Downloads · 30 days
6
4% of all-time downloads
USS-reward-model-ordinal
athirorg/USS-reward-model-ordinal
USS-reward-model-ordinal 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
141
Public
Parameters
396M
15.8 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
- Jun 5, 2026
- Updated
- Jun 5, 2026
- SHA
- dbd78d10
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-ordinal
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: 0.1466
- Accuracy: 0.7957
- Mae: 0.2074
- Mse: 0.2136
- Spearman: 0.1565
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 | Accuracy | Mae | Mse | Spearman |
|---|---|---|---|---|---|---|---|
| 1.9625 | 1.0 | 97 | 0.1664 | 0.7895 | 0.2136 | 0.2198 | nan |
| 1.7734 | 2.0 | 194 | 0.1560 | 0.7864 | 0.2167 | 0.2229 | -0.0219 |
| 1.6929 | 3.0 | 291 | 0.1500 | 0.7895 | 0.2136 | 0.2198 | 0.1267 |
| 1.6534 | 4.0 | 388 | 0.1466 | 0.7957 | 0.2074 | 0.2136 | 0.1565 |
| 1.5126 | 5.0 | 485 | 0.1476 | 0.7771 | 0.2260 | 0.2322 | 0.0783 |
| 1.2003 | 6.0 | 582 | 0.1716 | 0.7647 | 0.2353 | 0.2353 | 0.2609 |
| 0.5857 | 7.0 | 679 | 0.2275 | 0.6997 | 0.3003 | 0.3003 | 0.2808 |
| 0.1346 | 8.0 | 776 | 0.2655 | 0.7492 | 0.2508 | 0.2508 | 0.2835 |
| 0.0169 | 9.0 | 873 | 0.3173 | 0.7616 | 0.2384 | 0.2384 | 0.2765 |
| 0.0017 | 10.0 | 970 | 0.3322 | 0.7709 | 0.2291 | 0.2291 | 0.2520 |
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
- Jun 5, 2026
- Updated
- Jun 5, 2026