Bisher/train_run-gemma-3-4b-it-arabic-diacritization_10k
04
<!-- 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. -->
trainrun-gemma-3-4b-it-arabic-diacritization10k
This model is a fine-tuned version of google/gemma-3-4b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0929
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: 4
- evalbatchsize: 8
- seed: 42
- gradientaccumulationsteps: 4
- totaltrainbatch_size: 16
- optimizer: Use OptimizerNames.PAGEDADAMW with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: constant
- lrschedulerwarmup_ratio: 0.03
- num_epochs: 1
Training results
Framework versions
- PEFT 0.14.0
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1