camel_qwen_sft_rag
This model is a fine-tuned version of Qwen/Qwen3-0.6B-Base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5022
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: 2
- seed: 42
- gradient_accumulation_steps: 6
- total_train_batch_size: 24
- 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: 100
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5499 | 0.1939 | 400 | 0.5159 |
| 0.5288 | 0.3879 | 800 | 0.5077 |
| 0.5257 | 0.5818 | 1200 | 0.5040 |
| 0.5191 | 0.7758 | 1600 | 0.5025 |
| 0.5174 | 0.9697 | 2000 | 0.5022 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0