metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-base-uncased-finetuned-hateful-meme
results: []
bert-base-uncased-finetuned-hateful-meme
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0538
- Accuracy: 0.544
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 |
|---|---|---|---|---|
| 0.5795 | 1.0 | 532 | 0.7869 | 0.564 |
| 0.5101 | 2.0 | 1064 | 0.8646 | 0.56 |
| 0.4455 | 3.0 | 1596 | 0.9011 | 0.538 |
| 0.3926 | 4.0 | 2128 | 1.1856 | 0.542 |
| 0.3387 | 5.0 | 2660 | 1.1351 | 0.552 |
| 0.3056 | 6.0 | 3192 | 1.3704 | 0.55 |
| 0.2942 | 7.0 | 3724 | 1.7288 | 0.538 |
| 0.2665 | 8.0 | 4256 | 1.7215 | 0.544 |
| 0.2498 | 9.0 | 4788 | 1.8634 | 0.542 |
| 0.2357 | 10.0 | 5320 | 2.0538 | 0.544 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3