bengali-ocr-qwen

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: 2.6446

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_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: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss
3.9540 1.0 106 2.6780
4.4672 2.0 212 2.6517
4.2089 3.0 318 2.6446

Framework versions

  • PEFT 0.16.0
  • Transformers 5.0.0.dev0
  • Pytorch 2.6.0+cu124
  • Datasets 4.4.1
  • Tokenizers 0.22.1
Downloads last month
1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for shadid113/bengali-ocr-qwen

Adapter
(85)
this model