mms-1b-all-bigcgen-balanced-52
This model is a fine-tuned version of facebook/mms-1b-all on the BIGCGEN - BEM dataset. It achieves the following results on the evaluation set:
- Loss: inf
- Wer: 0.6061
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: 4
- seed: 52
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 30.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 8.9738 | 0.6098 | 100 | inf | 1.0002 |
| 4.7526 | 1.2195 | 200 | inf | 0.9998 |
| 3.9141 | 1.8293 | 300 | inf | 1.0182 |
| 1.0184 | 2.4390 | 400 | inf | 0.5978 |
| 0.856 | 3.0488 | 500 | inf | 0.6063 |
Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.0
- Downloads last month
- 7
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for csikasote/mms-1b-all-bigcgen-balanced-52
Base model
facebook/mms-1b-all