Numina_QwQ_5k
This model is a fine-tuned version of meta-llama/Llama-3.1-8B on the Numina_QwQ_5k dataset. It achieves the following results on the evaluation set:
- Loss: 0.7715
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 4
- total_eval_batch_size: 4
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4365 | 0.8475 | 100 | 0.4594 |
| 0.3153 | 1.6949 | 200 | 0.4605 |
| 0.1431 | 2.5424 | 300 | 0.5334 |
| 0.0624 | 3.3898 | 400 | 0.6490 |
| 0.0161 | 4.2373 | 500 | 0.7637 |
Framework versions
- Transformers 4.46.1
- Pytorch 2.6.0+cu124
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 3
Model tree for cutelemonlili/random_1DySG3Auj8b4bq1b
Base model
meta-llama/Llama-3.1-8B