| --- |
| library_name: transformers |
| license: cc-by-nc-4.0 |
| base_model: facebook/mms-1b |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: mms-1b-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. --> |
|
|
| # mms-1b-gui |
|
|
| This model is a fine-tuned version of [facebook/mms-1b](https://huggingface.co/facebook/mms-1b) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.1145 |
| - Cer: 0.2776 |
|
|
| ## 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: 100 |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Cer | |
| |:-------------:|:------:|:----:|:---------------:|:------:| |
| | 7.8773 | 0.4329 | 100 | 1.5370 | 0.4601 | |
| | 2.6159 | 0.8658 | 200 | 1.0908 | 0.3136 | |
| | 2.2120 | 1.2987 | 300 | 0.8812 | 0.2603 | |
| | 1.9035 | 1.7316 | 400 | 0.8390 | 0.2335 | |
| | 1.7596 | 2.1645 | 500 | 0.7883 | 0.2456 | |
| | 1.4815 | 2.5974 | 600 | 0.7664 | 0.2175 | |
| | 1.5555 | 3.0303 | 700 | 0.7294 | 0.2231 | |
| | 1.2112 | 3.4632 | 800 | 0.7387 | 0.2377 | |
| | 1.2092 | 3.8961 | 900 | 0.6927 | 0.2201 | |
| | 1.1119 | 4.3290 | 1000 | 0.6847 | 0.2048 | |
| | 1.0152 | 4.7619 | 1100 | 0.6740 | 0.1889 | |
| | 1.0220 | 5.1948 | 1200 | 0.6773 | 0.2003 | |
| | 1.2641 | 5.6277 | 1300 | 0.9480 | 0.2511 | |
| | 2.1819 | 6.0606 | 1400 | 1.4692 | 0.3210 | |
| | 2.7651 | 6.4935 | 1500 | 1.4108 | 0.4450 | |
| | 2.4741 | 6.9264 | 1600 | 1.2238 | 0.3591 | |
| | 3.6614 | 7.3593 | 1700 | 1.1802 | 0.3484 | |
| | 2.1207 | 7.7922 | 1800 | 1.1016 | 0.3315 | |
| | 2.0560 | 8.2251 | 1900 | 1.0702 | 0.3137 | |
| | 2.0227 | 8.6580 | 2000 | 1.1102 | 0.2817 | |
| | 2.0418 | 9.0909 | 2100 | 1.1127 | 0.2782 | |
| | 2.0239 | 9.5238 | 2200 | 1.1074 | 0.2811 | |
| | 2.0523 | 9.9567 | 2300 | 1.1145 | 0.2776 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.1.0 |
| - Pytorch 2.9.1+cu128 |
| - Datasets 3.6.0 |
| - Tokenizers 0.22.2 |
| |
