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_v6
results: []
SFT-Qwen2.5-Coder-3B_v6
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: 0.9536
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 |
|---|---|---|---|
| 1.064 | 0.2974 | 20 | 1.0908 |
| 0.8857 | 0.5948 | 40 | 1.0361 |
| 0.8355 | 0.8922 | 60 | 1.0029 |
| 0.7792 | 1.1784 | 80 | 0.9860 |
| 0.8453 | 1.4758 | 100 | 0.9692 |
| 0.738 | 1.7732 | 120 | 0.9574 |
| 0.7202 | 2.0595 | 140 | 0.9543 |
| 0.7281 | 2.3569 | 160 | 0.9545 |
| 0.5788 | 2.6543 | 180 | 0.9579 |
| 0.6853 | 2.9517 | 200 | 0.9536 |
Framework versions
- PEFT 0.18.0
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.4.1
- Tokenizers 0.22.1