metadata
base_model: vinai/bertweet-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bertweet-base-finetuned-hateful-meme
results: []
bertweet-base-finetuned-hateful-meme
This model is a fine-tuned version of vinai/bertweet-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6262
- Accuracy: 0.532
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5865 | 1.0 | 532 | 0.7576 | 0.564 |
| 0.5203 | 2.0 | 1064 | 0.8139 | 0.562 |
| 0.4746 | 3.0 | 1596 | 0.9082 | 0.566 |
| 0.4377 | 4.0 | 2128 | 1.0089 | 0.538 |
| 0.3858 | 5.0 | 2660 | 0.9339 | 0.558 |
| 0.3561 | 6.0 | 3192 | 1.0688 | 0.54 |
| 0.3292 | 7.0 | 3724 | 1.4158 | 0.532 |
| 0.3009 | 8.0 | 4256 | 1.3316 | 0.54 |
| 0.2831 | 9.0 | 4788 | 1.5418 | 0.532 |
| 0.269 | 10.0 | 5320 | 1.6262 | 0.532 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3