t5-whisper-training
This model is a fine-tuned version of UrukHan/t5-russian-spell on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1410
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2206 | 1.0 | 86 | 0.1880 |
| 0.0862 | 2.0 | 172 | 0.1808 |
| 0.0182 | 3.0 | 258 | 0.1594 |
| 0.0089 | 4.0 | 344 | 0.1431 |
| 0.0078 | 5.0 | 430 | 0.1410 |
Framework versions
- Transformers 5.17.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.1
- Tokenizers 0.23.1
- Downloads last month
- 34
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for polinOchka33/t5-whisper-training
Base model
UrukHan/t5-russian-spell