LawToken-7B-a2
This model is a fine-tuned version of Qwen/Qwen2-7B on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.6911
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: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 8
- total_eval_batch_size: 32
- 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 |
|---|---|---|---|
| 1.1242 | 0.14 | 10000 | 1.1254 |
| 1.0428 | 0.28 | 20000 | 1.0009 |
| 0.9558 | 0.42 | 30000 | 0.9209 |
| 0.9393 | 0.56 | 40000 | 0.8528 |
| 0.8714 | 0.71 | 50000 | 0.7903 |
| 0.6933 | 0.85 | 60000 | 0.7313 |
| 0.6799 | 0.99 | 70000 | 0.6911 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.3.0a0+ebedce2
- Datasets 2.19.1
- Tokenizers 0.15.2