BingoGuard-qwen3-embedding-0.6B-classifier-2
This model is a fine-tuned version of Qwen/Qwen3-Embedding-0.6B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1683
- Accuracy: 0.9536
- F1: 0.7202
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: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 48
- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 3.2587 | 1.0 | 1215 | 0.1498 | 0.9319 | 0.6330 |
| 2.4709 | 2.0 | 2430 | 0.1254 | 0.9428 | 0.6705 |
| 1.9946 | 3.0 | 3645 | 0.1293 | 0.9452 | 0.6764 |
| 1.634 | 4.0 | 4860 | 0.1333 | 0.9457 | 0.6978 |
| 1.0223 | 5.0 | 6075 | 0.1683 | 0.9536 | 0.7202 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.4
- Downloads last month
- 5