rubaistt-uz-ft2
This model is a fine-tuned version of islomov/rubaistt_v2_medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0188
- Wer: 2.0305
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: 5e-06
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1916 | 2.7855 | 1000 | 0.0188 | 2.0305 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2