qwen36-27b-cyber-lora
This model is a fine-tuned version of Qwen/Qwen3.6-27B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7466
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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- 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: cosine
- lr_scheduler_warmup_steps: 21
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1136 | 0.2860 | 100 | 1.1353 |
| 0.9834 | 0.5719 | 200 | 1.0500 |
| 0.9057 | 0.8579 | 300 | 0.9419 |
| 0.5367 | 1.1430 | 400 | 0.8974 |
| 0.5223 | 1.4290 | 500 | 0.8172 |
| 0.4351 | 1.7149 | 600 | 0.7637 |
| 0.4466 | 2.0 | 700 | 0.7466 |
Framework versions
- PEFT 0.20.0
- Transformers 5.14.1
- Pytorch 2.11.0+cu130
- Datasets 5.0.1
- Tokenizers 0.22.2