zlm_b64_le5_s4000 / README.md
mikhail-panzo's picture
End of training
f2ba687 verified
---
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: zlm_b64_le5_s4000
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# zlm_b64_le5_s4000
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: 0.4036
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- training_steps: 4010
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.7085 | 0.4188 | 500 | 0.6076 |
| 0.5896 | 0.8375 | 1000 | 0.5031 |
| 0.5195 | 1.2563 | 1500 | 0.4606 |
| 0.5009 | 1.6750 | 2000 | 0.4391 |
| 0.4854 | 2.0938 | 2500 | 0.4273 |
| 0.4643 | 2.5126 | 3000 | 0.4128 |
| 0.4572 | 2.9313 | 3500 | 0.4065 |
| 0.4508 | 3.3501 | 4000 | 0.4036 |
### Framework versions
- Transformers 4.41.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1