sikandermukhtar/urdu-htr-gemma3-4b-lora

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

urdu-htr-gemma-3-4b

This model is a fine-tuned version of google/gemma-3-4b-it on the urduhtrtrain dataset. It achieves the following results on the evaluation set:

• —Loss: 1.3550

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
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 2
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 8
• —totalevalbatch_size: 2
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 5

Training results

Framework versions

• —PEFT 0.15.2
• —Transformers 4.57.1
• —Pytorch 2.10.0+cu128
• —Datasets 3.5.0
• —Tokenizers 0.22.2