toxicity-scorer-qwen
This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1649
- F1: 0.9371
- Accuracy: 0.9380
- Precision: 0.9365
- Recall: 0.9380
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 128
- total_eval_batch_size: 128
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Accuracy | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 0 | 0 | 2.2577 | 0.5343 | 0.4464 | 0.7333 | 0.4464 |
| 0.1462 | 1.0 | 8816 | 0.1422 | 0.9383 | 0.9400 | 0.9375 | 0.9400 |
| 0.1101 | 2.0 | 17632 | 0.1456 | 0.9386 | 0.9399 | 0.9379 | 0.9399 |
| 0.0869 | 3.0 | 26448 | 0.1649 | 0.9371 | 0.9380 | 0.9365 | 0.9380 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1
- Datasets 3.1.0
- Tokenizers 0.20.3