Downloads · 30 days
5
2% of all-time downloads
USS-reward-model-baseline
athirorg/USS-reward-model-baseline
USS-reward-model-baseline is a machine learning model from athirorg. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
208
Public
Parameters
396M
22.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.2 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Model type
- modernbert
- Access
- Public
- Created
- May 27, 2026
- Updated
- May 27, 2026
- SHA
- c667c214
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
USS-reward-model-baseline
This model is a fine-tuned version of answerdotai/ModernBERT-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1701
- Mse: 0.1701
- Mae: 0.2693
- R2: 0.1181
- Spearman Correlation: 0.2833
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: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 10
- total_train_batch_size: 20
- 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: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Mse | Mae | R2 | Spearman Correlation |
|---|---|---|---|---|---|---|---|
| 7.0444 | 1.0 | 97 | 0.2106 | 0.2106 | 0.3080 | -0.0916 | nan |
| 2.0581 | 2.0 | 194 | 0.1701 | 0.1701 | 0.2693 | 0.1181 | 0.2833 |
| 1.6404 | 3.0 | 291 | 0.1800 | 0.1800 | 0.3289 | 0.0670 | 0.3333 |
| 1.1040 | 4.0 | 388 | 0.2168 | 0.2168 | 0.3728 | -0.1240 | 0.2631 |
| 0.5726 | 5.0 | 485 | 0.1988 | 0.1988 | 0.3510 | -0.0306 | 0.2295 |
| 0.3258 | 6.0 | 582 | 0.1803 | 0.1803 | 0.3161 | 0.0651 | 0.1804 |
| 0.1733 | 7.0 | 679 | 0.1891 | 0.1891 | 0.3286 | 0.0195 | 0.1746 |
| 0.1145 | 8.0 | 776 | 0.1812 | 0.1812 | 0.3248 | 0.0608 | 0.2181 |
| 0.0574 | 9.0 | 873 | 0.1823 | 0.1823 | 0.3247 | 0.0547 | 0.2339 |
| 0.0217 | 10.0 | 970 | 0.1814 | 0.1814 | 0.3183 | 0.0594 | 0.2032 |
Framework versions
- Transformers 5.9.0
- Pytorch 2.12.0+cu130
- Datasets 4.8.5
- Tokenizers 0.22.2
- Library
- transformers
- Type
- modernbert
- License
- apache-2.0
- Created
- May 27, 2026
- Updated
- May 27, 2026