LawToken-0.5B-a2
This model is a fine-tuned version of Qwen/Qwen2-0.5B on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.8634
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.14 | 0.14 | 10000 | 1.1605 |
| 1.0485 | 0.28 | 20000 | 1.0663 |
| 1.0592 | 0.42 | 30000 | 1.0069 |
| 0.9293 | 0.56 | 40000 | 0.9609 |
| 0.8503 | 0.71 | 50000 | 0.9210 |
| 0.9322 | 0.85 | 60000 | 0.8858 |
| 0.8238 | 0.99 | 70000 | 0.8634 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.3.0a0+ebedce2
- Datasets 2.19.1
- Tokenizers 0.15.2