cyberone-20250516-q2505b-ep05-instruct
This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0435
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 64
- total_train_batch_size: 8192
- total_eval_batch_size: 16
- 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_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4804 | 0.7054 | 30 | 0.1997 |
| 0.1283 | 1.4232 | 60 | 0.0682 |
| 0.0668 | 2.1411 | 90 | 0.0588 |
| 0.0549 | 2.8464 | 120 | 0.0551 |
| 0.0627 | 3.5643 | 150 | 0.0640 |
| 0.0568 | 4.2821 | 180 | 0.0535 |
| 0.0454 | 4.9875 | 210 | 0.0435 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.7.0+cu126
- Tokenizers 0.21.1
- Downloads last month
- 2