camel_qwen_sft
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: 0.5013
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 |
|---|---|---|---|
| 0.5374 | 0.1212 | 500 | 0.5227 |
| 0.5229 | 0.2424 | 1000 | 0.5129 |
| 0.5135 | 0.3636 | 1500 | 0.5077 |
| 0.5113 | 0.4848 | 2000 | 0.5045 |
| 0.51 | 0.6061 | 2500 | 0.5027 |
| 0.5119 | 0.7273 | 3000 | 0.5017 |
| 0.5069 | 0.8485 | 3500 | 0.5014 |
| 0.508 | 0.9697 | 4000 | 0.5013 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0