ssc-mmc-mms-model-mix-adapt-max2
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1691
- Cer: 0.2699
- Wer: 0.6424
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: 1
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Use OptimizerNames.ADAMW_TORCH 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 |
|---|---|---|---|---|---|
| 0.8458 | 0.9112 | 200 | 1.2395 | 0.2885 | 0.6768 |
| 0.7683 | 1.8200 | 400 | 1.1760 | 0.2768 | 0.6548 |
| 0.7494 | 2.7289 | 600 | 1.2018 | 0.2785 | 0.6542 |
| 0.6769 | 3.6378 | 800 | 1.1792 | 0.2782 | 0.6574 |
| 0.6291 | 4.5467 | 1000 | 1.1691 | 0.2699 | 0.6424 |
Framework versions
- Transformers 4.52.1
- Pytorch 2.9.1+cu128
- Datasets 3.6.0
- Tokenizers 0.21.4
- Downloads last month
- -