7ad432f8a4f88a6a1d34837fa4cc61d0cd2e88730aeec649927074956b3e57d
+size 9600