| --- |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: FT-S5-LM |
| 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. --> |
|
|
| # FT-S5-LM |
|
|
| This model was trained from scratch on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.7422 |
| - Wer: 0.2650 |
|
|
| ## 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: 32 |
| - eval_batch_size: 8 |
| - seed: 42 |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_ratio: 0.1 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Wer | |
| |:-------------:|:-----:|:-----:|:---------------:|:------:| |
| | 1.9414 | 0.99 | 7100 | 0.8335 | 0.3649 | |
| | 0.408 | 1.97 | 14200 | 0.7352 | 0.3037 | |
| | 0.3353 | 2.96 | 21300 | 0.7797 | 0.2922 | |
| | 0.2987 | 3.95 | 28400 | 0.7119 | 0.2804 | |
| | 0.2745 | 4.94 | 35500 | 0.7512 | 0.2738 | |
| | 0.2565 | 5.92 | 42600 | 0.7550 | 0.2705 | |
| | 0.2431 | 6.91 | 49700 | 0.7319 | 0.2662 | |
| | 0.2315 | 7.9 | 56800 | 0.7422 | 0.2650 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.17.0 |
| - Pytorch 2.5.1+cu124 |
| - Datasets 3.6.0 |
| - Tokenizers 0.22.2 |
| |
