w2v-bert-2.0-armenian-CV20.0
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: 0.1436
- Wer: 0.1106
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: 24
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 48
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.3661 | 1.9231 | 600 | 0.1561 | 0.1946 |
| 0.0878 | 3.8462 | 1200 | 0.1293 | 0.1404 |
| 0.0415 | 5.7692 | 1800 | 0.1203 | 0.1238 |
| 0.0199 | 7.6923 | 2400 | 0.1285 | 0.1136 |
| 0.0087 | 9.6154 | 3000 | 0.1436 | 0.1106 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0