metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: boss-toxicity-3000-bert-base-uncased
results: []
boss-toxicity-3000-bert-base-uncased
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- F1: 0.7041
- Acc: 0.8559
- Loss: 0.7057
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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | F1 | Acc | Validation Loss |
|---|---|---|---|---|---|
| No log | 1.0 | 188 | 0.5425 | 0.6756 | 0.5975 |
| No log | 2.0 | 376 | 0.7372 | 0.8909 | 0.2901 |
| 0.4492 | 3.0 | 564 | 0.7260 | 0.8775 | 0.3477 |
| 0.4492 | 4.0 | 752 | 0.6595 | 0.8084 | 0.8310 |
| 0.4492 | 5.0 | 940 | 0.7041 | 0.8559 | 0.7057 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1