mms-1bl1107-toratan-60
This model is a fine-tuned version of facebook/mms-1b-l1107 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6195
- Cer: 0.2022
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 3.4772 | 8.3333 | 400 | 1.1662 | 0.2992 |
| 1.2712 | 16.6667 | 800 | 0.8517 | 0.2568 |
| 1.0191 | 25.0 | 1200 | 0.6195 | 0.2022 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- 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 colorlessideas/mms-1bl1107-toratan-60
Base model
facebook/mms-1b-l1107