Downloads · 30 days
1
2% of all-time downloads
USS-reward-model-grl-source
athirorg/USS-reward-model-grl-source
USS-reward-model-grl-source 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
45
Public
Parameters
396M
7.9 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
- 6385ac2d
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-grl-source
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: 52.9809
- Mse: 0.1859
- Mae: 0.2835
- R2: 0.0363
- Spearman Correlation: 0.1418
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 |
|---|---|---|---|---|---|---|---|
| 22.9021 | 1.0 | 97 | 1.5700 | 0.1938 | 0.2856 | -0.0045 | nan |
| 17.8187 | 2.0 | 194 | 2.1893 | 0.2106 | 0.3009 | -0.0917 | 0.1105 |
| 290.6176 | 3.0 | 291 | 47.6834 | 0.5032 | 0.5697 | -1.6088 | 0.1146 |
| 518.1736 | 4.0 | 388 | 54.6556 | 0.2628 | 0.3755 | -0.3622 | 0.1508 |
| 567.3146 | 5.0 | 485 | 57.8539 | 0.3017 | 0.4718 | -0.5641 | 0.1994 |
| 574.1879 | 6.0 | 582 | 56.7874 | 0.2290 | 0.4001 | -0.1873 | 0.1062 |
| 559.3920 | 7.0 | 679 | 55.2139 | 0.2447 | 0.3755 | -0.2685 | 0.1472 |
| 544.8656 | 8.0 | 776 | 54.0387 | 0.2628 | 0.3924 | -0.3626 | 0.1332 |
| 535.0054 | 9.0 | 873 | 53.2574 | 0.2067 | 0.2983 | -0.0716 | 0.1215 |
| 529.6823 | 10.0 | 970 | 52.9809 | 0.1859 | 0.2835 | 0.0363 | 0.1418 |
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