Qwen3-Reranker-0.6B-finetune-lower-lr
This model is a fine-tuned version of Qwen/Qwen3-Reranker-0.6B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3753
- Spearman: 0.5984
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: 9e-06
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Spearman |
|---|---|---|---|---|
| No log | 0 | 0 | 1.2718 | -0.0290 |
| 0.5353 | 0.4916 | 1000 | 0.3884 | 0.5245 |
| 0.216 | 0.9833 | 2000 | 0.3760 | 0.5713 |
| 0.5578 | 1.4749 | 3000 | 0.3800 | 0.5892 |
| 0.5515 | 1.9666 | 4000 | 0.3692 | 0.5993 |
| 0.4673 | 2.4582 | 5000 | 0.3753 | 0.5983 |
| 0.2112 | 2.9499 | 6000 | 0.3753 | 0.5984 |
Framework versions
- Transformers 4.56.2
- Pytorch 2.8.0+cu128
- Datasets 3.6.0
- Tokenizers 0.22.1
- Downloads last month
- 5