db2-qwen14b-next-v017-lora
This model is a fine-tuned version of Qwen/Qwen2.5-14B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1416
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: 3e-05
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 7
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.236 | 0.3172 | 25 | 2.1044 |
| 1.7 | 0.6344 | 50 | 1.5967 |
| 1.3488 | 0.9516 | 75 | 1.2718 |
| 1.1836 | 1.2688 | 100 | 1.1851 |
| 1.1498 | 1.5860 | 125 | 1.1501 |
| 1.103 | 1.9033 | 150 | 1.1416 |
Framework versions
- PEFT 0.13.0
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 4.8.5
- Tokenizers 0.20.3
- Downloads last month
- 37
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support