sft
This model is a fine-tuned version of Qwen/Qwen2.5-VL-7B-Instruct on the and_ctrl_skt dataset. It achieves the following results on the evaluation set:
- Loss: 0.1610
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: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 48
- total_train_batch_size: 768
- total_eval_batch_size: 4
- optimizer: Use 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_ratio: 0.1
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2389 | 1.1120 | 100 | 0.2237 |
| 0.153 | 2.2239 | 200 | 0.1694 |
| 0.0898 | 3.3359 | 300 | 0.1497 |
| 0.0425 | 4.4479 | 400 | 0.1605 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.5.0a0+b465a5843b.nv24.09
- Datasets 3.0.1
- Tokenizers 0.22.1
- Downloads last month
- 19