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_v7
results: []
SFT-Qwen2.5-Coder-3B_v7
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: 0.9745
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: 8
- 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 |
|---|---|---|---|
| 1.0502 | 0.2974 | 20 | 1.1186 |
| 0.9305 | 0.5948 | 40 | 1.0609 |
| 0.8083 | 0.8922 | 60 | 1.0288 |
| 0.8055 | 1.1784 | 80 | 1.0087 |
| 0.732 | 1.4758 | 100 | 0.9920 |
| 0.7372 | 1.7732 | 120 | 0.9833 |
| 0.7176 | 2.0595 | 140 | 0.9775 |
| 0.6343 | 2.3569 | 160 | 0.9807 |
| 0.7514 | 2.6543 | 180 | 0.9745 |
| 0.6888 | 2.9517 | 200 | 0.9752 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1