Downloads · 30 days
38
8% of all-time downloads
incar-nlu-qwen1.5b-v31
marcuschill1823/incar-nlu-qwen1.5b-v31
incar-nlu-qwen1.5b-v31 is a machine learning model from marcuschill1823. 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
491
Public
Repo size
4.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.8 GB · 60%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jun 10, 2026
- Updated
- Jun 10, 2026
- SHA
- 30ba5965
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. -->
incar-nlu-qwen1.5b-v31
This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the incar_nlu dataset. It achieves the following results on the evaluation set:
- Loss: 0.1843
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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- total_eval_batch_size: 8
- 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: 0.03
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2358 | 0.1584 | 200 | 0.2502 |
| 0.2186 | 0.3169 | 400 | 0.2291 |
| 0.2148 | 0.4753 | 600 | 0.2118 |
| 0.1912 | 0.6338 | 800 | 0.2052 |
| 0.1944 | 0.7922 | 1000 | 0.2026 |
| 0.2061 | 0.9507 | 1200 | 0.1971 |
| 0.1589 | 1.1091 | 1400 | 0.1950 |
| 0.1771 | 1.2676 | 1600 | 0.1934 |
| 0.1592 | 1.4260 | 1800 | 0.1897 |
| 0.1418 | 1.5845 | 2000 | 0.1891 |
| 0.1494 | 1.7429 | 2200 | 0.1862 |
| 0.1389 | 1.9014 | 2400 | 0.1843 |
| 0.1005 | 2.0600 | 2600 | 0.1877 |
| 0.0992 | 2.2187 | 2800 | 0.1912 |
| 0.0977 | 2.3771 | 3000 | 0.1917 |
| 0.1093 | 2.5356 | 3200 | 0.1910 |
| 0.1042 | 2.6940 | 3400 | 0.1899 |
| 0.1035 | 2.8524 | 3600 | 0.1901 |
Framework versions
- PEFT 0.12.0
- Transformers 4.46.1
- Pytorch 2.10.0+cu128
- Datasets 3.1.0
- Tokenizers 0.20.3
- Library
- peft
- License
- apache-2.0
- Created
- Jun 10, 2026
- Updated
- Jun 10, 2026