metadata
library_name: peft
license: other
base_model: Qwen/Qwen2.5-Coder-3B-Instruct
tags:
- base_model:adapter:Qwen/Qwen2.5-Coder-3B-Instruct
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: SFT-Qwen2.5-Coder-3B_v1.2s
results: []
SFT-Qwen2.5-Coder-3B_v1.2s
This model is a fine-tuned version of Qwen/Qwen2.5-Coder-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4859
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: 2
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9411 | 0.1985 | 20 | 0.7566 |
| 0.7658 | 0.3970 | 40 | 0.6418 |
| 0.6313 | 0.5955 | 60 | 0.5926 |
| 0.6186 | 0.7940 | 80 | 0.5650 |
| 0.5868 | 0.9926 | 100 | 0.5429 |
| 0.467 | 1.1886 | 120 | 0.5286 |
| 0.5086 | 1.3871 | 140 | 0.5205 |
| 0.4747 | 1.5856 | 160 | 0.5111 |
| 0.4872 | 1.7841 | 180 | 0.5012 |
| 0.5184 | 1.9826 | 200 | 0.4954 |
| 0.404 | 2.1787 | 220 | 0.5021 |
| 0.3772 | 2.3772 | 240 | 0.5040 |
| 0.4188 | 2.5757 | 260 | 0.4901 |
| 0.446 | 2.7742 | 280 | 0.4885 |
| 0.4378 | 2.9727 | 300 | 0.4859 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1