pszemraj / deberta-v3-base-unified-mcqa-2-choice

huggingface.co
Total runs: 15
24-hour runs: -2
7-day runs: 0
30-day runs: 10
Model's Last Updated: December 29 2025
multiple-choice

Introduction of deberta-v3-base-unified-mcqa-2-choice

Model Details of deberta-v3-base-unified-mcqa-2-choice

deberta-v3-base-unified-mcqa-2-choice

If finetuning this further on downstream tasks (classification, etc) you may need to pass ignore_mismatched_sizes=True when loading this model.

This model is a fine-tuned version of microsoft/deberta-v3-base on the pszemraj/unified-mcqa dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3384
  • Accuracy: 0.9010
  • Num Input Tokens Seen: 15919768
Training procedure
Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 69
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 300
  • num_epochs: 3.0
Training results
Training Loss Epoch Step Validation Loss Accuracy Input Tokens Seen
0.3639 0.4579 400 0.3093 0.8700 2444384
0.308 0.9157 800 0.2792 0.8920 4861008
0.2517 1.3732 1200 0.2989 0.8890 7293776
0.2399 1.8310 1600 0.2796 0.8990 9723744
0.1082 2.2885 2000 0.3557 0.9030 12157608
0.1269 2.7463 2400 0.3486 0.8980 14592584
Framework versions
  • Transformers 4.51.3
  • Pytorch 2.6.0+cu124
  • Datasets 3.5.0
  • Tokenizers 0.21.1

Runs of pszemraj deberta-v3-base-unified-mcqa-2-choice on huggingface.co

15
Total runs
-2
24-hour runs
-3
3-day runs
0
7-day runs
10
30-day runs

More Information About deberta-v3-base-unified-mcqa-2-choice huggingface.co Model

More deberta-v3-base-unified-mcqa-2-choice license Visit here:

https://choosealicense.com/licenses/mit

deberta-v3-base-unified-mcqa-2-choice huggingface.co

deberta-v3-base-unified-mcqa-2-choice huggingface.co is an AI model on huggingface.co that provides deberta-v3-base-unified-mcqa-2-choice's model effect (), which can be used instantly with this pszemraj deberta-v3-base-unified-mcqa-2-choice model. huggingface.co supports a free trial of the deberta-v3-base-unified-mcqa-2-choice model, and also provides paid use of the deberta-v3-base-unified-mcqa-2-choice. Support call deberta-v3-base-unified-mcqa-2-choice model through api, including Node.js, Python, http.

deberta-v3-base-unified-mcqa-2-choice huggingface.co Url

https://huggingface.co/pszemraj/deberta-v3-base-unified-mcqa-2-choice

pszemraj deberta-v3-base-unified-mcqa-2-choice online free

deberta-v3-base-unified-mcqa-2-choice huggingface.co is an online trial and call api platform, which integrates deberta-v3-base-unified-mcqa-2-choice's modeling effects, including api services, and provides a free online trial of deberta-v3-base-unified-mcqa-2-choice, you can try deberta-v3-base-unified-mcqa-2-choice online for free by clicking the link below.

pszemraj deberta-v3-base-unified-mcqa-2-choice online free url in huggingface.co:

https://huggingface.co/pszemraj/deberta-v3-base-unified-mcqa-2-choice

deberta-v3-base-unified-mcqa-2-choice install

deberta-v3-base-unified-mcqa-2-choice is an open source model from GitHub that offers a free installation service, and any user can find deberta-v3-base-unified-mcqa-2-choice on GitHub to install. At the same time, huggingface.co provides the effect of deberta-v3-base-unified-mcqa-2-choice install, users can directly use deberta-v3-base-unified-mcqa-2-choice installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

deberta-v3-base-unified-mcqa-2-choice install url in huggingface.co:

https://huggingface.co/pszemraj/deberta-v3-base-unified-mcqa-2-choice

Url of deberta-v3-base-unified-mcqa-2-choice

deberta-v3-base-unified-mcqa-2-choice huggingface.co Url

Provider of deberta-v3-base-unified-mcqa-2-choice huggingface.co

pszemraj
ORGANIZATIONS

Other API from pszemraj