metadata
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_male_globo_add_token_2
results: []
speecht5_finetuned_male_globo_add_token_2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3445
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: 4
- eval_batch_size: 2
- 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: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3989 | 6.48 | 1000 | 0.3666 |
| 0.3899 | 12.97 | 2000 | 0.3541 |
| 0.3787 | 19.45 | 3000 | 0.3500 |
| 0.3756 | 25.93 | 4000 | 0.3494 |
| 0.3739 | 32.41 | 5000 | 0.3463 |
| 0.3728 | 38.9 | 6000 | 0.3448 |
| 0.3686 | 45.38 | 7000 | 0.3447 |
| 0.3687 | 51.86 | 8000 | 0.3446 |
| 0.3682 | 58.35 | 9000 | 0.3465 |
| 0.3683 | 64.83 | 10000 | 0.3445 |
Framework versions
- Transformers 4.39.0.dev0
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.2