Sponsored by Vmake Labs Video Enhancer
Toolify Toolify logo
AI Models
roberta-bias-reward-model

SaketR1 / roberta-bias-reward-model

Run on huggingface.co
huggingface.co
Total runs: 8
24-hour runs: 0
7-day runs: -26
30-day runs: -41
Model's Last Updated: November 11 2025
text-classification

Introduction of roberta-bias-reward-model

Model Details of roberta-bias-reward-model

roberta-bias-reward-model

This model is a fine-tuned version of nlply/quantifying-stereotype-roberta on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0122
  • Mse: 0.0122
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: 0.0001
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 30
Training results
Training Loss Epoch Step Validation Loss Mse
0.0322 1.0 54 0.0408 0.0408
0.0172 2.0 108 0.0175 0.0175
0.0121 3.0 162 0.0124 0.0124
0.0126 4.0 216 0.0123 0.0123
0.0099 5.0 270 0.0167 0.0167
0.0097 6.0 324 0.0122 0.0122
0.0089 7.0 378 0.0154 0.0154
0.007 8.0 432 0.0121 0.0121
0.007 9.0 486 0.0119 0.0119
0.0057 10.0 540 0.0122 0.0122
0.0055 11.0 594 0.0184 0.0184
0.0055 12.0 648 0.0128 0.0128
0.0048 13.0 702 0.0164 0.0164
0.004 14.0 756 0.0128 0.0128
0.003 15.0 810 0.0125 0.0125
0.0033 16.0 864 0.0124 0.0124
0.0029 17.0 918 0.0120 0.0120
0.0026 18.0 972 0.0131 0.0131
0.0026 19.0 1026 0.0130 0.0130
0.0025 20.0 1080 0.0124 0.0124
0.0026 21.0 1134 0.0132 0.0132
0.0026 22.0 1188 0.0130 0.0130
0.0023 23.0 1242 0.0127 0.0127
0.0023 24.0 1296 0.0123 0.0123
0.0019 25.0 1350 0.0129 0.0129
0.0019 26.0 1404 0.0121 0.0121
0.0019 27.0 1458 0.0123 0.0123
0.0018 28.0 1512 0.0123 0.0123
0.0019 29.0 1566 0.0123 0.0123
0.0016 30.0 1620 0.0122 0.0122
Framework versions
  • Transformers 4.56.1
  • Pytorch 2.8.0+cu126
  • Datasets 4.0.0
  • Tokenizers 0.22.0

Runs of SaketR1 roberta-bias-reward-model on huggingface.co

8
Total runs
0
24-hour runs
0
3-day runs
-26
7-day runs
-41
30-day runs

More Information About roberta-bias-reward-model huggingface.co Model

More roberta-bias-reward-model license Visit here:

https://choosealicense.com/licenses/mit

roberta-bias-reward-model huggingface.co

roberta-bias-reward-model huggingface.co is an AI model on huggingface.co that provides roberta-bias-reward-model's model effect (), which can be used instantly with this SaketR1 roberta-bias-reward-model model. huggingface.co supports a free trial of the roberta-bias-reward-model model, and also provides paid use of the roberta-bias-reward-model. Support call roberta-bias-reward-model model through api, including Node.js, Python, http.

roberta-bias-reward-model huggingface.co Url

https://huggingface.co/SaketR1/roberta-bias-reward-model

SaketR1 roberta-bias-reward-model online free

roberta-bias-reward-model huggingface.co is an online trial and call api platform, which integrates roberta-bias-reward-model's modeling effects, including api services, and provides a free online trial of roberta-bias-reward-model, you can try roberta-bias-reward-model online for free by clicking the link below.

SaketR1 roberta-bias-reward-model online free url in huggingface.co:

https://huggingface.co/SaketR1/roberta-bias-reward-model

roberta-bias-reward-model install

roberta-bias-reward-model is an open source model from GitHub that offers a free installation service, and any user can find roberta-bias-reward-model on GitHub to install. At the same time, huggingface.co provides the effect of roberta-bias-reward-model install, users can directly use roberta-bias-reward-model installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

roberta-bias-reward-model install url in huggingface.co:

https://huggingface.co/SaketR1/roberta-bias-reward-model

Url of roberta-bias-reward-model

roberta-bias-reward-model huggingface.co Url

Provider of roberta-bias-reward-model huggingface.co

SaketR1
ORGANIZATIONS
huggingface.co

Other API from SaketR1

 huggingface.co
SaketR1/scc_rm

Total runs: 32
Run Growth: 14
Growth Rate: 43.75%
Updated:November 28 2025
huggingface.co
SaketR1/bias-grpo-rm

Total runs: 26
Run Growth: -11
Growth Rate: -42.31%
Updated:November 28 2025
huggingface.co
SaketR1/more_scc_rm

Total runs: 21
Run Growth: 3
Growth Rate: 14.29%
Updated:December 10 2025
huggingface.co
SaketR1/fresh_qa_rm

Total runs: 19
Run Growth: 6
Growth Rate: 31.58%
Updated:November 25 2025
huggingface.co
SaketR1/bias-dpo-uq

Total runs: 7
Run Growth: -9
Growth Rate: -128.57%
Updated:October 23 2025
huggingface.co
SaketR1/biasdpo-v3

Total runs: 6
Run Growth: 4
Growth Rate: 66.67%
Updated:October 08 2025
huggingface.co
SaketR1/ai4mars

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:October 22 2025
huggingface.co
SaketR1/bias-gspo

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:February 17 2026