Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
qwen2.5-sft-translated-v1
This model is a fine-tuned version of ZeynepAltundal/qwen2.5-phase2-sft-v1-tr on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5072
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- 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
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5565 | 1.0 | 260 | 0.5660 |
| 0.495 | 2.0 | 520 | 0.5186 |
| 0.4333 | 3.0 | 780 | 0.5072 |
Framework versions
- PEFT 0.15.2
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.1
- Tokenizers 0.21.1
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ZeynepAltundal/qwen2.5-sft-translated-v1
Base model
ZeynepAltundal/qwen2.5-phase2-sft-v1-tr