metadata
library_name: peft
license: apache-2.0
base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
tags:
- base_model:adapter:Qwen/Qwen3-Coder-30B-A3B-Instruct
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: SFT-Qwen3-Coder-30B
results: []
SFT-Qwen3-Coder-30B
This model is a fine-tuned version of Qwen/Qwen3-Coder-30B-A3B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6170
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: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0338 | 0.2985 | 20 | 0.8592 |
| 0.7854 | 0.5970 | 40 | 0.7745 |
| 0.7071 | 0.8955 | 60 | 0.7222 |
| 0.6461 | 1.1940 | 80 | 0.6904 |
| 0.597 | 1.4925 | 100 | 0.6732 |
| 0.6358 | 1.7910 | 120 | 0.6513 |
| 0.634 | 2.0896 | 140 | 0.6401 |
| 0.5645 | 2.3881 | 160 | 0.6328 |
| 0.5858 | 2.6866 | 180 | 0.6240 |
| 0.5167 | 2.9851 | 200 | 0.6170 |
| 0.5141 | 3.2836 | 220 | 0.6325 |
| 0.4637 | 3.5821 | 240 | 0.6199 |
| 0.4506 | 3.8806 | 260 | 0.6183 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1