m2m100-1.2B-singlish-lora
This model is a fine-tuned version of facebook/m2m100_1.2B on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7277
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1135 | 1.0 | 626 | 0.9299 |
| 0.8521 | 2.0 | 1252 | 0.7741 |
| 0.7458 | 3.0 | 1878 | 0.7277 |
Framework versions
- PEFT 0.18.1
- Transformers 4.57.6
- Pytorch 2.9.1+cu128
- Datasets 4.5.0
- Tokenizers 0.22.2
- Downloads last month
- 4
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for RukDias/m2m100-1.2B-singlish-lora
Base model
facebook/m2m100_1.2B