qwen25-7b-instruct-trl-sft-geolocalize-43k
This model is a fine-tuned version of Qwen/Qwen2.5-VL-7B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1585
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- 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: 0.03
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1601 | 0.8269 | 1000 | 0.1604 |
| 0.1574 | 1.6532 | 2000 | 0.1597 |
| 0.1598 | 2.4796 | 3000 | 0.1585 |
Framework versions
- PEFT 0.13.0
- Transformers 4.50.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.0.1
- Tokenizers 0.21.0
- Downloads last month
- 2
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for Ellight/qwen25-7b-instruct-trl-sft-geolocalize-43k
Base model
Qwen/Qwen2.5-VL-7B-Instruct