| | --- |
| | library_name: transformers |
| | tags: |
| | - generated_from_trainer |
| | metrics: |
| | - wer |
| | model-index: |
| | - name: ssc-sco-w2vbase-model |
| | 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. --> |
| |
|
| | # ssc-sco-w2vbase-model |
| |
|
| | This model was trained from scratch on an unknown dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 3.2065 |
| | - Cer: 0.9997 |
| | - Wer: 1.0 |
| |
|
| | ## 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: 2 |
| | - eval_batch_size: 12 |
| | - seed: 42 |
| | - gradient_accumulation_steps: 2 |
| | - total_train_batch_size: 4 |
| | - 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 | |
| | |:-------------:|:------:|:----:|:---------------:|:------:|:---:| |
| | | 3.002 | 1.9231 | 200 | 3.2523 | 0.9997 | 1.0 | |
| | | 3.0059 | 3.8462 | 400 | 3.2065 | 0.9997 | 1.0 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.52.1 |
| | - Pytorch 2.9.1+cu128 |
| | - Datasets 3.6.0 |
| | - Tokenizers 0.21.4 |
| |
|
