metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: bert-base-uncased-finetuned-toxic-comment-detection-ws23
results: []
bert-base-uncased-finetuned-toxic-comment-detection-ws23
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: 0.1991
- Accuracy: 0.945
- Precision: 0.7273
- Recall: 0.7619
- F1: 0.7442
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
---|---|---|---|---|---|---|---|
0.4756 | 1.0 | 50 | 0.2585 | 0.91 | 1.0 | 0.1429 | 0.25 |
0.1843 | 2.0 | 100 | 0.1417 | 0.93 | 0.7333 | 0.5238 | 0.6111 |
0.1014 | 3.0 | 150 | 0.2207 | 0.935 | 0.9 | 0.4286 | 0.5806 |
0.0481 | 4.0 | 200 | 0.1991 | 0.945 | 0.7273 | 0.7619 | 0.7442 |
0.0105 | 5.0 | 250 | 0.2082 | 0.945 | 0.75 | 0.7143 | 0.7317 |
0.0028 | 6.0 | 300 | 0.2249 | 0.945 | 0.75 | 0.7143 | 0.7317 |
0.0017 | 7.0 | 350 | 0.2379 | 0.945 | 0.7273 | 0.7619 | 0.7442 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Tokenizers 0.15.0