Training in progress, step 4200

README.md

@@ -15,6 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
 # Sindhi-TTS
 
 This model is a fine-tuned version of [fahadqazi/Sindhi-TTS](https://huggingface.co/fahadqazi/Sindhi-TTS) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.5151
+- eval_runtime: 21.1648
+- eval_samples_per_second: 84.197
+- eval_steps_per_second: 1.795
+- epoch: 16.7331
+- step: 4200
 
 ## Model description
 
@@ -37,8 +44,6 @@ The following hyperparameters were used during training:
 - train_batch_size: 64
 - eval_batch_size: 48
 - seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 256
 - 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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceaab5efc4d8b9b8dbb2286588140d59eb3e272d638359fd2e27ba325a2ee934
+oid sha256:c1a52fe441b8c3bce69cb04c1e4ac2a0ea155d02f813270e9cda44db9234dcb5
 size 617574792

runs/Nov14_23-54-25_6aa7ecbbcfb5/events.out.tfevents.1731628470.6aa7ecbbcfb5.1822.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e90948489b2253cfb6e387ae9bbbd8dff943f3db78a84a1cc18e77d3c38f0d9b
-size 52310
+oid sha256:ac2400b7eb034ff63fd9c3f6f429f0cfa0c8d18d588b8186b7e9cd828f920c06
+size 53425