Configuration Parsing
Warning:
In adapter_config.json: "peft.base_model_name_or_path" must be a string
hindi-bengali-translator
This model is a fine-tuned version of unsloth/tinyllama-chat-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 9.0804
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- 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_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.0309 | 0.9906 | 92 | 9.5557 |
| 3.9824 | 1.9906 | 184 | 9.3047 |
| 3.9119 | 2.9906 | 276 | 9.2470 |
| 3.8886 | 3.9906 | 368 | 9.1900 |
| 3.8639 | 4.9906 | 460 | 9.1643 |
| 3.8628 | 5.9906 | 552 | 9.1318 |
| 3.9097 | 6.9906 | 644 | 9.1108 |
| 3.8363 | 7.9906 | 736 | 9.0947 |
| 3.8156 | 8.9906 | 828 | 9.0838 |
| 3.8048 | 9.9906 | 920 | 9.0804 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.3
- Pytorch 2.5.1+cu121
- Datasets 3.3.0
- Tokenizers 0.21.0
- Downloads last month
- 93
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for sudeshna84/hindi-bengali-translator
Base model
unsloth/tinyllama-chat-bnb-4bit