furniture-qwen2vl
This model is a fine-tuned version of Qwen/Qwen2-VL-2B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4357
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.ADAMW_HF 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: 100
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4458 | 0.4444 | 500 | 0.3009 |
| 0.3612 | 0.8889 | 1000 | 0.3340 |
| 0.3343 | 1.3333 | 1500 | 0.3580 |
| 0.3203 | 1.7778 | 2000 | 0.3702 |
| 0.3063 | 2.2222 | 2500 | 0.3925 |
| 0.3033 | 2.6667 | 3000 | 0.4087 |
| 0.2936 | 3.1111 | 3500 | 0.4150 |
| 0.2848 | 3.5556 | 4000 | 0.4184 |
| 0.2851 | 4.0 | 4500 | 0.4290 |
| 0.2793 | 4.4444 | 5000 | 0.4350 |
| 0.2799 | 4.8889 | 5500 | 0.4357 |
Framework versions
- PEFT 0.14.0
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 21