ocr-ex5-q3b-122k
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: 0.2659
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 512
- total_eval_batch_size: 4
- 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: 0.1
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2918 | 0.8480 | 200 | 0.3100 |
| 0.2302 | 1.6996 | 400 | 0.2659 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 4
Model tree for ahmedheakl/ocr-ex5-q3b-122k
Base model
Qwen/Qwen2.5-VL-3B-Instruct