g-assismoraes/deberta-semeval25task10-gpt2en

<!-- 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. -->

deberta-semeval25-fulltrain-translateen-gpt

This model is a fine-tuned version of microsoft/deberta-v3-base on the "Semeval-2025 Task 10, Subtask 2" dataset.

Model description

This model was trained for multi-label classification in the "SemEval 2025 Task 10, Subtask 2" taxonomy, with article texts translated into English by the GPT-4o-mini model.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 2e-05
• —trainbatchsize: 16
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —num_epochs: 10

Framework versions

• —Transformers 4.48.1
• —Pytorch 2.5.1+cu121
• —Datasets 3.2.0
• —Tokenizers 0.21.0