End of training

README.md

@@ -14,8 +14,6 @@ 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: 0.5368
 
 ## Model description
 
@@ -34,26 +32,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 1e-10
 - train_batch_size: 4
-- eval_batch_size: 2
+- eval_batch_size: 3
 - seed: 42
-- gradient_accumulation_steps: 8
-- 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: 500
-- training_steps: 4000
-- mixed_precision_training: Native AMP
+- num_epochs: 3.0
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 0.8421        | 64.52  | 1000 | 0.7543          |
-| 0.6685        | 129.03 | 2000 | 0.5976          |
-| 0.6247        | 193.55 | 3000 | 0.5445          |
-| 0.6202        | 258.06 | 4000 | 0.5368          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96965b900133c64c75a9cb820662700f7c72e60577ba32a3ef66ba8ec86ed942
+oid sha256:201e9d1ad26c835eccf785d6021237f14b3f23def2c73997bf6c09cbedbab496
 size 577789320

runs/Apr04_10-46-42_ab33e364ce2f/events.out.tfevents.1712227602.ab33e364ce2f.1299.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf64a82658e2abbb3ee5344619c72077022fa201d189563f21095645ab22506
+size 6708

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c293a76f1be5b31eded05d498f87cae22722628d61e94a21c48a141be1fc9fba
+oid sha256:a50e85a1c0fd816a925528614d0d1b9573f7434c51d93002824edd0f6ccd9903
 size 5176