metadata
library_name: transformers
license: cc-by-nc-4.0
base_model: facebook/mms-1b-l1107
tags:
- generated_from_trainer
model-index:
- name: mms-1bl1107-tenakichwa-120
results: []
mms-1bl1107-tenakichwa-120
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: 0.2002
- Cer: 0.0571
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 |
|---|---|---|---|---|
| 2.3699 | 6.6723 | 400 | 0.5899 | 0.1454 |
| 0.7405 | 13.3361 | 800 | 0.4014 | 0.1038 |
| 0.5809 | 20.0 | 1200 | 0.2816 | 0.0806 |
| 0.4731 | 26.6723 | 1600 | 0.2002 | 0.0571 |
Framework versions
- Transformers 4.48.2
- Pytorch 2.5.1+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0