metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: bert-based_uncased-finetuned-binary_hate_speech
results: []
bert-based_uncased-finetuned-binary_hate_speech
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: 0.5093
- Accuracy: 0.8300
- F1: 0.8383
- Precision: 0.7992
- Recall: 0.8815
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.4752 | 1.0 | 1941 | 0.4343 | 0.8135 | 0.8171 | 0.8017 | 0.8331 |
| 0.3456 | 2.0 | 3882 | 0.4221 | 0.8305 | 0.8394 | 0.7974 | 0.8861 |
| 0.2434 | 3.0 | 5823 | 0.5093 | 0.8300 | 0.8383 | 0.7992 | 0.8815 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1