w2v-bert-2.0-waxal_lin_sna-1epoch
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the ./WAXAL_LIN_SNA - NA dataset. It achieves the following results on the evaluation set:
- Loss: 0.3524
- Wer: 0.3383
- Cer: 0.1054
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- 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_ratio: 0.1
- num_epochs: 1.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.7427 | 0.2236 | 250 | 0.4935 | 0.4386 | 0.1293 |
| 0.6489 | 0.4472 | 500 | 0.4214 | 0.3674 | 0.1133 |
| 0.3253 | 0.6708 | 750 | 0.3839 | 0.3446 | 0.1077 |
| 0.3311 | 0.8945 | 1000 | 0.3524 | 0.3381 | 0.1054 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.8.0+cu128
- Datasets 5.0.1
- Tokenizers 0.21.4