g-assismoraes / mdeberta-semeval25_maxf1_fold4

huggingface.co
Total runs: 213
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: October 28 2024
text-classification

Introduction of mdeberta-semeval25_maxf1_fold4

Model Details of mdeberta-semeval25_maxf1_fold4

mdeberta-semeval25_maxf1_fold4

This model is a fine-tuned version of microsoft/mdeberta-v3-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 9.5014
  • Precision Samples: 0.1859
  • Recall Samples: 0.4699
  • F1 Samples: 0.2429
  • Precision Macro: 0.8926
  • Recall Macro: 0.3346
  • F1 Macro: 0.2682
  • Precision Micro: 0.1665
  • Recall Micro: 0.3667
  • F1 Micro: 0.2290
  • Precision Weighted: 0.6548
  • Recall Weighted: 0.3667
  • F1 Weighted: 0.1249
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: 32
  • eval_batch_size: 32
  • 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: 10
Training results
Training Loss Epoch Step Validation Loss Precision Samples Recall Samples F1 Samples Precision Macro Recall Macro F1 Macro Precision Micro Recall Micro F1 Micro Precision Weighted Recall Weighted F1 Weighted
10.3744 1.0 19 10.7628 0.8966 0.0276 0.0276 0.9912 0.2349 0.2352 0.2105 0.0111 0.0211 0.9364 0.0111 0.0134
10.0964 2.0 38 10.4150 0.1931 0.2487 0.2006 0.9819 0.2551 0.2402 0.1855 0.1417 0.1606 0.8825 0.1417 0.0452
9.7497 3.0 57 10.2289 0.1563 0.3064 0.1883 0.9622 0.2717 0.2444 0.1528 0.1889 0.1689 0.8281 0.1889 0.0564
9.5354 4.0 76 10.0861 0.1637 0.3508 0.2028 0.9368 0.2875 0.2527 0.1555 0.2389 0.1884 0.7498 0.2389 0.0850
9.4556 5.0 95 9.8949 0.1741 0.4008 0.2220 0.9182 0.3137 0.2614 0.1610 0.3139 0.2128 0.7027 0.3139 0.1085
8.9584 6.0 114 9.7492 0.1781 0.4272 0.2286 0.9166 0.3207 0.2604 0.1565 0.3333 0.2130 0.6984 0.3333 0.1062
8.7492 7.0 133 9.6473 0.1947 0.4416 0.2409 0.9160 0.3267 0.2654 0.1647 0.35 0.224 0.6963 0.35 0.1186
8.2566 8.0 152 9.5650 0.1889 0.4622 0.2434 0.8985 0.3328 0.2666 0.1690 0.3639 0.2308 0.6673 0.3639 0.1223
8.7461 9.0 171 9.5200 0.1842 0.4668 0.2406 0.8925 0.3325 0.2680 0.1665 0.3611 0.2279 0.6552 0.3611 0.1250
8.5201 10.0 190 9.5014 0.1859 0.4699 0.2429 0.8926 0.3346 0.2682 0.1665 0.3667 0.2290 0.6548 0.3667 0.1249
Framework versions
  • Transformers 4.46.0
  • Pytorch 2.3.1
  • Datasets 2.21.0
  • Tokenizers 0.20.1

Runs of g-assismoraes mdeberta-semeval25_maxf1_fold4 on huggingface.co

213
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About mdeberta-semeval25_maxf1_fold4 huggingface.co Model

More mdeberta-semeval25_maxf1_fold4 license Visit here:

https://choosealicense.com/licenses/mit

mdeberta-semeval25_maxf1_fold4 huggingface.co

mdeberta-semeval25_maxf1_fold4 huggingface.co is an AI model on huggingface.co that provides mdeberta-semeval25_maxf1_fold4's model effect (), which can be used instantly with this g-assismoraes mdeberta-semeval25_maxf1_fold4 model. huggingface.co supports a free trial of the mdeberta-semeval25_maxf1_fold4 model, and also provides paid use of the mdeberta-semeval25_maxf1_fold4. Support call mdeberta-semeval25_maxf1_fold4 model through api, including Node.js, Python, http.

mdeberta-semeval25_maxf1_fold4 huggingface.co Url

https://huggingface.co/g-assismoraes/mdeberta-semeval25_maxf1_fold4

g-assismoraes mdeberta-semeval25_maxf1_fold4 online free

mdeberta-semeval25_maxf1_fold4 huggingface.co is an online trial and call api platform, which integrates mdeberta-semeval25_maxf1_fold4's modeling effects, including api services, and provides a free online trial of mdeberta-semeval25_maxf1_fold4, you can try mdeberta-semeval25_maxf1_fold4 online for free by clicking the link below.

g-assismoraes mdeberta-semeval25_maxf1_fold4 online free url in huggingface.co:

https://huggingface.co/g-assismoraes/mdeberta-semeval25_maxf1_fold4

mdeberta-semeval25_maxf1_fold4 install

mdeberta-semeval25_maxf1_fold4 is an open source model from GitHub that offers a free installation service, and any user can find mdeberta-semeval25_maxf1_fold4 on GitHub to install. At the same time, huggingface.co provides the effect of mdeberta-semeval25_maxf1_fold4 install, users can directly use mdeberta-semeval25_maxf1_fold4 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

mdeberta-semeval25_maxf1_fold4 install url in huggingface.co:

https://huggingface.co/g-assismoraes/mdeberta-semeval25_maxf1_fold4

Url of mdeberta-semeval25_maxf1_fold4

mdeberta-semeval25_maxf1_fold4 huggingface.co Url

Provider of mdeberta-semeval25_maxf1_fold4 huggingface.co

g-assismoraes
ORGANIZATIONS

Other API from g-assismoraes