metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: bert-finetuned-toxic
results: []
bert-finetuned-toxic
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: 0.3207
- F1: 0.7032
- Roc Auc: 0.9143
- Accuracy: 0.9069
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: 256
- eval_batch_size: 256
- 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 | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 499 | 0.1740 | 0.5646 | 0.9544 | 0.8619 |
| 0.2962 | 2.0 | 998 | 0.1595 | 0.5994 | 0.9551 | 0.8691 |
| 0.1545 | 3.0 | 1497 | 0.1715 | 0.6322 | 0.9509 | 0.8776 |
| 0.1218 | 4.0 | 1996 | 0.1883 | 0.6412 | 0.9467 | 0.8870 |
| 0.0976 | 5.0 | 2495 | 0.2497 | 0.6808 | 0.9265 | 0.9037 |
| 0.0807 | 6.0 | 2994 | 0.2411 | 0.6742 | 0.9331 | 0.8917 |
| 0.0682 | 7.0 | 3493 | 0.2955 | 0.6922 | 0.9183 | 0.8995 |
| 0.0597 | 8.0 | 3992 | 0.3207 | 0.7032 | 0.9143 | 0.9069 |
| 0.0533 | 9.0 | 4491 | 0.3207 | 0.6977 | 0.9158 | 0.9044 |
| 0.0487 | 10.0 | 4990 | 0.3407 | 0.7028 | 0.9091 | 0.9073 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1