Qwen3-Reranker-0.6B-finetune

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: 0.3883
  • Spearman: 0.5197

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: 5e-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
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Spearman
No log 0 0 0.4995 -0.0788
0.5452 0.4916 1000 0.3987 0.4798
0.234 0.9833 2000 0.3926 0.5032
0.7425 1.4749 3000 0.3907 0.5146
0.5159 1.9666 4000 0.3893 0.5188
0.5286 2.4582 5000 0.3883 0.5192
0.2859 2.9499 6000 0.3883 0.5197

Framework versions

  • Transformers 4.56.2
  • Pytorch 2.8.0+cu128
  • Datasets 3.6.0
  • Tokenizers 0.22.1
Downloads last month
126
Safetensors
Model size
0.6B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Mithilss/Qwen3-Reranker-0.6B-finetune

Finetuned
(11)
this model