End of training
Browse files
README.md
CHANGED
|
@@ -16,7 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [fahadqazi/Sindhi-TTS](https://huggingface.co/fahadqazi/Sindhi-TTS) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,34 +40,18 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate:
|
| 39 |
-
- train_batch_size:
|
| 40 |
- eval_batch_size: 2
|
| 41 |
- seed: 42
|
| 42 |
-
- gradient_accumulation_steps:
|
| 43 |
- total_train_batch_size: 32
|
| 44 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 200
|
| 47 |
-
- training_steps:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
-
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
-
| 0.4462 | 0.2042 | 100 | 0.4506 |
|
| 55 |
-
| 0.4456 | 0.4084 | 200 | 0.4482 |
|
| 56 |
-
| 0.4424 | 0.6126 | 300 | 0.4468 |
|
| 57 |
-
| 0.4501 | 0.8167 | 400 | 0.4429 |
|
| 58 |
-
| 0.4393 | 1.0219 | 500 | 0.4435 |
|
| 59 |
-
| 0.4518 | 1.2261 | 600 | 0.4439 |
|
| 60 |
-
| 0.4459 | 1.4303 | 700 | 0.4423 |
|
| 61 |
-
| 0.4404 | 1.6345 | 800 | 0.4430 |
|
| 62 |
-
| 0.4414 | 1.8387 | 900 | 0.4423 |
|
| 63 |
-
| 0.4396 | 2.0439 | 1000 | 0.4421 |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.46.2
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [fahadqazi/Sindhi-TTS](https://huggingface.co/fahadqazi/Sindhi-TTS) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- eval_loss: 0.4602
|
| 20 |
+
- eval_runtime: 47.8291
|
| 21 |
+
- eval_samples_per_second: 36.421
|
| 22 |
+
- eval_steps_per_second: 18.211
|
| 23 |
+
- epoch: 13.2653
|
| 24 |
+
- step: 6500
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|
| 43 |
+
- learning_rate: 0.0001
|
| 44 |
+
- train_batch_size: 16
|
| 45 |
- eval_batch_size: 2
|
| 46 |
- seed: 42
|
| 47 |
+
- gradient_accumulation_steps: 2
|
| 48 |
- total_train_batch_size: 32
|
| 49 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- lr_scheduler_warmup_steps: 200
|
| 52 |
+
- training_steps: 10000
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
### Framework versions
|
| 56 |
|
| 57 |
- Transformers 4.46.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 617574792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61247efcd96572c3f52f6d23bee60e3ae41a058b91d77f8b0abe3b846cb6bf26
|
| 3 |
size 617574792
|
runs/Nov18_22-15-13_40219603e0ec/events.out.tfevents.1731968118.40219603e0ec.425.5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:406858290ef9506da99461a7020e3022af8fbf919e69f0d09eafb46e3307c7ce
|
| 3 |
+
size 79070
|