mms-1b-fl102-isixhosa-colab_10epochs_15warmup
This model is a fine-tuned version of facebook/mms-1b-fl102 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.9972
- 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: 8
- seed: 42
- gradient_accumulation_steps: 16
- 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: 15
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 9.1825 | 1.0 | 10 | 5.2773 | 0.9997 |
| 4.7278 | 2.0 | 20 | 4.3350 | 0.9997 |
| 3.8472 | 3.0 | 30 | 3.5459 | 0.9993 |
| 3.2713 | 4.0 | 40 | 3.2943 | 0.9982 |
| 3.0499 | 5.0 | 50 | 3.1241 | 1.0 |
| 2.9367 | 6.0 | 60 | 3.0573 | 0.9999 |
| 2.8904 | 7.0 | 70 | 3.0077 | 1.0 |
| 2.8566 | 8.0 | 80 | 2.9926 | 1.0 |
| 2.8472 | 9.0 | 90 | 2.9972 | 1.0 |
Framework versions
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 0
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for Jenalea/mms-1b-fl102-isixhosa-colab_10epochs_15warmup
Base model
facebook/mms-1b-fl102