metadata
base_model: Qwen/Qwen2.5-0.5B
library_name: peft
license: apache-2.0
tags:
- base_model:adapter:Qwen/Qwen2.5-0.5B
- lora
- transformers
model-index:
- name: Qwen2.5-0.5B-hate-classifier
results: []
Qwen2.5-0.5B-hate-classifier
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: 0.9760
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7272 | 1.0 | 450 | 0.6198 |
| 0.5183 | 2.0 | 900 | 0.6486 |
| 0.1324 | 3.0 | 1350 | 0.8556 |
| 0.0005 | 4.0 | 1800 | 0.9689 |
| 0.1691 | 5.0 | 2250 | 0.9760 |
Framework versions
- PEFT 0.17.1
- Transformers 4.46.3
- Pytorch 2.8.0+cu128
- Datasets 2.17.0
- Tokenizers 0.20.0