Downloads · 30 days
17
35% of all-time downloads
qwen2.5-1.5b-instruct-genai-v0.1
mmustafa2194/qwen2.5-1.5b-instruct-genai-v0.1
qwen2.5-1.5b-instruct-genai-v0.1 is a machine learning model from mmustafa2194. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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
48
Public
Repo size
4.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt591 MB · 49%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jul 1, 2025
- Updated
- Jul 3, 2025
- SHA
- 26c22bea
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-instruct-genai-v0.1
This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the finetune_train_genai_v1 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7441
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5869 | 0.4 | 100 | 0.5143 |
| 0.5893 | 0.8 | 200 | 0.4920 |
| 0.2421 | 1.2 | 300 | 0.5033 |
| 0.2821 | 1.6 | 400 | 0.5048 |
| 0.2339 | 2.0 | 500 | 0.5030 |
| 0.1408 | 2.4 | 600 | 0.5608 |
| 0.1487 | 2.8 | 700 | 0.5603 |
| 0.4367 | 0.8 | 800 | 0.4151 |
| 0.4604 | 0.9 | 900 | 0.3941 |
| 0.3256 | 1.0 | 1000 | 0.3951 |
| 0.3905 | 1.1 | 1100 | 0.3965 |
| 0.2926 | 1.2 | 1200 | 0.4004 |
| 0.4345 | 1.3 | 1300 | 0.3873 |
| 0.2715 | 1.4 | 1400 | 0.3850 |
| 0.4099 | 1.5 | 1500 | 0.3720 |
| 0.3202 | 1.6 | 1600 | 0.3702 |
| 0.4214 | 1.7 | 1700 | 0.3661 |
| 0.3209 | 1.8 | 1800 | 0.3618 |
| 0.3264 | 1.9 | 1900 | 0.3567 |
| 0.2974 | 2.0 | 2000 | 0.3557 |
| 0.1331 | 2.1 | 2100 | 0.3806 |
| 0.1087 | 2.2 | 2200 | 0.3833 |
| 0.1281 | 2.3 | 2300 | 0.3796 |
| 0.1454 | 2.4 | 2400 | 0.3831 |
| 0.1032 | 2.5 | 2500 | 0.3799 |
| 0.1061 | 2.6 | 2600 | 0.3781 |
| 0.1467 | 2.7 | 2700 | 0.3797 |
| 0.1213 | 2.8 | 2800 | 0.3795 |
| 0.1876 | 2.9 | 2900 | 0.3788 |
| 0.1197 | 3.0 | 3000 | 0.3784 |
Framework versions
- PEFT 0.15.2
- Transformers 4.48.3
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.1
- Library
- peft
- License
- apache-2.0
- Created
- Jul 1, 2025
- Updated
- Jul 3, 2025