--- license: apache-2.0 tags: - generated_from_trainer base_model: bert-base-uncased model-index: - name: bert-hateful-memes-expanded results: [] --- # bert-hateful-memes-expanded This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on texts from the following datasets: - [Hateful Memes](https://hatefulmemeschallenge.com/), `train`, `dev_seen` and `dev_unseen` - [HarMeme](https://github.com/di-dimitrov/harmeme), `train`, `val` and `test` - [MultiOFF](https://github.com/bharathichezhiyan/Multimodal-Meme-Classification-Identifying-Offensive-Content-in-Image-and-Text), `Training`, `Validation` and `Testing` It achieves the following results on the evaluation set: - Loss: 3.7600 ## 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: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3.0 ### Training results ### Framework versions - Transformers 4.11.0 - Pytorch 1.8.1+cu102 - Datasets 1.8.0 - Tokenizers 0.10.2