Downloads · 30 days
24
4% of all-time downloads
qwen2.5-1.5b-mbpp-reasoning-sft
tokhey/qwen2.5-1.5b-mbpp-reasoning-sft
qwen2.5-1.5b-mbpp-reasoning-sft is a text generation model from tokhey. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
567
Public
Repo size
6.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt591 MB · 49%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Aug 1, 2026
- Updated
- Aug 1, 2026
- SHA
- 4a58413a
Try a prompt
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
qwen2.5-1.5b-mbpp-reasoning-sft
This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the reasoning_data dataset. It achieves the following results on the evaluation set:
- Loss: 0.3179
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 0.05
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4993 | 0.7921 | 50 | 0.3521 |
| 0.4264 | 1.5703 | 100 | 0.3239 |
| 0.3461 | 2.3485 | 150 | 0.3179 |
| 0.3491 | 3.1267 | 200 | 0.3195 |
| 0.3112 | 3.9188 | 250 | 0.3185 |
| 0.2995 | 4.6970 | 300 | 0.3243 |
| 0.2886 | 5.0 | 320 | 0.3243 |
Framework versions
- PEFT 0.18.1
- Transformers 5.8.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Created
- Aug 1, 2026
- Updated
- Aug 1, 2026