diemlnt-qwen-3B-lora-wiki-1.0
This model is a fine-tuned version of Qwen/Qwen2.5-3B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5847
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 6875 | 1.5916 |
| 1.9156 | 2.0 | 13750 | 1.5860 |
| 1.8756 | 3.0 | 20625 | 1.5861 |
| 1.8756 | 4.0 | 27500 | 1.5833 |
| 1.86 | 5.0 | 34375 | 1.5828 |
| 1.8596 | 6.0 | 41250 | 1.5863 |
| 1.8596 | 7.0 | 48125 | 1.5847 |
Framework versions
- PEFT 0.15.0
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for Kudod/diemlnt-qwen-3B-lora-wiki-1.0
Base model
Qwen/Qwen2.5-3B