WAXAL-mas-lug-sog-w2v-bert-2.0
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4913
- Cer: 0.0871
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-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use 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: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 8.5286 | 1.5088 | 300 | 0.6984 | 0.1722 |
| 1.5726 | 3.0151 | 600 | 0.5030 | 0.1168 |
| 0.8499 | 4.5239 | 900 | 0.4128 | 0.0979 |
| 0.5808 | 6.0302 | 1200 | 0.3862 | 0.0906 |
| 0.3597 | 7.5390 | 1500 | 0.4201 | 0.0886 |
| 0.2199 | 9.0453 | 1800 | 0.4574 | 0.0869 |
| 0.2199 | 10.0 | 1990 | 0.4913 | 0.0871 |
Framework versions
- Transformers 5.13.0
- Pytorch 2.13.0+cu130
- Datasets 5.0.0
- Tokenizers 0.22.2