| --- |
| library_name: transformers |
| license: mit |
| base_model: facebook/w2v-bert-2.0 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: w2v-bert-2.0-gui |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # w2v-bert-2.0-gui |
|
|
| This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 2.9872 |
| - Cer: 0.9839 |
|
|
| ## 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: 0.0003 |
| - train_batch_size: 8 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - gradient_accumulation_steps: 2 |
| - total_train_batch_size: 16 |
| - 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: 500 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Cer | |
| |:-------------:|:------:|:----:|:---------------:|:------:| |
| | 20.5172 | 0.4329 | 100 | 6.1927 | 1.0 | |
| | 9.1755 | 0.8658 | 200 | 3.0737 | 1.0 | |
| | 5.9769 | 1.2987 | 300 | 2.9275 | 0.9839 | |
| | 5.8767 | 1.7316 | 400 | 2.9258 | 0.9839 | |
| | 6.0773 | 2.1645 | 500 | 2.9087 | 0.9839 | |
| | 5.9225 | 2.5974 | 600 | 2.9052 | 0.9839 | |
| | 5.9328 | 3.0303 | 700 | 2.9009 | 0.9839 | |
| | 5.8895 | 3.4632 | 800 | 2.8969 | 0.9368 | |
| | 5.8888 | 3.8961 | 900 | 2.9218 | 0.9839 | |
| | 5.9117 | 4.3290 | 1000 | 2.9595 | 0.9672 | |
| | 5.9625 | 4.7619 | 1100 | 2.9033 | 0.9839 | |
| | 6.0566 | 5.1948 | 1200 | 2.9598 | 0.9839 | |
| | 5.9214 | 5.6277 | 1300 | 2.9107 | 0.9839 | |
| | 5.9976 | 6.0606 | 1400 | 2.9289 | 0.9839 | |
| | 5.9904 | 6.4935 | 1500 | 2.9166 | 0.9839 | |
| | 5.9354 | 6.9264 | 1600 | 2.9257 | 0.9839 | |
| | 6.0097 | 7.3593 | 1700 | 2.9428 | 0.9839 | |
| | 6.0392 | 7.7922 | 1800 | 2.9378 | 0.9839 | |
| | 5.9639 | 8.2251 | 1900 | 2.9657 | 0.9839 | |
| | 6.0595 | 8.6580 | 2000 | 2.9771 | 0.9839 | |
| | 6.0797 | 9.0909 | 2100 | 2.9865 | 0.9839 | |
| | 6.0741 | 9.5238 | 2200 | 2.9870 | 0.9839 | |
| | 6.0342 | 9.9567 | 2300 | 2.9872 | 0.9839 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.1.0 |
| - Pytorch 2.9.1+cu128 |
| - Datasets 3.6.0 |
| - Tokenizers 0.22.2 |
| |
