qwen25vl-3b-edit-detection-20260324091849
This model is a fine-tuned version of Qwen/Qwen2.5-VL-3B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.3323
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- 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: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5117 | 1.0 | 500 | 4.3662 |
| 4.2987 | 2.0 | 1000 | 4.3358 |
| 4.2539 | 3.0 | 1500 | 4.3323 |
Framework versions
- PEFT 0.18.1
- Transformers 5.3.0
- Pytorch 2.10.0+cu128
- Tokenizers 0.22.2
- Downloads last month
- 34
Model tree for vanloc1808/qwen25vl-3b-edit-detection-20260324091849
Base model
Qwen/Qwen2.5-VL-3B-Instruct