ssc-hch-mms-model-mix-adapt-max
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4899
- Cer: 0.1630
- Wer: 0.7874
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: 0.001
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- 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
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer | Wer |
|---|---|---|---|---|---|
| 0.517 | 0.9479 | 200 | 0.5976 | 0.1904 | 0.9079 |
| 0.4674 | 1.8957 | 400 | 0.5464 | 0.1734 | 0.8182 |
| 0.4283 | 2.8436 | 600 | 0.5049 | 0.1653 | 0.7932 |
| 0.3721 | 3.7915 | 800 | 0.4870 | 0.1591 | 0.7805 |
| 0.3533 | 4.7393 | 1000 | 0.4899 | 0.1630 | 0.7874 |
Framework versions
- Transformers 4.57.2
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.22.0
- Downloads last month
- -