router-qwen3-0.6b-text-only-v3
This model is a fine-tuned version of Qwen/Qwen3-0.6B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5504
- Accuracy: 0.7443
- Precision: 0.7406
- Recall: 0.7443
- F1: 0.7302
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- 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
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 0 | 0 | 0.8251 | 0.5568 | 0.5940 | 0.5568 | 0.5652 |
| 0.7025 | 0.2273 | 20 | 0.5792 | 0.7102 | 0.7296 | 0.7102 | 0.6644 |
| 0.6662 | 0.4545 | 40 | 0.5866 | 0.7273 | 0.7263 | 0.7273 | 0.7042 |
| 0.5552 | 0.6818 | 60 | 0.6031 | 0.7159 | 0.7225 | 0.7159 | 0.7184 |
| 0.6073 | 0.9091 | 80 | 0.5718 | 0.7045 | 0.7166 | 0.7045 | 0.7083 |
| 0.5158 | 1.1364 | 100 | 0.5326 | 0.75 | 0.7452 | 0.75 | 0.7460 |
| 0.6436 | 1.3636 | 120 | 0.7685 | 0.5739 | 0.7245 | 0.5739 | 0.5608 |
| 0.5496 | 1.5909 | 140 | 0.5376 | 0.7045 | 0.7009 | 0.7045 | 0.7024 |
| 0.5128 | 1.8182 | 160 | 0.5504 | 0.7443 | 0.7406 | 0.7443 | 0.7302 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu128
- Datasets 4.2.0
- Tokenizers 0.22.1