<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
roberta-base-finetuned-toxic-comment-detection
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1329
- Accuracy: 0.98
- Precision: 1.0
- Recall: 0.8095
- F1: 0.8947
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 |
|---|---|---|---|---|---|---|---|
| 0.4974 | 1.0 | 50 | 0.2428 | 0.895 | 0.0 | 0.0 | 0.0 |
| 0.2136 | 2.0 | 100 | 0.1820 | 0.935 | 0.6176 | 1.0 | 0.7636 |
| 0.18 | 3.0 | 150 | 0.1115 | 0.965 | 0.8182 | 0.8571 | 0.8372 |
| 0.1056 | 4.0 | 200 | 0.1426 | 0.97 | 1.0 | 0.7143 | 0.8333 |
| 0.0527 | 5.0 | 250 | 0.1483 | 0.975 | 0.9444 | 0.8095 | 0.8718 |
| 0.0474 | 6.0 | 300 | 0.1222 | 0.975 | 0.9444 | 0.8095 | 0.8718 |
| 0.0294 | 7.0 | 350 | 0.1329 | 0.98 | 1.0 | 0.8095 | 0.8947 |
| 0.0145 | 8.0 | 400 | 0.1271 | 0.975 | 0.9444 | 0.8095 | 0.8718 |
Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3
