metadata
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
model-index:
- name: my-roberta-for-hateful-meme-classification
results: []
datasets:
- limjiayi/hateful_memes_expanded
my-roberta-for-hateful-meme-classification
This model is a fine-tuned version of xlm-roberta-base on an hateful meme dataset. It achieves the following results on the evaluation set:
- Loss: 0.6894
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5181 | 1.0 | 806 | 0.7357 |
| 0.5235 | 2.0 | 1612 | 0.7480 |
| 0.4906 | 3.0 | 2418 | 0.7239 |
| 0.4673 | 4.0 | 3224 | 0.7252 |
| 0.4678 | 5.0 | 4030 | 0.6894 |
| 0.4481 | 6.0 | 4836 | 0.7794 |
| 0.4038 | 7.0 | 5642 | 0.7926 |
| 0.3052 | 8.0 | 6448 | 0.9150 |
| 0.2344 | 9.0 | 7254 | 1.1734 |
| 0.271 | 10.0 | 8060 | 1.1404 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1